diff options
1753 files changed, 43804 insertions, 14240 deletions
diff --git a/Documentation/ABI/testing/sysfs-firmware-ofw b/Documentation/ABI/testing/sysfs-firmware-ofw new file mode 100644 index 000000000000..f562b188e71d --- /dev/null +++ b/Documentation/ABI/testing/sysfs-firmware-ofw @@ -0,0 +1,28 @@ +What: /sys/firmware/devicetree/* +Date: November 2013 +Contact: Grant Likely <grant.likely@linaro.org> +Description: + When using OpenFirmware or a Flattened Device Tree to enumerate + hardware, the device tree structure will be exposed in this + directory. + + It is possible for multiple device-tree directories to exist. + Some device drivers use a separate detached device tree which + have no attachment to the system tree and will appear in a + different subdirectory under /sys/firmware/devicetree. + + Userspace must not use the /sys/firmware/devicetree/base + path directly, but instead should follow /proc/device-tree + symlink. It is possible that the absolute path will change + in the future, but the symlink is the stable ABI. + + The /proc/device-tree symlink replaces the devicetree /proc + filesystem support, and has largely the same semantics and + should be compatible with existing userspace. + + The contents of /sys/firmware/devicetree/ is a + hierarchy of directories, one per device tree node. The + directory name is the resolved path component name (node + name plus address). Properties are represented as files + in the directory. The contents of each file is the exact + binary data from the device tree. diff --git a/Documentation/devicetree/bindings/arm/coresight.txt b/Documentation/devicetree/bindings/arm/coresight.txt new file mode 100644 index 000000000000..a3089359aaa6 --- /dev/null +++ b/Documentation/devicetree/bindings/arm/coresight.txt @@ -0,0 +1,200 @@ +* CoreSight Components: + +CoreSight components are compliant with the ARM CoreSight architecture +specification and can be connected in various topologies to suit a particular +SoCs tracing needs. These trace components can generally be classified as +sinks, links and sources. Trace data produced by one or more sources flows +through the intermediate links connecting the source to the currently selected +sink. Each CoreSight component device should use these properties to describe +its hardware characteristcs. + +* Required properties for all components *except* non-configurable replicators: + + * compatible: These have to be supplemented with "arm,primecell" as + drivers are using the AMBA bus interface. Possible values include: + - "arm,coresight-etb10", "arm,primecell"; + - "arm,coresight-tpiu", "arm,primecell"; + - "arm,coresight-tmc", "arm,primecell"; + - "arm,coresight-funnel", "arm,primecell"; + - "arm,coresight-etm3x", "arm,primecell"; + + * reg: physical base address and length of the register + set(s) of the component. + + * clocks: the clock associated to this component. + + * clock-names: the name of the clock as referenced by the code. + Since we are using the AMBA framework, the name should be + "apb_pclk". + + * port or ports: The representation of the component's port + layout using the generic DT graph presentation found in + "bindings/graph.txt". + +* Required properties for devices that don't show up on the AMBA bus, such as + non-configurable replicators: + + * compatible: Currently supported value is (note the absence of the + AMBA markee): + - "arm,coresight-replicator" + + * port or ports: same as above. + +* Optional properties for ETM/PTMs: + + * arm,cp14: must be present if the system accesses ETM/PTM management + registers via co-processor 14. + + * cpu: the cpu phandle this ETM/PTM is affined to. When omitted the + source is considered to belong to CPU0. + +* Optional property for TMC: + + * arm,buffer-size: size of contiguous buffer space for TMC ETR + (embedded trace router) + + +Example: + +1. Sinks + etb@20010000 { + compatible = "arm,coresight-etb10", "arm,primecell"; + reg = <0 0x20010000 0 0x1000>; + + coresight-default-sink; + clocks = <&oscclk6a>; + clock-names = "apb_pclk"; + port { + etb_in_port: endpoint@0 { + slave-mode; + remote-endpoint = <&replicator_out_port0>; + }; + }; + }; + + tpiu@20030000 { + compatible = "arm,coresight-tpiu", "arm,primecell"; + reg = <0 0x20030000 0 0x1000>; + + clocks = <&oscclk6a>; + clock-names = "apb_pclk"; + port { + tpiu_in_port: endpoint@0 { + slave-mode; + remote-endpoint = <&replicator_out_port1>; + }; + }; + }; + +2. Links + replicator { + /* non-configurable replicators don't show up on the + * AMBA bus. As such no need to add "arm,primecell". + */ + compatible = "arm,coresight-replicator"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + /* replicator output ports */ + port@0 { + reg = <0>; + replicator_out_port0: endpoint { + remote-endpoint = <&etb_in_port>; + }; + }; + + port@1 { + reg = <1>; + replicator_out_port1: endpoint { + remote-endpoint = <&tpiu_in_port>; + }; + }; + + /* replicator input port */ + port@2 { + reg = <0>; + replicator_in_port0: endpoint { + slave-mode; + remote-endpoint = <&funnel_out_port0>; + }; + }; + }; + }; + + funnel@20040000 { + compatible = "arm,coresight-funnel", "arm,primecell"; + reg = <0 0x20040000 0 0x1000>; + + clocks = <&oscclk6a>; + clock-names = "apb_pclk"; + ports { + #address-cells = <1>; + #size-cells = <0>; + + /* funnel output port */ + port@0 { + reg = <0>; + funnel_out_port0: endpoint { + remote-endpoint = + <&replicator_in_port0>; + }; + }; + + /* funnel input ports */ + port@1 { + reg = <0>; + funnel_in_port0: endpoint { + slave-mode; + remote-endpoint = <&ptm0_out_port>; + }; + }; + + port@2 { + reg = <1>; + funnel_in_port1: endpoint { + slave-mode; + remote-endpoint = <&ptm1_out_port>; + }; + }; + + port@3 { + reg = <2>; + funnel_in_port2: endpoint { + slave-mode; + remote-endpoint = <&etm0_out_port>; + }; + }; + + }; + }; + +3. Sources + ptm@2201c000 { + compatible = "arm,coresight-etm3x", "arm,primecell"; + reg = <0 0x2201c000 0 0x1000>; + + cpu = <&cpu0>; + clocks = <&oscclk6a>; + clock-names = "apb_pclk"; + port { + ptm0_out_port: endpoint { + remote-endpoint = <&funnel_in_port0>; + }; + }; + }; + + ptm@2201d000 { + compatible = "arm,coresight-etm3x", "arm,primecell"; + reg = <0 0x2201d000 0 0x1000>; + + cpu = <&cpu1>; + clocks = <&oscclk6a>; + clock-names = "apb_pclk"; + port { + ptm1_out_port: endpoint { + remote-endpoint = <&funnel_in_port1>; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/ata/sata_rcar.txt b/Documentation/devicetree/bindings/ata/sata_rcar.txt index 1e6111333fa8..7dd32d321a34 100644 --- a/Documentation/devicetree/bindings/ata/sata_rcar.txt +++ b/Documentation/devicetree/bindings/ata/sata_rcar.txt @@ -3,7 +3,8 @@ Required properties: - compatible : should contain one of the following: - "renesas,sata-r8a7779" for R-Car H1 - - "renesas,sata-r8a7790" for R-Car H2 + - "renesas,sata-r8a7790-es1" for R-Car H2 ES1 + - "renesas,sata-r8a7790" for R-Car H2 other than ES1 - "renesas,sata-r8a7791" for R-Car M2 - reg : address and length of the SATA registers; - interrupts : must consist of one interrupt specifier. diff --git a/Documentation/devicetree/bindings/interrupt-controller/interrupts.txt b/Documentation/devicetree/bindings/interrupt-controller/interrupts.txt index 1486497a24c1..8a3c40829899 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/interrupts.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/interrupts.txt @@ -4,11 +4,13 @@ Specifying interrupt information for devices 1) Interrupt client nodes ------------------------- -Nodes that describe devices which generate interrupts must contain an either an -"interrupts" property or an "interrupts-extended" property. These properties -contain a list of interrupt specifiers, one per output interrupt. The format of -the interrupt specifier is determined by the interrupt controller to which the -interrupts are routed; see section 2 below for details. +Nodes that describe devices which generate interrupts must contain an +"interrupts" property, an "interrupts-extended" property, or both. If both are +present, the latter should take precedence; the former may be provided simply +for compatibility with software that does not recognize the latter. These +properties contain a list of interrupt specifiers, one per output interrupt. The +format of the interrupt specifier is determined by the interrupt controller to +which the interrupts are routed; see section 2 below for details. Example: interrupt-parent = <&intc1>; @@ -28,10 +30,6 @@ should only be used when a device has multiple interrupt parents. Example: interrupts-extended = <&intc1 5 1>, <&intc2 1 0>; -A device node may contain either "interrupts" or "interrupts-extended", but not -both. If both properties are present, then the operating system should log an -error and use only the data in "interrupts". - 2) Interrupt controller nodes ----------------------------- diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt new file mode 100644 index 000000000000..98c16672ab5f --- /dev/null +++ b/Documentation/devicetree/bindings/power/power_domain.txt @@ -0,0 +1,49 @@ +* Generic PM domains + +System on chip designs are often divided into multiple PM domains that can be +used for power gating of selected IP blocks for power saving by reduced leakage +current. + +This device tree binding can be used to bind PM domain consumer devices with +their PM domains provided by PM domain providers. A PM domain provider can be +represented by any node in the device tree and can provide one or more PM +domains. A consumer node can refer to the provider by a phandle and a set of +phandle arguments (so called PM domain specifiers) of length specified by the +#power-domain-cells property in the PM domain provider node. + +==PM domain providers== + +Required properties: + - #power-domain-cells : Number of cells in a PM domain specifier; + Typically 0 for nodes representing a single PM domain and 1 for nodes + providing multiple PM domains (e.g. power controllers), but can be any value + as specified by device tree binding documentation of particular provider. + +Example: + + power: power-controller@12340000 { + compatible = "foo,power-controller"; + reg = <0x12340000 0x1000>; + #power-domain-cells = <1>; + }; + +The node above defines a power controller that is a PM domain provider and +expects one cell as its phandle argument. + +==PM domain consumers== + +Required properties: + - power-domains : A phandle and PM domain specifier as defined by bindings of + the power controller specified by phandle. + +Example: + + leaky-device@12350000 { + compatible = "foo,i-leak-current"; + reg = <0x12350000 0x1000>; + power-domains = <&power 0>; + }; + +The node above defines a typical PM domain consumer device, which is located +inside a PM domain with index 0 of a power controller represented by a node +with the label "power". diff --git a/Documentation/devicetree/bindings/unittest.txt b/Documentation/devicetree/bindings/unittest.txt new file mode 100644 index 000000000000..8933211f32f9 --- /dev/null +++ b/Documentation/devicetree/bindings/unittest.txt @@ -0,0 +1,71 @@ +1) OF selftest platform device + +** selftest + +Required properties: +- compatible: must be "selftest" + +All other properties are optional. + +Example: + selftest { + compatible = "selftest"; + status = "okay"; + }; + +2) OF selftest i2c adapter platform device + +** platform device unittest adapter + +Required properties: +- compatible: must be selftest-i2c-bus + +Children nodes contain selftest i2c devices. + +Example: + selftest-i2c-bus { + compatible = "selftest-i2c-bus"; + status = "okay"; + }; + +3) OF selftest i2c device + +** I2C selftest device + +Required properties: +- compatible: must be selftest-i2c-dev + +All other properties are optional + +Example: + selftest-i2c-dev { + compatible = "selftest-i2c-dev"; + status = "okay"; + }; + +4) OF selftest i2c mux device + +** I2C selftest mux + +Required properties: +- compatible: must be selftest-i2c-mux + +Children nodes contain selftest i2c bus nodes per channel. + +Example: + selftest-i2c-mux { + compatible = "selftest-i2c-mux"; + status = "okay"; + #address-cells = <1>; + #size-cells = <0>; + channel-0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + i2c-dev { + reg = <8>; + compatible = "selftest-i2c-dev"; + status = "okay"; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/usb/dwc3.txt b/Documentation/devicetree/bindings/usb/dwc3.txt index e807635f9e1c..471366d6a129 100644 --- a/Documentation/devicetree/bindings/usb/dwc3.txt +++ b/Documentation/devicetree/bindings/usb/dwc3.txt @@ -6,11 +6,13 @@ Required properties: - compatible: must be "snps,dwc3" - reg : Address and length of the register set for the device - interrupts: Interrupts used by the dwc3 controller. + +Optional properties: - usb-phy : array of phandle for the PHY device. The first element in the array is expected to be a handle to the USB2/HS PHY and the second element is expected to be a handle to the USB3/SS PHY - -Optional properties: + - phys: from the *Generic PHY* bindings + - phy-names: from the *Generic PHY* bindings - tx-fifo-resize: determines if the FIFO *has* to be reallocated. This is usually a subnode to DWC3 glue to which it is connected. diff --git a/Documentation/devicetree/bindings/usb/usb-xhci.txt b/Documentation/devicetree/bindings/usb/usb-xhci.txt index 5752df0e17a2..98424d5363e6 100644 --- a/Documentation/devicetree/bindings/usb/usb-xhci.txt +++ b/Documentation/devicetree/bindings/usb/usb-xhci.txt @@ -6,6 +6,9 @@ Required properties: register set for the device. - interrupts: one XHCI interrupt should be described here. +Optional properties: + - usb3-lpm-capable: determines if platform is USB3 LPM capable + Example: usb@f0931000 { compatible = "xhci-platform"; diff --git a/Documentation/devicetree/changesets.txt b/Documentation/devicetree/changesets.txt new file mode 100644 index 000000000000..935ba5acc34e --- /dev/null +++ b/Documentation/devicetree/changesets.txt @@ -0,0 +1,40 @@ +A DT changeset is a method which allows one to apply changes +in the live tree in such a way that either the full set of changes +will be applied, or none of them will be. If an error occurs partway +through applying the changeset, then the tree will be rolled back to the +previous state. A changeset can also be removed after it has been +applied. + +When a changeset is applied, all of the changes get applied to the tree +at once before emitting OF_RECONFIG notifiers. This is so that the +receiver sees a complete and consistent state of the tree when it +receives the notifier. + +The sequence of a changeset is as follows. + +1. of_changeset_init() - initializes a changeset + +2. A number of DT tree change calls, of_changeset_attach_node(), +of_changeset_detach_node(), of_changeset_add_property(), +of_changeset_remove_property, of_changeset_update_property() to prepare +a set of changes. No changes to the active tree are made at this point. +All the change operations are recorded in the of_changeset 'entries' +list. + +3. mutex_lock(of_mutex) - starts a changeset; The global of_mutex +ensures there can only be one editor at a time. + +4. of_changeset_apply() - Apply the changes to the tree. Either the +entire changeset will get applied, or if there is an error the tree will +be restored to the previous state + +5. mutex_unlock(of_mutex) - All operations complete, release the mutex + +If a successfully applied changeset needs to be removed, it can be done +with the following sequence. + +1. mutex_lock(of_mutex) + +2. of_changeset_revert() + +3. mutex_unlock(of_mutex) diff --git a/Documentation/devicetree/dynamic-resolution-notes.txt b/Documentation/devicetree/dynamic-resolution-notes.txt new file mode 100644 index 000000000000..083d23262abe --- /dev/null +++ b/Documentation/devicetree/dynamic-resolution-notes.txt @@ -0,0 +1,25 @@ +Device Tree Dynamic Resolver Notes +---------------------------------- + +This document describes the implementation of the in-kernel +Device Tree resolver, residing in drivers/of/resolver.c and is a +companion document to Documentation/devicetree/dt-object-internal.txt[1] + +How the resolver works +---------------------- + +The resolver is given as an input an arbitrary tree compiled with the +proper dtc option and having a /plugin/ tag. This generates the +appropriate __fixups__ & __local_fixups__ nodes as described in [1]. + +In sequence the resolver works by the following steps: + +1. Get the maximum device tree phandle value from the live tree + 1. +2. Adjust all the local phandles of the tree to resolve by that amount. +3. Using the __local__fixups__ node information adjust all local references + by the same amount. +4. For each property in the __fixups__ node locate the node it references + in the live tree. This is the label used to tag the node. +5. Retrieve the phandle of the target of the fixup. +6. For each fixup in the property locate the node:property:offset location + and replace it with the phandle value. diff --git a/Documentation/devicetree/overlay-notes.txt b/Documentation/devicetree/overlay-notes.txt new file mode 100644 index 000000000000..30ae758e3eef --- /dev/null +++ b/Documentation/devicetree/overlay-notes.txt @@ -0,0 +1,133 @@ +Device Tree Overlay Notes +------------------------- + +This document describes the implementation of the in-kernel +device tree overlay functionality residing in drivers/of/overlay.c and is a +companion document to Documentation/devicetree/dt-object-internal.txt[1] & +Documentation/devicetree/dynamic-resolution-notes.txt[2] + +How overlays work +----------------- + +A Device Tree's overlay purpose is to modify the kernel's live tree, and +have the modification affecting the state of the the kernel in a way that +is reflecting the changes. +Since the kernel mainly deals with devices, any new device node that result +in an active device should have it created while if the device node is either +disabled or removed all together, the affected device should be deregistered. + +Lets take an example where we have a foo board with the following base tree +which is taken from [1]. + +---- foo.dts ----------------------------------------------------------------- + /* FOO platform */ + / { + compatible = "corp,foo"; + + /* shared resources */ + res: res { + }; + + /* On chip peripherals */ + ocp: ocp { + /* peripherals that are always instantiated */ + peripheral1 { ... }; + } + }; +---- foo.dts ----------------------------------------------------------------- + +The overlay bar.dts, when loaded (and resolved as described in [2]) should + +---- bar.dts ----------------------------------------------------------------- +/plugin/; /* allow undefined label references and record them */ +/ { + .... /* various properties for loader use; i.e. part id etc. */ + fragment@0 { + target = <&ocp>; + __overlay__ { + /* bar peripheral */ + bar { + compatible = "corp,bar"; + ... /* various properties and child nodes */ + } + }; + }; +}; +---- bar.dts ----------------------------------------------------------------- + +result in foo+bar.dts + +---- foo+bar.dts ------------------------------------------------------------- + /* FOO platform + bar peripheral */ + / { + compatible = "corp,foo"; + + /* shared resources */ + res: res { + }; + + /* On chip peripherals */ + ocp: ocp { + /* peripherals that are always instantiated */ + peripheral1 { ... }; + + /* bar peripheral */ + bar { + compatible = "corp,bar"; + ... /* various properties and child nodes */ + } + } + }; +---- foo+bar.dts ------------------------------------------------------------- + +As a result of the the overlay, a new device node (bar) has been created +so a bar platform device will be registered and if a matching device driver +is loaded the device will be created as expected. + +Overlay in-kernel API +-------------------------------- + +The API is quite easy to use. + +1. Call of_overlay_create() to create and apply an overlay. The return value +is a cookie identifying this overlay. + +2. Call of_overlay_destroy() to remove and cleanup the overlay previously +created via the call to of_overlay_create(). Removal of an overlay that +is stacked by another will not be permitted. + +Finally, if you need to remove all overlays in one-go, just call +of_overlay_destroy_all() which will remove every single one in the correct +order. + +Overlay DTS Format +------------------ + +The DTS of an overlay should have the following format: + +{ + /* ignored properties by the overlay */ + + fragment@0 { /* first child node */ + + target=<phandle>; /* phandle target of the overlay */ + or + target-path="/path"; /* target path of the overlay */ + + __overlay__ { + property-a; /* add property-a to the target */ + node-a { /* add to an existing, or create a node-a */ + ... + }; + }; + } + fragment@1 { /* second child node */ + ... + }; + /* more fragments follow */ +} + +Using the non-phandle based target method allows one to use a base DT which does +not contain a __symbols__ node, i.e. it was not compiled with the -@ option. +The __symbols__ node is only required for the target=<phandle> method, since it +contains the information required to map from a phandle to a tree location. diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 5b0c083d7c0e..821c8f4d359f 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -47,6 +47,8 @@ prototypes: int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t); int (*rename) (struct inode *, struct dentry *, struct inode *, struct dentry *); + int (*rename2) (struct inode *, struct dentry *, + struct inode *, struct dentry *, unsigned int); int (*readlink) (struct dentry *, char __user *,int); void * (*follow_link) (struct dentry *, struct nameidata *); void (*put_link) (struct dentry *, struct nameidata *, void *); @@ -65,6 +67,7 @@ prototypes: struct file *, unsigned open_flag, umode_t create_mode, int *opened); int (*tmpfile) (struct inode *, struct dentry *, umode_t); + int (*dentry_open)(struct dentry *, struct file *, const struct cred *); locking rules: all may block @@ -78,6 +81,7 @@ mkdir: yes unlink: yes (both) rmdir: yes (both) (see below) rename: yes (all) (see below) +rename2: yes (all) (see below) readlink: no follow_link: no put_link: no @@ -93,10 +97,12 @@ fiemap: no update_time: no atomic_open: yes tmpfile: no +dentry_open: no Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on victim. - cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem. + cross-directory ->rename() and rename2() has (per-superblock) +->s_vfs_rename_sem. See Documentation/filesystems/directory-locking for more detailed discussion of the locking scheme for directory operations. diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt new file mode 100644 index 000000000000..6db0e5d1da07 --- /dev/null +++ b/Documentation/filesystems/overlayfs.txt @@ -0,0 +1,226 @@ +Written by: Neil Brown <neilb@suse.de> + +Overlay Filesystem +================== + +This document describes a prototype for a new approach to providing +overlay-filesystem functionality in Linux (sometimes referred to as +union-filesystems). An overlay-filesystem tries to present a +filesystem which is the result over overlaying one filesystem on top +of the other. + +The result will inevitably fail to look exactly like a normal +filesystem for various technical reasons. The expectation is that +many use cases will be able to ignore these differences. + +This approach is 'hybrid' because the objects that appear in the +filesystem do not all appear to belong to that filesystem. In many +cases an object accessed in the union will be indistinguishable +from accessing the corresponding object from the original filesystem. +This is most obvious from the 'st_dev' field returned by stat(2). + +While directories will report an st_dev from the overlay-filesystem, +all non-directory objects will report an st_dev from the lower or +upper filesystem that is providing the object. Similarly st_ino will +only be unique when combined with st_dev, and both of these can change +over the lifetime of a non-directory object. Many applications and +tools ignore these values and will not be affected. + +Upper and Lower +--------------- + +An overlay filesystem combines two filesystems - an 'upper' filesystem +and a 'lower' filesystem. When a name exists in both filesystems, the +object in the 'upper' filesystem is visible while the object in the +'lower' filesystem is either hidden or, in the case of directories, +merged with the 'upper' object. + +It would be more correct to refer to an upper and lower 'directory +tree' rather than 'filesystem' as it is quite possible for both +directory trees to be in the same filesystem and there is no +requirement that the root of a filesystem be given for either upper or +lower. + +The lower filesystem can be any filesystem supported by Linux and does +not need to be writable. The lower filesystem can even be another +overlayfs. The upper filesystem will normally be writable and if it +is it must support the creation of trusted.* extended attributes, and +must provide valid d_type in readdir responses, so NFS is not suitable. + +A read-only overlay of two read-only filesystems may use any +filesystem type. + +Directories +----------- + +Overlaying mainly involves directories. If a given name appears in both +upper and lower filesystems and refers to a non-directory in either, +then the lower object is hidden - the name refers only to the upper +object. + +Where both upper and lower objects are directories, a merged directory +is formed. + +At mount time, the two directories given as mount options "lowerdir" and +"upperdir" are combined into a merged directory: + + mount -t overlay overlay -olowerdir=/lower,upperdir=/upper,\ +workdir=/work /merged + +The "workdir" needs to be an empty directory on the same filesystem +as upperdir. + +Then whenever a lookup is requested in such a merged directory, the +lookup is performed in each actual directory and the combined result +is cached in the dentry belonging to the overlay filesystem. If both +actual lookups find directories, both are stored and a merged +directory is created, otherwise only one is stored: the upper if it +exists, else the lower. + +Only the lists of names from directories are merged. Other content +such as metadata and extended attributes are reported for the upper +directory only. These attributes of the lower directory are hidden. + +whiteouts and opaque directories +-------------------------------- + +In order to support rm and rmdir without changing the lower +filesystem, an overlay filesystem needs to record in the upper filesystem +that files have been removed. This is done using whiteouts and opaque +directories (non-directories are always opaque). + +A whiteout is created as a character device with 0/0 device number. +When a whiteout is found in the upper level of a merged directory, any +matching name in the lower level is ignored, and the whiteout itself +is also hidden. + +A directory is made opaque by setting the xattr "trusted.overlay.opaque" +to "y". Where the upper filesystem contains an opaque directory, any +directory in the lower filesystem with the same name is ignored. + +readdir +------- + +When a 'readdir' request is made on a merged directory, the upper and +lower directories are each read and the name lists merged in the +obvious way (upper is read first, then lower - entries that already +exist are not re-added). This merged name list is cached in the +'struct file' and so remains as long as the file is kept open. If the +directory is opened and read by two processes at the same time, they +will each have separate caches. A seekdir to the start of the +directory (offset 0) followed by a readdir will cause the cache to be +discarded and rebuilt. + +This means that changes to the merged directory do not appear while a +directory is being read. This is unlikely to be noticed by many +programs. + +seek offsets are assigned sequentially when the directories are read. +Thus if + - read part of a directory + - remember an offset, and close the directory + - re-open the directory some time later + - seek to the remembered offset + +there may be little correlation between the old and new locations in +the list of filenames, particularly if anything has changed in the +directory. + +Readdir on directories that are not merged is simply handled by the +underlying directory (upper or lower). + + +Non-directories +--------------- + +Objects that are not directories (files, symlinks, device-special +files etc.) are presented either from the upper or lower filesystem as +appropriate. When a file in the lower filesystem is accessed in a way +the requires write-access, such as opening for write access, changing +some metadata etc., the file is first copied from the lower filesystem +to the upper filesystem (copy_up). Note that creating a hard-link +also requires copy_up, though of course creation of a symlink does +not. + +The copy_up may turn out to be unnecessary, for example if the file is +opened for read-write but the data is not modified. + +The copy_up process first makes sure that the containing directory +exists in the upper filesystem - creating it and any parents as +necessary. It then creates the object with the same metadata (owner, +mode, mtime, symlink-target etc.) and then if the object is a file, the +data is copied from the lower to the upper filesystem. Finally any +extended attributes are copied up. + +Once the copy_up is complete, the overlay filesystem simply +provides direct access to the newly created file in the upper +filesystem - future operations on the file are barely noticed by the +overlay filesystem (though an operation on the name of the file such as +rename or unlink will of course be noticed and handled). + + +Multiple lower layers +--------------------- + +Multiple lower layers can now be given using the the colon (":") as a +separator character between the directory names. For example: + + mount -t overlay overlay -olowerdir=/lower1:/lower2:/lower3 /merged + +As the example shows, "upperdir=" and "workdir=" may be omitted. In +that case the overlay will be read-only. + +The specified lower directories will be stacked beginning from the +rightmost one and going left. In the above example lower1 will be the +top, lower2 the middle and lower3 the bottom layer. + + +Non-standard behavior +--------------------- + +The copy_up operation essentially creates a new, identical file and +moves it over to the old name. The new file may be on a different +filesystem, so both st_dev and st_ino of the file may change. + +Any open files referring to this inode will access the old data and +metadata. Similarly any file locks obtained before copy_up will not +apply to the copied up file. + +On a file opened with O_RDONLY fchmod(2), fchown(2), futimesat(2) and +fsetxattr(2) will fail with EROFS. + +If a file with multiple hard links is copied up, then this will +"break" the link. Changes will not be propagated to other names +referring to the same inode. + +Symlinks in /proc/PID/ and /proc/PID/fd which point to a non-directory +object in overlayfs will not contain valid absolute paths, only +relative paths leading up to the filesystem's root. This will be +fixed in the future. + +Some operations are not atomic, for example a crash during copy_up or +rename will leave the filesystem in an inconsistent state. This will +be addressed in the future. + +Changes to underlying filesystems +--------------------------------- + +Offline changes, when the overlay is not mounted, are allowed to either +the upper or the lower trees. + +Changes to the underlying filesystems while part of a mounted overlay +filesystem are not allowed. If the underlying filesystem is changed, +the behavior of the overlay is undefined, though it will not result in +a crash or deadlock. + +Testsuite +--------- + +There's testsuite developed by David Howells at: + + git://git.infradead.org/users/dhowells/unionmount-testsuite.git + +Run as root: + + # cd unionmount-testsuite + # ./run --ov diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index c53784c119c8..5d06f2a19798 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -347,6 +347,8 @@ struct inode_operations { int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t); int (*rename) (struct inode *, struct dentry *, struct inode *, struct dentry *); + int (*rename2) (struct inode *, struct dentry *, + struct inode *, struct dentry *, unsigned int); int (*readlink) (struct dentry *, char __user *,int); void * (*follow_link) (struct dentry *, struct nameidata *); void (*put_link) (struct dentry *, struct nameidata *, void *); @@ -362,6 +364,7 @@ struct inode_operations { int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode, int *opened); int (*tmpfile) (struct inode *, struct dentry *, umode_t); + int (*dentry_open)(struct dentry *, struct file *, const struct cred *); }; Again, all methods are called without any locks being held, unless @@ -414,6 +417,20 @@ otherwise noted. rename: called by the rename(2) system call to rename the object to have the parent and name given by the second inode and dentry. + rename2: this has an additional flags argument compared to rename. + If no flags are supported by the filesystem then this method + need not be implemented. If some flags are supported then the + filesystem must return -EINVAL for any unsupported or unknown + flags. Currently the following flags are implemented: + (1) RENAME_NOREPLACE: this flag indicates that if the target + of the rename exists the rename should fail with -EEXIST + instead of replacing the target. The VFS already checks for + existence, so for local filesystems the RENAME_NOREPLACE + implementation is equivalent to plain rename. + (2) RENAME_EXCHANGE: exchange source and target. Both must + exist; this is checked by the VFS. Unlike plain rename, + source and target may be of different type. + readlink: called by the readlink(2) system call. Only required if you want to support reading symbolic links @@ -681,6 +698,12 @@ struct address_space_operations { but instead uses bmap to find out where the blocks in the file are and uses those addresses directly. + dentry_open: *WARNING: probably going away soon, do not use!* This is an + alternative to f_op->open(), the difference is that this method may open + a file not necessarily originating from the same filesystem as the one + i_op->open() was called on. It may be useful for stacking filesystems + which want to allow native I/O directly on underlying files. + invalidatepage: If a page has PagePrivate set, then invalidatepage will be called when part or all of the page is to be removed diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 7116fda7077f..5d91ba1606bb 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1172,6 +1172,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. i8042.notimeout [HW] Ignore timeout condition signalled by controller i8042.reset [HW] Reset the controller during init and cleanup i8042.unlock [HW] Unlock (ignore) the keylock + i8042.kbdreset [HW] Reset device connected to KBD port i810= [HW,DRM] diff --git a/Documentation/lzo.txt b/Documentation/lzo.txt new file mode 100644 index 000000000000..ea45dd3901e3 --- /dev/null +++ b/Documentation/lzo.txt @@ -0,0 +1,164 @@ + +LZO stream format as understood by Linux's LZO decompressor +=========================================================== + +Introduction + + This is not a specification. No specification seems to be publicly available + for the LZO stream format. This document describes what input format the LZO + decompressor as implemented in the Linux kernel understands. The file subject + of this analysis is lib/lzo/lzo1x_decompress_safe.c. No analysis was made on + the compressor nor on any other implementations though it seems likely that + the format matches the standard one. The purpose of this document is to + better understand what the code does in order to propose more efficient fixes + for future bug reports. + +Description + + The stream is composed of a series of instructions, operands, and data. The + instructions consist in a few bits representing an opcode, and bits forming + the operands for the instruction, whose size and position depend on the + opcode and on the number of literals copied by previous instruction. The + operands are used to indicate : + + - a distance when copying data from the dictionary (past output buffer) + - a length (number of bytes to copy from dictionary) + - the number of literals to copy, which is retained in variable "state" + as a piece of information for next instructions. + + Optionally depending on the opcode and operands, extra data may follow. These + extra data can be a complement for the operand (eg: a length or a distance + encoded on larger values), or a literal to be copied to the output buffer. + + The first byte of the block follows a different encoding from other bytes, it + seems to be optimized for literal use only, since there is no dictionary yet + prior to that byte. + + Lengths are always encoded on a variable size starting with a small number + of bits in the operand. If the number of bits isn't enough to represent the + length, up to 255 may be added in increments by consuming more bytes with a + rate of at most 255 per extra byte (thus the compression ratio cannot exceed + around 255:1). The variable length encoding using #bits is always the same : + + length = byte & ((1 << #bits) - 1) + if (!length) { + length = ((1 << #bits) - 1) + length += 255*(number of zero bytes) + length += first-non-zero-byte + } + length += constant (generally 2 or 3) + + For references to the dictionary, distances are relative to the output + pointer. Distances are encoded using very few bits belonging to certain + ranges, resulting in multiple copy instructions using different encodings. + Certain encodings involve one extra byte, others involve two extra bytes + forming a little-endian 16-bit quantity (marked LE16 below). + + After any instruction except the large literal copy, 0, 1, 2 or 3 literals + are copied before starting the next instruction. The number of literals that + were copied may change the meaning and behaviour of the next instruction. In + practice, only one instruction needs to know whether 0, less than 4, or more + literals were copied. This is the information stored in the <state> variable + in this implementation. This number of immediate literals to be copied is + generally encoded in the last two bits of the instruction but may also be + taken from the last two bits of an extra operand (eg: distance). + + End of stream is declared when a block copy of distance 0 is seen. Only one + instruction may encode this distance (0001HLLL), it takes one LE16 operand + for the distance, thus requiring 3 bytes. + + IMPORTANT NOTE : in the code some length checks are missing because certain + instructions are called under the assumption that a certain number of bytes + follow because it has already been garanteed before parsing the instructions. + They just have to "refill" this credit if they consume extra bytes. This is + an implementation design choice independant on the algorithm or encoding. + +Byte sequences + + First byte encoding : + + 0..17 : follow regular instruction encoding, see below. It is worth + noting that codes 16 and 17 will represent a block copy from + the dictionary which is empty, and that they will always be + invalid at this place. + + 18..21 : copy 0..3 literals + state = (byte - 17) = 0..3 [ copy <state> literals ] + skip byte + + 22..255 : copy literal string + length = (byte - 17) = 4..238 + state = 4 [ don't copy extra literals ] + skip byte + + Instruction encoding : + + 0 0 0 0 X X X X (0..15) + Depends on the number of literals copied by the last instruction. + If last instruction did not copy any literal (state == 0), this + encoding will be a copy of 4 or more literal, and must be interpreted + like this : + + 0 0 0 0 L L L L (0..15) : copy long literal string + length = 3 + (L ?: 15 + (zero_bytes * 255) + non_zero_byte) + state = 4 (no extra literals are copied) + + If last instruction used to copy between 1 to 3 literals (encoded in + the instruction's opcode or distance), the instruction is a copy of a + 2-byte block from the dictionary within a 1kB distance. It is worth + noting that this instruction provides little savings since it uses 2 + bytes to encode a copy of 2 other bytes but it encodes the number of + following literals for free. It must be interpreted like this : + + 0 0 0 0 D D S S (0..15) : copy 2 bytes from <= 1kB distance + length = 2 + state = S (copy S literals after this block) + Always followed by exactly one byte : H H H H H H H H + distance = (H << 2) + D + 1 + + If last instruction used to copy 4 or more literals (as detected by + state == 4), the instruction becomes a copy of a 3-byte block from the + dictionary from a 2..3kB distance, and must be interpreted like this : + + 0 0 0 0 D D S S (0..15) : copy 3 bytes from 2..3 kB distance + length = 3 + state = S (copy S literals after this block) + Always followed by exactly one byte : H H H H H H H H + distance = (H << 2) + D + 2049 + + 0 0 0 1 H L L L (16..31) + Copy of a block within 16..48kB distance (preferably less than 10B) + length = 2 + (L ?: 7 + (zero_bytes * 255) + non_zero_byte) + Always followed by exactly one LE16 : D D D D D D D D : D D D D D D S S + distance = 16384 + (H << 14) + D + state = S (copy S literals after this block) + End of stream is reached if distance == 16384 + + 0 0 1 L L L L L (32..63) + Copy of small block within 16kB distance (preferably less than 34B) + length = 2 + (L ?: 31 + (zero_bytes * 255) + non_zero_byte) + Always followed by exactly one LE16 : D D D D D D D D : D D D D D D S S + distance = D + 1 + state = S (copy S literals after this block) + + 0 1 L D D D S S (64..127) + Copy 3-4 bytes from block within 2kB distance + state = S (copy S literals after this block) + length = 3 + L + Always followed by exactly one byte : H H H H H H H H + distance = (H << 3) + D + 1 + + 1 L L D D D S S (128..255) + Copy 5-8 bytes from block within 2kB distance + state = S (copy S literals after this block) + length = 5 + L + Always followed by exactly one byte : H H H H H H H H + distance = (H << 3) + D + 1 + +Authors + + This document was written by Willy Tarreau <w@1wt.eu> on 2014/07/19 during an + analysis of the decompression code available in Linux 3.16-rc5. The code is + tricky, it is possible that this document contains mistakes or that a few + corner cases were overlooked. In any case, please report any doubt, fix, or + proposed updates to the author(s) so that the document can be updated. diff --git a/Documentation/ramoops.txt b/Documentation/ramoops.txt index 69b3cac4749d..5d8675615e59 100644 --- a/Documentation/ramoops.txt +++ b/Documentation/ramoops.txt @@ -14,11 +14,19 @@ survive after a restart. 1. Ramoops concepts -Ramoops uses a predefined memory area to store the dump. The start and size of -the memory area are set using two variables: +Ramoops uses a predefined memory area to store the dump. The start and size +and type of the memory area are set using three variables: * "mem_address" for the start * "mem_size" for the size. The memory size will be rounded down to a power of two. + * "mem_type" to specifiy if the memory type (default is pgprot_writecombine). + +Typically the default value of mem_type=0 should be used as that sets the pstore +mapping to pgprot_writecombine. Setting mem_type=1 attempts to use +pgprot_noncached, which only works on some platforms. This is because pstore +depends on atomic operations. At least on ARM, pgprot_noncached causes the +memory to be mapped strongly ordered, and atomic operations on strongly ordered +memory are implementation defined, and won't work on many ARMs such as omaps. The memory area is divided into "record_size" chunks (also rounded down to power of two) and each oops/panic writes a "record_size" chunk of @@ -55,6 +63,7 @@ Setting the ramoops parameters can be done in 2 different manners: static struct ramoops_platform_data ramoops_data = { .mem_size = <...>, .mem_address = <...>, + .mem_type = <...>, .record_size = <...>, .dump_oops = <...>, .ecc = <...>, diff --git a/Documentation/trace/coresight.txt b/Documentation/trace/coresight.txt new file mode 100644 index 000000000000..02361552a3ea --- /dev/null +++ b/Documentation/trace/coresight.txt @@ -0,0 +1,299 @@ + Coresight - HW Assisted Tracing on ARM + ====================================== + + Author: Mathieu Poirier <mathieu.poirier@linaro.org> + Date: September 11th, 2014 + +Introduction +------------ + +Coresight is an umbrella of technologies allowing for the debugging of ARM +based SoC. It includes solutions for JTAG and HW assisted tracing. This +document is concerned with the latter. + +HW assisted tracing is becoming increasingly useful when dealing with systems +that have many SoCs and other components like GPU and DMA engines. ARM has +developed a HW assisted tracing solution by means of different components, each +being added to a design at systhesis time to cater to specific tracing needs. +Compoments are generally categorised as source, link and sinks and are +(usually) discovered using the AMBA bus. + +"Sources" generate a compressed stream representing the processor instruction +path based on tracing scenarios as configured by users. From there the stream +flows through the coresight system (via ATB bus) using links that are connecting +the emanating source to a sink(s). Sinks serve as endpoints to the coresight +implementation, either storing the compressed stream in a memory buffer or +creating an interface to the outside world where data can be transferred to a +host without fear of filling up the onboard coresight memory buffer. + +At typical coresight system would look like this: + + ***************************************************************** + **************************** AMBA AXI ****************************===|| + ***************************************************************** || + ^ ^ | || + | | * ** + 0000000 ::::: 0000000 ::::: ::::: @@@@@@@ |||||||||||| + 0 CPU 0<-->: C : 0 CPU 0<-->: C : : C : @ STM @ || System || + |->0000000 : T : |->0000000 : T : : T :<--->@@@@@ || Memory || + | #######<-->: I : | #######<-->: I : : I : @@@<-| |||||||||||| + | # ETM # ::::: | # PTM # ::::: ::::: @ | + | ##### ^ ^ | ##### ^ ! ^ ! . | ||||||||| + | |->### | ! | |->### | ! | ! . | || DAP || + | | # | ! | | # | ! | ! . | ||||||||| + | | . | ! | | . | ! | ! . | | | + | | . | ! | | . | ! | ! . | | * + | | . | ! | | . | ! | ! . | | SWD/ + | | . | ! | | . | ! | ! . | | JTAG + *****************************************************************<-| + *************************** AMBA Debug APB ************************ + ***************************************************************** + | . ! . ! ! . | + | . * . * * . | + ***************************************************************** + ******************** Cross Trigger Matrix (CTM) ******************* + ***************************************************************** + | . ^ . . | + | * ! * * | + ***************************************************************** + ****************** AMBA Advanced Trace Bus (ATB) ****************** + ***************************************************************** + | ! =============== | + | * ===== F =====<---------| + | ::::::::: ==== U ==== + |-->:: CTI ::<!! === N === + | ::::::::: ! == N == + | ^ * == E == + | ! &&&&&&&&& IIIIIII == L == + |------>&& ETB &&<......II I ======= + | ! &&&&&&&&& II I . + | ! I I . + | ! I REP I<.......... + | ! I I + | !!>&&&&&&&&& II I *Source: ARM ltd. + |------>& TPIU &<......II I DAP = Debug Access Port + &&&&&&&&& IIIIIII ETM = Embedded Trace Macrocell + ; PTM = Program Trace Macrocell + ; CTI = Cross Trigger Interface + * ETB = Embedded Trace Buffer + To trace port TPIU= Trace Port Interface Unit + SWD = Serial Wire Debug + +While on target configuration of the components is done via the APB bus, +all trace data are carried out-of-band on the ATB bus. The CTM provides +a way to aggregate and distribute signals between CoreSight components. + +The coresight framework provides a central point to represent, configure and +manage coresight devices on a platform. This first implementation centers on +the basic tracing functionality, enabling components such ETM/PTM, funnel, +replicator, TMC, TPIU and ETB. Future work will enable more +intricate IP blocks such as STM and CTI. + + +Acronyms and Classification +--------------------------- + +Acronyms: + +PTM: Program Trace Macrocell +ETM: Embedded Trace Macrocell +STM: System trace Macrocell +ETB: Embedded Trace Buffer +ITM: Instrumentation Trace Macrocell +TPIU: Trace Port Interface Unit +TMC-ETR: Trace Memory Controller, configured as Embedded Trace Router +TMC-ETF: Trace Memory Controller, configured as Embedded Trace FIFO +CTI: Cross Trigger Interface + +Classification: + +Source: + ETMv3.x ETMv4, PTMv1.0, PTMv1.1, STM, STM500, ITM +Link: + Funnel, replicator (intelligent or not), TMC-ETR +Sinks: + ETBv1.0, ETB1.1, TPIU, TMC-ETF +Misc: + CTI + + +Device Tree Bindings +---------------------- + +See Documentation/devicetree/bindings/arm/coresight.txt for details. + +As of this writing drivers for ITM, STMs and CTIs are not provided but are +expected to be added as the solution matures. + + +Framework and implementation +---------------------------- + +The coresight framework provides a central point to represent, configure and +manage coresight devices on a platform. Any coresight compliant device can +register with the framework for as long as they use the right APIs: + +struct coresight_device *coresight_register(struct coresight_desc *desc); +void coresight_unregister(struct coresight_device *csdev); + +The registering function is taking a "struct coresight_device *csdev" and +register the device with the core framework. The unregister function takes +a reference to a "strut coresight_device", obtained at registration time. + +If everything goes well during the registration process the new devices will +show up under /sys/bus/coresight/devices, as showns here for a TC2 platform: + +root:~# ls /sys/bus/coresight/devices/ +replicator 20030000.tpiu 2201c000.ptm 2203c000.etm 2203e000.etm +20010000.etb 20040000.funnel 2201d000.ptm 2203d000.etm +root:~# + +The functions take a "struct coresight_device", which looks like this: + +struct coresight_desc { + enum coresight_dev_type type; + struct coresight_dev_subtype subtype; + const struct coresight_ops *ops; + struct coresight_platform_data *pdata; + struct device *dev; + const struct attribute_group **groups; +}; + + +The "coresight_dev_type" identifies what the device is, i.e, source link or +sink while the "coresight_dev_subtype" will characterise that type further. + +The "struct coresight_ops" is mandatory and will tell the framework how to +perform base operations related to the components, each component having +a different set of requirement. For that "struct coresight_ops_sink", +"struct coresight_ops_link" and "struct coresight_ops_source" have been +provided. + +The next field, "struct coresight_platform_data *pdata" is acquired by calling +"of_get_coresight_platform_data()", as part of the driver's _probe routine and +"struct device *dev" gets the device reference embedded in the "amba_device": + +static int etm_probe(struct amba_device *adev, const struct amba_id *id) +{ + ... + ... + drvdata->dev = &adev->dev; + ... +} + +Specific class of device (source, link, or sink) have generic operations +that can be performed on them (see "struct coresight_ops"). The +"**groups" is a list of sysfs entries pertaining to operations +specific to that component only. "Implementation defined" customisations are +expected to be accessed and controlled using those entries. + +Last but not least, "struct module *owner" is expected to be set to reflect +the information carried in "THIS_MODULE". + +How to use +---------- + +Before trace collection can start, a coresight sink needs to be identify. +There is no limit on the amount of sinks (nor sources) that can be enabled at +any given moment. As a generic operation, all device pertaining to the sink +class will have an "active" entry in sysfs: + +root:/sys/bus/coresight/devices# ls +replicator 20030000.tpiu 2201c000.ptm 2203c000.etm 2203e000.etm +20010000.etb 20040000.funnel 2201d000.ptm 2203d000.etm +root:/sys/bus/coresight/devices# ls 20010000.etb +enable_sink status trigger_cntr +root:/sys/bus/coresight/devices# echo 1 > 20010000.etb/enable_sink +root:/sys/bus/coresight/devices# cat 20010000.etb/enable_sink +1 +root:/sys/bus/coresight/devices# + +At boot time the current etm3x driver will configure the first address +comparator with "_stext" and "_etext", essentially tracing any instruction +that falls within that range. As such "enabling" a source will immediately +trigger a trace capture: + +root:/sys/bus/coresight/devices# echo 1 > 2201c000.ptm/enable_source +root:/sys/bus/coresight/devices# cat 2201c000.ptm/enable_source +1 +root:/sys/bus/coresight/devices# cat 20010000.etb/status +Depth: 0x2000 +Status: 0x1 +RAM read ptr: 0x0 +RAM wrt ptr: 0x19d3 <----- The write pointer is moving +Trigger cnt: 0x0 +Control: 0x1 +Flush status: 0x0 +Flush ctrl: 0x2001 +root:/sys/bus/coresight/devices# + +Trace collection is stopped the same way: + +root:/sys/bus/coresight/devices# echo 0 > 2201c000.ptm/enable_source +root:/sys/bus/coresight/devices# + +The content of the ETB buffer can be harvested directly from /dev: + +root:/sys/bus/coresight/devices# dd if=/dev/20010000.etb \ +of=~/cstrace.bin + +64+0 records in +64+0 records out +32768 bytes (33 kB) copied, 0.00125258 s, 26.2 MB/s +root:/sys/bus/coresight/devices# + +The file cstrace.bin can be decompressed using "ptm2human", DS-5 or Trace32. + +Following is a DS-5 output of an experimental loop that increments a variable up +to a certain value. The example is simple and yet provides a glimpse of the +wealth of possibilities that coresight provides. + +Info Tracing enabled +Instruction 106378866 0x8026B53C E52DE004 false PUSH {lr} +Instruction 0 0x8026B540 E24DD00C false SUB sp,sp,#0xc +Instruction 0 0x8026B544 E3A03000 false MOV r3,#0 +Instruction 0 0x8026B548 E58D3004 false STR r3,[sp,#4] +Instruction 0 0x8026B54C E59D3004 false LDR r3,[sp,#4] +Instruction 0 0x8026B550 E3530004 false CMP r3,#4 +Instruction 0 0x8026B554 E2833001 false ADD r3,r3,#1 +Instruction 0 0x8026B558 E58D3004 false STR r3,[sp,#4] +Instruction 0 0x8026B55C DAFFFFFA true BLE {pc}-0x10 ; 0x8026b54c +Timestamp Timestamp: 17106715833 +Instruction 319 0x8026B54C E59D3004 false LDR r3,[sp,#4] +Instruction 0 0x8026B550 E3530004 false CMP r3,#4 +Instruction 0 0x8026B554 E2833001 false ADD r3,r3,#1 +Instruction 0 0x8026B558 E58D3004 false STR r3,[sp,#4] +Instruction 0 0x8026B55C DAFFFFFA true BLE {pc}-0x10 ; 0x8026b54c +Instruction 9 0x8026B54C E59D3004 false LDR r3,[sp,#4] +Instruction 0 0x8026B550 E3530004 false CMP r3,#4 +Instruction 0 0x8026B554 E2833001 false ADD r3,r3,#1 +Instruction 0 0x8026B558 E58D3004 false STR r3,[sp,#4] +Instruction 0 0x8026B55C DAFFFFFA true BLE {pc}-0x10 ; 0x8026b54c +Instruction 7 0x8026B54C E59D3004 false LDR r3,[sp,#4] +Instruction 0 0x8026B550 E3530004 false CMP r3,#4 +Instruction 0 0x8026B554 E2833001 false ADD r3,r3,#1 +Instruction 0 0x8026B558 E58D3004 false STR r3,[sp,#4] +Instruction 0 0x8026B55C DAFFFFFA true BLE {pc}-0x10 ; 0x8026b54c +Instruction 7 0x8026B54C E59D3004 false LDR r3,[sp,#4] +Instruction 0 0x8026B550 E3530004 false CMP r3,#4 +Instruction 0 0x8026B554 E2833001 false ADD r3,r3,#1 +Instruction 0 0x8026B558 E58D3004 false STR r3,[sp,#4] +Instruction 0 0x8026B55C DAFFFFFA true BLE {pc}-0x10 ; 0x8026b54c +Instruction 10 0x8026B54C E59D3004 false LDR r3,[sp,#4] +Instruction 0 0x8026B550 E3530004 false CMP r3,#4 +Instruction 0 0x8026B554 E2833001 false ADD r3,r3,#1 +Instruction 0 0x8026B558 E58D3004 false STR r3,[sp,#4] +Instruction 0 0x8026B55C DAFFFFFA true BLE {pc}-0x10 ; 0x8026b54c +Instruction 6 0x8026B560 EE1D3F30 false MRC p15,#0x0,r3,c13,c0,#1 +Instruction 0 0x8026B564 E1A0100D false MOV r1,sp +Instruction 0 0x8026B568 E3C12D7F false BIC r2,r1,#0x1fc0 +Instruction 0 0x8026B56C E3C2203F false BIC r2,r2,#0x3f +Instruction 0 0x8026B570 E59D1004 false LDR r1,[sp,#4] +Instruction 0 0x8026B574 E59F0010 false LDR r0,[pc,#16] ; [0x8026B58C] = 0x80550368 +Instruction 0 0x8026B578 E592200C false LDR r2,[r2,#0xc] +Instruction 0 0x8026B57C E59221D0 false LDR r2,[r2,#0x1d0] +Instruction 0 0x8026B580 EB07A4CF true BL {pc}+0x1e9344 ; 0x804548c4 +Info Tracing enabled +Instruction 13570831 0x8026B584 E28DD00C false ADD sp,sp,#0xc +Instruction 0 0x8026B588 E8BD8000 true LDM sp!,{pc} +Timestamp Timestamp: 17107041535 diff --git a/MAINTAINERS b/MAINTAINERS index 4a4296ed9929..cad9448ea92d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -849,6 +849,14 @@ M: Hubert Feurstein <hubert.feurstein@contec.at> S: Maintained F: arch/arm/mach-ep93xx/micro9.c +ARM/CORESIGHT FRAMEWORK AND DRIVERS +M: Mathieu Poirier <mathieu.poirier@linaro.org> +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +S: Maintained +F: drivers/coresight/* +F: Documentation/trace/coresight.txt +F: Documentation/devicetree/bindings/arm/coresight.txt + ARM/CORGI MACHINE SUPPORT M: Richard Purdie <rpurdie@rpsys.net> S: Maintained @@ -6460,6 +6468,13 @@ F: drivers/scsi/osd/ F: include/scsi/osd_* F: fs/exofs/ +OVERLAY FILESYSTEM +M: Miklos Szeredi <miklos@szeredi.hu> +L: linux-fsdevel@vger.kernel.org +S: Supported +F: fs/overlayfs/* +F: Documentation/filesystems/overlayfs.txt + P54 WIRELESS DRIVER M: Christian Lamparter <chunkeey@googlemail.com> L: linux-wireless@vger.kernel.org @@ -1,6 +1,6 @@ VERSION = 3 PATCHLEVEL = 14 -SUBLEVEL = 19 +SUBLEVEL = 39 EXTRAVERSION = NAME = Remembering Coco diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 1402fcc11c2c..98f57d34923a 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -104,11 +104,12 @@ struct osf_dirent_callback { }; static int -osf_filldir(void *__buf, const char *name, int namlen, loff_t offset, - u64 ino, unsigned int d_type) +osf_filldir(struct dir_context *ctx, const char *name, int namlen, + loff_t offset, u64 ino, unsigned int d_type) { struct osf_dirent __user *dirent; - struct osf_dirent_callback *buf = (struct osf_dirent_callback *) __buf; + struct osf_dirent_callback *buf = + container_of(ctx, struct osf_dirent_callback, ctx); unsigned int reclen = ALIGN(NAME_OFFSET + namlen + 1, sizeof(u32)); unsigned int d_ino; diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts index 4f31b2eb5cdf..4c169d825415 100644 --- a/arch/arc/boot/dts/nsimosci.dts +++ b/arch/arc/boot/dts/nsimosci.dts @@ -20,7 +20,7 @@ /* this is for console on PGU */ /* bootargs = "console=tty0 consoleblank=0"; */ /* this is for console on serial */ - bootargs = "earlycon=uart8250,mmio32,0xc0000000,115200n8 console=ttyS0,115200n8 consoleblank=0 debug"; + bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug"; }; aliases { @@ -46,9 +46,9 @@ #interrupt-cells = <1>; }; - uart0: serial@c0000000 { + uart0: serial@f0000000 { compatible = "ns8250"; - reg = <0xc0000000 0x2000>; + reg = <0xf0000000 0x2000>; interrupts = <11>; clock-frequency = <3686400>; baud = <115200>; @@ -57,21 +57,21 @@ no-loopback-test = <1>; }; - pgu0: pgu@c9000000 { + pgu0: pgu@f9000000 { compatible = "snps,arcpgufb"; - reg = <0xc9000000 0x400>; + reg = <0xf9000000 0x400>; }; - ps2: ps2@c9001000 { + ps2: ps2@f9001000 { compatible = "snps,arc_ps2"; - reg = <0xc9000400 0x14>; + reg = <0xf9000400 0x14>; interrupts = <13>; interrupt-names = "arc_ps2_irq"; }; - eth0: ethernet@c0003000 { + eth0: ethernet@f0003000 { compatible = "snps,oscilan"; - reg = <0xc0003000 0x44>; + reg = <0xf0003000 0x44>; interrupts = <7>, <8>; interrupt-names = "rx", "tx"; }; diff --git a/arch/arc/include/asm/barrier.h b/arch/arc/include/asm/barrier.h deleted file mode 100644 index c32245c3d1e9..000000000000 --- a/arch/arc/include/asm/barrier.h +++ /dev/null @@ -1,37 +0,0 @@ -/* - * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#ifndef __ASM_BARRIER_H -#define __ASM_BARRIER_H - -#ifndef __ASSEMBLY__ - -/* TODO-vineetg: Need to see what this does, don't we need sync anywhere */ -#define mb() __asm__ __volatile__ ("" : : : "memory") -#define rmb() mb() -#define wmb() mb() -#define set_mb(var, value) do { var = value; mb(); } while (0) -#define set_wmb(var, value) do { var = value; wmb(); } while (0) -#define read_barrier_depends() mb() - -/* TODO-vineetg verify the correctness of macros here */ -#ifdef CONFIG_SMP -#define smp_mb() mb() -#define smp_rmb() rmb() -#define smp_wmb() wmb() -#else -#define smp_mb() barrier() -#define smp_rmb() barrier() -#define smp_wmb() barrier() -#endif - -#define smp_read_barrier_depends() do { } while (0) - -#endif - -#endif diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h index 2fd3162ec4df..c1d3d2da1191 100644 --- a/arch/arc/include/asm/cache.h +++ b/arch/arc/include/asm/cache.h @@ -55,4 +55,31 @@ extern void read_decode_cache_bcr(void); #endif /* !__ASSEMBLY__ */ +/* Instruction cache related Auxiliary registers */ +#define ARC_REG_IC_BCR 0x77 /* Build Config reg */ +#define ARC_REG_IC_IVIC 0x10 +#define ARC_REG_IC_CTRL 0x11 +#define ARC_REG_IC_IVIL 0x19 +#if defined(CONFIG_ARC_MMU_V3) || defined (CONFIG_ARC_MMU_V4) +#define ARC_REG_IC_PTAG 0x1E +#endif + +/* Bit val in IC_CTRL */ +#define IC_CTRL_CACHE_DISABLE 0x1 + +/* Data cache related Auxiliary registers */ +#define ARC_REG_DC_BCR 0x72 /* Build Config reg */ +#define ARC_REG_DC_IVDC 0x47 +#define ARC_REG_DC_CTRL 0x48 +#define ARC_REG_DC_IVDL 0x4A +#define ARC_REG_DC_FLSH 0x4B +#define ARC_REG_DC_FLDL 0x4C +#if defined(CONFIG_ARC_MMU_V3) || defined (CONFIG_ARC_MMU_V4) +#define ARC_REG_DC_PTAG 0x5C +#endif + +/* Bit val in DC_CTRL */ +#define DC_CTRL_INV_MODE_FLUSH 0x40 +#define DC_CTRL_FLUSH_STATUS 0x100 + #endif /* _ASM_CACHE_H */ diff --git a/arch/arc/include/asm/kgdb.h b/arch/arc/include/asm/kgdb.h index b65fca7ffeb5..fea931634136 100644 --- a/arch/arc/include/asm/kgdb.h +++ b/arch/arc/include/asm/kgdb.h @@ -19,7 +19,7 @@ * register API yet */ #undef DBG_MAX_REG_NUM -#define GDB_MAX_REGS 39 +#define GDB_MAX_REGS 87 #define BREAK_INSTR_SIZE 2 #define CACHE_FLUSH_IS_SAFE 1 @@ -33,23 +33,27 @@ static inline void arch_kgdb_breakpoint(void) extern void kgdb_trap(struct pt_regs *regs); -enum arc700_linux_regnums { +/* This is the numbering of registers according to the GDB. See GDB's + * arc-tdep.h for details. + * + * Registers are ordered for GDB 7.5. It is incompatible with GDB 6.8. */ +enum arc_linux_regnums { _R0 = 0, _R1, _R2, _R3, _R4, _R5, _R6, _R7, _R8, _R9, _R10, _R11, _R12, _R13, _R14, _R15, _R16, _R17, _R18, _R19, _R20, _R21, _R22, _R23, _R24, _R25, _R26, - _BTA = 27, - _LP_START = 28, - _LP_END = 29, - _LP_COUNT = 30, - _STATUS32 = 31, - _BLINK = 32, - _FP = 33, - __SP = 34, - _EFA = 35, - _RET = 36, - _ORIG_R8 = 37, - _STOP_PC = 38 + _FP = 27, + __SP = 28, + _R30 = 30, + _BLINK = 31, + _LP_COUNT = 60, + _STOP_PC = 64, + _RET = 64, + _LP_START = 65, + _LP_END = 66, + _STATUS32 = 67, + _ECR = 76, + _BTA = 82, }; #else diff --git a/arch/arc/include/asm/linkage.h b/arch/arc/include/asm/linkage.h index 66ee5527aefc..5faad17118b4 100644 --- a/arch/arc/include/asm/linkage.h +++ b/arch/arc/include/asm/linkage.h @@ -13,20 +13,6 @@ #define ASM_NL ` /* use '`' to mark new line in macro */ -/* Can't use the ENTRY macro in linux/linkage.h - * gas considers ';' as comment vs. newline - */ -.macro ARC_ENTRY name - .global \name - .align 4 - \name: -.endm - -.macro ARC_EXIT name -#define ASM_PREV_SYM_ADDR(name) .-##name - .size \ name, ASM_PREV_SYM_ADDR(\name) -.endm - /* annotation for data we want in DCCM - if enabled in .config */ .macro ARCFP_DATA nm #ifdef CONFIG_ARC_HAS_DCCM diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index 6b0b7f7ef783..7670f33b9ce2 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -259,7 +259,8 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep) #define pmd_clear(xp) do { pmd_val(*(xp)) = 0; } while (0) #define pte_page(x) (mem_map + \ - (unsigned long)(((pte_val(x) - PAGE_OFFSET) >> PAGE_SHIFT))) + (unsigned long)(((pte_val(x) - CONFIG_LINUX_LINK_BASE) >> \ + PAGE_SHIFT))) #define mk_pte(page, pgprot) \ ({ \ diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h index 15334ab66b56..fb95aa807215 100644 --- a/arch/arc/include/asm/processor.h +++ b/arch/arc/include/asm/processor.h @@ -69,18 +69,19 @@ unsigned long thread_saved_pc(struct task_struct *t); #define release_segments(mm) do { } while (0) #define KSTK_EIP(tsk) (task_pt_regs(tsk)->ret) +#define KSTK_ESP(tsk) (task_pt_regs(tsk)->sp) /* * Where abouts of Task's sp, fp, blink when it was last seen in kernel mode. * Look in process.c for details of kernel stack layout */ -#define KSTK_ESP(tsk) (tsk->thread.ksp) +#define TSK_K_ESP(tsk) (tsk->thread.ksp) -#define KSTK_REG(tsk, off) (*((unsigned int *)(KSTK_ESP(tsk) + \ +#define TSK_K_REG(tsk, off) (*((unsigned int *)(TSK_K_ESP(tsk) + \ sizeof(struct callee_regs) + off))) -#define KSTK_BLINK(tsk) KSTK_REG(tsk, 4) -#define KSTK_FP(tsk) KSTK_REG(tsk, 0) +#define TSK_K_BLINK(tsk) TSK_K_REG(tsk, 4) +#define TSK_K_FP(tsk) TSK_K_REG(tsk, 0) /* * Do necessary setup to start up a newly executed thread. diff --git a/arch/arc/kernel/ctx_sw_asm.S b/arch/arc/kernel/ctx_sw_asm.S index 65690e7fcc8c..e248594097e7 100644 --- a/arch/arc/kernel/ctx_sw_asm.S +++ b/arch/arc/kernel/ctx_sw_asm.S @@ -10,9 +10,9 @@ * -This is the more "natural" hand written assembler */ +#include <linux/linkage.h> #include <asm/entry.h> /* For the SAVE_* macros */ #include <asm/asm-offsets.h> -#include <asm/linkage.h> #define KSP_WORD_OFF ((TASK_THREAD + THREAD_KSP) / 4) @@ -62,4 +62,4 @@ __switch_to: ld.ab blink, [sp, 4] j [blink] -ARC_EXIT __switch_to +END(__switch_to) diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index 6e8f83a32522..29b82adbf0b4 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -141,7 +141,7 @@ VECTOR EV_Extension ; 0x130, Extn Intruction Excp (0x26) VECTOR reserved ; Reserved Exceptions .endr -#include <linux/linkage.h> /* ARC_{EXTRY,EXIT} */ +#include <linux/linkage.h> /* {EXTRY,EXIT} */ #include <asm/entry.h> /* SAVE_ALL_{INT1,INT2,SYS...} */ #include <asm/errno.h> #include <asm/arcregs.h> @@ -184,7 +184,7 @@ reserved: ; processor restart ; --------------------------------------------- ; Level 2 ISR: Can interrupt a Level 1 ISR ; --------------------------------------------- -ARC_ENTRY handle_interrupt_level2 +ENTRY(handle_interrupt_level2) ; TODO-vineetg for SMP this wont work ; free up r9 as scratchpad @@ -225,14 +225,14 @@ ARC_ENTRY handle_interrupt_level2 b ret_from_exception -ARC_EXIT handle_interrupt_level2 +END(handle_interrupt_level2) #endif ; --------------------------------------------- ; Level 1 ISR ; --------------------------------------------- -ARC_ENTRY handle_interrupt_level1 +ENTRY(handle_interrupt_level1) /* free up r9 as scratchpad */ #ifdef CONFIG_SMP @@ -265,7 +265,7 @@ ARC_ENTRY handle_interrupt_level1 sr r8, [AUX_IRQ_LV12] ; clear bit in Sticky Status Reg b ret_from_exception -ARC_EXIT handle_interrupt_level1 +END(handle_interrupt_level1) ;################### Non TLB Exception Handling ############################# @@ -273,7 +273,7 @@ ARC_EXIT handle_interrupt_level1 ; Instruction Error Exception Handler ; --------------------------------------------- -ARC_ENTRY instr_service +ENTRY(instr_service) EXCEPTION_PROLOGUE @@ -284,13 +284,13 @@ ARC_ENTRY instr_service bl do_insterror_or_kprobe b ret_from_exception -ARC_EXIT instr_service +END(instr_service) ; --------------------------------------------- ; Memory Error Exception Handler ; --------------------------------------------- -ARC_ENTRY mem_service +ENTRY(mem_service) EXCEPTION_PROLOGUE @@ -301,13 +301,13 @@ ARC_ENTRY mem_service bl do_memory_error b ret_from_exception -ARC_EXIT mem_service +END(mem_service) ; --------------------------------------------- ; Machine Check Exception Handler ; --------------------------------------------- -ARC_ENTRY EV_MachineCheck +ENTRY(EV_MachineCheck) EXCEPTION_PROLOGUE @@ -331,13 +331,13 @@ ARC_ENTRY EV_MachineCheck j do_machine_check_fault -ARC_EXIT EV_MachineCheck +END(EV_MachineCheck) ; --------------------------------------------- ; Protection Violation Exception Handler ; --------------------------------------------- -ARC_ENTRY EV_TLBProtV +ENTRY(EV_TLBProtV) EXCEPTION_PROLOGUE @@ -385,12 +385,12 @@ ARC_ENTRY EV_TLBProtV b ret_from_exception -ARC_EXIT EV_TLBProtV +END(EV_TLBProtV) ; --------------------------------------------- ; Privilege Violation Exception Handler ; --------------------------------------------- -ARC_ENTRY EV_PrivilegeV +ENTRY(EV_PrivilegeV) EXCEPTION_PROLOGUE @@ -401,12 +401,12 @@ ARC_ENTRY EV_PrivilegeV bl do_privilege_fault b ret_from_exception -ARC_EXIT EV_PrivilegeV +END(EV_PrivilegeV) ; --------------------------------------------- ; Extension Instruction Exception Handler ; --------------------------------------------- -ARC_ENTRY EV_Extension +ENTRY(EV_Extension) EXCEPTION_PROLOGUE @@ -417,7 +417,7 @@ ARC_ENTRY EV_Extension bl do_extension_fault b ret_from_exception -ARC_EXIT EV_Extension +END(EV_Extension) ;######################### System Call Tracing ######################### @@ -504,7 +504,7 @@ trap_with_param: ; (2) Break Points ;------------------------------------------------------------------ -ARC_ENTRY EV_Trap +ENTRY(EV_Trap) EXCEPTION_PROLOGUE @@ -534,9 +534,9 @@ ARC_ENTRY EV_Trap jl [r9] ; Entry into Sys Call Handler ; fall through to ret_from_system_call -ARC_EXIT EV_Trap +END(EV_Trap) -ARC_ENTRY ret_from_system_call +ENTRY(ret_from_system_call) st r0, [sp, PT_r0] ; sys call return value in pt_regs @@ -546,7 +546,7 @@ ARC_ENTRY ret_from_system_call ; ; If ret to user mode do we need to handle signals, schedule() et al. -ARC_ENTRY ret_from_exception +ENTRY(ret_from_exception) ; Pre-{IRQ,Trap,Exception} K/U mode from pt_regs->status32 ld r8, [sp, PT_status32] ; returning to User/Kernel Mode @@ -728,9 +728,9 @@ not_level1_interrupt: debug_marker_syscall: rtie -ARC_EXIT ret_from_exception +END(ret_from_exception) -ARC_ENTRY ret_from_fork +ENTRY(ret_from_fork) ; when the forked child comes here from the __switch_to function ; r0 has the last task pointer. ; put last task in scheduler queue @@ -747,11 +747,11 @@ ARC_ENTRY ret_from_fork ; special case of kernel_thread entry point returning back due to ; kernel_execve() - pretend return from syscall to ret to userland b ret_from_exception -ARC_EXIT ret_from_fork +END(ret_from_fork) ;################### Special Sys Call Wrappers ########################## -ARC_ENTRY sys_clone_wrapper +ENTRY(sys_clone_wrapper) SAVE_CALLEE_SAVED_USER bl @sys_clone DISCARD_CALLEE_SAVED_USER @@ -761,7 +761,7 @@ ARC_ENTRY sys_clone_wrapper bnz tracesys_exit b ret_from_system_call -ARC_EXIT sys_clone_wrapper +END(sys_clone_wrapper) #ifdef CONFIG_ARC_DW2_UNWIND ; Workaround for bug 94179 (STAR ): diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S index 991997269d02..07a58f2d3077 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -12,10 +12,42 @@ * to skip certain things during boot on simulator */ +#include <linux/linkage.h> #include <asm/asm-offsets.h> #include <asm/entry.h> -#include <linux/linkage.h> #include <asm/arcregs.h> +#include <asm/cache.h> + +.macro CPU_EARLY_SETUP + + ; Setting up Vectror Table (in case exception happens in early boot + sr @_int_vec_base_lds, [AUX_INTR_VEC_BASE] + + ; Disable I-cache/D-cache if kernel so configured + lr r5, [ARC_REG_IC_BCR] + breq r5, 0, 1f ; I$ doesn't exist + lr r5, [ARC_REG_IC_CTRL] +#ifdef CONFIG_ARC_HAS_ICACHE + bclr r5, r5, 0 ; 0 - Enable, 1 is Disable +#else + bset r5, r5, 0 ; I$ exists, but is not used +#endif + sr r5, [ARC_REG_IC_CTRL] + +1: + lr r5, [ARC_REG_DC_BCR] + breq r5, 0, 1f ; D$ doesn't exist + lr r5, [ARC_REG_DC_CTRL] + bclr r5, r5, 6 ; Invalidate (discard w/o wback) +#ifdef CONFIG_ARC_HAS_DCACHE + bclr r5, r5, 0 ; Enable (+Inv) +#else + bset r5, r5, 0 ; Disable (+Inv) +#endif + sr r5, [ARC_REG_DC_CTRL] + +1: +.endm .cpu A7 @@ -24,13 +56,13 @@ .globl stext stext: ;------------------------------------------------------------------- - ; Don't clobber r0-r4 yet. It might have bootloader provided info + ; Don't clobber r0-r2 yet. It might have bootloader provided info ;------------------------------------------------------------------- - sr @_int_vec_base_lds, [AUX_INTR_VEC_BASE] + CPU_EARLY_SETUP #ifdef CONFIG_SMP - ; Only Boot (Master) proceeds. Others wait in platform dependent way + ; Ensure Boot (Master) proceeds. Others wait in platform dependent way ; IDENTITY Reg [ 3 2 1 0 ] ; (cpu-id) ^^^ => Zero for UP ARC700 ; => #Core-ID if SMP (Master 0) @@ -39,7 +71,8 @@ stext: ; need to make sure only boot cpu takes this path. GET_CPU_ID r5 cmp r5, 0 - jnz arc_platform_smp_wait_to_boot + mov.ne r0, r5 + jne arc_platform_smp_wait_to_boot #endif ; Clear BSS before updating any globals ; XXX: use ZOL here @@ -89,7 +122,7 @@ stext: first_lines_of_secondary: - sr @_int_vec_base_lds, [AUX_INTR_VEC_BASE] + CPU_EARLY_SETUP ; setup per-cpu idle task as "current" on this CPU ld r0, [@secondary_idle_tsk] diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index 7e95e1a86510..d68b410595c8 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -67,7 +67,7 @@ stash_usr_regs(struct rt_sigframe __user *sf, struct pt_regs *regs, sigset_t *set) { int err; - err = __copy_to_user(&(sf->uc.uc_mcontext.regs), regs, + err = __copy_to_user(&(sf->uc.uc_mcontext.regs.scratch), regs, sizeof(sf->uc.uc_mcontext.regs.scratch)); err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t)); @@ -83,7 +83,7 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf) if (!err) set_current_blocked(&set); - err |= __copy_from_user(regs, &(sf->uc.uc_mcontext.regs), + err |= __copy_from_user(regs, &(sf->uc.uc_mcontext.regs.scratch), sizeof(sf->uc.uc_mcontext.regs.scratch)); return err; diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index 9ce47cfe2303..fb98769b6a98 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -64,9 +64,9 @@ static void seed_unwind_frame_info(struct task_struct *tsk, frame_info->task = tsk; - frame_info->regs.r27 = KSTK_FP(tsk); - frame_info->regs.r28 = KSTK_ESP(tsk); - frame_info->regs.r31 = KSTK_BLINK(tsk); + frame_info->regs.r27 = TSK_K_FP(tsk); + frame_info->regs.r28 = TSK_K_ESP(tsk); + frame_info->regs.r31 = TSK_K_BLINK(tsk); frame_info->regs.r63 = (unsigned int)__switch_to; /* In the prologue of __switch_to, first FP is saved on stack diff --git a/arch/arc/lib/memcmp.S b/arch/arc/lib/memcmp.S index bc813d55b6c3..978bf8314dfb 100644 --- a/arch/arc/lib/memcmp.S +++ b/arch/arc/lib/memcmp.S @@ -6,7 +6,7 @@ * published by the Free Software Foundation. */ -#include <asm/linkage.h> +#include <linux/linkage.h> #ifdef __LITTLE_ENDIAN__ #define WORD2 r2 @@ -16,7 +16,7 @@ #define SHIFT r2 #endif -ARC_ENTRY memcmp +ENTRY(memcmp) or r12,r0,r1 asl_s r12,r12,30 sub r3,r2,1 @@ -121,4 +121,4 @@ ARC_ENTRY memcmp .Lnil: j_s.d [blink] mov r0,0 -ARC_EXIT memcmp +END(memcmp) diff --git a/arch/arc/lib/memcpy-700.S b/arch/arc/lib/memcpy-700.S index b64cc10ac918..3222573e50de 100644 --- a/arch/arc/lib/memcpy-700.S +++ b/arch/arc/lib/memcpy-700.S @@ -6,9 +6,9 @@ * published by the Free Software Foundation. */ -#include <asm/linkage.h> +#include <linux/linkage.h> -ARC_ENTRY memcpy +ENTRY(memcpy) or r3,r0,r1 asl_s r3,r3,30 mov_s r5,r0 @@ -63,4 +63,4 @@ ARC_ENTRY memcpy .Lendbloop: j_s.d [blink] stb r12,[r5,0] -ARC_EXIT memcpy +END(memcpy) diff --git a/arch/arc/lib/memset.S b/arch/arc/lib/memset.S index 9b2d88d2e141..d36bd43fc98d 100644 --- a/arch/arc/lib/memset.S +++ b/arch/arc/lib/memset.S @@ -6,11 +6,11 @@ * published by the Free Software Foundation. */ -#include <asm/linkage.h> +#include <linux/linkage.h> #define SMALL 7 /* Must be at least 6 to deal with alignment/loop issues. */ -ARC_ENTRY memset +ENTRY(memset) mov_s r4,r0 or r12,r0,r2 bmsk.f r12,r12,1 @@ -46,14 +46,14 @@ ARC_ENTRY memset stb.ab r1,[r4,1] .Ltiny_end: j_s [blink] -ARC_EXIT memset +END(memset) ; memzero: @r0 = mem, @r1 = size_t ; memset: @r0 = mem, @r1 = char, @r2 = size_t -ARC_ENTRY memzero +ENTRY(memzero) ; adjust bzero args to memset args mov r2, r1 mov r1, 0 b memset ;tail call so need to tinker with blink -ARC_EXIT memzero +END(memzero) diff --git a/arch/arc/lib/strchr-700.S b/arch/arc/lib/strchr-700.S index 9c548c7cf001..b725d5862107 100644 --- a/arch/arc/lib/strchr-700.S +++ b/arch/arc/lib/strchr-700.S @@ -11,9 +11,9 @@ presence of the norm instruction makes it easier to operate on whole words branch-free. */ -#include <asm/linkage.h> +#include <linux/linkage.h> -ARC_ENTRY strchr +ENTRY(strchr) extb_s r1,r1 asl r5,r1,8 bmsk r2,r0,1 @@ -130,4 +130,4 @@ ARC_ENTRY strchr j_s.d [blink] mov.mi r0,0 #endif /* ENDIAN */ -ARC_EXIT strchr +END(strchr) diff --git a/arch/arc/lib/strcmp.S b/arch/arc/lib/strcmp.S index 5dc802b45cf3..3544600fefe6 100644 --- a/arch/arc/lib/strcmp.S +++ b/arch/arc/lib/strcmp.S @@ -13,9 +13,9 @@ source 1; however, that would increase the overhead for loop setup / finish, and strcmp might often terminate early. */ -#include <asm/linkage.h> +#include <linux/linkage.h> -ARC_ENTRY strcmp +ENTRY(strcmp) or r2,r0,r1 bmsk_s r2,r2,1 brne r2,0,.Lcharloop @@ -93,4 +93,4 @@ ARC_ENTRY strcmp .Lcmpend: j_s.d [blink] sub r0,r2,r3 -ARC_EXIT strcmp +END(strcmp) diff --git a/arch/arc/lib/strcpy-700.S b/arch/arc/lib/strcpy-700.S index b7ca4ae81d88..8422f38e1218 100644 --- a/arch/arc/lib/strcpy-700.S +++ b/arch/arc/lib/strcpy-700.S @@ -16,9 +16,9 @@ there, but the it is not likely to be taken often, and it would also be likey to cost an unaligned mispredict at the next call. */ -#include <asm/linkage.h> +#include <linux/linkage.h> -ARC_ENTRY strcpy +ENTRY(strcpy) or r2,r0,r1 bmsk_s r2,r2,1 brne.d r2,0,charloop @@ -67,4 +67,4 @@ charloop: brne.d r3,0,charloop stb.ab r3,[r10,1] j [blink] -ARC_EXIT strcpy +END(strcpy) diff --git a/arch/arc/lib/strlen.S b/arch/arc/lib/strlen.S index 39759e099696..53cfd5685a5f 100644 --- a/arch/arc/lib/strlen.S +++ b/arch/arc/lib/strlen.S @@ -6,9 +6,9 @@ * published by the Free Software Foundation. */ -#include <asm/linkage.h> +#include <linux/linkage.h> -ARC_ENTRY strlen +ENTRY(strlen) or r3,r0,7 ld r2,[r3,-7] ld.a r6,[r3,-3] @@ -80,4 +80,4 @@ ARC_ENTRY strlen .Learly_end: b.d .Lend sub_s.ne r1,r1,r1 -ARC_EXIT strlen +END(strlen) diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c index 400c663b21c2..1f676c4794e0 100644 --- a/arch/arc/mm/cache_arc700.c +++ b/arch/arc/mm/cache_arc700.c @@ -73,37 +73,9 @@ #include <asm/cachectl.h> #include <asm/setup.h> -/* Instruction cache related Auxiliary registers */ -#define ARC_REG_IC_BCR 0x77 /* Build Config reg */ -#define ARC_REG_IC_IVIC 0x10 -#define ARC_REG_IC_CTRL 0x11 -#define ARC_REG_IC_IVIL 0x19 -#if (CONFIG_ARC_MMU_VER > 2) -#define ARC_REG_IC_PTAG 0x1E -#endif - -/* Bit val in IC_CTRL */ -#define IC_CTRL_CACHE_DISABLE 0x1 - -/* Data cache related Auxiliary registers */ -#define ARC_REG_DC_BCR 0x72 /* Build Config reg */ -#define ARC_REG_DC_IVDC 0x47 -#define ARC_REG_DC_CTRL 0x48 -#define ARC_REG_DC_IVDL 0x4A -#define ARC_REG_DC_FLSH 0x4B -#define ARC_REG_DC_FLDL 0x4C -#if (CONFIG_ARC_MMU_VER > 2) -#define ARC_REG_DC_PTAG 0x5C -#endif - -/* Bit val in DC_CTRL */ -#define DC_CTRL_INV_MODE_FLUSH 0x40 -#define DC_CTRL_FLUSH_STATUS 0x100 - -char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len) +char *arc_cache_mumbojumbo(int c, char *buf, int len) { int n = 0; - unsigned int c = smp_processor_id(); #define PR_CACHE(p, enb, str) \ { \ @@ -169,72 +141,43 @@ void read_decode_cache_bcr(void) */ void arc_cache_init(void) { - unsigned int cpu = smp_processor_id(); - struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache; - struct cpuinfo_arc_cache *dc = &cpuinfo_arc700[cpu].dcache; - unsigned int dcache_does_alias, temp; + unsigned int __maybe_unused cpu = smp_processor_id(); + struct cpuinfo_arc_cache __maybe_unused *ic, __maybe_unused *dc; char str[256]; printk(arc_cache_mumbojumbo(0, str, sizeof(str))); - if (!ic->ver) - goto chk_dc; - -#ifdef CONFIG_ARC_HAS_ICACHE - /* 1. Confirm some of I-cache params which Linux assumes */ - if (ic->line_len != L1_CACHE_BYTES) - panic("Cache H/W doesn't match kernel Config"); - - if (ic->ver != CONFIG_ARC_MMU_VER) - panic("Cache ver doesn't match MMU ver\n"); -#endif - - /* Enable/disable I-Cache */ - temp = read_aux_reg(ARC_REG_IC_CTRL); - #ifdef CONFIG_ARC_HAS_ICACHE - temp &= ~IC_CTRL_CACHE_DISABLE; -#else - temp |= IC_CTRL_CACHE_DISABLE; + ic = &cpuinfo_arc700[cpu].icache; + if (ic->ver) { + if (ic->line_len != L1_CACHE_BYTES) + panic("ICache line [%d] != kernel Config [%d]", + ic->line_len, L1_CACHE_BYTES); + + if (ic->ver != CONFIG_ARC_MMU_VER) + panic("Cache ver [%d] doesn't match MMU ver [%d]\n", + ic->ver, CONFIG_ARC_MMU_VER); + } #endif - write_aux_reg(ARC_REG_IC_CTRL, temp); - -chk_dc: - if (!dc->ver) - return; - #ifdef CONFIG_ARC_HAS_DCACHE - if (dc->line_len != L1_CACHE_BYTES) - panic("Cache H/W doesn't match kernel Config"); + dc = &cpuinfo_arc700[cpu].dcache; + if (dc->ver) { + unsigned int dcache_does_alias; - /* check for D-Cache aliasing */ - dcache_does_alias = (dc->sz / dc->assoc) > PAGE_SIZE; + if (dc->line_len != L1_CACHE_BYTES) + panic("DCache line [%d] != kernel Config [%d]", + dc->line_len, L1_CACHE_BYTES); - if (dcache_does_alias && !cache_is_vipt_aliasing()) - panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n"); - else if (!dcache_does_alias && cache_is_vipt_aliasing()) - panic("Don't need CONFIG_ARC_CACHE_VIPT_ALIASING\n"); -#endif - - /* Set the default Invalidate Mode to "simpy discard dirty lines" - * as this is more frequent then flush before invalidate - * Ofcourse we toggle this default behviour when desired - */ - temp = read_aux_reg(ARC_REG_DC_CTRL); - temp &= ~DC_CTRL_INV_MODE_FLUSH; + /* check for D-Cache aliasing */ + dcache_does_alias = (dc->sz / dc->assoc) > PAGE_SIZE; -#ifdef CONFIG_ARC_HAS_DCACHE - /* Enable D-Cache: Clear Bit 0 */ - write_aux_reg(ARC_REG_DC_CTRL, temp & ~IC_CTRL_CACHE_DISABLE); -#else - /* Flush D cache */ - write_aux_reg(ARC_REG_DC_FLSH, 0x1); - /* Disable D cache */ - write_aux_reg(ARC_REG_DC_CTRL, temp | IC_CTRL_CACHE_DISABLE); + if (dcache_does_alias && !cache_is_vipt_aliasing()) + panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n"); + else if (!dcache_does_alias && cache_is_vipt_aliasing()) + panic("Don't need CONFIG_ARC_CACHE_VIPT_ALIASING\n"); + } #endif - - return; } #define OP_INV 0x1 @@ -254,12 +197,16 @@ static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr, if (cacheop == OP_INV_IC) { aux_cmd = ARC_REG_IC_IVIL; +#if (CONFIG_ARC_MMU_VER > 2) aux_tag = ARC_REG_IC_PTAG; +#endif } else { /* d$ cmd: INV (discard or wback-n-discard) OR FLUSH (wback) */ aux_cmd = cacheop & OP_INV ? ARC_REG_DC_IVDL : ARC_REG_DC_FLDL; +#if (CONFIG_ARC_MMU_VER > 2) aux_tag = ARC_REG_DC_PTAG; +#endif } /* Ensure we properly floor/ceil the non-line aligned/sized requests diff --git a/arch/arc/mm/tlbex.S b/arch/arc/mm/tlbex.S index 3fcfdb38d242..79bfc81358c9 100644 --- a/arch/arc/mm/tlbex.S +++ b/arch/arc/mm/tlbex.S @@ -260,7 +260,7 @@ ARCFP_CODE ;Fast Path Code, candidate for ICCM ; I-TLB Miss Exception Handler ;----------------------------------------------------------------------------- -ARC_ENTRY EV_TLBMissI +ENTRY(EV_TLBMissI) TLBMISS_FREEUP_REGS @@ -293,13 +293,13 @@ ARC_ENTRY EV_TLBMissI TLBMISS_RESTORE_REGS rtie -ARC_EXIT EV_TLBMissI +END(EV_TLBMissI) ;----------------------------------------------------------------------------- ; D-TLB Miss Exception Handler ;----------------------------------------------------------------------------- -ARC_ENTRY EV_TLBMissD +ENTRY(EV_TLBMissD) TLBMISS_FREEUP_REGS @@ -381,6 +381,4 @@ do_slow_path_pf: bl do_page_fault b ret_from_exception -ARC_EXIT EV_TLBMissD - -ARC_ENTRY EV_TLBMissB ; Bogus entry to measure sz of DTLBMiss hdlr +END(EV_TLBMissD) diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 4733d327cfb1..3d053aaa98a7 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -5,6 +5,7 @@ config ARM select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAVE_CUSTOM_GPIO_H + select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_USE_BUILTIN_BSWAP diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index 0531da8e5216..6a5a2b481463 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -1172,14 +1172,6 @@ config EARLY_PRINTK kernel low-level debugging functions. Add earlyprintk to your kernel parameters to enable this console. -config OC_ETM - bool "On-chip ETM and ETB" - depends on ARM_AMBA - help - Enables the on-chip embedded trace macrocell and embedded trace - buffer driver that will allow you to collect traces of the - kernel code. - config ARM_KPROBES_TEST tristate "Kprobes test module" depends on KPROBES && MODULES @@ -1206,4 +1198,59 @@ config DEBUG_SET_MODULE_RONX against certain classes of kernel exploits. If in doubt, say "N". +menuconfig CORESIGHT + bool "CoreSight Tracing Support" + select ARM_AMBA + help + This framework provides a kernel interface for the CoreSight debug + and trace drivers to register themselves with. It's intended to build + a topological view of the CoreSight components based on a DT + specification and configure the right serie of components when a + trace source gets enabled. + +if CORESIGHT +config CORESIGHT_LINKS_AND_SINKS + bool "CoreSight Link and Sink drivers" + help + This enables support for CoreSight link and sink drivers that are + responsible for transporting and collecting the trace data + respectively. Link and sinks are dynamically aggregated with a trace + entity at run time to form a complete trace path. + +config CORESIGHT_LINK_AND_SINK_TMC + bool "Coresight generic TMC driver" + depends on CORESIGHT_LINKS_AND_SINKS + help + This enables support for the Trace Memory Controller driver. Depending + on its configuration the device can act as a link (embedded trace router + - ETR) or sink (embedded trace FIFO). The driver complies with the + generic implementation of the component without special enhancement or + added features. + +config CORESIGHT_SINK_TPIU + bool "Coresight generic TPIU driver" + depends on CORESIGHT_LINKS_AND_SINKS + help + This enables support for the Trace Port Interface Unit driver, responsible + for bridging the gap between the on-chip coresight components and a trace + port collection engine, typically connected to an external host for use + case capturing more traces than the on-board coresight memory can handle. + +config CORESIGHT_SINK_ETBV10 + bool "Coresight ETBv1.0 driver" + depends on CORESIGHT_LINKS_AND_SINKS + help + This enables support for the Embedded Trace Buffer version 1.0 driver + that complies with the generic implementation of the component without + special enhancement or added features. + +config CORESIGHT_SOURCE_ETM3X + bool "CoreSight Embedded Trace Macrocell 3.x driver" + select CORESIGHT_LINKS_AND_SINKS + help + This driver provides support for processor ETM3.x and PTM1.x modules, + which allows tracing the instructions that a processor is executing + This is primarily useful for instruction level tracing. Depending + the ETM version data tracing may also be available. +endif endmenu diff --git a/arch/arm/boot/bootp/Makefile b/arch/arm/boot/bootp/Makefile index c394e305447c..5761f0039133 100644 --- a/arch/arm/boot/bootp/Makefile +++ b/arch/arm/boot/bootp/Makefile @@ -5,6 +5,8 @@ # architecture-specific flags and dependencies. # +GCOV_PROFILE := n + LDFLAGS_bootp :=-p --no-undefined -X \ --defsym initrd_phys=$(INITRD_PHYS) \ --defsym params_phys=$(PARAMS_PHYS) -T diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 68c918362b79..b5ad32efcd33 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -37,6 +37,8 @@ ifeq ($(CONFIG_ARM_VIRT_EXT),y) OBJS += hyp-stub.o endif +GCOV_PROFILE := n + # # Architecture dependencies # diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 066b03480b63..8017cde13648 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -400,8 +400,7 @@ dtb_check_done: add sp, sp, r6 #endif - tst r4, #1 - bleq cache_clean_flush + bl cache_clean_flush adr r0, BSYM(restart) add r0, r0, r6 @@ -1050,6 +1049,8 @@ cache_clean_flush: b call_cache_fn __armv4_mpu_cache_flush: + tst r4, #1 + movne pc, lr mov r2, #1 mov r3, #0 mcr p15, 0, ip, c7, c6, 0 @ invalidate D cache @@ -1067,6 +1068,8 @@ __armv4_mpu_cache_flush: mov pc, lr __fa526_cache_flush: + tst r4, #1 + movne pc, lr mov r1, #0 mcr p15, 0, r1, c7, c14, 0 @ clean and invalidate D cache mcr p15, 0, r1, c7, c5, 0 @ flush I cache @@ -1075,13 +1078,16 @@ __fa526_cache_flush: __armv6_mmu_cache_flush: mov r1, #0 - mcr p15, 0, r1, c7, c14, 0 @ clean+invalidate D + tst r4, #1 + mcreq p15, 0, r1, c7, c14, 0 @ clean+invalidate D mcr p15, 0, r1, c7, c5, 0 @ invalidate I+BTB - mcr p15, 0, r1, c7, c15, 0 @ clean+invalidate unified + mcreq p15, 0, r1, c7, c15, 0 @ clean+invalidate unified mcr p15, 0, r1, c7, c10, 4 @ drain WB mov pc, lr __armv7_mmu_cache_flush: + tst r4, #1 + bne iflush mrc p15, 0, r10, c0, c1, 5 @ read ID_MMFR1 tst r10, #0xf << 16 @ hierarchical cache (ARMv7) mov r10, #0 @@ -1142,6 +1148,8 @@ iflush: mov pc, lr __armv5tej_mmu_cache_flush: + tst r4, #1 + movne pc, lr 1: mrc p15, 0, r15, c7, c14, 3 @ test,clean,invalidate D cache bne 1b mcr p15, 0, r0, c7, c5, 0 @ flush I cache @@ -1149,6 +1157,8 @@ __armv5tej_mmu_cache_flush: mov pc, lr __armv4_mmu_cache_flush: + tst r4, #1 + movne pc, lr mov r2, #64*1024 @ default: 32K dcache size (*2) mov r11, #32 @ default: 32 byte line size mrc p15, 0, r3, c0, c0, 1 @ read cache type @@ -1182,6 +1192,8 @@ no_cache_id: __armv3_mmu_cache_flush: __armv3_mpu_cache_flush: + tst r4, #1 + movne pc, lr mov r1, #0 mcr p15, 0, r1, c7, c0, 0 @ invalidate whole cache v3 mov pc, lr diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi index 2e7d932887b5..b3eff40188c6 100644 --- a/arch/arm/boot/dts/am335x-bone-common.dtsi +++ b/arch/arm/boot/dts/am335x-bone-common.dtsi @@ -197,6 +197,7 @@ usb@47401000 { status = "okay"; + dr_mode = "peripheral"; }; usb@47401800 { diff --git a/arch/arm/boot/dts/armada-370-netgear-rn102.dts b/arch/arm/boot/dts/armada-370-netgear-rn102.dts index 651aeb5ef439..f3188e953de4 100644 --- a/arch/arm/boot/dts/armada-370-netgear-rn102.dts +++ b/arch/arm/boot/dts/armada-370-netgear-rn102.dts @@ -144,6 +144,10 @@ marvell,nand-enable-arbiter; nand-on-flash-bbt; + /* Use Hardware BCH ECC */ + nand-ecc-strength = <4>; + nand-ecc-step-size = <512>; + partition@0 { label = "u-boot"; reg = <0x0000000 0x180000>; /* 1.5MB */ diff --git a/arch/arm/boot/dts/armada-370-netgear-rn104.dts b/arch/arm/boot/dts/armada-370-netgear-rn104.dts index 4e27587667bf..da406c1c726a 100644 --- a/arch/arm/boot/dts/armada-370-netgear-rn104.dts +++ b/arch/arm/boot/dts/armada-370-netgear-rn104.dts @@ -146,6 +146,10 @@ marvell,nand-enable-arbiter; nand-on-flash-bbt; + /* Use Hardware BCH ECC */ + nand-ecc-strength = <4>; + nand-ecc-step-size = <512>; + partition@0 { label = "u-boot"; reg = <0x0000000 0x180000>; /* 1.5MB */ diff --git a/arch/arm/boot/dts/armada-370.dtsi b/arch/arm/boot/dts/armada-370.dtsi index 0d8530c98cf5..34841fc1a977 100644 --- a/arch/arm/boot/dts/armada-370.dtsi +++ b/arch/arm/boot/dts/armada-370.dtsi @@ -106,11 +106,6 @@ reg = <0x11100 0x20>; }; - system-controller@18200 { - compatible = "marvell,armada-370-xp-system-controller"; - reg = <0x18200 0x100>; - }; - pinctrl { compatible = "marvell,mv88f6710-pinctrl"; reg = <0x18000 0x38>; @@ -167,6 +162,11 @@ interrupts = <91>; }; + system-controller@18200 { + compatible = "marvell,armada-370-xp-system-controller"; + reg = <0x18200 0x100>; + }; + gateclk: clock-gating-control@18220 { compatible = "marvell,armada-370-gating-clock"; reg = <0x18220 0x4>; diff --git a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts index ff049ee862eb..b4aba09de911 100644 --- a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts +++ b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts @@ -224,6 +224,10 @@ marvell,nand-enable-arbiter; nand-on-flash-bbt; + /* Use Hardware BCH ECC */ + nand-ecc-strength = <4>; + nand-ecc-step-size = <512>; + partition@0 { label = "u-boot"; reg = <0x0000000 0x180000>; /* 1.5MB */ diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi index fece8665fb63..b8f234bf7de8 100644 --- a/arch/arm/boot/dts/at91sam9263.dtsi +++ b/arch/arm/boot/dts/at91sam9263.dtsi @@ -535,6 +535,7 @@ compatible = "atmel,hsmci"; reg = <0xfff80000 0x600>; interrupts = <10 IRQ_TYPE_LEVEL_HIGH 0>; + pinctrl-names = "default"; #address-cells = <1>; #size-cells = <0>; status = "disabled"; @@ -544,6 +545,7 @@ compatible = "atmel,hsmci"; reg = <0xfff84000 0x600>; interrupts = <11 IRQ_TYPE_LEVEL_HIGH 0>; + pinctrl-names = "default"; #address-cells = <1>; #size-cells = <0>; status = "disabled"; diff --git a/arch/arm/boot/dts/dra7-evm.dts b/arch/arm/boot/dts/dra7-evm.dts index 904dcf5973f3..9381754b35cc 100644 --- a/arch/arm/boot/dts/dra7-evm.dts +++ b/arch/arm/boot/dts/dra7-evm.dts @@ -50,13 +50,13 @@ mcspi1_pins: pinmux_mcspi1_pins { pinctrl-single,pins = < - 0x3a4 (PIN_INPUT | MUX_MODE0) /* spi2_clk */ - 0x3a8 (PIN_INPUT | MUX_MODE0) /* spi2_d1 */ - 0x3ac (PIN_INPUT | MUX_MODE0) /* spi2_d0 */ - 0x3b0 (PIN_INPUT_SLEW | MUX_MODE0) /* spi2_cs0 */ - 0x3b4 (PIN_INPUT_SLEW | MUX_MODE0) /* spi2_cs1 */ - 0x3b8 (PIN_INPUT_SLEW | MUX_MODE6) /* spi2_cs2 */ - 0x3bc (PIN_INPUT_SLEW | MUX_MODE6) /* spi2_cs3 */ + 0x3a4 (PIN_INPUT | MUX_MODE0) /* spi1_sclk */ + 0x3a8 (PIN_INPUT | MUX_MODE0) /* spi1_d1 */ + 0x3ac (PIN_INPUT | MUX_MODE0) /* spi1_d0 */ + 0x3b0 (PIN_INPUT_SLEW | MUX_MODE0) /* spi1_cs0 */ + 0x3b4 (PIN_INPUT_SLEW | MUX_MODE0) /* spi1_cs1 */ + 0x3b8 (PIN_INPUT_SLEW | MUX_MODE6) /* spi1_cs2.hdmi1_hpd */ + 0x3bc (PIN_INPUT_SLEW | MUX_MODE6) /* spi1_cs3.hdmi1_cec */ >; }; diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index 1fd75aa4639d..f60aeee2fc9e 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -178,7 +178,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; gpio2: gpio@48055000 { @@ -189,7 +189,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; gpio3: gpio@48057000 { @@ -200,7 +200,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; gpio4: gpio@48059000 { @@ -211,7 +211,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; gpio5: gpio@4805b000 { @@ -222,7 +222,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; gpio6: gpio@4805d000 { @@ -233,7 +233,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; gpio7: gpio@48051000 { @@ -244,7 +244,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; gpio8: gpio@48053000 { @@ -255,7 +255,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; - #interrupt-cells = <1>; + #interrupt-cells = <2>; }; uart1: serial@4806a000 { @@ -458,7 +458,7 @@ }; wdt2: wdt@4ae14000 { - compatible = "ti,omap4-wdt"; + compatible = "ti,omap3-wdt"; reg = <0x4ae14000 0x80>; interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>; ti,hwmods = "wd_timer2"; diff --git a/arch/arm/boot/dts/dra7xx-clocks.dtsi b/arch/arm/boot/dts/dra7xx-clocks.dtsi index e96da9a898ad..f2512e1d28c7 100644 --- a/arch/arm/boot/dts/dra7xx-clocks.dtsi +++ b/arch/arm/boot/dts/dra7xx-clocks.dtsi @@ -243,10 +243,18 @@ ti,invert-autoidle-bit; }; + dpll_core_byp_mux: dpll_core_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + ti,bit-shift = <23>; + reg = <0x012c>; + }; + dpll_core_ck: dpll_core_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-core-clock"; - clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + clocks = <&sys_clkin1>, <&dpll_core_byp_mux>; reg = <0x0120>, <0x0124>, <0x012c>, <0x0128>; }; @@ -309,10 +317,18 @@ clock-div = <1>; }; + dpll_dsp_byp_mux: dpll_dsp_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&dsp_dpll_hs_clk_div>; + ti,bit-shift = <23>; + reg = <0x0240>; + }; + dpll_dsp_ck: dpll_dsp_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin1>, <&dsp_dpll_hs_clk_div>; + clocks = <&sys_clkin1>, <&dpll_dsp_byp_mux>; reg = <0x0234>, <0x0238>, <0x0240>, <0x023c>; }; @@ -335,10 +351,18 @@ clock-div = <1>; }; + dpll_iva_byp_mux: dpll_iva_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&iva_dpll_hs_clk_div>; + ti,bit-shift = <23>; + reg = <0x01ac>; + }; + dpll_iva_ck: dpll_iva_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin1>, <&iva_dpll_hs_clk_div>; + clocks = <&sys_clkin1>, <&dpll_iva_byp_mux>; reg = <0x01a0>, <0x01a4>, <0x01ac>, <0x01a8>; }; @@ -361,10 +385,18 @@ clock-div = <1>; }; + dpll_gpu_byp_mux: dpll_gpu_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + ti,bit-shift = <23>; + reg = <0x02e4>; + }; + dpll_gpu_ck: dpll_gpu_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + clocks = <&sys_clkin1>, <&dpll_gpu_byp_mux>; reg = <0x02d8>, <0x02dc>, <0x02e4>, <0x02e0>; }; @@ -398,10 +430,18 @@ clock-div = <1>; }; + dpll_ddr_byp_mux: dpll_ddr_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + ti,bit-shift = <23>; + reg = <0x021c>; + }; + dpll_ddr_ck: dpll_ddr_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + clocks = <&sys_clkin1>, <&dpll_ddr_byp_mux>; reg = <0x0210>, <0x0214>, <0x021c>, <0x0218>; }; @@ -416,10 +456,18 @@ ti,invert-autoidle-bit; }; + dpll_gmac_byp_mux: dpll_gmac_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + ti,bit-shift = <23>; + reg = <0x02b4>; + }; + dpll_gmac_ck: dpll_gmac_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + clocks = <&sys_clkin1>, <&dpll_gmac_byp_mux>; reg = <0x02a8>, <0x02ac>, <0x02b4>, <0x02b0>; }; @@ -482,10 +530,18 @@ clock-div = <1>; }; + dpll_eve_byp_mux: dpll_eve_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&eve_dpll_hs_clk_div>; + ti,bit-shift = <23>; + reg = <0x0290>; + }; + dpll_eve_ck: dpll_eve_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin1>, <&eve_dpll_hs_clk_div>; + clocks = <&sys_clkin1>, <&dpll_eve_byp_mux>; reg = <0x0284>, <0x0288>, <0x0290>, <0x028c>; }; @@ -1214,10 +1270,18 @@ clock-div = <1>; }; + dpll_per_byp_mux: dpll_per_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&per_dpll_hs_clk_div>; + ti,bit-shift = <23>; + reg = <0x014c>; + }; + dpll_per_ck: dpll_per_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin1>, <&per_dpll_hs_clk_div>; + clocks = <&sys_clkin1>, <&dpll_per_byp_mux>; reg = <0x0140>, <0x0144>, <0x014c>, <0x0148>; }; @@ -1240,10 +1304,18 @@ clock-div = <1>; }; + dpll_usb_byp_mux: dpll_usb_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&usb_dpll_hs_clk_div>; + ti,bit-shift = <23>; + reg = <0x018c>; + }; + dpll_usb_ck: dpll_usb_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-j-type-clock"; - clocks = <&sys_clkin1>, <&usb_dpll_hs_clk_div>; + clocks = <&sys_clkin1>, <&dpll_usb_byp_mux>; reg = <0x0180>, <0x0184>, <0x018c>, <0x0188>; }; diff --git a/arch/arm/boot/dts/hip04.dtsi b/arch/arm/boot/dts/hip04.dtsi new file mode 100644 index 000000000000..238814596a87 --- /dev/null +++ b/arch/arm/boot/dts/hip04.dtsi @@ -0,0 +1,984 @@ +/* + * Hisilicon Ltd. HiP04 SoC + * + * Copyright (C) 2013-2014 Hisilicon Ltd. + * Copyright (C) 2013-2014 Linaro Ltd. + * + * Author: Haojian Zhuang <haojian.zhuang@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/ { + /* memory bus is 64-bit */ + #address-cells = <2>; + #size-cells = <2>; + + aliases { + serial0 = &uart0; + }; + + bootwrapper { + compatible = "hisilicon,hip04-bootwrapper"; + boot-method = <0x10c00000 0x10000>, <0xe0000100 0x1000>; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu-map { + cluster0 { + core0 { + cpu = <&CPU0>; + }; + core1 { + cpu = <&CPU1>; + }; + core2 { + cpu = <&CPU2>; + }; + core3 { + cpu = <&CPU3>; + }; + }; + cluster1 { + core0 { + cpu = <&CPU4>; + }; + core1 { + cpu = <&CPU5>; + }; + core2 { + cpu = <&CPU6>; + }; + core3 { + cpu = <&CPU7>; + }; + }; + cluster2 { + core0 { + cpu = <&CPU8>; + }; + core1 { + cpu = <&CPU9>; + }; + core2 { + cpu = <&CPU10>; + }; + core3 { + cpu = <&CPU11>; + }; + }; + cluster3 { + core0 { + cpu = <&CPU12>; + }; + core1 { + cpu = <&CPU13>; + }; + core2 { + cpu = <&CPU14>; + }; + core3 { + cpu = <&CPU15>; + }; + }; + }; + CPU0: cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0>; + }; + CPU1: cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <1>; + }; + CPU2: cpu@2 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <2>; + }; + CPU3: cpu@3 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <3>; + }; + CPU4: cpu@100 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0x100>; + }; + CPU5: cpu@101 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0x101>; + }; + CPU6: cpu@102 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0x102>; + }; + CPU7: cpu@103 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0x103>; + }; + CPU8: cpu@200 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0x200>; + }; + CPU9: cpu@201 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0x201>; + }; + CPU10: cpu@202 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0x202>; + }; + CPU11: cpu@203 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0x203>; + }; + CPU12: cpu@300 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0x300>; + }; + CPU13: cpu@301 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0x301>; + }; + CPU14: cpu@302 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0x302>; + }; + CPU15: cpu@303 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0x303>; + }; + }; + + timer { + compatible = "arm,armv7-timer"; + interrupt-parent = <&gic>; + interrupts = <1 13 0xf08>, + <1 14 0xf08>, + <1 11 0xf08>, + <1 10 0xf08>; + }; + + clk_50m: clk_50m { + #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <50000000>; + }; + + clk_168m: clk_168m { + #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <168000000>; + }; + + clk_375m: clk_375m { + #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <375000000>; + }; + + soc { + /* It's a 32-bit SoC. */ + #address-cells = <1>; + #size-cells = <1>; + compatible = "simple-bus"; + interrupt-parent = <&gic>; + ranges = <0 0 0xe0000000 0x10000000>; + + gic: interrupt-controller@c01000 { + compatible = "hisilicon,hip04-intc"; + #interrupt-cells = <3>; + #address-cells = <0>; + interrupt-controller; + interrupts = <1 9 0xf04>; + + reg = <0xc01000 0x1000>, <0xc02000 0x1000>, + <0xc04000 0x2000>, <0xc06000 0x2000>; + }; + + sysctrl: sysctrl { + compatible = "hisilicon,sysctrl"; + reg = <0x3e00000 0x00100000>; + }; + + fabric: fabric { + compatible = "hisilicon,hip04-fabric"; + reg = <0x302a000 0x1000>; + }; + + dual_timer0: dual_timer@3000000 { + compatible = "arm,sp804", "arm,primecell"; + reg = <0x3000000 0x1000>; + interrupts = <0 224 4>; + clocks = <&clk_50m>, <&clk_50m>; + clock-names = "apb_pclk"; + }; + + arm-pmu { + compatible = "arm,cortex-a15-pmu"; + interrupts = <0 64 4>, + <0 65 4>, + <0 66 4>, + <0 67 4>, + <0 68 4>, + <0 69 4>, + <0 70 4>, + <0 71 4>, + <0 72 4>, + <0 73 4>, + <0 74 4>, + <0 75 4>, + <0 76 4>, + <0 77 4>, + <0 78 4>, + <0 79 4>; + }; + + uart0: uart@4007000 { + compatible = "snps,dw-apb-uart"; + reg = <0x4007000 0x1000>; + interrupts = <0 381 4>; + clocks = <&clk_168m>; + clock-names = "uartclk"; + reg-shift = <2>; + status = "disabled"; + }; + + sata0: sata@a000000 { + compatible = "hisilicon,hisi-ahci"; + reg = <0xa000000 0x1000000>; + interrupts = <0 372 4>; + }; + + }; + + etb@0,e3c42000 { + compatible = "arm,coresight-etb10", "arm,primecell"; + reg = <0 0xe3c42000 0 0x1000>; + + coresight-default-sink; + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + port { + etb0_in_port: endpoint@0 { + slave-mode; + remote-endpoint = <&replicator0_out_port0>; + }; + }; + }; + + etb@0,e3c82000 { + compatible = "arm,coresight-etb10", "arm,primecell"; + reg = <0 0xe3c82000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + port { + etb1_in_port: endpoint@0 { + slave-mode; + remote-endpoint = <&replicator1_out_port0>; + }; + }; + }; + + etb@0,e3cc2000 { + compatible = "arm,coresight-etb10", "arm,primecell"; + reg = <0 0xe3cc2000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + port { + etb2_in_port: endpoint@0 { + slave-mode; + remote-endpoint = <&replicator2_out_port0>; + }; + }; + }; + + etb@0,e3d02000 { + compatible = "arm,coresight-etb10", "arm,primecell"; + reg = <0 0xe3d02000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + port { + etb3_in_port: endpoint@0 { + slave-mode; + remote-endpoint = <&replicator3_out_port0>; + }; + }; + }; + + tpiu@0,e3c05000 { + compatible = "arm,coresight-tpiu", "arm,primecell"; + reg = <0 0xe3c05000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + port { + tpiu_in_port: endpoint@0 { + slave-mode; + remote-endpoint = <&funnel4_out_port0>; + }; + }; + }; + + replicator0 { + /* non-configurable replicators don't show up on the + * AMBA bus. As such no need to add "arm,primecell". + */ + compatible = "arm,coresight-replicator"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + /* replicator output ports */ + port@0 { + reg = <0>; + replicator0_out_port0: endpoint { + remote-endpoint = <&etb0_in_port>; + }; + }; + + port@1 { + reg = <1>; + replicator0_out_port1: endpoint { + remote-endpoint = <&funnel4_in_port0>; + }; + }; + + /* replicator input port */ + port@2 { + reg = <0>; + replicator0_in_port0: endpoint { + slave-mode; + remote-endpoint = <&funnel0_out_port0>; + }; + }; + }; + }; + + replicator1 { + /* non-configurable replicators don't show up on the + * AMBA bus. As such no need to add "arm,primecell". + */ + compatible = "arm,coresight-replicator"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + /* replicator output ports */ + port@0 { + reg = <0>; + replicator1_out_port0: endpoint { + remote-endpoint = <&etb1_in_port>; + }; + }; + + port@1 { + reg = <1>; + replicator1_out_port1: endpoint { + remote-endpoint = <&funnel4_in_port1>; + }; + }; + + /* replicator input port */ + port@2 { + reg = <0>; + replicator1_in_port0: endpoint { + slave-mode; + remote-endpoint = <&funnel1_out_port0>; + }; + }; + }; + }; + + replicator2 { + /* non-configurable replicators don't show up on the + * AMBA bus. As such no need to add "arm,primecell". + */ + compatible = "arm,coresight-replicator"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + /* replicator output ports */ + port@0 { + reg = <0>; + replicator2_out_port0: endpoint { + remote-endpoint = <&etb2_in_port>; + }; + }; + + port@1 { + reg = <1>; + replicator2_out_port1: endpoint { + remote-endpoint = <&funnel4_in_port2>; + }; + }; + + /* replicator input port */ + port@2 { + reg = <0>; + replicator2_in_port0: endpoint { + slave-mode; + remote-endpoint = <&funnel2_out_port0>; + }; + }; + }; + }; + + replicator3 { + /* non-configurable replicators don't show up on the + * AMBA bus. As such no need to add "arm,primecell". + */ + compatible = "arm,coresight-replicator"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + /* replicator output ports */ + port@0 { + reg = <0>; + replicator3_out_port0: endpoint { + remote-endpoint = <&etb3_in_port>; + }; + }; + + port@1 { + reg = <1>; + replicator3_out_port1: endpoint { + remote-endpoint = <&funnel4_in_port3>; + }; + }; + + /* replicator input port */ + port@2 { + reg = <0>; + replicator3_in_port0: endpoint { + slave-mode; + remote-endpoint = <&funnel3_out_port0>; + }; + }; + }; + }; + + funnel@0,e3c41000 { + compatible = "arm,coresight-funnel", "arm,primecell"; + reg = <0 0xe3c41000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + ports { + #address-cells = <1>; + #size-cells = <0>; + + /* funnel output port */ + port@0 { + reg = <0>; + funnel0_out_port0: endpoint { + remote-endpoint = + <&replicator0_in_port0>; + }; + }; + + /* funnel input ports */ + port@1 { + reg = <0>; + funnel0_in_port0: endpoint { + slave-mode; + remote-endpoint = <&ptm0_out_port>; + }; + }; + + port@2 { + reg = <1>; + funnel0_in_port1: endpoint { + slave-mode; + remote-endpoint = <&ptm1_out_port>; + }; + }; + + port@3 { + reg = <2>; + funnel0_in_port2: endpoint { + slave-mode; + remote-endpoint = <&ptm2_out_port>; + }; + }; + + port@4 { + reg = <3>; + funnel0_in_port3: endpoint { + slave-mode; + remote-endpoint = <&ptm3_out_port>; + }; + }; + }; + }; + + funnel@0,e3c81000 { + compatible = "arm,coresight-funnel", "arm,primecell"; + reg = <0 0xe3c81000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + ports { + #address-cells = <1>; + #size-cells = <0>; + + /* funnel output port */ + port@0 { + reg = <0>; + funnel1_out_port0: endpoint { + remote-endpoint = + <&replicator1_in_port0>; + }; + }; + + /* funnel input ports */ + port@1 { + reg = <0>; + funnel1_in_port0: endpoint { + slave-mode; + remote-endpoint = <&ptm4_out_port>; + }; + }; + + port@2 { + reg = <1>; + funnel1_in_port1: endpoint { + slave-mode; + remote-endpoint = <&ptm5_out_port>; + }; + }; + + port@3 { + reg = <2>; + funnel1_in_port2: endpoint { + slave-mode; + remote-endpoint = <&ptm6_out_port>; + }; + }; + + port@4 { + reg = <3>; + funnel1_in_port3: endpoint { + slave-mode; + remote-endpoint = <&ptm7_out_port>; + }; + }; + }; + }; + + funnel@0,e3cc1000 { + compatible = "arm,coresight-funnel", "arm,primecell"; + reg = <0 0xe3cc1000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + ports { + #address-cells = <1>; + #size-cells = <0>; + + /* funnel output port */ + port@0 { + reg = <0>; + funnel2_out_port0: endpoint { + remote-endpoint = + <&replicator2_in_port0>; + }; + }; + + /* funnel input ports */ + port@1 { + reg = <0>; + funnel2_in_port0: endpoint { + slave-mode; + remote-endpoint = <&ptm8_out_port>; + }; + }; + + port@2 { + reg = <1>; + funnel2_in_port1: endpoint { + slave-mode; + remote-endpoint = <&ptm9_out_port>; + }; + }; + + port@3 { + reg = <2>; + funnel2_in_port2: endpoint { + slave-mode; + remote-endpoint = <&ptm10_out_port>; + }; + }; + + port@4 { + reg = <3>; + funnel2_in_port3: endpoint { + slave-mode; + remote-endpoint = <&ptm11_out_port>; + }; + }; + }; + }; + + funnel@0,e3d01000 { + compatible = "arm,coresight-funnel", "arm,primecell"; + reg = <0 0xe3d01000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + ports { + #address-cells = <1>; + #size-cells = <0>; + + /* funnel output port */ + port@0 { + reg = <0>; + funnel3_out_port0: endpoint { + remote-endpoint = + <&replicator3_in_port0>; + }; + }; + + /* funnel input ports */ + port@1 { + reg = <0>; + funnel3_in_port0: endpoint { + slave-mode; + remote-endpoint = <&ptm12_out_port>; + }; + }; + + port@2 { + reg = <1>; + funnel3_in_port1: endpoint { + slave-mode; + remote-endpoint = <&ptm13_out_port>; + }; + }; + + port@3 { + reg = <2>; + funnel3_in_port2: endpoint { + slave-mode; + remote-endpoint = <&ptm14_out_port>; + }; + }; + + port@4 { + reg = <3>; + funnel3_in_port3: endpoint { + slave-mode; + remote-endpoint = <&ptm15_out_port>; + }; + }; + }; + }; + + funnel@0,e3c04000 { + compatible = "arm,coresight-funnel", "arm,primecell"; + reg = <0 0xe3c04000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + ports { + #address-cells = <1>; + #size-cells = <0>; + + /* funnel output port */ + port@0 { + reg = <0>; + funnel4_out_port0: endpoint { + remote-endpoint = <&tpiu_in_port>; + }; + }; + + /* funnel input ports */ + port@1 { + reg = <0>; + funnel4_in_port0: endpoint { + slave-mode; + remote-endpoint = + <&replicator0_out_port1>; + }; + }; + + port@2 { + reg = <1>; + funnel4_in_port1: endpoint { + slave-mode; + remote-endpoint = + <&replicator1_out_port1>; + }; + }; + + port@3 { + reg = <2>; + funnel4_in_port2: endpoint { + slave-mode; + remote-endpoint = + <&replicator2_out_port1>; + }; + }; + + port@4 { + reg = <3>; + funnel4_in_port3: endpoint { + slave-mode; + remote-endpoint = + <&replicator3_out_port1>; + }; + }; + }; + }; + + ptm@0,e3c7c000 { + compatible = "arm,coresight-etm3x", "arm,primecell"; + reg = <0 0xe3c7c000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + cpu = <&CPU0>; + port { + ptm0_out_port: endpoint { + remote-endpoint = <&funnel0_in_port0>; + }; + }; + }; + + ptm@0,e3c7d000 { + compatible = "arm,coresight-etm3x", "arm,primecell"; + reg = <0 0xe3c7d000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + cpu = <&CPU1>; + port { + ptm1_out_port: endpoint { + remote-endpoint = <&funnel0_in_port1>; + }; + }; + }; + + ptm@0,e3c7e000 { + compatible = "arm,coresight-etm3x", "arm,primecell"; + reg = <0 0xe3c7e000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + cpu = <&CPU2>; + port { + ptm2_out_port: endpoint { + remote-endpoint = <&funnel0_in_port2>; + }; + }; + }; + + ptm@0,e3c7f000 { + compatible = "arm,coresight-etm3x", "arm,primecell"; + reg = <0 0xe3c7f000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + cpu = <&CPU3>; + port { + ptm3_out_port: endpoint { + remote-endpoint = <&funnel0_in_port3>; + }; + }; + }; + + ptm@0,e3cbc000 { + compatible = "arm,coresight-etm3x", "arm,primecell"; + reg = <0 0xe3cbc000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + cpu = <&CPU4>; + port { + ptm4_out_port: endpoint { + remote-endpoint = <&funnel1_in_port0>; + }; + }; + }; + + ptm@0,e3cbd000 { + compatible = "arm,coresight-etm3x", "arm,primecell"; + reg = <0 0xe3cbd000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + cpu = <&CPU5>; + port { + ptm5_out_port: endpoint { + remote-endpoint = <&funnel1_in_port1>; + }; + }; + }; + + ptm@0,e3cbe000 { + compatible = "arm,coresight-etm3x", "arm,primecell"; + reg = <0 0xe3cbe000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + cpu = <&CPU6>; + port { + ptm6_out_port: endpoint { + remote-endpoint = <&funnel1_in_port2>; + }; + }; + }; + + ptm@0,e3cbf000 { + compatible = "arm,coresight-etm3x", "arm,primecell"; + reg = <0 0xe3cbf000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + cpu = <&CPU7>; + port { + ptm7_out_port: endpoint { + remote-endpoint = <&funnel1_in_port3>; + }; + }; + }; + + ptm@0,e3cfc000 { + compatible = "arm,coresight-etm3x", "arm,primecell"; + reg = <0 0xe3cfc000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + cpu = <&CPU8>; + port { + ptm8_out_port: endpoint { + remote-endpoint = <&funnel2_in_port0>; + }; + }; + }; + + ptm@0,e3cfd000 { + compatible = "arm,coresight-etm3x", "arm,primecell"; + reg = <0 0xe3cfd000 0 0x1000>; + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + cpu = <&CPU9>; + port { + ptm9_out_port: endpoint { + remote-endpoint = <&funnel2_in_port1>; + }; + }; + }; + + ptm@0,e3cfe000 { + compatible = "arm,coresight-etm3x", "arm,primecell"; + reg = <0 0xe3cfe000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + cpu = <&CPU10>; + port { + ptm10_out_port: endpoint { + remote-endpoint = <&funnel2_in_port2>; + }; + }; + }; + + ptm@0,e3cff000 { + compatible = "arm,coresight-etm3x", "arm,primecell"; + reg = <0 0xe3cff000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + cpu = <&CPU11>; + port { + ptm11_out_port: endpoint { + remote-endpoint = <&funnel2_in_port3>; + }; + }; + }; + + ptm@0,e3d3c000 { + compatible = "arm,coresight-etm3x", "arm,primecell"; + reg = <0 0xe3d3c000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + cpu = <&CPU12>; + port { + ptm12_out_port: endpoint { + remote-endpoint = <&funnel3_in_port0>; + }; + }; + }; + + ptm@0,e3d3d000 { + compatible = "arm,coresight-etm3x", "arm,primecell"; + reg = <0 0xe3d3d000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + cpu = <&CPU13>; + port { + ptm13_out_port: endpoint { + remote-endpoint = <&funnel3_in_port1>; + }; + }; + }; + + ptm@0,e3d3e000 { + compatible = "arm,coresight-etm3x", "arm,primecell"; + reg = <0 0xe3d3e000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + cpu = <&CPU14>; + port { + ptm14_out_port: endpoint { + remote-endpoint = <&funnel3_in_port2>; + }; + }; + }; + + ptm@0,e3d3f000 { + compatible = "arm,coresight-etm3x", "arm,primecell"; + reg = <0 0xe3d3f000 0 0x1000>; + + clocks = <&clk_375m>; + clock-names = "apb_pclk"; + cpu = <&CPU15>; + port { + ptm15_out_port: endpoint { + remote-endpoint = <&funnel3_in_port3>; + }; + }; + }; +}; diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi index de1611966d8b..cf3300a3071d 100644 --- a/arch/arm/boot/dts/imx25.dtsi +++ b/arch/arm/boot/dts/imx25.dtsi @@ -158,7 +158,7 @@ #size-cells = <0>; compatible = "fsl,imx25-cspi", "fsl,imx35-cspi"; reg = <0x43fa4000 0x4000>; - clocks = <&clks 62>, <&clks 62>; + clocks = <&clks 78>, <&clks 78>; clock-names = "ipg", "per"; interrupts = <14>; status = "disabled"; @@ -352,7 +352,7 @@ compatible = "fsl,imx25-pwm", "fsl,imx27-pwm"; #pwm-cells = <2>; reg = <0x53fa0000 0x4000>; - clocks = <&clks 106>, <&clks 36>; + clocks = <&clks 106>, <&clks 52>; clock-names = "ipg", "per"; interrupts = <36>; }; @@ -371,7 +371,7 @@ compatible = "fsl,imx25-pwm", "fsl,imx27-pwm"; #pwm-cells = <2>; reg = <0x53fa8000 0x4000>; - clocks = <&clks 107>, <&clks 36>; + clocks = <&clks 107>, <&clks 52>; clock-names = "ipg", "per"; interrupts = <41>; }; @@ -412,7 +412,7 @@ pwm4: pwm@53fc8000 { compatible = "fsl,imx25-pwm", "fsl,imx27-pwm"; reg = <0x53fc8000 0x4000>; - clocks = <&clks 108>, <&clks 36>; + clocks = <&clks 108>, <&clks 52>; clock-names = "ipg", "per"; interrupts = <42>; }; @@ -458,7 +458,7 @@ compatible = "fsl,imx25-pwm", "fsl,imx27-pwm"; #pwm-cells = <2>; reg = <0x53fe0000 0x4000>; - clocks = <&clks 105>, <&clks 36>; + clocks = <&clks 105>, <&clks 52>; clock-names = "ipg", "per"; interrupts = <26>; }; diff --git a/arch/arm/boot/dts/s3c6410-mini6410.dts b/arch/arm/boot/dts/s3c6410-mini6410.dts index 57e00f9bce99..a25debb50401 100644 --- a/arch/arm/boot/dts/s3c6410-mini6410.dts +++ b/arch/arm/boot/dts/s3c6410-mini6410.dts @@ -198,10 +198,6 @@ status = "okay"; }; -&pwm { - status = "okay"; -}; - &pinctrl0 { gpio_leds: gpio-leds { samsung,pins = "gpk-4", "gpk-5", "gpk-6", "gpk-7"; diff --git a/arch/arm/boot/dts/s3c64xx.dtsi b/arch/arm/boot/dts/s3c64xx.dtsi index 4e3be4d3493d..4f1eff3420f6 100644 --- a/arch/arm/boot/dts/s3c64xx.dtsi +++ b/arch/arm/boot/dts/s3c64xx.dtsi @@ -168,7 +168,6 @@ clocks = <&clocks PCLK_PWM>; samsung,pwm-outputs = <0>, <1>; #pwm-cells = <3>; - status = "disabled"; }; pinctrl0: pinctrl@7f008000 { diff --git a/arch/arm/boot/dts/sama5d3_can.dtsi b/arch/arm/boot/dts/sama5d3_can.dtsi index a0775851cce5..eaf41451ad0c 100644 --- a/arch/arm/boot/dts/sama5d3_can.dtsi +++ b/arch/arm/boot/dts/sama5d3_can.dtsi @@ -40,7 +40,7 @@ atmel,clk-output-range = <0 66000000>; }; - can1_clk: can0_clk { + can1_clk: can1_clk { #clock-cells = <0>; reg = <41>; atmel,clk-output-range = <0 66000000>; diff --git a/arch/arm/boot/dts/tegra20.dtsi b/arch/arm/boot/dts/tegra20.dtsi index 48d2a7f4d0c0..ce978bc5b6d4 100644 --- a/arch/arm/boot/dts/tegra20.dtsi +++ b/arch/arm/boot/dts/tegra20.dtsi @@ -76,9 +76,9 @@ reset-names = "2d"; }; - gr3d@54140000 { + gr3d@54180000 { compatible = "nvidia,tegra20-gr3d"; - reg = <0x54140000 0x00040000>; + reg = <0x54180000 0x00040000>; clocks = <&tegra_car TEGRA20_CLK_GR3D>; resets = <&tegra_car 24>; reset-names = "3d"; @@ -138,9 +138,9 @@ status = "disabled"; }; - dsi@542c0000 { + dsi@54300000 { compatible = "nvidia,tegra20-dsi"; - reg = <0x542c0000 0x00040000>; + reg = <0x54300000 0x00040000>; clocks = <&tegra_car TEGRA20_CLK_DSI>; resets = <&tegra_car 48>; reset-names = "dsi"; diff --git a/arch/arm/boot/dts/versatile-pb.dts b/arch/arm/boot/dts/versatile-pb.dts index 65f657711323..8d39677b7d4c 100644 --- a/arch/arm/boot/dts/versatile-pb.dts +++ b/arch/arm/boot/dts/versatile-pb.dts @@ -46,5 +46,3 @@ }; }; }; - -#include <testcases.dtsi> diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index ee6982976d66..cf4823bc111d 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -235,6 +235,7 @@ CONFIG_SND_SOC_TEGRA_MAX98090=y CONFIG_USB=y CONFIG_USB_XHCI_HCD=y CONFIG_USB_EHCI_HCD=y +CONFIG_USB_EHCI_EXYNOS=y CONFIG_USB_EHCI_TEGRA=y CONFIG_USB_EHCI_HCD_PLATFORM=y CONFIG_USB_ISP1760_HCD=y diff --git a/arch/arm/crypto/aes_glue.c b/arch/arm/crypto/aes_glue.c index 3003fa1f6fb4..0409b8f89782 100644 --- a/arch/arm/crypto/aes_glue.c +++ b/arch/arm/crypto/aes_glue.c @@ -93,6 +93,6 @@ module_exit(aes_fini); MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm (ASM)"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("aes"); -MODULE_ALIAS("aes-asm"); +MODULE_ALIAS_CRYPTO("aes"); +MODULE_ALIAS_CRYPTO("aes-asm"); MODULE_AUTHOR("David McCullough <ucdevel@gmail.com>"); diff --git a/arch/arm/crypto/aesbs-core.S_shipped b/arch/arm/crypto/aesbs-core.S_shipped index 71e5fc7cfb18..1d1800f71c5b 100644 --- a/arch/arm/crypto/aesbs-core.S_shipped +++ b/arch/arm/crypto/aesbs-core.S_shipped @@ -58,14 +58,18 @@ # define VFP_ABI_FRAME 0 # define BSAES_ASM_EXTENDED_KEY # define XTS_CHAIN_TWEAK -# define __ARM_ARCH__ 7 +# define __ARM_ARCH__ __LINUX_ARM_ARCH__ +# define __ARM_MAX_ARCH__ 7 #endif #ifdef __thumb__ # define adrl adr #endif -#if __ARM_ARCH__>=7 +#if __ARM_MAX_ARCH__>=7 +.arch armv7-a +.fpu neon + .text .syntax unified @ ARMv7-capable assembler is expected to handle this #ifdef __thumb2__ @@ -74,8 +78,6 @@ .code 32 #endif -.fpu neon - .type _bsaes_decrypt8,%function .align 4 _bsaes_decrypt8: @@ -2095,9 +2097,11 @@ bsaes_xts_decrypt: vld1.8 {q8}, [r0] @ initial tweak adr r2, .Lxts_magic +#ifndef XTS_CHAIN_TWEAK tst r9, #0xf @ if not multiple of 16 it ne @ Thumb2 thing, sanity check in ARM subne r9, #0x10 @ subtract another 16 bytes +#endif subs r9, #0x80 blo .Lxts_dec_short diff --git a/arch/arm/crypto/bsaes-armv7.pl b/arch/arm/crypto/bsaes-armv7.pl index be068db960ee..a4d3856e7d24 100644 --- a/arch/arm/crypto/bsaes-armv7.pl +++ b/arch/arm/crypto/bsaes-armv7.pl @@ -701,14 +701,18 @@ $code.=<<___; # define VFP_ABI_FRAME 0 # define BSAES_ASM_EXTENDED_KEY # define XTS_CHAIN_TWEAK -# define __ARM_ARCH__ 7 +# define __ARM_ARCH__ __LINUX_ARM_ARCH__ +# define __ARM_MAX_ARCH__ 7 #endif #ifdef __thumb__ # define adrl adr #endif -#if __ARM_ARCH__>=7 +#if __ARM_MAX_ARCH__>=7 +.arch armv7-a +.fpu neon + .text .syntax unified @ ARMv7-capable assembler is expected to handle this #ifdef __thumb2__ @@ -717,8 +721,6 @@ $code.=<<___; .code 32 #endif -.fpu neon - .type _bsaes_decrypt8,%function .align 4 _bsaes_decrypt8: @@ -2076,9 +2078,11 @@ bsaes_xts_decrypt: vld1.8 {@XMM[8]}, [r0] @ initial tweak adr $magic, .Lxts_magic +#ifndef XTS_CHAIN_TWEAK tst $len, #0xf @ if not multiple of 16 it ne @ Thumb2 thing, sanity check in ARM subne $len, #0x10 @ subtract another 16 bytes +#endif subs $len, #0x80 blo .Lxts_dec_short diff --git a/arch/arm/crypto/sha1_glue.c b/arch/arm/crypto/sha1_glue.c index 76cd976230bc..ace4cd67464c 100644 --- a/arch/arm/crypto/sha1_glue.c +++ b/arch/arm/crypto/sha1_glue.c @@ -175,5 +175,5 @@ module_exit(sha1_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm (ARM)"); -MODULE_ALIAS("sha1"); +MODULE_ALIAS_CRYPTO("sha1"); MODULE_AUTHOR("David McCullough <ucdevel@gmail.com>"); diff --git a/arch/arm/include/asm/hardware/coresight.h b/arch/arm/include/asm/hardware/coresight.h deleted file mode 100644 index ad774f37c47c..000000000000 --- a/arch/arm/include/asm/hardware/coresight.h +++ /dev/null @@ -1,157 +0,0 @@ -/* - * linux/arch/arm/include/asm/hardware/coresight.h - * - * CoreSight components' registers - * - * Copyright (C) 2009 Nokia Corporation. - * Alexander Shishkin - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#ifndef __ASM_HARDWARE_CORESIGHT_H -#define __ASM_HARDWARE_CORESIGHT_H - -#define TRACER_ACCESSED_BIT 0 -#define TRACER_RUNNING_BIT 1 -#define TRACER_CYCLE_ACC_BIT 2 -#define TRACER_ACCESSED BIT(TRACER_ACCESSED_BIT) -#define TRACER_RUNNING BIT(TRACER_RUNNING_BIT) -#define TRACER_CYCLE_ACC BIT(TRACER_CYCLE_ACC_BIT) - -#define TRACER_TIMEOUT 10000 - -#define etm_writel(t, v, x) \ - (writel_relaxed((v), (t)->etm_regs + (x))) -#define etm_readl(t, x) (readl_relaxed((t)->etm_regs + (x))) - -/* CoreSight Management Registers */ -#define CSMR_LOCKACCESS 0xfb0 -#define CSMR_LOCKSTATUS 0xfb4 -#define CSMR_AUTHSTATUS 0xfb8 -#define CSMR_DEVID 0xfc8 -#define CSMR_DEVTYPE 0xfcc -/* CoreSight Component Registers */ -#define CSCR_CLASS 0xff4 - -#define CS_LAR_KEY 0xc5acce55 - -/* ETM control register, "ETM Architecture", 3.3.1 */ -#define ETMR_CTRL 0 -#define ETMCTRL_POWERDOWN 1 -#define ETMCTRL_PROGRAM (1 << 10) -#define ETMCTRL_PORTSEL (1 << 11) -#define ETMCTRL_DO_CONTEXTID (3 << 14) -#define ETMCTRL_PORTMASK1 (7 << 4) -#define ETMCTRL_PORTMASK2 (1 << 21) -#define ETMCTRL_PORTMASK (ETMCTRL_PORTMASK1 | ETMCTRL_PORTMASK2) -#define ETMCTRL_PORTSIZE(x) ((((x) & 7) << 4) | (!!((x) & 8)) << 21) -#define ETMCTRL_DO_CPRT (1 << 1) -#define ETMCTRL_DATAMASK (3 << 2) -#define ETMCTRL_DATA_DO_DATA (1 << 2) -#define ETMCTRL_DATA_DO_ADDR (1 << 3) -#define ETMCTRL_DATA_DO_BOTH (ETMCTRL_DATA_DO_DATA | ETMCTRL_DATA_DO_ADDR) -#define ETMCTRL_BRANCH_OUTPUT (1 << 8) -#define ETMCTRL_CYCLEACCURATE (1 << 12) - -/* ETM configuration code register */ -#define ETMR_CONFCODE (0x04) - -/* ETM trace start/stop resource control register */ -#define ETMR_TRACESSCTRL (0x18) - -/* ETM trigger event register */ -#define ETMR_TRIGEVT (0x08) - -/* address access type register bits, "ETM architecture", - * table 3-27 */ -/* - access type */ -#define ETMAAT_IFETCH 0 -#define ETMAAT_IEXEC 1 -#define ETMAAT_IEXECPASS 2 -#define ETMAAT_IEXECFAIL 3 -#define ETMAAT_DLOADSTORE 4 -#define ETMAAT_DLOAD 5 -#define ETMAAT_DSTORE 6 -/* - comparison access size */ -#define ETMAAT_JAVA (0 << 3) -#define ETMAAT_THUMB (1 << 3) -#define ETMAAT_ARM (3 << 3) -/* - data value comparison control */ -#define ETMAAT_NOVALCMP (0 << 5) -#define ETMAAT_VALMATCH (1 << 5) -#define ETMAAT_VALNOMATCH (3 << 5) -/* - exact match */ -#define ETMAAT_EXACTMATCH (1 << 7) -/* - context id comparator control */ -#define ETMAAT_IGNCONTEXTID (0 << 8) -#define ETMAAT_VALUE1 (1 << 8) -#define ETMAAT_VALUE2 (2 << 8) -#define ETMAAT_VALUE3 (3 << 8) -/* - security level control */ -#define ETMAAT_IGNSECURITY (0 << 10) -#define ETMAAT_NSONLY (1 << 10) -#define ETMAAT_SONLY (2 << 10) - -#define ETMR_COMP_VAL(x) (0x40 + (x) * 4) -#define ETMR_COMP_ACC_TYPE(x) (0x80 + (x) * 4) - -/* ETM status register, "ETM Architecture", 3.3.2 */ -#define ETMR_STATUS (0x10) -#define ETMST_OVERFLOW BIT(0) -#define ETMST_PROGBIT BIT(1) -#define ETMST_STARTSTOP BIT(2) -#define ETMST_TRIGGER BIT(3) - -#define etm_progbit(t) (etm_readl((t), ETMR_STATUS) & ETMST_PROGBIT) -#define etm_started(t) (etm_readl((t), ETMR_STATUS) & ETMST_STARTSTOP) -#define etm_triggered(t) (etm_readl((t), ETMR_STATUS) & ETMST_TRIGGER) - -#define ETMR_TRACEENCTRL2 0x1c -#define ETMR_TRACEENCTRL 0x24 -#define ETMTE_INCLEXCL BIT(24) -#define ETMR_TRACEENEVT 0x20 -#define ETMCTRL_OPTS (ETMCTRL_DO_CPRT | \ - ETMCTRL_DATA_DO_ADDR | \ - ETMCTRL_BRANCH_OUTPUT | \ - ETMCTRL_DO_CONTEXTID) - -/* ETM management registers, "ETM Architecture", 3.5.24 */ -#define ETMMR_OSLAR 0x300 -#define ETMMR_OSLSR 0x304 -#define ETMMR_OSSRR 0x308 -#define ETMMR_PDSR 0x314 - -/* ETB registers, "CoreSight Components TRM", 9.3 */ -#define ETBR_DEPTH 0x04 -#define ETBR_STATUS 0x0c -#define ETBR_READMEM 0x10 -#define ETBR_READADDR 0x14 -#define ETBR_WRITEADDR 0x18 -#define ETBR_TRIGGERCOUNT 0x1c -#define ETBR_CTRL 0x20 -#define ETBR_FORMATTERCTRL 0x304 -#define ETBFF_ENFTC 1 -#define ETBFF_ENFCONT BIT(1) -#define ETBFF_FONFLIN BIT(4) -#define ETBFF_MANUAL_FLUSH BIT(6) -#define ETBFF_TRIGIN BIT(8) -#define ETBFF_TRIGEVT BIT(9) -#define ETBFF_TRIGFL BIT(10) - -#define etb_writel(t, v, x) \ - (writel_relaxed((v), (t)->etb_regs + (x))) -#define etb_readl(t, x) (readl_relaxed((t)->etb_regs + (x))) - -#define etm_lock(t) do { etm_writel((t), 0, CSMR_LOCKACCESS); } while (0) -#define etm_unlock(t) \ - do { etm_writel((t), CS_LAR_KEY, CSMR_LOCKACCESS); } while (0) - -#define etb_lock(t) do { etb_writel((t), 0, CSMR_LOCKACCESS); } while (0) -#define etb_unlock(t) \ - do { etb_writel((t), CS_LAR_KEY, CSMR_LOCKACCESS); } while (0) - -#endif /* __ASM_HARDWARE_CORESIGHT_H */ - diff --git a/arch/arm/include/asm/hardware/cp14.h b/arch/arm/include/asm/hardware/cp14.h new file mode 100644 index 000000000000..61576dc58ede --- /dev/null +++ b/arch/arm/include/asm/hardware/cp14.h @@ -0,0 +1,542 @@ +/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __ASM_HARDWARE_CP14_H +#define __ASM_HARDWARE_CP14_H + +#include <linux/types.h> + +/* Accessors for CP14 registers */ +#define dbg_read(reg) RCP14_##reg() +#define dbg_write(val, reg) WCP14_##reg(val) +#define etm_read(reg) RCP14_##reg() +#define etm_write(val, reg) WCP14_##reg(val) + +/* MRC14 and MCR14 */ +#define MRC14(op1, crn, crm, op2) \ +({ \ +u32 val; \ +asm volatile("mrc p14, "#op1", %0, "#crn", "#crm", "#op2 : "=r" (val)); \ +val; \ +}) + +#define MCR14(val, op1, crn, crm, op2) \ +({ \ +asm volatile("mcr p14, "#op1", %0, "#crn", "#crm", "#op2 : : "r" (val));\ +}) + +/* + * Debug Registers + * + * Available only in DBGv7 + * DBGECR, DBGDSCCR, DBGDSMCR, DBGDRCR + * + * Available only in DBGv7.1 + * DBGBXVRm, DBGOSDLR, DBGDEVID2, DBGDEVID1 + * + * Read only + * DBGDIDR, DBGDSCRint, DBGDTRRXint, DBGDRAR, DBGOSLSR, DBGOSSRR, DBGPRSR, + * DBGPRSR, DBGDSAR, DBGAUTHSTATUS, DBGDEVID2, DBGDEVID1, DBGDEVID + * + * Write only + * DBGDTRTXint, DBGOSLAR + */ +#define RCP14_DBGDIDR() MRC14(0, c0, c0, 0) +#define RCP14_DBGDSCRint() MRC14(0, c0, c1, 0) +#define RCP14_DBGDTRRXint() MRC14(0, c0, c5, 0) +#define RCP14_DBGWFAR() MRC14(0, c0, c6, 0) +#define RCP14_DBGVCR() MRC14(0, c0, c7, 0) +#define RCP14_DBGECR() MRC14(0, c0, c9, 0) +#define RCP14_DBGDSCCR() MRC14(0, c0, c10, 0) +#define RCP14_DBGDSMCR() MRC14(0, c0, c11, 0) +#define RCP14_DBGDTRRXext() MRC14(0, c0, c0, 2) +#define RCP14_DBGDSCRext() MRC14(0, c0, c2, 2) +#define RCP14_DBGDTRTXext() MRC14(0, c0, c3, 2) +#define RCP14_DBGDRCR() MRC14(0, c0, c4, 2) +#define RCP14_DBGBVR0() MRC14(0, c0, c0, 4) +#define RCP14_DBGBVR1() MRC14(0, c0, c1, 4) +#define RCP14_DBGBVR2() MRC14(0, c0, c2, 4) +#define RCP14_DBGBVR3() MRC14(0, c0, c3, 4) +#define RCP14_DBGBVR4() MRC14(0, c0, c4, 4) +#define RCP14_DBGBVR5() MRC14(0, c0, c5, 4) +#define RCP14_DBGBVR6() MRC14(0, c0, c6, 4) +#define RCP14_DBGBVR7() MRC14(0, c0, c7, 4) +#define RCP14_DBGBVR8() MRC14(0, c0, c8, 4) +#define RCP14_DBGBVR9() MRC14(0, c0, c9, 4) +#define RCP14_DBGBVR10() MRC14(0, c0, c10, 4) +#define RCP14_DBGBVR11() MRC14(0, c0, c11, 4) +#define RCP14_DBGBVR12() MRC14(0, c0, c12, 4) +#define RCP14_DBGBVR13() MRC14(0, c0, c13, 4) +#define RCP14_DBGBVR14() MRC14(0, c0, c14, 4) +#define RCP14_DBGBVR15() MRC14(0, c0, c15, 4) +#define RCP14_DBGBCR0() MRC14(0, c0, c0, 5) +#define RCP14_DBGBCR1() MRC14(0, c0, c1, 5) +#define RCP14_DBGBCR2() MRC14(0, c0, c2, 5) +#define RCP14_DBGBCR3() MRC14(0, c0, c3, 5) +#define RCP14_DBGBCR4() MRC14(0, c0, c4, 5) +#define RCP14_DBGBCR5() MRC14(0, c0, c5, 5) +#define RCP14_DBGBCR6() MRC14(0, c0, c6, 5) +#define RCP14_DBGBCR7() MRC14(0, c0, c7, 5) +#define RCP14_DBGBCR8() MRC14(0, c0, c8, 5) +#define RCP14_DBGBCR9() MRC14(0, c0, c9, 5) +#define RCP14_DBGBCR10() MRC14(0, c0, c10, 5) +#define RCP14_DBGBCR11() MRC14(0, c0, c11, 5) +#define RCP14_DBGBCR12() MRC14(0, c0, c12, 5) +#define RCP14_DBGBCR13() MRC14(0, c0, c13, 5) +#define RCP14_DBGBCR14() MRC14(0, c0, c14, 5) +#define RCP14_DBGBCR15() MRC14(0, c0, c15, 5) +#define RCP14_DBGWVR0() MRC14(0, c0, c0, 6) +#define RCP14_DBGWVR1() MRC14(0, c0, c1, 6) +#define RCP14_DBGWVR2() MRC14(0, c0, c2, 6) +#define RCP14_DBGWVR3() MRC14(0, c0, c3, 6) +#define RCP14_DBGWVR4() MRC14(0, c0, c4, 6) +#define RCP14_DBGWVR5() MRC14(0, c0, c5, 6) +#define RCP14_DBGWVR6() MRC14(0, c0, c6, 6) +#define RCP14_DBGWVR7() MRC14(0, c0, c7, 6) +#define RCP14_DBGWVR8() MRC14(0, c0, c8, 6) +#define RCP14_DBGWVR9() MRC14(0, c0, c9, 6) +#define RCP14_DBGWVR10() MRC14(0, c0, c10, 6) +#define RCP14_DBGWVR11() MRC14(0, c0, c11, 6) +#define RCP14_DBGWVR12() MRC14(0, c0, c12, 6) +#define RCP14_DBGWVR13() MRC14(0, c0, c13, 6) +#define RCP14_DBGWVR14() MRC14(0, c0, c14, 6) +#define RCP14_DBGWVR15() MRC14(0, c0, c15, 6) +#define RCP14_DBGWCR0() MRC14(0, c0, c0, 7) +#define RCP14_DBGWCR1() MRC14(0, c0, c1, 7) +#define RCP14_DBGWCR2() MRC14(0, c0, c2, 7) +#define RCP14_DBGWCR3() MRC14(0, c0, c3, 7) +#define RCP14_DBGWCR4() MRC14(0, c0, c4, 7) +#define RCP14_DBGWCR5() MRC14(0, c0, c5, 7) +#define RCP14_DBGWCR6() MRC14(0, c0, c6, 7) +#define RCP14_DBGWCR7() MRC14(0, c0, c7, 7) +#define RCP14_DBGWCR8() MRC14(0, c0, c8, 7) +#define RCP14_DBGWCR9() MRC14(0, c0, c9, 7) +#define RCP14_DBGWCR10() MRC14(0, c0, c10, 7) +#define RCP14_DBGWCR11() MRC14(0, c0, c11, 7) +#define RCP14_DBGWCR12() MRC14(0, c0, c12, 7) +#define RCP14_DBGWCR13() MRC14(0, c0, c13, 7) +#define RCP14_DBGWCR14() MRC14(0, c0, c14, 7) +#define RCP14_DBGWCR15() MRC14(0, c0, c15, 7) +#define RCP14_DBGDRAR() MRC14(0, c1, c0, 0) +#define RCP14_DBGBXVR0() MRC14(0, c1, c0, 1) +#define RCP14_DBGBXVR1() MRC14(0, c1, c1, 1) +#define RCP14_DBGBXVR2() MRC14(0, c1, c2, 1) +#define RCP14_DBGBXVR3() MRC14(0, c1, c3, 1) +#define RCP14_DBGBXVR4() MRC14(0, c1, c4, 1) +#define RCP14_DBGBXVR5() MRC14(0, c1, c5, 1) +#define RCP14_DBGBXVR6() MRC14(0, c1, c6, 1) +#define RCP14_DBGBXVR7() MRC14(0, c1, c7, 1) +#define RCP14_DBGBXVR8() MRC14(0, c1, c8, 1) +#define RCP14_DBGBXVR9() MRC14(0, c1, c9, 1) +#define RCP14_DBGBXVR10() MRC14(0, c1, c10, 1) +#define RCP14_DBGBXVR11() MRC14(0, c1, c11, 1) +#define RCP14_DBGBXVR12() MRC14(0, c1, c12, 1) +#define RCP14_DBGBXVR13() MRC14(0, c1, c13, 1) +#define RCP14_DBGBXVR14() MRC14(0, c1, c14, 1) +#define RCP14_DBGBXVR15() MRC14(0, c1, c15, 1) +#define RCP14_DBGOSLSR() MRC14(0, c1, c1, 4) +#define RCP14_DBGOSSRR() MRC14(0, c1, c2, 4) +#define RCP14_DBGOSDLR() MRC14(0, c1, c3, 4) +#define RCP14_DBGPRCR() MRC14(0, c1, c4, 4) +#define RCP14_DBGPRSR() MRC14(0, c1, c5, 4) +#define RCP14_DBGDSAR() MRC14(0, c2, c0, 0) +#define RCP14_DBGITCTRL() MRC14(0, c7, c0, 4) +#define RCP14_DBGCLAIMSET() MRC14(0, c7, c8, 6) +#define RCP14_DBGCLAIMCLR() MRC14(0, c7, c9, 6) +#define RCP14_DBGAUTHSTATUS() MRC14(0, c7, c14, 6) +#define RCP14_DBGDEVID2() MRC14(0, c7, c0, 7) +#define RCP14_DBGDEVID1() MRC14(0, c7, c1, 7) +#define RCP14_DBGDEVID() MRC14(0, c7, c2, 7) + +#define WCP14_DBGDTRTXint(val) MCR14(val, 0, c0, c5, 0) +#define WCP14_DBGWFAR(val) MCR14(val, 0, c0, c6, 0) +#define WCP14_DBGVCR(val) MCR14(val, 0, c0, c7, 0) +#define WCP14_DBGECR(val) MCR14(val, 0, c0, c9, 0) +#define WCP14_DBGDSCCR(val) MCR14(val, 0, c0, c10, 0) +#define WCP14_DBGDSMCR(val) MCR14(val, 0, c0, c11, 0) +#define WCP14_DBGDTRRXext(val) MCR14(val, 0, c0, c0, 2) +#define WCP14_DBGDSCRext(val) MCR14(val, 0, c0, c2, 2) +#define WCP14_DBGDTRTXext(val) MCR14(val, 0, c0, c3, 2) +#define WCP14_DBGDRCR(val) MCR14(val, 0, c0, c4, 2) +#define WCP14_DBGBVR0(val) MCR14(val, 0, c0, c0, 4) +#define WCP14_DBGBVR1(val) MCR14(val, 0, c0, c1, 4) +#define WCP14_DBGBVR2(val) MCR14(val, 0, c0, c2, 4) +#define WCP14_DBGBVR3(val) MCR14(val, 0, c0, c3, 4) +#define WCP14_DBGBVR4(val) MCR14(val, 0, c0, c4, 4) +#define WCP14_DBGBVR5(val) MCR14(val, 0, c0, c5, 4) +#define WCP14_DBGBVR6(val) MCR14(val, 0, c0, c6, 4) +#define WCP14_DBGBVR7(val) MCR14(val, 0, c0, c7, 4) +#define WCP14_DBGBVR8(val) MCR14(val, 0, c0, c8, 4) +#define WCP14_DBGBVR9(val) MCR14(val, 0, c0, c9, 4) +#define WCP14_DBGBVR10(val) MCR14(val, 0, c0, c10, 4) +#define WCP14_DBGBVR11(val) MCR14(val, 0, c0, c11, 4) +#define WCP14_DBGBVR12(val) MCR14(val, 0, c0, c12, 4) +#define WCP14_DBGBVR13(val) MCR14(val, 0, c0, c13, 4) +#define WCP14_DBGBVR14(val) MCR14(val, 0, c0, c14, 4) +#define WCP14_DBGBVR15(val) MCR14(val, 0, c0, c15, 4) +#define WCP14_DBGBCR0(val) MCR14(val, 0, c0, c0, 5) +#define WCP14_DBGBCR1(val) MCR14(val, 0, c0, c1, 5) +#define WCP14_DBGBCR2(val) MCR14(val, 0, c0, c2, 5) +#define WCP14_DBGBCR3(val) MCR14(val, 0, c0, c3, 5) +#define WCP14_DBGBCR4(val) MCR14(val, 0, c0, c4, 5) +#define WCP14_DBGBCR5(val) MCR14(val, 0, c0, c5, 5) +#define WCP14_DBGBCR6(val) MCR14(val, 0, c0, c6, 5) +#define WCP14_DBGBCR7(val) MCR14(val, 0, c0, c7, 5) +#define WCP14_DBGBCR8(val) MCR14(val, 0, c0, c8, 5) +#define WCP14_DBGBCR9(val) MCR14(val, 0, c0, c9, 5) +#define WCP14_DBGBCR10(val) MCR14(val, 0, c0, c10, 5) +#define WCP14_DBGBCR11(val) MCR14(val, 0, c0, c11, 5) +#define WCP14_DBGBCR12(val) MCR14(val, 0, c0, c12, 5) +#define WCP14_DBGBCR13(val) MCR14(val, 0, c0, c13, 5) +#define WCP14_DBGBCR14(val) MCR14(val, 0, c0, c14, 5) +#define WCP14_DBGBCR15(val) MCR14(val, 0, c0, c15, 5) +#define WCP14_DBGWVR0(val) MCR14(val, 0, c0, c0, 6) +#define WCP14_DBGWVR1(val) MCR14(val, 0, c0, c1, 6) +#define WCP14_DBGWVR2(val) MCR14(val, 0, c0, c2, 6) +#define WCP14_DBGWVR3(val) MCR14(val, 0, c0, c3, 6) +#define WCP14_DBGWVR4(val) MCR14(val, 0, c0, c4, 6) +#define WCP14_DBGWVR5(val) MCR14(val, 0, c0, c5, 6) +#define WCP14_DBGWVR6(val) MCR14(val, 0, c0, c6, 6) +#define WCP14_DBGWVR7(val) MCR14(val, 0, c0, c7, 6) +#define WCP14_DBGWVR8(val) MCR14(val, 0, c0, c8, 6) +#define WCP14_DBGWVR9(val) MCR14(val, 0, c0, c9, 6) +#define WCP14_DBGWVR10(val) MCR14(val, 0, c0, c10, 6) +#define WCP14_DBGWVR11(val) MCR14(val, 0, c0, c11, 6) +#define WCP14_DBGWVR12(val) MCR14(val, 0, c0, c12, 6) +#define WCP14_DBGWVR13(val) MCR14(val, 0, c0, c13, 6) +#define WCP14_DBGWVR14(val) MCR14(val, 0, c0, c14, 6) +#define WCP14_DBGWVR15(val) MCR14(val, 0, c0, c15, 6) +#define WCP14_DBGWCR0(val) MCR14(val, 0, c0, c0, 7) +#define WCP14_DBGWCR1(val) MCR14(val, 0, c0, c1, 7) +#define WCP14_DBGWCR2(val) MCR14(val, 0, c0, c2, 7) +#define WCP14_DBGWCR3(val) MCR14(val, 0, c0, c3, 7) +#define WCP14_DBGWCR4(val) MCR14(val, 0, c0, c4, 7) +#define WCP14_DBGWCR5(val) MCR14(val, 0, c0, c5, 7) +#define WCP14_DBGWCR6(val) MCR14(val, 0, c0, c6, 7) +#define WCP14_DBGWCR7(val) MCR14(val, 0, c0, c7, 7) +#define WCP14_DBGWCR8(val) MCR14(val, 0, c0, c8, 7) +#define WCP14_DBGWCR9(val) MCR14(val, 0, c0, c9, 7) +#define WCP14_DBGWCR10(val) MCR14(val, 0, c0, c10, 7) +#define WCP14_DBGWCR11(val) MCR14(val, 0, c0, c11, 7) +#define WCP14_DBGWCR12(val) MCR14(val, 0, c0, c12, 7) +#define WCP14_DBGWCR13(val) MCR14(val, 0, c0, c13, 7) +#define WCP14_DBGWCR14(val) MCR14(val, 0, c0, c14, 7) +#define WCP14_DBGWCR15(val) MCR14(val, 0, c0, c15, 7) +#define WCP14_DBGBXVR0(val) MCR14(val, 0, c1, c0, 1) +#define WCP14_DBGBXVR1(val) MCR14(val, 0, c1, c1, 1) +#define WCP14_DBGBXVR2(val) MCR14(val, 0, c1, c2, 1) +#define WCP14_DBGBXVR3(val) MCR14(val, 0, c1, c3, 1) +#define WCP14_DBGBXVR4(val) MCR14(val, 0, c1, c4, 1) +#define WCP14_DBGBXVR5(val) MCR14(val, 0, c1, c5, 1) +#define WCP14_DBGBXVR6(val) MCR14(val, 0, c1, c6, 1) +#define WCP14_DBGBXVR7(val) MCR14(val, 0, c1, c7, 1) +#define WCP14_DBGBXVR8(val) MCR14(val, 0, c1, c8, 1) +#define WCP14_DBGBXVR9(val) MCR14(val, 0, c1, c9, 1) +#define WCP14_DBGBXVR10(val) MCR14(val, 0, c1, c10, 1) +#define WCP14_DBGBXVR11(val) MCR14(val, 0, c1, c11, 1) +#define WCP14_DBGBXVR12(val) MCR14(val, 0, c1, c12, 1) +#define WCP14_DBGBXVR13(val) MCR14(val, 0, c1, c13, 1) +#define WCP14_DBGBXVR14(val) MCR14(val, 0, c1, c14, 1) +#define WCP14_DBGBXVR15(val) MCR14(val, 0, c1, c15, 1) +#define WCP14_DBGOSLAR(val) MCR14(val, 0, c1, c0, 4) +#define WCP14_DBGOSSRR(val) MCR14(val, 0, c1, c2, 4) +#define WCP14_DBGOSDLR(val) MCR14(val, 0, c1, c3, 4) +#define WCP14_DBGPRCR(val) MCR14(val, 0, c1, c4, 4) +#define WCP14_DBGITCTRL(val) MCR14(val, 0, c7, c0, 4) +#define WCP14_DBGCLAIMSET(val) MCR14(val, 0, c7, c8, 6) +#define WCP14_DBGCLAIMCLR(val) MCR14(val, 0, c7, c9, 6) + +/* + * ETM Registers + * + * Available only in ETMv3.3, 3.4, 3.5 + * ETMASICCR, ETMTECR2, ETMFFRR, ETMVDEVR, ETMVDCR1, ETMVDCR2, ETMVDCR3, + * ETMDCVRn, ETMDCMRn + * + * Available only in ETMv3.5 as read only + * ETMIDR2 + * + * Available only in ETMv3.5, PFTv1.0, 1.1 + * ETMTSEVR, ETMVMIDCVR, ETMPDCR + * + * Read only + * ETMCCR, ETMSCR, ETMIDR, ETMCCER, ETMOSLSR + * ETMLSR, ETMAUTHSTATUS, ETMDEVID, ETMDEVTYPE, ETMPIDR4, ETMPIDR5, ETMPIDR6, + * ETMPIDR7, ETMPIDR0, ETMPIDR1, ETMPIDR2, ETMPIDR2, ETMPIDR3, ETMCIDR0, + * ETMCIDR1, ETMCIDR2, ETMCIDR3 + * + * Write only + * ETMOSLAR, ETMLAR + * Note: ETMCCER[11] controls WO nature of certain regs. Refer ETM arch spec. + */ +#define RCP14_ETMCR() MRC14(1, c0, c0, 0) +#define RCP14_ETMCCR() MRC14(1, c0, c1, 0) +#define RCP14_ETMTRIGGER() MRC14(1, c0, c2, 0) +#define RCP14_ETMASICCR() MRC14(1, c0, c3, 0) +#define RCP14_ETMSR() MRC14(1, c0, c4, 0) +#define RCP14_ETMSCR() MRC14(1, c0, c5, 0) +#define RCP14_ETMTSSCR() MRC14(1, c0, c6, 0) +#define RCP14_ETMTECR2() MRC14(1, c0, c7, 0) +#define RCP14_ETMTEEVR() MRC14(1, c0, c8, 0) +#define RCP14_ETMTECR1() MRC14(1, c0, c9, 0) +#define RCP14_ETMFFRR() MRC14(1, c0, c10, 0) +#define RCP14_ETMFFLR() MRC14(1, c0, c11, 0) +#define RCP14_ETMVDEVR() MRC14(1, c0, c12, 0) +#define RCP14_ETMVDCR1() MRC14(1, c0, c13, 0) +#define RCP14_ETMVDCR2() MRC14(1, c0, c14, 0) +#define RCP14_ETMVDCR3() MRC14(1, c0, c15, 0) +#define RCP14_ETMACVR0() MRC14(1, c0, c0, 1) +#define RCP14_ETMACVR1() MRC14(1, c0, c1, 1) +#define RCP14_ETMACVR2() MRC14(1, c0, c2, 1) +#define RCP14_ETMACVR3() MRC14(1, c0, c3, 1) +#define RCP14_ETMACVR4() MRC14(1, c0, c4, 1) +#define RCP14_ETMACVR5() MRC14(1, c0, c5, 1) +#define RCP14_ETMACVR6() MRC14(1, c0, c6, 1) +#define RCP14_ETMACVR7() MRC14(1, c0, c7, 1) +#define RCP14_ETMACVR8() MRC14(1, c0, c8, 1) +#define RCP14_ETMACVR9() MRC14(1, c0, c9, 1) +#define RCP14_ETMACVR10() MRC14(1, c0, c10, 1) +#define RCP14_ETMACVR11() MRC14(1, c0, c11, 1) +#define RCP14_ETMACVR12() MRC14(1, c0, c12, 1) +#define RCP14_ETMACVR13() MRC14(1, c0, c13, 1) +#define RCP14_ETMACVR14() MRC14(1, c0, c14, 1) +#define RCP14_ETMACVR15() MRC14(1, c0, c15, 1) +#define RCP14_ETMACTR0() MRC14(1, c0, c0, 2) +#define RCP14_ETMACTR1() MRC14(1, c0, c1, 2) +#define RCP14_ETMACTR2() MRC14(1, c0, c2, 2) +#define RCP14_ETMACTR3() MRC14(1, c0, c3, 2) +#define RCP14_ETMACTR4() MRC14(1, c0, c4, 2) +#define RCP14_ETMACTR5() MRC14(1, c0, c5, 2) +#define RCP14_ETMACTR6() MRC14(1, c0, c6, 2) +#define RCP14_ETMACTR7() MRC14(1, c0, c7, 2) +#define RCP14_ETMACTR8() MRC14(1, c0, c8, 2) +#define RCP14_ETMACTR9() MRC14(1, c0, c9, 2) +#define RCP14_ETMACTR10() MRC14(1, c0, c10, 2) +#define RCP14_ETMACTR11() MRC14(1, c0, c11, 2) +#define RCP14_ETMACTR12() MRC14(1, c0, c12, 2) +#define RCP14_ETMACTR13() MRC14(1, c0, c13, 2) +#define RCP14_ETMACTR14() MRC14(1, c0, c14, 2) +#define RCP14_ETMACTR15() MRC14(1, c0, c15, 2) +#define RCP14_ETMDCVR0() MRC14(1, c0, c0, 3) +#define RCP14_ETMDCVR2() MRC14(1, c0, c2, 3) +#define RCP14_ETMDCVR4() MRC14(1, c0, c4, 3) +#define RCP14_ETMDCVR6() MRC14(1, c0, c6, 3) +#define RCP14_ETMDCVR8() MRC14(1, c0, c8, 3) +#define RCP14_ETMDCVR10() MRC14(1, c0, c10, 3) +#define RCP14_ETMDCVR12() MRC14(1, c0, c12, 3) +#define RCP14_ETMDCVR14() MRC14(1, c0, c14, 3) +#define RCP14_ETMDCMR0() MRC14(1, c0, c0, 4) +#define RCP14_ETMDCMR2() MRC14(1, c0, c2, 4) +#define RCP14_ETMDCMR4() MRC14(1, c0, c4, 4) +#define RCP14_ETMDCMR6() MRC14(1, c0, c6, 4) +#define RCP14_ETMDCMR8() MRC14(1, c0, c8, 4) +#define RCP14_ETMDCMR10() MRC14(1, c0, c10, 4) +#define RCP14_ETMDCMR12() MRC14(1, c0, c12, 4) +#define RCP14_ETMDCMR14() MRC14(1, c0, c14, 4) +#define RCP14_ETMCNTRLDVR0() MRC14(1, c0, c0, 5) +#define RCP14_ETMCNTRLDVR1() MRC14(1, c0, c1, 5) +#define RCP14_ETMCNTRLDVR2() MRC14(1, c0, c2, 5) +#define RCP14_ETMCNTRLDVR3() MRC14(1, c0, c3, 5) +#define RCP14_ETMCNTENR0() MRC14(1, c0, c4, 5) +#define RCP14_ETMCNTENR1() MRC14(1, c0, c5, 5) +#define RCP14_ETMCNTENR2() MRC14(1, c0, c6, 5) +#define RCP14_ETMCNTENR3() MRC14(1, c0, c7, 5) +#define RCP14_ETMCNTRLDEVR0() MRC14(1, c0, c8, 5) +#define RCP14_ETMCNTRLDEVR1() MRC14(1, c0, c9, 5) +#define RCP14_ETMCNTRLDEVR2() MRC14(1, c0, c10, 5) +#define RCP14_ETMCNTRLDEVR3() MRC14(1, c0, c11, 5) +#define RCP14_ETMCNTVR0() MRC14(1, c0, c12, 5) +#define RCP14_ETMCNTVR1() MRC14(1, c0, c13, 5) +#define RCP14_ETMCNTVR2() MRC14(1, c0, c14, 5) +#define RCP14_ETMCNTVR3() MRC14(1, c0, c15, 5) +#define RCP14_ETMSQ12EVR() MRC14(1, c0, c0, 6) +#define RCP14_ETMSQ21EVR() MRC14(1, c0, c1, 6) +#define RCP14_ETMSQ23EVR() MRC14(1, c0, c2, 6) +#define RCP14_ETMSQ31EVR() MRC14(1, c0, c3, 6) +#define RCP14_ETMSQ32EVR() MRC14(1, c0, c4, 6) +#define RCP14_ETMSQ13EVR() MRC14(1, c0, c5, 6) +#define RCP14_ETMSQR() MRC14(1, c0, c7, 6) +#define RCP14_ETMEXTOUTEVR0() MRC14(1, c0, c8, 6) +#define RCP14_ETMEXTOUTEVR1() MRC14(1, c0, c9, 6) +#define RCP14_ETMEXTOUTEVR2() MRC14(1, c0, c10, 6) +#define RCP14_ETMEXTOUTEVR3() MRC14(1, c0, c11, 6) +#define RCP14_ETMCIDCVR0() MRC14(1, c0, c12, 6) +#define RCP14_ETMCIDCVR1() MRC14(1, c0, c13, 6) +#define RCP14_ETMCIDCVR2() MRC14(1, c0, c14, 6) +#define RCP14_ETMCIDCMR() MRC14(1, c0, c15, 6) +#define RCP14_ETMIMPSPEC0() MRC14(1, c0, c0, 7) +#define RCP14_ETMIMPSPEC1() MRC14(1, c0, c1, 7) +#define RCP14_ETMIMPSPEC2() MRC14(1, c0, c2, 7) +#define RCP14_ETMIMPSPEC3() MRC14(1, c0, c3, 7) +#define RCP14_ETMIMPSPEC4() MRC14(1, c0, c4, 7) +#define RCP14_ETMIMPSPEC5() MRC14(1, c0, c5, 7) +#define RCP14_ETMIMPSPEC6() MRC14(1, c0, c6, 7) +#define RCP14_ETMIMPSPEC7() MRC14(1, c0, c7, 7) +#define RCP14_ETMSYNCFR() MRC14(1, c0, c8, 7) +#define RCP14_ETMIDR() MRC14(1, c0, c9, 7) +#define RCP14_ETMCCER() MRC14(1, c0, c10, 7) +#define RCP14_ETMEXTINSELR() MRC14(1, c0, c11, 7) +#define RCP14_ETMTESSEICR() MRC14(1, c0, c12, 7) +#define RCP14_ETMEIBCR() MRC14(1, c0, c13, 7) +#define RCP14_ETMTSEVR() MRC14(1, c0, c14, 7) +#define RCP14_ETMAUXCR() MRC14(1, c0, c15, 7) +#define RCP14_ETMTRACEIDR() MRC14(1, c1, c0, 0) +#define RCP14_ETMIDR2() MRC14(1, c1, c2, 0) +#define RCP14_ETMVMIDCVR() MRC14(1, c1, c0, 1) +#define RCP14_ETMOSLSR() MRC14(1, c1, c1, 4) +/* Not available in PFTv1.1 */ +#define RCP14_ETMOSSRR() MRC14(1, c1, c2, 4) +#define RCP14_ETMPDCR() MRC14(1, c1, c4, 4) +#define RCP14_ETMPDSR() MRC14(1, c1, c5, 4) +#define RCP14_ETMITCTRL() MRC14(1, c7, c0, 4) +#define RCP14_ETMCLAIMSET() MRC14(1, c7, c8, 6) +#define RCP14_ETMCLAIMCLR() MRC14(1, c7, c9, 6) +#define RCP14_ETMLSR() MRC14(1, c7, c13, 6) +#define RCP14_ETMAUTHSTATUS() MRC14(1, c7, c14, 6) +#define RCP14_ETMDEVID() MRC14(1, c7, c2, 7) +#define RCP14_ETMDEVTYPE() MRC14(1, c7, c3, 7) +#define RCP14_ETMPIDR4() MRC14(1, c7, c4, 7) +#define RCP14_ETMPIDR5() MRC14(1, c7, c5, 7) +#define RCP14_ETMPIDR6() MRC14(1, c7, c6, 7) +#define RCP14_ETMPIDR7() MRC14(1, c7, c7, 7) +#define RCP14_ETMPIDR0() MRC14(1, c7, c8, 7) +#define RCP14_ETMPIDR1() MRC14(1, c7, c9, 7) +#define RCP14_ETMPIDR2() MRC14(1, c7, c10, 7) +#define RCP14_ETMPIDR3() MRC14(1, c7, c11, 7) +#define RCP14_ETMCIDR0() MRC14(1, c7, c12, 7) +#define RCP14_ETMCIDR1() MRC14(1, c7, c13, 7) +#define RCP14_ETMCIDR2() MRC14(1, c7, c14, 7) +#define RCP14_ETMCIDR3() MRC14(1, c7, c15, 7) + +#define WCP14_ETMCR(val) MCR14(val, 1, c0, c0, 0) +#define WCP14_ETMTRIGGER(val) MCR14(val, 1, c0, c2, 0) +#define WCP14_ETMASICCR(val) MCR14(val, 1, c0, c3, 0) +#define WCP14_ETMSR(val) MCR14(val, 1, c0, c4, 0) +#define WCP14_ETMTSSCR(val) MCR14(val, 1, c0, c6, 0) +#define WCP14_ETMTECR2(val) MCR14(val, 1, c0, c7, 0) +#define WCP14_ETMTEEVR(val) MCR14(val, 1, c0, c8, 0) +#define WCP14_ETMTECR1(val) MCR14(val, 1, c0, c9, 0) +#define WCP14_ETMFFRR(val) MCR14(val, 1, c0, c10, 0) +#define WCP14_ETMFFLR(val) MCR14(val, 1, c0, c11, 0) +#define WCP14_ETMVDEVR(val) MCR14(val, 1, c0, c12, 0) +#define WCP14_ETMVDCR1(val) MCR14(val, 1, c0, c13, 0) +#define WCP14_ETMVDCR2(val) MCR14(val, 1, c0, c14, 0) +#define WCP14_ETMVDCR3(val) MCR14(val, 1, c0, c15, 0) +#define WCP14_ETMACVR0(val) MCR14(val, 1, c0, c0, 1) +#define WCP14_ETMACVR1(val) MCR14(val, 1, c0, c1, 1) +#define WCP14_ETMACVR2(val) MCR14(val, 1, c0, c2, 1) +#define WCP14_ETMACVR3(val) MCR14(val, 1, c0, c3, 1) +#define WCP14_ETMACVR4(val) MCR14(val, 1, c0, c4, 1) +#define WCP14_ETMACVR5(val) MCR14(val, 1, c0, c5, 1) +#define WCP14_ETMACVR6(val) MCR14(val, 1, c0, c6, 1) +#define WCP14_ETMACVR7(val) MCR14(val, 1, c0, c7, 1) +#define WCP14_ETMACVR8(val) MCR14(val, 1, c0, c8, 1) +#define WCP14_ETMACVR9(val) MCR14(val, 1, c0, c9, 1) +#define WCP14_ETMACVR10(val) MCR14(val, 1, c0, c10, 1) +#define WCP14_ETMACVR11(val) MCR14(val, 1, c0, c11, 1) +#define WCP14_ETMACVR12(val) MCR14(val, 1, c0, c12, 1) +#define WCP14_ETMACVR13(val) MCR14(val, 1, c0, c13, 1) +#define WCP14_ETMACVR14(val) MCR14(val, 1, c0, c14, 1) +#define WCP14_ETMACVR15(val) MCR14(val, 1, c0, c15, 1) +#define WCP14_ETMACTR0(val) MCR14(val, 1, c0, c0, 2) +#define WCP14_ETMACTR1(val) MCR14(val, 1, c0, c1, 2) +#define WCP14_ETMACTR2(val) MCR14(val, 1, c0, c2, 2) +#define WCP14_ETMACTR3(val) MCR14(val, 1, c0, c3, 2) +#define WCP14_ETMACTR4(val) MCR14(val, 1, c0, c4, 2) +#define WCP14_ETMACTR5(val) MCR14(val, 1, c0, c5, 2) +#define WCP14_ETMACTR6(val) MCR14(val, 1, c0, c6, 2) +#define WCP14_ETMACTR7(val) MCR14(val, 1, c0, c7, 2) +#define WCP14_ETMACTR8(val) MCR14(val, 1, c0, c8, 2) +#define WCP14_ETMACTR9(val) MCR14(val, 1, c0, c9, 2) +#define WCP14_ETMACTR10(val) MCR14(val, 1, c0, c10, 2) +#define WCP14_ETMACTR11(val) MCR14(val, 1, c0, c11, 2) +#define WCP14_ETMACTR12(val) MCR14(val, 1, c0, c12, 2) +#define WCP14_ETMACTR13(val) MCR14(val, 1, c0, c13, 2) +#define WCP14_ETMACTR14(val) MCR14(val, 1, c0, c14, 2) +#define WCP14_ETMACTR15(val) MCR14(val, 1, c0, c15, 2) +#define WCP14_ETMDCVR0(val) MCR14(val, 1, c0, c0, 3) +#define WCP14_ETMDCVR2(val) MCR14(val, 1, c0, c2, 3) +#define WCP14_ETMDCVR4(val) MCR14(val, 1, c0, c4, 3) +#define WCP14_ETMDCVR6(val) MCR14(val, 1, c0, c6, 3) +#define WCP14_ETMDCVR8(val) MCR14(val, 1, c0, c8, 3) +#define WCP14_ETMDCVR10(val) MCR14(val, 1, c0, c10, 3) +#define WCP14_ETMDCVR12(val) MCR14(val, 1, c0, c12, 3) +#define WCP14_ETMDCVR14(val) MCR14(val, 1, c0, c14, 3) +#define WCP14_ETMDCMR0(val) MCR14(val, 1, c0, c0, 4) +#define WCP14_ETMDCMR2(val) MCR14(val, 1, c0, c2, 4) +#define WCP14_ETMDCMR4(val) MCR14(val, 1, c0, c4, 4) +#define WCP14_ETMDCMR6(val) MCR14(val, 1, c0, c6, 4) +#define WCP14_ETMDCMR8(val) MCR14(val, 1, c0, c8, 4) +#define WCP14_ETMDCMR10(val) MCR14(val, 1, c0, c10, 4) +#define WCP14_ETMDCMR12(val) MCR14(val, 1, c0, c12, 4) +#define WCP14_ETMDCMR14(val) MCR14(val, 1, c0, c14, 4) +#define WCP14_ETMCNTRLDVR0(val) MCR14(val, 1, c0, c0, 5) +#define WCP14_ETMCNTRLDVR1(val) MCR14(val, 1, c0, c1, 5) +#define WCP14_ETMCNTRLDVR2(val) MCR14(val, 1, c0, c2, 5) +#define WCP14_ETMCNTRLDVR3(val) MCR14(val, 1, c0, c3, 5) +#define WCP14_ETMCNTENR0(val) MCR14(val, 1, c0, c4, 5) +#define WCP14_ETMCNTENR1(val) MCR14(val, 1, c0, c5, 5) +#define WCP14_ETMCNTENR2(val) MCR14(val, 1, c0, c6, 5) +#define WCP14_ETMCNTENR3(val) MCR14(val, 1, c0, c7, 5) +#define WCP14_ETMCNTRLDEVR0(val) MCR14(val, 1, c0, c8, 5) +#define WCP14_ETMCNTRLDEVR1(val) MCR14(val, 1, c0, c9, 5) +#define WCP14_ETMCNTRLDEVR2(val) MCR14(val, 1, c0, c10, 5) +#define WCP14_ETMCNTRLDEVR3(val) MCR14(val, 1, c0, c11, 5) +#define WCP14_ETMCNTVR0(val) MCR14(val, 1, c0, c12, 5) +#define WCP14_ETMCNTVR1(val) MCR14(val, 1, c0, c13, 5) +#define WCP14_ETMCNTVR2(val) MCR14(val, 1, c0, c14, 5) +#define WCP14_ETMCNTVR3(val) MCR14(val, 1, c0, c15, 5) +#define WCP14_ETMSQ12EVR(val) MCR14(val, 1, c0, c0, 6) +#define WCP14_ETMSQ21EVR(val) MCR14(val, 1, c0, c1, 6) +#define WCP14_ETMSQ23EVR(val) MCR14(val, 1, c0, c2, 6) +#define WCP14_ETMSQ31EVR(val) MCR14(val, 1, c0, c3, 6) +#define WCP14_ETMSQ32EVR(val) MCR14(val, 1, c0, c4, 6) +#define WCP14_ETMSQ13EVR(val) MCR14(val, 1, c0, c5, 6) +#define WCP14_ETMSQR(val) MCR14(val, 1, c0, c7, 6) +#define WCP14_ETMEXTOUTEVR0(val) MCR14(val, 1, c0, c8, 6) +#define WCP14_ETMEXTOUTEVR1(val) MCR14(val, 1, c0, c9, 6) +#define WCP14_ETMEXTOUTEVR2(val) MCR14(val, 1, c0, c10, 6) +#define WCP14_ETMEXTOUTEVR3(val) MCR14(val, 1, c0, c11, 6) +#define WCP14_ETMCIDCVR0(val) MCR14(val, 1, c0, c12, 6) +#define WCP14_ETMCIDCVR1(val) MCR14(val, 1, c0, c13, 6) +#define WCP14_ETMCIDCVR2(val) MCR14(val, 1, c0, c14, 6) +#define WCP14_ETMCIDCMR(val) MCR14(val, 1, c0, c15, 6) +#define WCP14_ETMIMPSPEC0(val) MCR14(val, 1, c0, c0, 7) +#define WCP14_ETMIMPSPEC1(val) MCR14(val, 1, c0, c1, 7) +#define WCP14_ETMIMPSPEC2(val) MCR14(val, 1, c0, c2, 7) +#define WCP14_ETMIMPSPEC3(val) MCR14(val, 1, c0, c3, 7) +#define WCP14_ETMIMPSPEC4(val) MCR14(val, 1, c0, c4, 7) +#define WCP14_ETMIMPSPEC5(val) MCR14(val, 1, c0, c5, 7) +#define WCP14_ETMIMPSPEC6(val) MCR14(val, 1, c0, c6, 7) +#define WCP14_ETMIMPSPEC7(val) MCR14(val, 1, c0, c7, 7) +/* Can be read only in ETMv3.4, ETMv3.5 */ +#define WCP14_ETMSYNCFR(val) MCR14(val, 1, c0, c8, 7) +#define WCP14_ETMEXTINSELR(val) MCR14(val, 1, c0, c11, 7) +#define WCP14_ETMTESSEICR(val) MCR14(val, 1, c0, c12, 7) +#define WCP14_ETMEIBCR(val) MCR14(val, 1, c0, c13, 7) +#define WCP14_ETMTSEVR(val) MCR14(val, 1, c0, c14, 7) +#define WCP14_ETMAUXCR(val) MCR14(val, 1, c0, c15, 7) +#define WCP14_ETMTRACEIDR(val) MCR14(val, 1, c1, c0, 0) +#define WCP14_ETMIDR2(val) MCR14(val, 1, c1, c2, 0) +#define WCP14_ETMVMIDCVR(val) MCR14(val, 1, c1, c0, 1) +#define WCP14_ETMOSLAR(val) MCR14(val, 1, c1, c0, 4) +/* Not available in PFTv1.1 */ +#define WCP14_ETMOSSRR(val) MCR14(val, 1, c1, c2, 4) +#define WCP14_ETMPDCR(val) MCR14(val, 1, c1, c4, 4) +#define WCP14_ETMPDSR(val) MCR14(val, 1, c1, c5, 4) +#define WCP14_ETMITCTRL(val) MCR14(val, 1, c7, c0, 4) +#define WCP14_ETMCLAIMSET(val) MCR14(val, 1, c7, c8, 6) +#define WCP14_ETMCLAIMCLR(val) MCR14(val, 1, c7, c9, 6) +/* Writes to this from CP14 interface are ignored */ +#define WCP14_ETMLAR(val) MCR14(val, 1, c7, c12, 6) + +#endif diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index 71a06b293489..3e635eed9c6c 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -43,16 +43,6 @@ struct cpu_context_save { __u32 extra[2]; /* Xscale 'acc' register, etc */ }; -struct arm_restart_block { - union { - /* For user cache flushing */ - struct { - unsigned long start; - unsigned long end; - } cache; - }; -}; - /* * low level task data that entry.S needs immediate access to. * __switch_to() assumes cpu_context follows immediately after cpu_domain. @@ -78,7 +68,6 @@ struct thread_info { unsigned long thumbee_state; /* ThumbEE Handler Base register */ #endif struct restart_block restart_block; - struct arm_restart_block arm_restart_block; }; #define INIT_THREAD_INFO(tsk) \ diff --git a/arch/arm/include/asm/tls.h b/arch/arm/include/asm/tls.h index 83259b873333..5f833f7adba1 100644 --- a/arch/arm/include/asm/tls.h +++ b/arch/arm/include/asm/tls.h @@ -1,6 +1,9 @@ #ifndef __ASMARM_TLS_H #define __ASMARM_TLS_H +#include <linux/compiler.h> +#include <asm/thread_info.h> + #ifdef __ASSEMBLY__ #include <asm/asm-offsets.h> .macro switch_tls_none, base, tp, tpuser, tmp1, tmp2 @@ -50,6 +53,49 @@ #endif #ifndef __ASSEMBLY__ + +static inline void set_tls(unsigned long val) +{ + struct thread_info *thread; + + thread = current_thread_info(); + + thread->tp_value[0] = val; + + /* + * This code runs with preemption enabled and therefore must + * be reentrant with respect to switch_tls. + * + * We need to ensure ordering between the shadow state and the + * hardware state, so that we don't corrupt the hardware state + * with a stale shadow state during context switch. + * + * If we're preempted here, switch_tls will load TPIDRURO from + * thread_info upon resuming execution and the following mcr + * is merely redundant. + */ + barrier(); + + if (!tls_emu) { + if (has_tls_reg) { + asm("mcr p15, 0, %0, c13, c0, 3" + : : "r" (val)); + } else { +#ifdef CONFIG_KUSER_HELPERS + /* + * User space must never try to access this + * directly. Expect your app to break + * eventually if you do so. The user helper + * at 0xffff0fe0 must be used instead. (see + * entry-armv.S for details) + */ + *((unsigned int *)0xffff0ff0) = val; +#endif + } + + } +} + static inline unsigned long get_tpuser(void) { unsigned long reg = 0; @@ -59,5 +105,23 @@ static inline unsigned long get_tpuser(void) return reg; } + +static inline void set_tpuser(unsigned long val) +{ + /* Since TPIDRURW is fully context-switched (unlike TPIDRURO), + * we need not update thread_info. + */ + if (has_tls_reg && !tls_emu) { + asm("mcr p15, 0, %0, c13, c0, 2" + : : "r" (val)); + } +} + +static inline void flush_tls(void) +{ + set_tls(0); + set_tpuser(0); +} + #endif #endif /* __ASMARM_TLS_H */ diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index a30fc9be9e9e..b4ea607ff6de 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -30,7 +30,6 @@ else obj-y += entry-armv.o endif -obj-$(CONFIG_OC_ETM) += etm.o obj-$(CONFIG_CPU_IDLE) += cpuidle.o obj-$(CONFIG_ISA_DMA_API) += dma.o obj-$(CONFIG_FIQ) += fiq.o fiqasm.o diff --git a/arch/arm/kernel/etm.c b/arch/arm/kernel/etm.c deleted file mode 100644 index 131a6ab5f355..000000000000 --- a/arch/arm/kernel/etm.c +++ /dev/null @@ -1,654 +0,0 @@ -/* - * linux/arch/arm/kernel/etm.c - * - * Driver for ARM's Embedded Trace Macrocell and Embedded Trace Buffer. - * - * Copyright (C) 2009 Nokia Corporation. - * Alexander Shishkin - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/types.h> -#include <linux/io.h> -#include <linux/sysrq.h> -#include <linux/device.h> -#include <linux/clk.h> -#include <linux/amba/bus.h> -#include <linux/fs.h> -#include <linux/uaccess.h> -#include <linux/miscdevice.h> -#include <linux/vmalloc.h> -#include <linux/mutex.h> -#include <linux/module.h> -#include <asm/hardware/coresight.h> -#include <asm/sections.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Alexander Shishkin"); - -/* - * ETM tracer state - */ -struct tracectx { - unsigned int etb_bufsz; - void __iomem *etb_regs; - void __iomem *etm_regs; - unsigned long flags; - int ncmppairs; - int etm_portsz; - struct device *dev; - struct clk *emu_clk; - struct mutex mutex; -}; - -static struct tracectx tracer; - -static inline bool trace_isrunning(struct tracectx *t) -{ - return !!(t->flags & TRACER_RUNNING); -} - -static int etm_setup_address_range(struct tracectx *t, int n, - unsigned long start, unsigned long end, int exclude, int data) -{ - u32 flags = ETMAAT_ARM | ETMAAT_IGNCONTEXTID | ETMAAT_NSONLY | \ - ETMAAT_NOVALCMP; - - if (n < 1 || n > t->ncmppairs) - return -EINVAL; - - /* comparators and ranges are numbered starting with 1 as opposed - * to bits in a word */ - n--; - - if (data) - flags |= ETMAAT_DLOADSTORE; - else - flags |= ETMAAT_IEXEC; - - /* first comparator for the range */ - etm_writel(t, flags, ETMR_COMP_ACC_TYPE(n * 2)); - etm_writel(t, start, ETMR_COMP_VAL(n * 2)); - - /* second comparator is right next to it */ - etm_writel(t, flags, ETMR_COMP_ACC_TYPE(n * 2 + 1)); - etm_writel(t, end, ETMR_COMP_VAL(n * 2 + 1)); - - flags = exclude ? ETMTE_INCLEXCL : 0; - etm_writel(t, flags | (1 << n), ETMR_TRACEENCTRL); - - return 0; -} - -static int trace_start(struct tracectx *t) -{ - u32 v; - unsigned long timeout = TRACER_TIMEOUT; - - etb_unlock(t); - - etb_writel(t, 0, ETBR_FORMATTERCTRL); - etb_writel(t, 1, ETBR_CTRL); - - etb_lock(t); - - /* configure etm */ - v = ETMCTRL_OPTS | ETMCTRL_PROGRAM | ETMCTRL_PORTSIZE(t->etm_portsz); - - if (t->flags & TRACER_CYCLE_ACC) - v |= ETMCTRL_CYCLEACCURATE; - - etm_unlock(t); - - etm_writel(t, v, ETMR_CTRL); - - while (!(etm_readl(t, ETMR_CTRL) & ETMCTRL_PROGRAM) && --timeout) - ; - if (!timeout) { - dev_dbg(t->dev, "Waiting for progbit to assert timed out\n"); - etm_lock(t); - return -EFAULT; - } - - etm_setup_address_range(t, 1, (unsigned long)_stext, - (unsigned long)_etext, 0, 0); - etm_writel(t, 0, ETMR_TRACEENCTRL2); - etm_writel(t, 0, ETMR_TRACESSCTRL); - etm_writel(t, 0x6f, ETMR_TRACEENEVT); - - v &= ~ETMCTRL_PROGRAM; - v |= ETMCTRL_PORTSEL; - - etm_writel(t, v, ETMR_CTRL); - - timeout = TRACER_TIMEOUT; - while (etm_readl(t, ETMR_CTRL) & ETMCTRL_PROGRAM && --timeout) - ; - if (!timeout) { - dev_dbg(t->dev, "Waiting for progbit to deassert timed out\n"); - etm_lock(t); - return -EFAULT; - } - - etm_lock(t); - - t->flags |= TRACER_RUNNING; - - return 0; -} - -static int trace_stop(struct tracectx *t) -{ - unsigned long timeout = TRACER_TIMEOUT; - - etm_unlock(t); - - etm_writel(t, 0x440, ETMR_CTRL); - while (!(etm_readl(t, ETMR_CTRL) & ETMCTRL_PROGRAM) && --timeout) - ; - if (!timeout) { - dev_dbg(t->dev, "Waiting for progbit to assert timed out\n"); - etm_lock(t); - return -EFAULT; - } - - etm_lock(t); - - etb_unlock(t); - etb_writel(t, ETBFF_MANUAL_FLUSH, ETBR_FORMATTERCTRL); - - timeout = TRACER_TIMEOUT; - while (etb_readl(t, ETBR_FORMATTERCTRL) & - ETBFF_MANUAL_FLUSH && --timeout) - ; - if (!timeout) { - dev_dbg(t->dev, "Waiting for formatter flush to commence " - "timed out\n"); - etb_lock(t); - return -EFAULT; - } - - etb_writel(t, 0, ETBR_CTRL); - - etb_lock(t); - - t->flags &= ~TRACER_RUNNING; - - return 0; -} - -static int etb_getdatalen(struct tracectx *t) -{ - u32 v; - int rp, wp; - - v = etb_readl(t, ETBR_STATUS); - - if (v & 1) - return t->etb_bufsz; - - rp = etb_readl(t, ETBR_READADDR); - wp = etb_readl(t, ETBR_WRITEADDR); - - if (rp > wp) { - etb_writel(t, 0, ETBR_READADDR); - etb_writel(t, 0, ETBR_WRITEADDR); - - return 0; - } - - return wp - rp; -} - -/* sysrq+v will always stop the running trace and leave it at that */ -static void etm_dump(void) -{ - struct tracectx *t = &tracer; - u32 first = 0; - int length; - - if (!t->etb_regs) { - printk(KERN_INFO "No tracing hardware found\n"); - return; - } - - if (trace_isrunning(t)) - trace_stop(t); - - etb_unlock(t); - - length = etb_getdatalen(t); - - if (length == t->etb_bufsz) - first = etb_readl(t, ETBR_WRITEADDR); - - etb_writel(t, first, ETBR_READADDR); - - printk(KERN_INFO "Trace buffer contents length: %d\n", length); - printk(KERN_INFO "--- ETB buffer begin ---\n"); - for (; length; length--) - printk("%08x", cpu_to_be32(etb_readl(t, ETBR_READMEM))); - printk(KERN_INFO "\n--- ETB buffer end ---\n"); - - /* deassert the overflow bit */ - etb_writel(t, 1, ETBR_CTRL); - etb_writel(t, 0, ETBR_CTRL); - - etb_writel(t, 0, ETBR_TRIGGERCOUNT); - etb_writel(t, 0, ETBR_READADDR); - etb_writel(t, 0, ETBR_WRITEADDR); - - etb_lock(t); -} - -static void sysrq_etm_dump(int key) -{ - dev_dbg(tracer.dev, "Dumping ETB buffer\n"); - etm_dump(); -} - -static struct sysrq_key_op sysrq_etm_op = { - .handler = sysrq_etm_dump, - .help_msg = "etm-buffer-dump(v)", - .action_msg = "etm", -}; - -static int etb_open(struct inode *inode, struct file *file) -{ - if (!tracer.etb_regs) - return -ENODEV; - - file->private_data = &tracer; - - return nonseekable_open(inode, file); -} - -static ssize_t etb_read(struct file *file, char __user *data, - size_t len, loff_t *ppos) -{ - int total, i; - long length; - struct tracectx *t = file->private_data; - u32 first = 0; - u32 *buf; - - mutex_lock(&t->mutex); - - if (trace_isrunning(t)) { - length = 0; - goto out; - } - - etb_unlock(t); - - total = etb_getdatalen(t); - if (total == t->etb_bufsz) - first = etb_readl(t, ETBR_WRITEADDR); - - etb_writel(t, first, ETBR_READADDR); - - length = min(total * 4, (int)len); - buf = vmalloc(length); - - dev_dbg(t->dev, "ETB buffer length: %d\n", total); - dev_dbg(t->dev, "ETB status reg: %x\n", etb_readl(t, ETBR_STATUS)); - for (i = 0; i < length / 4; i++) - buf[i] = etb_readl(t, ETBR_READMEM); - - /* the only way to deassert overflow bit in ETB status is this */ - etb_writel(t, 1, ETBR_CTRL); - etb_writel(t, 0, ETBR_CTRL); - - etb_writel(t, 0, ETBR_WRITEADDR); - etb_writel(t, 0, ETBR_READADDR); - etb_writel(t, 0, ETBR_TRIGGERCOUNT); - - etb_lock(t); - - length -= copy_to_user(data, buf, length); - vfree(buf); - -out: - mutex_unlock(&t->mutex); - - return length; -} - -static int etb_release(struct inode *inode, struct file *file) -{ - /* there's nothing to do here, actually */ - return 0; -} - -static const struct file_operations etb_fops = { - .owner = THIS_MODULE, - .read = etb_read, - .open = etb_open, - .release = etb_release, - .llseek = no_llseek, -}; - -static struct miscdevice etb_miscdev = { - .name = "tracebuf", - .minor = 0, - .fops = &etb_fops, -}; - -static int etb_probe(struct amba_device *dev, const struct amba_id *id) -{ - struct tracectx *t = &tracer; - int ret = 0; - - ret = amba_request_regions(dev, NULL); - if (ret) - goto out; - - t->etb_regs = ioremap_nocache(dev->res.start, resource_size(&dev->res)); - if (!t->etb_regs) { - ret = -ENOMEM; - goto out_release; - } - - amba_set_drvdata(dev, t); - - etb_miscdev.parent = &dev->dev; - - ret = misc_register(&etb_miscdev); - if (ret) - goto out_unmap; - - t->emu_clk = clk_get(&dev->dev, "emu_src_ck"); - if (IS_ERR(t->emu_clk)) { - dev_dbg(&dev->dev, "Failed to obtain emu_src_ck.\n"); - return -EFAULT; - } - - clk_enable(t->emu_clk); - - etb_unlock(t); - t->etb_bufsz = etb_readl(t, ETBR_DEPTH); - dev_dbg(&dev->dev, "Size: %x\n", t->etb_bufsz); - - /* make sure trace capture is disabled */ - etb_writel(t, 0, ETBR_CTRL); - etb_writel(t, 0x1000, ETBR_FORMATTERCTRL); - etb_lock(t); - - dev_dbg(&dev->dev, "ETB AMBA driver initialized.\n"); - -out: - return ret; - -out_unmap: - iounmap(t->etb_regs); - -out_release: - amba_release_regions(dev); - - return ret; -} - -static int etb_remove(struct amba_device *dev) -{ - struct tracectx *t = amba_get_drvdata(dev); - - iounmap(t->etb_regs); - t->etb_regs = NULL; - - clk_disable(t->emu_clk); - clk_put(t->emu_clk); - - amba_release_regions(dev); - - return 0; -} - -static struct amba_id etb_ids[] = { - { - .id = 0x0003b907, - .mask = 0x0007ffff, - }, - { 0, 0 }, -}; - -static struct amba_driver etb_driver = { - .drv = { - .name = "etb", - .owner = THIS_MODULE, - }, - .probe = etb_probe, - .remove = etb_remove, - .id_table = etb_ids, -}; - -/* use a sysfs file "trace_running" to start/stop tracing */ -static ssize_t trace_running_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - return sprintf(buf, "%x\n", trace_isrunning(&tracer)); -} - -static ssize_t trace_running_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t n) -{ - unsigned int value; - int ret; - - if (sscanf(buf, "%u", &value) != 1) - return -EINVAL; - - mutex_lock(&tracer.mutex); - ret = value ? trace_start(&tracer) : trace_stop(&tracer); - mutex_unlock(&tracer.mutex); - - return ret ? : n; -} - -static struct kobj_attribute trace_running_attr = - __ATTR(trace_running, 0644, trace_running_show, trace_running_store); - -static ssize_t trace_info_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - u32 etb_wa, etb_ra, etb_st, etb_fc, etm_ctrl, etm_st; - int datalen; - - etb_unlock(&tracer); - datalen = etb_getdatalen(&tracer); - etb_wa = etb_readl(&tracer, ETBR_WRITEADDR); - etb_ra = etb_readl(&tracer, ETBR_READADDR); - etb_st = etb_readl(&tracer, ETBR_STATUS); - etb_fc = etb_readl(&tracer, ETBR_FORMATTERCTRL); - etb_lock(&tracer); - - etm_unlock(&tracer); - etm_ctrl = etm_readl(&tracer, ETMR_CTRL); - etm_st = etm_readl(&tracer, ETMR_STATUS); - etm_lock(&tracer); - - return sprintf(buf, "Trace buffer len: %d\nComparator pairs: %d\n" - "ETBR_WRITEADDR:\t%08x\n" - "ETBR_READADDR:\t%08x\n" - "ETBR_STATUS:\t%08x\n" - "ETBR_FORMATTERCTRL:\t%08x\n" - "ETMR_CTRL:\t%08x\n" - "ETMR_STATUS:\t%08x\n", - datalen, - tracer.ncmppairs, - etb_wa, - etb_ra, - etb_st, - etb_fc, - etm_ctrl, - etm_st - ); -} - -static struct kobj_attribute trace_info_attr = - __ATTR(trace_info, 0444, trace_info_show, NULL); - -static ssize_t trace_mode_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - return sprintf(buf, "%d %d\n", - !!(tracer.flags & TRACER_CYCLE_ACC), - tracer.etm_portsz); -} - -static ssize_t trace_mode_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t n) -{ - unsigned int cycacc, portsz; - - if (sscanf(buf, "%u %u", &cycacc, &portsz) != 2) - return -EINVAL; - - mutex_lock(&tracer.mutex); - if (cycacc) - tracer.flags |= TRACER_CYCLE_ACC; - else - tracer.flags &= ~TRACER_CYCLE_ACC; - - tracer.etm_portsz = portsz & 0x0f; - mutex_unlock(&tracer.mutex); - - return n; -} - -static struct kobj_attribute trace_mode_attr = - __ATTR(trace_mode, 0644, trace_mode_show, trace_mode_store); - -static int etm_probe(struct amba_device *dev, const struct amba_id *id) -{ - struct tracectx *t = &tracer; - int ret = 0; - - if (t->etm_regs) { - dev_dbg(&dev->dev, "ETM already initialized\n"); - ret = -EBUSY; - goto out; - } - - ret = amba_request_regions(dev, NULL); - if (ret) - goto out; - - t->etm_regs = ioremap_nocache(dev->res.start, resource_size(&dev->res)); - if (!t->etm_regs) { - ret = -ENOMEM; - goto out_release; - } - - amba_set_drvdata(dev, t); - - mutex_init(&t->mutex); - t->dev = &dev->dev; - t->flags = TRACER_CYCLE_ACC; - t->etm_portsz = 1; - - etm_unlock(t); - (void)etm_readl(t, ETMMR_PDSR); - /* dummy first read */ - (void)etm_readl(&tracer, ETMMR_OSSRR); - - t->ncmppairs = etm_readl(t, ETMR_CONFCODE) & 0xf; - etm_writel(t, 0x440, ETMR_CTRL); - etm_lock(t); - - ret = sysfs_create_file(&dev->dev.kobj, - &trace_running_attr.attr); - if (ret) - goto out_unmap; - - /* failing to create any of these two is not fatal */ - ret = sysfs_create_file(&dev->dev.kobj, &trace_info_attr.attr); - if (ret) - dev_dbg(&dev->dev, "Failed to create trace_info in sysfs\n"); - - ret = sysfs_create_file(&dev->dev.kobj, &trace_mode_attr.attr); - if (ret) - dev_dbg(&dev->dev, "Failed to create trace_mode in sysfs\n"); - - dev_dbg(t->dev, "ETM AMBA driver initialized.\n"); - -out: - return ret; - -out_unmap: - iounmap(t->etm_regs); - -out_release: - amba_release_regions(dev); - - return ret; -} - -static int etm_remove(struct amba_device *dev) -{ - struct tracectx *t = amba_get_drvdata(dev); - - iounmap(t->etm_regs); - t->etm_regs = NULL; - - amba_release_regions(dev); - - sysfs_remove_file(&dev->dev.kobj, &trace_running_attr.attr); - sysfs_remove_file(&dev->dev.kobj, &trace_info_attr.attr); - sysfs_remove_file(&dev->dev.kobj, &trace_mode_attr.attr); - - return 0; -} - -static struct amba_id etm_ids[] = { - { - .id = 0x0003b921, - .mask = 0x0007ffff, - }, - { 0, 0 }, -}; - -static struct amba_driver etm_driver = { - .drv = { - .name = "etm", - .owner = THIS_MODULE, - }, - .probe = etm_probe, - .remove = etm_remove, - .id_table = etm_ids, -}; - -static int __init etm_init(void) -{ - int retval; - - retval = amba_driver_register(&etb_driver); - if (retval) { - printk(KERN_ERR "Failed to register etb\n"); - return retval; - } - - retval = amba_driver_register(&etm_driver); - if (retval) { - amba_driver_unregister(&etb_driver); - printk(KERN_ERR "Failed to probe etm\n"); - return retval; - } - - /* not being able to install this handler is not fatal */ - (void)register_sysrq_key('v', &sysrq_etm_op); - - return 0; -} - -device_initcall(etm_init); - diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 3d446605cbf8..c609f6712929 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -29,6 +29,7 @@ #include <linux/hw_breakpoint.h> #include <linux/smp.h> #include <linux/cpu_pm.h> +#include <linux/coresight.h> #include <asm/cacheflush.h> #include <asm/cputype.h> @@ -36,7 +37,6 @@ #include <asm/hw_breakpoint.h> #include <asm/kdebug.h> #include <asm/traps.h> -#include <asm/hardware/coresight.h> /* Breakpoint currently in use for each BRP. */ static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[ARM_MAX_BRP]); @@ -975,7 +975,7 @@ static void reset_ctrl_regs(void *unused) * Unconditionally clear the OS lock by writing a value * other than CS_LAR_KEY to the access register. */ - ARM_DBG_WRITE(c1, c0, 4, ~CS_LAR_KEY); + ARM_DBG_WRITE(c1, c0, 4, ~CORESIGHT_UNLOCK); isb(); /* diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index 9723d17b8f38..1e782bdeee49 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -163,7 +163,7 @@ static bool migrate_one_irq(struct irq_desc *desc) c = irq_data_get_irq_chip(d); if (!c->irq_set_affinity) pr_debug("IRQ%u: unable to set affinity\n", d->irq); - else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret) + else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret) cpumask_copy(d->affinity, affinity); return ret; diff --git a/arch/arm/kernel/kprobes-common.c b/arch/arm/kernel/kprobes-common.c index 18a76282970e..380c20fb9c85 100644 --- a/arch/arm/kernel/kprobes-common.c +++ b/arch/arm/kernel/kprobes-common.c @@ -14,6 +14,7 @@ #include <linux/kernel.h> #include <linux/kprobes.h> #include <asm/system_info.h> +#include <asm/opcodes.h> #include "kprobes.h" @@ -305,7 +306,8 @@ kprobe_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi) if (handler) { /* We can emulate the instruction in (possibly) modified form */ - asi->insn[0] = (insn & 0xfff00000) | (rn << 16) | reglist; + asi->insn[0] = __opcode_to_mem_arm((insn & 0xfff00000) | + (rn << 16) | reglist); asi->insn_handler = handler; return INSN_GOOD; } @@ -334,13 +336,14 @@ prepare_emulated_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi, #ifdef CONFIG_THUMB2_KERNEL if (thumb) { u16 *thumb_insn = (u16 *)asi->insn; - thumb_insn[1] = 0x4770; /* Thumb bx lr */ - thumb_insn[2] = 0x4770; /* Thumb bx lr */ + /* Thumb bx lr */ + thumb_insn[1] = __opcode_to_mem_thumb16(0x4770); + thumb_insn[2] = __opcode_to_mem_thumb16(0x4770); return insn; } - asi->insn[1] = 0xe12fff1e; /* ARM bx lr */ + asi->insn[1] = __opcode_to_mem_arm(0xe12fff1e); /* ARM bx lr */ #else - asi->insn[1] = 0xe1a0f00e; /* mov pc, lr */ + asi->insn[1] = __opcode_to_mem_arm(0xe1a0f00e); /* mov pc, lr */ #endif /* Make an ARM instruction unconditional */ if (insn < 0xe0000000) @@ -360,12 +363,12 @@ set_emulated_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi, if (thumb) { u16 *ip = (u16 *)asi->insn; if (is_wide_instruction(insn)) - *ip++ = insn >> 16; - *ip++ = insn; + *ip++ = __opcode_to_mem_thumb16(insn >> 16); + *ip++ = __opcode_to_mem_thumb16(insn); return; } #endif - asi->insn[0] = insn; + asi->insn[0] = __opcode_to_mem_arm(insn); } /* diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index 6123daf397a7..241222c66a13 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -11,6 +11,7 @@ #include <linux/kernel.h> #include <linux/kprobes.h> #include <linux/module.h> +#include <asm/opcodes.h> #include "kprobes.h" @@ -163,9 +164,9 @@ t32_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi) enum kprobe_insn ret = kprobe_decode_ldmstm(insn, asi); /* Fixup modified instruction to have halfwords in correct order...*/ - insn = asi->insn[0]; - ((u16 *)asi->insn)[0] = insn >> 16; - ((u16 *)asi->insn)[1] = insn & 0xffff; + insn = __mem_to_opcode_arm(asi->insn[0]); + ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(insn >> 16); + ((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0xffff); return ret; } @@ -1153,7 +1154,7 @@ t16_decode_hiregs(kprobe_opcode_t insn, struct arch_specific_insn *asi) { insn &= ~0x00ff; insn |= 0x001; /* Set Rdn = R1 and Rm = R0 */ - ((u16 *)asi->insn)[0] = insn; + ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(insn); asi->insn_handler = t16_emulate_hiregs; return INSN_GOOD; } @@ -1182,8 +1183,10 @@ t16_decode_push(kprobe_opcode_t insn, struct arch_specific_insn *asi) * and call it with R9=SP and LR in the register list represented * by R8. */ - ((u16 *)asi->insn)[0] = 0xe929; /* 1st half STMDB R9!,{} */ - ((u16 *)asi->insn)[1] = insn & 0x1ff; /* 2nd half (register list) */ + /* 1st half STMDB R9!,{} */ + ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(0xe929); + /* 2nd half (register list) */ + ((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0x1ff); asi->insn_handler = t16_emulate_push; return INSN_GOOD; } @@ -1232,8 +1235,10 @@ t16_decode_pop(kprobe_opcode_t insn, struct arch_specific_insn *asi) * and call it with R9=SP and PC in the register list represented * by R8. */ - ((u16 *)asi->insn)[0] = 0xe8b9; /* 1st half LDMIA R9!,{} */ - ((u16 *)asi->insn)[1] = insn & 0x1ff; /* 2nd half (register list) */ + /* 1st half LDMIA R9!,{} */ + ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(0xe8b9); + /* 2nd half (register list) */ + ((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0x1ff); asi->insn_handler = insn & 0x100 ? t16_emulate_pop_pc : t16_emulate_pop_nopc; return INSN_GOOD; diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c index a7b621ece23d..49a87b6d0bf3 100644 --- a/arch/arm/kernel/kprobes.c +++ b/arch/arm/kernel/kprobes.c @@ -26,6 +26,7 @@ #include <linux/stop_machine.h> #include <linux/stringify.h> #include <asm/traps.h> +#include <asm/opcodes.h> #include <asm/cacheflush.h> #include "kprobes.h" @@ -62,10 +63,10 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) #ifdef CONFIG_THUMB2_KERNEL thumb = true; addr &= ~1; /* Bit 0 would normally be set to indicate Thumb code */ - insn = ((u16 *)addr)[0]; + insn = __mem_to_opcode_thumb16(((u16 *)addr)[0]); if (is_wide_instruction(insn)) { - insn <<= 16; - insn |= ((u16 *)addr)[1]; + u16 inst2 = __mem_to_opcode_thumb16(((u16 *)addr)[1]); + insn = __opcode_thumb32_compose(insn, inst2); decode_insn = thumb32_kprobe_decode_insn; } else decode_insn = thumb16_kprobe_decode_insn; @@ -73,7 +74,7 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) thumb = false; if (addr & 0x3) return -EINVAL; - insn = *p->addr; + insn = __mem_to_opcode_arm(*p->addr); decode_insn = arm_kprobe_decode_insn; #endif diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 92f7b15dd221..5f6e650ec9ab 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -334,6 +334,8 @@ void flush_thread(void) memset(&tsk->thread.debug, 0, sizeof(struct debug_info)); memset(&thread->fpstate, 0, sizeof(union fp_state)); + flush_tls(); + thread_notify(THREAD_NOTIFY_FLUSH, thread); } diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 4a5e9430f16b..a4ef472c0d5e 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -1034,6 +1034,15 @@ static int c_show(struct seq_file *m, void *v) seq_printf(m, "model name\t: %s rev %d (%s)\n", cpu_name, cpuid & 15, elf_platform); +#if defined(CONFIG_SMP) + seq_printf(m, "BogoMIPS\t: %lu.%02lu\n", + per_cpu(cpu_data, i).loops_per_jiffy / (500000UL/HZ), + (per_cpu(cpu_data, i).loops_per_jiffy / (5000UL/HZ)) % 100); +#else + seq_printf(m, "BogoMIPS\t: %lu.%02lu\n", + loops_per_jiffy / (500000/HZ), + (loops_per_jiffy / (5000/HZ)) % 100); +#endif /* dump out the processor features */ seq_puts(m, "Features\t: "); diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index b7b4c86e338b..8cd3724714fe 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -388,8 +388,17 @@ asmlinkage void secondary_start_kernel(void) void __init smp_cpus_done(unsigned int max_cpus) { - printk(KERN_INFO "SMP: Total of %d processors activated.\n", - num_online_cpus()); + int cpu; + unsigned long bogosum = 0; + + for_each_online_cpu(cpu) + bogosum += per_cpu(cpu_data, cpu).loops_per_jiffy; + + printk(KERN_INFO "SMP: Total of %d processors activated " + "(%lu.%02lu BogoMIPS).\n", + num_online_cpus(), + bogosum / (500000/HZ), + (bogosum / (5000/HZ)) % 100); hyp_mode_check(); } diff --git a/arch/arm/kernel/thumbee.c b/arch/arm/kernel/thumbee.c index 7b8403b76666..80f0d69205e7 100644 --- a/arch/arm/kernel/thumbee.c +++ b/arch/arm/kernel/thumbee.c @@ -45,7 +45,7 @@ static int thumbee_notifier(struct notifier_block *self, unsigned long cmd, void switch (cmd) { case THREAD_NOTIFY_FLUSH: - thread->thumbee_state = 0; + teehbr_write(0); break; case THREAD_NOTIFY_SWITCH: current_thread_info()->thumbee_state = teehbr_read(); diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 172ee18ff124..3f314433d653 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -510,8 +510,6 @@ static int bad_syscall(int n, struct pt_regs *regs) return regs->ARM_r0; } -static long do_cache_op_restart(struct restart_block *); - static inline int __do_cache_op(unsigned long start, unsigned long end) { @@ -520,24 +518,8 @@ __do_cache_op(unsigned long start, unsigned long end) do { unsigned long chunk = min(PAGE_SIZE, end - start); - if (signal_pending(current)) { - struct thread_info *ti = current_thread_info(); - - ti->restart_block = (struct restart_block) { - .fn = do_cache_op_restart, - }; - - ti->arm_restart_block = (struct arm_restart_block) { - { - .cache = { - .start = start, - .end = end, - }, - }, - }; - - return -ERESTART_RESTARTBLOCK; - } + if (fatal_signal_pending(current)) + return 0; ret = flush_cache_user_range(start, start + chunk); if (ret) @@ -550,15 +532,6 @@ __do_cache_op(unsigned long start, unsigned long end) return 0; } -static long do_cache_op_restart(struct restart_block *unused) -{ - struct arm_restart_block *restart_block; - - restart_block = ¤t_thread_info()->arm_restart_block; - return __do_cache_op(restart_block->cache.start, - restart_block->cache.end); -} - static inline int do_cache_op(unsigned long start, unsigned long end, int flags) { @@ -578,7 +551,6 @@ do_cache_op(unsigned long start, unsigned long end, int flags) #define NR(x) ((__ARM_NR_##x) - __ARM_NR_BASE) asmlinkage int arm_syscall(int no, struct pt_regs *regs) { - struct thread_info *thread = current_thread_info(); siginfo_t info; if ((no >> 16) != (__ARM_NR_BASE>> 16)) @@ -629,21 +601,7 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs) return regs->ARM_r0; case NR(set_tls): - thread->tp_value[0] = regs->ARM_r0; - if (tls_emu) - return 0; - if (has_tls_reg) { - asm ("mcr p15, 0, %0, c13, c0, 3" - : : "r" (regs->ARM_r0)); - } else { - /* - * User space must never try to access this directly. - * Expect your app to break eventually if you do so. - * The user helper at 0xffff0fe0 must be used instead. - * (see entry-armv.S for details) - */ - *((unsigned int *)0xffff0ff0) = regs->ARM_r0; - } + set_tls(regs->ARM_r0); return 0; #ifdef CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c index 4c979d466cc1..a96a8043277c 100644 --- a/arch/arm/kvm/handle_exit.c +++ b/arch/arm/kvm/handle_exit.c @@ -93,6 +93,8 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run) else kvm_vcpu_block(vcpu); + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + return 1; } diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S index 2cc14dfad049..768e711c4c1e 100644 --- a/arch/arm/kvm/init.S +++ b/arch/arm/kvm/init.S @@ -98,6 +98,10 @@ __do_hyp_init: mrc p15, 0, r0, c10, c2, 1 mcr p15, 4, r0, c10, c2, 1 + @ Invalidate the stale TLBs from Bootloader + mcr p15, 4, r0, c8, c7, 0 @ TLBIALLH + dsb ish + @ Set the HSCTLR to: @ - ARM/THUMB exceptions: Kernel config (Thumb-2 kernel) @ - Endianness: Kernel config diff --git a/arch/arm/mach-at91/clock.c b/arch/arm/mach-at91/clock.c index 034529d801b2..d66f102c352a 100644 --- a/arch/arm/mach-at91/clock.c +++ b/arch/arm/mach-at91/clock.c @@ -962,6 +962,7 @@ static int __init at91_clock_reset(void) } at91_pmc_write(AT91_PMC_SCDR, scdr); + at91_pmc_write(AT91_PMC_PCDR, pcdr); if (cpu_is_sama5d3()) at91_pmc_write(AT91_PMC_PCDR1, pcdr1); diff --git a/arch/arm/mach-at91/pm.h b/arch/arm/mach-at91/pm.h index c5101dcb4fb0..1d4df3b70ebc 100644 --- a/arch/arm/mach-at91/pm.h +++ b/arch/arm/mach-at91/pm.h @@ -45,7 +45,7 @@ static inline void at91rm9200_standby(void) " mcr p15, 0, %0, c7, c0, 4\n\t" " str %5, [%1, %2]" : - : "r" (0), "r" (AT91_BASE_SYS), "r" (AT91RM9200_SDRAMC_LPR), + : "r" (0), "r" (at91_ramc_base[0]), "r" (AT91RM9200_SDRAMC_LPR), "r" (1), "r" (AT91RM9200_SDRAMC_SRR), "r" (lpr)); } diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c index 4d677f442539..01a5765a8b26 100644 --- a/arch/arm/mach-imx/clk-imx6q.c +++ b/arch/arm/mach-imx/clk-imx6q.c @@ -161,8 +161,8 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node) post_div_table[1].div = 1; post_div_table[2].div = 1; video_div_table[1].div = 1; - video_div_table[2].div = 1; - }; + video_div_table[3].div = 1; + } /* type name parent_name base div_mask */ clk[pll1_sys] = imx_clk_pllv3(IMX_PLLV3_SYS, "pll1_sys", "osc", base, 0x7f); diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c index 4e9d58148ca7..c295c10f9217 100644 --- a/arch/arm/mach-mvebu/coherency.c +++ b/arch/arm/mach-mvebu/coherency.c @@ -125,6 +125,29 @@ int __init coherency_init(void) { struct device_node *np; + /* + * The coherency fabric is needed: + * - For coherency between processors on Armada XP, so only + * when SMP is enabled. + * - For coherency between the processor and I/O devices, but + * this coherency requires many pre-requisites (write + * allocate cache policy, shareable pages, SMP bit set) that + * are only meant in SMP situations. + * + * Note that this means that on Armada 370, there is currently + * no way to use hardware I/O coherency, because even when + * CONFIG_SMP is enabled, is_smp() returns false due to the + * Armada 370 being a single-core processor. To lift this + * limitation, we would have to find a way to make the cache + * policy set to write-allocate (on all Armada SoCs), and to + * set the shareable attribute in page tables (on all Armada + * SoCs except the Armada 370). Unfortunately, such decisions + * are taken very early in the kernel boot process, at a point + * where we don't know yet on which SoC we are running. + */ + if (!is_smp()) + return 0; + np = of_find_matching_node(NULL, of_coherency_table); if (np) { struct resource res; @@ -151,6 +174,9 @@ static int __init coherency_late_init(void) { struct device_node *np; + if (!is_smp()) + return 0; + np = of_find_matching_node(NULL, of_coherency_table); if (np) { bus_register_notifier(&platform_bus_type, diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index 0af7ca02314d..6c0ab828b751 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -324,13 +324,21 @@ config MACH_TI8148EVM depends on SOC_TI81XX default y -config OMAP3_EMU - bool "OMAP3 debugging peripherals" - depends on ARCH_OMAP3 - select ARM_AMBA - select OC_ETM - help - Say Y here to enable debugging hardware of omap3 +config MACH_OMAP_4430SDP + bool "OMAP 4430 SDP board" + default y + depends on ARCH_OMAP4 + select OMAP_PACKAGE_CBL + select OMAP_PACKAGE_CBS + select REGULATOR_FIXED_VOLTAGE if REGULATOR + +config MACH_OMAP4_PANDA + bool "OMAP4 Panda Board" + default y + depends on ARCH_OMAP4 + select OMAP_PACKAGE_CBL + select OMAP_PACKAGE_CBS + select REGULATOR_FIXED_VOLTAGE if REGULATOR config OMAP3_SDRC_AC_TIMING bool "Enable SDRC AC timing register changes" diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile index e6eec6f72fd3..8abb3d806134 100644 --- a/arch/arm/mach-omap2/Makefile +++ b/arch/arm/mach-omap2/Makefile @@ -223,7 +223,6 @@ obj-$(CONFIG_SOC_OMAP5) += omap_hwmod_54xx_data.o obj-$(CONFIG_SOC_DRA7XX) += omap_hwmod_7xx_data.o # EMU peripherals -obj-$(CONFIG_OMAP3_EMU) += emu.o obj-$(CONFIG_HW_PERF_EVENTS) += pmu.o iommu-$(CONFIG_OMAP_IOMMU) := omap-iommu.o diff --git a/arch/arm/mach-omap2/emu.c b/arch/arm/mach-omap2/emu.c deleted file mode 100644 index cbeaca2d7695..000000000000 --- a/arch/arm/mach-omap2/emu.c +++ /dev/null @@ -1,50 +0,0 @@ -/* - * emu.c - * - * ETM and ETB CoreSight components' resources as found in OMAP3xxx. - * - * Copyright (C) 2009 Nokia Corporation. - * Alexander Shishkin - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/types.h> -#include <linux/module.h> -#include <linux/device.h> -#include <linux/amba/bus.h> -#include <linux/io.h> -#include <linux/clk.h> -#include <linux/err.h> - -#include "soc.h" -#include "iomap.h" - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Alexander Shishkin"); - -/* Cortex CoreSight components within omap3xxx EMU */ -#define ETM_BASE (L4_EMU_34XX_PHYS + 0x10000) -#define DBG_BASE (L4_EMU_34XX_PHYS + 0x11000) -#define ETB_BASE (L4_EMU_34XX_PHYS + 0x1b000) -#define DAPCTL (L4_EMU_34XX_PHYS + 0x1d000) - -static AMBA_APB_DEVICE(omap3_etb, "etb", 0x000bb907, ETB_BASE, { }, NULL); -static AMBA_APB_DEVICE(omap3_etm, "etm", 0x102bb921, ETM_BASE, { }, NULL); - -static int __init emu_init(void) -{ - if (!cpu_is_omap34xx()) - return -ENODEV; - - amba_device_register(&omap3_etb_device, &iomem_resource); - amba_device_register(&omap3_etm_device, &iomem_resource); - - return 0; -} - -omap_subsys_initcall(emu_init); diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index c914b0052fb9..4551efd28f8d 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -3349,6 +3349,9 @@ int __init omap_hwmod_register_links(struct omap_hwmod_ocp_if **ois) if (!ois) return 0; + if (ois[0] == NULL) /* Empty list */ + return 0; + if (!linkspace) { if (_alloc_linkspace(ois)) { pr_err("omap_hwmod: could not allocate link space\n"); diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c index 810c205d668b..d3ac4c634624 100644 --- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c @@ -35,6 +35,7 @@ #include "i2c.h" #include "mmc.h" #include "wd_timer.h" +#include "soc.h" /* Base offset for all DRA7XX interrupts external to MPUSS */ #define DRA7XX_IRQ_GIC_START 32 @@ -1668,7 +1669,7 @@ static struct omap_hwmod dra7xx_uart3_hwmod = { .class = &dra7xx_uart_hwmod_class, .clkdm_name = "l4per_clkdm", .main_clk = "uart3_gfclk_mux", - .flags = HWMOD_SWSUP_SIDLE_ACT, + .flags = HWMOD_SWSUP_SIDLE_ACT | DEBUG_OMAP4UART3_FLAGS, .prcm = { .omap4 = { .clkctrl_offs = DRA7XX_CM_L4PER_UART3_CLKCTRL_OFFSET, @@ -2707,7 +2708,6 @@ static struct omap_hwmod_ocp_if *dra7xx_hwmod_ocp_ifs[] __initdata = { &dra7xx_l4_per3__usb_otg_ss1, &dra7xx_l4_per3__usb_otg_ss2, &dra7xx_l4_per3__usb_otg_ss3, - &dra7xx_l4_per3__usb_otg_ss4, &dra7xx_l3_main_1__vcp1, &dra7xx_l4_per2__vcp1, &dra7xx_l3_main_1__vcp2, @@ -2716,8 +2716,26 @@ static struct omap_hwmod_ocp_if *dra7xx_hwmod_ocp_ifs[] __initdata = { NULL, }; +static struct omap_hwmod_ocp_if *dra74x_hwmod_ocp_ifs[] __initdata = { + &dra7xx_l4_per3__usb_otg_ss4, + NULL, +}; + +static struct omap_hwmod_ocp_if *dra72x_hwmod_ocp_ifs[] __initdata = { + NULL, +}; + int __init dra7xx_hwmod_init(void) { + int ret; + omap_hwmod_init(); - return omap_hwmod_register_links(dra7xx_hwmod_ocp_ifs); + ret = omap_hwmod_register_links(dra7xx_hwmod_ocp_ifs); + + if (!ret && soc_is_dra74x()) + return omap_hwmod_register_links(dra74x_hwmod_ocp_ifs); + else if (!ret && soc_is_dra72x()) + return omap_hwmod_register_links(dra72x_hwmod_ocp_ifs); + + return ret; } diff --git a/arch/arm/mach-omap2/pm44xx.c b/arch/arm/mach-omap2/pm44xx.c index eefb30cfcabd..2b9cff960af2 100644 --- a/arch/arm/mach-omap2/pm44xx.c +++ b/arch/arm/mach-omap2/pm44xx.c @@ -148,26 +148,6 @@ static inline int omap4_init_static_deps(void) struct clockdomain *ducati_clkdm, *l3_2_clkdm; int ret = 0; - if (omap_rev() == OMAP4430_REV_ES1_0) { - WARN(1, "Power Management not supported on OMAP4430 ES1.0\n"); - return -ENODEV; - } - - pr_err("Power Management for TI OMAP4.\n"); - /* - * OMAP4 chip PM currently works only with certain (newer) - * versions of bootloaders. This is due to missing code in the - * kernel to properly reset and initialize some devices. - * http://www.spinics.net/lists/arm-kernel/msg218641.html - */ - pr_warn("OMAP4 PM: u-boot >= v2012.07 is required for full PM support\n"); - - ret = pwrdm_for_each(pwrdms_setup, NULL); - if (ret) { - pr_err("Failed to setup powerdomains\n"); - return ret; - } - /* * The dynamic dependency between MPUSS -> MEMIF and * MPUSS -> L4_PER/L3_* and DUCATI -> L3_* doesn't work as @@ -231,6 +211,15 @@ int __init omap4_pm_init(void) pr_info("Power Management for TI OMAP4+ devices.\n"); + /* + * OMAP4 chip PM currently works only with certain (newer) + * versions of bootloaders. This is due to missing code in the + * kernel to properly reset and initialize some devices. + * http://www.spinics.net/lists/arm-kernel/msg218641.html + */ + if (cpu_is_omap44xx()) + pr_warn("OMAP4 PM: u-boot >= v2012.07 is required for full PM support\n"); + ret = pwrdm_for_each(pwrdms_setup, NULL); if (ret) { pr_err("Failed to setup powerdomains.\n"); diff --git a/arch/arm/mach-omap2/soc.h b/arch/arm/mach-omap2/soc.h index 076bd90a6ce0..8a9be09d9f38 100644 --- a/arch/arm/mach-omap2/soc.h +++ b/arch/arm/mach-omap2/soc.h @@ -245,6 +245,8 @@ IS_AM_SUBCLASS(437x, 0x437) #define soc_is_omap54xx() 0 #define soc_is_omap543x() 0 #define soc_is_dra7xx() 0 +#define soc_is_dra74x() 0 +#define soc_is_dra72x() 0 #if defined(MULTI_OMAP2) # if defined(CONFIG_ARCH_OMAP2) @@ -393,7 +395,11 @@ IS_OMAP_TYPE(3430, 0x3430) #if defined(CONFIG_SOC_DRA7XX) #undef soc_is_dra7xx +#undef soc_is_dra74x +#undef soc_is_dra72x #define soc_is_dra7xx() (of_machine_is_compatible("ti,dra7")) +#define soc_is_dra74x() (of_machine_is_compatible("ti,dra74")) +#define soc_is_dra72x() (of_machine_is_compatible("ti,dra72")) #endif /* Various silicon revisions for omap2 */ diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c index 74044aaf438b..73d80b8576c3 100644 --- a/arch/arm/mach-omap2/timer.c +++ b/arch/arm/mach-omap2/timer.c @@ -513,11 +513,11 @@ static void __init realtime_counter_init(void) rate = clk_get_rate(sys_clk); /* Numerator/denumerator values refer TRM Realtime Counter section */ switch (rate) { - case 1200000: + case 12000000: num = 64; den = 125; break; - case 1300000: + case 13000000: num = 768; den = 1625; break; @@ -529,11 +529,11 @@ static void __init realtime_counter_init(void) num = 192; den = 625; break; - case 2600000: + case 26000000: num = 384; den = 1625; break; - case 2700000: + case 27000000: num = 256; den = 1125; break; diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c index f162f1b77cd2..82fd9dd17ed1 100644 --- a/arch/arm/mach-pxa/corgi.c +++ b/arch/arm/mach-pxa/corgi.c @@ -26,6 +26,7 @@ #include <linux/i2c.h> #include <linux/i2c/pxa-i2c.h> #include <linux/io.h> +#include <linux/regulator/machine.h> #include <linux/spi/spi.h> #include <linux/spi/ads7846.h> #include <linux/spi/corgi_lcd.h> @@ -711,6 +712,8 @@ static void __init corgi_init(void) sharpsl_nand_partitions[1].size = 53 * 1024 * 1024; platform_add_devices(devices, ARRAY_SIZE(devices)); + + regulator_has_full_constraints(); } static void __init fixup_corgi(struct tag *tags, char **cmdline, diff --git a/arch/arm/mach-pxa/hx4700.c b/arch/arm/mach-pxa/hx4700.c index a7c30eb0c8db..007fd8a237d9 100644 --- a/arch/arm/mach-pxa/hx4700.c +++ b/arch/arm/mach-pxa/hx4700.c @@ -892,6 +892,8 @@ static void __init hx4700_init(void) mdelay(10); gpio_set_value(GPIO71_HX4700_ASIC3_nRESET, 1); mdelay(10); + + regulator_has_full_constraints(); } MACHINE_START(H4700, "HP iPAQ HX4700") diff --git a/arch/arm/mach-pxa/poodle.c b/arch/arm/mach-pxa/poodle.c index aedf053a1de5..b4fff2998b8a 100644 --- a/arch/arm/mach-pxa/poodle.c +++ b/arch/arm/mach-pxa/poodle.c @@ -25,6 +25,7 @@ #include <linux/gpio.h> #include <linux/i2c.h> #include <linux/i2c/pxa-i2c.h> +#include <linux/regulator/machine.h> #include <linux/spi/spi.h> #include <linux/spi/ads7846.h> #include <linux/spi/pxa2xx_spi.h> @@ -454,6 +455,7 @@ static void __init poodle_init(void) pxa_set_i2c_info(NULL); i2c_register_board_info(0, ARRAY_AND_SIZE(poodle_i2c_devices)); poodle_init_spi(); + regulator_has_full_constraints(); } static void __init fixup_poodle(struct tag *tags, char **cmdline, diff --git a/arch/arm/mach-sa1100/pm.c b/arch/arm/mach-sa1100/pm.c index 6645d1e31f14..34853d5dfda2 100644 --- a/arch/arm/mach-sa1100/pm.c +++ b/arch/arm/mach-sa1100/pm.c @@ -81,6 +81,7 @@ static int sa11x0_pm_enter(suspend_state_t state) /* * Ensure not to come back here if it wasn't intended */ + RCSR = RCSR_SMR; PSPR = 0; /* diff --git a/arch/arm/mach-shmobile/setup-sh73a0.c b/arch/arm/mach-shmobile/setup-sh73a0.c index f74ab530c71d..2b73c8a0c244 100644 --- a/arch/arm/mach-shmobile/setup-sh73a0.c +++ b/arch/arm/mach-shmobile/setup-sh73a0.c @@ -617,6 +617,7 @@ static struct platform_device ipmmu_device = { static struct renesas_intc_irqpin_config irqpin0_platform_data = { .irq_base = irq_pin(0), /* IRQ0 -> IRQ7 */ + .control_parent = true, }; static struct resource irqpin0_resources[] = { @@ -678,6 +679,7 @@ static struct platform_device irqpin1_device = { static struct renesas_intc_irqpin_config irqpin2_platform_data = { .irq_base = irq_pin(16), /* IRQ16 -> IRQ23 */ + .control_parent = true, }; static struct resource irqpin2_resources[] = { @@ -708,6 +710,7 @@ static struct platform_device irqpin2_device = { static struct renesas_intc_irqpin_config irqpin3_platform_data = { .irq_base = irq_pin(24), /* IRQ24 -> IRQ31 */ + .control_parent = true, }; static struct resource irqpin3_resources[] = { diff --git a/arch/arm/mach-tegra/reset-handler.S b/arch/arm/mach-tegra/reset-handler.S index 8c1ba4fea384..350579961e78 100644 --- a/arch/arm/mach-tegra/reset-handler.S +++ b/arch/arm/mach-tegra/reset-handler.S @@ -51,6 +51,7 @@ ENTRY(tegra_resume) THUMB( it ne ) bne cpu_resume @ no + tegra_get_soc_id TEGRA_APB_MISC_BASE, r6 /* Are we on Tegra20? */ cmp r6, #TEGRA20 beq 1f @ Yes diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index ca8ecdee47d8..e9c290c21744 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -798,6 +798,7 @@ config NEED_KUSER_HELPERS config KUSER_HELPERS bool "Enable kuser helpers in vector page" if !NEED_KUSER_HELPERS + depends on MMU default y help Warning: disabling this option may break user programs. diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S index 3815a8262af0..8c48c5c22a33 100644 --- a/arch/arm/mm/abort-ev6.S +++ b/arch/arm/mm/abort-ev6.S @@ -17,12 +17,6 @@ */ .align 5 ENTRY(v6_early_abort) -#ifdef CONFIG_CPU_V6 - sub r1, sp, #4 @ Get unused stack location - strex r0, r1, [r1] @ Clear the exclusive monitor -#elif defined(CONFIG_CPU_32v6K) - clrex -#endif mrc p15, 0, r1, c5, c0, 0 @ get FSR mrc p15, 0, r0, c6, c0, 0 @ get FAR /* diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S index 703375277ba6..4812ad054214 100644 --- a/arch/arm/mm/abort-ev7.S +++ b/arch/arm/mm/abort-ev7.S @@ -13,12 +13,6 @@ */ .align 5 ENTRY(v7_early_abort) - /* - * The effect of data aborts on on the exclusive access monitor are - * UNPREDICTABLE. Do a CLREX to clear the state - */ - clrex - mrc p15, 0, r1, c5, c0, 0 @ get FSR mrc p15, 0, r0, c6, c0, 0 @ get FAR diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 924036473b16..d301662b7b32 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -40,6 +40,7 @@ * This code is not portable to processors with late data abort handling. */ #define CODING_BITS(i) (i & 0x0e000000) +#define COND_BITS(i) (i & 0xf0000000) #define LDST_I_BIT(i) (i & (1 << 26)) /* Immediate constant */ #define LDST_P_BIT(i) (i & (1 << 24)) /* Preindex */ @@ -817,6 +818,8 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) break; case 0x04000000: /* ldr or str immediate */ + if (COND_BITS(instr) == 0xf0000000) /* NEON VLDn, VSTn */ + goto bad; offset.un = OFFSET_BITS(instr); handler = do_alignment_ldrstr; break; diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index 6eb97b3a7481..4370933f16cd 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -144,21 +144,17 @@ static void flush_context(unsigned int cpu) /* Update the list of reserved ASIDs and the ASID bitmap. */ bitmap_clear(asid_map, 0, NUM_USER_ASIDS); for_each_possible_cpu(i) { - if (i == cpu) { - asid = 0; - } else { - asid = atomic64_xchg(&per_cpu(active_asids, i), 0); - /* - * If this CPU has already been through a - * rollover, but hasn't run another task in - * the meantime, we must preserve its reserved - * ASID, as this is the only trace we have of - * the process it is still running. - */ - if (asid == 0) - asid = per_cpu(reserved_asids, i); - __set_bit(asid & ~ASID_MASK, asid_map); - } + asid = atomic64_xchg(&per_cpu(active_asids, i), 0); + /* + * If this CPU has already been through a + * rollover, but hasn't run another task in + * the meantime, we must preserve its reserved + * ASID, as this is the only trace we have of + * the process it is still running. + */ + if (asid == 0) + asid = per_cpu(reserved_asids, i); + __set_bit(asid & ~ASID_MASK, asid_map); per_cpu(reserved_asids, i) = asid; } diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 11b3914660d2..42f2fb8c5a00 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -464,12 +464,21 @@ void __init dma_contiguous_remap(void) map.type = MT_MEMORY_DMA_READY; /* - * Clear previous low-memory mapping + * Clear previous low-memory mapping to ensure that the + * TLB does not see any conflicting entries, then flush + * the TLB of the old entries before creating new mappings. + * + * This ensures that any speculatively loaded TLB entries + * (even though they may be rare) can not cause any problems, + * and ensures that this code is architecturally compliant. */ for (addr = __phys_to_virt(start); addr < __phys_to_virt(end); addr += PMD_SIZE) pmd_clear(pmd_off_k(addr)); + flush_tlb_kernel_range(__phys_to_virt(start), + __phys_to_virt(end)); + iotable_init(&map, 1); } } diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 74f6033e76dd..fdedc31e0f40 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -211,7 +211,6 @@ __v7_pj4b_setup: /* Auxiliary Debug Modes Control 1 Register */ #define PJ4B_STATIC_BP (1 << 2) /* Enable Static BP */ #define PJ4B_INTER_PARITY (1 << 8) /* Disable Internal Parity Handling */ -#define PJ4B_BCK_OFF_STREX (1 << 5) /* Enable the back off of STREX instr */ #define PJ4B_CLEAN_LINE (1 << 16) /* Disable data transfer for clean line */ /* Auxiliary Debug Modes Control 2 Register */ @@ -234,7 +233,6 @@ __v7_pj4b_setup: /* Auxiliary Debug Modes Control 1 Register */ mrc p15, 1, r0, c15, c1, 1 orr r0, r0, #PJ4B_CLEAN_LINE - orr r0, r0, #PJ4B_BCK_OFF_STREX orr r0, r0, #PJ4B_INTER_PARITY bic r0, r0, #PJ4B_STATIC_BP mcr p15, 1, r0, c15, c1, 1 diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S index d19b1cfcad91..b34b95f45cb3 100644 --- a/arch/arm/mm/proc-xscale.S +++ b/arch/arm/mm/proc-xscale.S @@ -535,7 +535,7 @@ ENTRY(cpu_xscale_do_suspend) mrc p15, 0, r5, c15, c1, 0 @ CP access reg mrc p15, 0, r6, c13, c0, 0 @ PID mrc p15, 0, r7, c3, c0, 0 @ domain ID - mrc p15, 0, r8, c1, c1, 0 @ auxiliary control reg + mrc p15, 0, r8, c1, c0, 1 @ auxiliary control reg mrc p15, 0, r9, c1, c0, 0 @ control reg bic r4, r4, #2 @ clear frequency change bit stmia r0, {r4 - r9} @ store cp regs @@ -552,7 +552,7 @@ ENTRY(cpu_xscale_do_resume) mcr p15, 0, r6, c13, c0, 0 @ PID mcr p15, 0, r7, c3, c0, 0 @ domain ID mcr p15, 0, r1, c2, c0, 0 @ translation table base addr - mcr p15, 0, r8, c1, c1, 0 @ auxiliary control reg + mcr p15, 0, r8, c1, c0, 1 @ auxiliary control reg mov r0, r9 @ control register b cpu_resume_mmu ENDPROC(cpu_xscale_do_resume) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 43564fce31a8..40eb58df9377 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1,6 +1,7 @@ config ARM64 def_bool y select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE + select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_USE_CMPXCHG_LOCKREF select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST @@ -64,6 +65,7 @@ config ARM64 select RTC_LIB select SPARSE_IRQ select SYSCTL_EXCEPTION_TRACE + select HAVE_CONTEXT_TRACKING help ARM 64-bit (AArch64) Linux support. @@ -404,6 +406,20 @@ config CMDLINE_FORCE This is useful if you cannot or don't want to change the command-line options your boot loader passes to the kernel. +config EFI + bool "UEFI runtime support" + depends on OF && !CPU_BIG_ENDIAN + select LIBFDT + select UCS2_STRING + select EFI_PARAMS_FROM_FDT + default y + help + This option provides support for runtime services provided + by UEFI firmware (such as non-volatile variables, realtime + clock, and platform reset). A UEFI stub is also provided to + allow the kernel to be booted as an EFI application. This + is only useful on systems that have UEFI firmware. + endmenu menu "Userspace binary formats" @@ -453,6 +469,8 @@ source "net/Kconfig" source "drivers/Kconfig" +source "drivers/firmware/Kconfig" + source "fs/Kconfig" source "arch/arm64/kvm/Kconfig" diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h index 253e33bc94fb..56de5aadede2 100644 --- a/arch/arm64/include/asm/compat.h +++ b/arch/arm64/include/asm/compat.h @@ -37,8 +37,8 @@ typedef s32 compat_ssize_t; typedef s32 compat_time_t; typedef s32 compat_clock_t; typedef s32 compat_pid_t; -typedef u32 __compat_uid_t; -typedef u32 __compat_gid_t; +typedef u16 __compat_uid_t; +typedef u16 __compat_gid_t; typedef u16 __compat_uid16_t; typedef u16 __compat_gid16_t; typedef u32 __compat_uid32_t; diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 27f54a7cc81b..ad08bc71fad8 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -78,6 +78,8 @@ static inline u32 __attribute_const__ read_cpuid_cachetype(void) return read_cpuid(CTR_EL0); } +void cpuinfo_store_cpu(void); + #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h new file mode 100644 index 000000000000..5a46c4e7f539 --- /dev/null +++ b/arch/arm64/include/asm/efi.h @@ -0,0 +1,14 @@ +#ifndef _ASM_EFI_H +#define _ASM_EFI_H + +#include <asm/io.h> + +#ifdef CONFIG_EFI +extern void efi_init(void); +extern void efi_idmap_init(void); +#else +#define efi_init() +#define efi_idmap_init() +#endif + +#endif /* _ASM_EFI_H */ diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index c43b4ac13008..50f559f574fe 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -37,8 +37,21 @@ struct fpsimd_state { u32 fpcr; }; }; + /* the id of the last cpu to have restored this state */ + unsigned int cpu; }; +/* + * Struct for stacking the bottom 'n' FP/SIMD registers. + */ +struct fpsimd_partial_state { + u32 fpsr; + u32 fpcr; + u32 num_regs; + __uint128_t vregs[32]; +}; + + #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* Masks for extracting the FPSR and FPCR from the FPSCR */ #define VFP_FPSCR_STAT_MASK 0xf800009f @@ -58,6 +71,16 @@ extern void fpsimd_load_state(struct fpsimd_state *state); extern void fpsimd_thread_switch(struct task_struct *next); extern void fpsimd_flush_thread(void); +extern void fpsimd_preserve_current_state(void); +extern void fpsimd_restore_current_state(void); +extern void fpsimd_update_current_state(struct fpsimd_state *state); + +extern void fpsimd_flush_task_state(struct task_struct *target); + +extern void fpsimd_save_partial_state(struct fpsimd_partial_state *state, + u32 num_regs); +extern void fpsimd_load_partial_state(struct fpsimd_partial_state *state); + #endif #endif diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h index bbec599c96bd..768414d55e64 100644 --- a/arch/arm64/include/asm/fpsimdmacros.h +++ b/arch/arm64/include/asm/fpsimdmacros.h @@ -62,3 +62,38 @@ ldr w\tmpnr, [\state, #16 * 2 + 4] msr fpcr, x\tmpnr .endm + +.altmacro +.macro fpsimd_save_partial state, numnr, tmpnr1, tmpnr2 + mrs x\tmpnr1, fpsr + str w\numnr, [\state, #8] + mrs x\tmpnr2, fpcr + stp w\tmpnr1, w\tmpnr2, [\state] + adr x\tmpnr1, 0f + add \state, \state, x\numnr, lsl #4 + sub x\tmpnr1, x\tmpnr1, x\numnr, lsl #1 + br x\tmpnr1 + .irp qa, 30, 28, 26, 24, 22, 20, 18, 16, 14, 12, 10, 8, 6, 4, 2, 0 + .irp qb, %(qa + 1) + stp q\qa, q\qb, [\state, # -16 * \qa - 16] + .endr + .endr +0: +.endm + +.macro fpsimd_restore_partial state, tmpnr1, tmpnr2 + ldp w\tmpnr1, w\tmpnr2, [\state] + msr fpsr, x\tmpnr1 + msr fpcr, x\tmpnr2 + adr x\tmpnr1, 0f + ldr w\tmpnr2, [\state, #8] + add \state, \state, x\tmpnr2, lsl #4 + sub x\tmpnr1, x\tmpnr1, x\tmpnr2, lsl #1 + br x\tmpnr1 + .irp qa, 30, 28, 26, 24, 22, 20, 18, 16, 14, 12, 10, 8, 6, 4, 2, 0 + .irp qb, %(qa + 1) + ldp q\qa, q\qb, [\state, # -16 * \qa - 16] + .endr + .endr +0: +.endm diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h index ae4801d77514..0be67821f9ce 100644 --- a/arch/arm64/include/asm/hardirq.h +++ b/arch/arm64/include/asm/hardirq.h @@ -20,7 +20,7 @@ #include <linux/threads.h> #include <asm/irq.h> -#define NR_IPI 5 +#define NR_IPI 6 typedef struct { unsigned int __softirq_pending; diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h index d064047612b1..52b484b6aa1a 100644 --- a/arch/arm64/include/asm/hw_breakpoint.h +++ b/arch/arm64/include/asm/hw_breakpoint.h @@ -79,7 +79,6 @@ static inline void decode_ctrl_reg(u32 reg, */ #define ARM_MAX_BRP 16 #define ARM_MAX_WRP 16 -#define ARM_MAX_HBP_SLOTS (ARM_MAX_BRP + ARM_MAX_WRP) /* Virtual debug register bases. */ #define AARCH64_DBG_REG_BVR 0 diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index 024c46183c3c..0ad735166d9f 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -30,6 +30,7 @@ #define COMPAT_HWCAP_IDIVA (1 << 17) #define COMPAT_HWCAP_IDIVT (1 << 18) #define COMPAT_HWCAP_IDIV (COMPAT_HWCAP_IDIVA|COMPAT_HWCAP_IDIVT) +#define COMPAT_HWCAP_LPAE (1 << 20) #define COMPAT_HWCAP_EVTSTRM (1 << 21) #define COMPAT_HWCAP2_AES (1 << 0) diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index a9eee33dfa62..101a42bde728 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -151,6 +151,15 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next, { unsigned int cpu = smp_processor_id(); + /* + * init_mm.pgd does not contain any user mappings and it is always + * active for kernel addresses in TTBR1. Just set the reserved TTBR0. + */ + if (next == &init_mm) { + cpu_set_reserved_ttbr0(); + return; + } + if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next) check_and_switch_context(next, tsk); } diff --git a/arch/arm64/include/asm/neon.h b/arch/arm64/include/asm/neon.h index b0cc58a97780..13ce4cc18e26 100644 --- a/arch/arm64/include/asm/neon.h +++ b/arch/arm64/include/asm/neon.h @@ -8,7 +8,11 @@ * published by the Free Software Foundation. */ +#include <linux/types.h> + #define cpu_has_neon() (1) -void kernel_neon_begin(void); +#define kernel_neon_begin() kernel_neon_begin_partial(32) + +void kernel_neon_begin_partial(u32 num_regs); void kernel_neon_end(void); diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 33608f263ad0..e28747e15a36 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -271,7 +271,7 @@ static inline pmd_t pte_pmd(pte_t pte) #define pmd_page(pmd) pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK)) -#define set_pmd_at(mm, addr, pmdp, pmd) set_pmd(pmdp, pmd) +#define set_pmd_at(mm, addr, pmdp, pmd) set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd)) static inline int has_transparent_hugepage(void) { diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h index e9c149c042e0..456d67c1f0fa 100644 --- a/arch/arm64/include/asm/suspend.h +++ b/arch/arm64/include/asm/suspend.h @@ -21,6 +21,7 @@ struct sleep_save_sp { phys_addr_t save_ptr_stash_phys; }; +extern int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long)); extern void cpu_resume(void); extern int cpu_suspend(unsigned long); diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 0a8b2a97a32e..8da65c37193d 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -103,6 +103,8 @@ static inline struct thread_info *current_thread_info(void) #define TIF_SIGPENDING 0 #define TIF_NEED_RESCHED 1 #define TIF_NOTIFY_RESUME 2 /* callback before returning to user */ +#define TIF_FOREIGN_FPSTATE 3 /* CPU's FP state is not current's */ +#define TIF_NOHZ 7 #define TIF_SYSCALL_TRACE 8 #define TIF_SYSCALL_AUDIT 9 #define TIF_SYSCALL_TRACEPOINT 10 @@ -118,17 +120,20 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) +#define _TIF_NOHZ (1 << TIF_NOHZ) #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) +#define _TIF_FOREIGN_FPSTATE (1 << TIF_FOREIGN_FPSTATE) #define _TIF_32BIT (1 << TIF_32BIT) #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ - _TIF_NOTIFY_RESUME) + _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE) #define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ - _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP) + _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \ + _TIF_NOHZ) #endif /* __KERNEL__ */ #endif /* __ASM_THREAD_INFO_H */ diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 6ae85d55308b..376e18e79b9a 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -4,6 +4,8 @@ CPPFLAGS_vmlinux.lds := -DTEXT_OFFSET=$(TEXT_OFFSET) AFLAGS_head.o := -DTEXT_OFFSET=$(TEXT_OFFSET) +CFLAGS_efi-stub.o := -DTEXT_OFFSET=$(TEXT_OFFSET) \ + -I$(src)/../../../scripts/dtc/libfdt CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_insn.o = -pg @@ -28,6 +30,7 @@ arm64-obj-$(CONFIG_EARLY_PRINTK) += early_printk.o arm64-obj-$(CONFIG_ARM64_CPU_SUSPEND) += sleep.o suspend.o arm64-obj-$(CONFIG_JUMP_LABEL) += jump_label.o arm64-obj-$(CONFIG_KGDB) += kgdb.o +arm64-obj-$(CONFIG_EFI) += efi.o efi-stub.o efi-entry.o obj-y += $(arm64-obj-y) vdso/ obj-m += $(arm64-obj-m) diff --git a/arch/arm64/kernel/efi-entry.S b/arch/arm64/kernel/efi-entry.S new file mode 100644 index 000000000000..66716c9b9e5f --- /dev/null +++ b/arch/arm64/kernel/efi-entry.S @@ -0,0 +1,109 @@ +/* + * EFI entry point. + * + * Copyright (C) 2013, 2014 Red Hat, Inc. + * Author: Mark Salter <msalter@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ +#include <linux/linkage.h> +#include <linux/init.h> + +#include <asm/assembler.h> + +#define EFI_LOAD_ERROR 0x8000000000000001 + + __INIT + + /* + * We arrive here from the EFI boot manager with: + * + * * CPU in little-endian mode + * * MMU on with identity-mapped RAM + * * Icache and Dcache on + * + * We will most likely be running from some place other than where + * we want to be. The kernel image wants to be placed at TEXT_OFFSET + * from start of RAM. + */ +ENTRY(efi_stub_entry) + /* + * Create a stack frame to save FP/LR with extra space + * for image_addr variable passed to efi_entry(). + */ + stp x29, x30, [sp, #-32]! + + /* + * Call efi_entry to do the real work. + * x0 and x1 are already set up by firmware. Current runtime + * address of image is calculated and passed via *image_addr. + * + * unsigned long efi_entry(void *handle, + * efi_system_table_t *sys_table, + * unsigned long *image_addr) ; + */ + adrp x8, _text + add x8, x8, #:lo12:_text + add x2, sp, 16 + str x8, [x2] + bl efi_entry + cmn x0, #1 + b.eq efi_load_fail + + /* + * efi_entry() will have relocated the kernel image if necessary + * and we return here with device tree address in x0 and the kernel + * entry point stored at *image_addr. Save those values in registers + * which are callee preserved. + */ + mov x20, x0 // DTB address + ldr x0, [sp, #16] // relocated _text address + mov x21, x0 + + /* + * Flush dcache covering current runtime addresses + * of kernel text/data. Then flush all of icache. + */ + adrp x1, _text + add x1, x1, #:lo12:_text + adrp x2, _edata + add x2, x2, #:lo12:_edata + sub x1, x2, x1 + + bl __flush_dcache_area + ic ialluis + + /* Turn off Dcache and MMU */ + mrs x0, CurrentEL + cmp x0, #PSR_MODE_EL2t + ccmp x0, #PSR_MODE_EL2h, #0x4, ne + b.ne 1f + mrs x0, sctlr_el2 + bic x0, x0, #1 << 0 // clear SCTLR.M + bic x0, x0, #1 << 2 // clear SCTLR.C + msr sctlr_el2, x0 + isb + b 2f +1: + mrs x0, sctlr_el1 + bic x0, x0, #1 << 0 // clear SCTLR.M + bic x0, x0, #1 << 2 // clear SCTLR.C + msr sctlr_el1, x0 + isb +2: + /* Jump to kernel entry point */ + mov x0, x20 + mov x1, xzr + mov x2, xzr + mov x3, xzr + br x21 + +efi_load_fail: + mov x0, #EFI_LOAD_ERROR + ldp x29, x30, [sp], #32 + ret + +ENDPROC(efi_stub_entry) diff --git a/arch/arm64/kernel/efi-stub.c b/arch/arm64/kernel/efi-stub.c new file mode 100644 index 000000000000..e786e6cdc400 --- /dev/null +++ b/arch/arm64/kernel/efi-stub.c @@ -0,0 +1,79 @@ +/* + * Copyright (C) 2013, 2014 Linaro Ltd; <roy.franz@linaro.org> + * + * This file implements the EFI boot stub for the arm64 kernel. + * Adapted from ARM version by Mark Salter <msalter@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ +#include <linux/efi.h> +#include <linux/libfdt.h> +#include <asm/sections.h> + +/* + * AArch64 requires the DTB to be 8-byte aligned in the first 512MiB from + * start of kernel and may not cross a 2MiB boundary. We set alignment to + * 2MiB so we know it won't cross a 2MiB boundary. + */ +#define EFI_FDT_ALIGN SZ_2M /* used by allocate_new_fdt_and_exit_boot() */ +#define MAX_FDT_OFFSET SZ_512M + +#define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__) + +static void efi_char16_printk(efi_system_table_t *sys_table_arg, + efi_char16_t *str); + +static efi_status_t efi_open_volume(efi_system_table_t *sys_table, + void *__image, void **__fh); +static efi_status_t efi_file_close(void *handle); + +static efi_status_t +efi_file_read(void *handle, unsigned long *size, void *addr); + +static efi_status_t +efi_file_size(efi_system_table_t *sys_table, void *__fh, + efi_char16_t *filename_16, void **handle, u64 *file_sz); + +/* Include shared EFI stub code */ +#include "../../../drivers/firmware/efi/efi-stub-helper.c" +#include "../../../drivers/firmware/efi/fdt.c" +#include "../../../drivers/firmware/efi/arm-stub.c" + + +static efi_status_t handle_kernel_image(efi_system_table_t *sys_table, + unsigned long *image_addr, + unsigned long *image_size, + unsigned long *reserve_addr, + unsigned long *reserve_size, + unsigned long dram_base, + efi_loaded_image_t *image) +{ + efi_status_t status; + unsigned long kernel_size, kernel_memsize = 0; + + /* Relocate the image, if required. */ + kernel_size = _edata - _text; + if (*image_addr != (dram_base + TEXT_OFFSET)) { + kernel_memsize = kernel_size + (_end - _edata); + status = efi_relocate_kernel(sys_table, image_addr, + kernel_size, kernel_memsize, + dram_base + TEXT_OFFSET, + PAGE_SIZE); + if (status != EFI_SUCCESS) { + pr_efi_err(sys_table, "Failed to relocate kernel\n"); + return status; + } + if (*image_addr != (dram_base + TEXT_OFFSET)) { + pr_efi_err(sys_table, "Failed to alloc kernel memory\n"); + efi_free(sys_table, kernel_memsize, *image_addr); + return EFI_ERROR; + } + *image_size = kernel_memsize; + } + + + return EFI_SUCCESS; +} diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c new file mode 100644 index 000000000000..14db1f6e8d7f --- /dev/null +++ b/arch/arm64/kernel/efi.c @@ -0,0 +1,469 @@ +/* + * Extensible Firmware Interface + * + * Based on Extensible Firmware Interface Specification version 2.4 + * + * Copyright (C) 2013, 2014 Linaro Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include <linux/efi.h> +#include <linux/export.h> +#include <linux/memblock.h> +#include <linux/bootmem.h> +#include <linux/of.h> +#include <linux/of_fdt.h> +#include <linux/sched.h> +#include <linux/slab.h> + +#include <asm/cacheflush.h> +#include <asm/efi.h> +#include <asm/tlbflush.h> +#include <asm/mmu_context.h> + +struct efi_memory_map memmap; + +static efi_runtime_services_t *runtime; + +static u64 efi_system_table; + +static int uefi_debug __initdata; +static int __init uefi_debug_setup(char *str) +{ + uefi_debug = 1; + + return 0; +} +early_param("uefi_debug", uefi_debug_setup); + +static int __init is_normal_ram(efi_memory_desc_t *md) +{ + if (md->attribute & EFI_MEMORY_WB) + return 1; + return 0; +} + +static void __init efi_setup_idmap(void) +{ + struct memblock_region *r; + efi_memory_desc_t *md; + u64 paddr, npages, size; + + for_each_memblock(memory, r) + create_id_mapping(r->base, r->size, 0); + + /* map runtime io spaces */ + for_each_efi_memory_desc(&memmap, md) { + if (!(md->attribute & EFI_MEMORY_RUNTIME) || is_normal_ram(md)) + continue; + paddr = md->phys_addr; + npages = md->num_pages; + memrange_efi_to_native(&paddr, &npages); + size = npages << PAGE_SHIFT; + create_id_mapping(paddr, size, 1); + } +} + +static int __init uefi_init(void) +{ + efi_char16_t *c16; + char vendor[100] = "unknown"; + int i, retval; + + efi.systab = early_memremap(efi_system_table, + sizeof(efi_system_table_t)); + if (efi.systab == NULL) { + pr_warn("Unable to map EFI system table.\n"); + return -ENOMEM; + } + + set_bit(EFI_BOOT, &efi.flags); + set_bit(EFI_64BIT, &efi.flags); + + /* + * Verify the EFI Table + */ + if (efi.systab->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) { + pr_err("System table signature incorrect\n"); + return -EINVAL; + } + if ((efi.systab->hdr.revision >> 16) < 2) + pr_warn("Warning: EFI system table version %d.%02d, expected 2.00 or greater\n", + efi.systab->hdr.revision >> 16, + efi.systab->hdr.revision & 0xffff); + + /* Show what we know for posterity */ + c16 = early_memremap(efi.systab->fw_vendor, + sizeof(vendor)); + if (c16) { + for (i = 0; i < (int) sizeof(vendor) - 1 && *c16; ++i) + vendor[i] = c16[i]; + vendor[i] = '\0'; + } + + pr_info("EFI v%u.%.02u by %s\n", + efi.systab->hdr.revision >> 16, + efi.systab->hdr.revision & 0xffff, vendor); + + retval = efi_config_init(NULL); + if (retval == 0) + set_bit(EFI_CONFIG_TABLES, &efi.flags); + + early_memunmap(c16, sizeof(vendor)); + early_memunmap(efi.systab, sizeof(efi_system_table_t)); + + return retval; +} + +static __initdata char memory_type_name[][32] = { + {"Reserved"}, + {"Loader Code"}, + {"Loader Data"}, + {"Boot Code"}, + {"Boot Data"}, + {"Runtime Code"}, + {"Runtime Data"}, + {"Conventional Memory"}, + {"Unusable Memory"}, + {"ACPI Reclaim Memory"}, + {"ACPI Memory NVS"}, + {"Memory Mapped I/O"}, + {"MMIO Port Space"}, + {"PAL Code"}, +}; + +/* + * Return true for RAM regions we want to permanently reserve. + */ +static __init int is_reserve_region(efi_memory_desc_t *md) +{ + if (!is_normal_ram(md)) + return 0; + + if (md->attribute & EFI_MEMORY_RUNTIME) + return 1; + + if (md->type == EFI_ACPI_RECLAIM_MEMORY || + md->type == EFI_RESERVED_TYPE) + return 1; + + return 0; +} + +static __init void reserve_regions(void) +{ + efi_memory_desc_t *md; + u64 paddr, npages, size; + + if (uefi_debug) + pr_info("Processing EFI memory map:\n"); + + for_each_efi_memory_desc(&memmap, md) { + paddr = md->phys_addr; + npages = md->num_pages; + + if (uefi_debug) + pr_info(" 0x%012llx-0x%012llx [%s]", + paddr, paddr + (npages << EFI_PAGE_SHIFT) - 1, + memory_type_name[md->type]); + + memrange_efi_to_native(&paddr, &npages); + size = npages << PAGE_SHIFT; + + if (is_normal_ram(md)) + early_init_dt_add_memory_arch(paddr, size); + + if (is_reserve_region(md) || + md->type == EFI_BOOT_SERVICES_CODE || + md->type == EFI_BOOT_SERVICES_DATA) { + memblock_reserve(paddr, size); + if (uefi_debug) + pr_cont("*"); + } + + if (uefi_debug) + pr_cont("\n"); + } +} + + +static u64 __init free_one_region(u64 start, u64 end) +{ + u64 size = end - start; + + if (uefi_debug) + pr_info(" EFI freeing: 0x%012llx-0x%012llx\n", start, end - 1); + + free_bootmem_late(start, size); + return size; +} + +static u64 __init free_region(u64 start, u64 end) +{ + u64 map_start, map_end, total = 0; + + if (end <= start) + return total; + + map_start = (u64)memmap.phys_map; + map_end = PAGE_ALIGN(map_start + (memmap.map_end - memmap.map)); + map_start &= PAGE_MASK; + + if (start < map_end && end > map_start) { + /* region overlaps UEFI memmap */ + if (start < map_start) + total += free_one_region(start, map_start); + + if (map_end < end) + total += free_one_region(map_end, end); + } else + total += free_one_region(start, end); + + return total; +} + +static void __init free_boot_services(void) +{ + u64 total_freed = 0; + u64 keep_end, free_start, free_end; + efi_memory_desc_t *md; + + /* + * If kernel uses larger pages than UEFI, we have to be careful + * not to inadvertantly free memory we want to keep if there is + * overlap at the kernel page size alignment. We do not want to + * free is_reserve_region() memory nor the UEFI memmap itself. + * + * The memory map is sorted, so we keep track of the end of + * any previous region we want to keep, remember any region + * we want to free and defer freeing it until we encounter + * the next region we want to keep. This way, before freeing + * it, we can clip it as needed to avoid freeing memory we + * want to keep for UEFI. + */ + + keep_end = 0; + free_start = 0; + + for_each_efi_memory_desc(&memmap, md) { + u64 paddr, npages, size; + + if (is_reserve_region(md)) { + /* + * We don't want to free any memory from this region. + */ + if (free_start) { + /* adjust free_end then free region */ + if (free_end > md->phys_addr) + free_end -= PAGE_SIZE; + total_freed += free_region(free_start, free_end); + free_start = 0; + } + keep_end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT); + continue; + } + + if (md->type != EFI_BOOT_SERVICES_CODE && + md->type != EFI_BOOT_SERVICES_DATA) { + /* no need to free this region */ + continue; + } + + /* + * We want to free memory from this region. + */ + paddr = md->phys_addr; + npages = md->num_pages; + memrange_efi_to_native(&paddr, &npages); + size = npages << PAGE_SHIFT; + + if (free_start) { + if (paddr <= free_end) + free_end = paddr + size; + else { + total_freed += free_region(free_start, free_end); + free_start = paddr; + free_end = paddr + size; + } + } else { + free_start = paddr; + free_end = paddr + size; + } + if (free_start < keep_end) { + free_start += PAGE_SIZE; + if (free_start >= free_end) + free_start = 0; + } + } + if (free_start) + total_freed += free_region(free_start, free_end); + + if (total_freed) + pr_info("Freed 0x%llx bytes of EFI boot services memory", + total_freed); +} + +void __init efi_init(void) +{ + struct efi_fdt_params params; + + /* Grab UEFI information placed in FDT by stub */ + if (!efi_get_fdt_params(¶ms, uefi_debug)) + return; + + efi_system_table = params.system_table; + + memblock_reserve(params.mmap & PAGE_MASK, + PAGE_ALIGN(params.mmap_size + (params.mmap & ~PAGE_MASK))); + memmap.phys_map = (void *)params.mmap; + memmap.map = early_memremap(params.mmap, params.mmap_size); + memmap.map_end = memmap.map + params.mmap_size; + memmap.desc_size = params.desc_size; + memmap.desc_version = params.desc_ver; + + if (uefi_init() < 0) + return; + + reserve_regions(); +} + +void __init efi_idmap_init(void) +{ + if (!efi_enabled(EFI_BOOT)) + return; + + /* boot time idmap_pg_dir is incomplete, so fill in missing parts */ + efi_setup_idmap(); +} + +static int __init remap_region(efi_memory_desc_t *md, void **new) +{ + u64 paddr, vaddr, npages, size; + + paddr = md->phys_addr; + npages = md->num_pages; + memrange_efi_to_native(&paddr, &npages); + size = npages << PAGE_SHIFT; + + if (is_normal_ram(md)) + vaddr = (__force u64)ioremap_cache(paddr, size); + else + vaddr = (__force u64)ioremap(paddr, size); + + if (!vaddr) { + pr_err("Unable to remap 0x%llx pages @ %p\n", + npages, (void *)paddr); + return 0; + } + + /* adjust for any rounding when EFI and system pagesize differs */ + md->virt_addr = vaddr + (md->phys_addr - paddr); + + if (uefi_debug) + pr_info(" EFI remap 0x%012llx => %p\n", + md->phys_addr, (void *)md->virt_addr); + + memcpy(*new, md, memmap.desc_size); + *new += memmap.desc_size; + + return 1; +} + +/* + * Switch UEFI from an identity map to a kernel virtual map + */ +static int __init arm64_enter_virtual_mode(void) +{ + efi_memory_desc_t *md; + phys_addr_t virtmap_phys; + void *virtmap, *virt_md; + efi_status_t status; + u64 mapsize; + int count = 0; + unsigned long flags; + + if (!efi_enabled(EFI_BOOT)) { + pr_info("EFI services will not be available.\n"); + return -1; + } + + pr_info("Remapping and enabling EFI services.\n"); + + /* replace early memmap mapping with permanent mapping */ + mapsize = memmap.map_end - memmap.map; + early_memunmap(memmap.map, mapsize); + memmap.map = (__force void *)ioremap_cache((phys_addr_t)memmap.phys_map, + mapsize); + memmap.map_end = memmap.map + mapsize; + + efi.memmap = &memmap; + + /* Map the runtime regions */ + virtmap = kmalloc(mapsize, GFP_KERNEL); + if (!virtmap) { + pr_err("Failed to allocate EFI virtual memmap\n"); + return -1; + } + virtmap_phys = virt_to_phys(virtmap); + virt_md = virtmap; + + for_each_efi_memory_desc(&memmap, md) { + if (!(md->attribute & EFI_MEMORY_RUNTIME)) + continue; + if (remap_region(md, &virt_md)) + ++count; + } + + efi.systab = (__force void *)efi_lookup_mapped_addr(efi_system_table); + if (efi.systab) + set_bit(EFI_SYSTEM_TABLES, &efi.flags); + + local_irq_save(flags); + cpu_switch_mm(idmap_pg_dir, &init_mm); + + /* Call SetVirtualAddressMap with the physical address of the map */ + runtime = efi.systab->runtime; + efi.set_virtual_address_map = runtime->set_virtual_address_map; + + status = efi.set_virtual_address_map(count * memmap.desc_size, + memmap.desc_size, + memmap.desc_version, + (efi_memory_desc_t *)virtmap_phys); + cpu_set_reserved_ttbr0(); + flush_tlb_all(); + local_irq_restore(flags); + + kfree(virtmap); + + free_boot_services(); + + if (status != EFI_SUCCESS) { + pr_err("Failed to set EFI virtual address map! [%lx]\n", + status); + return -1; + } + + /* Set up runtime services function pointers */ + runtime = efi.systab->runtime; + efi.get_time = runtime->get_time; + efi.set_time = runtime->set_time; + efi.get_wakeup_time = runtime->get_wakeup_time; + efi.set_wakeup_time = runtime->set_wakeup_time; + efi.get_variable = runtime->get_variable; + efi.get_next_variable = runtime->get_next_variable; + efi.set_variable = runtime->set_variable; + efi.query_variable_info = runtime->query_variable_info; + efi.update_capsule = runtime->update_capsule; + efi.query_capsule_caps = runtime->query_capsule_caps; + efi.get_next_high_mono_count = runtime->get_next_high_mono_count; + efi.reset_system = runtime->reset_system; + + set_bit(EFI_RUNTIME_SERVICES, &efi.flags); + + return 0; +} +early_initcall(arm64_enter_virtual_mode); diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S index 6a27cd6dbfa6..d358ccacfc00 100644 --- a/arch/arm64/kernel/entry-fpsimd.S +++ b/arch/arm64/kernel/entry-fpsimd.S @@ -41,3 +41,27 @@ ENTRY(fpsimd_load_state) fpsimd_restore x0, 8 ret ENDPROC(fpsimd_load_state) + +#ifdef CONFIG_KERNEL_MODE_NEON + +/* + * Save the bottom n FP registers. + * + * x0 - pointer to struct fpsimd_partial_state + */ +ENTRY(fpsimd_save_partial_state) + fpsimd_save_partial x0, 1, 8, 9 + ret +ENDPROC(fpsimd_load_partial_state) + +/* + * Load the bottom n FP registers. + * + * x0 - pointer to struct fpsimd_partial_state + */ +ENTRY(fpsimd_load_partial_state) + fpsimd_restore_partial x0, 8, 9 + ret +ENDPROC(fpsimd_load_partial_state) + +#endif diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 6d26ebc260ad..a010e3af4597 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -30,6 +30,32 @@ #include <asm/unistd32.h> /* + * Context tracking subsystem. Used to instrument transitions + * between user and kernel mode. + */ + .macro ct_user_exit, syscall = 0 +#ifdef CONFIG_CONTEXT_TRACKING + bl context_tracking_user_exit + .if \syscall == 1 + /* + * Save/restore needed during syscalls. Restore syscall arguments from + * the values already saved on stack during kernel_entry. + */ + ldp x0, x1, [sp] + ldp x2, x3, [sp, #S_X2] + ldp x4, x5, [sp, #S_X4] + ldp x6, x7, [sp, #S_X6] + .endif +#endif + .endm + + .macro ct_user_enter +#ifdef CONFIG_CONTEXT_TRACKING + bl context_tracking_user_enter +#endif + .endm + +/* * Bad Abort numbers *----------------- */ @@ -88,6 +114,7 @@ .macro kernel_exit, el, ret = 0 ldp x21, x22, [sp, #S_PC] // load ELR, SPSR .if \el == 0 + ct_user_enter ldr x23, [sp, #S_SP] // load return stack pointer .endif .if \ret @@ -348,7 +375,6 @@ el0_sync: lsr x24, x25, #ESR_EL1_EC_SHIFT // exception class cmp x24, #ESR_EL1_EC_SVC64 // SVC in 64-bit state b.eq el0_svc - adr lr, ret_from_exception cmp x24, #ESR_EL1_EC_DABT_EL0 // data abort in EL0 b.eq el0_da cmp x24, #ESR_EL1_EC_IABT_EL0 // instruction abort in EL0 @@ -377,7 +403,6 @@ el0_sync_compat: lsr x24, x25, #ESR_EL1_EC_SHIFT // exception class cmp x24, #ESR_EL1_EC_SVC32 // SVC in 32-bit state b.eq el0_svc_compat - adr lr, ret_from_exception cmp x24, #ESR_EL1_EC_DABT_EL0 // data abort in EL0 b.eq el0_da cmp x24, #ESR_EL1_EC_IABT_EL0 // instruction abort in EL0 @@ -420,78 +445,94 @@ el0_da: /* * Data abort handling */ - mrs x0, far_el1 - bic x0, x0, #(0xff << 56) + mrs x26, far_el1 disable_step x1 isb enable_dbg // enable interrupts before calling the main handler enable_irq + ct_user_exit + bic x0, x26, #(0xff << 56) mov x1, x25 mov x2, sp + adr lr, ret_from_exception b do_mem_abort el0_ia: /* * Instruction abort handling */ - mrs x0, far_el1 + mrs x26, far_el1 disable_step x1 isb enable_dbg // enable interrupts before calling the main handler enable_irq + ct_user_exit + mov x0, x26 orr x1, x25, #1 << 24 // use reserved ISS bit for instruction aborts mov x2, sp + adr lr, ret_from_exception b do_mem_abort el0_fpsimd_acc: /* * Floating Point or Advanced SIMD access */ + ct_user_exit mov x0, x25 mov x1, sp + adr lr, ret_from_exception b do_fpsimd_acc el0_fpsimd_exc: /* * Floating Point or Advanced SIMD exception */ + ct_user_exit mov x0, x25 mov x1, sp + adr lr, ret_from_exception b do_fpsimd_exc el0_sp_pc: /* * Stack or PC alignment exception handling */ - mrs x0, far_el1 + mrs x26, far_el1 disable_step x1 isb enable_dbg // enable interrupts before calling the main handler enable_irq + mov x0, x26 mov x1, x25 mov x2, sp + adr lr, ret_from_exception b do_sp_pc_abort el0_undef: /* * Undefined instruction */ - mov x0, sp // enable interrupts before calling the main handler + ct_user_exit enable_irq + mov x0, sp + adr lr, ret_from_exception b do_undefinstr el0_dbg: /* * Debug exception handling */ tbnz x24, #0, el0_inv // EL0 only + ct_user_exit mrs x0, far_el1 disable_step x1 mov x1, x25 mov x2, sp b do_debug_exception el0_inv: + ct_user_exit mov x0, sp mov x1, #BAD_SYNC mrs x2, esr_el1 + adr lr, ret_from_exception b bad_mode ENDPROC(el0_sync) @@ -506,6 +547,7 @@ el0_irq_naked: bl trace_hardirqs_off #endif + ct_user_exit irq_handler get_thread_info tsk @@ -575,7 +617,7 @@ fast_work_pending: str x0, [sp, #S_X0] // returned x0 work_pending: tbnz x1, #TIF_NEED_RESCHED, work_resched - /* TIF_SIGPENDING or TIF_NOTIFY_RESUME case */ + /* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */ ldr x2, [sp, #S_PSTATE] mov x0, sp // 'regs' tst x2, #PSR_MODE_MASK // user mode regs? @@ -628,6 +670,7 @@ el0_svc_naked: // compat entry point isb enable_dbg enable_irq + ct_user_exit 1 get_thread_info tsk ldr x16, [tsk, #TI_FLAGS] // check for syscall hooks diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 4aef42a04bdc..ad8aebb1cdef 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -35,6 +35,60 @@ #define FPEXC_IDF (1 << 7) /* + * In order to reduce the number of times the FPSIMD state is needlessly saved + * and restored, we need to keep track of two things: + * (a) for each task, we need to remember which CPU was the last one to have + * the task's FPSIMD state loaded into its FPSIMD registers; + * (b) for each CPU, we need to remember which task's userland FPSIMD state has + * been loaded into its FPSIMD registers most recently, or whether it has + * been used to perform kernel mode NEON in the meantime. + * + * For (a), we add a 'cpu' field to struct fpsimd_state, which gets updated to + * the id of the current CPU everytime the state is loaded onto a CPU. For (b), + * we add the per-cpu variable 'fpsimd_last_state' (below), which contains the + * address of the userland FPSIMD state of the task that was loaded onto the CPU + * the most recently, or NULL if kernel mode NEON has been performed after that. + * + * With this in place, we no longer have to restore the next FPSIMD state right + * when switching between tasks. Instead, we can defer this check to userland + * resume, at which time we verify whether the CPU's fpsimd_last_state and the + * task's fpsimd_state.cpu are still mutually in sync. If this is the case, we + * can omit the FPSIMD restore. + * + * As an optimization, we use the thread_info flag TIF_FOREIGN_FPSTATE to + * indicate whether or not the userland FPSIMD state of the current task is + * present in the registers. The flag is set unless the FPSIMD registers of this + * CPU currently contain the most recent userland FPSIMD state of the current + * task. + * + * For a certain task, the sequence may look something like this: + * - the task gets scheduled in; if both the task's fpsimd_state.cpu field + * contains the id of the current CPU, and the CPU's fpsimd_last_state per-cpu + * variable points to the task's fpsimd_state, the TIF_FOREIGN_FPSTATE flag is + * cleared, otherwise it is set; + * + * - the task returns to userland; if TIF_FOREIGN_FPSTATE is set, the task's + * userland FPSIMD state is copied from memory to the registers, the task's + * fpsimd_state.cpu field is set to the id of the current CPU, the current + * CPU's fpsimd_last_state pointer is set to this task's fpsimd_state and the + * TIF_FOREIGN_FPSTATE flag is cleared; + * + * - the task executes an ordinary syscall; upon return to userland, the + * TIF_FOREIGN_FPSTATE flag will still be cleared, so no FPSIMD state is + * restored; + * + * - the task executes a syscall which executes some NEON instructions; this is + * preceded by a call to kernel_neon_begin(), which copies the task's FPSIMD + * register contents to memory, clears the fpsimd_last_state per-cpu variable + * and sets the TIF_FOREIGN_FPSTATE flag; + * + * - the task gets preempted after kernel_neon_end() is called; as we have not + * returned from the 2nd syscall yet, TIF_FOREIGN_FPSTATE is still set so + * whatever is in the FPSIMD registers is not saved to memory, but discarded. + */ +static DEFINE_PER_CPU(struct fpsimd_state *, fpsimd_last_state); + +/* * Trapped FP/ASIMD access. */ void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs) @@ -72,43 +126,137 @@ void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs) void fpsimd_thread_switch(struct task_struct *next) { - /* check if not kernel threads */ - if (current->mm) + /* + * Save the current FPSIMD state to memory, but only if whatever is in + * the registers is in fact the most recent userland FPSIMD state of + * 'current'. + */ + if (current->mm && !test_thread_flag(TIF_FOREIGN_FPSTATE)) fpsimd_save_state(¤t->thread.fpsimd_state); - if (next->mm) - fpsimd_load_state(&next->thread.fpsimd_state); + + if (next->mm) { + /* + * If we are switching to a task whose most recent userland + * FPSIMD state is already in the registers of *this* cpu, + * we can skip loading the state from memory. Otherwise, set + * the TIF_FOREIGN_FPSTATE flag so the state will be loaded + * upon the next return to userland. + */ + struct fpsimd_state *st = &next->thread.fpsimd_state; + + if (__this_cpu_read(fpsimd_last_state) == st + && st->cpu == smp_processor_id()) + clear_ti_thread_flag(task_thread_info(next), + TIF_FOREIGN_FPSTATE); + else + set_ti_thread_flag(task_thread_info(next), + TIF_FOREIGN_FPSTATE); + } } void fpsimd_flush_thread(void) { - preempt_disable(); memset(¤t->thread.fpsimd_state, 0, sizeof(struct fpsimd_state)); - fpsimd_load_state(¤t->thread.fpsimd_state); + set_thread_flag(TIF_FOREIGN_FPSTATE); +} + +/* + * Save the userland FPSIMD state of 'current' to memory, but only if the state + * currently held in the registers does in fact belong to 'current' + */ +void fpsimd_preserve_current_state(void) +{ + preempt_disable(); + if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) + fpsimd_save_state(¤t->thread.fpsimd_state); + preempt_enable(); +} + +/* + * Load the userland FPSIMD state of 'current' from memory, but only if the + * FPSIMD state already held in the registers is /not/ the most recent FPSIMD + * state of 'current' + */ +void fpsimd_restore_current_state(void) +{ + preempt_disable(); + if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) { + struct fpsimd_state *st = ¤t->thread.fpsimd_state; + + fpsimd_load_state(st); + this_cpu_write(fpsimd_last_state, st); + st->cpu = smp_processor_id(); + } + preempt_enable(); +} + +/* + * Load an updated userland FPSIMD state for 'current' from memory and set the + * flag that indicates that the FPSIMD register contents are the most recent + * FPSIMD state of 'current' + */ +void fpsimd_update_current_state(struct fpsimd_state *state) +{ + preempt_disable(); + fpsimd_load_state(state); + if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) { + struct fpsimd_state *st = ¤t->thread.fpsimd_state; + + this_cpu_write(fpsimd_last_state, st); + st->cpu = smp_processor_id(); + } preempt_enable(); } +/* + * Invalidate live CPU copies of task t's FPSIMD state + */ +void fpsimd_flush_task_state(struct task_struct *t) +{ + t->thread.fpsimd_state.cpu = NR_CPUS; +} + #ifdef CONFIG_KERNEL_MODE_NEON +static DEFINE_PER_CPU(struct fpsimd_partial_state, hardirq_fpsimdstate); +static DEFINE_PER_CPU(struct fpsimd_partial_state, softirq_fpsimdstate); + /* * Kernel-side NEON support functions */ -void kernel_neon_begin(void) +void kernel_neon_begin_partial(u32 num_regs) { - /* Avoid using the NEON in interrupt context */ - BUG_ON(in_interrupt()); - preempt_disable(); + if (in_interrupt()) { + struct fpsimd_partial_state *s = this_cpu_ptr( + in_irq() ? &hardirq_fpsimdstate : &softirq_fpsimdstate); - if (current->mm) - fpsimd_save_state(¤t->thread.fpsimd_state); + BUG_ON(num_regs > 32); + fpsimd_save_partial_state(s, roundup(num_regs, 2)); + } else { + /* + * Save the userland FPSIMD state if we have one and if we + * haven't done so already. Clear fpsimd_last_state to indicate + * that there is no longer userland FPSIMD state in the + * registers. + */ + preempt_disable(); + if (current->mm && + !test_and_set_thread_flag(TIF_FOREIGN_FPSTATE)) + fpsimd_save_state(¤t->thread.fpsimd_state); + this_cpu_write(fpsimd_last_state, NULL); + } } -EXPORT_SYMBOL(kernel_neon_begin); +EXPORT_SYMBOL(kernel_neon_begin_partial); void kernel_neon_end(void) { - if (current->mm) - fpsimd_load_state(¤t->thread.fpsimd_state); - - preempt_enable(); + if (in_interrupt()) { + struct fpsimd_partial_state *s = this_cpu_ptr( + in_irq() ? &hardirq_fpsimdstate : &softirq_fpsimdstate); + fpsimd_load_partial_state(s); + } else { + preempt_enable(); + } } EXPORT_SYMBOL(kernel_neon_end); @@ -120,12 +268,12 @@ static int fpsimd_cpu_pm_notifier(struct notifier_block *self, { switch (cmd) { case CPU_PM_ENTER: - if (current->mm) + if (current->mm && !test_thread_flag(TIF_FOREIGN_FPSTATE)) fpsimd_save_state(¤t->thread.fpsimd_state); break; case CPU_PM_EXIT: if (current->mm) - fpsimd_load_state(¤t->thread.fpsimd_state); + set_thread_flag(TIF_FOREIGN_FPSTATE); break; case CPU_PM_ENTER_FAILED: default: diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 650ec9ea42fd..e28eaef0568f 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -97,8 +97,18 @@ /* * DO NOT MODIFY. Image header expected by Linux boot-loaders. */ +#ifdef CONFIG_EFI +efi_head: + /* + * This add instruction has no meaningful effect except that + * its opcode forms the magic "MZ" signature required by UEFI. + */ + add x13, x18, #0x16 + b stext +#else b stext // branch to kernel start, magic .long 0 // reserved +#endif .quad TEXT_OFFSET // Image load offset from start of RAM .quad 0 // reserved .quad 0 // reserved @@ -109,7 +119,109 @@ .byte 0x52 .byte 0x4d .byte 0x64 +#ifdef CONFIG_EFI + .long pe_header - efi_head // Offset to the PE header. +#else .word 0 // reserved +#endif + +#ifdef CONFIG_EFI + .align 3 +pe_header: + .ascii "PE" + .short 0 +coff_header: + .short 0xaa64 // AArch64 + .short 2 // nr_sections + .long 0 // TimeDateStamp + .long 0 // PointerToSymbolTable + .long 1 // NumberOfSymbols + .short section_table - optional_header // SizeOfOptionalHeader + .short 0x206 // Characteristics. + // IMAGE_FILE_DEBUG_STRIPPED | + // IMAGE_FILE_EXECUTABLE_IMAGE | + // IMAGE_FILE_LINE_NUMS_STRIPPED +optional_header: + .short 0x20b // PE32+ format + .byte 0x02 // MajorLinkerVersion + .byte 0x14 // MinorLinkerVersion + .long _edata - stext // SizeOfCode + .long 0 // SizeOfInitializedData + .long 0 // SizeOfUninitializedData + .long efi_stub_entry - efi_head // AddressOfEntryPoint + .long stext - efi_head // BaseOfCode + +extra_header_fields: + .quad 0 // ImageBase + .long 0x20 // SectionAlignment + .long 0x8 // FileAlignment + .short 0 // MajorOperatingSystemVersion + .short 0 // MinorOperatingSystemVersion + .short 0 // MajorImageVersion + .short 0 // MinorImageVersion + .short 0 // MajorSubsystemVersion + .short 0 // MinorSubsystemVersion + .long 0 // Win32VersionValue + + .long _edata - efi_head // SizeOfImage + + // Everything before the kernel image is considered part of the header + .long stext - efi_head // SizeOfHeaders + .long 0 // CheckSum + .short 0xa // Subsystem (EFI application) + .short 0 // DllCharacteristics + .quad 0 // SizeOfStackReserve + .quad 0 // SizeOfStackCommit + .quad 0 // SizeOfHeapReserve + .quad 0 // SizeOfHeapCommit + .long 0 // LoaderFlags + .long 0x6 // NumberOfRvaAndSizes + + .quad 0 // ExportTable + .quad 0 // ImportTable + .quad 0 // ResourceTable + .quad 0 // ExceptionTable + .quad 0 // CertificationTable + .quad 0 // BaseRelocationTable + + // Section table +section_table: + + /* + * The EFI application loader requires a relocation section + * because EFI applications must be relocatable. This is a + * dummy section as far as we are concerned. + */ + .ascii ".reloc" + .byte 0 + .byte 0 // end of 0 padding of section name + .long 0 + .long 0 + .long 0 // SizeOfRawData + .long 0 // PointerToRawData + .long 0 // PointerToRelocations + .long 0 // PointerToLineNumbers + .short 0 // NumberOfRelocations + .short 0 // NumberOfLineNumbers + .long 0x42100040 // Characteristics (section flags) + + + .ascii ".text" + .byte 0 + .byte 0 + .byte 0 // end of 0 padding of section name + .long _edata - stext // VirtualSize + .long stext - efi_head // VirtualAddress + .long _edata - stext // SizeOfRawData + .long stext - efi_head // PointerToRawData + + .long 0 // PointerToRelocations (0 for executables) + .long 0 // PointerToLineNumbers (0 for executables) + .short 0 // NumberOfRelocations (0 for executables) + .short 0 // NumberOfLineNumbers (0 for executables) + .long 0xe0500020 // Characteristics (section flags) + .align 5 +#endif ENTRY(stext) mov x21, x0 // x21=FDT diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index 92f36835486b..565e26f23f31 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -156,9 +156,10 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg) * which ends with "dsb; isb" pair guaranteeing global * visibility. */ - atomic_set(&pp->cpu_count, -1); + /* Notify other processors with an additional increment. */ + atomic_inc(&pp->cpu_count); } else { - while (atomic_read(&pp->cpu_count) != -1) + while (atomic_read(&pp->cpu_count) <= num_online_cpus()) cpu_relax(); isb(); } diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index 0f08dfd69ebc..dfa6e3e74fdd 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -97,19 +97,15 @@ static bool migrate_one_irq(struct irq_desc *desc) if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity)) return false; - if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) + if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { + affinity = cpu_online_mask; ret = true; + } - /* - * when using forced irq_set_affinity we must ensure that the cpu - * being offlined is not present in the affinity mask, it may be - * selected as the target CPU otherwise - */ - affinity = cpu_online_mask; c = irq_data_get_irq_chip(d); if (!c->irq_set_affinity) pr_debug("IRQ%u: unable to set affinity\n", d->irq); - else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret) + else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret) cpumask_copy(d->affinity, affinity); return ret; diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 0e9ce28145d9..6601cda23170 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -188,9 +188,27 @@ void exit_thread(void) { } +static void tls_thread_flush(void) +{ + asm ("msr tpidr_el0, xzr"); + + if (is_compat_task()) { + current->thread.tp_value = 0; + + /* + * We need to ensure ordering between the shadow state and the + * hardware state, so that we don't corrupt the hardware state + * with a stale shadow state during context switch. + */ + barrier(); + asm ("msr tpidrro_el0, xzr"); + } +} + void flush_thread(void) { fpsimd_flush_thread(); + tls_thread_flush(); flush_ptrace_hw_breakpoint(current); } @@ -200,7 +218,7 @@ void release_thread(struct task_struct *dead_task) int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { - fpsimd_save_state(¤t->thread.fpsimd_state); + fpsimd_preserve_current_state(); *dst = *src; return 0; } diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 7c8e809bdbde..167c5edecad4 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -85,7 +85,8 @@ static void ptrace_hbptriggered(struct perf_event *bp, break; } } - for (i = ARM_MAX_BRP; i < ARM_MAX_HBP_SLOTS && !bp; ++i) { + + for (i = 0; i < ARM_MAX_WRP; ++i) { if (current->thread.debug.hbp_watch[i] == bp) { info.si_errno = -((i << 1) + 1); break; @@ -521,6 +522,7 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset, return ret; target->thread.fpsimd_state.user_fpsimd = newstate; + fpsimd_flush_task_state(target); return ret; } @@ -778,6 +780,7 @@ static int compat_vfp_set(struct task_struct *target, uregs->fpcr = fpscr & VFP_FPSCR_CTRL_MASK; } + fpsimd_flush_task_state(target); return ret; } diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 46b441679d8f..90c4c129f71a 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -41,6 +41,8 @@ #include <linux/memblock.h> #include <linux/of_fdt.h> #include <linux/of_platform.h> +#include <linux/efi.h> +#include <linux/personality.h> #include <asm/fixmap.h> #include <asm/cputype.h> @@ -55,6 +57,7 @@ #include <asm/traps.h> #include <asm/memblock.h> #include <asm/psci.h> +#include <asm/efi.h> unsigned int processor_id; EXPORT_SYMBOL(processor_id); @@ -68,13 +71,13 @@ EXPORT_SYMBOL_GPL(elf_hwcap); COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\ COMPAT_HWCAP_TLS|COMPAT_HWCAP_VFP|\ COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\ - COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV) + COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV|\ + COMPAT_HWCAP_LPAE) unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT; unsigned int compat_elf_hwcap2 __read_mostly; #endif static const char *cpu_name; -static const char *machine_name; phys_addr_t __fdt_pointer __initdata; /* @@ -194,6 +197,19 @@ static void __init smp_build_mpidr_hash(void) } #endif +struct cpuinfo_arm64 { + struct cpu cpu; + u32 reg_midr; +}; + +static DEFINE_PER_CPU(struct cpuinfo_arm64, cpu_data); + +void cpuinfo_store_cpu(void) +{ + struct cpuinfo_arm64 *info = this_cpu_ptr(&cpu_data); + info->reg_midr = read_cpuid_id(); +} + static void __init setup_processor(void) { struct cpu_info *cpu_info; @@ -214,6 +230,8 @@ static void __init setup_processor(void) sprintf(init_utsname()->machine, ELF_PLATFORM); elf_hwcap = 0; + cpuinfo_store_cpu(); + /* * ID_AA64ISAR0_EL1 contains 4-bit wide signed feature blocks. * The blocks we test below represent incremental functionality @@ -290,8 +308,6 @@ static void __init setup_machine_fdt(phys_addr_t dt_phys) while (true) cpu_relax(); } - - machine_name = of_flat_dt_get_machine_name(); } /* @@ -365,11 +381,14 @@ void __init setup_arch(char **cmdline_p) parse_early_param(); + efi_init(); arm64_memblock_init(); paging_init(); request_standard_resources(); + efi_idmap_init(); + unflatten_device_tree(); psci_init(); @@ -398,14 +417,12 @@ static int __init arm64_device_init(void) } arch_initcall_sync(arm64_device_init); -static DEFINE_PER_CPU(struct cpu, cpu_data); - static int __init topology_init(void) { int i; for_each_possible_cpu(i) { - struct cpu *cpu = &per_cpu(cpu_data, i); + struct cpu *cpu = &per_cpu(cpu_data.cpu, i); cpu->hotpluggable = 1; register_cpu(cpu, i); } @@ -426,14 +443,41 @@ static const char *hwcap_str[] = { NULL }; +#ifdef CONFIG_COMPAT +static const char *compat_hwcap_str[] = { + "swp", + "half", + "thumb", + "26bit", + "fastmult", + "fpa", + "vfp", + "edsp", + "java", + "iwmmxt", + "crunch", + "thumbee", + "neon", + "vfpv3", + "vfpv3d16", + "tls", + "vfpv4", + "idiva", + "idivt", + "vfpd32", + "lpae", + "evtstrm" +}; +#endif /* CONFIG_COMPAT */ + static int c_show(struct seq_file *m, void *v) { - int i; - - seq_printf(m, "Processor\t: %s rev %d (%s)\n", - cpu_name, read_cpuid_id() & 15, ELF_PLATFORM); + int i, j; for_each_online_cpu(i) { + struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i); + u32 midr = cpuinfo->reg_midr; + /* * glibc reads /proc/cpuinfo to determine the number of * online processors, looking for lines beginning with @@ -442,24 +486,33 @@ static int c_show(struct seq_file *m, void *v) #ifdef CONFIG_SMP seq_printf(m, "processor\t: %d\n", i); #endif - } - - /* dump out the processor features */ - seq_puts(m, "Features\t: "); - - for (i = 0; hwcap_str[i]; i++) - if (elf_hwcap & (1 << i)) - seq_printf(m, "%s ", hwcap_str[i]); - seq_printf(m, "\nCPU implementer\t: 0x%02x\n", read_cpuid_id() >> 24); - seq_printf(m, "CPU architecture: AArch64\n"); - seq_printf(m, "CPU variant\t: 0x%x\n", (read_cpuid_id() >> 20) & 15); - seq_printf(m, "CPU part\t: 0x%03x\n", (read_cpuid_id() >> 4) & 0xfff); - seq_printf(m, "CPU revision\t: %d\n", read_cpuid_id() & 15); - - seq_puts(m, "\n"); + /* + * Dump out the common processor features in a single line. + * Userspace should read the hwcaps with getauxval(AT_HWCAP) + * rather than attempting to parse this, but there's a body of + * software which does already (at least for 32-bit). + */ + seq_puts(m, "Features\t:"); + if (personality(current->personality) == PER_LINUX32) { +#ifdef CONFIG_COMPAT + for (j = 0; compat_hwcap_str[j]; j++) + if (compat_elf_hwcap & (1 << j)) + seq_printf(m, " %s", compat_hwcap_str[j]); +#endif /* CONFIG_COMPAT */ + } else { + for (j = 0; hwcap_str[j]; j++) + if (elf_hwcap & (1 << j)) + seq_printf(m, " %s", hwcap_str[j]); + } + seq_puts(m, "\n"); - seq_printf(m, "Hardware\t: %s\n", machine_name); + seq_printf(m, "CPU implementer\t: 0x%02x\n", (midr >> 24)); + seq_printf(m, "CPU architecture: 8\n"); + seq_printf(m, "CPU variant\t: 0x%x\n", ((midr >> 20) & 0xf)); + seq_printf(m, "CPU part\t: 0x%03x\n", ((midr >> 4) & 0xfff)); + seq_printf(m, "CPU revision\t: %d\n\n", (midr & 0xf)); + } return 0; } diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index e3cf09626245..bbc1aad21ce6 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -51,7 +51,7 @@ static int preserve_fpsimd_context(struct fpsimd_context __user *ctx) int err; /* dump the hardware registers to the fpsimd_state structure */ - fpsimd_save_state(fpsimd); + fpsimd_preserve_current_state(); /* copy the FP and status/control registers */ err = __copy_to_user(ctx->vregs, fpsimd->vregs, sizeof(fpsimd->vregs)); @@ -86,11 +86,8 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx) __get_user_error(fpsimd.fpcr, &ctx->fpcr, err); /* load the hardware registers from the fpsimd_state structure */ - if (!err) { - preempt_disable(); - fpsimd_load_state(&fpsimd); - preempt_enable(); - } + if (!err) + fpsimd_update_current_state(&fpsimd); return err ? -EFAULT : 0; } @@ -423,4 +420,8 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, clear_thread_flag(TIF_NOTIFY_RESUME); tracehook_notify_resume(regs); } + + if (thread_flags & _TIF_FOREIGN_FPSTATE) + fpsimd_restore_current_state(); + } diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index b3fc9f5ec6d3..6653cd6fccdc 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -151,8 +151,7 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) case __SI_TIMER: err |= __put_user(from->si_tid, &to->si_tid); err |= __put_user(from->si_overrun, &to->si_overrun); - err |= __put_user((compat_uptr_t)(unsigned long)from->si_ptr, - &to->si_ptr); + err |= __put_user(from->si_int, &to->si_int); break; case __SI_POLL: err |= __put_user(from->si_band, &to->si_band); @@ -181,7 +180,7 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) case __SI_MESGQ: /* But this is */ err |= __put_user(from->si_pid, &to->si_pid); err |= __put_user(from->si_uid, &to->si_uid); - err |= __put_user((compat_uptr_t)(unsigned long)from->si_ptr, &to->si_ptr); + err |= __put_user(from->si_int, &to->si_int); break; default: /* this is just in case for now ... */ err |= __put_user(from->si_pid, &to->si_pid); @@ -219,7 +218,7 @@ static int compat_preserve_vfp_context(struct compat_vfp_sigframe __user *frame) * Note that this also saves V16-31, which aren't visible * in AArch32. */ - fpsimd_save_state(fpsimd); + fpsimd_preserve_current_state(); /* Place structure header on the stack */ __put_user_error(magic, &frame->magic, err); @@ -282,11 +281,8 @@ static int compat_restore_vfp_context(struct compat_vfp_sigframe __user *frame) * We don't need to touch the exception register, so * reload the hardware state. */ - if (!err) { - preempt_disable(); - fpsimd_load_state(&fpsimd); - preempt_enable(); - } + if (!err) + fpsimd_update_current_state(&fpsimd); return err ? -EFAULT : 0; } diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index b1925729c692..ede186cdd452 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -49,28 +49,39 @@ orr \dst, \dst, \mask // dst|=(aff3>>rs3) .endm /* - * Save CPU state for a suspend. This saves callee registers, and allocates - * space on the kernel stack to save the CPU specific registers + some - * other data for resume. + * Save CPU state for a suspend and execute the suspend finisher. + * On success it will return 0 through cpu_resume - ie through a CPU + * soft/hard reboot from the reset vector. + * On failure it returns the suspend finisher return value or force + * -EOPNOTSUPP if the finisher erroneously returns 0 (the suspend finisher + * is not allowed to return, if it does this must be considered failure). + * It saves callee registers, and allocates space on the kernel stack + * to save the CPU specific registers + some other data for resume. * * x0 = suspend finisher argument + * x1 = suspend finisher function pointer */ -ENTRY(__cpu_suspend) +ENTRY(__cpu_suspend_enter) stp x29, lr, [sp, #-96]! stp x19, x20, [sp,#16] stp x21, x22, [sp,#32] stp x23, x24, [sp,#48] stp x25, x26, [sp,#64] stp x27, x28, [sp,#80] + /* + * Stash suspend finisher and its argument in x20 and x19 + */ + mov x19, x0 + mov x20, x1 mov x2, sp sub sp, sp, #CPU_SUSPEND_SZ // allocate cpu_suspend_ctx - mov x1, sp + mov x0, sp /* - * x1 now points to struct cpu_suspend_ctx allocated on the stack + * x0 now points to struct cpu_suspend_ctx allocated on the stack */ - str x2, [x1, #CPU_CTX_SP] - ldr x2, =sleep_save_sp - ldr x2, [x2, #SLEEP_SAVE_SP_VIRT] + str x2, [x0, #CPU_CTX_SP] + ldr x1, =sleep_save_sp + ldr x1, [x1, #SLEEP_SAVE_SP_VIRT] #ifdef CONFIG_SMP mrs x7, mpidr_el1 ldr x9, =mpidr_hash @@ -82,11 +93,21 @@ ENTRY(__cpu_suspend) ldp w3, w4, [x9, #MPIDR_HASH_SHIFTS] ldp w5, w6, [x9, #(MPIDR_HASH_SHIFTS + 8)] compute_mpidr_hash x8, x3, x4, x5, x6, x7, x10 - add x2, x2, x8, lsl #3 + add x1, x1, x8, lsl #3 #endif - bl __cpu_suspend_finisher + bl __cpu_suspend_save + /* + * Grab suspend finisher in x20 and its argument in x19 + */ + mov x0, x19 + mov x1, x20 + /* + * We are ready for power down, fire off the suspend finisher + * in x1, with argument in x0 + */ + blr x1 /* - * Never gets here, unless suspend fails. + * Never gets here, unless suspend finisher fails. * Successful cpu_suspend should return from cpu_resume, returning * through this code path is considered an error * If the return value is set to 0 force x0 = -EOPNOTSUPP @@ -103,7 +124,7 @@ ENTRY(__cpu_suspend) ldp x27, x28, [sp, #80] ldp x29, lr, [sp], #96 ret -ENDPROC(__cpu_suspend) +ENDPROC(__cpu_suspend_enter) .ltorg /* @@ -126,14 +147,12 @@ cpu_resume_after_mmu: ret ENDPROC(cpu_resume_after_mmu) - .data ENTRY(cpu_resume) bl el2_setup // if in EL2 drop to EL1 cleanly #ifdef CONFIG_SMP mrs x1, mpidr_el1 - adr x4, mpidr_hash_ptr - ldr x5, [x4] - add x8, x4, x5 // x8 = struct mpidr_hash phys address + adrp x8, mpidr_hash + add x8, x8, #:lo12:mpidr_hash // x8 = struct mpidr_hash phys address /* retrieve mpidr_hash members to compute the hash */ ldr x2, [x8, #MPIDR_HASH_MASK] ldp w3, w4, [x8, #MPIDR_HASH_SHIFTS] @@ -143,14 +162,15 @@ ENTRY(cpu_resume) #else mov x7, xzr #endif - adr x0, sleep_save_sp + adrp x0, sleep_save_sp + add x0, x0, #:lo12:sleep_save_sp ldr x0, [x0, #SLEEP_SAVE_SP_PHYS] ldr x0, [x0, x7, lsl #3] /* load sp from context */ ldr x2, [x0, #CPU_CTX_SP] - adr x1, sleep_idmap_phys + adrp x1, sleep_idmap_phys /* load physical address of identity map page table in x1 */ - ldr x1, [x1] + ldr x1, [x1, #:lo12:sleep_idmap_phys] mov sp, x2 /* * cpu_do_resume expects x0 to contain context physical address @@ -159,26 +179,3 @@ ENTRY(cpu_resume) bl cpu_do_resume // PC relative jump, MMU off b cpu_resume_mmu // Resume MMU, never returns ENDPROC(cpu_resume) - - .align 3 -mpidr_hash_ptr: - /* - * offset of mpidr_hash symbol from current location - * used to obtain run-time mpidr_hash address with MMU off - */ - .quad mpidr_hash - . -/* - * physical address of identity mapped page tables - */ - .type sleep_idmap_phys, #object -ENTRY(sleep_idmap_phys) - .quad 0 -/* - * struct sleep_save_sp { - * phys_addr_t *save_ptr_stash; - * phys_addr_t save_ptr_stash_phys; - * }; - */ - .type sleep_save_sp, #object -ENTRY(sleep_save_sp) - .space SLEEP_SAVE_SP_SZ // struct sleep_save_sp diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 9660750f34ba..33b57b9a7c4f 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -35,6 +35,7 @@ #include <linux/clockchips.h> #include <linux/completion.h> #include <linux/of.h> +#include <linux/irq_work.h> #include <asm/atomic.h> #include <asm/cacheflush.h> @@ -62,6 +63,7 @@ enum ipi_msg_type { IPI_CALL_FUNC_SINGLE, IPI_CPU_STOP, IPI_TIMER, + IPI_IRQ_WORK, }; /* @@ -153,6 +155,11 @@ asmlinkage void secondary_start_kernel(void) cpu_ops[cpu]->cpu_postboot(); /* + * Log the CPU info before it is marked online and might get read. + */ + cpuinfo_store_cpu(); + + /* * Enable GIC and timers. */ notify_cpu_starting(cpu); @@ -454,6 +461,14 @@ void arch_send_call_function_single_ipi(int cpu) smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE); } +#ifdef CONFIG_IRQ_WORK +void arch_irq_work_raise(void) +{ + if (smp_cross_call) + smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK); +} +#endif + static const char *ipi_types[NR_IPI] = { #define S(x,s) [x - IPI_RESCHEDULE] = s S(IPI_RESCHEDULE, "Rescheduling interrupts"), @@ -461,6 +476,7 @@ static const char *ipi_types[NR_IPI] = { S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"), S(IPI_CPU_STOP, "CPU stop interrupts"), S(IPI_TIMER, "Timer broadcast interrupts"), + S(IPI_IRQ_WORK, "IRQ work interrupts"), }; void show_ipi_list(struct seq_file *p, int prec) @@ -553,6 +569,14 @@ void handle_IPI(int ipinr, struct pt_regs *regs) break; #endif +#ifdef CONFIG_IRQ_WORK + case IPI_IRQ_WORK: + irq_enter(); + irq_work_run(); + irq_exit(); + break; +#endif + default: pr_crit("CPU%u: Unknown IPI message 0x%x\n", cpu, ipinr); break; diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 1fa9ce4afd8f..2d6b6065fe7f 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -5,26 +5,24 @@ #include <asm/debug-monitors.h> #include <asm/pgtable.h> #include <asm/memory.h> +#include <asm/mmu_context.h> #include <asm/smp_plat.h> #include <asm/suspend.h> #include <asm/tlbflush.h> -extern int __cpu_suspend(unsigned long); +extern int __cpu_suspend_enter(unsigned long arg, int (*fn)(unsigned long)); /* - * This is called by __cpu_suspend() to save the state, and do whatever + * This is called by __cpu_suspend_enter() to save the state, and do whatever * flushing is required to ensure that when the CPU goes to sleep we have * the necessary data available when the caches are not searched. * - * @arg: Argument to pass to suspend operations - * @ptr: CPU context virtual address - * @save_ptr: address of the location where the context physical address - * must be saved + * ptr: CPU context virtual address + * save_ptr: address of the location where the context physical address + * must be saved */ -int __cpu_suspend_finisher(unsigned long arg, struct cpu_suspend_ctx *ptr, - phys_addr_t *save_ptr) +void notrace __cpu_suspend_save(struct cpu_suspend_ctx *ptr, + phys_addr_t *save_ptr) { - int cpu = smp_processor_id(); - *save_ptr = virt_to_phys(ptr); cpu_do_suspend(ptr); @@ -35,8 +33,6 @@ int __cpu_suspend_finisher(unsigned long arg, struct cpu_suspend_ctx *ptr, */ __flush_dcache_area(ptr, sizeof(*ptr)); __flush_dcache_area(save_ptr, sizeof(*save_ptr)); - - return cpu_ops[cpu]->cpu_suspend(arg); } /* @@ -56,15 +52,15 @@ void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *)) } /** - * cpu_suspend + * cpu_suspend() - function to enter a low-power state + * @arg: argument to pass to CPU suspend operations * - * @arg: argument to pass to the finisher function + * Return: 0 on success, -EOPNOTSUPP if CPU suspend hook not initialized, CPU + * operations back-end error code otherwise. */ int cpu_suspend(unsigned long arg) { - struct mm_struct *mm = current->active_mm; - int ret, cpu = smp_processor_id(); - unsigned long flags; + int cpu = smp_processor_id(); /* * If cpu_ops have not been registered or suspend @@ -72,6 +68,21 @@ int cpu_suspend(unsigned long arg) */ if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_suspend) return -EOPNOTSUPP; + return cpu_ops[cpu]->cpu_suspend(arg); +} + +/* + * __cpu_suspend + * + * arg: argument to pass to the finisher function + * fn: finisher function pointer + * + */ +int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) +{ + struct mm_struct *mm = current->active_mm; + int ret; + unsigned long flags; /* * From this point debug exceptions are disabled to prevent @@ -86,16 +97,27 @@ int cpu_suspend(unsigned long arg) * page tables, so that the thread address space is properly * set-up on function return. */ - ret = __cpu_suspend(arg); + ret = __cpu_suspend_enter(arg, fn); if (ret == 0) { - cpu_switch_mm(mm->pgd, mm); + /* + * We are resuming from reset with TTBR0_EL1 set to the + * idmap to enable the MMU; restore the active_mm mappings in + * TTBR0_EL1 unless the active_mm == &init_mm, in which case + * the thread entered __cpu_suspend with TTBR0_EL1 set to + * reserved TTBR0 page tables and should be restored as such. + */ + if (mm == &init_mm) + cpu_set_reserved_ttbr0(); + else + cpu_switch_mm(mm->pgd, mm); + flush_tlb_all(); /* * Restore per-cpu offset before any kernel * subsystem relying on it has a chance to run. */ - set_my_cpu_offset(per_cpu_offset(cpu)); + set_my_cpu_offset(per_cpu_offset(smp_processor_id())); /* * Restore HW breakpoint registers to sane values @@ -116,10 +138,10 @@ int cpu_suspend(unsigned long arg) return ret; } -extern struct sleep_save_sp sleep_save_sp; -extern phys_addr_t sleep_idmap_phys; +struct sleep_save_sp sleep_save_sp; +phys_addr_t sleep_idmap_phys; -static int cpu_suspend_init(void) +static int __init cpu_suspend_init(void) { void *ctx_ptr; diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c index 26e9c4eeaba8..78039927c807 100644 --- a/arch/arm64/kernel/sys_compat.c +++ b/arch/arm64/kernel/sys_compat.c @@ -79,6 +79,12 @@ long compat_arm_syscall(struct pt_regs *regs) case __ARM_NR_compat_set_tls: current->thread.tp_value = regs->regs[0]; + + /* + * Protect against register corruption from context switch. + * See comment in tls_thread_flush. + */ + barrier(); asm ("msr tpidrro_el0, %0" : : "r" (regs->regs[0])); return 0; diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index e28be510380c..34b8bd0711e9 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -66,6 +66,8 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run) else kvm_vcpu_block(vcpu); + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + return 1; } diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S index d968796f4b2d..c3191168a994 100644 --- a/arch/arm64/kvm/hyp-init.S +++ b/arch/arm64/kvm/hyp-init.S @@ -80,6 +80,10 @@ __do_hyp_init: msr mair_el2, x4 isb + /* Invalidate the stale TLBs from Bootloader */ + tlbi alle2 + dsb sy + mrs x4, sctlr_el2 and x4, x4, #SCTLR_EL2_EE // preserve endianness of EL2 ldr x5, =SCTLR_EL2_FLAGS diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S index 6e0ed93d51fe..c17967fdf5f6 100644 --- a/arch/arm64/lib/clear_user.S +++ b/arch/arm64/lib/clear_user.S @@ -46,7 +46,7 @@ USER(9f, strh wzr, [x0], #2 ) sub x1, x1, #2 4: adds x1, x1, #1 b.mi 5f - strb wzr, [x0] +USER(9f, strb wzr, [x0] ) 5: mov x0, #0 ret ENDPROC(__clear_user) diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 4164c5ace9f8..de3abbe6c59f 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -55,6 +55,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size, flags |= GFP_DMA; if (IS_ENABLED(CONFIG_DMA_CMA)) { struct page *page; + void *addr; size = PAGE_ALIGN(size); page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT, @@ -63,7 +64,10 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size, return NULL; *dma_handle = phys_to_dma(dev, page_to_phys(page)); - return page_address(page); + addr = page_address(page); + if (flags & __GFP_ZERO) + memset(addr, 0, size); + return addr; } else { return swiotlb_alloc_coherent(dev, size, dma_handle, flags); } diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c index da5b462e6de6..741b99c1a0b1 100644 --- a/arch/ia64/kernel/efi.c +++ b/arch/ia64/kernel/efi.c @@ -477,6 +477,9 @@ efi_init (void) char *cp, vendor[100] = "unknown"; int i; + set_bit(EFI_BOOT, &efi.flags); + set_bit(EFI_64BIT, &efi.flags); + /* * It's too early to be able to use the standard kernel command line * support... @@ -529,6 +532,8 @@ efi_init (void) efi.systab->hdr.revision >> 16, efi.systab->hdr.revision & 0xffff, vendor); + set_bit(EFI_SYSTEM_TABLES, &efi.flags); + palo_phys = EFI_INVALID_TABLE_ADDR; if (efi_config_init(arch_tables) != 0) @@ -657,6 +662,8 @@ efi_enter_virtual_mode (void) return; } + set_bit(EFI_RUNTIME_SERVICES, &efi.flags); + /* * Now that EFI is in virtual mode, we call the EFI functions more * efficiently: diff --git a/arch/m68k/mm/hwtest.c b/arch/m68k/mm/hwtest.c index 2c7dde3c6430..2a5259fd23eb 100644 --- a/arch/m68k/mm/hwtest.c +++ b/arch/m68k/mm/hwtest.c @@ -28,9 +28,11 @@ int hwreg_present( volatile void *regp ) { int ret = 0; + unsigned long flags; long save_sp, save_vbr; long tmp_vectors[3]; + local_irq_save(flags); __asm__ __volatile__ ( "movec %/vbr,%2\n\t" "movel #Lberr1,%4@(8)\n\t" @@ -46,6 +48,7 @@ int hwreg_present( volatile void *regp ) : "=&d" (ret), "=&r" (save_sp), "=&r" (save_vbr) : "a" (regp), "a" (tmp_vectors) ); + local_irq_restore(flags); return( ret ); } @@ -58,9 +61,11 @@ EXPORT_SYMBOL(hwreg_present); int hwreg_write( volatile void *regp, unsigned short val ) { int ret; + unsigned long flags; long save_sp, save_vbr; long tmp_vectors[3]; + local_irq_save(flags); __asm__ __volatile__ ( "movec %/vbr,%2\n\t" "movel #Lberr2,%4@(8)\n\t" @@ -78,6 +83,7 @@ int hwreg_write( volatile void *regp, unsigned short val ) : "=&d" (ret), "=&r" (save_sp), "=&r" (save_vbr) : "a" (regp), "a" (tmp_vectors), "g" (val) ); + local_irq_restore(flags); return( ret ); } diff --git a/arch/metag/include/asm/processor.h b/arch/metag/include/asm/processor.h index a8a37477c66e..eb2005bd3c79 100644 --- a/arch/metag/include/asm/processor.h +++ b/arch/metag/include/asm/processor.h @@ -149,8 +149,8 @@ extern void exit_thread(void); unsigned long get_wchan(struct task_struct *p); -#define KSTK_EIP(tsk) ((tsk)->thread.kernel_context->CurrPC) -#define KSTK_ESP(tsk) ((tsk)->thread.kernel_context->AX[0].U0) +#define KSTK_EIP(tsk) (task_pt_regs(tsk)->ctx.CurrPC) +#define KSTK_ESP(tsk) (task_pt_regs(tsk)->ctx.AX[0].U0) #define user_stack_pointer(regs) ((regs)->ctx.AX[0].U0) diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 79b9bcdfe498..d618d3633122 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -1,5 +1,6 @@ config MICROBLAZE def_bool y + select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_MIGHT_HAVE_PC_PARPORT select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c index c00c4ddf4514..5244cecf1e45 100644 --- a/arch/mips/boot/compressed/decompress.c +++ b/arch/mips/boot/compressed/decompress.c @@ -13,6 +13,7 @@ #include <linux/types.h> #include <linux/kernel.h> +#include <linux/string.h> #include <asm/addrspace.h> diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index 67a078ffc464..34467ac8220c 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -263,9 +263,7 @@ static int octeon_cpu_disable(void) set_cpu_online(cpu, false); cpu_clear(cpu, cpu_callin_map); - local_irq_disable(); octeon_fixup_irqs(); - local_irq_enable(); flush_cache_all(); local_flush_tlb_all(); diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h index 992aaba603b5..b463f2aa5a61 100644 --- a/arch/mips/include/asm/ftrace.h +++ b/arch/mips/include/asm/ftrace.h @@ -24,7 +24,7 @@ do { \ asm volatile ( \ "1: " load " %[tmp_dst], 0(%[tmp_src])\n" \ " li %[tmp_err], 0\n" \ - "2:\n" \ + "2: .insn\n" \ \ ".section .fixup, \"ax\"\n" \ "3: li %[tmp_err], 1\n" \ @@ -46,7 +46,7 @@ do { \ asm volatile ( \ "1: " store " %[tmp_src], 0(%[tmp_dst])\n"\ " li %[tmp_err], 0\n" \ - "2:\n" \ + "2: .insn\n" \ \ ".section .fixup, \"ax\"\n" \ "3: li %[tmp_err], 1\n" \ diff --git a/arch/mips/kernel/irq_cpu.c b/arch/mips/kernel/irq_cpu.c index e498f2b3646a..f5598e25e906 100644 --- a/arch/mips/kernel/irq_cpu.c +++ b/arch/mips/kernel/irq_cpu.c @@ -56,6 +56,8 @@ static struct irq_chip mips_cpu_irq_controller = { .irq_mask_ack = mask_mips_irq, .irq_unmask = unmask_mips_irq, .irq_eoi = unmask_mips_irq, + .irq_disable = mask_mips_irq, + .irq_enable = unmask_mips_irq, }; /* @@ -92,6 +94,8 @@ static struct irq_chip mips_mt_cpu_irq_controller = { .irq_mask_ack = mips_mt_cpu_irq_ack, .irq_unmask = unmask_mips_irq, .irq_eoi = unmask_mips_irq, + .irq_disable = mask_mips_irq, + .irq_enable = unmask_mips_irq, }; void __init mips_cpu_irq_init(void) diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S index 539b6294b613..8f89ff4ed524 100644 --- a/arch/mips/kernel/mcount.S +++ b/arch/mips/kernel/mcount.S @@ -123,7 +123,11 @@ NESTED(_mcount, PT_SIZE, ra) nop #endif b ftrace_stub +#ifdef CONFIG_32BIT + addiu sp, sp, 8 +#else nop +#endif static_trace: MCOUNT_SAVE_REGS @@ -133,6 +137,9 @@ static_trace: move a1, AT /* arg2: parent's return address */ MCOUNT_RESTORE_REGS +#ifdef CONFIG_32BIT + addiu sp, sp, 8 +#endif .globl ftrace_stub ftrace_stub: RETURN_BACK @@ -177,6 +184,11 @@ NESTED(ftrace_graph_caller, PT_SIZE, ra) jal prepare_ftrace_return nop MCOUNT_RESTORE_REGS +#ifndef CONFIG_DYNAMIC_FTRACE +#ifdef CONFIG_32BIT + addiu sp, sp, 8 +#endif +#endif RETURN_BACK END(ftrace_graph_caller) diff --git a/arch/mips/kernel/mips_ksyms.c b/arch/mips/kernel/mips_ksyms.c index 6e58e97fcd39..cedeb5686eb5 100644 --- a/arch/mips/kernel/mips_ksyms.c +++ b/arch/mips/kernel/mips_ksyms.c @@ -14,6 +14,7 @@ #include <linux/mm.h> #include <asm/uaccess.h> #include <asm/ftrace.h> +#include <asm/fpu.h> extern void *__bzero(void *__s, size_t __count); extern long __strncpy_from_user_nocheck_asm(char *__to, @@ -26,6 +27,13 @@ extern long __strnlen_user_nocheck_asm(const char *s); extern long __strnlen_user_asm(const char *s); /* + * Core architecture code + */ +#ifdef CONFIG_CPU_R4K_FPU +EXPORT_SYMBOL_GPL(_save_fp); +#endif + +/* * String functions */ EXPORT_SYMBOL(memset); diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index 0a022ee33b2a..18ed11275052 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -109,10 +109,10 @@ asmlinkage void start_secondary(void) else #endif /* CONFIG_MIPS_MT_SMTC */ cpu_probe(); - cpu_report(); per_cpu_trap_init(false); mips_clockevent_init(); mp_ops->init_secondary(); + cpu_report(); /* * XXX parity protection should be folded in here when it's converted diff --git a/arch/mips/kvm/kvm_locore.S b/arch/mips/kvm/kvm_locore.S index bbace092ad0a..03a2db58b22d 100644 --- a/arch/mips/kvm/kvm_locore.S +++ b/arch/mips/kvm/kvm_locore.S @@ -428,7 +428,7 @@ __kvm_mips_return_to_guest: /* Setup status register for running guest in UM */ .set at or v1, v1, (ST0_EXL | KSU_USER | ST0_IE) - and v1, v1, ~ST0_CU0 + and v1, v1, ~(ST0_CU0 | ST0_MX) .set noat mtc0 v1, CP0_STATUS ehb diff --git a/arch/mips/kvm/kvm_mips.c b/arch/mips/kvm/kvm_mips.c index 3e0ff8d0fbf9..897c605263f2 100644 --- a/arch/mips/kvm/kvm_mips.c +++ b/arch/mips/kvm/kvm_mips.c @@ -15,6 +15,7 @@ #include <linux/vmalloc.h> #include <linux/fs.h> #include <linux/bootmem.h> +#include <asm/fpu.h> #include <asm/page.h> #include <asm/cacheflush.h> #include <asm/mmu_context.h> @@ -418,11 +419,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) vcpu->mmio_needed = 0; } + lose_fpu(1); + + local_irq_disable(); /* Check if we have any exceptions/interrupts pending */ kvm_mips_deliver_interrupts(vcpu, kvm_read_c0_guest_cause(vcpu->arch.cop0)); - local_irq_disable(); kvm_guest_enter(); r = __kvm_mips_vcpu_run(run, vcpu); @@ -1021,9 +1024,6 @@ void kvm_mips_set_c0_status(void) { uint32_t status = read_c0_status(); - if (cpu_has_fpu) - status |= (ST0_CU1); - if (cpu_has_dsp) status |= (ST0_MX); diff --git a/arch/mips/kvm/trace.h b/arch/mips/kvm/trace.h index bc9e0f406c08..e51621e36152 100644 --- a/arch/mips/kvm/trace.h +++ b/arch/mips/kvm/trace.h @@ -26,18 +26,18 @@ TRACE_EVENT(kvm_exit, TP_PROTO(struct kvm_vcpu *vcpu, unsigned int reason), TP_ARGS(vcpu, reason), TP_STRUCT__entry( - __field(struct kvm_vcpu *, vcpu) + __field(unsigned long, pc) __field(unsigned int, reason) ), TP_fast_assign( - __entry->vcpu = vcpu; + __entry->pc = vcpu->arch.pc; __entry->reason = reason; ), TP_printk("[%s]PC: 0x%08lx", kvm_mips_exit_types_str[__entry->reason], - __entry->vcpu->arch.pc) + __entry->pc) ); #endif /* _TRACE_KVM_H */ diff --git a/arch/mips/loongson/common/Makefile b/arch/mips/loongson/common/Makefile index 9e4484ccbb03..9005a8d60969 100644 --- a/arch/mips/loongson/common/Makefile +++ b/arch/mips/loongson/common/Makefile @@ -11,7 +11,8 @@ obj-$(CONFIG_PCI) += pci.o # Serial port support # obj-$(CONFIG_EARLY_PRINTK) += early_printk.o -obj-$(CONFIG_SERIAL_8250) += serial.o +loongson-serial-$(CONFIG_SERIAL_8250) := serial.o +obj-y += $(loongson-serial-m) $(loongson-serial-y) obj-$(CONFIG_LOONGSON_UART_BASE) += uart_base.o obj-$(CONFIG_LOONGSON_MC146818) += rtc.o diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 65d452aa1fda..dd012c599ad1 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -1057,6 +1057,7 @@ static void build_update_entries(u32 **p, unsigned int tmp, unsigned int ptep) struct mips_huge_tlb_info { int huge_pte; int restore_scratch; + bool need_reload_pte; }; static struct mips_huge_tlb_info @@ -1071,6 +1072,7 @@ build_fast_tlb_refill_handler (u32 **p, struct uasm_label **l, rv.huge_pte = scratch; rv.restore_scratch = 0; + rv.need_reload_pte = false; if (check_for_high_segbits) { UASM_i_MFC0(p, tmp, C0_BADVADDR); @@ -1259,6 +1261,7 @@ static void build_r4000_tlb_refill_handler(void) } else { htlb_info.huge_pte = K0; htlb_info.restore_scratch = 0; + htlb_info.need_reload_pte = true; vmalloc_mode = refill_noscratch; /* * create the plain linear handler @@ -1295,7 +1298,8 @@ static void build_r4000_tlb_refill_handler(void) } #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT uasm_l_tlb_huge_update(&l, p); - UASM_i_LW(&p, K0, 0, K1); + if (htlb_info.need_reload_pte) + UASM_i_LW(&p, htlb_info.huge_pte, 0, K1); build_huge_update_entries(&p, htlb_info.huge_pte, K1); build_huge_tlb_write_entry(&p, &l, &r, K0, tlb_random, htlb_info.restore_scratch); diff --git a/arch/mips/oprofile/backtrace.c b/arch/mips/oprofile/backtrace.c index 6854ed5097d2..83a1dfd8f0e3 100644 --- a/arch/mips/oprofile/backtrace.c +++ b/arch/mips/oprofile/backtrace.c @@ -92,7 +92,7 @@ static inline int unwind_user_frame(struct stackframe *old_frame, /* This marks the end of the previous function, which means we overran. */ break; - stack_size = (unsigned) stack_adjustment; + stack_size = (unsigned long) stack_adjustment; } else if (is_ra_save_ins(&ip)) { int ra_slot = ip.i_format.simmediate; if (ra_slot < 0) diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index 7187664034c3..5db8882f732c 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -48,7 +48,12 @@ cflags-y := -pipe # These flags should be implied by an hppa-linux configuration, but they # are not in gcc 3.2. -cflags-y += -mno-space-regs -mfast-indirect-calls +cflags-y += -mno-space-regs + +# -mfast-indirect-calls is only relevant for 32-bit kernels. +ifndef CONFIG_64BIT +cflags-y += -mfast-indirect-calls +endif # Currently we save and restore fpregs on all kernel entry/interruption paths. # If that gets optimized, we might need to disable the use of fpregs in the diff --git a/arch/parisc/hpux/fs.c b/arch/parisc/hpux/fs.c index 2bedafea3d94..97a7bf8df348 100644 --- a/arch/parisc/hpux/fs.c +++ b/arch/parisc/hpux/fs.c @@ -56,11 +56,12 @@ struct getdents_callback { #define NAME_OFFSET(de) ((int) ((de)->d_name - (char __user *) (de))) -static int filldir(void * __buf, const char * name, int namlen, loff_t offset, - u64 ino, unsigned d_type) +static int filldir(struct dir_context *ctx, const char *name, int namlen, + loff_t offset, u64 ino, unsigned d_type) { struct hpux_dirent __user * dirent; - struct getdents_callback * buf = (struct getdents_callback *) __buf; + struct getdents_callback *buf = + container_of(ctx, struct getdents_callback, ctx); ino_t d_ino; int reclen = ALIGN(NAME_OFFSET(dirent) + namlen + 1, sizeof(long)); diff --git a/arch/parisc/include/asm/ldcw.h b/arch/parisc/include/asm/ldcw.h index d2d11b7055ba..8121aa6db2ff 100644 --- a/arch/parisc/include/asm/ldcw.h +++ b/arch/parisc/include/asm/ldcw.h @@ -33,11 +33,18 @@ #endif /*!CONFIG_PA20*/ -/* LDCW, the only atomic read-write operation PA-RISC has. *sigh*. */ +/* LDCW, the only atomic read-write operation PA-RISC has. *sigh*. + We don't explicitly expose that "*a" may be written as reload + fails to find a register in class R1_REGS when "a" needs to be + reloaded when generating 64-bit PIC code. Instead, we clobber + memory to indicate to the compiler that the assembly code reads + or writes to items other than those listed in the input and output + operands. This may pessimize the code somewhat but __ldcw is + usually used within code blocks surrounded by memory barriors. */ #define __ldcw(a) ({ \ unsigned __ret; \ - __asm__ __volatile__(__LDCW " 0(%2),%0" \ - : "=r" (__ret), "+m" (*(a)) : "r" (a)); \ + __asm__ __volatile__(__LDCW " 0(%1),%0" \ + : "=r" (__ret) : "r" (a) : "memory"); \ __ret; \ }) diff --git a/arch/parisc/include/uapi/asm/shmbuf.h b/arch/parisc/include/uapi/asm/shmbuf.h index 0a3eada1863b..f395cde7b593 100644 --- a/arch/parisc/include/uapi/asm/shmbuf.h +++ b/arch/parisc/include/uapi/asm/shmbuf.h @@ -36,23 +36,16 @@ struct shmid64_ds { unsigned int __unused2; }; -#ifdef CONFIG_64BIT -/* The 'unsigned int' (formerly 'unsigned long') data types below will - * ensure that a 32-bit app calling shmctl(*,IPC_INFO,*) will work on - * a wide kernel, but if some of these values are meant to contain pointers - * they may need to be 'long long' instead. -PB XXX FIXME - */ -#endif struct shminfo64 { - unsigned int shmmax; - unsigned int shmmin; - unsigned int shmmni; - unsigned int shmseg; - unsigned int shmall; - unsigned int __unused1; - unsigned int __unused2; - unsigned int __unused3; - unsigned int __unused4; + unsigned long shmmax; + unsigned long shmmin; + unsigned long shmmni; + unsigned long shmseg; + unsigned long shmall; + unsigned long __unused1; + unsigned long __unused2; + unsigned long __unused3; + unsigned long __unused4; }; #endif /* _PARISC_SHMBUF_H */ diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 838786011037..7ef22e3387e0 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -74,7 +74,7 @@ ENTRY(linux_gateway_page) /* ADDRESS 0xb0 to 0xb8, lws uses two insns for entry */ /* Light-weight-syscall entry must always be located at 0xb0 */ /* WARNING: Keep this number updated with table size changes */ -#define __NR_lws_entries (2) +#define __NR_lws_entries (3) lws_entry: gate lws_start, %r0 /* increase privilege */ @@ -502,7 +502,7 @@ lws_exit: /*************************************************** - Implementing CAS as an atomic operation: + Implementing 32bit CAS as an atomic operation: %r26 - Address to examine %r25 - Old value to check (old) @@ -659,6 +659,230 @@ cas_action: ASM_EXCEPTIONTABLE_ENTRY(2b-linux_gateway_page, 3b-linux_gateway_page) + /*************************************************** + New CAS implementation which uses pointers and variable size + information. The value pointed by old and new MUST NOT change + while performing CAS. The lock only protect the value at %r26. + + %r26 - Address to examine + %r25 - Pointer to the value to check (old) + %r24 - Pointer to the value to set (new) + %r23 - Size of the variable (0/1/2/3 for 8/16/32/64 bit) + %r28 - Return non-zero on failure + %r21 - Kernel error code + + %r21 has the following meanings: + + EAGAIN - CAS is busy, ldcw failed, try again. + EFAULT - Read or write failed. + + Scratch: r20, r22, r28, r29, r1, fr4 (32bit for 64bit CAS only) + + ****************************************************/ + + /* ELF32 Process entry path */ +lws_compare_and_swap_2: +#ifdef CONFIG_64BIT + /* Clip the input registers */ + depdi 0, 31, 32, %r26 + depdi 0, 31, 32, %r25 + depdi 0, 31, 32, %r24 + depdi 0, 31, 32, %r23 +#endif + + /* Check the validity of the size pointer */ + subi,>>= 4, %r23, %r0 + b,n lws_exit_nosys + + /* Jump to the functions which will load the old and new values into + registers depending on the their size */ + shlw %r23, 2, %r29 + blr %r29, %r0 + nop + + /* 8bit load */ +4: ldb 0(%sr3,%r25), %r25 + b cas2_lock_start +5: ldb 0(%sr3,%r24), %r24 + nop + nop + nop + nop + nop + + /* 16bit load */ +6: ldh 0(%sr3,%r25), %r25 + b cas2_lock_start +7: ldh 0(%sr3,%r24), %r24 + nop + nop + nop + nop + nop + + /* 32bit load */ +8: ldw 0(%sr3,%r25), %r25 + b cas2_lock_start +9: ldw 0(%sr3,%r24), %r24 + nop + nop + nop + nop + nop + + /* 64bit load */ +#ifdef CONFIG_64BIT +10: ldd 0(%sr3,%r25), %r25 +11: ldd 0(%sr3,%r24), %r24 +#else + /* Load new value into r22/r23 - high/low */ +10: ldw 0(%sr3,%r25), %r22 +11: ldw 4(%sr3,%r25), %r23 + /* Load new value into fr4 for atomic store later */ +12: flddx 0(%sr3,%r24), %fr4 +#endif + +cas2_lock_start: + /* Load start of lock table */ + ldil L%lws_lock_start, %r20 + ldo R%lws_lock_start(%r20), %r28 + + /* Extract four bits from r26 and hash lock (Bits 4-7) */ + extru %r26, 27, 4, %r20 + + /* Find lock to use, the hash is either one of 0 to + 15, multiplied by 16 (keep it 16-byte aligned) + and add to the lock table offset. */ + shlw %r20, 4, %r20 + add %r20, %r28, %r20 + + rsm PSW_SM_I, %r0 /* Disable interrupts */ + /* COW breaks can cause contention on UP systems */ + LDCW 0(%sr2,%r20), %r28 /* Try to acquire the lock */ + cmpb,<>,n %r0, %r28, cas2_action /* Did we get it? */ +cas2_wouldblock: + ldo 2(%r0), %r28 /* 2nd case */ + ssm PSW_SM_I, %r0 + b lws_exit /* Contended... */ + ldo -EAGAIN(%r0), %r21 /* Spin in userspace */ + + /* + prev = *addr; + if ( prev == old ) + *addr = new; + return prev; + */ + + /* NOTES: + This all works becuse intr_do_signal + and schedule both check the return iasq + and see that we are on the kernel page + so this process is never scheduled off + or is ever sent any signal of any sort, + thus it is wholly atomic from usrspaces + perspective + */ +cas2_action: + /* Jump to the correct function */ + blr %r29, %r0 + /* Set %r28 as non-zero for now */ + ldo 1(%r0),%r28 + + /* 8bit CAS */ +13: ldb,ma 0(%sr3,%r26), %r29 + sub,= %r29, %r25, %r0 + b,n cas2_end +14: stb,ma %r24, 0(%sr3,%r26) + b cas2_end + copy %r0, %r28 + nop + nop + + /* 16bit CAS */ +15: ldh,ma 0(%sr3,%r26), %r29 + sub,= %r29, %r25, %r0 + b,n cas2_end +16: sth,ma %r24, 0(%sr3,%r26) + b cas2_end + copy %r0, %r28 + nop + nop + + /* 32bit CAS */ +17: ldw,ma 0(%sr3,%r26), %r29 + sub,= %r29, %r25, %r0 + b,n cas2_end +18: stw,ma %r24, 0(%sr3,%r26) + b cas2_end + copy %r0, %r28 + nop + nop + + /* 64bit CAS */ +#ifdef CONFIG_64BIT +19: ldd,ma 0(%sr3,%r26), %r29 + sub,= %r29, %r25, %r0 + b,n cas2_end +20: std,ma %r24, 0(%sr3,%r26) + copy %r0, %r28 +#else + /* Compare first word */ +19: ldw,ma 0(%sr3,%r26), %r29 + sub,= %r29, %r22, %r0 + b,n cas2_end + /* Compare second word */ +20: ldw,ma 4(%sr3,%r26), %r29 + sub,= %r29, %r23, %r0 + b,n cas2_end + /* Perform the store */ +21: fstdx %fr4, 0(%sr3,%r26) + copy %r0, %r28 +#endif + +cas2_end: + /* Free lock */ + stw,ma %r20, 0(%sr2,%r20) + /* Enable interrupts */ + ssm PSW_SM_I, %r0 + /* Return to userspace, set no error */ + b lws_exit + copy %r0, %r21 + +22: + /* Error occurred on load or store */ + /* Free lock */ + stw %r20, 0(%sr2,%r20) + ssm PSW_SM_I, %r0 + ldo 1(%r0),%r28 + b lws_exit + ldo -EFAULT(%r0),%r21 /* set errno */ + nop + nop + nop + + /* Exception table entries, for the load and store, return EFAULT. + Each of the entries must be relocated. */ + ASM_EXCEPTIONTABLE_ENTRY(4b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(5b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(6b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(7b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(8b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(9b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(10b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(11b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(13b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(14b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(15b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(16b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(17b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(18b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(19b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(20b-linux_gateway_page, 22b-linux_gateway_page) +#ifndef CONFIG_64BIT + ASM_EXCEPTIONTABLE_ENTRY(12b-linux_gateway_page, 22b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(21b-linux_gateway_page, 22b-linux_gateway_page) +#endif + /* Make sure nothing else is placed on this page */ .align PAGE_SIZE END(linux_gateway_page) @@ -675,8 +899,9 @@ ENTRY(end_linux_gateway_page) /* Light-weight-syscall table */ /* Start of lws table. */ ENTRY(lws_table) - LWS_ENTRY(compare_and_swap32) /* 0 - ELF32 Atomic compare and swap */ - LWS_ENTRY(compare_and_swap64) /* 1 - ELF64 Atomic compare and swap */ + LWS_ENTRY(compare_and_swap32) /* 0 - ELF32 Atomic 32bit CAS */ + LWS_ENTRY(compare_and_swap64) /* 1 - ELF64 Atomic 32bit CAS */ + LWS_ENTRY(compare_and_swap_2) /* 2 - ELF32 Atomic 64bit CAS */ END(lws_table) /* End of lws table */ diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index 7dd8a3b22147..fc77d53e2ca5 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -286,11 +286,11 @@ ENTRY_COMP(msgsnd) ENTRY_COMP(msgrcv) ENTRY_SAME(msgget) /* 190 */ - ENTRY_SAME(msgctl) - ENTRY_SAME(shmat) + ENTRY_COMP(msgctl) + ENTRY_COMP(shmat) ENTRY_SAME(shmdt) ENTRY_SAME(shmget) - ENTRY_SAME(shmctl) /* 195 */ + ENTRY_COMP(shmctl) /* 195 */ ENTRY_SAME(ni_syscall) /* streams1 */ ENTRY_SAME(ni_syscall) /* streams2 */ ENTRY_SAME(lstat64) @@ -323,7 +323,7 @@ ENTRY_SAME(epoll_ctl) /* 225 */ ENTRY_SAME(epoll_wait) ENTRY_SAME(remap_file_pages) - ENTRY_SAME(semtimedop) + ENTRY_COMP(semtimedop) ENTRY_COMP(mq_open) ENTRY_SAME(mq_unlink) /* 230 */ ENTRY_COMP(mq_timedsend) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index ee3c6608126a..ad16bc90503e 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -126,6 +126,7 @@ config PPC select HAVE_BPF_JIT if PPC64 select HAVE_ARCH_JUMP_LABEL select ARCH_HAVE_NMI_SAFE_CMPXCHG + select ARCH_HAS_GCOV_PROFILE_ALL select GENERIC_SMP_IDLE_THREAD select GENERIC_CMOS_UPDATE select GENERIC_TIME_VSYSCALL_OLD diff --git a/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi b/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi index 1382fec9e8c5..7fcb1ac0f232 100644 --- a/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi @@ -50,6 +50,7 @@ ethernet@b0000 { fsl,num_tx_queues = <0x8>; fsl,magic-packet; local-mac-address = [ 00 00 00 00 00 00 ]; + ranges; queue-group@b0000 { #address-cells = <1>; diff --git a/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi b/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi index 221cd2ea5b31..9f25427c1527 100644 --- a/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi +++ b/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi @@ -50,6 +50,7 @@ ethernet@b1000 { fsl,num_tx_queues = <0x8>; fsl,magic-packet; local-mac-address = [ 00 00 00 00 00 00 ]; + ranges; queue-group@b1000 { #address-cells = <1>; diff --git a/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi b/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi index 61456c317609..cd7c318ab131 100644 --- a/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi +++ b/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi @@ -49,6 +49,7 @@ ethernet@b2000 { fsl,num_tx_queues = <0x8>; fsl,magic-packet; local-mac-address = [ 00 00 00 00 00 00 ]; + ranges; queue-group@b2000 { #address-cells = <1>; diff --git a/arch/powerpc/crypto/sha1.c b/arch/powerpc/crypto/sha1.c index f9e8b9491efc..b51da9132744 100644 --- a/arch/powerpc/crypto/sha1.c +++ b/arch/powerpc/crypto/sha1.c @@ -154,4 +154,5 @@ module_exit(sha1_powerpc_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm"); -MODULE_ALIAS("sha1-powerpc"); +MODULE_ALIAS_CRYPTO("sha1"); +MODULE_ALIAS_CRYPTO("sha1-powerpc"); diff --git a/arch/powerpc/include/asm/dcr-mmio.h b/arch/powerpc/include/asm/dcr-mmio.h index acd491dbd45a..93a68b28e695 100644 --- a/arch/powerpc/include/asm/dcr-mmio.h +++ b/arch/powerpc/include/asm/dcr-mmio.h @@ -51,10 +51,6 @@ static inline void dcr_write_mmio(dcr_host_mmio_t host, out_be32(host.token + ((host.base + dcr_n) * host.stride), value); } -extern u64 of_translate_dcr_address(struct device_node *dev, - unsigned int dcr_n, - unsigned int *stride); - #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_DCR_MMIO_H */ diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index 279b80f3bb29..c0c61fa9cd9e 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -47,6 +47,12 @@ STACK_FRAME_OVERHEAD + KERNEL_REDZONE_SIZE) #define STACK_FRAME_MARKER 12 +#if defined(_CALL_ELF) && _CALL_ELF == 2 +#define STACK_FRAME_MIN_SIZE 32 +#else +#define STACK_FRAME_MIN_SIZE STACK_FRAME_OVERHEAD +#endif + /* Size of dummy stack frame allocated when calling signal handler. */ #define __SIGNAL_FRAMESIZE 128 #define __SIGNAL_FRAMESIZE32 64 @@ -60,6 +66,7 @@ #define STACK_FRAME_REGS_MARKER ASM_CONST(0x72656773) #define STACK_INT_FRAME_SIZE (sizeof(struct pt_regs) + STACK_FRAME_OVERHEAD) #define STACK_FRAME_MARKER 2 +#define STACK_FRAME_MIN_SIZE STACK_FRAME_OVERHEAD /* Size of stack frame allocated when calling signal handler. */ #define __SIGNAL_FRAMESIZE 64 diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index 35aa339410bd..4dbe072eecbe 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -61,6 +61,7 @@ static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) static inline int arch_spin_is_locked(arch_spinlock_t *lock) { + smp_mb(); return !arch_spin_value_unlocked(*lock); } diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 38d507306a11..5193116eadc0 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1422,7 +1422,7 @@ machine_check_handle_early: bne 9f /* continue in V mode if we are. */ 5: -#ifdef CONFIG_KVM_BOOK3S_64_HV +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER /* * We are coming from kernel context. Check if we are coming from * guest. if yes, then we can continue. We will fall through diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index 27c93f41166f..fc0927a162ff 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -78,7 +78,7 @@ static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits) } if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) { if (cur_cpu_spec && cur_cpu_spec->flush_tlb) - cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE); + cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET); /* reset error bits */ dsisr &= ~P7_DSISR_MC_TLB_MULTIHIT_MFTLB; } @@ -109,7 +109,7 @@ static long mce_handle_common_ierror(uint64_t srr1) break; case P7_SRR1_MC_IFETCH_TLB_MULTIHIT: if (cur_cpu_spec && cur_cpu_spec->flush_tlb) { - cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE); + cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET); handled = 1; } break; diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 8dd5a093195b..05b549fcb9fd 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -838,76 +838,6 @@ int cpu_to_chip_id(int cpu) } EXPORT_SYMBOL(cpu_to_chip_id); -#ifdef CONFIG_PPC_PSERIES -/* - * Fix up the uninitialized fields in a new device node: - * name, type and pci-specific fields - */ - -static int of_finish_dynamic_node(struct device_node *node) -{ - struct device_node *parent = of_get_parent(node); - int err = 0; - const phandle *ibm_phandle; - - node->name = of_get_property(node, "name", NULL); - node->type = of_get_property(node, "device_type", NULL); - - if (!node->name) - node->name = "<NULL>"; - if (!node->type) - node->type = "<NULL>"; - - if (!parent) { - err = -ENODEV; - goto out; - } - - /* We don't support that function on PowerMac, at least - * not yet - */ - if (machine_is(powermac)) - return -ENODEV; - - /* fix up new node's phandle field */ - if ((ibm_phandle = of_get_property(node, "ibm,phandle", NULL))) - node->phandle = *ibm_phandle; - -out: - of_node_put(parent); - return err; -} - -static int prom_reconfig_notifier(struct notifier_block *nb, - unsigned long action, void *node) -{ - int err; - - switch (action) { - case OF_RECONFIG_ATTACH_NODE: - err = of_finish_dynamic_node(node); - if (err < 0) - printk(KERN_ERR "finish_node returned %d\n", err); - break; - default: - err = 0; - break; - } - return notifier_from_errno(err); -} - -static struct notifier_block prom_reconfig_nb = { - .notifier_call = prom_reconfig_notifier, - .priority = 10, /* This one needs to run first */ -}; - -static int __init prom_reconfig_setup(void) -{ - return of_reconfig_notifier_register(&prom_reconfig_nb); -} -__initcall(prom_reconfig_setup); -#endif - bool arch_match_cpu_phys_id(int cpu, u64 phys_id) { return (int)phys_id == get_hard_smp_processor_id(cpu); diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c index 75702e207b29..f7089fcfaa5d 100644 --- a/arch/powerpc/kernel/udbg_16550.c +++ b/arch/powerpc/kernel/udbg_16550.c @@ -69,8 +69,12 @@ static void udbg_uart_putc(char c) static int udbg_uart_getc_poll(void) { - if (!udbg_uart_in || !(udbg_uart_in(UART_LSR) & LSR_DR)) + if (!udbg_uart_in) + return -1; + + if (!(udbg_uart_in(UART_LSR) & LSR_DR)) return udbg_uart_in(UART_RBR); + return -1; } diff --git a/arch/powerpc/kernel/vdso32/getcpu.S b/arch/powerpc/kernel/vdso32/getcpu.S index 47afd08c90f7..fe7e97a1aad9 100644 --- a/arch/powerpc/kernel/vdso32/getcpu.S +++ b/arch/powerpc/kernel/vdso32/getcpu.S @@ -30,8 +30,8 @@ V_FUNCTION_BEGIN(__kernel_getcpu) .cfi_startproc mfspr r5,SPRN_USPRG3 - cmpdi cr0,r3,0 - cmpdi cr1,r4,0 + cmpwi cr0,r3,0 + cmpwi cr1,r4,0 clrlwi r6,r5,16 rlwinm r7,r5,16,31-15,31-0 beq cr0,1f diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c index 0c9c8d7d0734..170a0346f756 100644 --- a/arch/powerpc/lib/locks.c +++ b/arch/powerpc/lib/locks.c @@ -70,12 +70,16 @@ void __rw_yield(arch_rwlock_t *rw) void arch_spin_unlock_wait(arch_spinlock_t *lock) { + smp_mb(); + while (lock->slock) { HMT_low(); if (SHARED_PROCESSOR) __spin_yield(lock); } HMT_medium(); + + smp_mb(); } EXPORT_SYMBOL(arch_spin_unlock_wait); diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index a5fff173be4f..c3ab060b94b2 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1659,12 +1659,11 @@ static void stage_topology_update(int core_id) static int dt_update_callback(struct notifier_block *nb, unsigned long action, void *data) { - struct of_prop_reconfig *update; + struct of_reconfig_data *update = data; int rc = NOTIFY_DONE; switch (action) { case OF_RECONFIG_UPDATE_PROPERTY: - update = (struct of_prop_reconfig *)data; if (!of_prop_cmp(update->dn->type, "cpu") && !of_prop_cmp(update->prop->name, "ibm,associativity")) { u32 core_id; diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c index 74d1e780748b..2396dda282cd 100644 --- a/arch/powerpc/perf/callchain.c +++ b/arch/powerpc/perf/callchain.c @@ -35,7 +35,7 @@ static int valid_next_sp(unsigned long sp, unsigned long prev_sp) return 0; /* must be 16-byte aligned */ if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD)) return 0; - if (sp >= prev_sp + STACK_FRAME_OVERHEAD) + if (sp >= prev_sp + STACK_FRAME_MIN_SIZE) return 1; /* * sp could decrease when we jump off an interrupt stack diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index beedaf0c5e75..d558b8595e6f 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -902,7 +902,6 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, unsigned int is_64, struct msi_msg *msg) { struct pnv_ioda_pe *pe = pnv_ioda_get_pe(dev); - struct pci_dn *pdn = pci_get_pdn(dev); struct irq_data *idata; struct irq_chip *ichip; unsigned int xive_num = hwirq - phb->msi_base; @@ -918,7 +917,7 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, return -ENXIO; /* Force 32-bit MSI on some broken devices */ - if (pdn && pdn->force_32bit_msi) + if (dev->no_64bit_msi) is_64 = 0; /* Assign XIVE to PE */ diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 8518817dcdfd..52c1162bcee3 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -1,3 +1,4 @@ + /* * Support PCI/PCIe on PowerNV platforms * @@ -50,9 +51,8 @@ static int pnv_msi_check_device(struct pci_dev* pdev, int nvec, int type) { struct pci_controller *hose = pci_bus_to_host(pdev->bus); struct pnv_phb *phb = hose->private_data; - struct pci_dn *pdn = pci_get_pdn(pdev); - if (pdn && pdn->force_32bit_msi && !phb->msi32_support) + if (pdev->no_64bit_msi && !phb->msi32_support) return -ENODEV; return (phb && phb->msi_bmp.bitmap) ? 0 : -ENODEV; diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index a8fe5aa3d34f..e27681d97fc1 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -11,7 +11,6 @@ */ #include <linux/kernel.h> -#include <linux/kref.h> #include <linux/notifier.h> #include <linux/spinlock.h> #include <linux/cpu.h> @@ -87,7 +86,6 @@ static struct device_node *dlpar_parse_cc_node(struct cc_workarea *ccwa, } of_node_set_flag(dn, OF_DYNAMIC); - kref_init(&dn->kref); return dn; } @@ -380,7 +378,7 @@ static int dlpar_online_cpu(struct device_node *dn) BUG_ON(get_cpu_current_state(cpu) != CPU_STATE_OFFLINE); cpu_maps_update_done(); - rc = cpu_up(cpu); + rc = device_online(get_cpu_device(cpu)); if (rc) goto out; cpu_maps_update_begin(); @@ -463,7 +461,7 @@ static int dlpar_offline_cpu(struct device_node *dn) if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) { set_preferred_offline_state(cpu, CPU_STATE_OFFLINE); cpu_maps_update_done(); - rc = cpu_down(cpu); + rc = device_offline(get_cpu_device(cpu)); if (rc) goto out; cpu_maps_update_begin(); diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 2d6fe89ff89d..d6eb25961211 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -338,16 +338,17 @@ static void pseries_remove_processor(struct device_node *np) } static int pseries_smp_notifier(struct notifier_block *nb, - unsigned long action, void *node) + unsigned long action, void *data) { + struct of_reconfig_data *rd = data; int err = 0; switch (action) { case OF_RECONFIG_ATTACH_NODE: - err = pseries_add_processor(node); + err = pseries_add_processor(rd->dn); break; case OF_RECONFIG_DETACH_NODE: - pseries_remove_processor(node); + pseries_remove_processor(rd->dn); break; } return notifier_from_errno(err); diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index b9a82042760f..f25c36220aef 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -200,7 +200,7 @@ static int pseries_add_memory(struct device_node *np) return (ret < 0) ? -EINVAL : 0; } -static int pseries_update_drconf_memory(struct of_prop_reconfig *pr) +static int pseries_update_drconf_memory(struct of_reconfig_data *pr) { struct of_drconf_cell *new_drmem, *old_drmem; unsigned long memblock_size; @@ -212,7 +212,7 @@ static int pseries_update_drconf_memory(struct of_prop_reconfig *pr) if (!memblock_size) return -EINVAL; - p = (u32 *)of_get_property(pr->dn, "ibm,dynamic-memory", NULL); + p = (u32 *) pr->old_prop->value; if (!p) return -EINVAL; @@ -247,9 +247,9 @@ static int pseries_update_drconf_memory(struct of_prop_reconfig *pr) } static int pseries_memory_notifier(struct notifier_block *nb, - unsigned long action, void *node) + unsigned long action, void *data) { - struct of_prop_reconfig *pr; + struct of_reconfig_data *rd = data; int err = 0; switch (action) { @@ -260,9 +260,8 @@ static int pseries_memory_notifier(struct notifier_block *nb, err = pseries_remove_memory(node); break; case OF_RECONFIG_UPDATE_PROPERTY: - pr = (struct of_prop_reconfig *)node; - if (!strcmp(pr->prop->name, "ibm,dynamic-memory")) - err = pseries_update_drconf_memory(pr); + if (!strcmp(rd->prop->name, "ibm,dynamic-memory")) + err = pseries_update_drconf_memory(rd); break; } return notifier_from_errno(err); diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 4642d6a4d356..31a3308ab939 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -329,16 +329,16 @@ struct direct_window { /* Dynamic DMA Window support */ struct ddw_query_response { - __be32 windows_available; - __be32 largest_available_block; - __be32 page_size; - __be32 migration_capable; + u32 windows_available; + u32 largest_available_block; + u32 page_size; + u32 migration_capable; }; struct ddw_create_response { - __be32 liobn; - __be32 addr_hi; - __be32 addr_lo; + u32 liobn; + u32 addr_hi; + u32 addr_lo; }; static LIST_HEAD(direct_window_list); @@ -725,16 +725,18 @@ static void remove_ddw(struct device_node *np, bool remove_prop) { struct dynamic_dma_window_prop *dwp; struct property *win64; - const u32 *ddw_avail; + u32 ddw_avail[3]; u64 liobn; - int len, ret = 0; + int ret = 0; + + ret = of_property_read_u32_array(np, "ibm,ddw-applicable", + &ddw_avail[0], 3); - ddw_avail = of_get_property(np, "ibm,ddw-applicable", &len); win64 = of_find_property(np, DIRECT64_PROPNAME, NULL); if (!win64) return; - if (!ddw_avail || len < 3 * sizeof(u32) || win64->length < sizeof(*dwp)) + if (ret || win64->length < sizeof(*dwp)) goto delprop; dwp = win64->value; @@ -872,8 +874,9 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail, do { /* extra outputs are LIOBN and dma-addr (hi, lo) */ - ret = rtas_call(ddw_avail[1], 5, 4, (u32 *)create, cfg_addr, - BUID_HI(buid), BUID_LO(buid), page_shift, window_shift); + ret = rtas_call(ddw_avail[1], 5, 4, (u32 *)create, + cfg_addr, BUID_HI(buid), BUID_LO(buid), + page_shift, window_shift); } while (rtas_busy_delay(ret)); dev_info(&dev->dev, "ibm,create-pe-dma-window(%x) %x %x %x %x %x returned %d " @@ -910,7 +913,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) int page_shift; u64 dma_addr, max_addr; struct device_node *dn; - const u32 *uninitialized_var(ddw_avail); + u32 ddw_avail[3]; struct direct_window *window; struct property *win64; struct dynamic_dma_window_prop *ddwprop; @@ -942,8 +945,9 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) * for the given node in that order. * the property is actually in the parent, not the PE */ - ddw_avail = of_get_property(pdn, "ibm,ddw-applicable", &len); - if (!ddw_avail || len < 3 * sizeof(u32)) + ret = of_property_read_u32_array(pdn, "ibm,ddw-applicable", + &ddw_avail[0], 3); + if (ret) goto out_failed; /* @@ -966,11 +970,11 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) dev_dbg(&dev->dev, "no free dynamic windows"); goto out_failed; } - if (be32_to_cpu(query.page_size) & 4) { + if (query.page_size & 4) { page_shift = 24; /* 16MB */ - } else if (be32_to_cpu(query.page_size) & 2) { + } else if (query.page_size & 2) { page_shift = 16; /* 64kB */ - } else if (be32_to_cpu(query.page_size) & 1) { + } else if (query.page_size & 1) { page_shift = 12; /* 4kB */ } else { dev_dbg(&dev->dev, "no supported direct page size in mask %x", @@ -980,7 +984,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) /* verify the window * number of ptes will map the partition */ /* check largest block * page size > max memory hotplug addr */ max_addr = memory_hotplug_max(); - if (be32_to_cpu(query.largest_available_block) < (max_addr >> page_shift)) { + if (query.largest_available_block < (max_addr >> page_shift)) { dev_dbg(&dev->dev, "can't map partiton max 0x%llx with %u " "%llu-sized pages\n", max_addr, query.largest_available_block, 1ULL << page_shift); @@ -1006,8 +1010,9 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) if (ret != 0) goto out_free_prop; - ddwprop->liobn = create.liobn; - ddwprop->dma_base = cpu_to_be64(of_read_number(&create.addr_hi, 2)); + ddwprop->liobn = cpu_to_be32(create.liobn); + ddwprop->dma_base = cpu_to_be64(((u64)create.addr_hi << 32) | + create.addr_lo); ddwprop->tce_shift = cpu_to_be32(page_shift); ddwprop->window_shift = cpu_to_be32(len); @@ -1039,7 +1044,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) list_add(&window->list, &direct_window_list); spin_unlock(&direct_window_list_lock); - dma_addr = of_read_number(&create.addr_hi, 2); + dma_addr = be64_to_cpu(ddwprop->dma_base); goto out_unlock; out_free_window: @@ -1247,10 +1252,11 @@ static struct notifier_block iommu_mem_nb = { .notifier_call = iommu_mem_notifier, }; -static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long action, void *node) +static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long action, void *data) { int err = NOTIFY_OK; - struct device_node *np = node; + struct of_reconfig_data *rd = data; + struct device_node *np = rd->dn; struct pci_dn *pci = PCI_DN(np); struct direct_window *window; diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index cde4e0a095ae..bf3829242aff 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -24,10 +24,10 @@ static struct kobject *mobility_kobj; struct update_props_workarea { - u32 phandle; - u32 state; - u64 reserved; - u32 nprops; + __be32 phandle; + __be32 state; + __be64 reserved; + __be32 nprops; } __packed; #define NODE_ACTION_MASK 0xff000000 @@ -53,11 +53,11 @@ static int mobility_rtas_call(int token, char *buf, s32 scope) return rc; } -static int delete_dt_node(u32 phandle) +static int delete_dt_node(__be32 phandle) { struct device_node *dn; - dn = of_find_node_by_phandle(phandle); + dn = of_find_node_by_phandle(be32_to_cpu(phandle)); if (!dn) return -ENOENT; @@ -126,7 +126,7 @@ static int update_dt_property(struct device_node *dn, struct property **prop, return 0; } -static int update_dt_node(u32 phandle, s32 scope) +static int update_dt_node(__be32 phandle, s32 scope) { struct update_props_workarea *upwa; struct device_node *dn; @@ -135,6 +135,7 @@ static int update_dt_node(u32 phandle, s32 scope) char *prop_data; char *rtas_buf; int update_properties_token; + u32 nprops; u32 vd; update_properties_token = rtas_token("ibm,update-properties"); @@ -145,7 +146,7 @@ static int update_dt_node(u32 phandle, s32 scope) if (!rtas_buf) return -ENOMEM; - dn = of_find_node_by_phandle(phandle); + dn = of_find_node_by_phandle(be32_to_cpu(phandle)); if (!dn) { kfree(rtas_buf); return -ENOENT; @@ -161,6 +162,7 @@ static int update_dt_node(u32 phandle, s32 scope) break; prop_data = rtas_buf + sizeof(*upwa); + nprops = be32_to_cpu(upwa->nprops); /* On the first call to ibm,update-properties for a node the * the first property value descriptor contains an empty @@ -169,17 +171,17 @@ static int update_dt_node(u32 phandle, s32 scope) */ if (*prop_data == 0) { prop_data++; - vd = *(u32 *)prop_data; + vd = be32_to_cpu(*(__be32 *)prop_data); prop_data += vd + sizeof(vd); - upwa->nprops--; + nprops--; } - for (i = 0; i < upwa->nprops; i++) { + for (i = 0; i < nprops; i++) { char *prop_name; prop_name = prop_data; prop_data += strlen(prop_name) + 1; - vd = *(u32 *)prop_data; + vd = be32_to_cpu(*(__be32 *)prop_data); prop_data += sizeof(vd); switch (vd) { @@ -211,13 +213,13 @@ static int update_dt_node(u32 phandle, s32 scope) return 0; } -static int add_dt_node(u32 parent_phandle, u32 drc_index) +static int add_dt_node(__be32 parent_phandle, __be32 drc_index) { struct device_node *dn; struct device_node *parent_dn; int rc; - parent_dn = of_find_node_by_phandle(parent_phandle); + parent_dn = of_find_node_by_phandle(be32_to_cpu(parent_phandle)); if (!parent_dn) return -ENOENT; @@ -236,7 +238,7 @@ static int add_dt_node(u32 parent_phandle, u32 drc_index) int pseries_devicetree_update(s32 scope) { char *rtas_buf; - u32 *data; + __be32 *data; int update_nodes_token; int rc; @@ -253,17 +255,17 @@ int pseries_devicetree_update(s32 scope) if (rc && rc != 1) break; - data = (u32 *)rtas_buf + 4; - while (*data & NODE_ACTION_MASK) { + data = (__be32 *)rtas_buf + 4; + while (be32_to_cpu(*data) & NODE_ACTION_MASK) { int i; - u32 action = *data & NODE_ACTION_MASK; - int node_count = *data & NODE_COUNT_MASK; + u32 action = be32_to_cpu(*data) & NODE_ACTION_MASK; + u32 node_count = be32_to_cpu(*data) & NODE_COUNT_MASK; data++; for (i = 0; i < node_count; i++) { - u32 phandle = *data++; - u32 drc_index; + __be32 phandle = *data++; + __be32 drc_index; switch (action) { case DELETE_DT_NODE: diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index 0c882e83c4ce..6849d85ea0d5 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -428,7 +428,7 @@ static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type) */ again: if (type == PCI_CAP_ID_MSI) { - if (pdn->force_32bit_msi) { + if (pdev->no_64bit_msi) { rc = rtas_change_msi(pdn, RTAS_CHANGE_32MSI_FN, nvec); if (rc < 0) { /* diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c index f93cdf55628c..0435bb65d0aa 100644 --- a/arch/powerpc/platforms/pseries/reconfig.c +++ b/arch/powerpc/platforms/pseries/reconfig.c @@ -12,7 +12,6 @@ */ #include <linux/kernel.h> -#include <linux/kref.h> #include <linux/notifier.h> #include <linux/proc_fs.h> #include <linux/slab.h> @@ -70,7 +69,6 @@ static int pSeries_reconfig_add_node(const char *path, struct property *proplist np->properties = proplist; of_node_set_flag(np, OF_DYNAMIC); - kref_init(&np->kref); np->parent = derive_parent(path); if (IS_ERR(np->parent)) { diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 0b84df948ed6..7649bee48b09 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -253,9 +253,10 @@ static void __init pseries_discover_pic(void) " interrupt-controller\n"); } -static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long action, void *node) +static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long action, void *data) { - struct device_node *np = node; + struct of_reconfig_data *rd = data; + struct device_node *np = rd->dn; struct pci_dn *pci = NULL; int err = NOTIFY_OK; diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c index 47b6b9f81d43..830edc83c12a 100644 --- a/arch/powerpc/sysdev/axonram.c +++ b/arch/powerpc/sysdev/axonram.c @@ -156,7 +156,7 @@ axon_ram_direct_access(struct block_device *device, sector_t sector, } *kaddr = (void *)(bank->ph_addr + offset); - *pfn = virt_to_phys(kaddr) >> PAGE_SHIFT; + *pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT; return 0; } diff --git a/arch/powerpc/sysdev/dcr.c b/arch/powerpc/sysdev/dcr.c index 1bd0eba4d355..e9056e438575 100644 --- a/arch/powerpc/sysdev/dcr.c +++ b/arch/powerpc/sysdev/dcr.c @@ -152,9 +152,9 @@ EXPORT_SYMBOL_GPL(dcr_resource_len); #ifdef CONFIG_PPC_DCR_MMIO -u64 of_translate_dcr_address(struct device_node *dev, - unsigned int dcr_n, - unsigned int *out_stride) +static u64 of_translate_dcr_address(struct device_node *dev, + unsigned int dcr_n, + unsigned int *out_stride) { struct device_node *dp; const u32 *p; diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c index 0968b66b4cf9..8ba60424be95 100644 --- a/arch/powerpc/sysdev/msi_bitmap.c +++ b/arch/powerpc/sysdev/msi_bitmap.c @@ -202,7 +202,7 @@ void __init test_of_node(void) /* There should really be a struct device_node allocator */ memset(&of_node, 0, sizeof(of_node)); - kref_init(&of_node.kref); + kref_init(&of_node.kobj.kref); of_node.full_name = node_name; check(0 == msi_bitmap_alloc(&bmp, size, &of_node)); diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index b07909850f77..f89389f634d7 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -288,10 +288,11 @@ static inline void disable_surveillance(void) args.token = rtas_token("set-indicator"); if (args.token == RTAS_UNKNOWN_SERVICE) return; - args.nargs = 3; - args.nret = 1; + args.token = cpu_to_be32(args.token); + args.nargs = cpu_to_be32(3); + args.nret = cpu_to_be32(1); args.rets = &args.args[3]; - args.args[0] = SURVEILLANCE_TOKEN; + args.args[0] = cpu_to_be32(SURVEILLANCE_TOKEN); args.args[1] = 0; args.args[2] = 0; enter_rtas(__pa(&args)); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index a0a3bed6e4dc..51b6516684db 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -63,6 +63,7 @@ config S390 select ARCH_DISCARD_MEMBLOCK select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS + select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_INLINE_READ_LOCK select ARCH_INLINE_READ_LOCK_BH diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index 23223cd63e54..1f272b24fc0b 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -979,7 +979,7 @@ static void __exit aes_s390_fini(void) module_init(aes_s390_init); module_exit(aes_s390_fini); -MODULE_ALIAS("aes-all"); +MODULE_ALIAS_CRYPTO("aes-all"); MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm"); MODULE_LICENSE("GPL"); diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c index 7acb77f7ef1a..9e05cc453a40 100644 --- a/arch/s390/crypto/des_s390.c +++ b/arch/s390/crypto/des_s390.c @@ -619,8 +619,8 @@ static void __exit des_s390_exit(void) module_init(des_s390_init); module_exit(des_s390_exit); -MODULE_ALIAS("des"); -MODULE_ALIAS("des3_ede"); +MODULE_ALIAS_CRYPTO("des"); +MODULE_ALIAS_CRYPTO("des3_ede"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("DES & Triple DES EDE Cipher Algorithms"); diff --git a/arch/s390/crypto/ghash_s390.c b/arch/s390/crypto/ghash_s390.c index d43485d142e9..7940dc90e80b 100644 --- a/arch/s390/crypto/ghash_s390.c +++ b/arch/s390/crypto/ghash_s390.c @@ -160,7 +160,7 @@ static void __exit ghash_mod_exit(void) module_init(ghash_mod_init); module_exit(ghash_mod_exit); -MODULE_ALIAS("ghash"); +MODULE_ALIAS_CRYPTO("ghash"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("GHASH Message Digest Algorithm, s390 implementation"); diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c index a1b3a9dc9d8a..5b2bee323694 100644 --- a/arch/s390/crypto/sha1_s390.c +++ b/arch/s390/crypto/sha1_s390.c @@ -103,6 +103,6 @@ static void __exit sha1_s390_fini(void) module_init(sha1_s390_init); module_exit(sha1_s390_fini); -MODULE_ALIAS("sha1"); +MODULE_ALIAS_CRYPTO("sha1"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm"); diff --git a/arch/s390/crypto/sha256_s390.c b/arch/s390/crypto/sha256_s390.c index 9b853809a492..b74ff158108c 100644 --- a/arch/s390/crypto/sha256_s390.c +++ b/arch/s390/crypto/sha256_s390.c @@ -143,7 +143,7 @@ static void __exit sha256_s390_fini(void) module_init(sha256_s390_init); module_exit(sha256_s390_fini); -MODULE_ALIAS("sha256"); -MODULE_ALIAS("sha224"); +MODULE_ALIAS_CRYPTO("sha256"); +MODULE_ALIAS_CRYPTO("sha224"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA256 and SHA224 Secure Hash Algorithm"); diff --git a/arch/s390/crypto/sha512_s390.c b/arch/s390/crypto/sha512_s390.c index 32a81383b69c..0c36989ba182 100644 --- a/arch/s390/crypto/sha512_s390.c +++ b/arch/s390/crypto/sha512_s390.c @@ -86,7 +86,7 @@ static struct shash_alg sha512_alg = { } }; -MODULE_ALIAS("sha512"); +MODULE_ALIAS_CRYPTO("sha512"); static int sha384_init(struct shash_desc *desc) { @@ -126,7 +126,7 @@ static struct shash_alg sha384_alg = { } }; -MODULE_ALIAS("sha384"); +MODULE_ALIAS_CRYPTO("sha384"); static int __init init(void) { diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index db02052bd137..5426c9eb5114 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -245,7 +245,7 @@ asmlinkage long sys32_setgroups16(int gidsetsize, u16 __user *grouplist) struct group_info *group_info; int retval; - if (!capable(CAP_SETGID)) + if (!may_setgroups()) return -EPERM; if ((unsigned)gidsetsize > NGROUPS_MAX) return -EINVAL; diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 3584ed9b20a1..e309c5c41158 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -810,11 +810,21 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep; down_read(&mm->mmap_sem); +retry: ptep = get_locked_pte(current->mm, addr, &ptl); if (unlikely(!ptep)) { up_read(&mm->mmap_sem); return -EFAULT; } + if (!(pte_val(*ptep) & _PAGE_INVALID) && + (pte_val(*ptep) & _PAGE_PROTECT)) { + pte_unmap_unlock(*ptep, ptl); + if (fixup_user_fault(current, mm, addr, FAULT_FLAG_WRITE)) { + up_read(&mm->mmap_sem); + return -EFAULT; + } + goto retry; + } new = old = pgste_get_lock(ptep); pgste_val(new) &= ~(PGSTE_GR_BIT | PGSTE_GC_BIT | diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 6357710753d5..4032f9268436 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -16,6 +16,7 @@ config SUPERH select HAVE_DEBUG_BUGVERBOSE select ARCH_HAVE_CUSTOM_GPIO_H select ARCH_HAVE_NMI_SAFE_CMPXCHG if (GUSA_RB || CPU_SH4A) + select ARCH_HAS_GCOV_PROFILE_ALL select PERF_USE_VMALLOC select HAVE_DEBUG_KMEMLEAK select HAVE_KERNEL_GZIP diff --git a/arch/sh/kernel/cpu/sh3/setup-sh770x.c b/arch/sh/kernel/cpu/sh3/setup-sh770x.c index ff1465c0519c..5acf89c1afc5 100644 --- a/arch/sh/kernel/cpu/sh3/setup-sh770x.c +++ b/arch/sh/kernel/cpu/sh3/setup-sh770x.c @@ -118,7 +118,7 @@ static struct plat_sci_port scif0_platform_data = { }; static struct resource scif0_resources[] = { - DEFINE_RES_MEM(0xfffffe80, 0x100), + DEFINE_RES_MEM(0xfffffe80, 0x10), DEFINE_RES_IRQ(evt2irq(0x4e0)), }; @@ -143,7 +143,7 @@ static struct plat_sci_port scif1_platform_data = { }; static struct resource scif1_resources[] = { - DEFINE_RES_MEM(0xa4000150, 0x100), + DEFINE_RES_MEM(0xa4000150, 0x10), DEFINE_RES_IRQ(evt2irq(0x900)), }; @@ -169,7 +169,7 @@ static struct plat_sci_port scif2_platform_data = { }; static struct resource scif2_resources[] = { - DEFINE_RES_MEM(0xa4000140, 0x100), + DEFINE_RES_MEM(0xa4000140, 0x10), DEFINE_RES_IRQ(evt2irq(0x880)), }; diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index b398c68b2713..a38513c33a62 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -67,6 +67,7 @@ config SPARC64 select HAVE_SYSCALL_TRACEPOINTS select HAVE_CONTEXT_TRACKING select HAVE_DEBUG_KMEMLEAK + select SPARSE_IRQ select RTC_DRV_CMOS select RTC_DRV_BQ4802 select RTC_DRV_SUN4V diff --git a/arch/sparc/crypto/aes_glue.c b/arch/sparc/crypto/aes_glue.c index 503e6d96ad4e..ded4cee35318 100644 --- a/arch/sparc/crypto/aes_glue.c +++ b/arch/sparc/crypto/aes_glue.c @@ -499,6 +499,6 @@ module_exit(aes_sparc64_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("AES Secure Hash Algorithm, sparc64 aes opcode accelerated"); -MODULE_ALIAS("aes"); +MODULE_ALIAS_CRYPTO("aes"); #include "crop_devid.c" diff --git a/arch/sparc/crypto/camellia_glue.c b/arch/sparc/crypto/camellia_glue.c index 888f6260b4ec..641f55cb61c3 100644 --- a/arch/sparc/crypto/camellia_glue.c +++ b/arch/sparc/crypto/camellia_glue.c @@ -322,6 +322,6 @@ module_exit(camellia_sparc64_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Camellia Cipher Algorithm, sparc64 camellia opcode accelerated"); -MODULE_ALIAS("aes"); +MODULE_ALIAS_CRYPTO("aes"); #include "crop_devid.c" diff --git a/arch/sparc/crypto/crc32c_glue.c b/arch/sparc/crypto/crc32c_glue.c index 5162fad912ce..d1064e46efe8 100644 --- a/arch/sparc/crypto/crc32c_glue.c +++ b/arch/sparc/crypto/crc32c_glue.c @@ -176,6 +176,6 @@ module_exit(crc32c_sparc64_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("CRC32c (Castagnoli), sparc64 crc32c opcode accelerated"); -MODULE_ALIAS("crc32c"); +MODULE_ALIAS_CRYPTO("crc32c"); #include "crop_devid.c" diff --git a/arch/sparc/crypto/des_glue.c b/arch/sparc/crypto/des_glue.c index 3065bc61f9d3..d11500972994 100644 --- a/arch/sparc/crypto/des_glue.c +++ b/arch/sparc/crypto/des_glue.c @@ -532,6 +532,6 @@ module_exit(des_sparc64_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("DES & Triple DES EDE Cipher Algorithms, sparc64 des opcode accelerated"); -MODULE_ALIAS("des"); +MODULE_ALIAS_CRYPTO("des"); #include "crop_devid.c" diff --git a/arch/sparc/crypto/md5_glue.c b/arch/sparc/crypto/md5_glue.c index 09a9ea1dfb69..64c7ff5f72a9 100644 --- a/arch/sparc/crypto/md5_glue.c +++ b/arch/sparc/crypto/md5_glue.c @@ -185,6 +185,6 @@ module_exit(md5_sparc64_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("MD5 Secure Hash Algorithm, sparc64 md5 opcode accelerated"); -MODULE_ALIAS("md5"); +MODULE_ALIAS_CRYPTO("md5"); #include "crop_devid.c" diff --git a/arch/sparc/crypto/sha1_glue.c b/arch/sparc/crypto/sha1_glue.c index 6cd5f29e1e0d..1b3e47accc74 100644 --- a/arch/sparc/crypto/sha1_glue.c +++ b/arch/sparc/crypto/sha1_glue.c @@ -180,6 +180,6 @@ module_exit(sha1_sparc64_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, sparc64 sha1 opcode accelerated"); -MODULE_ALIAS("sha1"); +MODULE_ALIAS_CRYPTO("sha1"); #include "crop_devid.c" diff --git a/arch/sparc/crypto/sha256_glue.c b/arch/sparc/crypto/sha256_glue.c index 04f555ab2680..41f27cca2a22 100644 --- a/arch/sparc/crypto/sha256_glue.c +++ b/arch/sparc/crypto/sha256_glue.c @@ -237,7 +237,7 @@ module_exit(sha256_sparc64_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA-224 and SHA-256 Secure Hash Algorithm, sparc64 sha256 opcode accelerated"); -MODULE_ALIAS("sha224"); -MODULE_ALIAS("sha256"); +MODULE_ALIAS_CRYPTO("sha224"); +MODULE_ALIAS_CRYPTO("sha256"); #include "crop_devid.c" diff --git a/arch/sparc/crypto/sha512_glue.c b/arch/sparc/crypto/sha512_glue.c index f04d1994d19a..9fff88541b8c 100644 --- a/arch/sparc/crypto/sha512_glue.c +++ b/arch/sparc/crypto/sha512_glue.c @@ -222,7 +222,7 @@ module_exit(sha512_sparc64_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA-384 and SHA-512 Secure Hash Algorithm, sparc64 sha512 opcode accelerated"); -MODULE_ALIAS("sha384"); -MODULE_ALIAS("sha512"); +MODULE_ALIAS_CRYPTO("sha384"); +MODULE_ALIAS_CRYPTO("sha512"); #include "crop_devid.c" diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h index 905832aa9e9e..a0ed182ae73c 100644 --- a/arch/sparc/include/asm/atomic_32.h +++ b/arch/sparc/include/asm/atomic_32.h @@ -21,7 +21,7 @@ extern int __atomic_add_return(int, atomic_t *); extern int atomic_cmpxchg(atomic_t *, int, int); -#define atomic_xchg(v, new) (xchg(&((v)->counter), new)) +extern int atomic_xchg(atomic_t *, int); extern int __atomic_add_unless(atomic_t *, int, int); extern void atomic_set(atomic_t *, int); diff --git a/arch/sparc/include/asm/cmpxchg_32.h b/arch/sparc/include/asm/cmpxchg_32.h index 1fae1a02e3c2..ae0f9a7a314d 100644 --- a/arch/sparc/include/asm/cmpxchg_32.h +++ b/arch/sparc/include/asm/cmpxchg_32.h @@ -11,22 +11,14 @@ #ifndef __ARCH_SPARC_CMPXCHG__ #define __ARCH_SPARC_CMPXCHG__ -static inline unsigned long xchg_u32(__volatile__ unsigned long *m, unsigned long val) -{ - __asm__ __volatile__("swap [%2], %0" - : "=&r" (val) - : "0" (val), "r" (m) - : "memory"); - return val; -} - +extern unsigned long __xchg_u32(volatile u32 *m, u32 new); extern void __xchg_called_with_bad_pointer(void); static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int size) { switch (size) { case 4: - return xchg_u32(ptr, x); + return __xchg_u32(ptr, x); } __xchg_called_with_bad_pointer(); return x; diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h index ca121f0fa3ec..17be9d618335 100644 --- a/arch/sparc/include/asm/hypervisor.h +++ b/arch/sparc/include/asm/hypervisor.h @@ -2944,6 +2944,16 @@ extern unsigned long sun4v_vt_set_perfreg(unsigned long reg_num, unsigned long reg_val); #endif +#define HV_FAST_T5_GET_PERFREG 0x1a8 +#define HV_FAST_T5_SET_PERFREG 0x1a9 + +#ifndef __ASSEMBLY__ +unsigned long sun4v_t5_get_perfreg(unsigned long reg_num, + unsigned long *reg_val); +unsigned long sun4v_t5_set_perfreg(unsigned long reg_num, + unsigned long reg_val); +#endif + /* Function numbers for HV_CORE_TRAP. */ #define HV_CORE_SET_VER 0x00 #define HV_CORE_PUTCHAR 0x01 @@ -2975,6 +2985,7 @@ extern unsigned long sun4v_vt_set_perfreg(unsigned long reg_num, #define HV_GRP_VF_CPU 0x0205 #define HV_GRP_KT_CPU 0x0209 #define HV_GRP_VT_CPU 0x020c +#define HV_GRP_T5_CPU 0x0211 #define HV_GRP_DIAG 0x0300 #ifndef __ASSEMBLY__ diff --git a/arch/sparc/include/asm/irq_64.h b/arch/sparc/include/asm/irq_64.h index abf6afe82ca8..3deb07ff1e00 100644 --- a/arch/sparc/include/asm/irq_64.h +++ b/arch/sparc/include/asm/irq_64.h @@ -37,7 +37,7 @@ * * ino_bucket->irq allocation is made during {sun4v_,}build_irq(). */ -#define NR_IRQS 255 +#define NR_IRQS (2048) extern void irq_install_pre_handler(int irq, void (*func)(unsigned int, void *, void *), @@ -57,11 +57,8 @@ extern unsigned int sun4u_build_msi(u32 portid, unsigned int *irq_p, unsigned long iclr_base); extern void sun4u_destroy_msi(unsigned int irq); -extern unsigned char irq_alloc(unsigned int dev_handle, - unsigned int dev_ino); -#ifdef CONFIG_PCI_MSI -extern void irq_free(unsigned int irq); -#endif +unsigned int irq_alloc(unsigned int dev_handle, unsigned int dev_ino); +void irq_free(unsigned int irq); extern void __init init_IRQ(void); extern void fixup_irqs(void); diff --git a/arch/sparc/include/asm/ldc.h b/arch/sparc/include/asm/ldc.h index bdb524a7b814..8732ed391aff 100644 --- a/arch/sparc/include/asm/ldc.h +++ b/arch/sparc/include/asm/ldc.h @@ -53,13 +53,14 @@ struct ldc_channel; /* Allocate state for a channel. */ extern struct ldc_channel *ldc_alloc(unsigned long id, const struct ldc_channel_config *cfgp, - void *event_arg); + void *event_arg, + const char *name); /* Shut down and free state for a channel. */ extern void ldc_free(struct ldc_channel *lp); /* Register TX and RX queues of the link with the hypervisor. */ -extern int ldc_bind(struct ldc_channel *lp, const char *name); +extern int ldc_bind(struct ldc_channel *lp); /* For non-RAW protocols we need to complete a handshake before * communication can proceed. ldc_connect() does that, if the diff --git a/arch/sparc/include/asm/oplib_64.h b/arch/sparc/include/asm/oplib_64.h index a12dbe3b7762..e48fdf4e16ff 100644 --- a/arch/sparc/include/asm/oplib_64.h +++ b/arch/sparc/include/asm/oplib_64.h @@ -62,7 +62,8 @@ struct linux_mem_p1275 { /* You must call prom_init() before using any of the library services, * preferably as early as possible. Pass it the romvec pointer. */ -extern void prom_init(void *cif_handler, void *cif_stack); +extern void prom_init(void *cif_handler); +extern void prom_init_report(void); /* Boot argument acquisition, returns the boot command line string. */ extern char *prom_getbootargs(void); diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h index aac53fcea807..b18e602fcac4 100644 --- a/arch/sparc/include/asm/page_64.h +++ b/arch/sparc/include/asm/page_64.h @@ -57,18 +57,21 @@ extern void copy_user_page(void *to, void *from, unsigned long vaddr, struct pag typedef struct { unsigned long pte; } pte_t; typedef struct { unsigned long iopte; } iopte_t; typedef struct { unsigned long pmd; } pmd_t; +typedef struct { unsigned long pud; } pud_t; typedef struct { unsigned long pgd; } pgd_t; typedef struct { unsigned long pgprot; } pgprot_t; #define pte_val(x) ((x).pte) #define iopte_val(x) ((x).iopte) #define pmd_val(x) ((x).pmd) +#define pud_val(x) ((x).pud) #define pgd_val(x) ((x).pgd) #define pgprot_val(x) ((x).pgprot) #define __pte(x) ((pte_t) { (x) } ) #define __iopte(x) ((iopte_t) { (x) } ) #define __pmd(x) ((pmd_t) { (x) } ) +#define __pud(x) ((pud_t) { (x) } ) #define __pgd(x) ((pgd_t) { (x) } ) #define __pgprot(x) ((pgprot_t) { (x) } ) @@ -77,18 +80,21 @@ typedef struct { unsigned long pgprot; } pgprot_t; typedef unsigned long pte_t; typedef unsigned long iopte_t; typedef unsigned long pmd_t; +typedef unsigned long pud_t; typedef unsigned long pgd_t; typedef unsigned long pgprot_t; #define pte_val(x) (x) #define iopte_val(x) (x) #define pmd_val(x) (x) +#define pud_val(x) (x) #define pgd_val(x) (x) #define pgprot_val(x) (x) #define __pte(x) (x) #define __iopte(x) (x) #define __pmd(x) (x) +#define __pud(x) (x) #define __pgd(x) (x) #define __pgprot(x) (x) @@ -96,21 +102,14 @@ typedef unsigned long pgprot_t; typedef pte_t *pgtable_t; -/* These two values define the virtual address space range in which we - * must forbid 64-bit user processes from making mappings. It used to - * represent precisely the virtual address space hole present in most - * early sparc64 chips including UltraSPARC-I. But now it also is - * further constrained by the limits of our page tables, which is - * 43-bits of virtual address. - */ -#define SPARC64_VA_HOLE_TOP _AC(0xfffffc0000000000,UL) -#define SPARC64_VA_HOLE_BOTTOM _AC(0x0000040000000000,UL) +extern unsigned long sparc64_va_hole_top; +extern unsigned long sparc64_va_hole_bottom; /* The next two defines specify the actual exclusion region we * enforce, wherein we use a 4GB red zone on each side of the VA hole. */ -#define VA_EXCLUDE_START (SPARC64_VA_HOLE_BOTTOM - (1UL << 32UL)) -#define VA_EXCLUDE_END (SPARC64_VA_HOLE_TOP + (1UL << 32UL)) +#define VA_EXCLUDE_START (sparc64_va_hole_bottom - (1UL << 32UL)) +#define VA_EXCLUDE_END (sparc64_va_hole_top + (1UL << 32UL)) #define TASK_UNMAPPED_BASE (test_thread_flag(TIF_32BIT) ? \ _AC(0x0000000070000000,UL) : \ @@ -118,20 +117,16 @@ typedef pte_t *pgtable_t; #include <asm-generic/memory_model.h> -#define PAGE_OFFSET_BY_BITS(X) (-(_AC(1,UL) << (X))) extern unsigned long PAGE_OFFSET; #endif /* !(__ASSEMBLY__) */ -/* The maximum number of physical memory address bits we support, this - * is used to size various tables used to manage kernel TLB misses and - * also the sparsemem code. +/* The maximum number of physical memory address bits we support. The + * largest value we can support is whatever "KPGD_SHIFT + KPTE_BITS" + * evaluates to. */ -#define MAX_PHYS_ADDRESS_BITS 47 +#define MAX_PHYS_ADDRESS_BITS 53 -/* These two shift counts are used when indexing sparc64_valid_addr_bitmap - * and kpte_linear_bitmap. - */ #define ILOG2_4MB 22 #define ILOG2_256MB 28 diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h index bcfe063bce23..2c8d41fb13a4 100644 --- a/arch/sparc/include/asm/pgalloc_64.h +++ b/arch/sparc/include/asm/pgalloc_64.h @@ -15,6 +15,13 @@ extern struct kmem_cache *pgtable_cache; +static inline void __pgd_populate(pgd_t *pgd, pud_t *pud) +{ + pgd_set(pgd, pud); +} + +#define pgd_populate(MM, PGD, PUD) __pgd_populate(PGD, PUD) + static inline pgd_t *pgd_alloc(struct mm_struct *mm) { return kmem_cache_alloc(pgtable_cache, GFP_KERNEL); @@ -25,7 +32,23 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) kmem_cache_free(pgtable_cache, pgd); } -#define pud_populate(MM, PUD, PMD) pud_set(PUD, PMD) +static inline void __pud_populate(pud_t *pud, pmd_t *pmd) +{ + pud_set(pud, pmd); +} + +#define pud_populate(MM, PUD, PMD) __pud_populate(PUD, PMD) + +static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) +{ + return kmem_cache_alloc(pgtable_cache, + GFP_KERNEL|__GFP_REPEAT); +} + +static inline void pud_free(struct mm_struct *mm, pud_t *pud) +{ + kmem_cache_free(pgtable_cache, pud); +} static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { @@ -91,4 +114,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pte_t *pte, #define __pmd_free_tlb(tlb, pmd, addr) \ pgtable_free_tlb(tlb, pmd, false) +#define __pud_free_tlb(tlb, pud, addr) \ + pgtable_free_tlb(tlb, pud, false) + #endif /* _SPARC64_PGALLOC_H */ diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 1a49ffdf9da9..e8dfabf156c7 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -20,8 +20,6 @@ #include <asm/page.h> #include <asm/processor.h> -#include <asm-generic/pgtable-nopud.h> - /* The kernel image occupies 0x4000000 to 0x6000000 (4MB --> 96MB). * The page copy blockops can use 0x6000000 to 0x8000000. * The 8K TSB is mapped in the 0x8000000 to 0x8400000 range. @@ -42,10 +40,7 @@ #define LOW_OBP_ADDRESS _AC(0x00000000f0000000,UL) #define HI_OBP_ADDRESS _AC(0x0000000100000000,UL) #define VMALLOC_START _AC(0x0000000100000000,UL) -#define VMALLOC_END _AC(0x0000010000000000,UL) -#define VMEMMAP_BASE _AC(0x0000010000000000,UL) - -#define vmemmap ((struct page *)VMEMMAP_BASE) +#define VMEMMAP_BASE VMALLOC_END /* PMD_SHIFT determines the size of the area a second-level page * table can map @@ -55,13 +50,25 @@ #define PMD_MASK (~(PMD_SIZE-1)) #define PMD_BITS (PAGE_SHIFT - 3) -/* PGDIR_SHIFT determines what a third-level page table entry can map */ -#define PGDIR_SHIFT (PAGE_SHIFT + (PAGE_SHIFT-3) + PMD_BITS) +/* PUD_SHIFT determines the size of the area a third-level page + * table can map + */ +#define PUD_SHIFT (PMD_SHIFT + PMD_BITS) +#define PUD_SIZE (_AC(1,UL) << PUD_SHIFT) +#define PUD_MASK (~(PUD_SIZE-1)) +#define PUD_BITS (PAGE_SHIFT - 3) + +/* PGDIR_SHIFT determines what a fourth-level page table entry can map */ +#define PGDIR_SHIFT (PUD_SHIFT + PUD_BITS) #define PGDIR_SIZE (_AC(1,UL) << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE-1)) #define PGDIR_BITS (PAGE_SHIFT - 3) -#if (PGDIR_SHIFT + PGDIR_BITS) != 43 +#if (MAX_PHYS_ADDRESS_BITS > PGDIR_SHIFT + PGDIR_BITS) +#error MAX_PHYS_ADDRESS_BITS exceeds what kernel page tables can support +#endif + +#if (PGDIR_SHIFT + PGDIR_BITS) != 53 #error Page table parameters do not cover virtual address space properly. #endif @@ -71,28 +78,18 @@ #ifndef __ASSEMBLY__ -#include <linux/sched.h> - -extern unsigned long sparc64_valid_addr_bitmap[]; +extern unsigned long VMALLOC_END; -/* Needs to be defined here and not in linux/mm.h, as it is arch dependent */ -static inline bool __kern_addr_valid(unsigned long paddr) -{ - if ((paddr >> MAX_PHYS_ADDRESS_BITS) != 0UL) - return false; - return test_bit(paddr >> ILOG2_4MB, sparc64_valid_addr_bitmap); -} +#define vmemmap ((struct page *)VMEMMAP_BASE) -static inline bool kern_addr_valid(unsigned long addr) -{ - unsigned long paddr = __pa(addr); +#include <linux/sched.h> - return __kern_addr_valid(paddr); -} +bool kern_addr_valid(unsigned long addr); /* Entries per page directory level. */ #define PTRS_PER_PTE (1UL << (PAGE_SHIFT-3)) #define PTRS_PER_PMD (1UL << PMD_BITS) +#define PTRS_PER_PUD (1UL << PUD_BITS) #define PTRS_PER_PGD (1UL << PGDIR_BITS) /* Kernel has a separate 44bit address space. */ @@ -101,6 +98,9 @@ static inline bool kern_addr_valid(unsigned long addr) #define pmd_ERROR(e) \ pr_err("%s:%d: bad pmd %p(%016lx) seen at (%pS)\n", \ __FILE__, __LINE__, &(e), pmd_val(e), __builtin_return_address(0)) +#define pud_ERROR(e) \ + pr_err("%s:%d: bad pud %p(%016lx) seen at (%pS)\n", \ + __FILE__, __LINE__, &(e), pud_val(e), __builtin_return_address(0)) #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %p(%016lx) seen at (%pS)\n", \ __FILE__, __LINE__, &(e), pgd_val(e), __builtin_return_address(0)) @@ -112,6 +112,7 @@ static inline bool kern_addr_valid(unsigned long addr) #define _PAGE_R _AC(0x8000000000000000,UL) /* Keep ref bit uptodate*/ #define _PAGE_SPECIAL _AC(0x0200000000000000,UL) /* Special page */ #define _PAGE_PMD_HUGE _AC(0x0100000000000000,UL) /* Huge page */ +#define _PAGE_PUD_HUGE _PAGE_PMD_HUGE /* Advertise support for _PAGE_SPECIAL */ #define __HAVE_ARCH_PTE_SPECIAL @@ -658,26 +659,26 @@ static inline unsigned long pmd_large(pmd_t pmd) return pte_val(pte) & _PAGE_PMD_HUGE; } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -static inline unsigned long pmd_young(pmd_t pmd) +static inline unsigned long pmd_pfn(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - return pte_young(pte); + return pte_pfn(pte); } -static inline unsigned long pmd_write(pmd_t pmd) +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +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_pfn(pmd_t pmd) +static inline unsigned long pmd_write(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - return pte_pfn(pte); + return pte_write(pte); } static inline unsigned long pmd_trans_huge(pmd_t pmd) @@ -771,13 +772,15 @@ static inline int pmd_present(pmd_t pmd) * the top bits outside of the range of any physical address size we * support are clear as well. We also validate the physical itself. */ -#define pmd_bad(pmd) ((pmd_val(pmd) & ~PAGE_MASK) || \ - !__kern_addr_valid(pmd_val(pmd))) +#define pmd_bad(pmd) (pmd_val(pmd) & ~PAGE_MASK) #define pud_none(pud) (!pud_val(pud)) -#define pud_bad(pud) ((pud_val(pud) & ~PAGE_MASK) || \ - !__kern_addr_valid(pud_val(pud))) +#define pud_bad(pud) (pud_val(pud) & ~PAGE_MASK) + +#define pgd_none(pgd) (!pgd_val(pgd)) + +#define pgd_bad(pgd) (pgd_val(pgd) & ~PAGE_MASK) #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, @@ -815,10 +818,31 @@ static inline unsigned long __pmd_page(pmd_t pmd) #define pmd_clear(pmdp) (pmd_val(*(pmdp)) = 0UL) #define pud_present(pud) (pud_val(pud) != 0U) #define pud_clear(pudp) (pud_val(*(pudp)) = 0UL) +#define pgd_page_vaddr(pgd) \ + ((unsigned long) __va(pgd_val(pgd))) +#define pgd_present(pgd) (pgd_val(pgd) != 0U) +#define pgd_clear(pgdp) (pgd_val(*(pgd)) = 0UL) + +static inline unsigned long pud_large(pud_t pud) +{ + pte_t pte = __pte(pud_val(pud)); + + return pte_val(pte) & _PAGE_PMD_HUGE; +} + +static inline unsigned long pud_pfn(pud_t pud) +{ + pte_t pte = __pte(pud_val(pud)); + + return pte_pfn(pte); +} /* Same in both SUN4V and SUN4U. */ #define pte_none(pte) (!pte_val(pte)) +#define pgd_set(pgdp, pudp) \ + (pgd_val(*(pgdp)) = (__pa((unsigned long) (pudp)))) + /* to find an entry in a page-table-directory. */ #define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)) #define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address)) @@ -826,6 +850,11 @@ static inline unsigned long __pmd_page(pmd_t pmd) /* to find an entry in a kernel page-table-directory */ #define pgd_offset_k(address) pgd_offset(&init_mm, address) +/* Find an entry in the third-level page table.. */ +#define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) +#define pud_offset(pgdp, address) \ + ((pud_t *) pgd_page_vaddr(*(pgdp)) + pud_index(address)) + /* Find an entry in the second-level page table.. */ #define pmd_offset(pudp, address) \ ((pmd_t *) pud_page_vaddr(*(pudp)) + \ @@ -898,7 +927,6 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, #endif extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; -extern pmd_t swapper_low_pmd_dir[PTRS_PER_PMD]; extern void paging_init(void); extern unsigned long find_ecache_flush_span(unsigned long size); diff --git a/arch/sparc/include/asm/setup.h b/arch/sparc/include/asm/setup.h index 5e35e0517318..acd614668ec1 100644 --- a/arch/sparc/include/asm/setup.h +++ b/arch/sparc/include/asm/setup.h @@ -24,6 +24,10 @@ static inline int con_is_present(void) } #endif +#ifdef CONFIG_SPARC64 +extern void __init start_early_boot(void); +#endif + extern void sun_do_break(void); extern int stop_a_enabled; extern int scons_pwroff; diff --git a/arch/sparc/include/asm/spitfire.h b/arch/sparc/include/asm/spitfire.h index 6b67e50fb9b4..69424d48cbb7 100644 --- a/arch/sparc/include/asm/spitfire.h +++ b/arch/sparc/include/asm/spitfire.h @@ -45,6 +45,8 @@ #define SUN4V_CHIP_NIAGARA3 0x03 #define SUN4V_CHIP_NIAGARA4 0x04 #define SUN4V_CHIP_NIAGARA5 0x05 +#define SUN4V_CHIP_SPARC_M6 0x06 +#define SUN4V_CHIP_SPARC_M7 0x07 #define SUN4V_CHIP_SPARC64X 0x8a #define SUN4V_CHIP_UNKNOWN 0xff diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h index a5f01ac6d0f1..cc6275c931a5 100644 --- a/arch/sparc/include/asm/thread_info_64.h +++ b/arch/sparc/include/asm/thread_info_64.h @@ -63,7 +63,8 @@ struct thread_info { struct pt_regs *kern_una_regs; unsigned int kern_una_insn; - unsigned long fpregs[0] __attribute__ ((aligned(64))); + unsigned long fpregs[(7 * 256) / sizeof(unsigned long)] + __attribute__ ((aligned(64))); }; #endif /* !(__ASSEMBLY__) */ @@ -102,6 +103,7 @@ struct thread_info { #define FAULT_CODE_ITLB 0x04 /* Miss happened in I-TLB */ #define FAULT_CODE_WINFIXUP 0x08 /* Miss happened during spill/fill */ #define FAULT_CODE_BLKCOMMIT 0x10 /* Use blk-commit ASI in copy_page */ +#define FAULT_CODE_BAD_RA 0x20 /* Bad RA for sun4v */ #if PAGE_SHIFT == 13 #define THREAD_SIZE (2*PAGE_SIZE) diff --git a/arch/sparc/include/asm/tsb.h b/arch/sparc/include/asm/tsb.h index 90916f955cac..ecb49cfa3be9 100644 --- a/arch/sparc/include/asm/tsb.h +++ b/arch/sparc/include/asm/tsb.h @@ -133,9 +133,24 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; sub TSB, 0x8, TSB; \ TSB_STORE(TSB, TAG); - /* Do a kernel page table walk. Leaves physical PTE pointer in - * REG1. Jumps to FAIL_LABEL on early page table walk termination. - * VADDR will not be clobbered, but REG2 will. + /* Do a kernel page table walk. Leaves valid PTE value in + * REG1. Jumps to FAIL_LABEL on early page table walk + * termination. VADDR will not be clobbered, but REG2 will. + * + * There are two masks we must apply to propagate bits from + * the virtual address into the PTE physical address field + * when dealing with huge pages. This is because the page + * table boundaries do not match the huge page size(s) the + * hardware supports. + * + * In these cases we propagate the bits that are below the + * page table level where we saw the huge page mapping, but + * are still within the relevant physical bits for the huge + * page size in question. So for PMD mappings (which fall on + * bit 23, for 8MB per PMD) we must propagate bit 22 for a + * 4MB huge page. For huge PUDs (which fall on bit 33, for + * 8GB per PUD), we have to accomodate 256MB and 2GB huge + * pages. So for those we propagate bits 32 to 28. */ #define KERN_PGTABLE_WALK(VADDR, REG1, REG2, FAIL_LABEL) \ sethi %hi(swapper_pg_dir), REG1; \ @@ -145,15 +160,40 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; andn REG2, 0x7, REG2; \ ldx [REG1 + REG2], REG1; \ brz,pn REG1, FAIL_LABEL; \ - sllx VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \ + sllx VADDR, 64 - (PUD_SHIFT + PUD_BITS), REG2; \ srlx REG2, 64 - PAGE_SHIFT, REG2; \ andn REG2, 0x7, REG2; \ ldxa [REG1 + REG2] ASI_PHYS_USE_EC, REG1; \ brz,pn REG1, FAIL_LABEL; \ - sllx VADDR, 64 - PMD_SHIFT, REG2; \ + sethi %uhi(_PAGE_PUD_HUGE), REG2; \ + brz,pn REG1, FAIL_LABEL; \ + sllx REG2, 32, REG2; \ + andcc REG1, REG2, %g0; \ + sethi %hi(0xf8000000), REG2; \ + bne,pt %xcc, 697f; \ + sllx REG2, 1, REG2; \ + sllx VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \ srlx REG2, 64 - PAGE_SHIFT, REG2; \ andn REG2, 0x7, REG2; \ - add REG1, REG2, REG1; + ldxa [REG1 + REG2] ASI_PHYS_USE_EC, REG1; \ + sethi %uhi(_PAGE_PMD_HUGE), REG2; \ + brz,pn REG1, FAIL_LABEL; \ + sllx REG2, 32, REG2; \ + andcc REG1, REG2, %g0; \ + be,pn %xcc, 698f; \ + sethi %hi(0x400000), REG2; \ +697: brgez,pn REG1, FAIL_LABEL; \ + andn REG1, REG2, REG1; \ + and VADDR, REG2, REG2; \ + ba,pt %xcc, 699f; \ + or REG1, REG2, REG1; \ +698: sllx VADDR, 64 - PMD_SHIFT, REG2; \ + srlx REG2, 64 - PAGE_SHIFT, REG2; \ + andn REG2, 0x7, REG2; \ + ldxa [REG1 + REG2] ASI_PHYS_USE_EC, REG1; \ + brgez,pn REG1, FAIL_LABEL; \ + nop; \ +699: /* PMD has been loaded into REG1, interpret the value, seeing * if it is a HUGE PMD or a normal one. If it is not valid @@ -198,6 +238,11 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; andn REG2, 0x7, REG2; \ ldxa [PHYS_PGD + REG2] ASI_PHYS_USE_EC, REG1; \ brz,pn REG1, FAIL_LABEL; \ + sllx VADDR, 64 - (PUD_SHIFT + PUD_BITS), REG2; \ + srlx REG2, 64 - PAGE_SHIFT, REG2; \ + andn REG2, 0x7, REG2; \ + ldxa [REG1 + REG2] ASI_PHYS_USE_EC, REG1; \ + brz,pn REG1, FAIL_LABEL; \ sllx VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \ srlx REG2, 64 - PAGE_SHIFT, REG2; \ andn REG2, 0x7, REG2; \ @@ -246,8 +291,6 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; (KERNEL_TSB_SIZE_BYTES / 16) #define KERNEL_TSB4M_NENTRIES 4096 -#define KTSB_PHYS_SHIFT 15 - /* Do a kernel TSB lookup at tl>0 on VADDR+TAG, branch to OK_LABEL * on TSB hit. REG1, REG2, REG3, and REG4 are used as temporaries * and the found TTE will be left in REG1. REG3 and REG4 must @@ -256,17 +299,15 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; * VADDR and TAG will be preserved and not clobbered by this macro. */ #define KERN_TSB_LOOKUP_TL1(VADDR, TAG, REG1, REG2, REG3, REG4, OK_LABEL) \ -661: sethi %hi(swapper_tsb), REG1; \ - or REG1, %lo(swapper_tsb), REG1; \ +661: sethi %uhi(swapper_tsb), REG1; \ + sethi %hi(swapper_tsb), REG2; \ + or REG1, %ulo(swapper_tsb), REG1; \ + or REG2, %lo(swapper_tsb), REG2; \ .section .swapper_tsb_phys_patch, "ax"; \ .word 661b; \ .previous; \ -661: nop; \ - .section .tsb_ldquad_phys_patch, "ax"; \ - .word 661b; \ - sllx REG1, KTSB_PHYS_SHIFT, REG1; \ - sllx REG1, KTSB_PHYS_SHIFT, REG1; \ - .previous; \ + sllx REG1, 32, REG1; \ + or REG1, REG2, REG1; \ srlx VADDR, PAGE_SHIFT, REG2; \ and REG2, (KERNEL_TSB_NENTRIES - 1), REG2; \ sllx REG2, 4, REG2; \ @@ -281,17 +322,15 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; * we can make use of that for the index computation. */ #define KERN_TSB4M_LOOKUP_TL1(TAG, REG1, REG2, REG3, REG4, OK_LABEL) \ -661: sethi %hi(swapper_4m_tsb), REG1; \ - or REG1, %lo(swapper_4m_tsb), REG1; \ +661: sethi %uhi(swapper_4m_tsb), REG1; \ + sethi %hi(swapper_4m_tsb), REG2; \ + or REG1, %ulo(swapper_4m_tsb), REG1; \ + or REG2, %lo(swapper_4m_tsb), REG2; \ .section .swapper_4m_tsb_phys_patch, "ax"; \ .word 661b; \ .previous; \ -661: nop; \ - .section .tsb_ldquad_phys_patch, "ax"; \ - .word 661b; \ - sllx REG1, KTSB_PHYS_SHIFT, REG1; \ - sllx REG1, KTSB_PHYS_SHIFT, REG1; \ - .previous; \ + sllx REG1, 32, REG1; \ + or REG1, REG2, REG1; \ and TAG, (KERNEL_TSB4M_NENTRIES - 1), REG2; \ sllx REG2, 4, REG2; \ add REG1, REG2, REG2; \ diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h index 432afa838861..55841c184e6d 100644 --- a/arch/sparc/include/asm/vio.h +++ b/arch/sparc/include/asm/vio.h @@ -118,12 +118,18 @@ struct vio_disk_attr_info { u8 vdisk_type; #define VD_DISK_TYPE_SLICE 0x01 /* Slice in block device */ #define VD_DISK_TYPE_DISK 0x02 /* Entire block device */ - u16 resv1; + u8 vdisk_mtype; /* v1.1 */ +#define VD_MEDIA_TYPE_FIXED 0x01 /* Fixed device */ +#define VD_MEDIA_TYPE_CD 0x02 /* CD Device */ +#define VD_MEDIA_TYPE_DVD 0x03 /* DVD Device */ + u8 resv1; u32 vdisk_block_size; u64 operations; - u64 vdisk_size; + u64 vdisk_size; /* v1.1 */ u64 max_xfer_size; - u64 resv2[2]; + u32 phys_block_size; /* v1.2 */ + u32 resv2; + u64 resv3[1]; }; struct vio_disk_desc { @@ -259,7 +265,7 @@ static inline u32 vio_dring_avail(struct vio_dring_state *dr, unsigned int ring_size) { return (dr->pending - - ((dr->prod - dr->cons) & (ring_size - 1))); + ((dr->prod - dr->cons) & (ring_size - 1)) - 1); } #define VIO_MAX_TYPE_LEN 32 diff --git a/arch/sparc/include/asm/visasm.h b/arch/sparc/include/asm/visasm.h index 39ca301920db..11fdf0ef50bb 100644 --- a/arch/sparc/include/asm/visasm.h +++ b/arch/sparc/include/asm/visasm.h @@ -39,6 +39,14 @@ 297: wr %o5, FPRS_FEF, %fprs; \ 298: +#define VISEntryHalfFast(fail_label) \ + rd %fprs, %o5; \ + andcc %o5, FPRS_FEF, %g0; \ + be,pt %icc, 297f; \ + nop; \ + ba,a,pt %xcc, fail_label; \ +297: wr %o5, FPRS_FEF, %fprs; + #define VISExitHalf \ wr %o5, 0, %fprs; diff --git a/arch/sparc/include/uapi/asm/swab.h b/arch/sparc/include/uapi/asm/swab.h index a34ad079487e..4c7c12d69bea 100644 --- a/arch/sparc/include/uapi/asm/swab.h +++ b/arch/sparc/include/uapi/asm/swab.h @@ -9,9 +9,9 @@ static inline __u16 __arch_swab16p(const __u16 *addr) { __u16 ret; - __asm__ __volatile__ ("lduha [%1] %2, %0" + __asm__ __volatile__ ("lduha [%2] %3, %0" : "=r" (ret) - : "r" (addr), "i" (ASI_PL)); + : "m" (*addr), "r" (addr), "i" (ASI_PL)); return ret; } #define __arch_swab16p __arch_swab16p @@ -20,9 +20,9 @@ static inline __u32 __arch_swab32p(const __u32 *addr) { __u32 ret; - __asm__ __volatile__ ("lduwa [%1] %2, %0" + __asm__ __volatile__ ("lduwa [%2] %3, %0" : "=r" (ret) - : "r" (addr), "i" (ASI_PL)); + : "m" (*addr), "r" (addr), "i" (ASI_PL)); return ret; } #define __arch_swab32p __arch_swab32p @@ -31,9 +31,9 @@ static inline __u64 __arch_swab64p(const __u64 *addr) { __u64 ret; - __asm__ __volatile__ ("ldxa [%1] %2, %0" + __asm__ __volatile__ ("ldxa [%2] %3, %0" : "=r" (ret) - : "r" (addr), "i" (ASI_PL)); + : "m" (*addr), "r" (addr), "i" (ASI_PL)); return ret; } #define __arch_swab64p __arch_swab64p diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c index 5c5125895db8..52e10defedc4 100644 --- a/arch/sparc/kernel/cpu.c +++ b/arch/sparc/kernel/cpu.c @@ -493,6 +493,18 @@ static void __init sun4v_cpu_probe(void) sparc_pmu_type = "niagara5"; break; + case SUN4V_CHIP_SPARC_M6: + sparc_cpu_type = "SPARC-M6"; + sparc_fpu_type = "SPARC-M6 integrated FPU"; + sparc_pmu_type = "sparc-m6"; + break; + + case SUN4V_CHIP_SPARC_M7: + sparc_cpu_type = "SPARC-M7"; + sparc_fpu_type = "SPARC-M7 integrated FPU"; + sparc_pmu_type = "sparc-m7"; + break; + case SUN4V_CHIP_SPARC64X: sparc_cpu_type = "SPARC64-X"; sparc_fpu_type = "SPARC64-X integrated FPU"; diff --git a/arch/sparc/kernel/cpumap.c b/arch/sparc/kernel/cpumap.c index de1c844dfabc..e69ec0e3f155 100644 --- a/arch/sparc/kernel/cpumap.c +++ b/arch/sparc/kernel/cpumap.c @@ -326,6 +326,8 @@ static int iterate_cpu(struct cpuinfo_tree *t, unsigned int root_index) case SUN4V_CHIP_NIAGARA3: case SUN4V_CHIP_NIAGARA4: case SUN4V_CHIP_NIAGARA5: + case SUN4V_CHIP_SPARC_M6: + case SUN4V_CHIP_SPARC_M7: case SUN4V_CHIP_SPARC64X: rover_inc_table = niagara_iterate_method; break; diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c index dff60abbea01..f87a55d77094 100644 --- a/arch/sparc/kernel/ds.c +++ b/arch/sparc/kernel/ds.c @@ -1200,14 +1200,14 @@ static int ds_probe(struct vio_dev *vdev, const struct vio_device_id *id) ds_cfg.tx_irq = vdev->tx_irq; ds_cfg.rx_irq = vdev->rx_irq; - lp = ldc_alloc(vdev->channel_id, &ds_cfg, dp); + lp = ldc_alloc(vdev->channel_id, &ds_cfg, dp, "DS"); if (IS_ERR(lp)) { err = PTR_ERR(lp); goto out_free_ds_states; } dp->lp = lp; - err = ldc_bind(lp, "DS"); + err = ldc_bind(lp); if (err) goto out_free_ldc; diff --git a/arch/sparc/kernel/dtlb_prot.S b/arch/sparc/kernel/dtlb_prot.S index b2c2c5be281c..d668ca149e64 100644 --- a/arch/sparc/kernel/dtlb_prot.S +++ b/arch/sparc/kernel/dtlb_prot.S @@ -24,11 +24,11 @@ mov TLB_TAG_ACCESS, %g4 ! For reload of vaddr /* PROT ** ICACHE line 2: More real fault processing */ + ldxa [%g4] ASI_DMMU, %g5 ! Put tagaccess in %g5 bgu,pn %xcc, winfix_trampoline ! Yes, perform winfixup - ldxa [%g4] ASI_DMMU, %g5 ! Put tagaccess in %g5 - ba,pt %xcc, sparc64_realfault_common ! Nope, normal fault mov FAULT_CODE_DTLB | FAULT_CODE_WRITE, %g4 - nop + ba,pt %xcc, sparc64_realfault_common ! Nope, normal fault + nop nop nop nop diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h index 140966fbd303..c88ffb9ee482 100644 --- a/arch/sparc/kernel/entry.h +++ b/arch/sparc/kernel/entry.h @@ -66,13 +66,10 @@ struct pause_patch_entry { extern struct pause_patch_entry __pause_3insn_patch, __pause_3insn_patch_end; -extern void __init per_cpu_patch(void); extern void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *, struct sun4v_1insn_patch_entry *); extern void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *, struct sun4v_2insn_patch_entry *); -extern void __init sun4v_patch(void); -extern void __init boot_cpu_id_too_large(int cpu); extern unsigned int dcache_parity_tl1_occurred; extern unsigned int icache_parity_tl1_occurred; diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index 452f04fe8da6..3d61fcae7ee3 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -427,6 +427,12 @@ sun4v_chip_type: cmp %g2, '5' be,pt %xcc, 5f mov SUN4V_CHIP_NIAGARA5, %g4 + cmp %g2, '6' + be,pt %xcc, 5f + mov SUN4V_CHIP_SPARC_M6, %g4 + cmp %g2, '7' + be,pt %xcc, 5f + mov SUN4V_CHIP_SPARC_M7, %g4 ba,pt %xcc, 49f nop @@ -585,6 +591,12 @@ niagara_tlb_fixup: cmp %g1, SUN4V_CHIP_NIAGARA5 be,pt %xcc, niagara4_patch nop + cmp %g1, SUN4V_CHIP_SPARC_M6 + be,pt %xcc, niagara4_patch + nop + cmp %g1, SUN4V_CHIP_SPARC_M7 + be,pt %xcc, niagara4_patch + nop call generic_patch_copyops nop @@ -660,14 +672,12 @@ tlb_fixup_done: sethi %hi(init_thread_union), %g6 or %g6, %lo(init_thread_union), %g6 ldx [%g6 + TI_TASK], %g4 - mov %sp, %l6 wr %g0, ASI_P, %asi mov 1, %g1 sllx %g1, THREAD_SHIFT, %g1 sub %g1, (STACKFRAME_SZ + STACK_BIAS), %g1 add %g6, %g1, %sp - mov 0, %fp /* Set per-cpu pointer initially to zero, this makes * the boot-cpu use the in-kernel-image per-cpu areas @@ -694,44 +704,14 @@ tlb_fixup_done: nop #endif - mov %l6, %o1 ! OpenPROM stack call prom_init mov %l7, %o0 ! OpenPROM cif handler - /* Initialize current_thread_info()->cpu as early as possible. - * In order to do that accurately we have to patch up the get_cpuid() - * assembler sequences. And that, in turn, requires that we know - * if we are on a Starfire box or not. While we're here, patch up - * the sun4v sequences as well. + /* To create a one-register-window buffer between the kernel's + * initial stack and the last stack frame we use from the firmware, + * do the rest of the boot from a C helper function. */ - call check_if_starfire - nop - call per_cpu_patch - nop - call sun4v_patch - nop - -#ifdef CONFIG_SMP - call hard_smp_processor_id - nop - cmp %o0, NR_CPUS - blu,pt %xcc, 1f - nop - call boot_cpu_id_too_large - nop - /* Not reached... */ - -1: -#else - mov 0, %o0 -#endif - sth %o0, [%g6 + TI_CPU] - - call prom_init_report - nop - - /* Off we go.... */ - call start_kernel + call start_early_boot nop /* Not reached... */ diff --git a/arch/sparc/kernel/hvapi.c b/arch/sparc/kernel/hvapi.c index c0a2de0fd624..5c55145bfbf0 100644 --- a/arch/sparc/kernel/hvapi.c +++ b/arch/sparc/kernel/hvapi.c @@ -46,6 +46,7 @@ static struct api_info api_table[] = { { .group = HV_GRP_VF_CPU, }, { .group = HV_GRP_KT_CPU, }, { .group = HV_GRP_VT_CPU, }, + { .group = HV_GRP_T5_CPU, }, { .group = HV_GRP_DIAG, .flags = FLAG_PRE_API }, }; diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S index f3ab509b76a8..caedf8320416 100644 --- a/arch/sparc/kernel/hvcalls.S +++ b/arch/sparc/kernel/hvcalls.S @@ -821,3 +821,19 @@ ENTRY(sun4v_vt_set_perfreg) retl nop ENDPROC(sun4v_vt_set_perfreg) + +ENTRY(sun4v_t5_get_perfreg) + mov %o1, %o4 + mov HV_FAST_T5_GET_PERFREG, %o5 + ta HV_FAST_TRAP + stx %o1, [%o4] + retl + nop +ENDPROC(sun4v_t5_get_perfreg) + +ENTRY(sun4v_t5_set_perfreg) + mov HV_FAST_T5_SET_PERFREG, %o5 + ta HV_FAST_TRAP + retl + nop +ENDPROC(sun4v_t5_set_perfreg) diff --git a/arch/sparc/kernel/hvtramp.S b/arch/sparc/kernel/hvtramp.S index b7ddcdd1dea9..cdbfec299f2f 100644 --- a/arch/sparc/kernel/hvtramp.S +++ b/arch/sparc/kernel/hvtramp.S @@ -109,7 +109,6 @@ hv_cpu_startup: sllx %g5, THREAD_SHIFT, %g5 sub %g5, (STACKFRAME_SZ + STACK_BIAS), %g5 add %g6, %g5, %sp - mov 0, %fp call init_irqwork_curcpu nop diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c index e7e215dfa866..c2d81ad62e78 100644 --- a/arch/sparc/kernel/ioport.c +++ b/arch/sparc/kernel/ioport.c @@ -278,7 +278,8 @@ static void *sbus_alloc_coherent(struct device *dev, size_t len, } order = get_order(len_total); - if ((va = __get_free_pages(GFP_KERNEL|__GFP_COMP, order)) == 0) + va = __get_free_pages(gfp, order); + if (va == 0) goto err_nopages; if ((res = kzalloc(sizeof(struct resource), GFP_KERNEL)) == NULL) @@ -443,7 +444,7 @@ static void *pci32_alloc_coherent(struct device *dev, size_t len, } order = get_order(len_total); - va = (void *) __get_free_pages(GFP_KERNEL, order); + va = (void *) __get_free_pages(gfp, order); if (va == NULL) { printk("pci_alloc_consistent: no %ld pages\n", len_total>>PAGE_SHIFT); goto err_nopages; diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index 666193f4e8bb..4033c23bdfa6 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -47,8 +47,6 @@ #include "cpumap.h" #include "kstack.h" -#define NUM_IVECS (IMAP_INR + 1) - struct ino_bucket *ivector_table; unsigned long ivector_table_pa; @@ -107,55 +105,196 @@ static void bucket_set_irq(unsigned long bucket_pa, unsigned int irq) #define irq_work_pa(__cpu) &(trap_block[(__cpu)].irq_worklist_pa) -static struct { - unsigned int dev_handle; - unsigned int dev_ino; - unsigned int in_use; -} irq_table[NR_IRQS]; -static DEFINE_SPINLOCK(irq_alloc_lock); +static unsigned long hvirq_major __initdata; +static int __init early_hvirq_major(char *p) +{ + int rc = kstrtoul(p, 10, &hvirq_major); + + return rc; +} +early_param("hvirq", early_hvirq_major); + +static int hv_irq_version; + +/* Major version 2.0 of HV_GRP_INTR added support for the VIRQ cookie + * based interfaces, but: + * + * 1) Several OSs, Solaris and Linux included, use them even when only + * negotiating version 1.0 (or failing to negotiate at all). So the + * hypervisor has a workaround that provides the VIRQ interfaces even + * when only verion 1.0 of the API is in use. + * + * 2) Second, and more importantly, with major version 2.0 these VIRQ + * interfaces only were actually hooked up for LDC interrupts, even + * though the Hypervisor specification clearly stated: + * + * The new interrupt API functions will be available to a guest + * when it negotiates version 2.0 in the interrupt API group 0x2. When + * a guest negotiates version 2.0, all interrupt sources will only + * support using the cookie interface, and any attempt to use the + * version 1.0 interrupt APIs numbered 0xa0 to 0xa6 will result in the + * ENOTSUPPORTED error being returned. + * + * with an emphasis on "all interrupt sources". + * + * To correct this, major version 3.0 was created which does actually + * support VIRQs for all interrupt sources (not just LDC devices). So + * if we want to move completely over the cookie based VIRQs we must + * negotiate major version 3.0 or later of HV_GRP_INTR. + */ +static bool sun4v_cookie_only_virqs(void) +{ + if (hv_irq_version >= 3) + return true; + return false; +} -unsigned char irq_alloc(unsigned int dev_handle, unsigned int dev_ino) +static void __init irq_init_hv(void) { - unsigned long flags; - unsigned char ent; + unsigned long hv_error, major, minor = 0; + + if (tlb_type != hypervisor) + return; - BUILD_BUG_ON(NR_IRQS >= 256); + if (hvirq_major) + major = hvirq_major; + else + major = 3; - spin_lock_irqsave(&irq_alloc_lock, flags); + hv_error = sun4v_hvapi_register(HV_GRP_INTR, major, &minor); + if (!hv_error) + hv_irq_version = major; + else + hv_irq_version = 1; - for (ent = 1; ent < NR_IRQS; ent++) { - if (!irq_table[ent].in_use) + pr_info("SUN4V: Using IRQ API major %d, cookie only virqs %s\n", + hv_irq_version, + sun4v_cookie_only_virqs() ? "enabled" : "disabled"); +} + +/* This function is for the timer interrupt.*/ +int __init arch_probe_nr_irqs(void) +{ + return 1; +} + +#define DEFAULT_NUM_IVECS (0xfffU) +static unsigned int nr_ivec = DEFAULT_NUM_IVECS; +#define NUM_IVECS (nr_ivec) + +static unsigned int __init size_nr_ivec(void) +{ + if (tlb_type == hypervisor) { + switch (sun4v_chip_type) { + /* Athena's devhandle|devino is large.*/ + case SUN4V_CHIP_SPARC64X: + nr_ivec = 0xffff; break; + } } - if (ent >= NR_IRQS) { - printk(KERN_ERR "IRQ: Out of virtual IRQs.\n"); - ent = 0; - } else { - irq_table[ent].dev_handle = dev_handle; - irq_table[ent].dev_ino = dev_ino; - irq_table[ent].in_use = 1; - } + return nr_ivec; +} + +struct irq_handler_data { + union { + struct { + unsigned int dev_handle; + unsigned int dev_ino; + }; + unsigned long sysino; + }; + struct ino_bucket bucket; + unsigned long iclr; + unsigned long imap; +}; + +static inline unsigned int irq_data_to_handle(struct irq_data *data) +{ + struct irq_handler_data *ihd = data->handler_data; + + return ihd->dev_handle; +} + +static inline unsigned int irq_data_to_ino(struct irq_data *data) +{ + struct irq_handler_data *ihd = data->handler_data; - spin_unlock_irqrestore(&irq_alloc_lock, flags); + return ihd->dev_ino; +} + +static inline unsigned long irq_data_to_sysino(struct irq_data *data) +{ + struct irq_handler_data *ihd = data->handler_data; - return ent; + return ihd->sysino; } -#ifdef CONFIG_PCI_MSI void irq_free(unsigned int irq) { - unsigned long flags; + void *data = irq_get_handler_data(irq); - if (irq >= NR_IRQS) - return; + kfree(data); + irq_set_handler_data(irq, NULL); + irq_free_descs(irq, 1); +} - spin_lock_irqsave(&irq_alloc_lock, flags); +unsigned int irq_alloc(unsigned int dev_handle, unsigned int dev_ino) +{ + int irq; - irq_table[irq].in_use = 0; + irq = __irq_alloc_descs(-1, 1, 1, numa_node_id(), NULL); + if (irq <= 0) + goto out; - spin_unlock_irqrestore(&irq_alloc_lock, flags); + return irq; +out: + return 0; +} + +static unsigned int cookie_exists(u32 devhandle, unsigned int devino) +{ + unsigned long hv_err, cookie; + struct ino_bucket *bucket; + unsigned int irq = 0U; + + hv_err = sun4v_vintr_get_cookie(devhandle, devino, &cookie); + if (hv_err) { + pr_err("HV get cookie failed hv_err = %ld\n", hv_err); + goto out; + } + + if (cookie & ((1UL << 63UL))) { + cookie = ~cookie; + bucket = (struct ino_bucket *) __va(cookie); + irq = bucket->__irq; + } +out: + return irq; +} + +static unsigned int sysino_exists(u32 devhandle, unsigned int devino) +{ + unsigned long sysino = sun4v_devino_to_sysino(devhandle, devino); + struct ino_bucket *bucket; + unsigned int irq; + + bucket = &ivector_table[sysino]; + irq = bucket_get_irq(__pa(bucket)); + + return irq; +} + +void ack_bad_irq(unsigned int irq) +{ + pr_crit("BAD IRQ ack %d\n", irq); +} + +void irq_install_pre_handler(int irq, + void (*func)(unsigned int, void *, void *), + void *arg1, void *arg2) +{ + pr_warn("IRQ pre handler NOT supported.\n"); } -#endif /* * /proc/interrupts printing: @@ -206,15 +345,6 @@ static unsigned int sun4u_compute_tid(unsigned long imap, unsigned long cpuid) return tid; } -struct irq_handler_data { - unsigned long iclr; - unsigned long imap; - - void (*pre_handler)(unsigned int, void *, void *); - void *arg1; - void *arg2; -}; - #ifdef CONFIG_SMP static int irq_choose_cpu(unsigned int irq, const struct cpumask *affinity) { @@ -316,8 +446,8 @@ static void sun4u_irq_eoi(struct irq_data *data) static void sun4v_irq_enable(struct irq_data *data) { - unsigned int ino = irq_table[data->irq].dev_ino; unsigned long cpuid = irq_choose_cpu(data->irq, data->affinity); + unsigned int ino = irq_data_to_sysino(data); int err; err = sun4v_intr_settarget(ino, cpuid); @@ -337,8 +467,8 @@ static void sun4v_irq_enable(struct irq_data *data) static int sun4v_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { - unsigned int ino = irq_table[data->irq].dev_ino; unsigned long cpuid = irq_choose_cpu(data->irq, mask); + unsigned int ino = irq_data_to_sysino(data); int err; err = sun4v_intr_settarget(ino, cpuid); @@ -351,7 +481,7 @@ static int sun4v_set_affinity(struct irq_data *data, static void sun4v_irq_disable(struct irq_data *data) { - unsigned int ino = irq_table[data->irq].dev_ino; + unsigned int ino = irq_data_to_sysino(data); int err; err = sun4v_intr_setenabled(ino, HV_INTR_DISABLED); @@ -362,7 +492,7 @@ static void sun4v_irq_disable(struct irq_data *data) static void sun4v_irq_eoi(struct irq_data *data) { - unsigned int ino = irq_table[data->irq].dev_ino; + unsigned int ino = irq_data_to_sysino(data); int err; err = sun4v_intr_setstate(ino, HV_INTR_STATE_IDLE); @@ -373,14 +503,13 @@ static void sun4v_irq_eoi(struct irq_data *data) static void sun4v_virq_enable(struct irq_data *data) { - unsigned long cpuid, dev_handle, dev_ino; + unsigned long dev_handle = irq_data_to_handle(data); + unsigned long dev_ino = irq_data_to_ino(data); + unsigned long cpuid; int err; cpuid = irq_choose_cpu(data->irq, data->affinity); - dev_handle = irq_table[data->irq].dev_handle; - dev_ino = irq_table[data->irq].dev_ino; - err = sun4v_vintr_set_target(dev_handle, dev_ino, cpuid); if (err != HV_EOK) printk(KERN_ERR "sun4v_vintr_set_target(%lx,%lx,%lu): " @@ -403,14 +532,13 @@ static void sun4v_virq_enable(struct irq_data *data) static int sun4v_virt_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { - unsigned long cpuid, dev_handle, dev_ino; + unsigned long dev_handle = irq_data_to_handle(data); + unsigned long dev_ino = irq_data_to_ino(data); + unsigned long cpuid; int err; cpuid = irq_choose_cpu(data->irq, mask); - dev_handle = irq_table[data->irq].dev_handle; - dev_ino = irq_table[data->irq].dev_ino; - err = sun4v_vintr_set_target(dev_handle, dev_ino, cpuid); if (err != HV_EOK) printk(KERN_ERR "sun4v_vintr_set_target(%lx,%lx,%lu): " @@ -422,11 +550,10 @@ static int sun4v_virt_set_affinity(struct irq_data *data, static void sun4v_virq_disable(struct irq_data *data) { - unsigned long dev_handle, dev_ino; + unsigned long dev_handle = irq_data_to_handle(data); + unsigned long dev_ino = irq_data_to_ino(data); int err; - dev_handle = irq_table[data->irq].dev_handle; - dev_ino = irq_table[data->irq].dev_ino; err = sun4v_vintr_set_valid(dev_handle, dev_ino, HV_INTR_DISABLED); @@ -438,12 +565,10 @@ static void sun4v_virq_disable(struct irq_data *data) static void sun4v_virq_eoi(struct irq_data *data) { - unsigned long dev_handle, dev_ino; + unsigned long dev_handle = irq_data_to_handle(data); + unsigned long dev_ino = irq_data_to_ino(data); int err; - dev_handle = irq_table[data->irq].dev_handle; - dev_ino = irq_table[data->irq].dev_ino; - err = sun4v_vintr_set_state(dev_handle, dev_ino, HV_INTR_STATE_IDLE); if (err != HV_EOK) @@ -479,31 +604,10 @@ static struct irq_chip sun4v_virq = { .flags = IRQCHIP_EOI_IF_HANDLED, }; -static void pre_flow_handler(struct irq_data *d) -{ - struct irq_handler_data *handler_data = irq_data_get_irq_handler_data(d); - unsigned int ino = irq_table[d->irq].dev_ino; - - handler_data->pre_handler(ino, handler_data->arg1, handler_data->arg2); -} - -void irq_install_pre_handler(int irq, - void (*func)(unsigned int, void *, void *), - void *arg1, void *arg2) -{ - struct irq_handler_data *handler_data = irq_get_handler_data(irq); - - handler_data->pre_handler = func; - handler_data->arg1 = arg1; - handler_data->arg2 = arg2; - - __irq_set_preflow_handler(irq, pre_flow_handler); -} - unsigned int build_irq(int inofixup, unsigned long iclr, unsigned long imap) { - struct ino_bucket *bucket; struct irq_handler_data *handler_data; + struct ino_bucket *bucket; unsigned int irq; int ino; @@ -537,119 +641,166 @@ out: return irq; } -static unsigned int sun4v_build_common(unsigned long sysino, - struct irq_chip *chip) +static unsigned int sun4v_build_common(u32 devhandle, unsigned int devino, + void (*handler_data_init)(struct irq_handler_data *data, + u32 devhandle, unsigned int devino), + struct irq_chip *chip) { - struct ino_bucket *bucket; - struct irq_handler_data *handler_data; + struct irq_handler_data *data; unsigned int irq; - BUG_ON(tlb_type != hypervisor); + irq = irq_alloc(devhandle, devino); + if (!irq) + goto out; - bucket = &ivector_table[sysino]; - irq = bucket_get_irq(__pa(bucket)); - if (!irq) { - irq = irq_alloc(0, sysino); - bucket_set_irq(__pa(bucket), irq); - irq_set_chip_and_handler_name(irq, chip, handle_fasteoi_irq, - "IVEC"); + data = kzalloc(sizeof(struct irq_handler_data), GFP_ATOMIC); + if (unlikely(!data)) { + pr_err("IRQ handler data allocation failed.\n"); + irq_free(irq); + irq = 0; + goto out; } - handler_data = irq_get_handler_data(irq); - if (unlikely(handler_data)) - goto out; + irq_set_handler_data(irq, data); + handler_data_init(data, devhandle, devino); + irq_set_chip_and_handler_name(irq, chip, handle_fasteoi_irq, "IVEC"); + data->imap = ~0UL; + data->iclr = ~0UL; +out: + return irq; +} - handler_data = kzalloc(sizeof(struct irq_handler_data), GFP_ATOMIC); - if (unlikely(!handler_data)) { - prom_printf("IRQ: kzalloc(irq_handler_data) failed.\n"); - prom_halt(); - } - irq_set_handler_data(irq, handler_data); +static unsigned long cookie_assign(unsigned int irq, u32 devhandle, + unsigned int devino) +{ + struct irq_handler_data *ihd = irq_get_handler_data(irq); + unsigned long hv_error, cookie; - /* Catch accidental accesses to these things. IMAP/ICLR handling - * is done by hypervisor calls on sun4v platforms, not by direct - * register accesses. + /* handler_irq needs to find the irq. cookie is seen signed in + * sun4v_dev_mondo and treated as a non ivector_table delivery. */ - handler_data->imap = ~0UL; - handler_data->iclr = ~0UL; + ihd->bucket.__irq = irq; + cookie = ~__pa(&ihd->bucket); -out: - return irq; + hv_error = sun4v_vintr_set_cookie(devhandle, devino, cookie); + if (hv_error) + pr_err("HV vintr set cookie failed = %ld\n", hv_error); + + return hv_error; } -unsigned int sun4v_build_irq(u32 devhandle, unsigned int devino) +static void cookie_handler_data(struct irq_handler_data *data, + u32 devhandle, unsigned int devino) { - unsigned long sysino = sun4v_devino_to_sysino(devhandle, devino); + data->dev_handle = devhandle; + data->dev_ino = devino; +} - return sun4v_build_common(sysino, &sun4v_irq); +static unsigned int cookie_build_irq(u32 devhandle, unsigned int devino, + struct irq_chip *chip) +{ + unsigned long hv_error; + unsigned int irq; + + irq = sun4v_build_common(devhandle, devino, cookie_handler_data, chip); + + hv_error = cookie_assign(irq, devhandle, devino); + if (hv_error) { + irq_free(irq); + irq = 0; + } + + return irq; } -unsigned int sun4v_build_virq(u32 devhandle, unsigned int devino) +static unsigned int sun4v_build_cookie(u32 devhandle, unsigned int devino) { - struct irq_handler_data *handler_data; - unsigned long hv_err, cookie; - struct ino_bucket *bucket; unsigned int irq; - bucket = kzalloc(sizeof(struct ino_bucket), GFP_ATOMIC); - if (unlikely(!bucket)) - return 0; + irq = cookie_exists(devhandle, devino); + if (irq) + goto out; - /* The only reference we store to the IRQ bucket is - * by physical address which kmemleak can't see, tell - * it that this object explicitly is not a leak and - * should be scanned. - */ - kmemleak_not_leak(bucket); + irq = cookie_build_irq(devhandle, devino, &sun4v_virq); - __flush_dcache_range((unsigned long) bucket, - ((unsigned long) bucket + - sizeof(struct ino_bucket))); +out: + return irq; +} - irq = irq_alloc(devhandle, devino); +static void sysino_set_bucket(unsigned int irq) +{ + struct irq_handler_data *ihd = irq_get_handler_data(irq); + struct ino_bucket *bucket; + unsigned long sysino; + + sysino = sun4v_devino_to_sysino(ihd->dev_handle, ihd->dev_ino); + BUG_ON(sysino >= nr_ivec); + bucket = &ivector_table[sysino]; bucket_set_irq(__pa(bucket), irq); +} - irq_set_chip_and_handler_name(irq, &sun4v_virq, handle_fasteoi_irq, - "IVEC"); +static void sysino_handler_data(struct irq_handler_data *data, + u32 devhandle, unsigned int devino) +{ + unsigned long sysino; - handler_data = kzalloc(sizeof(struct irq_handler_data), GFP_ATOMIC); - if (unlikely(!handler_data)) - return 0; + sysino = sun4v_devino_to_sysino(devhandle, devino); + data->sysino = sysino; +} - /* In order to make the LDC channel startup sequence easier, - * especially wrt. locking, we do not let request_irq() enable - * the interrupt. - */ - irq_set_status_flags(irq, IRQ_NOAUTOEN); - irq_set_handler_data(irq, handler_data); +static unsigned int sysino_build_irq(u32 devhandle, unsigned int devino, + struct irq_chip *chip) +{ + unsigned int irq; - /* Catch accidental accesses to these things. IMAP/ICLR handling - * is done by hypervisor calls on sun4v platforms, not by direct - * register accesses. - */ - handler_data->imap = ~0UL; - handler_data->iclr = ~0UL; + irq = sun4v_build_common(devhandle, devino, sysino_handler_data, chip); + if (!irq) + goto out; - cookie = ~__pa(bucket); - hv_err = sun4v_vintr_set_cookie(devhandle, devino, cookie); - if (hv_err) { - prom_printf("IRQ: Fatal, cannot set cookie for [%x:%x] " - "err=%lu\n", devhandle, devino, hv_err); - prom_halt(); - } + sysino_set_bucket(irq); +out: + return irq; +} +static int sun4v_build_sysino(u32 devhandle, unsigned int devino) +{ + int irq; + + irq = sysino_exists(devhandle, devino); + if (irq) + goto out; + + irq = sysino_build_irq(devhandle, devino, &sun4v_irq); +out: return irq; } -void ack_bad_irq(unsigned int irq) +unsigned int sun4v_build_irq(u32 devhandle, unsigned int devino) { - unsigned int ino = irq_table[irq].dev_ino; + unsigned int irq; - if (!ino) - ino = 0xdeadbeef; + if (sun4v_cookie_only_virqs()) + irq = sun4v_build_cookie(devhandle, devino); + else + irq = sun4v_build_sysino(devhandle, devino); - printk(KERN_CRIT "Unexpected IRQ from ino[%x] irq[%u]\n", - ino, irq); + return irq; +} + +unsigned int sun4v_build_virq(u32 devhandle, unsigned int devino) +{ + int irq; + + irq = cookie_build_irq(devhandle, devino, &sun4v_virq); + if (!irq) + goto out; + + /* This is borrowed from the original function. + */ + irq_set_status_flags(irq, IRQ_NOAUTOEN); + +out: + return irq; } void *hardirq_stack[NR_CPUS]; @@ -720,9 +871,12 @@ void fixup_irqs(void) for (irq = 0; irq < NR_IRQS; irq++) { struct irq_desc *desc = irq_to_desc(irq); - struct irq_data *data = irq_desc_get_irq_data(desc); + struct irq_data *data; unsigned long flags; + if (!desc) + continue; + data = irq_desc_get_irq_data(desc); raw_spin_lock_irqsave(&desc->lock, flags); if (desc->action && !irqd_is_per_cpu(data)) { if (data->chip->irq_set_affinity) @@ -922,16 +1076,22 @@ static struct irqaction timer_irq_action = { .name = "timer", }; -/* Only invoked on boot processor. */ -void __init init_IRQ(void) +static void __init irq_ivector_init(void) { - unsigned long size; + unsigned long size, order; + unsigned int ivecs; - map_prom_timers(); - kill_prom_timer(); + /* If we are doing cookie only VIRQs then we do not need the ivector + * table to process interrupts. + */ + if (sun4v_cookie_only_virqs()) + return; - size = sizeof(struct ino_bucket) * NUM_IVECS; - ivector_table = kzalloc(size, GFP_KERNEL); + ivecs = size_nr_ivec(); + size = sizeof(struct ino_bucket) * ivecs; + order = get_order(size); + ivector_table = (struct ino_bucket *) + __get_free_pages(GFP_KERNEL | __GFP_ZERO, order); if (!ivector_table) { prom_printf("Fatal error, cannot allocate ivector_table\n"); prom_halt(); @@ -940,6 +1100,15 @@ void __init init_IRQ(void) ((unsigned long) ivector_table) + size); ivector_table_pa = __pa(ivector_table); +} + +/* Only invoked on boot processor.*/ +void __init init_IRQ(void) +{ + irq_init_hv(); + irq_ivector_init(); + map_prom_timers(); + kill_prom_timer(); if (tlb_type == hypervisor) sun4v_init_mondo_queues(); diff --git a/arch/sparc/kernel/ktlb.S b/arch/sparc/kernel/ktlb.S index 605d49204580..ef0d8e9e1210 100644 --- a/arch/sparc/kernel/ktlb.S +++ b/arch/sparc/kernel/ktlb.S @@ -47,14 +47,6 @@ kvmap_itlb_vmalloc_addr: KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_itlb_longpath) TSB_LOCK_TAG(%g1, %g2, %g7) - - /* Load and check PTE. */ - ldxa [%g5] ASI_PHYS_USE_EC, %g5 - mov 1, %g7 - sllx %g7, TSB_TAG_INVALID_BIT, %g7 - brgez,a,pn %g5, kvmap_itlb_longpath - TSB_STORE(%g1, %g7) - TSB_WRITE(%g1, %g5, %g6) /* fallthrough to TLB load */ @@ -118,6 +110,12 @@ kvmap_dtlb_obp: ba,pt %xcc, kvmap_dtlb_load nop +kvmap_linear_early: + sethi %hi(kern_linear_pte_xor), %g7 + ldx [%g7 + %lo(kern_linear_pte_xor)], %g2 + ba,pt %xcc, kvmap_dtlb_tsb4m_load + xor %g2, %g4, %g5 + .align 32 kvmap_dtlb_tsb4m_load: TSB_LOCK_TAG(%g1, %g2, %g7) @@ -146,105 +144,17 @@ kvmap_dtlb_4v: /* Correct TAG_TARGET is already in %g6, check 4mb TSB. */ KERN_TSB4M_LOOKUP_TL1(%g6, %g5, %g1, %g2, %g3, kvmap_dtlb_load) #endif - /* TSB entry address left in %g1, lookup linear PTE. - * Must preserve %g1 and %g6 (TAG). - */ -kvmap_dtlb_tsb4m_miss: - /* Clear the PAGE_OFFSET top virtual bits, shift - * down to get PFN, and make sure PFN is in range. - */ -661: sllx %g4, 0, %g5 - .section .page_offset_shift_patch, "ax" - .word 661b - .previous - - /* Check to see if we know about valid memory at the 4MB - * chunk this physical address will reside within. + /* Linear mapping TSB lookup failed. Fallthrough to kernel + * page table based lookup. */ -661: srlx %g5, MAX_PHYS_ADDRESS_BITS, %g2 - .section .page_offset_shift_patch, "ax" - .word 661b - .previous - - brnz,pn %g2, kvmap_dtlb_longpath - nop - - /* This unconditional branch and delay-slot nop gets patched - * by the sethi sequence once the bitmap is properly setup. - */ - .globl valid_addr_bitmap_insn -valid_addr_bitmap_insn: - ba,pt %xcc, 2f - nop - .subsection 2 - .globl valid_addr_bitmap_patch -valid_addr_bitmap_patch: - sethi %hi(sparc64_valid_addr_bitmap), %g7 - or %g7, %lo(sparc64_valid_addr_bitmap), %g7 - .previous - -661: srlx %g5, ILOG2_4MB, %g2 - .section .page_offset_shift_patch, "ax" - .word 661b - .previous - - srlx %g2, 6, %g5 - and %g2, 63, %g2 - sllx %g5, 3, %g5 - ldx [%g7 + %g5], %g5 - mov 1, %g7 - sllx %g7, %g2, %g7 - andcc %g5, %g7, %g0 - be,pn %xcc, kvmap_dtlb_longpath - -2: sethi %hi(kpte_linear_bitmap), %g2 - - /* Get the 256MB physical address index. */ -661: sllx %g4, 0, %g5 - .section .page_offset_shift_patch, "ax" - .word 661b - .previous - - or %g2, %lo(kpte_linear_bitmap), %g2 - -661: srlx %g5, ILOG2_256MB, %g5 - .section .page_offset_shift_patch, "ax" - .word 661b - .previous - - and %g5, (32 - 1), %g7 - - /* Divide by 32 to get the offset into the bitmask. */ - srlx %g5, 5, %g5 - add %g7, %g7, %g7 - sllx %g5, 3, %g5 - - /* kern_linear_pte_xor[(mask >> shift) & 3)] */ - ldx [%g2 + %g5], %g2 - srlx %g2, %g7, %g7 - sethi %hi(kern_linear_pte_xor), %g5 - and %g7, 3, %g7 - or %g5, %lo(kern_linear_pte_xor), %g5 - sllx %g7, 3, %g7 - ldx [%g5 + %g7], %g2 - .globl kvmap_linear_patch kvmap_linear_patch: - ba,pt %xcc, kvmap_dtlb_tsb4m_load - xor %g2, %g4, %g5 + ba,a,pt %xcc, kvmap_linear_early kvmap_dtlb_vmalloc_addr: KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_dtlb_longpath) TSB_LOCK_TAG(%g1, %g2, %g7) - - /* Load and check PTE. */ - ldxa [%g5] ASI_PHYS_USE_EC, %g5 - mov 1, %g7 - sllx %g7, TSB_TAG_INVALID_BIT, %g7 - brgez,a,pn %g5, kvmap_dtlb_longpath - TSB_STORE(%g1, %g7) - TSB_WRITE(%g1, %g5, %g6) /* fallthrough to TLB load */ @@ -276,13 +186,8 @@ kvmap_dtlb_load: #ifdef CONFIG_SPARSEMEM_VMEMMAP kvmap_vmemmap: - sub %g4, %g5, %g5 - srlx %g5, ILOG2_4MB, %g5 - sethi %hi(vmemmap_table), %g1 - sllx %g5, 3, %g5 - or %g1, %lo(vmemmap_table), %g1 - ba,pt %xcc, kvmap_dtlb_load - ldx [%g1 + %g5], %g5 + KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_dtlb_longpath) + ba,a,pt %xcc, kvmap_dtlb_load #endif kvmap_dtlb_nonlinear: @@ -294,8 +199,8 @@ kvmap_dtlb_nonlinear: #ifdef CONFIG_SPARSEMEM_VMEMMAP /* Do not use the TSB for vmemmap. */ - mov (VMEMMAP_BASE >> 40), %g5 - sllx %g5, 40, %g5 + sethi %hi(VMEMMAP_BASE), %g5 + ldx [%g5 + %lo(VMEMMAP_BASE)], %g5 cmp %g4,%g5 bgeu,pn %xcc, kvmap_vmemmap nop @@ -307,8 +212,8 @@ kvmap_dtlb_tsbmiss: sethi %hi(MODULES_VADDR), %g5 cmp %g4, %g5 blu,pn %xcc, kvmap_dtlb_longpath - mov (VMALLOC_END >> 40), %g5 - sllx %g5, 40, %g5 + sethi %hi(VMALLOC_END), %g5 + ldx [%g5 + %lo(VMALLOC_END)], %g5 cmp %g4, %g5 bgeu,pn %xcc, kvmap_dtlb_longpath nop diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c index 66dacd56bb10..27bb55485472 100644 --- a/arch/sparc/kernel/ldc.c +++ b/arch/sparc/kernel/ldc.c @@ -1078,7 +1078,8 @@ static void ldc_iommu_release(struct ldc_channel *lp) struct ldc_channel *ldc_alloc(unsigned long id, const struct ldc_channel_config *cfgp, - void *event_arg) + void *event_arg, + const char *name) { struct ldc_channel *lp; const struct ldc_mode_ops *mops; @@ -1093,6 +1094,8 @@ struct ldc_channel *ldc_alloc(unsigned long id, err = -EINVAL; if (!cfgp) goto out_err; + if (!name) + goto out_err; switch (cfgp->mode) { case LDC_MODE_RAW: @@ -1185,6 +1188,21 @@ struct ldc_channel *ldc_alloc(unsigned long id, INIT_HLIST_HEAD(&lp->mh_list); + snprintf(lp->rx_irq_name, LDC_IRQ_NAME_MAX, "%s RX", name); + snprintf(lp->tx_irq_name, LDC_IRQ_NAME_MAX, "%s TX", name); + + err = request_irq(lp->cfg.rx_irq, ldc_rx, 0, + lp->rx_irq_name, lp); + if (err) + goto out_free_txq; + + err = request_irq(lp->cfg.tx_irq, ldc_tx, 0, + lp->tx_irq_name, lp); + if (err) { + free_irq(lp->cfg.rx_irq, lp); + goto out_free_txq; + } + return lp; out_free_txq: @@ -1237,31 +1255,14 @@ EXPORT_SYMBOL(ldc_free); * state. This does not initiate a handshake, ldc_connect() does * that. */ -int ldc_bind(struct ldc_channel *lp, const char *name) +int ldc_bind(struct ldc_channel *lp) { unsigned long hv_err, flags; int err = -EINVAL; - if (!name || - (lp->state != LDC_STATE_INIT)) + if (lp->state != LDC_STATE_INIT) return -EINVAL; - snprintf(lp->rx_irq_name, LDC_IRQ_NAME_MAX, "%s RX", name); - snprintf(lp->tx_irq_name, LDC_IRQ_NAME_MAX, "%s TX", name); - - err = request_irq(lp->cfg.rx_irq, ldc_rx, 0, - lp->rx_irq_name, lp); - if (err) - return err; - - err = request_irq(lp->cfg.tx_irq, ldc_tx, 0, - lp->tx_irq_name, lp); - if (err) { - free_irq(lp->cfg.rx_irq, lp); - return err; - } - - spin_lock_irqsave(&lp->lock, flags); enable_irq(lp->cfg.rx_irq); diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c index 6479256fd5a4..fce8ab17bcbb 100644 --- a/arch/sparc/kernel/nmi.c +++ b/arch/sparc/kernel/nmi.c @@ -141,7 +141,6 @@ static inline unsigned int get_nmi_count(int cpu) static __init void nmi_cpu_busy(void *data) { - local_irq_enable_in_hardirq(); while (endflag == 0) mb(); } diff --git a/arch/sparc/kernel/pci_schizo.c b/arch/sparc/kernel/pci_schizo.c index 8f76f23dac38..f9c6813c132d 100644 --- a/arch/sparc/kernel/pci_schizo.c +++ b/arch/sparc/kernel/pci_schizo.c @@ -581,7 +581,7 @@ static irqreturn_t schizo_pcierr_intr_other(struct pci_pbm_info *pbm) { unsigned long csr_reg, csr, csr_error_bits; irqreturn_t ret = IRQ_NONE; - u16 stat; + u32 stat; csr_reg = pbm->pbm_regs + SCHIZO_PCI_CTRL; csr = upa_readq(csr_reg); @@ -617,7 +617,7 @@ static irqreturn_t schizo_pcierr_intr_other(struct pci_pbm_info *pbm) pbm->name); ret = IRQ_HANDLED; } - pci_read_config_word(pbm->pci_bus->self, PCI_STATUS, &stat); + pbm->pci_ops->read(pbm->pci_bus, 0, PCI_STATUS, 2, &stat); if (stat & (PCI_STATUS_PARITY | PCI_STATUS_SIG_TARGET_ABORT | PCI_STATUS_REC_TARGET_ABORT | @@ -625,7 +625,7 @@ static irqreturn_t schizo_pcierr_intr_other(struct pci_pbm_info *pbm) PCI_STATUS_SIG_SYSTEM_ERROR)) { printk("%s: PCI bus error, PCI_STATUS[%04x]\n", pbm->name, stat); - pci_write_config_word(pbm->pci_bus->self, PCI_STATUS, 0xffff); + pbm->pci_ops->write(pbm->pci_bus, 0, PCI_STATUS, 2, 0xffff); ret = IRQ_HANDLED; } return ret; diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c index 269af58497aa..7e967c8018c8 100644 --- a/arch/sparc/kernel/pcr.c +++ b/arch/sparc/kernel/pcr.c @@ -191,12 +191,41 @@ static const struct pcr_ops n4_pcr_ops = { .pcr_nmi_disable = PCR_N4_PICNPT, }; +static u64 n5_pcr_read(unsigned long reg_num) +{ + unsigned long val; + + (void) sun4v_t5_get_perfreg(reg_num, &val); + + return val; +} + +static void n5_pcr_write(unsigned long reg_num, u64 val) +{ + (void) sun4v_t5_set_perfreg(reg_num, val); +} + +static const struct pcr_ops n5_pcr_ops = { + .read_pcr = n5_pcr_read, + .write_pcr = n5_pcr_write, + .read_pic = n4_pic_read, + .write_pic = n4_pic_write, + .nmi_picl_value = n4_picl_value, + .pcr_nmi_enable = (PCR_N4_PICNPT | PCR_N4_STRACE | + PCR_N4_UTRACE | PCR_N4_TOE | + (26 << PCR_N4_SL_SHIFT)), + .pcr_nmi_disable = PCR_N4_PICNPT, +}; + + static unsigned long perf_hsvc_group; static unsigned long perf_hsvc_major; static unsigned long perf_hsvc_minor; static int __init register_perf_hsvc(void) { + unsigned long hverror; + if (tlb_type == hypervisor) { switch (sun4v_chip_type) { case SUN4V_CHIP_NIAGARA1: @@ -215,6 +244,10 @@ static int __init register_perf_hsvc(void) perf_hsvc_group = HV_GRP_VT_CPU; break; + case SUN4V_CHIP_NIAGARA5: + perf_hsvc_group = HV_GRP_T5_CPU; + break; + default: return -ENODEV; } @@ -222,10 +255,12 @@ static int __init register_perf_hsvc(void) perf_hsvc_major = 1; perf_hsvc_minor = 0; - if (sun4v_hvapi_register(perf_hsvc_group, - perf_hsvc_major, - &perf_hsvc_minor)) { - printk("perfmon: Could not register hvapi.\n"); + hverror = sun4v_hvapi_register(perf_hsvc_group, + perf_hsvc_major, + &perf_hsvc_minor); + if (hverror) { + pr_err("perfmon: Could not register hvapi(0x%lx).\n", + hverror); return -ENODEV; } } @@ -254,6 +289,10 @@ static int __init setup_sun4v_pcr_ops(void) pcr_ops = &n4_pcr_ops; break; + case SUN4V_CHIP_NIAGARA5: + pcr_ops = &n5_pcr_ops; + break; + default: ret = -ENODEV; break; diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index b5c38faa4ead..3ccb6777a7e1 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -960,6 +960,8 @@ out: cpuc->pcr[0] |= cpuc->event[0]->hw.config_base; } +static void sparc_pmu_start(struct perf_event *event, int flags); + /* On this PMU each PIC has it's own PCR control register. */ static void calculate_multiple_pcrs(struct cpu_hw_events *cpuc) { @@ -972,20 +974,13 @@ static void calculate_multiple_pcrs(struct cpu_hw_events *cpuc) struct perf_event *cp = cpuc->event[i]; struct hw_perf_event *hwc = &cp->hw; int idx = hwc->idx; - u64 enc; if (cpuc->current_idx[i] != PIC_NO_INDEX) continue; - sparc_perf_event_set_period(cp, hwc, idx); cpuc->current_idx[i] = idx; - enc = perf_event_get_enc(cpuc->events[i]); - cpuc->pcr[idx] &= ~mask_for_index(idx); - if (hwc->state & PERF_HES_STOPPED) - cpuc->pcr[idx] |= nop_for_index(idx); - else - cpuc->pcr[idx] |= event_encoding(enc, idx); + sparc_pmu_start(cp, PERF_EF_RELOAD); } out: for (i = 0; i < cpuc->n_events; i++) { @@ -1101,7 +1096,6 @@ static void sparc_pmu_del(struct perf_event *event, int _flags) int i; local_irq_save(flags); - perf_pmu_disable(event->pmu); for (i = 0; i < cpuc->n_events; i++) { if (event == cpuc->event[i]) { @@ -1127,7 +1121,6 @@ static void sparc_pmu_del(struct perf_event *event, int _flags) } } - perf_pmu_enable(event->pmu); local_irq_restore(flags); } @@ -1361,7 +1354,6 @@ static int sparc_pmu_add(struct perf_event *event, int ef_flags) unsigned long flags; local_irq_save(flags); - perf_pmu_disable(event->pmu); n0 = cpuc->n_events; if (n0 >= sparc_pmu->max_hw_events) @@ -1394,7 +1386,6 @@ nocheck: ret = 0; out: - perf_pmu_enable(event->pmu); local_irq_restore(flags); return ret; } @@ -1662,7 +1653,8 @@ static bool __init supported_pmu(void) sparc_pmu = &niagara2_pmu; return true; } - if (!strcmp(sparc_pmu_type, "niagara4")) { + if (!strcmp(sparc_pmu_type, "niagara4") || + !strcmp(sparc_pmu_type, "niagara5")) { sparc_pmu = &niagara4_pmu; return true; } @@ -1671,9 +1663,12 @@ static bool __init supported_pmu(void) int __init init_hw_perf_events(void) { + int err; + pr_info("Performance events: "); - if (!supported_pmu()) { + err = pcr_arch_init(); + if (err || !supported_pmu()) { pr_cont("No support for PMU type '%s'\n", sparc_pmu_type); return 0; } @@ -1685,7 +1680,7 @@ int __init init_hw_perf_events(void) return 0; } -early_initcall(init_hw_perf_events); +pure_initcall(init_hw_perf_events); void perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index d7b4967f8fa6..1a79d6877981 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -281,6 +281,8 @@ void arch_trigger_all_cpu_backtrace(void) printk(" TPC[%lx] O7[%lx] I7[%lx] RPC[%lx]\n", gp->tpc, gp->o7, gp->i7, gp->rpc); } + + touch_nmi_watchdog(); } memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot)); @@ -306,6 +308,9 @@ static void __global_pmu_self(int this_cpu) struct global_pmu_snapshot *pp; int i, num; + if (!pcr_ops) + return; + pp = &global_cpu_snapshot[this_cpu].pmu; num = 1; @@ -353,6 +358,8 @@ static void pmu_snapshot_all_cpus(void) (cpu == this_cpu ? '*' : ' '), cpu, pp->pcr[0], pp->pcr[1], pp->pcr[2], pp->pcr[3], pp->pic[0], pp->pic[1], pp->pic[2], pp->pic[3]); + + touch_nmi_watchdog(); } memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot)); diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index 3fdb455e3318..61a519808cb7 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -30,6 +30,7 @@ #include <linux/cpu.h> #include <linux/initrd.h> #include <linux/module.h> +#include <linux/start_kernel.h> #include <asm/io.h> #include <asm/processor.h> @@ -174,7 +175,7 @@ char reboot_command[COMMAND_LINE_SIZE]; static struct pt_regs fake_swapper_regs = { { 0, }, 0, 0, 0, 0 }; -void __init per_cpu_patch(void) +static void __init per_cpu_patch(void) { struct cpuid_patch_entry *p; unsigned long ver; @@ -266,7 +267,7 @@ void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *start, } } -void __init sun4v_patch(void) +static void __init sun4v_patch(void) { extern void sun4v_hvapi_init(void); @@ -335,14 +336,25 @@ static void __init pause_patch(void) } } -#ifdef CONFIG_SMP -void __init boot_cpu_id_too_large(int cpu) +void __init start_early_boot(void) { - prom_printf("Serious problem, boot cpu id (%d) >= NR_CPUS (%d)\n", - cpu, NR_CPUS); - prom_halt(); + int cpu; + + check_if_starfire(); + per_cpu_patch(); + sun4v_patch(); + + cpu = hard_smp_processor_id(); + if (cpu >= NR_CPUS) { + prom_printf("Serious problem, boot cpu id (%d) >= NR_CPUS (%d)\n", + cpu, NR_CPUS); + prom_halt(); + } + current_thread_info()->cpu = cpu; + + prom_init_report(); + start_kernel(); } -#endif /* On Ultra, we support all of the v8 capabilities. */ unsigned long sparc64_elf_hwcap = (HWCAP_SPARC_FLUSH | HWCAP_SPARC_STBAR | @@ -500,12 +512,16 @@ static void __init init_sparc64_elf_hwcap(void) sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= HWCAP_SPARC_BLKINIT; if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 || sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= HWCAP_SPARC_N2; } @@ -533,6 +549,8 @@ static void __init init_sparc64_elf_hwcap(void) sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= (AV_SPARC_VIS | AV_SPARC_VIS2 | AV_SPARC_ASI_BLK_INIT | @@ -540,6 +558,8 @@ static void __init init_sparc64_elf_hwcap(void) if (sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= (AV_SPARC_VIS3 | AV_SPARC_HPC | AV_SPARC_FMAF); diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 8416d7fadcce..9af0a5dbb36d 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -823,13 +823,17 @@ void arch_send_call_function_single_ipi(int cpu) void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs) { clear_softint(1 << irq); + irq_enter(); generic_smp_call_function_interrupt(); + irq_exit(); } void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs) { clear_softint(1 << irq); + irq_enter(); generic_smp_call_function_single_interrupt(); + irq_exit(); } static void tsb_sync(void *info) @@ -1395,7 +1399,6 @@ void __cpu_die(unsigned int cpu) void __init smp_cpus_done(unsigned int max_cpus) { - pcr_arch_init(); } void smp_send_reschedule(int cpu) @@ -1480,6 +1483,13 @@ static void __init pcpu_populate_pte(unsigned long addr) pud_t *pud; pmd_t *pmd; + if (pgd_none(*pgd)) { + pud_t *new; + + new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); + pgd_populate(&init_mm, pgd, new); + } + pud = pud_offset(pgd, addr); if (pud_none(*pud)) { pmd_t *new; diff --git a/arch/sparc/kernel/sun4v_tlb_miss.S b/arch/sparc/kernel/sun4v_tlb_miss.S index e0c09bf85610..6179e19bc9b9 100644 --- a/arch/sparc/kernel/sun4v_tlb_miss.S +++ b/arch/sparc/kernel/sun4v_tlb_miss.S @@ -195,6 +195,11 @@ sun4v_tsb_miss_common: ldx [%g2 + TRAP_PER_CPU_PGD_PADDR], %g7 sun4v_itlb_error: + rdpr %tl, %g1 + cmp %g1, 1 + ble,pt %icc, sun4v_bad_ra + or %g0, FAULT_CODE_BAD_RA | FAULT_CODE_ITLB, %g1 + sethi %hi(sun4v_err_itlb_vaddr), %g1 stx %g4, [%g1 + %lo(sun4v_err_itlb_vaddr)] sethi %hi(sun4v_err_itlb_ctx), %g1 @@ -206,15 +211,10 @@ sun4v_itlb_error: sethi %hi(sun4v_err_itlb_error), %g1 stx %o0, [%g1 + %lo(sun4v_err_itlb_error)] + sethi %hi(1f), %g7 rdpr %tl, %g4 - cmp %g4, 1 - ble,pt %icc, 1f - sethi %hi(2f), %g7 ba,pt %xcc, etraptl1 - or %g7, %lo(2f), %g7 - -1: ba,pt %xcc, etrap -2: or %g7, %lo(2b), %g7 +1: or %g7, %lo(1f), %g7 mov %l4, %o1 call sun4v_itlb_error_report add %sp, PTREGS_OFF, %o0 @@ -222,6 +222,11 @@ sun4v_itlb_error: /* NOTREACHED */ sun4v_dtlb_error: + rdpr %tl, %g1 + cmp %g1, 1 + ble,pt %icc, sun4v_bad_ra + or %g0, FAULT_CODE_BAD_RA | FAULT_CODE_DTLB, %g1 + sethi %hi(sun4v_err_dtlb_vaddr), %g1 stx %g4, [%g1 + %lo(sun4v_err_dtlb_vaddr)] sethi %hi(sun4v_err_dtlb_ctx), %g1 @@ -233,21 +238,23 @@ sun4v_dtlb_error: sethi %hi(sun4v_err_dtlb_error), %g1 stx %o0, [%g1 + %lo(sun4v_err_dtlb_error)] + sethi %hi(1f), %g7 rdpr %tl, %g4 - cmp %g4, 1 - ble,pt %icc, 1f - sethi %hi(2f), %g7 ba,pt %xcc, etraptl1 - or %g7, %lo(2f), %g7 - -1: ba,pt %xcc, etrap -2: or %g7, %lo(2b), %g7 +1: or %g7, %lo(1f), %g7 mov %l4, %o1 call sun4v_dtlb_error_report add %sp, PTREGS_OFF, %o0 /* NOTREACHED */ +sun4v_bad_ra: + or %g0, %g4, %g5 + ba,pt %xcc, sparc64_realfault_common + or %g1, %g0, %g4 + + /* NOTREACHED */ + /* Instruction Access Exception, tl0. */ sun4v_iacc: ldxa [%g0] ASI_SCRATCHPAD, %g2 diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index beb0b5a5f21f..25db14a33d03 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -332,7 +332,7 @@ SYSCALL_DEFINE6(sparc_ipc, unsigned int, call, int, first, unsigned long, second long err; /* No need for backward compatibility. We can start fresh... */ - if (call <= SEMCTL) { + if (call <= SEMTIMEDOP) { switch (call) { case SEMOP: err = sys_semtimedop(first, ptr, diff --git a/arch/sparc/kernel/trampoline_64.S b/arch/sparc/kernel/trampoline_64.S index 737f8cbc7d56..88ede1d53b4c 100644 --- a/arch/sparc/kernel/trampoline_64.S +++ b/arch/sparc/kernel/trampoline_64.S @@ -109,10 +109,13 @@ startup_continue: brnz,pn %g1, 1b nop - sethi %hi(p1275buf), %g2 - or %g2, %lo(p1275buf), %g2 - ldx [%g2 + 0x10], %l2 - add %l2, -(192 + 128), %sp + /* Get onto temporary stack which will be in the locked + * kernel image. + */ + sethi %hi(tramp_stack), %g1 + or %g1, %lo(tramp_stack), %g1 + add %g1, TRAMP_STACK_SIZE, %g1 + sub %g1, STACKFRAME_SZ + STACK_BIAS + 256, %sp flushw /* Setup the loop variables: @@ -394,7 +397,6 @@ after_lock_tlb: sllx %g5, THREAD_SHIFT, %g5 sub %g5, (STACKFRAME_SZ + STACK_BIAS), %g5 add %g6, %g5, %sp - mov 0, %fp rdpr %pstate, %o1 or %o1, PSTATE_IE, %o1 diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index 4ced92f05358..25d0c7ece9cc 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -2102,6 +2102,11 @@ void sun4v_nonresum_overflow(struct pt_regs *regs) atomic_inc(&sun4v_nonresum_oflow_cnt); } +static void sun4v_tlb_error(struct pt_regs *regs) +{ + die_if_kernel("TLB/TSB error", regs); +} + unsigned long sun4v_err_itlb_vaddr; unsigned long sun4v_err_itlb_ctx; unsigned long sun4v_err_itlb_pte; @@ -2109,8 +2114,7 @@ unsigned long sun4v_err_itlb_error; void sun4v_itlb_error_report(struct pt_regs *regs, int tl) { - if (tl > 1) - dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); + dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); printk(KERN_EMERG "SUN4V-ITLB: Error at TPC[%lx], tl %d\n", regs->tpc, tl); @@ -2123,7 +2127,7 @@ void sun4v_itlb_error_report(struct pt_regs *regs, int tl) sun4v_err_itlb_vaddr, sun4v_err_itlb_ctx, sun4v_err_itlb_pte, sun4v_err_itlb_error); - prom_halt(); + sun4v_tlb_error(regs); } unsigned long sun4v_err_dtlb_vaddr; @@ -2133,8 +2137,7 @@ unsigned long sun4v_err_dtlb_error; void sun4v_dtlb_error_report(struct pt_regs *regs, int tl) { - if (tl > 1) - dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); + dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); printk(KERN_EMERG "SUN4V-DTLB: Error at TPC[%lx], tl %d\n", regs->tpc, tl); @@ -2147,7 +2150,7 @@ void sun4v_dtlb_error_report(struct pt_regs *regs, int tl) sun4v_err_dtlb_vaddr, sun4v_err_dtlb_ctx, sun4v_err_dtlb_pte, sun4v_err_dtlb_error); - prom_halt(); + sun4v_tlb_error(regs); } void hypervisor_tlbop_error(unsigned long err, unsigned long op) diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S index 14158d40ba76..be98685c14c6 100644 --- a/arch/sparc/kernel/tsb.S +++ b/arch/sparc/kernel/tsb.S @@ -162,10 +162,10 @@ tsb_miss_page_table_walk_sun4v_fastpath: nop .previous - rdpr %tl, %g3 - cmp %g3, 1 + rdpr %tl, %g7 + cmp %g7, 1 bne,pn %xcc, winfix_trampoline - nop + mov %g3, %g4 ba,pt %xcc, etrap rd %pc, %g7 call hugetlb_setup diff --git a/arch/sparc/kernel/viohs.c b/arch/sparc/kernel/viohs.c index f8e7dd53e1c7..9c5fbd0b8a04 100644 --- a/arch/sparc/kernel/viohs.c +++ b/arch/sparc/kernel/viohs.c @@ -714,7 +714,7 @@ int vio_ldc_alloc(struct vio_driver_state *vio, cfg.tx_irq = vio->vdev->tx_irq; cfg.rx_irq = vio->vdev->rx_irq; - lp = ldc_alloc(vio->vdev->channel_id, &cfg, event_arg); + lp = ldc_alloc(vio->vdev->channel_id, &cfg, event_arg, vio->name); if (IS_ERR(lp)) return PTR_ERR(lp); @@ -746,7 +746,7 @@ void vio_port_up(struct vio_driver_state *vio) err = 0; if (state == LDC_STATE_INIT) { - err = ldc_bind(vio->lp, vio->name); + err = ldc_bind(vio->lp); if (err) printk(KERN_WARNING "%s: Port %lu bind failed, " "err=%d\n", diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index 932ff90fd760..09243057cb0b 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -35,8 +35,9 @@ jiffies = jiffies_64; SECTIONS { - /* swapper_low_pmd_dir is sparc64 only */ - swapper_low_pmd_dir = 0x0000000000402000; +#ifdef CONFIG_SPARC64 + swapper_pg_dir = 0x0000000000402000; +#endif . = INITIAL_ADDRESS; .text TEXTSTART : { @@ -122,11 +123,6 @@ SECTIONS *(.swapper_4m_tsb_phys_patch) __swapper_4m_tsb_phys_patch_end = .; } - .page_offset_shift_patch : { - __page_offset_shift_patch = .; - *(.page_offset_shift_patch) - __page_offset_shift_patch_end = .; - } .popc_3insn_patch : { __popc_3insn_patch = .; *(.popc_3insn_patch) diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S index 9cf2ee01cee3..140527a20e7d 100644 --- a/arch/sparc/lib/NG4memcpy.S +++ b/arch/sparc/lib/NG4memcpy.S @@ -41,6 +41,10 @@ #endif #endif +#if !defined(EX_LD) && !defined(EX_ST) +#define NON_USER_COPY +#endif + #ifndef EX_LD #define EX_LD(x) x #endif @@ -197,9 +201,13 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ mov EX_RETVAL(%o3), %o0 .Llarge_src_unaligned: +#ifdef NON_USER_COPY + VISEntryHalfFast(.Lmedium_vis_entry_fail) +#else + VISEntryHalf +#endif andn %o2, 0x3f, %o4 sub %o2, %o4, %o2 - VISEntryHalf alignaddr %o1, %g0, %g1 add %o1, %o4, %o1 EX_LD(LOAD(ldd, %g1 + 0x00, %f0)) @@ -240,6 +248,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ nop ba,a,pt %icc, .Lmedium_unaligned +#ifdef NON_USER_COPY +.Lmedium_vis_entry_fail: + or %o0, %o1, %g2 +#endif .Lmedium: LOAD(prefetch, %o1 + 0x40, #n_reads_strong) andcc %g2, 0x7, %g0 diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c index 1d32b54089aa..8f2f94d53434 100644 --- a/arch/sparc/lib/atomic32.c +++ b/arch/sparc/lib/atomic32.c @@ -40,6 +40,19 @@ int __atomic_add_return(int i, atomic_t *v) } EXPORT_SYMBOL(__atomic_add_return); +int atomic_xchg(atomic_t *v, int new) +{ + int ret; + unsigned long flags; + + spin_lock_irqsave(ATOMIC_HASH(v), flags); + ret = v->counter; + v->counter = new; + spin_unlock_irqrestore(ATOMIC_HASH(v), flags); + return ret; +} +EXPORT_SYMBOL(atomic_xchg); + int atomic_cmpxchg(atomic_t *v, int old, int new) { int ret; @@ -132,3 +145,17 @@ unsigned long __cmpxchg_u32(volatile u32 *ptr, u32 old, u32 new) return (unsigned long)prev; } EXPORT_SYMBOL(__cmpxchg_u32); + +unsigned long __xchg_u32(volatile u32 *ptr, u32 new) +{ + unsigned long flags; + u32 prev; + + spin_lock_irqsave(ATOMIC_HASH(ptr), flags); + prev = *ptr; + *ptr = new; + spin_unlock_irqrestore(ATOMIC_HASH(ptr), flags); + + return (unsigned long)prev; +} +EXPORT_SYMBOL(__xchg_u32); diff --git a/arch/sparc/lib/memmove.S b/arch/sparc/lib/memmove.S index b7f6334e159f..857ad4f8905f 100644 --- a/arch/sparc/lib/memmove.S +++ b/arch/sparc/lib/memmove.S @@ -8,9 +8,11 @@ .text ENTRY(memmove) /* o0=dst o1=src o2=len */ - mov %o0, %g1 + brz,pn %o2, 99f + mov %o0, %g1 + cmp %o0, %o1 - bleu,pt %xcc, memcpy + bleu,pt %xcc, 2f add %o1, %o2, %g7 cmp %g7, %o0 bleu,pt %xcc, memcpy @@ -24,7 +26,34 @@ ENTRY(memmove) /* o0=dst o1=src o2=len */ stb %g7, [%o0] bne,pt %icc, 1b sub %o0, 1, %o0 - +99: retl mov %g1, %o0 + + /* We can't just call memcpy for these memmove cases. On some + * chips the memcpy uses cache initializing stores and when dst + * and src are close enough, those can clobber the source data + * before we've loaded it in. + */ +2: or %o0, %o1, %g7 + or %o2, %g7, %g7 + andcc %g7, 0x7, %g0 + bne,pn %xcc, 4f + nop + +3: ldx [%o1], %g7 + add %o1, 8, %o1 + subcc %o2, 8, %o2 + add %o0, 8, %o0 + bne,pt %icc, 3b + stx %g7, [%o0 - 0x8] + ba,a,pt %xcc, 99b + +4: ldub [%o1], %g7 + add %o1, 1, %o1 + subcc %o2, 1, %o2 + add %o0, 1, %o0 + bne,pt %icc, 4b + stb %g7, [%o0 - 0x1] + ba,a,pt %xcc, 99b ENDPROC(memmove) diff --git a/arch/sparc/lib/memset.S b/arch/sparc/lib/memset.S index 99c017be8719..f75e6906df14 100644 --- a/arch/sparc/lib/memset.S +++ b/arch/sparc/lib/memset.S @@ -3,8 +3,9 @@ * Copyright (C) 1996,1997 Jakub Jelinek (jj@sunsite.mff.cuni.cz) * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu) * - * Returns 0, if ok, and number of bytes not yet set if exception - * occurs and we were called as clear_user. + * Calls to memset returns initial %o0. Calls to bzero returns 0, if ok, and + * number of bytes not yet set if exception occurs and we were called as + * clear_user. */ #include <asm/ptrace.h> @@ -65,6 +66,8 @@ __bzero_begin: .globl __memset_start, __memset_end __memset_start: memset: + mov %o0, %g1 + mov 1, %g4 and %o1, 0xff, %g3 sll %g3, 8, %g2 or %g3, %g2, %g3 @@ -89,6 +92,7 @@ memset: sub %o0, %o2, %o0 __bzero: + clr %g4 mov %g0, %g3 1: cmp %o1, 7 @@ -151,8 +155,8 @@ __bzero: bne,a 8f EX(stb %g3, [%o0], and %o1, 1) 8: - retl - clr %o0 + b 0f + nop 7: be 13b orcc %o1, 0, %g0 @@ -164,6 +168,12 @@ __bzero: bne 8b EX(stb %g3, [%o0 - 1], add %o1, 1) 0: + andcc %g4, 1, %g0 + be 5f + nop + retl + mov %g1, %o0 +5: retl clr %o0 __memset_end: diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 4ced3fc66130..45a413e4380a 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -348,6 +348,9 @@ retry: down_read(&mm->mmap_sem); } + if (fault_code & FAULT_CODE_BAD_RA) + goto do_sigbus; + vma = find_vma(mm, address); if (!vma) goto bad_area; diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c index 1aed0432c64b..ae6ce383d4df 100644 --- a/arch/sparc/mm/gup.c +++ b/arch/sparc/mm/gup.c @@ -160,6 +160,36 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, return 1; } +int __get_user_pages_fast(unsigned long start, int nr_pages, int write, + struct page **pages) +{ + struct mm_struct *mm = current->mm; + unsigned long addr, len, end; + unsigned long next, flags; + pgd_t *pgdp; + int nr = 0; + + start &= PAGE_MASK; + addr = start; + len = (unsigned long) nr_pages << PAGE_SHIFT; + end = start + len; + + local_irq_save(flags); + pgdp = pgd_offset(mm, addr); + do { + pgd_t pgd = *pgdp; + + next = pgd_addr_end(addr, end); + if (pgd_none(pgd)) + break; + if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) + break; + } while (pgdp++, addr = next, addr != end); + local_irq_restore(flags); + + return nr; +} + int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages) { diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 96862241b342..34506f292533 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -73,7 +73,6 @@ unsigned long kern_linear_pte_xor[4] __read_mostly; * 'cpu' properties, but we need to have this table setup before the * MDESC is initialized. */ -unsigned long kpte_linear_bitmap[KPTE_BITMAP_BYTES / sizeof(unsigned long)]; #ifndef CONFIG_DEBUG_PAGEALLOC /* A special kernel TSB for 4MB, 256MB, 2GB and 16GB linear mappings. @@ -82,10 +81,11 @@ unsigned long kpte_linear_bitmap[KPTE_BITMAP_BYTES / sizeof(unsigned long)]; */ extern struct tsb swapper_4m_tsb[KERNEL_TSB4M_NENTRIES]; #endif +extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES]; static unsigned long cpu_pgsz_mask; -#define MAX_BANKS 32 +#define MAX_BANKS 1024 static struct linux_prom64_registers pavail[MAX_BANKS]; static int pavail_ents; @@ -163,10 +163,6 @@ static void __init read_obp_memory(const char *property, cmp_p64, NULL); } -unsigned long sparc64_valid_addr_bitmap[VALID_ADDR_BITMAP_BYTES / - sizeof(unsigned long)]; -EXPORT_SYMBOL(sparc64_valid_addr_bitmap); - /* Kernel physical address base and size in bytes. */ unsigned long kern_base __read_mostly; unsigned long kern_size __read_mostly; @@ -838,7 +834,10 @@ static int find_node(unsigned long addr) if ((addr & p->mask) == p->val) return i; } - return -1; + /* 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; } static u64 memblock_nid_range(u64 start, u64 end, int *nid) @@ -1360,9 +1359,144 @@ static unsigned long __init bootmem_init(unsigned long phys_base) static struct linux_prom64_registers pall[MAX_BANKS] __initdata; static int pall_ents __initdata; -#ifdef CONFIG_DEBUG_PAGEALLOC +static unsigned long max_phys_bits = 40; + +bool kern_addr_valid(unsigned long addr) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + if ((long)addr < 0L) { + unsigned long pa = __pa(addr); + + if ((addr >> max_phys_bits) != 0UL) + return false; + + return pfn_valid(pa >> PAGE_SHIFT); + } + + if (addr >= (unsigned long) KERNBASE && + addr < (unsigned long)&_end) + return true; + + pgd = pgd_offset_k(addr); + if (pgd_none(*pgd)) + return 0; + + pud = pud_offset(pgd, addr); + if (pud_none(*pud)) + return 0; + + if (pud_large(*pud)) + return pfn_valid(pud_pfn(*pud)); + + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + return 0; + + if (pmd_large(*pmd)) + return pfn_valid(pmd_pfn(*pmd)); + + pte = pte_offset_kernel(pmd, addr); + if (pte_none(*pte)) + return 0; + + return pfn_valid(pte_pfn(*pte)); +} +EXPORT_SYMBOL(kern_addr_valid); + +static unsigned long __ref kernel_map_hugepud(unsigned long vstart, + unsigned long vend, + pud_t *pud) +{ + const unsigned long mask16gb = (1UL << 34) - 1UL; + u64 pte_val = vstart; + + /* Each PUD is 8GB */ + if ((vstart & mask16gb) || + (vend - vstart <= mask16gb)) { + pte_val ^= kern_linear_pte_xor[2]; + pud_val(*pud) = pte_val | _PAGE_PUD_HUGE; + + return vstart + PUD_SIZE; + } + + pte_val ^= kern_linear_pte_xor[3]; + pte_val |= _PAGE_PUD_HUGE; + + vend = vstart + mask16gb + 1UL; + while (vstart < vend) { + pud_val(*pud) = pte_val; + + pte_val += PUD_SIZE; + vstart += PUD_SIZE; + pud++; + } + return vstart; +} + +static bool kernel_can_map_hugepud(unsigned long vstart, unsigned long vend, + bool guard) +{ + if (guard && !(vstart & ~PUD_MASK) && (vend - vstart) >= PUD_SIZE) + return true; + + return false; +} + +static unsigned long __ref kernel_map_hugepmd(unsigned long vstart, + unsigned long vend, + pmd_t *pmd) +{ + const unsigned long mask256mb = (1UL << 28) - 1UL; + const unsigned long mask2gb = (1UL << 31) - 1UL; + u64 pte_val = vstart; + + /* Each PMD is 8MB */ + if ((vstart & mask256mb) || + (vend - vstart <= mask256mb)) { + pte_val ^= kern_linear_pte_xor[0]; + pmd_val(*pmd) = pte_val | _PAGE_PMD_HUGE; + + return vstart + PMD_SIZE; + } + + if ((vstart & mask2gb) || + (vend - vstart <= mask2gb)) { + pte_val ^= kern_linear_pte_xor[1]; + pte_val |= _PAGE_PMD_HUGE; + vend = vstart + mask256mb + 1UL; + } else { + pte_val ^= kern_linear_pte_xor[2]; + pte_val |= _PAGE_PMD_HUGE; + vend = vstart + mask2gb + 1UL; + } + + while (vstart < vend) { + pmd_val(*pmd) = pte_val; + + pte_val += PMD_SIZE; + vstart += PMD_SIZE; + pmd++; + } + + return vstart; +} + +static bool kernel_can_map_hugepmd(unsigned long vstart, unsigned long vend, + bool guard) +{ + if (guard && !(vstart & ~PMD_MASK) && (vend - vstart) >= PMD_SIZE) + return true; + + return false; +} + static unsigned long __ref kernel_map_range(unsigned long pstart, - unsigned long pend, pgprot_t prot) + unsigned long pend, pgprot_t prot, + bool use_huge) { unsigned long vstart = PAGE_OFFSET + pstart; unsigned long vend = PAGE_OFFSET + pend; @@ -1381,19 +1515,34 @@ static unsigned long __ref kernel_map_range(unsigned long pstart, pmd_t *pmd; pte_t *pte; + if (pgd_none(*pgd)) { + pud_t *new; + + new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); + alloc_bytes += PAGE_SIZE; + pgd_populate(&init_mm, pgd, new); + } pud = pud_offset(pgd, vstart); if (pud_none(*pud)) { pmd_t *new; + if (kernel_can_map_hugepud(vstart, vend, use_huge)) { + vstart = kernel_map_hugepud(vstart, vend, pud); + continue; + } new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); alloc_bytes += PAGE_SIZE; pud_populate(&init_mm, pud, new); } pmd = pmd_offset(pud, vstart); - if (!pmd_present(*pmd)) { + if (pmd_none(*pmd)) { pte_t *new; + if (kernel_can_map_hugepmd(vstart, vend, use_huge)) { + vstart = kernel_map_hugepmd(vstart, vend, pmd); + continue; + } new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); alloc_bytes += PAGE_SIZE; pmd_populate_kernel(&init_mm, pmd, new); @@ -1416,100 +1565,34 @@ static unsigned long __ref kernel_map_range(unsigned long pstart, return alloc_bytes; } -extern unsigned int kvmap_linear_patch[1]; -#endif /* CONFIG_DEBUG_PAGEALLOC */ - -static void __init kpte_set_val(unsigned long index, unsigned long val) +static void __init flush_all_kernel_tsbs(void) { - unsigned long *ptr = kpte_linear_bitmap; - - val <<= ((index % (BITS_PER_LONG / 2)) * 2); - ptr += (index / (BITS_PER_LONG / 2)); - - *ptr |= val; -} - -static const unsigned long kpte_shift_min = 28; /* 256MB */ -static const unsigned long kpte_shift_max = 34; /* 16GB */ -static const unsigned long kpte_shift_incr = 3; - -static unsigned long kpte_mark_using_shift(unsigned long start, unsigned long end, - unsigned long shift) -{ - unsigned long size = (1UL << shift); - unsigned long mask = (size - 1UL); - unsigned long remains = end - start; - unsigned long val; - - if (remains < size || (start & mask)) - return start; - - /* VAL maps: - * - * shift 28 --> kern_linear_pte_xor index 1 - * shift 31 --> kern_linear_pte_xor index 2 - * shift 34 --> kern_linear_pte_xor index 3 - */ - val = ((shift - kpte_shift_min) / kpte_shift_incr) + 1; - - remains &= ~mask; - if (shift != kpte_shift_max) - remains = size; - - while (remains) { - unsigned long index = start >> kpte_shift_min; + int i; - kpte_set_val(index, val); + for (i = 0; i < KERNEL_TSB_NENTRIES; i++) { + struct tsb *ent = &swapper_tsb[i]; - start += 1UL << kpte_shift_min; - remains -= 1UL << kpte_shift_min; + ent->tag = (1UL << TSB_TAG_INVALID_BIT); } +#ifndef CONFIG_DEBUG_PAGEALLOC + for (i = 0; i < KERNEL_TSB4M_NENTRIES; i++) { + struct tsb *ent = &swapper_4m_tsb[i]; - return start; -} - -static void __init mark_kpte_bitmap(unsigned long start, unsigned long end) -{ - unsigned long smallest_size, smallest_mask; - unsigned long s; - - smallest_size = (1UL << kpte_shift_min); - smallest_mask = (smallest_size - 1UL); - - while (start < end) { - unsigned long orig_start = start; - - for (s = kpte_shift_max; s >= kpte_shift_min; s -= kpte_shift_incr) { - start = kpte_mark_using_shift(start, end, s); - - if (start != orig_start) - break; - } - - if (start == orig_start) - start = (start + smallest_size) & ~smallest_mask; + ent->tag = (1UL << TSB_TAG_INVALID_BIT); } +#endif } -static void __init init_kpte_bitmap(void) -{ - unsigned long i; - - for (i = 0; i < pall_ents; i++) { - unsigned long phys_start, phys_end; - - phys_start = pall[i].phys_addr; - phys_end = phys_start + pall[i].reg_size; - - mark_kpte_bitmap(phys_start, phys_end); - } -} +extern unsigned int kvmap_linear_patch[1]; static void __init kernel_physical_mapping_init(void) { -#ifdef CONFIG_DEBUG_PAGEALLOC unsigned long i, mem_alloced = 0UL; + bool use_huge = true; +#ifdef CONFIG_DEBUG_PAGEALLOC + use_huge = false; +#endif for (i = 0; i < pall_ents; i++) { unsigned long phys_start, phys_end; @@ -1517,7 +1600,7 @@ static void __init kernel_physical_mapping_init(void) phys_end = phys_start + pall[i].reg_size; mem_alloced += kernel_map_range(phys_start, phys_end, - PAGE_KERNEL); + PAGE_KERNEL, use_huge); } printk("Allocated %ld bytes for kernel page tables.\n", @@ -1526,8 +1609,9 @@ static void __init kernel_physical_mapping_init(void) kvmap_linear_patch[0] = 0x01000000; /* nop */ flushi(&kvmap_linear_patch[0]); + flush_all_kernel_tsbs(); + __flush_tlb_all(); -#endif } #ifdef CONFIG_DEBUG_PAGEALLOC @@ -1537,7 +1621,7 @@ void kernel_map_pages(struct page *page, int numpages, int enable) unsigned long phys_end = phys_start + (numpages * PAGE_SIZE); kernel_map_range(phys_start, phys_end, - (enable ? PAGE_KERNEL : __pgprot(0))); + (enable ? PAGE_KERNEL : __pgprot(0)), false); flush_tsb_kernel_range(PAGE_OFFSET + phys_start, PAGE_OFFSET + phys_end); @@ -1565,76 +1649,56 @@ unsigned long __init find_ecache_flush_span(unsigned long size) unsigned long PAGE_OFFSET; EXPORT_SYMBOL(PAGE_OFFSET); -static void __init page_offset_shift_patch_one(unsigned int *insn, unsigned long phys_bits) -{ - unsigned long final_shift; - unsigned int val = *insn; - unsigned int cnt; - - /* We are patching in ilog2(max_supported_phys_address), and - * we are doing so in a manner similar to a relocation addend. - * That is, we are adding the shift value to whatever value - * is in the shift instruction count field already. - */ - cnt = (val & 0x3f); - val &= ~0x3f; - - /* If we are trying to shift >= 64 bits, clear the destination - * register. This can happen when phys_bits ends up being equal - * to MAX_PHYS_ADDRESS_BITS. - */ - final_shift = (cnt + (64 - phys_bits)); - if (final_shift >= 64) { - unsigned int rd = (val >> 25) & 0x1f; - - val = 0x80100000 | (rd << 25); - } else { - val |= final_shift; - } - *insn = val; - - __asm__ __volatile__("flush %0" - : /* no outputs */ - : "r" (insn)); -} - -static void __init page_offset_shift_patch(unsigned long phys_bits) -{ - extern unsigned int __page_offset_shift_patch; - extern unsigned int __page_offset_shift_patch_end; - unsigned int *p; - - p = &__page_offset_shift_patch; - while (p < &__page_offset_shift_patch_end) { - unsigned int *insn = (unsigned int *)(unsigned long)*p; +unsigned long VMALLOC_END = 0x0000010000000000UL; +EXPORT_SYMBOL(VMALLOC_END); - page_offset_shift_patch_one(insn, phys_bits); - - p++; - } -} +unsigned long sparc64_va_hole_top = 0xfffff80000000000UL; +unsigned long sparc64_va_hole_bottom = 0x0000080000000000UL; static void __init setup_page_offset(void) { - unsigned long max_phys_bits = 40; - if (tlb_type == cheetah || tlb_type == cheetah_plus) { + /* Cheetah/Panther support a full 64-bit virtual + * address, so we can use all that our page tables + * support. + */ + sparc64_va_hole_top = 0xfff0000000000000UL; + sparc64_va_hole_bottom = 0x0010000000000000UL; + max_phys_bits = 42; } else if (tlb_type == hypervisor) { switch (sun4v_chip_type) { case SUN4V_CHIP_NIAGARA1: case SUN4V_CHIP_NIAGARA2: + /* T1 and T2 support 48-bit virtual addresses. */ + sparc64_va_hole_top = 0xffff800000000000UL; + sparc64_va_hole_bottom = 0x0000800000000000UL; + max_phys_bits = 39; break; case SUN4V_CHIP_NIAGARA3: + /* T3 supports 48-bit virtual addresses. */ + sparc64_va_hole_top = 0xffff800000000000UL; + sparc64_va_hole_bottom = 0x0000800000000000UL; + max_phys_bits = 43; break; case SUN4V_CHIP_NIAGARA4: case SUN4V_CHIP_NIAGARA5: case SUN4V_CHIP_SPARC64X: - default: + case SUN4V_CHIP_SPARC_M6: + /* T4 and later support 52-bit virtual addresses. */ + sparc64_va_hole_top = 0xfff8000000000000UL; + sparc64_va_hole_bottom = 0x0008000000000000UL; max_phys_bits = 47; break; + case SUN4V_CHIP_SPARC_M7: + default: + /* M7 and later support 52-bit virtual addresses. */ + sparc64_va_hole_top = 0xfff8000000000000UL; + sparc64_va_hole_bottom = 0x0008000000000000UL; + max_phys_bits = 49; + break; } } @@ -1644,12 +1708,16 @@ static void __init setup_page_offset(void) prom_halt(); } - PAGE_OFFSET = PAGE_OFFSET_BY_BITS(max_phys_bits); + PAGE_OFFSET = sparc64_va_hole_top; + VMALLOC_END = ((sparc64_va_hole_bottom >> 1) + + (sparc64_va_hole_bottom >> 2)); - pr_info("PAGE_OFFSET is 0x%016lx (max_phys_bits == %lu)\n", + pr_info("MM: PAGE_OFFSET is 0x%016lx (max_phys_bits == %lu)\n", PAGE_OFFSET, max_phys_bits); - - page_offset_shift_patch(max_phys_bits); + pr_info("MM: VMALLOC [0x%016lx --> 0x%016lx]\n", + VMALLOC_START, VMALLOC_END); + pr_info("MM: VMEMMAP [0x%016lx --> 0x%016lx]\n", + VMEMMAP_BASE, VMEMMAP_BASE << 1); } static void __init tsb_phys_patch(void) @@ -1694,21 +1762,42 @@ static void __init tsb_phys_patch(void) #define NUM_KTSB_DESCR 1 #endif static struct hv_tsb_descr ktsb_descr[NUM_KTSB_DESCR]; -extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES]; + +/* The swapper TSBs are loaded with a base sequence of: + * + * sethi %uhi(SYMBOL), REG1 + * sethi %hi(SYMBOL), REG2 + * or REG1, %ulo(SYMBOL), REG1 + * or REG2, %lo(SYMBOL), REG2 + * sllx REG1, 32, REG1 + * or REG1, REG2, REG1 + * + * When we use physical addressing for the TSB accesses, we patch the + * first four instructions in the above sequence. + */ static void patch_one_ktsb_phys(unsigned int *start, unsigned int *end, unsigned long pa) { - pa >>= KTSB_PHYS_SHIFT; + unsigned long high_bits, low_bits; + + high_bits = (pa >> 32) & 0xffffffff; + low_bits = (pa >> 0) & 0xffffffff; while (start < end) { unsigned int *ia = (unsigned int *)(unsigned long)*start; - ia[0] = (ia[0] & ~0x3fffff) | (pa >> 10); + ia[0] = (ia[0] & ~0x3fffff) | (high_bits >> 10); __asm__ __volatile__("flush %0" : : "r" (ia)); - ia[1] = (ia[1] & ~0x3ff) | (pa & 0x3ff); + ia[1] = (ia[1] & ~0x3fffff) | (low_bits >> 10); __asm__ __volatile__("flush %0" : : "r" (ia + 1)); + ia[2] = (ia[2] & ~0x1fff) | (high_bits & 0x3ff); + __asm__ __volatile__("flush %0" : : "r" (ia + 2)); + + ia[3] = (ia[3] & ~0x1fff) | (low_bits & 0x3ff); + __asm__ __volatile__("flush %0" : : "r" (ia + 3)); + start++; } } @@ -1847,7 +1936,6 @@ static void __init sun4v_linear_pte_xor_finalize(void) /* paging_init() sets up the page tables */ static unsigned long last_valid_pfn; -pgd_t swapper_pg_dir[PTRS_PER_PGD]; static void sun4u_pgprot_init(void); static void sun4v_pgprot_init(void); @@ -1950,16 +2038,10 @@ void __init paging_init(void) */ init_mm.pgd += ((shift) / (sizeof(pgd_t))); - memset(swapper_low_pmd_dir, 0, sizeof(swapper_low_pmd_dir)); + memset(swapper_pg_dir, 0, sizeof(swapper_pg_dir)); - /* Now can init the kernel/bad page tables. */ - pud_set(pud_offset(&swapper_pg_dir[0], 0), - swapper_low_pmd_dir + (shift / sizeof(pgd_t))); - inherit_prom_mappings(); - init_kpte_bitmap(); - /* Ok, we can use our TLB miss and window trap handlers safely. */ setup_tba(); @@ -2066,70 +2148,6 @@ int page_in_phys_avail(unsigned long paddr) return 0; } -static struct linux_prom64_registers pavail_rescan[MAX_BANKS] __initdata; -static int pavail_rescan_ents __initdata; - -/* Certain OBP calls, such as fetching "available" properties, can - * claim physical memory. So, along with initializing the valid - * address bitmap, what we do here is refetch the physical available - * memory list again, and make sure it provides at least as much - * memory as 'pavail' does. - */ -static void __init setup_valid_addr_bitmap_from_pavail(unsigned long *bitmap) -{ - int i; - - read_obp_memory("available", &pavail_rescan[0], &pavail_rescan_ents); - - for (i = 0; i < pavail_ents; i++) { - unsigned long old_start, old_end; - - old_start = pavail[i].phys_addr; - old_end = old_start + pavail[i].reg_size; - while (old_start < old_end) { - int n; - - for (n = 0; n < pavail_rescan_ents; n++) { - unsigned long new_start, new_end; - - new_start = pavail_rescan[n].phys_addr; - new_end = new_start + - pavail_rescan[n].reg_size; - - if (new_start <= old_start && - new_end >= (old_start + PAGE_SIZE)) { - set_bit(old_start >> ILOG2_4MB, bitmap); - goto do_next_page; - } - } - - prom_printf("mem_init: Lost memory in pavail\n"); - prom_printf("mem_init: OLD start[%lx] size[%lx]\n", - pavail[i].phys_addr, - pavail[i].reg_size); - prom_printf("mem_init: NEW start[%lx] size[%lx]\n", - pavail_rescan[i].phys_addr, - pavail_rescan[i].reg_size); - prom_printf("mem_init: Cannot continue, aborting.\n"); - prom_halt(); - - do_next_page: - old_start += PAGE_SIZE; - } - } -} - -static void __init patch_tlb_miss_handler_bitmap(void) -{ - extern unsigned int valid_addr_bitmap_insn[]; - extern unsigned int valid_addr_bitmap_patch[]; - - valid_addr_bitmap_insn[1] = valid_addr_bitmap_patch[1]; - mb(); - valid_addr_bitmap_insn[0] = valid_addr_bitmap_patch[0]; - flushi(&valid_addr_bitmap_insn[0]); -} - static void __init register_page_bootmem_info(void) { #ifdef CONFIG_NEED_MULTIPLE_NODES @@ -2142,18 +2160,6 @@ static void __init register_page_bootmem_info(void) } void __init mem_init(void) { - unsigned long addr, last; - - addr = PAGE_OFFSET + kern_base; - last = PAGE_ALIGN(kern_size) + addr; - while (addr < last) { - set_bit(__pa(addr) >> ILOG2_4MB, sparc64_valid_addr_bitmap); - addr += PAGE_SIZE; - } - - setup_valid_addr_bitmap_from_pavail(sparc64_valid_addr_bitmap); - patch_tlb_miss_handler_bitmap(); - high_memory = __va(last_valid_pfn << PAGE_SHIFT); register_page_bootmem_info(); @@ -2243,18 +2249,9 @@ unsigned long _PAGE_CACHE __read_mostly; EXPORT_SYMBOL(_PAGE_CACHE); #ifdef CONFIG_SPARSEMEM_VMEMMAP -unsigned long vmemmap_table[VMEMMAP_SIZE]; - -static long __meminitdata addr_start, addr_end; -static int __meminitdata node_start; - int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend, int node) { - unsigned long phys_start = (vstart - VMEMMAP_BASE); - unsigned long phys_end = (vend - VMEMMAP_BASE); - unsigned long addr = phys_start & VMEMMAP_CHUNK_MASK; - unsigned long end = VMEMMAP_ALIGN(phys_end); unsigned long pte_base; pte_base = (_PAGE_VALID | _PAGE_SZ4MB_4U | @@ -2265,47 +2262,52 @@ int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend, _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_P_4V | _PAGE_W_4V); - for (; addr < end; addr += VMEMMAP_CHUNK) { - unsigned long *vmem_pp = - vmemmap_table + (addr >> VMEMMAP_CHUNK_SHIFT); - void *block; + pte_base |= _PAGE_PMD_HUGE; - if (!(*vmem_pp & _PAGE_VALID)) { - block = vmemmap_alloc_block(1UL << ILOG2_4MB, node); - if (!block) + vstart = vstart & PMD_MASK; + vend = ALIGN(vend, PMD_SIZE); + for (; vstart < vend; vstart += PMD_SIZE) { + pgd_t *pgd = pgd_offset_k(vstart); + unsigned long pte; + pud_t *pud; + pmd_t *pmd; + + if (pgd_none(*pgd)) { + pud_t *new = vmemmap_alloc_block(PAGE_SIZE, node); + + if (!new) return -ENOMEM; + pgd_populate(&init_mm, pgd, new); + } - *vmem_pp = pte_base | __pa(block); + pud = pud_offset(pgd, vstart); + if (pud_none(*pud)) { + pmd_t *new = vmemmap_alloc_block(PAGE_SIZE, node); - /* check to see if we have contiguous blocks */ - if (addr_end != addr || node_start != node) { - if (addr_start) - printk(KERN_DEBUG " [%lx-%lx] on node %d\n", - addr_start, addr_end-1, node_start); - addr_start = addr; - node_start = node; - } - addr_end = addr + VMEMMAP_CHUNK; + if (!new) + return -ENOMEM; + pud_populate(&init_mm, pud, new); } - } - return 0; -} -void __meminit vmemmap_populate_print_last(void) -{ - if (addr_start) { - printk(KERN_DEBUG " [%lx-%lx] on node %d\n", - addr_start, addr_end-1, node_start); - addr_start = 0; - addr_end = 0; - node_start = 0; + pmd = pmd_offset(pud, vstart); + + pte = pmd_val(*pmd); + if (!(pte & _PAGE_VALID)) { + void *block = vmemmap_alloc_block(PMD_SIZE, node); + + if (!block) + return -ENOMEM; + + pmd_val(*pmd) = pte_base | __pa(block); + } } + + return 0; } void vmemmap_free(unsigned long start, unsigned long end) { } - #endif /* CONFIG_SPARSEMEM_VMEMMAP */ static void prot_init_common(unsigned long page_none, @@ -2717,8 +2719,8 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end) do_flush_tlb_kernel_range(start, LOW_OBP_ADDRESS); } if (end > HI_OBP_ADDRESS) { - flush_tsb_kernel_range(end, HI_OBP_ADDRESS); - do_flush_tlb_kernel_range(end, HI_OBP_ADDRESS); + flush_tsb_kernel_range(HI_OBP_ADDRESS, end); + do_flush_tlb_kernel_range(HI_OBP_ADDRESS, end); } } else { flush_tsb_kernel_range(start, end); diff --git a/arch/sparc/mm/init_64.h b/arch/sparc/mm/init_64.h index 5d3782deb403..ac491193cb54 100644 --- a/arch/sparc/mm/init_64.h +++ b/arch/sparc/mm/init_64.h @@ -8,15 +8,8 @@ */ #define MAX_PHYS_ADDRESS (1UL << MAX_PHYS_ADDRESS_BITS) -#define KPTE_BITMAP_CHUNK_SZ (256UL * 1024UL * 1024UL) -#define KPTE_BITMAP_BYTES \ - ((MAX_PHYS_ADDRESS / KPTE_BITMAP_CHUNK_SZ) / 4) -#define VALID_ADDR_BITMAP_CHUNK_SZ (4UL * 1024UL * 1024UL) -#define VALID_ADDR_BITMAP_BYTES \ - ((MAX_PHYS_ADDRESS / VALID_ADDR_BITMAP_CHUNK_SZ) / 8) extern unsigned long kern_linear_pte_xor[4]; -extern unsigned long kpte_linear_bitmap[KPTE_BITMAP_BYTES / sizeof(unsigned long)]; extern unsigned int sparc64_highest_unlocked_tlb_ent; extern unsigned long sparc64_kern_pri_context; extern unsigned long sparc64_kern_pri_nuc_bits; @@ -38,15 +31,4 @@ extern unsigned long kern_locked_tte_data; extern void prom_world(int enter); -#ifdef CONFIG_SPARSEMEM_VMEMMAP -#define VMEMMAP_CHUNK_SHIFT 22 -#define VMEMMAP_CHUNK (1UL << VMEMMAP_CHUNK_SHIFT) -#define VMEMMAP_CHUNK_MASK ~(VMEMMAP_CHUNK - 1UL) -#define VMEMMAP_ALIGN(x) (((x)+VMEMMAP_CHUNK-1UL)&VMEMMAP_CHUNK_MASK) - -#define VMEMMAP_SIZE ((((1UL << MAX_PHYSADDR_BITS) >> PAGE_SHIFT) * \ - sizeof(struct page)) >> VMEMMAP_CHUNK_SHIFT) -extern unsigned long vmemmap_table[VMEMMAP_SIZE]; -#endif - #endif /* _SPARC64_MM_INIT_H */ diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index cfbe53c17b0d..09daebdee552 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -460,10 +460,12 @@ static void __init sparc_context_init(int numctx) void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, struct task_struct *tsk) { + unsigned long flags; + if (mm->context == NO_CONTEXT) { - spin_lock(&srmmu_context_spinlock); + spin_lock_irqsave(&srmmu_context_spinlock, flags); alloc_context(old_mm, mm); - spin_unlock(&srmmu_context_spinlock); + spin_unlock_irqrestore(&srmmu_context_spinlock, flags); srmmu_ctxd_set(&srmmu_context_table[mm->context], mm->pgd); } @@ -988,14 +990,15 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) void destroy_context(struct mm_struct *mm) { + unsigned long flags; if (mm->context != NO_CONTEXT) { flush_cache_mm(mm); srmmu_ctxd_set(&srmmu_context_table[mm->context], srmmu_swapper_pg_dir); flush_tlb_mm(mm); - spin_lock(&srmmu_context_spinlock); + spin_lock_irqsave(&srmmu_context_spinlock, flags); free_context(mm->context); - spin_unlock(&srmmu_context_spinlock); + spin_unlock_irqrestore(&srmmu_context_spinlock, flags); mm->context = NO_CONTEXT; } } diff --git a/arch/sparc/power/hibernate_asm.S b/arch/sparc/power/hibernate_asm.S index 79942166df84..d7d9017dcb15 100644 --- a/arch/sparc/power/hibernate_asm.S +++ b/arch/sparc/power/hibernate_asm.S @@ -54,8 +54,8 @@ ENTRY(swsusp_arch_resume) nop /* Write PAGE_OFFSET to %g7 */ - sethi %uhi(PAGE_OFFSET), %g7 - sllx %g7, 32, %g7 + sethi %hi(PAGE_OFFSET), %g7 + ldx [%g7 + %lo(PAGE_OFFSET)], %g7 setuw (PAGE_SIZE-8), %g3 diff --git a/arch/sparc/prom/bootstr_64.c b/arch/sparc/prom/bootstr_64.c index ab9ccc63b388..7149e77714a4 100644 --- a/arch/sparc/prom/bootstr_64.c +++ b/arch/sparc/prom/bootstr_64.c @@ -14,7 +14,10 @@ * the .bss section or it will break things. */ -#define BARG_LEN 256 +/* We limit BARG_LEN to 1024 because this is the size of the + * 'barg_out' command line buffer in the SILO bootloader. + */ +#define BARG_LEN 1024 struct { int bootstr_len; int bootstr_valid; diff --git a/arch/sparc/prom/cif.S b/arch/sparc/prom/cif.S index 9c86b4b7d429..8050f381f518 100644 --- a/arch/sparc/prom/cif.S +++ b/arch/sparc/prom/cif.S @@ -11,11 +11,10 @@ .text .globl prom_cif_direct prom_cif_direct: + save %sp, -192, %sp sethi %hi(p1275buf), %o1 or %o1, %lo(p1275buf), %o1 - ldx [%o1 + 0x0010], %o2 ! prom_cif_stack - save %o2, -192, %sp - ldx [%i1 + 0x0008], %l2 ! prom_cif_handler + ldx [%o1 + 0x0008], %l2 ! prom_cif_handler mov %g4, %l0 mov %g5, %l1 mov %g6, %l3 diff --git a/arch/sparc/prom/init_64.c b/arch/sparc/prom/init_64.c index d95db755828f..110b0d78b864 100644 --- a/arch/sparc/prom/init_64.c +++ b/arch/sparc/prom/init_64.c @@ -26,13 +26,13 @@ phandle prom_chosen_node; * It gets passed the pointer to the PROM vector. */ -extern void prom_cif_init(void *, void *); +extern void prom_cif_init(void *); -void __init prom_init(void *cif_handler, void *cif_stack) +void __init prom_init(void *cif_handler) { phandle node; - prom_cif_init(cif_handler, cif_stack); + prom_cif_init(cif_handler); prom_chosen_node = prom_finddevice(prom_chosen_path); if (!prom_chosen_node || (s32)prom_chosen_node == -1) diff --git a/arch/sparc/prom/p1275.c b/arch/sparc/prom/p1275.c index e58b81726319..545d8bb79b65 100644 --- a/arch/sparc/prom/p1275.c +++ b/arch/sparc/prom/p1275.c @@ -9,6 +9,7 @@ #include <linux/smp.h> #include <linux/string.h> #include <linux/spinlock.h> +#include <linux/irqflags.h> #include <asm/openprom.h> #include <asm/oplib.h> @@ -19,7 +20,6 @@ struct { long prom_callback; /* 0x00 */ void (*prom_cif_handler)(long *); /* 0x08 */ - unsigned long prom_cif_stack; /* 0x10 */ } p1275buf; extern void prom_world(int); @@ -36,8 +36,8 @@ void p1275_cmd_direct(unsigned long *args) { unsigned long flags; - raw_local_save_flags(flags); - raw_local_irq_restore((unsigned long)PIL_NMI); + local_save_flags(flags); + local_irq_restore((unsigned long)PIL_NMI); raw_spin_lock(&prom_entry_lock); prom_world(1); @@ -45,11 +45,10 @@ void p1275_cmd_direct(unsigned long *args) prom_world(0); raw_spin_unlock(&prom_entry_lock); - raw_local_irq_restore(flags); + local_irq_restore(flags); } void prom_cif_init(void *cif_handler, void *cif_stack) { p1275buf.prom_cif_handler = (void (*)(long *))cif_handler; - p1275buf.prom_cif_stack = (unsigned long)cif_stack; } diff --git a/arch/tile/mm/homecache.c b/arch/tile/mm/homecache.c index 004ba568d93f..33294fdc402e 100644 --- a/arch/tile/mm/homecache.c +++ b/arch/tile/mm/homecache.c @@ -417,7 +417,7 @@ void __homecache_free_pages(struct page *page, unsigned int order) if (put_page_testzero(page)) { homecache_change_page_home(page, order, PAGE_HOME_HASH); if (order == 0) { - free_hot_cold_page(page, 0); + free_hot_cold_page(page, false); } else { init_page_count(page); __free_pages(page, order); diff --git a/arch/um/Kconfig.common b/arch/um/Kconfig.common index 21ca44c4f6d5..1f0ea5537e8a 100644 --- a/arch/um/Kconfig.common +++ b/arch/um/Kconfig.common @@ -2,6 +2,7 @@ config UML bool default y select HAVE_UID16 + select HAVE_FUTEX_CMPXCHG if FUTEX select GENERIC_IRQ_SHOW select GENERIC_CPU_DEVICES select GENERIC_IO diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 3716e6952554..e8ab93c3e638 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1277,7 +1277,7 @@ static void do_ubd_request(struct request_queue *q) while(1){ struct ubd *dev = q->queuedata; - if(dev->end_sg == 0){ + if(dev->request == NULL){ struct request *req = blk_fetch_request(q); if(req == NULL) return; @@ -1299,7 +1299,8 @@ static void do_ubd_request(struct request_queue *q) return; } prepare_flush_request(req, io_req); - submit_request(io_req, dev); + if (submit_request(io_req, dev) == false) + return; } while(dev->start_sg < dev->end_sg){ diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h index fb5e4c658f7a..ef470a7a3d0f 100644 --- a/arch/unicore32/include/asm/mmu_context.h +++ b/arch/unicore32/include/asm/mmu_context.h @@ -14,6 +14,8 @@ #include <linux/compiler.h> #include <linux/sched.h> +#include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/io.h> #include <asm/cacheflush.h> @@ -73,7 +75,7 @@ do { \ else \ mm->mmap = NULL; \ rb_erase(&high_vma->vm_rb, &mm->mm_rb); \ - mm->mmap_cache = NULL; \ + vmacache_invalidate(mm); \ mm->map_count--; \ remove_vma(high_vma); \ } \ diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e4098912fef2..09468b045172 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -22,6 +22,7 @@ config X86_64 config X86 def_bool y select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS + select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO select HAVE_AOUT if X86_32 @@ -854,7 +855,7 @@ source "kernel/Kconfig.preempt" config X86_UP_APIC bool "Local APIC support on uniprocessors" - depends on X86_32 && !SMP && !X86_32_NON_STANDARD && !PCI_MSI + depends on X86_32 && !SMP && !X86_32_NON_STANDARD ---help--- A local APIC (Advanced Programmable Interrupt Controller) is an integrated interrupt controller in the CPU. If you have a single-CPU @@ -865,6 +866,10 @@ config X86_UP_APIC performance counters), and the NMI watchdog which detects hard lockups. +config X86_UP_APIC_MSI + def_bool y + select X86_UP_APIC if X86_32 && !SMP && !X86_32_NON_STANDARD && PCI_MSI + config X86_UP_IOAPIC bool "IO-APIC support on uniprocessors" depends on X86_UP_APIC @@ -2436,12 +2441,9 @@ config X86_DMA_REMAP depends on STA2X11 config IOSF_MBI - bool + tristate + default m depends on PCI - ---help--- - To be selected by modules requiring access to the Intel OnChip System - Fabric (IOSF) Sideband MailBox Interface (MBI). For MBI platforms - enumerable by PCI. source "net/Kconfig" diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 0fcd9133790c..67e9f5cc91ed 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -75,8 +75,10 @@ suffix-$(CONFIG_KERNEL_XZ) := xz suffix-$(CONFIG_KERNEL_LZO) := lzo suffix-$(CONFIG_KERNEL_LZ4) := lz4 +RUN_SIZE = $(shell $(OBJDUMP) -h vmlinux | \ + $(CONFIG_SHELL) $(srctree)/arch/x86/tools/calc_run_size.sh) quiet_cmd_mkpiggy = MKPIGGY $@ - cmd_mkpiggy = $(obj)/mkpiggy $< > $@ || ( rm -f $@ ; false ) + cmd_mkpiggy = $(obj)/mkpiggy $< $(RUN_SIZE) > $@ || ( rm -f $@ ; false ) targets += piggy.S $(obj)/piggy.S: $(obj)/vmlinux.bin.$(suffix-y) $(obj)/mkpiggy FORCE diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c index 4dbf967da50d..6cfcf2a2eb93 100644 --- a/arch/x86/boot/compressed/aslr.c +++ b/arch/x86/boot/compressed/aslr.c @@ -183,12 +183,27 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, static bool mem_avoid_overlap(struct mem_vector *img) { int i; + struct setup_data *ptr; for (i = 0; i < MEM_AVOID_MAX; i++) { if (mem_overlaps(img, &mem_avoid[i])) return true; } + /* Avoid all entries in the setup_data linked list. */ + ptr = (struct setup_data *)(unsigned long)real_mode->hdr.setup_data; + while (ptr) { + struct mem_vector avoid; + + avoid.start = (u64)ptr; + avoid.size = sizeof(*ptr) + ptr->len; + + if (mem_overlaps(img, &avoid)) + return true; + + ptr = (struct setup_data *)(unsigned long)ptr->next; + } + return false; } diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 78cbb2db5a85..832a6590e9b3 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -489,8 +489,7 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table) hdr->type_of_loader = 0x21; /* Convert unicode cmdline to ascii */ - cmdline_ptr = efi_convert_cmdline_to_ascii(sys_table, image, - &options_size); + cmdline_ptr = efi_convert_cmdline(sys_table, image, &options_size); if (!cmdline_ptr) goto fail; hdr->cmd_line_ptr = (unsigned long)cmdline_ptr; diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h index 81b6b652b46a..cc78e2da7af9 100644 --- a/arch/x86/boot/compressed/eboot.h +++ b/arch/x86/boot/compressed/eboot.h @@ -10,6 +10,7 @@ #define SEG_GRANULARITY_4KB (1 << 0) #define DESC_TYPE_CODE_DATA (1 << 0) +#define EFI_READ_CHUNK_SIZE (1024 * 1024) #define EFI_CONSOLE_OUT_DEVICE_GUID \ EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, 0x9a, 0x46, 0x0, 0x90, 0x27, \ @@ -37,6 +38,24 @@ struct efi_graphics_output_mode_info { u32 pixels_per_scan_line; } __packed; +struct efi_graphics_output_protocol_mode_32 { + u32 max_mode; + u32 mode; + u32 info; + u32 size_of_info; + u64 frame_buffer_base; + u32 frame_buffer_size; +} __packed; + +struct efi_graphics_output_protocol_mode_64 { + u32 max_mode; + u32 mode; + u64 info; + u64 size_of_info; + u64 frame_buffer_base; + u64 frame_buffer_size; +} __packed; + struct efi_graphics_output_protocol_mode { u32 max_mode; u32 mode; @@ -46,6 +65,20 @@ struct efi_graphics_output_protocol_mode { unsigned long frame_buffer_size; } __packed; +struct efi_graphics_output_protocol_32 { + u32 query_mode; + u32 set_mode; + u32 blt; + u32 mode; +}; + +struct efi_graphics_output_protocol_64 { + u64 query_mode; + u64 set_mode; + u64 blt; + u64 mode; +}; + struct efi_graphics_output_protocol { void *query_mode; unsigned long set_mode; @@ -53,6 +86,18 @@ struct efi_graphics_output_protocol { struct efi_graphics_output_protocol_mode *mode; }; +struct efi_uga_draw_protocol_32 { + u32 get_mode; + u32 set_mode; + u32 blt; +}; + +struct efi_uga_draw_protocol_64 { + u64 get_mode; + u64 set_mode; + u64 blt; +}; + struct efi_uga_draw_protocol { void *get_mode; void *set_mode; diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index f45ab7a36fb6..c5b56ed10aff 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -186,7 +186,8 @@ relocated: * Do the decompression, and jump to the new kernel.. */ /* push arguments for decompress_kernel: */ - pushl $z_output_len /* decompressed length */ + pushl $z_run_size /* size of kernel with .bss and .brk */ + pushl $z_output_len /* decompressed length, end of relocs */ leal z_extract_offset_negative(%ebx), %ebp pushl %ebp /* output address */ pushl $z_input_len /* input_len */ @@ -196,7 +197,7 @@ relocated: pushl %eax /* heap area */ pushl %esi /* real mode pointer */ call decompress_kernel /* returns kernel location in %eax */ - addl $24, %esp + addl $28, %esp /* * Jump to the decompressed kernel. diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index b10fa66a2540..34bbc0911b7c 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -334,13 +334,16 @@ relocated: * Do the decompression, and jump to the new kernel.. */ pushq %rsi /* Save the real mode argument */ + movq $z_run_size, %r9 /* size of kernel with .bss and .brk */ + pushq %r9 movq %rsi, %rdi /* real mode address */ leaq boot_heap(%rip), %rsi /* malloc area for uncompression */ leaq input_data(%rip), %rdx /* input_data */ movl $z_input_len, %ecx /* input_len */ movq %rbp, %r8 /* output target address */ - movq $z_output_len, %r9 /* decompressed length */ + movq $z_output_len, %r9 /* decompressed length, end of relocs */ call decompress_kernel /* returns kernel location in %rax */ + popq %r9 popq %rsi /* diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 196eaf373a06..8f45c855f84c 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -393,8 +393,11 @@ asmlinkage void *decompress_kernel(void *rmode, memptr heap, unsigned char *input_data, unsigned long input_len, unsigned char *output, - unsigned long output_len) + unsigned long output_len, + unsigned long run_size) { + unsigned char *output_orig = output; + real_mode = rmode; sanitize_boot_params(real_mode); @@ -416,8 +419,14 @@ asmlinkage void *decompress_kernel(void *rmode, memptr heap, free_mem_ptr = heap; /* Heap */ free_mem_end_ptr = heap + BOOT_HEAP_SIZE; - output = choose_kernel_location(input_data, input_len, - output, output_len); + /* + * The memory hole needed for the kernel is the larger of either + * the entire decompressed kernel plus relocation table, or the + * entire decompressed kernel plus .bss and .brk sections. + */ + output = choose_kernel_location(input_data, input_len, output, + output_len > run_size ? output_len + : run_size); /* Validate memory location choices. */ if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1)) @@ -437,7 +446,12 @@ asmlinkage void *decompress_kernel(void *rmode, memptr heap, debug_putstr("\nDecompressing Linux... "); decompress(input_data, input_len, NULL, NULL, output, NULL, error); parse_elf(output); - handle_relocations(output, output_len); + /* + * 32-bit always performs relocations. 64-bit relocations are only + * needed if kASLR has chosen a different load address. + */ + if (!IS_ENABLED(CONFIG_X86_64) || output != output_orig) + handle_relocations(output, output_len); debug_putstr("done.\nBooting the kernel.\n"); return output; } diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c index b669ab65bf6c..d8222f213182 100644 --- a/arch/x86/boot/compressed/mkpiggy.c +++ b/arch/x86/boot/compressed/mkpiggy.c @@ -36,11 +36,13 @@ int main(int argc, char *argv[]) uint32_t olen; long ilen; unsigned long offs; + unsigned long run_size; FILE *f = NULL; int retval = 1; - if (argc < 2) { - fprintf(stderr, "Usage: %s compressed_file\n", argv[0]); + if (argc < 3) { + fprintf(stderr, "Usage: %s compressed_file run_size\n", + argv[0]); goto bail; } @@ -74,6 +76,7 @@ int main(int argc, char *argv[]) offs += olen >> 12; /* Add 8 bytes for each 32K block */ offs += 64*1024 + 128; /* Add 64K + 128 bytes slack */ offs = (offs+4095) & ~4095; /* Round to a 4K boundary */ + run_size = atoi(argv[2]); printf(".section \".rodata..compressed\",\"a\",@progbits\n"); printf(".globl z_input_len\n"); @@ -85,6 +88,8 @@ int main(int argc, char *argv[]) /* z_extract_offset_negative allows simplification of head_32.S */ printf(".globl z_extract_offset_negative\n"); printf("z_extract_offset_negative = -0x%lx\n", offs); + printf(".globl z_run_size\n"); + printf("z_run_size = %lu\n", run_size); printf(".globl input_data, input_data_end\n"); printf("input_data:\n"); diff --git a/arch/x86/crypto/aes_glue.c b/arch/x86/crypto/aes_glue.c index aafe8ce0d65d..e26984f7ab8d 100644 --- a/arch/x86/crypto/aes_glue.c +++ b/arch/x86/crypto/aes_glue.c @@ -66,5 +66,5 @@ module_exit(aes_fini); MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, asm optimized"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("aes"); -MODULE_ALIAS("aes-asm"); +MODULE_ALIAS_CRYPTO("aes"); +MODULE_ALIAS_CRYPTO("aes-asm"); diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 948ad0e77741..6d4fabac779c 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -1109,7 +1109,7 @@ static int __driver_rfc4106_decrypt(struct aead_request *req) src = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC); if (!src) return -ENOMEM; - assoc = (src + req->cryptlen + auth_tag_len); + assoc = (src + req->cryptlen); scatterwalk_map_and_copy(src, req->src, 0, req->cryptlen, 0); scatterwalk_map_and_copy(assoc, req->assoc, 0, req->assoclen, 0); @@ -1134,7 +1134,7 @@ static int __driver_rfc4106_decrypt(struct aead_request *req) scatterwalk_done(&src_sg_walk, 0, 0); scatterwalk_done(&assoc_sg_walk, 0, 0); } else { - scatterwalk_map_and_copy(dst, req->dst, 0, req->cryptlen, 1); + scatterwalk_map_and_copy(dst, req->dst, 0, tempCipherLen, 1); kfree(src); } return retval; @@ -1514,4 +1514,4 @@ module_exit(aesni_exit); MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, Intel AES-NI instructions optimized"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("aes"); +MODULE_ALIAS_CRYPTO("aes"); diff --git a/arch/x86/crypto/blowfish_glue.c b/arch/x86/crypto/blowfish_glue.c index 50ec333b70e6..1477cfcdbf6b 100644 --- a/arch/x86/crypto/blowfish_glue.c +++ b/arch/x86/crypto/blowfish_glue.c @@ -481,5 +481,5 @@ module_exit(fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Blowfish Cipher Algorithm, asm optimized"); -MODULE_ALIAS("blowfish"); -MODULE_ALIAS("blowfish-asm"); +MODULE_ALIAS_CRYPTO("blowfish"); +MODULE_ALIAS_CRYPTO("blowfish-asm"); diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c index 4209a76fcdaa..9a07fafe3831 100644 --- a/arch/x86/crypto/camellia_aesni_avx2_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c @@ -582,5 +582,5 @@ module_exit(camellia_aesni_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Camellia Cipher Algorithm, AES-NI/AVX2 optimized"); -MODULE_ALIAS("camellia"); -MODULE_ALIAS("camellia-asm"); +MODULE_ALIAS_CRYPTO("camellia"); +MODULE_ALIAS_CRYPTO("camellia-asm"); diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c index 87a041a10f4a..ed38d959add6 100644 --- a/arch/x86/crypto/camellia_aesni_avx_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx_glue.c @@ -574,5 +574,5 @@ module_exit(camellia_aesni_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Camellia Cipher Algorithm, AES-NI/AVX optimized"); -MODULE_ALIAS("camellia"); -MODULE_ALIAS("camellia-asm"); +MODULE_ALIAS_CRYPTO("camellia"); +MODULE_ALIAS_CRYPTO("camellia-asm"); diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c index c171dcbf192d..5c8b6266a394 100644 --- a/arch/x86/crypto/camellia_glue.c +++ b/arch/x86/crypto/camellia_glue.c @@ -1725,5 +1725,5 @@ module_exit(fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Camellia Cipher Algorithm, asm optimized"); -MODULE_ALIAS("camellia"); -MODULE_ALIAS("camellia-asm"); +MODULE_ALIAS_CRYPTO("camellia"); +MODULE_ALIAS_CRYPTO("camellia-asm"); diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c index e6a3700489b9..f62e9db5a462 100644 --- a/arch/x86/crypto/cast5_avx_glue.c +++ b/arch/x86/crypto/cast5_avx_glue.c @@ -494,4 +494,4 @@ module_exit(cast5_exit); MODULE_DESCRIPTION("Cast5 Cipher Algorithm, AVX optimized"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("cast5"); +MODULE_ALIAS_CRYPTO("cast5"); diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c index 09f3677393e4..0160f68a57ff 100644 --- a/arch/x86/crypto/cast6_avx_glue.c +++ b/arch/x86/crypto/cast6_avx_glue.c @@ -611,4 +611,4 @@ module_exit(cast6_exit); MODULE_DESCRIPTION("Cast6 Cipher Algorithm, AVX optimized"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("cast6"); +MODULE_ALIAS_CRYPTO("cast6"); diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c index 9d014a74ef96..1937fc1d8763 100644 --- a/arch/x86/crypto/crc32-pclmul_glue.c +++ b/arch/x86/crypto/crc32-pclmul_glue.c @@ -197,5 +197,5 @@ module_exit(crc32_pclmul_mod_fini); MODULE_AUTHOR("Alexander Boyko <alexander_boyko@xyratex.com>"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("crc32"); -MODULE_ALIAS("crc32-pclmul"); +MODULE_ALIAS_CRYPTO("crc32"); +MODULE_ALIAS_CRYPTO("crc32-pclmul"); diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c index 6812ad98355c..28640c3d6af7 100644 --- a/arch/x86/crypto/crc32c-intel_glue.c +++ b/arch/x86/crypto/crc32c-intel_glue.c @@ -280,5 +280,5 @@ MODULE_AUTHOR("Austin Zhang <austin.zhang@intel.com>, Kent Liu <kent.liu@intel.c MODULE_DESCRIPTION("CRC32c (Castagnoli) optimization using Intel Hardware."); MODULE_LICENSE("GPL"); -MODULE_ALIAS("crc32c"); -MODULE_ALIAS("crc32c-intel"); +MODULE_ALIAS_CRYPTO("crc32c"); +MODULE_ALIAS_CRYPTO("crc32c-intel"); diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c index 7845d7fd54c0..b6c67bf30fdf 100644 --- a/arch/x86/crypto/crct10dif-pclmul_glue.c +++ b/arch/x86/crypto/crct10dif-pclmul_glue.c @@ -147,5 +147,5 @@ MODULE_AUTHOR("Tim Chen <tim.c.chen@linux.intel.com>"); MODULE_DESCRIPTION("T10 DIF CRC calculation accelerated with PCLMULQDQ."); MODULE_LICENSE("GPL"); -MODULE_ALIAS("crct10dif"); -MODULE_ALIAS("crct10dif-pclmul"); +MODULE_ALIAS_CRYPTO("crct10dif"); +MODULE_ALIAS_CRYPTO("crct10dif-pclmul"); diff --git a/arch/x86/crypto/fpu.c b/arch/x86/crypto/fpu.c index 98d7a188f46b..f368ba261739 100644 --- a/arch/x86/crypto/fpu.c +++ b/arch/x86/crypto/fpu.c @@ -17,6 +17,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/slab.h> +#include <linux/crypto.h> #include <asm/i387.h> struct crypto_fpu_ctx { @@ -159,3 +160,5 @@ void __exit crypto_fpu_exit(void) { crypto_unregister_template(&crypto_fpu_tmpl); } + +MODULE_ALIAS_CRYPTO("fpu"); diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index d785cf2c529c..a8d6f69f92a3 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -341,4 +341,4 @@ module_exit(ghash_pclmulqdqni_mod_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("GHASH Message Digest Algorithm, " "acclerated by PCLMULQDQ-NI"); -MODULE_ALIAS("ghash"); +MODULE_ALIAS_CRYPTO("ghash"); diff --git a/arch/x86/crypto/salsa20_glue.c b/arch/x86/crypto/salsa20_glue.c index 5e8e67739bb5..399a29d067d6 100644 --- a/arch/x86/crypto/salsa20_glue.c +++ b/arch/x86/crypto/salsa20_glue.c @@ -119,5 +119,5 @@ module_exit(fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION ("Salsa20 stream cipher algorithm (optimized assembly version)"); -MODULE_ALIAS("salsa20"); -MODULE_ALIAS("salsa20-asm"); +MODULE_ALIAS_CRYPTO("salsa20"); +MODULE_ALIAS_CRYPTO("salsa20-asm"); diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c index 2fae489b1524..437e47a4d302 100644 --- a/arch/x86/crypto/serpent_avx2_glue.c +++ b/arch/x86/crypto/serpent_avx2_glue.c @@ -558,5 +558,5 @@ module_exit(fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Serpent Cipher Algorithm, AVX2 optimized"); -MODULE_ALIAS("serpent"); -MODULE_ALIAS("serpent-asm"); +MODULE_ALIAS_CRYPTO("serpent"); +MODULE_ALIAS_CRYPTO("serpent-asm"); diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c index ff4870870972..7e217398b4eb 100644 --- a/arch/x86/crypto/serpent_avx_glue.c +++ b/arch/x86/crypto/serpent_avx_glue.c @@ -617,4 +617,4 @@ module_exit(serpent_exit); MODULE_DESCRIPTION("Serpent Cipher Algorithm, AVX optimized"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("serpent"); +MODULE_ALIAS_CRYPTO("serpent"); diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c index 8c95f8637306..bf025adaea01 100644 --- a/arch/x86/crypto/serpent_sse2_glue.c +++ b/arch/x86/crypto/serpent_sse2_glue.c @@ -618,4 +618,4 @@ module_exit(serpent_sse2_exit); MODULE_DESCRIPTION("Serpent Cipher Algorithm, SSE2 optimized"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("serpent"); +MODULE_ALIAS_CRYPTO("serpent"); diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index 4a11a9d72451..29e1060e9001 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -237,4 +237,4 @@ module_exit(sha1_ssse3_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, Supplemental SSE3 accelerated"); -MODULE_ALIAS("sha1"); +MODULE_ALIAS_CRYPTO("sha1"); diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c index f248546da1ca..4dc100d82902 100644 --- a/arch/x86/crypto/sha256_ssse3_glue.c +++ b/arch/x86/crypto/sha256_ssse3_glue.c @@ -318,5 +318,5 @@ module_exit(sha256_ssse3_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm, Supplemental SSE3 accelerated"); -MODULE_ALIAS("sha256"); -MODULE_ALIAS("sha224"); +MODULE_ALIAS_CRYPTO("sha256"); +MODULE_ALIAS_CRYPTO("sha224"); diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c index 8626b03e83b7..26a5898a6f26 100644 --- a/arch/x86/crypto/sha512_ssse3_glue.c +++ b/arch/x86/crypto/sha512_ssse3_glue.c @@ -326,5 +326,5 @@ module_exit(sha512_ssse3_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, Supplemental SSE3 accelerated"); -MODULE_ALIAS("sha512"); -MODULE_ALIAS("sha384"); +MODULE_ALIAS_CRYPTO("sha512"); +MODULE_ALIAS_CRYPTO("sha384"); diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c index 4e3c665be129..1ac531ea9bcc 100644 --- a/arch/x86/crypto/twofish_avx_glue.c +++ b/arch/x86/crypto/twofish_avx_glue.c @@ -579,4 +579,4 @@ module_exit(twofish_exit); MODULE_DESCRIPTION("Twofish Cipher Algorithm, AVX optimized"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("twofish"); +MODULE_ALIAS_CRYPTO("twofish"); diff --git a/arch/x86/crypto/twofish_glue.c b/arch/x86/crypto/twofish_glue.c index 0a5202303501..77e06c2da83d 100644 --- a/arch/x86/crypto/twofish_glue.c +++ b/arch/x86/crypto/twofish_glue.c @@ -96,5 +96,5 @@ module_exit(fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION ("Twofish Cipher Algorithm, asm optimized"); -MODULE_ALIAS("twofish"); -MODULE_ALIAS("twofish-asm"); +MODULE_ALIAS_CRYPTO("twofish"); +MODULE_ALIAS_CRYPTO("twofish-asm"); diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c index 13e63b3e1dfb..56d8a08ee479 100644 --- a/arch/x86/crypto/twofish_glue_3way.c +++ b/arch/x86/crypto/twofish_glue_3way.c @@ -495,5 +495,5 @@ module_exit(fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Twofish Cipher Algorithm, 3-way parallel asm optimized"); -MODULE_ALIAS("twofish"); -MODULE_ALIAS("twofish-asm"); +MODULE_ALIAS_CRYPTO("twofish"); +MODULE_ALIAS_CRYPTO("twofish-asm"); diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 4299eb05023c..92a2e9333620 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -151,6 +151,16 @@ ENTRY(ia32_sysenter_target) 1: movl (%rbp),%ebp _ASM_EXTABLE(1b,ia32_badarg) ASM_CLAC + + /* + * Sysenter doesn't filter flags, so we need to clear NT + * ourselves. To save a few cycles, we can check whether + * NT was set instead of doing an unconditional popfq. + */ + testl $X86_EFLAGS_NT,EFLAGS-ARGOFFSET(%rsp) + jnz sysenter_fix_flags +sysenter_flags_fixed: + orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET) testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) CFI_REMEMBER_STATE @@ -184,6 +194,8 @@ sysexit_from_sys_call: TRACE_IRQS_ON ENABLE_INTERRUPTS_SYSEXIT32 + CFI_RESTORE_STATE + #ifdef CONFIG_AUDITSYSCALL .macro auditsys_entry_common movl %esi,%r9d /* 6th arg: 4th syscall arg */ @@ -226,7 +238,6 @@ sysexit_from_sys_call: .endm sysenter_auditsys: - CFI_RESTORE_STATE auditsys_entry_common movl %ebp,%r9d /* reload 6th syscall arg */ jmp sysenter_dispatch @@ -235,6 +246,11 @@ sysexit_audit: auditsys_exit sysexit_from_sys_call #endif +sysenter_fix_flags: + pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED) + popfq_cfi + jmp sysenter_flags_fixed + sysenter_tracesys: #ifdef CONFIG_AUDITSYSCALL testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 5f1296872aed..1717156f4dd1 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -203,6 +203,7 @@ #define X86_FEATURE_DECODEASSISTS (8*32+12) /* AMD Decode Assists support */ #define X86_FEATURE_PAUSEFILTER (8*32+13) /* AMD filtered pause intercept */ #define X86_FEATURE_PFTHRESHOLD (8*32+14) /* AMD pause filter threshold */ +#define X86_FEATURE_VMMCALL (8*32+15) /* Prefer vmmcall to vmcall */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 50d033a8947d..a94b82e8f156 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -251,7 +251,8 @@ static inline void native_load_tls(struct thread_struct *t, unsigned int cpu) gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i]; } -#define _LDT_empty(info) \ +/* This intentionally ignores lm, since 32-bit apps don't have that field. */ +#define LDT_empty(info) \ ((info)->base_addr == 0 && \ (info)->limit == 0 && \ (info)->contents == 0 && \ @@ -261,11 +262,18 @@ static inline void native_load_tls(struct thread_struct *t, unsigned int cpu) (info)->seg_not_present == 1 && \ (info)->useable == 0) -#ifdef CONFIG_X86_64 -#define LDT_empty(info) (_LDT_empty(info) && ((info)->lm == 0)) -#else -#define LDT_empty(info) (_LDT_empty(info)) -#endif +/* Lots of programs expect an all-zero user_desc to mean "no segment at all". */ +static inline bool LDT_zero(const struct user_desc *info) +{ + return (info->base_addr == 0 && + info->limit == 0 && + info->contents == 0 && + info->read_exec_only == 0 && + info->seg_32bit == 0 && + info->limit_in_pages == 0 && + info->seg_not_present == 0 && + info->useable == 0); +} static inline void clear_LDT(void) { diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 9c999c1674fa..01f15b227d7e 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -155,8 +155,9 @@ do { \ #define elf_check_arch(x) \ ((x)->e_machine == EM_X86_64) -#define compat_elf_check_arch(x) \ - (elf_check_arch_ia32(x) || (x)->e_machine == EM_X86_64) +#define compat_elf_check_arch(x) \ + (elf_check_arch_ia32(x) || \ + (IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64)) #if __USER32_DS != __USER_DS # error "The following code assumes __USER32_DS == __USER_DS" diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 7252cd339175..6762a55b798a 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -123,14 +123,14 @@ enum fixed_addresses { __end_of_permanent_fixed_addresses, /* - * 256 temporary boot-time mappings, used by early_ioremap(), + * 512 temporary boot-time mappings, used by early_ioremap(), * before ioremap() is functional. * - * If necessary we round it up to the next 256 pages boundary so + * If necessary we round it up to the next 512 pages boundary so * that we can have a single pgd entry and a single pte table: */ #define NR_FIX_BTMAPS 64 -#define FIX_BTMAPS_SLOTS 4 +#define FIX_BTMAPS_SLOTS 8 #define TOTAL_FIX_BTMAPS (NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS) FIX_BTMAP_END = (__end_of_permanent_fixed_addresses ^ diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h index cea1c76d49bf..1ac1c009090d 100644 --- a/arch/x86/include/asm/fpu-internal.h +++ b/arch/x86/include/asm/fpu-internal.h @@ -368,7 +368,7 @@ static inline void drop_fpu(struct task_struct *tsk) preempt_disable(); tsk->thread.fpu_counter = 0; __drop_fpu(tsk); - clear_used_math(); + clear_stopped_child_used_math(tsk); preempt_enable(); } diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h index 8e71c7941767..57995f0596a6 100644 --- a/arch/x86/include/asm/iosf_mbi.h +++ b/arch/x86/include/asm/iosf_mbi.h @@ -50,6 +50,32 @@ #define BT_MBI_PCIE_READ 0x00 #define BT_MBI_PCIE_WRITE 0x01 +/* Quark available units */ +#define QRK_MBI_UNIT_HBA 0x00 +#define QRK_MBI_UNIT_HB 0x03 +#define QRK_MBI_UNIT_RMU 0x04 +#define QRK_MBI_UNIT_MM 0x05 +#define QRK_MBI_UNIT_MMESRAM 0x05 +#define QRK_MBI_UNIT_SOC 0x31 + +/* Quark read/write opcodes */ +#define QRK_MBI_HBA_READ 0x10 +#define QRK_MBI_HBA_WRITE 0x11 +#define QRK_MBI_HB_READ 0x10 +#define QRK_MBI_HB_WRITE 0x11 +#define QRK_MBI_RMU_READ 0x10 +#define QRK_MBI_RMU_WRITE 0x11 +#define QRK_MBI_MM_READ 0x10 +#define QRK_MBI_MM_WRITE 0x11 +#define QRK_MBI_MMESRAM_READ 0x12 +#define QRK_MBI_MMESRAM_WRITE 0x13 +#define QRK_MBI_SOC_READ 0x06 +#define QRK_MBI_SOC_WRITE 0x07 + +#if IS_ENABLED(CONFIG_IOSF_MBI) + +bool iosf_mbi_available(void); + /** * iosf_mbi_read() - MailBox Interface read command * @port: port indicating subunit being accessed @@ -87,4 +113,33 @@ int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr); */ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask); +#else /* CONFIG_IOSF_MBI is not enabled */ +static inline +bool iosf_mbi_available(void) +{ + return false; +} + +static inline +int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr) +{ + WARN(1, "IOSF_MBI driver not available"); + return -EPERM; +} + +static inline +int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr) +{ + WARN(1, "IOSF_MBI driver not available"); + return -EPERM; +} + +static inline +int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask) +{ + WARN(1, "IOSF_MBI driver not available"); + return -EPERM; +} +#endif /* CONFIG_IOSF_MBI */ + #endif /* IOSF_MBI_SYMS_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f86dea1ccb5c..829e3088b5a0 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -476,6 +476,7 @@ struct kvm_vcpu_arch { u64 mmio_gva; unsigned access; gfn_t mmio_gfn; + u64 mmio_gen; struct kvm_pmu pmu; @@ -979,6 +980,20 @@ static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code) kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); } +static inline u64 get_canonical(u64 la) +{ + return ((int64_t)la << 16) >> 16; +} + +static inline bool is_noncanonical_address(u64 la) +{ +#ifdef CONFIG_X86_64 + return get_canonical(la) != la; +#else + return false; +#endif +} + #define TSS_IOPB_BASE_OFFSET 0x66 #define TSS_BASE_SIZE 0x68 #define TSS_IOPB_SIZE (65536 / 8) @@ -1037,7 +1052,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu); void kvm_define_shared_msr(unsigned index, u32 msr); -void kvm_set_shared_msr(unsigned index, u64 val, u64 mask); +int kvm_set_shared_msr(unsigned index, u64 val, u64 mask); bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip); diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index c7678e43465b..e62cf897f781 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -2,6 +2,7 @@ #define _ASM_X86_KVM_PARA_H #include <asm/processor.h> +#include <asm/alternative.h> #include <uapi/asm/kvm_para.h> extern void kvmclock_init(void); @@ -16,10 +17,15 @@ static inline bool kvm_check_and_clear_guest_paused(void) } #endif /* CONFIG_KVM_GUEST */ -/* This instruction is vmcall. On non-VT architectures, it will generate a - * trap that we will then rewrite to the appropriate instruction. +#ifdef CONFIG_DEBUG_RODATA +#define KVM_HYPERCALL \ + ALTERNATIVE(".byte 0x0f,0x01,0xc1", ".byte 0x0f,0x01,0xd9", X86_FEATURE_VMMCALL) +#else +/* On AMD processors, vmcall will generate a trap that we will + * then rewrite to the appropriate instruction. */ #define KVM_HYPERCALL ".byte 0x0f,0x01,0xc1" +#endif /* For KVM hypercalls, a three-byte sequence of either the vmcall or the vmmcall * instruction. The hypervisor may replace it with something else but only the diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h index f48b17df4224..3a52ee0e726d 100644 --- a/arch/x86/include/asm/page_32_types.h +++ b/arch/x86/include/asm/page_32_types.h @@ -20,7 +20,6 @@ #define THREAD_SIZE_ORDER 1 #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) -#define STACKFAULT_STACK 0 #define DOUBLEFAULT_STACK 1 #define NMI_STACK 0 #define DEBUG_STACK 0 diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 8de6d9cf3b95..d54d1eebeffe 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -14,12 +14,11 @@ #define IRQ_STACK_ORDER 2 #define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER) -#define STACKFAULT_STACK 1 -#define DOUBLEFAULT_STACK 2 -#define NMI_STACK 3 -#define DEBUG_STACK 4 -#define MCE_STACK 5 -#define N_EXCEPTION_STACKS 5 /* hw limit: 7 */ +#define DOUBLEFAULT_STACK 1 +#define NMI_STACK 2 +#define DEBUG_STACK 3 +#define MCE_STACK 4 +#define N_EXCEPTION_STACKS 4 /* hw limit: 7 */ #define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT) #define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1)) diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index e22c1dbf7feb..d869931bde62 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -19,6 +19,7 @@ extern pud_t level3_ident_pgt[512]; extern pmd_t level2_kernel_pgt[512]; extern pmd_t level2_fixmap_pgt[512]; extern pmd_t level2_ident_pgt[512]; +extern pte_t level1_fixmap_pgt[512]; extern pgd_t init_level4_pgt[]; #define swapper_pg_dir init_level4_pgt diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index e1940c06ed02..e870ea9232c3 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -144,7 +144,7 @@ struct thread_info { /* Only used for 64 bit */ #define _TIF_DO_NOTIFY_MASK \ (_TIF_SIGPENDING | _TIF_MCE_NOTIFY | _TIF_NOTIFY_RESUME | \ - _TIF_USER_RETURN_NOTIFY) + _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE) /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW \ diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 58d66fe06b61..b409b17efb48 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -39,6 +39,7 @@ asmlinkage void simd_coprocessor_error(void); #ifdef CONFIG_TRACING asmlinkage void trace_page_fault(void); +#define trace_stack_segment stack_segment #define trace_divide_error divide_error #define trace_bounds bounds #define trace_invalid_op invalid_op diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h index 2a46ca720afc..2874be9aef0a 100644 --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -34,7 +34,7 @@ static inline unsigned int __getcpu(void) native_read_tscp(&p); } else { /* Load per CPU data from GDT */ - asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG)); + asm volatile ("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG)); } return p; diff --git a/arch/x86/include/uapi/asm/ldt.h b/arch/x86/include/uapi/asm/ldt.h index 46727eb37bfe..6e1aaf73852a 100644 --- a/arch/x86/include/uapi/asm/ldt.h +++ b/arch/x86/include/uapi/asm/ldt.h @@ -28,6 +28,13 @@ struct user_desc { unsigned int seg_not_present:1; unsigned int useable:1; #ifdef __x86_64__ + /* + * Because this bit is not present in 32-bit user code, user + * programs can pass uninitialized values here. Therefore, in + * any context in which a user_desc comes from a 32-bit program, + * the kernel must act as though lm == 0, regardless of the + * actual value. + */ unsigned int lm:1; #endif }; diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index 0e79420376eb..990a2fe1588d 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -67,6 +67,7 @@ #define EXIT_REASON_EPT_MISCONFIG 49 #define EXIT_REASON_INVEPT 50 #define EXIT_REASON_PREEMPTION_TIMER 52 +#define EXIT_REASON_INVVPID 53 #define EXIT_REASON_WBINVD 54 #define EXIT_REASON_XSETBV 55 #define EXIT_REASON_APIC_WRITE 56 @@ -114,6 +115,7 @@ { EXIT_REASON_EOI_INDUCED, "EOI_INDUCED" }, \ { EXIT_REASON_INVALID_STATE, "INVALID_STATE" }, \ { EXIT_REASON_INVD, "INVD" }, \ + { EXIT_REASON_INVVPID, "INVVPID" }, \ { EXIT_REASON_INVPCID, "INVPCID" } #endif /* _UAPIVMX_H */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 7f26c9a70a9e..523f147b2470 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1290,7 +1290,7 @@ void setup_local_APIC(void) unsigned int value, queued; int i, j, acked = 0; unsigned long long tsc = 0, ntsc; - long long max_loops = cpu_khz; + long long max_loops = cpu_khz ? cpu_khz : 1000000; if (cpu_has_tsc) rdtscll(tsc); @@ -1387,7 +1387,7 @@ void setup_local_APIC(void) break; } if (queued) { - if (cpu_has_tsc) { + if (cpu_has_tsc && cpu_khz) { rdtscll(ntsc); max_loops = (cpu_khz << 10) - (ntsc - tsc); } else diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index c67ffa686064..c005fdd52529 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -508,6 +508,13 @@ static void early_init_amd(struct cpuinfo_x86 *c) } #endif + /* + * This is only needed to tell the kernel whether to use VMCALL + * and VMMCALL. VMMCALL is never executed except under virt, so + * we can set it unconditionally. + */ + set_cpu_cap(c, X86_FEATURE_VMMCALL); + /* F16h erratum 793, CVE-2013-6885 */ if (c->x86 == 0x16 && c->x86_model <= 0xf) { u64 val; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 8e28bf2fc3ef..e6bddd5b9da3 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -144,6 +144,8 @@ EXPORT_PER_CPU_SYMBOL_GPL(gdt_page); static int __init x86_xsave_setup(char *s) { + if (strlen(s)) + return 0; setup_clear_cpu_cap(X86_FEATURE_XSAVE); setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); setup_clear_cpu_cap(X86_FEATURE_AVX); @@ -1141,7 +1143,7 @@ void syscall_init(void) /* Flags to clear on syscall */ wrmsrl(MSR_SYSCALL_MASK, X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF| - X86_EFLAGS_IOPL|X86_EFLAGS_AC); + X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT); } /* diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 5cd9bfabd645..66746a880dec 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -153,6 +153,21 @@ static void early_init_intel(struct cpuinfo_x86 *c) setup_clear_cpu_cap(X86_FEATURE_ERMS); } } + + /* + * Intel Quark Core DevMan_001.pdf section 6.4.11 + * "The operating system also is required to invalidate (i.e., flush) + * the TLB when any changes are made to any of the page table entries. + * The operating system must reload CR3 to cause the TLB to be flushed" + * + * As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should + * be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE + * to be modified + */ + if (c->x86 == 5 && c->x86_model == 9) { + pr_info("Disabling PGE capability bit\n"); + setup_clear_cpu_cap(X86_FEATURE_PGE); + } } #ifdef CONFIG_X86_32 @@ -368,6 +383,13 @@ static void init_intel(struct cpuinfo_x86 *c) detect_extended_topology(c); l2 = init_intel_cacheinfo(c); + + /* Detect legacy cache sizes if init_intel_cacheinfo did not */ + if (l2 == 0) { + cpu_detect_cache_sizes(c); + l2 = c->x86_cache_size; + } + if (c->cpuid_level > 9) { unsigned eax = cpuid_eax(10); /* Check for version and the number of counters */ @@ -482,6 +504,13 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size) */ if ((c->x86 == 6) && (c->x86_model == 11) && (size == 0)) size = 256; + + /* + * Intel Quark SoC X1000 contains a 4-way set associative + * 16K cache with a 16 byte cache line and 256 lines per tag + */ + if ((c->x86 == 5) && (c->x86_model == 9)) + size = 16; return size; } #endif @@ -709,7 +738,8 @@ static const struct cpu_dev intel_cpu_dev = { [3] = "OverDrive PODP5V83", [4] = "Pentium MMX", [7] = "Mobile Pentium 75 - 200", - [8] = "Mobile Pentium MMX" + [8] = "Mobile Pentium MMX", + [9] = "Quark SoC X1000", } }, { .family = 6, .model_names = diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c index 617a9e284245..b63773ba1646 100644 --- a/arch/x86/kernel/cpu/microcode/amd_early.c +++ b/arch/x86/kernel/cpu/microcode/amd_early.c @@ -108,12 +108,13 @@ static size_t compute_container_size(u8 *data, u32 total_size) * load_microcode_amd() to save equivalent cpu table and microcode patches in * kernel heap memory. */ -static void apply_ucode_in_initrd(void *ucode, size_t size) +static void apply_ucode_in_initrd(void *ucode, size_t size, bool save_patch) { struct equiv_cpu_entry *eq; size_t *cont_sz; u32 *header; u8 *data, **cont; + u8 (*patch)[PATCH_MAX_SIZE]; u16 eq_id = 0; int offset, left; u32 rev, eax, ebx, ecx, edx; @@ -123,10 +124,12 @@ static void apply_ucode_in_initrd(void *ucode, size_t size) new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); cont_sz = (size_t *)__pa_nodebug(&container_size); cont = (u8 **)__pa_nodebug(&container); + patch = (u8 (*)[PATCH_MAX_SIZE])__pa_nodebug(&amd_ucode_patch); #else new_rev = &ucode_new_rev; cont_sz = &container_size; cont = &container; + patch = &amd_ucode_patch; #endif data = ucode; @@ -213,9 +216,9 @@ static void apply_ucode_in_initrd(void *ucode, size_t size) rev = mc->hdr.patch_id; *new_rev = rev; - /* save ucode patch */ - memcpy(amd_ucode_patch, mc, - min_t(u32, header[1], PATCH_MAX_SIZE)); + if (save_patch) + memcpy(patch, mc, + min_t(u32, header[1], PATCH_MAX_SIZE)); } } @@ -246,7 +249,7 @@ void __init load_ucode_amd_bsp(void) *data = cp.data; *size = cp.size; - apply_ucode_in_initrd(cp.data, cp.size); + apply_ucode_in_initrd(cp.data, cp.size, true); } #ifdef CONFIG_X86_32 @@ -263,7 +266,7 @@ void load_ucode_amd_ap(void) size_t *usize; void **ucode; - mc = (struct microcode_amd *)__pa(amd_ucode_patch); + mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch); if (mc->hdr.patch_id && mc->hdr.processor_rev_id) { __apply_microcode_amd(mc); return; @@ -275,7 +278,7 @@ void load_ucode_amd_ap(void) if (!*ucode || !*usize) return; - apply_ucode_in_initrd(*ucode, *usize); + apply_ucode_in_initrd(*ucode, *usize, false); } static void __init collect_cpu_sig_on_bsp(void *arg) @@ -339,7 +342,7 @@ void load_ucode_amd_ap(void) * AP has a different equivalence ID than BSP, looks like * mixed-steppings silicon so go through the ucode blob anew. */ - apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size); + apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size, false); } } #endif @@ -347,7 +350,9 @@ void load_ucode_amd_ap(void) int __init save_microcode_in_initrd_amd(void) { unsigned long cont; + int retval = 0; enum ucode_state ret; + u8 *cont_va; u32 eax; if (!container) @@ -355,13 +360,15 @@ int __init save_microcode_in_initrd_amd(void) #ifdef CONFIG_X86_32 get_bsp_sig(); - cont = (unsigned long)container; + cont = (unsigned long)container; + cont_va = __va(container); #else /* * We need the physical address of the container for both bitness since * boot_params.hdr.ramdisk_image is a physical address. */ - cont = __pa(container); + cont = __pa(container); + cont_va = container; #endif /* @@ -372,6 +379,8 @@ int __init save_microcode_in_initrd_amd(void) if (relocated_ramdisk) container = (u8 *)(__va(relocated_ramdisk) + (cont - boot_params.hdr.ramdisk_image)); + else + container = cont_va; if (ucode_new_rev) pr_info("microcode: updated early to new patch_level=0x%08x\n", @@ -382,7 +391,7 @@ int __init save_microcode_in_initrd_amd(void) ret = load_microcode_amd(eax, container, container_size); if (ret != UCODE_OK) - return -EINVAL; + retval = -EINVAL; /* * This will be freed any msec now, stash patches for the current @@ -391,5 +400,5 @@ int __init save_microcode_in_initrd_amd(void) container = NULL; container_size = 0; - return 0; + return retval; } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 832d05a914ba..317c81172c18 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -67,6 +67,7 @@ static struct clocksource hyperv_cs = { .rating = 400, /* use this when running on Hyperv*/ .read = read_hv_clock, .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; static void __init ms_hyperv_init_platform(void) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 79f9f848bee4..fb345c43815f 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -118,6 +118,9 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event) continue; if (event->attr.config1 & ~er->valid_mask) return -EINVAL; + /* Check if the extra msrs can be safely accessed*/ + if (!er->extra_msr_access) + return -ENXIO; reg->idx = er->idx; reg->config = event->attr.config1; diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 4972c244d0bc..7876c346ed1a 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -293,14 +293,16 @@ struct extra_reg { u64 config_mask; u64 valid_mask; int idx; /* per_xxx->regs[] reg index */ + bool extra_msr_access; }; #define EVENT_EXTRA_REG(e, ms, m, vm, i) { \ - .event = (e), \ - .msr = (ms), \ - .config_mask = (m), \ - .valid_mask = (vm), \ - .idx = EXTRA_REG_##i, \ + .event = (e), \ + .msr = (ms), \ + .config_mask = (m), \ + .valid_mask = (vm), \ + .idx = EXTRA_REG_##i, \ + .extra_msr_access = true, \ } #define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx) \ diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 1340ebfcb467..d4c0a0e46040 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -2183,6 +2183,41 @@ static void intel_snb_check_microcode(void) } } +/* + * Under certain circumstances, access certain MSR may cause #GP. + * The function tests if the input MSR can be safely accessed. + */ +static bool check_msr(unsigned long msr, u64 mask) +{ + u64 val_old, val_new, val_tmp; + + /* + * Read the current value, change it and read it back to see if it + * matches, this is needed to detect certain hardware emulators + * (qemu/kvm) that don't trap on the MSR access and always return 0s. + */ + if (rdmsrl_safe(msr, &val_old)) + return false; + + /* + * Only change the bits which can be updated by wrmsrl. + */ + val_tmp = val_old ^ mask; + if (wrmsrl_safe(msr, val_tmp) || + rdmsrl_safe(msr, &val_new)) + return false; + + if (val_new != val_tmp) + return false; + + /* Here it's sure that the MSR can be safely accessed. + * Restore the old value and return. + */ + wrmsrl(msr, val_old); + + return true; +} + static __init void intel_sandybridge_quirk(void) { x86_pmu.check_microcode = intel_snb_check_microcode; @@ -2272,7 +2307,8 @@ __init int intel_pmu_init(void) union cpuid10_ebx ebx; struct event_constraint *c; unsigned int unused; - int version; + struct extra_reg *er; + int version, i; if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { switch (boot_cpu_data.x86) { @@ -2475,6 +2511,9 @@ __init int intel_pmu_init(void) case 62: /* IvyBridge EP */ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + /* dTLB-load-misses on IVB is different than SNB */ + hw_cache_event_ids[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = 0x8108; /* DTLB_LOAD_MISSES.DEMAND_LD_MISS_CAUSES_A_WALK */ + memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); @@ -2575,6 +2614,34 @@ __init int intel_pmu_init(void) } } + /* + * Access LBR MSR may cause #GP under certain circumstances. + * E.g. KVM doesn't support LBR MSR + * Check all LBT MSR here. + * Disable LBR access if any LBR MSRs can not be accessed. + */ + if (x86_pmu.lbr_nr && !check_msr(x86_pmu.lbr_tos, 0x3UL)) + x86_pmu.lbr_nr = 0; + for (i = 0; i < x86_pmu.lbr_nr; i++) { + if (!(check_msr(x86_pmu.lbr_from + i, 0xffffUL) && + check_msr(x86_pmu.lbr_to + i, 0xffffUL))) + x86_pmu.lbr_nr = 0; + } + + /* + * Access extra MSR may cause #GP under certain circumstances. + * E.g. KVM doesn't support offcore event + * Check all extra_regs here. + */ + if (x86_pmu.extra_regs) { + for (er = x86_pmu.extra_regs; er->msr; er++) { + er->extra_msr_access = check_msr(er->msr, 0x1ffUL); + /* Disable LBR select mapping */ + if ((er->idx == EXTRA_REG_LBR) && !er->extra_msr_access) + x86_pmu.lbr_sel_map = NULL; + } + } + /* Support full width counters using alternative MSR range */ if (x86_pmu.intel_cap.full_width_write) { x86_pmu.max_period = x86_pmu.cntval_mask; diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c index 5ad35ad94d0f..95700e52061d 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -511,6 +511,7 @@ static int rapl_cpu_prepare(int cpu) struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu); int phys_id = topology_physical_package_id(cpu); u64 ms; + u64 msr_rapl_power_unit_bits; if (pmu) return 0; @@ -518,6 +519,9 @@ static int rapl_cpu_prepare(int cpu) if (phys_id < 0) return -1; + if (!rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits)) + return -1; + pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); if (!pmu) return -1; @@ -531,8 +535,7 @@ static int rapl_cpu_prepare(int cpu) * * we cache in local PMU instance */ - rdmsrl(MSR_RAPL_POWER_UNIT, pmu->hw_unit); - pmu->hw_unit = (pmu->hw_unit >> 8) & 0x1FULL; + pmu->hw_unit = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; pmu->pmu = &rapl_pmu_class; /* @@ -649,7 +652,9 @@ static int __init rapl_pmu_init(void) get_online_cpus(); for_each_online_cpu(cpu) { - rapl_cpu_prepare(cpu); + ret = rapl_cpu_prepare(cpu); + if (ret) + goto out; rapl_cpu_init(cpu); } @@ -672,6 +677,7 @@ static int __init rapl_pmu_init(void) hweight32(rapl_cntr_mask), ktime_to_ms(pmu->timer_interval)); +out: put_online_cpus(); return 0; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 047f540cf3f7..2f9858894d5a 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -2886,6 +2886,17 @@ static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id()); } +/* + * Using uncore_pmu_event_init pmu event_init callback + * as a detection point for uncore events. + */ +static int uncore_pmu_event_init(struct perf_event *event); + +static bool is_uncore_event(struct perf_event *event) +{ + return event->pmu->event_init == uncore_pmu_event_init; +} + static int uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp) { @@ -2900,13 +2911,18 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, b return -EINVAL; n = box->n_events; - box->event_list[n] = leader; - n++; + + if (is_uncore_event(leader)) { + box->event_list[n] = leader; + n++; + } + if (!dogrp) return n; list_for_each_entry(event, &leader->sibling_list, group_entry) { - if (event->state <= PERF_EVENT_STATE_OFF) + if (!is_uncore_event(event) || + event->state <= PERF_EVENT_STATE_OFF) continue; if (n >= max_count) diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index addb207dab92..66e274a3d968 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -24,7 +24,6 @@ static char x86_stack_ids[][8] = { [ DEBUG_STACK-1 ] = "#DB", [ NMI_STACK-1 ] = "NMI", [ DOUBLEFAULT_STACK-1 ] = "#DF", - [ STACKFAULT_STACK-1 ] = "#SS", [ MCE_STACK-1 ] = "#MC", #if DEBUG_STKSZ > EXCEPTION_STKSZ [ N_EXCEPTION_STACKS ... diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 03cd2a8f6009..06469ee0f26e 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -542,11 +542,14 @@ ENTRY(ret_from_fork) testl $3, CS-ARGOFFSET(%rsp) # from kernel_thread? jz 1f - testl $_TIF_IA32, TI_flags(%rcx) # 32-bit compat task needs IRET - jnz int_ret_from_sys_call - - RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET - jmp ret_from_sys_call # go to the SYSRET fastpath + /* + * By the time we get here, we have no idea whether our pt_regs, + * ti flags, and ti status came from the 64-bit SYSCALL fast path, + * the slow path, or one of the ia32entry paths. + * Use int_ret_from_sys_call to return, since it can safely handle + * all of the above. + */ + jmp int_ret_from_sys_call 1: subq $REST_SKIP, %rsp # leave space for volatiles @@ -1053,9 +1056,15 @@ ENTRY(native_iret) jnz native_irq_return_ldt #endif +.global native_irq_return_iret native_irq_return_iret: + /* + * This may fault. Non-paranoid faults on return to userspace are + * handled by fixup_bad_iret. These include #SS, #GP, and #NP. + * Double-faults due to espfix64 are handled in do_double_fault. + * Other faults here are fatal. + */ iretq - _ASM_EXTABLE(native_irq_return_iret, bad_iret) #ifdef CONFIG_X86_ESPFIX64 native_irq_return_ldt: @@ -1083,25 +1092,6 @@ native_irq_return_ldt: jmp native_irq_return_iret #endif - .section .fixup,"ax" -bad_iret: - /* - * The iret traps when the %cs or %ss being restored is bogus. - * We've lost the original trap vector and error code. - * #GPF is the most likely one to get for an invalid selector. - * So pretend we completed the iret and took the #GPF in user mode. - * - * We are now running with the kernel GS after exception recovery. - * But error_entry expects us to have user GS to match the user %cs, - * so swap back. - */ - pushq $0 - - SWAPGS - jmp general_protection - - .previous - /* edi: workmask, edx: work */ retint_careful: CFI_RESTORE_STATE @@ -1147,37 +1137,6 @@ ENTRY(retint_kernel) CFI_ENDPROC END(common_interrupt) - /* - * If IRET takes a fault on the espfix stack, then we - * end up promoting it to a doublefault. In that case, - * modify the stack to make it look like we just entered - * the #GP handler from user space, similar to bad_iret. - */ -#ifdef CONFIG_X86_ESPFIX64 - ALIGN -__do_double_fault: - XCPT_FRAME 1 RDI+8 - movq RSP(%rdi),%rax /* Trap on the espfix stack? */ - sarq $PGDIR_SHIFT,%rax - cmpl $ESPFIX_PGD_ENTRY,%eax - jne do_double_fault /* No, just deliver the fault */ - cmpl $__KERNEL_CS,CS(%rdi) - jne do_double_fault - movq RIP(%rdi),%rax - cmpq $native_irq_return_iret,%rax - jne do_double_fault /* This shouldn't happen... */ - movq PER_CPU_VAR(kernel_stack),%rax - subq $(6*8-KERNEL_STACK_OFFSET),%rax /* Reset to original stack */ - movq %rax,RSP(%rdi) - movq $0,(%rax) /* Missing (lost) #GP error code */ - movq $general_protection,RIP(%rdi) - retq - CFI_ENDPROC -END(__do_double_fault) -#else -# define __do_double_fault do_double_fault -#endif - /* * End of kprobes section */ @@ -1379,7 +1338,7 @@ zeroentry overflow do_overflow zeroentry bounds do_bounds zeroentry invalid_op do_invalid_op zeroentry device_not_available do_device_not_available -paranoiderrorentry double_fault __do_double_fault +paranoiderrorentry double_fault do_double_fault zeroentry coprocessor_segment_overrun do_coprocessor_segment_overrun errorentry invalid_TSS do_invalid_TSS errorentry segment_not_present do_segment_not_present @@ -1549,7 +1508,7 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ paranoidzeroentry_ist debug do_debug DEBUG_STACK paranoidzeroentry_ist int3 do_int3 DEBUG_STACK -paranoiderrorentry stack_segment do_stack_segment +errorentry stack_segment do_stack_segment #ifdef CONFIG_XEN zeroentry xen_debug do_debug zeroentry xen_int3 do_int3 @@ -1659,16 +1618,15 @@ error_sti: /* * There are two places in the kernel that can potentially fault with - * usergs. Handle them here. The exception handlers after iret run with - * kernel gs again, so don't set the user space flag. B stepping K8s - * sometimes report an truncated RIP for IRET exceptions returning to - * compat mode. Check for these here too. + * usergs. Handle them here. B stepping K8s sometimes report a + * truncated RIP for IRET exceptions returning to compat mode. Check + * for these here too. */ error_kernelspace: incl %ebx leaq native_irq_return_iret(%rip),%rcx cmpq %rcx,RIP+8(%rsp) - je error_swapgs + je error_bad_iret movl %ecx,%eax /* zero extend */ cmpq %rax,RIP+8(%rsp) je bstep_iret @@ -1679,7 +1637,15 @@ error_kernelspace: bstep_iret: /* Fix truncated RIP */ movq %rcx,RIP+8(%rsp) - jmp error_swapgs + /* fall through */ + +error_bad_iret: + SWAPGS + mov %rsp,%rdi + call fixup_bad_iret + mov %rax,%rsp + decl %ebx /* Return to usergs */ + jmp error_sti CFI_ENDPROC END(error_entry) diff --git a/arch/x86/kernel/iosf_mbi.c b/arch/x86/kernel/iosf_mbi.c index c3aae6672843..2e97b3cfa6c7 100644 --- a/arch/x86/kernel/iosf_mbi.c +++ b/arch/x86/kernel/iosf_mbi.c @@ -25,6 +25,10 @@ #include <asm/iosf_mbi.h> +#define PCI_DEVICE_ID_BAYTRAIL 0x0F00 +#define PCI_DEVICE_ID_BRASWELL 0x2280 +#define PCI_DEVICE_ID_QUARK_X1000 0x0958 + static DEFINE_SPINLOCK(iosf_mbi_lock); static inline u32 iosf_mbi_form_mcr(u8 op, u8 port, u8 offset) @@ -177,6 +181,13 @@ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask) } EXPORT_SYMBOL(iosf_mbi_modify); +bool iosf_mbi_available(void) +{ + /* Mbi isn't hot-pluggable. No remove routine is provided */ + return mbi_pdev; +} +EXPORT_SYMBOL(iosf_mbi_available); + static int iosf_mbi_probe(struct pci_dev *pdev, const struct pci_device_id *unused) { @@ -193,7 +204,9 @@ static int iosf_mbi_probe(struct pci_dev *pdev, } static DEFINE_PCI_DEVICE_TABLE(iosf_mbi_pci_ids) = { - { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x0F00) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BAYTRAIL) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BRASWELL) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_QUARK_X1000) }, { 0, }, }; MODULE_DEVICE_TABLE(pci, iosf_mbi_pci_ids); diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 79a3f9682871..a1f5b1866cbe 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -1017,6 +1017,15 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) regs->flags &= ~X86_EFLAGS_IF; trace_hardirqs_off(); regs->ip = (unsigned long)(jp->entry); + + /* + * jprobes use jprobe_return() which skips the normal return + * path of the function, and this messes up the accounting of the + * function graph tracer to get messed up. + * + * Pause function graph tracing while performing the jprobe function. + */ + pause_graph_tracing(); return 1; } @@ -1042,24 +1051,25 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); u8 *addr = (u8 *) (regs->ip - 1); struct jprobe *jp = container_of(p, struct jprobe, kp); + void *saved_sp = kcb->jprobe_saved_sp; if ((addr > (u8 *) jprobe_return) && (addr < (u8 *) jprobe_return_end)) { - if (stack_addr(regs) != kcb->jprobe_saved_sp) { + if (stack_addr(regs) != saved_sp) { struct pt_regs *saved_regs = &kcb->jprobe_saved_regs; printk(KERN_ERR "current sp %p does not match saved sp %p\n", - stack_addr(regs), kcb->jprobe_saved_sp); + stack_addr(regs), saved_sp); printk(KERN_ERR "Saved registers for jprobe %p\n", jp); show_regs(saved_regs); printk(KERN_ERR "Current registers\n"); show_regs(regs); BUG(); } + /* It's OK to start function graph tracing again */ + unpause_graph_tracing(); *regs = kcb->jprobe_saved_regs; - memcpy((kprobe_opcode_t *)(kcb->jprobe_saved_sp), - kcb->jprobes_stack, - MIN_STACK_SIZE(kcb->jprobe_saved_sp)); + memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp)); preempt_enable_no_resched(); return 1; } diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 713f1b3bad52..0b1e1d5dbc5b 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -280,7 +280,14 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) static void __init paravirt_ops_setup(void) { pv_info.name = "KVM"; - pv_info.paravirt_enabled = 1; + + /* + * KVM isn't paravirt in the sense of paravirt_enabled. A KVM + * guest kernel works like a bare metal kernel with additional + * features, and paravirt_enabled is about features that are + * missing. + */ + pv_info.paravirt_enabled = 0; if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY)) pv_cpu_ops.io_delay = kvm_io_delay; diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index e6041094ff26..c8e98cdc84c2 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -263,7 +263,6 @@ void __init kvmclock_init(void) #endif kvm_get_preset_lpj(); clocksource_register_hz(&kvm_clock, NSEC_PER_SEC); - pv_info.paravirt_enabled = 1; pv_info.name = "KVM"; if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 9c0280f93d05..e2d26ce9b854 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -286,24 +286,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) fpu = switch_fpu_prepare(prev_p, next_p, cpu); - /* - * Reload esp0, LDT and the page table pointer: - */ + /* Reload esp0 and ss1. */ load_sp0(tss, next); - /* - * Switch DS and ES. - * This won't pick up thread selector changes, but I guess that is ok. - */ - savesegment(es, prev->es); - if (unlikely(next->es | prev->es)) - loadsegment(es, next->es); - - savesegment(ds, prev->ds); - if (unlikely(next->ds | prev->ds)) - loadsegment(ds, next->ds); - - /* We must save %fs and %gs before load_TLS() because * %fs and %gs may be cleared by load_TLS(). * @@ -312,41 +297,101 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) savesegment(fs, fsindex); savesegment(gs, gsindex); + /* + * Load TLS before restoring any segments so that segment loads + * reference the correct GDT entries. + */ load_TLS(next, cpu); /* - * Leave lazy mode, flushing any hypercalls made here. - * This must be done before restoring TLS segments so - * the GDT and LDT are properly updated, and must be - * done before math_state_restore, so the TS bit is up - * to date. + * Leave lazy mode, flushing any hypercalls made here. This + * must be done after loading TLS entries in the GDT but before + * loading segments that might reference them, and and it must + * be done before math_state_restore, so the TS bit is up to + * date. */ arch_end_context_switch(next_p); + /* Switch DS and ES. + * + * Reading them only returns the selectors, but writing them (if + * nonzero) loads the full descriptor from the GDT or LDT. The + * LDT for next is loaded in switch_mm, and the GDT is loaded + * above. + * + * We therefore need to write new values to the segment + * registers on every context switch unless both the new and old + * values are zero. + * + * Note that we don't need to do anything for CS and SS, as + * those are saved and restored as part of pt_regs. + */ + savesegment(es, prev->es); + if (unlikely(next->es | prev->es)) + loadsegment(es, next->es); + + savesegment(ds, prev->ds); + if (unlikely(next->ds | prev->ds)) + loadsegment(ds, next->ds); + /* * Switch FS and GS. * - * Segment register != 0 always requires a reload. Also - * reload when it has changed. When prev process used 64bit - * base always reload to avoid an information leak. + * These are even more complicated than FS and GS: they have + * 64-bit bases are that controlled by arch_prctl. Those bases + * only differ from the values in the GDT or LDT if the selector + * is 0. + * + * Loading the segment register resets the hidden base part of + * the register to 0 or the value from the GDT / LDT. If the + * next base address zero, writing 0 to the segment register is + * much faster than using wrmsr to explicitly zero the base. + * + * The thread_struct.fs and thread_struct.gs values are 0 + * if the fs and gs bases respectively are not overridden + * from the values implied by fsindex and gsindex. They + * are nonzero, and store the nonzero base addresses, if + * the bases are overridden. + * + * (fs != 0 && fsindex != 0) || (gs != 0 && gsindex != 0) should + * be impossible. + * + * Therefore we need to reload the segment registers if either + * the old or new selector is nonzero, and we need to override + * the base address if next thread expects it to be overridden. + * + * This code is unnecessarily slow in the case where the old and + * new indexes are zero and the new base is nonzero -- it will + * unnecessarily write 0 to the selector before writing the new + * base address. + * + * Note: This all depends on arch_prctl being the only way that + * user code can override the segment base. Once wrfsbase and + * wrgsbase are enabled, most of this code will need to change. */ if (unlikely(fsindex | next->fsindex | prev->fs)) { loadsegment(fs, next->fsindex); + /* - * Check if the user used a selector != 0; if yes - * clear 64bit base, since overloaded base is always - * mapped to the Null selector + * If user code wrote a nonzero value to FS, then it also + * cleared the overridden base address. + * + * XXX: if user code wrote 0 to FS and cleared the base + * address itself, we won't notice and we'll incorrectly + * restore the prior base address next time we reschdule + * the process. */ if (fsindex) prev->fs = 0; } - /* when next process has a 64bit base use it */ if (next->fs) wrmsrl(MSR_FS_BASE, next->fs); prev->fsindex = fsindex; if (unlikely(gsindex | next->gsindex | prev->gs)) { load_gs_index(next->gsindex); + + /* This works (and fails) the same way as fsindex above. */ if (gsindex) prev->gs = 0; } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 7461f50d5bb1..0686fe313b3b 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1441,15 +1441,6 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, force_sig_info(SIGTRAP, &info, tsk); } - -#ifdef CONFIG_X86_32 -# define IS_IA32 1 -#elif defined CONFIG_IA32_EMULATION -# define IS_IA32 is_compat_task() -#else -# define IS_IA32 0 -#endif - /* * We must return the syscall number to actually look up in the table. * This can be -1L to skip running any syscall at all. @@ -1487,7 +1478,7 @@ long syscall_trace_enter(struct pt_regs *regs) if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->orig_ax); - if (IS_IA32) + if (is_ia32_task()) audit_syscall_entry(AUDIT_ARCH_I386, regs->orig_ax, regs->bx, regs->cx, diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index c752cb43e52f..a6aa91f77654 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -181,6 +181,16 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { }, }, + /* ASRock */ + { /* Handle problems with rebooting on ASRock Q1900DC-ITX */ + .callback = set_pci_reboot, + .ident = "ASRock Q1900DC-ITX", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASRock"), + DMI_MATCH(DMI_BOARD_NAME, "Q1900DC-ITX"), + }, + }, + /* ASUS */ { /* Handle problems with rebooting on ASUS P4S800 */ .callback = set_bios_reboot, diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index ce72964b2f46..fa511acff7e6 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -926,11 +926,11 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_EFI if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, "EL32", 4)) { - set_bit(EFI_BOOT, &x86_efi_facility); + set_bit(EFI_BOOT, &efi.flags); } else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, "EL64", 4)) { - set_bit(EFI_BOOT, &x86_efi_facility); - set_bit(EFI_64BIT, &x86_efi_facility); + set_bit(EFI_BOOT, &efi.flags); + set_bit(EFI_64BIT, &efi.flags); } if (efi_enabled(EFI_BOOT)) diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 9e5de6813e1f..b88fc86309bc 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -673,6 +673,11 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) * handler too. */ regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF); + /* + * Ensure the signal handler starts with the new fpu state. + */ + if (used_math()) + drop_init_fpu(current); } signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP)); } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 395be6d8bbde..682876533ed9 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1287,6 +1287,9 @@ static void remove_siblinginfo(int cpu) for_each_cpu(sibling, cpu_sibling_mask(cpu)) cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling)); + for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) + cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling)); + cpumask_clear(cpu_llc_shared_mask(cpu)); cpumask_clear(cpu_sibling_mask(cpu)); cpumask_clear(cpu_core_mask(cpu)); c->phys_proc_id = 0; diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index f7fec09e3e3a..7fc5e843f247 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -27,6 +27,58 @@ static int get_free_idx(void) return -ESRCH; } +static bool tls_desc_okay(const struct user_desc *info) +{ + /* + * For historical reasons (i.e. no one ever documented how any + * of the segmentation APIs work), user programs can and do + * assume that a struct user_desc that's all zeros except for + * entry_number means "no segment at all". This never actually + * worked. In fact, up to Linux 3.19, a struct user_desc like + * this would create a 16-bit read-write segment with base and + * limit both equal to zero. + * + * That was close enough to "no segment at all" until we + * hardened this function to disallow 16-bit TLS segments. Fix + * it up by interpreting these zeroed segments the way that they + * were almost certainly intended to be interpreted. + * + * The correct way to ask for "no segment at all" is to specify + * a user_desc that satisfies LDT_empty. To keep everything + * working, we accept both. + * + * Note that there's a similar kludge in modify_ldt -- look at + * the distinction between modes 1 and 0x11. + */ + if (LDT_empty(info) || LDT_zero(info)) + return true; + + /* + * espfix is required for 16-bit data segments, but espfix + * only works for LDT segments. + */ + if (!info->seg_32bit) + return false; + + /* Only allow data segments in the TLS array. */ + if (info->contents > 1) + return false; + + /* + * Non-present segments with DPL 3 present an interesting attack + * surface. The kernel should handle such segments correctly, + * but TLS is very difficult to protect in a sandbox, so prevent + * such segments from being created. + * + * If userspace needs to remove a TLS entry, it can still delete + * it outright. + */ + if (info->seg_not_present) + return false; + + return true; +} + static void set_tls_desc(struct task_struct *p, int idx, const struct user_desc *info, int n) { @@ -40,7 +92,7 @@ static void set_tls_desc(struct task_struct *p, int idx, cpu = get_cpu(); while (n-- > 0) { - if (LDT_empty(info)) + if (LDT_empty(info) || LDT_zero(info)) desc->a = desc->b = 0; else fill_ldt(desc, info); @@ -66,6 +118,9 @@ int do_set_thread_area(struct task_struct *p, int idx, if (copy_from_user(&info, u_info, sizeof(info))) return -EFAULT; + if (!tls_desc_okay(&info)) + return -EINVAL; + if (idx == -1) idx = info.entry_number; @@ -192,6 +247,7 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset, { struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES]; const struct user_desc *info; + int i; if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) || (pos % sizeof(struct user_desc)) != 0 || @@ -205,6 +261,10 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset, else info = infobuf; + for (i = 0; i < count / sizeof(struct user_desc); i++) + if (!tls_desc_okay(info + i)) + return -EINVAL; + set_tls_desc(target, GDT_ENTRY_TLS_MIN + (pos / sizeof(struct user_desc)), info, count / sizeof(struct user_desc)); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 57409f6b8c62..b1d9002af7db 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -218,32 +218,40 @@ DO_ERROR_INFO(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op, ILL DO_ERROR (X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun ) DO_ERROR (X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS ) DO_ERROR (X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present ) -#ifdef CONFIG_X86_32 DO_ERROR (X86_TRAP_SS, SIGBUS, "stack segment", stack_segment ) -#endif DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0 ) #ifdef CONFIG_X86_64 /* Runs on IST stack */ -dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code) -{ - enum ctx_state prev_state; - - prev_state = exception_enter(); - if (notify_die(DIE_TRAP, "stack segment", regs, error_code, - X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) { - preempt_conditional_sti(regs); - do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL); - preempt_conditional_cli(regs); - } - exception_exit(prev_state); -} - dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) { static const char str[] = "double fault"; struct task_struct *tsk = current; +#ifdef CONFIG_X86_ESPFIX64 + extern unsigned char native_irq_return_iret[]; + + /* + * If IRET takes a non-IST fault on the espfix64 stack, then we + * end up promoting it to a doublefault. In that case, modify + * the stack to make it look like we just entered the #GP + * handler from user space, similar to bad_iret. + */ + if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY && + regs->cs == __KERNEL_CS && + regs->ip == (unsigned long)native_irq_return_iret) + { + struct pt_regs *normal_regs = task_pt_regs(current); + + /* Fake a #GP(0) from userspace. */ + memmove(&normal_regs->ip, (void *)regs->sp, 5*8); + normal_regs->orig_ax = 0; /* Missing (lost) #GP error code */ + regs->ip = (unsigned long)general_protection; + regs->sp = (unsigned long)&normal_regs->orig_ax; + return; + } +#endif + exception_enter(); /* Return not checked because double check cannot be ignored */ notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); @@ -357,7 +365,7 @@ exit: * for scheduling or signal handling. The actual stack switch is done in * entry.S */ -asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) +asmlinkage notrace __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) { struct pt_regs *regs = eregs; /* Did already sync */ @@ -376,6 +384,35 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) *regs = *eregs; return regs; } + +struct bad_iret_stack { + void *error_entry_ret; + struct pt_regs regs; +}; + +asmlinkage __visible notrace __kprobes +struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) +{ + /* + * This is called from entry_64.S early in handling a fault + * caused by a bad iret to user mode. To handle the fault + * correctly, we want move our stack frame to task_pt_regs + * and we want to pretend that the exception came from the + * iret target. + */ + struct bad_iret_stack *new_stack = + container_of(task_pt_regs(current), + struct bad_iret_stack, regs); + + /* Copy the IRET target to the new stack. */ + memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8); + + /* Copy the remainder of the stack from the current stack. */ + memmove(new_stack, s, offsetof(struct bad_iret_stack, regs.ip)); + + BUG_ON(!user_mode_vm(&new_stack->regs)); + return new_stack; +} #endif /* @@ -748,7 +785,7 @@ void __init trap_init(void) set_intr_gate(X86_TRAP_OLD_MF, coprocessor_segment_overrun); set_intr_gate(X86_TRAP_TS, invalid_TSS); set_intr_gate(X86_TRAP_NP, segment_not_present); - set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK); + set_intr_gate(X86_TRAP_SS, stack_segment); set_intr_gate(X86_TRAP_GP, general_protection); set_intr_gate(X86_TRAP_SPURIOUS, spurious_interrupt_bug); set_intr_gate(X86_TRAP_MF, coprocessor_error); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index e0d1d7a8354e..b20bced0090f 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -618,7 +618,7 @@ static unsigned long quick_pit_calibrate(void) goto success; } } - pr_err("Fast TSC calibration failed\n"); + pr_info("Fast TSC calibration failed\n"); return 0; success: @@ -1173,14 +1173,17 @@ void __init tsc_init(void) x86_init.timers.tsc_pre_init(); - if (!cpu_has_tsc) + if (!cpu_has_tsc) { + setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; + } tsc_khz = x86_platform.calibrate_tsc(); cpu_khz = tsc_khz; if (!tsc_khz) { mark_tsc_unstable("could not calculate TSC khz"); + setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; } diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index a4b451c6addf..7a09aca4b33a 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -268,8 +268,6 @@ int save_xstate_sig(void __user *buf, void __user *buf_fx, int size) if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate)) return -1; - drop_init_fpu(tsk); /* trigger finit */ - return 0; } @@ -377,7 +375,7 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) * thread's fpu state, reconstruct fxstate from the fsave * header. Sanitize the copied state etc. */ - struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave; + struct fpu *fpu = &tsk->thread.fpu; struct user_i387_ia32_struct env; int err = 0; @@ -391,16 +389,20 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) */ drop_fpu(tsk); - if (__copy_from_user(xsave, buf_fx, state_size) || + if (__copy_from_user(&fpu->state->xsave, buf_fx, state_size) || __copy_from_user(&env, buf, sizeof(env))) { + fpu_finit(fpu); err = -1; } else { sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only); - set_used_math(); } - if (use_eager_fpu()) + set_used_math(); + if (use_eager_fpu()) { + preempt_disable(); math_state_restore(); + preempt_enable(); + } return err; } else { diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 7bff3e2a7a11..09651d4a9038 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -498,11 +498,6 @@ static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc) masked_increment(reg_rmw(ctxt, VCPU_REGS_RSP), stack_mask(ctxt), inc); } -static inline void jmp_rel(struct x86_emulate_ctxt *ctxt, int rel) -{ - register_address_increment(ctxt, &ctxt->_eip, rel); -} - static u32 desc_limit_scaled(struct desc_struct *desc) { u32 limit = get_desc_limit(desc); @@ -576,6 +571,38 @@ static int emulate_nm(struct x86_emulate_ctxt *ctxt) return emulate_exception(ctxt, NM_VECTOR, 0, false); } +static inline int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst, + int cs_l) +{ + switch (ctxt->op_bytes) { + case 2: + ctxt->_eip = (u16)dst; + break; + case 4: + ctxt->_eip = (u32)dst; + break; + case 8: + if ((cs_l && is_noncanonical_address(dst)) || + (!cs_l && (dst & ~(u32)-1))) + return emulate_gp(ctxt, 0); + ctxt->_eip = dst; + break; + default: + WARN(1, "unsupported eip assignment size\n"); + } + return X86EMUL_CONTINUE; +} + +static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst) +{ + return assign_eip_far(ctxt, dst, ctxt->mode == X86EMUL_MODE_PROT64); +} + +static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel) +{ + return assign_eip_near(ctxt, ctxt->_eip + rel); +} + static u16 get_segment_selector(struct x86_emulate_ctxt *ctxt, unsigned seg) { u16 selector; @@ -1958,13 +1985,15 @@ static int em_grp45(struct x86_emulate_ctxt *ctxt) case 2: /* call near abs */ { long int old_eip; old_eip = ctxt->_eip; - ctxt->_eip = ctxt->src.val; + rc = assign_eip_near(ctxt, ctxt->src.val); + if (rc != X86EMUL_CONTINUE) + break; ctxt->src.val = old_eip; rc = em_push(ctxt); break; } case 4: /* jmp abs */ - ctxt->_eip = ctxt->src.val; + rc = assign_eip_near(ctxt, ctxt->src.val); break; case 5: /* jmp far */ rc = em_jmp_far(ctxt); @@ -1996,10 +2025,14 @@ static int em_cmpxchg8b(struct x86_emulate_ctxt *ctxt) static int em_ret(struct x86_emulate_ctxt *ctxt) { - ctxt->dst.type = OP_REG; - ctxt->dst.addr.reg = &ctxt->_eip; - ctxt->dst.bytes = ctxt->op_bytes; - return em_pop(ctxt); + int rc; + unsigned long eip; + + rc = emulate_pop(ctxt, &eip, ctxt->op_bytes); + if (rc != X86EMUL_CONTINUE) + return rc; + + return assign_eip_near(ctxt, eip); } static int em_ret_far(struct x86_emulate_ctxt *ctxt) @@ -2277,7 +2310,7 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) { const struct x86_emulate_ops *ops = ctxt->ops; struct desc_struct cs, ss; - u64 msr_data; + u64 msr_data, rcx, rdx; int usermode; u16 cs_sel = 0, ss_sel = 0; @@ -2293,6 +2326,9 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) else usermode = X86EMUL_MODE_PROT32; + rcx = reg_read(ctxt, VCPU_REGS_RCX); + rdx = reg_read(ctxt, VCPU_REGS_RDX); + cs.dpl = 3; ss.dpl = 3; ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data); @@ -2310,6 +2346,9 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) ss_sel = cs_sel + 8; cs.d = 0; cs.l = 1; + if (is_noncanonical_address(rcx) || + is_noncanonical_address(rdx)) + return emulate_gp(ctxt, 0); break; } cs_sel |= SELECTOR_RPL_MASK; @@ -2318,8 +2357,8 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS); ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); - ctxt->_eip = reg_read(ctxt, VCPU_REGS_RDX); - *reg_write(ctxt, VCPU_REGS_RSP) = reg_read(ctxt, VCPU_REGS_RCX); + ctxt->_eip = rdx; + *reg_write(ctxt, VCPU_REGS_RSP) = rcx; return X86EMUL_CONTINUE; } @@ -2858,10 +2897,13 @@ static int em_aad(struct x86_emulate_ctxt *ctxt) static int em_call(struct x86_emulate_ctxt *ctxt) { + int rc; long rel = ctxt->src.val; ctxt->src.val = (unsigned long)ctxt->_eip; - jmp_rel(ctxt, rel); + rc = jmp_rel(ctxt, rel); + if (rc != X86EMUL_CONTINUE) + return rc; return em_push(ctxt); } @@ -2893,11 +2935,12 @@ static int em_call_far(struct x86_emulate_ctxt *ctxt) static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt) { int rc; + unsigned long eip; - ctxt->dst.type = OP_REG; - ctxt->dst.addr.reg = &ctxt->_eip; - ctxt->dst.bytes = ctxt->op_bytes; - rc = emulate_pop(ctxt, &ctxt->dst.val, ctxt->op_bytes); + rc = emulate_pop(ctxt, &eip, ctxt->op_bytes); + if (rc != X86EMUL_CONTINUE) + return rc; + rc = assign_eip_near(ctxt, eip); if (rc != X86EMUL_CONTINUE) return rc; rsp_increment(ctxt, ctxt->src.val); @@ -3227,20 +3270,24 @@ static int em_lmsw(struct x86_emulate_ctxt *ctxt) static int em_loop(struct x86_emulate_ctxt *ctxt) { + int rc = X86EMUL_CONTINUE; + register_address_increment(ctxt, reg_rmw(ctxt, VCPU_REGS_RCX), -1); if ((address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) != 0) && (ctxt->b == 0xe2 || test_cc(ctxt->b ^ 0x5, ctxt->eflags))) - jmp_rel(ctxt, ctxt->src.val); + rc = jmp_rel(ctxt, ctxt->src.val); - return X86EMUL_CONTINUE; + return rc; } static int em_jcxz(struct x86_emulate_ctxt *ctxt) { + int rc = X86EMUL_CONTINUE; + if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0) - jmp_rel(ctxt, ctxt->src.val); + rc = jmp_rel(ctxt, ctxt->src.val); - return X86EMUL_CONTINUE; + return rc; } static int em_in(struct x86_emulate_ctxt *ctxt) @@ -4599,7 +4646,8 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) goto done; } - ctxt->dst.orig_val = ctxt->dst.val; + /* Copy full 64-bit value for CMPXCHG8B. */ + ctxt->dst.orig_val64 = ctxt->dst.val64; special_insn: @@ -4637,7 +4685,7 @@ special_insn: break; case 0x70 ... 0x7f: /* jcc (short) */ if (test_cc(ctxt->b, ctxt->eflags)) - jmp_rel(ctxt, ctxt->src.val); + rc = jmp_rel(ctxt, ctxt->src.val); break; case 0x8d: /* lea r16/r32, m */ ctxt->dst.val = ctxt->src.addr.mem.ea; @@ -4666,7 +4714,7 @@ special_insn: break; case 0xe9: /* jmp rel */ case 0xeb: /* jmp rel short */ - jmp_rel(ctxt, ctxt->src.val); + rc = jmp_rel(ctxt, ctxt->src.val); ctxt->dst.type = OP_NONE; /* Disable writeback. */ break; case 0xf4: /* hlt */ @@ -4786,7 +4834,7 @@ twobyte_insn: break; case 0x80 ... 0x8f: /* jnz rel, etc*/ if (test_cc(ctxt->b, ctxt->eflags)) - jmp_rel(ctxt, ctxt->src.val); + rc = jmp_rel(ctxt, ctxt->src.val); break; case 0x90 ... 0x9f: /* setcc r/m8 */ ctxt->dst.val = test_cc(ctxt->b, ctxt->eflags); diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 518d86471b76..298781d4cfb4 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -262,8 +262,10 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu) return; timer = &pit->pit_state.timer; + mutex_lock(&pit->pit_state.lock); if (hrtimer_cancel(timer)) hrtimer_start_expires(timer, HRTIMER_MODE_ABS); + mutex_unlock(&pit->pit_state.lock); } static void destroy_pit_timer(struct kvm_pit *pit) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 2790d688c780..32e5329ab0b6 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3156,7 +3156,7 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu) if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) return; - vcpu_clear_mmio_info(vcpu, ~0ul); + vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY); kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC); if (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL) { hpa_t root = vcpu->arch.mmu.root_hpa; @@ -4379,7 +4379,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm) * zap all shadow pages. */ if (unlikely(kvm_current_mmio_generation(kvm) == 0)) { - printk_ratelimited(KERN_INFO "kvm: zapping shadow pages for mmio generation wraparound\n"); + printk_ratelimited(KERN_DEBUG "kvm: zapping shadow pages for mmio generation wraparound\n"); kvm_mmu_invalidate_zap_all_pages(kvm); } } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 945b426c2550..78cfcb348f8a 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -3213,7 +3213,7 @@ static int wrmsr_interception(struct vcpu_svm *svm) msr.host_initiated = false; svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; - if (svm_set_msr(&svm->vcpu, &msr)) { + if (kvm_set_msr(&svm->vcpu, &msr)) { trace_kvm_msr_write_ex(ecx, data); kvm_inject_gp(&svm->vcpu, 0); } else { @@ -3495,9 +3495,9 @@ static int handle_exit(struct kvm_vcpu *vcpu) if (exit_code >= ARRAY_SIZE(svm_exit_handlers) || !svm_exit_handlers[exit_code]) { - kvm_run->exit_reason = KVM_EXIT_UNKNOWN; - kvm_run->hw.hardware_exit_reason = exit_code; - return 0; + WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_code); + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; } return svm_exit_handlers[exit_code](svm); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 8123dc70b443..8b75f5f90a96 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -441,6 +441,7 @@ struct vcpu_vmx { #endif int gs_ldt_reload_needed; int fs_reload_needed; + unsigned long vmcs_host_cr4; /* May not match real cr4 */ } host_state; struct { int vm86_active; @@ -2320,12 +2321,12 @@ static __init void nested_vmx_setup_ctls_msrs(void) nested_vmx_secondary_ctls_low = 0; nested_vmx_secondary_ctls_high &= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | - SECONDARY_EXEC_UNRESTRICTED_GUEST | SECONDARY_EXEC_WBINVD_EXITING; if (enable_ept) { /* nested EPT: emulate EPT also to L1 */ - nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT; + nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT | + SECONDARY_EXEC_UNRESTRICTED_GUEST; nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT | VMX_EPTP_WB_BIT | VMX_EPT_2MB_PAGE_BIT | VMX_EPT_INVEPT_BIT; @@ -2582,12 +2583,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) default: msr = find_msr_entry(vmx, msr_index); if (msr) { + u64 old_msr_data = msr->data; msr->data = data; if (msr - vmx->guest_msrs < vmx->save_nmsrs) { preempt_disable(); - kvm_set_shared_msr(msr->index, msr->data, - msr->mask); + ret = kvm_set_shared_msr(msr->index, msr->data, + msr->mask); preempt_enable(); + if (ret) + msr->data = old_msr_data; } break; } @@ -4162,11 +4166,16 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx) u32 low32, high32; unsigned long tmpl; struct desc_ptr dt; + unsigned long cr4; vmcs_writel(HOST_CR0, read_cr0() & ~X86_CR0_TS); /* 22.2.3 */ - vmcs_writel(HOST_CR4, read_cr4()); /* 22.2.3, 22.2.5 */ vmcs_writel(HOST_CR3, read_cr3()); /* 22.2.3 FIXME: shadow tables */ + /* Save the most likely value for this task's CR4 in the VMCS. */ + cr4 = read_cr4(); + vmcs_writel(HOST_CR4, cr4); /* 22.2.3, 22.2.5 */ + vmx->host_state.vmcs_host_cr4 = cr4; + vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */ #ifdef CONFIG_X86_64 /* @@ -5169,7 +5178,7 @@ static int handle_wrmsr(struct kvm_vcpu *vcpu) msr.data = data; msr.index = ecx; msr.host_initiated = false; - if (vmx_set_msr(vcpu, &msr) != 0) { + if (kvm_set_msr(vcpu, &msr) != 0) { trace_kvm_msr_write_ex(ecx, data); kvm_inject_gp(vcpu, 0); return 1; @@ -6441,6 +6450,12 @@ static int handle_invept(struct kvm_vcpu *vcpu) return 1; } +static int handle_invvpid(struct kvm_vcpu *vcpu) +{ + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; +} + /* * The exit handlers return 1 if the exit was handled fully and guest execution * may resume. Otherwise they set the kvm_run parameter to indicate what needs @@ -6486,6 +6501,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_MWAIT_INSTRUCTION] = handle_invalid_op, [EXIT_REASON_MONITOR_INSTRUCTION] = handle_invalid_op, [EXIT_REASON_INVEPT] = handle_invept, + [EXIT_REASON_INVVPID] = handle_invvpid, }; static const int kvm_vmx_max_exit_handlers = @@ -6719,7 +6735,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_VMPTRST: case EXIT_REASON_VMREAD: case EXIT_REASON_VMRESUME: case EXIT_REASON_VMWRITE: case EXIT_REASON_VMOFF: case EXIT_REASON_VMON: - case EXIT_REASON_INVEPT: + case EXIT_REASON_INVEPT: case EXIT_REASON_INVVPID: /* * VMX instructions trap unconditionally. This allows L1 to * emulate them for its L2 guest, i.e., allows 3-level nesting! @@ -6884,10 +6900,10 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) && kvm_vmx_exit_handlers[exit_reason]) return kvm_vmx_exit_handlers[exit_reason](vcpu); else { - vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; - vcpu->run->hw.hardware_exit_reason = exit_reason; + WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_reason); + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; } - return 0; } static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) @@ -7186,7 +7202,7 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long debugctlmsr; + unsigned long debugctlmsr, cr4; /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked)) @@ -7207,6 +7223,12 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty)) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); + cr4 = read_cr4(); + if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) { + vmcs_writel(HOST_CR4, cr4); + vmx->host_state.vmcs_host_cr4 = cr4; + } + /* When single-stepping over STI and MOV SS, we must clear the * corresponding interruptibility bits in the guest state. Otherwise * vmentry fails as it then expects bit 14 (BS) in pending debug diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index fc39a0cdfd03..52b2f778f329 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -225,20 +225,25 @@ static void kvm_shared_msr_cpu_online(void) shared_msr_update(i, shared_msrs_global.msrs[i]); } -void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) +int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) { unsigned int cpu = smp_processor_id(); struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); + int err; if (((value ^ smsr->values[slot].curr) & mask) == 0) - return; + return 0; smsr->values[slot].curr = value; - wrmsrl(shared_msrs_global.msrs[slot], value); + err = wrmsrl_safe(shared_msrs_global.msrs[slot], value); + if (err) + return 1; + if (!smsr->registered) { smsr->urn.on_user_return = kvm_on_user_return; user_return_notifier_register(&smsr->urn); smsr->registered = true; } + return 0; } EXPORT_SYMBOL_GPL(kvm_set_shared_msr); @@ -946,7 +951,6 @@ void kvm_enable_efer_bits(u64 mask) } EXPORT_SYMBOL_GPL(kvm_enable_efer_bits); - /* * Writes msr value into into the appropriate "register". * Returns 0 on success, non-0 otherwise. @@ -954,8 +958,34 @@ EXPORT_SYMBOL_GPL(kvm_enable_efer_bits); */ int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { + switch (msr->index) { + case MSR_FS_BASE: + case MSR_GS_BASE: + case MSR_KERNEL_GS_BASE: + case MSR_CSTAR: + case MSR_LSTAR: + if (is_noncanonical_address(msr->data)) + return 1; + break; + case MSR_IA32_SYSENTER_EIP: + case MSR_IA32_SYSENTER_ESP: + /* + * IA32_SYSENTER_ESP and IA32_SYSENTER_EIP cause #GP if + * non-canonical address is written on Intel but not on + * AMD (which ignores the top 32-bits, because it does + * not implement 64-bit SYSENTER). + * + * 64-bit code should hence be able to write a non-canonical + * value on AMD. Making the address canonical ensures that + * vmentry does not fail on Intel after writing a non-canonical + * value, and that something deterministic happens if the guest + * invokes 64-bit SYSENTER. + */ + msr->data = get_canonical(msr->data); + } return kvm_x86_ops->set_msr(vcpu, msr); } +EXPORT_SYMBOL_GPL(kvm_set_msr); /* * Adapt set_msr() to msr_io()'s calling convention @@ -1177,21 +1207,22 @@ void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) { #ifdef CONFIG_X86_64 bool vcpus_matched; - bool do_request = false; struct kvm_arch *ka = &vcpu->kvm->arch; struct pvclock_gtod_data *gtod = &pvclock_gtod_data; vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 == atomic_read(&vcpu->kvm->online_vcpus)); - if (vcpus_matched && gtod->clock.vclock_mode == VCLOCK_TSC) - if (!ka->use_master_clock) - do_request = 1; - - if (!vcpus_matched && ka->use_master_clock) - do_request = 1; - - if (do_request) + /* + * Once the masterclock is enabled, always perform request in + * order to update it. + * + * In order to enable masterclock, the host clocksource must be TSC + * and the vcpus need to have matched TSCs. When that happens, + * perform request to enable masterclock. + */ + if (ka->use_master_clock || + (gtod->clock.vclock_mode == VCLOCK_TSC && vcpus_matched)) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc, @@ -4881,7 +4912,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu) ++vcpu->stat.insn_emulation_fail; trace_kvm_emulate_insn_failed(vcpu); - if (!is_guest_mode(vcpu)) { + if (!is_guest_mode(vcpu) && kvm_x86_ops->get_cpl(vcpu) == 0) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; vcpu->run->internal.ndata = 0; diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 8da5823bcde6..21ea4fc91b5b 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -78,15 +78,23 @@ static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu, vcpu->arch.mmio_gva = gva & PAGE_MASK; vcpu->arch.access = access; vcpu->arch.mmio_gfn = gfn; + vcpu->arch.mmio_gen = kvm_memslots(vcpu->kvm)->generation; +} + +static inline bool vcpu_match_mmio_gen(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.mmio_gen == kvm_memslots(vcpu->kvm)->generation; } /* - * Clear the mmio cache info for the given gva, - * specially, if gva is ~0ul, we clear all mmio cache info. + * Clear the mmio cache info for the given gva. If gva is MMIO_GVA_ANY, we + * clear all mmio cache info. */ +#define MMIO_GVA_ANY (~(gva_t)0) + static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva) { - if (gva != (~0ul) && vcpu->arch.mmio_gva != (gva & PAGE_MASK)) + if (gva != MMIO_GVA_ANY && vcpu->arch.mmio_gva != (gva & PAGE_MASK)) return; vcpu->arch.mmio_gva = 0; @@ -94,7 +102,8 @@ static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva) static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva) { - if (vcpu->arch.mmio_gva && vcpu->arch.mmio_gva == (gva & PAGE_MASK)) + if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gva && + vcpu->arch.mmio_gva == (gva & PAGE_MASK)) return true; return false; @@ -102,7 +111,8 @@ static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva) static inline bool vcpu_match_mmio_gpa(struct kvm_vcpu *vcpu, gpa_t gpa) { - if (vcpu->arch.mmio_gfn && vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT) + if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gfn && + vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT) return true; return false; diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index 207d9aef662d..448ee8912d9b 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -172,7 +172,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, */ if (pmd_none(pmd) || pmd_trans_splitting(pmd)) return 0; - if (unlikely(pmd_large(pmd))) { + if (unlikely(pmd_large(pmd) || !pmd_present(pmd))) { /* * NUMA hinting faults need to be handled in the GUP * slowpath for accounting purposes and so that they diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 8b977ebf9388..006cc914994b 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -66,9 +66,15 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address, int write) return ERR_PTR(-EINVAL); } +/* + * pmd_huge() returns 1 if @pmd is hugetlb related entry, that is normal + * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry. + * Otherwise, returns 0. + */ int pmd_huge(pmd_t pmd) { - return !!(pmd_val(pmd) & _PAGE_PSE); + return !pmd_none(pmd) && + (pmd_val(pmd) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT; } int pud_huge(pud_t pud) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index f35c66c5959a..2308a401a1c5 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1110,7 +1110,7 @@ void mark_rodata_ro(void) unsigned long end = (unsigned long) &__end_rodata_hpage_align; unsigned long text_end = PFN_ALIGN(&__stop___ex_table); unsigned long rodata_end = PFN_ALIGN(&__end_rodata); - unsigned long all_end = PFN_ALIGN(&_end); + unsigned long all_end; printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n", (end - start) >> 10); @@ -1121,7 +1121,16 @@ void mark_rodata_ro(void) /* * The rodata/data/bss/brk section (but not the kernel text!) * should also be not-executable. + * + * We align all_end to PMD_SIZE because the existing mapping + * is a full PMD. If we would align _brk_end to PAGE_SIZE we + * split the PMD and the reminder between _brk_end and the end + * of the PMD will remain mapped executable. + * + * Any PMD which was setup after the one which covers _brk_end + * has been zapped already via cleanup_highmem(). */ + all_end = roundup((unsigned long)_brk_end, PMD_SIZE); set_memory_nx(rodata_start, (all_end - rodata_start) >> PAGE_SHIFT); rodata_test(); diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 25e7e1372bb2..3601ff284b92 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -35,12 +35,12 @@ struct __read_mostly va_alignment va_align = { .flags = -1, }; -static unsigned int stack_maxrandom_size(void) +static unsigned long stack_maxrandom_size(void) { - unsigned int max = 0; + unsigned long max = 0; if ((current->flags & PF_RANDOMIZE) && !(current->personality & ADDR_NO_RANDOMIZE)) { - max = ((-1U) & STACK_RND_MASK) << PAGE_SHIFT; + max = ((-1UL) & STACK_RND_MASK) << PAGE_SHIFT; } return max; diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index a3488689e301..fed892de9baf 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -405,7 +405,7 @@ phys_addr_t slow_virt_to_phys(void *__virt_addr) psize = page_level_size(level); pmask = page_level_mask(level); offset = virt_addr & ~pmask; - phys_addr = pte_pfn(*pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; return (phys_addr | offset); } EXPORT_SYMBOL_GPL(slow_virt_to_phys); diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index c96314abd144..0004ac72dbdd 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -399,13 +399,20 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma, int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { - int young; - - young = ptep_test_and_clear_young(vma, address, ptep); - if (young) - flush_tlb_page(vma, address); - - return young; + /* + * On x86 CPUs, clearing the accessed bit without a TLB flush + * doesn't cause data corruption. [ It could cause incorrect + * page aging and the (mistaken) reclaim of hot pages, but the + * chance of that should be relatively low. ] + * + * So as a performance optimization don't flush the TLB when + * clearing the accessed bit, it will eventually be flushed by + * a context switch or a VM operation anyway. [ In the rare + * event of it not getting flushed for a long time the delay + * shouldn't really matter because there's no real memory + * pressure for swapout to react to. ] + */ + return ptep_test_and_clear_young(vma, address, ptep); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 981c2dbd72cc..88f143d9754e 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -448,6 +448,22 @@ static const struct dmi_system_id pciprobe_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "ftServer"), }, }, + { + .callback = set_scan_all, + .ident = "Stratus/NEC ftServer", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "NEC"), + DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R32"), + }, + }, + { + .callback = set_scan_all, + .ident = "Stratus/NEC ftServer", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "NEC"), + DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R31"), + }, + }, {} }; diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index abb81b0ad83f..2b42f0a6d381 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -68,8 +68,6 @@ struct efi_memory_map memmap; static struct efi efi_phys __initdata; static efi_system_table_t efi_systab __initdata; -unsigned long x86_efi_facility; - static __initdata efi_config_table_type_t arch_tables[] = { #ifdef CONFIG_X86_UV {UV_SYSTEM_TABLE_GUID, "UVsystab", &efi.uv_systab}, @@ -79,15 +77,6 @@ static __initdata efi_config_table_type_t arch_tables[] = { u64 efi_setup; /* efi setup_data physical address */ -/* - * Returns 1 if 'facility' is enabled, 0 otherwise. - */ -int efi_enabled(int facility) -{ - return test_bit(facility, &x86_efi_facility) != 0; -} -EXPORT_SYMBOL(efi_enabled); - static bool __initdata disable_runtime = false; static int __init setup_noefi(char *arg) { @@ -456,7 +445,7 @@ void __init efi_reserve_boot_services(void) void __init efi_unmap_memmap(void) { - clear_bit(EFI_MEMMAP, &x86_efi_facility); + clear_bit(EFI_MEMMAP, &efi.flags); if (memmap.map) { early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size); memmap.map = NULL; @@ -589,6 +578,8 @@ static int __init efi_systab_init(void *phys) efi.systab->hdr.revision >> 16, efi.systab->hdr.revision & 0xffff); + set_bit(EFI_SYSTEM_TABLES, &efi.flags); + return 0; } @@ -624,6 +615,8 @@ static int __init efi_runtime_init(void) efi.get_time = phys_efi_get_time; early_iounmap(runtime, sizeof(efi_runtime_services_t)); + set_bit(EFI_RUNTIME_SERVICES, &efi.flags); + return 0; } @@ -641,6 +634,8 @@ static int __init efi_memmap_init(void) if (add_efi_memmap) do_add_efi_memmap(); + set_bit(EFI_MEMMAP, &efi.flags); + return 0; } @@ -723,7 +718,7 @@ void __init efi_init(void) if (efi_systab_init(efi_phys.systab)) return; - set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility); + set_bit(EFI_SYSTEM_TABLES, &efi.flags); efi.config_table = (unsigned long)efi.systab->tables; efi.fw_vendor = (unsigned long)efi.systab->fw_vendor; @@ -751,8 +746,6 @@ void __init efi_init(void) if (efi_config_init(arch_tables)) return; - set_bit(EFI_CONFIG_TABLES, &x86_efi_facility); - /* * Note: We currently don't support runtime services on an EFI * that doesn't match the kernel 32/64-bit mode. @@ -763,12 +756,11 @@ void __init efi_init(void) else { if (disable_runtime || efi_runtime_init()) return; - set_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility); } if (efi_memmap_init()) return; - set_bit(EFI_MEMMAP, &x86_efi_facility); + set_bit(EFI_MEMMAP, &efi.flags); print_efi_memmap(); } @@ -1263,7 +1255,7 @@ static int __init parse_efi_cmdline(char *str) str++; if (!strncmp(str, "old_map", 7)) - set_bit(EFI_OLD_MEMMAP, &x86_efi_facility); + set_bit(EFI_OLD_MEMMAP, &efi.flags); return 0; } diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl index 7f517ca19d32..ec255a1646d2 100644 --- a/arch/x86/syscalls/syscall_64.tbl +++ b/arch/x86/syscalls/syscall_64.tbl @@ -322,6 +322,7 @@ 313 common finit_module sys_finit_module 314 common sched_setattr sys_sched_setattr 315 common sched_getattr sys_sched_getattr +316 common renameat2 sys_renameat2 # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/arch/x86/tools/calc_run_size.sh b/arch/x86/tools/calc_run_size.sh new file mode 100644 index 000000000000..1a4c17bb3910 --- /dev/null +++ b/arch/x86/tools/calc_run_size.sh @@ -0,0 +1,42 @@ +#!/bin/sh +# +# Calculate the amount of space needed to run the kernel, including room for +# the .bss and .brk sections. +# +# Usage: +# objdump -h a.out | sh calc_run_size.sh + +NUM='\([0-9a-fA-F]*[ \t]*\)' +OUT=$(sed -n 's/^[ \t0-9]*.b[sr][sk][ \t]*'"$NUM$NUM$NUM$NUM"'.*/\1\4/p') +if [ -z "$OUT" ] ; then + echo "Never found .bss or .brk file offset" >&2 + exit 1 +fi + +OUT=$(echo ${OUT# }) +sizeA=$(printf "%d" 0x${OUT%% *}) +OUT=${OUT#* } +offsetA=$(printf "%d" 0x${OUT%% *}) +OUT=${OUT#* } +sizeB=$(printf "%d" 0x${OUT%% *}) +OUT=${OUT#* } +offsetB=$(printf "%d" 0x${OUT%% *}) + +run_size=$(( $offsetA + $sizeA + $sizeB )) + +# BFD linker shows the same file offset in ELF. +if [ "$offsetA" -ne "$offsetB" ] ; then + # Gold linker shows them as consecutive. + endB=$(( $offsetB + $sizeB )) + if [ "$endB" != "$run_size" ] ; then + printf "sizeA: 0x%x\n" $sizeA >&2 + printf "offsetA: 0x%x\n" $offsetA >&2 + printf "sizeB: 0x%x\n" $sizeB >&2 + printf "offsetB: 0x%x\n" $offsetB >&2 + echo ".bss and .brk are non-contiguous" >&2 + exit 1 + fi +fi + +printf "%d\n" $run_size +exit 0 diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c index 531d4269e2e3..bd16d6c370ec 100644 --- a/arch/x86/um/sys_call_table_32.c +++ b/arch/x86/um/sys_call_table_32.c @@ -34,7 +34,7 @@ typedef asmlinkage void (*sys_call_ptr_t)(void); extern asmlinkage void sys_ni_syscall(void); -const sys_call_ptr_t sys_call_table[] __cacheline_aligned = { +const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = { /* * Smells like a compiler bug -- it doesn't work * when the & below is removed. diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c index f2f0723070ca..95783087f0d3 100644 --- a/arch/x86/um/sys_call_table_64.c +++ b/arch/x86/um/sys_call_table_64.c @@ -46,7 +46,7 @@ typedef void (*sys_call_ptr_t)(void); extern void sys_ni_syscall(void); -const sys_call_ptr_t sys_call_table[] __cacheline_aligned = { +const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = { /* * Smells like a compiler bug -- it doesn't work * when the & below is removed. diff --git a/arch/x86/vdso/vdso32/sigreturn.S b/arch/x86/vdso/vdso32/sigreturn.S index 31776d0efc8c..d7ec4e251c0a 100644 --- a/arch/x86/vdso/vdso32/sigreturn.S +++ b/arch/x86/vdso/vdso32/sigreturn.S @@ -17,6 +17,7 @@ .text .globl __kernel_sigreturn .type __kernel_sigreturn,@function + nop /* this guy is needed for .LSTARTFDEDLSI1 below (watch for HACK) */ ALIGN __kernel_sigreturn: .LSTART_sigreturn: diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c index 431e87544411..ab6ba35a9357 100644 --- a/arch/x86/vdso/vma.c +++ b/arch/x86/vdso/vma.c @@ -117,30 +117,45 @@ subsys_initcall(init_vdso); struct linux_binprm; -/* Put the vdso above the (randomized) stack with another randomized offset. - This way there is no hole in the middle of address space. - To save memory make sure it is still in the same PTE as the stack top. - This doesn't give that many random bits */ +/* + * Put the vdso above the (randomized) stack with another randomized + * offset. This way there is no hole in the middle of address space. + * To save memory make sure it is still in the same PTE as the stack + * top. This doesn't give that many random bits. + * + * Note that this algorithm is imperfect: the distribution of the vdso + * start address within a PMD is biased toward the end. + * + * Only used for the 64-bit and x32 vdsos. + */ static unsigned long vdso_addr(unsigned long start, unsigned len) { unsigned long addr, end; unsigned offset; - end = (start + PMD_SIZE - 1) & PMD_MASK; + + /* + * Round up the start address. It can start out unaligned as a result + * of stack start randomization. + */ + start = PAGE_ALIGN(start); + + /* Round the lowest possible end address up to a PMD boundary. */ + end = (start + len + PMD_SIZE - 1) & PMD_MASK; if (end >= TASK_SIZE_MAX) end = TASK_SIZE_MAX; end -= len; - /* This loses some more bits than a modulo, but is cheaper */ - offset = get_random_int() & (PTRS_PER_PTE - 1); - addr = start + (offset << PAGE_SHIFT); - if (addr >= end) - addr = end; + + if (end > start) { + offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1); + addr = start + (offset << PAGE_SHIFT); + } else { + addr = start; + } /* - * page-align it here so that get_unmapped_area doesn't - * align it wrongfully again to the next page. addr can come in 4K - * unaligned here as a result of stack start randomization. + * Forcibly align the final address in case we have a hardware + * issue that requires alignment for performance reasons. */ - addr = PAGE_ALIGN(addr); addr = align_vdso_addr(addr); return addr; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 2423ef04ffea..c83da6fb2dee 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1866,12 +1866,11 @@ static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end, * * We can construct this by grafting the Xen provided pagetable into * head_64.S's preconstructed pagetables. We copy the Xen L2's into - * level2_ident_pgt, level2_kernel_pgt and level2_fixmap_pgt. This - * means that only the kernel has a physical mapping to start with - - * but that's enough to get __va working. We need to fill in the rest - * of the physical mapping once some sort of allocator has been set - * up. - * NOTE: for PVH, the page tables are native. + * level2_ident_pgt, and level2_kernel_pgt. This means that only the + * kernel has a physical mapping to start with - but that's enough to + * get __va working. We need to fill in the rest of the physical + * mapping once some sort of allocator has been set up. NOTE: for + * PVH, the page tables are native. */ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) { @@ -1902,8 +1901,11 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) /* L3_i[0] -> level2_ident_pgt */ convert_pfn_mfn(level3_ident_pgt); /* L3_k[510] -> level2_kernel_pgt - * L3_i[511] -> level2_fixmap_pgt */ + * L3_k[511] -> level2_fixmap_pgt */ convert_pfn_mfn(level3_kernel_pgt); + + /* L3_k[511][506] -> level1_fixmap_pgt */ + convert_pfn_mfn(level2_fixmap_pgt); } /* We get [511][511] and have Xen's version of level2_kernel_pgt */ l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd); @@ -1913,21 +1915,15 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) addr[1] = (unsigned long)l3; addr[2] = (unsigned long)l2; /* Graft it onto L4[272][0]. Note that we creating an aliasing problem: - * Both L4[272][0] and L4[511][511] have entries that point to the same + * Both L4[272][0] and L4[511][510] have entries that point to the same * L2 (PMD) tables. Meaning that if you modify it in __va space * it will be also modified in the __ka space! (But if you just * modify the PMD table to point to other PTE's or none, then you * are OK - which is what cleanup_highmap does) */ copy_page(level2_ident_pgt, l2); - /* Graft it onto L4[511][511] */ + /* Graft it onto L4[511][510] */ copy_page(level2_kernel_pgt, l2); - /* Get [511][510] and graft that in level2_fixmap_pgt */ - l3 = m2v(pgd[pgd_index(__START_KERNEL_map + PMD_SIZE)].pgd); - l2 = m2v(l3[pud_index(__START_KERNEL_map + PMD_SIZE)].pud); - copy_page(level2_fixmap_pgt, l2); - /* Note that we don't do anything with level1_fixmap_pgt which - * we don't need. */ if (!xen_feature(XENFEAT_auto_translated_physmap)) { /* Make pagetable pieces RO */ set_page_prot(init_level4_pgt, PAGE_KERNEL_RO); @@ -1937,6 +1933,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO); set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO); + set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO); /* Pin down new L4 */ pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h index 216446295ada..51230ba97bef 100644 --- a/arch/xtensa/include/asm/pgtable.h +++ b/arch/xtensa/include/asm/pgtable.h @@ -67,7 +67,12 @@ #define VMALLOC_START 0xC0000000 #define VMALLOC_END 0xC7FEFFFF #define TLBTEMP_BASE_1 0xC7FF0000 -#define TLBTEMP_BASE_2 0xC7FF8000 +#define TLBTEMP_BASE_2 (TLBTEMP_BASE_1 + DCACHE_WAY_SIZE) +#if 2 * DCACHE_WAY_SIZE > ICACHE_WAY_SIZE +#define TLBTEMP_SIZE (2 * DCACHE_WAY_SIZE) +#else +#define TLBTEMP_SIZE ICACHE_WAY_SIZE +#endif /* * For the Xtensa architecture, the PTE layout is as follows: diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h index fd686dc45d1a..c7211e7e182d 100644 --- a/arch/xtensa/include/asm/uaccess.h +++ b/arch/xtensa/include/asm/uaccess.h @@ -52,7 +52,12 @@ */ .macro get_fs ad, sp GET_CURRENT(\ad,\sp) +#if THREAD_CURRENT_DS > 1020 + addi \ad, \ad, TASK_THREAD + l32i \ad, \ad, THREAD_CURRENT_DS - TASK_THREAD +#else l32i \ad, \ad, THREAD_CURRENT_DS +#endif .endm /* diff --git a/arch/xtensa/include/uapi/asm/ioctls.h b/arch/xtensa/include/uapi/asm/ioctls.h index b4cb1100c0fb..a47909f0c34b 100644 --- a/arch/xtensa/include/uapi/asm/ioctls.h +++ b/arch/xtensa/include/uapi/asm/ioctls.h @@ -28,17 +28,17 @@ #define TCSETSW 0x5403 #define TCSETSF 0x5404 -#define TCGETA _IOR('t', 23, struct termio) -#define TCSETA _IOW('t', 24, struct termio) -#define TCSETAW _IOW('t', 25, struct termio) -#define TCSETAF _IOW('t', 28, struct termio) +#define TCGETA 0x80127417 /* _IOR('t', 23, struct termio) */ +#define TCSETA 0x40127418 /* _IOW('t', 24, struct termio) */ +#define TCSETAW 0x40127419 /* _IOW('t', 25, struct termio) */ +#define TCSETAF 0x4012741C /* _IOW('t', 28, struct termio) */ #define TCSBRK _IO('t', 29) #define TCXONC _IO('t', 30) #define TCFLSH _IO('t', 31) -#define TIOCSWINSZ _IOW('t', 103, struct winsize) -#define TIOCGWINSZ _IOR('t', 104, struct winsize) +#define TIOCSWINSZ 0x40087467 /* _IOW('t', 103, struct winsize) */ +#define TIOCGWINSZ 0x80087468 /* _IOR('t', 104, struct winsize) */ #define TIOCSTART _IO('t', 110) /* start output, like ^Q */ #define TIOCSTOP _IO('t', 111) /* stop output, like ^S */ #define TIOCOUTQ _IOR('t', 115, int) /* output queue size */ @@ -88,7 +88,6 @@ #define TIOCSETD _IOW('T', 35, int) #define TIOCGETD _IOR('T', 36, int) #define TCSBRKP _IOW('T', 37, int) /* Needed for POSIX tcsendbreak()*/ -#define TIOCTTYGSTRUCT _IOR('T', 38, struct tty_struct) /* For debugging only*/ #define TIOCSBRK _IO('T', 39) /* BSD compatibility */ #define TIOCCBRK _IO('T', 40) /* BSD compatibility */ #define TIOCGSID _IOR('T', 41, pid_t) /* Return the session ID of FD*/ @@ -114,8 +113,10 @@ #define TIOCSERGETLSR _IOR('T', 89, unsigned int) /* Get line status reg. */ /* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */ # define TIOCSER_TEMT 0x01 /* Transmitter physically empty */ -#define TIOCSERGETMULTI _IOR('T', 90, struct serial_multiport_struct) /* Get multiport config */ -#define TIOCSERSETMULTI _IOW('T', 91, struct serial_multiport_struct) /* Set multiport config */ +#define TIOCSERGETMULTI 0x80a8545a /* Get multiport config */ + /* _IOR('T', 90, struct serial_multiport_struct) */ +#define TIOCSERSETMULTI 0x40a8545b /* Set multiport config */ + /* _IOW('T', 91, struct serial_multiport_struct) */ #define TIOCMIWAIT _IO('T', 92) /* wait for a change on serial input line(s) */ #define TIOCGICOUNT 0x545D /* read serial port inline interrupt counts */ diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h index b9395529f02d..50084f7c01c8 100644 --- a/arch/xtensa/include/uapi/asm/unistd.h +++ b/arch/xtensa/include/uapi/asm/unistd.h @@ -384,7 +384,8 @@ __SYSCALL(174, sys_chroot, 1) #define __NR_pivot_root 175 __SYSCALL(175, sys_pivot_root, 2) #define __NR_umount 176 -__SYSCALL(176, sys_umount, 2) +__SYSCALL(176, sys_oldumount, 1) +#define __ARCH_WANT_SYS_OLDUMOUNT #define __NR_swapoff 177 __SYSCALL(177, sys_swapoff, 1) #define __NR_sync 178 diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S index ef7f4990722b..a06b7efaae82 100644 --- a/arch/xtensa/kernel/entry.S +++ b/arch/xtensa/kernel/entry.S @@ -1001,9 +1001,8 @@ ENTRY(fast_syscall_xtensa) movi a7, 4 # sizeof(unsigned int) access_ok a3, a7, a0, a2, .Leac # a0: scratch reg, a2: sp - addi a6, a6, -1 # assuming SYS_XTENSA_ATOMIC_SET = 1 - _bgeui a6, SYS_XTENSA_COUNT - 1, .Lill - _bnei a6, SYS_XTENSA_ATOMIC_CMP_SWP - 1, .Lnswp + _bgeui a6, SYS_XTENSA_COUNT, .Lill + _bnei a6, SYS_XTENSA_ATOMIC_CMP_SWP, .Lnswp /* Fall through for ATOMIC_CMP_SWP. */ @@ -1015,27 +1014,26 @@ TRY s32i a5, a3, 0 # different, modify value l32i a7, a2, PT_AREG7 # restore a7 l32i a0, a2, PT_AREG0 # restore a0 movi a2, 1 # and return 1 - addi a6, a6, 1 # restore a6 (really necessary?) rfe 1: l32i a7, a2, PT_AREG7 # restore a7 l32i a0, a2, PT_AREG0 # restore a0 movi a2, 0 # return 0 (note that we cannot set - addi a6, a6, 1 # restore a6 (really necessary?) rfe .Lnswp: /* Atomic set, add, and exg_add. */ TRY l32i a7, a3, 0 # orig + addi a6, a6, -SYS_XTENSA_ATOMIC_SET add a0, a4, a7 # + arg moveqz a0, a4, a6 # set + addi a6, a6, SYS_XTENSA_ATOMIC_SET TRY s32i a0, a3, 0 # write new value mov a0, a2 mov a2, a7 l32i a7, a0, PT_AREG7 # restore a7 l32i a0, a0, PT_AREG0 # restore a0 - addi a6, a6, 1 # restore a6 (really necessary?) rfe CATCH @@ -1044,7 +1042,7 @@ CATCH movi a2, -EFAULT rfe -.Lill: l32i a7, a2, PT_AREG0 # restore a7 +.Lill: l32i a7, a2, PT_AREG7 # restore a7 l32i a0, a2, PT_AREG0 # restore a0 movi a2, -EINVAL rfe @@ -1565,7 +1563,7 @@ ENTRY(fast_second_level_miss) rsr a0, excvaddr bltu a0, a3, 2f - addi a1, a0, -(2 << (DCACHE_ALIAS_ORDER + PAGE_SHIFT)) + addi a1, a0, -TLBTEMP_SIZE bgeu a1, a3, 2f /* Check if we have to restore an ITLB mapping. */ @@ -1820,7 +1818,6 @@ ENTRY(_switch_to) entry a1, 16 - mov a10, a2 # preserve 'prev' (a2) mov a11, a3 # and 'next' (a3) l32i a4, a2, TASK_THREAD_INFO @@ -1828,8 +1825,14 @@ ENTRY(_switch_to) save_xtregs_user a4 a6 a8 a9 a12 a13 THREAD_XTREGS_USER - s32i a0, a10, THREAD_RA # save return address - s32i a1, a10, THREAD_SP # save stack pointer +#if THREAD_RA > 1020 || THREAD_SP > 1020 + addi a10, a2, TASK_THREAD + s32i a0, a10, THREAD_RA - TASK_THREAD # save return address + s32i a1, a10, THREAD_SP - TASK_THREAD # save stack pointer +#else + s32i a0, a2, THREAD_RA # save return address + s32i a1, a2, THREAD_SP # save stack pointer +#endif /* Disable ints while we manipulate the stack pointer. */ @@ -1870,7 +1873,6 @@ ENTRY(_switch_to) load_xtregs_user a5 a6 a8 a9 a12 a13 THREAD_XTREGS_USER wsr a14, ps - mov a2, a10 # return 'prev' rsync retw diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c index 2d9cc6dbfd78..e8b76b8e4b29 100644 --- a/arch/xtensa/kernel/pci-dma.c +++ b/arch/xtensa/kernel/pci-dma.c @@ -49,9 +49,8 @@ dma_alloc_coherent(struct device *dev,size_t size,dma_addr_t *handle,gfp_t flag) /* We currently don't support coherent memory outside KSEG */ - if (ret < XCHAL_KSEG_CACHED_VADDR - || ret >= XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE) - BUG(); + BUG_ON(ret < XCHAL_KSEG_CACHED_VADDR || + ret > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1); if (ret != 0) { @@ -68,10 +67,11 @@ EXPORT_SYMBOL(dma_alloc_coherent); void dma_free_coherent(struct device *hwdev, size_t size, void *vaddr, dma_addr_t dma_handle) { - long addr=(long)vaddr+XCHAL_KSEG_CACHED_VADDR-XCHAL_KSEG_BYPASS_VADDR; + unsigned long addr = (unsigned long)vaddr + + XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR; - if (addr < 0 || addr >= XCHAL_KSEG_SIZE) - BUG(); + BUG_ON(addr < XCHAL_KSEG_CACHED_VADDR || + addr > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1); free_pages(addr, get_order(size)); } diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c index f8721278601c..78d38352bf8d 100644 --- a/block/blk-mq-cpumap.c +++ b/block/blk-mq-cpumap.c @@ -95,7 +95,7 @@ unsigned int *blk_mq_make_queue_map(struct blk_mq_reg *reg) unsigned int *map; /* If cpus are offline, map them to first hctx */ - map = kzalloc_node(sizeof(*map) * num_possible_cpus(), GFP_KERNEL, + map = kzalloc_node(sizeof(*map) * nr_cpu_ids, GFP_KERNEL, reg->numa_node); if (!map) return NULL; diff --git a/block/blk-settings.c b/block/blk-settings.c index 5d21239bc859..95138e9d0ad5 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -553,7 +553,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, bottom = max(b->physical_block_size, b->io_min) + alignment; /* Verify that top and bottom intervals line up */ - if (max(top, bottom) & (min(top, bottom) - 1)) { + if (max(top, bottom) % min(top, bottom)) { t->misaligned = 1; ret = -1; } @@ -598,7 +598,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, /* Find lowest common alignment_offset */ t->alignment_offset = lcm(t->alignment_offset, alignment) - & (max(t->physical_block_size, t->io_min) - 1); + % max(t->physical_block_size, t->io_min); /* Verify that new alignment_offset is on a logical block boundary */ if (t->alignment_offset & (t->logical_block_size - 1)) { diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 1474c3ab7e72..15998784c00e 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -1292,6 +1292,9 @@ static u64 tg_prfill_cpu_rwstat(struct seq_file *sf, struct blkg_rwstat rwstat = { }, tmp; int i, cpu; + if (tg->stats_cpu == NULL) + return 0; + for_each_possible_cpu(cpu) { struct tg_stats_cpu *sc = per_cpu_ptr(tg->stats_cpu, cpu); diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 744833b630c6..d9bba9915420 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -1275,12 +1275,16 @@ __cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg) static void cfq_update_group_weight(struct cfq_group *cfqg) { - BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node)); - if (cfqg->new_weight) { cfqg->weight = cfqg->new_weight; cfqg->new_weight = 0; } +} + +static void +cfq_update_group_leaf_weight(struct cfq_group *cfqg) +{ + BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node)); if (cfqg->new_leaf_weight) { cfqg->leaf_weight = cfqg->new_leaf_weight; @@ -1299,7 +1303,7 @@ cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg) /* add to the service tree */ BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node)); - cfq_update_group_weight(cfqg); + cfq_update_group_leaf_weight(cfqg); __cfq_group_service_tree_add(st, cfqg); /* @@ -1323,6 +1327,7 @@ cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg) */ while ((parent = cfqg_parent(pos))) { if (propagate) { + cfq_update_group_weight(pos); propagate = !parent->nr_active++; parent->children_weight += pos->weight; } @@ -3580,6 +3585,11 @@ retry: blkcg = bio_blkcg(bio); cfqg = cfq_lookup_create_cfqg(cfqd, blkcg); + if (!cfqg) { + cfqq = &cfqd->oom_cfqq; + goto out; + } + cfqq = cic_to_cfqq(cic, is_sync); /* @@ -3616,7 +3626,7 @@ retry: } else cfqq = &cfqd->oom_cfqq; } - +out: if (new_cfqq) kmem_cache_free(cfq_pool, new_cfqq); @@ -3646,12 +3656,17 @@ static struct cfq_queue * cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct cfq_io_cq *cic, struct bio *bio, gfp_t gfp_mask) { - const int ioprio_class = IOPRIO_PRIO_CLASS(cic->ioprio); - const int ioprio = IOPRIO_PRIO_DATA(cic->ioprio); + int ioprio_class = IOPRIO_PRIO_CLASS(cic->ioprio); + int ioprio = IOPRIO_PRIO_DATA(cic->ioprio); struct cfq_queue **async_cfqq = NULL; struct cfq_queue *cfqq = NULL; if (!is_sync) { + if (!ioprio_valid(cic->ioprio)) { + struct task_struct *tsk = current; + ioprio = task_nice_ioprio(tsk); + ioprio_class = task_nice_ioclass(tsk); + } async_cfqq = cfq_async_queue_prio(cfqd, ioprio_class, ioprio); cfqq = *async_cfqq; } diff --git a/block/genhd.c b/block/genhd.c index 791f41943132..a8d586a729bb 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -28,10 +28,10 @@ struct kobject *block_depr; /* for extended dynamic devt allocation, currently only one major is used */ #define NR_EXT_DEVT (1 << MINORBITS) -/* For extended devt allocation. ext_devt_mutex prevents look up +/* For extended devt allocation. ext_devt_lock prevents look up * results from going away underneath its user. */ -static DEFINE_MUTEX(ext_devt_mutex); +static DEFINE_SPINLOCK(ext_devt_lock); static DEFINE_IDR(ext_devt_idr); static struct device_type disk_type; @@ -420,9 +420,13 @@ int blk_alloc_devt(struct hd_struct *part, dev_t *devt) } /* allocate ext devt */ - mutex_lock(&ext_devt_mutex); - idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_KERNEL); - mutex_unlock(&ext_devt_mutex); + idr_preload(GFP_KERNEL); + + spin_lock(&ext_devt_lock); + idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_NOWAIT); + spin_unlock(&ext_devt_lock); + + idr_preload_end(); if (idx < 0) return idx == -ENOSPC ? -EBUSY : idx; @@ -441,15 +445,13 @@ int blk_alloc_devt(struct hd_struct *part, dev_t *devt) */ void blk_free_devt(dev_t devt) { - might_sleep(); - if (devt == MKDEV(0, 0)) return; if (MAJOR(devt) == BLOCK_EXT_MAJOR) { - mutex_lock(&ext_devt_mutex); + spin_lock(&ext_devt_lock); idr_remove(&ext_devt_idr, blk_mangle_minor(MINOR(devt))); - mutex_unlock(&ext_devt_mutex); + spin_unlock(&ext_devt_lock); } } @@ -665,7 +667,6 @@ void del_gendisk(struct gendisk *disk) sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk))); pm_runtime_set_memalloc_noio(disk_to_dev(disk), false); device_del(disk_to_dev(disk)); - blk_free_devt(disk_to_dev(disk)->devt); } EXPORT_SYMBOL(del_gendisk); @@ -690,13 +691,13 @@ struct gendisk *get_gendisk(dev_t devt, int *partno) } else { struct hd_struct *part; - mutex_lock(&ext_devt_mutex); + spin_lock(&ext_devt_lock); part = idr_find(&ext_devt_idr, blk_mangle_minor(MINOR(devt))); if (part && get_disk(part_to_disk(part))) { *partno = part->partno; disk = part_to_disk(part); } - mutex_unlock(&ext_devt_mutex); + spin_unlock(&ext_devt_lock); } return disk; @@ -1069,9 +1070,16 @@ int disk_expand_part_tbl(struct gendisk *disk, int partno) struct disk_part_tbl *old_ptbl = disk->part_tbl; struct disk_part_tbl *new_ptbl; int len = old_ptbl ? old_ptbl->len : 0; - int target = partno + 1; + int i, target; size_t size; - int i; + + /* + * check for int overflow, since we can get here from blkpg_ioctl() + * with a user passed 'partno'. + */ + target = partno + 1; + if (target < 0) + return -EINVAL; /* disk_max_parts() is zero during initialization, ignore if so */ if (disk_max_parts(disk) && target > disk_max_parts(disk)) @@ -1098,6 +1106,7 @@ static void disk_release(struct device *dev) { struct gendisk *disk = dev_to_disk(dev); + blk_free_devt(dev->devt); disk_release_events(disk); kfree(disk->random); disk_replace_part_tbl(disk, NULL); diff --git a/block/partition-generic.c b/block/partition-generic.c index 789cdea05893..0d9e5f97f0a8 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -211,6 +211,7 @@ static const struct attribute_group *part_attr_groups[] = { static void part_release(struct device *dev) { struct hd_struct *p = dev_to_part(dev); + blk_free_devt(dev->devt); free_part_stats(p); free_part_info(p); kfree(p); @@ -253,7 +254,6 @@ void delete_partition(struct gendisk *disk, int partno) rcu_assign_pointer(ptbl->last_lookup, NULL); kobject_put(part->holder_dir); device_del(part_to_dev(part)); - blk_free_devt(part_devt(part)); hd_struct_put(part); } diff --git a/block/partitions/aix.c b/block/partitions/aix.c index 43be471d9b1d..0931f5136ab2 100644 --- a/block/partitions/aix.c +++ b/block/partitions/aix.c @@ -253,7 +253,7 @@ int aix_partition(struct parsed_partitions *state) continue; } lv_ix = be16_to_cpu(p->lv_ix) - 1; - if (lv_ix > state->limit) { + if (lv_ix >= state->limit) { cur_lv_ix = -1; continue; } diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index 26487972ac54..4044cf789c7a 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -489,7 +489,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, __GFP_WAIT)) { err = DRIVER_ERROR << 24; - goto out; + goto error; } memset(sense, 0, sizeof(sense)); @@ -499,7 +499,6 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, blk_execute_rq(q, disk, rq, 0); -out: err = rq->errors & 0xff; /* only 8 bit SCSI status */ if (err) { if (rq->sense_len && rq->sense) { diff --git a/crypto/842.c b/crypto/842.c index 65c7a89cfa09..b48f4f108c47 100644 --- a/crypto/842.c +++ b/crypto/842.c @@ -180,3 +180,4 @@ module_exit(nx842_mod_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("842 Compression Algorithm"); +MODULE_ALIAS_CRYPTO("842"); diff --git a/crypto/aes_generic.c b/crypto/aes_generic.c index fd0d6b454975..3dd101144a58 100644 --- a/crypto/aes_generic.c +++ b/crypto/aes_generic.c @@ -1474,4 +1474,5 @@ module_exit(aes_fini); MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm"); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_ALIAS("aes"); +MODULE_ALIAS_CRYPTO("aes"); +MODULE_ALIAS_CRYPTO("aes-generic"); diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 6a3ad8011585..1de4beeb25f8 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -449,6 +449,9 @@ void af_alg_complete(struct crypto_async_request *req, int err) { struct af_alg_completion *completion = req->data; + if (err == -EINPROGRESS) + return; + completion->err = err; complete(&completion->completion); } diff --git a/crypto/algapi.c b/crypto/algapi.c index 7a1ae87f1683..00d8d939733b 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -495,8 +495,8 @@ static struct crypto_template *__crypto_lookup_template(const char *name) struct crypto_template *crypto_lookup_template(const char *name) { - return try_then_request_module(__crypto_lookup_template(name), "%s", - name); + return try_then_request_module(__crypto_lookup_template(name), + "crypto-%s", name); } EXPORT_SYMBOL_GPL(crypto_lookup_template); diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index a19c027b29bd..83187f497c7c 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -49,7 +49,7 @@ struct skcipher_ctx { struct ablkcipher_request req; }; -#define MAX_SGL_ENTS ((PAGE_SIZE - sizeof(struct skcipher_sg_list)) / \ +#define MAX_SGL_ENTS ((4096 - sizeof(struct skcipher_sg_list)) / \ sizeof(struct scatterlist) - 1) static inline int skcipher_sndbuf(struct sock *sk) diff --git a/crypto/ansi_cprng.c b/crypto/ansi_cprng.c index 666f1962a160..6f5bebc9bf01 100644 --- a/crypto/ansi_cprng.c +++ b/crypto/ansi_cprng.c @@ -476,4 +476,5 @@ module_param(dbg, int, 0); MODULE_PARM_DESC(dbg, "Boolean to enable debugging (0/1 == off/on)"); module_init(prng_mod_init); module_exit(prng_mod_fini); -MODULE_ALIAS("stdrng"); +MODULE_ALIAS_CRYPTO("stdrng"); +MODULE_ALIAS_CRYPTO("ansi_cprng"); diff --git a/crypto/anubis.c b/crypto/anubis.c index 008c8a4fb67c..4bb187c2a902 100644 --- a/crypto/anubis.c +++ b/crypto/anubis.c @@ -704,3 +704,4 @@ module_exit(anubis_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Anubis Cryptographic Algorithm"); +MODULE_ALIAS_CRYPTO("anubis"); diff --git a/crypto/api.c b/crypto/api.c index a2b39c5f3649..2a81e98a0021 100644 --- a/crypto/api.c +++ b/crypto/api.c @@ -216,11 +216,11 @@ struct crypto_alg *crypto_larval_lookup(const char *name, u32 type, u32 mask) alg = crypto_alg_lookup(name, type, mask); if (!alg) { - request_module("%s", name); + request_module("crypto-%s", name); if (!((type ^ CRYPTO_ALG_NEED_FALLBACK) & mask & CRYPTO_ALG_NEED_FALLBACK)) - request_module("%s-all", name); + request_module("crypto-%s-all", name); alg = crypto_alg_lookup(name, type, mask); } diff --git a/crypto/arc4.c b/crypto/arc4.c index 5a772c3657d5..f1a81925558f 100644 --- a/crypto/arc4.c +++ b/crypto/arc4.c @@ -166,3 +166,4 @@ module_exit(arc4_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("ARC4 Cipher Algorithm"); MODULE_AUTHOR("Jon Oberheide <jon@oberheide.org>"); +MODULE_ALIAS_CRYPTO("arc4"); diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c index 3c562f5a60bb..e1bce26cd4f9 100644 --- a/crypto/async_tx/async_xor.c +++ b/crypto/async_tx/async_xor.c @@ -78,8 +78,6 @@ do_async_xor(struct dma_chan *chan, struct dmaengine_unmap_data *unmap, tx = dma->device_prep_dma_xor(chan, dma_dest, src_list, xor_src_cnt, unmap->len, dma_flags); - src_list[0] = tmp; - if (unlikely(!tx)) async_tx_quiesce(&submit->depend_tx); @@ -92,6 +90,7 @@ do_async_xor(struct dma_chan *chan, struct dmaengine_unmap_data *unmap, xor_src_cnt, unmap->len, dma_flags); } + src_list[0] = tmp; dma_set_unmap(tx, unmap); async_tx_submit(chan, tx, submit); diff --git a/crypto/authenc.c b/crypto/authenc.c index e1223559d5df..78fb16cab13f 100644 --- a/crypto/authenc.c +++ b/crypto/authenc.c @@ -721,3 +721,4 @@ module_exit(crypto_authenc_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Simple AEAD wrapper for IPsec"); +MODULE_ALIAS_CRYPTO("authenc"); diff --git a/crypto/authencesn.c b/crypto/authencesn.c index 4be0dd4373a9..024bff2344fc 100644 --- a/crypto/authencesn.c +++ b/crypto/authencesn.c @@ -814,3 +814,4 @@ module_exit(crypto_authenc_esn_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>"); MODULE_DESCRIPTION("AEAD wrapper for IPsec with extended sequence numbers"); +MODULE_ALIAS_CRYPTO("authencesn"); diff --git a/crypto/blowfish_generic.c b/crypto/blowfish_generic.c index 8baf5447d35b..87b392a77a93 100644 --- a/crypto/blowfish_generic.c +++ b/crypto/blowfish_generic.c @@ -138,4 +138,5 @@ module_exit(blowfish_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Blowfish Cipher Algorithm"); -MODULE_ALIAS("blowfish"); +MODULE_ALIAS_CRYPTO("blowfish"); +MODULE_ALIAS_CRYPTO("blowfish-generic"); diff --git a/crypto/camellia_generic.c b/crypto/camellia_generic.c index 26bcd7a2d6b4..a02286bf319e 100644 --- a/crypto/camellia_generic.c +++ b/crypto/camellia_generic.c @@ -1098,4 +1098,5 @@ module_exit(camellia_fini); MODULE_DESCRIPTION("Camellia Cipher Algorithm"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("camellia"); +MODULE_ALIAS_CRYPTO("camellia"); +MODULE_ALIAS_CRYPTO("camellia-generic"); diff --git a/crypto/cast5_generic.c b/crypto/cast5_generic.c index 5558f630a0eb..df5c72629383 100644 --- a/crypto/cast5_generic.c +++ b/crypto/cast5_generic.c @@ -549,4 +549,5 @@ module_exit(cast5_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Cast5 Cipher Algorithm"); -MODULE_ALIAS("cast5"); +MODULE_ALIAS_CRYPTO("cast5"); +MODULE_ALIAS_CRYPTO("cast5-generic"); diff --git a/crypto/cast6_generic.c b/crypto/cast6_generic.c index de732528a430..058c8d755d03 100644 --- a/crypto/cast6_generic.c +++ b/crypto/cast6_generic.c @@ -291,4 +291,5 @@ module_exit(cast6_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Cast6 Cipher Algorithm"); -MODULE_ALIAS("cast6"); +MODULE_ALIAS_CRYPTO("cast6"); +MODULE_ALIAS_CRYPTO("cast6-generic"); diff --git a/crypto/cbc.c b/crypto/cbc.c index 61ac42e1e32b..780ee27b2d43 100644 --- a/crypto/cbc.c +++ b/crypto/cbc.c @@ -289,3 +289,4 @@ module_exit(crypto_cbc_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("CBC block cipher algorithm"); +MODULE_ALIAS_CRYPTO("cbc"); diff --git a/crypto/ccm.c b/crypto/ccm.c index 1df84217f7c9..003bbbd21a2b 100644 --- a/crypto/ccm.c +++ b/crypto/ccm.c @@ -879,5 +879,6 @@ module_exit(crypto_ccm_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Counter with CBC MAC"); -MODULE_ALIAS("ccm_base"); -MODULE_ALIAS("rfc4309"); +MODULE_ALIAS_CRYPTO("ccm_base"); +MODULE_ALIAS_CRYPTO("rfc4309"); +MODULE_ALIAS_CRYPTO("ccm"); diff --git a/crypto/chainiv.c b/crypto/chainiv.c index 834d8dd3d4fc..22b7e55b0e1b 100644 --- a/crypto/chainiv.c +++ b/crypto/chainiv.c @@ -359,3 +359,4 @@ module_exit(chainiv_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Chain IV Generator"); +MODULE_ALIAS_CRYPTO("chainiv"); diff --git a/crypto/cmac.c b/crypto/cmac.c index 50880cf17fad..7a8bfbd548f6 100644 --- a/crypto/cmac.c +++ b/crypto/cmac.c @@ -313,3 +313,4 @@ module_exit(crypto_cmac_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("CMAC keyed hash algorithm"); +MODULE_ALIAS_CRYPTO("cmac"); diff --git a/crypto/crc32.c b/crypto/crc32.c index 9d1c41569898..187ded28cb0b 100644 --- a/crypto/crc32.c +++ b/crypto/crc32.c @@ -156,3 +156,4 @@ module_exit(crc32_mod_fini); MODULE_AUTHOR("Alexander Boyko <alexander_boyko@xyratex.com>"); MODULE_DESCRIPTION("CRC32 calculations wrapper for lib/crc32"); MODULE_LICENSE("GPL"); +MODULE_ALIAS_CRYPTO("crc32"); diff --git a/crypto/crc32c.c b/crypto/crc32c.c index 06f7018c9d95..238f0e627ef3 100644 --- a/crypto/crc32c.c +++ b/crypto/crc32c.c @@ -170,3 +170,4 @@ module_exit(crc32c_mod_fini); MODULE_AUTHOR("Clay Haapala <chaapala@cisco.com>"); MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations wrapper for lib/crc32c"); MODULE_LICENSE("GPL"); +MODULE_ALIAS_CRYPTO("crc32c"); diff --git a/crypto/crct10dif_generic.c b/crypto/crct10dif_generic.c index 877e7114ec5c..c1229614c7e3 100644 --- a/crypto/crct10dif_generic.c +++ b/crypto/crct10dif_generic.c @@ -124,4 +124,5 @@ module_exit(crct10dif_mod_fini); MODULE_AUTHOR("Tim Chen <tim.c.chen@linux.intel.com>"); MODULE_DESCRIPTION("T10 DIF CRC calculation."); MODULE_LICENSE("GPL"); -MODULE_ALIAS("crct10dif"); +MODULE_ALIAS_CRYPTO("crct10dif"); +MODULE_ALIAS_CRYPTO("crct10dif-generic"); diff --git a/crypto/cryptd.c b/crypto/cryptd.c index 7bdd61b867c8..75c415d37086 100644 --- a/crypto/cryptd.c +++ b/crypto/cryptd.c @@ -955,3 +955,4 @@ module_exit(cryptd_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Software async crypto daemon"); +MODULE_ALIAS_CRYPTO("cryptd"); diff --git a/crypto/crypto_null.c b/crypto/crypto_null.c index fee7265cd35d..7b39fa3deac2 100644 --- a/crypto/crypto_null.c +++ b/crypto/crypto_null.c @@ -149,9 +149,9 @@ static struct crypto_alg null_algs[3] = { { .coa_decompress = null_compress } } } }; -MODULE_ALIAS("compress_null"); -MODULE_ALIAS("digest_null"); -MODULE_ALIAS("cipher_null"); +MODULE_ALIAS_CRYPTO("compress_null"); +MODULE_ALIAS_CRYPTO("digest_null"); +MODULE_ALIAS_CRYPTO("cipher_null"); static int __init crypto_null_mod_init(void) { diff --git a/crypto/ctr.c b/crypto/ctr.c index f2b94f27bb2c..2386f7313952 100644 --- a/crypto/ctr.c +++ b/crypto/ctr.c @@ -466,4 +466,5 @@ module_exit(crypto_ctr_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("CTR Counter block mode"); -MODULE_ALIAS("rfc3686"); +MODULE_ALIAS_CRYPTO("rfc3686"); +MODULE_ALIAS_CRYPTO("ctr"); diff --git a/crypto/cts.c b/crypto/cts.c index 042223f8e733..60b9da3fa7c1 100644 --- a/crypto/cts.c +++ b/crypto/cts.c @@ -350,3 +350,4 @@ module_exit(crypto_cts_module_exit); MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION("CTS-CBC CipherText Stealing for CBC"); +MODULE_ALIAS_CRYPTO("cts"); diff --git a/crypto/deflate.c b/crypto/deflate.c index b57d70eb156b..95d8d37c5021 100644 --- a/crypto/deflate.c +++ b/crypto/deflate.c @@ -222,4 +222,4 @@ module_exit(deflate_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Deflate Compression Algorithm for IPCOMP"); MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>"); - +MODULE_ALIAS_CRYPTO("deflate"); diff --git a/crypto/des_generic.c b/crypto/des_generic.c index f6cf63f88468..3ec6071309d9 100644 --- a/crypto/des_generic.c +++ b/crypto/des_generic.c @@ -971,8 +971,6 @@ static struct crypto_alg des_algs[2] = { { .cia_decrypt = des3_ede_decrypt } } } }; -MODULE_ALIAS("des3_ede"); - static int __init des_generic_mod_init(void) { return crypto_register_algs(des_algs, ARRAY_SIZE(des_algs)); @@ -989,4 +987,7 @@ module_exit(des_generic_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("DES & Triple DES EDE Cipher Algorithms"); MODULE_AUTHOR("Dag Arne Osvik <da@osvik.no>"); -MODULE_ALIAS("des"); +MODULE_ALIAS_CRYPTO("des"); +MODULE_ALIAS_CRYPTO("des-generic"); +MODULE_ALIAS_CRYPTO("des3_ede"); +MODULE_ALIAS_CRYPTO("des3_ede-generic"); diff --git a/crypto/ecb.c b/crypto/ecb.c index 935cfef4aa84..12011aff0971 100644 --- a/crypto/ecb.c +++ b/crypto/ecb.c @@ -185,3 +185,4 @@ module_exit(crypto_ecb_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("ECB block cipher algorithm"); +MODULE_ALIAS_CRYPTO("ecb"); diff --git a/crypto/eseqiv.c b/crypto/eseqiv.c index 42ce9f570aec..388f582ab0b9 100644 --- a/crypto/eseqiv.c +++ b/crypto/eseqiv.c @@ -267,3 +267,4 @@ module_exit(eseqiv_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Encrypted Sequence Number IV Generator"); +MODULE_ALIAS_CRYPTO("eseqiv"); diff --git a/crypto/fcrypt.c b/crypto/fcrypt.c index 021d7fec6bc8..77286ea28865 100644 --- a/crypto/fcrypt.c +++ b/crypto/fcrypt.c @@ -420,3 +420,4 @@ module_exit(fcrypt_mod_fini); MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION("FCrypt Cipher Algorithm"); MODULE_AUTHOR("David Howells <dhowells@redhat.com>"); +MODULE_ALIAS_CRYPTO("fcrypt"); diff --git a/crypto/gcm.c b/crypto/gcm.c index b4f017939004..9cea4d0b6904 100644 --- a/crypto/gcm.c +++ b/crypto/gcm.c @@ -1441,6 +1441,7 @@ module_exit(crypto_gcm_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Galois/Counter Mode"); MODULE_AUTHOR("Mikko Herranen <mh1@iki.fi>"); -MODULE_ALIAS("gcm_base"); -MODULE_ALIAS("rfc4106"); -MODULE_ALIAS("rfc4543"); +MODULE_ALIAS_CRYPTO("gcm_base"); +MODULE_ALIAS_CRYPTO("rfc4106"); +MODULE_ALIAS_CRYPTO("rfc4543"); +MODULE_ALIAS_CRYPTO("gcm"); diff --git a/crypto/ghash-generic.c b/crypto/ghash-generic.c index 9d3f0c69a86f..bac70995e064 100644 --- a/crypto/ghash-generic.c +++ b/crypto/ghash-generic.c @@ -172,4 +172,5 @@ module_exit(ghash_mod_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("GHASH Message Digest Algorithm"); -MODULE_ALIAS("ghash"); +MODULE_ALIAS_CRYPTO("ghash"); +MODULE_ALIAS_CRYPTO("ghash-generic"); diff --git a/crypto/hmac.c b/crypto/hmac.c index 8d9544cf8169..ade790b454e9 100644 --- a/crypto/hmac.c +++ b/crypto/hmac.c @@ -271,3 +271,4 @@ module_exit(hmac_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("HMAC hash algorithm"); +MODULE_ALIAS_CRYPTO("hmac"); diff --git a/crypto/khazad.c b/crypto/khazad.c index 60e7cd66facc..873eb5ded6d7 100644 --- a/crypto/khazad.c +++ b/crypto/khazad.c @@ -880,3 +880,4 @@ module_exit(khazad_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Khazad Cryptographic Algorithm"); +MODULE_ALIAS_CRYPTO("khazad"); diff --git a/crypto/krng.c b/crypto/krng.c index a2d2b72fc135..0224841b6579 100644 --- a/crypto/krng.c +++ b/crypto/krng.c @@ -62,4 +62,5 @@ module_exit(krng_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Kernel Random Number Generator"); -MODULE_ALIAS("stdrng"); +MODULE_ALIAS_CRYPTO("stdrng"); +MODULE_ALIAS_CRYPTO("krng"); diff --git a/crypto/lrw.c b/crypto/lrw.c index ba42acc4deba..6f9908a7ebcb 100644 --- a/crypto/lrw.c +++ b/crypto/lrw.c @@ -400,3 +400,4 @@ module_exit(crypto_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("LRW block cipher mode"); +MODULE_ALIAS_CRYPTO("lrw"); diff --git a/crypto/lz4.c b/crypto/lz4.c index 4586dd15b0d8..53279ab8c3a6 100644 --- a/crypto/lz4.c +++ b/crypto/lz4.c @@ -104,3 +104,4 @@ module_exit(lz4_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("LZ4 Compression Algorithm"); +MODULE_ALIAS_CRYPTO("lz4"); diff --git a/crypto/lz4hc.c b/crypto/lz4hc.c index 151ba31d34e3..eaec5fa3debf 100644 --- a/crypto/lz4hc.c +++ b/crypto/lz4hc.c @@ -104,3 +104,4 @@ module_exit(lz4hc_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("LZ4HC Compression Algorithm"); +MODULE_ALIAS_CRYPTO("lz4hc"); diff --git a/crypto/lzo.c b/crypto/lzo.c index 1c2aa69c54b8..d1ff69404353 100644 --- a/crypto/lzo.c +++ b/crypto/lzo.c @@ -103,3 +103,4 @@ module_exit(lzo_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("LZO Compression Algorithm"); +MODULE_ALIAS_CRYPTO("lzo"); diff --git a/crypto/md4.c b/crypto/md4.c index 0477a6a01d58..3515af425cc9 100644 --- a/crypto/md4.c +++ b/crypto/md4.c @@ -255,4 +255,4 @@ module_exit(md4_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("MD4 Message Digest Algorithm"); - +MODULE_ALIAS_CRYPTO("md4"); diff --git a/crypto/md5.c b/crypto/md5.c index 7febeaab923b..36f5e5b103f3 100644 --- a/crypto/md5.c +++ b/crypto/md5.c @@ -168,3 +168,4 @@ module_exit(md5_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("MD5 Message Digest Algorithm"); +MODULE_ALIAS_CRYPTO("md5"); diff --git a/crypto/michael_mic.c b/crypto/michael_mic.c index 079b761bc70d..46195e0d0f4d 100644 --- a/crypto/michael_mic.c +++ b/crypto/michael_mic.c @@ -184,3 +184,4 @@ module_exit(michael_mic_exit); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("Michael MIC"); MODULE_AUTHOR("Jouni Malinen <j@w1.fi>"); +MODULE_ALIAS_CRYPTO("michael_mic"); diff --git a/crypto/pcbc.c b/crypto/pcbc.c index d1b8bdfb5855..f654965f0933 100644 --- a/crypto/pcbc.c +++ b/crypto/pcbc.c @@ -295,3 +295,4 @@ module_exit(crypto_pcbc_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("PCBC block cipher algorithm"); +MODULE_ALIAS_CRYPTO("pcbc"); diff --git a/crypto/pcrypt.c b/crypto/pcrypt.c index 309d345ead95..c305d4112735 100644 --- a/crypto/pcrypt.c +++ b/crypto/pcrypt.c @@ -565,3 +565,4 @@ module_exit(pcrypt_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>"); MODULE_DESCRIPTION("Parallel crypto wrapper"); +MODULE_ALIAS_CRYPTO("pcrypt"); diff --git a/crypto/rmd128.c b/crypto/rmd128.c index 8a0f68b7f257..049486ede938 100644 --- a/crypto/rmd128.c +++ b/crypto/rmd128.c @@ -327,3 +327,4 @@ module_exit(rmd128_mod_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>"); MODULE_DESCRIPTION("RIPEMD-128 Message Digest"); +MODULE_ALIAS_CRYPTO("rmd128"); diff --git a/crypto/rmd160.c b/crypto/rmd160.c index 525d7bb752cf..de585e51d455 100644 --- a/crypto/rmd160.c +++ b/crypto/rmd160.c @@ -371,3 +371,4 @@ module_exit(rmd160_mod_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>"); MODULE_DESCRIPTION("RIPEMD-160 Message Digest"); +MODULE_ALIAS_CRYPTO("rmd160"); diff --git a/crypto/rmd256.c b/crypto/rmd256.c index 69293d9b56e0..4ec02a754e09 100644 --- a/crypto/rmd256.c +++ b/crypto/rmd256.c @@ -346,3 +346,4 @@ module_exit(rmd256_mod_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>"); MODULE_DESCRIPTION("RIPEMD-256 Message Digest"); +MODULE_ALIAS_CRYPTO("rmd256"); diff --git a/crypto/rmd320.c b/crypto/rmd320.c index 09f97dfdfbba..770f2cb369f8 100644 --- a/crypto/rmd320.c +++ b/crypto/rmd320.c @@ -395,3 +395,4 @@ module_exit(rmd320_mod_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>"); MODULE_DESCRIPTION("RIPEMD-320 Message Digest"); +MODULE_ALIAS_CRYPTO("rmd320"); diff --git a/crypto/salsa20_generic.c b/crypto/salsa20_generic.c index 9a4770c02284..f550b5d94630 100644 --- a/crypto/salsa20_generic.c +++ b/crypto/salsa20_generic.c @@ -248,4 +248,5 @@ module_exit(salsa20_generic_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION ("Salsa20 stream cipher algorithm"); -MODULE_ALIAS("salsa20"); +MODULE_ALIAS_CRYPTO("salsa20"); +MODULE_ALIAS_CRYPTO("salsa20-generic"); diff --git a/crypto/seed.c b/crypto/seed.c index 9c904d6d2151..c6ba8438be43 100644 --- a/crypto/seed.c +++ b/crypto/seed.c @@ -476,3 +476,4 @@ module_exit(seed_fini); MODULE_DESCRIPTION("SEED Cipher Algorithm"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Hye-Shik Chang <perky@FreeBSD.org>, Kim Hyun <hkim@kisa.or.kr>"); +MODULE_ALIAS_CRYPTO("seed"); diff --git a/crypto/seqiv.c b/crypto/seqiv.c index f2cba4ed6f25..49a4069ff453 100644 --- a/crypto/seqiv.c +++ b/crypto/seqiv.c @@ -362,3 +362,4 @@ module_exit(seqiv_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Sequence Number IV Generator"); +MODULE_ALIAS_CRYPTO("seqiv"); diff --git a/crypto/serpent_generic.c b/crypto/serpent_generic.c index 7ddbd7e88859..94970a794975 100644 --- a/crypto/serpent_generic.c +++ b/crypto/serpent_generic.c @@ -665,5 +665,6 @@ module_exit(serpent_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Serpent and tnepres (kerneli compatible serpent reversed) Cipher Algorithm"); MODULE_AUTHOR("Dag Arne Osvik <osvik@ii.uib.no>"); -MODULE_ALIAS("tnepres"); -MODULE_ALIAS("serpent"); +MODULE_ALIAS_CRYPTO("tnepres"); +MODULE_ALIAS_CRYPTO("serpent"); +MODULE_ALIAS_CRYPTO("serpent-generic"); diff --git a/crypto/sha1_generic.c b/crypto/sha1_generic.c index 42794803c480..fdf7c00de4b0 100644 --- a/crypto/sha1_generic.c +++ b/crypto/sha1_generic.c @@ -153,4 +153,5 @@ module_exit(sha1_generic_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm"); -MODULE_ALIAS("sha1"); +MODULE_ALIAS_CRYPTO("sha1"); +MODULE_ALIAS_CRYPTO("sha1-generic"); diff --git a/crypto/sha256_generic.c b/crypto/sha256_generic.c index 543366779524..136381bdd48d 100644 --- a/crypto/sha256_generic.c +++ b/crypto/sha256_generic.c @@ -384,5 +384,7 @@ module_exit(sha256_generic_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA-224 and SHA-256 Secure Hash Algorithm"); -MODULE_ALIAS("sha224"); -MODULE_ALIAS("sha256"); +MODULE_ALIAS_CRYPTO("sha224"); +MODULE_ALIAS_CRYPTO("sha224-generic"); +MODULE_ALIAS_CRYPTO("sha256"); +MODULE_ALIAS_CRYPTO("sha256-generic"); diff --git a/crypto/sha512_generic.c b/crypto/sha512_generic.c index 6ed124f3ea0f..6c6d901a7cc1 100644 --- a/crypto/sha512_generic.c +++ b/crypto/sha512_generic.c @@ -287,5 +287,7 @@ module_exit(sha512_generic_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA-512 and SHA-384 Secure Hash Algorithms"); -MODULE_ALIAS("sha384"); -MODULE_ALIAS("sha512"); +MODULE_ALIAS_CRYPTO("sha384"); +MODULE_ALIAS_CRYPTO("sha384-generic"); +MODULE_ALIAS_CRYPTO("sha512"); +MODULE_ALIAS_CRYPTO("sha512-generic"); diff --git a/crypto/tea.c b/crypto/tea.c index 0a572323ee4a..b70b441c7d1e 100644 --- a/crypto/tea.c +++ b/crypto/tea.c @@ -270,8 +270,9 @@ static void __exit tea_mod_fini(void) crypto_unregister_algs(tea_algs, ARRAY_SIZE(tea_algs)); } -MODULE_ALIAS("xtea"); -MODULE_ALIAS("xeta"); +MODULE_ALIAS_CRYPTO("tea"); +MODULE_ALIAS_CRYPTO("xtea"); +MODULE_ALIAS_CRYPTO("xeta"); module_init(tea_mod_init); module_exit(tea_mod_fini); diff --git a/crypto/tgr192.c b/crypto/tgr192.c index 87403556fd0b..f7ed2fba396c 100644 --- a/crypto/tgr192.c +++ b/crypto/tgr192.c @@ -676,8 +676,9 @@ static void __exit tgr192_mod_fini(void) crypto_unregister_shashes(tgr_algs, ARRAY_SIZE(tgr_algs)); } -MODULE_ALIAS("tgr160"); -MODULE_ALIAS("tgr128"); +MODULE_ALIAS_CRYPTO("tgr192"); +MODULE_ALIAS_CRYPTO("tgr160"); +MODULE_ALIAS_CRYPTO("tgr128"); module_init(tgr192_mod_init); module_exit(tgr192_mod_fini); diff --git a/crypto/twofish_generic.c b/crypto/twofish_generic.c index 2d5000552d0f..ebf7a3efb572 100644 --- a/crypto/twofish_generic.c +++ b/crypto/twofish_generic.c @@ -211,4 +211,5 @@ module_exit(twofish_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION ("Twofish Cipher Algorithm"); -MODULE_ALIAS("twofish"); +MODULE_ALIAS_CRYPTO("twofish"); +MODULE_ALIAS_CRYPTO("twofish-generic"); diff --git a/crypto/vmac.c b/crypto/vmac.c index 2eb11a30c29c..bf2d3a89845f 100644 --- a/crypto/vmac.c +++ b/crypto/vmac.c @@ -713,3 +713,4 @@ module_exit(vmac_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("VMAC hash algorithm"); +MODULE_ALIAS_CRYPTO("vmac"); diff --git a/crypto/wp512.c b/crypto/wp512.c index 180f1d6e03f4..253db94b5479 100644 --- a/crypto/wp512.c +++ b/crypto/wp512.c @@ -1167,8 +1167,9 @@ static void __exit wp512_mod_fini(void) crypto_unregister_shashes(wp_algs, ARRAY_SIZE(wp_algs)); } -MODULE_ALIAS("wp384"); -MODULE_ALIAS("wp256"); +MODULE_ALIAS_CRYPTO("wp512"); +MODULE_ALIAS_CRYPTO("wp384"); +MODULE_ALIAS_CRYPTO("wp256"); module_init(wp512_mod_init); module_exit(wp512_mod_fini); diff --git a/crypto/xcbc.c b/crypto/xcbc.c index a5fbdf3738cf..df90b332554c 100644 --- a/crypto/xcbc.c +++ b/crypto/xcbc.c @@ -286,3 +286,4 @@ module_exit(crypto_xcbc_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("XCBC keyed hash algorithm"); +MODULE_ALIAS_CRYPTO("xcbc"); diff --git a/crypto/xts.c b/crypto/xts.c index ca1608f44cb5..f6fd43f100c8 100644 --- a/crypto/xts.c +++ b/crypto/xts.c @@ -362,3 +362,4 @@ module_exit(crypto_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("XTS block cipher mode"); +MODULE_ALIAS_CRYPTO("xts"); diff --git a/crypto/zlib.c b/crypto/zlib.c index 06b62e5cdcc7..d98078835281 100644 --- a/crypto/zlib.c +++ b/crypto/zlib.c @@ -378,3 +378,4 @@ module_exit(zlib_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Zlib Compression Algorithm"); MODULE_AUTHOR("Sony Corporation"); +MODULE_ALIAS_CRYPTO("zlib"); diff --git a/drivers/Makefile b/drivers/Makefile index 7edd884f2b5a..5bf13fd5ad65 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -157,3 +157,4 @@ obj-$(CONFIG_FMC) += fmc/ obj-$(CONFIG_POWERCAP) += powercap/ obj-$(CONFIG_GATOR) += gator/ +obj-$(CONFIG_CORESIGHT) += coresight/ diff --git a/drivers/acpi/acpi_cmos_rtc.c b/drivers/acpi/acpi_cmos_rtc.c index 84190ed89c04..aff69d9bfcbf 100644 --- a/drivers/acpi/acpi_cmos_rtc.c +++ b/drivers/acpi/acpi_cmos_rtc.c @@ -35,7 +35,7 @@ acpi_cmos_rtc_space_handler(u32 function, acpi_physical_address address, void *handler_context, void *region_context) { int i; - u8 *value = (u8 *)&value64; + u8 *value = (u8 *)value64; if (address > 0xff || !value64) return AE_BAD_PARAMETER; diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h index d95ca5449ace..e6ab104afe42 100644 --- a/drivers/acpi/acpica/aclocal.h +++ b/drivers/acpi/acpica/aclocal.h @@ -254,6 +254,7 @@ struct acpi_create_field_info { u32 field_bit_position; u32 field_bit_length; u16 resource_length; + u16 pin_number_index; u8 field_flags; u8 attribute; u8 field_type; diff --git a/drivers/acpi/acpica/acobject.h b/drivers/acpi/acpica/acobject.h index cc7ab6dd724e..a47cc78ffd4f 100644 --- a/drivers/acpi/acpica/acobject.h +++ b/drivers/acpi/acpica/acobject.h @@ -263,6 +263,7 @@ struct acpi_object_region_field { ACPI_OBJECT_COMMON_HEADER ACPI_COMMON_FIELD_INFO u16 resource_length; union acpi_operand_object *region_obj; /* Containing op_region object */ u8 *resource_buffer; /* resource_template for serial regions/fields */ + u16 pin_number_index; /* Index relative to previous Connection/Template */ }; struct acpi_object_bank_field { diff --git a/drivers/acpi/acpica/dsfield.c b/drivers/acpi/acpica/dsfield.c index e7a57c554e84..9af55bd6c4d7 100644 --- a/drivers/acpi/acpica/dsfield.c +++ b/drivers/acpi/acpica/dsfield.c @@ -360,6 +360,7 @@ acpi_ds_get_field_names(struct acpi_create_field_info *info, */ info->resource_buffer = NULL; info->connection_node = NULL; + info->pin_number_index = 0; /* * A Connection() is either an actual resource descriptor (buffer) @@ -437,6 +438,7 @@ acpi_ds_get_field_names(struct acpi_create_field_info *info, } info->field_bit_position += info->field_bit_length; + info->pin_number_index++; /* Index relative to previous Connection() */ break; default: diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c index 144cbb9b73bc..cd4b231ae760 100644 --- a/drivers/acpi/acpica/evregion.c +++ b/drivers/acpi/acpica/evregion.c @@ -142,6 +142,7 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj, union acpi_operand_object *region_obj2; void *region_context = NULL; struct acpi_connection_info *context; + acpi_physical_address address; ACPI_FUNCTION_TRACE(ev_address_space_dispatch); @@ -231,25 +232,23 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj, /* We have everything we need, we can invoke the address space handler */ handler = handler_desc->address_space.handler; - - ACPI_DEBUG_PRINT((ACPI_DB_OPREGION, - "Handler %p (@%p) Address %8.8X%8.8X [%s]\n", - ®ion_obj->region.handler->address_space, handler, - ACPI_FORMAT_NATIVE_UINT(region_obj->region.address + - region_offset), - acpi_ut_get_region_name(region_obj->region. - space_id))); + address = (region_obj->region.address + region_offset); /* * Special handling for generic_serial_bus and general_purpose_io: * There are three extra parameters that must be passed to the * handler via the context: - * 1) Connection buffer, a resource template from Connection() op. - * 2) Length of the above buffer. - * 3) Actual access length from the access_as() op. + * 1) Connection buffer, a resource template from Connection() op + * 2) Length of the above buffer + * 3) Actual access length from the access_as() op + * + * In addition, for general_purpose_io, the Address and bit_width fields + * are defined as follows: + * 1) Address is the pin number index of the field (bit offset from + * the previous Connection) + * 2) bit_width is the actual bit length of the field (number of pins) */ - if (((region_obj->region.space_id == ACPI_ADR_SPACE_GSBUS) || - (region_obj->region.space_id == ACPI_ADR_SPACE_GPIO)) && + if ((region_obj->region.space_id == ACPI_ADR_SPACE_GSBUS) && context && field_obj) { /* Get the Connection (resource_template) buffer */ @@ -258,6 +257,24 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj, context->length = field_obj->field.resource_length; context->access_length = field_obj->field.access_length; } + if ((region_obj->region.space_id == ACPI_ADR_SPACE_GPIO) && + context && field_obj) { + + /* Get the Connection (resource_template) buffer */ + + context->connection = field_obj->field.resource_buffer; + context->length = field_obj->field.resource_length; + context->access_length = field_obj->field.access_length; + address = field_obj->field.pin_number_index; + bit_width = field_obj->field.bit_length; + } + + ACPI_DEBUG_PRINT((ACPI_DB_OPREGION, + "Handler %p (@%p) Address %8.8X%8.8X [%s]\n", + ®ion_obj->region.handler->address_space, handler, + ACPI_FORMAT_NATIVE_UINT(address), + acpi_ut_get_region_name(region_obj->region. + space_id))); if (!(handler_desc->address_space.handler_flags & ACPI_ADDR_HANDLER_DEFAULT_INSTALLED)) { @@ -271,9 +288,7 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj, /* Call the handler */ - status = handler(function, - (region_obj->region.address + region_offset), - bit_width, value, context, + status = handler(function, address, bit_width, value, context, region_obj2->extra.region_context); if (ACPI_FAILURE(status)) { diff --git a/drivers/acpi/acpica/exfield.c b/drivers/acpi/acpica/exfield.c index cfd875243421..d36894a228b1 100644 --- a/drivers/acpi/acpica/exfield.c +++ b/drivers/acpi/acpica/exfield.c @@ -178,6 +178,37 @@ acpi_ex_read_data_from_field(struct acpi_walk_state *walk_state, buffer = &buffer_desc->integer.value; } + if ((obj_desc->common.type == ACPI_TYPE_LOCAL_REGION_FIELD) && + (obj_desc->field.region_obj->region.space_id == + ACPI_ADR_SPACE_GPIO)) { + /* + * For GPIO (general_purpose_io), the Address will be the bit offset + * from the previous Connection() operator, making it effectively a + * pin number index. The bit_length is the length of the field, which + * is thus the number of pins. + */ + ACPI_DEBUG_PRINT((ACPI_DB_BFIELD, + "GPIO FieldRead [FROM]: Pin %u Bits %u\n", + obj_desc->field.pin_number_index, + obj_desc->field.bit_length)); + + /* Lock entire transaction if requested */ + + acpi_ex_acquire_global_lock(obj_desc->common_field.field_flags); + + /* Perform the write */ + + status = acpi_ex_access_region(obj_desc, 0, + (u64 *)buffer, ACPI_READ); + acpi_ex_release_global_lock(obj_desc->common_field.field_flags); + if (ACPI_FAILURE(status)) { + acpi_ut_remove_reference(buffer_desc); + } else { + *ret_buffer_desc = buffer_desc; + } + return_ACPI_STATUS(status); + } + ACPI_DEBUG_PRINT((ACPI_DB_BFIELD, "FieldRead [TO]: Obj %p, Type %X, Buf %p, ByteLen %X\n", obj_desc, obj_desc->common.type, buffer, @@ -325,6 +356,42 @@ acpi_ex_write_data_to_field(union acpi_operand_object *source_desc, *result_desc = buffer_desc; return_ACPI_STATUS(status); + } else if ((obj_desc->common.type == ACPI_TYPE_LOCAL_REGION_FIELD) && + (obj_desc->field.region_obj->region.space_id == + ACPI_ADR_SPACE_GPIO)) { + /* + * For GPIO (general_purpose_io), we will bypass the entire field + * mechanism and handoff the bit address and bit width directly to + * the handler. The Address will be the bit offset + * from the previous Connection() operator, making it effectively a + * pin number index. The bit_length is the length of the field, which + * is thus the number of pins. + */ + if (source_desc->common.type != ACPI_TYPE_INTEGER) { + return_ACPI_STATUS(AE_AML_OPERAND_TYPE); + } + + ACPI_DEBUG_PRINT((ACPI_DB_BFIELD, + "GPIO FieldWrite [FROM]: (%s:%X), Val %.8X [TO]: Pin %u Bits %u\n", + acpi_ut_get_type_name(source_desc->common. + type), + source_desc->common.type, + (u32)source_desc->integer.value, + obj_desc->field.pin_number_index, + obj_desc->field.bit_length)); + + buffer = &source_desc->integer.value; + + /* Lock entire transaction if requested */ + + acpi_ex_acquire_global_lock(obj_desc->common_field.field_flags); + + /* Perform the write */ + + status = acpi_ex_access_region(obj_desc, 0, + (u64 *)buffer, ACPI_WRITE); + acpi_ex_release_global_lock(obj_desc->common_field.field_flags); + return_ACPI_STATUS(status); } /* Get a pointer to the data to be written */ diff --git a/drivers/acpi/acpica/exprep.c b/drivers/acpi/acpica/exprep.c index 5a588611ab48..8c88cfdec441 100644 --- a/drivers/acpi/acpica/exprep.c +++ b/drivers/acpi/acpica/exprep.c @@ -484,6 +484,8 @@ acpi_status acpi_ex_prep_field_value(struct acpi_create_field_info *info) obj_desc->field.resource_length = info->resource_length; } + obj_desc->field.pin_number_index = info->pin_number_index; + /* Allow full data read from EC address space */ if ((obj_desc->field.region_obj->region.space_id == diff --git a/drivers/acpi/container.c b/drivers/acpi/container.c index 368f9ddb8480..e4a6f78f3bbc 100644 --- a/drivers/acpi/container.c +++ b/drivers/acpi/container.c @@ -96,6 +96,13 @@ static void container_device_detach(struct acpi_device *adev) device_unregister(dev); } +static void container_device_online(struct acpi_device *adev) +{ + struct device *dev = acpi_driver_data(adev); + + kobject_uevent(&dev->kobj, KOBJ_ONLINE); +} + static struct acpi_scan_handler container_handler = { .ids = container_device_ids, .attach = container_device_attach, @@ -103,6 +110,7 @@ static struct acpi_scan_handler container_handler = { .hotplug = { .enabled = true, .demand_offline = true, + .notify_online = container_device_online, }, }; diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index c14a00d3dca6..22621c7b1867 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -257,7 +257,7 @@ int acpi_bus_init_power(struct acpi_device *device) device->power.state = ACPI_STATE_UNKNOWN; if (!acpi_device_is_present(device)) - return 0; + return -ENXIO; result = acpi_device_get_power(device, &state); if (result) @@ -987,6 +987,8 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on) acpi_dev_pm_full_power(adev); __acpi_device_run_wake(adev, false); } + + dev->pm_domain->detach = acpi_dev_pm_detach; return 0; } EXPORT_SYMBOL_GPL(acpi_dev_pm_attach); diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 17f9ec501972..fd8496a92b45 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -962,7 +962,7 @@ static int acpi_processor_setup_cpuidle_states(struct acpi_processor *pr) return -EINVAL; drv->safe_state_index = -1; - for (i = 0; i < CPUIDLE_STATE_MAX; i++) { + for (i = CPUIDLE_DRIVER_STATE_START; i < CPUIDLE_STATE_MAX; i++) { drv->states[i].name[0] = '\0'; drv->states[i].desc[0] = '\0'; } diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 92d5184e3654..666beea3bf1c 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -106,7 +106,7 @@ static int create_modalias(struct acpi_device *acpi_dev, char *modalias, list_for_each_entry(id, &acpi_dev->pnp.ids, list) { count = snprintf(&modalias[len], size, "%s:", id->id); if (count < 0) - return EINVAL; + return -EINVAL; if (count >= size) return -ENOMEM; len += count; @@ -865,7 +865,7 @@ static void acpi_free_power_resources_lists(struct acpi_device *device) if (device->wakeup.flags.valid) acpi_power_resources_list_free(&device->wakeup.resources); - if (!device->flags.power_manageable) + if (!device->power.flags.power_resources) return; for (i = ACPI_STATE_D0; i <= ACPI_STATE_D3_HOT; i++) { @@ -1554,10 +1554,8 @@ static void acpi_bus_get_power_flags(struct acpi_device *device) device->power.flags.power_resources) device->power.states[ACPI_STATE_D3_COLD].flags.os_accessible = 1; - if (acpi_bus_init_power(device)) { - acpi_free_power_resources_lists(device); + if (acpi_bus_init_power(device)) device->flags.power_manageable = 0; - } } static void acpi_bus_get_flags(struct acpi_device *device) @@ -2043,13 +2041,18 @@ static void acpi_bus_attach(struct acpi_device *device) /* Skip devices that are not present. */ if (!acpi_device_is_present(device)) { device->flags.visited = false; + device->flags.power_manageable = 0; return; } if (device->handler) goto ok; if (!device->flags.initialized) { - acpi_bus_update_power(device, NULL); + device->flags.power_manageable = + device->power.states[ACPI_STATE_D0].flags.valid; + if (acpi_bus_init_power(device)) + device->flags.power_manageable = 0; + device->flags.initialized = true; } device->flags.visited = false; @@ -2068,6 +2071,9 @@ static void acpi_bus_attach(struct acpi_device *device) ok: list_for_each_entry(child, &device->children, node) acpi_bus_attach(child); + + if (device->handler && device->handler->hotplug.notify_online) + device->handler->hotplug.notify_online(device); } /** diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c index bb0b90461a6b..997540dc8250 100644 --- a/drivers/acpi/video.c +++ b/drivers/acpi/video.c @@ -2064,6 +2064,17 @@ EXPORT_SYMBOL(acpi_video_unregister); static int __init acpi_video_init(void) { + /* + * Let the module load even if ACPI is disabled (e.g. due to + * a broken BIOS) so that i915.ko can still be loaded on such + * old systems without an AcpiOpRegion. + * + * acpi_video_register() will report -ENODEV later as well due + * to acpi_disabled when i915.ko tries to register itself afterwards. + */ + if (acpi_disabled) + return 0; + dmi_check_system(video_dmi_table); if (intel_opregion_present()) diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index 9e6029105607..0b3ce7bce836 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -327,7 +327,7 @@ int amba_device_add(struct amba_device *dev, struct resource *parent) amba_put_disable_pclk(dev); - if (cid == AMBA_CID) + if (cid == AMBA_CID || cid == CORESIGHT_CID) dev->periphid = pid; if (!dev->periphid) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index b54f8b3c7924..cc5f102bebf3 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -61,6 +61,7 @@ enum board_ids { /* board IDs by feature in alphabetical order */ board_ahci, board_ahci_ign_iferr, + board_ahci_nomsi, board_ahci_noncq, board_ahci_nosntf, board_ahci_yes_fbs, @@ -122,6 +123,13 @@ static const struct ata_port_info ahci_port_info[] = { .udma_mask = ATA_UDMA6, .port_ops = &ahci_ops, }, + [board_ahci_nomsi] = { + AHCI_HFLAGS (AHCI_HFLAG_NO_MSI), + .flags = AHCI_FLAG_COMMON, + .pio_mask = ATA_PIO4, + .udma_mask = ATA_UDMA6, + .port_ops = &ahci_ops, + }, [board_ahci_noncq] = { AHCI_HFLAGS (AHCI_HFLAG_NO_NCQ), .flags = AHCI_FLAG_COMMON, @@ -306,6 +314,22 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x9c85), board_ahci }, /* Wildcat Point-LP RAID */ { PCI_VDEVICE(INTEL, 0x9c87), board_ahci }, /* Wildcat Point-LP RAID */ { PCI_VDEVICE(INTEL, 0x9c8f), board_ahci }, /* Wildcat Point-LP RAID */ + { PCI_VDEVICE(INTEL, 0x8c82), board_ahci }, /* 9 Series AHCI */ + { PCI_VDEVICE(INTEL, 0x8c83), board_ahci }, /* 9 Series AHCI */ + { PCI_VDEVICE(INTEL, 0x8c84), board_ahci }, /* 9 Series RAID */ + { PCI_VDEVICE(INTEL, 0x8c85), board_ahci }, /* 9 Series RAID */ + { PCI_VDEVICE(INTEL, 0x8c86), board_ahci }, /* 9 Series RAID */ + { PCI_VDEVICE(INTEL, 0x8c87), board_ahci }, /* 9 Series RAID */ + { PCI_VDEVICE(INTEL, 0x8c8e), board_ahci }, /* 9 Series RAID */ + { PCI_VDEVICE(INTEL, 0x8c8f), board_ahci }, /* 9 Series RAID */ + { PCI_VDEVICE(INTEL, 0x9d03), board_ahci }, /* Sunrise Point-LP AHCI */ + { PCI_VDEVICE(INTEL, 0x9d05), board_ahci }, /* Sunrise Point-LP RAID */ + { PCI_VDEVICE(INTEL, 0x9d07), board_ahci }, /* Sunrise Point-LP RAID */ + { PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H AHCI */ + { PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H RAID */ + { PCI_VDEVICE(INTEL, 0xa105), board_ahci }, /* Sunrise Point-H RAID */ + { PCI_VDEVICE(INTEL, 0xa107), board_ahci }, /* Sunrise Point-H RAID */ + { PCI_VDEVICE(INTEL, 0xa10f), board_ahci }, /* Sunrise Point-H RAID */ /* JMicron 360/1/3/5/6, match class to avoid IDE function */ { PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, @@ -443,6 +467,8 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x917a), .driver_data = board_ahci_yes_fbs }, /* 88se9172 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9172), + .driver_data = board_ahci_yes_fbs }, /* 88se9182 */ + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9182), .driver_data = board_ahci_yes_fbs }, /* 88se9172 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9192), .driver_data = board_ahci_yes_fbs }, /* 88se9172 on some Gigabyte */ @@ -466,10 +492,11 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci }, /* ASM1062 */ /* - * Samsung SSDs found on some macbooks. NCQ times out. - * https://bugzilla.kernel.org/show_bug.cgi?id=60731 + * Samsung SSDs found on some macbooks. NCQ times out if MSI is + * enabled. https://bugzilla.kernel.org/show_bug.cgi?id=60731 */ - { PCI_VDEVICE(SAMSUNG, 0x1600), board_ahci_noncq }, + { PCI_VDEVICE(SAMSUNG, 0x1600), board_ahci_nomsi }, + { PCI_VDEVICE(SAMSUNG, 0xa800), board_ahci_nomsi }, /* Enmotus */ { PCI_DEVICE(0x1c44, 0x8000), board_ahci }, diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c index 6334c8d7c3f1..39f76b987c75 100644 --- a/drivers/ata/ata_piix.c +++ b/drivers/ata/ata_piix.c @@ -340,6 +340,14 @@ static const struct pci_device_id piix_pci_tbl[] = { { 0x8086, 0x0F21, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata_byt }, /* SATA Controller IDE (Coleto Creek) */ { 0x8086, 0x23a6, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata }, + /* SATA Controller IDE (9 Series) */ + { 0x8086, 0x8c88, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata_snb }, + /* SATA Controller IDE (9 Series) */ + { 0x8086, 0x8c89, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata_snb }, + /* SATA Controller IDE (9 Series) */ + { 0x8086, 0x8c80, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb }, + /* SATA Controller IDE (9 Series) */ + { 0x8086, 0x8c81, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb }, { } /* terminate list */ }; diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index f7616036663b..538574f98e22 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4227,7 +4227,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "Micron_M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, { "Crucial_CT???M500SSD*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, { "Micron_M550*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, - { "Crucial_CT???M550SSD*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, + { "Crucial_CT*M550SSD*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, /* * Some WD SATA-I drives spin up and down erratically when the link diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index b603720b877d..136803c47cdb 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -1333,7 +1333,19 @@ void ata_sff_flush_pio_task(struct ata_port *ap) DPRINTK("ENTER\n"); cancel_delayed_work_sync(&ap->sff_pio_task); + + /* + * We wanna reset the HSM state to IDLE. If we do so without + * grabbing the port lock, critical sections protected by it which + * expect the HSM state to stay stable may get surprised. For + * example, we may set IDLE in between the time + * __ata_sff_port_intr() checks for HSM_ST_IDLE and before it calls + * ata_sff_hsm_move() causing ata_sff_hsm_move() to BUG(). + */ + spin_lock_irq(ap->lock); ap->hsm_task_state = HSM_ST_IDLE; + spin_unlock_irq(ap->lock); + ap->sff_pio_task_link = NULL; if (ata_msg_ctl(ap)) @@ -2008,13 +2020,15 @@ static int ata_bus_softreset(struct ata_port *ap, unsigned int devmask, DPRINTK("ata%u: bus reset via SRST\n", ap->print_id); - /* software reset. causes dev0 to be selected */ - iowrite8(ap->ctl, ioaddr->ctl_addr); - udelay(20); /* FIXME: flush */ - iowrite8(ap->ctl | ATA_SRST, ioaddr->ctl_addr); - udelay(20); /* FIXME: flush */ - iowrite8(ap->ctl, ioaddr->ctl_addr); - ap->last_ctl = ap->ctl; + if (ap->ioaddr.ctl_addr) { + /* software reset. causes dev0 to be selected */ + iowrite8(ap->ctl, ioaddr->ctl_addr); + udelay(20); /* FIXME: flush */ + iowrite8(ap->ctl | ATA_SRST, ioaddr->ctl_addr); + udelay(20); /* FIXME: flush */ + iowrite8(ap->ctl, ioaddr->ctl_addr); + ap->last_ctl = ap->ctl; + } /* wait the port to become ready */ return ata_sff_wait_after_reset(&ap->link, devmask, deadline); @@ -2215,10 +2229,6 @@ void ata_sff_error_handler(struct ata_port *ap) spin_unlock_irqrestore(ap->lock, flags); - /* ignore ata_sff_softreset if ctl isn't accessible */ - if (softreset == ata_sff_softreset && !ap->ioaddr.ctl_addr) - softreset = NULL; - /* ignore built-in hardresets if SCR access is not available */ if ((hardreset == sata_std_hardreset || hardreset == sata_sff_hardreset) && !sata_scr_valid(&ap->link)) diff --git a/drivers/ata/pata_scc.c b/drivers/ata/pata_scc.c index f35f15f4d83e..f7badaa39eb6 100644 --- a/drivers/ata/pata_scc.c +++ b/drivers/ata/pata_scc.c @@ -586,7 +586,7 @@ static int scc_wait_after_reset(struct ata_link *link, unsigned int devmask, * Note: Original code is ata_bus_softreset(). */ -static unsigned int scc_bus_softreset(struct ata_port *ap, unsigned int devmask, +static int scc_bus_softreset(struct ata_port *ap, unsigned int devmask, unsigned long deadline) { struct ata_ioports *ioaddr = &ap->ioaddr; @@ -600,9 +600,7 @@ static unsigned int scc_bus_softreset(struct ata_port *ap, unsigned int devmask, udelay(20); out_be32(ioaddr->ctl_addr, ap->ctl); - scc_wait_after_reset(&ap->link, devmask, deadline); - - return 0; + return scc_wait_after_reset(&ap->link, devmask, deadline); } /** @@ -619,7 +617,8 @@ static int scc_softreset(struct ata_link *link, unsigned int *classes, { struct ata_port *ap = link->ap; unsigned int slave_possible = ap->flags & ATA_FLAG_SLAVE_POSS; - unsigned int devmask = 0, err_mask; + unsigned int devmask = 0; + int rc; u8 err; DPRINTK("ENTER\n"); @@ -635,9 +634,9 @@ static int scc_softreset(struct ata_link *link, unsigned int *classes, /* issue bus reset */ DPRINTK("about to softreset, devmask=%x\n", devmask); - err_mask = scc_bus_softreset(ap, devmask, deadline); - if (err_mask) { - ata_port_err(ap, "SRST failed (err_mask=0x%x)\n", err_mask); + rc = scc_bus_softreset(ap, devmask, deadline); + if (rc) { + ata_port_err(ap, "SRST failed (err_mask=0x%x)\n", rc); return -EIO; } diff --git a/drivers/ata/pata_serverworks.c b/drivers/ata/pata_serverworks.c index 96c6a79ef606..79dedbae282c 100644 --- a/drivers/ata/pata_serverworks.c +++ b/drivers/ata/pata_serverworks.c @@ -252,12 +252,18 @@ static void serverworks_set_dmamode(struct ata_port *ap, struct ata_device *adev pci_write_config_byte(pdev, 0x54, ultra_cfg); } -static struct scsi_host_template serverworks_sht = { +static struct scsi_host_template serverworks_osb4_sht = { + ATA_BMDMA_SHT(DRV_NAME), + .sg_tablesize = LIBATA_DUMB_MAX_PRD, +}; + +static struct scsi_host_template serverworks_csb_sht = { ATA_BMDMA_SHT(DRV_NAME), }; static struct ata_port_operations serverworks_osb4_port_ops = { .inherits = &ata_bmdma_port_ops, + .qc_prep = ata_bmdma_dumb_qc_prep, .cable_detect = serverworks_cable_detect, .mode_filter = serverworks_osb4_filter, .set_piomode = serverworks_set_piomode, @@ -266,6 +272,7 @@ static struct ata_port_operations serverworks_osb4_port_ops = { static struct ata_port_operations serverworks_csb_port_ops = { .inherits = &serverworks_osb4_port_ops, + .qc_prep = ata_bmdma_qc_prep, .mode_filter = serverworks_csb_filter, }; @@ -405,6 +412,7 @@ static int serverworks_init_one(struct pci_dev *pdev, const struct pci_device_id } }; const struct ata_port_info *ppi[] = { &info[id->driver_data], NULL }; + struct scsi_host_template *sht = &serverworks_csb_sht; int rc; rc = pcim_enable_device(pdev); @@ -418,6 +426,7 @@ static int serverworks_init_one(struct pci_dev *pdev, const struct pci_device_id /* Select non UDMA capable OSB4 if we can't do fixups */ if (rc < 0) ppi[0] = &info[1]; + sht = &serverworks_osb4_sht; } /* setup CSB5/CSB6 : South Bridge and IDE option RAID */ else if ((pdev->device == PCI_DEVICE_ID_SERVERWORKS_CSB5IDE) || @@ -434,7 +443,7 @@ static int serverworks_init_one(struct pci_dev *pdev, const struct pci_device_id ppi[1] = &ata_dummy_port_info; } - return ata_pci_bmdma_init_one(pdev, ppi, &serverworks_sht, NULL, 0); + return ata_pci_bmdma_init_one(pdev, ppi, sht, NULL, 0); } #ifdef CONFIG_PM diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c index 523524b68022..f71e09d6cfe6 100644 --- a/drivers/ata/sata_dwc_460ex.c +++ b/drivers/ata/sata_dwc_460ex.c @@ -799,7 +799,7 @@ static int dma_dwc_init(struct sata_dwc_device *hsdev, int irq) if (err) { dev_err(host_pvt.dwc_dev, "%s: dma_request_interrupts returns" " %d\n", __func__, err); - goto error_out; + return err; } /* Enabe DMA */ @@ -810,11 +810,6 @@ static int dma_dwc_init(struct sata_dwc_device *hsdev, int irq) sata_dma_regs); return 0; - -error_out: - dma_dwc_exit(hsdev); - - return err; } static int sata_dwc_scr_read(struct ata_link *link, unsigned int scr, u32 *val) @@ -1664,7 +1659,7 @@ static int sata_dwc_probe(struct platform_device *ofdev) char *ver = (char *)&versionr; u8 *base = NULL; int err = 0; - int irq, rc; + int irq; struct ata_host *host; struct ata_port_info pi = sata_dwc_port_info[0]; const struct ata_port_info *ppi[] = { &pi, NULL }; @@ -1727,7 +1722,7 @@ static int sata_dwc_probe(struct platform_device *ofdev) if (irq == NO_IRQ) { dev_err(&ofdev->dev, "no SATA DMA irq\n"); err = -ENODEV; - goto error_out; + goto error_iomap; } /* Get physical SATA DMA register base address */ @@ -1736,14 +1731,16 @@ static int sata_dwc_probe(struct platform_device *ofdev) dev_err(&ofdev->dev, "ioremap failed for AHBDMA register" " address\n"); err = -ENODEV; - goto error_out; + goto error_iomap; } /* Save dev for later use in dev_xxx() routines */ host_pvt.dwc_dev = &ofdev->dev; /* Initialize AHB DMAC */ - dma_dwc_init(hsdev, irq); + err = dma_dwc_init(hsdev, irq); + if (err) + goto error_dma_iomap; /* Enable SATA Interrupts */ sata_dwc_enable_interrupts(hsdev); @@ -1761,9 +1758,8 @@ static int sata_dwc_probe(struct platform_device *ofdev) * device discovery process, invoking our port_start() handler & * error_handler() to execute a dummy Softreset EH session */ - rc = ata_host_activate(host, irq, sata_dwc_isr, 0, &sata_dwc_sht); - - if (rc != 0) + err = ata_host_activate(host, irq, sata_dwc_isr, 0, &sata_dwc_sht); + if (err) dev_err(&ofdev->dev, "failed to activate host"); dev_set_drvdata(&ofdev->dev, host); @@ -1772,7 +1768,8 @@ static int sata_dwc_probe(struct platform_device *ofdev) error_out: /* Free SATA DMA resources */ dma_dwc_exit(hsdev); - +error_dma_iomap: + iounmap((void __iomem *)host_pvt.sata_dma_regs); error_iomap: iounmap(base); error_kmalloc: @@ -1793,6 +1790,7 @@ static int sata_dwc_remove(struct platform_device *ofdev) /* Free SATA DMA resources */ dma_dwc_exit(hsdev); + iounmap((void __iomem *)host_pvt.sata_dma_regs); iounmap(hsdev->reg_base); kfree(hsdev); kfree(host); diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index fb0b40a191c2..ee2780dd90a8 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -1503,7 +1503,7 @@ static int sata_fsl_probe(struct platform_device *ofdev) host_priv->csr_base = csr_base; irq = irq_of_parse_and_map(ofdev->dev.of_node, 0); - if (irq < 0) { + if (!irq) { dev_err(&ofdev->dev, "invalid irq from platform\n"); goto error_exit_with_cleanup; } diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c index 2b25bd83fc9d..c1ea780fca07 100644 --- a/drivers/ata/sata_rcar.c +++ b/drivers/ata/sata_rcar.c @@ -146,6 +146,7 @@ enum sata_rcar_type { RCAR_GEN1_SATA, RCAR_GEN2_SATA, + RCAR_R8A7790_ES1_SATA, }; struct sata_rcar_priv { @@ -763,6 +764,9 @@ static void sata_rcar_setup_port(struct ata_host *host) ap->udma_mask = ATA_UDMA6; ap->flags |= ATA_FLAG_SATA; + if (priv->type == RCAR_R8A7790_ES1_SATA) + ap->flags |= ATA_FLAG_NO_DIPM; + ioaddr->cmd_addr = base + SDATA_REG; ioaddr->ctl_addr = base + SSDEVCON_REG; ioaddr->scr_addr = base + SCRSSTS_REG; @@ -792,6 +796,7 @@ static void sata_rcar_init_controller(struct ata_host *host) sata_rcar_gen1_phy_init(priv); break; case RCAR_GEN2_SATA: + case RCAR_R8A7790_ES1_SATA: sata_rcar_gen2_phy_init(priv); break; default: @@ -838,6 +843,10 @@ static struct of_device_id sata_rcar_match[] = { .data = (void *)RCAR_GEN2_SATA }, { + .compatible = "renesas,sata-r8a7790-es1", + .data = (void *)RCAR_R8A7790_ES1_SATA + }, + { .compatible = "renesas,sata-r8a7791", .data = (void *)RCAR_GEN2_SATA }, @@ -849,6 +858,7 @@ static const struct platform_device_id sata_rcar_id_table[] = { { "sata_rcar", RCAR_GEN1_SATA }, /* Deprecated by "sata-r8a7779" */ { "sata-r8a7779", RCAR_GEN1_SATA }, { "sata-r8a7790", RCAR_GEN2_SATA }, + { "sata-r8a7790-es1", RCAR_R8A7790_ES1_SATA }, { "sata-r8a7791", RCAR_GEN2_SATA }, { }, }; diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 59dc8086e4fa..45d0fa78981c 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -254,13 +254,15 @@ static ssize_t store_drivers_probe(struct bus_type *bus, const char *buf, size_t count) { struct device *dev; + int err = -EINVAL; dev = bus_find_device_by_name(bus, NULL, buf); if (!dev) return -ENODEV; - if (bus_rescan_devices_helper(dev, NULL) != 0) - return -EINVAL; - return count; + if (bus_rescan_devices_helper(dev, NULL) == 0) + err = count; + put_device(dev); + return err; } static struct device *next_device(struct klist_iter *i) diff --git a/drivers/base/core.c b/drivers/base/core.c index 2b567177ef78..6a8955e78610 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -741,12 +741,12 @@ class_dir_create_and_add(struct class *class, struct kobject *parent_kobj) return &dir->kobj; } +static DEFINE_MUTEX(gdp_mutex); static struct kobject *get_device_parent(struct device *dev, struct device *parent) { if (dev->class) { - static DEFINE_MUTEX(gdp_mutex); struct kobject *kobj = NULL; struct kobject *parent_kobj; struct kobject *k; @@ -810,7 +810,9 @@ static void cleanup_glue_dir(struct device *dev, struct kobject *glue_dir) glue_dir->kset != &dev->class->p->glue_dirs) return; + mutex_lock(&gdp_mutex); kobject_put(glue_dir); + mutex_unlock(&gdp_mutex); } static void cleanup_device_parent(struct device *dev) diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c index c30df50e4440..2495ee577a64 100644 --- a/drivers/base/firmware_class.c +++ b/drivers/base/firmware_class.c @@ -1081,6 +1081,9 @@ _request_firmware(const struct firmware **firmware_p, const char *name, if (!firmware_p) return -EINVAL; + if (!name || name[0] == '\0') + return -EINVAL; + ret = _request_firmware_prepare(&fw, name, device); if (ret <= 0) /* error or already assigned */ goto out; diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 9dbf4ef2b2a3..e988313ece30 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -947,6 +947,7 @@ int __init platform_bus_init(void) error = bus_register(&platform_bus_type); if (error) device_unregister(&platform_bus); + of_platform_register_reconfig_notifier(); return error; } diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index bfb8955c406c..35081d42661e 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -9,6 +9,7 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/io.h> +#include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/pm_domain.h> #include <linux/pm_qos.h> @@ -2177,3 +2178,291 @@ void pm_genpd_init(struct generic_pm_domain *genpd, list_add(&genpd->gpd_list_node, &gpd_list); mutex_unlock(&gpd_list_lock); } + +#ifdef CONFIG_PM_GENERIC_DOMAINS_OF +/* + * Device Tree based PM domain providers. + * + * The code below implements generic device tree based PM domain providers that + * bind device tree nodes with generic PM domains registered in the system. + * + * Any driver that registers generic PM domains and needs to support binding of + * devices to these domains is supposed to register a PM domain provider, which + * maps a PM domain specifier retrieved from the device tree to a PM domain. + * + * Two simple mapping functions have been provided for convenience: + * - __of_genpd_xlate_simple() for 1:1 device tree node to PM domain mapping. + * - __of_genpd_xlate_onecell() for mapping of multiple PM domains per node by + * index. + */ + +/** + * struct of_genpd_provider - PM domain provider registration structure + * @link: Entry in global list of PM domain providers + * @node: Pointer to device tree node of PM domain provider + * @xlate: Provider-specific xlate callback mapping a set of specifier cells + * into a PM domain. + * @data: context pointer to be passed into @xlate callback + */ +struct of_genpd_provider { + struct list_head link; + struct device_node *node; + genpd_xlate_t xlate; + void *data; +}; + +/* List of registered PM domain providers. */ +static LIST_HEAD(of_genpd_providers); +/* Mutex to protect the list above. */ +static DEFINE_MUTEX(of_genpd_mutex); + +/** + * __of_genpd_xlate_simple() - Xlate function for direct node-domain mapping + * @genpdspec: OF phandle args to map into a PM domain + * @data: xlate function private data - pointer to struct generic_pm_domain + * + * This is a generic xlate function that can be used to model PM domains that + * have their own device tree nodes. The private data of xlate function needs + * to be a valid pointer to struct generic_pm_domain. + */ +struct generic_pm_domain *__of_genpd_xlate_simple( + struct of_phandle_args *genpdspec, + void *data) +{ + if (genpdspec->args_count != 0) + return ERR_PTR(-EINVAL); + return data; +} +EXPORT_SYMBOL_GPL(__of_genpd_xlate_simple); + +/** + * __of_genpd_xlate_onecell() - Xlate function using a single index. + * @genpdspec: OF phandle args to map into a PM domain + * @data: xlate function private data - pointer to struct genpd_onecell_data + * + * This is a generic xlate function that can be used to model simple PM domain + * controllers that have one device tree node and provide multiple PM domains. + * A single cell is used as an index into an array of PM domains specified in + * the genpd_onecell_data struct when registering the provider. + */ +struct generic_pm_domain *__of_genpd_xlate_onecell( + struct of_phandle_args *genpdspec, + void *data) +{ + struct genpd_onecell_data *genpd_data = data; + unsigned int idx = genpdspec->args[0]; + + if (genpdspec->args_count != 1) + return ERR_PTR(-EINVAL); + + if (idx >= genpd_data->num_domains) { + pr_err("%s: invalid domain index %u\n", __func__, idx); + return ERR_PTR(-EINVAL); + } + + if (!genpd_data->domains[idx]) + return ERR_PTR(-ENOENT); + + return genpd_data->domains[idx]; +} +EXPORT_SYMBOL_GPL(__of_genpd_xlate_onecell); + +/** + * __of_genpd_add_provider() - Register a PM domain provider for a node + * @np: Device node pointer associated with the PM domain provider. + * @xlate: Callback for decoding PM domain from phandle arguments. + * @data: Context pointer for @xlate callback. + */ +int __of_genpd_add_provider(struct device_node *np, genpd_xlate_t xlate, + void *data) +{ + struct of_genpd_provider *cp; + + cp = kzalloc(sizeof(*cp), GFP_KERNEL); + if (!cp) + return -ENOMEM; + + cp->node = of_node_get(np); + cp->data = data; + cp->xlate = xlate; + + mutex_lock(&of_genpd_mutex); + list_add(&cp->link, &of_genpd_providers); + mutex_unlock(&of_genpd_mutex); + pr_debug("Added domain provider from %s\n", np->full_name); + + return 0; +} +EXPORT_SYMBOL_GPL(__of_genpd_add_provider); + +/** + * of_genpd_del_provider() - Remove a previously registered PM domain provider + * @np: Device node pointer associated with the PM domain provider + */ +void of_genpd_del_provider(struct device_node *np) +{ + struct of_genpd_provider *cp; + + mutex_lock(&of_genpd_mutex); + list_for_each_entry(cp, &of_genpd_providers, link) { + if (cp->node == np) { + list_del(&cp->link); + of_node_put(cp->node); + kfree(cp); + break; + } + } + mutex_unlock(&of_genpd_mutex); +} +EXPORT_SYMBOL_GPL(of_genpd_del_provider); + +/** + * of_genpd_get_from_provider() - Look-up PM domain + * @genpdspec: OF phandle args to use for look-up + * + * Looks for a PM domain provider under the node specified by @genpdspec and if + * found, uses xlate function of the provider to map phandle args to a PM + * domain. + * + * Returns a valid pointer to struct generic_pm_domain on success or ERR_PTR() + * on failure. + */ +static struct generic_pm_domain *of_genpd_get_from_provider( + struct of_phandle_args *genpdspec) +{ + struct generic_pm_domain *genpd = ERR_PTR(-ENOENT); + struct of_genpd_provider *provider; + + mutex_lock(&of_genpd_mutex); + + /* Check if we have such a provider in our array */ + list_for_each_entry(provider, &of_genpd_providers, link) { + if (provider->node == genpdspec->np) + genpd = provider->xlate(genpdspec, provider->data); + if (!IS_ERR(genpd)) + break; + } + + mutex_unlock(&of_genpd_mutex); + + return genpd; +} + +/** + * genpd_dev_pm_detach - Detach a device from its PM domain. + * @dev: Device to attach. + * @power_off: Currently not used + * + * Try to locate a corresponding generic PM domain, which the device was + * attached to previously. If such is found, the device is detached from it. + */ +static void genpd_dev_pm_detach(struct device *dev, bool power_off) +{ + struct generic_pm_domain *pd = NULL, *gpd; + int ret = 0; + + if (!dev->pm_domain) + return; + + mutex_lock(&gpd_list_lock); + list_for_each_entry(gpd, &gpd_list, gpd_list_node) { + if (&gpd->domain == dev->pm_domain) { + pd = gpd; + break; + } + } + mutex_unlock(&gpd_list_lock); + + if (!pd) + return; + + dev_dbg(dev, "removing from PM domain %s\n", pd->name); + + while (1) { + ret = pm_genpd_remove_device(pd, dev); + if (ret != -EAGAIN) + break; + cond_resched(); + } + + if (ret < 0) { + dev_err(dev, "failed to remove from PM domain %s: %d", + pd->name, ret); + return; + } + + /* Check if PM domain can be powered off after removing this device. */ + genpd_queue_power_off_work(pd); +} + +/** + * genpd_dev_pm_attach - Attach a device to its PM domain using DT. + * @dev: Device to attach. + * + * Parse device's OF node to find a PM domain specifier. If such is found, + * attaches the device to retrieved pm_domain ops. + * + * Both generic and legacy Samsung-specific DT bindings are supported to keep + * backwards compatibility with existing DTBs. + * + * Returns 0 on successfully attached PM domain or negative error code. + */ +int genpd_dev_pm_attach(struct device *dev) +{ + struct of_phandle_args pd_args; + struct generic_pm_domain *pd; + int ret; + + if (!dev->of_node) + return -ENODEV; + + if (dev->pm_domain) + return -EEXIST; + + ret = of_parse_phandle_with_args(dev->of_node, "power-domains", + "#power-domain-cells", 0, &pd_args); + if (ret < 0) { + if (ret != -ENOENT) + return ret; + + /* + * Try legacy Samsung-specific bindings + * (for backwards compatibility of DT ABI) + */ + pd_args.args_count = 0; + pd_args.np = of_parse_phandle(dev->of_node, + "samsung,power-domain", 0); + if (!pd_args.np) + return -ENOENT; + } + + pd = of_genpd_get_from_provider(&pd_args); + if (IS_ERR(pd)) { + dev_dbg(dev, "%s() failed to find PM domain: %ld\n", + __func__, PTR_ERR(pd)); + of_node_put(dev->of_node); + return PTR_ERR(pd); + } + + dev_dbg(dev, "adding to PM domain %s\n", pd->name); + + while (1) { + ret = pm_genpd_add_device(pd, dev); + if (ret != -EAGAIN) + break; + cond_resched(); + } + + if (ret < 0) { + dev_err(dev, "failed to add to PM domain %s: %d", + pd->name, ret); + of_node_put(dev->of_node); + return ret; + } + + dev->pm_domain->detach = genpd_dev_pm_detach; + + return 0; +} +EXPORT_SYMBOL_GPL(genpd_dev_pm_attach); +#endif diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c index 930cad4e5df8..2b946bc4212d 100644 --- a/drivers/base/regmap/regcache-rbtree.c +++ b/drivers/base/regmap/regcache-rbtree.c @@ -313,7 +313,7 @@ static int regcache_rbtree_insert_to_block(struct regmap *map, if (pos == 0) { memmove(blk + offset * map->cache_word_size, blk, rbnode->blklen * map->cache_word_size); - bitmap_shift_right(present, present, offset, blklen); + bitmap_shift_left(present, present, offset, blklen); } /* update the rbnode block, its size and the base register */ diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c index d4dd77134814..154e7a8c0a04 100644 --- a/drivers/base/regmap/regcache.c +++ b/drivers/base/regmap/regcache.c @@ -701,7 +701,7 @@ int regcache_sync_block(struct regmap *map, void *block, unsigned int block_base, unsigned int start, unsigned int end) { - if (regmap_can_raw_write(map)) + if (regmap_can_raw_write(map) && !map->use_single_rw) return regcache_sync_block_raw(map, block, cache_present, block_base, start, end); else diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c index c5471cd6ebb7..d39fd610aa3b 100644 --- a/drivers/base/regmap/regmap-debugfs.c +++ b/drivers/base/regmap/regmap-debugfs.c @@ -473,6 +473,7 @@ void regmap_debugfs_init(struct regmap *map, const char *name) { struct rb_node *next; struct regmap_range_node *range_node; + const char *devname = "dummy"; /* If we don't have the debugfs root yet, postpone init */ if (!regmap_debugfs_root) { @@ -491,12 +492,15 @@ void regmap_debugfs_init(struct regmap *map, const char *name) INIT_LIST_HEAD(&map->debugfs_off_cache); mutex_init(&map->cache_lock); + if (map->dev) + devname = dev_name(map->dev); + if (name) { map->debugfs_name = kasprintf(GFP_KERNEL, "%s-%s", - dev_name(map->dev), name); + devname, name); name = map->debugfs_name; } else { - name = dev_name(map->dev); + name = devname; } map->debugfs = debugfs_create_dir(name, regmap_debugfs_root); diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 6a19515f8a45..2f9a3d8ecbbf 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -105,7 +105,7 @@ bool regmap_readable(struct regmap *map, unsigned int reg) bool regmap_volatile(struct regmap *map, unsigned int reg) { - if (!regmap_readable(map, reg)) + if (!map->format.format_write && !regmap_readable(map, reg)) return false; if (map->volatile_reg) @@ -1308,7 +1308,7 @@ int _regmap_write(struct regmap *map, unsigned int reg, } #ifdef LOG_DEVICE - if (strcmp(dev_name(map->dev), LOG_DEVICE) == 0) + if (map->dev && strcmp(dev_name(map->dev), LOG_DEVICE) == 0) dev_info(map->dev, "%x <= %x\n", reg, val); #endif @@ -1557,6 +1557,11 @@ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val, } else { void *wval; + if (!val_count) { + ret = -EINVAL; + goto out; + } + wval = kmemdup(val, val_count * val_bytes, GFP_KERNEL); if (!wval) { ret = -ENOMEM; @@ -1739,7 +1744,7 @@ static int _regmap_read(struct regmap *map, unsigned int reg, ret = map->reg_read(context, reg, val); if (ret == 0) { #ifdef LOG_DEVICE - if (strcmp(dev_name(map->dev), LOG_DEVICE) == 0) + if (map->dev && strcmp(dev_name(map->dev), LOG_DEVICE) == 0) dev_info(map->dev, "%x => %x\n", reg, *val); #endif diff --git a/drivers/block/drbd/drbd_interval.c b/drivers/block/drbd/drbd_interval.c index 89c497c630b4..04a14e0f8878 100644 --- a/drivers/block/drbd/drbd_interval.c +++ b/drivers/block/drbd/drbd_interval.c @@ -79,6 +79,7 @@ bool drbd_insert_interval(struct rb_root *root, struct drbd_interval *this) { struct rb_node **new = &root->rb_node, *parent = NULL; + sector_t this_end = this->sector + (this->size >> 9); BUG_ON(!IS_ALIGNED(this->size, 512)); @@ -87,6 +88,8 @@ drbd_insert_interval(struct rb_root *root, struct drbd_interval *this) rb_entry(*new, struct drbd_interval, rb); parent = *new; + if (here->end < this_end) + here->end = this_end; if (this->sector < here->sector) new = &(*new)->rb_left; else if (this->sector > here->sector) @@ -99,6 +102,7 @@ drbd_insert_interval(struct rb_root *root, struct drbd_interval *this) return false; } + this->end = this_end; rb_link_node(&this->rb, parent, new); rb_insert_augmented(&this->rb, root, &augment_callbacks); return true; diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index c706d50a8b06..8c16c2f97026 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -525,6 +525,12 @@ void conn_try_outdate_peer_async(struct drbd_tconn *tconn) struct task_struct *opa; kref_get(&tconn->kref); + /* We may just have force_sig()'ed this thread + * to get it out of some blocking network function. + * Clear signals; otherwise kthread_run(), which internally uses + * wait_on_completion_killable(), will mistake our pending signal + * for a new fatal signal and fail. */ + flush_signals(current); opa = kthread_run(_try_outdate_peer_async, tconn, "drbd_async_h"); if (IS_ERR(opa)) { conn_err(tconn, "out of mem, failed to invoke fence-peer helper\n"); diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 104a040f24de..6efdbeafa33c 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -1310,6 +1310,7 @@ int drbd_merge_bvec(struct request_queue *q, struct bvec_merge_data *bvm, struct struct request_queue * const b = mdev->ldev->backing_bdev->bd_disk->queue; if (b->merge_bvec_fn) { + bvm->bi_bdev = mdev->ldev->backing_bdev; backing_limit = b->merge_bvec_fn(b, bvm, bvec); limit = min(limit, backing_limit); } diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 55298db36b2d..d18093681af2 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -814,10 +814,6 @@ static int __init nbd_init(void) return -EINVAL; } - nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL); - if (!nbd_dev) - return -ENOMEM; - part_shift = 0; if (max_part > 0) { part_shift = fls(max_part); @@ -839,6 +835,10 @@ static int __init nbd_init(void) if (nbds_max > 1UL << (MINORBITS - part_shift)) return -EINVAL; + nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL); + if (!nbd_dev) + return -ENOMEM; + for (i = 0; i < nbds_max; i++) { struct gendisk *disk = alloc_disk(1 << part_shift); if (!disk) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 7296c7f074bd..275a7dc2b06c 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -1926,32 +1926,26 @@ static void rbd_dev_parent_put(struct rbd_device *rbd_dev) * If an image has a non-zero parent overlap, get a reference to its * parent. * - * We must get the reference before checking for the overlap to - * coordinate properly with zeroing the parent overlap in - * rbd_dev_v2_parent_info() when an image gets flattened. We - * drop it again if there is no overlap. - * * Returns true if the rbd device has a parent with a non-zero * overlap and a reference for it was successfully taken, or * false otherwise. */ static bool rbd_dev_parent_get(struct rbd_device *rbd_dev) { - int counter; + int counter = 0; if (!rbd_dev->parent_spec) return false; - counter = atomic_inc_return_safe(&rbd_dev->parent_ref); - if (counter > 0 && rbd_dev->parent_overlap) - return true; - - /* Image was flattened, but parent is not yet torn down */ + down_read(&rbd_dev->header_rwsem); + if (rbd_dev->parent_overlap) + counter = atomic_inc_return_safe(&rbd_dev->parent_ref); + up_read(&rbd_dev->header_rwsem); if (counter < 0) rbd_warn(rbd_dev, "parent reference overflow\n"); - return false; + return counter > 0; } /* @@ -3217,7 +3211,7 @@ static int rbd_obj_read_sync(struct rbd_device *rbd_dev, page_count = (u32) calc_pages_for(offset, length); pages = ceph_alloc_page_vector(page_count, GFP_KERNEL); if (IS_ERR(pages)) - ret = PTR_ERR(pages); + return PTR_ERR(pages); ret = -ENOMEM; obj_request = rbd_obj_request_create(object_name, offset, length, @@ -3904,7 +3898,6 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) */ if (rbd_dev->parent_overlap) { rbd_dev->parent_overlap = 0; - smp_mb(); rbd_dev_parent_put(rbd_dev); pr_info("%s: clone image has been flattened\n", rbd_dev->disk->disk_name); @@ -3948,7 +3941,6 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) * treat it specially. */ rbd_dev->parent_overlap = overlap; - smp_mb(); if (!overlap) { /* A null parent_spec indicates it's the initial probe */ @@ -4764,10 +4756,7 @@ static void rbd_dev_unprobe(struct rbd_device *rbd_dev) { struct rbd_image_header *header; - /* Drop parent reference unless it's already been done (or none) */ - - if (rbd_dev->parent_overlap) - rbd_dev_parent_put(rbd_dev); + rbd_dev_parent_put(rbd_dev); /* Free dynamic fields from the header, then zero it out */ diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 5814deb6963d..0ebadf93b6c5 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -9,6 +9,7 @@ #include <linux/blkdev.h> #include <linux/hdreg.h> #include <linux/genhd.h> +#include <linux/cdrom.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/completion.h> @@ -22,8 +23,8 @@ #define DRV_MODULE_NAME "sunvdc" #define PFX DRV_MODULE_NAME ": " -#define DRV_MODULE_VERSION "1.0" -#define DRV_MODULE_RELDATE "June 25, 2007" +#define DRV_MODULE_VERSION "1.1" +#define DRV_MODULE_RELDATE "February 13, 2013" static char version[] = DRV_MODULE_NAME ".c:v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n"; @@ -32,7 +33,7 @@ MODULE_DESCRIPTION("Sun LDOM virtual disk client driver"); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_MODULE_VERSION); -#define VDC_TX_RING_SIZE 256 +#define VDC_TX_RING_SIZE 512 #define WAITING_FOR_LINK_UP 0x01 #define WAITING_FOR_TX_SPACE 0x02 @@ -65,11 +66,9 @@ struct vdc_port { u64 operations; u32 vdisk_size; u8 vdisk_type; + u8 vdisk_mtype; char disk_name[32]; - - struct vio_disk_geom geom; - struct vio_disk_vtoc label; }; static inline struct vdc_port *to_vdc_port(struct vio_driver_state *vio) @@ -79,9 +78,16 @@ static inline struct vdc_port *to_vdc_port(struct vio_driver_state *vio) /* Ordered from largest major to lowest */ static struct vio_version vdc_versions[] = { + { .major = 1, .minor = 1 }, { .major = 1, .minor = 0 }, }; +static inline int vdc_version_supported(struct vdc_port *port, + u16 major, u16 minor) +{ + return port->vio.ver.major == major && port->vio.ver.minor >= minor; +} + #define VDCBLK_NAME "vdisk" static int vdc_major; #define PARTITION_SHIFT 3 @@ -94,18 +100,54 @@ static inline u32 vdc_tx_dring_avail(struct vio_dring_state *dr) static int vdc_getgeo(struct block_device *bdev, struct hd_geometry *geo) { struct gendisk *disk = bdev->bd_disk; - struct vdc_port *port = disk->private_data; + sector_t nsect = get_capacity(disk); + sector_t cylinders = nsect; - geo->heads = (u8) port->geom.num_hd; - geo->sectors = (u8) port->geom.num_sec; - geo->cylinders = port->geom.num_cyl; + geo->heads = 0xff; + geo->sectors = 0x3f; + sector_div(cylinders, geo->heads * geo->sectors); + geo->cylinders = cylinders; + if ((sector_t)(geo->cylinders + 1) * geo->heads * geo->sectors < nsect) + geo->cylinders = 0xffff; return 0; } +/* Add ioctl/CDROM_GET_CAPABILITY to support cdrom_id in udev + * when vdisk_mtype is VD_MEDIA_TYPE_CD or VD_MEDIA_TYPE_DVD. + * Needed to be able to install inside an ldom from an iso image. + */ +static int vdc_ioctl(struct block_device *bdev, fmode_t mode, + unsigned command, unsigned long argument) +{ + int i; + struct gendisk *disk; + + switch (command) { + case CDROMMULTISESSION: + pr_debug(PFX "Multisession CDs not supported\n"); + for (i = 0; i < sizeof(struct cdrom_multisession); i++) + if (put_user(0, (char __user *)(argument + i))) + return -EFAULT; + return 0; + + case CDROM_GET_CAPABILITY: + disk = bdev->bd_disk; + + if (bdev->bd_disk && (disk->flags & GENHD_FL_CD)) + return 0; + return -EINVAL; + + default: + pr_debug(PFX "ioctl %08x not supported\n", command); + return -EINVAL; + } +} + static const struct block_device_operations vdc_fops = { .owner = THIS_MODULE, .getgeo = vdc_getgeo, + .ioctl = vdc_ioctl, }; static void vdc_finish(struct vio_driver_state *vio, int err, int waiting_for) @@ -165,9 +207,9 @@ static int vdc_handle_attr(struct vio_driver_state *vio, void *arg) struct vio_disk_attr_info *pkt = arg; viodbg(HS, "GOT ATTR stype[0x%x] ops[%llx] disk_size[%llu] disk_type[%x] " - "xfer_mode[0x%x] blksz[%u] max_xfer[%llu]\n", + "mtype[0x%x] xfer_mode[0x%x] blksz[%u] max_xfer[%llu]\n", pkt->tag.stype, pkt->operations, - pkt->vdisk_size, pkt->vdisk_type, + pkt->vdisk_size, pkt->vdisk_type, pkt->vdisk_mtype, pkt->xfer_mode, pkt->vdisk_block_size, pkt->max_xfer_size); @@ -192,8 +234,11 @@ static int vdc_handle_attr(struct vio_driver_state *vio, void *arg) } port->operations = pkt->operations; - port->vdisk_size = pkt->vdisk_size; port->vdisk_type = pkt->vdisk_type; + if (vdc_version_supported(port, 1, 1)) { + port->vdisk_size = pkt->vdisk_size; + port->vdisk_mtype = pkt->vdisk_mtype; + } if (pkt->max_xfer_size < port->max_xfer_size) port->max_xfer_size = pkt->max_xfer_size; port->vdisk_block_size = pkt->vdisk_block_size; @@ -236,7 +281,9 @@ static void vdc_end_one(struct vdc_port *port, struct vio_dring_state *dr, __blk_end_request(req, (desc->status ? -EIO : 0), desc->size); - if (blk_queue_stopped(port->disk->queue)) + /* restart blk queue when ring is half emptied */ + if (blk_queue_stopped(port->disk->queue) && + vdc_tx_dring_avail(dr) * 100 / VDC_TX_RING_SIZE >= 50) blk_start_queue(port->disk->queue); } @@ -388,12 +435,6 @@ static int __send_request(struct request *req) for (i = 0; i < nsg; i++) len += sg[i].length; - if (unlikely(vdc_tx_dring_avail(dr) < 1)) { - blk_stop_queue(port->disk->queue); - err = -ENOMEM; - goto out; - } - desc = vio_dring_cur(dr); err = ldc_map_sg(port->vio.lp, sg, nsg, @@ -433,21 +474,32 @@ static int __send_request(struct request *req) port->req_id++; dr->prod = (dr->prod + 1) & (VDC_TX_RING_SIZE - 1); } -out: return err; } -static void do_vdc_request(struct request_queue *q) +static void do_vdc_request(struct request_queue *rq) { - while (1) { - struct request *req = blk_fetch_request(q); + struct request *req; - if (!req) - break; + while ((req = blk_peek_request(rq)) != NULL) { + struct vdc_port *port; + struct vio_dring_state *dr; - if (__send_request(req) < 0) - __blk_end_request_all(req, -EIO); + port = req->rq_disk->private_data; + dr = &port->vio.drings[VIO_DRIVER_TX_RING]; + if (unlikely(vdc_tx_dring_avail(dr) < 1)) + goto wait; + + blk_start_request(req); + + if (__send_request(req) < 0) { + blk_requeue_request(rq, req); +wait: + /* Avoid pointless unplugs. */ + blk_stop_queue(rq); + break; + } } } @@ -656,25 +708,27 @@ static int probe_disk(struct vdc_port *port) if (comp.err) return comp.err; - err = generic_request(port, VD_OP_GET_VTOC, - &port->label, sizeof(port->label)); - if (err < 0) { - printk(KERN_ERR PFX "VD_OP_GET_VTOC returns error %d\n", err); - return err; - } - - err = generic_request(port, VD_OP_GET_DISKGEOM, - &port->geom, sizeof(port->geom)); - if (err < 0) { - printk(KERN_ERR PFX "VD_OP_GET_DISKGEOM returns " - "error %d\n", err); - return err; + if (vdc_version_supported(port, 1, 1)) { + /* vdisk_size should be set during the handshake, if it wasn't + * then the underlying disk is reserved by another system + */ + if (port->vdisk_size == -1) + return -ENODEV; + } else { + struct vio_disk_geom geom; + + err = generic_request(port, VD_OP_GET_DISKGEOM, + &geom, sizeof(geom)); + if (err < 0) { + printk(KERN_ERR PFX "VD_OP_GET_DISKGEOM returns " + "error %d\n", err); + return err; + } + port->vdisk_size = ((u64)geom.num_cyl * + (u64)geom.num_hd * + (u64)geom.num_sec); } - port->vdisk_size = ((u64)port->geom.num_cyl * - (u64)port->geom.num_hd * - (u64)port->geom.num_sec); - q = blk_init_queue(do_vdc_request, &port->vio.lock); if (!q) { printk(KERN_ERR PFX "%s: Could not allocate queue.\n", @@ -691,6 +745,10 @@ static int probe_disk(struct vdc_port *port) port->disk = g; + /* Each segment in a request is up to an aligned page in size. */ + blk_queue_segment_boundary(q, PAGE_SIZE - 1); + blk_queue_max_segment_size(q, PAGE_SIZE); + blk_queue_max_segments(q, port->ring_cookies); blk_queue_max_hw_sectors(q, port->max_xfer_size); g->major = vdc_major; @@ -704,9 +762,32 @@ static int probe_disk(struct vdc_port *port) set_capacity(g, port->vdisk_size); - printk(KERN_INFO PFX "%s: %u sectors (%u MB)\n", + if (vdc_version_supported(port, 1, 1)) { + switch (port->vdisk_mtype) { + case VD_MEDIA_TYPE_CD: + pr_info(PFX "Virtual CDROM %s\n", port->disk_name); + g->flags |= GENHD_FL_CD; + g->flags |= GENHD_FL_REMOVABLE; + set_disk_ro(g, 1); + break; + + case VD_MEDIA_TYPE_DVD: + pr_info(PFX "Virtual DVD %s\n", port->disk_name); + g->flags |= GENHD_FL_CD; + g->flags |= GENHD_FL_REMOVABLE; + set_disk_ro(g, 1); + break; + + case VD_MEDIA_TYPE_FIXED: + pr_info(PFX "Virtual Hard disk %s\n", port->disk_name); + break; + } + } + + pr_info(PFX "%s: %u sectors (%u MB) protocol %d.%d\n", g->disk_name, - port->vdisk_size, (port->vdisk_size >> (20 - 9))); + port->vdisk_size, (port->vdisk_size >> (20 - 9)), + port->vio.ver.major, port->vio.ver.minor); add_disk(g); @@ -765,6 +846,7 @@ static int vdc_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) else snprintf(port->disk_name, sizeof(port->disk_name), VDCBLK_NAME "%c", 'a' + ((int)vdev->dev_no % 26)); + port->vdisk_size = -1; err = vio_driver_init(&port->vio, vdev, VDEV_DISK, vdc_versions, ARRAY_SIZE(vdc_versions), diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 64c60edcdfbc..63fc7f06a014 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -763,6 +763,7 @@ again: BUG_ON(new_map_idx >= segs_to_map); if (unlikely(map[new_map_idx].status != 0)) { pr_debug(DRV_PFX "invalid buffer -- could not remap it\n"); + put_free_pages(blkif, &pages[seg_idx]->page, 1); pages[seg_idx]->handle = BLKBACK_INVALID_HANDLE; ret |= 1; goto next; diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 51c557cfd92b..d8ddb8e2adc1 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -447,7 +447,8 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, } if (page_zero_filled(uncmem)) { - kunmap_atomic(user_mem); + if (user_mem) + kunmap_atomic(user_mem); /* Free memory associated with this sector now. */ write_lock(&zram->meta->tb_lock); zram_free_page(zram, index); diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c index b11949c5b029..f667e37394da 100644 --- a/drivers/bluetooth/ath3k.c +++ b/drivers/bluetooth/ath3k.c @@ -157,6 +157,8 @@ static const struct usb_device_id ath3k_blist_tbl[] = { #define USB_REQ_DFU_DNLOAD 1 #define BULK_SIZE 4096 #define FW_HDR_SIZE 20 +#define TIMEGAP_USEC_MIN 50 +#define TIMEGAP_USEC_MAX 100 static int ath3k_load_firmware(struct usb_device *udev, const struct firmware *firmware) @@ -187,6 +189,9 @@ static int ath3k_load_firmware(struct usb_device *udev, count -= 20; while (count) { + /* workaround the compatibility issue with xHCI controller*/ + usleep_range(TIMEGAP_USEC_MIN, TIMEGAP_USEC_MAX); + size = min_t(uint, count, BULK_SIZE); pipe = usb_sndbulkpipe(udev, 0x02); memcpy(send_buf, firmware->data + sent, size); @@ -283,6 +288,9 @@ static int ath3k_load_fwfile(struct usb_device *udev, count -= size; while (count) { + /* workaround the compatibility issue with xHCI controller*/ + usleep_range(TIMEGAP_USEC_MIN, TIMEGAP_USEC_MAX); + size = min_t(uint, count, BULK_SIZE); pipe = usb_sndbulkpipe(udev, 0x02); diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 1c7b5040d921..e00c3f84a4cf 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -309,6 +309,9 @@ static void btusb_intr_complete(struct urb *urb) BT_ERR("%s corrupted event packet", hdev->name); hdev->stat.err_rx++; } + } else if (urb->status == -ENOENT) { + /* Avoid suspend failed when usb_kill_urb */ + return; } if (!test_bit(BTUSB_INTR_RUNNING, &data->flags)) @@ -397,6 +400,9 @@ static void btusb_bulk_complete(struct urb *urb) BT_ERR("%s corrupted ACL packet", hdev->name); hdev->stat.err_rx++; } + } else if (urb->status == -ENOENT) { + /* Avoid suspend failed when usb_kill_urb */ + return; } if (!test_bit(BTUSB_BULK_RUNNING, &data->flags)) @@ -491,6 +497,9 @@ static void btusb_isoc_complete(struct urb *urb) hdev->stat.err_rx++; } } + } else if (urb->status == -ENOENT) { + /* Avoid suspend failed when usb_kill_urb */ + return; } if (!test_bit(BTUSB_ISOC_RUNNING, &data->flags)) diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c index e36a0245f2c1..56519927479f 100644 --- a/drivers/bluetooth/hci_h5.c +++ b/drivers/bluetooth/hci_h5.c @@ -237,7 +237,7 @@ static void h5_pkt_cull(struct h5 *h5) break; to_remove--; - seq = (seq - 1) % 8; + seq = (seq - 1) & 0x07; } if (seq != h5->rx_ack) diff --git a/drivers/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c index 372ae72cce34..e990deed2d33 100644 --- a/drivers/bus/mvebu-mbus.c +++ b/drivers/bus/mvebu-mbus.c @@ -181,12 +181,25 @@ static void mvebu_mbus_disable_window(struct mvebu_mbus_state *mbus, } /* Checks whether the given window number is available */ + +/* On Armada XP, 375 and 38x the MBus window 13 has the remap + * capability, like windows 0 to 7. However, the mvebu-mbus driver + * isn't currently taking into account this special case, which means + * that when window 13 is actually used, the remap registers are left + * to 0, making the device using this MBus window unavailable. The + * quick fix for stable is to not use window 13. A follow up patch + * will correctly handle this window. +*/ static int mvebu_mbus_window_is_free(struct mvebu_mbus_state *mbus, const int win) { void __iomem *addr = mbus->mbuswins_base + mbus->soc->win_cfg_offset(win); u32 ctrl = readl(addr + WIN_CTRL_OFF); + + if (win == 13) + return false; + return !(ctrl & WIN_CTRL_ENABLE); } diff --git a/drivers/char/hw_random/pseries-rng.c b/drivers/char/hw_random/pseries-rng.c index ab7ffdec0ec3..f38f2c13e79c 100644 --- a/drivers/char/hw_random/pseries-rng.c +++ b/drivers/char/hw_random/pseries-rng.c @@ -25,18 +25,21 @@ #include <asm/vio.h> -static int pseries_rng_data_read(struct hwrng *rng, u32 *data) +static int pseries_rng_read(struct hwrng *rng, void *data, size_t max, bool wait) { + u64 buffer[PLPAR_HCALL_BUFSIZE]; + size_t size = max < 8 ? max : 8; int rc; - rc = plpar_hcall(H_RANDOM, (unsigned long *)data); + rc = plpar_hcall(H_RANDOM, (unsigned long *)buffer); if (rc != H_SUCCESS) { pr_err_ratelimited("H_RANDOM call failed %d\n", rc); return -EIO; } + memcpy(data, buffer, size); /* The hypervisor interface returns 64 bits */ - return 8; + return size; } /** @@ -55,7 +58,7 @@ static unsigned long pseries_rng_get_desired_dma(struct vio_dev *vdev) static struct hwrng pseries_rng = { .name = KBUILD_MODNAME, - .data_read = pseries_rng_data_read, + .read = pseries_rng_read, }; static int __init pseries_rng_probe(struct vio_dev *dev, diff --git a/drivers/char/random.c b/drivers/char/random.c index 429b75bb60e8..8a64dbeae7b1 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1063,8 +1063,8 @@ static void extract_buf(struct entropy_store *r, __u8 *out) * pool while mixing, and hash one final time. */ sha_transform(hash.w, extract, workspace); - memset(extract, 0, sizeof(extract)); - memset(workspace, 0, sizeof(workspace)); + memzero_explicit(extract, sizeof(extract)); + memzero_explicit(workspace, sizeof(workspace)); /* * In case the hash function has some recognizable output @@ -1076,7 +1076,7 @@ static void extract_buf(struct entropy_store *r, __u8 *out) hash.w[2] ^= rol32(hash.w[2], 16); memcpy(out, &hash, EXTRACT_SIZE); - memset(&hash, 0, sizeof(hash)); + memzero_explicit(&hash, sizeof(hash)); } static ssize_t extract_entropy(struct entropy_store *r, void *buf, @@ -1124,7 +1124,7 @@ static ssize_t extract_entropy(struct entropy_store *r, void *buf, } /* Wipe data just returned from memory */ - memset(tmp, 0, sizeof(tmp)); + memzero_explicit(tmp, sizeof(tmp)); return ret; } @@ -1162,7 +1162,7 @@ static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf, } /* Wipe data just returned from memory */ - memset(tmp, 0, sizeof(tmp)); + memzero_explicit(tmp, sizeof(tmp)); return ret; } diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index 6af17002a115..cfb9089887bd 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -1122,7 +1122,7 @@ struct tpm_chip *tpm_register_hardware(struct device *dev, /* Make chip available */ spin_lock(&driver_lock); - list_add_rcu(&chip->list, &tpm_chip_list); + list_add_tail_rcu(&chip->list, &tpm_chip_list); spin_unlock(&driver_lock); return chip; diff --git a/drivers/char/tpm/tpm_i2c_atmel.c b/drivers/char/tpm/tpm_i2c_atmel.c index 77272925dee6..503a85ae176c 100644 --- a/drivers/char/tpm/tpm_i2c_atmel.c +++ b/drivers/char/tpm/tpm_i2c_atmel.c @@ -168,6 +168,10 @@ static int i2c_atmel_probe(struct i2c_client *client, chip->vendor.priv = devm_kzalloc(dev, sizeof(struct priv_data), GFP_KERNEL); + if (!chip->vendor.priv) { + rc = -ENOMEM; + goto out_err; + } /* Default timeouts */ chip->vendor.timeout_a = msecs_to_jiffies(TPM_I2C_SHORT_TIMEOUT); diff --git a/drivers/char/tpm/tpm_i2c_nuvoton.c b/drivers/char/tpm/tpm_i2c_nuvoton.c index 7b158efd49f7..23c7b137a7fd 100644 --- a/drivers/char/tpm/tpm_i2c_nuvoton.c +++ b/drivers/char/tpm/tpm_i2c_nuvoton.c @@ -538,6 +538,11 @@ static int i2c_nuvoton_probe(struct i2c_client *client, chip->vendor.priv = devm_kzalloc(dev, sizeof(struct priv_data), GFP_KERNEL); + if (!chip->vendor.priv) { + rc = -ENOMEM; + goto out_err; + } + init_waitqueue_head(&chip->vendor.read_queue); init_waitqueue_head(&chip->vendor.int_queue); diff --git a/drivers/char/tpm/tpm_i2c_stm_st33.c b/drivers/char/tpm/tpm_i2c_stm_st33.c index be9af2e6ca5a..576d1112ac57 100644 --- a/drivers/char/tpm/tpm_i2c_stm_st33.c +++ b/drivers/char/tpm/tpm_i2c_stm_st33.c @@ -488,7 +488,7 @@ static int tpm_stm_i2c_send(struct tpm_chip *chip, unsigned char *buf, if (burstcnt < 0) return burstcnt; size = min_t(int, len - i - 1, burstcnt); - ret = I2C_WRITE_DATA(client, TPM_DATA_FIFO, buf, size); + ret = I2C_WRITE_DATA(client, TPM_DATA_FIFO, buf + i, size); if (ret < 0) goto out_err; diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c index af74c57e5090..102463ba745d 100644 --- a/drivers/char/tpm/tpm_ibmvtpm.c +++ b/drivers/char/tpm/tpm_ibmvtpm.c @@ -124,7 +124,7 @@ static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count) { struct ibmvtpm_dev *ibmvtpm; struct ibmvtpm_crq crq; - u64 *word = (u64 *) &crq; + __be64 *word = (__be64 *)&crq; int rc; ibmvtpm = (struct ibmvtpm_dev *)TPM_VPRIV(chip); @@ -145,10 +145,11 @@ static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count) memcpy((void *)ibmvtpm->rtce_buf, (void *)buf, count); crq.valid = (u8)IBMVTPM_VALID_CMD; crq.msg = (u8)VTPM_TPM_COMMAND; - crq.len = (u16)count; - crq.data = ibmvtpm->rtce_dma_handle; + crq.len = cpu_to_be16(count); + crq.data = cpu_to_be32(ibmvtpm->rtce_dma_handle); - rc = ibmvtpm_send_crq(ibmvtpm->vdev, word[0], word[1]); + rc = ibmvtpm_send_crq(ibmvtpm->vdev, be64_to_cpu(word[0]), + be64_to_cpu(word[1])); if (rc != H_SUCCESS) { dev_err(ibmvtpm->dev, "tpm_ibmvtpm_send failed rc=%d\n", rc); rc = 0; @@ -186,7 +187,8 @@ static int ibmvtpm_crq_get_rtce_size(struct ibmvtpm_dev *ibmvtpm) crq.valid = (u8)IBMVTPM_VALID_CMD; crq.msg = (u8)VTPM_GET_RTCE_BUFFER_SIZE; - rc = ibmvtpm_send_crq(ibmvtpm->vdev, buf[0], buf[1]); + rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]), + cpu_to_be64(buf[1])); if (rc != H_SUCCESS) dev_err(ibmvtpm->dev, "ibmvtpm_crq_get_rtce_size failed rc=%d\n", rc); @@ -212,7 +214,8 @@ static int ibmvtpm_crq_get_version(struct ibmvtpm_dev *ibmvtpm) crq.valid = (u8)IBMVTPM_VALID_CMD; crq.msg = (u8)VTPM_GET_VERSION; - rc = ibmvtpm_send_crq(ibmvtpm->vdev, buf[0], buf[1]); + rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]), + cpu_to_be64(buf[1])); if (rc != H_SUCCESS) dev_err(ibmvtpm->dev, "ibmvtpm_crq_get_version failed rc=%d\n", rc); @@ -307,6 +310,14 @@ static int tpm_ibmvtpm_remove(struct vio_dev *vdev) static unsigned long tpm_ibmvtpm_get_desired_dma(struct vio_dev *vdev) { struct ibmvtpm_dev *ibmvtpm = ibmvtpm_get_data(&vdev->dev); + + /* ibmvtpm initializes at probe time, so the data we are + * asking for may not be set yet. Estimate that 4K required + * for TCE-mapped buffer in addition to CRQ. + */ + if (!ibmvtpm) + return CRQ_RES_BUF_SIZE + PAGE_SIZE; + return CRQ_RES_BUF_SIZE + ibmvtpm->rtce_size; } @@ -327,7 +338,8 @@ static int tpm_ibmvtpm_suspend(struct device *dev) crq.valid = (u8)IBMVTPM_VALID_CMD; crq.msg = (u8)VTPM_PREPARE_TO_SUSPEND; - rc = ibmvtpm_send_crq(ibmvtpm->vdev, buf[0], buf[1]); + rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]), + cpu_to_be64(buf[1])); if (rc != H_SUCCESS) dev_err(ibmvtpm->dev, "tpm_ibmvtpm_suspend failed rc=%d\n", rc); @@ -472,11 +484,11 @@ static void ibmvtpm_crq_process(struct ibmvtpm_crq *crq, case IBMVTPM_VALID_CMD: switch (crq->msg) { case VTPM_GET_RTCE_BUFFER_SIZE_RES: - if (crq->len <= 0) { + if (be16_to_cpu(crq->len) <= 0) { dev_err(ibmvtpm->dev, "Invalid rtce size\n"); return; } - ibmvtpm->rtce_size = crq->len; + ibmvtpm->rtce_size = be16_to_cpu(crq->len); ibmvtpm->rtce_buf = kmalloc(ibmvtpm->rtce_size, GFP_KERNEL); if (!ibmvtpm->rtce_buf) { @@ -497,11 +509,11 @@ static void ibmvtpm_crq_process(struct ibmvtpm_crq *crq, return; case VTPM_GET_VERSION_RES: - ibmvtpm->vtpm_version = crq->data; + ibmvtpm->vtpm_version = be32_to_cpu(crq->data); return; case VTPM_TPM_COMMAND_RES: /* len of the data in rtce buffer */ - ibmvtpm->res_len = crq->len; + ibmvtpm->res_len = be16_to_cpu(crq->len); wake_up_interruptible(&ibmvtpm->wq); return; default: diff --git a/drivers/char/tpm/tpm_ibmvtpm.h b/drivers/char/tpm/tpm_ibmvtpm.h index bd82a791f995..b2c231b1beec 100644 --- a/drivers/char/tpm/tpm_ibmvtpm.h +++ b/drivers/char/tpm/tpm_ibmvtpm.h @@ -22,9 +22,9 @@ struct ibmvtpm_crq { u8 valid; u8 msg; - u16 len; - u32 data; - u64 reserved; + __be16 len; + __be32 data; + __be64 reserved; } __attribute__((packed, aligned(8))); struct ibmvtpm_crq_queue { diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index 2c46734b266d..51350cd0847e 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -75,6 +75,10 @@ enum tis_defaults { #define TPM_DID_VID(l) (0x0F00 | ((l) << 12)) #define TPM_RID(l) (0x0F04 | ((l) << 12)) +struct priv_data { + bool irq_tested; +}; + static LIST_HEAD(tis_chips); static DEFINE_MUTEX(tis_lock); @@ -338,12 +342,27 @@ out_err: return rc; } +static void disable_interrupts(struct tpm_chip *chip) +{ + u32 intmask; + + intmask = + ioread32(chip->vendor.iobase + + TPM_INT_ENABLE(chip->vendor.locality)); + intmask &= ~TPM_GLOBAL_INT_ENABLE; + iowrite32(intmask, + chip->vendor.iobase + + TPM_INT_ENABLE(chip->vendor.locality)); + free_irq(chip->vendor.irq, chip); + chip->vendor.irq = 0; +} + /* * If interrupts are used (signaled by an irq set in the vendor structure) * tpm.c can skip polling for the data to be available as the interrupt is * waited for here */ -static int tpm_tis_send(struct tpm_chip *chip, u8 *buf, size_t len) +static int tpm_tis_send_main(struct tpm_chip *chip, u8 *buf, size_t len) { int rc; u32 ordinal; @@ -373,6 +392,30 @@ out_err: return rc; } +static int tpm_tis_send(struct tpm_chip *chip, u8 *buf, size_t len) +{ + int rc, irq; + struct priv_data *priv = chip->vendor.priv; + + if (!chip->vendor.irq || priv->irq_tested) + return tpm_tis_send_main(chip, buf, len); + + /* Verify receipt of the expected IRQ */ + irq = chip->vendor.irq; + chip->vendor.irq = 0; + rc = tpm_tis_send_main(chip, buf, len); + chip->vendor.irq = irq; + if (!priv->irq_tested) + msleep(1); + if (!priv->irq_tested) { + disable_interrupts(chip); + dev_err(chip->dev, + FW_BUG "TPM interrupt not working, polling instead\n"); + } + priv->irq_tested = true; + return rc; +} + struct tis_vendor_timeout_override { u32 did_vid; unsigned long timeout_us[4]; @@ -505,6 +548,7 @@ static irqreturn_t tis_int_handler(int dummy, void *dev_id) if (interrupt == 0) return IRQ_NONE; + ((struct priv_data *)chip->vendor.priv)->irq_tested = true; if (interrupt & TPM_INTF_DATA_AVAIL_INT) wake_up_interruptible(&chip->vendor.read_queue); if (interrupt & TPM_INTF_LOCALITY_CHANGE_INT) @@ -534,9 +578,14 @@ static int tpm_tis_init(struct device *dev, resource_size_t start, u32 vendor, intfcaps, intmask; int rc, i, irq_s, irq_e, probe; struct tpm_chip *chip; + struct priv_data *priv; + priv = devm_kzalloc(dev, sizeof(struct priv_data), GFP_KERNEL); + if (priv == NULL) + return -ENOMEM; if (!(chip = tpm_register_hardware(dev, &tpm_tis))) return -ENODEV; + chip->vendor.priv = priv; chip->vendor.iobase = ioremap(start, len); if (!chip->vendor.iobase) { @@ -605,19 +654,6 @@ static int tpm_tis_init(struct device *dev, resource_size_t start, if (intfcaps & TPM_INTF_DATA_AVAIL_INT) dev_dbg(dev, "\tData Avail Int Support\n"); - /* get the timeouts before testing for irqs */ - if (tpm_get_timeouts(chip)) { - dev_err(dev, "Could not get TPM timeouts and durations\n"); - rc = -ENODEV; - goto out_err; - } - - if (tpm_do_selftest(chip)) { - dev_err(dev, "TPM self test failed\n"); - rc = -ENODEV; - goto out_err; - } - /* INTERRUPT Setup */ init_waitqueue_head(&chip->vendor.read_queue); init_waitqueue_head(&chip->vendor.int_queue); @@ -719,6 +755,18 @@ static int tpm_tis_init(struct device *dev, resource_size_t start, } } + if (tpm_get_timeouts(chip)) { + dev_err(dev, "Could not get TPM timeouts and durations\n"); + rc = -ENODEV; + goto out_err; + } + + if (tpm_do_selftest(chip)) { + dev_err(dev, "TPM self test failed\n"); + rc = -ENODEV; + goto out_err; + } + INIT_LIST_HEAD(&chip->vendor.list); mutex_lock(&tis_lock); list_add(&chip->vendor.list, &tis_chips); diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 6928d094451d..b08eadb4b1d2 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -142,6 +142,7 @@ struct ports_device { * notification */ struct work_struct control_work; + struct work_struct config_work; struct list_head ports; @@ -1832,10 +1833,21 @@ static void config_intr(struct virtio_device *vdev) portdev = vdev->priv; + if (!use_multiport(portdev)) + schedule_work(&portdev->config_work); +} + +static void config_work_handler(struct work_struct *work) +{ + struct ports_device *portdev; + + portdev = container_of(work, struct ports_device, control_work); if (!use_multiport(portdev)) { + struct virtio_device *vdev; struct port *port; u16 rows, cols; + vdev = portdev->vdev; virtio_cread(vdev, struct virtio_console_config, cols, &cols); virtio_cread(vdev, struct virtio_console_config, rows, &rows); @@ -2024,12 +2036,14 @@ static int virtcons_probe(struct virtio_device *vdev) spin_lock_init(&portdev->ports_lock); INIT_LIST_HEAD(&portdev->ports); + INIT_WORK(&portdev->config_work, &config_work_handler); + INIT_WORK(&portdev->control_work, &control_work_handler); + if (multiport) { unsigned int nr_added_bufs; spin_lock_init(&portdev->c_ivq_lock); spin_lock_init(&portdev->c_ovq_lock); - INIT_WORK(&portdev->control_work, &control_work_handler); nr_added_bufs = fill_queue(portdev->c_ivq, &portdev->c_ivq_lock); @@ -2097,6 +2111,8 @@ static void virtcons_remove(struct virtio_device *vdev) /* Finish up work that's lined up */ if (use_multiport(portdev)) cancel_work_sync(&portdev->control_work); + else + cancel_work_sync(&portdev->config_work); list_for_each_entry_safe(port, port2, &portdev->ports, list) unplug_port(port); @@ -2148,6 +2164,7 @@ static int virtcons_freeze(struct virtio_device *vdev) virtqueue_disable_cb(portdev->c_ivq); cancel_work_sync(&portdev->control_work); + cancel_work_sync(&portdev->config_work); /* * Once more: if control_work_handler() was running, it would * enable the cb as the last step. diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c index 5543b7df8e16..d95f120af5c5 100644 --- a/drivers/clk/clk-divider.c +++ b/drivers/clk/clk-divider.c @@ -24,7 +24,7 @@ * Traits of this clock: * prepare - clk_prepare only ensures that parents are prepared * enable - clk_enable only ensures that parents are enabled - * rate - rate is adjustable. clk->rate = parent->rate / divisor + * rate - rate is adjustable. clk->rate = DIV_ROUND_UP(parent->rate / divisor) * parent - fixed parent. No clk_set_parent support */ @@ -43,6 +43,17 @@ static unsigned int _get_table_maxdiv(const struct clk_div_table *table) return maxdiv; } +static unsigned int _get_table_mindiv(const struct clk_div_table *table) +{ + unsigned int mindiv = UINT_MAX; + const struct clk_div_table *clkt; + + for (clkt = table; clkt->div; clkt++) + if (clkt->div < mindiv) + mindiv = clkt->div; + return mindiv; +} + static unsigned int _get_maxdiv(struct clk_divider *divider) { if (divider->flags & CLK_DIVIDER_ONE_BASED) @@ -115,7 +126,7 @@ static unsigned long clk_divider_recalc_rate(struct clk_hw *hw, return parent_rate; } - return parent_rate / div; + return DIV_ROUND_UP(parent_rate, div); } /* @@ -144,6 +155,91 @@ static bool _is_valid_div(struct clk_divider *divider, unsigned int div) return true; } +static int _round_up_table(const struct clk_div_table *table, int div) +{ + const struct clk_div_table *clkt; + int up = INT_MAX; + + for (clkt = table; clkt->div; clkt++) { + if (clkt->div == div) + return clkt->div; + else if (clkt->div < div) + continue; + + if ((clkt->div - div) < (up - div)) + up = clkt->div; + } + + return up; +} + +static int _round_down_table(const struct clk_div_table *table, int div) +{ + const struct clk_div_table *clkt; + int down = _get_table_mindiv(table); + + for (clkt = table; clkt->div; clkt++) { + if (clkt->div == div) + return clkt->div; + else if (clkt->div > div) + continue; + + if ((div - clkt->div) < (div - down)) + down = clkt->div; + } + + return down; +} + +static int _div_round_up(struct clk_divider *divider, + unsigned long parent_rate, unsigned long rate) +{ + int div = DIV_ROUND_UP(parent_rate, rate); + + if (divider->flags & CLK_DIVIDER_POWER_OF_TWO) + div = __roundup_pow_of_two(div); + if (divider->table) + div = _round_up_table(divider->table, div); + + return div; +} + +static int _div_round_closest(struct clk_divider *divider, + unsigned long parent_rate, unsigned long rate) +{ + int up, down, div; + + up = down = div = DIV_ROUND_CLOSEST(parent_rate, rate); + + if (divider->flags & CLK_DIVIDER_POWER_OF_TWO) { + up = __roundup_pow_of_two(div); + down = __rounddown_pow_of_two(div); + } else if (divider->table) { + up = _round_up_table(divider->table, div); + down = _round_down_table(divider->table, div); + } + + return (up - div) <= (div - down) ? up : down; +} + +static int _div_round(struct clk_divider *divider, unsigned long parent_rate, + unsigned long rate) +{ + if (divider->flags & CLK_DIVIDER_ROUND_CLOSEST) + return _div_round_closest(divider, parent_rate, rate); + + return _div_round_up(divider, parent_rate, rate); +} + +static bool _is_best_div(struct clk_divider *divider, + unsigned long rate, unsigned long now, unsigned long best) +{ + if (divider->flags & CLK_DIVIDER_ROUND_CLOSEST) + return abs(rate - now) < abs(rate - best); + + return now <= rate && now > best; +} + static int clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate, unsigned long *best_parent_rate) { @@ -159,7 +255,7 @@ static int clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate, if (!(__clk_get_flags(hw->clk) & CLK_SET_RATE_PARENT)) { parent_rate = *best_parent_rate; - bestdiv = DIV_ROUND_UP(parent_rate, rate); + bestdiv = _div_round(divider, parent_rate, rate); bestdiv = bestdiv == 0 ? 1 : bestdiv; bestdiv = bestdiv > maxdiv ? maxdiv : bestdiv; return bestdiv; @@ -185,8 +281,8 @@ static int clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate, } parent_rate = __clk_round_rate(__clk_get_parent(hw->clk), MULT_ROUND_UP(rate, i)); - now = parent_rate / i; - if (now <= rate && now > best) { + now = DIV_ROUND_UP(parent_rate, i); + if (_is_best_div(divider, rate, now, best)) { bestdiv = i; best = now; *best_parent_rate = parent_rate; @@ -207,7 +303,7 @@ static long clk_divider_round_rate(struct clk_hw *hw, unsigned long rate, int div; div = clk_divider_bestdiv(hw, rate, prate); - return *prate / div; + return DIV_ROUND_UP(*prate, div); } static int clk_divider_set_rate(struct clk_hw *hw, unsigned long rate, @@ -218,7 +314,11 @@ static int clk_divider_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long flags = 0; u32 val; - div = parent_rate / rate; + div = DIV_ROUND_UP(parent_rate, rate); + + if (!_is_valid_div(divider, div)) + return -EINVAL; + value = _get_val(divider, div); if (value > div_mask(divider)) diff --git a/drivers/clk/clk-gate.c b/drivers/clk/clk-gate.c index 4a58c55255bd..797bab97cea6 100644 --- a/drivers/clk/clk-gate.c +++ b/drivers/clk/clk-gate.c @@ -128,7 +128,7 @@ struct clk *clk_register_gate(struct device *dev, const char *name, struct clk_init_data init; if (clk_gate_flags & CLK_GATE_HIWORD_MASK) { - if (bit_idx > 16) { + if (bit_idx > 15) { pr_err("gate bit exceeds LOWORD field\n"); return ERR_PTR(-EINVAL); } diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index b94a311e5ab6..7145f6d93567 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1487,6 +1487,7 @@ static struct clk *clk_propagate_rate_change(struct clk *clk, unsigned long even static void clk_change_rate(struct clk *clk) { struct clk *child; + struct hlist_node *tmp; unsigned long old_rate; unsigned long best_parent_rate = 0; bool skip_set_rate = false; @@ -1525,7 +1526,11 @@ static void clk_change_rate(struct clk *clk) if (clk->notifier_count && old_rate != clk->rate) __clk_notify(clk, POST_RATE_CHANGE, old_rate, clk->rate); - hlist_for_each_entry(child, &clk->children, child_node) { + /* + * Use safe iteration, as change_rate can actually swap parents + * for certain clock types. + */ + hlist_for_each_entry_safe(child, tmp, &clk->children, child_node) { /* Skip children who will be reparented to another clock */ if (child->new_parent && child->new_parent != clk) continue; @@ -2227,14 +2232,17 @@ int __clk_get(struct clk *clk) void __clk_put(struct clk *clk) { + struct module *owner; + if (!clk || WARN_ON_ONCE(IS_ERR(clk))) return; clk_prepare_lock(); + owner = clk->owner; kref_put(&clk->ref, __clk_release); clk_prepare_unlock(); - module_put(clk->owner); + module_put(owner); } /*** clk rate change notifiers ***/ diff --git a/drivers/clk/qcom/mmcc-msm8960.c b/drivers/clk/qcom/mmcc-msm8960.c index 9be47a829144..f3c95d648a53 100644 --- a/drivers/clk/qcom/mmcc-msm8960.c +++ b/drivers/clk/qcom/mmcc-msm8960.c @@ -37,6 +37,8 @@ #define P_PLL2 2 #define P_PLL3 3 +#define F_MN(f, s, _m, _n) { .freq = f, .src = s, .m = _m, .n = _n } + static u8 mmcc_pxo_pll8_pll2_map[] = { [P_PXO] = 0, [P_PLL8] = 2, @@ -58,8 +60,8 @@ static u8 mmcc_pxo_pll8_pll2_pll3_map[] = { static const char *mmcc_pxo_pll8_pll2_pll3[] = { "pxo", - "pll2", "pll8_vote", + "pll2", "pll3", }; @@ -709,18 +711,18 @@ static struct clk_branch csiphy2_timer_clk = { }; static struct freq_tbl clk_tbl_gfx2d[] = { - { 27000000, P_PXO, 1, 0 }, - { 48000000, P_PLL8, 1, 8 }, - { 54857000, P_PLL8, 1, 7 }, - { 64000000, P_PLL8, 1, 6 }, - { 76800000, P_PLL8, 1, 5 }, - { 96000000, P_PLL8, 1, 4 }, - { 128000000, P_PLL8, 1, 3 }, - { 145455000, P_PLL2, 2, 11 }, - { 160000000, P_PLL2, 1, 5 }, - { 177778000, P_PLL2, 2, 9 }, - { 200000000, P_PLL2, 1, 4 }, - { 228571000, P_PLL2, 2, 7 }, + F_MN( 27000000, P_PXO, 1, 0), + F_MN( 48000000, P_PLL8, 1, 8), + F_MN( 54857000, P_PLL8, 1, 7), + F_MN( 64000000, P_PLL8, 1, 6), + F_MN( 76800000, P_PLL8, 1, 5), + F_MN( 96000000, P_PLL8, 1, 4), + F_MN(128000000, P_PLL8, 1, 3), + F_MN(145455000, P_PLL2, 2, 11), + F_MN(160000000, P_PLL2, 1, 5), + F_MN(177778000, P_PLL2, 2, 9), + F_MN(200000000, P_PLL2, 1, 4), + F_MN(228571000, P_PLL2, 2, 7), { } }; @@ -841,22 +843,22 @@ static struct clk_branch gfx2d1_clk = { }; static struct freq_tbl clk_tbl_gfx3d[] = { - { 27000000, P_PXO, 1, 0 }, - { 48000000, P_PLL8, 1, 8 }, - { 54857000, P_PLL8, 1, 7 }, - { 64000000, P_PLL8, 1, 6 }, - { 76800000, P_PLL8, 1, 5 }, - { 96000000, P_PLL8, 1, 4 }, - { 128000000, P_PLL8, 1, 3 }, - { 145455000, P_PLL2, 2, 11 }, - { 160000000, P_PLL2, 1, 5 }, - { 177778000, P_PLL2, 2, 9 }, - { 200000000, P_PLL2, 1, 4 }, - { 228571000, P_PLL2, 2, 7 }, - { 266667000, P_PLL2, 1, 3 }, - { 300000000, P_PLL3, 1, 4 }, - { 320000000, P_PLL2, 2, 5 }, - { 400000000, P_PLL2, 1, 2 }, + F_MN( 27000000, P_PXO, 1, 0), + F_MN( 48000000, P_PLL8, 1, 8), + F_MN( 54857000, P_PLL8, 1, 7), + F_MN( 64000000, P_PLL8, 1, 6), + F_MN( 76800000, P_PLL8, 1, 5), + F_MN( 96000000, P_PLL8, 1, 4), + F_MN(128000000, P_PLL8, 1, 3), + F_MN(145455000, P_PLL2, 2, 11), + F_MN(160000000, P_PLL2, 1, 5), + F_MN(177778000, P_PLL2, 2, 9), + F_MN(200000000, P_PLL2, 1, 4), + F_MN(228571000, P_PLL2, 2, 7), + F_MN(266667000, P_PLL2, 1, 3), + F_MN(300000000, P_PLL3, 1, 4), + F_MN(320000000, P_PLL2, 2, 5), + F_MN(400000000, P_PLL2, 1, 2), { } }; @@ -896,7 +898,7 @@ static struct clk_dyn_rcg gfx3d_src = { .hw.init = &(struct clk_init_data){ .name = "gfx3d_src", .parent_names = mmcc_pxo_pll8_pll2_pll3, - .num_parents = 3, + .num_parents = 4, .ops = &clk_dyn_rcg_ops, }, }, @@ -994,7 +996,7 @@ static struct clk_rcg jpegd_src = { .ns_reg = 0x00ac, .p = { .pre_div_shift = 12, - .pre_div_width = 2, + .pre_div_width = 4, }, .s = { .src_sel_shift = 0, @@ -1114,7 +1116,7 @@ static struct clk_branch mdp_lut_clk = { .enable_reg = 0x016c, .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ - .parent_names = (const char *[]){ "mdp_clk" }, + .parent_names = (const char *[]){ "mdp_src" }, .num_parents = 1, .name = "mdp_lut_clk", .ops = &clk_branch_ops, @@ -1341,15 +1343,15 @@ static struct clk_branch hdmi_app_clk = { }; static struct freq_tbl clk_tbl_vcodec[] = { - { 27000000, P_PXO, 1, 0 }, - { 32000000, P_PLL8, 1, 12 }, - { 48000000, P_PLL8, 1, 8 }, - { 54860000, P_PLL8, 1, 7 }, - { 96000000, P_PLL8, 1, 4 }, - { 133330000, P_PLL2, 1, 6 }, - { 200000000, P_PLL2, 1, 4 }, - { 228570000, P_PLL2, 2, 7 }, - { 266670000, P_PLL2, 1, 3 }, + F_MN( 27000000, P_PXO, 1, 0), + F_MN( 32000000, P_PLL8, 1, 12), + F_MN( 48000000, P_PLL8, 1, 8), + F_MN( 54860000, P_PLL8, 1, 7), + F_MN( 96000000, P_PLL8, 1, 4), + F_MN(133330000, P_PLL2, 1, 6), + F_MN(200000000, P_PLL2, 1, 4), + F_MN(228570000, P_PLL2, 2, 7), + F_MN(266670000, P_PLL2, 1, 3), { } }; diff --git a/drivers/clk/samsung/clk-exynos-audss.c b/drivers/clk/samsung/clk-exynos-audss.c index 884187fbfe00..7f30b94c00a5 100644 --- a/drivers/clk/samsung/clk-exynos-audss.c +++ b/drivers/clk/samsung/clk-exynos-audss.c @@ -210,6 +210,10 @@ static int exynos_audss_clk_remove(struct platform_device *pdev) { int i; +#ifdef CONFIG_PM_SLEEP + unregister_syscore_ops(&exynos_audss_clk_syscore_ops); +#endif + of_clk_del_provider(pdev->dev.of_node); for (i = 0; i < clk_data.clk_num; i++) { diff --git a/drivers/clk/sunxi/clk-factors.c b/drivers/clk/sunxi/clk-factors.c index 9e232644f07e..ea4db844aee3 100644 --- a/drivers/clk/sunxi/clk-factors.c +++ b/drivers/clk/sunxi/clk-factors.c @@ -62,7 +62,7 @@ static unsigned long clk_factors_recalc_rate(struct clk_hw *hw, p = FACTOR_GET(config->pshift, config->pwidth, reg); /* Calculate the rate */ - rate = (parent_rate * n * (k + 1) >> p) / (m + 1); + rate = (parent_rate * (n + config->n_start) * (k + 1) >> p) / (m + 1); return rate; } diff --git a/drivers/clk/sunxi/clk-factors.h b/drivers/clk/sunxi/clk-factors.h index 02e1a43ebac7..d2d0efa39379 100644 --- a/drivers/clk/sunxi/clk-factors.h +++ b/drivers/clk/sunxi/clk-factors.h @@ -15,6 +15,7 @@ struct clk_factors_config { u8 mwidth; u8 pshift; u8 pwidth; + u8 n_start; }; struct clk_factors { diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c index abb6c5ac8a10..06a14b808683 100644 --- a/drivers/clk/sunxi/clk-sunxi.c +++ b/drivers/clk/sunxi/clk-sunxi.c @@ -407,6 +407,7 @@ static struct clk_factors_config sun6i_a31_pll1_config = { .kwidth = 2, .mshift = 0, .mwidth = 2, + .n_start = 1, }; static struct clk_factors_config sun4i_pll5_config = { diff --git a/drivers/clk/zynq/clkc.c b/drivers/clk/zynq/clkc.c index 09dd0173ea0a..5f52f3f62644 100644 --- a/drivers/clk/zynq/clkc.c +++ b/drivers/clk/zynq/clkc.c @@ -300,6 +300,7 @@ static void __init zynq_clk_setup(struct device_node *np) clks[cpu_2x] = clk_register_gate(NULL, clk_output_name[cpu_2x], "cpu_2x_div", CLK_IGNORE_UNUSED, SLCR_ARM_CLK_CTRL, 26, 0, &armclk_lock); + clk_prepare_enable(clks[cpu_2x]); clk = clk_register_fixed_factor(NULL, "cpu_1x_div", "cpu_div", 0, 1, 4 + 2 * tmp); diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c index e252939b9ee1..831b48287a22 100644 --- a/drivers/clocksource/exynos_mct.c +++ b/drivers/clocksource/exynos_mct.c @@ -98,8 +98,8 @@ static void exynos4_mct_write(unsigned int value, unsigned long offset) __raw_writel(value, reg_base + offset); if (likely(offset >= EXYNOS4_MCT_L_BASE(0))) { - stat_addr = (offset & ~EXYNOS4_MCT_L_MASK) + MCT_L_WSTAT_OFFSET; - switch (offset & EXYNOS4_MCT_L_MASK) { + stat_addr = (offset & EXYNOS4_MCT_L_MASK) + MCT_L_WSTAT_OFFSET; + switch (offset & ~EXYNOS4_MCT_L_MASK) { case MCT_L_TCON_OFFSET: mask = 1 << 3; /* L_TCON write status */ break; diff --git a/drivers/clocksource/sun4i_timer.c b/drivers/clocksource/sun4i_timer.c index bf497afba9ad..7d19f86012f2 100644 --- a/drivers/clocksource/sun4i_timer.c +++ b/drivers/clocksource/sun4i_timer.c @@ -182,6 +182,12 @@ static void __init sun4i_timer_init(struct device_node *node) /* Make sure timer is stopped before playing with interrupts */ sun4i_clkevt_time_stop(0); + sun4i_clockevent.cpumask = cpu_possible_mask; + sun4i_clockevent.irq = irq; + + clockevents_config_and_register(&sun4i_clockevent, rate, + TIMER_SYNC_TICKS, 0xffffffff); + ret = setup_irq(irq, &sun4i_timer_irq); if (ret) pr_warn("failed to setup irq %d\n", irq); @@ -189,12 +195,6 @@ static void __init sun4i_timer_init(struct device_node *node) /* Enable timer0 interrupt */ val = readl(timer_base + TIMER_IRQ_EN_REG); writel(val | TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_EN_REG); - - sun4i_clockevent.cpumask = cpu_possible_mask; - sun4i_clockevent.irq = irq; - - clockevents_config_and_register(&sun4i_clockevent, rate, - TIMER_SYNC_TICKS, 0xffffffff); } CLOCKSOURCE_OF_DECLARE(sun4i, "allwinner,sun4i-timer", sun4i_timer_init); diff --git a/drivers/clocksource/time-efm32.c b/drivers/clocksource/time-efm32.c index 1a6205b7bed3..35b016100673 100644 --- a/drivers/clocksource/time-efm32.c +++ b/drivers/clocksource/time-efm32.c @@ -225,12 +225,12 @@ static int __init efm32_clockevent_init(struct device_node *np) clock_event_ddata.base = base; clock_event_ddata.periodic_top = DIV_ROUND_CLOSEST(rate, 1024 * HZ); - setup_irq(irq, &efm32_clock_event_irq); - clockevents_config_and_register(&clock_event_ddata.evtdev, DIV_ROUND_CLOSEST(rate, 1024), 0xf, 0xffff); + setup_irq(irq, &efm32_clock_event_irq); + return 0; err_get_irq: diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c index deebcd6469fc..4f0f3610371a 100644 --- a/drivers/clocksource/timer-sun5i.c +++ b/drivers/clocksource/timer-sun5i.c @@ -172,10 +172,6 @@ static void __init sun5i_timer_init(struct device_node *node) ticks_per_jiffy = DIV_ROUND_UP(rate, HZ); - ret = setup_irq(irq, &sun5i_timer_irq); - if (ret) - pr_warn("failed to setup irq %d\n", irq); - /* Enable timer0 interrupt */ val = readl(timer_base + TIMER_IRQ_EN_REG); writel(val | TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_EN_REG); @@ -185,6 +181,10 @@ static void __init sun5i_timer_init(struct device_node *node) clockevents_config_and_register(&sun5i_clockevent, rate, TIMER_SYNC_TICKS, 0xffffffff); + + ret = setup_irq(irq, &sun5i_timer_irq); + if (ret) + pr_warn("failed to setup irq %d\n", irq); } CLOCKSOURCE_OF_DECLARE(sun5i_a13, "allwinner,sun5i-a13-hstimer", sun5i_timer_init); diff --git a/drivers/coresight/Makefile b/drivers/coresight/Makefile new file mode 100644 index 000000000000..4b4bec890ef5 --- /dev/null +++ b/drivers/coresight/Makefile @@ -0,0 +1,11 @@ +# +# Makefile for CoreSight drivers. +# +obj-$(CONFIG_CORESIGHT) += coresight.o +obj-$(CONFIG_OF) += of_coresight.o +obj-$(CONFIG_CORESIGHT_LINK_AND_SINK_TMC) += coresight-tmc.o +obj-$(CONFIG_CORESIGHT_SINK_TPIU) += coresight-tpiu.o +obj-$(CONFIG_CORESIGHT_SINK_ETBV10) += coresight-etb10.o +obj-$(CONFIG_CORESIGHT_LINKS_AND_SINKS) += coresight-funnel.o \ + coresight-replicator.o +obj-$(CONFIG_CORESIGHT_SOURCE_ETM3X) += coresight-etm3x.o coresight-etm-cp14.o diff --git a/drivers/coresight/coresight-etb10.c b/drivers/coresight/coresight-etb10.c new file mode 100644 index 000000000000..c9acd406f0d0 --- /dev/null +++ b/drivers/coresight/coresight-etb10.c @@ -0,0 +1,527 @@ +/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/types.h> +#include <linux/device.h> +#include <linux/io.h> +#include <linux/err.h> +#include <linux/fs.h> +#include <linux/miscdevice.h> +#include <linux/uaccess.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/clk.h> +#include <linux/seq_file.h> +#include <linux/coresight.h> +#include <linux/amba/bus.h> + +#include "coresight-priv.h" + +#define ETB_RAM_DEPTH_REG 0x004 +#define ETB_STATUS_REG 0x00c +#define ETB_RAM_READ_DATA_REG 0x010 +#define ETB_RAM_READ_POINTER 0x014 +#define ETB_RAM_WRITE_POINTER 0x018 +#define ETB_TRG 0x01c +#define ETB_CTL_REG 0x020 +#define ETB_RWD_REG 0x024 +#define ETB_FFSR 0x300 +#define ETB_FFCR 0x304 +#define ETB_ITMISCOP0 0xee0 +#define ETB_ITTRFLINACK 0xee4 +#define ETB_ITTRFLIN 0xee8 +#define ETB_ITATBDATA0 0xeeC +#define ETB_ITATBCTR2 0xef0 +#define ETB_ITATBCTR1 0xef4 +#define ETB_ITATBCTR0 0xef8 + +/* register description */ +/* STS - 0x00C */ +#define ETB_STATUS_RAM_FULL BIT(0) +/* CTL - 0x020 */ +#define ETB_CTL_CAPT_EN BIT(0) +/* FFCR - 0x304 */ +#define ETB_FFCR_EN_FTC BIT(0) +#define ETB_FFCR_FON_MAN BIT(6) +#define ETB_FFCR_STOP_FI BIT(12) +#define ETB_FFCR_STOP_TRIGGER BIT(13) + +#define ETB_FFCR_BIT 6 +#define ETB_FFSR_BIT 1 +#define ETB_FRAME_SIZE_WORDS 4 + +/** + * struct etb_drvdata - specifics associated to an ETB component + * @base: memory mapped base address for this component. + * @dev: the device entity associated to this component. + * @csdev: component vitals needed by the framework. + * @miscdev: specifics to handle "/dev/xyz.etb" entry. + * @clk: the clock this component is associated to. + * @spinlock: only one at a time pls. + * @in_use: synchronise user space access to etb buffer. + * @buf: area of memory where ETB buffer content gets sent. + * @buffer_depth: size of @buf. + * @enable: this ETB is being used. + * @trigger_cntr: amount of words to store after a trigger. + */ +struct etb_drvdata { + void __iomem *base; + struct device *dev; + struct coresight_device *csdev; + struct miscdevice miscdev; + struct clk *clk; + spinlock_t spinlock; + atomic_t in_use; + u8 *buf; + u32 buffer_depth; + bool enable; + u32 trigger_cntr; +}; + +static unsigned int etb_get_buffer_depth(struct etb_drvdata *drvdata) +{ + int ret; + u32 depth = 0; + + ret = clk_prepare_enable(drvdata->clk); + if (ret) + return ret; + + /* RO registers don't need locking */ + depth = readl_relaxed(drvdata->base + ETB_RAM_DEPTH_REG); + + clk_disable_unprepare(drvdata->clk); + return depth; +} + +static void etb_enable_hw(struct etb_drvdata *drvdata) +{ + int i; + u32 depth; + + CS_UNLOCK(drvdata->base); + + depth = drvdata->buffer_depth; + /* reset write RAM pointer address */ + writel_relaxed(0x0, drvdata->base + ETB_RAM_WRITE_POINTER); + /* clear entire RAM buffer */ + for (i = 0; i < depth; i++) + writel_relaxed(0x0, drvdata->base + ETB_RWD_REG); + + /* reset write RAM pointer address */ + writel_relaxed(0x0, drvdata->base + ETB_RAM_WRITE_POINTER); + /* reset read RAM pointer address */ + writel_relaxed(0x0, drvdata->base + ETB_RAM_READ_POINTER); + + writel_relaxed(drvdata->trigger_cntr, drvdata->base + ETB_TRG); + writel_relaxed(ETB_FFCR_EN_FTC | ETB_FFCR_STOP_TRIGGER, + drvdata->base + ETB_FFCR); + /* ETB trace capture enable */ + writel_relaxed(ETB_CTL_CAPT_EN, drvdata->base + ETB_CTL_REG); + + CS_LOCK(drvdata->base); +} + +static int etb_enable(struct coresight_device *csdev) +{ + struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + int ret; + unsigned long flags; + + ret = clk_prepare_enable(drvdata->clk); + if (ret) + return ret; + + spin_lock_irqsave(&drvdata->spinlock, flags); + etb_enable_hw(drvdata); + drvdata->enable = true; + spin_unlock_irqrestore(&drvdata->spinlock, flags); + + dev_info(drvdata->dev, "ETB enabled\n"); + return 0; +} + +static void etb_disable_hw(struct etb_drvdata *drvdata) +{ + u32 ffcr; + + CS_UNLOCK(drvdata->base); + + ffcr = readl_relaxed(drvdata->base + ETB_FFCR); + /* stop formatter when a stop has completed */ + ffcr |= ETB_FFCR_STOP_FI; + writel_relaxed(ffcr, drvdata->base + ETB_FFCR); + /* manually generate a flush of the system */ + ffcr |= ETB_FFCR_FON_MAN; + writel_relaxed(ffcr, drvdata->base + ETB_FFCR); + + if (coresight_timeout(drvdata->base, ETB_FFCR, ETB_FFCR_BIT, 0)) { + dev_err(drvdata->dev, + "timeout observed when probing at offset %#x\n", + ETB_FFCR); + } + + /* disable trace capture */ + writel_relaxed(0x0, drvdata->base + ETB_CTL_REG); + + if (coresight_timeout(drvdata->base, ETB_FFSR, ETB_FFSR_BIT, 1)) { + dev_err(drvdata->dev, + "timeout observed when probing at offset %#x\n", + ETB_FFCR); + } + + CS_LOCK(drvdata->base); +} + +static void etb_dump_hw(struct etb_drvdata *drvdata) +{ + int i; + u8 *buf_ptr; + u32 read_data, depth; + u32 read_ptr, write_ptr; + u32 frame_off, frame_endoff; + + CS_UNLOCK(drvdata->base); + + read_ptr = readl_relaxed(drvdata->base + ETB_RAM_READ_POINTER); + write_ptr = readl_relaxed(drvdata->base + ETB_RAM_WRITE_POINTER); + + frame_off = write_ptr % ETB_FRAME_SIZE_WORDS; + frame_endoff = ETB_FRAME_SIZE_WORDS - frame_off; + if (frame_off) { + dev_err(drvdata->dev, + "write_ptr: %lu not aligned to formatter frame size\n", + (unsigned long)write_ptr); + dev_err(drvdata->dev, "frameoff: %lu, frame_endoff: %lu\n", + (unsigned long)frame_off, (unsigned long)frame_endoff); + write_ptr += frame_endoff; + } + + if ((readl_relaxed(drvdata->base + ETB_STATUS_REG) + & ETB_STATUS_RAM_FULL) == 0) + writel_relaxed(0x0, drvdata->base + ETB_RAM_READ_POINTER); + else + writel_relaxed(write_ptr, drvdata->base + ETB_RAM_READ_POINTER); + + depth = drvdata->buffer_depth; + buf_ptr = drvdata->buf; + for (i = 0; i < depth; i++) { + read_data = readl_relaxed(drvdata->base + + ETB_RAM_READ_DATA_REG); + *buf_ptr++ = read_data >> 0; + *buf_ptr++ = read_data >> 8; + *buf_ptr++ = read_data >> 16; + *buf_ptr++ = read_data >> 24; + } + + if (frame_off) { + buf_ptr -= (frame_endoff * 4); + for (i = 0; i < frame_endoff; i++) { + *buf_ptr++ = 0x0; + *buf_ptr++ = 0x0; + *buf_ptr++ = 0x0; + *buf_ptr++ = 0x0; + } + } + + writel_relaxed(read_ptr, drvdata->base + ETB_RAM_READ_POINTER); + + CS_LOCK(drvdata->base); +} + +static void etb_disable(struct coresight_device *csdev) +{ + struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + unsigned long flags; + + spin_lock_irqsave(&drvdata->spinlock, flags); + etb_disable_hw(drvdata); + etb_dump_hw(drvdata); + drvdata->enable = false; + spin_unlock_irqrestore(&drvdata->spinlock, flags); + + clk_disable_unprepare(drvdata->clk); + + dev_info(drvdata->dev, "ETB disabled\n"); +} + +static const struct coresight_ops_sink etb_sink_ops = { + .enable = etb_enable, + .disable = etb_disable, +}; + +static const struct coresight_ops etb_cs_ops = { + .sink_ops = &etb_sink_ops, +}; + +static void etb_dump(struct etb_drvdata *drvdata) +{ + unsigned long flags; + + spin_lock_irqsave(&drvdata->spinlock, flags); + if (drvdata->enable) { + etb_disable_hw(drvdata); + etb_dump_hw(drvdata); + etb_enable_hw(drvdata); + } + spin_unlock_irqrestore(&drvdata->spinlock, flags); + + dev_info(drvdata->dev, "ETB dumped\n"); +} + +static int etb_open(struct inode *inode, struct file *file) +{ + struct etb_drvdata *drvdata = container_of(file->private_data, + struct etb_drvdata, miscdev); + + if (atomic_cmpxchg(&drvdata->in_use, 0, 1)) + return -EBUSY; + + dev_dbg(drvdata->dev, "%s: successfully opened\n", __func__); + return 0; +} + +static ssize_t etb_read(struct file *file, char __user *data, + size_t len, loff_t *ppos) +{ + u32 depth; + struct etb_drvdata *drvdata = container_of(file->private_data, + struct etb_drvdata, miscdev); + + etb_dump(drvdata); + + depth = drvdata->buffer_depth; + if (*ppos + len > depth * 4) + len = depth * 4 - *ppos; + + if (copy_to_user(data, drvdata->buf + *ppos, len)) { + dev_dbg(drvdata->dev, "%s: copy_to_user failed\n", __func__); + return -EFAULT; + } + + *ppos += len; + + dev_dbg(drvdata->dev, "%s: %d bytes copied, %d bytes left\n", + __func__, len, (int) (depth * 4 - *ppos)); + return len; +} + +static int etb_release(struct inode *inode, struct file *file) +{ + struct etb_drvdata *drvdata = container_of(file->private_data, + struct etb_drvdata, miscdev); + atomic_set(&drvdata->in_use, 0); + + dev_dbg(drvdata->dev, "%s: released\n", __func__); + return 0; +} + +static const struct file_operations etb_fops = { + .owner = THIS_MODULE, + .open = etb_open, + .read = etb_read, + .release = etb_release, + .llseek = no_llseek, +}; + +static ssize_t status_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int ret; + unsigned long flags; + u32 etb_rdr, etb_sr, etb_rrp, etb_rwp; + u32 etb_trg, etb_cr, etb_ffsr, etb_ffcr; + struct etb_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = clk_prepare_enable(drvdata->clk); + if (ret) + goto out; + + spin_lock_irqsave(&drvdata->spinlock, flags); + CS_UNLOCK(drvdata->base); + + etb_rdr = readl_relaxed(drvdata->base + ETB_RAM_DEPTH_REG); + etb_sr = readl_relaxed(drvdata->base + ETB_STATUS_REG); + etb_rrp = readl_relaxed(drvdata->base + ETB_RAM_READ_POINTER); + etb_rwp = readl_relaxed(drvdata->base + ETB_RAM_WRITE_POINTER); + etb_trg = readl_relaxed(drvdata->base + ETB_TRG); + etb_cr = readl_relaxed(drvdata->base + ETB_CTL_REG); + etb_ffsr = readl_relaxed(drvdata->base + ETB_FFSR); + etb_ffcr = readl_relaxed(drvdata->base + ETB_FFCR); + + CS_LOCK(drvdata->base); + spin_unlock_irqrestore(&drvdata->spinlock, flags); + + clk_disable_unprepare(drvdata->clk); + + return sprintf(buf, + "Depth:\t\t0x%x\n" + "Status:\t\t0x%x\n" + "RAM read ptr:\t0x%x\n" + "RAM wrt ptr:\t0x%x\n" + "Trigger cnt:\t0x%x\n" + "Control:\t0x%x\n" + "Flush status:\t0x%x\n" + "Flush ctrl:\t0x%x\n", + etb_rdr, etb_sr, etb_rrp, etb_rwp, + etb_trg, etb_cr, etb_ffsr, etb_ffcr); +out: + return -EINVAL; +} +static DEVICE_ATTR_RO(status); + +static ssize_t trigger_cntr_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct etb_drvdata *drvdata = dev_get_drvdata(dev->parent); + unsigned long val = drvdata->trigger_cntr; + + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t trigger_cntr_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etb_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + drvdata->trigger_cntr = val; + return size; +} +static DEVICE_ATTR_RW(trigger_cntr); + +static struct attribute *coresight_etb_attrs[] = { + &dev_attr_trigger_cntr.attr, + &dev_attr_status.attr, + NULL, +}; +ATTRIBUTE_GROUPS(coresight_etb); + +static int etb_probe(struct amba_device *adev, const struct amba_id *id) +{ + int ret; + void __iomem *base; + struct device *dev = &adev->dev; + struct coresight_platform_data *pdata = NULL; + struct etb_drvdata *drvdata; + struct resource *res = &adev->res; + struct coresight_desc *desc; + struct device_node *np = adev->dev.of_node; + + if (np) { + pdata = of_get_coresight_platform_data(dev, np); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); + adev->dev.platform_data = pdata; + } + + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + + drvdata->dev = &adev->dev; + dev_set_drvdata(dev, drvdata); + + /* validity for the resource is already checked by the AMBA core */ + base = devm_ioremap_resource(dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); + + drvdata->base = base; + + spin_lock_init(&drvdata->spinlock); + + drvdata->clk = adev->pclk; + ret = clk_prepare_enable(drvdata->clk); + if (ret) + return ret; + + drvdata->buffer_depth = etb_get_buffer_depth(drvdata); + clk_disable_unprepare(drvdata->clk); + + if (drvdata->buffer_depth < 0) + return -EINVAL; + + drvdata->buf = devm_kzalloc(dev, + drvdata->buffer_depth * 4, GFP_KERNEL); + if (!drvdata->buf) + return -ENOMEM; + + desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL); + if (!desc) + return -ENOMEM; + + desc->type = CORESIGHT_DEV_TYPE_SINK; + desc->subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER; + desc->ops = &etb_cs_ops; + desc->pdata = pdata; + desc->dev = dev; + desc->groups = coresight_etb_groups; + drvdata->csdev = coresight_register(desc); + if (IS_ERR(drvdata->csdev)) + return PTR_ERR(drvdata->csdev); + + drvdata->miscdev.name = pdata->name; + drvdata->miscdev.minor = MISC_DYNAMIC_MINOR; + drvdata->miscdev.fops = &etb_fops; + ret = misc_register(&drvdata->miscdev); + if (ret) + goto err_misc_register; + + dev_info(dev, "ETB initialized\n"); + return 0; + +err_misc_register: + coresight_unregister(drvdata->csdev); + return ret; +} + +static int etb_remove(struct amba_device *adev) +{ + struct etb_drvdata *drvdata = amba_get_drvdata(adev); + + misc_deregister(&drvdata->miscdev); + coresight_unregister(drvdata->csdev); + return 0; +} + +static struct amba_id etb_ids[] = { + { + .id = 0x0003b907, + .mask = 0x0003ffff, + }, + { 0, 0}, +}; + +static struct amba_driver etb_driver = { + .drv = { + .name = "coresight-etb10", + .owner = THIS_MODULE, + }, + .probe = etb_probe, + .remove = etb_remove, + .id_table = etb_ids, +}; + +module_amba_driver(etb_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("CoreSight Embedded Trace Buffer driver"); diff --git a/drivers/coresight/coresight-etm-cp14.c b/drivers/coresight/coresight-etm-cp14.c new file mode 100644 index 000000000000..12a220682117 --- /dev/null +++ b/drivers/coresight/coresight-etm-cp14.c @@ -0,0 +1,591 @@ +/* Copyright (c) 2012, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/bug.h> +#include <asm/hardware/cp14.h> + +#include "coresight-etm.h" + +int etm_readl_cp14(u32 reg, unsigned int *val) +{ + switch (reg) { + case ETMCR: + *val = etm_read(ETMCR); + return 0; + case ETMCCR: + *val = etm_read(ETMCCR); + return 0; + case ETMTRIGGER: + *val = etm_read(ETMTRIGGER); + return 0; + case ETMSR: + *val = etm_read(ETMSR); + return 0; + case ETMSCR: + *val = etm_read(ETMSCR); + return 0; + case ETMTSSCR: + *val = etm_read(ETMTSSCR); + return 0; + case ETMTEEVR: + *val = etm_read(ETMTEEVR); + return 0; + case ETMTECR1: + *val = etm_read(ETMTECR1); + return 0; + case ETMFFLR: + *val = etm_read(ETMFFLR); + return 0; + case ETMACVRn(0): + *val = etm_read(ETMACVR0); + return 0; + case ETMACVRn(1): + *val = etm_read(ETMACVR1); + return 0; + case ETMACVRn(2): + *val = etm_read(ETMACVR2); + return 0; + case ETMACVRn(3): + *val = etm_read(ETMACVR3); + return 0; + case ETMACVRn(4): + *val = etm_read(ETMACVR4); + return 0; + case ETMACVRn(5): + *val = etm_read(ETMACVR5); + return 0; + case ETMACVRn(6): + *val = etm_read(ETMACVR6); + return 0; + case ETMACVRn(7): + *val = etm_read(ETMACVR7); + return 0; + case ETMACVRn(8): + *val = etm_read(ETMACVR8); + return 0; + case ETMACVRn(9): + *val = etm_read(ETMACVR9); + return 0; + case ETMACVRn(10): + *val = etm_read(ETMACVR10); + return 0; + case ETMACVRn(11): + *val = etm_read(ETMACVR11); + return 0; + case ETMACVRn(12): + *val = etm_read(ETMACVR12); + return 0; + case ETMACVRn(13): + *val = etm_read(ETMACVR13); + return 0; + case ETMACVRn(14): + *val = etm_read(ETMACVR14); + return 0; + case ETMACVRn(15): + *val = etm_read(ETMACVR15); + return 0; + case ETMACTRn(0): + *val = etm_read(ETMACTR0); + return 0; + case ETMACTRn(1): + *val = etm_read(ETMACTR1); + return 0; + case ETMACTRn(2): + *val = etm_read(ETMACTR2); + return 0; + case ETMACTRn(3): + *val = etm_read(ETMACTR3); + return 0; + case ETMACTRn(4): + *val = etm_read(ETMACTR4); + return 0; + case ETMACTRn(5): + *val = etm_read(ETMACTR5); + return 0; + case ETMACTRn(6): + *val = etm_read(ETMACTR6); + return 0; + case ETMACTRn(7): + *val = etm_read(ETMACTR7); + return 0; + case ETMACTRn(8): + *val = etm_read(ETMACTR8); + return 0; + case ETMACTRn(9): + *val = etm_read(ETMACTR9); + return 0; + case ETMACTRn(10): + *val = etm_read(ETMACTR10); + return 0; + case ETMACTRn(11): + *val = etm_read(ETMACTR11); + return 0; + case ETMACTRn(12): + *val = etm_read(ETMACTR12); + return 0; + case ETMACTRn(13): + *val = etm_read(ETMACTR13); + return 0; + case ETMACTRn(14): + *val = etm_read(ETMACTR14); + return 0; + case ETMACTRn(15): + *val = etm_read(ETMACTR15); + return 0; + case ETMCNTRLDVRn(0): + *val = etm_read(ETMCNTRLDVR0); + return 0; + case ETMCNTRLDVRn(1): + *val = etm_read(ETMCNTRLDVR1); + return 0; + case ETMCNTRLDVRn(2): + *val = etm_read(ETMCNTRLDVR2); + return 0; + case ETMCNTRLDVRn(3): + *val = etm_read(ETMCNTRLDVR3); + return 0; + case ETMCNTENRn(0): + *val = etm_read(ETMCNTENR0); + return 0; + case ETMCNTENRn(1): + *val = etm_read(ETMCNTENR1); + return 0; + case ETMCNTENRn(2): + *val = etm_read(ETMCNTENR2); + return 0; + case ETMCNTENRn(3): + *val = etm_read(ETMCNTENR3); + return 0; + case ETMCNTRLDEVRn(0): + *val = etm_read(ETMCNTRLDEVR0); + return 0; + case ETMCNTRLDEVRn(1): + *val = etm_read(ETMCNTRLDEVR1); + return 0; + case ETMCNTRLDEVRn(2): + *val = etm_read(ETMCNTRLDEVR2); + return 0; + case ETMCNTRLDEVRn(3): + *val = etm_read(ETMCNTRLDEVR3); + return 0; + case ETMCNTVRn(0): + *val = etm_read(ETMCNTVR0); + return 0; + case ETMCNTVRn(1): + *val = etm_read(ETMCNTVR1); + return 0; + case ETMCNTVRn(2): + *val = etm_read(ETMCNTVR2); + return 0; + case ETMCNTVRn(3): + *val = etm_read(ETMCNTVR3); + return 0; + case ETMSQ12EVR: + *val = etm_read(ETMSQ12EVR); + return 0; + case ETMSQ21EVR: + *val = etm_read(ETMSQ21EVR); + return 0; + case ETMSQ23EVR: + *val = etm_read(ETMSQ23EVR); + return 0; + case ETMSQ31EVR: + *val = etm_read(ETMSQ31EVR); + return 0; + case ETMSQ32EVR: + *val = etm_read(ETMSQ32EVR); + return 0; + case ETMSQ13EVR: + *val = etm_read(ETMSQ13EVR); + return 0; + case ETMSQR: + *val = etm_read(ETMSQR); + return 0; + case ETMEXTOUTEVRn(0): + *val = etm_read(ETMEXTOUTEVR0); + return 0; + case ETMEXTOUTEVRn(1): + *val = etm_read(ETMEXTOUTEVR1); + return 0; + case ETMEXTOUTEVRn(2): + *val = etm_read(ETMEXTOUTEVR2); + return 0; + case ETMEXTOUTEVRn(3): + *val = etm_read(ETMEXTOUTEVR3); + return 0; + case ETMCIDCVRn(0): + *val = etm_read(ETMCIDCVR0); + return 0; + case ETMCIDCVRn(1): + *val = etm_read(ETMCIDCVR1); + return 0; + case ETMCIDCVRn(2): + *val = etm_read(ETMCIDCVR2); + return 0; + case ETMCIDCMR: + *val = etm_read(ETMCIDCMR); + return 0; + case ETMIMPSPEC0: + *val = etm_read(ETMIMPSPEC0); + return 0; + case ETMIMPSPEC1: + *val = etm_read(ETMIMPSPEC1); + return 0; + case ETMIMPSPEC2: + *val = etm_read(ETMIMPSPEC2); + return 0; + case ETMIMPSPEC3: + *val = etm_read(ETMIMPSPEC3); + return 0; + case ETMIMPSPEC4: + *val = etm_read(ETMIMPSPEC4); + return 0; + case ETMIMPSPEC5: + *val = etm_read(ETMIMPSPEC5); + return 0; + case ETMIMPSPEC6: + *val = etm_read(ETMIMPSPEC6); + return 0; + case ETMIMPSPEC7: + *val = etm_read(ETMIMPSPEC7); + return 0; + case ETMSYNCFR: + *val = etm_read(ETMSYNCFR); + return 0; + case ETMIDR: + *val = etm_read(ETMIDR); + return 0; + case ETMCCER: + *val = etm_read(ETMCCER); + return 0; + case ETMEXTINSELR: + *val = etm_read(ETMEXTINSELR); + return 0; + case ETMTESSEICR: + *val = etm_read(ETMTESSEICR); + return 0; + case ETMEIBCR: + *val = etm_read(ETMEIBCR); + return 0; + case ETMTSEVR: + *val = etm_read(ETMTSEVR); + return 0; + case ETMAUXCR: + *val = etm_read(ETMAUXCR); + return 0; + case ETMTRACEIDR: + *val = etm_read(ETMTRACEIDR); + return 0; + case ETMVMIDCVR: + *val = etm_read(ETMVMIDCVR); + return 0; + case ETMOSLSR: + *val = etm_read(ETMOSLSR); + return 0; + case ETMOSSRR: + *val = etm_read(ETMOSSRR); + return 0; + case ETMPDCR: + *val = etm_read(ETMPDCR); + return 0; + case ETMPDSR: + *val = etm_read(ETMPDSR); + return 0; + default: + *val = 0; + return -EINVAL; + } +} + +int etm_writel_cp14(u32 reg, u32 val) +{ + switch (reg) { + case ETMCR: + etm_write(val, ETMCR); + break; + case ETMTRIGGER: + etm_write(val, ETMTRIGGER); + break; + case ETMSR: + etm_write(val, ETMSR); + break; + case ETMTSSCR: + etm_write(val, ETMTSSCR); + break; + case ETMTEEVR: + etm_write(val, ETMTEEVR); + break; + case ETMTECR1: + etm_write(val, ETMTECR1); + break; + case ETMFFLR: + etm_write(val, ETMFFLR); + break; + case ETMACVRn(0): + etm_write(val, ETMACVR0); + break; + case ETMACVRn(1): + etm_write(val, ETMACVR1); + break; + case ETMACVRn(2): + etm_write(val, ETMACVR2); + break; + case ETMACVRn(3): + etm_write(val, ETMACVR3); + break; + case ETMACVRn(4): + etm_write(val, ETMACVR4); + break; + case ETMACVRn(5): + etm_write(val, ETMACVR5); + break; + case ETMACVRn(6): + etm_write(val, ETMACVR6); + break; + case ETMACVRn(7): + etm_write(val, ETMACVR7); + break; + case ETMACVRn(8): + etm_write(val, ETMACVR8); + break; + case ETMACVRn(9): + etm_write(val, ETMACVR9); + break; + case ETMACVRn(10): + etm_write(val, ETMACVR10); + break; + case ETMACVRn(11): + etm_write(val, ETMACVR11); + break; + case ETMACVRn(12): + etm_write(val, ETMACVR12); + break; + case ETMACVRn(13): + etm_write(val, ETMACVR13); + break; + case ETMACVRn(14): + etm_write(val, ETMACVR14); + break; + case ETMACVRn(15): + etm_write(val, ETMACVR15); + break; + case ETMACTRn(0): + etm_write(val, ETMACTR0); + break; + case ETMACTRn(1): + etm_write(val, ETMACTR1); + break; + case ETMACTRn(2): + etm_write(val, ETMACTR2); + break; + case ETMACTRn(3): + etm_write(val, ETMACTR3); + break; + case ETMACTRn(4): + etm_write(val, ETMACTR4); + break; + case ETMACTRn(5): + etm_write(val, ETMACTR5); + break; + case ETMACTRn(6): + etm_write(val, ETMACTR6); + break; + case ETMACTRn(7): + etm_write(val, ETMACTR7); + break; + case ETMACTRn(8): + etm_write(val, ETMACTR8); + break; + case ETMACTRn(9): + etm_write(val, ETMACTR9); + break; + case ETMACTRn(10): + etm_write(val, ETMACTR10); + break; + case ETMACTRn(11): + etm_write(val, ETMACTR11); + break; + case ETMACTRn(12): + etm_write(val, ETMACTR12); + break; + case ETMACTRn(13): + etm_write(val, ETMACTR13); + break; + case ETMACTRn(14): + etm_write(val, ETMACTR14); + break; + case ETMACTRn(15): + etm_write(val, ETMACTR15); + break; + case ETMCNTRLDVRn(0): + etm_write(val, ETMCNTRLDVR0); + break; + case ETMCNTRLDVRn(1): + etm_write(val, ETMCNTRLDVR1); + break; + case ETMCNTRLDVRn(2): + etm_write(val, ETMCNTRLDVR2); + break; + case ETMCNTRLDVRn(3): + etm_write(val, ETMCNTRLDVR3); + break; + case ETMCNTENRn(0): + etm_write(val, ETMCNTENR0); + break; + case ETMCNTENRn(1): + etm_write(val, ETMCNTENR1); + break; + case ETMCNTENRn(2): + etm_write(val, ETMCNTENR2); + break; + case ETMCNTENRn(3): + etm_write(val, ETMCNTENR3); + break; + case ETMCNTRLDEVRn(0): + etm_write(val, ETMCNTRLDEVR0); + break; + case ETMCNTRLDEVRn(1): + etm_write(val, ETMCNTRLDEVR1); + break; + case ETMCNTRLDEVRn(2): + etm_write(val, ETMCNTRLDEVR2); + break; + case ETMCNTRLDEVRn(3): + etm_write(val, ETMCNTRLDEVR3); + break; + case ETMCNTVRn(0): + etm_write(val, ETMCNTVR0); + break; + case ETMCNTVRn(1): + etm_write(val, ETMCNTVR1); + break; + case ETMCNTVRn(2): + etm_write(val, ETMCNTVR2); + break; + case ETMCNTVRn(3): + etm_write(val, ETMCNTVR3); + break; + case ETMSQ12EVR: + etm_write(val, ETMSQ12EVR); + break; + case ETMSQ21EVR: + etm_write(val, ETMSQ21EVR); + break; + case ETMSQ23EVR: + etm_write(val, ETMSQ23EVR); + break; + case ETMSQ31EVR: + etm_write(val, ETMSQ31EVR); + break; + case ETMSQ32EVR: + etm_write(val, ETMSQ32EVR); + break; + case ETMSQ13EVR: + etm_write(val, ETMSQ13EVR); + break; + case ETMSQR: + etm_write(val, ETMSQR); + break; + case ETMEXTOUTEVRn(0): + etm_write(val, ETMEXTOUTEVR0); + break; + case ETMEXTOUTEVRn(1): + etm_write(val, ETMEXTOUTEVR1); + break; + case ETMEXTOUTEVRn(2): + etm_write(val, ETMEXTOUTEVR2); + break; + case ETMEXTOUTEVRn(3): + etm_write(val, ETMEXTOUTEVR3); + break; + case ETMCIDCVRn(0): + etm_write(val, ETMCIDCVR0); + break; + case ETMCIDCVRn(1): + etm_write(val, ETMCIDCVR1); + break; + case ETMCIDCVRn(2): + etm_write(val, ETMCIDCVR2); + break; + case ETMCIDCMR: + etm_write(val, ETMCIDCMR); + break; + case ETMIMPSPEC0: + etm_write(val, ETMIMPSPEC0); + break; + case ETMIMPSPEC1: + etm_write(val, ETMIMPSPEC1); + break; + case ETMIMPSPEC2: + etm_write(val, ETMIMPSPEC2); + break; + case ETMIMPSPEC3: + etm_write(val, ETMIMPSPEC3); + break; + case ETMIMPSPEC4: + etm_write(val, ETMIMPSPEC4); + break; + case ETMIMPSPEC5: + etm_write(val, ETMIMPSPEC5); + break; + case ETMIMPSPEC6: + etm_write(val, ETMIMPSPEC6); + break; + case ETMIMPSPEC7: + etm_write(val, ETMIMPSPEC7); + break; + case ETMSYNCFR: + etm_write(val, ETMSYNCFR); + break; + case ETMEXTINSELR: + etm_write(val, ETMEXTINSELR); + break; + case ETMTESSEICR: + etm_write(val, ETMTESSEICR); + break; + case ETMEIBCR: + etm_write(val, ETMEIBCR); + break; + case ETMTSEVR: + etm_write(val, ETMTSEVR); + break; + case ETMAUXCR: + etm_write(val, ETMAUXCR); + break; + case ETMTRACEIDR: + etm_write(val, ETMTRACEIDR); + break; + case ETMVMIDCVR: + etm_write(val, ETMVMIDCVR); + break; + case ETMOSLAR: + etm_write(val, ETMOSLAR); + break; + case ETMOSSRR: + etm_write(val, ETMOSSRR); + break; + case ETMPDCR: + etm_write(val, ETMPDCR); + break; + case ETMPDSR: + etm_write(val, ETMPDSR); + break; + default: + return -EINVAL; + } + + return 0; +} diff --git a/drivers/coresight/coresight-etm.h b/drivers/coresight/coresight-etm.h new file mode 100644 index 000000000000..501c5fac8a45 --- /dev/null +++ b/drivers/coresight/coresight-etm.h @@ -0,0 +1,251 @@ +/* Copyright (c) 2014-2015, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _CORESIGHT_CORESIGHT_ETM_H +#define _CORESIGHT_CORESIGHT_ETM_H + +#include <linux/spinlock.h> +#include "coresight-priv.h" + +/* + * Device registers: + * 0x000 - 0x2FC: Trace registers + * 0x300 - 0x314: Management registers + * 0x318 - 0xEFC: Trace registers + * + * Coresight registers + * 0xF00 - 0xF9C: Management registers + * 0xFA0 - 0xFA4: Management registers in PFTv1.0 + * Trace registers in PFTv1.1 + * 0xFA8 - 0xFFC: Management registers + */ + +/* Trace registers (0x000-0x2FC) */ +#define ETMCR 0x000 +#define ETMCCR 0x004 +#define ETMTRIGGER 0x008 +#define ETMSR 0x010 +#define ETMSCR 0x014 +#define ETMTSSCR 0x018 +#define ETMTECR2 0x01c +#define ETMTEEVR 0x020 +#define ETMTECR1 0x024 +#define ETMFFLR 0x02c +#define ETMACVRn(n) (0x040 + (n * 4)) +#define ETMACTRn(n) (0x080 + (n * 4)) +#define ETMCNTRLDVRn(n) (0x140 + (n * 4)) +#define ETMCNTENRn(n) (0x150 + (n * 4)) +#define ETMCNTRLDEVRn(n) (0x160 + (n * 4)) +#define ETMCNTVRn(n) (0x170 + (n * 4)) +#define ETMSQ12EVR 0x180 +#define ETMSQ21EVR 0x184 +#define ETMSQ23EVR 0x188 +#define ETMSQ31EVR 0x18c +#define ETMSQ32EVR 0x190 +#define ETMSQ13EVR 0x194 +#define ETMSQR 0x19c +#define ETMEXTOUTEVRn(n) (0x1a0 + (n * 4)) +#define ETMCIDCVRn(n) (0x1b0 + (n * 4)) +#define ETMCIDCMR 0x1bc +#define ETMIMPSPEC0 0x1c0 +#define ETMIMPSPEC1 0x1c4 +#define ETMIMPSPEC2 0x1c8 +#define ETMIMPSPEC3 0x1cc +#define ETMIMPSPEC4 0x1d0 +#define ETMIMPSPEC5 0x1d4 +#define ETMIMPSPEC6 0x1d8 +#define ETMIMPSPEC7 0x1dc +#define ETMSYNCFR 0x1e0 +#define ETMIDR 0x1e4 +#define ETMCCER 0x1e8 +#define ETMEXTINSELR 0x1ec +#define ETMTESSEICR 0x1f0 +#define ETMEIBCR 0x1f4 +#define ETMTSEVR 0x1f8 +#define ETMAUXCR 0x1fc +#define ETMTRACEIDR 0x200 +#define ETMVMIDCVR 0x240 +/* Management registers (0x300-0x314) */ +#define ETMOSLAR 0x300 +#define ETMOSLSR 0x304 +#define ETMOSSRR 0x308 +#define ETMPDCR 0x310 +#define ETMPDSR 0x314 +#define ETM_MAX_ADDR_CMP 16 +#define ETM_MAX_CNTR 4 +#define ETM_MAX_CTXID_CMP 3 + +/* Register definition */ +/* ETMCR - 0x00 */ +#define ETMCR_PWD_DWN BIT(0) +#define ETMCR_STALL_MODE BIT(7) +#define ETMCR_ETM_PRG BIT(10) +#define ETMCR_ETM_EN BIT(11) +#define ETMCR_CYC_ACC BIT(12) +#define ETMCR_CTXID_SIZE (BIT(14)|BIT(15)) +#define ETMCR_TIMESTAMP_EN BIT(28) +/* ETMCCR - 0x04 */ +#define ETMCCR_FIFOFULL BIT(23) +/* ETMPDCR - 0x310 */ +#define ETMPDCR_PWD_UP BIT(3) +/* ETMTECR1 - 0x024 */ +#define ETMTECR1_ADDR_COMP_1 BIT(0) +#define ETMTECR1_INC_EXC BIT(24) +#define ETMTECR1_START_STOP BIT(25) +/* ETMCCER - 0x1E8 */ +#define ETMCCER_TIMESTAMP BIT(22) + +#define ETM_MODE_EXCLUDE BIT(0) +#define ETM_MODE_CYCACC BIT(1) +#define ETM_MODE_STALL BIT(2) +#define ETM_MODE_TIMESTAMP BIT(3) +#define ETM_MODE_CTXID BIT(4) +#define ETM_MODE_ALL 0x1f + +#define ETM_SQR_MASK 0x3 +#define ETM_TRACEID_MASK 0x3f +#define ETM_EVENT_MASK 0x1ffff +#define ETM_SYNC_MASK 0xfff +#define ETM_ALL_MASK 0xffffffff + +#define ETMSR_PROG_BIT 1 +#define ETM_SEQ_STATE_MAX_VAL (0x2) +#define PORT_SIZE_MASK (GENMASK(21, 21) | GENMASK(6, 4)) + +#define ETM_HARD_WIRE_RES_A /* Hard wired, always true */ \ + ((0x0f << 0) | \ + /* Resource index A */ \ + (0x06 << 4)) + +#define ETM_ADD_COMP_0 /* Single addr comparator 1 */ \ + ((0x00 << 7) | \ + /* Resource index B */ \ + (0x00 << 11)) + +#define ETM_EVENT_NOT_A BIT(14) /* NOT(A) */ + +#define ETM_DEFAULT_EVENT_VAL (ETM_HARD_WIRE_RES_A | \ + ETM_ADD_COMP_0 | \ + ETM_EVENT_NOT_A) +/** + * struct etm_drvdata - specifics associated to an ETM component + * @base: memory mapped base address for this component. + * @dev: the device entity associated to this component. + * @csdev: component vitals needed by the framework. + * @clk: the clock this component is associated to. + * @spinlock: only one at a time pls. + * @cpu: the cpu this component is affined to. + * @port_size: port size as reported by ETMCR bit 4-6 and 21. + * @arch: ETM/PTM version number. + * @use_cpu14: true if management registers need to be accessed via CP14. + * @enable: is this ETM/PTM currently tracing. + * @sticky_enable: true if ETM base configuration has been done. + * @boot_enable:true if we should start tracing at boot time. + * @os_unlock: true if access to management registers is allowed. + * @nr_addr_cmp:Number of pairs of address comparators as found in ETMCCR. + * @nr_cntr: Number of counters as found in ETMCCR bit 13-15. + * @nr_ext_inp: Number of external input as found in ETMCCR bit 17-19. + * @nr_ext_out: Number of external output as found in ETMCCR bit 20-22. + * @nr_ctxid_cmp: Number of contextID comparators as found in ETMCCR bit 24-25. + * @etmccr: value of register ETMCCR. + * @etmccer: value of register ETMCCER. + * @traceid: value of the current ID for this component. + * @mode: controls various modes supported by this ETM/PTM. + * @ctrl: used in conjunction with @mode. + * @trigger_event: setting for register ETMTRIGGER. + * @startstop_ctrl: setting for register ETMTSSCR. + * @enable_event: setting for register ETMTEEVR. + * @enable_ctrl1: setting for register ETMTECR1. + * @fifofull_level: setting for register ETMFFLR. + * @addr_idx: index for the address comparator selection. + * @addr_val: value for address comparator register. + * @addr_acctype: access type for address comparator register. + * @addr_type: current status of the comparator register. + * @cntr_idx: index for the counter register selection. + * @cntr_rld_val: reload value of a counter register. + * @cntr_event: control for counter enable register. + * @cntr_rld_event: value for counter reload event register. + * @cntr_val: counter value register. + * @seq_12_event: event causing the transition from 1 to 2. + * @seq_21_event: event causing the transition from 2 to 1. + * @seq_23_event: event causing the transition from 2 to 3. + * @seq_31_event: event causing the transition from 3 to 1. + * @seq_32_event: event causing the transition from 3 to 2. + * @seq_13_event: event causing the transition from 1 to 3. + * @seq_curr_state: current value of the sequencer register. + * @ctxid_idx: index for the context ID registers. + * @ctxid_val: value for the context ID to trigger on. + * @ctxid_mask: mask applicable to all the context IDs. + * @sync_freq: Synchronisation frequency. + * @timestamp_event: Defines an event that requests the insertion + of a timestamp into the trace stream. + */ +struct etm_drvdata { + void __iomem *base; + struct device *dev; + struct coresight_device *csdev; + struct clk *clk; + spinlock_t spinlock; + int cpu; + int port_size; + u8 arch; + bool use_cp14; + bool enable; + bool sticky_enable; + bool boot_enable; + bool os_unlock; + u8 nr_addr_cmp; + u8 nr_cntr; + u8 nr_ext_inp; + u8 nr_ext_out; + u8 nr_ctxid_cmp; + u32 etmccr; + u32 etmccer; + u32 traceid; + u32 mode; + u32 ctrl; + u32 trigger_event; + u32 startstop_ctrl; + u32 enable_event; + u32 enable_ctrl1; + u32 fifofull_level; + u8 addr_idx; + u32 addr_val[ETM_MAX_ADDR_CMP]; + u32 addr_acctype[ETM_MAX_ADDR_CMP]; + u32 addr_type[ETM_MAX_ADDR_CMP]; + u8 cntr_idx; + u32 cntr_rld_val[ETM_MAX_CNTR]; + u32 cntr_event[ETM_MAX_CNTR]; + u32 cntr_rld_event[ETM_MAX_CNTR]; + u32 cntr_val[ETM_MAX_CNTR]; + u32 seq_12_event; + u32 seq_21_event; + u32 seq_23_event; + u32 seq_31_event; + u32 seq_32_event; + u32 seq_13_event; + u32 seq_curr_state; + u8 ctxid_idx; + u32 ctxid_val[ETM_MAX_CTXID_CMP]; + u32 ctxid_mask; + u32 sync_freq; + u32 timestamp_event; +}; + +enum etm_addr_type { + ETM_ADDR_TYPE_NONE, + ETM_ADDR_TYPE_SINGLE, + ETM_ADDR_TYPE_RANGE, + ETM_ADDR_TYPE_START, + ETM_ADDR_TYPE_STOP, +}; +#endif diff --git a/drivers/coresight/coresight-etm3x.c b/drivers/coresight/coresight-etm3x.c new file mode 100644 index 000000000000..c965f5724abd --- /dev/null +++ b/drivers/coresight/coresight-etm3x.c @@ -0,0 +1,1932 @@ +/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/types.h> +#include <linux/device.h> +#include <linux/io.h> +#include <linux/err.h> +#include <linux/fs.h> +#include <linux/slab.h> +#include <linux/delay.h> +#include <linux/smp.h> +#include <linux/sysfs.h> +#include <linux/stat.h> +#include <linux/clk.h> +#include <linux/cpu.h> +#include <linux/of.h> +#include <linux/coresight.h> +#include <linux/amba/bus.h> +#include <linux/seq_file.h> +#include <linux/uaccess.h> +#include <asm/sections.h> + +#include "coresight-etm.h" + +static int boot_enable; +module_param_named(boot_enable, boot_enable, int, S_IRUGO); + +/* The number of ETM/PTM currently registered */ +static int etm_count; +static struct etm_drvdata *etmdrvdata[NR_CPUS]; + +static inline void etm_writel(struct etm_drvdata *drvdata, + u32 val, u32 off) +{ + if (drvdata->use_cp14) { + if (etm_writel_cp14(off, val)) { + dev_err(drvdata->dev, + "invalid CP14 access to ETM reg: %#x", off); + } + } else { + writel_relaxed(val, drvdata->base + off); + } +} + +static inline unsigned int etm_readl(struct etm_drvdata *drvdata, u32 off) +{ + u32 val; + + if (drvdata->use_cp14) { + if (etm_readl_cp14(off, &val)) { + dev_err(drvdata->dev, + "invalid CP14 access to ETM reg: %#x", off); + } + } else { + val = readl_relaxed(drvdata->base + off); + } + + return val; +} + +/* + * Memory mapped writes to clear os lock are not supported on some processors + * and OS lock must be unlocked before any memory mapped access on such + * processors, otherwise memory mapped reads/writes will be invalid. + */ +static void etm_os_unlock(void *info) +{ + struct etm_drvdata *drvdata = (struct etm_drvdata *)info; + /* Writing any value to ETMOSLAR unlocks the trace registers */ + etm_writel(drvdata, 0x0, ETMOSLAR); + isb(); +} + +static void etm_set_pwrdwn(struct etm_drvdata *drvdata) +{ + u32 etmcr; + + /* Ensure pending cp14 accesses complete before setting pwrdwn */ + mb(); + isb(); + etmcr = etm_readl(drvdata, ETMCR); + etmcr |= ETMCR_PWD_DWN; + etm_writel(drvdata, etmcr, ETMCR); +} + +static void etm_clr_pwrdwn(struct etm_drvdata *drvdata) +{ + u32 etmcr; + + etmcr = etm_readl(drvdata, ETMCR); + etmcr &= ~ETMCR_PWD_DWN; + etm_writel(drvdata, etmcr, ETMCR); + /* Ensure pwrup completes before subsequent cp14 accesses */ + mb(); + isb(); +} + +static void etm_set_pwrup(struct etm_drvdata *drvdata) +{ + u32 etmpdcr; + + etmpdcr = readl_relaxed(drvdata->base + ETMPDCR); + etmpdcr |= ETMPDCR_PWD_UP; + writel_relaxed(etmpdcr, drvdata->base + ETMPDCR); + /* Ensure pwrup completes before subsequent cp14 accesses */ + mb(); + isb(); +} + +static void etm_clr_pwrup(struct etm_drvdata *drvdata) +{ + u32 etmpdcr; + + /* Ensure pending cp14 accesses complete before clearing pwrup */ + mb(); + isb(); + etmpdcr = readl_relaxed(drvdata->base + ETMPDCR); + etmpdcr &= ~ETMPDCR_PWD_UP; + writel_relaxed(etmpdcr, drvdata->base + ETMPDCR); +} + +/** + * coresight_timeout_etm - loop until a bit has changed to a specific state. + * @drvdata: etm's private data structure. + * @offset: address of a register, starting from @addr. + * @position: the position of the bit of interest. + * @value: the value the bit should have. + * + * Basically the same as @coresight_timeout except for the register access + * method where we have to account for CP14 configurations. + + * Return: 0 as soon as the bit has taken the desired state or -EAGAIN if + * TIMEOUT_US has elapsed, which ever happens first. + */ + +static int coresight_timeout_etm(struct etm_drvdata *drvdata, u32 offset, + int position, int value) +{ + int i; + u32 val; + + for (i = TIMEOUT_US; i > 0; i--) { + val = etm_readl(drvdata, offset); + /* Waiting on the bit to go from 0 to 1 */ + if (value) { + if (val & BIT(position)) + return 0; + /* Waiting on the bit to go from 1 to 0 */ + } else { + if (!(val & BIT(position))) + return 0; + } + + /* + * Delay is arbitrary - the specification doesn't say how long + * we are expected to wait. Extra check required to make sure + * we don't wait needlessly on the last iteration. + */ + if (i - 1) + udelay(1); + } + + return -EAGAIN; +} + + +static void etm_set_prog(struct etm_drvdata *drvdata) +{ + u32 etmcr; + + etmcr = etm_readl(drvdata, ETMCR); + etmcr |= ETMCR_ETM_PRG; + etm_writel(drvdata, etmcr, ETMCR); + /* + * Recommended by spec for cp14 accesses to ensure etmcr write is + * complete before polling etmsr + */ + isb(); + if (coresight_timeout_etm(drvdata, ETMSR, ETMSR_PROG_BIT, 1)) { + dev_err(drvdata->dev, + "timeout observed when probing at offset %#x\n", ETMSR); + } +} + +static void etm_clr_prog(struct etm_drvdata *drvdata) +{ + u32 etmcr; + + etmcr = etm_readl(drvdata, ETMCR); + etmcr &= ~ETMCR_ETM_PRG; + etm_writel(drvdata, etmcr, ETMCR); + /* + * Recommended by spec for cp14 accesses to ensure etmcr write is + * complete before polling etmsr + */ + isb(); + if (coresight_timeout_etm(drvdata, ETMSR, ETMSR_PROG_BIT, 0)) { + dev_err(drvdata->dev, + "timeout observed when probing at offset %#x\n", ETMSR); + } +} + +static void etm_set_default(struct etm_drvdata *drvdata) +{ + int i; + + drvdata->trigger_event = ETM_DEFAULT_EVENT_VAL; + drvdata->enable_event = ETM_HARD_WIRE_RES_A; + + drvdata->seq_12_event = ETM_DEFAULT_EVENT_VAL; + drvdata->seq_21_event = ETM_DEFAULT_EVENT_VAL; + drvdata->seq_23_event = ETM_DEFAULT_EVENT_VAL; + drvdata->seq_31_event = ETM_DEFAULT_EVENT_VAL; + drvdata->seq_32_event = ETM_DEFAULT_EVENT_VAL; + drvdata->seq_13_event = ETM_DEFAULT_EVENT_VAL; + drvdata->timestamp_event = ETM_DEFAULT_EVENT_VAL; + + for (i = 0; i < drvdata->nr_cntr; i++) { + drvdata->cntr_rld_val[i] = 0x0; + drvdata->cntr_event[i] = ETM_DEFAULT_EVENT_VAL; + drvdata->cntr_rld_event[i] = ETM_DEFAULT_EVENT_VAL; + drvdata->cntr_val[i] = 0x0; + } + + drvdata->seq_curr_state = 0x0; + drvdata->ctxid_idx = 0x0; + for (i = 0; i < drvdata->nr_ctxid_cmp; i++) + drvdata->ctxid_val[i] = 0x0; + drvdata->ctxid_mask = 0x0; +} + +static void etm_enable_hw(void *info) +{ + int i; + u32 etmcr; + struct etm_drvdata *drvdata = info; + + CS_UNLOCK(drvdata->base); + + /* Turn engine on */ + etm_clr_pwrdwn(drvdata); + /* Apply power to trace registers */ + etm_set_pwrup(drvdata); + /* Make sure all registers are accessible */ + etm_os_unlock(drvdata); + + etm_set_prog(drvdata); + + etmcr = etm_readl(drvdata, ETMCR); + etmcr &= (ETMCR_PWD_DWN | ETMCR_ETM_PRG); + etmcr |= drvdata->port_size; + etm_writel(drvdata, drvdata->ctrl | etmcr, ETMCR); + etm_writel(drvdata, drvdata->trigger_event, ETMTRIGGER); + etm_writel(drvdata, drvdata->startstop_ctrl, ETMTSSCR); + etm_writel(drvdata, drvdata->enable_event, ETMTEEVR); + etm_writel(drvdata, drvdata->enable_ctrl1, ETMTECR1); + etm_writel(drvdata, drvdata->fifofull_level, ETMFFLR); + for (i = 0; i < drvdata->nr_addr_cmp; i++) { + etm_writel(drvdata, drvdata->addr_val[i], ETMACVRn(i)); + etm_writel(drvdata, drvdata->addr_acctype[i], ETMACTRn(i)); + } + for (i = 0; i < drvdata->nr_cntr; i++) { + etm_writel(drvdata, drvdata->cntr_rld_val[i], ETMCNTRLDVRn(i)); + etm_writel(drvdata, drvdata->cntr_event[i], ETMCNTENRn(i)); + etm_writel(drvdata, drvdata->cntr_rld_event[i], + ETMCNTRLDEVRn(i)); + etm_writel(drvdata, drvdata->cntr_val[i], ETMCNTVRn(i)); + } + etm_writel(drvdata, drvdata->seq_12_event, ETMSQ12EVR); + etm_writel(drvdata, drvdata->seq_21_event, ETMSQ21EVR); + etm_writel(drvdata, drvdata->seq_23_event, ETMSQ23EVR); + etm_writel(drvdata, drvdata->seq_31_event, ETMSQ31EVR); + etm_writel(drvdata, drvdata->seq_32_event, ETMSQ32EVR); + etm_writel(drvdata, drvdata->seq_13_event, ETMSQ13EVR); + etm_writel(drvdata, drvdata->seq_curr_state, ETMSQR); + for (i = 0; i < drvdata->nr_ext_out; i++) + etm_writel(drvdata, ETM_DEFAULT_EVENT_VAL, ETMEXTOUTEVRn(i)); + for (i = 0; i < drvdata->nr_ctxid_cmp; i++) + etm_writel(drvdata, drvdata->ctxid_val[i], ETMCIDCVRn(i)); + etm_writel(drvdata, drvdata->ctxid_mask, ETMCIDCMR); + etm_writel(drvdata, drvdata->sync_freq, ETMSYNCFR); + /* No external input selected */ + etm_writel(drvdata, 0x0, ETMEXTINSELR); + etm_writel(drvdata, drvdata->timestamp_event, ETMTSEVR); + /* No auxiliary control selected */ + etm_writel(drvdata, 0x0, ETMAUXCR); + etm_writel(drvdata, drvdata->traceid, ETMTRACEIDR); + /* No VMID comparator value selected */ + etm_writel(drvdata, 0x0, ETMVMIDCVR); + + /* Ensures trace output is enabled from this ETM */ + etm_writel(drvdata, drvdata->ctrl | ETMCR_ETM_EN | etmcr, ETMCR); + + etm_clr_prog(drvdata); + CS_LOCK(drvdata->base); + + dev_dbg(drvdata->dev, "cpu: %d enable smp call done\n", drvdata->cpu); +} + +static int etm_trace_id_simple(struct etm_drvdata *drvdata) +{ + if (!drvdata->enable) + return drvdata->traceid; + + return (etm_readl(drvdata, ETMTRACEIDR) & ETM_TRACEID_MASK); +} + +static int etm_trace_id(struct coresight_device *csdev) +{ + struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + unsigned long flags; + int trace_id = -1; + + if (!drvdata->enable) + return drvdata->traceid; + + if (clk_prepare_enable(drvdata->clk)) + goto out; + + spin_lock_irqsave(&drvdata->spinlock, flags); + + CS_UNLOCK(drvdata->base); + trace_id = (etm_readl(drvdata, ETMTRACEIDR) & ETM_TRACEID_MASK); + CS_LOCK(drvdata->base); + + spin_unlock_irqrestore(&drvdata->spinlock, flags); + clk_disable_unprepare(drvdata->clk); +out: + return trace_id; +} + +static int etm_enable(struct coresight_device *csdev) +{ + struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + int ret; + + ret = clk_prepare_enable(drvdata->clk); + if (ret) + goto err_clk; + + spin_lock(&drvdata->spinlock); + + /* + * Configure the ETM only if the CPU is online. If it isn't online + * hw configuration will take place when 'CPU_STARTING' is received + * in @etm_cpu_callback. + */ + if (cpu_online(drvdata->cpu)) { + ret = smp_call_function_single(drvdata->cpu, + etm_enable_hw, drvdata, 1); + if (ret) + goto err; + } + + drvdata->enable = true; + drvdata->sticky_enable = true; + + spin_unlock(&drvdata->spinlock); + + dev_info(drvdata->dev, "ETM tracing enabled\n"); + return 0; +err: + spin_unlock(&drvdata->spinlock); + clk_disable_unprepare(drvdata->clk); +err_clk: + return ret; +} + +static void etm_disable_hw(void *info) +{ + int i; + struct etm_drvdata *drvdata = info; + + CS_UNLOCK(drvdata->base); + etm_set_prog(drvdata); + + /* Program trace enable to low by using always false event */ + etm_writel(drvdata, ETM_HARD_WIRE_RES_A | ETM_EVENT_NOT_A, ETMTEEVR); + + /* Read back sequencer and counters for post trace analysis */ + drvdata->seq_curr_state = (etm_readl(drvdata, ETMSQR) & ETM_SQR_MASK); + + for (i = 0; i < drvdata->nr_cntr; i++) + drvdata->cntr_val[i] = etm_readl(drvdata, ETMCNTVRn(i)); + + etm_set_pwrdwn(drvdata); + CS_LOCK(drvdata->base); + + dev_dbg(drvdata->dev, "cpu: %d disable smp call done\n", drvdata->cpu); +} + +static void etm_disable(struct coresight_device *csdev) +{ + struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + /* + * Taking hotplug lock here protects from clocks getting disabled + * with tracing being left on (crash scenario) if user disable occurs + * after cpu online mask indicates the cpu is offline but before the + * DYING hotplug callback is serviced by the ETM driver. + */ + get_online_cpus(); + spin_lock(&drvdata->spinlock); + + /* + * Executing etm_disable_hw on the cpu whose ETM is being disabled + * ensures that register writes occur when cpu is powered. + */ + smp_call_function_single(drvdata->cpu, etm_disable_hw, drvdata, 1); + drvdata->enable = false; + + spin_unlock(&drvdata->spinlock); + put_online_cpus(); + + clk_disable_unprepare(drvdata->clk); + + dev_info(drvdata->dev, "ETM tracing disabled\n"); +} + +static const struct coresight_ops_source etm_source_ops = { + .trace_id = etm_trace_id, + .enable = etm_enable, + .disable = etm_disable, +}; + +static const struct coresight_ops etm_cs_ops = { + .source_ops = &etm_source_ops, +}; + +static ssize_t nr_addr_cmp_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = drvdata->nr_addr_cmp; + return sprintf(buf, "%#lx\n", val); +} +static DEVICE_ATTR_RO(nr_addr_cmp); + +static ssize_t nr_cntr_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = drvdata->nr_cntr; + return sprintf(buf, "%#lx\n", val); +} +static DEVICE_ATTR_RO(nr_cntr); + +static ssize_t nr_ctxid_cmp_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = drvdata->nr_ctxid_cmp; + return sprintf(buf, "%#lx\n", val); +} +static DEVICE_ATTR_RO(nr_ctxid_cmp); + +static ssize_t etmsr_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int ret; + unsigned long flags, val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = clk_prepare_enable(drvdata->clk); + if (ret) + return ret; + + spin_lock_irqsave(&drvdata->spinlock, flags); + CS_UNLOCK(drvdata->base); + + val = etm_readl(drvdata, ETMSR); + + CS_LOCK(drvdata->base); + spin_unlock_irqrestore(&drvdata->spinlock, flags); + clk_disable_unprepare(drvdata->clk); + + return sprintf(buf, "%#lx\n", val); +} +static DEVICE_ATTR_RO(etmsr); + +static ssize_t reset_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int i, ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + if (val) { + spin_lock(&drvdata->spinlock); + drvdata->mode = ETM_MODE_EXCLUDE; + drvdata->ctrl = 0x0; + drvdata->trigger_event = ETM_DEFAULT_EVENT_VAL; + drvdata->startstop_ctrl = 0x0; + drvdata->addr_idx = 0x0; + for (i = 0; i < drvdata->nr_addr_cmp; i++) { + drvdata->addr_val[i] = 0x0; + drvdata->addr_acctype[i] = 0x0; + drvdata->addr_type[i] = ETM_ADDR_TYPE_NONE; + } + drvdata->cntr_idx = 0x0; + + etm_set_default(drvdata); + spin_unlock(&drvdata->spinlock); + } + + return size; +} +static DEVICE_ATTR_WO(reset); + +static ssize_t mode_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = drvdata->mode; + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t mode_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + spin_lock(&drvdata->spinlock); + drvdata->mode = val & ETM_MODE_ALL; + + if (drvdata->mode & ETM_MODE_EXCLUDE) + drvdata->enable_ctrl1 |= ETMTECR1_INC_EXC; + else + drvdata->enable_ctrl1 &= ~ETMTECR1_INC_EXC; + + if (drvdata->mode & ETM_MODE_CYCACC) + drvdata->ctrl |= ETMCR_CYC_ACC; + else + drvdata->ctrl &= ~ETMCR_CYC_ACC; + + if (drvdata->mode & ETM_MODE_STALL) { + if (!(drvdata->etmccr & ETMCCR_FIFOFULL)) { + dev_warn(drvdata->dev, "stall mode not supported\n"); + ret = -EINVAL; + goto err_unlock; + } + drvdata->ctrl |= ETMCR_STALL_MODE; + } else + drvdata->ctrl &= ~ETMCR_STALL_MODE; + + if (drvdata->mode & ETM_MODE_TIMESTAMP) { + if (!(drvdata->etmccer & ETMCCER_TIMESTAMP)) { + dev_warn(drvdata->dev, "timestamp not supported\n"); + ret = -EINVAL; + goto err_unlock; + } + drvdata->ctrl |= ETMCR_TIMESTAMP_EN; + } else + drvdata->ctrl &= ~ETMCR_TIMESTAMP_EN; + + if (drvdata->mode & ETM_MODE_CTXID) + drvdata->ctrl |= ETMCR_CTXID_SIZE; + else + drvdata->ctrl &= ~ETMCR_CTXID_SIZE; + spin_unlock(&drvdata->spinlock); + + return size; + +err_unlock: + spin_unlock(&drvdata->spinlock); + return ret; +} +static DEVICE_ATTR_RW(mode); + +static ssize_t trigger_event_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = drvdata->trigger_event; + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t trigger_event_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + drvdata->trigger_event = val & ETM_EVENT_MASK; + + return size; +} +static DEVICE_ATTR_RW(trigger_event); + +static ssize_t enable_event_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = drvdata->enable_event; + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t enable_event_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + drvdata->enable_event = val & ETM_EVENT_MASK; + + return size; +} +static DEVICE_ATTR_RW(enable_event); + +static ssize_t fifofull_level_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = drvdata->fifofull_level; + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t fifofull_level_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + drvdata->fifofull_level = val; + + return size; +} +static DEVICE_ATTR_RW(fifofull_level); + +static ssize_t addr_idx_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = drvdata->addr_idx; + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t addr_idx_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + if (val >= drvdata->nr_addr_cmp) + return -EINVAL; + + /* + * Use spinlock to ensure index doesn't change while it gets + * dereferenced multiple times within a spinlock block elsewhere. + */ + spin_lock(&drvdata->spinlock); + drvdata->addr_idx = val; + spin_unlock(&drvdata->spinlock); + + return size; +} +static DEVICE_ATTR_RW(addr_idx); + +static ssize_t addr_single_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + u8 idx; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + spin_lock(&drvdata->spinlock); + idx = drvdata->addr_idx; + if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE || + drvdata->addr_type[idx] == ETM_ADDR_TYPE_SINGLE)) { + spin_unlock(&drvdata->spinlock); + return -EINVAL; + } + + val = drvdata->addr_val[idx]; + spin_unlock(&drvdata->spinlock); + + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t addr_single_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + u8 idx; + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + spin_lock(&drvdata->spinlock); + idx = drvdata->addr_idx; + if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE || + drvdata->addr_type[idx] == ETM_ADDR_TYPE_SINGLE)) { + spin_unlock(&drvdata->spinlock); + return -EINVAL; + } + + drvdata->addr_val[idx] = val; + drvdata->addr_type[idx] = ETM_ADDR_TYPE_SINGLE; + spin_unlock(&drvdata->spinlock); + + return size; +} +static DEVICE_ATTR_RW(addr_single); + +static ssize_t addr_range_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + u8 idx; + unsigned long val1, val2; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + spin_lock(&drvdata->spinlock); + idx = drvdata->addr_idx; + if (idx % 2 != 0) { + spin_unlock(&drvdata->spinlock); + return -EPERM; + } + if (!((drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE && + drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_NONE) || + (drvdata->addr_type[idx] == ETM_ADDR_TYPE_RANGE && + drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_RANGE))) { + spin_unlock(&drvdata->spinlock); + return -EPERM; + } + + val1 = drvdata->addr_val[idx]; + val2 = drvdata->addr_val[idx + 1]; + spin_unlock(&drvdata->spinlock); + + return sprintf(buf, "%#lx %#lx\n", val1, val2); +} + +static ssize_t addr_range_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + u8 idx; + unsigned long val1, val2; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + if (sscanf(buf, "%lx %lx", &val1, &val2) != 2) + return -EINVAL; + /* Lower address comparator cannot have a higher address value */ + if (val1 > val2) + return -EINVAL; + + spin_lock(&drvdata->spinlock); + idx = drvdata->addr_idx; + if (idx % 2 != 0) { + spin_unlock(&drvdata->spinlock); + return -EPERM; + } + if (!((drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE && + drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_NONE) || + (drvdata->addr_type[idx] == ETM_ADDR_TYPE_RANGE && + drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_RANGE))) { + spin_unlock(&drvdata->spinlock); + return -EPERM; + } + + drvdata->addr_val[idx] = val1; + drvdata->addr_type[idx] = ETM_ADDR_TYPE_RANGE; + drvdata->addr_val[idx + 1] = val2; + drvdata->addr_type[idx + 1] = ETM_ADDR_TYPE_RANGE; + drvdata->enable_ctrl1 |= (1 << (idx/2)); + spin_unlock(&drvdata->spinlock); + + return size; +} +static DEVICE_ATTR_RW(addr_range); + +static ssize_t addr_start_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + u8 idx; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + spin_lock(&drvdata->spinlock); + idx = drvdata->addr_idx; + if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE || + drvdata->addr_type[idx] == ETM_ADDR_TYPE_START)) { + spin_unlock(&drvdata->spinlock); + return -EPERM; + } + + val = drvdata->addr_val[idx]; + spin_unlock(&drvdata->spinlock); + + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t addr_start_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + u8 idx; + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + spin_lock(&drvdata->spinlock); + idx = drvdata->addr_idx; + if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE || + drvdata->addr_type[idx] == ETM_ADDR_TYPE_START)) { + spin_unlock(&drvdata->spinlock); + return -EPERM; + } + + drvdata->addr_val[idx] = val; + drvdata->addr_type[idx] = ETM_ADDR_TYPE_START; + drvdata->startstop_ctrl |= (1 << idx); + drvdata->enable_ctrl1 |= BIT(25); + spin_unlock(&drvdata->spinlock); + + return size; +} +static DEVICE_ATTR_RW(addr_start); + +static ssize_t addr_stop_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + u8 idx; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + spin_lock(&drvdata->spinlock); + idx = drvdata->addr_idx; + if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE || + drvdata->addr_type[idx] == ETM_ADDR_TYPE_STOP)) { + spin_unlock(&drvdata->spinlock); + return -EPERM; + } + + val = drvdata->addr_val[idx]; + spin_unlock(&drvdata->spinlock); + + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t addr_stop_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + u8 idx; + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + spin_lock(&drvdata->spinlock); + idx = drvdata->addr_idx; + if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE || + drvdata->addr_type[idx] == ETM_ADDR_TYPE_STOP)) { + spin_unlock(&drvdata->spinlock); + return -EPERM; + } + + drvdata->addr_val[idx] = val; + drvdata->addr_type[idx] = ETM_ADDR_TYPE_STOP; + drvdata->startstop_ctrl |= (1 << (idx + 16)); + drvdata->enable_ctrl1 |= ETMTECR1_START_STOP; + spin_unlock(&drvdata->spinlock); + + return size; +} +static DEVICE_ATTR_RW(addr_stop); + +static ssize_t addr_acctype_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + spin_lock(&drvdata->spinlock); + val = drvdata->addr_acctype[drvdata->addr_idx]; + spin_unlock(&drvdata->spinlock); + + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t addr_acctype_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + spin_lock(&drvdata->spinlock); + drvdata->addr_acctype[drvdata->addr_idx] = val; + spin_unlock(&drvdata->spinlock); + + return size; +} +static DEVICE_ATTR_RW(addr_acctype); + +static ssize_t cntr_idx_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = drvdata->cntr_idx; + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t cntr_idx_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + if (val >= drvdata->nr_cntr) + return -EINVAL; + /* + * Use spinlock to ensure index doesn't change while it gets + * dereferenced multiple times within a spinlock block elsewhere. + */ + spin_lock(&drvdata->spinlock); + drvdata->cntr_idx = val; + spin_unlock(&drvdata->spinlock); + + return size; +} +static DEVICE_ATTR_RW(cntr_idx); + +static ssize_t cntr_rld_val_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + spin_lock(&drvdata->spinlock); + val = drvdata->cntr_rld_val[drvdata->cntr_idx]; + spin_unlock(&drvdata->spinlock); + + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t cntr_rld_val_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + spin_lock(&drvdata->spinlock); + drvdata->cntr_rld_val[drvdata->cntr_idx] = val; + spin_unlock(&drvdata->spinlock); + + return size; +} +static DEVICE_ATTR_RW(cntr_rld_val); + +static ssize_t cntr_event_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + spin_lock(&drvdata->spinlock); + val = drvdata->cntr_event[drvdata->cntr_idx]; + spin_unlock(&drvdata->spinlock); + + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t cntr_event_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + spin_lock(&drvdata->spinlock); + drvdata->cntr_event[drvdata->cntr_idx] = val & ETM_EVENT_MASK; + spin_unlock(&drvdata->spinlock); + + return size; +} +static DEVICE_ATTR_RW(cntr_event); + +static ssize_t cntr_rld_event_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + spin_lock(&drvdata->spinlock); + val = drvdata->cntr_rld_event[drvdata->cntr_idx]; + spin_unlock(&drvdata->spinlock); + + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t cntr_rld_event_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + spin_lock(&drvdata->spinlock); + drvdata->cntr_rld_event[drvdata->cntr_idx] = val & ETM_EVENT_MASK; + spin_unlock(&drvdata->spinlock); + + return size; +} +static DEVICE_ATTR_RW(cntr_rld_event); + +static ssize_t cntr_val_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int i, ret = 0; + u32 val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + if (!drvdata->enable) { + spin_lock(&drvdata->spinlock); + for (i = 0; i < drvdata->nr_cntr; i++) + ret += sprintf(buf, "counter %d: %x\n", + i, drvdata->cntr_val[i]); + spin_unlock(&drvdata->spinlock); + return ret; + } + + for (i = 0; i < drvdata->nr_cntr; i++) { + val = etm_readl(drvdata, ETMCNTVRn(i)); + ret += sprintf(buf, "counter %d: %x\n", i, val); + } + + return ret; +} + +static ssize_t cntr_val_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + spin_lock(&drvdata->spinlock); + drvdata->cntr_val[drvdata->cntr_idx] = val; + spin_unlock(&drvdata->spinlock); + + return size; +} +static DEVICE_ATTR_RW(cntr_val); + +static ssize_t seq_12_event_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = drvdata->seq_12_event; + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t seq_12_event_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + drvdata->seq_12_event = val & ETM_EVENT_MASK; + return size; +} +static DEVICE_ATTR_RW(seq_12_event); + +static ssize_t seq_21_event_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = drvdata->seq_21_event; + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t seq_21_event_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + drvdata->seq_21_event = val & ETM_EVENT_MASK; + return size; +} +static DEVICE_ATTR_RW(seq_21_event); + +static ssize_t seq_23_event_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = drvdata->seq_23_event; + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t seq_23_event_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + drvdata->seq_23_event = val & ETM_EVENT_MASK; + return size; +} +static DEVICE_ATTR_RW(seq_23_event); + +static ssize_t seq_31_event_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = drvdata->seq_31_event; + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t seq_31_event_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + drvdata->seq_31_event = val & ETM_EVENT_MASK; + return size; +} +static DEVICE_ATTR_RW(seq_31_event); + +static ssize_t seq_32_event_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = drvdata->seq_32_event; + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t seq_32_event_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + drvdata->seq_32_event = val & ETM_EVENT_MASK; + return size; +} +static DEVICE_ATTR_RW(seq_32_event); + +static ssize_t seq_13_event_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = drvdata->seq_13_event; + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t seq_13_event_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + drvdata->seq_13_event = val & ETM_EVENT_MASK; + return size; +} +static DEVICE_ATTR_RW(seq_13_event); + +static ssize_t seq_curr_state_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int ret; + unsigned long val, flags; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + if (!drvdata->enable) { + val = drvdata->seq_curr_state; + goto out; + } + + ret = clk_prepare_enable(drvdata->clk); + if (ret) + return ret; + + spin_lock_irqsave(&drvdata->spinlock, flags); + + CS_UNLOCK(drvdata->base); + val = (etm_readl(drvdata, ETMSQR) & ETM_SQR_MASK); + CS_LOCK(drvdata->base); + + spin_unlock_irqrestore(&drvdata->spinlock, flags); + clk_disable_unprepare(drvdata->clk); +out: + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t seq_curr_state_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + if (val > ETM_SEQ_STATE_MAX_VAL) + return -EINVAL; + + drvdata->seq_curr_state = val; + + return size; +} +static DEVICE_ATTR_RW(seq_curr_state); + +static ssize_t ctxid_idx_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = drvdata->ctxid_idx; + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t ctxid_idx_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + if (val >= drvdata->nr_ctxid_cmp) + return -EINVAL; + + /* + * Use spinlock to ensure index doesn't change while it gets + * dereferenced multiple times within a spinlock block elsewhere. + */ + spin_lock(&drvdata->spinlock); + drvdata->ctxid_idx = val; + spin_unlock(&drvdata->spinlock); + + return size; +} +static DEVICE_ATTR_RW(ctxid_idx); + +static ssize_t ctxid_val_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + spin_lock(&drvdata->spinlock); + val = drvdata->ctxid_val[drvdata->ctxid_idx]; + spin_unlock(&drvdata->spinlock); + + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t ctxid_val_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + spin_lock(&drvdata->spinlock); + drvdata->ctxid_val[drvdata->ctxid_idx] = val; + spin_unlock(&drvdata->spinlock); + + return size; +} +static DEVICE_ATTR_RW(ctxid_val); + +static ssize_t ctxid_mask_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = drvdata->ctxid_mask; + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t ctxid_mask_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + drvdata->ctxid_mask = val; + return size; +} +static DEVICE_ATTR_RW(ctxid_mask); + +static ssize_t sync_freq_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = drvdata->sync_freq; + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t sync_freq_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + drvdata->sync_freq = val & ETM_SYNC_MASK; + return size; +} +static DEVICE_ATTR_RW(sync_freq); + +static ssize_t timestamp_event_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = drvdata->timestamp_event; + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t timestamp_event_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + drvdata->timestamp_event = val & ETM_EVENT_MASK; + return size; +} +static DEVICE_ATTR_RW(timestamp_event); + +static ssize_t status_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int ret; + unsigned long flags; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = clk_prepare_enable(drvdata->clk); + if (ret) + return ret; + + spin_lock_irqsave(&drvdata->spinlock, flags); + + CS_UNLOCK(drvdata->base); + ret = sprintf(buf, + "ETMCCR: 0x%08x\n" + "ETMCCER: 0x%08x\n" + "ETMSCR: 0x%08x\n" + "ETMIDR: 0x%08x\n" + "ETMCR: 0x%08x\n" + "ETMTRACEIDR: 0x%08x\n" + "Enable event: 0x%08x\n" + "Enable start/stop: 0x%08x\n" + "Enable control: CR1 0x%08x CR2 0x%08x\n" + "CPU affinity: %d\n", + drvdata->etmccr, drvdata->etmccer, + etm_readl(drvdata, ETMSCR), etm_readl(drvdata, ETMIDR), + etm_readl(drvdata, ETMCR), etm_trace_id_simple(drvdata), + etm_readl(drvdata, ETMTEEVR), + etm_readl(drvdata, ETMTSSCR), + etm_readl(drvdata, ETMTECR1), + etm_readl(drvdata, ETMTECR2), + drvdata->cpu); + CS_LOCK(drvdata->base); + + spin_unlock_irqrestore(&drvdata->spinlock, flags); + clk_disable_unprepare(drvdata->clk); + + return ret; +} +static DEVICE_ATTR_RO(status); + +static ssize_t traceid_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int ret; + unsigned long val, flags; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + if (!drvdata->enable) { + val = drvdata->traceid; + goto out; + } + + ret = clk_prepare_enable(drvdata->clk); + if (ret) + return ret; + + spin_lock_irqsave(&drvdata->spinlock, flags); + CS_UNLOCK(drvdata->base); + + val = (etm_readl(drvdata, ETMTRACEIDR) & ETM_TRACEID_MASK); + + CS_LOCK(drvdata->base); + spin_unlock_irqrestore(&drvdata->spinlock, flags); + clk_disable_unprepare(drvdata->clk); +out: + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t traceid_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + drvdata->traceid = val & ETM_TRACEID_MASK; + return size; +} +static DEVICE_ATTR_RW(traceid); + +static struct attribute *coresight_etm_attrs[] = { + &dev_attr_nr_addr_cmp.attr, + &dev_attr_nr_cntr.attr, + &dev_attr_nr_ctxid_cmp.attr, + &dev_attr_etmsr.attr, + &dev_attr_reset.attr, + &dev_attr_mode.attr, + &dev_attr_trigger_event.attr, + &dev_attr_enable_event.attr, + &dev_attr_fifofull_level.attr, + &dev_attr_addr_idx.attr, + &dev_attr_addr_single.attr, + &dev_attr_addr_range.attr, + &dev_attr_addr_start.attr, + &dev_attr_addr_stop.attr, + &dev_attr_addr_acctype.attr, + &dev_attr_cntr_idx.attr, + &dev_attr_cntr_rld_val.attr, + &dev_attr_cntr_event.attr, + &dev_attr_cntr_rld_event.attr, + &dev_attr_cntr_val.attr, + &dev_attr_seq_12_event.attr, + &dev_attr_seq_21_event.attr, + &dev_attr_seq_23_event.attr, + &dev_attr_seq_31_event.attr, + &dev_attr_seq_32_event.attr, + &dev_attr_seq_13_event.attr, + &dev_attr_seq_curr_state.attr, + &dev_attr_ctxid_idx.attr, + &dev_attr_ctxid_val.attr, + &dev_attr_ctxid_mask.attr, + &dev_attr_sync_freq.attr, + &dev_attr_timestamp_event.attr, + &dev_attr_status.attr, + &dev_attr_traceid.attr, + NULL, +}; +ATTRIBUTE_GROUPS(coresight_etm); + +static int etm_cpu_callback(struct notifier_block *nfb, unsigned long action, + void *hcpu) +{ + unsigned int cpu = (unsigned long)hcpu; + + if (!etmdrvdata[cpu]) + goto out; + + switch (action & (~CPU_TASKS_FROZEN)) { + case CPU_STARTING: + spin_lock(&etmdrvdata[cpu]->spinlock); + if (!etmdrvdata[cpu]->os_unlock) { + etm_os_unlock(etmdrvdata[cpu]); + etmdrvdata[cpu]->os_unlock = true; + } + + if (etmdrvdata[cpu]->enable) + etm_enable_hw(etmdrvdata[cpu]); + spin_unlock(&etmdrvdata[cpu]->spinlock); + break; + + case CPU_ONLINE: + if (etmdrvdata[cpu]->boot_enable && + !etmdrvdata[cpu]->sticky_enable) + coresight_enable(etmdrvdata[cpu]->csdev); + break; + + case CPU_DYING: + spin_lock(&etmdrvdata[cpu]->spinlock); + if (etmdrvdata[cpu]->enable) + etm_disable_hw(etmdrvdata[cpu]); + spin_unlock(&etmdrvdata[cpu]->spinlock); + break; + } +out: + return NOTIFY_OK; +} + +static struct notifier_block etm_cpu_notifier = { + .notifier_call = etm_cpu_callback, +}; + +static bool etm_arch_supported(u8 arch) +{ + switch (arch) { + case ETM_ARCH_V3_3: + break; + case ETM_ARCH_V3_5: + break; + case PFT_ARCH_V1_0: + break; + case PFT_ARCH_V1_1: + break; + default: + return false; + } + return true; +} + +static void etm_init_arch_data(void *info) +{ + u32 etmidr; + u32 etmccr; + struct etm_drvdata *drvdata = info; + + CS_UNLOCK(drvdata->base); + + /* First dummy read */ + (void)etm_readl(drvdata, ETMPDSR); + /* Provide power to ETM: ETMPDCR[3] == 1 */ + etm_set_pwrup(drvdata); + /* + * Clear power down bit since when this bit is set writes to + * certain registers might be ignored. + */ + etm_clr_pwrdwn(drvdata); + /* + * Set prog bit. It will be set from reset but this is included to + * ensure it is set + */ + etm_set_prog(drvdata); + + /* Find all capabilities */ + etmidr = etm_readl(drvdata, ETMIDR); + drvdata->arch = BMVAL(etmidr, 4, 11); + drvdata->port_size = etm_readl(drvdata, ETMCR) & PORT_SIZE_MASK; + + drvdata->etmccer = etm_readl(drvdata, ETMCCER); + etmccr = etm_readl(drvdata, ETMCCR); + drvdata->etmccr = etmccr; + drvdata->nr_addr_cmp = BMVAL(etmccr, 0, 3) * 2; + drvdata->nr_cntr = BMVAL(etmccr, 13, 15); + drvdata->nr_ext_inp = BMVAL(etmccr, 17, 19); + drvdata->nr_ext_out = BMVAL(etmccr, 20, 22); + drvdata->nr_ctxid_cmp = BMVAL(etmccr, 24, 25); + + etm_set_pwrdwn(drvdata); + etm_clr_pwrup(drvdata); + CS_LOCK(drvdata->base); +} + +static void etm_init_default_data(struct etm_drvdata *drvdata) +{ + /* + * A trace ID of value 0 is invalid, so let's start at some + * random value that fits in 7 bits and will be just as good. + */ + static int etm3x_traceid = 0x10; + + u32 flags = (1 << 0 | /* instruction execute*/ + 3 << 3 | /* ARM instruction */ + 0 << 5 | /* No data value comparison */ + 0 << 7 | /* No exact mach */ + 0 << 8 | /* Ignore context ID */ + 0 << 10); /* Security ignored */ + + /* + * Initial configuration only - guarantees sources handled by + * this driver have a unique ID at startup time but not between + * all other types of sources. For that we lean on the core + * framework. + */ + drvdata->traceid = etm3x_traceid++; + drvdata->ctrl = (ETMCR_CYC_ACC | ETMCR_TIMESTAMP_EN); + drvdata->enable_ctrl1 = ETMTECR1_ADDR_COMP_1; + if (drvdata->nr_addr_cmp >= 2) { + drvdata->addr_val[0] = (u32) _stext; + drvdata->addr_val[1] = (u32) _etext; + drvdata->addr_acctype[0] = flags; + drvdata->addr_acctype[1] = flags; + drvdata->addr_type[0] = ETM_ADDR_TYPE_RANGE; + drvdata->addr_type[1] = ETM_ADDR_TYPE_RANGE; + } + + etm_set_default(drvdata); +} + +static int etm_probe(struct amba_device *adev, const struct amba_id *id) +{ + int ret; + void __iomem *base; + struct device *dev = &adev->dev; + struct coresight_platform_data *pdata = NULL; + struct etm_drvdata *drvdata; + struct resource *res = &adev->res; + struct coresight_desc *desc; + struct device_node *np = adev->dev.of_node; + + desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL); + if (!desc) + return -ENOMEM; + + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + + if (np) { + pdata = of_get_coresight_platform_data(dev, np); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); + + adev->dev.platform_data = pdata; + drvdata->use_cp14 = of_property_read_bool(np, "arm,cp14"); + } + + drvdata->dev = &adev->dev; + dev_set_drvdata(dev, drvdata); + + /* Validity for the resource is already checked by the AMBA core */ + base = devm_ioremap_resource(dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); + + drvdata->base = base; + + spin_lock_init(&drvdata->spinlock); + + drvdata->clk = adev->pclk; + ret = clk_prepare_enable(drvdata->clk); + if (ret) + return ret; + + drvdata->cpu = pdata ? pdata->cpu : 0; + + get_online_cpus(); + etmdrvdata[drvdata->cpu] = drvdata; + + if (!smp_call_function_single(drvdata->cpu, etm_os_unlock, drvdata, 1)) + drvdata->os_unlock = true; + + if (smp_call_function_single(drvdata->cpu, + etm_init_arch_data, drvdata, 1)) + dev_err(dev, "ETM arch init failed\n"); + + if (!etm_count++) + register_hotcpu_notifier(&etm_cpu_notifier); + + put_online_cpus(); + + if (etm_arch_supported(drvdata->arch) == false) { + ret = -EINVAL; + goto err_arch_supported; + } + etm_init_default_data(drvdata); + + clk_disable_unprepare(drvdata->clk); + + desc->type = CORESIGHT_DEV_TYPE_SOURCE; + desc->subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_PROC; + desc->ops = &etm_cs_ops; + desc->pdata = pdata; + desc->dev = dev; + desc->groups = coresight_etm_groups; + drvdata->csdev = coresight_register(desc); + if (IS_ERR(drvdata->csdev)) { + ret = PTR_ERR(drvdata->csdev); + goto err_arch_supported; + } + + dev_info(dev, "ETM initialized\n"); + + if (boot_enable) { + coresight_enable(drvdata->csdev); + drvdata->boot_enable = true; + } + + return 0; + +err_arch_supported: + clk_disable_unprepare(drvdata->clk); + if (--etm_count == 0) + unregister_hotcpu_notifier(&etm_cpu_notifier); + return ret; +} + +static int etm_remove(struct amba_device *adev) +{ + struct etm_drvdata *drvdata = amba_get_drvdata(adev); + + coresight_unregister(drvdata->csdev); + if (--etm_count == 0) + unregister_hotcpu_notifier(&etm_cpu_notifier); + + return 0; +} + +static struct amba_id etm_ids[] = { + { /* ETM 3.3 */ + .id = 0x0003b921, + .mask = 0x0003ffff, + }, + { /* ETM 3.5 */ + .id = 0x0003b956, + .mask = 0x0003ffff, + }, + { /* PTM 1.0 */ + .id = 0x0003b950, + .mask = 0x0003ffff, + }, + { /* PTM 1.1 */ + .id = 0x0003b95f, + .mask = 0x0003ffff, + }, + { 0, 0}, +}; + +static struct amba_driver etm_driver = { + .drv = { + .name = "coresight-etm3x", + .owner = THIS_MODULE, + }, + .probe = etm_probe, + .remove = etm_remove, + .id_table = etm_ids, +}; + +int __init etm_init(void) +{ + return amba_driver_register(&etm_driver); +} +module_init(etm_init); + +void __exit etm_exit(void) +{ + amba_driver_unregister(&etm_driver); +} +module_exit(etm_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("CoreSight Program Flow Trace driver"); diff --git a/drivers/coresight/coresight-funnel.c b/drivers/coresight/coresight-funnel.c new file mode 100644 index 000000000000..3db36f70b666 --- /dev/null +++ b/drivers/coresight/coresight-funnel.c @@ -0,0 +1,258 @@ +/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/types.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/fs.h> +#include <linux/slab.h> +#include <linux/clk.h> +#include <linux/coresight.h> +#include <linux/amba/bus.h> + +#include "coresight-priv.h" + +#define FUNNEL_FUNCTL 0x000 +#define FUNNEL_PRICTL 0x004 + +#define FUNNEL_HOLDTIME_MASK 0xf00 +#define FUNNEL_HOLDTIME_SHFT 0x8 +#define FUNNEL_HOLDTIME (0x7 << FUNNEL_HOLDTIME_SHFT) + +/** + * struct funnel_drvdata - specifics associated to a funnel component + * @base: memory mapped base address for this component. + * @dev: the device entity associated to this component. + * @csdev: component vitals needed by the framework. + * @clk: the clock this component is associated to. + * @priority: port selection order. + */ +struct funnel_drvdata { + void __iomem *base; + struct device *dev; + struct coresight_device *csdev; + struct clk *clk; + unsigned long priority; +}; + +static void funnel_enable_hw(struct funnel_drvdata *drvdata, int port) +{ + u32 functl; + + CS_UNLOCK(drvdata->base); + + functl = readl_relaxed(drvdata->base + FUNNEL_FUNCTL); + functl &= ~FUNNEL_HOLDTIME_MASK; + functl |= FUNNEL_HOLDTIME; + functl |= (1 << port); + writel_relaxed(functl, drvdata->base + FUNNEL_FUNCTL); + writel_relaxed(drvdata->priority, drvdata->base + FUNNEL_PRICTL); + + CS_LOCK(drvdata->base); +} + +static int funnel_enable(struct coresight_device *csdev, int inport, + int outport) +{ + struct funnel_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + int ret; + + ret = clk_prepare_enable(drvdata->clk); + if (ret) + return ret; + + funnel_enable_hw(drvdata, inport); + + dev_info(drvdata->dev, "FUNNEL inport %d enabled\n", inport); + return 0; +} + +static void funnel_disable_hw(struct funnel_drvdata *drvdata, int inport) +{ + u32 functl; + + CS_UNLOCK(drvdata->base); + + functl = readl_relaxed(drvdata->base + FUNNEL_FUNCTL); + functl &= ~(1 << inport); + writel_relaxed(functl, drvdata->base + FUNNEL_FUNCTL); + + CS_LOCK(drvdata->base); +} + +static void funnel_disable(struct coresight_device *csdev, int inport, + int outport) +{ + struct funnel_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + funnel_disable_hw(drvdata, inport); + + clk_disable_unprepare(drvdata->clk); + + dev_info(drvdata->dev, "FUNNEL inport %d disabled\n", inport); +} + +static const struct coresight_ops_link funnel_link_ops = { + .enable = funnel_enable, + .disable = funnel_disable, +}; + +static const struct coresight_ops funnel_cs_ops = { + .link_ops = &funnel_link_ops, +}; + +static ssize_t priority_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct funnel_drvdata *drvdata = dev_get_drvdata(dev->parent); + unsigned long val = drvdata->priority; + + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t priority_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct funnel_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + drvdata->priority = val; + return size; +} +static DEVICE_ATTR_RW(priority); + +static u32 get_funnel_ctrl_hw(struct funnel_drvdata *drvdata) +{ + u32 functl; + + CS_UNLOCK(drvdata->base); + functl = readl_relaxed(drvdata->base + FUNNEL_FUNCTL); + CS_LOCK(drvdata->base); + + return functl; +} + +static ssize_t funnel_ctrl_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int ret; + u32 val; + struct funnel_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = clk_prepare_enable(drvdata->clk); + if (ret) + return ret; + + val = get_funnel_ctrl_hw(drvdata); + clk_disable_unprepare(drvdata->clk); + + return sprintf(buf, "%#x\n", val); +} +static DEVICE_ATTR_RO(funnel_ctrl); + +static struct attribute *coresight_funnel_attrs[] = { + &dev_attr_funnel_ctrl.attr, + &dev_attr_priority.attr, + NULL, +}; +ATTRIBUTE_GROUPS(coresight_funnel); + +static int funnel_probe(struct amba_device *adev, const struct amba_id *id) +{ + void __iomem *base; + struct device *dev = &adev->dev; + struct coresight_platform_data *pdata = NULL; + struct funnel_drvdata *drvdata; + struct resource *res = &adev->res; + struct coresight_desc *desc; + struct device_node *np = adev->dev.of_node; + + if (np) { + pdata = of_get_coresight_platform_data(dev, np); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); + adev->dev.platform_data = pdata; + } + + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + + drvdata->dev = &adev->dev; + dev_set_drvdata(dev, drvdata); + + /* Validity for the resource is already checked by the AMBA core */ + base = devm_ioremap_resource(dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); + + drvdata->base = base; + + drvdata->clk = adev->pclk; + + desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL); + if (!desc) + return -ENOMEM; + + desc->type = CORESIGHT_DEV_TYPE_LINK; + desc->subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_MERG; + desc->ops = &funnel_cs_ops; + desc->pdata = pdata; + desc->dev = dev; + desc->groups = coresight_funnel_groups; + drvdata->csdev = coresight_register(desc); + if (IS_ERR(drvdata->csdev)) + return PTR_ERR(drvdata->csdev); + + dev_info(dev, "FUNNEL initialized\n"); + return 0; +} + +static int funnel_remove(struct amba_device *adev) +{ + struct funnel_drvdata *drvdata = amba_get_drvdata(adev); + + coresight_unregister(drvdata->csdev); + return 0; +} + +static struct amba_id funnel_ids[] = { + { + .id = 0x0003b908, + .mask = 0x0003ffff, + }, + { 0, 0}, +}; + +static struct amba_driver funnel_driver = { + .drv = { + .name = "coresight-funnel", + .owner = THIS_MODULE, + }, + .probe = funnel_probe, + .remove = funnel_remove, + .id_table = funnel_ids, +}; + +module_amba_driver(funnel_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("CoreSight Funnel driver"); diff --git a/drivers/coresight/coresight-priv.h b/drivers/coresight/coresight-priv.h new file mode 100644 index 000000000000..62fcd98cc7cf --- /dev/null +++ b/drivers/coresight/coresight-priv.h @@ -0,0 +1,63 @@ +/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _CORESIGHT_PRIV_H +#define _CORESIGHT_PRIV_H + +#include <linux/bitops.h> +#include <linux/io.h> +#include <linux/coresight.h> + +/* + * Coresight management registers (0xf00-0xfcc) + * 0xfa0 - 0xfa4: Management registers in PFTv1.0 + * Trace registers in PFTv1.1 + */ +#define CORESIGHT_ITCTRL 0xf00 +#define CORESIGHT_CLAIMSET 0xfa0 +#define CORESIGHT_CLAIMCLR 0xfa4 +#define CORESIGHT_LAR 0xfb0 +#define CORESIGHT_LSR 0xfb4 +#define CORESIGHT_AUTHSTATUS 0xfb8 +#define CORESIGHT_DEVID 0xfc8 +#define CORESIGHT_DEVTYPE 0xfcc + +#define TIMEOUT_US 100 +#define BMVAL(val, lsb, msb) ((val & GENMASK(msb, lsb)) >> lsb) + +static inline void CS_LOCK(void __iomem *addr) +{ + do { + /* Wait for things to settle */ + mb(); + writel_relaxed(0x0, addr + CORESIGHT_LAR); + } while (0); +} + +static inline void CS_UNLOCK(void __iomem *addr) +{ + do { + writel_relaxed(CORESIGHT_UNLOCK, addr + CORESIGHT_LAR); + /* Make sure everyone has seen this */ + mb(); + } while (0); +} + +#ifdef CONFIG_CORESIGHT_SOURCE_ETM3X +extern int etm_readl_cp14(u32 off, unsigned int *val); +extern int etm_writel_cp14(u32 off, u32 val); +#else +static inline int etm_readl_cp14(u32 off, unsigned int *val) { return 0; } +static inline int etm_writel_cp14(u32 off, u32 val) { return 0; } +#endif + +#endif diff --git a/drivers/coresight/coresight-replicator.c b/drivers/coresight/coresight-replicator.c new file mode 100644 index 000000000000..cdf05537d574 --- /dev/null +++ b/drivers/coresight/coresight-replicator.c @@ -0,0 +1,137 @@ +/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/device.h> +#include <linux/platform_device.h> +#include <linux/io.h> +#include <linux/err.h> +#include <linux/slab.h> +#include <linux/clk.h> +#include <linux/of.h> +#include <linux/coresight.h> + +#include "coresight-priv.h" + +/** + * struct replicator_drvdata - specifics associated to a replicator component + * @dev: the device entity associated with this component + * @csdev: component vitals needed by the framework + */ +struct replicator_drvdata { + struct device *dev; + struct coresight_device *csdev; +}; + +static int replicator_enable(struct coresight_device *csdev, int inport, + int outport) +{ + struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + dev_info(drvdata->dev, "REPLICATOR enabled\n"); + return 0; +} + +static void replicator_disable(struct coresight_device *csdev, int inport, + int outport) +{ + struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + dev_info(drvdata->dev, "REPLICATOR disabled\n"); +} + +static const struct coresight_ops_link replicator_link_ops = { + .enable = replicator_enable, + .disable = replicator_disable, +}; + +static const struct coresight_ops replicator_cs_ops = { + .link_ops = &replicator_link_ops, +}; + +static int replicator_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct coresight_platform_data *pdata = NULL; + struct replicator_drvdata *drvdata; + struct coresight_desc *desc; + struct device_node *np = pdev->dev.of_node; + + if (np) { + pdata = of_get_coresight_platform_data(dev, np); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); + pdev->dev.platform_data = pdata; + } + + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + + drvdata->dev = &pdev->dev; + platform_set_drvdata(pdev, drvdata); + + desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL); + if (!desc) + return -ENOMEM; + + desc->type = CORESIGHT_DEV_TYPE_LINK; + desc->subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_SPLIT; + desc->ops = &replicator_cs_ops; + desc->pdata = pdev->dev.platform_data; + desc->dev = &pdev->dev; + drvdata->csdev = coresight_register(desc); + if (IS_ERR(drvdata->csdev)) + return PTR_ERR(drvdata->csdev); + + dev_info(dev, "REPLICATOR initialized\n"); + return 0; +} + +static int replicator_remove(struct platform_device *pdev) +{ + struct replicator_drvdata *drvdata = platform_get_drvdata(pdev); + + coresight_unregister(drvdata->csdev); + return 0; +} + +static struct of_device_id replicator_match[] = { + {.compatible = "arm,coresight-replicator"}, + {} +}; + +static struct platform_driver replicator_driver = { + .probe = replicator_probe, + .remove = replicator_remove, + .driver = { + .name = "coresight-replicator", + .of_match_table = replicator_match, + }, +}; + +static int __init replicator_init(void) +{ + return platform_driver_register(&replicator_driver); +} +module_init(replicator_init); + +static void __exit replicator_exit(void) +{ + platform_driver_unregister(&replicator_driver); +} +module_exit(replicator_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("CoreSight Replicator driver"); diff --git a/drivers/coresight/coresight-tmc.c b/drivers/coresight/coresight-tmc.c new file mode 100644 index 000000000000..3ff232f9ddf7 --- /dev/null +++ b/drivers/coresight/coresight-tmc.c @@ -0,0 +1,766 @@ +/* Copyright (c) 2012, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/types.h> +#include <linux/device.h> +#include <linux/io.h> +#include <linux/err.h> +#include <linux/fs.h> +#include <linux/miscdevice.h> +#include <linux/uaccess.h> +#include <linux/slab.h> +#include <linux/dma-mapping.h> +#include <linux/spinlock.h> +#include <linux/clk.h> +#include <linux/of.h> +#include <linux/coresight.h> +#include <linux/amba/bus.h> + +#include "coresight-priv.h" + +#define TMC_RSZ 0x004 +#define TMC_STS 0x00c +#define TMC_RRD 0x010 +#define TMC_RRP 0x014 +#define TMC_RWP 0x018 +#define TMC_TRG 0x01c +#define TMC_CTL 0x020 +#define TMC_RWD 0x024 +#define TMC_MODE 0x028 +#define TMC_LBUFLEVEL 0x02c +#define TMC_CBUFLEVEL 0x030 +#define TMC_BUFWM 0x034 +#define TMC_RRPHI 0x038 +#define TMC_RWPHI 0x03c +#define TMC_AXICTL 0x110 +#define TMC_DBALO 0x118 +#define TMC_DBAHI 0x11c +#define TMC_FFSR 0x300 +#define TMC_FFCR 0x304 +#define TMC_PSCR 0x308 +#define TMC_ITMISCOP0 0xee0 +#define TMC_ITTRFLIN 0xee8 +#define TMC_ITATBDATA0 0xeec +#define TMC_ITATBCTR2 0xef0 +#define TMC_ITATBCTR1 0xef4 +#define TMC_ITATBCTR0 0xef8 + +/* register description */ +/* TMC_CTL - 0x020 */ +#define TMC_CTL_CAPT_EN BIT(0) +/* TMC_STS - 0x00C */ +#define TMC_STS_TRIGGERED BIT(1) +/* TMC_AXICTL - 0x110 */ +#define TMC_AXICTL_PROT_CTL_B0 BIT(0) +#define TMC_AXICTL_PROT_CTL_B1 BIT(1) +#define TMC_AXICTL_SCT_GAT_MODE BIT(7) +#define TMC_AXICTL_WR_BURST_LEN 0xF00 +/* TMC_FFCR - 0x304 */ +#define TMC_FFCR_EN_FMT BIT(0) +#define TMC_FFCR_EN_TI BIT(1) +#define TMC_FFCR_FON_FLIN BIT(4) +#define TMC_FFCR_FON_TRIG_EVT BIT(5) +#define TMC_FFCR_FLUSHMAN BIT(6) +#define TMC_FFCR_TRIGON_TRIGIN BIT(8) +#define TMC_FFCR_STOP_ON_FLUSH BIT(12) + +#define TMC_STS_TRIGGERED_BIT 2 +#define TMC_FFCR_FLUSHMAN_BIT 6 + +enum tmc_config_type { + TMC_CONFIG_TYPE_ETB, + TMC_CONFIG_TYPE_ETR, + TMC_CONFIG_TYPE_ETF, +}; + +enum tmc_mode { + TMC_MODE_CIRCULAR_BUFFER, + TMC_MODE_SOFTWARE_FIFO, + TMC_MODE_HARDWARE_FIFO, +}; + +enum tmc_mem_intf_width { + TMC_MEM_INTF_WIDTH_32BITS = 0x2, + TMC_MEM_INTF_WIDTH_64BITS = 0x3, + TMC_MEM_INTF_WIDTH_128BITS = 0x4, + TMC_MEM_INTF_WIDTH_256BITS = 0x5, +}; + +/** + * struct tmc_drvdata - specifics associated to an TMC component + * @base: memory mapped base address for this component. + * @dev: the device entity associated to this component. + * @csdev: component vitals needed by the framework. + * @miscdev: specifics to handle "/dev/xyz.tmc" entry. + * @clk: the clock this component is associated to. + * @spinlock: only one at a time pls. + * @read_count: manages preparation of buffer for reading. + * @buf: area of memory where trace data get sent. + * @paddr: DMA start location in RAM. + * @vaddr: virtual representation of @paddr. + * @size: @buf size. + * @enable: this TMC is being used. + * @config_type: TMC variant, must be of type @tmc_config_type. + * @trigger_cntr: amount of words to store after a trigger. + */ +struct tmc_drvdata { + void __iomem *base; + struct device *dev; + struct coresight_device *csdev; + struct miscdevice miscdev; + struct clk *clk; + spinlock_t spinlock; + int read_count; + bool reading; + char *buf; + dma_addr_t paddr; + void __iomem *vaddr; + u32 size; + bool enable; + enum tmc_config_type config_type; + u32 trigger_cntr; +}; + +static void tmc_wait_for_ready(struct tmc_drvdata *drvdata) +{ + /* Ensure formatter, unformatter and hardware fifo are empty */ + if (coresight_timeout(drvdata->base, + TMC_STS, TMC_STS_TRIGGERED_BIT, 1)) { + dev_err(drvdata->dev, + "timeout observed when probing at offset %#x\n", + TMC_STS); + } +} + +static void tmc_flush_and_stop(struct tmc_drvdata *drvdata) +{ + u32 ffcr; + + ffcr = readl_relaxed(drvdata->base + TMC_FFCR); + ffcr |= TMC_FFCR_STOP_ON_FLUSH; + writel_relaxed(ffcr, drvdata->base + TMC_FFCR); + ffcr |= TMC_FFCR_FLUSHMAN; + writel_relaxed(ffcr, drvdata->base + TMC_FFCR); + /* Ensure flush completes */ + if (coresight_timeout(drvdata->base, + TMC_FFCR, TMC_FFCR_FLUSHMAN_BIT, 0)) { + dev_err(drvdata->dev, + "timeout observed when probing at offset %#x\n", + TMC_FFCR); + } + + tmc_wait_for_ready(drvdata); +} + +static void tmc_enable_hw(struct tmc_drvdata *drvdata) +{ + writel_relaxed(TMC_CTL_CAPT_EN, drvdata->base + TMC_CTL); +} + +static void tmc_disable_hw(struct tmc_drvdata *drvdata) +{ + writel_relaxed(0x0, drvdata->base + TMC_CTL); +} + +static void tmc_etb_enable_hw(struct tmc_drvdata *drvdata) +{ + /* Zero out the memory to help with debug */ + memset(drvdata->buf, 0, drvdata->size); + + CS_UNLOCK(drvdata->base); + + writel_relaxed(TMC_MODE_CIRCULAR_BUFFER, drvdata->base + TMC_MODE); + writel_relaxed(TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI | + TMC_FFCR_FON_FLIN | TMC_FFCR_FON_TRIG_EVT | + TMC_FFCR_TRIGON_TRIGIN, + drvdata->base + TMC_FFCR); + + writel_relaxed(drvdata->trigger_cntr, drvdata->base + TMC_TRG); + tmc_enable_hw(drvdata); + + CS_LOCK(drvdata->base); +} + +static void tmc_etr_enable_hw(struct tmc_drvdata *drvdata) +{ + u32 axictl; + + /* Zero out the memory to help with debug */ + memset(drvdata->vaddr, 0, drvdata->size); + + CS_UNLOCK(drvdata->base); + + writel_relaxed(drvdata->size / 4, drvdata->base + TMC_RSZ); + writel_relaxed(TMC_MODE_CIRCULAR_BUFFER, drvdata->base + TMC_MODE); + + axictl = readl_relaxed(drvdata->base + TMC_AXICTL); + axictl |= TMC_AXICTL_WR_BURST_LEN; + writel_relaxed(axictl, drvdata->base + TMC_AXICTL); + axictl &= ~TMC_AXICTL_SCT_GAT_MODE; + writel_relaxed(axictl, drvdata->base + TMC_AXICTL); + axictl = (axictl & + ~(TMC_AXICTL_PROT_CTL_B0 | TMC_AXICTL_PROT_CTL_B1)) | + TMC_AXICTL_PROT_CTL_B1; + writel_relaxed(axictl, drvdata->base + TMC_AXICTL); + + writel_relaxed(drvdata->paddr, drvdata->base + TMC_DBALO); + writel_relaxed(0x0, drvdata->base + TMC_DBAHI); + writel_relaxed(TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI | + TMC_FFCR_FON_FLIN | TMC_FFCR_FON_TRIG_EVT | + TMC_FFCR_TRIGON_TRIGIN, + drvdata->base + TMC_FFCR); + writel_relaxed(drvdata->trigger_cntr, drvdata->base + TMC_TRG); + tmc_enable_hw(drvdata); + + CS_LOCK(drvdata->base); +} + +static void tmc_etf_enable_hw(struct tmc_drvdata *drvdata) +{ + CS_UNLOCK(drvdata->base); + + writel_relaxed(TMC_MODE_HARDWARE_FIFO, drvdata->base + TMC_MODE); + writel_relaxed(TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI, + drvdata->base + TMC_FFCR); + writel_relaxed(0x0, drvdata->base + TMC_BUFWM); + tmc_enable_hw(drvdata); + + CS_LOCK(drvdata->base); +} + +static int tmc_enable(struct tmc_drvdata *drvdata, enum tmc_mode mode) +{ + int ret; + unsigned long flags; + + ret = clk_prepare_enable(drvdata->clk); + if (ret) + return ret; + + spin_lock_irqsave(&drvdata->spinlock, flags); + if (drvdata->reading) { + spin_unlock_irqrestore(&drvdata->spinlock, flags); + clk_disable_unprepare(drvdata->clk); + return -EBUSY; + } + + if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) { + tmc_etb_enable_hw(drvdata); + } else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) { + tmc_etr_enable_hw(drvdata); + } else { + if (mode == TMC_MODE_CIRCULAR_BUFFER) + tmc_etb_enable_hw(drvdata); + else + tmc_etf_enable_hw(drvdata); + } + drvdata->enable = true; + spin_unlock_irqrestore(&drvdata->spinlock, flags); + + dev_info(drvdata->dev, "TMC enabled\n"); + return 0; +} + +static int tmc_enable_sink(struct coresight_device *csdev) +{ + struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + return tmc_enable(drvdata, TMC_MODE_CIRCULAR_BUFFER); +} + +static int tmc_enable_link(struct coresight_device *csdev, int inport, + int outport) +{ + struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + return tmc_enable(drvdata, TMC_MODE_HARDWARE_FIFO); +} + +static void tmc_etb_dump_hw(struct tmc_drvdata *drvdata) +{ + enum tmc_mem_intf_width memwidth; + u8 memwords; + char *bufp; + u32 read_data; + int i; + + memwidth = BMVAL(readl_relaxed(drvdata->base + CORESIGHT_DEVID), 8, 10); + if (memwidth == TMC_MEM_INTF_WIDTH_32BITS) + memwords = 1; + else if (memwidth == TMC_MEM_INTF_WIDTH_64BITS) + memwords = 2; + else if (memwidth == TMC_MEM_INTF_WIDTH_128BITS) + memwords = 4; + else + memwords = 8; + + bufp = drvdata->buf; + while (1) { + for (i = 0; i < memwords; i++) { + read_data = readl_relaxed(drvdata->base + TMC_RRD); + if (read_data == 0xFFFFFFFF) + return; + memcpy(bufp, &read_data, 4); + bufp += 4; + } + } +} + +static void tmc_etb_disable_hw(struct tmc_drvdata *drvdata) +{ + CS_UNLOCK(drvdata->base); + + tmc_flush_and_stop(drvdata); + tmc_etb_dump_hw(drvdata); + tmc_disable_hw(drvdata); + + CS_LOCK(drvdata->base); +} + +static void tmc_etr_dump_hw(struct tmc_drvdata *drvdata) +{ + u32 rwp, val; + + rwp = readl_relaxed(drvdata->base + TMC_RWP); + val = readl_relaxed(drvdata->base + TMC_STS); + + /* How much memory do we still have */ + if (val & BIT(0)) + drvdata->buf = drvdata->vaddr + rwp - drvdata->paddr; + else + drvdata->buf = drvdata->vaddr; +} + +static void tmc_etr_disable_hw(struct tmc_drvdata *drvdata) +{ + CS_UNLOCK(drvdata->base); + + tmc_flush_and_stop(drvdata); + tmc_etr_dump_hw(drvdata); + tmc_disable_hw(drvdata); + + CS_LOCK(drvdata->base); +} + +static void tmc_etf_disable_hw(struct tmc_drvdata *drvdata) +{ + CS_UNLOCK(drvdata->base); + + tmc_flush_and_stop(drvdata); + tmc_disable_hw(drvdata); + + CS_LOCK(drvdata->base); +} + +static void tmc_disable(struct tmc_drvdata *drvdata, enum tmc_mode mode) +{ + unsigned long flags; + + spin_lock_irqsave(&drvdata->spinlock, flags); + if (drvdata->reading) + goto out; + + if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) { + tmc_etb_disable_hw(drvdata); + } else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) { + tmc_etr_disable_hw(drvdata); + } else { + if (mode == TMC_MODE_CIRCULAR_BUFFER) + tmc_etb_disable_hw(drvdata); + else + tmc_etf_disable_hw(drvdata); + } +out: + drvdata->enable = false; + spin_unlock_irqrestore(&drvdata->spinlock, flags); + + clk_disable_unprepare(drvdata->clk); + + dev_info(drvdata->dev, "TMC disabled\n"); +} + +static void tmc_disable_sink(struct coresight_device *csdev) +{ + struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + tmc_disable(drvdata, TMC_MODE_CIRCULAR_BUFFER); +} + +static void tmc_disable_link(struct coresight_device *csdev, int inport, + int outport) +{ + struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + tmc_disable(drvdata, TMC_MODE_HARDWARE_FIFO); +} + +static const struct coresight_ops_sink tmc_sink_ops = { + .enable = tmc_enable_sink, + .disable = tmc_disable_sink, +}; + +static const struct coresight_ops_link tmc_link_ops = { + .enable = tmc_enable_link, + .disable = tmc_disable_link, +}; + +static const struct coresight_ops tmc_etb_cs_ops = { + .sink_ops = &tmc_sink_ops, +}; + +static const struct coresight_ops tmc_etr_cs_ops = { + .sink_ops = &tmc_sink_ops, +}; + +static const struct coresight_ops tmc_etf_cs_ops = { + .sink_ops = &tmc_sink_ops, + .link_ops = &tmc_link_ops, +}; + +static int tmc_read_prepare(struct tmc_drvdata *drvdata) +{ + int ret; + unsigned long flags; + enum tmc_mode mode; + + spin_lock_irqsave(&drvdata->spinlock, flags); + if (!drvdata->enable) + goto out; + + if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) { + tmc_etb_disable_hw(drvdata); + } else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) { + tmc_etr_disable_hw(drvdata); + } else { + mode = readl_relaxed(drvdata->base + TMC_MODE); + if (mode == TMC_MODE_CIRCULAR_BUFFER) { + tmc_etb_disable_hw(drvdata); + } else { + ret = -ENODEV; + goto err; + } + } +out: + drvdata->reading = true; + spin_unlock_irqrestore(&drvdata->spinlock, flags); + + dev_info(drvdata->dev, "TMC read start\n"); + return 0; +err: + spin_unlock_irqrestore(&drvdata->spinlock, flags); + return ret; +} + +static void tmc_read_unprepare(struct tmc_drvdata *drvdata) +{ + unsigned long flags; + enum tmc_mode mode; + + spin_lock_irqsave(&drvdata->spinlock, flags); + if (!drvdata->enable) + goto out; + + if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) { + tmc_etb_enable_hw(drvdata); + } else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) { + tmc_etr_enable_hw(drvdata); + } else { + mode = readl_relaxed(drvdata->base + TMC_MODE); + if (mode == TMC_MODE_CIRCULAR_BUFFER) + tmc_etb_enable_hw(drvdata); + } +out: + drvdata->reading = false; + spin_unlock_irqrestore(&drvdata->spinlock, flags); + + dev_info(drvdata->dev, "TMC read end\n"); +} + +static int tmc_open(struct inode *inode, struct file *file) +{ + struct tmc_drvdata *drvdata = container_of(file->private_data, + struct tmc_drvdata, miscdev); + int ret = 0; + + if (drvdata->read_count++) + goto out; + + ret = tmc_read_prepare(drvdata); + if (ret) + return ret; +out: + nonseekable_open(inode, file); + + dev_dbg(drvdata->dev, "%s: successfully opened\n", __func__); + return 0; +} + +static ssize_t tmc_read(struct file *file, char __user *data, size_t len, + loff_t *ppos) +{ + struct tmc_drvdata *drvdata = container_of(file->private_data, + struct tmc_drvdata, miscdev); + char *bufp = drvdata->buf + *ppos; + + if (*ppos + len > drvdata->size) + len = drvdata->size - *ppos; + + if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) { + if (bufp == (char *)(drvdata->vaddr + drvdata->size)) + bufp = drvdata->vaddr; + else if (bufp > (char *)(drvdata->vaddr + drvdata->size)) + bufp -= drvdata->size; + if ((bufp + len) > (char *)(drvdata->vaddr + drvdata->size)) + len = (char *)(drvdata->vaddr + drvdata->size) - bufp; + } + + if (copy_to_user(data, bufp, len)) { + dev_dbg(drvdata->dev, "%s: copy_to_user failed\n", __func__); + return -EFAULT; + } + + *ppos += len; + + dev_dbg(drvdata->dev, "%s: %d bytes copied, %d bytes left\n", + __func__, len, (int) (drvdata->size - *ppos)); + return len; +} + +static int tmc_release(struct inode *inode, struct file *file) +{ + struct tmc_drvdata *drvdata = container_of(file->private_data, + struct tmc_drvdata, miscdev); + + if (--drvdata->read_count) { + if (drvdata->read_count < 0) { + dev_err(drvdata->dev, "mismatched close\n"); + drvdata->read_count = 0; + } + goto out; + } + + tmc_read_unprepare(drvdata); +out: + dev_dbg(drvdata->dev, "%s: released\n", __func__); + return 0; +} + +static const struct file_operations tmc_fops = { + .owner = THIS_MODULE, + .open = tmc_open, + .read = tmc_read, + .release = tmc_release, + .llseek = no_llseek, +}; + +static ssize_t trigger_cntr_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent); + unsigned long val = drvdata->trigger_cntr; + + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t trigger_cntr_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + drvdata->trigger_cntr = val; + return size; +} +static DEVICE_ATTR_RW(trigger_cntr); + +static struct attribute *coresight_etb_attrs[] = { + &dev_attr_trigger_cntr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(coresight_etb); + +static struct attribute *coresight_etr_attrs[] = { + &dev_attr_trigger_cntr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(coresight_etr); + +static struct attribute *coresight_etf_attrs[] = { + &dev_attr_trigger_cntr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(coresight_etf); + +static int tmc_probe(struct amba_device *adev, const struct amba_id *id) +{ + int ret = 0; + u32 devid; + void __iomem *base; + struct device *dev = &adev->dev; + struct coresight_platform_data *pdata = NULL; + struct tmc_drvdata *drvdata; + struct resource *res = &adev->res; + struct coresight_desc *desc; + struct device_node *np = adev->dev.of_node; + + if (np) { + pdata = of_get_coresight_platform_data(dev, np); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); + adev->dev.platform_data = pdata; + } + + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + + drvdata->dev = &adev->dev; + dev_set_drvdata(dev, drvdata); + + /* Validity for the resource is already checked by the AMBA core */ + base = devm_ioremap_resource(dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); + + drvdata->base = base; + + spin_lock_init(&drvdata->spinlock); + + drvdata->clk = adev->pclk; + ret = clk_prepare_enable(drvdata->clk); + if (ret) + return ret; + + devid = readl_relaxed(drvdata->base + CORESIGHT_DEVID); + drvdata->config_type = BMVAL(devid, 6, 7); + + if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) { + if (np) + ret = of_property_read_u32(np, + "arm,buffer-size", + &drvdata->size); + if (ret) + drvdata->size = SZ_1M; + } else { + drvdata->size = readl_relaxed(drvdata->base + TMC_RSZ) * 4; + } + + clk_disable_unprepare(drvdata->clk); + + if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) { + drvdata->vaddr = dma_alloc_coherent(dev, drvdata->size, + &drvdata->paddr, GFP_KERNEL); + if (!drvdata->vaddr) + return -ENOMEM; + + memset(drvdata->vaddr, 0, drvdata->size); + drvdata->buf = drvdata->vaddr; + } else { + drvdata->buf = devm_kzalloc(dev, drvdata->size, GFP_KERNEL); + if (!drvdata->buf) + return -ENOMEM; + } + + desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL); + if (!desc) { + ret = -ENOMEM; + goto err_devm_kzalloc; + } + + desc->pdata = pdata; + desc->dev = dev; + desc->subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER; + + if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) { + desc->type = CORESIGHT_DEV_TYPE_SINK; + desc->ops = &tmc_etb_cs_ops; + desc->groups = coresight_etb_groups; + } else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) { + desc->type = CORESIGHT_DEV_TYPE_SINK; + desc->ops = &tmc_etr_cs_ops; + desc->groups = coresight_etr_groups; + } else { + desc->type = CORESIGHT_DEV_TYPE_LINKSINK; + desc->subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_FIFO; + desc->ops = &tmc_etf_cs_ops; + desc->groups = coresight_etf_groups; + } + + drvdata->csdev = coresight_register(desc); + if (IS_ERR(drvdata->csdev)) { + ret = PTR_ERR(drvdata->csdev); + goto err_devm_kzalloc; + } + + drvdata->miscdev.name = pdata->name; + drvdata->miscdev.minor = MISC_DYNAMIC_MINOR; + drvdata->miscdev.fops = &tmc_fops; + ret = misc_register(&drvdata->miscdev); + if (ret) + goto err_misc_register; + + dev_info(dev, "TMC initialized\n"); + return 0; + +err_misc_register: + coresight_unregister(drvdata->csdev); +err_devm_kzalloc: + if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) + dma_free_coherent(dev, drvdata->size, + &drvdata->paddr, GFP_KERNEL); + return ret; +} + +static int tmc_remove(struct amba_device *adev) +{ + struct tmc_drvdata *drvdata = amba_get_drvdata(adev); + + misc_deregister(&drvdata->miscdev); + coresight_unregister(drvdata->csdev); + if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) + dma_free_coherent(drvdata->dev, drvdata->size, + &drvdata->paddr, GFP_KERNEL); + + return 0; +} + +static struct amba_id tmc_ids[] = { + { + .id = 0x0003b961, + .mask = 0x0003ffff, + }, + { 0, 0}, +}; + +static struct amba_driver tmc_driver = { + .drv = { + .name = "coresight-tmc", + .owner = THIS_MODULE, + }, + .probe = tmc_probe, + .remove = tmc_remove, + .id_table = tmc_ids, +}; + +module_amba_driver(tmc_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("CoreSight Trace Memory Controller driver"); diff --git a/drivers/coresight/coresight-tpiu.c b/drivers/coresight/coresight-tpiu.c new file mode 100644 index 000000000000..3b33af2416bb --- /dev/null +++ b/drivers/coresight/coresight-tpiu.c @@ -0,0 +1,207 @@ +/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/device.h> +#include <linux/io.h> +#include <linux/err.h> +#include <linux/slab.h> +#include <linux/clk.h> +#include <linux/coresight.h> +#include <linux/amba/bus.h> + +#include "coresight-priv.h" + +#define TPIU_SUPP_PORTSZ 0x000 +#define TPIU_CURR_PORTSZ 0x004 +#define TPIU_SUPP_TRIGMODES 0x100 +#define TPIU_TRIG_CNTRVAL 0x104 +#define TPIU_TRIG_MULT 0x108 +#define TPIU_SUPP_TESTPATM 0x200 +#define TPIU_CURR_TESTPATM 0x204 +#define TPIU_TEST_PATREPCNTR 0x208 +#define TPIU_FFSR 0x300 +#define TPIU_FFCR 0x304 +#define TPIU_FSYNC_CNTR 0x308 +#define TPIU_EXTCTL_INPORT 0x400 +#define TPIU_EXTCTL_OUTPORT 0x404 +#define TPIU_ITTRFLINACK 0xee4 +#define TPIU_ITTRFLIN 0xee8 +#define TPIU_ITATBDATA0 0xeec +#define TPIU_ITATBCTR2 0xef0 +#define TPIU_ITATBCTR1 0xef4 +#define TPIU_ITATBCTR0 0xef8 + +/** register definition **/ +/* FFCR - 0x304 */ +#define FFCR_FON_MAN BIT(6) + +/** + * @base: memory mapped base address for this component. + * @dev: the device entity associated to this component. + * @csdev: component vitals needed by the framework. + * @clk: the clock this component is associated to. + */ +struct tpiu_drvdata { + void __iomem *base; + struct device *dev; + struct coresight_device *csdev; + struct clk *clk; +}; + +static void tpiu_enable_hw(struct tpiu_drvdata *drvdata) +{ + CS_UNLOCK(drvdata->base); + + /* TODO: fill this up */ + + CS_LOCK(drvdata->base); +} + +static int tpiu_enable(struct coresight_device *csdev) +{ + struct tpiu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + int ret; + + ret = clk_prepare_enable(drvdata->clk); + if (ret) + return ret; + + tpiu_enable_hw(drvdata); + + dev_info(drvdata->dev, "TPIU enabled\n"); + return 0; +} + +static void tpiu_disable_hw(struct tpiu_drvdata *drvdata) +{ + CS_UNLOCK(drvdata->base); + + /* Clear formatter controle reg. */ + writel_relaxed(0x0, drvdata->base + TPIU_FFCR); + /* Generate manual flush */ + writel_relaxed(FFCR_FON_MAN, drvdata->base + TPIU_FFCR); + + CS_LOCK(drvdata->base); +} + +static void tpiu_disable(struct coresight_device *csdev) +{ + struct tpiu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + tpiu_disable_hw(drvdata); + + clk_disable_unprepare(drvdata->clk); + + dev_info(drvdata->dev, "TPIU disabled\n"); +} + +static const struct coresight_ops_sink tpiu_sink_ops = { + .enable = tpiu_enable, + .disable = tpiu_disable, +}; + +static const struct coresight_ops tpiu_cs_ops = { + .sink_ops = &tpiu_sink_ops, +}; + +static int tpiu_probe(struct amba_device *adev, const struct amba_id *id) +{ + int ret; + void __iomem *base; + struct device *dev = &adev->dev; + struct coresight_platform_data *pdata = NULL; + struct tpiu_drvdata *drvdata; + struct resource *res = &adev->res; + struct coresight_desc *desc; + struct device_node *np = adev->dev.of_node; + + if (np) { + pdata = of_get_coresight_platform_data(dev, np); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); + adev->dev.platform_data = pdata; + } + + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + + drvdata->dev = &adev->dev; + dev_set_drvdata(dev, drvdata); + + /* Validity for the resource is already checked by the AMBA core */ + base = devm_ioremap_resource(dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); + + drvdata->base = base; + + drvdata->clk = adev->pclk; + ret = clk_prepare_enable(drvdata->clk); + if (ret) + return ret; + + /* Disable tpiu to support older devices */ + tpiu_disable_hw(drvdata); + + clk_disable_unprepare(drvdata->clk); + + desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL); + if (!desc) + return -ENOMEM; + + desc->type = CORESIGHT_DEV_TYPE_SINK; + desc->subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_PORT; + desc->ops = &tpiu_cs_ops; + desc->pdata = pdata; + desc->dev = dev; + drvdata->csdev = coresight_register(desc); + if (IS_ERR(drvdata->csdev)) + return PTR_ERR(drvdata->csdev); + + dev_info(dev, "TPIU initialized\n"); + return 0; +} + +static int tpiu_remove(struct amba_device *adev) +{ + struct tpiu_drvdata *drvdata = amba_get_drvdata(adev); + + coresight_unregister(drvdata->csdev); + return 0; +} + +static struct amba_id tpiu_ids[] = { + { + .id = 0x0003b912, + .mask = 0x0003ffff, + }, + { 0, 0}, +}; + +static struct amba_driver tpiu_driver = { + .drv = { + .name = "coresight-tpiu", + .owner = THIS_MODULE, + }, + .probe = tpiu_probe, + .remove = tpiu_remove, + .id_table = tpiu_ids, +}; + +module_amba_driver(tpiu_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("CoreSight Trace Port Interface Unit driver"); diff --git a/drivers/coresight/coresight.c b/drivers/coresight/coresight.c new file mode 100644 index 000000000000..c5def9382357 --- /dev/null +++ b/drivers/coresight/coresight.c @@ -0,0 +1,718 @@ +/* Copyright (c) 2012, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/types.h> +#include <linux/device.h> +#include <linux/io.h> +#include <linux/err.h> +#include <linux/export.h> +#include <linux/slab.h> +#include <linux/mutex.h> +#include <linux/clk.h> +#include <linux/coresight.h> +#include <linux/of_platform.h> +#include <linux/delay.h> + +#include "coresight-priv.h" + +static DEFINE_MUTEX(coresight_mutex); + +static int coresight_id_match(struct device *dev, void *data) +{ + int trace_id, i_trace_id; + struct coresight_device *csdev, *i_csdev; + + csdev = data; + i_csdev = to_coresight_device(dev); + + /* + * No need to care about oneself and components that are not + * sources or not enabled + */ + if (i_csdev == csdev || !i_csdev->enable || + i_csdev->type != CORESIGHT_DEV_TYPE_SOURCE) + return 0; + + /* Get the source ID for both compoment */ + trace_id = source_ops(csdev)->trace_id(csdev); + i_trace_id = source_ops(i_csdev)->trace_id(i_csdev); + + /* All you need is one */ + if (trace_id == i_trace_id) + return 1; + + return 0; +} + +static int coresight_source_is_unique(struct coresight_device *csdev) +{ + int trace_id = source_ops(csdev)->trace_id(csdev); + + /* this shouldn't happen */ + if (trace_id < 0) + return 0; + + return !bus_for_each_dev(&coresight_bustype, NULL, + csdev, coresight_id_match); +} + +static int coresight_find_link_inport(struct coresight_device *csdev) +{ + int i; + struct coresight_device *parent; + struct coresight_connection *conn; + + parent = container_of(csdev->path_link.next, + struct coresight_device, path_link); + + for (i = 0; i < parent->nr_outport; i++) { + conn = &parent->conns[i]; + if (conn->child_dev == csdev) + return conn->child_port; + } + + dev_err(&csdev->dev, "couldn't find inport, parent: %s, child: %s\n", + dev_name(&parent->dev), dev_name(&csdev->dev)); + + return 0; +} + +static int coresight_find_link_outport(struct coresight_device *csdev) +{ + int i; + struct coresight_device *child; + struct coresight_connection *conn; + + child = container_of(csdev->path_link.prev, + struct coresight_device, path_link); + + for (i = 0; i < csdev->nr_outport; i++) { + conn = &csdev->conns[i]; + if (conn->child_dev == child) + return conn->outport; + } + + dev_err(&csdev->dev, "couldn't find outport, parent: %s, child: %s\n", + dev_name(&csdev->dev), dev_name(&child->dev)); + + return 0; +} + +static int coresight_enable_sink(struct coresight_device *csdev) +{ + int ret; + + if (!csdev->enable) { + if (sink_ops(csdev)->enable) { + ret = sink_ops(csdev)->enable(csdev); + if (ret) + return ret; + } + csdev->enable = true; + } + + atomic_inc(csdev->refcnt); + + return 0; +} + +static void coresight_disable_sink(struct coresight_device *csdev) +{ + if (atomic_dec_return(csdev->refcnt) == 0) { + if (sink_ops(csdev)->disable) { + sink_ops(csdev)->disable(csdev); + csdev->enable = false; + } + } +} + +static int coresight_enable_link(struct coresight_device *csdev) +{ + int ret; + int link_subtype; + int refport, inport, outport; + + inport = coresight_find_link_inport(csdev); + outport = coresight_find_link_outport(csdev); + link_subtype = csdev->subtype.link_subtype; + + if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG) + refport = inport; + else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT) + refport = outport; + else + refport = 0; + + if (atomic_inc_return(&csdev->refcnt[refport]) == 1) { + if (link_ops(csdev)->enable) { + ret = link_ops(csdev)->enable(csdev, inport, outport); + if (ret) + return ret; + } + } + + csdev->enable = true; + + return 0; +} + +static void coresight_disable_link(struct coresight_device *csdev) +{ + int i, nr_conns; + int link_subtype; + int refport, inport, outport; + + inport = coresight_find_link_inport(csdev); + outport = coresight_find_link_outport(csdev); + link_subtype = csdev->subtype.link_subtype; + + if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG) { + refport = inport; + nr_conns = csdev->nr_inport; + } else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT) { + refport = outport; + nr_conns = csdev->nr_outport; + } else { + refport = 0; + nr_conns = 1; + } + + if (atomic_dec_return(&csdev->refcnt[refport]) == 0) { + if (link_ops(csdev)->disable) + link_ops(csdev)->disable(csdev, inport, outport); + } + + for (i = 0; i < nr_conns; i++) + if (atomic_read(&csdev->refcnt[i]) != 0) + return; + + csdev->enable = false; +} + +static int coresight_enable_source(struct coresight_device *csdev) +{ + int ret; + + if (!coresight_source_is_unique(csdev)) { + dev_warn(&csdev->dev, "traceID %d not unique\n", + source_ops(csdev)->trace_id(csdev)); + return -EINVAL; + } + + if (!csdev->enable) { + if (source_ops(csdev)->enable) { + ret = source_ops(csdev)->enable(csdev); + if (ret) + return ret; + } + csdev->enable = true; + } + + atomic_inc(csdev->refcnt); + + return 0; +} + +static void coresight_disable_source(struct coresight_device *csdev) +{ + if (atomic_dec_return(csdev->refcnt) == 0) { + if (source_ops(csdev)->disable) { + source_ops(csdev)->disable(csdev); + csdev->enable = false; + } + } +} + +static int coresight_enable_path(struct list_head *path) +{ + int ret = 0; + struct coresight_device *cd; + + list_for_each_entry(cd, path, path_link) { + if (cd == list_first_entry(path, struct coresight_device, + path_link)) { + ret = coresight_enable_sink(cd); + } else if (list_is_last(&cd->path_link, path)) { + /* + * Don't enable the source just yet - this needs to + * happen at the very end when all links and sink + * along the path have been configured properly. + */ + ; + } else { + ret = coresight_enable_link(cd); + } + if (ret) + goto err; + } + + return 0; +err: + list_for_each_entry_continue_reverse(cd, path, path_link) { + if (cd == list_first_entry(path, struct coresight_device, + path_link)) { + coresight_disable_sink(cd); + } else if (list_is_last(&cd->path_link, path)) { + ; + } else { + coresight_disable_link(cd); + } + } + + return ret; +} + +static int coresight_disable_path(struct list_head *path) +{ + struct coresight_device *cd; + + list_for_each_entry_reverse(cd, path, path_link) { + if (cd == list_first_entry(path, struct coresight_device, + path_link)) { + coresight_disable_sink(cd); + } else if (list_is_last(&cd->path_link, path)) { + /* + * The source has already been stopped, no need + * to do it again here. + */ + ; + } else { + coresight_disable_link(cd); + } + } + + return 0; +} + +static int coresight_build_paths(struct coresight_device *csdev, + struct list_head *path, + bool enable) +{ + int i, ret = -EINVAL; + struct coresight_connection *conn; + + list_add(&csdev->path_link, path); + + if (csdev->type == CORESIGHT_DEV_TYPE_SINK && csdev->activated) { + if (enable) + ret = coresight_enable_path(path); + else + ret = coresight_disable_path(path); + } else { + for (i = 0; i < csdev->nr_outport; i++) { + conn = &csdev->conns[i]; + if (coresight_build_paths(conn->child_dev, + path, enable) == 0) + ret = 0; + } + } + + if (list_first_entry(path, struct coresight_device, path_link) != csdev) + dev_err(&csdev->dev, "wrong device in %s\n", __func__); + + list_del(&csdev->path_link); + + return ret; +} + +int coresight_enable(struct coresight_device *csdev) +{ + int ret = 0; + LIST_HEAD(path); + + mutex_lock(&coresight_mutex); + if (csdev->type != CORESIGHT_DEV_TYPE_SOURCE) { + ret = -EINVAL; + dev_err(&csdev->dev, "wrong device type in %s\n", __func__); + goto out; + } + if (csdev->enable) + goto out; + + if (coresight_build_paths(csdev, &path, true)) { + dev_err(&csdev->dev, "building path(s) failed\n"); + goto out; + } + + if (coresight_enable_source(csdev)) + dev_err(&csdev->dev, "source enable failed\n"); +out: + mutex_unlock(&coresight_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(coresight_enable); + +void coresight_disable(struct coresight_device *csdev) +{ + LIST_HEAD(path); + + mutex_lock(&coresight_mutex); + if (csdev->type != CORESIGHT_DEV_TYPE_SOURCE) { + dev_err(&csdev->dev, "wrong device type in %s\n", __func__); + goto out; + } + if (!csdev->enable) + goto out; + + coresight_disable_source(csdev); + if (coresight_build_paths(csdev, &path, false)) + dev_err(&csdev->dev, "releasing path(s) failed\n"); + +out: + mutex_unlock(&coresight_mutex); +} +EXPORT_SYMBOL_GPL(coresight_disable); + +static ssize_t enable_sink_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct coresight_device *csdev = to_coresight_device(dev); + + return scnprintf(buf, PAGE_SIZE, "%u\n", (unsigned)csdev->activated); +} + +static ssize_t enable_sink_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct coresight_device *csdev = to_coresight_device(dev); + + ret = kstrtoul(buf, 10, &val); + if (ret) + return ret; + + if (val) + csdev->activated = true; + else + csdev->activated = false; + + return size; + +} +static DEVICE_ATTR_RW(enable_sink); + +static ssize_t enable_source_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct coresight_device *csdev = to_coresight_device(dev); + + return scnprintf(buf, PAGE_SIZE, "%u\n", (unsigned)csdev->enable); +} + +static ssize_t enable_source_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret = 0; + unsigned long val; + struct coresight_device *csdev = to_coresight_device(dev); + + ret = kstrtoul(buf, 10, &val); + if (ret) + return ret; + + if (val) { + ret = coresight_enable(csdev); + if (ret) + return ret; + } else { + coresight_disable(csdev); + } + + return size; +} +static DEVICE_ATTR_RW(enable_source); + +static struct attribute *coresight_sink_attrs[] = { + &dev_attr_enable_sink.attr, + NULL, +}; +ATTRIBUTE_GROUPS(coresight_sink); + +static struct attribute *coresight_source_attrs[] = { + &dev_attr_enable_source.attr, + NULL, +}; +ATTRIBUTE_GROUPS(coresight_source); + +static struct device_type coresight_dev_type[] = { + { + .name = "none", + }, + { + .name = "sink", + .groups = coresight_sink_groups, + }, + { + .name = "link", + }, + { + .name = "linksink", + .groups = coresight_sink_groups, + }, + { + .name = "source", + .groups = coresight_source_groups, + }, +}; + +static void coresight_device_release(struct device *dev) +{ + struct coresight_device *csdev = to_coresight_device(dev); + + kfree(csdev); +} + +static int coresight_orphan_match(struct device *dev, void *data) +{ + int i; + bool still_orphan = false; + struct coresight_device *csdev, *i_csdev; + struct coresight_connection *conn; + + csdev = data; + i_csdev = to_coresight_device(dev); + + /* No need to check oneself */ + if (csdev == i_csdev) + return 0; + + /* Move on to another component if no connection is orphan */ + if (!i_csdev->orphan) + return 0; + /* + * Circle throuch all the connection of that component. If we find + * an orphan connection whose name matches @csdev, link it. + */ + for (i = 0; i < i_csdev->nr_outport; i++) { + conn = &i_csdev->conns[i]; + + /* We have found at least one orphan connection */ + if (conn->child_dev == NULL) { + /* Does it match this newly added device? */ + if (!strcmp(dev_name(&csdev->dev), conn->child_name)) { + conn->child_dev = csdev; + } else { + /* This component still has an orphan */ + still_orphan = true; + } + } + } + + i_csdev->orphan = still_orphan; + + /* + * Returning '0' ensures that all known component on the + * bus will be checked. + */ + return 0; +} + +static void coresight_fixup_orphan_conns(struct coresight_device *csdev) +{ + /* + * No need to check for a return value as orphan connection(s) + * are hooked-up with each newly added component. + */ + bus_for_each_dev(&coresight_bustype, NULL, + csdev, coresight_orphan_match); +} + + +static int coresight_name_match(struct device *dev, void *data) +{ + char *to_match; + struct coresight_device *i_csdev; + + to_match = data; + i_csdev = to_coresight_device(dev); + + if (!strcmp(to_match, dev_name(&i_csdev->dev))) + return 1; + + return 0; +} + +static void coresight_fixup_device_conns(struct coresight_device *csdev) +{ + int i; + struct device *dev = NULL; + struct coresight_connection *conn; + + for (i = 0; i < csdev->nr_outport; i++) { + conn = &csdev->conns[i]; + dev = bus_find_device(&coresight_bustype, NULL, + (void *)conn->child_name, + coresight_name_match); + + if (dev) { + conn->child_dev = to_coresight_device(dev); + } else { + csdev->orphan = true; + conn->child_dev = NULL; + } + } +} + +/** + * coresight_timeout - loop until a bit has changed to a specific state. + * @addr: base address of the area of interest. + * @offset: address of a register, starting from @addr. + * @position: the position of the bit of interest. + * @value: the value the bit should have. + * + * Return: 0 as soon as the bit has taken the desired state or -EAGAIN if + * TIMEOUT_US has elapsed, which ever happens first. + */ + +int coresight_timeout(void __iomem *addr, u32 offset, int position, int value) +{ + int i; + u32 val; + + for (i = TIMEOUT_US; i > 0; i--) { + val = __raw_readl(addr + offset); + /* waiting on the bit to go from 0 to 1 */ + if (value) { + if (val & BIT(position)) + return 0; + /* waiting on the bit to go from 1 to 0 */ + } else { + if (!(val & BIT(position))) + return 0; + } + + /* + * Delay is arbitrary - the specification doesn't say how long + * we are expected to wait. Extra check required to make sure + * we don't wait needlessly on the last iteration. + */ + if (i - 1) + udelay(1); + } + + return -EAGAIN; +} + +struct bus_type coresight_bustype = { + .name = "coresight", +}; + +static int __init coresight_init(void) +{ + return bus_register(&coresight_bustype); +} +postcore_initcall(coresight_init); + +struct coresight_device *coresight_register(struct coresight_desc *desc) +{ + int i; + int ret; + int link_subtype; + int nr_refcnts = 1; + atomic_t *refcnts = NULL; + struct coresight_device *csdev; + struct coresight_connection *conns; + + csdev = kzalloc(sizeof(*csdev), GFP_KERNEL); + if (!csdev) { + ret = -ENOMEM; + goto err_kzalloc_csdev; + } + + if (desc->type == CORESIGHT_DEV_TYPE_LINK || + desc->type == CORESIGHT_DEV_TYPE_LINKSINK) { + link_subtype = desc->subtype.link_subtype; + + if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG) + nr_refcnts = desc->pdata->nr_inport; + else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT) + nr_refcnts = desc->pdata->nr_outport; + } + + refcnts = kcalloc(nr_refcnts, sizeof(*refcnts), GFP_KERNEL); + if (!refcnts) { + ret = -ENOMEM; + goto err_kzalloc_refcnts; + } + + csdev->refcnt = refcnts; + + csdev->nr_inport = desc->pdata->nr_inport; + csdev->nr_outport = desc->pdata->nr_outport; + conns = kcalloc(csdev->nr_outport, sizeof(*conns), GFP_KERNEL); + if (!conns) { + ret = -ENOMEM; + goto err_kzalloc_conns; + } + + for (i = 0; i < csdev->nr_outport; i++) { + conns[i].outport = desc->pdata->outports[i]; + conns[i].child_name = desc->pdata->child_names[i]; + conns[i].child_port = desc->pdata->child_ports[i]; + } + + csdev->conns = conns; + + csdev->type = desc->type; + csdev->subtype = desc->subtype; + csdev->ops = desc->ops; + csdev->orphan = false; + + csdev->dev.type = &coresight_dev_type[desc->type]; + csdev->dev.groups = desc->groups; + csdev->dev.parent = desc->dev; + csdev->dev.release = coresight_device_release; + csdev->dev.bus = &coresight_bustype; + dev_set_name(&csdev->dev, "%s", desc->pdata->name); + + ret = device_register(&csdev->dev); + if (ret) + goto err_device_register; + + mutex_lock(&coresight_mutex); + + coresight_fixup_device_conns(csdev); + coresight_fixup_orphan_conns(csdev); + + mutex_unlock(&coresight_mutex); + + return csdev; + +err_device_register: + kfree(conns); +err_kzalloc_conns: + kfree(refcnts); +err_kzalloc_refcnts: + kfree(csdev); +err_kzalloc_csdev: + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(coresight_register); + +void coresight_unregister(struct coresight_device *csdev) +{ + mutex_lock(&coresight_mutex); + + kfree(csdev->conns); + device_unregister(&csdev->dev); + + mutex_unlock(&coresight_mutex); +} +EXPORT_SYMBOL_GPL(coresight_unregister); + +MODULE_LICENSE("GPL v2"); diff --git a/drivers/coresight/of_coresight.c b/drivers/coresight/of_coresight.c new file mode 100644 index 000000000000..c3efa418a86d --- /dev/null +++ b/drivers/coresight/of_coresight.c @@ -0,0 +1,206 @@ +/* Copyright (c) 2012, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/err.h> +#include <linux/slab.h> +#include <linux/clk.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_graph.h> +#include <linux/of_platform.h> +#include <linux/platform_device.h> +#include <linux/amba/bus.h> +#include <linux/coresight.h> +#include <asm/smp_plat.h> + + +static int of_dev_node_match(struct device *dev, void *data) +{ + return dev->of_node == data; +} + +static struct device * +of_coresight_get_endpoint_device(struct device_node *endpoint) +{ + struct device *dev = NULL; + + /* + * If we have a non-configuable replicator, it will be found on the + * platform bus. + */ + dev = bus_find_device(&platform_bus_type, NULL, + endpoint, of_dev_node_match); + if (dev) + return dev; + + /* + * We have a configurable component - circle through the AMBA bus + * looking for the device that matches the endpoint node. + */ + return bus_find_device(&amba_bustype, NULL, + endpoint, of_dev_node_match); +} + +static struct device_node *of_get_coresight_endpoint( + const struct device_node *parent, struct device_node *prev) +{ + struct device_node *node = of_graph_get_next_endpoint(parent, prev); + + of_node_put(prev); + return node; +} + +static void of_coresight_get_ports(struct device_node *node, + int *nr_inport, int *nr_outport) +{ + struct device_node *ep = NULL; + int in = 0, out = 0; + + do { + ep = of_get_coresight_endpoint(node, ep); + if (!ep) + break; + + if (of_property_read_bool(ep, "slave-mode")) + in++; + else + out++; + + } while (ep); + + *nr_inport = in; + *nr_outport = out; +} + +static int of_coresight_alloc_memory(struct device *dev, + struct coresight_platform_data *pdata) +{ + /* List of output port on this component */ + pdata->outports = devm_kzalloc(dev, pdata->nr_outport * + sizeof(*pdata->outports), + GFP_KERNEL); + if (!pdata->outports) + return -ENOMEM; + + /* Children connected to this component via @outports */ + pdata->child_names = devm_kzalloc(dev, pdata->nr_outport * + sizeof(*pdata->child_names), + GFP_KERNEL); + if (!pdata->child_names) + return -ENOMEM; + + /* Port number on the child this component is connected to */ + pdata->child_ports = devm_kzalloc(dev, pdata->nr_outport * + sizeof(*pdata->child_ports), + GFP_KERNEL); + if (!pdata->child_ports) + return -ENOMEM; + + return 0; +} + +struct coresight_platform_data *of_get_coresight_platform_data( + struct device *dev, struct device_node *node) +{ + int i = 0, ret = 0; + struct coresight_platform_data *pdata; + struct of_endpoint endpoint, rendpoint; + struct device *rdev; + struct device_node *dn; + struct device_node *ep = NULL; + struct device_node *rparent = NULL; + struct device_node *rport = NULL; + + pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL); + if (!pdata) + return ERR_PTR(-ENOMEM); + + /* Use device name as sysfs handle */ + pdata->name = dev_name(dev); + + /* Get the number of input and output port for this component */ + of_coresight_get_ports(node, &pdata->nr_inport, &pdata->nr_outport); + + if (pdata->nr_outport) { + ret = of_coresight_alloc_memory(dev, pdata); + if (ret) + return ERR_PTR(ret); + + /* Iterate through each port to discover topology */ + do { + /* Get a handle on a port */ + ep = of_get_coresight_endpoint(node, ep); + if (!ep) + break; + + /* + * No need to deal with input ports, processing for as + * processing for output ports will deal with them. + */ + if (of_find_property(ep, "slave-mode", NULL)) + continue; + + /* Get a handle on the local endpoint */ + ret = of_graph_parse_endpoint(ep, &endpoint); + + if (ret) + continue; + + /* The local out port number */ + pdata->outports[i] = endpoint.id; + + /* + * Get a handle on the remote port and parent + * attached to it. + */ + rparent = of_graph_get_remote_port_parent(ep); + rport = of_graph_get_remote_port(ep); + + if (!rparent || !rport) + continue; + + if (of_graph_parse_endpoint(rport, &rendpoint)) + continue; + + rdev = of_coresight_get_endpoint_device(rparent); + if (!rdev) + continue; + + pdata->child_names[i] = dev_name(rdev); + pdata->child_ports[i] = rendpoint.id; + + i++; + } while (ep); + } + + /* Affinity defaults to CPU0 */ + pdata->cpu = 0; + dn = of_parse_phandle(node, "cpu", 0); + if (dn) { + const u32 *cell; + int len, index; + u64 hwid; + + cell = of_get_property(dn, "reg", &len); + if (cell) { + hwid = of_read_number(cell, of_n_addr_cells(dn)); + index = get_logical_index(hwid); + if (index != -EINVAL) + pdata->cpu = index; + } + } + + return pdata; +} +EXPORT_SYMBOL_GPL(of_get_coresight_platform_data); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 153f4b92cc05..ef3b8adb9d47 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -460,7 +460,18 @@ show_one(cpuinfo_max_freq, cpuinfo.max_freq); show_one(cpuinfo_transition_latency, cpuinfo.transition_latency); show_one(scaling_min_freq, min); show_one(scaling_max_freq, max); -show_one(scaling_cur_freq, cur); + +static ssize_t show_scaling_cur_freq( + struct cpufreq_policy *policy, char *buf) +{ + ssize_t ret; + + if (cpufreq_driver && cpufreq_driver->setpolicy && cpufreq_driver->get) + ret = sprintf(buf, "%u\n", cpufreq_driver->get(policy->cpu)); + else + ret = sprintf(buf, "%u\n", policy->cur); + return ret; +} static int cpufreq_set_policy(struct cpufreq_policy *policy, struct cpufreq_policy *new_policy); @@ -854,11 +865,11 @@ static int cpufreq_add_dev_interface(struct cpufreq_policy *policy, if (ret) goto err_out_kobj_put; } - if (has_target()) { - ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr); - if (ret) - goto err_out_kobj_put; - } + + ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr); + if (ret) + goto err_out_kobj_put; + if (cpufreq_driver->bios_limit) { ret = sysfs_create_file(&policy->kobj, &bios_limit.attr); if (ret) @@ -1225,6 +1236,8 @@ err_get_freq: per_cpu(cpufreq_cpu_data, j) = NULL; write_unlock_irqrestore(&cpufreq_driver_lock, flags); + up_write(&policy->rwsem); + if (cpufreq_driver->exit) cpufreq_driver->exit(policy); err_set_policy_cpu: @@ -1352,9 +1365,10 @@ static int __cpufreq_remove_dev_finish(struct device *dev, unsigned long flags; struct cpufreq_policy *policy; - read_lock_irqsave(&cpufreq_driver_lock, flags); + write_lock_irqsave(&cpufreq_driver_lock, flags); policy = per_cpu(cpufreq_cpu_data, cpu); - read_unlock_irqrestore(&cpufreq_driver_lock, flags); + per_cpu(cpufreq_cpu_data, cpu) = NULL; + write_unlock_irqrestore(&cpufreq_driver_lock, flags); if (!policy) { pr_debug("%s: No cpu_data found\n", __func__); @@ -1409,7 +1423,6 @@ static int __cpufreq_remove_dev_finish(struct device *dev, } } - per_cpu(cpufreq_cpu_data, cpu) = NULL; return 0; } diff --git a/drivers/cpufreq/integrator-cpufreq.c b/drivers/cpufreq/integrator-cpufreq.c index 0e27844e8c2d..8089dd2cd9d8 100644 --- a/drivers/cpufreq/integrator-cpufreq.c +++ b/drivers/cpufreq/integrator-cpufreq.c @@ -213,9 +213,9 @@ static int __init integrator_cpufreq_probe(struct platform_device *pdev) return cpufreq_register_driver(&integrator_driver); } -static void __exit integrator_cpufreq_remove(struct platform_device *pdev) +static int __exit integrator_cpufreq_remove(struct platform_device *pdev) { - cpufreq_unregister_driver(&integrator_driver); + return cpufreq_unregister_driver(&integrator_driver); } static const struct of_device_id integrator_cpufreq_match[] = { diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index ae52c777339d..533a509439ca 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -55,6 +55,17 @@ static inline int32_t div_fp(int32_t x, int32_t y) return div_s64((int64_t)x << FRAC_BITS, (int64_t)y); } +static inline int ceiling_fp(int32_t x) +{ + int mask, ret; + + ret = fp_toint(x); + mask = (1 << FRAC_BITS) - 1; + if (x & mask) + ret += 1; + return ret; +} + struct sample { int32_t core_pct_busy; u64 aperf; @@ -67,6 +78,7 @@ struct pstate_data { int current_pstate; int min_pstate; int max_pstate; + int scaling; int turbo_pstate; }; @@ -118,6 +130,7 @@ struct pstate_funcs { int (*get_max)(void); int (*get_min)(void); int (*get_turbo)(void); + int (*get_scaling)(void); void (*set)(struct cpudata*, int pstate); void (*get_vid)(struct cpudata *); }; @@ -397,7 +410,7 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate) cpudata->vid.ratio); vid_fp = clamp_t(int32_t, vid_fp, cpudata->vid.min, cpudata->vid.max); - vid = fp_toint(vid_fp); + vid = ceiling_fp(vid_fp); if (pstate > cpudata->pstate.max_pstate) vid = cpudata->vid.turbo; @@ -407,6 +420,22 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate) wrmsrl(MSR_IA32_PERF_CTL, val); } +#define BYT_BCLK_FREQS 5 +static int byt_freq_table[BYT_BCLK_FREQS] = { 833, 1000, 1333, 1167, 800}; + +static int byt_get_scaling(void) +{ + u64 value; + int i; + + rdmsrl(MSR_FSB_FREQ, value); + i = value & 0x3; + + BUG_ON(i > BYT_BCLK_FREQS); + + return byt_freq_table[i] * 100; +} + static void byt_get_vid(struct cpudata *cpudata) { u64 value; @@ -451,6 +480,11 @@ static int core_get_turbo_pstate(void) return ret; } +static inline int core_get_scaling(void) +{ + return 100000; +} + static void core_set_pstate(struct cpudata *cpudata, int pstate) { u64 val; @@ -475,6 +509,7 @@ static struct cpu_defaults core_params = { .get_max = core_get_max_pstate, .get_min = core_get_min_pstate, .get_turbo = core_get_turbo_pstate, + .get_scaling = core_get_scaling, .set = core_set_pstate, }, }; @@ -493,6 +528,7 @@ static struct cpu_defaults byt_params = { .get_min = byt_get_min_pstate, .get_turbo = byt_get_turbo_pstate, .set = byt_set_pstate, + .get_scaling = byt_get_scaling, .get_vid = byt_get_vid, }, }; @@ -526,7 +562,7 @@ static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate) if (pstate == cpu->pstate.current_pstate) return; - trace_cpu_frequency(pstate * 100000, cpu->cpu); + trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu); cpu->pstate.current_pstate = pstate; @@ -555,6 +591,7 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) cpu->pstate.min_pstate = pstate_funcs.get_min(); cpu->pstate.max_pstate = pstate_funcs.get_max(); cpu->pstate.turbo_pstate = pstate_funcs.get_turbo(); + cpu->pstate.scaling = pstate_funcs.get_scaling(); if (pstate_funcs.get_vid) pstate_funcs.get_vid(cpu); @@ -574,7 +611,9 @@ static inline void intel_pstate_calc_busy(struct cpudata *cpu, core_pct += 1; sample->freq = fp_toint( - mul_fp(int_tofp(cpu->pstate.max_pstate * 1000), core_pct)); + mul_fp(int_tofp( + cpu->pstate.max_pstate * cpu->pstate.scaling / 100), + core_pct)); sample->core_pct_busy = (int32_t)core_pct; } @@ -685,10 +724,14 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = { ICPU(0x37, byt_params), ICPU(0x3a, core_params), ICPU(0x3c, core_params), + ICPU(0x3d, core_params), ICPU(0x3e, core_params), ICPU(0x3f, core_params), ICPU(0x45, core_params), ICPU(0x46, core_params), + ICPU(0x4c, byt_params), + ICPU(0x4f, core_params), + ICPU(0x56, core_params), {} }; MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids); @@ -751,6 +794,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) { limits.min_perf_pct = 100; limits.min_perf = int_tofp(1); + limits.max_policy_pct = 100; limits.max_perf_pct = 100; limits.max_perf = int_tofp(1); limits.no_turbo = limits.turbo_disabled; @@ -812,12 +856,13 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy) else policy->policy = CPUFREQ_POLICY_POWERSAVE; - policy->min = cpu->pstate.min_pstate * 100000; - policy->max = cpu->pstate.turbo_pstate * 100000; + policy->min = cpu->pstate.min_pstate * cpu->pstate.scaling; + policy->max = cpu->pstate.turbo_pstate * cpu->pstate.scaling; /* cpuinfo and default policy values */ - policy->cpuinfo.min_freq = cpu->pstate.min_pstate * 100000; - policy->cpuinfo.max_freq = cpu->pstate.turbo_pstate * 100000; + policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling; + policy->cpuinfo.max_freq = + cpu->pstate.turbo_pstate * cpu->pstate.scaling; policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL; cpumask_set_cpu(policy->cpu, policy->cpus); @@ -875,6 +920,7 @@ static void copy_cpu_funcs(struct pstate_funcs *funcs) pstate_funcs.get_max = funcs->get_max; pstate_funcs.get_min = funcs->get_min; pstate_funcs.get_turbo = funcs->get_turbo; + pstate_funcs.get_scaling = funcs->get_scaling; pstate_funcs.set = funcs->set; pstate_funcs.get_vid = funcs->get_vid; } diff --git a/drivers/cpufreq/s3c2416-cpufreq.c b/drivers/cpufreq/s3c2416-cpufreq.c index 826b8be23099..82cef00a27d9 100644 --- a/drivers/cpufreq/s3c2416-cpufreq.c +++ b/drivers/cpufreq/s3c2416-cpufreq.c @@ -263,7 +263,7 @@ out: } #ifdef CONFIG_ARM_S3C2416_CPUFREQ_VCORESCALE -static void __init s3c2416_cpufreq_cfg_regulator(struct s3c2416_data *s3c_freq) +static void s3c2416_cpufreq_cfg_regulator(struct s3c2416_data *s3c_freq) { int count, v, i, found; struct cpufreq_frequency_table *freq; @@ -335,7 +335,7 @@ static struct notifier_block s3c2416_cpufreq_reboot_notifier = { .notifier_call = s3c2416_cpufreq_reboot_notifier_evt, }; -static int __init s3c2416_cpufreq_driver_init(struct cpufreq_policy *policy) +static int s3c2416_cpufreq_driver_init(struct cpufreq_policy *policy) { struct s3c2416_data *s3c_freq = &s3c2416_cpufreq; struct cpufreq_frequency_table *freq; diff --git a/drivers/cpufreq/s3c24xx-cpufreq.c b/drivers/cpufreq/s3c24xx-cpufreq.c index 25069741b507..0eb5b405c2f0 100644 --- a/drivers/cpufreq/s3c24xx-cpufreq.c +++ b/drivers/cpufreq/s3c24xx-cpufreq.c @@ -454,7 +454,7 @@ static struct cpufreq_driver s3c24xx_driver = { }; -int __init s3c_cpufreq_register(struct s3c_cpufreq_info *info) +int s3c_cpufreq_register(struct s3c_cpufreq_info *info) { if (!info || !info->name) { printk(KERN_ERR "%s: failed to pass valid information\n", diff --git a/drivers/cpufreq/speedstep-lib.c b/drivers/cpufreq/speedstep-lib.c index 7047821a7f8a..4ab7a2156672 100644 --- a/drivers/cpufreq/speedstep-lib.c +++ b/drivers/cpufreq/speedstep-lib.c @@ -400,6 +400,7 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor, pr_debug("previous speed is %u\n", prev_speed); + preempt_disable(); local_irq_save(flags); /* switch to low state */ @@ -464,6 +465,8 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor, out: local_irq_restore(flags); + preempt_enable(); + return ret; } EXPORT_SYMBOL_GPL(speedstep_get_freqs); diff --git a/drivers/cpufreq/speedstep-smi.c b/drivers/cpufreq/speedstep-smi.c index 998c17b42200..b52d8af1ab3c 100644 --- a/drivers/cpufreq/speedstep-smi.c +++ b/drivers/cpufreq/speedstep-smi.c @@ -156,6 +156,7 @@ static void speedstep_set_state(unsigned int state) return; /* Disable IRQs */ + preempt_disable(); local_irq_save(flags); command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff); @@ -166,9 +167,19 @@ static void speedstep_set_state(unsigned int state) do { if (retry) { + /* + * We need to enable interrupts, otherwise the blockage + * won't resolve. + * + * We disable preemption so that other processes don't + * run. If other processes were running, they could + * submit more DMA requests, making the blockage worse. + */ pr_debug("retry %u, previous result %u, waiting...\n", retry, result); + local_irq_enable(); mdelay(retry * 50); + local_irq_disable(); } retry++; __asm__ __volatile__( @@ -185,6 +196,7 @@ static void speedstep_set_state(unsigned int state) /* enable IRQs */ local_irq_restore(flags); + preempt_enable(); if (new_state == state) pr_debug("change to %u MHz succeeded after %u tries " diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index a55e68f2cfc8..e3d2052e7552 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -252,9 +252,6 @@ int cpuidle_enable_device(struct cpuidle_device *dev) if (!dev->registered) return -EINVAL; - if (!dev->state_count) - dev->state_count = drv->state_count; - ret = cpuidle_add_device_sysfs(dev); if (ret) return ret; diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c index e918b6d0caf7..dcaae4c8bc08 100644 --- a/drivers/cpuidle/sysfs.c +++ b/drivers/cpuidle/sysfs.c @@ -398,7 +398,7 @@ static int cpuidle_add_state_sysfs(struct cpuidle_device *device) struct cpuidle_driver *drv = cpuidle_get_cpu_driver(device); /* state statistics */ - for (i = 0; i < device->state_count; i++) { + for (i = 0; i < drv->state_count; i++) { kobj = kzalloc(sizeof(struct cpuidle_state_kobj), GFP_KERNEL); if (!kobj) goto error_state; @@ -430,9 +430,10 @@ error_state: */ static void cpuidle_remove_state_sysfs(struct cpuidle_device *device) { + struct cpuidle_driver *drv = cpuidle_get_cpu_driver(device); int i; - for (i = 0; i < device->state_count; i++) + for (i = 0; i < drv->state_count; i++) cpuidle_free_state_kobj(device, i); } diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c index 0378328f47a7..d97a03dbf42c 100644 --- a/drivers/crypto/caam/caamhash.c +++ b/drivers/crypto/caam/caamhash.c @@ -835,8 +835,9 @@ static int ahash_update_ctx(struct ahash_request *req) edesc->sec4_sg + sec4_sg_src_index, chained); if (*next_buflen) { - sg_copy_part(next_buf, req->src, to_hash - - *buflen, req->nbytes); + scatterwalk_map_and_copy(next_buf, req->src, + to_hash - *buflen, + *next_buflen, 0); state->current_buf = !state->current_buf; } } else { @@ -869,7 +870,8 @@ static int ahash_update_ctx(struct ahash_request *req) kfree(edesc); } } else if (*next_buflen) { - sg_copy(buf + *buflen, req->src, req->nbytes); + scatterwalk_map_and_copy(buf + *buflen, req->src, 0, + req->nbytes, 0); *buflen = *next_buflen; *next_buflen = last_buflen; } @@ -1216,8 +1218,9 @@ static int ahash_update_no_ctx(struct ahash_request *req) src_map_to_sec4_sg(jrdev, req->src, src_nents, edesc->sec4_sg + 1, chained); if (*next_buflen) { - sg_copy_part(next_buf, req->src, to_hash - *buflen, - req->nbytes); + scatterwalk_map_and_copy(next_buf, req->src, + to_hash - *buflen, + *next_buflen, 0); state->current_buf = !state->current_buf; } @@ -1248,7 +1251,8 @@ static int ahash_update_no_ctx(struct ahash_request *req) kfree(edesc); } } else if (*next_buflen) { - sg_copy(buf + *buflen, req->src, req->nbytes); + scatterwalk_map_and_copy(buf + *buflen, req->src, 0, + req->nbytes, 0); *buflen = *next_buflen; *next_buflen = 0; } @@ -1348,9 +1352,9 @@ static int ahash_update_first(struct ahash_request *req) struct device *jrdev = ctx->jrdev; gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP)) ? GFP_KERNEL : GFP_ATOMIC; - u8 *next_buf = state->buf_0 + state->current_buf * - CAAM_MAX_HASH_BLOCK_SIZE; - int *next_buflen = &state->buflen_0 + state->current_buf; + u8 *next_buf = state->current_buf ? state->buf_1 : state->buf_0; + int *next_buflen = state->current_buf ? + &state->buflen_1 : &state->buflen_0; int to_hash; u32 *sh_desc = ctx->sh_desc_update_first, *desc; dma_addr_t ptr = ctx->sh_desc_update_first_dma; @@ -1405,7 +1409,8 @@ static int ahash_update_first(struct ahash_request *req) } if (*next_buflen) - sg_copy_part(next_buf, req->src, to_hash, req->nbytes); + scatterwalk_map_and_copy(next_buf, req->src, to_hash, + *next_buflen, 0); sh_len = desc_len(sh_desc); desc = edesc->hw_desc; @@ -1438,7 +1443,8 @@ static int ahash_update_first(struct ahash_request *req) state->update = ahash_update_no_ctx; state->finup = ahash_finup_no_ctx; state->final = ahash_final_no_ctx; - sg_copy(next_buf, req->src, req->nbytes); + scatterwalk_map_and_copy(next_buf, req->src, 0, + req->nbytes, 0); } #ifdef DEBUG print_hex_dump(KERN_ERR, "next buf@"__stringify(__LINE__)": ", diff --git a/drivers/crypto/caam/key_gen.c b/drivers/crypto/caam/key_gen.c index ea2e406610eb..b872eed2957b 100644 --- a/drivers/crypto/caam/key_gen.c +++ b/drivers/crypto/caam/key_gen.c @@ -51,23 +51,29 @@ int gen_split_key(struct device *jrdev, u8 *key_out, int split_key_len, u32 *desc; struct split_key_result result; dma_addr_t dma_addr_in, dma_addr_out; - int ret = 0; + int ret = -ENOMEM; desc = kmalloc(CAAM_CMD_SZ * 6 + CAAM_PTR_SZ * 2, GFP_KERNEL | GFP_DMA); if (!desc) { dev_err(jrdev, "unable to allocate key input memory\n"); - return -ENOMEM; + return ret; } - init_job_desc(desc, 0); - dma_addr_in = dma_map_single(jrdev, (void *)key_in, keylen, DMA_TO_DEVICE); if (dma_mapping_error(jrdev, dma_addr_in)) { dev_err(jrdev, "unable to map key input memory\n"); - kfree(desc); - return -ENOMEM; + goto out_free; } + + dma_addr_out = dma_map_single(jrdev, key_out, split_key_pad_len, + DMA_FROM_DEVICE); + if (dma_mapping_error(jrdev, dma_addr_out)) { + dev_err(jrdev, "unable to map key output memory\n"); + goto out_unmap_in; + } + + init_job_desc(desc, 0); append_key(desc, dma_addr_in, keylen, CLASS_2 | KEY_DEST_CLASS_REG); /* Sets MDHA up into an HMAC-INIT */ @@ -84,13 +90,6 @@ int gen_split_key(struct device *jrdev, u8 *key_out, int split_key_len, * FIFO_STORE with the explicit split-key content store * (0x26 output type) */ - dma_addr_out = dma_map_single(jrdev, key_out, split_key_pad_len, - DMA_FROM_DEVICE); - if (dma_mapping_error(jrdev, dma_addr_out)) { - dev_err(jrdev, "unable to map key output memory\n"); - kfree(desc); - return -ENOMEM; - } append_fifo_store(desc, dma_addr_out, split_key_len, LDST_CLASS_2_CCB | FIFOST_TYPE_SPLIT_KEK); @@ -118,10 +117,10 @@ int gen_split_key(struct device *jrdev, u8 *key_out, int split_key_len, dma_unmap_single(jrdev, dma_addr_out, split_key_pad_len, DMA_FROM_DEVICE); +out_unmap_in: dma_unmap_single(jrdev, dma_addr_in, keylen, DMA_TO_DEVICE); - +out_free: kfree(desc); - return ret; } EXPORT_SYMBOL(gen_split_key); diff --git a/drivers/crypto/caam/sg_sw_sec4.h b/drivers/crypto/caam/sg_sw_sec4.h index b12ff85f4241..ce28a563effc 100644 --- a/drivers/crypto/caam/sg_sw_sec4.h +++ b/drivers/crypto/caam/sg_sw_sec4.h @@ -116,57 +116,3 @@ static int dma_unmap_sg_chained(struct device *dev, struct scatterlist *sg, } return nents; } - -/* Map SG page in kernel virtual address space and copy */ -static inline void sg_map_copy(u8 *dest, struct scatterlist *sg, - int len, int offset) -{ - u8 *mapped_addr; - - /* - * Page here can be user-space pinned using get_user_pages - * Same must be kmapped before use and kunmapped subsequently - */ - mapped_addr = kmap_atomic(sg_page(sg)); - memcpy(dest, mapped_addr + offset, len); - kunmap_atomic(mapped_addr); -} - -/* Copy from len bytes of sg to dest, starting from beginning */ -static inline void sg_copy(u8 *dest, struct scatterlist *sg, unsigned int len) -{ - struct scatterlist *current_sg = sg; - int cpy_index = 0, next_cpy_index = current_sg->length; - - while (next_cpy_index < len) { - sg_map_copy(dest + cpy_index, current_sg, current_sg->length, - current_sg->offset); - current_sg = scatterwalk_sg_next(current_sg); - cpy_index = next_cpy_index; - next_cpy_index += current_sg->length; - } - if (cpy_index < len) - sg_map_copy(dest + cpy_index, current_sg, len-cpy_index, - current_sg->offset); -} - -/* Copy sg data, from to_skip to end, to dest */ -static inline void sg_copy_part(u8 *dest, struct scatterlist *sg, - int to_skip, unsigned int end) -{ - struct scatterlist *current_sg = sg; - int sg_index, cpy_index, offset; - - sg_index = current_sg->length; - while (sg_index <= to_skip) { - current_sg = scatterwalk_sg_next(current_sg); - sg_index += current_sg->length; - } - cpy_index = sg_index - to_skip; - offset = current_sg->offset + current_sg->length - cpy_index; - sg_map_copy(dest, current_sg, cpy_index, offset); - if (end - sg_index) { - current_sg = scatterwalk_sg_next(current_sg); - sg_copy(dest + cpy_index, current_sg, end - sg_index); - } -} diff --git a/drivers/crypto/nx/nx-842.c b/drivers/crypto/nx/nx-842.c index 1e5481d88a26..d2ab58569fdd 100644 --- a/drivers/crypto/nx/nx-842.c +++ b/drivers/crypto/nx/nx-842.c @@ -936,28 +936,14 @@ static int nx842_OF_upd(struct property *new_prop) goto error_out; } - /* Set ptr to new property if provided */ - if (new_prop) { - /* Single property */ - if (!strncmp(new_prop->name, "status", new_prop->length)) { - status = new_prop; - - } else if (!strncmp(new_prop->name, "ibm,max-sg-len", - new_prop->length)) { - maxsglen = new_prop; - - } else if (!strncmp(new_prop->name, "ibm,max-sync-cop", - new_prop->length)) { - maxsyncop = new_prop; - - } else { - /* - * Skip the update, the property being updated - * has no impact. - */ - goto out; - } - } + /* + * If this is a property update, there are only certain properties that + * we care about. Bail if it isn't in the below list + */ + if (new_prop && (strncmp(new_prop->name, "status", new_prop->length) || + strncmp(new_prop->name, "ibm,max-sg-len", new_prop->length) || + strncmp(new_prop->name, "ibm,max-sync-cop", new_prop->length))) + goto out; /* Perform property updates */ ret = nx842_OF_upd_status(new_devdata, status); @@ -1023,9 +1009,9 @@ error_out: * notifier_to_errno() to decode this value */ static int nx842_OF_notifier(struct notifier_block *np, unsigned long action, - void *update) + void *data) { - struct of_prop_reconfig *upd = update; + struct of_reconfig_data *upd = data; struct nx842_devdata *local_devdata; struct device_node *node = NULL; diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c index 633ba945e153..c178ed8c3908 100644 --- a/drivers/crypto/padlock-aes.c +++ b/drivers/crypto/padlock-aes.c @@ -563,4 +563,4 @@ MODULE_DESCRIPTION("VIA PadLock AES algorithm support"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Michal Ludvig"); -MODULE_ALIAS("aes"); +MODULE_ALIAS_CRYPTO("aes"); diff --git a/drivers/crypto/padlock-sha.c b/drivers/crypto/padlock-sha.c index 9266c0e25492..93d7753ab38a 100644 --- a/drivers/crypto/padlock-sha.c +++ b/drivers/crypto/padlock-sha.c @@ -593,7 +593,7 @@ MODULE_DESCRIPTION("VIA PadLock SHA1/SHA256 algorithms support."); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Michal Ludvig"); -MODULE_ALIAS("sha1-all"); -MODULE_ALIAS("sha256-all"); -MODULE_ALIAS("sha1-padlock"); -MODULE_ALIAS("sha256-padlock"); +MODULE_ALIAS_CRYPTO("sha1-all"); +MODULE_ALIAS_CRYPTO("sha256-all"); +MODULE_ALIAS_CRYPTO("sha1-padlock"); +MODULE_ALIAS_CRYPTO("sha256-padlock"); diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c index 92105f3dc8e0..e4cea7c45142 100644 --- a/drivers/crypto/ux500/cryp/cryp_core.c +++ b/drivers/crypto/ux500/cryp/cryp_core.c @@ -1810,7 +1810,7 @@ module_exit(ux500_cryp_mod_fini); module_param(cryp_mode, int, 0); MODULE_DESCRIPTION("Driver for ST-Ericsson UX500 CRYP crypto engine."); -MODULE_ALIAS("aes-all"); -MODULE_ALIAS("des-all"); +MODULE_ALIAS_CRYPTO("aes-all"); +MODULE_ALIAS_CRYPTO("des-all"); MODULE_LICENSE("GPL"); diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c index 1c73f4fbc252..8e5e0187506f 100644 --- a/drivers/crypto/ux500/hash/hash_core.c +++ b/drivers/crypto/ux500/hash/hash_core.c @@ -1995,7 +1995,7 @@ module_exit(ux500_hash_mod_fini); MODULE_DESCRIPTION("Driver for ST-Ericsson UX500 HASH engine."); MODULE_LICENSE("GPL"); -MODULE_ALIAS("sha1-all"); -MODULE_ALIAS("sha256-all"); -MODULE_ALIAS("hmac-sha1-all"); -MODULE_ALIAS("hmac-sha256-all"); +MODULE_ALIAS_CRYPTO("sha1-all"); +MODULE_ALIAS_CRYPTO("sha256-all"); +MODULE_ALIAS_CRYPTO("hmac-sha1-all"); +MODULE_ALIAS_CRYPTO("hmac-sha256-all"); diff --git a/drivers/dma/TODO b/drivers/dma/TODO index 734ed0206cd5..b8045cd42ee1 100644 --- a/drivers/dma/TODO +++ b/drivers/dma/TODO @@ -7,7 +7,6 @@ TODO for slave dma - imx-dma - imx-sdma - mxs-dma.c - - dw_dmac - intel_mid_dma 4. Check other subsystems for dma drivers and merge/move to dmaengine 5. Remove dma_slave_config's dma direction. diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c index 01a200cd0189..b0972b3869c7 100644 --- a/drivers/dma/dw/core.c +++ b/drivers/dma/dw/core.c @@ -279,6 +279,15 @@ static void dwc_dostart(struct dw_dma_chan *dwc, struct dw_desc *first) channel_set_bit(dw, CH_EN, dwc->mask); } +static void dwc_dostart_first_queued(struct dw_dma_chan *dwc) +{ + if (list_empty(&dwc->queue)) + return; + + list_move(dwc->queue.next, &dwc->active_list); + dwc_dostart(dwc, dwc_first_active(dwc)); +} + /*----------------------------------------------------------------------*/ static void @@ -335,10 +344,7 @@ static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc) * the completed ones. */ list_splice_init(&dwc->active_list, &list); - if (!list_empty(&dwc->queue)) { - list_move(dwc->queue.next, &dwc->active_list); - dwc_dostart(dwc, dwc_first_active(dwc)); - } + dwc_dostart_first_queued(dwc); spin_unlock_irqrestore(&dwc->lock, flags); @@ -467,10 +473,7 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc) /* Try to continue after resetting the channel... */ dwc_chan_disable(dw, dwc); - if (!list_empty(&dwc->queue)) { - list_move(dwc->queue.next, &dwc->active_list); - dwc_dostart(dwc, dwc_first_active(dwc)); - } + dwc_dostart_first_queued(dwc); spin_unlock_irqrestore(&dwc->lock, flags); } @@ -677,17 +680,9 @@ static dma_cookie_t dwc_tx_submit(struct dma_async_tx_descriptor *tx) * possible, perhaps even appending to those already submitted * for DMA. But this is hard to do in a race-free manner. */ - if (list_empty(&dwc->active_list)) { - dev_vdbg(chan2dev(tx->chan), "%s: started %u\n", __func__, - desc->txd.cookie); - list_add_tail(&desc->desc_node, &dwc->active_list); - dwc_dostart(dwc, dwc_first_active(dwc)); - } else { - dev_vdbg(chan2dev(tx->chan), "%s: queued %u\n", __func__, - desc->txd.cookie); - list_add_tail(&desc->desc_node, &dwc->queue); - } + dev_vdbg(chan2dev(tx->chan), "%s: queued %u\n", __func__, desc->txd.cookie); + list_add_tail(&desc->desc_node, &dwc->queue); spin_unlock_irqrestore(&dwc->lock, flags); @@ -1092,9 +1087,12 @@ dwc_tx_status(struct dma_chan *chan, static void dwc_issue_pending(struct dma_chan *chan) { struct dw_dma_chan *dwc = to_dw_dma_chan(chan); + unsigned long flags; - if (!list_empty(&dwc->queue)) - dwc_scan_descriptors(to_dw_dma(chan->device), dwc); + spin_lock_irqsave(&dwc->lock, flags); + if (list_empty(&dwc->active_list)) + dwc_dostart_first_queued(dwc); + spin_unlock_irqrestore(&dwc->lock, flags); } static int dwc_alloc_chan_resources(struct dma_chan *chan) diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c index 453822cc4f9d..fe8b0c991518 100644 --- a/drivers/dma/dw/platform.c +++ b/drivers/dma/dw/platform.c @@ -48,6 +48,8 @@ static bool dw_dma_of_filter(struct dma_chan *chan, void *param) return true; } +#define DRV_NAME "dw_dmac" + static struct dma_chan *dw_dma_of_xlate(struct of_phandle_args *dma_spec, struct of_dma *ofdma) { @@ -293,7 +295,7 @@ static struct platform_driver dw_driver = { .remove = dw_remove, .shutdown = dw_shutdown, .driver = { - .name = "dw_dmac", + .name = DRV_NAME, .pm = &dw_dev_pm_ops, .of_match_table = of_match_ptr(dw_dma_of_id_table), .acpi_match_table = ACPI_PTR(dw_dma_acpi_id_table), @@ -314,3 +316,4 @@ module_exit(dw_exit); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("Synopsys DesignWare DMA Controller platform driver"); +MODULE_ALIAS("platform:" DRV_NAME); diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c index 362e7c49f2e1..12f82942e347 100644 --- a/drivers/dma/omap-dma.c +++ b/drivers/dma/omap-dma.c @@ -487,6 +487,7 @@ static int omap_dma_terminate_all(struct omap_chan *c) * c->desc is NULL and exit.) */ if (c->desc) { + omap_dma_desc_free(&c->desc->vd); c->desc = NULL; /* Avoid stopping the dma twice */ if (!c->paused) diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 98e14ee4833c..278603c373ca 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -2006,14 +2006,20 @@ static void __log_bus_error(struct mem_ctl_info *mci, struct err_info *err, static inline void decode_bus_error(int node_id, struct mce *m) { - struct mem_ctl_info *mci = mcis[node_id]; - struct amd64_pvt *pvt = mci->pvt_info; + struct mem_ctl_info *mci; + struct amd64_pvt *pvt; u8 ecc_type = (m->status >> 45) & 0x3; u8 xec = XEC(m->status, 0x1f); u16 ec = EC(m->status); u64 sys_addr; struct err_info err; + mci = edac_mc_find(node_id); + if (!mci) + return; + + pvt = mci->pvt_info; + /* Bail out early if this was an 'observed' error */ if (PP(ec) == NBSL_PP_OBS) return; diff --git a/drivers/edac/cpc925_edac.c b/drivers/edac/cpc925_edac.c index df6575f1430d..682288ced4ac 100644 --- a/drivers/edac/cpc925_edac.c +++ b/drivers/edac/cpc925_edac.c @@ -562,7 +562,7 @@ static void cpc925_mc_check(struct mem_ctl_info *mci) if (apiexcp & UECC_EXCP_DETECTED) { cpc925_mc_printk(mci, KERN_INFO, "DRAM UECC Fault\n"); - edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1, + edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, pfn, offset, 0, csrow, -1, -1, mci->ctl_name, ""); diff --git a/drivers/edac/e7xxx_edac.c b/drivers/edac/e7xxx_edac.c index 3cda79bc8b00..ece3aef16bb1 100644 --- a/drivers/edac/e7xxx_edac.c +++ b/drivers/edac/e7xxx_edac.c @@ -226,7 +226,7 @@ static void process_ce(struct mem_ctl_info *mci, struct e7xxx_error_info *info) static void process_ce_no_info(struct mem_ctl_info *mci) { edac_dbg(3, "\n"); - edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, 0, 0, 0, -1, -1, -1, + edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1, 0, 0, 0, -1, -1, -1, "e7xxx CE log register overflow", ""); } diff --git a/drivers/edac/i3200_edac.c b/drivers/edac/i3200_edac.c index fa1326e5a4b0..ad76f10865c6 100644 --- a/drivers/edac/i3200_edac.c +++ b/drivers/edac/i3200_edac.c @@ -242,11 +242,11 @@ static void i3200_process_error_info(struct mem_ctl_info *mci, -1, -1, "i3000 UE", ""); } else if (log & I3200_ECCERRLOG_CE) { - edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, + edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1, 0, 0, eccerrlog_syndrome(log), eccerrlog_row(channel, log), -1, -1, - "i3000 UE", ""); + "i3000 CE", ""); } } } diff --git a/drivers/edac/i82860_edac.c b/drivers/edac/i82860_edac.c index 3382f6344e42..4382343a7c60 100644 --- a/drivers/edac/i82860_edac.c +++ b/drivers/edac/i82860_edac.c @@ -124,7 +124,7 @@ static int i82860_process_error_info(struct mem_ctl_info *mci, dimm->location[0], dimm->location[1], -1, "i82860 UE", ""); else - edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, + edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1, info->eap, 0, info->derrsyn, dimm->location[0], dimm->location[1], -1, "i82860 CE", ""); diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index d7d5c8af92b9..6d4456898007 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -1637,8 +1637,7 @@ static int dispatch_ioctl(struct client *client, _IOC_SIZE(cmd) > sizeof(buffer)) return -ENOTTY; - if (_IOC_DIR(cmd) == _IOC_READ) - memset(&buffer, 0, _IOC_SIZE(cmd)); + memset(&buffer, 0, sizeof(buffer)); if (_IOC_DIR(cmd) & _IOC_WRITE) if (copy_from_user(&buffer, arg, _IOC_SIZE(cmd))) diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig index 1e75f48b61f8..d420ae2d3413 100644 --- a/drivers/firmware/efi/Kconfig +++ b/drivers/firmware/efi/Kconfig @@ -47,6 +47,13 @@ config EFI_RUNTIME_MAP See also Documentation/ABI/testing/sysfs-firmware-efi-runtime-map. +config EFI_PARAMS_FROM_FDT + bool + help + Select this config option from the architecture Kconfig if + the EFI runtime support gets system table address, memory + map address, and other parameters from the device tree. + endmenu config UEFI_CPER diff --git a/drivers/firmware/efi/arm-stub.c b/drivers/firmware/efi/arm-stub.c new file mode 100644 index 000000000000..41114ce03b01 --- /dev/null +++ b/drivers/firmware/efi/arm-stub.c @@ -0,0 +1,278 @@ +/* + * EFI stub implementation that is shared by arm and arm64 architectures. + * This should be #included by the EFI stub implementation files. + * + * Copyright (C) 2013,2014 Linaro Limited + * Roy Franz <roy.franz@linaro.org + * Copyright (C) 2013 Red Hat, Inc. + * Mark Salter <msalter@redhat.com> + * + * This file is part of the Linux kernel, and is made available under the + * terms of the GNU General Public License version 2. + * + */ + +static int __init efi_secureboot_enabled(efi_system_table_t *sys_table_arg) +{ + static efi_guid_t const var_guid __initconst = EFI_GLOBAL_VARIABLE_GUID; + static efi_char16_t const var_name[] __initconst = { + 'S', 'e', 'c', 'u', 'r', 'e', 'B', 'o', 'o', 't', 0 }; + + efi_get_variable_t *f_getvar = sys_table_arg->runtime->get_variable; + unsigned long size = sizeof(u8); + efi_status_t status; + u8 val; + + status = f_getvar((efi_char16_t *)var_name, (efi_guid_t *)&var_guid, + NULL, &size, &val); + + switch (status) { + case EFI_SUCCESS: + return val; + case EFI_NOT_FOUND: + return 0; + default: + return 1; + } +} + +static efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, + void *__image, void **__fh) +{ + efi_file_io_interface_t *io; + efi_loaded_image_t *image = __image; + efi_file_handle_t *fh; + efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID; + efi_status_t status; + void *handle = (void *)(unsigned long)image->device_handle; + + status = sys_table_arg->boottime->handle_protocol(handle, + &fs_proto, (void **)&io); + if (status != EFI_SUCCESS) { + efi_printk(sys_table_arg, "Failed to handle fs_proto\n"); + return status; + } + + status = io->open_volume(io, &fh); + if (status != EFI_SUCCESS) + efi_printk(sys_table_arg, "Failed to open volume\n"); + + *__fh = fh; + return status; +} +static efi_status_t efi_file_close(void *handle) +{ + efi_file_handle_t *fh = handle; + + return fh->close(handle); +} + +static efi_status_t +efi_file_read(void *handle, unsigned long *size, void *addr) +{ + efi_file_handle_t *fh = handle; + + return fh->read(handle, size, addr); +} + + +static efi_status_t +efi_file_size(efi_system_table_t *sys_table_arg, void *__fh, + efi_char16_t *filename_16, void **handle, u64 *file_sz) +{ + efi_file_handle_t *h, *fh = __fh; + efi_file_info_t *info; + efi_status_t status; + efi_guid_t info_guid = EFI_FILE_INFO_ID; + unsigned long info_sz; + + status = fh->open(fh, &h, filename_16, EFI_FILE_MODE_READ, (u64)0); + if (status != EFI_SUCCESS) { + efi_printk(sys_table_arg, "Failed to open file: "); + efi_char16_printk(sys_table_arg, filename_16); + efi_printk(sys_table_arg, "\n"); + return status; + } + + *handle = h; + + info_sz = 0; + status = h->get_info(h, &info_guid, &info_sz, NULL); + if (status != EFI_BUFFER_TOO_SMALL) { + efi_printk(sys_table_arg, "Failed to get file info size\n"); + return status; + } + +grow: + status = sys_table_arg->boottime->allocate_pool(EFI_LOADER_DATA, + info_sz, (void **)&info); + if (status != EFI_SUCCESS) { + efi_printk(sys_table_arg, "Failed to alloc mem for file info\n"); + return status; + } + + status = h->get_info(h, &info_guid, &info_sz, + info); + if (status == EFI_BUFFER_TOO_SMALL) { + sys_table_arg->boottime->free_pool(info); + goto grow; + } + + *file_sz = info->file_size; + sys_table_arg->boottime->free_pool(info); + + if (status != EFI_SUCCESS) + efi_printk(sys_table_arg, "Failed to get initrd info\n"); + + return status; +} + + + +static void efi_char16_printk(efi_system_table_t *sys_table_arg, + efi_char16_t *str) +{ + struct efi_simple_text_output_protocol *out; + + out = (struct efi_simple_text_output_protocol *)sys_table_arg->con_out; + out->output_string(out, str); +} + + +/* + * This function handles the architcture specific differences between arm and + * arm64 regarding where the kernel image must be loaded and any memory that + * must be reserved. On failure it is required to free all + * all allocations it has made. + */ +static efi_status_t handle_kernel_image(efi_system_table_t *sys_table, + unsigned long *image_addr, + unsigned long *image_size, + unsigned long *reserve_addr, + unsigned long *reserve_size, + unsigned long dram_base, + efi_loaded_image_t *image); +/* + * EFI entry point for the arm/arm64 EFI stubs. This is the entrypoint + * that is described in the PE/COFF header. Most of the code is the same + * for both archictectures, with the arch-specific code provided in the + * handle_kernel_image() function. + */ +unsigned long __init efi_entry(void *handle, efi_system_table_t *sys_table, + unsigned long *image_addr) +{ + efi_loaded_image_t *image; + efi_status_t status; + unsigned long image_size = 0; + unsigned long dram_base; + /* addr/point and size pairs for memory management*/ + unsigned long initrd_addr; + u64 initrd_size = 0; + unsigned long fdt_addr = 0; /* Original DTB */ + u64 fdt_size = 0; /* We don't get size from configuration table */ + char *cmdline_ptr = NULL; + int cmdline_size = 0; + unsigned long new_fdt_addr; + efi_guid_t loaded_image_proto = LOADED_IMAGE_PROTOCOL_GUID; + unsigned long reserve_addr = 0; + unsigned long reserve_size = 0; + + /* Check if we were booted by the EFI firmware */ + if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) + goto fail; + + pr_efi(sys_table, "Booting Linux Kernel...\n"); + + /* + * Get a handle to the loaded image protocol. This is used to get + * information about the running image, such as size and the command + * line. + */ + status = sys_table->boottime->handle_protocol(handle, + &loaded_image_proto, (void *)&image); + if (status != EFI_SUCCESS) { + pr_efi_err(sys_table, "Failed to get loaded image protocol\n"); + goto fail; + } + + dram_base = get_dram_base(sys_table); + if (dram_base == EFI_ERROR) { + pr_efi_err(sys_table, "Failed to find DRAM base\n"); + goto fail; + } + status = handle_kernel_image(sys_table, image_addr, &image_size, + &reserve_addr, + &reserve_size, + dram_base, image); + if (status != EFI_SUCCESS) { + pr_efi_err(sys_table, "Failed to relocate kernel\n"); + goto fail; + } + + /* + * Get the command line from EFI, using the LOADED_IMAGE + * protocol. We are going to copy the command line into the + * device tree, so this can be allocated anywhere. + */ + cmdline_ptr = efi_convert_cmdline(sys_table, image, &cmdline_size); + if (!cmdline_ptr) { + pr_efi_err(sys_table, "getting command line via LOADED_IMAGE_PROTOCOL\n"); + goto fail_free_image; + } + + /* + * Unauthenticated device tree data is a security hazard, so + * ignore 'dtb=' unless UEFI Secure Boot is disabled. + */ + if (efi_secureboot_enabled(sys_table)) { + pr_efi(sys_table, "UEFI Secure Boot is enabled.\n"); + } else { + status = handle_cmdline_files(sys_table, image, cmdline_ptr, + "dtb=", + ~0UL, (unsigned long *)&fdt_addr, + (unsigned long *)&fdt_size); + + if (status != EFI_SUCCESS) { + pr_efi_err(sys_table, "Failed to load device tree!\n"); + goto fail_free_cmdline; + } + } + if (!fdt_addr) + /* Look for a device tree configuration table entry. */ + fdt_addr = (uintptr_t)get_fdt(sys_table); + + status = handle_cmdline_files(sys_table, image, cmdline_ptr, + "initrd=", dram_base + SZ_512M, + (unsigned long *)&initrd_addr, + (unsigned long *)&initrd_size); + if (status != EFI_SUCCESS) + pr_efi_err(sys_table, "Failed initrd from command line!\n"); + + new_fdt_addr = fdt_addr; + status = allocate_new_fdt_and_exit_boot(sys_table, handle, + &new_fdt_addr, dram_base + MAX_FDT_OFFSET, + initrd_addr, initrd_size, cmdline_ptr, + fdt_addr, fdt_size); + + /* + * If all went well, we need to return the FDT address to the + * calling function so it can be passed to kernel as part of + * the kernel boot protocol. + */ + if (status == EFI_SUCCESS) + return new_fdt_addr; + + pr_efi_err(sys_table, "Failed to update FDT and exit boot services\n"); + + efi_free(sys_table, initrd_size, initrd_addr); + efi_free(sys_table, fdt_size, fdt_addr); + +fail_free_cmdline: + efi_free(sys_table, cmdline_size, (unsigned long)cmdline_ptr); + +fail_free_image: + efi_free(sys_table, image_size, *image_addr); + efi_free(sys_table, reserve_size, reserve_addr); +fail: + return EFI_ERROR; +} diff --git a/drivers/firmware/efi/efi-stub-helper.c b/drivers/firmware/efi/efi-stub-helper.c index 3a74def216a5..eb6d4be9e722 100644 --- a/drivers/firmware/efi/efi-stub-helper.c +++ b/drivers/firmware/efi/efi-stub-helper.c @@ -11,23 +11,15 @@ */ #define EFI_READ_CHUNK_SIZE (1024 * 1024) +/* error code which can't be mistaken for valid address */ +#define EFI_ERROR (~0UL) + + struct file_info { efi_file_handle_t *handle; u64 size; }; - - - -static void efi_char16_printk(efi_system_table_t *sys_table_arg, - efi_char16_t *str) -{ - struct efi_simple_text_output_protocol *out; - - out = (struct efi_simple_text_output_protocol *)sys_table_arg->con_out; - efi_call_phys2(out->output_string, out, str); -} - static void efi_printk(efi_system_table_t *sys_table_arg, char *str) { char *s8; @@ -45,6 +37,9 @@ static void efi_printk(efi_system_table_t *sys_table_arg, char *str) } } +#define pr_efi(sys_table, msg) efi_printk(sys_table, "EFI stub: "msg) +#define pr_efi_err(sys_table, msg) efi_printk(sys_table, "EFI stub: ERROR: "msg) + static efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg, efi_memory_desc_t **map, @@ -65,20 +60,23 @@ again: * allocation which may be in a new descriptor region. */ *map_size += sizeof(*m); - status = efi_call_phys3(sys_table_arg->boottime->allocate_pool, - EFI_LOADER_DATA, *map_size, (void **)&m); + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, + *map_size, (void **)&m); if (status != EFI_SUCCESS) goto fail; - status = efi_call_phys5(sys_table_arg->boottime->get_memory_map, - map_size, m, &key, desc_size, &desc_version); + *desc_size = 0; + key = 0; + status = efi_call_early(get_memory_map, map_size, m, + &key, desc_size, &desc_version); if (status == EFI_BUFFER_TOO_SMALL) { - efi_call_phys1(sys_table_arg->boottime->free_pool, m); + efi_call_early(free_pool, m); goto again; } if (status != EFI_SUCCESS) - efi_call_phys1(sys_table_arg->boottime->free_pool, m); + efi_call_early(free_pool, m); + if (key_ptr && status == EFI_SUCCESS) *key_ptr = key; if (desc_ver && status == EFI_SUCCESS) @@ -89,6 +87,32 @@ fail: return status; } + +static unsigned long __init get_dram_base(efi_system_table_t *sys_table_arg) +{ + efi_status_t status; + unsigned long map_size; + unsigned long membase = EFI_ERROR; + struct efi_memory_map map; + efi_memory_desc_t *md; + + status = efi_get_memory_map(sys_table_arg, (efi_memory_desc_t **)&map.map, + &map_size, &map.desc_size, NULL, NULL); + if (status != EFI_SUCCESS) + return membase; + + map.map_end = map.map + map_size; + + for_each_efi_memory_desc(&map, md) + if (md->attribute & EFI_MEMORY_WB) + if (membase > md->phys_addr) + membase = md->phys_addr; + + efi_call_early(free_pool, map.map); + + return membase; +} + /* * Allocate at the highest possible address that is not above 'max'. */ @@ -158,7 +182,7 @@ again: if (!max_addr) status = EFI_NOT_FOUND; else { - status = efi_call_phys4(sys_table_arg->boottime->allocate_pages, + status = efi_call_early(allocate_pages, EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA, nr_pages, &max_addr); if (status != EFI_SUCCESS) { @@ -170,8 +194,7 @@ again: *addr = max_addr; } - efi_call_phys1(sys_table_arg->boottime->free_pool, map); - + efi_call_early(free_pool, map); fail: return status; } @@ -231,7 +254,7 @@ static efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg, if ((start + size) > end) continue; - status = efi_call_phys4(sys_table_arg->boottime->allocate_pages, + status = efi_call_early(allocate_pages, EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA, nr_pages, &start); if (status == EFI_SUCCESS) { @@ -243,7 +266,7 @@ static efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg, if (i == map_size / desc_size) status = EFI_NOT_FOUND; - efi_call_phys1(sys_table_arg->boottime->free_pool, map); + efi_call_early(free_pool, map); fail: return status; } @@ -257,7 +280,7 @@ static void efi_free(efi_system_table_t *sys_table_arg, unsigned long size, return; nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE; - efi_call_phys2(sys_table_arg->boottime->free_pages, addr, nr_pages); + efi_call_early(free_pages, addr, nr_pages); } @@ -276,10 +299,8 @@ static efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg, { struct file_info *files; unsigned long file_addr; - efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID; u64 file_size_total; - efi_file_io_interface_t *io; - efi_file_handle_t *fh; + efi_file_handle_t *fh = NULL; efi_status_t status; int nr_files; char *str; @@ -319,25 +340,18 @@ static efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg, if (!nr_files) return EFI_SUCCESS; - status = efi_call_phys3(sys_table_arg->boottime->allocate_pool, - EFI_LOADER_DATA, - nr_files * sizeof(*files), - (void **)&files); + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, + nr_files * sizeof(*files), (void **)&files); if (status != EFI_SUCCESS) { - efi_printk(sys_table_arg, "Failed to alloc mem for file handle list\n"); + pr_efi_err(sys_table_arg, "Failed to alloc mem for file handle list\n"); goto fail; } str = cmd_line; for (i = 0; i < nr_files; i++) { struct file_info *file; - efi_file_handle_t *h; - efi_file_info_t *info; efi_char16_t filename_16[256]; - unsigned long info_sz; - efi_guid_t info_guid = EFI_FILE_INFO_ID; efi_char16_t *p; - u64 file_sz; str = strstr(str, option_string); if (!str) @@ -368,71 +382,18 @@ static efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg, /* Only open the volume once. */ if (!i) { - efi_boot_services_t *boottime; - - boottime = sys_table_arg->boottime; - - status = efi_call_phys3(boottime->handle_protocol, - image->device_handle, &fs_proto, - (void **)&io); - if (status != EFI_SUCCESS) { - efi_printk(sys_table_arg, "Failed to handle fs_proto\n"); + status = efi_open_volume(sys_table_arg, image, + (void **)&fh); + if (status != EFI_SUCCESS) goto free_files; - } - - status = efi_call_phys2(io->open_volume, io, &fh); - if (status != EFI_SUCCESS) { - efi_printk(sys_table_arg, "Failed to open volume\n"); - goto free_files; - } - } - - status = efi_call_phys5(fh->open, fh, &h, filename_16, - EFI_FILE_MODE_READ, (u64)0); - if (status != EFI_SUCCESS) { - efi_printk(sys_table_arg, "Failed to open file: "); - efi_char16_printk(sys_table_arg, filename_16); - efi_printk(sys_table_arg, "\n"); - goto close_handles; } - file->handle = h; - - info_sz = 0; - status = efi_call_phys4(h->get_info, h, &info_guid, - &info_sz, NULL); - if (status != EFI_BUFFER_TOO_SMALL) { - efi_printk(sys_table_arg, "Failed to get file info size\n"); + status = efi_file_size(sys_table_arg, fh, filename_16, + (void **)&file->handle, &file->size); + if (status != EFI_SUCCESS) goto close_handles; - } -grow: - status = efi_call_phys3(sys_table_arg->boottime->allocate_pool, - EFI_LOADER_DATA, info_sz, - (void **)&info); - if (status != EFI_SUCCESS) { - efi_printk(sys_table_arg, "Failed to alloc mem for file info\n"); - goto close_handles; - } - - status = efi_call_phys4(h->get_info, h, &info_guid, - &info_sz, info); - if (status == EFI_BUFFER_TOO_SMALL) { - efi_call_phys1(sys_table_arg->boottime->free_pool, - info); - goto grow; - } - - file_sz = info->file_size; - efi_call_phys1(sys_table_arg->boottime->free_pool, info); - - if (status != EFI_SUCCESS) { - efi_printk(sys_table_arg, "Failed to get file info\n"); - goto close_handles; - } - - file->size = file_sz; - file_size_total += file_sz; + file_size_total += file->size; } if (file_size_total) { @@ -446,13 +407,13 @@ grow: status = efi_high_alloc(sys_table_arg, file_size_total, 0x1000, &file_addr, max_addr); if (status != EFI_SUCCESS) { - efi_printk(sys_table_arg, "Failed to alloc highmem for files\n"); + pr_efi_err(sys_table_arg, "Failed to alloc highmem for files\n"); goto close_handles; } /* We've run out of free low memory. */ if (file_addr > max_addr) { - efi_printk(sys_table_arg, "We've run out of free low memory\n"); + pr_efi_err(sys_table_arg, "We've run out of free low memory\n"); status = EFI_INVALID_PARAMETER; goto free_file_total; } @@ -468,24 +429,24 @@ grow: chunksize = EFI_READ_CHUNK_SIZE; else chunksize = size; - status = efi_call_phys3(files[j].handle->read, - files[j].handle, - &chunksize, - (void *)addr); + + status = efi_file_read(files[j].handle, + &chunksize, + (void *)addr); if (status != EFI_SUCCESS) { - efi_printk(sys_table_arg, "Failed to read file\n"); + pr_efi_err(sys_table_arg, "Failed to read file\n"); goto free_file_total; } addr += chunksize; size -= chunksize; } - efi_call_phys1(files[j].handle->close, files[j].handle); + efi_file_close(files[j].handle); } } - efi_call_phys1(sys_table_arg->boottime->free_pool, files); + efi_call_early(free_pool, files); *load_addr = file_addr; *load_size = file_size_total; @@ -497,9 +458,9 @@ free_file_total: close_handles: for (k = j; k < i; k++) - efi_call_phys1(files[k].handle->close, files[k].handle); + efi_file_close(files[k].handle); free_files: - efi_call_phys1(sys_table_arg->boottime->free_pool, files); + efi_call_early(free_pool, files); fail: *load_addr = 0; *load_size = 0; @@ -545,7 +506,7 @@ static efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg, * as possible while respecting the required alignment. */ nr_pages = round_up(alloc_size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE; - status = efi_call_phys4(sys_table_arg->boottime->allocate_pages, + status = efi_call_early(allocate_pages, EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA, nr_pages, &efi_addr); new_addr = efi_addr; @@ -558,7 +519,7 @@ static efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg, &new_addr); } if (status != EFI_SUCCESS) { - efi_printk(sys_table_arg, "ERROR: Failed to allocate usable memory for kernel.\n"); + pr_efi_err(sys_table_arg, "Failed to allocate usable memory for kernel.\n"); return status; } @@ -575,62 +536,99 @@ static efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg, } /* + * Get the number of UTF-8 bytes corresponding to an UTF-16 character. + * This overestimates for surrogates, but that is okay. + */ +static int efi_utf8_bytes(u16 c) +{ + return 1 + (c >= 0x80) + (c >= 0x800); +} + +/* + * Convert an UTF-16 string, not necessarily null terminated, to UTF-8. + */ +static u8 *efi_utf16_to_utf8(u8 *dst, const u16 *src, int n) +{ + unsigned int c; + + while (n--) { + c = *src++; + if (n && c >= 0xd800 && c <= 0xdbff && + *src >= 0xdc00 && *src <= 0xdfff) { + c = 0x10000 + ((c & 0x3ff) << 10) + (*src & 0x3ff); + src++; + n--; + } + if (c >= 0xd800 && c <= 0xdfff) + c = 0xfffd; /* Unmatched surrogate */ + if (c < 0x80) { + *dst++ = c; + continue; + } + if (c < 0x800) { + *dst++ = 0xc0 + (c >> 6); + goto t1; + } + if (c < 0x10000) { + *dst++ = 0xe0 + (c >> 12); + goto t2; + } + *dst++ = 0xf0 + (c >> 18); + *dst++ = 0x80 + ((c >> 12) & 0x3f); + t2: + *dst++ = 0x80 + ((c >> 6) & 0x3f); + t1: + *dst++ = 0x80 + (c & 0x3f); + } + + return dst; +} + +/* * Convert the unicode UEFI command line to ASCII to pass to kernel. * Size of memory allocated return in *cmd_line_len. * Returns NULL on error. */ -static char *efi_convert_cmdline_to_ascii(efi_system_table_t *sys_table_arg, - efi_loaded_image_t *image, - int *cmd_line_len) +static char *efi_convert_cmdline(efi_system_table_t *sys_table_arg, + efi_loaded_image_t *image, + int *cmd_line_len) { - u16 *s2; + const u16 *s2; u8 *s1 = NULL; unsigned long cmdline_addr = 0; - int load_options_size = image->load_options_size / 2; /* ASCII */ - void *options = image->load_options; - int options_size = 0; + int load_options_chars = image->load_options_size / 2; /* UTF-16 */ + const u16 *options = image->load_options; + int options_bytes = 0; /* UTF-8 bytes */ + int options_chars = 0; /* UTF-16 chars */ efi_status_t status; - int i; u16 zero = 0; if (options) { s2 = options; - while (*s2 && *s2 != '\n' && options_size < load_options_size) { - s2++; - options_size++; + while (*s2 && *s2 != '\n' + && options_chars < load_options_chars) { + options_bytes += efi_utf8_bytes(*s2++); + options_chars++; } } - if (options_size == 0) { + if (!options_chars) { /* No command line options, so return empty string*/ - options_size = 1; options = &zero; } - options_size++; /* NUL termination */ -#ifdef CONFIG_ARM - /* - * For ARM, allocate at a high address to avoid reserved - * regions at low addresses that we don't know the specfics of - * at the time we are processing the command line. - */ - status = efi_high_alloc(sys_table_arg, options_size, 0, - &cmdline_addr, 0xfffff000); -#else - status = efi_low_alloc(sys_table_arg, options_size, 0, - &cmdline_addr); -#endif + options_bytes++; /* NUL termination */ + + status = efi_low_alloc(sys_table_arg, options_bytes, 0, &cmdline_addr); if (status != EFI_SUCCESS) return NULL; s1 = (u8 *)cmdline_addr; - s2 = (u16 *)options; - - for (i = 0; i < options_size - 1; i++) - *s1++ = *s2++; + s2 = (const u16 *)options; + s1 = efi_utf16_to_utf8(s1, s2, options_chars); *s1 = '\0'; - *cmd_line_len = options_size; + *cmd_line_len = options_bytes; return (char *)cmdline_addr; } diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 4753bac65279..dc79346689e6 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -20,6 +20,8 @@ #include <linux/init.h> #include <linux/device.h> #include <linux/efi.h> +#include <linux/of.h> +#include <linux/of_fdt.h> #include <linux/io.h> struct efi __read_mostly efi = { @@ -233,7 +235,7 @@ static __initdata efi_config_table_type_t common_tables[] = { {SAL_SYSTEM_TABLE_GUID, "SALsystab", &efi.sal_systab}, {SMBIOS_TABLE_GUID, "SMBIOS", &efi.smbios}, {UGA_IO_PROTOCOL_GUID, "UGA", &efi.uga}, - {NULL_GUID, NULL, 0}, + {NULL_GUID, NULL, NULL}, }; static __init int match_config_table(efi_guid_t *guid, @@ -313,5 +315,93 @@ int __init efi_config_init(efi_config_table_type_t *arch_tables) } pr_cont("\n"); early_iounmap(config_tables, efi.systab->nr_tables * sz); + + set_bit(EFI_CONFIG_TABLES, &efi.flags); + return 0; } + +#ifdef CONFIG_EFI_PARAMS_FROM_FDT + +#define UEFI_PARAM(name, prop, field) \ + { \ + { name }, \ + { prop }, \ + offsetof(struct efi_fdt_params, field), \ + FIELD_SIZEOF(struct efi_fdt_params, field) \ + } + +static __initdata struct { + const char name[32]; + const char propname[32]; + int offset; + int size; +} dt_params[] = { + UEFI_PARAM("System Table", "linux,uefi-system-table", system_table), + UEFI_PARAM("MemMap Address", "linux,uefi-mmap-start", mmap), + UEFI_PARAM("MemMap Size", "linux,uefi-mmap-size", mmap_size), + UEFI_PARAM("MemMap Desc. Size", "linux,uefi-mmap-desc-size", desc_size), + UEFI_PARAM("MemMap Desc. Version", "linux,uefi-mmap-desc-ver", desc_ver) +}; + +struct param_info { + int verbose; + int found; + void *params; +}; + +static int __init fdt_find_uefi_params(unsigned long node, const char *uname, + int depth, void *data) +{ + struct param_info *info = data; + const void *prop; + void *dest; + u64 val; + int i, len; + + if (depth != 1 || + (strcmp(uname, "chosen") != 0 && strcmp(uname, "chosen@0") != 0)) + return 0; + + for (i = 0; i < ARRAY_SIZE(dt_params); i++) { + prop = of_get_flat_dt_prop(node, dt_params[i].propname, &len); + if (!prop) + return 0; + dest = info->params + dt_params[i].offset; + info->found++; + + val = of_read_number(prop, len / sizeof(u32)); + + if (dt_params[i].size == sizeof(u32)) + *(u32 *)dest = val; + else + *(u64 *)dest = val; + + if (info->verbose) + pr_info(" %s: 0x%0*llx\n", dt_params[i].name, + dt_params[i].size * 2, val); + } + return 1; +} + +int __init efi_get_fdt_params(struct efi_fdt_params *params, int verbose) +{ + struct param_info info; + int ret; + + pr_info("Getting EFI parameters from FDT:\n"); + + info.verbose = verbose; + info.found = 0; + info.params = params; + + ret = of_scan_flat_dt(fdt_find_uefi_params, &info); + if (!info.found) + pr_info("UEFI not found.\n"); + else if (!ret) + pr_err("Can't find '%s' in device tree!\n", + dt_params[info.found].name); + + return ret; +} +#endif /* CONFIG_EFI_PARAMS_FROM_FDT */ diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c index 3dc248239197..463c56545ae8 100644 --- a/drivers/firmware/efi/efivars.c +++ b/drivers/firmware/efi/efivars.c @@ -69,6 +69,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/ucs2_string.h> +#include <linux/compat.h> #define EFIVARS_VERSION "0.08" #define EFIVARS_DATE "2004-May-17" @@ -86,6 +87,15 @@ static struct kset *efivars_kset; static struct bin_attribute *efivars_new_var; static struct bin_attribute *efivars_del_var; +struct compat_efi_variable { + efi_char16_t VariableName[EFI_VAR_NAME_LEN/sizeof(efi_char16_t)]; + efi_guid_t VendorGuid; + __u32 DataSize; + __u8 Data[1024]; + __u32 Status; + __u32 Attributes; +} __packed; + struct efivar_attribute { struct attribute attr; ssize_t (*show) (struct efivar_entry *entry, char *buf); @@ -189,45 +199,107 @@ efivar_data_read(struct efivar_entry *entry, char *buf) memcpy(buf, var->Data, var->DataSize); return var->DataSize; } -/* - * We allow each variable to be edited via rewriting the - * entire efi variable structure. - */ -static ssize_t -efivar_store_raw(struct efivar_entry *entry, const char *buf, size_t count) -{ - struct efi_variable *new_var, *var = &entry->var; - int err; - if (count != sizeof(struct efi_variable)) - return -EINVAL; - - new_var = (struct efi_variable *)buf; +static inline int +sanity_check(struct efi_variable *var, efi_char16_t *name, efi_guid_t vendor, + unsigned long size, u32 attributes, u8 *data) +{ /* * If only updating the variable data, then the name * and guid should remain the same */ - if (memcmp(new_var->VariableName, var->VariableName, sizeof(var->VariableName)) || - efi_guidcmp(new_var->VendorGuid, var->VendorGuid)) { + if (memcmp(name, var->VariableName, sizeof(var->VariableName)) || + efi_guidcmp(vendor, var->VendorGuid)) { printk(KERN_ERR "efivars: Cannot edit the wrong variable!\n"); return -EINVAL; } - if ((new_var->DataSize <= 0) || (new_var->Attributes == 0)){ + if ((size <= 0) || (attributes == 0)){ printk(KERN_ERR "efivars: DataSize & Attributes must be valid!\n"); return -EINVAL; } - if ((new_var->Attributes & ~EFI_VARIABLE_MASK) != 0 || - efivar_validate(new_var, new_var->Data, new_var->DataSize) == false) { + if ((attributes & ~EFI_VARIABLE_MASK) != 0 || + efivar_validate(name, data, size) == false) { printk(KERN_ERR "efivars: Malformed variable content\n"); return -EINVAL; } - memcpy(&entry->var, new_var, count); + return 0; +} + +static inline bool is_compat(void) +{ + if (IS_ENABLED(CONFIG_COMPAT) && is_compat_task()) + return true; + + return false; +} + +static void +copy_out_compat(struct efi_variable *dst, struct compat_efi_variable *src) +{ + memcpy(dst->VariableName, src->VariableName, EFI_VAR_NAME_LEN); + memcpy(dst->Data, src->Data, sizeof(src->Data)); + + dst->VendorGuid = src->VendorGuid; + dst->DataSize = src->DataSize; + dst->Attributes = src->Attributes; +} + +/* + * We allow each variable to be edited via rewriting the + * entire efi variable structure. + */ +static ssize_t +efivar_store_raw(struct efivar_entry *entry, const char *buf, size_t count) +{ + struct efi_variable *new_var, *var = &entry->var; + efi_char16_t *name; + unsigned long size; + efi_guid_t vendor; + u32 attributes; + u8 *data; + int err; + + if (is_compat()) { + struct compat_efi_variable *compat; + + if (count != sizeof(*compat)) + return -EINVAL; + + compat = (struct compat_efi_variable *)buf; + attributes = compat->Attributes; + vendor = compat->VendorGuid; + name = compat->VariableName; + size = compat->DataSize; + data = compat->Data; + + err = sanity_check(var, name, vendor, size, attributes, data); + if (err) + return err; + + copy_out_compat(&entry->var, compat); + } else { + if (count != sizeof(struct efi_variable)) + return -EINVAL; + + new_var = (struct efi_variable *)buf; - err = efivar_entry_set(entry, new_var->Attributes, - new_var->DataSize, new_var->Data, false); + attributes = new_var->Attributes; + vendor = new_var->VendorGuid; + name = new_var->VariableName; + size = new_var->DataSize; + data = new_var->Data; + + err = sanity_check(var, name, vendor, size, attributes, data); + if (err) + return err; + + memcpy(&entry->var, new_var, count); + } + + err = efivar_entry_set(entry, attributes, size, data, NULL); if (err) { printk(KERN_WARNING "efivars: set_variable() failed: status=%d\n", err); return -EIO; @@ -240,6 +312,8 @@ static ssize_t efivar_show_raw(struct efivar_entry *entry, char *buf) { struct efi_variable *var = &entry->var; + struct compat_efi_variable *compat; + size_t size; if (!entry || !buf) return 0; @@ -249,9 +323,23 @@ efivar_show_raw(struct efivar_entry *entry, char *buf) &entry->var.DataSize, entry->var.Data)) return -EIO; - memcpy(buf, var, sizeof(*var)); + if (is_compat()) { + compat = (struct compat_efi_variable *)buf; + + size = sizeof(*compat); + memcpy(compat->VariableName, var->VariableName, + EFI_VAR_NAME_LEN); + memcpy(compat->Data, var->Data, sizeof(compat->Data)); + + compat->VendorGuid = var->VendorGuid; + compat->DataSize = var->DataSize; + compat->Attributes = var->Attributes; + } else { + size = sizeof(*var); + memcpy(buf, var, size); + } - return sizeof(*var); + return size; } /* @@ -326,15 +414,39 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count) { + struct compat_efi_variable *compat = (struct compat_efi_variable *)buf; struct efi_variable *new_var = (struct efi_variable *)buf; struct efivar_entry *new_entry; + bool need_compat = is_compat(); + efi_char16_t *name; + unsigned long size; + u32 attributes; + u8 *data; int err; if (!capable(CAP_SYS_ADMIN)) return -EACCES; - if ((new_var->Attributes & ~EFI_VARIABLE_MASK) != 0 || - efivar_validate(new_var, new_var->Data, new_var->DataSize) == false) { + if (need_compat) { + if (count != sizeof(*compat)) + return -EINVAL; + + attributes = compat->Attributes; + name = compat->VariableName; + size = compat->DataSize; + data = compat->Data; + } else { + if (count != sizeof(*new_var)) + return -EINVAL; + + attributes = new_var->Attributes; + name = new_var->VariableName; + size = new_var->DataSize; + data = new_var->Data; + } + + if ((attributes & ~EFI_VARIABLE_MASK) != 0 || + efivar_validate(name, data, size) == false) { printk(KERN_ERR "efivars: Malformed variable content\n"); return -EINVAL; } @@ -343,10 +455,13 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj, if (!new_entry) return -ENOMEM; - memcpy(&new_entry->var, new_var, sizeof(*new_var)); + if (need_compat) + copy_out_compat(&new_entry->var, compat); + else + memcpy(&new_entry->var, new_var, sizeof(*new_var)); - err = efivar_entry_set(new_entry, new_var->Attributes, new_var->DataSize, - new_var->Data, &efivar_sysfs_list); + err = efivar_entry_set(new_entry, attributes, size, + data, &efivar_sysfs_list); if (err) { if (err == -EEXIST) err = -EINVAL; @@ -369,15 +484,32 @@ static ssize_t efivar_delete(struct file *filp, struct kobject *kobj, char *buf, loff_t pos, size_t count) { struct efi_variable *del_var = (struct efi_variable *)buf; + struct compat_efi_variable *compat; struct efivar_entry *entry; + efi_char16_t *name; + efi_guid_t vendor; int err = 0; if (!capable(CAP_SYS_ADMIN)) return -EACCES; + if (is_compat()) { + if (count != sizeof(*compat)) + return -EINVAL; + + compat = (struct compat_efi_variable *)buf; + name = compat->VariableName; + vendor = compat->VendorGuid; + } else { + if (count != sizeof(*del_var)) + return -EINVAL; + + name = del_var->VariableName; + vendor = del_var->VendorGuid; + } + efivar_entry_iter_begin(); - entry = efivar_entry_find(del_var->VariableName, del_var->VendorGuid, - &efivar_sysfs_list, true); + entry = efivar_entry_find(name, vendor, &efivar_sysfs_list, true); if (!entry) err = -EINVAL; else if (__efivar_entry_delete(entry)) diff --git a/drivers/firmware/efi/fdt.c b/drivers/firmware/efi/fdt.c new file mode 100644 index 000000000000..507a3df46a5d --- /dev/null +++ b/drivers/firmware/efi/fdt.c @@ -0,0 +1,275 @@ +/* + * FDT related Helper functions used by the EFI stub on multiple + * architectures. This should be #included by the EFI stub + * implementation files. + * + * Copyright 2013 Linaro Limited; author Roy Franz + * + * This file is part of the Linux kernel, and is made available + * under the terms of the GNU General Public License version 2. + * + */ + +static efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt, + unsigned long orig_fdt_size, + void *fdt, int new_fdt_size, char *cmdline_ptr, + u64 initrd_addr, u64 initrd_size, + efi_memory_desc_t *memory_map, + unsigned long map_size, unsigned long desc_size, + u32 desc_ver) +{ + int node, prev; + int status; + u32 fdt_val32; + u64 fdt_val64; + + /* Do some checks on provided FDT, if it exists*/ + if (orig_fdt) { + if (fdt_check_header(orig_fdt)) { + pr_efi_err(sys_table, "Device Tree header not valid!\n"); + return EFI_LOAD_ERROR; + } + /* + * We don't get the size of the FDT if we get if from a + * configuration table. + */ + if (orig_fdt_size && fdt_totalsize(orig_fdt) > orig_fdt_size) { + pr_efi_err(sys_table, "Truncated device tree! foo!\n"); + return EFI_LOAD_ERROR; + } + } + + if (orig_fdt) + status = fdt_open_into(orig_fdt, fdt, new_fdt_size); + else + status = fdt_create_empty_tree(fdt, new_fdt_size); + + if (status != 0) + goto fdt_set_fail; + + /* + * Delete any memory nodes present. We must delete nodes which + * early_init_dt_scan_memory may try to use. + */ + prev = 0; + for (;;) { + const char *type; + int len; + + node = fdt_next_node(fdt, prev, NULL); + if (node < 0) + break; + + type = fdt_getprop(fdt, node, "device_type", &len); + if (type && strncmp(type, "memory", len) == 0) { + fdt_del_node(fdt, node); + continue; + } + + prev = node; + } + + node = fdt_subnode_offset(fdt, 0, "chosen"); + if (node < 0) { + node = fdt_add_subnode(fdt, 0, "chosen"); + if (node < 0) { + status = node; /* node is error code when negative */ + goto fdt_set_fail; + } + } + + if ((cmdline_ptr != NULL) && (strlen(cmdline_ptr) > 0)) { + status = fdt_setprop(fdt, node, "bootargs", cmdline_ptr, + strlen(cmdline_ptr) + 1); + if (status) + goto fdt_set_fail; + } + + /* Set initrd address/end in device tree, if present */ + if (initrd_size != 0) { + u64 initrd_image_end; + u64 initrd_image_start = cpu_to_fdt64(initrd_addr); + + status = fdt_setprop(fdt, node, "linux,initrd-start", + &initrd_image_start, sizeof(u64)); + if (status) + goto fdt_set_fail; + initrd_image_end = cpu_to_fdt64(initrd_addr + initrd_size); + status = fdt_setprop(fdt, node, "linux,initrd-end", + &initrd_image_end, sizeof(u64)); + if (status) + goto fdt_set_fail; + } + + /* Add FDT entries for EFI runtime services in chosen node. */ + node = fdt_subnode_offset(fdt, 0, "chosen"); + fdt_val64 = cpu_to_fdt64((u64)(unsigned long)sys_table); + status = fdt_setprop(fdt, node, "linux,uefi-system-table", + &fdt_val64, sizeof(fdt_val64)); + if (status) + goto fdt_set_fail; + + fdt_val64 = cpu_to_fdt64((u64)(unsigned long)memory_map); + status = fdt_setprop(fdt, node, "linux,uefi-mmap-start", + &fdt_val64, sizeof(fdt_val64)); + if (status) + goto fdt_set_fail; + + fdt_val32 = cpu_to_fdt32(map_size); + status = fdt_setprop(fdt, node, "linux,uefi-mmap-size", + &fdt_val32, sizeof(fdt_val32)); + if (status) + goto fdt_set_fail; + + fdt_val32 = cpu_to_fdt32(desc_size); + status = fdt_setprop(fdt, node, "linux,uefi-mmap-desc-size", + &fdt_val32, sizeof(fdt_val32)); + if (status) + goto fdt_set_fail; + + fdt_val32 = cpu_to_fdt32(desc_ver); + status = fdt_setprop(fdt, node, "linux,uefi-mmap-desc-ver", + &fdt_val32, sizeof(fdt_val32)); + if (status) + goto fdt_set_fail; + + /* + * Add kernel version banner so stub/kernel match can be + * verified. + */ + status = fdt_setprop_string(fdt, node, "linux,uefi-stub-kern-ver", + linux_banner); + if (status) + goto fdt_set_fail; + + return EFI_SUCCESS; + +fdt_set_fail: + if (status == -FDT_ERR_NOSPACE) + return EFI_BUFFER_TOO_SMALL; + + return EFI_LOAD_ERROR; +} + +#ifndef EFI_FDT_ALIGN +#define EFI_FDT_ALIGN EFI_PAGE_SIZE +#endif + +/* + * Allocate memory for a new FDT, then add EFI, commandline, and + * initrd related fields to the FDT. This routine increases the + * FDT allocation size until the allocated memory is large + * enough. EFI allocations are in EFI_PAGE_SIZE granules, + * which are fixed at 4K bytes, so in most cases the first + * allocation should succeed. + * EFI boot services are exited at the end of this function. + * There must be no allocations between the get_memory_map() + * call and the exit_boot_services() call, so the exiting of + * boot services is very tightly tied to the creation of the FDT + * with the final memory map in it. + */ + +efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table, + void *handle, + unsigned long *new_fdt_addr, + unsigned long max_addr, + u64 initrd_addr, u64 initrd_size, + char *cmdline_ptr, + unsigned long fdt_addr, + unsigned long fdt_size) +{ + unsigned long map_size, desc_size; + u32 desc_ver; + unsigned long mmap_key; + efi_memory_desc_t *memory_map; + unsigned long new_fdt_size; + efi_status_t status; + + /* + * Estimate size of new FDT, and allocate memory for it. We + * will allocate a bigger buffer if this ends up being too + * small, so a rough guess is OK here. + */ + new_fdt_size = fdt_size + EFI_PAGE_SIZE; + while (1) { + status = efi_high_alloc(sys_table, new_fdt_size, EFI_FDT_ALIGN, + new_fdt_addr, max_addr); + if (status != EFI_SUCCESS) { + pr_efi_err(sys_table, "Unable to allocate memory for new device tree.\n"); + goto fail; + } + + /* + * Now that we have done our final memory allocation (and free) + * we can get the memory map key needed for + * exit_boot_services(). + */ + status = efi_get_memory_map(sys_table, &memory_map, &map_size, + &desc_size, &desc_ver, &mmap_key); + if (status != EFI_SUCCESS) + goto fail_free_new_fdt; + + status = update_fdt(sys_table, + (void *)fdt_addr, fdt_size, + (void *)*new_fdt_addr, new_fdt_size, + cmdline_ptr, initrd_addr, initrd_size, + memory_map, map_size, desc_size, desc_ver); + + /* Succeeding the first time is the expected case. */ + if (status == EFI_SUCCESS) + break; + + if (status == EFI_BUFFER_TOO_SMALL) { + /* + * We need to allocate more space for the new + * device tree, so free existing buffer that is + * too small. Also free memory map, as we will need + * to get new one that reflects the free/alloc we do + * on the device tree buffer. + */ + efi_free(sys_table, new_fdt_size, *new_fdt_addr); + sys_table->boottime->free_pool(memory_map); + new_fdt_size += EFI_PAGE_SIZE; + } else { + pr_efi_err(sys_table, "Unable to constuct new device tree.\n"); + goto fail_free_mmap; + } + } + + /* Now we are ready to exit_boot_services.*/ + status = sys_table->boottime->exit_boot_services(handle, mmap_key); + + + if (status == EFI_SUCCESS) + return status; + + pr_efi_err(sys_table, "Exit boot services failed.\n"); + +fail_free_mmap: + sys_table->boottime->free_pool(memory_map); + +fail_free_new_fdt: + efi_free(sys_table, new_fdt_size, *new_fdt_addr); + +fail: + return EFI_LOAD_ERROR; +} + +static void *get_fdt(efi_system_table_t *sys_table) +{ + efi_guid_t fdt_guid = DEVICE_TREE_GUID; + efi_config_table_t *tables; + void *fdt; + int i; + + tables = (efi_config_table_t *) sys_table->tables; + fdt = NULL; + + for (i = 0; i < sys_table->nr_tables; i++) + if (efi_guidcmp(tables[i].guid, fdt_guid) == 0) { + fdt = (void *) tables[i].table; + break; + } + + return fdt; +} diff --git a/drivers/firmware/efi/runtime-map.c b/drivers/firmware/efi/runtime-map.c index 97cdd16a2169..c98b101a73ae 100644 --- a/drivers/firmware/efi/runtime-map.c +++ b/drivers/firmware/efi/runtime-map.c @@ -170,7 +170,7 @@ int __init efi_runtime_map_init(struct kobject *efi_kobj) return 0; out_add_entry: - for (j = i - 1; j > 0; j--) { + for (j = i - 1; j >= 0; j--) { entry = *(map_entries + j); kobject_put(&entry->kobj); } diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index e6125522860a..5abe943e3404 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -42,7 +42,7 @@ DECLARE_WORK(efivar_work, NULL); EXPORT_SYMBOL_GPL(efivar_work); static bool -validate_device_path(struct efi_variable *var, int match, u8 *buffer, +validate_device_path(efi_char16_t *var_name, int match, u8 *buffer, unsigned long len) { struct efi_generic_dev_path *node; @@ -75,7 +75,7 @@ validate_device_path(struct efi_variable *var, int match, u8 *buffer, } static bool -validate_boot_order(struct efi_variable *var, int match, u8 *buffer, +validate_boot_order(efi_char16_t *var_name, int match, u8 *buffer, unsigned long len) { /* An array of 16-bit integers */ @@ -86,18 +86,18 @@ validate_boot_order(struct efi_variable *var, int match, u8 *buffer, } static bool -validate_load_option(struct efi_variable *var, int match, u8 *buffer, +validate_load_option(efi_char16_t *var_name, int match, u8 *buffer, unsigned long len) { u16 filepathlength; int i, desclength = 0, namelen; - namelen = ucs2_strnlen(var->VariableName, sizeof(var->VariableName)); + namelen = ucs2_strnlen(var_name, EFI_VAR_NAME_LEN); /* Either "Boot" or "Driver" followed by four digits of hex */ for (i = match; i < match+4; i++) { - if (var->VariableName[i] > 127 || - hex_to_bin(var->VariableName[i] & 0xff) < 0) + if (var_name[i] > 127 || + hex_to_bin(var_name[i] & 0xff) < 0) return true; } @@ -132,12 +132,12 @@ validate_load_option(struct efi_variable *var, int match, u8 *buffer, /* * And, finally, check the filepath */ - return validate_device_path(var, match, buffer + desclength + 6, + return validate_device_path(var_name, match, buffer + desclength + 6, filepathlength); } static bool -validate_uint16(struct efi_variable *var, int match, u8 *buffer, +validate_uint16(efi_char16_t *var_name, int match, u8 *buffer, unsigned long len) { /* A single 16-bit integer */ @@ -148,7 +148,7 @@ validate_uint16(struct efi_variable *var, int match, u8 *buffer, } static bool -validate_ascii_string(struct efi_variable *var, int match, u8 *buffer, +validate_ascii_string(efi_char16_t *var_name, int match, u8 *buffer, unsigned long len) { int i; @@ -166,7 +166,7 @@ validate_ascii_string(struct efi_variable *var, int match, u8 *buffer, struct variable_validate { char *name; - bool (*validate)(struct efi_variable *var, int match, u8 *data, + bool (*validate)(efi_char16_t *var_name, int match, u8 *data, unsigned long len); }; @@ -189,10 +189,10 @@ static const struct variable_validate variable_validate[] = { }; bool -efivar_validate(struct efi_variable *var, u8 *data, unsigned long len) +efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len) { int i; - u16 *unicode_name = var->VariableName; + u16 *unicode_name = var_name; for (i = 0; variable_validate[i].validate != NULL; i++) { const char *name = variable_validate[i].name; @@ -208,7 +208,7 @@ efivar_validate(struct efi_variable *var, u8 *data, unsigned long len) /* Wildcard in the matching name means we've matched */ if (c == '*') - return variable_validate[i].validate(var, + return variable_validate[i].validate(var_name, match, data, len); /* Case sensitive match */ @@ -217,7 +217,7 @@ efivar_validate(struct efi_variable *var, u8 *data, unsigned long len) /* Reached the end of the string while matching */ if (!c) - return variable_validate[i].validate(var, + return variable_validate[i].validate(var_name, match, data, len); } } @@ -805,7 +805,7 @@ int efivar_entry_set_get_size(struct efivar_entry *entry, u32 attributes, *set = false; - if (efivar_validate(&entry->var, data, *size) == false) + if (efivar_validate(name, data, *size) == false) return -EINVAL; /* diff --git a/drivers/gator/Kconfig b/drivers/gator/Kconfig index 31f0c6fb8bae..a9503a9a4e9f 100644 --- a/drivers/gator/Kconfig +++ b/drivers/gator/Kconfig @@ -23,8 +23,8 @@ config GATOR_MALI_4XXMP bool "Mali-400MP or Mali-450MP" select GATOR_WITH_MALI_SUPPORT -config GATOR_MALI_T6XX - bool "Mali-T604 or Mali-T658" +config GATOR_MALI_MIDGARD + bool "Mali-T60x, Mali-T62x, Mali-T72x or Mali-T76x" select GATOR_WITH_MALI_SUPPORT endchoice diff --git a/drivers/gator/Makefile b/drivers/gator/Makefile index 2f86823313c6..28d2070b11d5 100644 --- a/drivers/gator/Makefile +++ b/drivers/gator/Makefile @@ -14,17 +14,16 @@ gator-y := gator_main.o \ gator_events_net.o \ gator_events_perf_pmu.o \ gator_events_sched.o \ - gator_events_threads.o \ # Convert the old GATOR_WITH_MALI_SUPPORT to the new kernel flags ifneq ($(GATOR_WITH_MALI_SUPPORT),) CONFIG_GATOR_WITH_MALI_SUPPORT := y - ifeq ($(GATOR_WITH_MALI_SUPPORT),MALI_T6xx) + ifeq ($(GATOR_WITH_MALI_SUPPORT),MALI_MIDGARD) CONFIG_GATOR_MALI_4XXMP := n - CONFIG_GATOR_MALI_T6XX := y + CONFIG_GATOR_MALI_MIDGARD := y else CONFIG_GATOR_MALI_4XXMP := y - CONFIG_GATOR_MALI_T6XX := n + CONFIG_GATOR_MALI_MIDGARD := n endif EXTRA_CFLAGS += -DMALI_SUPPORT=$(GATOR_WITH_MALI_SUPPORT) ifneq ($(GATOR_MALI_INTERFACE_STYLE),) @@ -33,10 +32,10 @@ ifneq ($(GATOR_WITH_MALI_SUPPORT),) endif ifeq ($(CONFIG_GATOR_WITH_MALI_SUPPORT),y) - ifeq ($(CONFIG_GATOR_MALI_T6XX),y) - gator-y += gator_events_mali_t6xx.o \ - gator_events_mali_t6xx_hw.o - include $(src)/mali_t6xx.mk + ifeq ($(CONFIG_GATOR_MALI_MIDGARD),y) + gator-y += gator_events_mali_midgard.o \ + gator_events_mali_midgard_hw.o + include $(src)/mali_midgard.mk else gator-y += gator_events_mali_4xx.o endif @@ -46,7 +45,7 @@ ifeq ($(CONFIG_GATOR_WITH_MALI_SUPPORT),y) ccflags-y += -I$(CONFIG_GATOR_MALI_PATH) endif ccflags-$(CONFIG_GATOR_MALI_4XXMP) += -DMALI_SUPPORT=MALI_4xx - ccflags-$(CONFIG_GATOR_MALI_T6XX) += -DMALI_SUPPORT=MALI_T6xx + ccflags-$(CONFIG_GATOR_MALI_MIDGARD) += -DMALI_SUPPORT=MALI_MIDGARD endif # GATOR_TEST controls whether to include (=1) or exclude (=0) test code. @@ -54,16 +53,15 @@ GATOR_TEST ?= 0 EXTRA_CFLAGS += -DGATOR_TEST=$(GATOR_TEST) # Should the original or new block_rq_complete API be used? -OLD_BLOCK_RQ_COMPLETE := $(shell grep -A3 block_rq_complete include/trace/events/block.h | grep nr_bytes > /dev/null; echo $$?) +OLD_BLOCK_RQ_COMPLETE := $(shell grep -A3 block_rq_complete $(srctree)/include/trace/events/block.h | grep nr_bytes -q; echo $$?) EXTRA_CFLAGS += -DOLD_BLOCK_RQ_COMPLETE=$(OLD_BLOCK_RQ_COMPLETE) gator-$(CONFIG_ARM) += gator_events_armv6.o \ gator_events_armv7.o \ - gator_events_ccn-504.o \ gator_events_l2c-310.o \ gator_events_scorpion.o -gator-$(CONFIG_ARM64) += gator_events_ccn-504.o +gator-$(CONFIG_ARM64) += else diff --git a/drivers/gator/gator.h b/drivers/gator/gator.h index 5ad0254d86a9..5cc73a388c4f 100644 --- a/drivers/gator/gator.h +++ b/drivers/gator/gator.h @@ -14,13 +14,13 @@ #include <linux/mm.h> #include <linux/list.h> -#define GATOR_PERF_SUPPORT LINUX_VERSION_CODE >= KERNEL_VERSION(3, 0, 0) -#define GATOR_PERF_PMU_SUPPORT GATOR_PERF_SUPPORT && defined(CONFIG_PERF_EVENTS) && (!(defined(__arm__) || defined(__aarch64__)) || defined(CONFIG_HW_PERF_EVENTS)) +#define GATOR_PERF_SUPPORT (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 0, 0)) +#define GATOR_PERF_PMU_SUPPORT (GATOR_PERF_SUPPORT && defined(CONFIG_PERF_EVENTS) && (!(defined(__arm__) || defined(__aarch64__)) || defined(CONFIG_HW_PERF_EVENTS))) #define GATOR_NO_PERF_SUPPORT (!(GATOR_PERF_SUPPORT)) -#define GATOR_CPU_FREQ_SUPPORT (LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 38)) && defined(CONFIG_CPU_FREQ) +#define GATOR_CPU_FREQ_SUPPORT ((LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 38)) && defined(CONFIG_CPU_FREQ)) #define GATOR_IKS_SUPPORT defined(CONFIG_BL_SWITCHER) -// cpu ids +/* cpu ids */ #define ARM1136 0xb36 #define ARM1156 0xb56 #define ARM1176 0xb76 @@ -29,7 +29,6 @@ #define CORTEX_A7 0xc07 #define CORTEX_A8 0xc08 #define CORTEX_A9 0xc09 -#define CORTEX_A12 0xc0d #define CORTEX_A15 0xc0f #define CORTEX_A17 0xc0e #define SCORPION 0x00f @@ -42,20 +41,20 @@ #define AARCH64 0xd0f #define OTHER 0xfff -// gpu enums +/* gpu enums */ #define MALI_4xx 1 -#define MALI_T6xx 2 +#define MALI_MIDGARD 2 #define MAXSIZE_CORE_NAME 32 struct gator_cpu { const int cpuid; - // Human readable name + /* Human readable name */ const char core_name[MAXSIZE_CORE_NAME]; - // gatorfs event and Perf PMU name - const char * const pmnc_name; - // compatible from Documentation/devicetree/bindings/arm/cpus.txt - const char * const dt_name; + /* gatorfs event and Perf PMU name */ + const char *const pmnc_name; + /* compatible from Documentation/devicetree/bindings/arm/cpus.txt */ + const char *const dt_name; const int pmnc_counters; }; @@ -98,7 +97,7 @@ int gatorfs_create_ro_ulong(struct super_block *sb, struct dentry *root, extern struct tracepoint *gator_tracepoint_##probe_name; \ static void probe_##probe_name(void *data, PARAMS(proto)) # define GATOR_REGISTER_TRACE(probe_name) \ - tracepoint_probe_register(gator_tracepoint_##probe_name, probe_##probe_name, NULL) + ((gator_tracepoint_##probe_name == NULL) || tracepoint_probe_register(gator_tracepoint_##probe_name, probe_##probe_name, NULL)) # define GATOR_UNREGISTER_TRACE(probe_name) \ tracepoint_probe_unregister(gator_tracepoint_##probe_name, probe_##probe_name, NULL) #endif @@ -107,15 +106,19 @@ int gatorfs_create_ro_ulong(struct super_block *sb, struct dentry *root, * Events ******************************************************************************/ struct gator_interface { - void (*shutdown)(void); // Complementary function to init + /* Complementary function to init */ + void (*shutdown)(void); int (*create_files)(struct super_block *sb, struct dentry *root); int (*start)(void); - void (*stop)(void); // Complementary function to start + /* Complementary function to start */ + void (*stop)(void); int (*online)(int **buffer, bool migrate); int (*offline)(int **buffer, bool migrate); - void (*online_dispatch)(int cpu, bool migrate); // called in process context but may not be running on core 'cpu' - void (*offline_dispatch)(int cpu, bool migrate); // called in process context but may not be running on core 'cpu' - int (*read)(int **buffer); + /* called in process context but may not be running on core 'cpu' */ + void (*online_dispatch)(int cpu, bool migrate); + /* called in process context but may not be running on core 'cpu' */ + void (*offline_dispatch)(int cpu, bool migrate); + int (*read)(int **buffer, bool sched_switch); int (*read64)(long long **buffer); int (*read_proc)(long long **buffer, struct task_struct *); struct list_head list; @@ -146,4 +149,4 @@ int pcpu_to_lcpu(const int pcpu); #define get_logical_cpu() smp_processor_id() #define on_primary_core() (get_logical_cpu() == 0) -#endif // GATOR_H_ +#endif /* GATOR_H_ */ diff --git a/drivers/gator/gator_annotate.c b/drivers/gator/gator_annotate.c index 7e2c6e5d8715..ff9a3cef7b2e 100644 --- a/drivers/gator/gator_annotate.c +++ b/drivers/gator/gator_annotate.c @@ -11,12 +11,12 @@ #include <linux/fs.h> #include <linux/mm.h> #include <linux/sched.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/current.h> #include <linux/spinlock.h> static DEFINE_SPINLOCK(annotate_lock); -static bool collect_annotations = false; +static bool collect_annotations; static int annotate_copy(struct file *file, char const __user *buf, size_t count) { @@ -24,10 +24,10 @@ static int annotate_copy(struct file *file, char const __user *buf, size_t count int write = per_cpu(gator_buffer_write, cpu)[ANNOTATE_BUF]; if (file == NULL) { - // copy from kernel + /* copy from kernel */ memcpy(&per_cpu(gator_buffer, cpu)[ANNOTATE_BUF][write], buf, count); } else { - // copy from user space + /* copy from user space */ if (copy_from_user(&per_cpu(gator_buffer, cpu)[ANNOTATE_BUF][write], buf, count) != 0) return -1; } @@ -41,70 +41,70 @@ static ssize_t annotate_write(struct file *file, char const __user *buf, size_t int pid, cpu, header_size, available, contiguous, length1, length2, size, count = count_orig & 0x7fffffff; bool interrupt_context; - if (*offset) { + if (*offset) return -EINVAL; - } interrupt_context = in_interrupt(); - // Annotations are not supported in interrupt context, but may work if you comment out the the next four lines of code. - // By doing so, annotations in interrupt context can result in deadlocks and lost data. + /* Annotations are not supported in interrupt context, but may work + * if you comment out the the next four lines of code. By doing so, + * annotations in interrupt context can result in deadlocks and lost + * data. + */ if (interrupt_context) { - printk(KERN_WARNING "gator: Annotations are not supported in interrupt context. Edit gator_annotate.c in the gator driver to enable annotations in interrupt context.\n"); + pr_warning("gator: Annotations are not supported in interrupt context. Edit gator_annotate.c in the gator driver to enable annotations in interrupt context.\n"); return -EINVAL; } retry: - // synchronize between cores and with collect_annotations + /* synchronize between cores and with collect_annotations */ spin_lock(&annotate_lock); if (!collect_annotations) { - // Not collecting annotations, tell the caller everything was written + /* Not collecting annotations, tell the caller everything was written */ size = count_orig; goto annotate_write_out; } - // Annotation only uses a single per-cpu buffer as the data must be in order to the engine + /* Annotation only uses a single per-cpu buffer as the data must be in order to the engine */ cpu = 0; - if (current == NULL) { + if (current == NULL) pid = 0; - } else { + else pid = current->pid; - } - // determine total size of the payload + /* determine total size of the payload */ header_size = MAXSIZE_PACK32 * 3 + MAXSIZE_PACK64; available = buffer_bytes_available(cpu, ANNOTATE_BUF) - header_size; size = count < available ? count : available; if (size <= 0) { - // Buffer is full, wait until space is available + /* Buffer is full, wait until space is available */ spin_unlock(&annotate_lock); - // Drop the annotation as blocking is not allowed in interrupt context - if (interrupt_context) { + /* Drop the annotation as blocking is not allowed in interrupt context */ + if (interrupt_context) return -EINVAL; - } wait_event_interruptible(gator_annotate_wait, buffer_bytes_available(cpu, ANNOTATE_BUF) > header_size || !collect_annotations); - // Check to see if a signal is pending - if (signal_pending(current)) { + /* Check to see if a signal is pending */ + if (signal_pending(current)) return -EINTR; - } goto retry; } - // synchronize shared variables annotateBuf and annotatePos + /* synchronize shared variables annotateBuf and annotatePos */ if (per_cpu(gator_buffer, cpu)[ANNOTATE_BUF]) { u64 time = gator_get_time(); + gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, get_physical_cpu()); gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, pid); gator_buffer_write_packed_int64(cpu, ANNOTATE_BUF, time); gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, size); - // determine the sizes to capture, length1 + length2 will equal size + /* determine the sizes to capture, length1 + length2 will equal size */ contiguous = contiguous_space_available(cpu, ANNOTATE_BUF); if (size < contiguous) { length1 = size; @@ -124,14 +124,14 @@ static ssize_t annotate_write(struct file *file, char const __user *buf, size_t goto annotate_write_out; } - // Check and commit; commit is set to occur once buffer is 3/4 full + /* Check and commit; commit is set to occur once buffer is 3/4 full */ buffer_check(cpu, ANNOTATE_BUF, time); } annotate_write_out: spin_unlock(&annotate_lock); - // return the number of bytes written + /* return the number of bytes written */ return size; } @@ -141,18 +141,21 @@ static int annotate_release(struct inode *inode, struct file *file) { int cpu = 0; - // synchronize between cores + /* synchronize between cores */ spin_lock(&annotate_lock); if (per_cpu(gator_buffer, cpu)[ANNOTATE_BUF] && buffer_check_space(cpu, ANNOTATE_BUF, MAXSIZE_PACK64 + 3 * MAXSIZE_PACK32)) { uint32_t pid = current->pid; + gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, get_physical_cpu()); gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, pid); - gator_buffer_write_packed_int64(cpu, ANNOTATE_BUF, 0); // time - gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, 0); // size + /* time */ + gator_buffer_write_packed_int64(cpu, ANNOTATE_BUF, 0); + /* size */ + gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, 0); } - // Check and commit; commit is set to occur once buffer is 3/4 full + /* Check and commit; commit is set to occur once buffer is 3/4 full */ buffer_check(cpu, ANNOTATE_BUF, gator_get_time()); spin_unlock(&annotate_lock); @@ -178,7 +181,7 @@ static int gator_annotate_start(void) static void gator_annotate_stop(void) { - // the spinlock here will ensure that when this function exits, we are not in the middle of an annotation + /* the spinlock here will ensure that when this function exits, we are not in the middle of an annotation */ spin_lock(&annotate_lock); collect_annotations = false; wake_up(&gator_annotate_wait); diff --git a/drivers/gator/gator_annotate_kernel.c b/drivers/gator/gator_annotate_kernel.c index 010806825529..69471f99e5fb 100644 --- a/drivers/gator/gator_annotate_kernel.c +++ b/drivers/gator/gator_annotate_kernel.c @@ -19,10 +19,11 @@ static void kannotate_write(const char *ptr, unsigned int size) int retval; int pos = 0; loff_t offset = 0; + while (pos < size) { retval = annotate_write(NULL, &ptr[pos], size - pos, &offset); if (retval < 0) { - printk(KERN_WARNING "gator: kannotate_write failed with return value %d\n", retval); + pr_warning("gator: kannotate_write failed with return value %d\n", retval); return; } pos += retval; @@ -47,6 +48,7 @@ void gator_annotate_channel(int channel, const char *str) { const u16 str_size = strlen(str) & 0xffff; char header[8]; + header[0] = ESCAPE_CODE; header[1] = STRING_ANNOTATION; marshal_u32(header + 2, channel); @@ -54,20 +56,19 @@ void gator_annotate_channel(int channel, const char *str) kannotate_write(header, sizeof(header)); kannotate_write(str, str_size); } - EXPORT_SYMBOL(gator_annotate_channel); void gator_annotate(const char *str) { gator_annotate_channel(0, str); } - EXPORT_SYMBOL(gator_annotate); void gator_annotate_channel_color(int channel, int color, const char *str) { const u16 str_size = (strlen(str) + 4) & 0xffff; char header[12]; + header[0] = ESCAPE_CODE; header[1] = STRING_ANNOTATION; marshal_u32(header + 2, channel); @@ -76,39 +77,37 @@ void gator_annotate_channel_color(int channel, int color, const char *str) kannotate_write(header, sizeof(header)); kannotate_write(str, str_size - 4); } - EXPORT_SYMBOL(gator_annotate_channel_color); void gator_annotate_color(int color, const char *str) { gator_annotate_channel_color(0, color, str); } - EXPORT_SYMBOL(gator_annotate_color); void gator_annotate_channel_end(int channel) { char header[8]; + header[0] = ESCAPE_CODE; header[1] = STRING_ANNOTATION; marshal_u32(header + 2, channel); marshal_u16(header + 6, 0); kannotate_write(header, sizeof(header)); } - EXPORT_SYMBOL(gator_annotate_channel_end); void gator_annotate_end(void) { gator_annotate_channel_end(0); } - EXPORT_SYMBOL(gator_annotate_end); -void gator_annotate_name_channel(int channel, int group, const char* str) +void gator_annotate_name_channel(int channel, int group, const char *str) { const u16 str_size = strlen(str) & 0xffff; char header[12]; + header[0] = ESCAPE_CODE; header[1] = NAME_CHANNEL_ANNOTATION; marshal_u32(header + 2, channel); @@ -117,13 +116,13 @@ void gator_annotate_name_channel(int channel, int group, const char* str) kannotate_write(header, sizeof(header)); kannotate_write(str, str_size); } - EXPORT_SYMBOL(gator_annotate_name_channel); -void gator_annotate_name_group(int group, const char* str) +void gator_annotate_name_group(int group, const char *str) { const u16 str_size = strlen(str) & 0xffff; char header[8]; + header[0] = ESCAPE_CODE; header[1] = NAME_GROUP_ANNOTATION; marshal_u32(header + 2, group); @@ -131,7 +130,6 @@ void gator_annotate_name_group(int group, const char* str) kannotate_write(header, sizeof(header)); kannotate_write(str, str_size); } - EXPORT_SYMBOL(gator_annotate_name_group); void gator_annotate_visual(const char *data, unsigned int length, const char *str) @@ -139,6 +137,7 @@ void gator_annotate_visual(const char *data, unsigned int length, const char *st const u16 str_size = strlen(str) & 0xffff; char header[4]; char header_length[4]; + header[0] = ESCAPE_CODE; header[1] = VISUAL_ANNOTATION; marshal_u16(header + 2, str_size); @@ -148,49 +147,49 @@ void gator_annotate_visual(const char *data, unsigned int length, const char *st kannotate_write(header_length, sizeof(header_length)); kannotate_write(data, length); } - EXPORT_SYMBOL(gator_annotate_visual); void gator_annotate_marker(void) { char header[4]; + header[0] = ESCAPE_CODE; header[1] = MARKER_ANNOTATION; marshal_u16(header + 2, 0); kannotate_write(header, sizeof(header)); } - EXPORT_SYMBOL(gator_annotate_marker); void gator_annotate_marker_str(const char *str) { const u16 str_size = strlen(str) & 0xffff; char header[4]; + header[0] = ESCAPE_CODE; header[1] = MARKER_ANNOTATION; marshal_u16(header + 2, str_size); kannotate_write(header, sizeof(header)); kannotate_write(str, str_size); } - EXPORT_SYMBOL(gator_annotate_marker_str); void gator_annotate_marker_color(int color) { char header[8]; + header[0] = ESCAPE_CODE; header[1] = MARKER_ANNOTATION; marshal_u16(header + 2, 4); marshal_u32(header + 4, color); kannotate_write(header, sizeof(header)); } - EXPORT_SYMBOL(gator_annotate_marker_color); void gator_annotate_marker_color_str(int color, const char *str) { const u16 str_size = (strlen(str) + 4) & 0xffff; char header[8]; + header[0] = ESCAPE_CODE; header[1] = MARKER_ANNOTATION; marshal_u16(header + 2, str_size); @@ -198,5 +197,4 @@ void gator_annotate_marker_color_str(int color, const char *str) kannotate_write(header, sizeof(header)); kannotate_write(str, str_size - 4); } - EXPORT_SYMBOL(gator_annotate_marker_color_str); diff --git a/drivers/gator/gator_backtrace.c b/drivers/gator/gator_backtrace.c index e03c1653c5b5..76c941d009a9 100644 --- a/drivers/gator/gator_backtrace.c +++ b/drivers/gator/gator_backtrace.c @@ -14,17 +14,17 @@ struct stack_frame_eabi { union { struct { unsigned long fp; - // May be the fp in the case of a leaf function or clang + /* May be the fp in the case of a leaf function or clang */ unsigned long lr; - // If lr is really the fp, lr2 is the corresponding lr + /* If lr is really the fp, lr2 is the corresponding lr */ unsigned long lr2; }; - // Used to read 32 bit fp/lr from a 64 bit kernel + /* Used to read 32 bit fp/lr from a 64 bit kernel */ struct { u32 fp_32; - // same as lr above + /* same as lr above */ u32 lr_32; - // same as lr2 above + /* same as lr2 above */ u32 lr2_32; }; }; @@ -35,9 +35,8 @@ static void gator_add_trace(int cpu, unsigned long address) off_t offset = 0; unsigned long cookie = get_address_cookie(cpu, current, address & ~1, &offset); - if (cookie == NO_COOKIE || cookie == UNRESOLVED_COOKIE) { + if (cookie == NO_COOKIE || cookie == UNRESOLVED_COOKIE) offset = address; - } marshal_backtrace(offset & ~1, cookie, 0); } @@ -54,36 +53,34 @@ static void arm_backtrace_eabi(int cpu, struct pt_regs *const regs, unsigned int unsigned long lr = regs->ARM_lr; const int gcc_frame_offset = sizeof(unsigned long); #else - // Is userspace aarch32 (32 bit) + /* Is userspace aarch32 (32 bit) */ const bool is_compat = compat_user_mode(regs); unsigned long fp = (is_compat ? regs->regs[11] : regs->regs[29]); unsigned long sp = (is_compat ? regs->compat_sp : regs->sp); unsigned long lr = (is_compat ? regs->compat_lr : regs->regs[30]); const int gcc_frame_offset = (is_compat ? sizeof(u32) : 0); #endif - // clang frame offset is always zero + /* clang frame offset is always zero */ int is_user_mode = user_mode(regs); - // pc (current function) has already been added + /* pc (current function) has already been added */ - if (!is_user_mode) { + if (!is_user_mode) return; - } - // Add the lr (parent function) - // entry preamble may not have executed + /* Add the lr (parent function), entry preamble may not have + * executed + */ gator_add_trace(cpu, lr); - // check fp is valid - if (fp == 0 || fp < sp) { + /* check fp is valid */ + if (fp == 0 || fp < sp) return; - } - // Get the current stack frame + /* Get the current stack frame */ curr = (struct stack_frame_eabi *)(fp - gcc_frame_offset); - if ((unsigned long)curr & 3) { + if ((unsigned long)curr & 3) return; - } while (depth-- && curr) { if (!access_ok(VERIFY_READ, curr, sizeof(struct stack_frame_eabi)) || @@ -95,13 +92,15 @@ static void arm_backtrace_eabi(int cpu, struct pt_regs *const regs, unsigned int lr = (is_compat ? bufcurr.lr_32 : bufcurr.lr); #define calc_next(reg) ((reg) - gcc_frame_offset) - // Returns true if reg is a valid fp + /* Returns true if reg is a valid fp */ #define validate_next(reg, curr) \ ((reg) != 0 && (calc_next(reg) & 3) == 0 && (unsigned long)(curr) < calc_next(reg)) - // Try lr from the stack as the fp because gcc leaf functions do not push lr - // If gcc_frame_offset is non-zero, the lr will also be the clang fp - // This assumes code is at a lower address than the stack + /* Try lr from the stack as the fp because gcc leaf functions do + * not push lr. If gcc_frame_offset is non-zero, the lr will also + * be the clang fp. This assumes code is at a lower address than + * the stack + */ if (validate_next(lr, curr)) { fp = lr; lr = (is_compat ? bufcurr.lr2_32 : bufcurr.lr2); @@ -109,11 +108,10 @@ static void arm_backtrace_eabi(int cpu, struct pt_regs *const regs, unsigned int gator_add_trace(cpu, lr); - if (!validate_next(fp, curr)) { + if (!validate_next(fp, curr)) return; - } - // Move to the next stack frame + /* Move to the next stack frame */ curr = (struct stack_frame_eabi *)calc_next(fp); } #endif @@ -129,6 +127,7 @@ static int report_trace(struct stackframe *frame, void *d) #if defined(MODULE) unsigned int cpu = get_physical_cpu(); struct module *mod = __module_address(addr); + if (mod) { cookie = get_cookie(cpu, current, mod->name, false); addr = addr - (unsigned long)mod->module_core; @@ -142,13 +141,13 @@ static int report_trace(struct stackframe *frame, void *d) } #endif -// Uncomment the following line to enable kernel stack unwinding within gator, note it can also be defined from the Makefile -// #define GATOR_KERNEL_STACK_UNWINDING +/* Uncomment the following line to enable kernel stack unwinding within gator, note it can also be defined from the Makefile */ +/* #define GATOR_KERNEL_STACK_UNWINDING */ #if (defined(__arm__) || defined(__aarch64__)) && !defined(GATOR_KERNEL_STACK_UNWINDING) -// Disabled by default +/* Disabled by default */ MODULE_PARM_DESC(kernel_stack_unwinding, "Allow kernel stack unwinding."); -static bool kernel_stack_unwinding = 0; +static bool kernel_stack_unwinding; module_param(kernel_stack_unwinding, bool, 0644); #endif @@ -161,6 +160,7 @@ static void kernel_backtrace(int cpu, struct pt_regs *const regs) int depth = (kernel_stack_unwinding ? gator_backtrace_depth : 1); #endif struct stackframe frame; + if (depth == 0) depth = 1; #if defined(__arm__) @@ -196,10 +196,10 @@ static void gator_add_sample(int cpu, struct pt_regs *const regs, u64 time) if (in_kernel) { kernel_backtrace(cpu, regs); } else { - // Cookie+PC + /* Cookie+PC */ gator_add_trace(cpu, PC_REG); - // Backtrace + /* Backtrace */ if (gator_backtrace_depth) arm_backtrace_eabi(cpu, regs, gator_backtrace_depth); } diff --git a/drivers/gator/gator_buffer.c b/drivers/gator/gator_buffer.c index dfbc97d80221..910d5aa15066 100644 --- a/drivers/gator/gator_buffer.c +++ b/drivers/gator/gator_buffer.c @@ -10,55 +10,65 @@ static void marshal_frame(int cpu, int buftype) { int frame; + bool write_cpu; - if (!per_cpu(gator_buffer, cpu)[buftype]) { + if (!per_cpu(gator_buffer, cpu)[buftype]) return; - } switch (buftype) { case SUMMARY_BUF: + write_cpu = false; frame = FRAME_SUMMARY; break; case BACKTRACE_BUF: + write_cpu = true; frame = FRAME_BACKTRACE; break; case NAME_BUF: + write_cpu = true; frame = FRAME_NAME; break; case COUNTER_BUF: + write_cpu = false; frame = FRAME_COUNTER; break; case BLOCK_COUNTER_BUF: + write_cpu = true; frame = FRAME_BLOCK_COUNTER; break; case ANNOTATE_BUF: + write_cpu = false; frame = FRAME_ANNOTATE; break; case SCHED_TRACE_BUF: + write_cpu = true; frame = FRAME_SCHED_TRACE; break; case IDLE_BUF: + write_cpu = false; frame = FRAME_IDLE; break; case ACTIVITY_BUF: + write_cpu = false; frame = FRAME_ACTIVITY; break; default: + write_cpu = false; frame = -1; break; } - // add response type - if (gator_response_type > 0) { + /* add response type */ + if (gator_response_type > 0) gator_buffer_write_packed_int(cpu, buftype, gator_response_type); - } - // leave space for 4-byte unpacked length + /* leave space for 4-byte unpacked length */ per_cpu(gator_buffer_write, cpu)[buftype] = (per_cpu(gator_buffer_write, cpu)[buftype] + sizeof(s32)) & gator_buffer_mask[buftype]; - // add frame type and core number + /* add frame type and core number */ gator_buffer_write_packed_int(cpu, buftype, frame); - gator_buffer_write_packed_int(cpu, buftype, cpu); + if (write_cpu) + gator_buffer_write_packed_int(cpu, buftype, cpu); } static int buffer_bytes_available(int cpu, int buftype) @@ -66,19 +76,17 @@ static int buffer_bytes_available(int cpu, int buftype) int remaining, filled; filled = per_cpu(gator_buffer_write, cpu)[buftype] - per_cpu(gator_buffer_read, cpu)[buftype]; - if (filled < 0) { + if (filled < 0) filled += gator_buffer_size[buftype]; - } remaining = gator_buffer_size[buftype] - filled; - if (per_cpu(buffer_space_available, cpu)[buftype]) { - // Give some extra room; also allows space to insert the overflow error packet + if (per_cpu(buffer_space_available, cpu)[buftype]) + /* Give some extra room; also allows space to insert the overflow error packet */ remaining -= 200; - } else { - // Hysteresis, prevents multiple overflow messages + else + /* Hysteresis, prevents multiple overflow messages */ remaining -= 2000; - } return remaining; } @@ -87,11 +95,10 @@ static bool buffer_check_space(int cpu, int buftype, int bytes) { int remaining = buffer_bytes_available(cpu, buftype); - if (remaining < bytes) { + if (remaining < bytes) per_cpu(buffer_space_available, cpu)[buftype] = false; - } else { + else per_cpu(buffer_space_available, cpu)[buftype] = true; - } return per_cpu(buffer_space_available, cpu)[buftype]; } @@ -100,10 +107,10 @@ static int contiguous_space_available(int cpu, int buftype) { int remaining = buffer_bytes_available(cpu, buftype); int contiguous = gator_buffer_size[buftype] - per_cpu(gator_buffer_write, cpu)[buftype]; + if (remaining < contiguous) return remaining; - else - return contiguous; + return contiguous; } static void gator_commit_buffer(int cpu, int buftype, u64 time) @@ -114,41 +121,38 @@ static void gator_commit_buffer(int cpu, int buftype, u64 time) if (!per_cpu(gator_buffer, cpu)[buftype]) return; - // post-populate the length, which does not include the response type length nor the length itself, i.e. only the length of the payload + /* post-populate the length, which does not include the response type length nor the length itself, i.e. only the length of the payload */ local_irq_save(flags); type_length = gator_response_type ? 1 : 0; commit = per_cpu(gator_buffer_commit, cpu)[buftype]; length = per_cpu(gator_buffer_write, cpu)[buftype] - commit; - if (length < 0) { + if (length < 0) length += gator_buffer_size[buftype]; - } length = length - type_length - sizeof(s32); if (length <= FRAME_HEADER_SIZE) { - // Nothing to write, only the frame header is present + /* Nothing to write, only the frame header is present */ local_irq_restore(flags); return; } - for (byte = 0; byte < sizeof(s32); byte++) { + for (byte = 0; byte < sizeof(s32); byte++) per_cpu(gator_buffer, cpu)[buftype][(commit + type_length + byte) & gator_buffer_mask[buftype]] = (length >> byte * 8) & 0xFF; - } per_cpu(gator_buffer_commit, cpu)[buftype] = per_cpu(gator_buffer_write, cpu)[buftype]; if (gator_live_rate > 0) { - while (time > per_cpu(gator_buffer_commit_time, cpu)) { + while (time > per_cpu(gator_buffer_commit_time, cpu)) per_cpu(gator_buffer_commit_time, cpu) += gator_live_rate; - } } marshal_frame(cpu, buftype); local_irq_restore(flags); - // had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater + /* had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater */ if (per_cpu(in_scheduler_context, cpu)) { #ifndef CONFIG_PREEMPT_RT_FULL - // mod_timer can not be used in interrupt context in RT-Preempt full + /* mod_timer can not be used in interrupt context in RT-Preempt full */ mod_timer(&gator_buffer_wake_up_timer, jiffies + 1); #endif } else { @@ -159,10 +163,9 @@ static void gator_commit_buffer(int cpu, int buftype, u64 time) static void buffer_check(int cpu, int buftype, u64 time) { int filled = per_cpu(gator_buffer_write, cpu)[buftype] - per_cpu(gator_buffer_commit, cpu)[buftype]; - if (filled < 0) { + + if (filled < 0) filled += gator_buffer_size[buftype]; - } - if (filled >= ((gator_buffer_size[buftype] * 3) / 4)) { + if (filled >= ((gator_buffer_size[buftype] * 3) / 4)) gator_commit_buffer(cpu, buftype, time); - } } diff --git a/drivers/gator/gator_buffer_write.c b/drivers/gator/gator_buffer_write.c index b621ba93ee5e..654ec606cfad 100644 --- a/drivers/gator/gator_buffer_write.c +++ b/drivers/gator/gator_buffer_write.c @@ -14,16 +14,17 @@ static void gator_buffer_write_packed_int(int cpu, int buftype, int x) char *buffer = per_cpu(gator_buffer, cpu)[buftype]; int packedBytes = 0; int more = true; + while (more) { - // low order 7 bits of x + /* low order 7 bits of x */ char b = x & 0x7f; + x >>= 7; - if ((x == 0 && (b & 0x40) == 0) || (x == -1 && (b & 0x40) != 0)) { + if ((x == 0 && (b & 0x40) == 0) || (x == -1 && (b & 0x40) != 0)) more = false; - } else { + else b |= 0x80; - } buffer[(write + packedBytes) & mask] = b; packedBytes++; @@ -39,16 +40,17 @@ static void gator_buffer_write_packed_int64(int cpu, int buftype, long long x) char *buffer = per_cpu(gator_buffer, cpu)[buftype]; int packedBytes = 0; int more = true; + while (more) { - // low order 7 bits of x + /* low order 7 bits of x */ char b = x & 0x7f; + x >>= 7; - if ((x == 0 && (b & 0x40) == 0) || (x == -1 && (b & 0x40) != 0)) { + if ((x == 0 && (b & 0x40) == 0) || (x == -1 && (b & 0x40) != 0)) more = false; - } else { + else b |= 0x80; - } buffer[(write + packedBytes) & mask] = b; packedBytes++; @@ -75,6 +77,7 @@ static void gator_buffer_write_bytes(int cpu, int buftype, const char *x, int le static void gator_buffer_write_string(int cpu, int buftype, const char *x) { int len = strlen(x); + gator_buffer_write_packed_int(cpu, buftype, len); gator_buffer_write_bytes(cpu, buftype, x, len); } diff --git a/drivers/gator/gator_cookies.c b/drivers/gator/gator_cookies.c index 5c7d842070e0..c43cce815226 100644 --- a/drivers/gator/gator_cookies.c +++ b/drivers/gator/gator_cookies.c @@ -7,8 +7,10 @@ * */ -#define COOKIEMAP_ENTRIES 1024 /* must be power of 2 */ -#define TRANSLATE_BUFFER_SIZE 512 // must be a power of 2 - 512/4 = 128 entries +/* must be power of 2 */ +#define COOKIEMAP_ENTRIES 1024 +/* must be a power of 2 - 512/4 = 128 entries */ +#define TRANSLATE_BUFFER_SIZE 512 #define TRANSLATE_TEXT_SIZE 256 #define MAX_COLLISIONS 2 @@ -38,6 +40,7 @@ static uint32_t cookiemap_code(uint64_t value64) { uint32_t value = (uint32_t)((value64 >> 32) + value64); uint32_t cookiecode = (value >> 24) & 0xff; + cookiecode = cookiecode * 31 + ((value >> 16) & 0xff); cookiecode = cookiecode * 31 + ((value >> 8) & 0xff); cookiecode = cookiecode * 31 + ((value >> 0) & 0xff); @@ -52,9 +55,8 @@ static uint32_t gator_chksum_crc32(const char *data) int i, length = strlen(data); crc = 0xFFFFFFFF; - for (i = 0; i < length; i++) { + for (i = 0; i < length; i++) crc = ((crc >> 8) & 0x00FFFFFF) ^ gator_crc32_table[(crc ^ *block++) & 0xFF]; - } return (crc ^ 0xFFFFFFFF); } @@ -72,11 +74,12 @@ static uint32_t cookiemap_exists(uint64_t key) uint64_t *keys = &(per_cpu(cookie_keys, cpu)[cookiecode]); uint32_t *values = &(per_cpu(cookie_values, cpu)[cookiecode]); - // Can be called from interrupt handler or from work queue + /* Can be called from interrupt handler or from work queue */ local_irq_save(flags); for (x = 0; x < MAX_COLLISIONS; x++) { if (keys[x] == key) { uint32_t value = values[x]; + for (; x > 0; x--) { keys[x] = keys[x - 1]; values[x] = values[x - 1]; @@ -126,7 +129,7 @@ static void translate_buffer_write_args(int cpu, struct task_struct *task, const write = per_cpu(translate_buffer_write, cpu); next_write = (write + 1) & translate_buffer_mask; - // At least one entry must always remain available as when read == write, the queue is empty not full + /* At least one entry must always remain available as when read == write, the queue is empty not full */ if (next_write != per_cpu(translate_buffer_read, cpu)) { args = &per_cpu(translate_buffer, cpu)[write]; args->task = task; @@ -178,11 +181,11 @@ static void wq_cookie_handler(struct work_struct *unused) static void app_process_wake_up_handler(unsigned long unused_data) { - // had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater + /* had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater */ schedule_work(&cookie_work); } -// Retrieve full name from proc/pid/cmdline for java processes on Android +/* Retrieve full name from proc/pid/cmdline for java processes on Android */ static int translate_app_process(const char **text, int cpu, struct task_struct *task, bool from_wq) { void *maddr; @@ -195,12 +198,16 @@ static int translate_app_process(const char **text, int cpu, struct task_struct char *buf = per_cpu(translate_text, cpu); #ifndef CONFIG_PREEMPT_RT_FULL - // Push work into a work queue if in atomic context as the kernel functions below might sleep - // Rely on the in_interrupt variable rather than in_irq() or in_interrupt() kernel functions, as the value of these functions seems - // inconsistent during a context switch between android/linux versions + /* Push work into a work queue if in atomic context as the kernel + * functions below might sleep. Rely on the in_interrupt variable + * rather than in_irq() or in_interrupt() kernel functions, as the + * value of these functions seems inconsistent during a context + * switch between android/linux versions + */ if (!from_wq) { - // Check if already in buffer + /* Check if already in buffer */ int pos = per_cpu(translate_buffer_read, cpu); + while (pos != per_cpu(translate_buffer_write, cpu)) { if (per_cpu(translate_buffer, cpu)[pos].task == task) goto out; @@ -209,7 +216,7 @@ static int translate_app_process(const char **text, int cpu, struct task_struct translate_buffer_write_args(cpu, task, *text); - // Not safe to call in RT-Preempt full in schedule switch context + /* Not safe to call in RT-Preempt full in schedule switch context */ mod_timer(&app_process_wake_up_timer, jiffies + 1); goto out; } @@ -239,7 +246,8 @@ static int translate_app_process(const char **text, int cpu, struct task_struct copy_from_user_page(page_vma, page, addr, buf, maddr + offset, bytes); - kunmap(page); // release page allocated by get_user_pages() + /* release page allocated by get_user_pages() */ + kunmap(page); page_cache_release(page); len -= bytes; @@ -250,7 +258,7 @@ static int translate_app_process(const char **text, int cpu, struct task_struct retval = 1; } - // On app_process startup, /proc/pid/cmdline is initially "zygote" then "<pre-initialized>" but changes after an initial startup period + /* On app_process startup, /proc/pid/cmdline is initially "zygote" then "<pre-initialized>" but changes after an initial startup period */ if (strcmp(*text, "zygote") == 0 || strcmp(*text, "<pre-initialized>") == 0) retval = 0; @@ -262,6 +270,8 @@ out: return retval; } +static const char APP_PROCESS[] = "app_process"; + static uint32_t get_cookie(int cpu, struct task_struct *task, const char *text, bool from_wq) { unsigned long flags, cookie; @@ -271,16 +281,16 @@ static uint32_t get_cookie(int cpu, struct task_struct *task, const char *text, key = (key << 32) | (uint32_t)task->tgid; cookie = cookiemap_exists(key); - if (cookie) { + if (cookie) return cookie; - } - if (strcmp(text, "app_process") == 0) { + /* On 64-bit android app_process can be app_process32 or app_process64 */ + if (strncmp(text, APP_PROCESS, sizeof(APP_PROCESS) - 1) == 0) { if (!translate_app_process(&text, cpu, task, from_wq)) return UNRESOLVED_COOKIE; } - // Can be called from interrupt handler or from work queue or from scheduler trace + /* Can be called from interrupt handler or from work queue or from scheduler trace */ local_irq_save(flags); cookie = UNRESOLVED_COOKIE; @@ -300,7 +310,7 @@ static int get_exec_cookie(int cpu, struct task_struct *task) struct mm_struct *mm = task->mm; const char *text; - // kernel threads have no address space + /* kernel threads have no address space */ if (!mm) return NO_COOKIE; @@ -355,7 +365,7 @@ static int cookies_initialize(void) per_cpu(cookie_next_key, cpu) = nr_cpu_ids + cpu; size = COOKIEMAP_ENTRIES * MAX_COLLISIONS * sizeof(uint64_t); - per_cpu(cookie_keys, cpu) = (uint64_t *)kmalloc(size, GFP_KERNEL); + per_cpu(cookie_keys, cpu) = kmalloc(size, GFP_KERNEL); if (!per_cpu(cookie_keys, cpu)) { err = -ENOMEM; goto cookie_setup_error; @@ -363,14 +373,14 @@ static int cookies_initialize(void) memset(per_cpu(cookie_keys, cpu), 0, size); size = COOKIEMAP_ENTRIES * MAX_COLLISIONS * sizeof(uint32_t); - per_cpu(cookie_values, cpu) = (uint32_t *)kmalloc(size, GFP_KERNEL); + per_cpu(cookie_values, cpu) = kmalloc(size, GFP_KERNEL); if (!per_cpu(cookie_values, cpu)) { err = -ENOMEM; goto cookie_setup_error; } memset(per_cpu(cookie_values, cpu), 0, size); - per_cpu(translate_buffer, cpu) = (struct cookie_args *)kmalloc(TRANSLATE_BUFFER_SIZE, GFP_KERNEL); + per_cpu(translate_buffer, cpu) = kmalloc(TRANSLATE_BUFFER_SIZE, GFP_KERNEL); if (!per_cpu(translate_buffer, cpu)) { err = -ENOMEM; goto cookie_setup_error; @@ -379,16 +389,16 @@ static int cookies_initialize(void) per_cpu(translate_buffer_write, cpu) = 0; per_cpu(translate_buffer_read, cpu) = 0; - per_cpu(translate_text, cpu) = (char *)kmalloc(TRANSLATE_TEXT_SIZE, GFP_KERNEL); + per_cpu(translate_text, cpu) = kmalloc(TRANSLATE_TEXT_SIZE, GFP_KERNEL); if (!per_cpu(translate_text, cpu)) { err = -ENOMEM; goto cookie_setup_error; } } - // build CRC32 table + /* build CRC32 table */ poly = 0x04c11db7; - gator_crc32_table = (uint32_t *)kmalloc(256 * sizeof(uint32_t), GFP_KERNEL); + gator_crc32_table = kmalloc(256 * sizeof(*gator_crc32_table), GFP_KERNEL); if (!gator_crc32_table) { err = -ENOMEM; goto cookie_setup_error; @@ -396,11 +406,10 @@ static int cookies_initialize(void) for (i = 0; i < 256; i++) { crc = i; for (j = 8; j > 0; j--) { - if (crc & 1) { + if (crc & 1) crc = (crc >> 1) ^ poly; - } else { + else crc >>= 1; - } } gator_crc32_table[i] = crc; } diff --git a/drivers/gator/gator_events_armv6.c b/drivers/gator/gator_events_armv6.c index 353645622306..a157a0013302 100644 --- a/drivers/gator/gator_events_armv6.c +++ b/drivers/gator/gator_events_armv6.c @@ -8,7 +8,7 @@ #include "gator.h" -// gator_events_perf_pmu.c is used if perf is supported +/* gator_events_perf_pmu.c is used if perf is supported */ #if GATOR_NO_PERF_SUPPORT static const char *pmnc_name; @@ -28,7 +28,7 @@ static const char *pmnc_name; #define CCNT 2 #define CNTMAX (CCNT+1) -static int pmnc_counters = 0; +static int pmnc_counters; static unsigned long pmnc_enabled[CNTMAX]; static unsigned long pmnc_event[CNTMAX]; static unsigned long pmnc_key[CNTMAX]; @@ -45,6 +45,7 @@ static inline void armv6_pmnc_write(u32 val) static inline u32 armv6_pmnc_read(void) { u32 val; + asm volatile("mrc p15, 0, %0, c15, c12, 0" : "=r" (val)); return val; } @@ -52,6 +53,7 @@ static inline u32 armv6_pmnc_read(void) static void armv6_pmnc_reset_counter(unsigned int cnt) { u32 val = 0; + switch (cnt) { case CCNT: asm volatile("mcr p15, 0, %0, c15, c12, 1" : : "r" (val)); @@ -74,20 +76,18 @@ int gator_events_armv6_create_files(struct super_block *sb, struct dentry *root) for (i = PMN0; i <= CCNT; i++) { char buf[40]; - if (i == CCNT) { - snprintf(buf, sizeof buf, "ARM_%s_ccnt", pmnc_name); - } else { - snprintf(buf, sizeof buf, "ARM_%s_cnt%d", pmnc_name, i); - } + + if (i == CCNT) + snprintf(buf, sizeof(buf), "ARM_%s_ccnt", pmnc_name); + else + snprintf(buf, sizeof(buf), "ARM_%s_cnt%d", pmnc_name, i); dir = gatorfs_mkdir(sb, root, buf); - if (!dir) { + if (!dir) return -1; - } gatorfs_create_ulong(sb, dir, "enabled", &pmnc_enabled[i]); gatorfs_create_ro_ulong(sb, dir, "key", &pmnc_key[i]); - if (i != CCNT) { + if (i != CCNT) gatorfs_create_ulong(sb, dir, "event", &pmnc_event[i]); - } } return 0; @@ -98,9 +98,8 @@ static int gator_events_armv6_online(int **buffer, bool migrate) unsigned int cnt, len = 0, cpu = smp_processor_id(); u32 pmnc; - if (armv6_pmnc_read() & PMCR_E) { + if (armv6_pmnc_read() & PMCR_E) armv6_pmnc_write(armv6_pmnc_read() & ~PMCR_E); - } /* initialize PMNC, reset overflow, D bit, C bit and P bit. */ armv6_pmnc_write(PMCR_OFL_PMN0 | PMCR_OFL_PMN1 | PMCR_OFL_CCNT | @@ -115,19 +114,18 @@ static int gator_events_armv6_online(int **buffer, bool migrate) event = pmnc_event[cnt] & 255; - // Set event (if destined for PMNx counters) - if (cnt == PMN0) { + /* Set event (if destined for PMNx counters) */ + if (cnt == PMN0) pmnc |= event << 20; - } else if (cnt == PMN1) { + else if (cnt == PMN1) pmnc |= event << 12; - } - // Reset counter + /* Reset counter */ armv6_pmnc_reset_counter(cnt); } armv6_pmnc_write(pmnc | PMCR_E); - // return zero values, no need to read as the counters were just reset + /* return zero values, no need to read as the counters were just reset */ for (cnt = PMN0; cnt <= CCNT; cnt++) { if (pmnc_enabled[cnt]) { per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt]; @@ -146,9 +144,8 @@ static int gator_events_armv6_offline(int **buffer, bool migrate) unsigned int cnt; armv6_pmnc_write(armv6_pmnc_read() & ~PMCR_E); - for (cnt = PMN0; cnt <= CCNT; cnt++) { + for (cnt = PMN0; cnt <= CCNT; cnt++) armv6_pmnc_reset_counter(cnt); - } return 0; } @@ -163,19 +160,19 @@ static void gator_events_armv6_stop(void) } } -static int gator_events_armv6_read(int **buffer) +static int gator_events_armv6_read(int **buffer, bool sched_switch) { int cnt, len = 0; int cpu = smp_processor_id(); - // a context switch may occur before the online hotplug event, thus need to check that the pmu is enabled - if (!(armv6_pmnc_read() & PMCR_E)) { + /* a context switch may occur before the online hotplug event, thus need to check that the pmu is enabled */ + if (!(armv6_pmnc_read() & PMCR_E)) return 0; - } for (cnt = PMN0; cnt <= CCNT; cnt++) { if (pmnc_enabled[cnt]) { u32 value = 0; + switch (cnt) { case CCNT: asm volatile("mrc p15, 0, %0, c15, c12, 1" : "=r" (value)); diff --git a/drivers/gator/gator_events_armv7.c b/drivers/gator/gator_events_armv7.c index bd8a9ba24e99..09c94220114c 100644 --- a/drivers/gator/gator_events_armv7.c +++ b/drivers/gator/gator_events_armv7.c @@ -15,16 +15,16 @@ #include "gator.h" -// gator_events_perf_pmu.c is used if perf is supported +/* gator_events_perf_pmu.c is used if perf is supported */ #if GATOR_NO_PERF_SUPPORT -// Per-CPU PMNC: config reg +/* Per-CPU PMNC: config reg */ #define PMNC_E (1 << 0) /* Enable all counters */ #define PMNC_P (1 << 1) /* Reset all counters */ #define PMNC_C (1 << 2) /* Cycle counter reset */ #define PMNC_MASK 0x3f /* Mask for writable bits */ -// ccnt reg +/* ccnt reg */ #define CCNT_REG (1 << 31) #define CCNT 0 @@ -49,6 +49,7 @@ inline void armv7_pmnc_write(u32 val) inline u32 armv7_pmnc_read(void) { u32 val; + asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (val)); return val; } @@ -61,10 +62,10 @@ inline u32 armv7_ccnt_read(u32 reset_value) u32 val; local_irq_save(flags); - asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (den)); // disable - asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val)); // read - asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (newval)); // new value - asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (den)); // enable + asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (den)); /* disable */ + asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val)); /* read */ + asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (newval)); /* new value */ + asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (den)); /* enable */ local_irq_restore(flags); return val; @@ -79,11 +80,11 @@ inline u32 armv7_cntn_read(unsigned int cnt, u32 reset_value) u32 oldval; local_irq_save(flags); - asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (den)); // disable - asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (sel)); // select - asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (oldval)); // read - asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" (newval)); // new value - asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (den)); // enable + asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (den)); /* disable */ + asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (sel)); /* select */ + asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (oldval)); /* read */ + asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" (newval)); /* new value */ + asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (den)); /* enable */ local_irq_restore(flags); return oldval; @@ -92,13 +93,15 @@ inline u32 armv7_cntn_read(unsigned int cnt, u32 reset_value) static inline void armv7_pmnc_disable_interrupt(unsigned int cnt) { u32 val = cnt ? (1 << (cnt - CNT0)) : (1 << 31); + asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (val)); } inline u32 armv7_pmnc_reset_interrupt(void) { - // Get and reset overflow status flags + /* Get and reset overflow status flags */ u32 flags; + asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (flags)); flags &= 0x8000003f; asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (flags)); @@ -108,6 +111,7 @@ inline u32 armv7_pmnc_reset_interrupt(void) static inline u32 armv7_pmnc_enable_counter(unsigned int cnt) { u32 val = cnt ? (1 << (cnt - CNT0)) : CCNT_REG; + asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (val)); return cnt; } @@ -115,6 +119,7 @@ static inline u32 armv7_pmnc_enable_counter(unsigned int cnt) static inline u32 armv7_pmnc_disable_counter(unsigned int cnt) { u32 val = cnt ? (1 << (cnt - CNT0)) : CCNT_REG; + asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (val)); return cnt; } @@ -122,15 +127,15 @@ static inline u32 armv7_pmnc_disable_counter(unsigned int cnt) static inline int armv7_pmnc_select_counter(unsigned int cnt) { u32 val = (cnt - CNT0); + asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (val)); return cnt; } static inline void armv7_pmnc_write_evtsel(unsigned int cnt, u32 val) { - if (armv7_pmnc_select_counter(cnt) == cnt) { + if (armv7_pmnc_select_counter(cnt) == cnt) asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val)); - } } static int gator_events_armv7_create_files(struct super_block *sb, struct dentry *root) @@ -140,20 +145,18 @@ static int gator_events_armv7_create_files(struct super_block *sb, struct dentry for (i = 0; i < pmnc_counters; i++) { char buf[40]; - if (i == 0) { - snprintf(buf, sizeof buf, "%s_ccnt", pmnc_name); - } else { - snprintf(buf, sizeof buf, "%s_cnt%d", pmnc_name, i - 1); - } + + if (i == 0) + snprintf(buf, sizeof(buf), "%s_ccnt", pmnc_name); + else + snprintf(buf, sizeof(buf), "%s_cnt%d", pmnc_name, i - 1); dir = gatorfs_mkdir(sb, root, buf); - if (!dir) { + if (!dir) return -1; - } gatorfs_create_ulong(sb, dir, "enabled", &pmnc_enabled[i]); gatorfs_create_ro_ulong(sb, dir, "key", &pmnc_key[i]); - if (i > 0) { + if (i > 0) gatorfs_create_ulong(sb, dir, "event", &pmnc_event[i]); - } } return 0; @@ -163,14 +166,13 @@ static int gator_events_armv7_online(int **buffer, bool migrate) { unsigned int cnt, len = 0, cpu = smp_processor_id(); - if (armv7_pmnc_read() & PMNC_E) { + if (armv7_pmnc_read() & PMNC_E) armv7_pmnc_write(armv7_pmnc_read() & ~PMNC_E); - } - // Initialize & Reset PMNC: C bit and P bit + /* Initialize & Reset PMNC: C bit and P bit */ armv7_pmnc_write(PMNC_P | PMNC_C); - // Reset overflow flags + /* Reset overflow flags */ armv7_pmnc_reset_interrupt(); for (cnt = CCNT; cnt < CNTMAX; cnt++) { @@ -179,28 +181,28 @@ static int gator_events_armv7_online(int **buffer, bool migrate) if (!pmnc_enabled[cnt]) continue; - // Disable counter + /* Disable counter */ armv7_pmnc_disable_counter(cnt); event = pmnc_event[cnt] & 255; - // Set event (if destined for PMNx counters), we don't need to set the event if it's a cycle count + /* Set event (if destined for PMNx counters), we don't need to set the event if it's a cycle count */ if (cnt != CCNT) armv7_pmnc_write_evtsel(cnt, event); armv7_pmnc_disable_interrupt(cnt); - // Reset counter + /* Reset counter */ cnt ? armv7_cntn_read(cnt, 0) : armv7_ccnt_read(0); - // Enable counter + /* Enable counter */ armv7_pmnc_enable_counter(cnt); } - // enable + /* enable */ armv7_pmnc_write(armv7_pmnc_read() | PMNC_E); - // return zero values, no need to read as the counters were just reset + /* return zero values, no need to read as the counters were just reset */ for (cnt = 0; cnt < pmnc_counters; cnt++) { if (pmnc_enabled[cnt]) { per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt]; @@ -216,7 +218,7 @@ static int gator_events_armv7_online(int **buffer, bool migrate) static int gator_events_armv7_offline(int **buffer, bool migrate) { - // disable all counters, including PMCCNTR; overflow IRQs will not be signaled + /* disable all counters, including PMCCNTR; overflow IRQs will not be signaled */ armv7_pmnc_write(armv7_pmnc_read() & ~PMNC_E); return 0; @@ -232,24 +234,23 @@ static void gator_events_armv7_stop(void) } } -static int gator_events_armv7_read(int **buffer) +static int gator_events_armv7_read(int **buffer, bool sched_switch) { int cnt, len = 0; int cpu = smp_processor_id(); - // a context switch may occur before the online hotplug event, thus need to check that the pmu is enabled - if (!(armv7_pmnc_read() & PMNC_E)) { + /* a context switch may occur before the online hotplug event, thus need to check that the pmu is enabled */ + if (!(armv7_pmnc_read() & PMNC_E)) return 0; - } for (cnt = 0; cnt < pmnc_counters; cnt++) { if (pmnc_enabled[cnt]) { int value; - if (cnt == CCNT) { + + if (cnt == CCNT) value = armv7_ccnt_read(0); - } else { + else value = armv7_cntn_read(cnt, 0); - } per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt]; per_cpu(perfCnt, cpu)[len++] = value; } @@ -290,17 +291,16 @@ int gator_events_armv7_init(void) pmnc_name = "ARMv7_Cortex_A9"; pmnc_counters = 6; break; - // ARM Cortex A12 is not supported by version of Linux before 3.0 case CORTEX_A15: pmnc_name = "ARMv7_Cortex_A15"; pmnc_counters = 6; break; - // ARM Cortex A17 is not supported by version of Linux before 3.0 + /* ARM Cortex A17 is not supported by version of Linux before 3.0 */ default: return -1; } - pmnc_counters++; // CNT[n] + CCNT + pmnc_counters++; /* CNT[n] + CCNT */ for (cnt = CCNT; cnt < CNTMAX; cnt++) { pmnc_enabled[cnt] = 0; diff --git a/drivers/gator/gator_events_block.c b/drivers/gator/gator_events_block.c index 03eed4fb9ebb..a352a54afa02 100644 --- a/drivers/gator/gator_events_block.c +++ b/drivers/gator/gator_events_block.c @@ -28,7 +28,7 @@ static ulong block_rq_rd_key; static atomic_t blockCnt[BLOCK_TOTAL]; static int blockGet[BLOCK_TOTAL * 4]; -// Tracepoint changed in 3.15 backported to older kernels. The Makefile tries to autodetect the correct value, but if it fails change the #if below +/* Tracepoint changed in 3.15 backported to older kernels. The Makefile tries to autodetect the correct value, but if it fails change the #if below */ #if OLD_BLOCK_RQ_COMPLETE GATOR_DEFINE_PROBE(block_rq_complete, TP_PROTO(struct request_queue *q, struct request *rq)) #else @@ -52,13 +52,11 @@ GATOR_DEFINE_PROBE(block_rq_complete, TP_PROTO(struct request_queue *q, struct r return; if (write) { - if (block_rq_wr_enabled) { + if (block_rq_wr_enabled) atomic_add(size, &blockCnt[BLOCK_RQ_WR]); - } } else { - if (block_rq_rd_enabled) { + if (block_rq_rd_enabled) atomic_add(size, &blockCnt[BLOCK_RQ_RD]); - } } } @@ -68,17 +66,15 @@ static int gator_events_block_create_files(struct super_block *sb, struct dentry /* block_complete_wr */ dir = gatorfs_mkdir(sb, root, "Linux_block_rq_wr"); - if (!dir) { + if (!dir) return -1; - } gatorfs_create_ulong(sb, dir, "enabled", &block_rq_wr_enabled); gatorfs_create_ro_ulong(sb, dir, "key", &block_rq_wr_key); /* block_complete_rd */ dir = gatorfs_mkdir(sb, root, "Linux_block_rq_rd"); - if (!dir) { + if (!dir) return -1; - } gatorfs_create_ulong(sb, dir, "enabled", &block_rq_rd_enabled); gatorfs_create_ro_ulong(sb, dir, "key", &block_rq_rd_key); @@ -87,7 +83,7 @@ static int gator_events_block_create_files(struct super_block *sb, struct dentry static int gator_events_block_start(void) { - // register tracepoints + /* register tracepoints */ if (block_rq_wr_enabled || block_rq_rd_enabled) if (GATOR_REGISTER_TRACE(block_rq_complete)) goto fail_block_rq_exit; @@ -95,7 +91,7 @@ static int gator_events_block_start(void) return 0; - // unregister tracepoints on error + /* unregister tracepoints on error */ fail_block_rq_exit: pr_err("gator: block event tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n"); @@ -112,19 +108,19 @@ static void gator_events_block_stop(void) block_rq_rd_enabled = 0; } -static int gator_events_block_read(int **buffer) +static int gator_events_block_read(int **buffer, bool sched_switch) { int len, value, data = 0; - if (!on_primary_core()) { + if (!on_primary_core()) return 0; - } len = 0; if (block_rq_wr_enabled && (value = atomic_read(&blockCnt[BLOCK_RQ_WR])) > 0) { atomic_sub(value, &blockCnt[BLOCK_RQ_WR]); blockGet[len++] = block_rq_wr_key; - blockGet[len++] = 0; // indicates to Streamline that value bytes were written now, not since the last message + /* Indicates to Streamline that value bytes were written now, not since the last message */ + blockGet[len++] = 0; blockGet[len++] = block_rq_wr_key; blockGet[len++] = value; data += value; @@ -132,7 +128,8 @@ static int gator_events_block_read(int **buffer) if (block_rq_rd_enabled && (value = atomic_read(&blockCnt[BLOCK_RQ_RD])) > 0) { atomic_sub(value, &blockCnt[BLOCK_RQ_RD]); blockGet[len++] = block_rq_rd_key; - blockGet[len++] = 0; // indicates to Streamline that value bytes were read now, not since the last message + /* Indicates to Streamline that value bytes were read now, not since the last message */ + blockGet[len++] = 0; blockGet[len++] = block_rq_rd_key; blockGet[len++] = value; data += value; diff --git a/drivers/gator/gator_events_ccn-504.c b/drivers/gator/gator_events_ccn-504.c deleted file mode 100644 index 024ffc2856aa..000000000000 --- a/drivers/gator/gator_events_ccn-504.c +++ /dev/null @@ -1,346 +0,0 @@ -/** - * Copyright (C) ARM Limited 2013-2014. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/io.h> -#include <linux/module.h> - -#include "gator.h" - -#define NUM_REGIONS 256 -#define REGION_SIZE (64*1024) -#define REGION_DEBUG 1 -#define REGION_XP 64 -#define NUM_XPS 11 - -// DT (Debug) region -#define PMEVCNTSR0 0x0150 -#define PMCCNTRSR 0x0190 -#define PMCR 0x01A8 -#define PMSR 0x01B0 -#define PMSR_REQ 0x01B8 -#define PMSR_CLR 0x01C0 - -// XP region -#define DT_CONFIG 0x0300 -#define DT_CONTROL 0x0370 - -// Multiple -#define PMU_EVENT_SEL 0x0600 -#define OLY_ID 0xFF00 - -#define CCNT 4 -#define CNTMAX (CCNT + 1) - -#define get_pmu_event_id(event) (((event) >> 0) & 0xFF) -#define get_node_type(event) (((event) >> 8) & 0xFF) -#define get_region(event) (((event) >> 16) & 0xFF) - -#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36) - -// From kernel/params.c -#define STANDARD_PARAM_DEF(name, type, format, tmptype, strtolfn) \ - int param_set_##name(const char *val, struct kernel_param *kp) \ - { \ - tmptype l; \ - int ret; \ - \ - if (!val) return -EINVAL; \ - ret = strtolfn(val, 0, &l); \ - if (ret == -EINVAL || ((type)l != l)) \ - return -EINVAL; \ - *((type *)kp->arg) = l; \ - return 0; \ - } \ - int param_get_##name(char *buffer, struct kernel_param *kp) \ - { \ - return sprintf(buffer, format, *((type *)kp->arg)); \ - } - -#else - -// From kernel/params.c -#define STANDARD_PARAM_DEF(name, type, format, tmptype, strtolfn) \ - int param_set_##name(const char *val, const struct kernel_param *kp) \ - { \ - tmptype l; \ - int ret; \ - \ - ret = strtolfn(val, 0, &l); \ - if (ret < 0 || ((type)l != l)) \ - return ret < 0 ? ret : -EINVAL; \ - *((type *)kp->arg) = l; \ - return 0; \ - } \ - int param_get_##name(char *buffer, const struct kernel_param *kp) \ - { \ - return scnprintf(buffer, PAGE_SIZE, format, \ - *((type *)kp->arg)); \ - } \ - struct kernel_param_ops param_ops_##name = { \ - .set = param_set_##name, \ - .get = param_get_##name, \ - }; \ - EXPORT_SYMBOL(param_set_##name); \ - EXPORT_SYMBOL(param_get_##name); \ - EXPORT_SYMBOL(param_ops_##name) - -#endif - -STANDARD_PARAM_DEF(u64, u64, "%llu", u64, strict_strtoull); - -// From include/linux/moduleparam.h -#define param_check_u64(name, p) __param_check(name, p, u64) - -MODULE_PARM_DESC(ccn504_addr, "CCN-504 physical base address"); -static u64 ccn504_addr = 0; -module_param(ccn504_addr, u64, 0444); - -static void __iomem *gator_events_ccn504_base; -static bool gator_events_ccn504_global_enabled; -static unsigned long gator_events_ccn504_enabled[CNTMAX]; -static unsigned long gator_events_ccn504_event[CNTMAX]; -static unsigned long gator_events_ccn504_key[CNTMAX]; -static int gator_events_ccn504_buffer[2*CNTMAX]; -static int gator_events_ccn504_prev[CNTMAX]; - -static void gator_events_ccn504_create_shutdown(void) -{ - if (gator_events_ccn504_base != NULL) { - iounmap(gator_events_ccn504_base); - } -} - -static int gator_events_ccn504_create_files(struct super_block *sb, struct dentry *root) -{ - struct dentry *dir; - int i; - char buf[32]; - - for (i = 0; i < CNTMAX; ++i) { - if (i == CCNT) { - snprintf(buf, sizeof(buf), "CCN-504_ccnt"); - } else { - snprintf(buf, sizeof(buf), "CCN-504_cnt%i", i); - } - dir = gatorfs_mkdir(sb, root, buf); - if (!dir) { - return -1; - } - - gatorfs_create_ulong(sb, dir, "enabled", &gator_events_ccn504_enabled[i]); - if (i != CCNT) { - gatorfs_create_ulong(sb, dir, "event", &gator_events_ccn504_event[i]); - } - gatorfs_create_ro_ulong(sb, dir, "key", &gator_events_ccn504_key[i]); - } - - return 0; -} - -static void gator_events_ccn504_set_dt_config(int xp_node_id, int event_num, int value) -{ - u32 dt_config; - - dt_config = readl(gator_events_ccn504_base + (REGION_XP + xp_node_id)*REGION_SIZE + DT_CONFIG); - dt_config |= (value + event_num) << (4*event_num); - writel(dt_config, gator_events_ccn504_base + (REGION_XP + xp_node_id)*REGION_SIZE + DT_CONFIG); -} - -static int gator_events_ccn504_start(void) -{ - int i; - - gator_events_ccn504_global_enabled = 0; - for (i = 0; i < CNTMAX; ++i) { - if (gator_events_ccn504_enabled[i]) { - gator_events_ccn504_global_enabled = 1; - break; - } - } - - if (!gator_events_ccn504_global_enabled) { - return 0; - } - - memset(&gator_events_ccn504_prev, 0x80, sizeof(gator_events_ccn504_prev)); - - // Disable INTREQ on overflow - // [6] ovfl_intr_en = 0 - // perhaps set to 1? - // [5] cntr_rst = 0 - // No register paring - // [4:1] cntcfg = 0 - // Enable PMU features - // [0] pmu_en = 1 - writel(0x1, gator_events_ccn504_base + REGION_DEBUG*REGION_SIZE + PMCR); - - // Configure the XPs - for (i = 0; i < NUM_XPS; ++i) { - int dt_control; - - // Pass on all events - writel(0, gator_events_ccn504_base + (REGION_XP + i)*REGION_SIZE + DT_CONFIG); - - // Enable PMU capability - // [0] dt_enable = 1 - dt_control = readl(gator_events_ccn504_base + (REGION_XP + i)*REGION_SIZE + DT_CONTROL); - dt_control |= 0x1; - writel(dt_control, gator_events_ccn504_base + (REGION_XP + i)*REGION_SIZE + DT_CONTROL); - } - - // Assume no other pmu_event_sel registers are set - - // cycle counter does not need to be enabled - for (i = 0; i < CCNT; ++i) { - int pmu_event_id; - int node_type; - int region; - u32 pmu_event_sel; - u32 oly_id_whole; - u32 oly_id; - u32 node_id; - - if (!gator_events_ccn504_enabled[i]) { - continue; - } - - pmu_event_id = get_pmu_event_id(gator_events_ccn504_event[i]); - node_type = get_node_type(gator_events_ccn504_event[i]); - region = get_region(gator_events_ccn504_event[i]); - - // Verify the node_type - oly_id_whole = readl(gator_events_ccn504_base + region*REGION_SIZE + OLY_ID); - oly_id = oly_id_whole & 0x1F; - node_id = (oly_id_whole >> 8) & 0x7F; - if ((oly_id != node_type) || - ((node_type == 0x16) && ((oly_id != 0x14) && (oly_id != 0x15) && (oly_id != 0x16) && (oly_id != 0x18) && (oly_id != 0x19) && (oly_id != 0x1A)))) { - printk(KERN_ERR "gator: oly_id is 0x%x expected 0x%x\n", oly_id, node_type); - return -1; - } - - // Set the control register - pmu_event_sel = readl(gator_events_ccn504_base + region*REGION_SIZE + PMU_EVENT_SEL); - switch (node_type) { - case 0x08: // XP - pmu_event_sel |= pmu_event_id << (7*i); - gator_events_ccn504_set_dt_config(node_id, i, 0x4); - break; - case 0x04: // HN-F - case 0x16: // RN-I - case 0x10: // SBAS - pmu_event_sel |= pmu_event_id << (4*i); - gator_events_ccn504_set_dt_config(node_id/2, i, (node_id & 1) == 0 ? 0x8 : 0xC); - break; - } - writel(pmu_event_sel, gator_events_ccn504_base + region*REGION_SIZE + PMU_EVENT_SEL); - } - - return 0; -} - -static void gator_events_ccn504_stop(void) -{ - int i; - - if (!gator_events_ccn504_global_enabled) { - return; - } - - // cycle counter does not need to be disabled - for (i = 0; i < CCNT; ++i) { - int region; - - if (!gator_events_ccn504_enabled[i]) { - continue; - } - - region = get_region(gator_events_ccn504_event[i]); - - writel(0, gator_events_ccn504_base + region*REGION_SIZE + PMU_EVENT_SEL); - } - - // Clear dt_config - for (i = 0; i < NUM_XPS; ++i) { - writel(0, gator_events_ccn504_base + (REGION_XP + i)*REGION_SIZE + DT_CONFIG); - } -} - -static int gator_events_ccn504_read(int **buffer) -{ - int i; - int len = 0; - int value; - - if (!on_primary_core() || !gator_events_ccn504_global_enabled) { - return 0; - } - - // Verify the pmsr register is zero - while (readl(gator_events_ccn504_base + REGION_DEBUG*REGION_SIZE + PMSR) != 0); - - // Request a PMU snapshot - writel(1, gator_events_ccn504_base + REGION_DEBUG*REGION_SIZE + PMSR_REQ); - - // Wait for the snapshot - while (readl(gator_events_ccn504_base + REGION_DEBUG*REGION_SIZE + PMSR) == 0); - - // Read the shadow registers - for (i = 0; i < CNTMAX; ++i) { - if (!gator_events_ccn504_enabled[i]) { - continue; - } - - value = readl(gator_events_ccn504_base + REGION_DEBUG*REGION_SIZE + (i == CCNT ? PMCCNTRSR : PMEVCNTSR0 + 8*i)); - if (gator_events_ccn504_prev[i] != 0x80808080) { - gator_events_ccn504_buffer[len++] = gator_events_ccn504_key[i]; - gator_events_ccn504_buffer[len++] = value - gator_events_ccn504_prev[i]; - } - gator_events_ccn504_prev[i] = value; - - // Are the counters registers cleared when read? Is that what the cntr_rst bit on the pmcr register does? - } - - // Clear the PMU snapshot status - writel(1, gator_events_ccn504_base + REGION_DEBUG*REGION_SIZE + PMSR_CLR); - - if (buffer) - *buffer = gator_events_ccn504_buffer; - - return len; -} - -static struct gator_interface gator_events_ccn504_interface = { - .shutdown = gator_events_ccn504_create_shutdown, - .create_files = gator_events_ccn504_create_files, - .start = gator_events_ccn504_start, - .stop = gator_events_ccn504_stop, - .read = gator_events_ccn504_read, -}; - -int gator_events_ccn504_init(void) -{ - int i; - - if (ccn504_addr == 0) { - return -1; - } - - gator_events_ccn504_base = ioremap(ccn504_addr, NUM_REGIONS*REGION_SIZE); - if (gator_events_ccn504_base == NULL) { - printk(KERN_ERR "gator: ioremap returned NULL\n"); - return -1; - } - - for (i = 0; i < CNTMAX; ++i) { - gator_events_ccn504_enabled[i] = 0; - gator_events_ccn504_event[i] = 0; - gator_events_ccn504_key[i] = gator_events_get_key(); - } - - return gator_events_install(&gator_events_ccn504_interface); -} diff --git a/drivers/gator/gator_events_irq.c b/drivers/gator/gator_events_irq.c index facbdd62325e..5221aac581b3 100644 --- a/drivers/gator/gator_events_irq.c +++ b/drivers/gator/gator_events_irq.c @@ -42,17 +42,15 @@ static int gator_events_irq_create_files(struct super_block *sb, struct dentry * /* irq */ dir = gatorfs_mkdir(sb, root, "Linux_irq_irq"); - if (!dir) { + if (!dir) return -1; - } gatorfs_create_ulong(sb, dir, "enabled", &hardirq_enabled); gatorfs_create_ro_ulong(sb, dir, "key", &hardirq_key); /* soft irq */ dir = gatorfs_mkdir(sb, root, "Linux_irq_softirq"); - if (!dir) { + if (!dir) return -1; - } gatorfs_create_ulong(sb, dir, "enabled", &softirq_enabled); gatorfs_create_ro_ulong(sb, dir, "key", &softirq_key); @@ -63,7 +61,7 @@ static int gator_events_irq_online(int **buffer, bool migrate) { int len = 0, cpu = get_physical_cpu(); - // synchronization with the irq_exit functions is not necessary as the values are being reset + /* synchronization with the irq_exit functions is not necessary as the values are being reset */ if (hardirq_enabled) { atomic_set(&per_cpu(irqCnt, cpu)[HARDIRQ], 0); per_cpu(irqGet, cpu)[len++] = hardirq_key; @@ -84,7 +82,7 @@ static int gator_events_irq_online(int **buffer, bool migrate) static int gator_events_irq_start(void) { - // register tracepoints + /* register tracepoints */ if (hardirq_enabled) if (GATOR_REGISTER_TRACE(irq_handler_exit)) goto fail_hardirq_exit; @@ -95,7 +93,7 @@ static int gator_events_irq_start(void) return 0; - // unregister tracepoints on error + /* unregister tracepoints on error */ fail_softirq_exit: if (hardirq_enabled) GATOR_UNREGISTER_TRACE(irq_handler_exit); @@ -117,7 +115,7 @@ static void gator_events_irq_stop(void) softirq_enabled = 0; } -static int gator_events_irq_read(int **buffer) +static int gator_events_irq_read(int **buffer, bool sched_switch) { int len, value; int cpu = get_physical_cpu(); diff --git a/drivers/gator/gator_events_l2c-310.c b/drivers/gator/gator_events_l2c-310.c index 553f9707bdbf..73aaac32327e 100644 --- a/drivers/gator/gator_events_l2c-310.c +++ b/drivers/gator/gator_events_l2c-310.c @@ -91,7 +91,7 @@ static void gator_events_l2c310_stop(void) writel(0, l2c310_base + L2X0_EVENT_CNT_CTRL); } -static int gator_events_l2c310_read(int **buffer) +static int gator_events_l2c310_read(int **buffer, bool sched_switch) { static const unsigned long l2x0_event_cntx_val[L2C310_COUNTERS_NUM] = { L2X0_EVENT_CNT0_VAL, @@ -149,8 +149,8 @@ static void __iomem *gator_events_l2c310_probe(void) 0xa0412000, #endif #if defined(CONFIG_ARCH_VEXPRESS) - 0x1e00a000, // A9x4 core tile (HBI-0191) - 0x2c0f0000, // New memory map tiles + 0x1e00a000, /* A9x4 core tile (HBI-0191) */ + 0x2c0f0000, /* New memory map tiles */ #endif }; int i; diff --git a/drivers/gator/gator_events_mali_4xx.c b/drivers/gator/gator_events_mali_4xx.c index 9e1c7064bd73..9cf43fe2c29b 100644 --- a/drivers/gator/gator_events_mali_4xx.c +++ b/drivers/gator/gator_events_mali_4xx.c @@ -36,7 +36,7 @@ #elif GATOR_MALI_INTERFACE_STYLE == 2 #error GATOR_MALI_INTERFACE_STYLE 2 is obsolete #elif GATOR_MALI_INTERFACE_STYLE >= 3 -// Valid GATOR_MALI_INTERFACE_STYLE +/* Valid GATOR_MALI_INTERFACE_STYLE */ #else #error Unknown GATOR_MALI_INTERFACE_STYLE option. #endif @@ -54,7 +54,7 @@ #error MALI_SUPPORT set to an invalid device code: expecting MALI_4xx #endif -static const char mali_name[] = "Mali-4xx"; +static const char mali_name[] = "4xx"; /* gatorfs variables for counter enable state, * the event the counter should count and the @@ -73,8 +73,8 @@ static u32 *counter_address[NUMBER_OF_EVENTS]; /* An array used to return the data we recorded * as key,value pairs hence the *2 */ -static unsigned long counter_dump[NUMBER_OF_EVENTS * 2]; -static unsigned long counter_prev[NUMBER_OF_EVENTS]; +static int counter_dump[NUMBER_OF_EVENTS * 2]; +static int counter_prev[NUMBER_OF_EVENTS]; static bool prev_set[NUMBER_OF_EVENTS]; /* Note whether tracepoints have been registered */ @@ -89,8 +89,8 @@ static unsigned int n_vp_cores = MAX_NUM_VP_CORES; static unsigned int n_l2_cores = MAX_NUM_L2_CACHE_CORES; static unsigned int n_fp_cores = MAX_NUM_FP_CORES; -extern mali_counter mali_activity[2]; -static const char* const mali_activity_names[] = { +extern struct mali_counter mali_activity[2]; +static const char *const mali_activity_names[] = { "fragment", "vertex", }; @@ -112,36 +112,11 @@ static inline int is_hw_counter(unsigned int event_id) return (event_id >= FIRST_HW_COUNTER && event_id <= LAST_HW_COUNTER); } -/* - * These are provided for utgard compatibility. - */ -typedef void _mali_profiling_get_mali_version_type(struct _mali_profiling_mali_version *values); -typedef u32 _mali_profiling_get_l2_counters_type(_mali_profiling_l2_counter_values *values); - -/* Probe for continuously sampled counter */ -#if 0 //WE_DONT_CURRENTLY_USE_THIS_SO_SUPPRESS_WARNING -GATOR_DEFINE_PROBE(mali_sample_address, TP_PROTO(unsigned int event_id, u32 *addr)) -{ - /* Turning on too many pr_debug statements in frequently called functions - * can cause stability and/or performance problems - */ - //pr_debug("gator: mali_sample_address %d %d\n", event_id, addr); - if (event_id >= ACTIVITY_VP && event_id <= COUNTER_FP3_C1) { - counter_address[event_id] = addr; - } -} -#endif - /* Probe for hardware counter events */ GATOR_DEFINE_PROBE(mali_hw_counter, TP_PROTO(unsigned int event_id, unsigned int value)) { - /* Turning on too many pr_debug statements in frequently called functions - * can cause stability and/or performance problems - */ - //pr_debug("gator: mali_hw_counter %d %d\n", event_id, value); - if (is_hw_counter(event_id)) { + if (is_hw_counter(event_id)) counter_data[event_id] = value; - } } GATOR_DEFINE_PROBE(mali_sw_counters, TP_PROTO(pid_t pid, pid_t tid, void *surface_id, unsigned int *counters)) @@ -150,9 +125,8 @@ GATOR_DEFINE_PROBE(mali_sw_counters, TP_PROTO(pid_t pid, pid_t tid, void *surfac /* Copy over the values for those counters which are enabled. */ for (i = FIRST_SW_COUNTER; i <= LAST_SW_COUNTER; i++) { - if (counter_enabled[i]) { + if (counter_enabled[i]) counter_data[i] = (u32)(counters[i - FIRST_SW_COUNTER]); - } } } @@ -172,13 +146,11 @@ static int create_fs_entry(struct super_block *sb, struct dentry *root, const ch dir = gatorfs_mkdir(sb, root, name); - if (!dir) { + if (!dir) return -1; - } - if (create_event_item) { + if (create_event_item) gatorfs_create_ulong(sb, dir, "event", &counter_event[event]); - } gatorfs_create_ulong(sb, dir, "enabled", &counter_enabled[event]); gatorfs_create_ro_ulong(sb, dir, "key", &counter_key[event]); @@ -192,7 +164,7 @@ static int create_fs_entry(struct super_block *sb, struct dentry *root, const ch */ static void initialise_version_info(void) { - _mali_profiling_get_mali_version_type *mali_profiling_get_mali_version_symbol; + void (*mali_profiling_get_mali_version_symbol)(struct _mali_profiling_mali_version *values); mali_profiling_get_mali_version_symbol = symbol_get(_mali_profiling_get_mali_version); @@ -214,8 +186,8 @@ static void initialise_version_info(void) /* Release the function - we're done with it. */ symbol_put(_mali_profiling_get_mali_version); } else { - printk("gator: mali online _mali_profiling_get_mali_version symbol not found\n"); - printk("gator: check your Mali DDK version versus the GATOR_MALI_INTERFACE_STYLE setting\n"); + pr_err("gator: mali online _mali_profiling_get_mali_version symbol not found\n"); + pr_err("gator: check your Mali DDK version versus the GATOR_MALI_INTERFACE_STYLE setting\n"); } } #endif @@ -242,26 +214,24 @@ static int create_files(struct super_block *sb, struct dentry *root) mali_activity[0].cores = n_fp_cores; mali_activity[1].cores = n_vp_cores; for (event = 0; event < ARRAY_SIZE(mali_activity); event++) { - if (gator_mali_create_file_system(mali_name, mali_activity_names[event], sb, root, &mali_activity[event], NULL) != 0) { + if (gator_mali_create_file_system(mali_name, mali_activity_names[event], sb, root, &mali_activity[event], NULL) != 0) return -1; - } } /* Vertex processor counters */ for (core_id = 0; core_id < n_vp_cores; core_id++) { int activity_counter_id = ACTIVITY_VP_0; - snprintf(buf, sizeof buf, "ARM_%s_VP_%d_active", mali_name, core_id); - if (create_fs_entry(sb, root, buf, activity_counter_id, 0) != 0) { + + snprintf(buf, sizeof(buf), "ARM_Mali-%s_VP_%d_active", mali_name, core_id); + if (create_fs_entry(sb, root, buf, activity_counter_id, 0) != 0) return -1; - } for (counter_number = 0; counter_number < 2; counter_number++) { int counter_id = COUNTER_VP_0_C0 + (2 * core_id) + counter_number; - snprintf(buf, sizeof buf, "ARM_%s_VP_%d_cnt%d", mali_name, core_id, counter_number); - if (create_fs_entry(sb, root, buf, counter_id, 1) != 0) { + snprintf(buf, sizeof(buf), "ARM_Mali-%s_VP_%d_cnt%d", mali_name, core_id, counter_number); + if (create_fs_entry(sb, root, buf, counter_id, 1) != 0) return -1; - } } } @@ -269,18 +239,16 @@ static int create_files(struct super_block *sb, struct dentry *root) for (core_id = 0; core_id < n_fp_cores; core_id++) { int activity_counter_id = ACTIVITY_FP_0 + core_id; - snprintf(buf, sizeof buf, "ARM_%s_FP_%d_active", mali_name, core_id); - if (create_fs_entry(sb, root, buf, activity_counter_id, 0) != 0) { + snprintf(buf, sizeof(buf), "ARM_Mali-%s_FP_%d_active", mali_name, core_id); + if (create_fs_entry(sb, root, buf, activity_counter_id, 0) != 0) return -1; - } for (counter_number = 0; counter_number < 2; counter_number++) { int counter_id = COUNTER_FP_0_C0 + (2 * core_id) + counter_number; - snprintf(buf, sizeof buf, "ARM_%s_FP_%d_cnt%d", mali_name, core_id, counter_number); - if (create_fs_entry(sb, root, buf, counter_id, 1) != 0) { + snprintf(buf, sizeof(buf), "ARM_Mali-%s_FP_%d_cnt%d", mali_name, core_id, counter_number); + if (create_fs_entry(sb, root, buf, counter_id, 1) != 0) return -1; - } } } @@ -289,38 +257,33 @@ static int create_files(struct super_block *sb, struct dentry *root) for (counter_number = 0; counter_number < 2; counter_number++) { int counter_id = COUNTER_L2_0_C0 + (2 * core_id) + counter_number; - snprintf(buf, sizeof buf, "ARM_%s_L2_%d_cnt%d", mali_name, core_id, counter_number); - if (create_fs_entry(sb, root, buf, counter_id, 1) != 0) { + snprintf(buf, sizeof(buf), "ARM_Mali-%s_L2_%d_cnt%d", mali_name, core_id, counter_number); + if (create_fs_entry(sb, root, buf, counter_id, 1) != 0) return -1; - } } } /* Now set up the software counter entries */ for (event = FIRST_SW_COUNTER; event <= LAST_SW_COUNTER; event++) { - snprintf(buf, sizeof(buf), "ARM_%s_SW_%d", mali_name, event - FIRST_SW_COUNTER); + snprintf(buf, sizeof(buf), "ARM_Mali-%s_SW_%d", mali_name, event - FIRST_SW_COUNTER); - if (create_fs_entry(sb, root, buf, event, 0) != 0) { + if (create_fs_entry(sb, root, buf, event, 0) != 0) return -1; - } } /* Now set up the special counter entries */ - snprintf(buf, sizeof(buf), "ARM_%s_Filmstrip_cnt0", mali_name); - if (create_fs_entry(sb, root, buf, COUNTER_FILMSTRIP, 1) != 0) { + snprintf(buf, sizeof(buf), "ARM_Mali-%s_Filmstrip_cnt0", mali_name); + if (create_fs_entry(sb, root, buf, COUNTER_FILMSTRIP, 1) != 0) return -1; - } #ifdef DVFS_REPORTED_BY_DDK - snprintf(buf, sizeof(buf), "ARM_%s_Frequency", mali_name); - if (create_fs_entry(sb, root, buf, COUNTER_FREQUENCY, 1) != 0) { + snprintf(buf, sizeof(buf), "ARM_Mali-%s_Frequency", mali_name); + if (create_fs_entry(sb, root, buf, COUNTER_FREQUENCY, 1) != 0) return -1; - } - snprintf(buf, sizeof(buf), "ARM_%s_Voltage", mali_name); - if (create_fs_entry(sb, root, buf, COUNTER_VOLTAGE, 1) != 0) { + snprintf(buf, sizeof(buf), "ARM_Mali-%s_Voltage", mali_name); + if (create_fs_entry(sb, root, buf, COUNTER_VOLTAGE, 1) != 0) return -1; - } #endif return 0; @@ -330,8 +293,8 @@ static int create_files(struct super_block *sb, struct dentry *root) * Local store for the get_counters entry point into the DDK. * This is stored here since it is used very regularly. */ -static mali_profiling_get_counters_type *mali_get_counters = NULL; -static _mali_profiling_get_l2_counters_type *mali_get_l2_counters = NULL; +static void (*mali_get_counters)(unsigned int *, unsigned int *, unsigned int *, unsigned int *); +static u32 (*mali_get_l2_counters)(struct _mali_profiling_l2_counter_values *values); /* * Examine list of counters between two index limits and determine if any one is enabled. @@ -342,9 +305,8 @@ static int is_any_counter_enabled(unsigned int first_counter, unsigned int last_ unsigned int i; for (i = first_counter; i <= last_counter; i++) { - if (counter_enabled[i]) { + if (counter_enabled[i]) return 1; /* At least one counter is enabled */ - } } return 0; /* No s/w counters enabled */ @@ -366,16 +328,15 @@ static void init_counters(unsigned int from_counter, unsigned int to_counter) pr_debug("gator: mali online _mali_profiling_set_event symbol @ %p\n", mali_set_hw_event); for (counter_id = from_counter; counter_id <= to_counter; counter_id++) { - if (counter_enabled[counter_id]) { + if (counter_enabled[counter_id]) mali_set_hw_event(counter_id, counter_event[counter_id]); - } else { + else mali_set_hw_event(counter_id, 0xFFFFFFFF); - } } symbol_put(_mali_profiling_set_event); } else { - printk("gator: mali online _mali_profiling_set_event symbol not found\n"); + pr_err("gator: mali online _mali_profiling_set_event symbol not found\n"); } } @@ -407,27 +368,23 @@ static void mali_counter_initialize(void) symbol_put(_mali_profiling_control); } else { - printk("gator: mali online _mali_profiling_control symbol not found\n"); + pr_err("gator: mali online _mali_profiling_control symbol not found\n"); } mali_get_counters = symbol_get(_mali_profiling_get_counters); - if (mali_get_counters) { + if (mali_get_counters) pr_debug("gator: mali online _mali_profiling_get_counters symbol @ %p\n", mali_get_counters); - - } else { - pr_debug("gator WARNING: mali _mali_profiling_get_counters symbol not defined"); - } + else + pr_debug("gator WARNING: mali _mali_profiling_get_counters symbol not defined\n"); mali_get_l2_counters = symbol_get(_mali_profiling_get_l2_counters); - if (mali_get_l2_counters) { + if (mali_get_l2_counters) pr_debug("gator: mali online _mali_profiling_get_l2_counters symbol @ %p\n", mali_get_l2_counters); - - } else { - pr_debug("gator WARNING: mali _mali_profiling_get_l2_counters symbol not defined"); - } + else + pr_debug("gator WARNING: mali _mali_profiling_get_l2_counters symbol not defined\n"); if (!mali_get_counters && !mali_get_l2_counters) { - pr_debug("gator: WARNING: no L2 counters available"); + pr_debug("gator: WARNING: no L2 counters available\n"); n_l2_cores = 0; } @@ -449,13 +406,12 @@ static void mali_counter_deinitialize(void) int i; pr_debug("gator: mali offline _mali_profiling_set_event symbol @ %p\n", mali_set_hw_event); - for (i = FIRST_HW_COUNTER; i <= LAST_HW_COUNTER; i++) { + for (i = FIRST_HW_COUNTER; i <= LAST_HW_COUNTER; i++) mali_set_hw_event(i, 0xFFFFFFFF); - } symbol_put(_mali_profiling_set_event); } else { - printk("gator: mali offline _mali_profiling_set_event symbol not found\n"); + pr_err("gator: mali offline _mali_profiling_set_event symbol not found\n"); } /* Generic control interface for Mali DDK. */ @@ -471,29 +427,27 @@ static void mali_counter_deinitialize(void) symbol_put(_mali_profiling_control); } else { - printk("gator: mali offline _mali_profiling_control symbol not found\n"); + pr_err("gator: mali offline _mali_profiling_control symbol not found\n"); } - if (mali_get_counters) { + if (mali_get_counters) symbol_put(_mali_profiling_get_counters); - } - if (mali_get_l2_counters) { + if (mali_get_l2_counters) symbol_put(_mali_profiling_get_l2_counters); - } } static int start(void) { - // register tracepoints + /* register tracepoints */ if (GATOR_REGISTER_TRACE(mali_hw_counter)) { - printk("gator: mali_hw_counter tracepoint failed to activate\n"); + pr_err("gator: mali_hw_counter tracepoint failed to activate\n"); return -1; } /* For Mali drivers with built-in support. */ if (GATOR_REGISTER_TRACE(mali_sw_counters)) { - printk("gator: mali_sw_counters tracepoint failed to activate\n"); + pr_err("gator: mali_sw_counters tracepoint failed to activate\n"); return -1; } @@ -543,17 +497,17 @@ static void dump_counters(unsigned int from_counter, unsigned int to_counter, un } } -static int read(int **buffer) +static int read(int **buffer, bool sched_switch) { int len = 0; if (!on_primary_core()) return 0; - // Read the L2 C0 and C1 here. + /* Read the L2 C0 and C1 here. */ if (n_l2_cores > 0 && is_any_counter_enabled(COUNTER_L2_0_C0, COUNTER_L2_0_C0 + (2 * n_l2_cores))) { unsigned int unavailable_l2_caches = 0; - _mali_profiling_l2_counter_values cache_values; + struct _mali_profiling_l2_counter_values cache_values; unsigned int cache_id; struct _mali_profiling_core_counters *per_core; @@ -572,25 +526,24 @@ static int read(int **buffer) unsigned int counter_id_0 = COUNTER_L2_0_C0 + (2 * cache_id); unsigned int counter_id_1 = counter_id_0 + 1; - if ((1 << cache_id) & unavailable_l2_caches) { + if ((1 << cache_id) & unavailable_l2_caches) continue; /* This cache is unavailable (powered-off, possibly). */ - } per_core = &cache_values.cores[cache_id]; if (counter_enabled[counter_id_0] && prev_set[counter_id_0]) { - // Calculate and save src0's counter val0 + /* Calculate and save src0's counter val0 */ counter_dump[len++] = counter_key[counter_id_0]; counter_dump[len++] = per_core->value0 - counter_prev[counter_id_0]; } if (counter_enabled[counter_id_1] && prev_set[counter_id_1]) { - // Calculate and save src1's counter val1 + /* Calculate and save src1's counter val1 */ counter_dump[len++] = counter_key[counter_id_1]; counter_dump[len++] = per_core->value1 - counter_prev[counter_id_1]; } - // Save the previous values for the counters. + /* Save the previous values for the counters. */ counter_prev[counter_id_0] = per_core->value0; prev_set[counter_id_0] = true; counter_prev[counter_id_1] = per_core->value1; @@ -608,8 +561,9 @@ static int read(int **buffer) { int cnt; /* - * Add in the voltage and frequency counters if enabled. Note that, since these are - * actually passed as events, the counter value should not be cleared. + * Add in the voltage and frequency counters if enabled. Note + * that, since these are actually passed as events, the counter + * value should not be cleared. */ cnt = COUNTER_FREQUENCY; if (counter_enabled[cnt]) { @@ -625,9 +579,8 @@ static int read(int **buffer) } #endif - if (buffer) { - *buffer = (int *)counter_dump; - } + if (buffer) + *buffer = counter_dump; return len; } diff --git a/drivers/gator/gator_events_mali_common.c b/drivers/gator/gator_events_mali_common.c index 4f2cce4ce67b..1af87d649afe 100644 --- a/drivers/gator/gator_events_mali_common.c +++ b/drivers/gator/gator_events_mali_common.c @@ -8,7 +8,7 @@ */ #include "gator_events_mali_common.h" -extern int gator_mali_create_file_system(const char *mali_name, const char *event_name, struct super_block *sb, struct dentry *root, mali_counter *counter, unsigned long *event) +extern int gator_mali_create_file_system(const char *mali_name, const char *event_name, struct super_block *sb, struct dentry *root, struct mali_counter *counter, unsigned long *event) { int err; char buf[255]; @@ -17,36 +17,39 @@ extern int gator_mali_create_file_system(const char *mali_name, const char *even /* If the counter name is empty ignore it */ if (strlen(event_name) != 0) { /* Set up the filesystem entry for this event. */ - snprintf(buf, sizeof(buf), "ARM_%s_%s", mali_name, event_name); + if (mali_name == NULL) + snprintf(buf, sizeof(buf), "ARM_Mali-%s", event_name); + else + snprintf(buf, sizeof(buf), "ARM_Mali-%s_%s", mali_name, event_name); dir = gatorfs_mkdir(sb, root, buf); if (dir == NULL) { - pr_debug("gator: %s: error creating file system for: %s (%s)", mali_name, event_name, buf); + pr_debug("gator: %s: error creating file system for: %s (%s)\n", mali_name, event_name, buf); return -1; } err = gatorfs_create_ulong(sb, dir, "enabled", &counter->enabled); if (err != 0) { - pr_debug("gator: %s: error calling gatorfs_create_ulong for: %s (%s)", mali_name, event_name, buf); + pr_debug("gator: %s: error calling gatorfs_create_ulong for: %s (%s)\n", mali_name, event_name, buf); return -1; } err = gatorfs_create_ro_ulong(sb, dir, "key", &counter->key); if (err != 0) { - pr_debug("gator: %s: error calling gatorfs_create_ro_ulong for: %s (%s)", mali_name, event_name, buf); + pr_debug("gator: %s: error calling gatorfs_create_ro_ulong for: %s (%s)\n", mali_name, event_name, buf); return -1; } if (counter->cores != -1) { err = gatorfs_create_ro_ulong(sb, dir, "cores", &counter->cores); if (err != 0) { - pr_debug("gator: %s: error calling gatorfs_create_ro_ulong for: %s (%s)", mali_name, event_name, buf); + pr_debug("gator: %s: error calling gatorfs_create_ro_ulong for: %s (%s)\n", mali_name, event_name, buf); return -1; } } if (event != NULL) { err = gatorfs_create_ulong(sb, dir, "event", event); if (err != 0) { - pr_debug("gator: %s: error calling gatorfs_create_ro_ulong for: %s (%s)", mali_name, event_name, buf); + pr_debug("gator: %s: error calling gatorfs_create_ro_ulong for: %s (%s)\n", mali_name, event_name, buf); return -1; } } @@ -55,12 +58,12 @@ extern int gator_mali_create_file_system(const char *mali_name, const char *even return 0; } -extern void gator_mali_initialise_counters(mali_counter counters[], unsigned int n_counters) +extern void gator_mali_initialise_counters(struct mali_counter counters[], unsigned int n_counters) { unsigned int cnt; for (cnt = 0; cnt < n_counters; cnt++) { - mali_counter *counter = &counters[cnt]; + struct mali_counter *counter = &counters[cnt]; counter->key = gator_events_get_key(); counter->enabled = 0; diff --git a/drivers/gator/gator_events_mali_common.h b/drivers/gator/gator_events_mali_common.h index 91d871bc915a..e7082e62fe88 100644 --- a/drivers/gator/gator_events_mali_common.h +++ b/drivers/gator/gator_events_mali_common.h @@ -16,7 +16,7 @@ #include <linux/time.h> #include <linux/math64.h> #include <linux/slab.h> -#include <asm/io.h> +#include <linux/io.h> /* Ensure that MALI_SUPPORT has been defined to something. */ #ifndef MALI_SUPPORT @@ -30,21 +30,20 @@ /* * Runtime state information for a counter. */ -typedef struct { - // 'key' (a unique id set by gatord and returned by gator.ko) +struct mali_counter { + /* 'key' (a unique id set by gatord and returned by gator.ko) */ unsigned long key; - // counter enable state + /* counter enable state */ unsigned long enabled; - // for activity counters, the number of cores, otherwise -1 + /* for activity counters, the number of cores, otherwise -1 */ unsigned long cores; -} mali_counter; +}; /* * Mali-4xx */ typedef int mali_profiling_set_event_type(unsigned int, int); typedef void mali_profiling_control_type(unsigned int, unsigned int); -typedef void mali_profiling_get_counters_type(unsigned int *, unsigned int *, unsigned int *, unsigned int *); /* * Driver entry points for functions called directly by gator. @@ -65,7 +64,7 @@ extern void _mali_profiling_get_counters(unsigned int *, unsigned int *, unsigne * * @return 0 if entry point was created, non-zero if not. */ -extern int gator_mali_create_file_system(const char *mali_name, const char *event_name, struct super_block *sb, struct dentry *root, mali_counter *counter, unsigned long *event); +extern int gator_mali_create_file_system(const char *mali_name, const char *event_name, struct super_block *sb, struct dentry *root, struct mali_counter *counter, unsigned long *event); /** * Initializes the counter array. @@ -73,6 +72,6 @@ extern int gator_mali_create_file_system(const char *mali_name, const char *even * @param keys The array of counters * @param n_counters The number of entries in each of the arrays. */ -extern void gator_mali_initialise_counters(mali_counter counters[], unsigned int n_counters); +extern void gator_mali_initialise_counters(struct mali_counter counters[], unsigned int n_counters); #endif /* GATOR_EVENTS_MALI_COMMON_H */ diff --git a/drivers/gator/gator_events_mali_t6xx.c b/drivers/gator/gator_events_mali_midgard.c index e56ba84aefb8..0aec906d7ae5 100644 --- a/drivers/gator/gator_events_mali_t6xx.c +++ b/drivers/gator/gator_events_mali_midgard.c @@ -13,7 +13,7 @@ #include <linux/time.h> #include <linux/math64.h> #include <linux/slab.h> -#include <asm/io.h> +#include <linux/io.h> #ifdef MALI_DIR_MIDGARD /* New DDK Directory structure with kernel/drivers/gpu/arm/midgard*/ @@ -28,13 +28,13 @@ /* * Check that the MALI_SUPPORT define is set to one of the allowable device codes. */ -#if (MALI_SUPPORT != MALI_T6xx) -#error MALI_SUPPORT set to an invalid device code: expecting MALI_T6xx +#if (MALI_SUPPORT != MALI_MIDGARD) +#error MALI_SUPPORT set to an invalid device code: expecting MALI_MIDGARD #endif -static const char mali_name[] = "Mali-T6xx"; +static const char mali_name[] = "Midgard"; -/* Counters for Mali-T6xx: +/* Counters for Mali-Midgard: * * - Timeline events * They are tracepoints, but instead of reporting a number they report a START/STOP event. @@ -49,7 +49,7 @@ static const char mali_name[] = "Mali-T6xx"; */ /* Timeline (start/stop) activity */ -static const char *timeline_event_names[] = { +static const char *const timeline_event_names[] = { "PM_SHADER_0", "PM_SHADER_1", "PM_SHADER_2", @@ -88,7 +88,7 @@ enum { #define NUM_PM_SHADER (8) /* Software Counters */ -static const char *software_counter_names[] = { +static const char *const software_counter_names[] = { "MMU_PAGE_FAULT_0", "MMU_PAGE_FAULT_1", "MMU_PAGE_FAULT_2", @@ -103,7 +103,7 @@ enum { }; /* Software Counters */ -static const char *accumulators_names[] = { +static const char *const accumulators_names[] = { "TOTAL_ALLOC_PAGES" }; @@ -123,17 +123,18 @@ enum { /* * gatorfs variables for counter enable state */ -static mali_counter counters[NUMBER_OF_EVENTS]; +static struct mali_counter counters[NUMBER_OF_EVENTS]; static unsigned long filmstrip_event; /* An array used to return the data we recorded * as key,value pairs hence the *2 */ -static unsigned long counter_dump[NUMBER_OF_EVENTS * 2]; +static int counter_dump[NUMBER_OF_EVENTS * 2]; /* - * Array holding counter start times (in ns) for each counter. A zero here - * indicates that the activity monitored by this counter is not running. + * Array holding counter start times (in ns) for each counter. A zero + * here indicates that the activity monitored by this counter is not + * running. */ static struct timespec timeline_event_starttime[NUMBER_OF_TIMELINE_EVENTS]; @@ -156,6 +157,7 @@ static struct timespec prev_timestamp; static inline long get_duration_us(const struct timespec *start, const struct timespec *end) { long event_duration_us = (end->tv_nsec - start->tv_nsec) / 1000; + event_duration_us += (end->tv_sec - start->tv_sec) * 1000000; return event_duration_us; @@ -172,9 +174,8 @@ static void record_timeline_event(unsigned int timeline_index, unsigned int type getnstimeofday(&event_timestamp); /* Remember the start time if the activity is not already started */ - if (event_start->tv_sec == 0) { + if (event_start->tv_sec == 0) *event_start = event_timestamp; /* Structure copy */ - } break; case ACTIVITY_STOP: @@ -208,9 +209,9 @@ GATOR_DEFINE_PROBE(mali_pm_status, TP_PROTO(unsigned int event_id, unsigned long #define L2_PRESENT_LO 0x120 /* (RO) Level 2 cache present bitmap, low word */ #define BIT_AT(value, pos) ((value >> pos) & 1) - static unsigned long long previous_shader_bitmask = 0; - static unsigned long long previous_tiler_bitmask = 0; - static unsigned long long previous_l2_bitmask = 0; + static unsigned long long previous_shader_bitmask; + static unsigned long long previous_tiler_bitmask; + static unsigned long long previous_l2_bitmask; switch (event_id) { case SHADER_PRESENT_LO: @@ -219,9 +220,8 @@ GATOR_DEFINE_PROBE(mali_pm_status, TP_PROTO(unsigned int event_id, unsigned long int pos; for (pos = 0; pos < NUM_PM_SHADER; ++pos) { - if (BIT_AT(changed_bitmask, pos)) { + if (BIT_AT(changed_bitmask, pos)) record_timeline_event(PM_SHADER_0 + pos, BIT_AT(value, pos) ? ACTIVITY_START : ACTIVITY_STOP); - } } previous_shader_bitmask = value; @@ -232,9 +232,8 @@ GATOR_DEFINE_PROBE(mali_pm_status, TP_PROTO(unsigned int event_id, unsigned long { unsigned long long changed = previous_tiler_bitmask ^ value; - if (BIT_AT(changed, 0)) { + if (BIT_AT(changed, 0)) record_timeline_event(PM_TILER_0, BIT_AT(value, 0) ? ACTIVITY_START : ACTIVITY_STOP); - } previous_tiler_bitmask = value; break; @@ -244,12 +243,10 @@ GATOR_DEFINE_PROBE(mali_pm_status, TP_PROTO(unsigned int event_id, unsigned long { unsigned long long changed = previous_l2_bitmask ^ value; - if (BIT_AT(changed, 0)) { + if (BIT_AT(changed, 0)) record_timeline_event(PM_L2_0, BIT_AT(value, 0) ? ACTIVITY_START : ACTIVITY_STOP); - } - if (BIT_AT(changed, 4)) { + if (BIT_AT(changed, 4)) record_timeline_event(PM_L2_1, BIT_AT(value, 4) ? ACTIVITY_START : ACTIVITY_STOP); - } previous_l2_bitmask = value; break; @@ -297,31 +294,27 @@ static int create_files(struct super_block *sb, struct dentry *root) mali_profiling_control_type *mali_control; for (event = FIRST_TIMELINE_EVENT; event < FIRST_TIMELINE_EVENT + NUMBER_OF_TIMELINE_EVENTS; event++) { - if (gator_mali_create_file_system(mali_name, timeline_event_names[counter_index], sb, root, &counters[event], NULL) != 0) { + if (gator_mali_create_file_system(mali_name, timeline_event_names[counter_index], sb, root, &counters[event], NULL) != 0) return -1; - } counter_index++; } counter_index = 0; for (event = FIRST_SOFTWARE_COUNTER; event < FIRST_SOFTWARE_COUNTER + NUMBER_OF_SOFTWARE_COUNTERS; event++) { - if (gator_mali_create_file_system(mali_name, software_counter_names[counter_index], sb, root, &counters[event], NULL) != 0) { + if (gator_mali_create_file_system(mali_name, software_counter_names[counter_index], sb, root, &counters[event], NULL) != 0) return -1; - } counter_index++; } counter_index = 0; for (event = FIRST_ACCUMULATOR; event < FIRST_ACCUMULATOR + NUMBER_OF_ACCUMULATORS; event++) { - if (gator_mali_create_file_system(mali_name, accumulators_names[counter_index], sb, root, &counters[event], NULL) != 0) { + if (gator_mali_create_file_system(mali_name, accumulators_names[counter_index], sb, root, &counters[event], NULL) != 0) return -1; - } counter_index++; } mali_control = symbol_get(_mali_profiling_control); if (mali_control) { - if (gator_mali_create_file_system(mali_name, "Filmstrip_cnt0", sb, root, &counters[FILMSTRIP], &filmstrip_event) != 0) { + if (gator_mali_create_file_system(mali_name, "Filmstrip_cnt0", sb, root, &counters[FILMSTRIP], &filmstrip_event) != 0) return -1; - } symbol_put(_mali_profiling_control); } @@ -331,36 +324,36 @@ static int create_files(struct super_block *sb, struct dentry *root) static int register_tracepoints(void) { if (GATOR_REGISTER_TRACE(mali_pm_status)) { - pr_debug("gator: Mali-T6xx: mali_pm_status tracepoint failed to activate\n"); + pr_debug("gator: Mali-Midgard: mali_pm_status tracepoint failed to activate\n"); return 0; } if (GATOR_REGISTER_TRACE(mali_page_fault_insert_pages)) { - pr_debug("gator: Mali-T6xx: mali_page_fault_insert_pages tracepoint failed to activate\n"); + pr_debug("gator: Mali-Midgard: mali_page_fault_insert_pages tracepoint failed to activate\n"); return 0; } if (GATOR_REGISTER_TRACE(mali_mmu_as_in_use)) { - pr_debug("gator: Mali-T6xx: mali_mmu_as_in_use tracepoint failed to activate\n"); + pr_debug("gator: Mali-Midgard: mali_mmu_as_in_use tracepoint failed to activate\n"); return 0; } if (GATOR_REGISTER_TRACE(mali_mmu_as_released)) { - pr_debug("gator: Mali-T6xx: mali_mmu_as_released tracepoint failed to activate\n"); + pr_debug("gator: Mali-Midgard: mali_mmu_as_released tracepoint failed to activate\n"); return 0; } if (GATOR_REGISTER_TRACE(mali_total_alloc_pages_change)) { - pr_debug("gator: Mali-T6xx: mali_total_alloc_pages_change tracepoint failed to activate\n"); + pr_debug("gator: Mali-Midgard: mali_total_alloc_pages_change tracepoint failed to activate\n"); return 0; } - pr_debug("gator: Mali-T6xx: start\n"); - pr_debug("gator: Mali-T6xx: mali_pm_status probe is at %p\n", &probe_mali_pm_status); - pr_debug("gator: Mali-T6xx: mali_page_fault_insert_pages probe is at %p\n", &probe_mali_page_fault_insert_pages); - pr_debug("gator: Mali-T6xx: mali_mmu_as_in_use probe is at %p\n", &probe_mali_mmu_as_in_use); - pr_debug("gator: Mali-T6xx: mali_mmu_as_released probe is at %p\n", &probe_mali_mmu_as_released); - pr_debug("gator: Mali-T6xx: mali_total_alloc_pages_change probe is at %p\n", &probe_mali_total_alloc_pages_change); + pr_debug("gator: Mali-Midgard: start\n"); + pr_debug("gator: Mali-Midgard: mali_pm_status probe is at %p\n", &probe_mali_pm_status); + pr_debug("gator: Mali-Midgard: mali_page_fault_insert_pages probe is at %p\n", &probe_mali_page_fault_insert_pages); + pr_debug("gator: Mali-Midgard: mali_mmu_as_in_use probe is at %p\n", &probe_mali_mmu_as_in_use); + pr_debug("gator: Mali-Midgard: mali_mmu_as_released probe is at %p\n", &probe_mali_mmu_as_released); + pr_debug("gator: Mali-Midgard: mali_total_alloc_pages_change probe is at %p\n", &probe_mali_total_alloc_pages_change); return 1; } @@ -376,18 +369,15 @@ static int start(void) timeline_data[cnt] = 0; } - for (cnt = 0; cnt < NUMBER_OF_SOFTWARE_COUNTERS; cnt++) { + for (cnt = 0; cnt < NUMBER_OF_SOFTWARE_COUNTERS; cnt++) sw_counter_data[cnt] = 0; - } - for (cnt = 0; cnt < NUMBER_OF_ACCUMULATORS; cnt++) { + for (cnt = 0; cnt < NUMBER_OF_ACCUMULATORS; cnt++) accumulators_data[cnt] = 0; - } /* Register tracepoints */ - if (register_tracepoints() == 0) { + if (register_tracepoints() == 0) return -1; - } /* Generic control interface for Mali DDK. */ mali_control = symbol_get(_mali_profiling_control); @@ -410,7 +400,7 @@ static int start(void) symbol_put(_mali_profiling_control); } else { - printk("gator: mali online _mali_profiling_control symbol not found\n"); + pr_err("gator: mali online _mali_profiling_control symbol not found\n"); } /* @@ -427,26 +417,26 @@ static void stop(void) { mali_profiling_control_type *mali_control; - pr_debug("gator: Mali-T6xx: stop\n"); + pr_debug("gator: Mali-Midgard: stop\n"); /* * It is safe to unregister traces even if they were not successfully * registered, so no need to check. */ GATOR_UNREGISTER_TRACE(mali_pm_status); - pr_debug("gator: Mali-T6xx: mali_pm_status tracepoint deactivated\n"); + pr_debug("gator: Mali-Midgard: mali_pm_status tracepoint deactivated\n"); GATOR_UNREGISTER_TRACE(mali_page_fault_insert_pages); - pr_debug("gator: Mali-T6xx: mali_page_fault_insert_pages tracepoint deactivated\n"); + pr_debug("gator: Mali-Midgard: mali_page_fault_insert_pages tracepoint deactivated\n"); GATOR_UNREGISTER_TRACE(mali_mmu_as_in_use); - pr_debug("gator: Mali-T6xx: mali_mmu_as_in_use tracepoint deactivated\n"); + pr_debug("gator: Mali-Midgard: mali_mmu_as_in_use tracepoint deactivated\n"); GATOR_UNREGISTER_TRACE(mali_mmu_as_released); - pr_debug("gator: Mali-T6xx: mali_mmu_as_released tracepoint deactivated\n"); + pr_debug("gator: Mali-Midgard: mali_mmu_as_released tracepoint deactivated\n"); GATOR_UNREGISTER_TRACE(mali_total_alloc_pages_change); - pr_debug("gator: Mali-T6xx: mali_total_alloc_pages_change tracepoint deactivated\n"); + pr_debug("gator: Mali-Midgard: mali_total_alloc_pages_change tracepoint deactivated\n"); /* Generic control interface for Mali DDK. */ mali_control = symbol_get(_mali_profiling_control); @@ -457,20 +447,19 @@ static void stop(void) symbol_put(_mali_profiling_control); } else { - printk("gator: mali offline _mali_profiling_control symbol not found\n"); + pr_err("gator: mali offline _mali_profiling_control symbol not found\n"); } } -static int read(int **buffer) +static int read(int **buffer, bool sched_switch) { int cnt; int len = 0; long sample_interval_us = 0; struct timespec read_timestamp; - if (!on_primary_core()) { + if (!on_primary_core()) return 0; - } /* Get the start of this sample period. */ getnstimeofday(&read_timestamp); @@ -479,9 +468,8 @@ static int read(int **buffer) * Calculate the sample interval if the previous sample time is valid. * We use tv_sec since it will not be 0. */ - if (prev_timestamp.tv_sec != 0) { + if (prev_timestamp.tv_sec != 0) sample_interval_us = get_duration_us(&prev_timestamp, &read_timestamp); - } /* Structure copy. Update the previous timestamp. */ prev_timestamp = read_timestamp; @@ -490,15 +478,19 @@ static int read(int **buffer) * Report the timeline counters (ACTIVITY_START/STOP) */ for (cnt = FIRST_TIMELINE_EVENT; cnt < (FIRST_TIMELINE_EVENT + NUMBER_OF_TIMELINE_EVENTS); cnt++) { - mali_counter *counter = &counters[cnt]; + struct mali_counter *counter = &counters[cnt]; + if (counter->enabled) { const int index = cnt - FIRST_TIMELINE_EVENT; unsigned int value; - /* If the activity is still running, reset its start time to the start of this sample period - * to correct the count. Add the time up to the end of the sample onto the count. */ + /* If the activity is still running, reset its start time to the + * start of this sample period to correct the count. Add the + * time up to the end of the sample onto the count. + */ if (timeline_event_starttime[index].tv_sec != 0) { const long event_duration = get_duration_us(&timeline_event_starttime[index], &read_timestamp); + timeline_data[index] += event_duration; timeline_event_starttime[index] = read_timestamp; /* Activity is still running. */ } @@ -507,7 +499,7 @@ static int read(int **buffer) /* Convert the counter to a percent-of-sample value */ value = (timeline_data[index] * 100) / sample_interval_us; } else { - pr_debug("gator: Mali-T6xx: setting value to zero\n"); + pr_debug("gator: Mali-Midgard: setting value to zero\n"); value = 0; } @@ -521,9 +513,11 @@ static int read(int **buffer) /* Report the software counters */ for (cnt = FIRST_SOFTWARE_COUNTER; cnt < (FIRST_SOFTWARE_COUNTER + NUMBER_OF_SOFTWARE_COUNTERS); cnt++) { - const mali_counter *counter = &counters[cnt]; + const struct mali_counter *counter = &counters[cnt]; + if (counter->enabled) { const int index = cnt - FIRST_SOFTWARE_COUNTER; + counter_dump[len++] = counter->key; counter_dump[len++] = sw_counter_data[index]; /* Set the value to zero for the next time */ @@ -533,9 +527,11 @@ static int read(int **buffer) /* Report the accumulators */ for (cnt = FIRST_ACCUMULATOR; cnt < (FIRST_ACCUMULATOR + NUMBER_OF_ACCUMULATORS); cnt++) { - const mali_counter *counter = &counters[cnt]; + const struct mali_counter *counter = &counters[cnt]; + if (counter->enabled) { const int index = cnt - FIRST_ACCUMULATOR; + counter_dump[len++] = counter->key; counter_dump[len++] = accumulators_data[index]; /* Do not zero the accumulator */ @@ -543,25 +539,24 @@ static int read(int **buffer) } /* Update the buffer */ - if (buffer) { - *buffer = (int *)counter_dump; - } + if (buffer) + *buffer = counter_dump; return len; } -static struct gator_interface gator_events_mali_t6xx_interface = { +static struct gator_interface gator_events_mali_midgard_interface = { .create_files = create_files, .start = start, .stop = stop, .read = read }; -extern int gator_events_mali_t6xx_init(void) +extern int gator_events_mali_midgard_init(void) { - pr_debug("gator: Mali-T6xx: sw_counters init\n"); + pr_debug("gator: Mali-Midgard: sw_counters init\n"); gator_mali_initialise_counters(counters, NUMBER_OF_EVENTS); - return gator_events_install(&gator_events_mali_t6xx_interface); + return gator_events_install(&gator_events_mali_midgard_interface); } diff --git a/drivers/gator/gator_events_mali_t6xx_hw.c b/drivers/gator/gator_events_mali_midgard_hw.c index 3a072bb6ac06..c8065da56815 100644 --- a/drivers/gator/gator_events_mali_t6xx_hw.c +++ b/drivers/gator/gator_events_mali_midgard_hw.c @@ -13,19 +13,19 @@ #include <linux/time.h> #include <linux/math64.h> #include <linux/slab.h> -#include <asm/io.h> +#include <linux/io.h> -/* Mali T6xx DDK includes */ +/* Mali Midgard DDK includes */ #if defined(MALI_SIMPLE_API) /* Header with wrapper functions to kbase structures and functions */ -#include "mali/mali_dd_gator_api.h" +#include "mali/mali_kbase_gator_api.h" #elif defined(MALI_DIR_MIDGARD) -/* New DDK Directory structure with kernel/drivers/gpu/arm/midgard*/ +/* New DDK Directory structure with kernel/drivers/gpu/arm/midgard */ #include "mali_linux_trace.h" #include "mali_kbase.h" #include "mali_kbase_mem_linux.h" #else -/* Old DDK Directory structure with kernel/drivers/gpu/arm/t6xx*/ +/* Old DDK Directory structure with kernel/drivers/gpu/arm/t6xx */ #include "linux/mali_linux_trace.h" #include "kbase/src/common/mali_kbase.h" #include "kbase/src/linux/mali_kbase_mem_linux.h" @@ -37,76 +37,63 @@ #endif #if (MALI_DDK_GATOR_API_VERSION != 1) && (MALI_DDK_GATOR_API_VERSION != 2) && (MALI_DDK_GATOR_API_VERSION != 3) -#error MALI_DDK_GATOR_API_VERSION is invalid (must be 1 for r1/r2 DDK, or 2 for r3 DDK, or 3 for r? DDK). +#error MALI_DDK_GATOR_API_VERSION is invalid (must be 1 for r1/r2 DDK, or 2 for r3/r4 DDK, or 3 for r5 and later DDK). #endif #include "gator_events_mali_common.h" /* - * Mali-T6xx + * Mali-Midgard */ #if MALI_DDK_GATOR_API_VERSION == 3 -typedef uint32_t kbase_dd_instr_hwcnt_dump_irq_type(struct mali_dd_hwcnt_handles *); -typedef uint32_t kbase_dd_instr_hwcnt_dump_complete_type(struct mali_dd_hwcnt_handles *, uint32_t *); -typedef struct mali_dd_hwcnt_handles* mali_dd_hwcnt_init_type(struct mali_dd_hwcnt_info *); -typedef void mali_dd_hwcnt_clear_type(struct mali_dd_hwcnt_info *, struct mali_dd_hwcnt_handles *); - -static kbase_dd_instr_hwcnt_dump_irq_type *kbase_dd_instr_hwcnt_dump_irq_symbol; -static kbase_dd_instr_hwcnt_dump_complete_type *kbase_dd_instr_hwcnt_dump_complete_symbol; -static mali_dd_hwcnt_init_type *mali_dd_hwcnt_init_symbol; -static mali_dd_hwcnt_clear_type *mali_dd_hwcnt_clear_symbol; +static uint32_t (*kbase_gator_instr_hwcnt_dump_irq_symbol)(struct kbase_gator_hwcnt_handles *); +static uint32_t (*kbase_gator_instr_hwcnt_dump_complete_symbol)(struct kbase_gator_hwcnt_handles *, uint32_t *const); +static struct kbase_gator_hwcnt_handles *(*kbase_gator_hwcnt_init_symbol)(struct kbase_gator_hwcnt_info *); +static void (*kbase_gator_hwcnt_term_symbol)(struct kbase_gator_hwcnt_info *, struct kbase_gator_hwcnt_handles *); #else -typedef struct kbase_device *kbase_find_device_type(int); -typedef struct kbase_context *kbase_create_context_type(struct kbase_device *); -typedef void kbase_destroy_context_type(struct kbase_context *); +static struct kbase_device *(*kbase_find_device_symbol)(int); +static struct kbase_context *(*kbase_create_context_symbol)(struct kbase_device *); +static void (*kbase_destroy_context_symbol)(struct kbase_context *); #if MALI_DDK_GATOR_API_VERSION == 1 -typedef void *kbase_va_alloc_type(struct kbase_context *, u32); -typedef void kbase_va_free_type(struct kbase_context *, void *); +static void *(*kbase_va_alloc_symbol)(struct kbase_context *, u32); +static void (*kbase_va_free_symbol)(struct kbase_context *, void *); #elif MALI_DDK_GATOR_API_VERSION == 2 -typedef void *kbase_va_alloc_type(struct kbase_context *, u32, kbase_hwc_dma_mapping * handle); -typedef void kbase_va_free_type(struct kbase_context *, kbase_hwc_dma_mapping * handle); +static void *(*kbase_va_alloc_symbol)(struct kbase_context *, u32, struct kbase_hwc_dma_mapping *); +static void (*kbase_va_free_symbol)(struct kbase_context *, struct kbase_hwc_dma_mapping *); #endif -typedef mali_error kbase_instr_hwcnt_enable_type(struct kbase_context *, struct kbase_uk_hwcnt_setup *); -typedef mali_error kbase_instr_hwcnt_disable_type(struct kbase_context *); -typedef mali_error kbase_instr_hwcnt_clear_type(struct kbase_context *); -typedef mali_error kbase_instr_hwcnt_dump_irq_type(struct kbase_context *); -typedef mali_bool kbase_instr_hwcnt_dump_complete_type(struct kbase_context *, mali_bool *); - -static kbase_find_device_type *kbase_find_device_symbol; -static kbase_create_context_type *kbase_create_context_symbol; -static kbase_va_alloc_type *kbase_va_alloc_symbol; -static kbase_instr_hwcnt_enable_type *kbase_instr_hwcnt_enable_symbol; -static kbase_instr_hwcnt_clear_type *kbase_instr_hwcnt_clear_symbol; -static kbase_instr_hwcnt_dump_irq_type *kbase_instr_hwcnt_dump_irq_symbol; -static kbase_instr_hwcnt_dump_complete_type *kbase_instr_hwcnt_dump_complete_symbol; -static kbase_instr_hwcnt_disable_type *kbase_instr_hwcnt_disable_symbol; -static kbase_va_free_type *kbase_va_free_symbol; -static kbase_destroy_context_type *kbase_destroy_context_symbol; -#endif +static mali_error (*kbase_instr_hwcnt_enable_symbol)(struct kbase_context *, struct kbase_uk_hwcnt_setup *); +static mali_error (*kbase_instr_hwcnt_disable_symbol)(struct kbase_context *); +static mali_error (*kbase_instr_hwcnt_clear_symbol)(struct kbase_context *); +static mali_error (*kbase_instr_hwcnt_dump_irq_symbol)(struct kbase_context *); +static mali_bool (*kbase_instr_hwcnt_dump_complete_symbol)(struct kbase_context *, mali_bool *); -static long shader_present_low = 0; +static long shader_present_low; +#endif /** The interval between reads, in ns. * - * Earlier we introduced - * a 'hold off for 1ms after last read' to resolve MIDBASE-2178 and MALINE-724. - * However, the 1ms hold off is too long if no context switches occur as there is a race - * between this value and the tick of the read clock in gator which is also 1ms. If we 'miss' the - * current read, the counter values are effectively 'spread' over 2ms and the values seen are half - * what they should be (since Streamline averages over sample time). In the presence of context switches - * this spread can vary and markedly affect the counters. Currently there is no 'proper' solution to - * this, but empirically we have found that reducing the minimum read interval to 950us causes the - * counts to be much more stable. + * Earlier we introduced a 'hold off for 1ms after last read' to + * resolve MIDBASE-2178 and MALINE-724. However, the 1ms hold off is + * too long if no context switches occur as there is a race between + * this value and the tick of the read clock in gator which is also + * 1ms. If we 'miss' the current read, the counter values are + * effectively 'spread' over 2ms and the values seen are half what + * they should be (since Streamline averages over sample time). In the + * presence of context switches this spread can vary and markedly + * affect the counters. Currently there is no 'proper' solution to + * this, but empirically we have found that reducing the minimum read + * interval to 950us causes the counts to be much more stable. */ static const int READ_INTERVAL_NSEC = 950000; #if GATOR_TEST -#include "gator_events_mali_t6xx_hw_test.c" +#include "gator_events_mali_midgard_hw_test.c" #endif +#if MALI_DDK_GATOR_API_VERSION != 3 /* Blocks for HW counters */ enum { JM_BLOCK = 0, @@ -114,12 +101,12 @@ enum { SHADER_BLOCK, MMU_BLOCK }; +#endif -static const char mali_name[] = "Mali-T6xx"; +static const char *mali_name; -/* Counters for Mali-T6xx: +/* Counters for Mali-Midgard: * - * - HW counters, 4 blocks * For HW counters we need strings to create /dev/gator/events files. * Enums are not needed because the position of the HW name in the array is the same * of the corresponding value in the received block of memory. @@ -128,6 +115,13 @@ static const char mali_name[] = "Mali-T6xx"; */ /* Hardware Counters */ +#if MALI_DDK_GATOR_API_VERSION == 3 + +static const char *const *hardware_counter_names; +static int number_of_hardware_counters; + +#else + static const char *const hardware_counter_names[] = { /* Job Manager */ "", @@ -394,17 +388,19 @@ static const char *const hardware_counter_names[] = { "L2_REPLAY_FULL" }; -#define NUMBER_OF_HARDWARE_COUNTERS (sizeof(hardware_counter_names) / sizeof(hardware_counter_names[0])) +static const int number_of_hardware_counters = ARRAY_SIZE(hardware_counter_names); + +#endif #define GET_HW_BLOCK(c) (((c) >> 6) & 0x3) #define GET_COUNTER_OFFSET(c) ((c) & 0x3f) #if MALI_DDK_GATOR_API_VERSION == 3 /* Opaque handles for kbase_context and kbase_hwc_dma_mapping */ -static struct mali_dd_hwcnt_handles *handles; +static struct kbase_gator_hwcnt_handles *handles; /* Information about hardware counters */ -static struct mali_dd_hwcnt_info *in_out_info; +static struct kbase_gator_hwcnt_info *in_out_info; #else /* Memory to dump hardware counters into */ @@ -412,56 +408,58 @@ static void *kernel_dump_buffer; #if MALI_DDK_GATOR_API_VERSION == 2 /* DMA state used to manage lifetime of the buffer */ -kbase_hwc_dma_mapping kernel_dump_buffer_handle; +struct kbase_hwc_dma_mapping kernel_dump_buffer_handle; #endif /* kbase context and device */ -static struct kbase_context *kbcontext = NULL; -static struct kbase_device *kbdevice = NULL; +static struct kbase_context *kbcontext; +static struct kbase_device *kbdevice; + +/* + * The following function has no external prototype in older DDK + * revisions. When the DDK is updated then this should be removed. + */ +struct kbase_device *kbase_find_device(int minor); #endif -static volatile bool kbase_device_busy = false; +static volatile bool kbase_device_busy; static unsigned int num_hardware_counters_enabled; -/* - * gatorfs variables for counter enable state - */ -static mali_counter counters[NUMBER_OF_HARDWARE_COUNTERS]; +/* gatorfs variables for counter enable state */ +static struct mali_counter *counters; -/* An array used to return the data we recorded - * as key,value pairs hence the *2 - */ -static unsigned long counter_dump[NUMBER_OF_HARDWARE_COUNTERS * 2]; +/* An array used to return the data we recorded as key,value pairs */ +static int *counter_dump; + +extern struct mali_counter mali_activity[3]; -extern mali_counter mali_activity[3]; -static const char* const mali_activity_names[] = { +static const char *const mali_activity_names[] = { "fragment", "vertex", "opencl", }; #define SYMBOL_GET(FUNCTION, ERROR_COUNT) \ - if(FUNCTION ## _symbol) \ - { \ - printk("gator: mali " #FUNCTION " symbol was already registered\n"); \ - (ERROR_COUNT)++; \ - } \ - else \ - { \ - FUNCTION ## _symbol = symbol_get(FUNCTION); \ - if(! FUNCTION ## _symbol) \ - { \ - printk("gator: mali online " #FUNCTION " symbol not found\n"); \ + do { \ + if (FUNCTION ## _symbol) { \ + pr_err("gator: mali " #FUNCTION " symbol was already registered\n"); \ (ERROR_COUNT)++; \ + } else { \ + FUNCTION ## _symbol = symbol_get(FUNCTION); \ + if (!FUNCTION ## _symbol) { \ + pr_err("gator: mali online " #FUNCTION " symbol not found\n"); \ + (ERROR_COUNT)++; \ + } \ } \ - } + } while (0) #define SYMBOL_CLEANUP(FUNCTION) \ - if(FUNCTION ## _symbol) \ - { \ - symbol_put(FUNCTION); \ - FUNCTION ## _symbol = NULL; \ - } + do { \ + if (FUNCTION ## _symbol) { \ + symbol_put(FUNCTION); \ + FUNCTION ## _symbol = NULL; \ + } \ + } while (0) /** * Execute symbol_get for all the Mali symbols and check for success. @@ -471,10 +469,10 @@ static int init_symbols(void) { int error_count = 0; #if MALI_DDK_GATOR_API_VERSION == 3 - SYMBOL_GET(kbase_dd_instr_hwcnt_dump_irq, error_count); - SYMBOL_GET(kbase_dd_instr_hwcnt_dump_complete, error_count); - SYMBOL_GET(mali_dd_hwcnt_init, error_count); - SYMBOL_GET(mali_dd_hwcnt_clear, error_count); + SYMBOL_GET(kbase_gator_instr_hwcnt_dump_irq, error_count); + SYMBOL_GET(kbase_gator_instr_hwcnt_dump_complete, error_count); + SYMBOL_GET(kbase_gator_hwcnt_init, error_count); + SYMBOL_GET(kbase_gator_hwcnt_term, error_count); #else SYMBOL_GET(kbase_find_device, error_count); SYMBOL_GET(kbase_create_context, error_count); @@ -497,10 +495,10 @@ static int init_symbols(void) static void clean_symbols(void) { #if MALI_DDK_GATOR_API_VERSION == 3 - SYMBOL_CLEANUP(kbase_dd_instr_hwcnt_dump_irq); - SYMBOL_CLEANUP(kbase_dd_instr_hwcnt_dump_complete); - SYMBOL_CLEANUP(mali_dd_hwcnt_init); - SYMBOL_CLEANUP(mali_dd_hwcnt_clear); + SYMBOL_CLEANUP(kbase_gator_instr_hwcnt_dump_irq); + SYMBOL_CLEANUP(kbase_gator_instr_hwcnt_dump_complete); + SYMBOL_CLEANUP(kbase_gator_hwcnt_init); + SYMBOL_CLEANUP(kbase_gator_hwcnt_term); #else SYMBOL_CLEANUP(kbase_find_device); SYMBOL_CLEANUP(kbase_create_context); @@ -526,14 +524,12 @@ static void clean_symbols(void) static int is_read_scheduled(const struct timespec *current_time, u32 *prev_time_s, s32 *next_read_time_ns) { /* If the current ns count rolls over a second, roll the next read time too. */ - if (current_time->tv_sec != *prev_time_s) { + if (current_time->tv_sec != *prev_time_s) *next_read_time_ns = *next_read_time_ns - NSEC_PER_SEC; - } /* Abort the read if the next read time has not arrived. */ - if (current_time->tv_nsec < *next_read_time_ns) { + if (current_time->tv_nsec < *next_read_time_ns) return 0; - } /* Set the next read some fixed time after this one, and update the read timestamp. */ *next_read_time_ns = current_time->tv_nsec + READ_INTERVAL_NSEC; @@ -544,7 +540,7 @@ static int is_read_scheduled(const struct timespec *current_time, u32 *prev_time static int start(void) { -#if MALI_DDK_GATOR_API_VERSION < 3 +#if MALI_DDK_GATOR_API_VERSION != 3 struct kbase_uk_hwcnt_setup setup; unsigned long long shadersPresent = 0; u16 bitmask[] = { 0, 0, 0, 0 }; @@ -552,37 +548,27 @@ static int start(void) #endif int cnt; +#if MALI_DDK_GATOR_API_VERSION == 3 /* Setup HW counters */ num_hardware_counters_enabled = 0; - if (NUMBER_OF_HARDWARE_COUNTERS != 256) { - pr_debug("Unexpected number of hardware counters defined: expecting 256, got %d\n", NUMBER_OF_HARDWARE_COUNTERS); - } - -#if MALI_DDK_GATOR_API_VERSION == 3 - /* Declare and initialise mali_dd_hwcnt_info structure */ - in_out_info = kmalloc(sizeof(struct mali_dd_hwcnt_info), GFP_KERNEL); - for (cnt = 0; cnt < 4; cnt++){ + /* Declare and initialise kbase_gator_hwcnt_info structure */ + in_out_info = kmalloc(sizeof(*in_out_info), GFP_KERNEL); + for (cnt = 0; cnt < ARRAY_SIZE(in_out_info->bitmask); cnt++) in_out_info->bitmask[cnt] = 0; - } -#endif + /* Calculate enable bitmasks based on counters_enabled array */ - for (cnt = 0; cnt < NUMBER_OF_HARDWARE_COUNTERS; cnt++) { - const mali_counter *counter = &counters[cnt]; - if (counter->enabled) { + for (cnt = 0; cnt < number_of_hardware_counters; cnt++) { + if (counters[cnt].enabled) { int block = GET_HW_BLOCK(cnt); int enable_bit = GET_COUNTER_OFFSET(cnt) / 4; -#if MALI_DDK_GATOR_API_VERSION == 3 + in_out_info->bitmask[block] |= (1 << enable_bit); -#else - bitmask[block] |= (1 << enable_bit); -#endif - pr_debug("gator: Mali-T6xx: hardware counter %s selected [%d]\n", hardware_counter_names[cnt], cnt); + pr_debug("gator: Mali-Midgard: hardware counter %s selected [%d]\n", hardware_counter_names[cnt], cnt); num_hardware_counters_enabled++; } } -#if MALI_DDK_GATOR_API_VERSION == 3 /* Create a kbase context for HW counters */ if (num_hardware_counters_enabled > 0) { if (init_symbols() > 0) { @@ -591,20 +577,33 @@ static int start(void) return 0; } - handles = mali_dd_hwcnt_init_symbol(in_out_info); + handles = kbase_gator_hwcnt_init_symbol(in_out_info); - if(handles == NULL) { + if (handles == NULL) goto out; - } - - /* See if we can get the number of shader cores */ - shader_present_low = (unsigned long)in_out_info->shader_present_bitmap; kbase_device_busy = false; } return 0; #else + /* Setup HW counters */ + num_hardware_counters_enabled = 0; + + /* Calculate enable bitmasks based on counters_enabled array */ + for (cnt = 0; cnt < number_of_hardware_counters; cnt++) { + const struct mali_counter *counter = &counters[cnt]; + + if (counter->enabled) { + int block = GET_HW_BLOCK(cnt); + int enable_bit = GET_COUNTER_OFFSET(cnt) / 4; + + bitmask[block] |= (1 << enable_bit); + pr_debug("gator: Mali-Midgard: hardware counter %s selected [%d]\n", hardware_counter_names[cnt], cnt); + num_hardware_counters_enabled++; + } + } + /* Create a kbase context for HW counters */ if (num_hardware_counters_enabled > 0) { if (init_symbols() > 0) { @@ -617,18 +616,17 @@ static int start(void) /* If we already got a context, fail */ if (kbcontext) { - pr_debug("gator: Mali-T6xx: error context already present\n"); + pr_debug("gator: Mali-Midgard: error context already present\n"); goto out; } /* kbcontext will only be valid after all the Mali symbols are loaded successfully */ kbcontext = kbase_create_context_symbol(kbdevice); if (!kbcontext) { - pr_debug("gator: Mali-T6xx: error creating kbase context\n"); + pr_debug("gator: Mali-Midgard: error creating kbase context\n"); goto out; } - /* See if we can get the number of shader cores */ shadersPresent = kbdevice->shader_present_bitmap; shader_present_low = (unsigned long)shadersPresent; @@ -639,8 +637,8 @@ static int start(void) * * number of blocks (always 8 for midgard) * * number of counters per block (always 64 for midgard) * * number of bytes per counter (always 4 in midgard) - * For a Mali-T6xx with a single core group = 1 * 8 * 64 * 4 = 2048 - * For a Mali-T6xx with a dual core group = 2 * 8 * 64 * 4 = 4096 + * For a Mali-Midgard with a single core group = 1 * 8 * 64 * 4 = 2048 + * For a Mali-Midgard with a dual core group = 2 * 8 * 64 * 4 = 4096 */ #if MALI_DDK_GATOR_API_VERSION == 1 kernel_dump_buffer = kbase_va_alloc_symbol(kbcontext, 4096); @@ -648,7 +646,7 @@ static int start(void) kernel_dump_buffer = kbase_va_alloc_symbol(kbcontext, 4096, &kernel_dump_buffer_handle); #endif if (!kernel_dump_buffer) { - pr_debug("gator: Mali-T6xx: error trying to allocate va\n"); + pr_debug("gator: Mali-Midgard: error trying to allocate va\n"); goto destroy_context; } @@ -663,12 +661,12 @@ static int start(void) /* Use kbase API to enable hardware counters and provide dump buffer */ err = kbase_instr_hwcnt_enable_symbol(kbcontext, &setup); if (err != MALI_ERROR_NONE) { - pr_debug("gator: Mali-T6xx: can't setup hardware counters\n"); + pr_debug("gator: Mali-Midgard: can't setup hardware counters\n"); goto free_buffer; } - pr_debug("gator: Mali-T6xx: hardware counters enabled\n"); + pr_debug("gator: Mali-Midgard: hardware counters enabled\n"); kbase_instr_hwcnt_clear_symbol(kbcontext); - pr_debug("gator: Mali-T6xx: hardware counters cleared \n"); + pr_debug("gator: Mali-Midgard: hardware counters cleared\n"); kbase_device_busy = false; } @@ -695,17 +693,16 @@ static void stop(void) { unsigned int cnt; #if MALI_DDK_GATOR_API_VERSION == 3 - struct mali_dd_hwcnt_handles *temp_hand; + struct kbase_gator_hwcnt_handles *temp_hand; #else struct kbase_context *temp_kbcontext; #endif - pr_debug("gator: Mali-T6xx: stop\n"); + pr_debug("gator: Mali-Midgard: stop\n"); /* Set all counters as disabled */ - for (cnt = 0; cnt < NUMBER_OF_HARDWARE_COUNTERS; cnt++) { + for (cnt = 0; cnt < number_of_hardware_counters; cnt++) counters[cnt].enabled = 0; - } /* Destroy the context for HW counters */ #if MALI_DDK_GATOR_API_VERSION == 3 @@ -717,7 +714,7 @@ static void stop(void) temp_hand = handles; handles = NULL; - mali_dd_hwcnt_clear_symbol(in_out_info, temp_hand); + kbase_gator_hwcnt_term_symbol(in_out_info, temp_hand); kfree(in_out_info); @@ -741,60 +738,117 @@ static void stop(void) kbase_destroy_context_symbol(temp_kbcontext); #endif - pr_debug("gator: Mali-T6xx: hardware counters stopped\n"); + pr_debug("gator: Mali-Midgard: hardware counters stopped\n"); clean_symbols(); } } -static int read(int **buffer) +static int read_counter(const int cnt, const int len, const struct mali_counter *counter) +{ + const int block = GET_HW_BLOCK(cnt); + const int counter_offset = GET_COUNTER_OFFSET(cnt); + +#if MALI_DDK_GATOR_API_VERSION == 3 + const char *block_base_address = (char *)in_out_info->kernel_dump_buffer; + int i; + int shader_core_count = 0; + u32 value = 0; + + for (i = 0; i < in_out_info->nr_hwc_blocks; i++) { + if (block == in_out_info->hwc_layout[i]) { + value += *((u32 *)(block_base_address + (0x100 * i)) + counter_offset); + if (block == SHADER_BLOCK) + ++shader_core_count; + } + } + + if (shader_core_count > 1) + value /= shader_core_count; +#else + const char *block_base_address = (char *)kernel_dump_buffer + vithar_blocks[block]; + + /* If counter belongs to shader block need to take into account all cores */ + if (block == SHADER_BLOCK) { + int i = 0; + int shader_core_count = 0; + + value = 0; + + for (i = 0; i < 4; i++) { + if ((shader_present_low >> i) & 1) { + value += *((u32 *)(block_base_address + (0x100 * i)) + counter_offset); + shader_core_count++; + } + } + + for (i = 0; i < 4; i++) { + if ((shader_present_low >> (i+4)) & 1) { + value += *((u32 *)(block_base_address + (0x100 * i) + 0x800) + counter_offset); + shader_core_count++; + } + } + + /* Need to total by number of cores to produce an average */ + if (shader_core_count != 0) + value /= shader_core_count; + } else { + value = *((u32 *)block_base_address + counter_offset); + } +#endif + + counter_dump[len + 0] = counter->key; + counter_dump[len + 1] = value; + + return 2; +} + +static int read(int **buffer, bool sched_switch) { int cnt; int len = 0; - u32 value = 0; uint32_t success; struct timespec current_time; - static u32 prev_time_s = 0; - static s32 next_read_time_ns = 0; + static u32 prev_time_s; + static s32 next_read_time_ns; - if (!on_primary_core()) { + if (!on_primary_core() || sched_switch) return 0; - } getnstimeofday(¤t_time); /* - * Discard reads unless a respectable time has passed. This reduces the load on the GPU without sacrificing - * accuracy on the Streamline display. + * Discard reads unless a respectable time has passed. This + * reduces the load on the GPU without sacrificing accuracy on + * the Streamline display. */ - if (!is_read_scheduled(¤t_time, &prev_time_s, &next_read_time_ns)) { + if (!is_read_scheduled(¤t_time, &prev_time_s, &next_read_time_ns)) return 0; - } /* * Report the HW counters * Only process hardware counters if at least one of the hardware counters is enabled. */ if (num_hardware_counters_enabled > 0) { +#if MALI_DDK_GATOR_API_VERSION != 3 const unsigned int vithar_blocks[] = { 0x700, /* VITHAR_JOB_MANAGER, Block 0 */ 0x400, /* VITHAR_TILER, Block 1 */ 0x000, /* VITHAR_SHADER_CORE, Block 2 */ 0x500 /* VITHAR_MEMORY_SYSTEM, Block 3 */ }; +#endif #if MALI_DDK_GATOR_API_VERSION == 3 - if (!handles) { + if (!handles) return -1; - } /* Mali symbols can be called safely since a kbcontext is valid */ - if (kbase_dd_instr_hwcnt_dump_complete_symbol(handles, &success) == MALI_TRUE) { + if (kbase_gator_instr_hwcnt_dump_complete_symbol(handles, &success) == MALI_TRUE) { #else - if (!kbcontext) { + if (!kbcontext) return -1; - } /* Mali symbols can be called safely since a kbcontext is valid */ if (kbase_instr_hwcnt_dump_complete_symbol(kbcontext, &success) == MALI_TRUE) { @@ -803,49 +857,11 @@ static int read(int **buffer) if (success == MALI_TRUE) { /* Cycle through hardware counters and accumulate totals */ - for (cnt = 0; cnt < NUMBER_OF_HARDWARE_COUNTERS; cnt++) { - const mali_counter *counter = &counters[cnt]; - if (counter->enabled) { - const int block = GET_HW_BLOCK(cnt); - const int counter_offset = GET_COUNTER_OFFSET(cnt); - -#if MALI_DDK_GATOR_API_VERSION == 3 - const char* block_base_address = (char*)in_out_info->kernel_dump_buffer + vithar_blocks[block]; -#else - const char* block_base_address = (char*)kernel_dump_buffer + vithar_blocks[block]; -#endif + for (cnt = 0; cnt < number_of_hardware_counters; cnt++) { + const struct mali_counter *counter = &counters[cnt]; - /* If counter belongs to shader block need to take into account all cores */ - if (block == SHADER_BLOCK) { - int i = 0; - int shader_core_count = 0; - value = 0; - - for (i = 0; i < 4; i++) { - if ((shader_present_low >> i) & 1) { - value += *((u32*) (block_base_address + (0x100 * i)) + counter_offset); - shader_core_count++; - } - } - - for (i = 0; i < 4; i++) { - if((shader_present_low >> (i+4)) & 1) { - value += *((u32*)(block_base_address + (0x100 * i) + 0x800) + counter_offset); - shader_core_count++; - } - } - - /* Need to total by number of cores to produce an average */ - if (shader_core_count != 0) { - value /= shader_core_count; - } - } else { - value = *((u32*)block_base_address + counter_offset); - } - - counter_dump[len++] = counter->key; - counter_dump[len++] = value; - } + if (counter->enabled) + len += read_counter(cnt, len, counter); } } } @@ -853,7 +869,7 @@ static int read(int **buffer) if (!kbase_device_busy) { kbase_device_busy = true; #if MALI_DDK_GATOR_API_VERSION == 3 - kbase_dd_instr_hwcnt_dump_irq_symbol(handles); + kbase_gator_instr_hwcnt_dump_irq_symbol(handles); #else kbase_instr_hwcnt_dump_irq_symbol(kbcontext); #endif @@ -861,9 +877,8 @@ static int read(int **buffer) } /* Update the buffer */ - if (buffer) { - *buffer = (int *)counter_dump; - } + if (buffer) + *buffer = counter_dump; return len; } @@ -874,40 +889,89 @@ static int create_files(struct super_block *sb, struct dentry *root) /* * Create the filesystem for all events */ - int counter_index = 0; - for (event = 0; event < ARRAY_SIZE(mali_activity); event++) { - if (gator_mali_create_file_system(mali_name, mali_activity_names[event], sb, root, &mali_activity[event], NULL) != 0) { + if (gator_mali_create_file_system("Midgard", mali_activity_names[event], sb, root, &mali_activity[event], NULL) != 0) return -1; - } } - for (event = 0; event < NUMBER_OF_HARDWARE_COUNTERS; event++) { - if (gator_mali_create_file_system(mali_name, hardware_counter_names[counter_index], sb, root, &counters[event], NULL) != 0) + for (event = 0; event < number_of_hardware_counters; event++) { + if (gator_mali_create_file_system(mali_name, hardware_counter_names[event], sb, root, &counters[event], NULL) != 0) return -1; - counter_index++; } return 0; } -static struct gator_interface gator_events_mali_t6xx_interface = { +static void shutdown(void) +{ +#if MALI_DDK_GATOR_API_VERSION == 3 + void (*kbase_gator_hwcnt_term_names_symbol)(void) = NULL; + int error_count = 0; +#endif + + kfree(counters); + kfree(counter_dump); + +#if MALI_DDK_GATOR_API_VERSION == 3 + SYMBOL_GET(kbase_gator_hwcnt_term_names, error_count); + + number_of_hardware_counters = -1; + hardware_counter_names = NULL; + if (kbase_gator_hwcnt_term_names_symbol != NULL) { + kbase_gator_hwcnt_term_names_symbol(); + pr_err("Released symbols\n"); + } + + SYMBOL_CLEANUP(kbase_gator_hwcnt_term_names); +#endif +} + +static struct gator_interface gator_events_mali_midgard_interface = { + .shutdown = shutdown, .create_files = create_files, .start = start, .stop = stop, .read = read }; -int gator_events_mali_t6xx_hw_init(void) +int gator_events_mali_midgard_hw_init(void) { - pr_debug("gator: Mali-T6xx: sw_counters init\n"); +#if MALI_DDK_GATOR_API_VERSION == 3 + const char *const *(*kbase_gator_hwcnt_init_names_symbol)(uint32_t *) = NULL; + int error_count = 0; +#endif + + pr_debug("gator: Mali-Midgard: sw_counters init\n"); #if GATOR_TEST test_all_is_read_scheduled(); #endif +#if MALI_DDK_GATOR_API_VERSION == 3 + SYMBOL_GET(kbase_gator_hwcnt_init_names, error_count); + if (error_count > 0) { + SYMBOL_CLEANUP(kbase_gator_hwcnt_init_names); + return 1; + } + + number_of_hardware_counters = -1; + hardware_counter_names = kbase_gator_hwcnt_init_names_symbol(&number_of_hardware_counters); + + SYMBOL_CLEANUP(kbase_gator_hwcnt_init_names); + + if ((hardware_counter_names == NULL) || (number_of_hardware_counters <= 0)) { + pr_err("gator: Error reading hardware counters names: got %d names\n", number_of_hardware_counters); + return -1; + } +#else + mali_name = "Midgard"; +#endif + + counters = kmalloc(sizeof(*counters)*number_of_hardware_counters, GFP_KERNEL); + counter_dump = kmalloc(sizeof(*counter_dump)*number_of_hardware_counters*2, GFP_KERNEL); + gator_mali_initialise_counters(mali_activity, ARRAY_SIZE(mali_activity)); - gator_mali_initialise_counters(counters, NUMBER_OF_HARDWARE_COUNTERS); + gator_mali_initialise_counters(counters, number_of_hardware_counters); - return gator_events_install(&gator_events_mali_t6xx_interface); + return gator_events_install(&gator_events_mali_midgard_interface); } diff --git a/drivers/gator/gator_events_mali_t6xx_hw_test.c b/drivers/gator/gator_events_mali_midgard_hw_test.c index ba6553f3540f..31a91e1c72b2 100644 --- a/drivers/gator/gator_events_mali_t6xx_hw_test.c +++ b/drivers/gator/gator_events_mali_midgard_hw_test.c @@ -23,12 +23,12 @@ static int test_is_read_scheduled(u32 s, u32 ns, u32 prev_s, s32 next_ns, int ex current_time.tv_nsec = ns; if (is_read_scheduled(¤t_time, &prev_time_s, &next_read_time_ns) != expected_result) { - printk("Failed do_read(%u, %u, %u, %d): expected %d\n", s, ns, prev_s, next_ns, expected_result); + pr_err("Failed do_read(%u, %u, %u, %d): expected %d\n", s, ns, prev_s, next_ns, expected_result); return 0; } if (next_read_time_ns != expected_next_ns) { - printk("Failed: next_read_ns expected=%d, actual=%d\n", expected_next_ns, next_read_time_ns); + pr_err("Failed: next_read_ns expected=%d, actual=%d\n", expected_next_ns, next_read_time_ns); return 0; } @@ -40,7 +40,7 @@ static void test_all_is_read_scheduled(void) const int HIGHEST_NS = 999999999; int n_tests_passed = 0; - printk("gator: running tests on %s\n", __FILE__); + pr_err("gator: running tests on %s\n", __FILE__); n_tests_passed += test_is_read_scheduled(0, 0, 0, 0, 1, READ_INTERVAL_NSEC); /* Null time */ n_tests_passed += test_is_read_scheduled(100, 1000, 0, 0, 1, READ_INTERVAL_NSEC + 1000); /* Initial values */ @@ -51,5 +51,5 @@ static void test_all_is_read_scheduled(void) n_tests_passed += test_is_read_scheduled(101, 600, 100, HIGHEST_NS + 500, 1, 600 + READ_INTERVAL_NSEC); - printk("gator: %d tests passed\n", n_tests_passed); + pr_err("gator: %d tests passed\n", n_tests_passed); } diff --git a/drivers/gator/gator_events_meminfo.c b/drivers/gator/gator_events_meminfo.c index c633dfdce306..c625ac5af9cd 100644 --- a/drivers/gator/gator_events_meminfo.c +++ b/drivers/gator/gator_events_meminfo.c @@ -16,6 +16,8 @@ #include <linux/workqueue.h> #include <trace/events/kmem.h> +#define USE_THREAD defined(CONFIG_PREEMPT_RT_FULL) + enum { MEMINFO_MEMFREE, MEMINFO_MEMUSED, @@ -48,7 +50,7 @@ static bool meminfo_global_enabled; static ulong meminfo_enabled[MEMINFO_TOTAL]; static ulong meminfo_keys[MEMINFO_TOTAL]; static long long meminfo_buffer[2 * (MEMINFO_TOTAL + 2)]; -static int meminfo_length = 0; +static int meminfo_length; static bool new_data_avail; static bool proc_global_enabled; @@ -56,22 +58,44 @@ static ulong proc_enabled[PROC_COUNT]; static ulong proc_keys[PROC_COUNT]; static DEFINE_PER_CPU(long long, proc_buffer[2 * (PROC_COUNT + 3)]); +#if USE_THREAD + static int gator_meminfo_func(void *data); static bool gator_meminfo_run; -// Initialize semaphore unlocked to initialize memory values +/* Initialize semaphore unlocked to initialize memory values */ #if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36) static DECLARE_MUTEX(gator_meminfo_sem); #else static DEFINE_SEMAPHORE(gator_meminfo_sem); #endif +static void notify(void) +{ + up(&gator_meminfo_sem); +} + +#else + +static unsigned int mem_event; +static void wq_sched_handler(struct work_struct *wsptr); +DECLARE_WORK(work, wq_sched_handler); +static struct timer_list meminfo_wake_up_timer; +static void meminfo_wake_up_handler(unsigned long unused_data); + +static void notify(void) +{ + mem_event++; +} + +#endif + #if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0) GATOR_DEFINE_PROBE(mm_page_free_direct, TP_PROTO(struct page *page, unsigned int order)) #else GATOR_DEFINE_PROBE(mm_page_free, TP_PROTO(struct page *page, unsigned int order)) #endif { - up(&gator_meminfo_sem); + notify(); } #if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0) @@ -80,12 +104,12 @@ GATOR_DEFINE_PROBE(mm_pagevec_free, TP_PROTO(struct page *page, int cold)) GATOR_DEFINE_PROBE(mm_page_free_batched, TP_PROTO(struct page *page, int cold)) #endif { - up(&gator_meminfo_sem); + notify(); } GATOR_DEFINE_PROBE(mm_page_alloc, TP_PROTO(struct page *page, unsigned int order, gfp_t gfp_flags, int migratetype)) { - up(&gator_meminfo_sem); + notify(); } static int gator_events_meminfo_create_files(struct super_block *sb, struct dentry *root) @@ -95,18 +119,16 @@ static int gator_events_meminfo_create_files(struct super_block *sb, struct dent for (i = 0; i < MEMINFO_TOTAL; i++) { dir = gatorfs_mkdir(sb, root, meminfo_names[i]); - if (!dir) { + if (!dir) return -1; - } gatorfs_create_ulong(sb, dir, "enabled", &meminfo_enabled[i]); gatorfs_create_ro_ulong(sb, dir, "key", &meminfo_keys[i]); } for (i = 0; i < PROC_COUNT; ++i) { dir = gatorfs_mkdir(sb, root, proc_names[i]); - if (!dir) { + if (!dir) return -1; - } gatorfs_create_ulong(sb, dir, "enabled", &proc_enabled[i]); gatorfs_create_ro_ulong(sb, dir, "key", &proc_keys[i]); } @@ -134,9 +156,8 @@ static int gator_events_meminfo_start(void) break; } } - if (meminfo_enabled[MEMINFO_MEMUSED]) { + if (meminfo_enabled[MEMINFO_MEMUSED]) proc_global_enabled = 1; - } if (meminfo_global_enabled == 0) return 0; @@ -156,16 +177,22 @@ static int gator_events_meminfo_start(void) if (GATOR_REGISTER_TRACE(mm_page_alloc)) goto mm_page_alloc_exit; - // Start worker thread +#if USE_THREAD + /* Start worker thread */ gator_meminfo_run = true; - // Since the mutex starts unlocked, memory values will be initialized + /* Since the mutex starts unlocked, memory values will be initialized */ if (IS_ERR(kthread_run(gator_meminfo_func, NULL, "gator_meminfo"))) goto kthread_run_exit; +#else + setup_timer(&meminfo_wake_up_timer, meminfo_wake_up_handler, 0); +#endif return 0; +#if USE_THREAD kthread_run_exit: GATOR_UNREGISTER_TRACE(mm_page_alloc); +#endif mm_page_alloc_exit: #if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0) GATOR_UNREGISTER_TRACE(mm_pagevec_free); @@ -194,75 +221,111 @@ static void gator_events_meminfo_stop(void) #endif GATOR_UNREGISTER_TRACE(mm_page_alloc); - // Stop worker thread +#if USE_THREAD + /* Stop worker thread */ gator_meminfo_run = false; up(&gator_meminfo_sem); +#else + del_timer_sync(&meminfo_wake_up_timer); +#endif } } -// Must be run in process context as the kernel function si_meminfo() can sleep -static int gator_meminfo_func(void *data) +static void do_read(void) { struct sysinfo info; int i, len; unsigned long long value; - for (;;) { - if (down_killable(&gator_meminfo_sem)) { - break; + meminfo_length = len = 0; + + si_meminfo(&info); + for (i = 0; i < MEMINFO_TOTAL; i++) { + if (meminfo_enabled[i]) { + switch (i) { + case MEMINFO_MEMFREE: + value = info.freeram * PAGE_SIZE; + break; + case MEMINFO_MEMUSED: + /* pid -1 means system wide */ + meminfo_buffer[len++] = 1; + meminfo_buffer[len++] = -1; + /* Emit value */ + meminfo_buffer[len++] = meminfo_keys[MEMINFO_MEMUSED]; + meminfo_buffer[len++] = (info.totalram - info.freeram) * PAGE_SIZE; + /* Clear pid */ + meminfo_buffer[len++] = 1; + meminfo_buffer[len++] = 0; + continue; + case MEMINFO_BUFFERRAM: + value = info.bufferram * PAGE_SIZE; + break; + default: + value = 0; + break; + } + meminfo_buffer[len++] = meminfo_keys[i]; + meminfo_buffer[len++] = value; } + } - // Eat up any pending events - while (!down_trylock(&gator_meminfo_sem)); + meminfo_length = len; + new_data_avail = true; +} - if (!gator_meminfo_run) { +#if USE_THREAD + +static int gator_meminfo_func(void *data) +{ + for (;;) { + if (down_killable(&gator_meminfo_sem)) break; - } - meminfo_length = len = 0; - - si_meminfo(&info); - for (i = 0; i < MEMINFO_TOTAL; i++) { - if (meminfo_enabled[i]) { - switch (i) { - case MEMINFO_MEMFREE: - value = info.freeram * PAGE_SIZE; - break; - case MEMINFO_MEMUSED: - // pid -1 means system wide - meminfo_buffer[len++] = 1; - meminfo_buffer[len++] = -1; - // Emit value - meminfo_buffer[len++] = meminfo_keys[MEMINFO_MEMUSED]; - meminfo_buffer[len++] = (info.totalram - info.freeram) * PAGE_SIZE; - // Clear pid - meminfo_buffer[len++] = 1; - meminfo_buffer[len++] = 0; - continue; - case MEMINFO_BUFFERRAM: - value = info.bufferram * PAGE_SIZE; - break; - default: - value = 0; - break; - } - meminfo_buffer[len++] = meminfo_keys[i]; - meminfo_buffer[len++] = value; - } - } + /* Eat up any pending events */ + while (!down_trylock(&gator_meminfo_sem)) + ; + + if (!gator_meminfo_run) + break; - meminfo_length = len; - new_data_avail = true; + do_read(); } return 0; } +#else + +/* Must be run in process context as the kernel function si_meminfo() can sleep */ +static void wq_sched_handler(struct work_struct *wsptr) +{ + do_read(); +} + +static void meminfo_wake_up_handler(unsigned long unused_data) +{ + /* had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater */ + schedule_work(&work); +} + +#endif + static int gator_events_meminfo_read(long long **buffer) { +#if !USE_THREAD + static unsigned int last_mem_event; +#endif + if (!on_primary_core() || !meminfo_global_enabled) return 0; +#if !USE_THREAD + if (last_mem_event != mem_event) { + last_mem_event = mem_event; + mod_timer(&meminfo_wake_up_timer, jiffies + 1); + } +#endif + if (!new_data_avail) return 0; @@ -280,6 +343,7 @@ static inline unsigned long gator_get_mm_counter(struct mm_struct *mm, int membe { #ifdef SPLIT_RSS_COUNTING long val = atomic_long_read(&mm->rss_stat.count[member]); + if (val < 0) val = 0; return (unsigned long)val; @@ -306,22 +370,19 @@ static int gator_events_meminfo_read_proc(long long **buffer, struct task_struct int cpu = get_physical_cpu(); long long *buf = per_cpu(proc_buffer, cpu); - if (!proc_global_enabled) { + if (!proc_global_enabled) return 0; - } - // Collect the memory stats of the process instead of the thread - if (task->group_leader != NULL) { + /* Collect the memory stats of the process instead of the thread */ + if (task->group_leader != NULL) task = task->group_leader; - } - // get_task_mm/mmput is not needed in this context because the task and it's mm are required as part of the sched_switch + /* get_task_mm/mmput is not needed in this context because the task and it's mm are required as part of the sched_switch */ mm = task->mm; - if (mm == NULL) { + if (mm == NULL) return 0; - } - // Derived from task_statm in fs/proc/task_mmu.c + /* Derived from task_statm in fs/proc/task_mmu.c */ if (meminfo_enabled[MEMINFO_MEMUSED] || proc_enabled[PROC_SHARE]) { share = get_mm_counter(mm, #if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 32) && LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 34) @@ -332,7 +393,7 @@ static int gator_events_meminfo_read_proc(long long **buffer, struct task_struct ); } - // key of 1 indicates a pid + /* key of 1 indicates a pid */ buf[len++] = 1; buf[len++] = task->pid; @@ -366,12 +427,12 @@ static int gator_events_meminfo_read_proc(long long **buffer, struct task_struct MM_ANONPAGES #endif ); - // Send resident for this pid + /* Send resident for this pid */ buf[len++] = meminfo_keys[MEMINFO_MEMUSED]; buf[len++] = value * PAGE_SIZE; } - // Clear pid + /* Clear pid */ buf[len++] = 1; buf[len++] = 0; diff --git a/drivers/gator/gator_events_mmapped.c b/drivers/gator/gator_events_mmapped.c index 5bc01c42c3a2..6b2af995ed41 100644 --- a/drivers/gator/gator_events_mmapped.c +++ b/drivers/gator/gator_events_mmapped.c @@ -103,7 +103,7 @@ static int mmapped_simulate(int counter, int delta_in_us) switch (counter) { case 0: /* sort-of-sine */ { - static int t = 0; + static int t; int x; t += delta_in_us; @@ -140,7 +140,7 @@ static int mmapped_simulate(int counter, int delta_in_us) break; case 2: /* PWM signal */ { - static int dc, x, t = 0; + static int dc, x, t; t += delta_in_us; if (t > 1000000) @@ -157,7 +157,7 @@ static int mmapped_simulate(int counter, int delta_in_us) return result; } -static int gator_events_mmapped_read(int **buffer) +static int gator_events_mmapped_read(int **buffer, bool sched_switch) { int i; int len = 0; diff --git a/drivers/gator/gator_events_net.c b/drivers/gator/gator_events_net.c index 11c10e375511..d21b4db7b77c 100644 --- a/drivers/gator/gator_events_net.c +++ b/drivers/gator/gator_events_net.c @@ -25,7 +25,7 @@ static int netGet[TOTALNET * 4]; static struct timer_list net_wake_up_timer; -// Must be run in process context as the kernel function dev_get_stats() can sleep +/* Must be run in process context as the kernel function dev_get_stats() can sleep */ static void get_network_stats(struct work_struct *wsptr) { int rx = 0, tx = 0; @@ -49,7 +49,7 @@ DECLARE_WORK(wq_get_stats, get_network_stats); static void net_wake_up_handler(unsigned long unused_data) { - // had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater + /* had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater */ schedule_work(&wq_get_stats); } @@ -73,21 +73,19 @@ static void calculate_delta(int *rx, int *tx) static int gator_events_net_create_files(struct super_block *sb, struct dentry *root) { - // Network counters are not currently supported in RT-Preempt full because mod_timer is used + /* Network counters are not currently supported in RT-Preempt full because mod_timer is used */ #ifndef CONFIG_PREEMPT_RT_FULL struct dentry *dir; dir = gatorfs_mkdir(sb, root, "Linux_net_rx"); - if (!dir) { + if (!dir) return -1; - } gatorfs_create_ulong(sb, dir, "enabled", &netrx_enabled); gatorfs_create_ro_ulong(sb, dir, "key", &netrx_key); dir = gatorfs_mkdir(sb, root, "Linux_net_tx"); - if (!dir) { + if (!dir) return -1; - } gatorfs_create_ulong(sb, dir, "enabled", &nettx_enabled); gatorfs_create_ro_ulong(sb, dir, "key", &nettx_key); #endif @@ -115,10 +113,10 @@ static void gator_events_net_stop(void) nettx_enabled = 0; } -static int gator_events_net_read(int **buffer) +static int gator_events_net_read(int **buffer, bool sched_switch) { int len, rx_delta, tx_delta; - static int last_rx_delta = 0, last_tx_delta = 0; + static int last_rx_delta, last_tx_delta; if (!on_primary_core()) return 0; @@ -134,7 +132,8 @@ static int gator_events_net_read(int **buffer) if (netrx_enabled && last_rx_delta != rx_delta) { last_rx_delta = rx_delta; netGet[len++] = netrx_key; - netGet[len++] = 0; // indicates to Streamline that rx_delta bytes were transmitted now, not since the last message + /* indicates to Streamline that rx_delta bytes were transmitted now, not since the last message */ + netGet[len++] = 0; netGet[len++] = netrx_key; netGet[len++] = rx_delta; } @@ -142,7 +141,8 @@ static int gator_events_net_read(int **buffer) if (nettx_enabled && last_tx_delta != tx_delta) { last_tx_delta = tx_delta; netGet[len++] = nettx_key; - netGet[len++] = 0; // indicates to Streamline that tx_delta bytes were transmitted now, not since the last message + /* indicates to Streamline that tx_delta bytes were transmitted now, not since the last message */ + netGet[len++] = 0; netGet[len++] = nettx_key; netGet[len++] = tx_delta; } diff --git a/drivers/gator/gator_events_perf_pmu.c b/drivers/gator/gator_events_perf_pmu.c index 06bbad5b10c3..47cf278e508b 100644 --- a/drivers/gator/gator_events_perf_pmu.c +++ b/drivers/gator/gator_events_perf_pmu.c @@ -8,7 +8,7 @@ #include "gator.h" -// gator_events_armvX.c is used for Linux 2.6.x +/* gator_events_armvX.c is used for Linux 2.6.x */ #if GATOR_PERF_PMU_SUPPORT #include <linux/io.h> @@ -20,39 +20,41 @@ extern bool event_based_sampling; -// Maximum number of per-core counters - currently reserves enough space for two full hardware PMUs for big.LITTLE +/* Maximum number of per-core counters - currently reserves enough space for two full hardware PMUs for big.LITTLE */ #define CNTMAX 16 #define CCI_400 4 -// Maximum number of uncore counters -// + 1 for the cci-400 cycles counter -#define UCCNT (CCI_400 + 1) +#define CCN_5XX 8 +/* Maximum number of uncore counters */ +/* + 1 for the cci-400 cycles counter */ +/* + 1 for the CCN-5xx cycles counter */ +#define UCCNT (CCI_400 + 1 + CCN_5XX + 1) -// Default to 0 if unable to probe the revision which was the previous behavior +/* Default to 0 if unable to probe the revision which was the previous behavior */ #define DEFAULT_CCI_REVISION 0 -// A gator_attr is needed for every counter +/* A gator_attr is needed for every counter */ struct gator_attr { - // Set once in gator_events_perf_pmu_*_init - the name of the event in the gatorfs + /* Set once in gator_events_perf_pmu_*_init - the name of the event in the gatorfs */ char name[40]; - // Exposed in gatorfs - set by gatord to enable this counter + /* Exposed in gatorfs - set by gatord to enable this counter */ unsigned long enabled; - // Set once in gator_events_perf_pmu_*_init - the perf type to use, see perf_type_id in the perf_event.h header file. + /* Set once in gator_events_perf_pmu_*_init - the perf type to use, see perf_type_id in the perf_event.h header file. */ unsigned long type; - // Exposed in gatorfs - set by gatord to select the event to collect + /* Exposed in gatorfs - set by gatord to select the event to collect */ unsigned long event; - // Exposed in gatorfs - set by gatord with the sample period to use and enable EBS for this counter + /* Exposed in gatorfs - set by gatord with the sample period to use and enable EBS for this counter */ unsigned long count; - // Exposed as read only in gatorfs - set once in __attr_init as the key to use in the APC data + /* Exposed as read only in gatorfs - set once in __attr_init as the key to use in the APC data */ unsigned long key; }; -// Per-core counter attributes +/* Per-core counter attributes */ static struct gator_attr attrs[CNTMAX]; -// Number of initialized per-core counters +/* Number of initialized per-core counters */ static int attr_count; -// Uncore counter attributes +/* Uncore counter attributes */ static struct gator_attr uc_attrs[UCCNT]; -// Number of initialized uncore counters +/* Number of initialized uncore counters */ static int uc_attr_count; struct gator_event { @@ -74,13 +76,11 @@ static int __create_files(struct super_block *sb, struct dentry *root, struct ga { struct dentry *dir; - if (attr->name[0] == '\0') { + if (attr->name[0] == '\0') return 0; - } dir = gatorfs_mkdir(sb, root, attr->name); - if (!dir) { + if (!dir) return -1; - } gatorfs_create_ulong(sb, dir, "enabled", &attr->enabled); gatorfs_create_ulong(sb, dir, "count", &attr->count); gatorfs_create_ro_ulong(sb, dir, "key", &attr->key); @@ -94,15 +94,13 @@ static int gator_events_perf_pmu_create_files(struct super_block *sb, struct den int cnt; for (cnt = 0; cnt < attr_count; cnt++) { - if (__create_files(sb, root, &attrs[cnt]) != 0) { + if (__create_files(sb, root, &attrs[cnt]) != 0) return -1; - } } for (cnt = 0; cnt < uc_attr_count; cnt++) { - if (__create_files(sb, root, &uc_attrs[cnt]) != 0) { + if (__create_files(sb, root, &uc_attrs[cnt]) != 0) return -1; - } } return 0; @@ -123,14 +121,14 @@ static void dummy_handler(struct perf_event *event, int unused, struct perf_samp static void dummy_handler(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs) #endif { -// Required as perf_event_create_kernel_counter() requires an overflow handler, even though all we do is poll + /* Required as perf_event_create_kernel_counter() requires an overflow handler, even though all we do is poll */ } -static int gator_events_perf_pmu_read(int **buffer); +static int gator_events_perf_pmu_read(int **buffer, bool sched_switch); static int gator_events_perf_pmu_online(int **buffer, bool migrate) { - return gator_events_perf_pmu_read(buffer); + return gator_events_perf_pmu_read(buffer, false); } static void __online_dispatch(int cpu, bool migrate, struct gator_attr *const attr, struct gator_event *const event) @@ -139,15 +137,13 @@ static void __online_dispatch(int cpu, bool migrate, struct gator_attr *const at event->zero = true; - if (event->pevent != NULL || event->pevent_attr == 0 || migrate) { + if (event->pevent != NULL || event->pevent_attr == 0 || migrate) return; - } - if (attr->count > 0) { + if (attr->count > 0) handler = ebs_overflow_handler; - } else { + else handler = dummy_handler; - } #if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0) event->pevent = perf_event_create_kernel_counter(event->pevent_attr, cpu, 0, handler); @@ -174,14 +170,12 @@ static void gator_events_perf_pmu_online_dispatch(int cpu, bool migrate) cpu = pcpu_to_lcpu(cpu); - for (cnt = 0; cnt < attr_count; cnt++) { + for (cnt = 0; cnt < attr_count; cnt++) __online_dispatch(cpu, migrate, &attrs[cnt], &per_cpu(events, cpu)[cnt]); - } if (cpu == 0) { - for (cnt = 0; cnt < uc_attr_count; cnt++) { + for (cnt = 0; cnt < uc_attr_count; cnt++) __online_dispatch(cpu, migrate, &uc_attrs[cnt], &uc_events[cnt]); - } } } @@ -194,28 +188,24 @@ static void __offline_dispatch(int cpu, struct gator_event *const event) event->pevent = NULL; } - if (pe) { + if (pe) perf_event_release_kernel(pe); - } } static void gator_events_perf_pmu_offline_dispatch(int cpu, bool migrate) { int cnt; - if (migrate) { + if (migrate) return; - } cpu = pcpu_to_lcpu(cpu); - for (cnt = 0; cnt < attr_count; cnt++) { + for (cnt = 0; cnt < attr_count; cnt++) __offline_dispatch(cpu, &per_cpu(events, cpu)[cnt]); - } if (cpu == 0) { - for (cnt = 0; cnt < uc_attr_count; cnt++) { + for (cnt = 0; cnt < uc_attr_count; cnt++) __offline_dispatch(cpu, &uc_events[cnt]); - } } } @@ -225,7 +215,7 @@ static int __check_ebs(struct gator_attr *const attr) if (!event_based_sampling) { event_based_sampling = true; } else { - printk(KERN_WARNING "gator: Only one ebs counter is allowed\n"); + pr_warning("gator: Only one ebs counter is allowed\n"); return -1; } } @@ -238,9 +228,9 @@ static int __start(struct gator_attr *const attr, struct gator_event *const even u32 size = sizeof(struct perf_event_attr); event->pevent = NULL; - if (!attr->enabled) { // Skip disabled counters + /* Skip disabled counters */ + if (!attr->enabled) return 0; - } event->prev = 0; event->curr = 0; @@ -267,29 +257,25 @@ static int gator_events_perf_pmu_start(void) event_based_sampling = false; for (cnt = 0; cnt < attr_count; cnt++) { - if (__check_ebs(&attrs[cnt]) != 0) { + if (__check_ebs(&attrs[cnt]) != 0) return -1; - } } for (cnt = 0; cnt < uc_attr_count; cnt++) { - if (__check_ebs(&uc_attrs[cnt]) != 0) { + if (__check_ebs(&uc_attrs[cnt]) != 0) return -1; - } } for_each_present_cpu(cpu) { for (cnt = 0; cnt < attr_count; cnt++) { - if (__start(&attrs[cnt], &per_cpu(events, cpu)[cnt]) != 0) { + if (__start(&attrs[cnt], &per_cpu(events, cpu)[cnt]) != 0) return -1; - } } } for (cnt = 0; cnt < uc_attr_count; cnt++) { - if (__start(&uc_attrs[cnt], &uc_events[cnt]) != 0) { + if (__start(&uc_attrs[cnt], &uc_events[cnt]) != 0) return -1; - } } return 0; @@ -297,10 +283,8 @@ static int gator_events_perf_pmu_start(void) static void __event_stop(struct gator_event *const event) { - if (event->pevent_attr) { - kfree(event->pevent_attr); - event->pevent_attr = NULL; - } + kfree(event->pevent_attr); + event->pevent_attr = NULL; } static void __attr_stop(struct gator_attr *const attr) @@ -315,29 +299,25 @@ static void gator_events_perf_pmu_stop(void) unsigned int cnt, cpu; for_each_present_cpu(cpu) { - for (cnt = 0; cnt < attr_count; cnt++) { + for (cnt = 0; cnt < attr_count; cnt++) __event_stop(&per_cpu(events, cpu)[cnt]); - } } - for (cnt = 0; cnt < uc_attr_count; cnt++) { + for (cnt = 0; cnt < uc_attr_count; cnt++) __event_stop(&uc_events[cnt]); - } - for (cnt = 0; cnt < attr_count; cnt++) { + for (cnt = 0; cnt < attr_count; cnt++) __attr_stop(&attrs[cnt]); - } - for (cnt = 0; cnt < uc_attr_count; cnt++) { + for (cnt = 0; cnt < uc_attr_count; cnt++) __attr_stop(&uc_attrs[cnt]); - } } static void __read(int *const len, int cpu, struct gator_attr *const attr, struct gator_event *const event) { int delta; - struct perf_event *const ev = event->pevent; + if (ev != NULL && ev->state == PERF_EVENT_STATE_ACTIVE) { /* After creating the perf counter in __online_dispatch, there * is a race condition between gator_events_perf_pmu_online and @@ -361,33 +341,29 @@ static void __read(int *const len, int cpu, struct gator_attr *const attr, struc event->prev_delta = delta; event->prev = event->curr; per_cpu(perf_cnt, cpu)[(*len)++] = attr->key; - if (delta < 0) { + if (delta < 0) delta *= -1; - } per_cpu(perf_cnt, cpu)[(*len)++] = delta; } } } } -static int gator_events_perf_pmu_read(int **buffer) +static int gator_events_perf_pmu_read(int **buffer, bool sched_switch) { int cnt, len = 0; const int cpu = get_logical_cpu(); - for (cnt = 0; cnt < attr_count; cnt++) { + for (cnt = 0; cnt < attr_count; cnt++) __read(&len, cpu, &attrs[cnt], &per_cpu(events, cpu)[cnt]); - } if (cpu == 0) { - for (cnt = 0; cnt < uc_attr_count; cnt++) { + for (cnt = 0; cnt < uc_attr_count; cnt++) __read(&len, cpu, &uc_attrs[cnt], &uc_events[cnt]); - } } - if (buffer) { + if (buffer) *buffer = per_cpu(perf_cnt, cpu); - } return len; } @@ -428,23 +404,20 @@ static int probe_cci_revision(void) int ret = DEFAULT_CCI_REVISION; np = of_find_matching_node(NULL, arm_cci_matches); - if (!np) { + if (!np) return ret; - } - if (of_address_to_resource(np, 0, &res)) { + if (of_address_to_resource(np, 0, &res)) goto node_put; - } cci_ctrl_base = ioremap(res.start, resource_size(&res)); rev = (readl_relaxed(cci_ctrl_base + 0xfe8) >> 4) & 0xf; - if (rev <= 4) { + if (rev <= 4) ret = 0; - } else if (rev <= 6) { + else if (rev <= 6) ret = 1; - } iounmap(cci_ctrl_base); @@ -463,9 +436,24 @@ static int probe_cci_revision(void) #endif -static void gator_events_perf_pmu_cci_init(const int type) +static void gator_events_perf_pmu_uncore_init(const char *const name, const int type, const int count) { int cnt; + + snprintf(uc_attrs[uc_attr_count].name, sizeof(uc_attrs[uc_attr_count].name), "%s_ccnt", name); + uc_attrs[uc_attr_count].type = type; + ++uc_attr_count; + + for (cnt = 0; cnt < count; ++cnt, ++uc_attr_count) { + struct gator_attr *const attr = &uc_attrs[uc_attr_count]; + + snprintf(attr->name, sizeof(attr->name), "%s_cnt%d", name, cnt); + attr->type = type; + } +} + +static void gator_events_perf_pmu_cci_init(const int type) +{ const char *cci_name; switch (probe_cci_revision()) { @@ -480,15 +468,7 @@ static void gator_events_perf_pmu_cci_init(const int type) return; } - snprintf(uc_attrs[uc_attr_count].name, sizeof(uc_attrs[uc_attr_count].name), "%s_ccnt", cci_name); - uc_attrs[uc_attr_count].type = type; - ++uc_attr_count; - - for (cnt = 0; cnt < CCI_400; ++cnt, ++uc_attr_count) { - struct gator_attr *const attr = &uc_attrs[uc_attr_count]; - snprintf(attr->name, sizeof(attr->name), "%s_cnt%d", cci_name, cnt); - attr->type = type; - } + gator_events_perf_pmu_uncore_init(cci_name, type, CCI_400); } static void gator_events_perf_pmu_cpu_init(const struct gator_cpu *const gator_cpu, const int type) @@ -501,6 +481,7 @@ static void gator_events_perf_pmu_cpu_init(const struct gator_cpu *const gator_c for (cnt = 0; cnt < gator_cpu->pmnc_counters; ++cnt, ++attr_count) { struct gator_attr *const attr = &attrs[attr_count]; + snprintf(attr->name, sizeof(attr->name), "%s_cnt%d", gator_cpu->pmnc_name, cnt); attr->type = type; } @@ -516,12 +497,10 @@ int gator_events_perf_pmu_init(void) int cnt; bool found_cpu = false; - for (cnt = 0; cnt < CNTMAX; cnt++) { + for (cnt = 0; cnt < CNTMAX; cnt++) __attr_init(&attrs[cnt]); - } - for (cnt = 0; cnt < UCCNT; cnt++) { + for (cnt = 0; cnt < UCCNT; cnt++) __attr_init(&uc_attrs[cnt]); - } memset(&pea, 0, sizeof(pea)); pea.size = sizeof(pea); @@ -531,7 +510,7 @@ int gator_events_perf_pmu_init(void) for (type = PERF_TYPE_MAX; type < 0x20; ++type) { pea.type = type; - // A particular PMU may work on some but not all cores, so try on each core + /* A particular PMU may work on some but not all cores, so try on each core */ pe = NULL; for_each_present_cpu(cpu) { #if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0) @@ -539,23 +518,31 @@ int gator_events_perf_pmu_init(void) #else pe = perf_event_create_kernel_counter(&pea, cpu, 0, dummy_handler, 0); #endif - if (!IS_ERR(pe)) { + if (!IS_ERR(pe)) break; - } } - // Assume that valid PMUs are contiguous + /* Assume that valid PMUs are contiguous */ if (IS_ERR(pe)) { - break; + pea.config = 0xff00; +#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0) + pe = perf_event_create_kernel_counter(&pea, 0, 0, dummy_handler); +#else + pe = perf_event_create_kernel_counter(&pea, 0, 0, dummy_handler, 0); +#endif + if (IS_ERR(pe)) + break; } if (pe->pmu != NULL && type == pe->pmu->type) { if (strcmp("CCI", pe->pmu->name) == 0 || strcmp("CCI_400", pe->pmu->name) == 0 || strcmp("CCI_400-r1", pe->pmu->name) == 0) { gator_events_perf_pmu_cci_init(type); + } else if (strcmp("ccn", pe->pmu->name) == 0) { + gator_events_perf_pmu_uncore_init("ARM_CCN_5XX", type, CCN_5XX); } else if ((gator_cpu = gator_find_cpu_by_pmu_name(pe->pmu->name)) != NULL) { found_cpu = true; gator_events_perf_pmu_cpu_init(gator_cpu, type); } - // Initialize gator_attrs for dynamic PMUs here + /* Initialize gator_attrs for dynamic PMUs here */ } perf_event_release_kernel(pe); @@ -563,21 +550,21 @@ int gator_events_perf_pmu_init(void) if (!found_cpu) { const struct gator_cpu *const gator_cpu = gator_find_cpu_by_cpuid(gator_cpuid()); - if (gator_cpu == NULL) { + + if (gator_cpu == NULL) return -1; - } gator_events_perf_pmu_cpu_init(gator_cpu, PERF_TYPE_RAW); } - // Initialize gator_attrs for non-dynamic PMUs here + /* Initialize gator_attrs for non-dynamic PMUs here */ if (attr_count > CNTMAX) { - printk(KERN_ERR "gator: Too many perf counters\n"); + pr_err("gator: Too many perf counters\n"); return -1; } if (uc_attr_count > UCCNT) { - printk(KERN_ERR "gator: Too many perf uncore counters\n"); + pr_err("gator: Too many perf uncore counters\n"); return -1; } diff --git a/drivers/gator/gator_events_sched.c b/drivers/gator/gator_events_sched.c index 9e3915830182..637107d6af1d 100644 --- a/drivers/gator/gator_events_sched.c +++ b/drivers/gator/gator_events_sched.c @@ -26,8 +26,9 @@ GATOR_DEFINE_PROBE(sched_switch, TP_PROTO(struct task_struct *prev, struct task_ { unsigned long flags; - // disable interrupts to synchronize with gator_events_sched_read() - // spinlocks not needed since percpu buffers are used + /* disable interrupts to synchronize with gator_events_sched_read() + * spinlocks not needed since percpu buffers are used + */ local_irq_save(flags); per_cpu(schedCnt, get_physical_cpu())[SCHED_SWITCH]++; local_irq_restore(flags); @@ -39,9 +40,8 @@ static int gator_events_sched_create_files(struct super_block *sb, struct dentry /* switch */ dir = gatorfs_mkdir(sb, root, "Linux_sched_switch"); - if (!dir) { + if (!dir) return -1; - } gatorfs_create_ulong(sb, dir, "enabled", &sched_switch_enabled); gatorfs_create_ro_ulong(sb, dir, "key", &sched_switch_key); @@ -50,7 +50,7 @@ static int gator_events_sched_create_files(struct super_block *sb, struct dentry static int gator_events_sched_start(void) { - // register tracepoints + /* register tracepoints */ if (sched_switch_enabled) if (GATOR_REGISTER_TRACE(sched_switch)) goto sched_switch_exit; @@ -58,7 +58,7 @@ static int gator_events_sched_start(void) return 0; - // unregister tracepoints on error + /* unregister tracepoints on error */ sched_switch_exit: pr_err("gator: scheduler event tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n"); @@ -74,7 +74,7 @@ static void gator_events_sched_stop(void) sched_switch_enabled = 0; } -static int gator_events_sched_read(int **buffer) +static int gator_events_sched_read(int **buffer, bool sched_switch) { unsigned long flags; int len, value; diff --git a/drivers/gator/gator_events_scorpion.c b/drivers/gator/gator_events_scorpion.c index 2e5be8d50e9d..49219362db09 100644 --- a/drivers/gator/gator_events_scorpion.c +++ b/drivers/gator/gator_events_scorpion.c @@ -8,13 +8,13 @@ #include "gator.h" -// gator_events_perf_pmu.c is used if perf is supported +/* gator_events_perf_pmu.c is used if perf is supported */ #if GATOR_NO_PERF_SUPPORT static const char *pmnc_name; static int pmnc_counters; -// Per-CPU PMNC: config reg +/* Per-CPU PMNC: config reg */ #define PMNC_E (1 << 0) /* Enable all counters */ #define PMNC_P (1 << 1) /* Reset all counters */ #define PMNC_C (1 << 2) /* Cycle counter reset */ @@ -23,7 +23,7 @@ static int pmnc_counters; #define PMNC_DP (1 << 5) /* Disable CCNT if non-invasive debug */ #define PMNC_MASK 0x3f /* Mask for writable bits */ -// ccnt reg +/* ccnt reg */ #define CCNT_REG (1 << 31) #define CCNT 0 @@ -243,6 +243,7 @@ static inline void scorpion_pmnc_write(u32 val) static inline u32 scorpion_pmnc_read(void) { u32 val; + asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (val)); return val; } @@ -250,6 +251,7 @@ static inline u32 scorpion_pmnc_read(void) static inline u32 scorpion_ccnt_read(void) { u32 val; + asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val)); return val; } @@ -257,6 +259,7 @@ static inline u32 scorpion_ccnt_read(void) static inline u32 scorpion_cntn_read(void) { u32 val; + asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (val)); return val; } @@ -317,6 +320,7 @@ static inline int scorpion_pmnc_select_counter(unsigned int cnt) static u32 scorpion_read_lpm0(void) { u32 val; + asm volatile("mrc p15, 0, %0, c15, c0, 0" : "=r" (val)); return val; } @@ -329,6 +333,7 @@ static void scorpion_write_lpm0(u32 val) static u32 scorpion_read_lpm1(void) { u32 val; + asm volatile("mrc p15, 1, %0, c15, c0, 0" : "=r" (val)); return val; } @@ -341,6 +346,7 @@ static void scorpion_write_lpm1(u32 val) static u32 scorpion_read_lpm2(void) { u32 val; + asm volatile("mrc p15, 2, %0, c15, c0, 0" : "=r" (val)); return val; } @@ -353,6 +359,7 @@ static void scorpion_write_lpm2(u32 val) static u32 scorpion_read_l2lpm(void) { u32 val; + asm volatile("mrc p15, 3, %0, c15, c2, 0" : "=r" (val)); return val; } @@ -365,6 +372,7 @@ static void scorpion_write_l2lpm(u32 val) static u32 scorpion_read_vlpm(void) { u32 val; + asm volatile("mrc p10, 7, %0, c11, c0, 0" : "=r" (val)); return val; } @@ -375,7 +383,7 @@ static void scorpion_write_vlpm(u32 val) } struct scorpion_access_funcs { - u32(*read)(void); + u32 (*read)(void); void (*write)(u32); }; @@ -420,17 +428,17 @@ static u32 scorpion_get_columnmask(u32 setval) { if (setval & COLMN0MASK) return 0xffffff00; - else if (setval & COLMN1MASK) + if (setval & COLMN1MASK) return 0xffff00ff; - else if (setval & COLMN2MASK) + if (setval & COLMN2MASK) return 0xff00ffff; - else - return 0x80ffffff; + return 0x80ffffff; } static void scorpion_evt_setup(u32 gr, u32 setval) { u32 val; + if (gr == 4) scorpion_pre_vlpm(); val = scorpion_get_columnmask(setval) & scor_func[gr].read(); @@ -443,6 +451,7 @@ static void scorpion_evt_setup(u32 gr, u32 setval) static int get_scorpion_evtinfo(unsigned int evt_type, struct scorp_evt *evtinfo) { u32 idx; + if ((evt_type < 0x4c) || (evt_type >= MSM_MAX_EVT)) return 0; idx = evt_type - 0x4c; @@ -463,7 +472,7 @@ static inline void scorpion_pmnc_write_evtsel(unsigned int cnt, u32 val) } else { u32 zero = 0; struct scorp_evt evtinfo; - // extract evtinfo.grp and evtinfo.tevt_type_act from val + /* extract evtinfo.grp and evtinfo.tevt_type_act from val */ if (get_scorpion_evtinfo(val, &evtinfo) == 0) return; asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (evtinfo.evt_type_act)); @@ -505,20 +514,18 @@ static int gator_events_scorpion_create_files(struct super_block *sb, struct den for (i = 0; i < pmnc_counters; i++) { char buf[40]; - if (i == 0) { - snprintf(buf, sizeof buf, "%s_ccnt", pmnc_name); - } else { - snprintf(buf, sizeof buf, "%s_cnt%d", pmnc_name, i - 1); - } + + if (i == 0) + snprintf(buf, sizeof(buf), "%s_ccnt", pmnc_name); + else + snprintf(buf, sizeof(buf), "%s_cnt%d", pmnc_name, i - 1); dir = gatorfs_mkdir(sb, root, buf); - if (!dir) { + if (!dir) return -1; - } gatorfs_create_ulong(sb, dir, "enabled", &pmnc_enabled[i]); gatorfs_create_ro_ulong(sb, dir, "key", &pmnc_key[i]); - if (i > 0) { + if (i > 0) gatorfs_create_ulong(sb, dir, "event", &pmnc_event[i]); - } } return 0; @@ -528,9 +535,8 @@ static int gator_events_scorpion_online(int **buffer, bool migrate) { unsigned int cnt, len = 0, cpu = smp_processor_id(); - if (scorpion_pmnc_read() & PMNC_E) { + if (scorpion_pmnc_read() & PMNC_E) scorpion_pmnc_write(scorpion_pmnc_read() & ~PMNC_E); - } /* Initialize & Reset PMNC: C bit and P bit */ scorpion_pmnc_write(PMNC_P | PMNC_C); @@ -541,33 +547,32 @@ static int gator_events_scorpion_online(int **buffer, bool migrate) if (!pmnc_enabled[cnt]) continue; - // disable counter + /* disable counter */ scorpion_pmnc_disable_counter(cnt); event = pmnc_event[cnt] & 255; - // Set event (if destined for PMNx counters), We don't need to set the event if it's a cycle count + /* Set event (if destined for PMNx counters), We don't need to set the event if it's a cycle count */ if (cnt != CCNT) scorpion_pmnc_write_evtsel(cnt, event); - // reset counter + /* reset counter */ scorpion_pmnc_reset_counter(cnt); - // Enable counter, do not enable interrupt for this counter + /* Enable counter, do not enable interrupt for this counter */ scorpion_pmnc_enable_counter(cnt); } - // enable + /* enable */ scorpion_pmnc_write(scorpion_pmnc_read() | PMNC_E); - // read the counters and toss the invalid data, return zero instead + /* read the counters and toss the invalid data, return zero instead */ for (cnt = 0; cnt < pmnc_counters; cnt++) { if (pmnc_enabled[cnt]) { - if (cnt == CCNT) { + if (cnt == CCNT) scorpion_ccnt_read(); - } else if (scorpion_pmnc_select_counter(cnt) == cnt) { + else if (scorpion_pmnc_select_counter(cnt) == cnt) scorpion_cntn_read(); - } scorpion_pmnc_reset_counter(cnt); per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt]; @@ -597,26 +602,25 @@ static void gator_events_scorpion_stop(void) } } -static int gator_events_scorpion_read(int **buffer) +static int gator_events_scorpion_read(int **buffer, bool sched_switch) { int cnt, len = 0; int cpu = smp_processor_id(); - // a context switch may occur before the online hotplug event, thus need to check that the pmu is enabled - if (!(scorpion_pmnc_read() & PMNC_E)) { + /* a context switch may occur before the online hotplug event, thus need to check that the pmu is enabled */ + if (!(scorpion_pmnc_read() & PMNC_E)) return 0; - } for (cnt = 0; cnt < pmnc_counters; cnt++) { if (pmnc_enabled[cnt]) { int value; - if (cnt == CCNT) { + + if (cnt == CCNT) value = scorpion_ccnt_read(); - } else if (scorpion_pmnc_select_counter(cnt) == cnt) { + else if (scorpion_pmnc_select_counter(cnt) == cnt) value = scorpion_cntn_read(); - } else { + else value = 0; - } scorpion_pmnc_reset_counter(cnt); per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt]; @@ -655,7 +659,8 @@ int gator_events_scorpion_init(void) return -1; } - pmnc_counters++; // CNT[n] + CCNT + /* CNT[n] + CCNT */ + pmnc_counters++; for (cnt = CCNT; cnt < CNTMAX; cnt++) { pmnc_enabled[cnt] = 0; diff --git a/drivers/gator/gator_events_threads.c b/drivers/gator/gator_events_threads.c deleted file mode 100644 index 9de85862fe6c..000000000000 --- a/drivers/gator/gator_events_threads.c +++ /dev/null @@ -1,115 +0,0 @@ -/* - * Sample activity provider - * - * Copyright (C) ARM Limited 2014. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * See gator_events_mmapped.c for additional directions and - * troubleshooting. - * - * For this sample to work these entries must be present in the - * events.xml file. So create an events-threads.xml in the gator - * daemon source directory with the following contents and rebuild - * gatord: - * - * <category name="threads"> - * <event counter="Linux_threads" title="Linux" name="Threads" class="activity" activity1="odd" activity_color1="0x000000ff" rendering_type="bar" average_selection="yes" average_cores="yes" percentage="yes" description="Linux syscall activity"/> - * </category> - */ - -#include <trace/events/sched.h> - -#include "gator.h" - -static ulong threads_enabled; -static ulong threads_key; -static ulong threads_cores; - -#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 35) -GATOR_DEFINE_PROBE(sched_switch, TP_PROTO(struct rq *rq, struct task_struct *prev, struct task_struct *next)) -#else -GATOR_DEFINE_PROBE(sched_switch, TP_PROTO(struct task_struct *prev, struct task_struct *next)) -#endif -{ - int cpu = get_physical_cpu(); - int pid = next->pid; - if (pid == 0) { - // idle - gator_marshal_activity_switch(cpu, threads_key, 0, 0); - } else if (pid & 1) { - // odd - gator_marshal_activity_switch(cpu, threads_key, 1, pid); - } else { - // even - //gator_marshal_activity_switch(cpu, threads_key, 2, current->pid); - // Multiple activities are not yet supported so emit idle - gator_marshal_activity_switch(cpu, threads_key, 0, 0); - } -} - -// Adds Linux_threads directory and enabled, key, and cores files to /dev/gator/events -static int gator_events_threads_create_files(struct super_block *sb, struct dentry *root) -{ - struct dentry *dir; - - dir = gatorfs_mkdir(sb, root, "Linux_threads"); - if (!dir) { - return -1; - } - gatorfs_create_ulong(sb, dir, "enabled", &threads_enabled); - gatorfs_create_ro_ulong(sb, dir, "key", &threads_key); - // Number of cores associated with this activity - gatorfs_create_ro_ulong(sb, dir, "cores", &threads_cores); - - return 0; -} - -static int gator_events_threads_start(void) -{ - int cpu; - - if (threads_enabled) { - preempt_disable(); - for (cpu = 0; cpu < nr_cpu_ids; ++cpu) { - gator_marshal_activity_switch(cpu, threads_key, 0, 0); - } - preempt_enable(); - - if (GATOR_REGISTER_TRACE(sched_switch)) { - goto fail_sched_switch; - } - } - - return 0; - -fail_sched_switch: - return -1; -} - -static void gator_events_threads_stop(void) -{ - if (threads_enabled) { - GATOR_UNREGISTER_TRACE(sched_switch); - } - - threads_enabled = 0; -} - -static struct gator_interface gator_events_threads_interface = { - .create_files = gator_events_threads_create_files, - .start = gator_events_threads_start, - .stop = gator_events_threads_stop, -}; - -// Must not be static. Ensure that this init function is added to GATOR_EVENTS_LIST in gator_main.c -int __init gator_events_threads_init(void) -{ - threads_enabled = 0; - threads_key = gator_events_get_key(); - threads_cores = nr_cpu_ids; - - return gator_events_install(&gator_events_threads_interface); -} diff --git a/drivers/gator/gator_fs.c b/drivers/gator/gator_fs.c index 166cfe7d681d..d8fb357b9eda 100644 --- a/drivers/gator/gator_fs.c +++ b/drivers/gator/gator_fs.c @@ -14,7 +14,7 @@ #include <linux/module.h> #include <linux/fs.h> #include <linux/pagemap.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #define gatorfs_MAGIC 0x24051020 #define TMPBUFSIZE 50 @@ -43,6 +43,7 @@ static ssize_t gatorfs_ulong_to_user(unsigned long val, char __user *buf, size_t { char tmpbuf[TMPBUFSIZE]; size_t maxlen = snprintf(tmpbuf, TMPBUFSIZE, "%lu\n", val); + if (maxlen > TMPBUFSIZE) maxlen = TMPBUFSIZE; return simple_read_from_buffer(buf, count, offset, tmpbuf, maxlen); @@ -52,6 +53,7 @@ static ssize_t gatorfs_u64_to_user(u64 val, char __user *buf, size_t count, loff { char tmpbuf[TMPBUFSIZE]; size_t maxlen = snprintf(tmpbuf, TMPBUFSIZE, "%llu\n", val); + if (maxlen > TMPBUFSIZE) maxlen = TMPBUFSIZE; return simple_read_from_buffer(buf, count, offset, tmpbuf, maxlen); @@ -104,12 +106,14 @@ static int gatorfs_u64_from_user(u64 *val, char const __user *buf, size_t count) static ssize_t ulong_read_file(struct file *file, char __user *buf, size_t count, loff_t *offset) { unsigned long *val = file->private_data; + return gatorfs_ulong_to_user(*val, buf, count, offset); } static ssize_t u64_read_file(struct file *file, char __user *buf, size_t count, loff_t *offset) { u64 *val = file->private_data; + return gatorfs_u64_to_user(*val, buf, count, offset); } @@ -231,7 +235,7 @@ int gatorfs_create_ro_ulong(struct super_block *sb, struct dentry *root, } static int gatorfs_create_ro_u64(struct super_block *sb, struct dentry *root, - char const *name, u64 * val) + char const *name, u64 *val) { struct dentry *d = __gatorfs_create_file(sb, root, name, &u64_ro_fops, 0444); @@ -245,6 +249,7 @@ static int gatorfs_create_ro_u64(struct super_block *sb, struct dentry *root, static ssize_t atomic_read_file(struct file *file, char __user *buf, size_t count, loff_t *offset) { atomic_t *val = file->private_data; + return gatorfs_ulong_to_user(atomic_read(val), buf, count, offset); } diff --git a/drivers/gator/gator_hrtimer_gator.c b/drivers/gator/gator_hrtimer_gator.c index 76584554b00f..c1525e10a8da 100644 --- a/drivers/gator/gator_hrtimer_gator.c +++ b/drivers/gator/gator_hrtimer_gator.c @@ -18,6 +18,7 @@ static void gator_hrtimer_offline(void); static enum hrtimer_restart gator_hrtimer_notify(struct hrtimer *hrtimer) { int cpu = get_logical_cpu(); + hrtimer_forward(hrtimer, per_cpu(hrtimer_expire, cpu), profiling_interval); per_cpu(hrtimer_expire, cpu) = ktime_add(per_cpu(hrtimer_expire, cpu), profiling_interval); (*callback)(); @@ -64,12 +65,11 @@ static int gator_hrtimer_init(int interval, void (*func)(void)) per_cpu(hrtimer_is_active, cpu) = 0; } - // calculate profiling interval - if (interval > 0) { + /* calculate profiling interval */ + if (interval > 0) profiling_interval = ns_to_ktime(1000000000UL / interval); - } else { + else profiling_interval.tv64 = 0; - } return 0; } diff --git a/drivers/gator/gator_iks.c b/drivers/gator/gator_iks.c index 9180b874457a..fb78c10fd987 100644 --- a/drivers/gator/gator_iks.c +++ b/drivers/gator/gator_iks.c @@ -16,7 +16,7 @@ static bool map_cpuids; static int mpidr_cpuids[NR_CPUS]; -static const struct gator_cpu * mpidr_cpus[NR_CPUS]; +static const struct gator_cpu *mpidr_cpus[NR_CPUS]; static int __lcpu_to_pcpu[NR_CPUS]; static const struct gator_cpu *gator_find_cpu_by_dt_name(const char *const name) @@ -25,9 +25,9 @@ static const struct gator_cpu *gator_find_cpu_by_dt_name(const char *const name) for (i = 0; gator_cpus[i].cpuid != 0; ++i) { const struct gator_cpu *const gator_cpu = &gator_cpus[i]; - if (gator_cpu->dt_name != NULL && strcmp(gator_cpu->dt_name, name) == 0) { + + if (gator_cpu->dt_name != NULL && strcmp(gator_cpu->dt_name, name) == 0) return gator_cpu; - } } return NULL; @@ -41,7 +41,7 @@ static void calc_first_cluster_size(void) struct device_node *cn = NULL; int mpidr_cpuids_count = 0; - // Zero is a valid cpuid, so initialize the array to 0xff's + /* Zero is a valid cpuid, so initialize the array to 0xff's */ memset(&mpidr_cpuids, 0xff, sizeof(mpidr_cpuids)); memset(&mpidr_cpus, 0, sizeof(mpidr_cpus)); @@ -70,10 +70,10 @@ static void calc_first_cluster_size(void) static int linearize_mpidr(int mpidr) { int i; + for (i = 0; i < nr_cpu_ids; ++i) { - if (mpidr_cpuids[i] == mpidr) { + if (mpidr_cpuids[i] == mpidr) return i; - } } BUG(); @@ -113,6 +113,7 @@ static void gator_update_cpu_mapping(u32 cpu_hwid) { int lcpu = smp_processor_id(); int pcpu = linearize_mpidr(cpu_hwid & MPIDR_HWID_BITMASK); + BUG_ON(lcpu >= nr_cpu_ids || lcpu < 0); BUG_ON(pcpu >= nr_cpu_ids || pcpu < 0); __lcpu_to_pcpu[lcpu] = pcpu; @@ -132,7 +133,7 @@ GATOR_DEFINE_PROBE(cpu_migrate_finish, TP_PROTO(u64 timestamp, u32 cpu_hwid)) gator_update_cpu_mapping(cpu_hwid); - // get_physical_cpu must be called after gator_update_cpu_mapping + /* get_physical_cpu must be called after gator_update_cpu_mapping */ cpu = get_physical_cpu(); gator_timer_online_dispatch(cpu, true); gator_timer_online((void *)1); @@ -146,12 +147,11 @@ GATOR_DEFINE_PROBE(cpu_migrate_current, TP_PROTO(u64 timestamp, u32 cpu_hwid)) static void gator_send_iks_core_names(void) { int cpu; - // Send the cpu names + /* Send the cpu names */ preempt_disable(); for (cpu = 0; cpu < nr_cpu_ids; ++cpu) { - if (mpidr_cpus[cpu] != NULL) { + if (mpidr_cpus[cpu] != NULL) gator_send_core_name(cpu, mpidr_cpus[cpu]->cpuid); - } } preempt_enable(); } @@ -170,7 +170,7 @@ static int gator_migrate_start(void) if (retval == 0) retval = GATOR_REGISTER_TRACE(cpu_migrate_current); if (retval == 0) { - // Initialize the logical to physical cpu mapping + /* Initialize the logical to physical cpu mapping */ memset(&__lcpu_to_pcpu, 0xff, sizeof(__lcpu_to_pcpu)); bL_switcher_trace_trigger(); } diff --git a/drivers/gator/gator_main.c b/drivers/gator/gator_main.c index 0d867f22364f..30bf60d95286 100644 --- a/drivers/gator/gator_main.c +++ b/drivers/gator/gator_main.c @@ -7,8 +7,8 @@ * */ -// This version must match the gator daemon version -#define PROTOCOL_VERSION 19 +/* This version must match the gator daemon version */ +#define PROTOCOL_VERSION 20 static unsigned long gator_protocol_version = PROTOCOL_VERSION; #include <linux/slab.h> @@ -25,7 +25,7 @@ static unsigned long gator_protocol_version = PROTOCOL_VERSION; #include <linux/utsname.h> #include <linux/kthread.h> #include <asm/stacktrace.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include "gator.h" @@ -67,11 +67,11 @@ static unsigned long gator_protocol_version = PROTOCOL_VERSION; #define SUMMARY_BUFFER_SIZE (1*1024) #define BACKTRACE_BUFFER_SIZE (128*1024) #define NAME_BUFFER_SIZE (64*1024) -#define COUNTER_BUFFER_SIZE (64*1024) // counters have the core as part of the data and the core value in the frame header may be discarded +#define COUNTER_BUFFER_SIZE (64*1024) /* counters have the core as part of the data and the core value in the frame header may be discarded */ #define BLOCK_COUNTER_BUFFER_SIZE (128*1024) -#define ANNOTATE_BUFFER_SIZE (128*1024) // annotate counters have the core as part of the data and the core value in the frame header may be discarded +#define ANNOTATE_BUFFER_SIZE (128*1024) /* annotate counters have the core as part of the data and the core value in the frame header may be discarded */ #define SCHED_TRACE_BUFFER_SIZE (128*1024) -#define IDLE_BUFFER_SIZE (32*1024) // idle counters have the core as part of the data and the core value in the frame header may be discarded +#define IDLE_BUFFER_SIZE (32*1024) /* idle counters have the core as part of the data and the core value in the frame header may be discarded */ #define ACTIVITY_BUFFER_SIZE (128*1024) #define NO_COOKIE 0U @@ -89,24 +89,24 @@ static unsigned long gator_protocol_version = PROTOCOL_VERSION; #define MESSAGE_END_BACKTRACE 1 -// Name Frame Messages +/* Name Frame Messages */ #define MESSAGE_COOKIE 1 #define MESSAGE_THREAD_NAME 2 #define MESSAGE_LINK 4 -// Scheduler Trace Frame Messages +/* Scheduler Trace Frame Messages */ #define MESSAGE_SCHED_SWITCH 1 #define MESSAGE_SCHED_EXIT 2 -// Idle Frame Messages +/* Idle Frame Messages */ #define MESSAGE_IDLE_ENTER 1 #define MESSAGE_IDLE_EXIT 2 -// Summary Frame Messages +/* Summary Frame Messages */ #define MESSAGE_SUMMARY 1 #define MESSAGE_CORE_NAME 3 -// Activity Frame Messages +/* Activity Frame Messages */ #define MESSAGE_SWITCH 2 #define MESSAGE_EXIT 3 @@ -140,14 +140,15 @@ enum { * Globals ******************************************************************************/ static unsigned long gator_cpu_cores; -// Size of the largest buffer. Effectively constant, set in gator_op_create_files +/* Size of the largest buffer. Effectively constant, set in gator_op_create_files */ static unsigned long userspace_buffer_size; static unsigned long gator_backtrace_depth; -// How often to commit the buffers for live in nanoseconds +/* How often to commit the buffers for live in nanoseconds */ static u64 gator_live_rate; static unsigned long gator_started; static u64 gator_monotonic_started; +static u64 gator_sync_time; static u64 gator_hibernate_time; static unsigned long gator_buffer_opened; static unsigned long gator_timer_count; @@ -161,7 +162,7 @@ static DECLARE_WAIT_QUEUE_HEAD(gator_buffer_wait); static DECLARE_WAIT_QUEUE_HEAD(gator_annotate_wait); static struct timer_list gator_buffer_wake_up_timer; static bool gator_buffer_wake_run; -// Initialize semaphore unlocked to initialize memory values +/* Initialize semaphore unlocked to initialize memory values */ #if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36) static DECLARE_MUTEX(gator_buffer_wake_sem); #else @@ -183,33 +184,43 @@ static DEFINE_PER_CPU(bool, in_scheduler_context); * Prototypes ******************************************************************************/ static u64 gator_get_time(void); +static void gator_emit_perf_time(u64 time); static void gator_op_create_files(struct super_block *sb, struct dentry *root); -// gator_buffer is protected by being per_cpu and by having IRQs disabled when writing to it. -// Most marshal_* calls take care of this except for marshal_cookie*, marshal_backtrace* and marshal_frame where the caller is responsible for doing so. -// No synchronization is needed with the backtrace buffer as it is per cpu and is only used from the hrtimer. -// The annotate_lock must be held when using the annotation buffer as it is not per cpu. -// collect_counters which is the sole writer to the block counter frame is additionally protected by the per cpu collecting flag +/* gator_buffer is protected by being per_cpu and by having IRQs + * disabled when writing to it. Most marshal_* calls take care of this + * except for marshal_cookie*, marshal_backtrace* and marshal_frame + * where the caller is responsible for doing so. No synchronization is + * needed with the backtrace buffer as it is per cpu and is only used + * from the hrtimer. The annotate_lock must be held when using the + * annotation buffer as it is not per cpu. collect_counters which is + * the sole writer to the block counter frame is additionally + * protected by the per cpu collecting flag. + */ -// Size of the buffer, must be a power of 2. Effectively constant, set in gator_op_setup. +/* Size of the buffer, must be a power of 2. Effectively constant, set in gator_op_setup. */ static uint32_t gator_buffer_size[NUM_GATOR_BUFS]; -// gator_buffer_size - 1, bitwise and with pos to get offset into the array. Effectively constant, set in gator_op_setup. +/* gator_buffer_size - 1, bitwise and with pos to get offset into the array. Effectively constant, set in gator_op_setup. */ static uint32_t gator_buffer_mask[NUM_GATOR_BUFS]; -// Read position in the buffer. Initialized to zero in gator_op_setup and incremented after bytes are read by userspace in userspace_buffer_read +/* Read position in the buffer. Initialized to zero in gator_op_setup and incremented after bytes are read by userspace in userspace_buffer_read */ static DEFINE_PER_CPU(int[NUM_GATOR_BUFS], gator_buffer_read); -// Write position in the buffer. Initialized to zero in gator_op_setup and incremented after bytes are written to the buffer +/* Write position in the buffer. Initialized to zero in gator_op_setup and incremented after bytes are written to the buffer */ static DEFINE_PER_CPU(int[NUM_GATOR_BUFS], gator_buffer_write); -// Commit position in the buffer. Initialized to zero in gator_op_setup and incremented after a frame is ready to be read by userspace +/* Commit position in the buffer. Initialized to zero in gator_op_setup and incremented after a frame is ready to be read by userspace */ static DEFINE_PER_CPU(int[NUM_GATOR_BUFS], gator_buffer_commit); -// If set to false, decreases the number of bytes returned by buffer_bytes_available. Set in buffer_check_space if no space is remaining. Initialized to true in gator_op_setup -// This means that if we run out of space, continue to report that no space is available until bytes are read by userspace +/* If set to false, decreases the number of bytes returned by + * buffer_bytes_available. Set in buffer_check_space if no space is + * remaining. Initialized to true in gator_op_setup. This means that + * if we run out of space, continue to report that no space is + * available until bytes are read by userspace + */ static DEFINE_PER_CPU(int[NUM_GATOR_BUFS], buffer_space_available); -// The buffer. Allocated in gator_op_setup +/* The buffer. Allocated in gator_op_setup */ static DEFINE_PER_CPU(char *[NUM_GATOR_BUFS], gator_buffer); -// The time after which the buffer should be committed for live display +/* The time after which the buffer should be committed for live display */ static DEFINE_PER_CPU(u64, gator_buffer_commit_time); -// List of all gator events - new events must be added to this list +/* List of all gator events - new events must be added to this list */ #define GATOR_EVENTS_LIST \ GATOR_EVENT(gator_events_armv6_init) \ GATOR_EVENT(gator_events_armv7_init) \ @@ -218,15 +229,14 @@ static DEFINE_PER_CPU(u64, gator_buffer_commit_time); GATOR_EVENT(gator_events_irq_init) \ GATOR_EVENT(gator_events_l2c310_init) \ GATOR_EVENT(gator_events_mali_init) \ - GATOR_EVENT(gator_events_mali_t6xx_hw_init) \ - GATOR_EVENT(gator_events_mali_t6xx_init) \ + GATOR_EVENT(gator_events_mali_midgard_hw_init) \ + GATOR_EVENT(gator_events_mali_midgard_init) \ GATOR_EVENT(gator_events_meminfo_init) \ GATOR_EVENT(gator_events_mmapped_init) \ GATOR_EVENT(gator_events_net_init) \ GATOR_EVENT(gator_events_perf_pmu_init) \ GATOR_EVENT(gator_events_sched_init) \ GATOR_EVENT(gator_events_scorpion_init) \ - GATOR_EVENT(gator_events_threads_init) \ #define GATOR_EVENT(EVENT_INIT) __weak int EVENT_INIT(void); GATOR_EVENTS_LIST @@ -315,13 +325,6 @@ static const struct gator_cpu gator_cpus[] = { .pmnc_counters = 6, }, { - .cpuid = CORTEX_A12, - .core_name = "Cortex-A12", - .pmnc_name = "ARMv7_Cortex_A12", - .dt_name = "arm,cortex-a12", - .pmnc_counters = 6, - }, - { .cpuid = CORTEX_A15, .core_name = "Cortex-A15", .pmnc_name = "ARMv7_Cortex_A15", @@ -400,23 +403,32 @@ const struct gator_cpu *gator_find_cpu_by_cpuid(const u32 cpuid) for (i = 0; gator_cpus[i].cpuid != 0; ++i) { const struct gator_cpu *const gator_cpu = &gator_cpus[i]; - if (gator_cpu->cpuid == cpuid) { + + if (gator_cpu->cpuid == cpuid) return gator_cpu; - } } return NULL; } +static const char OLD_PMU_PREFIX[] = "ARMv7 Cortex-"; +static const char NEW_PMU_PREFIX[] = "ARMv7_Cortex_"; + const struct gator_cpu *gator_find_cpu_by_pmu_name(const char *const name) { int i; for (i = 0; gator_cpus[i].cpuid != 0; ++i) { const struct gator_cpu *const gator_cpu = &gator_cpus[i]; - if (gator_cpu->pmnc_name != NULL && strcmp(gator_cpu->pmnc_name, name) == 0) { + + if (gator_cpu->pmnc_name != NULL && + /* Do the names match exactly? */ + (strcasecmp(gator_cpu->pmnc_name, name) == 0 || + /* Do these names match but have the old vs new prefix? */ + ((strncasecmp(name, OLD_PMU_PREFIX, sizeof(OLD_PMU_PREFIX) - 1) == 0 && + strncasecmp(gator_cpu->pmnc_name, NEW_PMU_PREFIX, sizeof(NEW_PMU_PREFIX) - 1) == 0 && + strcasecmp(name + sizeof(OLD_PMU_PREFIX) - 1, gator_cpu->pmnc_name + sizeof(NEW_PMU_PREFIX) - 1) == 0)))) return gator_cpu; - } } return NULL; @@ -445,16 +457,15 @@ static void gator_buffer_wake_up(unsigned long data) static int gator_buffer_wake_func(void *data) { for (;;) { - if (down_killable(&gator_buffer_wake_sem)) { + if (down_killable(&gator_buffer_wake_sem)) break; - } - // Eat up any pending events - while (!down_trylock(&gator_buffer_wake_sem)); + /* Eat up any pending events */ + while (!down_trylock(&gator_buffer_wake_sem)) + ; - if (!gator_buffer_wake_run) { + if (!gator_buffer_wake_run) break; - } gator_buffer_wake_up(0); } @@ -468,6 +479,7 @@ static int gator_buffer_wake_func(void *data) static bool buffer_commit_ready(int *cpu, int *buftype) { int cpu_x, x; + for_each_present_cpu(cpu_x) { for (x = 0; x < NUM_GATOR_BUFS; x++) if (per_cpu(gator_buffer_commit, cpu_x)[x] != per_cpu(gator_buffer_read, cpu_x)[x]) { @@ -487,6 +499,7 @@ static bool buffer_commit_ready(int *cpu, int *buftype) static void gator_timer_interrupt(void) { struct pt_regs *const regs = get_irq_regs(); + gator_backtrace_handler(regs); } @@ -495,15 +508,14 @@ void gator_backtrace_handler(struct pt_regs *const regs) u64 time = gator_get_time(); int cpu = get_physical_cpu(); - // Output backtrace + /* Output backtrace */ gator_add_sample(cpu, regs, time); - // Collect counters - if (!per_cpu(collecting, cpu)) { - collect_counters(time, NULL); - } + /* Collect counters */ + if (!per_cpu(collecting, cpu)) + collect_counters(time, current, false); - // No buffer flushing occurs during sched switch for RT-Preempt full. The block counter frame will be flushed by collect_counters, but the sched buffer needs to be explicitly flushed + /* No buffer flushing occurs during sched switch for RT-Preempt full. The block counter frame will be flushed by collect_counters, but the sched buffer needs to be explicitly flushed */ #ifdef CONFIG_PREEMPT_RT_FULL buffer_check(cpu, SCHED_TRACE_BUF, time); #endif @@ -511,7 +523,7 @@ void gator_backtrace_handler(struct pt_regs *const regs) static int gator_running; -// This function runs in interrupt context and on the appropriate core +/* This function runs in interrupt context and on the appropriate core */ static void gator_timer_offline(void *migrate) { struct gator_interface *gi; @@ -522,11 +534,10 @@ static void gator_timer_offline(void *migrate) gator_trace_sched_offline(); gator_trace_power_offline(); - if (!migrate) { + if (!migrate) gator_hrtimer_offline(); - } - // Offline any events and output counters + /* Offline any events and output counters */ time = gator_get_time(); if (marshal_event_header(time)) { list_for_each_entry(gi, &gator_events, list) { @@ -535,24 +546,23 @@ static void gator_timer_offline(void *migrate) marshal_event(len, buffer); } } - // Only check after writing all counters so that time and corresponding counters appear in the same frame + /* Only check after writing all counters so that time and corresponding counters appear in the same frame */ buffer_check(cpu, BLOCK_COUNTER_BUF, time); } - // Flush all buffers on this core + /* Flush all buffers on this core */ for (i = 0; i < NUM_GATOR_BUFS; i++) gator_commit_buffer(cpu, i, time); } -// This function runs in interrupt context and may be running on a core other than core 'cpu' +/* This function runs in interrupt context and may be running on a core other than core 'cpu' */ static void gator_timer_offline_dispatch(int cpu, bool migrate) { struct gator_interface *gi; list_for_each_entry(gi, &gator_events, list) { - if (gi->offline_dispatch) { + if (gi->offline_dispatch) gi->offline_dispatch(cpu, migrate); - } } } @@ -579,16 +589,15 @@ static void gator_send_core_name(const int cpu, const u32 cpuid) const char *core_name = NULL; char core_name_buf[32]; - // Save off this cpuid + /* Save off this cpuid */ gator_cpuids[cpu] = cpuid; if (gator_cpu != NULL) { core_name = gator_cpu->core_name; } else { - if (cpuid == -1) { + if (cpuid == -1) snprintf(core_name_buf, sizeof(core_name_buf), "Unknown"); - } else { + else snprintf(core_name_buf, sizeof(core_name_buf), "Unknown (0x%.3x)", cpuid); - } core_name = core_name_buf; } @@ -598,12 +607,12 @@ static void gator_send_core_name(const int cpu, const u32 cpuid) #endif } -static void gator_read_cpuid(void * arg) +static void gator_read_cpuid(void *arg) { gator_cpuids[get_physical_cpu()] = gator_cpuid(); } -// This function runs in interrupt context and on the appropriate core +/* This function runs in interrupt context and on the appropriate core */ static void gator_timer_online(void *migrate) { struct gator_interface *gi; @@ -611,12 +620,12 @@ static void gator_timer_online(void *migrate) int *buffer; u64 time; - // Send what is currently running on this core + /* Send what is currently running on this core */ marshal_sched_trace_switch(current->pid, 0); gator_trace_power_online(); - // online any events and output counters + /* online any events and output counters */ time = gator_get_time(); if (marshal_event_header(time)) { list_for_each_entry(gi, &gator_events, list) { @@ -625,26 +634,24 @@ static void gator_timer_online(void *migrate) marshal_event(len, buffer); } } - // Only check after writing all counters so that time and corresponding counters appear in the same frame + /* Only check after writing all counters so that time and corresponding counters appear in the same frame */ buffer_check(cpu, BLOCK_COUNTER_BUF, time); } - if (!migrate) { + if (!migrate) gator_hrtimer_online(); - } gator_send_core_name(cpu, gator_cpuid()); } -// This function runs in interrupt context and may be running on a core other than core 'cpu' +/* This function runs in interrupt context and may be running on a core other than core 'cpu' */ static void gator_timer_online_dispatch(int cpu, bool migrate) { struct gator_interface *gi; list_for_each_entry(gi, &gator_events, list) { - if (gi->online_dispatch) { + if (gi->online_dispatch) gi->online_dispatch(cpu, migrate); - } } } @@ -661,15 +668,14 @@ static int gator_timer_start(unsigned long sample_rate) gator_running = 1; - // event based sampling trumps hr timer based sampling - if (event_based_sampling) { + /* event based sampling trumps hr timer based sampling */ + if (event_based_sampling) sample_rate = 0; - } if (gator_hrtimer_init(sample_rate, gator_timer_interrupt) == -1) return -1; - // Send off the previously saved cpuids + /* Send off the previously saved cpuids */ for_each_present_cpu(cpu) { preempt_disable(); gator_send_core_name(cpu, gator_cpuids[cpu]); @@ -693,21 +699,24 @@ static u64 gator_get_time(void) u64 delta; int cpu = smp_processor_id(); - // Match clock_gettime(CLOCK_MONOTONIC_RAW, &ts) from userspace + /* Match clock_gettime(CLOCK_MONOTONIC_RAW, &ts) from userspace */ getrawmonotonic(&ts); timestamp = timespec_to_ns(&ts); - // getrawmonotonic is not monotonic on all systems. Detect and attempt to correct these cases. - // up to 0.5ms delta has been seen on some systems, which can skew Streamline data when viewing at high resolution. - // This doesn't work well with interrupts, but that it's OK - the real concern is to catch big jumps in time + /* getrawmonotonic is not monotonic on all systems. Detect and + * attempt to correct these cases. up to 0.5ms delta has been seen + * on some systems, which can skew Streamline data when viewing at + * high resolution. This doesn't work well with interrupts, but that + * it's OK - the real concern is to catch big jumps in time + */ prev_timestamp = per_cpu(last_timestamp, cpu); if (prev_timestamp <= timestamp) { per_cpu(last_timestamp, cpu) = timestamp; } else { delta = prev_timestamp - timestamp; - // Log the error once + /* Log the error once */ if (!printed_monotonic_warning && delta > 500000) { - printk(KERN_ERR "%s: getrawmonotonic is not monotonic cpu: %i delta: %lli\nSkew in Streamline data may be present at the fine zoom levels\n", __FUNCTION__, cpu, delta); + pr_err("%s: getrawmonotonic is not monotonic cpu: %i delta: %lli\nSkew in Streamline data may be present at the fine zoom levels\n", __func__, cpu, delta); printed_monotonic_warning = true; } timestamp = prev_timestamp; @@ -716,6 +725,19 @@ static u64 gator_get_time(void) return timestamp - gator_monotonic_started; } +static void gator_emit_perf_time(u64 time) +{ +#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 10, 0) + if (time >= gator_sync_time) { + int cpu = get_physical_cpu(); + + marshal_event_single64(0, -1, local_clock()); + gator_sync_time += NSEC_PER_SEC; + gator_commit_buffer(cpu, COUNTER_BUF, time); + } +#endif +} + /****************************************************************************** * cpu hotplug and pm notifiers ******************************************************************************/ @@ -743,8 +765,10 @@ static struct notifier_block __refdata gator_hotcpu_notifier = { .notifier_call = gator_hotcpu_notify, }; -// n.b. calling "on_each_cpu" only runs on those that are online -// Registered linux events are not disabled, so their counters will continue to collect +/* n.b. calling "on_each_cpu" only runs on those that are online. + * Registered linux events are not disabled, so their counters will + * continue to collect + */ static int gator_pm_notify(struct notifier_block *nb, unsigned long event, void *dummy) { int cpu; @@ -760,13 +784,13 @@ static int gator_pm_notify(struct notifier_block *nb, unsigned long event, void gator_timer_offline_dispatch(lcpu_to_pcpu(cpu), false); } - // Record the wallclock hibernate time + /* Record the wallclock hibernate time */ getnstimeofday(&ts); gator_hibernate_time = timespec_to_ns(&ts) - gator_get_time(); break; case PM_POST_HIBERNATION: case PM_POST_SUSPEND: - // Adjust gator_monotonic_started for the time spent sleeping, as gator_get_time does not account for it + /* Adjust gator_monotonic_started for the time spent sleeping, as gator_get_time does not account for it */ if (gator_hibernate_time > 0) { getnstimeofday(&ts); gator_monotonic_started += gator_hibernate_time + gator_get_time() - timespec_to_ns(&ts); @@ -792,6 +816,7 @@ static struct notifier_block gator_pm_notifier = { static int gator_notifier_start(void) { int retval; + retval = register_hotcpu_notifier(&gator_hotcpu_notifier); if (retval == 0) retval = register_pm_notifier(&gator_pm_notifier); @@ -812,28 +837,37 @@ static void gator_summary(void) u64 timestamp, uptime; struct timespec ts; char uname_buf[512]; - void (*m2b)(struct timespec *ts); snprintf(uname_buf, sizeof(uname_buf), "%s %s %s %s %s GNU/Linux", utsname()->sysname, utsname()->nodename, utsname()->release, utsname()->version, utsname()->machine); getnstimeofday(&ts); timestamp = timespec_to_ns(&ts); - do_posix_clock_monotonic_gettime(&ts); - // monotonic_to_bootbased is not defined for some versions of Android - m2b = symbol_get(monotonic_to_bootbased); - if (m2b) { - m2b(&ts); + /* Similar to reading /proc/uptime from fs/proc/uptime.c, calculate uptime */ +#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 11, 0) + { + void (*m2b)(struct timespec *ts); + + do_posix_clock_monotonic_gettime(&ts); + /* monotonic_to_bootbased is not defined for some versions of Android */ + m2b = symbol_get(monotonic_to_bootbased); + if (m2b) + m2b(&ts); } +#else + get_monotonic_boottime(&ts); +#endif uptime = timespec_to_ns(&ts); - // Disable preemption as gator_get_time calls smp_processor_id to verify time is monotonic + /* Disable preemption as gator_get_time calls smp_processor_id to verify time is monotonic */ preempt_disable(); - // Set monotonic_started to zero as gator_get_time is uptime minus monotonic_started + /* Set monotonic_started to zero as gator_get_time is uptime minus monotonic_started */ gator_monotonic_started = 0; gator_monotonic_started = gator_get_time(); marshal_summary(timestamp, uptime, gator_monotonic_started, uname_buf); + gator_sync_time = 0; + gator_emit_perf_time(gator_monotonic_started); preempt_enable(); } @@ -846,12 +880,14 @@ int gator_events_install(struct gator_interface *interface) int gator_events_get_key(void) { - // key 0 is reserved as a timestamp - // key 1 is reserved as the marker for thread specific counters - // Odd keys are assigned by the driver, even keys by the daemon + /* key 0 is reserved as a timestamp. key 1 is reserved as the marker + * for thread specific counters. key 2 is reserved as the marker for + * core. Odd keys are assigned by the driver, even keys by the + * daemon. + */ static int key = 3; - const int ret = key; + key += 2; return ret; } @@ -862,7 +898,7 @@ static int gator_init(void) calc_first_cluster_size(); - // events sources + /* events sources */ for (i = 0; i < ARRAY_SIZE(gator_events_list); i++) if (gator_events_list[i]) gator_events_list[i](); @@ -888,26 +924,25 @@ static int gator_start(void) struct gator_interface *gi; gator_buffer_wake_run = true; - if (IS_ERR(gator_buffer_wake_thread = kthread_run(gator_buffer_wake_func, NULL, "gator_bwake"))) { + gator_buffer_wake_thread = kthread_run(gator_buffer_wake_func, NULL, "gator_bwake"); + if (IS_ERR(gator_buffer_wake_thread)) goto bwake_failure; - } if (gator_migrate_start()) goto migrate_failure; - // Initialize the buffer with the frame type and core + /* Initialize the buffer with the frame type and core */ for_each_present_cpu(cpu) { - for (i = 0; i < NUM_GATOR_BUFS; i++) { + for (i = 0; i < NUM_GATOR_BUFS; i++) marshal_frame(cpu, i); - } per_cpu(last_timestamp, cpu) = 0; } printed_monotonic_warning = false; - // Capture the start time + /* Capture the start time */ gator_summary(); - // start all events + /* start all events */ list_for_each_entry(gi, &gator_events, list) { if (gi->start && gi->start() != 0) { struct list_head *ptr = gi->list.prev; @@ -924,7 +959,7 @@ static int gator_start(void) } } - // cookies shall be initialized before trace_sched_start() and gator_timer_start() + /* cookies shall be initialized before trace_sched_start() and gator_timer_start() */ if (cookies_initialize()) goto cookies_failure; if (gator_annotate_start()) @@ -955,7 +990,7 @@ sched_failure: annotate_failure: cookies_release(); cookies_failure: - // stop all events + /* stop all events */ list_for_each_entry(gi, &gator_events, list) if (gi->stop) gi->stop(); @@ -979,11 +1014,11 @@ static void gator_stop(void) gator_trace_power_stop(); gator_trace_gpu_stop(); - // stop all interrupt callback reads before tearing down other interfaces - gator_notifier_stop(); // should be called before gator_timer_stop to avoid re-enabling the hrtimer after it has been offlined + /* stop all interrupt callback reads before tearing down other interfaces */ + gator_notifier_stop(); /* should be called before gator_timer_stop to avoid re-enabling the hrtimer after it has been offlined */ gator_timer_stop(); - // stop all events + /* stop all events */ list_for_each_entry(gi, &gator_events, list) if (gi->stop) gi->stop(); @@ -1033,9 +1068,9 @@ static int gator_op_setup(void) gator_buffer_size[ACTIVITY_BUF] = ACTIVITY_BUFFER_SIZE; gator_buffer_mask[ACTIVITY_BUF] = ACTIVITY_BUFFER_SIZE - 1; - // Initialize percpu per buffer variables + /* Initialize percpu per buffer variables */ for (i = 0; i < NUM_GATOR_BUFS; i++) { - // Verify buffers are a power of 2 + /* Verify buffers are a power of 2 */ if (gator_buffer_size[i] & (gator_buffer_size[i] - 1)) { err = -ENOEXEC; goto setup_error; @@ -1048,7 +1083,7 @@ static int gator_op_setup(void) per_cpu(buffer_space_available, cpu)[i] = true; per_cpu(gator_buffer_commit_time, cpu) = gator_live_rate; - // Annotation is a special case that only uses a single buffer + /* Annotation is a special case that only uses a single buffer */ if (cpu > 0 && i == ANNOTATE_BUF) { per_cpu(gator_buffer, cpu)[i] = NULL; continue; @@ -1188,7 +1223,8 @@ static int userspace_buffer_open(struct inode *inode, struct file *file) if (test_and_set_bit_lock(0, &gator_buffer_opened)) return -EBUSY; - if ((err = gator_op_setup())) + err = gator_op_setup(); + if (err) goto fail; /* NB: the actual start happens from userspace @@ -1218,22 +1254,20 @@ static ssize_t userspace_buffer_read(struct file *file, char __user *buf, size_t int cpu, buftype; int written = 0; - // ensure there is enough space for a whole frame - if (count < userspace_buffer_size || *offset) { + /* ensure there is enough space for a whole frame */ + if (count < userspace_buffer_size || *offset) return -EINVAL; - } - // sleep until the condition is true or a signal is received - // the condition is checked each time gator_buffer_wait is woken up + /* sleep until the condition is true or a signal is received the + * condition is checked each time gator_buffer_wait is woken up + */ wait_event_interruptible(gator_buffer_wait, buffer_commit_ready(&cpu, &buftype) || !gator_started); - if (signal_pending(current)) { + if (signal_pending(current)) return -EINTR; - } - if (buftype == -1 || cpu == -1) { + if (buftype == -1 || cpu == -1) return 0; - } mutex_lock(&gator_buffer_mutex); @@ -1241,12 +1275,11 @@ static ssize_t userspace_buffer_read(struct file *file, char __user *buf, size_t read = per_cpu(gator_buffer_read, cpu)[buftype]; commit = per_cpu(gator_buffer_commit, cpu)[buftype]; - // May happen if the buffer is freed during pending reads. - if (!per_cpu(gator_buffer, cpu)[buftype]) { + /* May happen if the buffer is freed during pending reads. */ + if (!per_cpu(gator_buffer, cpu)[buftype]) break; - } - // determine the size of two halves + /* determine the size of two halves */ length1 = commit - read; length2 = 0; buffer1 = &(per_cpu(gator_buffer, cpu)[buftype][read]); @@ -1256,32 +1289,28 @@ static ssize_t userspace_buffer_read(struct file *file, char __user *buf, size_t length2 = commit; } - if (length1 + length2 > count - written) { + if (length1 + length2 > count - written) break; - } - // start, middle or end - if (length1 > 0 && copy_to_user(&buf[written], buffer1, length1)) { + /* start, middle or end */ + if (length1 > 0 && copy_to_user(&buf[written], buffer1, length1)) break; - } - // possible wrap around - if (length2 > 0 && copy_to_user(&buf[written + length1], buffer2, length2)) { + /* possible wrap around */ + if (length2 > 0 && copy_to_user(&buf[written + length1], buffer2, length2)) break; - } per_cpu(gator_buffer_read, cpu)[buftype] = commit; written += length1 + length2; - // Wake up annotate_write if more space is available - if (buftype == ANNOTATE_BUF) { + /* Wake up annotate_write if more space is available */ + if (buftype == ANNOTATE_BUF) wake_up(&gator_annotate_wait); - } } while (buffer_commit_ready(&cpu, &buftype)); mutex_unlock(&gator_buffer_mutex); - // kick just in case we've lost an SMP event + /* kick just in case we've lost an SMP event */ wake_up(&gator_buffer_wait); return written > 0 ? written : -EFAULT; @@ -1348,19 +1377,19 @@ static void gator_op_create_files(struct super_block *sb, struct dentry *root) gatorfs_create_ro_u64(sb, root, "started", &gator_monotonic_started); gatorfs_create_u64(sb, root, "live_rate", &gator_live_rate); - // Annotate interface + /* Annotate interface */ gator_annotate_create_files(sb, root); - // Linux Events + /* Linux Events */ dir = gatorfs_mkdir(sb, root, "events"); list_for_each_entry(gi, &gator_events, list) if (gi->create_files) gi->create_files(sb, dir); - // Sched Events + /* Sched Events */ sched_trace_create_files(sb, dir); - // Power interface + /* Power interface */ gator_trace_power_create_files(sb, dir); } @@ -1396,19 +1425,22 @@ static void gator_op_create_files(struct super_block *sb, struct dentry *root) GATOR_HANDLE_TRACEPOINT(sched_process_free); \ GATOR_HANDLE_TRACEPOINT(sched_switch); \ GATOR_HANDLE_TRACEPOINT(softirq_exit); \ + GATOR_HANDLE_TRACEPOINT(task_rename); \ #define GATOR_HANDLE_TRACEPOINT(probe_name) \ struct tracepoint *gator_tracepoint_##probe_name GATOR_TRACEPOINTS; #undef GATOR_HANDLE_TRACEPOINT -static void gator_fct(struct tracepoint *tp, void *priv) +static void gator_save_tracepoint(struct tracepoint *tp, void *priv) { #define GATOR_HANDLE_TRACEPOINT(probe_name) \ - if (strcmp(tp->name, #probe_name) == 0) { \ - gator_tracepoint_##probe_name = tp; \ - return; \ - } + do { \ + if (strcmp(tp->name, #probe_name) == 0) { \ + gator_tracepoint_##probe_name = tp; \ + return; \ + } \ + } while (0) GATOR_TRACEPOINTS; #undef GATOR_HANDLE_TRACEPOINT } @@ -1421,11 +1453,10 @@ GATOR_TRACEPOINTS; static int __init gator_module_init(void) { - for_each_kernel_tracepoint(gator_fct, NULL); + for_each_kernel_tracepoint(gator_save_tracepoint, NULL); - if (gatorfs_register()) { + if (gatorfs_register()) return -1; - } if (gator_init()) { gatorfs_unregister(); @@ -1434,7 +1465,7 @@ static int __init gator_module_init(void) setup_timer(&gator_buffer_wake_up_timer, gator_buffer_wake_up, 0); - // Initialize the list of cpuids + /* Initialize the list of cpuids */ memset(gator_cpuids, -1, sizeof(gator_cpuids)); on_each_cpu(gator_read_cpuid, NULL, 1); diff --git a/drivers/gator/gator_marshaling.c b/drivers/gator/gator_marshaling.c index 97b4ae6f9d4d..0d1167643642 100644 --- a/drivers/gator/gator_marshaling.c +++ b/drivers/gator/gator_marshaling.c @@ -23,7 +23,7 @@ #include "gator_events_mali_common.h" #endif -static void marshal_summary(long long timestamp, long long uptime, long long monotonic_delta, const char * uname) +static void marshal_summary(long long timestamp, long long uptime, long long monotonic_delta, const char *uname) { unsigned long flags; int cpu = 0; @@ -40,19 +40,27 @@ static void marshal_summary(long long timestamp, long long uptime, long long mon gator_buffer_write_string(cpu, SUMMARY_BUF, "iks"); gator_buffer_write_string(cpu, SUMMARY_BUF, ""); #endif - // Let Streamline know which GPU is used so that it can label the GPU Activity appropriately. This is a temporary fix, to be improved in a future release. +#ifdef CONFIG_PREEMPT_RTB + gator_buffer_write_string(cpu, SUMMARY_BUF, "preempt_rtb"); + gator_buffer_write_string(cpu, SUMMARY_BUF, ""); +#endif +#ifdef CONFIG_PREEMPT_RT_FULL + gator_buffer_write_string(cpu, SUMMARY_BUF, "preempt_rt_full"); + gator_buffer_write_string(cpu, SUMMARY_BUF, ""); +#endif + /* Let Streamline know which GPU is used so that it can label the GPU Activity appropriately. This is a temporary fix, to be improved in a future release. */ #ifdef MALI_SUPPORT gator_buffer_write_string(cpu, SUMMARY_BUF, "mali_type"); #if (MALI_SUPPORT == MALI_4xx) gator_buffer_write_string(cpu, SUMMARY_BUF, "4xx"); -#elif (MALI_SUPPORT == MALI_T6xx) +#elif (MALI_SUPPORT == MALI_MIDGARD) gator_buffer_write_string(cpu, SUMMARY_BUF, "6xx"); #else gator_buffer_write_string(cpu, SUMMARY_BUF, "unknown"); #endif #endif gator_buffer_write_string(cpu, SUMMARY_BUF, ""); - // Commit the buffer now so it can be one of the first frames read by Streamline + /* Commit the buffer now so it can be one of the first frames read by Streamline */ local_irq_restore(flags); gator_commit_buffer(cpu, SUMMARY_BUF, gator_get_time()); } @@ -60,13 +68,14 @@ static void marshal_summary(long long timestamp, long long uptime, long long mon static bool marshal_cookie_header(const char *text) { int cpu = get_physical_cpu(); + return buffer_check_space(cpu, NAME_BUF, strlen(text) + 3 * MAXSIZE_PACK32); } static void marshal_cookie(int cookie, const char *text) { int cpu = get_physical_cpu(); - // buffer_check_space already called by marshal_cookie_header + /* buffer_check_space already called by marshal_cookie_header */ gator_buffer_write_packed_int(cpu, NAME_BUF, MESSAGE_COOKIE); gator_buffer_write_packed_int(cpu, NAME_BUF, cookie); gator_buffer_write_string(cpu, NAME_BUF, text); @@ -77,6 +86,7 @@ static void marshal_thread_name(int pid, char *name) { unsigned long flags, cpu; u64 time; + local_irq_save(flags); cpu = get_physical_cpu(); time = gator_get_time(); @@ -105,15 +115,16 @@ static void marshal_link(int cookie, int tgid, int pid) gator_buffer_write_packed_int(cpu, NAME_BUF, pid); } local_irq_restore(flags); - // Check and commit; commit is set to occur once buffer is 3/4 full + /* Check and commit; commit is set to occur once buffer is 3/4 full */ buffer_check(cpu, NAME_BUF, time); } static bool marshal_backtrace_header(int exec_cookie, int tgid, int pid, u64 time) { int cpu = get_physical_cpu(); + if (!buffer_check_space(cpu, BACKTRACE_BUF, MAXSIZE_PACK64 + 5 * MAXSIZE_PACK32 + gator_backtrace_depth * 2 * MAXSIZE_PACK32)) { - // Check and commit; commit is set to occur once buffer is 3/4 full + /* Check and commit; commit is set to occur once buffer is 3/4 full */ buffer_check(cpu, BACKTRACE_BUF, time); return false; @@ -130,9 +141,9 @@ static bool marshal_backtrace_header(int exec_cookie, int tgid, int pid, u64 tim static void marshal_backtrace(unsigned long address, int cookie, int in_kernel) { int cpu = get_physical_cpu(); - if (cookie == 0 && !in_kernel) { + + if (cookie == 0 && !in_kernel) cookie = UNRESOLVED_COOKIE; - } gator_buffer_write_packed_int(cpu, BACKTRACE_BUF, cookie); gator_buffer_write_packed_int64(cpu, BACKTRACE_BUF, address); } @@ -140,9 +151,10 @@ static void marshal_backtrace(unsigned long address, int cookie, int in_kernel) static void marshal_backtrace_footer(u64 time) { int cpu = get_physical_cpu(); + gator_buffer_write_packed_int(cpu, BACKTRACE_BUF, MESSAGE_END_BACKTRACE); - // Check and commit; commit is set to occur once buffer is 3/4 full + /* Check and commit; commit is set to occur once buffer is 3/4 full */ buffer_check(cpu, BACKTRACE_BUF, time); } @@ -153,7 +165,7 @@ static bool marshal_event_header(u64 time) local_irq_save(flags); if (buffer_check_space(cpu, BLOCK_COUNTER_BUF, MAXSIZE_PACK32 + MAXSIZE_PACK64)) { - gator_buffer_write_packed_int(cpu, BLOCK_COUNTER_BUF, 0); // key of zero indicates a timestamp + gator_buffer_write_packed_int(cpu, BLOCK_COUNTER_BUF, 0); /* key of zero indicates a timestamp */ gator_buffer_write_packed_int64(cpu, BLOCK_COUNTER_BUF, time); retval = true; } @@ -169,18 +181,17 @@ static void marshal_event(int len, int *buffer) if (len <= 0) return; - // length must be even since all data is a (key, value) pair + /* length must be even since all data is a (key, value) pair */ if (len & 0x1) { - pr_err("gator: invalid counter data detected and discarded"); + pr_err("gator: invalid counter data detected and discarded\n"); return; } - // events must be written in key,value pairs + /* events must be written in key,value pairs */ local_irq_save(flags); for (i = 0; i < len; i += 2) { - if (!buffer_check_space(cpu, BLOCK_COUNTER_BUF, 2 * MAXSIZE_PACK32)) { + if (!buffer_check_space(cpu, BLOCK_COUNTER_BUF, 2 * MAXSIZE_PACK32)) break; - } gator_buffer_write_packed_int(cpu, BLOCK_COUNTER_BUF, buffer[i]); gator_buffer_write_packed_int(cpu, BLOCK_COUNTER_BUF, buffer[i + 1]); } @@ -194,26 +205,24 @@ static void marshal_event64(int len, long long *buffer64) if (len <= 0) return; - // length must be even since all data is a (key, value) pair + /* length must be even since all data is a (key, value) pair */ if (len & 0x1) { - pr_err("gator: invalid counter data detected and discarded"); + pr_err("gator: invalid counter data detected and discarded\n"); return; } - // events must be written in key,value pairs + /* events must be written in key,value pairs */ local_irq_save(flags); for (i = 0; i < len; i += 2) { - if (!buffer_check_space(cpu, BLOCK_COUNTER_BUF, 2 * MAXSIZE_PACK64)) { + if (!buffer_check_space(cpu, BLOCK_COUNTER_BUF, 2 * MAXSIZE_PACK64)) break; - } gator_buffer_write_packed_int64(cpu, BLOCK_COUNTER_BUF, buffer64[i]); gator_buffer_write_packed_int64(cpu, BLOCK_COUNTER_BUF, buffer64[i + 1]); } local_irq_restore(flags); } -#if GATOR_CPU_FREQ_SUPPORT -static void marshal_event_single(int core, int key, int value) +static void __maybe_unused marshal_event_single(int core, int key, int value) { unsigned long flags, cpu; u64 time; @@ -228,11 +237,11 @@ static void marshal_event_single(int core, int key, int value) gator_buffer_write_packed_int(cpu, COUNTER_BUF, value); } local_irq_restore(flags); - // Check and commit; commit is set to occur once buffer is 3/4 full + /* Check and commit; commit is set to occur once buffer is 3/4 full */ buffer_check(cpu, COUNTER_BUF, time); } -static void marshal_event_single64(int core, int key, long long value) +static void __maybe_unused marshal_event_single64(int core, int key, long long value) { unsigned long flags, cpu; u64 time; @@ -247,10 +256,9 @@ static void marshal_event_single64(int core, int key, long long value) gator_buffer_write_packed_int64(cpu, COUNTER_BUF, value); } local_irq_restore(flags); - // Check and commit; commit is set to occur once buffer is 3/4 full + /* Check and commit; commit is set to occur once buffer is 3/4 full */ buffer_check(cpu, COUNTER_BUF, time); } -#endif static void marshal_sched_trace_switch(int pid, int state) { @@ -269,7 +277,7 @@ static void marshal_sched_trace_switch(int pid, int state) gator_buffer_write_packed_int(cpu, SCHED_TRACE_BUF, state); } local_irq_restore(flags); - // Check and commit; commit is set to occur once buffer is 3/4 full + /* Check and commit; commit is set to occur once buffer is 3/4 full */ buffer_check(cpu, SCHED_TRACE_BUF, time); } @@ -289,7 +297,7 @@ static void marshal_sched_trace_exit(int tgid, int pid) gator_buffer_write_packed_int(cpu, SCHED_TRACE_BUF, pid); } local_irq_restore(flags); - // Check and commit; commit is set to occur once buffer is 3/4 full + /* Check and commit; commit is set to occur once buffer is 3/4 full */ buffer_check(cpu, SCHED_TRACE_BUF, time); } @@ -308,7 +316,7 @@ static void marshal_idle(int core, int state) gator_buffer_write_packed_int(cpu, IDLE_BUF, core); } local_irq_restore(flags); - // Check and commit; commit is set to occur once buffer is 3/4 full + /* Check and commit; commit is set to occur once buffer is 3/4 full */ buffer_check(cpu, IDLE_BUF, time); } #endif @@ -318,6 +326,7 @@ static void marshal_core_name(const int core, const int cpuid, const char *name) { int cpu = get_physical_cpu(); unsigned long flags; + local_irq_save(flags); if (buffer_check_space(cpu, SUMMARY_BUF, MAXSIZE_PACK32 + MAXSIZE_CORE_NAME)) { gator_buffer_write_packed_int(cpu, SUMMARY_BUF, MESSAGE_CORE_NAME); @@ -325,7 +334,7 @@ static void marshal_core_name(const int core, const int cpuid, const char *name) gator_buffer_write_packed_int(cpu, SUMMARY_BUF, cpuid); gator_buffer_write_string(cpu, SUMMARY_BUF, name); } - // Commit core names now so that they can show up in live + /* Commit core names now so that they can show up in live */ local_irq_restore(flags); gator_commit_buffer(cpu, SUMMARY_BUF, gator_get_time()); } @@ -351,12 +360,12 @@ static void marshal_activity_switch(int core, int key, int activity, int pid, in gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, state); } local_irq_restore(flags); - // Check and commit; commit is set to occur once buffer is 3/4 full + /* Check and commit; commit is set to occur once buffer is 3/4 full */ buffer_check(cpu, ACTIVITY_BUF, time); } void gator_marshal_activity_switch(int core, int key, int activity, int pid) { - // state is reserved for cpu use only + /* state is reserved for cpu use only */ marshal_activity_switch(core, key, activity, pid, 0); } diff --git a/drivers/gator/gator_trace_gpu.c b/drivers/gator/gator_trace_gpu.c index a8b9e7d61ece..5de9152e365a 100644 --- a/drivers/gator/gator_trace_gpu.c +++ b/drivers/gator/gator_trace_gpu.c @@ -58,11 +58,12 @@ struct mali_activity { static struct mali_activity mali_activities[NUMBER_OF_GPU_UNITS*NUMBER_OF_GPU_CORES]; static DEFINE_SPINLOCK(mali_activities_lock); -/* Only one event should be running on a unit and core at a time (ie, a start - * event can only be followed by a stop and vice versa), but because the kernel - * only knows when a job is enqueued and not started, it is possible for a - * start1, start2, stop1, stop2. Change it back into start1, stop1, start2, - * stop2 by queueing up start2 and releasing it when stop1 is received. +/* Only one event should be running on a unit and core at a time (ie, + * a start event can only be followed by a stop and vice versa), but + * because the kernel only knows when a job is enqueued and not + * started, it is possible for a start1, start2, stop1, stop2. Change + * it back into start1, stop1, start2, stop2 by queueing up start2 and + * releasing it when stop1 is received. */ static int mali_activity_index(int core, int key) @@ -70,9 +71,8 @@ static int mali_activity_index(int core, int key) int i; for (i = 0; i < ARRAY_SIZE(mali_activities); ++i) { - if ((mali_activities[i].core == core) && (mali_activities[i].key == key)) { + if ((mali_activities[i].core == core) && (mali_activities[i].key == key)) break; - } if ((mali_activities[i].core == 0) && (mali_activities[i].key == 0)) { mali_activities[i].core = core; mali_activities[i].key = key; @@ -101,9 +101,8 @@ static void mali_activity_enqueue(int core, int key, int activity, int pid) } spin_unlock(&mali_activities_lock); - if (!count) { + if (!count) gator_marshal_activity_switch(core, key, activity, pid); - } } static void mali_activity_stop(int core, int key) @@ -129,12 +128,11 @@ static void mali_activity_stop(int core, int key) spin_unlock(&mali_activities_lock); gator_marshal_activity_switch(core, key, 0, 0); - if (count) { + if (count) gator_marshal_activity_switch(core, key, last_activity, last_pid); - } } -void mali_activity_clear(mali_counter mali_activity[], size_t mali_activity_size) +void mali_activity_clear(struct mali_counter mali_activity[], size_t mali_activity_size) { int activity; int cores; @@ -142,12 +140,13 @@ void mali_activity_clear(mali_counter mali_activity[], size_t mali_activity_size for (activity = 0; activity < mali_activity_size; ++activity) { cores = mali_activity[activity].cores; - if (cores < 0) { + if (cores < 0) cores = 1; - } for (core = 0; core < cores; ++core) { if (mali_activity[activity].enabled) { + preempt_disable(); gator_marshal_activity_switch(core, mali_activity[activity].key, 0, 0); + preempt_enable(); } } } @@ -155,7 +154,7 @@ void mali_activity_clear(mali_counter mali_activity[], size_t mali_activity_size #endif -#if defined(MALI_SUPPORT) && (MALI_SUPPORT != MALI_T6xx) +#if defined(MALI_SUPPORT) && (MALI_SUPPORT != MALI_MIDGARD) #include "gator_events_mali_4xx.h" /* @@ -183,40 +182,36 @@ enum { EVENT_REASON_SINGLE_GPU_FREQ_VOLT_CHANGE = 1, }; -mali_counter mali_activity[2]; +struct mali_counter mali_activity[2]; GATOR_DEFINE_PROBE(mali_timeline_event, TP_PROTO(unsigned int event_id, unsigned int d0, unsigned int d1, unsigned int d2, unsigned int d3, unsigned int d4)) { unsigned int component, state; - // do as much work as possible before disabling interrupts - component = (event_id >> 16) & 0xFF; // component is an 8-bit field - state = (event_id >> 24) & 0xF; // state is a 4-bit field + /* do as much work as possible before disabling interrupts */ + component = (event_id >> 16) & 0xFF; /* component is an 8-bit field */ + state = (event_id >> 24) & 0xF; /* state is a 4-bit field */ switch (state) { case EVENT_TYPE_START: if (component == EVENT_CHANNEL_VP0) { /* tgid = d0; pid = d1; */ - if (mali_activity[1].enabled) { + if (mali_activity[1].enabled) mali_activity_enqueue(0, mali_activity[1].key, 1, d1); - } } else if (component >= EVENT_CHANNEL_FP0 && component <= EVENT_CHANNEL_FP7) { /* tgid = d0; pid = d1; */ - if (mali_activity[0].enabled) { + if (mali_activity[0].enabled) mali_activity_enqueue(component - EVENT_CHANNEL_FP0, mali_activity[0].key, 1, d1); - } } break; case EVENT_TYPE_STOP: if (component == EVENT_CHANNEL_VP0) { - if (mali_activity[1].enabled) { + if (mali_activity[1].enabled) mali_activity_stop(0, mali_activity[1].key); - } } else if (component >= EVENT_CHANNEL_FP0 && component <= EVENT_CHANNEL_FP7) { - if (mali_activity[0].enabled) { + if (mali_activity[0].enabled) mali_activity_stop(component - EVENT_CHANNEL_FP0, mali_activity[0].key); - } } break; @@ -224,9 +219,8 @@ GATOR_DEFINE_PROBE(mali_timeline_event, TP_PROTO(unsigned int event_id, unsigned if (component == EVENT_CHANNEL_GPU) { unsigned int reason = (event_id & 0xffff); - if (reason == EVENT_REASON_SINGLE_GPU_FREQ_VOLT_CHANGE) { + if (reason == EVENT_REASON_SINGLE_GPU_FREQ_VOLT_CHANGE) gator_events_mali_log_dvfs_event(d0, d1); - } } break; @@ -236,9 +230,9 @@ GATOR_DEFINE_PROBE(mali_timeline_event, TP_PROTO(unsigned int event_id, unsigned } #endif -#if defined(MALI_SUPPORT) && (MALI_SUPPORT == MALI_T6xx) +#if defined(MALI_SUPPORT) && (MALI_SUPPORT == MALI_MIDGARD) -mali_counter mali_activity[3]; +struct mali_counter mali_activity[3]; #if defined(MALI_JOB_SLOTS_EVENT_CHANGED) GATOR_DEFINE_PROBE(mali_job_slots_event, TP_PROTO(unsigned int event_id, unsigned int tgid, unsigned int pid, unsigned char job_id)) @@ -251,8 +245,8 @@ GATOR_DEFINE_PROBE(mali_job_slots_event, TP_PROTO(unsigned int event_id, unsigne unsigned char job_id = 0; #endif - component = (event_id >> 16) & 0xFF; // component is an 8-bit field - state = (event_id >> 24) & 0xF; // state is a 4-bit field + component = (event_id >> 16) & 0xFF; /* component is an 8-bit field */ + state = (event_id >> 24) & 0xF; /* state is a 4-bit field */ switch (component) { case 0: @@ -271,15 +265,13 @@ GATOR_DEFINE_PROBE(mali_job_slots_event, TP_PROTO(unsigned int event_id, unsigne if (unit != GPU_UNIT_NONE) { switch (state) { case EVENT_TYPE_START: - if (mali_activity[component].enabled) { + if (mali_activity[component].enabled) mali_activity_enqueue(0, mali_activity[component].key, 1, (pid != 0 ? pid : tgid)); - } break; case EVENT_TYPE_STOP: - default: // Some jobs can be soft-stopped, so ensure that this terminates the activity trace. - if (mali_activity[component].enabled) { + default: /* Some jobs can be soft-stopped, so ensure that this terminates the activity trace. */ + if (mali_activity[component].enabled) mali_activity_stop(0, mali_activity[component].key); - } break; } } @@ -298,18 +290,16 @@ static int gator_trace_gpu_start(void) #endif mali_timeline_trace_registered = mali_job_slots_trace_registered = 0; -#if defined(MALI_SUPPORT) && (MALI_SUPPORT != MALI_T6xx) +#if defined(MALI_SUPPORT) && (MALI_SUPPORT != MALI_MIDGARD) mali_activity_clear(mali_activity, ARRAY_SIZE(mali_activity)); - if (!GATOR_REGISTER_TRACE(mali_timeline_event)) { + if (!GATOR_REGISTER_TRACE(mali_timeline_event)) mali_timeline_trace_registered = 1; - } #endif -#if defined(MALI_SUPPORT) && (MALI_SUPPORT == MALI_T6xx) +#if defined(MALI_SUPPORT) && (MALI_SUPPORT == MALI_MIDGARD) mali_activity_clear(mali_activity, ARRAY_SIZE(mali_activity)); - if (!GATOR_REGISTER_TRACE(mali_job_slots_event)) { + if (!GATOR_REGISTER_TRACE(mali_job_slots_event)) mali_job_slots_trace_registered = 1; - } #endif return 0; @@ -317,16 +307,14 @@ static int gator_trace_gpu_start(void) static void gator_trace_gpu_stop(void) { -#if defined(MALI_SUPPORT) && (MALI_SUPPORT != MALI_T6xx) - if (mali_timeline_trace_registered) { +#if defined(MALI_SUPPORT) && (MALI_SUPPORT != MALI_MIDGARD) + if (mali_timeline_trace_registered) GATOR_UNREGISTER_TRACE(mali_timeline_event); - } #endif -#if defined(MALI_SUPPORT) && (MALI_SUPPORT == MALI_T6xx) - if (mali_job_slots_trace_registered) { +#if defined(MALI_SUPPORT) && (MALI_SUPPORT == MALI_MIDGARD) + if (mali_job_slots_trace_registered) GATOR_UNREGISTER_TRACE(mali_job_slots_event); - } #endif mali_timeline_trace_registered = mali_job_slots_trace_registered = 0; diff --git a/drivers/gator/gator_trace_power.c b/drivers/gator/gator_trace_power.c index f2754b1c2b56..46e04b29a187 100644 --- a/drivers/gator/gator_trace_power.c +++ b/drivers/gator/gator_trace_power.c @@ -22,18 +22,20 @@ #endif -// cpu_frequency and cpu_idle trace points were introduced in Linux kernel v2.6.38 -// the now deprecated power_frequency trace point was available prior to 2.6.38, but only for x86 +/* cpu_frequency and cpu_idle trace points were introduced in Linux + * kernel v2.6.38 the now deprecated power_frequency trace point was + * available prior to 2.6.38, but only for x86 + */ #if GATOR_CPU_FREQ_SUPPORT enum { POWER_CPU_FREQ, - POWER_CPU_IDLE, POWER_TOTAL }; static DEFINE_PER_CPU(ulong, idle_prev_state); static ulong power_cpu_enabled[POWER_TOTAL]; static ulong power_cpu_key[POWER_TOTAL]; +static ulong power_cpu_cores; static int gator_trace_power_create_files(struct super_block *sb, struct dentry *root) { @@ -41,8 +43,9 @@ static int gator_trace_power_create_files(struct super_block *sb, struct dentry int cpu; bool found_nonzero_freq = false; - // Even if CONFIG_CPU_FREQ is defined, it still may not be used. Check - // for non-zero values from cpufreq_quick_get + /* Even if CONFIG_CPU_FREQ is defined, it still may not be + * used. Check for non-zero values from cpufreq_quick_get + */ for_each_online_cpu(cpu) { if (cpufreq_quick_get(cpu) > 0) { found_nonzero_freq = true; @@ -51,27 +54,18 @@ static int gator_trace_power_create_files(struct super_block *sb, struct dentry } if (found_nonzero_freq) { - // cpu_frequency + /* cpu_frequency */ dir = gatorfs_mkdir(sb, root, "Linux_power_cpu_freq"); - if (!dir) { + if (!dir) return -1; - } gatorfs_create_ulong(sb, dir, "enabled", &power_cpu_enabled[POWER_CPU_FREQ]); gatorfs_create_ro_ulong(sb, dir, "key", &power_cpu_key[POWER_CPU_FREQ]); } - // cpu_idle - dir = gatorfs_mkdir(sb, root, "Linux_power_cpu_idle"); - if (!dir) { - return -1; - } - gatorfs_create_ulong(sb, dir, "enabled", &power_cpu_enabled[POWER_CPU_IDLE]); - gatorfs_create_ro_ulong(sb, dir, "key", &power_cpu_key[POWER_CPU_IDLE]); - return 0; } -// 'cpu' may not equal smp_processor_id(), i.e. may not be running on the core that is having the freq/idle state change +/* 'cpu' may not equal smp_processor_id(), i.e. may not be running on the core that is having the freq/idle state change */ GATOR_DEFINE_PROBE(cpu_frequency, TP_PROTO(unsigned int frequency, unsigned int cpu)) { cpu = lcpu_to_pcpu(cpu); @@ -82,56 +76,50 @@ GATOR_DEFINE_PROBE(cpu_idle, TP_PROTO(unsigned int state, unsigned int cpu)) { cpu = lcpu_to_pcpu(cpu); - if (state == per_cpu(idle_prev_state, cpu)) { + if (state == per_cpu(idle_prev_state, cpu)) return; - } if (implements_wfi()) { if (state == PWR_EVENT_EXIT) { - // transition from wfi to non-wfi + /* transition from wfi to non-wfi */ marshal_idle(cpu, MESSAGE_IDLE_EXIT); } else { - // transition from non-wfi to wfi + /* transition from non-wfi to wfi */ marshal_idle(cpu, MESSAGE_IDLE_ENTER); } } per_cpu(idle_prev_state, cpu) = state; - - if (power_cpu_enabled[POWER_CPU_IDLE]) { - // Increment state so that no negative numbers are sent - marshal_event_single(cpu, power_cpu_key[POWER_CPU_IDLE], state + 1); - } } static void gator_trace_power_online(void) { int pcpu = get_physical_cpu(); int lcpu = get_logical_cpu(); - if (power_cpu_enabled[POWER_CPU_FREQ]) { + + if (power_cpu_enabled[POWER_CPU_FREQ]) marshal_event_single64(pcpu, power_cpu_key[POWER_CPU_FREQ], cpufreq_quick_get(lcpu) * 1000L); - } } static void gator_trace_power_offline(void) { - // Set frequency to zero on an offline + /* Set frequency to zero on an offline */ int cpu = get_physical_cpu(); - if (power_cpu_enabled[POWER_CPU_FREQ]) { + + if (power_cpu_enabled[POWER_CPU_FREQ]) marshal_event_single(cpu, power_cpu_key[POWER_CPU_FREQ], 0); - } } static int gator_trace_power_start(void) { int cpu; - // register tracepoints + /* register tracepoints */ if (power_cpu_enabled[POWER_CPU_FREQ]) if (GATOR_REGISTER_TRACE(cpu_frequency)) goto fail_cpu_frequency_exit; - // Always register for cpu:idle for detecting WFI, independent of power_cpu_enabled[POWER_CPU_IDLE] + /* Always register for cpu_idle for detecting WFI */ if (GATOR_REGISTER_TRACE(cpu_idle)) goto fail_cpu_idle_exit; pr_debug("gator: registered power event tracepoints\n"); @@ -142,7 +130,7 @@ static int gator_trace_power_start(void) return 0; - // unregister tracepoints on error + /* unregister tracepoints on error */ fail_cpu_idle_exit: if (power_cpu_enabled[POWER_CPU_FREQ]) GATOR_UNREGISTER_TRACE(cpu_frequency); @@ -161,14 +149,15 @@ static void gator_trace_power_stop(void) GATOR_UNREGISTER_TRACE(cpu_idle); pr_debug("gator: unregistered power event tracepoints\n"); - for (i = 0; i < POWER_TOTAL; i++) { + for (i = 0; i < POWER_TOTAL; i++) power_cpu_enabled[i] = 0; - } } static void gator_trace_power_init(void) { int i; + + power_cpu_cores = nr_cpu_ids; for (i = 0; i < POWER_TOTAL; i++) { power_cpu_enabled[i] = 0; power_cpu_key[i] = gator_events_get_key(); diff --git a/drivers/gator/gator_trace_sched.c b/drivers/gator/gator_trace_sched.c index 655008628933..6d7cbd7348e1 100644 --- a/drivers/gator/gator_trace_sched.c +++ b/drivers/gator/gator_trace_sched.c @@ -8,6 +8,10 @@ */ #include <trace/events/sched.h> +#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0) +#include <trace/events/task.h> +#endif + #include "gator.h" #define TASK_MAP_ENTRIES 1024 /* must be power of 2 */ @@ -23,8 +27,10 @@ enum { static DEFINE_PER_CPU(uint64_t *, taskname_keys); static DEFINE_PER_CPU(int, collecting); -// this array is never read as the cpu wait charts are derived counters -// the files are needed, nonetheless, to show that these counters are available +/* this array is never read as the cpu wait charts are derived + * counters the files are needed, nonetheless, to show that these + * counters are available + */ static ulong cpu_wait_enabled[CPU_WAIT_TOTAL]; static ulong sched_cpu_key[CPU_WAIT_TOTAL]; @@ -32,26 +38,24 @@ static int sched_trace_create_files(struct super_block *sb, struct dentry *root) { struct dentry *dir; - // CPU Wait - Contention + /* CPU Wait - Contention */ dir = gatorfs_mkdir(sb, root, "Linux_cpu_wait_contention"); - if (!dir) { + if (!dir) return -1; - } gatorfs_create_ulong(sb, dir, "enabled", &cpu_wait_enabled[STATE_CONTENTION]); gatorfs_create_ro_ulong(sb, dir, "key", &sched_cpu_key[STATE_CONTENTION]); - // CPU Wait - I/O + /* CPU Wait - I/O */ dir = gatorfs_mkdir(sb, root, "Linux_cpu_wait_io"); - if (!dir) { + if (!dir) return -1; - } gatorfs_create_ulong(sb, dir, "enabled", &cpu_wait_enabled[STATE_WAIT_ON_IO]); gatorfs_create_ro_ulong(sb, dir, "key", &sched_cpu_key[STATE_WAIT_ON_IO]); return 0; } -static void emit_pid_name(struct task_struct *task) +static void emit_pid_name(const char *comm, struct task_struct *task) { bool found = false; char taskcomm[TASK_COMM_LEN + 3]; @@ -59,10 +63,10 @@ static void emit_pid_name(struct task_struct *task) uint64_t *keys = &(per_cpu(taskname_keys, cpu)[(task->pid & 0xFF) * TASK_MAX_COLLISIONS]); uint64_t value; - value = gator_chksum_crc32(task->comm); + value = gator_chksum_crc32(comm); value = (value << 32) | (uint32_t)task->pid; - // determine if the thread name was emitted already + /* determine if the thread name was emitted already */ for (x = 0; x < TASK_MAX_COLLISIONS; x++) { if (keys[x] == value) { found = true; @@ -71,17 +75,18 @@ static void emit_pid_name(struct task_struct *task) } if (!found) { - // shift values, new value always in front + /* shift values, new value always in front */ uint64_t oldv, newv = value; + for (x = 0; x < TASK_MAX_COLLISIONS; x++) { oldv = keys[x]; keys[x] = newv; newv = oldv; } - // emit pid names, cannot use get_task_comm, as it's not exported on all kernel versions - if (strlcpy(taskcomm, task->comm, TASK_COMM_LEN) == TASK_COMM_LEN - 1) { - // append ellipses if task->comm has length of TASK_COMM_LEN - 1 + /* emit pid names, cannot use get_task_comm, as it's not exported on all kernel versions */ + if (strlcpy(taskcomm, comm, TASK_COMM_LEN) == TASK_COMM_LEN - 1) { + /* append ellipses if comm has length of TASK_COMM_LEN - 1 */ strcat(taskcomm, "..."); } @@ -89,7 +94,7 @@ static void emit_pid_name(struct task_struct *task) } } -static void collect_counters(u64 time, struct task_struct *task) +static void collect_counters(u64 time, struct task_struct *task, bool sched_switch) { int *buffer, len, cpu = get_physical_cpu(); long long *buffer64; @@ -98,7 +103,7 @@ static void collect_counters(u64 time, struct task_struct *task) if (marshal_event_header(time)) { list_for_each_entry(gi, &gator_events, list) { if (gi->read) { - len = gi->read(&buffer); + len = gi->read(&buffer, sched_switch); marshal_event(len, buffer); } else if (gi->read64) { len = gi->read64(&buffer64); @@ -109,22 +114,26 @@ static void collect_counters(u64 time, struct task_struct *task) marshal_event64(len, buffer64); } } - // Only check after writing all counters so that time and corresponding counters appear in the same frame + if (cpu == 0) + gator_emit_perf_time(time); + /* Only check after writing all counters so that time and corresponding counters appear in the same frame */ buffer_check(cpu, BLOCK_COUNTER_BUF, time); - // Commit buffers on timeout + /* Commit buffers on timeout */ if (gator_live_rate > 0 && time >= per_cpu(gator_buffer_commit_time, cpu)) { static const int buftypes[] = { NAME_BUF, COUNTER_BUF, BLOCK_COUNTER_BUF, SCHED_TRACE_BUF, ACTIVITY_BUF }; int i; - for (i = 0; i < ARRAY_SIZE(buftypes); ++i) { + for (i = 0; i < ARRAY_SIZE(buftypes); ++i) gator_commit_buffer(cpu, buftypes[i], time); - } - // spinlocks are noops on uniprocessor machines and mutexes do not work in sched_switch context in - // RT-Preempt full, so disable proactive flushing of the annotate frame on uniprocessor machines. + /* spinlocks are noops on uniprocessor machines and mutexes do + * not work in sched_switch context in RT-Preempt full, so + * disable proactive flushing of the annotate frame on + * uniprocessor machines. + */ #ifdef CONFIG_SMP - // Try to preemptively flush the annotate buffer to reduce the chance of the buffer being full + /* Try to preemptively flush the annotate buffer to reduce the chance of the buffer being full */ if (on_primary_core() && spin_trylock(&annotate_lock)) { gator_commit_buffer(0, ANNOTATE_BUF, time); spin_unlock(&annotate_lock); @@ -134,7 +143,7 @@ static void collect_counters(u64 time, struct task_struct *task) } } -// special case used during a suspend of the system +/* special case used during a suspend of the system */ static void trace_sched_insert_idle(void) { marshal_sched_trace_switch(0, 0); @@ -146,7 +155,7 @@ static void gator_trace_emit_link(struct task_struct *p) int cpu = get_physical_cpu(); cookie = get_exec_cookie(cpu, p); - emit_pid_name(p); + emit_pid_name(p->comm, p); marshal_link(cookie, p->tgid, p->pid); } @@ -161,6 +170,15 @@ GATOR_DEFINE_PROBE(sched_process_exec, TP_PROTO(struct task_struct *p, pid_t old { gator_trace_emit_link(p); } + +#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 15, 0) +GATOR_DEFINE_PROBE(task_rename, TP_PROTO(struct task_struct *task, char *comm)) +#else +GATOR_DEFINE_PROBE(task_rename, TP_PROTO(struct task_struct *task, const char *comm)) +#endif +{ + emit_pid_name(comm, task); +} #endif #if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 35) @@ -174,17 +192,16 @@ GATOR_DEFINE_PROBE(sched_switch, TP_PROTO(struct task_struct *prev, struct task_ per_cpu(in_scheduler_context, cpu) = true; - // do as much work as possible before disabling interrupts - if (prev->state == TASK_RUNNING) { + /* do as much work as possible before disabling interrupts */ + if (prev->state == TASK_RUNNING) state = STATE_CONTENTION; - } else if (prev->in_iowait) { + else if (prev->in_iowait) state = STATE_WAIT_ON_IO; - } else { + else state = STATE_WAIT_ON_OTHER; - } per_cpu(collecting, cpu) = 1; - collect_counters(gator_get_time(), prev); + collect_counters(gator_get_time(), prev, true); per_cpu(collecting, cpu) = 0; #if LINUX_VERSION_CODE < KERNEL_VERSION(3, 4, 0) @@ -202,18 +219,20 @@ GATOR_DEFINE_PROBE(sched_process_free, TP_PROTO(struct task_struct *p)) static void do_nothing(void *info) { - // Intentionally do nothing + /* Intentionally do nothing */ (void)info; } static int register_scheduler_tracepoints(void) { - // register tracepoints + /* register tracepoints */ if (GATOR_REGISTER_TRACE(sched_process_fork)) goto fail_sched_process_fork; #if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0) if (GATOR_REGISTER_TRACE(sched_process_exec)) goto fail_sched_process_exec; + if (GATOR_REGISTER_TRACE(task_rename)) + goto fail_task_rename; #endif if (GATOR_REGISTER_TRACE(sched_switch)) goto fail_sched_switch; @@ -221,21 +240,24 @@ static int register_scheduler_tracepoints(void) goto fail_sched_process_free; pr_debug("gator: registered tracepoints\n"); - // Now that the scheduler tracepoint is registered, force a context switch - // on all cpus to capture what is currently running. + /* Now that the scheduler tracepoint is registered, force a context + * switch on all cpus to capture what is currently running. + */ on_each_cpu(do_nothing, NULL, 0); return 0; - // unregister tracepoints on error + /* unregister tracepoints on error */ fail_sched_process_free: GATOR_UNREGISTER_TRACE(sched_switch); fail_sched_switch: - GATOR_UNREGISTER_TRACE(sched_process_fork); #if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0) -fail_sched_process_exec: + GATOR_UNREGISTER_TRACE(task_rename); +fail_task_rename: GATOR_UNREGISTER_TRACE(sched_process_exec); +fail_sched_process_exec: #endif + GATOR_UNREGISTER_TRACE(sched_process_fork); fail_sched_process_fork: pr_err("gator: tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n"); @@ -247,6 +269,7 @@ static void unregister_scheduler_tracepoints(void) GATOR_UNREGISTER_TRACE(sched_process_fork); #if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0) GATOR_UNREGISTER_TRACE(sched_process_exec); + GATOR_UNREGISTER_TRACE(task_rename); #endif GATOR_UNREGISTER_TRACE(sched_switch); GATOR_UNREGISTER_TRACE(sched_process_free); @@ -271,7 +294,7 @@ static int gator_trace_sched_start(void) for_each_present_cpu(cpu) { size = TASK_MAP_ENTRIES * TASK_MAX_COLLISIONS * sizeof(uint64_t); - per_cpu(taskname_keys, cpu) = (uint64_t *)kmalloc(size, GFP_KERNEL); + per_cpu(taskname_keys, cpu) = kmalloc(size, GFP_KERNEL); if (!per_cpu(taskname_keys, cpu)) return -1; memset(per_cpu(taskname_keys, cpu), 0, size); @@ -290,6 +313,7 @@ static void gator_trace_sched_offline(void) static void gator_trace_sched_init(void) { int i; + for (i = 0; i < CPU_WAIT_TOTAL; i++) { cpu_wait_enabled[i] = 0; sched_cpu_key[i] = gator_events_get_key(); diff --git a/drivers/gator/mali/mali_dd_gator_api.h b/drivers/gator/mali/mali_dd_gator_api.h deleted file mode 100644 index 104b34f2d72a..000000000000 --- a/drivers/gator/mali/mali_dd_gator_api.h +++ /dev/null @@ -1,40 +0,0 @@ -#if !defined(MALI_DDK_GATOR_API_VERSION) - #define MALI_DDK_GATOR_API_VERSION 3 -#endif -#if !defined(MALI_TRUE) - #define MALI_TRUE ((unsigned int)1) -#endif - -#if !defined(MALI_FALSE) - #define MALI_FALSE ((unsigned int)0) -#endif - -struct mali_dd_hwcnt_info { - - /* Passed from Gator to kbase */ - //u32 in_mali_dd_hwcnt_version; - unsigned short int bitmask[4]; - - /* Passed from kbase to Gator */ - - /* ptr to counter dump memory */ - void *kernel_dump_buffer; - - /* size of counter dump memory */ - unsigned int size; - - unsigned int gpu_id; - - unsigned int nr_cores; - - unsigned int nr_core_groups; - - /* The cached present bitmaps - these are the same as the corresponding hardware registers*/ - unsigned long int shader_present_bitmap; -}; - -struct mali_dd_hwcnt_handles; -extern struct mali_dd_hwcnt_handles* mali_dd_hwcnt_init(struct mali_dd_hwcnt_info *in_out_info); -extern void mali_dd_hwcnt_clear(struct mali_dd_hwcnt_info *in_out_info, struct mali_dd_hwcnt_handles *opaque_handles); -extern unsigned int kbase_dd_instr_hwcnt_dump_complete(struct mali_dd_hwcnt_handles *opaque_handles, unsigned int * const success); -extern unsigned int kbase_dd_instr_hwcnt_dump_irq(struct mali_dd_hwcnt_handles *opaque_handles); diff --git a/drivers/gator/mali/mali_kbase_gator_api.h b/drivers/gator/mali/mali_kbase_gator_api.h new file mode 100644 index 000000000000..5ed069797e36 --- /dev/null +++ b/drivers/gator/mali/mali_kbase_gator_api.h @@ -0,0 +1,219 @@ +/** + * Copyright (C) ARM Limited 2014. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#ifndef _KBASE_GATOR_API_H_ +#define _KBASE_GATOR_API_H_ + +/** + * @brief This file describes the API used by Gator to collect hardware counters data from a Mali device. + */ + +/* This define is used by the gator kernel module compile to select which DDK + * API calling convention to use. If not defined (legacy DDK) gator assumes + * version 1. The version to DDK release mapping is: + * Version 1 API: DDK versions r1px, r2px + * Version 2 API: DDK versions r3px, r4px + * Version 3 API: DDK version r5p0 and newer + * + * API Usage + * ========= + * + * 1] Call kbase_gator_hwcnt_init_names() to return the list of short counter + * names for the GPU present in this device. + * + * 2] Create a kbase_gator_hwcnt_info structure and set the counter enables for + * the counters you want enabled. The enables can all be set for simplicity in + * most use cases, but disabling some will let you minimize bandwidth impact. + * + * 3] Call kbase_gator_hwcnt_init() using the above structure, to create a + * counter context. On successful return the DDK will have populated the + * structure with a variety of useful information. + * + * 4] Call kbase_gator_hwcnt_dump_irq() to queue a non-blocking request for a + * counter dump. If this returns a non-zero value the request has been queued, + * otherwise the driver has been unable to do so (typically because of another + * user of the instrumentation exists concurrently). + * + * 5] Call kbase_gator_hwcnt_dump_complete() to test whether the previously + * requested dump has been succesful. If this returns non-zero the counter dump + * has resolved, but the value of *success must also be tested as the dump + * may have not been successful. If it returns zero the counter dump was + * abandoned due to the device being busy (typically because of another + * user of the instrumentation exists concurrently). + * + * 6] Process the counters stored in the buffer pointed to by ... + * + * kbase_gator_hwcnt_info->kernel_dump_buffer + * + * In pseudo code you can find all of the counters via this approach: + * + * + * hwcnt_info # pointer to kbase_gator_hwcnt_info structure + * hwcnt_name # pointer to name list + * + * u32 * hwcnt_data = (u32*)hwcnt_info->kernel_dump_buffer + * + * # Iterate over each 64-counter block in this GPU configuration + * for( i = 0; i < hwcnt_info->nr_hwc_blocks; i++) { + * hwc_type type = hwcnt_info->hwc_layout[i]; + * + * # Skip reserved type blocks - they contain no counters at all + * if( type == RESERVED_BLOCK ) { + * continue; + * } + * + * size_t name_offset = type * 64; + * size_t data_offset = i * 64; + * + * # Iterate over the names of the counters in this block type + * for( j = 0; j < 64; j++) { + * const char * name = hwcnt_name[name_offset+j]; + * + * # Skip empty name strings - there is no counter here + * if( name[0] == '\0' ) { + * continue; + * } + * + * u32 data = hwcnt_data[data_offset+j]; + * + * printk( "COUNTER: %s DATA: %u\n", name, data ); + * } + * } + * + * + * Note that in most implementations you typically want to either SUM or + * AVERAGE multiple instances of the same counter if, for example, you have + * multiple shader cores or multiple L2 caches. The most sensible view for + * analysis is to AVERAGE shader core counters, but SUM L2 cache and MMU + * counters. + * + * 7] Goto 4, repeating until you want to stop collecting counters. + * + * 8] Release the dump resources by calling kbase_gator_hwcnt_term(). + * + * 9] Release the name table resources by calling kbase_gator_hwcnt_term_names(). + * This function must only be called if init_names() returned a non-NULL value. + **/ + +#define MALI_DDK_GATOR_API_VERSION 3 + +#if !defined(MALI_TRUE) + #define MALI_TRUE ((uint32_t)1) +#endif + +#if !defined(MALI_FALSE) + #define MALI_FALSE ((uint32_t)0) +#endif + +enum hwc_type { + JM_BLOCK = 0, + TILER_BLOCK, + SHADER_BLOCK, + MMU_L2_BLOCK, + RESERVED_BLOCK +}; + +struct kbase_gator_hwcnt_info { + + /* Passed from Gator to kbase */ + + /* the bitmask of enabled hardware counters for each counter block */ + uint16_t bitmask[4]; + + /* Passed from kbase to Gator */ + + /* ptr to counter dump memory */ + void *kernel_dump_buffer; + + /* size of counter dump memory */ + uint32_t size; + + /* the ID of the Mali device */ + uint32_t gpu_id; + + /* the number of shader cores in the GPU */ + uint32_t nr_cores; + + /* the number of core groups */ + uint32_t nr_core_groups; + + /* the memory layout of the performance counters */ + enum hwc_type *hwc_layout; + + /* the total number of hardware couter blocks */ + uint32_t nr_hwc_blocks; +}; + +/** + * @brief Opaque block of Mali data which Gator needs to return to the API later. + */ +struct kbase_gator_hwcnt_handles; + +/** + * @brief Initialize the resources Gator needs for performance profiling. + * + * @param in_out_info A pointer to a structure containing the enabled counters passed from Gator and all the Mali + * specific information that will be returned to Gator. On entry Gator must have populated the + * 'bitmask' field with the counters it wishes to enable for each class of counter block. + * Each entry in the array corresponds to a single counter class based on the "hwc_type" + * enumeration, and each bit corresponds to an enable for 4 sequential counters (LSB enables + * the first 4 counters in the block, and so on). See the GPU counter array as returned by + * kbase_gator_hwcnt_get_names() for the index values of each counter for the curernt GPU. + * + * @return Pointer to an opaque handle block on success, NULL on error. + */ +extern struct kbase_gator_hwcnt_handles *kbase_gator_hwcnt_init(struct kbase_gator_hwcnt_info *in_out_info); + +/** + * @brief Free all resources once Gator has finished using performance counters. + * + * @param in_out_info A pointer to a structure containing the enabled counters passed from Gator and all the + * Mali specific information that will be returned to Gator. + * @param opaque_handles A wrapper structure for kbase structures. + */ +extern void kbase_gator_hwcnt_term(struct kbase_gator_hwcnt_info *in_out_info, struct kbase_gator_hwcnt_handles *opaque_handles); + +/** + * @brief Poll whether a counter dump is successful. + * + * @param opaque_handles A wrapper structure for kbase structures. + * @param[out] success Non-zero on success, zero on failure. + * + * @return Zero if the dump is still pending, non-zero if the dump has completed. Note that a + * completed dump may not have dumped succesfully, so the caller must test for both + * a completed and successful dump before processing counters. + */ +extern uint32_t kbase_gator_instr_hwcnt_dump_complete(struct kbase_gator_hwcnt_handles *opaque_handles, uint32_t * const success); + +/** + * @brief Request the generation of a new counter dump. + * + * @param opaque_handles A wrapper structure for kbase structures. + * + * @return Zero if the hardware device is busy and cannot handle the request, non-zero otherwise. + */ +extern uint32_t kbase_gator_instr_hwcnt_dump_irq(struct kbase_gator_hwcnt_handles *opaque_handles); + +/** + * @brief This function is used to fetch the names table based on the Mali device in use. + * + * @param[out] total_number_of_counters The total number of counters short names in the Mali devices' list. + * + * @return Pointer to an array of strings of length *total_number_of_counters. + */ +extern const char * const *kbase_gator_hwcnt_init_names(uint32_t *total_number_of_counters); + +/** + * @brief This function is used to terminate the use of the names table. + * + * This function must only be called if the initial call to kbase_gator_hwcnt_init_names returned a non-NULL value. + */ +extern void kbase_gator_hwcnt_term_names(void); + +#endif diff --git a/drivers/gator/mali/mali_mjollnir_profiling_gator_api.h b/drivers/gator/mali/mali_mjollnir_profiling_gator_api.h index ff00d90cee78..2bc0b037eee6 100644 --- a/drivers/gator/mali/mali_mjollnir_profiling_gator_api.h +++ b/drivers/gator/mali/mali_mjollnir_profiling_gator_api.h @@ -23,83 +23,82 @@ extern "C" #define MAX_NUM_VP_CORES (1) #define MAX_NUM_L2_CACHE_CORES (1) -enum counters -{ - /* Timeline activity */ - ACTIVITY_VP_0 = 0, - ACTIVITY_FP_0, - ACTIVITY_FP_1, - ACTIVITY_FP_2, - ACTIVITY_FP_3, - - /* L2 cache counters */ - COUNTER_L2_0_C0, - COUNTER_L2_0_C1, - - /* Vertex processor counters */ - COUNTER_VP_0_C0, - COUNTER_VP_0_C1, - - /* Fragment processor counters */ - COUNTER_FP_0_C0, - COUNTER_FP_0_C1, - COUNTER_FP_1_C0, - COUNTER_FP_1_C1, - COUNTER_FP_2_C0, - COUNTER_FP_2_C1, - COUNTER_FP_3_C0, - COUNTER_FP_3_C1, - - /* EGL Software Counters */ - COUNTER_EGL_BLIT_TIME, - - /* GLES Software Counters */ - COUNTER_GLES_DRAW_ELEMENTS_CALLS, - COUNTER_GLES_DRAW_ELEMENTS_NUM_INDICES, - COUNTER_GLES_DRAW_ELEMENTS_NUM_TRANSFORMED, - COUNTER_GLES_DRAW_ARRAYS_CALLS, - COUNTER_GLES_DRAW_ARRAYS_NUM_TRANSFORMED, - COUNTER_GLES_DRAW_POINTS, - COUNTER_GLES_DRAW_LINES, - COUNTER_GLES_DRAW_LINE_LOOP, - COUNTER_GLES_DRAW_LINE_STRIP, - COUNTER_GLES_DRAW_TRIANGLES, - COUNTER_GLES_DRAW_TRIANGLE_STRIP, - COUNTER_GLES_DRAW_TRIANGLE_FAN, - COUNTER_GLES_NON_VBO_DATA_COPY_TIME, - COUNTER_GLES_UNIFORM_BYTES_COPIED_TO_MALI, - COUNTER_GLES_UPLOAD_TEXTURE_TIME, - COUNTER_GLES_UPLOAD_VBO_TIME, - COUNTER_GLES_NUM_FLUSHES, - COUNTER_GLES_NUM_VSHADERS_GENERATED, - COUNTER_GLES_NUM_FSHADERS_GENERATED, - COUNTER_GLES_VSHADER_GEN_TIME, - COUNTER_GLES_FSHADER_GEN_TIME, - COUNTER_GLES_INPUT_TRIANGLES, - COUNTER_GLES_VXCACHE_HIT, - COUNTER_GLES_VXCACHE_MISS, - COUNTER_GLES_VXCACHE_COLLISION, - COUNTER_GLES_CULLED_TRIANGLES, - COUNTER_GLES_CULLED_LINES, - COUNTER_GLES_BACKFACE_TRIANGLES, - COUNTER_GLES_GBCLIP_TRIANGLES, - COUNTER_GLES_GBCLIP_LINES, - COUNTER_GLES_TRIANGLES_DRAWN, - COUNTER_GLES_DRAWCALL_TIME, - COUNTER_GLES_TRIANGLES_COUNT, - COUNTER_GLES_INDEPENDENT_TRIANGLES_COUNT, - COUNTER_GLES_STRIP_TRIANGLES_COUNT, - COUNTER_GLES_FAN_TRIANGLES_COUNT, - COUNTER_GLES_LINES_COUNT, - COUNTER_GLES_INDEPENDENT_LINES_COUNT, - COUNTER_GLES_STRIP_LINES_COUNT, - COUNTER_GLES_LOOP_LINES_COUNT, - - COUNTER_FILMSTRIP, - COUNTER_FREQUENCY, - COUNTER_VOLTAGE, - - NUMBER_OF_EVENTS +enum counters { + /* Timeline activity */ + ACTIVITY_VP_0 = 0, + ACTIVITY_FP_0, + ACTIVITY_FP_1, + ACTIVITY_FP_2, + ACTIVITY_FP_3, + + /* L2 cache counters */ + COUNTER_L2_0_C0, + COUNTER_L2_0_C1, + + /* Vertex processor counters */ + COUNTER_VP_0_C0, + COUNTER_VP_0_C1, + + /* Fragment processor counters */ + COUNTER_FP_0_C0, + COUNTER_FP_0_C1, + COUNTER_FP_1_C0, + COUNTER_FP_1_C1, + COUNTER_FP_2_C0, + COUNTER_FP_2_C1, + COUNTER_FP_3_C0, + COUNTER_FP_3_C1, + + /* EGL Software Counters */ + COUNTER_EGL_BLIT_TIME, + + /* GLES Software Counters */ + COUNTER_GLES_DRAW_ELEMENTS_CALLS, + COUNTER_GLES_DRAW_ELEMENTS_NUM_INDICES, + COUNTER_GLES_DRAW_ELEMENTS_NUM_TRANSFORMED, + COUNTER_GLES_DRAW_ARRAYS_CALLS, + COUNTER_GLES_DRAW_ARRAYS_NUM_TRANSFORMED, + COUNTER_GLES_DRAW_POINTS, + COUNTER_GLES_DRAW_LINES, + COUNTER_GLES_DRAW_LINE_LOOP, + COUNTER_GLES_DRAW_LINE_STRIP, + COUNTER_GLES_DRAW_TRIANGLES, + COUNTER_GLES_DRAW_TRIANGLE_STRIP, + COUNTER_GLES_DRAW_TRIANGLE_FAN, + COUNTER_GLES_NON_VBO_DATA_COPY_TIME, + COUNTER_GLES_UNIFORM_BYTES_COPIED_TO_MALI, + COUNTER_GLES_UPLOAD_TEXTURE_TIME, + COUNTER_GLES_UPLOAD_VBO_TIME, + COUNTER_GLES_NUM_FLUSHES, + COUNTER_GLES_NUM_VSHADERS_GENERATED, + COUNTER_GLES_NUM_FSHADERS_GENERATED, + COUNTER_GLES_VSHADER_GEN_TIME, + COUNTER_GLES_FSHADER_GEN_TIME, + COUNTER_GLES_INPUT_TRIANGLES, + COUNTER_GLES_VXCACHE_HIT, + COUNTER_GLES_VXCACHE_MISS, + COUNTER_GLES_VXCACHE_COLLISION, + COUNTER_GLES_CULLED_TRIANGLES, + COUNTER_GLES_CULLED_LINES, + COUNTER_GLES_BACKFACE_TRIANGLES, + COUNTER_GLES_GBCLIP_TRIANGLES, + COUNTER_GLES_GBCLIP_LINES, + COUNTER_GLES_TRIANGLES_DRAWN, + COUNTER_GLES_DRAWCALL_TIME, + COUNTER_GLES_TRIANGLES_COUNT, + COUNTER_GLES_INDEPENDENT_TRIANGLES_COUNT, + COUNTER_GLES_STRIP_TRIANGLES_COUNT, + COUNTER_GLES_FAN_TRIANGLES_COUNT, + COUNTER_GLES_LINES_COUNT, + COUNTER_GLES_INDEPENDENT_LINES_COUNT, + COUNTER_GLES_STRIP_LINES_COUNT, + COUNTER_GLES_LOOP_LINES_COUNT, + + COUNTER_FILMSTRIP, + COUNTER_FREQUENCY, + COUNTER_VOLTAGE, + + NUMBER_OF_EVENTS }; #define FIRST_ACTIVITY_EVENT ACTIVITY_VP_0 @@ -117,34 +116,31 @@ enum counters /** * Structure to pass performance counter data of a Mali core */ -typedef struct _mali_profiling_core_counters -{ - u32 source0; - u32 value0; - u32 source1; - u32 value1; -} _mali_profiling_core_counters; +struct _mali_profiling_core_counters { + u32 source0; + u32 value0; + u32 source1; + u32 value1; +}; /* * For compatibility with utgard. */ -typedef struct _mali_profiling_l2_counter_values -{ - struct _mali_profiling_core_counters cores[MAX_NUM_L2_CACHE_CORES]; -} _mali_profiling_l2_counter_values; +struct _mali_profiling_l2_counter_values { + struct _mali_profiling_core_counters cores[MAX_NUM_L2_CACHE_CORES]; +}; -typedef struct _mali_profiling_mali_version -{ - u32 mali_product_id; - u32 mali_version_major; - u32 mali_version_minor; - u32 num_of_l2_cores; - u32 num_of_fp_cores; - u32 num_of_vp_cores; -} _mali_profiling_mali_version; +struct _mali_profiling_mali_version { + u32 mali_product_id; + u32 mali_version_major; + u32 mali_version_minor; + u32 num_of_l2_cores; + u32 num_of_fp_cores; + u32 num_of_vp_cores; +}; extern void _mali_profiling_get_mali_version(struct _mali_profiling_mali_version *values); -extern u32 _mali_profiling_get_l2_counters(_mali_profiling_l2_counter_values *values); +extern u32 _mali_profiling_get_l2_counters(struct _mali_profiling_l2_counter_values *values); /* * List of possible actions allowing DDK to be controlled by Streamline. diff --git a/drivers/gator/mali/mali_utgard_profiling_gator_api.h b/drivers/gator/mali/mali_utgard_profiling_gator_api.h index 43c576042880..d6465312628e 100644 --- a/drivers/gator/mali/mali_utgard_profiling_gator_api.h +++ b/drivers/gator/mali/mali_utgard_profiling_gator_api.h @@ -22,105 +22,104 @@ extern "C" #define MAX_NUM_VP_CORES 1 /** The list of events supported by the Mali DDK. */ -typedef enum -{ - /* Vertex processor activity */ - ACTIVITY_VP_0 = 0, - - /* Fragment processor activity */ - ACTIVITY_FP_0, /* 1 */ - ACTIVITY_FP_1, - ACTIVITY_FP_2, - ACTIVITY_FP_3, - ACTIVITY_FP_4, - ACTIVITY_FP_5, - ACTIVITY_FP_6, - ACTIVITY_FP_7, - - /* L2 cache counters */ - COUNTER_L2_0_C0, - COUNTER_L2_0_C1, - COUNTER_L2_1_C0, - COUNTER_L2_1_C1, - COUNTER_L2_2_C0, - COUNTER_L2_2_C1, - - /* Vertex processor counters */ - COUNTER_VP_0_C0, /*15*/ - COUNTER_VP_0_C1, - - /* Fragment processor counters */ - COUNTER_FP_0_C0, - COUNTER_FP_0_C1, - COUNTER_FP_1_C0, - COUNTER_FP_1_C1, - COUNTER_FP_2_C0, - COUNTER_FP_2_C1, - COUNTER_FP_3_C0, - COUNTER_FP_3_C1, - COUNTER_FP_4_C0, - COUNTER_FP_4_C1, - COUNTER_FP_5_C0, - COUNTER_FP_5_C1, - COUNTER_FP_6_C0, - COUNTER_FP_6_C1, - COUNTER_FP_7_C0, - COUNTER_FP_7_C1, /* 32 */ - - /* - * If more hardware counters are added, the _mali_osk_hw_counter_table - * below should also be updated. - */ - - /* EGL software counters */ - COUNTER_EGL_BLIT_TIME, - - /* GLES software counters */ - COUNTER_GLES_DRAW_ELEMENTS_CALLS, - COUNTER_GLES_DRAW_ELEMENTS_NUM_INDICES, - COUNTER_GLES_DRAW_ELEMENTS_NUM_TRANSFORMED, - COUNTER_GLES_DRAW_ARRAYS_CALLS, - COUNTER_GLES_DRAW_ARRAYS_NUM_TRANSFORMED, - COUNTER_GLES_DRAW_POINTS, - COUNTER_GLES_DRAW_LINES, - COUNTER_GLES_DRAW_LINE_LOOP, - COUNTER_GLES_DRAW_LINE_STRIP, - COUNTER_GLES_DRAW_TRIANGLES, - COUNTER_GLES_DRAW_TRIANGLE_STRIP, - COUNTER_GLES_DRAW_TRIANGLE_FAN, - COUNTER_GLES_NON_VBO_DATA_COPY_TIME, - COUNTER_GLES_UNIFORM_BYTES_COPIED_TO_MALI, - COUNTER_GLES_UPLOAD_TEXTURE_TIME, - COUNTER_GLES_UPLOAD_VBO_TIME, - COUNTER_GLES_NUM_FLUSHES, - COUNTER_GLES_NUM_VSHADERS_GENERATED, - COUNTER_GLES_NUM_FSHADERS_GENERATED, - COUNTER_GLES_VSHADER_GEN_TIME, - COUNTER_GLES_FSHADER_GEN_TIME, - COUNTER_GLES_INPUT_TRIANGLES, - COUNTER_GLES_VXCACHE_HIT, - COUNTER_GLES_VXCACHE_MISS, - COUNTER_GLES_VXCACHE_COLLISION, - COUNTER_GLES_CULLED_TRIANGLES, - COUNTER_GLES_CULLED_LINES, - COUNTER_GLES_BACKFACE_TRIANGLES, - COUNTER_GLES_GBCLIP_TRIANGLES, - COUNTER_GLES_GBCLIP_LINES, - COUNTER_GLES_TRIANGLES_DRAWN, - COUNTER_GLES_DRAWCALL_TIME, - COUNTER_GLES_TRIANGLES_COUNT, - COUNTER_GLES_INDEPENDENT_TRIANGLES_COUNT, - COUNTER_GLES_STRIP_TRIANGLES_COUNT, - COUNTER_GLES_FAN_TRIANGLES_COUNT, - COUNTER_GLES_LINES_COUNT, - COUNTER_GLES_INDEPENDENT_LINES_COUNT, - COUNTER_GLES_STRIP_LINES_COUNT, - COUNTER_GLES_LOOP_LINES_COUNT, - - /* Framebuffer capture pseudo-counter */ - COUNTER_FILMSTRIP, - - NUMBER_OF_EVENTS +enum { + /* Vertex processor activity */ + ACTIVITY_VP_0 = 0, + + /* Fragment processor activity */ + ACTIVITY_FP_0, /* 1 */ + ACTIVITY_FP_1, + ACTIVITY_FP_2, + ACTIVITY_FP_3, + ACTIVITY_FP_4, + ACTIVITY_FP_5, + ACTIVITY_FP_6, + ACTIVITY_FP_7, + + /* L2 cache counters */ + COUNTER_L2_0_C0, + COUNTER_L2_0_C1, + COUNTER_L2_1_C0, + COUNTER_L2_1_C1, + COUNTER_L2_2_C0, + COUNTER_L2_2_C1, + + /* Vertex processor counters */ + COUNTER_VP_0_C0, /*15*/ + COUNTER_VP_0_C1, + + /* Fragment processor counters */ + COUNTER_FP_0_C0, + COUNTER_FP_0_C1, + COUNTER_FP_1_C0, + COUNTER_FP_1_C1, + COUNTER_FP_2_C0, + COUNTER_FP_2_C1, + COUNTER_FP_3_C0, + COUNTER_FP_3_C1, + COUNTER_FP_4_C0, + COUNTER_FP_4_C1, + COUNTER_FP_5_C0, + COUNTER_FP_5_C1, + COUNTER_FP_6_C0, + COUNTER_FP_6_C1, + COUNTER_FP_7_C0, + COUNTER_FP_7_C1, /* 32 */ + + /* + * If more hardware counters are added, the _mali_osk_hw_counter_table + * below should also be updated. + */ + + /* EGL software counters */ + COUNTER_EGL_BLIT_TIME, + + /* GLES software counters */ + COUNTER_GLES_DRAW_ELEMENTS_CALLS, + COUNTER_GLES_DRAW_ELEMENTS_NUM_INDICES, + COUNTER_GLES_DRAW_ELEMENTS_NUM_TRANSFORMED, + COUNTER_GLES_DRAW_ARRAYS_CALLS, + COUNTER_GLES_DRAW_ARRAYS_NUM_TRANSFORMED, + COUNTER_GLES_DRAW_POINTS, + COUNTER_GLES_DRAW_LINES, + COUNTER_GLES_DRAW_LINE_LOOP, + COUNTER_GLES_DRAW_LINE_STRIP, + COUNTER_GLES_DRAW_TRIANGLES, + COUNTER_GLES_DRAW_TRIANGLE_STRIP, + COUNTER_GLES_DRAW_TRIANGLE_FAN, + COUNTER_GLES_NON_VBO_DATA_COPY_TIME, + COUNTER_GLES_UNIFORM_BYTES_COPIED_TO_MALI, + COUNTER_GLES_UPLOAD_TEXTURE_TIME, + COUNTER_GLES_UPLOAD_VBO_TIME, + COUNTER_GLES_NUM_FLUSHES, + COUNTER_GLES_NUM_VSHADERS_GENERATED, + COUNTER_GLES_NUM_FSHADERS_GENERATED, + COUNTER_GLES_VSHADER_GEN_TIME, + COUNTER_GLES_FSHADER_GEN_TIME, + COUNTER_GLES_INPUT_TRIANGLES, + COUNTER_GLES_VXCACHE_HIT, + COUNTER_GLES_VXCACHE_MISS, + COUNTER_GLES_VXCACHE_COLLISION, + COUNTER_GLES_CULLED_TRIANGLES, + COUNTER_GLES_CULLED_LINES, + COUNTER_GLES_BACKFACE_TRIANGLES, + COUNTER_GLES_GBCLIP_TRIANGLES, + COUNTER_GLES_GBCLIP_LINES, + COUNTER_GLES_TRIANGLES_DRAWN, + COUNTER_GLES_DRAWCALL_TIME, + COUNTER_GLES_TRIANGLES_COUNT, + COUNTER_GLES_INDEPENDENT_TRIANGLES_COUNT, + COUNTER_GLES_STRIP_TRIANGLES_COUNT, + COUNTER_GLES_FAN_TRIANGLES_COUNT, + COUNTER_GLES_LINES_COUNT, + COUNTER_GLES_INDEPENDENT_LINES_COUNT, + COUNTER_GLES_STRIP_LINES_COUNT, + COUNTER_GLES_LOOP_LINES_COUNT, + + /* Framebuffer capture pseudo-counter */ + COUNTER_FILMSTRIP, + + NUMBER_OF_EVENTS } _mali_osk_counter_id; #define FIRST_ACTIVITY_EVENT ACTIVITY_VP_0 @@ -138,21 +137,19 @@ typedef enum /** * Structure to pass performance counter data of a Mali core */ -typedef struct _mali_profiling_core_counters -{ +struct _mali_profiling_core_counters { u32 source0; u32 value0; u32 source1; u32 value1; -} _mali_profiling_core_counters; +}; /** * Structure to pass performance counter data of Mali L2 cache cores */ -typedef struct _mali_profiling_l2_counter_values -{ +struct _mali_profiling_l2_counter_values { struct _mali_profiling_core_counters cores[MAX_NUM_L2_CACHE_CORES]; -} _mali_profiling_l2_counter_values; +}; /** * Structure to pass data defining Mali instance in use: @@ -164,15 +161,14 @@ typedef struct _mali_profiling_l2_counter_values * num_of_fp_cores - number of fragment processor cores * num_of_vp_cores - number of vertex processor cores */ -typedef struct _mali_profiling_mali_version -{ +struct _mali_profiling_mali_version { u32 mali_product_id; u32 mali_version_major; u32 mali_version_minor; u32 num_of_l2_cores; u32 num_of_fp_cores; u32 num_of_vp_cores; -} _mali_profiling_mali_version; +}; /* * List of possible actions to be controlled by Streamline. @@ -186,7 +182,7 @@ typedef struct _mali_profiling_mali_version void _mali_profiling_control(u32 action, u32 value); -u32 _mali_profiling_get_l2_counters(_mali_profiling_l2_counter_values *values); +u32 _mali_profiling_get_l2_counters(struct _mali_profiling_l2_counter_values *values); int _mali_profiling_set_event(u32 counter_id, s32 event_id); diff --git a/drivers/gator/mali_t6xx.mk b/drivers/gator/mali_midgard.mk index fa7571ded17b..1b784d5c3d58 100644 --- a/drivers/gator/mali_t6xx.mk +++ b/drivers/gator/mali_midgard.mk @@ -1,4 +1,4 @@ -# Defines for Mali-T6xx driver +# Defines for Mali-Midgard driver EXTRA_CFLAGS += -DMALI_USE_UMP=1 \ -DMALI_LICENSE_IS_GPL=1 \ -DMALI_BASE_TRACK_MEMLEAK=0 \ @@ -21,7 +21,7 @@ OSK_DIR = $(DDK_DIR)/drivers/gpu/arm/midgard/osk EXTRA_CFLAGS += -DMALI_DIR_MIDGARD=1 endif -ifneq ($(wildcard $(DDK_DIR)/drivers/gpu/arm/midgard/mali_dd_gator_api.h),) +ifneq ($(wildcard $(DDK_DIR)/drivers/gpu/arm/midgard/mali_kbase_gator_api.h),) EXTRA_CFLAGS += -DMALI_SIMPLE_API=1 endif diff --git a/drivers/gpio/gpio-tps65912.c b/drivers/gpio/gpio-tps65912.c index 59ee486cb8b9..6005d260457d 100644 --- a/drivers/gpio/gpio-tps65912.c +++ b/drivers/gpio/gpio-tps65912.c @@ -26,9 +26,12 @@ struct tps65912_gpio_data { struct gpio_chip gpio_chip; }; +#define to_tgd(gc) container_of(gc, struct tps65912_gpio_data, gpio_chip) + static int tps65912_gpio_get(struct gpio_chip *gc, unsigned offset) { - struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio); + struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc); + struct tps65912 *tps65912 = tps65912_gpio->tps65912; int val; val = tps65912_reg_read(tps65912, TPS65912_GPIO1 + offset); @@ -42,7 +45,8 @@ static int tps65912_gpio_get(struct gpio_chip *gc, unsigned offset) static void tps65912_gpio_set(struct gpio_chip *gc, unsigned offset, int value) { - struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio); + struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc); + struct tps65912 *tps65912 = tps65912_gpio->tps65912; if (value) tps65912_set_bits(tps65912, TPS65912_GPIO1 + offset, @@ -55,7 +59,8 @@ static void tps65912_gpio_set(struct gpio_chip *gc, unsigned offset, static int tps65912_gpio_output(struct gpio_chip *gc, unsigned offset, int value) { - struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio); + struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc); + struct tps65912 *tps65912 = tps65912_gpio->tps65912; /* Set the initial value */ tps65912_gpio_set(gc, offset, value); @@ -66,7 +71,8 @@ static int tps65912_gpio_output(struct gpio_chip *gc, unsigned offset, static int tps65912_gpio_input(struct gpio_chip *gc, unsigned offset) { - struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio); + struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc); + struct tps65912 *tps65912 = tps65912_gpio->tps65912; return tps65912_clear_bits(tps65912, TPS65912_GPIO1 + offset, GPIO_CFG_MASK); diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index e0a98f581f58..d26028cb9eac 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -44,8 +44,15 @@ static int of_gpiochip_find_and_xlate(struct gpio_chip *gc, void *data) return false; ret = gc->of_xlate(gc, &gg_data->gpiospec, gg_data->flags); - if (ret < 0) + if (ret < 0) { + /* We've found a gpio chip, but the translation failed. + * Store translation error in out_gpio. + * Return false to keep looking, as more than one gpio chip + * could be registered per of-node. + */ + gg_data->out_gpio = ERR_PTR(ret); return false; + } gg_data->out_gpio = gpio_to_desc(ret + gc->base); return true; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 50c4922fe53a..8f42bd724682 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -408,7 +408,7 @@ static ssize_t gpio_value_store(struct device *dev, return status; } -static const DEVICE_ATTR(value, 0644, +static DEVICE_ATTR(value, 0644, gpio_value_show, gpio_value_store); static irqreturn_t gpio_sysfs_irq(int irq, void *priv) @@ -633,18 +633,16 @@ static ssize_t gpio_active_low_store(struct device *dev, return status ? : size; } -static const DEVICE_ATTR(active_low, 0644, +static DEVICE_ATTR(active_low, 0644, gpio_active_low_show, gpio_active_low_store); -static const struct attribute *gpio_attrs[] = { +static struct attribute *gpio_attrs[] = { &dev_attr_value.attr, &dev_attr_active_low.attr, NULL, }; -static const struct attribute_group gpio_attr_group = { - .attrs = (struct attribute **) gpio_attrs, -}; +ATTRIBUTE_GROUPS(gpio); /* * /sys/class/gpio/gpiochipN/ @@ -680,16 +678,13 @@ static ssize_t chip_ngpio_show(struct device *dev, } static DEVICE_ATTR(ngpio, 0444, chip_ngpio_show, NULL); -static const struct attribute *gpiochip_attrs[] = { +static struct attribute *gpiochip_attrs[] = { &dev_attr_base.attr, &dev_attr_label.attr, &dev_attr_ngpio.attr, NULL, }; - -static const struct attribute_group gpiochip_attr_group = { - .attrs = (struct attribute **) gpiochip_attrs, -}; +ATTRIBUTE_GROUPS(gpiochip); /* * /sys/class/gpio/export ... write-only @@ -844,18 +839,15 @@ int gpiod_export(struct gpio_desc *desc, bool direction_may_change) if (desc->chip->names && desc->chip->names[offset]) ioname = desc->chip->names[offset]; - dev = device_create(&gpio_class, desc->chip->dev, MKDEV(0, 0), - desc, ioname ? ioname : "gpio%u", - desc_to_gpio(desc)); + dev = device_create_with_groups(&gpio_class, desc->chip->dev, + MKDEV(0, 0), desc, gpio_groups, + ioname ? ioname : "gpio%u", + desc_to_gpio(desc)); if (IS_ERR(dev)) { status = PTR_ERR(dev); goto fail_unlock; } - status = sysfs_create_group(&dev->kobj, &gpio_attr_group); - if (status) - goto fail_unregister_device; - if (direction_may_change) { status = device_create_file(dev, &dev_attr_direction); if (status) @@ -866,13 +858,15 @@ int gpiod_export(struct gpio_desc *desc, bool direction_may_change) !test_bit(FLAG_IS_OUT, &desc->flags))) { status = device_create_file(dev, &dev_attr_edge); if (status) - goto fail_unregister_device; + goto fail_remove_attr_direction; } set_bit(FLAG_EXPORT, &desc->flags); mutex_unlock(&sysfs_lock); return 0; +fail_remove_attr_direction: + device_remove_file(dev, &dev_attr_direction); fail_unregister_device: device_unregister(dev); fail_unlock: @@ -917,6 +911,7 @@ int gpiod_export_link(struct device *dev, const char *name, if (tdev != NULL) { status = sysfs_create_link(&dev->kobj, &tdev->kobj, name); + put_device(tdev); } else { status = -ENODEV; } @@ -964,7 +959,7 @@ int gpiod_sysfs_set_active_low(struct gpio_desc *desc, int value) } status = sysfs_set_active_low(desc, dev, value); - + put_device(dev); unlock: mutex_unlock(&sysfs_lock); @@ -1006,6 +1001,8 @@ void gpiod_unexport(struct gpio_desc *desc) mutex_unlock(&sysfs_lock); if (dev) { + device_remove_file(dev, &dev_attr_edge); + device_remove_file(dev, &dev_attr_direction); device_unregister(dev); put_device(dev); } @@ -1030,13 +1027,13 @@ static int gpiochip_export(struct gpio_chip *chip) /* use chip->base for the ID; it's already known to be unique */ mutex_lock(&sysfs_lock); - dev = device_create(&gpio_class, chip->dev, MKDEV(0, 0), chip, - "gpiochip%d", chip->base); - if (!IS_ERR(dev)) { - status = sysfs_create_group(&dev->kobj, - &gpiochip_attr_group); - } else + dev = device_create_with_groups(&gpio_class, chip->dev, MKDEV(0, 0), + chip, gpiochip_groups, + "gpiochip%d", chip->base); + if (IS_ERR(dev)) status = PTR_ERR(dev); + else + status = 0; chip->exported = (status == 0); mutex_unlock(&sysfs_lock); @@ -1222,6 +1219,9 @@ int gpiochip_add(struct gpio_chip *chip) spin_unlock_irqrestore(&gpio_lock, flags); + if (status) + goto fail; + #ifdef CONFIG_PINCTRL INIT_LIST_HEAD(&chip->pin_ranges); #endif @@ -1229,12 +1229,12 @@ int gpiochip_add(struct gpio_chip *chip) of_gpiochip_add(chip); acpi_gpiochip_add(chip); - if (status) - goto fail; - status = gpiochip_export(chip); - if (status) + if (status) { + acpi_gpiochip_remove(chip); + of_gpiochip_remove(chip); goto fail; + } pr_debug("%s: registered GPIOs %d to %d on device: %s\n", __func__, chip->base, chip->base + chip->ngpio - 1, diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index 50535fd5a88d..d830b38e54f6 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -100,7 +100,7 @@ static int ast_detect_chip(struct drm_device *dev) } ast->vga2_clone = false; } else { - ast->chip = 2000; + ast->chip = AST2000; DRM_INFO("AST 2000 detected\n"); } } diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index cca063b11083..d2e56e95d886 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -1012,8 +1012,8 @@ static u32 copy_cursor_image(u8 *src, u8 *dst, int width, int height) srcdata32[1].ul = *((u32 *)(srcxor + 4)) & 0xf0f0f0f0; data32.b[0] = srcdata32[0].b[1] | (srcdata32[0].b[0] >> 4); data32.b[1] = srcdata32[0].b[3] | (srcdata32[0].b[2] >> 4); - data32.b[2] = srcdata32[0].b[1] | (srcdata32[1].b[0] >> 4); - data32.b[3] = srcdata32[0].b[3] | (srcdata32[1].b[2] >> 4); + data32.b[2] = srcdata32[1].b[1] | (srcdata32[1].b[0] >> 4); + data32.b[3] = srcdata32[1].b[3] | (srcdata32[1].b[2] >> 4); writel(data32.ul, dstxor); csum += data32.ul; diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.c b/drivers/gpu/drm/cirrus/cirrus_drv.c index 08ce520f61a5..faa1f421f1b8 100644 --- a/drivers/gpu/drm/cirrus/cirrus_drv.c +++ b/drivers/gpu/drm/cirrus/cirrus_drv.c @@ -32,6 +32,8 @@ static struct drm_driver driver; static DEFINE_PCI_DEVICE_TABLE(pciidlist) = { { PCI_VENDOR_ID_CIRRUS, PCI_DEVICE_ID_CIRRUS_5446, 0x1af4, 0x1100, 0, 0, 0 }, + { PCI_VENDOR_ID_CIRRUS, PCI_DEVICE_ID_CIRRUS_5446, PCI_VENDOR_ID_XEN, + 0x0001, 0, 0, 0 }, {0,} }; diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 3ecb332e7cfa..de5ab4876a89 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1426,10 +1426,13 @@ unlock: out: switch (ret) { case -EIO: - /* If this -EIO is due to a gpu hang, give the reset code a - * chance to clean up the mess. Otherwise return the proper - * SIGBUS. */ - if (i915_terminally_wedged(&dev_priv->gpu_error)) { + /* + * We eat errors when the gpu is terminally wedged to avoid + * userspace unduly crashing (gl has no provisions for mmaps to + * fail). But any other -EIO isn't ours (e.g. swap in failure) + * and so needs to be reported. + */ + if (!i915_terminally_wedged(&dev_priv->gpu_error)) { ret = VM_FAULT_SIGBUS; break; } @@ -2890,6 +2893,13 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg, u32 size = i915_gem_obj_ggtt_size(obj); uint64_t val; + /* Adjust fence size to match tiled area */ + if (obj->tiling_mode != I915_TILING_NONE) { + uint32_t row_size = obj->stride * + (obj->tiling_mode == I915_TILING_Y ? 32 : 8); + size = (size / row_size) * row_size; + } + val = (uint64_t)((i915_gem_obj_ggtt_offset(obj) + size - 4096) & 0xfffff000) << 32; val |= i915_gem_obj_ggtt_offset(obj) & 0xfffff000; @@ -4975,7 +4985,7 @@ 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_SMP) && !defined(CONFIG_DEBUG_MUTEXES) 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_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index d278be110805..1855cdca39cd 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -827,6 +827,16 @@ void i915_check_and_clear_faults(struct drm_device *dev) POSTING_READ(RING_FAULT_REG(&dev_priv->ring[RCS])); } +static void i915_ggtt_flush(struct drm_i915_private *dev_priv) +{ + if (INTEL_INFO(dev_priv->dev)->gen < 6) { + intel_gtt_chipset_flush(); + } else { + I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN); + POSTING_READ(GFX_FLSH_CNTL_GEN6); + } +} + void i915_gem_suspend_gtt_mappings(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -843,6 +853,8 @@ void i915_gem_suspend_gtt_mappings(struct drm_device *dev) dev_priv->gtt.base.start / PAGE_SIZE, dev_priv->gtt.base.total / PAGE_SIZE, true); + + i915_ggtt_flush(dev_priv); } void i915_gem_restore_gtt_mappings(struct drm_device *dev) @@ -863,7 +875,7 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev) i915_gem_gtt_bind_object(obj, obj->cache_level); } - i915_gem_chipset_flush(dev); + i915_ggtt_flush(dev_priv); } int i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj) diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index 3c78b2268209..800e06c28018 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -137,7 +137,11 @@ static unsigned long i915_stolen_to_physical(struct drm_device *dev) r = devm_request_mem_region(dev->dev, base + 1, dev_priv->gtt.stolen_size - 1, "Graphics Stolen Memory"); - if (r == NULL) { + /* + * GEN3 firmware likes to smash pci bridges into the stolen + * range. Apparently this works. + */ + if (r == NULL && !IS_GEN3(dev)) { DRM_ERROR("conflict detected with stolen region: [0x%08x - 0x%08x]\n", base, base + (uint32_t)dev_priv->gtt.stolen_size); base = 0; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 0a3b9386eb43..0c83b3dab58c 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -320,6 +320,7 @@ #define PIPE_CONTROL_GLOBAL_GTT_IVB (1<<24) /* gen7+ */ #define PIPE_CONTROL_CS_STALL (1<<20) #define PIPE_CONTROL_TLB_INVALIDATE (1<<18) +#define PIPE_CONTROL_MEDIA_STATE_CLEAR (1<<16) #define PIPE_CONTROL_QW_WRITE (1<<14) #define PIPE_CONTROL_DEPTH_STALL (1<<13) #define PIPE_CONTROL_WRITE_FLUSH (1<<12) diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index f22041973f3a..08105fddfd2a 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -839,7 +839,7 @@ init_vbt_defaults(struct drm_i915_private *dev_priv) } } -static int __init intel_no_opregion_vbt_callback(const struct dmi_system_id *id) +static int intel_no_opregion_vbt_callback(const struct dmi_system_id *id) { DRM_DEBUG_KMS("Falling back to manually reading VBT from " "VBIOS ROM for %s\n", diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index b19ddacbe19d..834847527982 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -750,7 +750,7 @@ static const struct drm_encoder_funcs intel_crt_enc_funcs = { .destroy = intel_encoder_destroy, }; -static int __init intel_no_crt_dmi_callback(const struct dmi_system_id *id) +static int intel_no_crt_dmi_callback(const struct dmi_system_id *id) { DRM_INFO("Skipping CRT initialization for %s\n", id->ident); return 1; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index b6fb3ebe553a..c51469051e41 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -3817,7 +3817,6 @@ static void ironlake_crtc_disable(struct drm_crtc *crtc) ironlake_fdi_disable(crtc); ironlake_disable_pch_transcoder(dev_priv, pipe); - intel_set_pch_fifo_underrun_reporting(dev, pipe, true); if (HAS_PCH_CPT(dev)) { /* disable TRANS_DP_CTL */ @@ -3883,7 +3882,6 @@ static void haswell_crtc_disable(struct drm_crtc *crtc) if (intel_crtc->config.has_pch_encoder) { lpt_disable_pch_transcoder(dev_priv); - intel_set_pch_fifo_underrun_reporting(dev, TRANSCODER_A, true); intel_ddi_fdi_disable(crtc); } diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index eb8f64b5fb85..af49b24d14cb 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -544,7 +544,7 @@ static const struct drm_encoder_funcs intel_lvds_enc_funcs = { .destroy = intel_encoder_destroy, }; -static int __init intel_no_lvds_dmi_callback(const struct dmi_system_id *id) +static int intel_no_lvds_dmi_callback(const struct dmi_system_id *id) { DRM_INFO("Skipping LVDS initialization for %s\n", id->ident); return 1; @@ -905,6 +905,17 @@ void intel_lvds_init(struct drm_device *dev) int pipe; u8 pin; + /* + * Unlock registers and just leave them unlocked. Do this before + * checking quirk lists to avoid bogus WARNINGs. + */ + if (HAS_PCH_SPLIT(dev)) { + I915_WRITE(PCH_PP_CONTROL, + I915_READ(PCH_PP_CONTROL) | PANEL_UNLOCK_REGS); + } else { + I915_WRITE(PP_CONTROL, + I915_READ(PP_CONTROL) | PANEL_UNLOCK_REGS); + } if (!intel_lvds_supported(dev)) return; @@ -1099,17 +1110,6 @@ out: DRM_DEBUG_KMS("detected %s-link lvds configuration\n", lvds_encoder->is_dual_link ? "dual" : "single"); - /* - * Unlock registers and just - * leave them unlocked - */ - if (HAS_PCH_SPLIT(dev)) { - I915_WRITE(PCH_PP_CONTROL, - I915_READ(PCH_PP_CONTROL) | PANEL_UNLOCK_REGS); - } else { - I915_WRITE(PP_CONTROL, - I915_READ(PP_CONTROL) | PANEL_UNLOCK_REGS); - } lvds_connector->lid_notifier.notifier_call = intel_lid_notify; if (acpi_lid_notifier_register(&lvds_connector->lid_notifier)) { DRM_DEBUG_KMS("lid notifier registration failed\n"); diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index fd98bec78816..c6d9777bdb45 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -645,7 +645,7 @@ static void pch_enable_backlight(struct intel_connector *connector) cpu_ctl2 = I915_READ(BLC_PWM_CPU_CTL2); if (cpu_ctl2 & BLM_PWM_ENABLE) { - WARN(1, "cpu backlight already enabled\n"); + DRM_DEBUG_KMS("cpu backlight already enabled\n"); cpu_ctl2 &= ~BLM_PWM_ENABLE; I915_WRITE(BLC_PWM_CPU_CTL2, cpu_ctl2); } @@ -693,7 +693,7 @@ static void i9xx_enable_backlight(struct intel_connector *connector) ctl = I915_READ(BLC_PWM_CTL); if (ctl & BACKLIGHT_DUTY_CYCLE_MASK_PNV) { - WARN(1, "backlight already enabled\n"); + DRM_DEBUG_KMS("backlight already enabled\n"); I915_WRITE(BLC_PWM_CTL, 0); } @@ -724,7 +724,7 @@ static void i965_enable_backlight(struct intel_connector *connector) ctl2 = I915_READ(BLC_PWM_CTL2); if (ctl2 & BLM_PWM_ENABLE) { - WARN(1, "backlight already enabled\n"); + DRM_DEBUG_KMS("backlight already enabled\n"); ctl2 &= ~BLM_PWM_ENABLE; I915_WRITE(BLC_PWM_CTL2, ctl2); } @@ -758,7 +758,7 @@ static void vlv_enable_backlight(struct intel_connector *connector) ctl2 = I915_READ(VLV_BLC_PWM_CTL2(pipe)); if (ctl2 & BLM_PWM_ENABLE) { - WARN(1, "backlight already enabled\n"); + DRM_DEBUG_KMS("backlight already enabled\n"); ctl2 &= ~BLM_PWM_ENABLE; I915_WRITE(VLV_BLC_PWM_CTL2(pipe), ctl2); } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 31b36c5ac894..d2af1e138c91 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -334,12 +334,15 @@ gen7_render_ring_flush(struct intel_ring_buffer *ring, flags |= PIPE_CONTROL_VF_CACHE_INVALIDATE; flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE; flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE; + flags |= PIPE_CONTROL_MEDIA_STATE_CLEAR; /* * TLB invalidate requires a post-sync write. */ flags |= PIPE_CONTROL_QW_WRITE; flags |= PIPE_CONTROL_GLOBAL_GTT_IVB; + flags |= PIPE_CONTROL_STALL_AT_SCOREBOARD; + /* Workaround: we must issue a pipe_control with CS-stall bit * set before a pipe_control command that has the state cache * invalidate bit set. */ @@ -475,6 +478,9 @@ static int init_ring_common(struct intel_ring_buffer *ring) } } + /* Enforce ordering by reading HEAD register back */ + I915_READ_HEAD(ring); + /* Initialize the ring. This must happen _after_ we've cleared the ring * registers with the above sequence (the readback of the HEAD registers * also enforces ordering), otherwise the hw might lose the new ring diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c index 365c7c47c46c..9c9606c8bb1a 100644 --- a/drivers/gpu/drm/i915/intel_tv.c +++ b/drivers/gpu/drm/i915/intel_tv.c @@ -854,6 +854,10 @@ intel_enable_tv(struct intel_encoder *encoder) struct drm_device *dev = encoder->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; + /* Prevents vblank waits from timing out in intel_tv_detect_type() */ + intel_wait_for_vblank(encoder->base.dev, + to_intel_crtc(encoder->base.crtc)->pipe); + I915_WRITE(TV_CTL, I915_READ(TV_CTL) | TV_ENC_ENABLE); } diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index c8796316d242..b6c063cad59b 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -451,8 +451,8 @@ hsw_unclaimed_reg_check(struct drm_i915_private *dev_priv, u32 reg) static void assert_device_not_suspended(struct drm_i915_private *dev_priv) { - WARN(HAS_RUNTIME_PM(dev_priv->dev) && dev_priv->pm.suspended, - "Device suspended\n"); + WARN_ONCE(HAS_RUNTIME_PM(dev_priv->dev) && dev_priv->pm.suspended, + "Device suspended\n"); } #define REG_READ_HEADER(x) \ diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c b/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c index 2d9b9d7a7992..f3edd2841f2d 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c +++ b/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c @@ -124,6 +124,7 @@ dcb_outp_parse(struct nouveau_bios *bios, u8 idx, u8 *ver, u8 *len, struct dcb_output *outp) { u16 dcb = dcb_outp(bios, idx, ver, len); + memset(outp, 0x00, sizeof(*outp)); if (dcb) { if (*ver >= 0x20) { u32 conn = nv_ro32(bios, dcb + 0x00); diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c index a75c35ccf25c..165401c4045c 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c +++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c @@ -24,13 +24,6 @@ #include "nv04.h" -static void -nv4c_mc_msi_rearm(struct nouveau_mc *pmc) -{ - struct nv04_mc_priv *priv = (void *)pmc; - nv_wr08(priv, 0x088050, 0xff); -} - struct nouveau_oclass * nv4c_mc_oclass = &(struct nouveau_mc_oclass) { .base.handle = NV_SUBDEV(MC, 0x4c), @@ -41,5 +34,4 @@ nv4c_mc_oclass = &(struct nouveau_mc_oclass) { .fini = _nouveau_mc_fini, }, .intr = nv04_mc_intr, - .msi_rearm = nv4c_mc_msi_rearm, }.base; diff --git a/drivers/gpu/drm/nouveau/nouveau_vga.c b/drivers/gpu/drm/nouveau/nouveau_vga.c index 471347edc27e..a92fb01459c9 100644 --- a/drivers/gpu/drm/nouveau/nouveau_vga.c +++ b/drivers/gpu/drm/nouveau/nouveau_vga.c @@ -100,7 +100,16 @@ void nouveau_vga_fini(struct nouveau_drm *drm) { struct drm_device *dev = drm->dev; + bool runtime = false; + + if (nouveau_runtime_pm == 1) + runtime = true; + if ((nouveau_runtime_pm == -1) && (nouveau_is_optimus() || nouveau_is_v1_dsm())) + runtime = true; + vga_switcheroo_unregister_client(dev->pdev); + if (runtime && nouveau_is_v1_dsm() && !nouveau_is_optimus()) + vga_switcheroo_fini_domain_pm_ops(drm->dev->dev); vga_client_register(dev->pdev, NULL, NULL, NULL); } diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index 798bde2e5881..c39c414c7751 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -523,7 +523,6 @@ static int qxl_crtc_mode_set(struct drm_crtc *crtc, struct qxl_framebuffer *qfb; struct qxl_bo *bo, *old_bo = NULL; struct qxl_crtc *qcrtc = to_qxl_crtc(crtc); - uint32_t width, height, base_offset; bool recreate_primary = false; int ret; int surf_id; @@ -553,9 +552,10 @@ static int qxl_crtc_mode_set(struct drm_crtc *crtc, if (qcrtc->index == 0) recreate_primary = true; - width = mode->hdisplay; - height = mode->vdisplay; - base_offset = 0; + if (bo->surf.stride * bo->surf.height > qdev->vram_size) { + DRM_ERROR("Mode doesn't fit in vram size (vgamem)"); + return -EINVAL; + } ret = qxl_bo_reserve(bo, false); if (ret != 0) @@ -569,10 +569,10 @@ static int qxl_crtc_mode_set(struct drm_crtc *crtc, if (recreate_primary) { qxl_io_destroy_primary(qdev); qxl_io_log(qdev, - "recreate primary: %dx%d (was %dx%d,%d,%d)\n", - width, height, bo->surf.width, - bo->surf.height, bo->surf.stride, bo->surf.format); - qxl_io_create_primary(qdev, base_offset, bo); + "recreate primary: %dx%d,%d,%d\n", + bo->surf.width, bo->surf.height, + bo->surf.stride, bo->surf.format); + qxl_io_create_primary(qdev, 0, bo); bo->is_primary = true; surf_id = 0; } else { diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index 0cca5f24196a..663394f0c166 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -1306,6 +1306,9 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc, (x << 16) | y); viewport_w = crtc->mode.hdisplay; viewport_h = (crtc->mode.vdisplay + 1) & ~1; + if ((rdev->family >= CHIP_BONAIRE) && + (crtc->mode.flags & DRM_MODE_FLAG_INTERLACE)) + viewport_h *= 2; WREG32(EVERGREEN_VIEWPORT_SIZE + radeon_crtc->crtc_offset, (viewport_w << 16) | viewport_h); diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c index 5727dbdeda7f..b4dbaded2caf 100644 --- a/drivers/gpu/drm/radeon/atombios_dp.c +++ b/drivers/gpu/drm/radeon/atombios_dp.c @@ -576,6 +576,10 @@ int radeon_dp_mode_valid_helper(struct drm_connector *connector, struct radeon_connector_atom_dig *dig_connector; int dp_clock; + if ((mode->clock > 340000) && + (!radeon_connector_is_dp12_capable(connector))) + return MODE_CLOCK_HIGH; + if (!radeon_connector->con_priv) return MODE_CLOCK_HIGH; dig_connector = radeon_connector->con_priv; diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c index 5fa854c84d62..c7c285646857 100644 --- a/drivers/gpu/drm/radeon/ci_dpm.c +++ b/drivers/gpu/drm/radeon/ci_dpm.c @@ -851,6 +851,9 @@ static int ci_set_thermal_temperature_range(struct radeon_device *rdev, WREG32_SMC(CG_THERMAL_CTRL, tmp); #endif + rdev->pm.dpm.thermal.min_temp = low_temp; + rdev->pm.dpm.thermal.max_temp = high_temp; + return 0; } @@ -922,7 +925,18 @@ static void ci_get_leakage_voltages(struct radeon_device *rdev) pi->vddc_leakage.count = 0; pi->vddci_leakage.count = 0; - if (radeon_atom_get_leakage_id_from_vbios(rdev, &leakage_id) == 0) { + if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_EVV) { + for (i = 0; i < CISLANDS_MAX_LEAKAGE_COUNT; i++) { + virtual_voltage_id = ATOM_VIRTUAL_VOLTAGE_ID0 + i; + if (radeon_atom_get_voltage_evv(rdev, virtual_voltage_id, &vddc) != 0) + continue; + if (vddc != 0 && vddc != virtual_voltage_id) { + pi->vddc_leakage.actual_voltage[pi->vddc_leakage.count] = vddc; + pi->vddc_leakage.leakage_id[pi->vddc_leakage.count] = virtual_voltage_id; + pi->vddc_leakage.count++; + } + } + } else if (radeon_atom_get_leakage_id_from_vbios(rdev, &leakage_id) == 0) { for (i = 0; i < CISLANDS_MAX_LEAKAGE_COUNT; i++) { virtual_voltage_id = ATOM_VIRTUAL_VOLTAGE_ID0 + i; if (radeon_atom_get_leakage_vddc_based_on_leakage_params(rdev, &vddc, &vddci, @@ -4719,7 +4733,7 @@ void ci_dpm_disable(struct radeon_device *rdev) ci_enable_spread_spectrum(rdev, false); ci_enable_auto_throttle_source(rdev, RADEON_DPM_AUTO_THROTTLE_SRC_THERMAL, false); ci_stop_dpm(rdev); - ci_enable_ds_master_switch(rdev, true); + ci_enable_ds_master_switch(rdev, false); ci_enable_ulv(rdev, false); ci_clear_vc(rdev); ci_reset_to_default(rdev); diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c index 7b3537c55c77..c3664bc05acf 100644 --- a/drivers/gpu/drm/radeon/cik.c +++ b/drivers/gpu/drm/radeon/cik.c @@ -3558,7 +3558,21 @@ void cik_fence_gfx_ring_emit(struct radeon_device *rdev, struct radeon_ring *ring = &rdev->ring[fence->ring]; u64 addr = rdev->fence_drv[fence->ring].gpu_addr; - /* EVENT_WRITE_EOP - flush caches, send int */ + /* Workaround for cache flush problems. First send a dummy EOP + * event down the pipe with seq one below. + */ + radeon_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4)); + radeon_ring_write(ring, (EOP_TCL1_ACTION_EN | + EOP_TC_ACTION_EN | + EVENT_TYPE(CACHE_FLUSH_AND_INV_TS_EVENT) | + EVENT_INDEX(5))); + radeon_ring_write(ring, addr & 0xfffffffc); + radeon_ring_write(ring, (upper_32_bits(addr) & 0xffff) | + DATA_SEL(1) | INT_SEL(0)); + radeon_ring_write(ring, fence->seq - 1); + radeon_ring_write(ring, 0); + + /* Then send the real EOP event down the pipe. */ radeon_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4)); radeon_ring_write(ring, (EOP_TCL1_ACTION_EN | EOP_TC_ACTION_EN | @@ -3936,8 +3950,8 @@ static int cik_cp_gfx_start(struct radeon_device *rdev) /* init the CE partitions. CE only used for gfx on CIK */ radeon_ring_write(ring, PACKET3(PACKET3_SET_BASE, 2)); radeon_ring_write(ring, PACKET3_BASE_INDEX(CE_PARTITION_BASE)); - radeon_ring_write(ring, 0xc000); - radeon_ring_write(ring, 0xc000); + radeon_ring_write(ring, 0x8000); + radeon_ring_write(ring, 0x8000); /* setup clear context state */ radeon_ring_write(ring, PACKET3(PACKET3_PREAMBLE_CNTL, 0)); @@ -4392,7 +4406,7 @@ struct bonaire_mqd */ static int cik_cp_compute_resume(struct radeon_device *rdev) { - int r, i, idx; + int r, i, j, idx; u32 tmp; bool use_doorbell = true; u64 hqd_gpu_addr; @@ -4511,7 +4525,7 @@ static int cik_cp_compute_resume(struct radeon_device *rdev) mqd->queue_state.cp_hqd_pq_wptr= 0; if (RREG32(CP_HQD_ACTIVE) & 1) { WREG32(CP_HQD_DEQUEUE_REQUEST, 1); - for (i = 0; i < rdev->usec_timeout; i++) { + for (j = 0; j < rdev->usec_timeout; j++) { if (!(RREG32(CP_HQD_ACTIVE) & 1)) break; udelay(1); @@ -5545,12 +5559,13 @@ static void cik_vm_decode_fault(struct radeon_device *rdev, void cik_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm) { struct radeon_ring *ring = &rdev->ring[ridx]; + int usepfp = (ridx == RADEON_RING_TYPE_GFX_INDEX); if (vm == NULL) return; radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3)); - radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) | + radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(usepfp) | WRITE_DATA_DST_SEL(0))); if (vm->id < 8) { radeon_ring_write(ring, @@ -5600,7 +5615,7 @@ void cik_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm) radeon_ring_write(ring, 1 << vm->id); /* compute doesn't have PFP */ - if (ridx == RADEON_RING_TYPE_GFX_INDEX) { + if (usepfp) { /* sync PFP to ME, otherwise we might get invalid PFP reads */ radeon_ring_write(ring, PACKET3(PACKET3_PFP_SYNC_ME, 0)); radeon_ring_write(ring, 0x0); @@ -5878,6 +5893,7 @@ static void cik_enable_mgcg(struct radeon_device *rdev, bool enable) } orig = data = RREG32(RLC_CGTT_MGCG_OVERRIDE); + data |= 0x00000001; data &= 0xfffffffd; if (orig != data) WREG32(RLC_CGTT_MGCG_OVERRIDE, data); @@ -5909,7 +5925,7 @@ static void cik_enable_mgcg(struct radeon_device *rdev, bool enable) } } else { orig = data = RREG32(RLC_CGTT_MGCG_OVERRIDE); - data |= 0x00000002; + data |= 0x00000003; if (orig != data) WREG32(RLC_CGTT_MGCG_OVERRIDE, data); @@ -6807,7 +6823,6 @@ int cik_irq_set(struct radeon_device *rdev) u32 hpd1, hpd2, hpd3, hpd4, hpd5, hpd6; u32 grbm_int_cntl = 0; u32 dma_cntl, dma_cntl1; - u32 thermal_int; if (!rdev->irq.installed) { WARN(1, "Can't enable IRQ/MSI because no handler is installed\n"); @@ -6844,13 +6859,6 @@ int cik_irq_set(struct radeon_device *rdev) cp_m2p2 = RREG32(CP_ME2_PIPE2_INT_CNTL) & ~TIME_STAMP_INT_ENABLE; cp_m2p3 = RREG32(CP_ME2_PIPE3_INT_CNTL) & ~TIME_STAMP_INT_ENABLE; - if (rdev->flags & RADEON_IS_IGP) - thermal_int = RREG32_SMC(CG_THERMAL_INT_CTRL) & - ~(THERM_INTH_MASK | THERM_INTL_MASK); - else - thermal_int = RREG32_SMC(CG_THERMAL_INT) & - ~(THERM_INT_MASK_HIGH | THERM_INT_MASK_LOW); - /* enable CP interrupts on all rings */ if (atomic_read(&rdev->irq.ring_int[RADEON_RING_TYPE_GFX_INDEX])) { DRM_DEBUG("cik_irq_set: sw int gfx\n"); @@ -7008,14 +7016,6 @@ int cik_irq_set(struct radeon_device *rdev) hpd6 |= DC_HPDx_INT_EN; } - if (rdev->irq.dpm_thermal) { - DRM_DEBUG("dpm thermal\n"); - if (rdev->flags & RADEON_IS_IGP) - thermal_int |= THERM_INTH_MASK | THERM_INTL_MASK; - else - thermal_int |= THERM_INT_MASK_HIGH | THERM_INT_MASK_LOW; - } - WREG32(CP_INT_CNTL_RING0, cp_int_cntl); WREG32(SDMA0_CNTL + SDMA0_REGISTER_OFFSET, dma_cntl); @@ -7069,10 +7069,8 @@ int cik_irq_set(struct radeon_device *rdev) WREG32(DC_HPD5_INT_CONTROL, hpd5); WREG32(DC_HPD6_INT_CONTROL, hpd6); - if (rdev->flags & RADEON_IS_IGP) - WREG32_SMC(CG_THERMAL_INT_CTRL, thermal_int); - else - WREG32_SMC(CG_THERMAL_INT, thermal_int); + /* posting read */ + RREG32(SRBM_STATUS); return 0; } @@ -8892,6 +8890,9 @@ void dce8_bandwidth_update(struct radeon_device *rdev) u32 num_heads = 0, lb_size; int i; + if (!rdev->mode_info.mode_config_initialized) + return; + radeon_update_display_priority(rdev); for (i = 0; i < rdev->num_crtc; i++) { diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c index aac8f487e6df..66ba713ba7d7 100644 --- a/drivers/gpu/drm/radeon/cik_sdma.c +++ b/drivers/gpu/drm/radeon/cik_sdma.c @@ -461,13 +461,6 @@ int cik_sdma_resume(struct radeon_device *rdev) { int r; - /* Reset dma */ - WREG32(SRBM_SOFT_RESET, SOFT_RESET_SDMA | SOFT_RESET_SDMA1); - RREG32(SRBM_SOFT_RESET); - udelay(50); - WREG32(SRBM_SOFT_RESET, 0); - RREG32(SRBM_SOFT_RESET); - r = cik_sdma_load_microcode(rdev); if (r) return r; diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 4b3c5f7ae63b..ee9f0b4e90d6 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -2362,6 +2362,9 @@ void evergreen_bandwidth_update(struct radeon_device *rdev) u32 num_heads = 0, lb_size; int i; + if (!rdev->mode_info.mode_config_initialized) + return; + radeon_update_display_priority(rdev); for (i = 0; i < rdev->num_crtc; i++) { @@ -2570,6 +2573,7 @@ void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *sav WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1); tmp |= EVERGREEN_CRTC_BLANK_DATA_EN; WREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i], tmp); + WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0); } } else { tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]); @@ -4592,6 +4596,9 @@ int evergreen_irq_set(struct radeon_device *rdev) WREG32(AFMT_AUDIO_PACKET_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, afmt5); WREG32(AFMT_AUDIO_PACKET_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, afmt6); + /* posting read */ + RREG32(SRBM_STATUS); + return 0; } diff --git a/drivers/gpu/drm/radeon/kv_dpm.c b/drivers/gpu/drm/radeon/kv_dpm.c index 351db361239d..c7c7bc5d573f 100644 --- a/drivers/gpu/drm/radeon/kv_dpm.c +++ b/drivers/gpu/drm/radeon/kv_dpm.c @@ -1121,6 +1121,19 @@ void kv_dpm_enable_bapm(struct radeon_device *rdev, bool enable) } } +static void kv_enable_thermal_int(struct radeon_device *rdev, bool enable) +{ + u32 thermal_int; + + thermal_int = RREG32_SMC(CG_THERMAL_INT_CTRL); + if (enable) + thermal_int |= THERM_INTH_MASK | THERM_INTL_MASK; + else + thermal_int &= ~(THERM_INTH_MASK | THERM_INTL_MASK); + WREG32_SMC(CG_THERMAL_INT_CTRL, thermal_int); + +} + int kv_dpm_enable(struct radeon_device *rdev) { struct kv_power_info *pi = kv_get_pi(rdev); @@ -1232,8 +1245,7 @@ int kv_dpm_late_enable(struct radeon_device *rdev) DRM_ERROR("kv_set_thermal_temperature_range failed\n"); return ret; } - rdev->irq.dpm_thermal = true; - radeon_irq_set(rdev); + kv_enable_thermal_int(rdev, true); } /* powerdown unused blocks for now */ @@ -1261,6 +1273,7 @@ void kv_dpm_disable(struct radeon_device *rdev) kv_stop_dpm(rdev); kv_enable_ulv(rdev, false); kv_reset_am(rdev); + kv_enable_thermal_int(rdev, false); kv_update_current_ps(rdev, rdev->pm.dpm.boot_ps); } diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c index bf6300cfd62d..f8c01b8d1594 100644 --- a/drivers/gpu/drm/radeon/ni.c +++ b/drivers/gpu/drm/radeon/ni.c @@ -1073,12 +1073,12 @@ static void cayman_gpu_init(struct radeon_device *rdev) if ((rdev->config.cayman.max_backends_per_se == 1) && (rdev->flags & RADEON_IS_IGP)) { - if ((disabled_rb_mask & 3) == 1) { - /* RB0 disabled, RB1 enabled */ - tmp = 0x11111111; - } else { + if ((disabled_rb_mask & 3) == 2) { /* RB1 disabled, RB0 enabled */ tmp = 0x00000000; + } else { + /* RB0 disabled, RB1 enabled */ + tmp = 0x11111111; } } else { tmp = gb_addr_config & NUM_PIPES_MASK; diff --git a/drivers/gpu/drm/radeon/ni_dma.c b/drivers/gpu/drm/radeon/ni_dma.c index 7cf96b15377f..94fa49e974eb 100644 --- a/drivers/gpu/drm/radeon/ni_dma.c +++ b/drivers/gpu/drm/radeon/ni_dma.c @@ -191,12 +191,6 @@ int cayman_dma_resume(struct radeon_device *rdev) u32 reg_offset, wb_offset; int i, r; - /* Reset dma */ - WREG32(SRBM_SOFT_RESET, SOFT_RESET_DMA | SOFT_RESET_DMA1); - RREG32(SRBM_SOFT_RESET); - udelay(50); - WREG32(SRBM_SOFT_RESET, 0); - for (i = 0; i < 2; i++) { if (i == 0) { ring = &rdev->ring[R600_RING_TYPE_DMA_INDEX]; diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index 3cc78bb66042..e28de20d469a 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -742,6 +742,10 @@ int r100_irq_set(struct radeon_device *rdev) tmp |= RADEON_FP2_DETECT_MASK; } WREG32(RADEON_GEN_INT_CNTL, tmp); + + /* read back to post the write */ + RREG32(RADEON_GEN_INT_CNTL); + return 0; } @@ -3219,6 +3223,9 @@ void r100_bandwidth_update(struct radeon_device *rdev) uint32_t pixel_bytes1 = 0; uint32_t pixel_bytes2 = 0; + if (!rdev->mode_info.mode_config_initialized) + return; + radeon_update_display_priority(rdev); if (rdev->mode_info.crtcs[0]->base.enabled) { diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index 788f602e8989..74a8a38db4d5 100644 --- a/drivers/gpu/drm/radeon/r600.c +++ b/drivers/gpu/drm/radeon/r600.c @@ -3647,6 +3647,9 @@ int r600_irq_set(struct radeon_device *rdev) WREG32(RV770_CG_THERMAL_INT, thermal_int); } + /* posting read */ + RREG32(R_000E50_SRBM_STATUS); + return 0; } diff --git a/drivers/gpu/drm/radeon/r600_dma.c b/drivers/gpu/drm/radeon/r600_dma.c index b2d4c91e6272..99495513f6b1 100644 --- a/drivers/gpu/drm/radeon/r600_dma.c +++ b/drivers/gpu/drm/radeon/r600_dma.c @@ -124,15 +124,6 @@ int r600_dma_resume(struct radeon_device *rdev) u32 rb_bufsz; int r; - /* Reset dma */ - if (rdev->family >= CHIP_RV770) - WREG32(SRBM_SOFT_RESET, RV770_SOFT_RESET_DMA); - else - WREG32(SRBM_SOFT_RESET, SOFT_RESET_DMA); - RREG32(SRBM_SOFT_RESET); - udelay(50); - WREG32(SRBM_SOFT_RESET, 0); - WREG32(DMA_SEM_INCOMPLETE_TIMER_CNTL, 0); WREG32(DMA_SEM_WAIT_FAIL_TIMER_CNTL, 0); diff --git a/drivers/gpu/drm/radeon/r600_dpm.c b/drivers/gpu/drm/radeon/r600_dpm.c index 813db8de52b7..e98108236e04 100644 --- a/drivers/gpu/drm/radeon/r600_dpm.c +++ b/drivers/gpu/drm/radeon/r600_dpm.c @@ -187,7 +187,7 @@ u32 r600_dpm_get_vrefresh(struct radeon_device *rdev) 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) { - vrefresh = radeon_crtc->hw_mode.vrefresh; + vrefresh = drm_mode_vrefresh(&radeon_crtc->hw_mode); break; } } @@ -1209,7 +1209,7 @@ int r600_parse_extended_power_table(struct radeon_device *rdev) (mode_info->atom_context->bios + data_offset + le16_to_cpu(ext_hdr->usPowerTuneTableOffset)); rdev->pm.dpm.dyn_state.cac_tdp_table->maximum_power_delivery_limit = - ppt->usMaximumPowerDeliveryLimit; + le16_to_cpu(ppt->usMaximumPowerDeliveryLimit); pt = &ppt->power_tune_table; } else { ATOM_PPLIB_POWERTUNE_Table *ppt = (ATOM_PPLIB_POWERTUNE_Table *) diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 08e86f90c9a4..b837e9f9f8ce 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -294,6 +294,9 @@ int radeon_atom_get_leakage_vddc_based_on_leakage_params(struct radeon_device *r u16 *vddc, u16 *vddci, u16 virtual_voltage_id, u16 vbios_voltage_id); +int radeon_atom_get_voltage_evv(struct radeon_device *rdev, + u16 virtual_voltage_id, + u16 *voltage); int radeon_atom_round_to_true_voltage(struct radeon_device *rdev, u8 voltage_type, u16 nominal_voltage, diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c index 5600d4c5f981..64d6cfba9952 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.c +++ b/drivers/gpu/drm/radeon/radeon_asic.c @@ -335,6 +335,20 @@ static struct radeon_asic_ring r300_gfx_ring = { .set_wptr = &r100_gfx_set_wptr, }; +static struct radeon_asic_ring rv515_gfx_ring = { + .ib_execute = &r100_ring_ib_execute, + .emit_fence = &r300_fence_ring_emit, + .emit_semaphore = &r100_semaphore_ring_emit, + .cs_parse = &r300_cs_parse, + .ring_start = &rv515_ring_start, + .ring_test = &r100_ring_test, + .ib_test = &r100_ib_test, + .is_lockup = &r100_gpu_is_lockup, + .get_rptr = &r100_gfx_get_rptr, + .get_wptr = &r100_gfx_get_wptr, + .set_wptr = &r100_gfx_set_wptr, +}; + static struct radeon_asic r300_asic = { .init = &r300_init, .fini = &r300_fini, @@ -756,7 +770,7 @@ static struct radeon_asic rv515_asic = { .set_page = &rv370_pcie_gart_set_page, }, .ring = { - [RADEON_RING_TYPE_GFX_INDEX] = &r300_gfx_ring + [RADEON_RING_TYPE_GFX_INDEX] = &rv515_gfx_ring }, .irq = { .set = &rs600_irq_set, @@ -823,7 +837,7 @@ static struct radeon_asic r520_asic = { .set_page = &rv370_pcie_gart_set_page, }, .ring = { - [RADEON_RING_TYPE_GFX_INDEX] = &r300_gfx_ring + [RADEON_RING_TYPE_GFX_INDEX] = &rv515_gfx_ring }, .irq = { .set = &rs600_irq_set, diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c index 30844814c25a..2fa3cf615a67 100644 --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -447,6 +447,13 @@ static bool radeon_atom_apply_quirks(struct drm_device *dev, } } + /* Fujitsu D3003-S2 board lists DVI-I as DVI-I and VGA */ + if ((dev->pdev->device == 0x9805) && + (dev->pdev->subsystem_vendor == 0x1734) && + (dev->pdev->subsystem_device == 0x11bd)) { + if (*connector_type == DRM_MODE_CONNECTOR_VGA) + return false; + } return true; } @@ -1955,7 +1962,7 @@ static const char *thermal_controller_names[] = { "adm1032", "adm1030", "max6649", - "lm64", + "lm63", /* lm64 */ "f75375", "asc7xxx", }; @@ -1966,7 +1973,7 @@ static const char *pp_lib_thermal_controller_names[] = { "adm1032", "adm1030", "max6649", - "lm64", + "lm63", /* lm64 */ "f75375", "RV6xx", "RV770", @@ -2273,19 +2280,31 @@ static void radeon_atombios_add_pplib_thermal_controller(struct radeon_device *r (controller->ucFanParameters & ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with"); rdev->pm.int_thermal_type = THERMAL_TYPE_KV; - } else if ((controller->ucType == - ATOM_PP_THERMALCONTROLLER_EXTERNAL_GPIO) || - (controller->ucType == - ATOM_PP_THERMALCONTROLLER_ADT7473_WITH_INTERNAL) || - (controller->ucType == - ATOM_PP_THERMALCONTROLLER_EMC2103_WITH_INTERNAL)) { - DRM_INFO("Special thermal controller config\n"); + } else if (controller->ucType == + ATOM_PP_THERMALCONTROLLER_EXTERNAL_GPIO) { + DRM_INFO("External GPIO thermal controller %s fan control\n", + (controller->ucFanParameters & + ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with"); + rdev->pm.int_thermal_type = THERMAL_TYPE_EXTERNAL_GPIO; + } else if (controller->ucType == + ATOM_PP_THERMALCONTROLLER_ADT7473_WITH_INTERNAL) { + DRM_INFO("ADT7473 with internal thermal controller %s fan control\n", + (controller->ucFanParameters & + ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with"); + rdev->pm.int_thermal_type = THERMAL_TYPE_ADT7473_WITH_INTERNAL; + } else if (controller->ucType == + ATOM_PP_THERMALCONTROLLER_EMC2103_WITH_INTERNAL) { + DRM_INFO("EMC2103 with internal thermal controller %s fan control\n", + (controller->ucFanParameters & + ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with"); + rdev->pm.int_thermal_type = THERMAL_TYPE_EMC2103_WITH_INTERNAL; } else if (controller->ucType < ARRAY_SIZE(pp_lib_thermal_controller_names)) { DRM_INFO("Possible %s thermal controller at 0x%02x %s fan control\n", pp_lib_thermal_controller_names[controller->ucType], controller->ucI2cAddress >> 1, (controller->ucFanParameters & ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with"); + rdev->pm.int_thermal_type = THERMAL_TYPE_EXTERNAL; i2c_bus = radeon_lookup_i2c_gpio(rdev, controller->ucI2cLine); rdev->pm.i2c_bus = radeon_i2c_lookup(rdev, &i2c_bus); if (rdev->pm.i2c_bus) { @@ -3228,6 +3247,42 @@ int radeon_atom_get_leakage_vddc_based_on_leakage_params(struct radeon_device *r return 0; } +union get_voltage_info { + struct _GET_VOLTAGE_INFO_INPUT_PARAMETER_V1_2 in; + struct _GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_2 evv_out; +}; + +int radeon_atom_get_voltage_evv(struct radeon_device *rdev, + u16 virtual_voltage_id, + u16 *voltage) +{ + int index = GetIndexIntoMasterTable(COMMAND, GetVoltageInfo); + u32 entry_id; + u32 count = rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.count; + union get_voltage_info args; + + for (entry_id = 0; entry_id < count; entry_id++) { + if (rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries[entry_id].v == + virtual_voltage_id) + break; + } + + if (entry_id >= count) + return -EINVAL; + + args.in.ucVoltageType = VOLTAGE_TYPE_VDDC; + args.in.ucVoltageMode = ATOM_GET_VOLTAGE_EVV_VOLTAGE; + args.in.usVoltageLevel = cpu_to_le16(virtual_voltage_id); + args.in.ulSCLKFreq = + cpu_to_le32(rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries[entry_id].clk); + + atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); + + *voltage = le16_to_cpu(args.evv_out.usVoltageLevel); + + return 0; +} + int radeon_atom_get_voltage_gpio_settings(struct radeon_device *rdev, u16 voltage_level, u8 voltage_type, u32 *gpio_value, u32 *gpio_mask) diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c index 9ab30976287d..c43335ce8778 100644 --- a/drivers/gpu/drm/radeon/radeon_bios.c +++ b/drivers/gpu/drm/radeon/radeon_bios.c @@ -76,7 +76,7 @@ static bool igp_read_bios_from_vram(struct radeon_device *rdev) static bool radeon_read_bios(struct radeon_device *rdev) { - uint8_t __iomem *bios; + uint8_t __iomem *bios, val1, val2; size_t size; rdev->bios = NULL; @@ -86,15 +86,19 @@ static bool radeon_read_bios(struct radeon_device *rdev) return false; } - if (size == 0 || bios[0] != 0x55 || bios[1] != 0xaa) { + val1 = readb(&bios[0]); + val2 = readb(&bios[1]); + + if (size == 0 || val1 != 0x55 || val2 != 0xaa) { pci_unmap_rom(rdev->pdev, bios); return false; } - rdev->bios = kmemdup(bios, size, GFP_KERNEL); + rdev->bios = kzalloc(size, GFP_KERNEL); if (rdev->bios == NULL) { pci_unmap_rom(rdev->pdev, bios); return false; } + memcpy_fromio(rdev->bios, bios, size); pci_unmap_rom(rdev->pdev, bios); return true; } diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c index 7f2d6c0d11c1..2f2d2ce34709 100644 --- a/drivers/gpu/drm/radeon/radeon_cs.c +++ b/drivers/gpu/drm/radeon/radeon_cs.c @@ -179,11 +179,13 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data) u32 ring = RADEON_CS_RING_GFX; s32 priority = 0; + INIT_LIST_HEAD(&p->validated); + if (!cs->num_chunks) { return 0; } + /* get chunks */ - INIT_LIST_HEAD(&p->validated); p->idx = 0; p->ib.sa_bo = NULL; p->ib.semaphore = NULL; diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 0bf6f4a2bb97..e39026cc7d07 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1314,7 +1314,7 @@ int radeon_device_init(struct radeon_device *rdev, r = radeon_init(rdev); if (r) - return r; + goto failed; r = radeon_ib_ring_tests(rdev); if (r) @@ -1334,7 +1334,7 @@ int radeon_device_init(struct radeon_device *rdev, radeon_agp_disable(rdev); r = radeon_init(rdev); if (r) - return r; + goto failed; } if ((radeon_testing & 1)) { @@ -1356,6 +1356,11 @@ int radeon_device_init(struct radeon_device *rdev, DRM_INFO("radeon: acceleration disabled, skipping benchmarks\n"); } return 0; + +failed: + if (runtime) + vga_switcheroo_fini_domain_pm_ops(rdev->dev); + return r; } static void radeon_debugfs_remove_files(struct radeon_device *rdev); @@ -1376,6 +1381,8 @@ void radeon_device_fini(struct radeon_device *rdev) radeon_bo_evict_vram(rdev); radeon_fini(rdev); vga_switcheroo_unregister_client(rdev->pdev); + if (rdev->flags & RADEON_IS_PX) + vga_switcheroo_fini_domain_pm_ops(rdev->dev); vga_client_register(rdev->pdev, NULL, NULL, NULL); if (rdev->rio_mem) pci_iounmap(rdev->pdev, rdev->rio_mem); @@ -1600,7 +1607,6 @@ int radeon_gpu_reset(struct radeon_device *rdev) radeon_save_bios_scratch_regs(rdev); /* block TTM */ resched = ttm_bo_lock_delayed_workqueue(&rdev->mman.bdev); - radeon_pm_suspend(rdev); radeon_suspend(rdev); for (i = 0; i < RADEON_NUM_RINGS; ++i) { @@ -1646,9 +1652,24 @@ retry: } } - radeon_pm_resume(rdev); + if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled) { + /* do dpm late init */ + r = radeon_pm_late_init(rdev); + if (r) { + rdev->pm.dpm_enabled = false; + DRM_ERROR("radeon_pm_late_init failed, disabling dpm\n"); + } + } else { + /* resume old pm late */ + radeon_pm_resume(rdev); + } + drm_helper_resume_force_mode(rdev->ddev); + /* set the power state here in case we are a PX system or headless */ + if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled) + radeon_pm_compute_clocks(rdev); + ttm_bo_unlock_delayed_workqueue(&rdev->mman.bdev, resched); if (r) { /* bad news, how to tell it to userspace ? */ diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c index 089c9ffb0aa9..b3f0293ba0d8 100644 --- a/drivers/gpu/drm/radeon/radeon_irq_kms.c +++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c @@ -202,6 +202,16 @@ static bool radeon_msi_ok(struct radeon_device *rdev) if (rdev->flags & RADEON_IS_AGP) return false; + /* + * Older chips have a HW limitation, they can only generate 40 bits + * of address for "64-bit" MSIs which breaks on some platforms, notably + * IBM POWER servers, so we limit them + */ + if (rdev->family < CHIP_BONAIRE) { + dev_info(rdev->dev, "radeon: MSI limited to 32-bit\n"); + rdev->pdev->no_64bit_msi = 1; + } + /* force MSI on */ if (radeon_msi == 1) return true; diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index ea34a31d3bc8..6bffe82f241c 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -254,7 +254,14 @@ static int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file } break; case RADEON_INFO_ACCEL_WORKING2: - *value = rdev->accel_working; + if (rdev->family == CHIP_HAWAII) { + if (rdev->accel_working) + *value = 2; + else + *value = 0; + } else { + *value = rdev->accel_working; + } break; case RADEON_INFO_TILING_CONFIG: if (rdev->family >= CHIP_BONAIRE) @@ -733,6 +740,8 @@ int radeon_get_vblank_timestamp_kms(struct drm_device *dev, int crtc, /* Get associated drm_crtc: */ drmcrtc = &rdev->mode_info.crtcs[crtc]->base; + if (!drmcrtc) + return -EINVAL; /* Helper routine in DRM core does all the work: */ return drm_calc_vbltimestamp_from_scanoutpos(dev, crtc, max_error, diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index f77d9d0d54b5..0095ee7fce34 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -458,10 +458,6 @@ static ssize_t radeon_get_dpm_state(struct device *dev, struct radeon_device *rdev = ddev->dev_private; enum radeon_pm_state_type pm = rdev->pm.dpm.user_state; - if ((rdev->flags & RADEON_IS_PX) && - (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) - return snprintf(buf, PAGE_SIZE, "off\n"); - return snprintf(buf, PAGE_SIZE, "%s\n", (pm == POWER_STATE_TYPE_BATTERY) ? "battery" : (pm == POWER_STATE_TYPE_BALANCED) ? "balanced" : "performance"); @@ -475,11 +471,6 @@ static ssize_t radeon_set_dpm_state(struct device *dev, struct drm_device *ddev = dev_get_drvdata(dev); struct radeon_device *rdev = ddev->dev_private; - /* Can't set dpm state when the card is off */ - if ((rdev->flags & RADEON_IS_PX) && - (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) - return -EINVAL; - mutex_lock(&rdev->pm.mutex); if (strncmp("battery", buf, strlen("battery")) == 0) rdev->pm.dpm.user_state = POWER_STATE_TYPE_BATTERY; @@ -493,7 +484,12 @@ static ssize_t radeon_set_dpm_state(struct device *dev, goto fail; } mutex_unlock(&rdev->pm.mutex); - radeon_pm_compute_clocks(rdev); + + /* Can't set dpm state when the card is off */ + if (!(rdev->flags & RADEON_IS_PX) || + (ddev->switch_power_state == DRM_SWITCH_POWER_ON)) + radeon_pm_compute_clocks(rdev); + fail: return count; } @@ -1264,8 +1260,39 @@ dpm_failed: return ret; } +struct radeon_dpm_quirk { + u32 chip_vendor; + u32 chip_device; + u32 subsys_vendor; + u32 subsys_device; +}; + +/* cards with dpm stability problems */ +static struct radeon_dpm_quirk radeon_dpm_quirk_list[] = { + /* TURKS - https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1386534 */ + { PCI_VENDOR_ID_ATI, 0x6759, 0x1682, 0x3195 }, + /* TURKS - https://bugzilla.kernel.org/show_bug.cgi?id=83731 */ + { PCI_VENDOR_ID_ATI, 0x6840, 0x1179, 0xfb81 }, + { 0, 0, 0, 0 }, +}; + int radeon_pm_init(struct radeon_device *rdev) { + struct radeon_dpm_quirk *p = radeon_dpm_quirk_list; + bool disable_dpm = false; + + /* Apply dpm quirks */ + while (p && p->chip_device != 0) { + if (rdev->pdev->vendor == p->chip_vendor && + rdev->pdev->device == p->chip_device && + rdev->pdev->subsystem_vendor == p->subsys_vendor && + rdev->pdev->subsystem_device == p->subsys_device) { + disable_dpm = true; + break; + } + ++p; + } + /* enable dpm on rv6xx+ */ switch (rdev->family) { case CHIP_RV610: @@ -1276,10 +1303,6 @@ int radeon_pm_init(struct radeon_device *rdev) case CHIP_RS780: case CHIP_RS880: case CHIP_RV770: - case CHIP_BARTS: - case CHIP_TURKS: - case CHIP_CAICOS: - case CHIP_CAYMAN: /* DPM requires the RLC, RV770+ dGPU requires SMC */ if (!rdev->rlc_fw) rdev->pm.pm_method = PM_METHOD_PROFILE; @@ -1303,6 +1326,10 @@ int radeon_pm_init(struct radeon_device *rdev) case CHIP_PALM: case CHIP_SUMO: case CHIP_SUMO2: + case CHIP_BARTS: + case CHIP_TURKS: + case CHIP_CAICOS: + case CHIP_CAYMAN: case CHIP_ARUBA: case CHIP_TAHITI: case CHIP_PITCAIRN: @@ -1320,6 +1347,8 @@ int radeon_pm_init(struct radeon_device *rdev) (!(rdev->flags & RADEON_IS_IGP)) && (!rdev->smc_fw)) rdev->pm.pm_method = PM_METHOD_PROFILE; + else if (disable_dpm && (radeon_dpm == -1)) + rdev->pm.pm_method = PM_METHOD_PROFILE; else if (radeon_dpm == 0) rdev->pm.pm_method = PM_METHOD_PROFILE; else diff --git a/drivers/gpu/drm/radeon/radeon_semaphore.c b/drivers/gpu/drm/radeon/radeon_semaphore.c index 9006b32d5eed..eb7b60047e86 100644 --- a/drivers/gpu/drm/radeon/radeon_semaphore.c +++ b/drivers/gpu/drm/radeon/radeon_semaphore.c @@ -34,7 +34,7 @@ int radeon_semaphore_create(struct radeon_device *rdev, struct radeon_semaphore **semaphore) { - uint32_t *cpu_addr; + uint64_t *cpu_addr; int i, r; *semaphore = kmalloc(sizeof(struct radeon_semaphore), GFP_KERNEL); diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 040a2a10ea17..45a9a03efc06 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -191,7 +191,7 @@ static void radeon_evict_flags(struct ttm_buffer_object *bo, rbo = container_of(bo, struct radeon_bo, tbo); switch (bo->mem.mem_type) { case TTM_PL_VRAM: - if (rbo->rdev->ring[RADEON_RING_TYPE_GFX_INDEX].ready == false) + if (rbo->rdev->ring[radeon_copy_ring_index(rbo->rdev)].ready == false) radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_CPU); else radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_GTT); diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c index 95b693c11640..4261b3865cb0 100644 --- a/drivers/gpu/drm/radeon/rs600.c +++ b/drivers/gpu/drm/radeon/rs600.c @@ -700,6 +700,10 @@ int rs600_irq_set(struct radeon_device *rdev) WREG32(R_007D18_DC_HOT_PLUG_DETECT2_INT_CONTROL, hpd2); if (ASIC_IS_DCE2(rdev)) WREG32(R_007408_HDMI0_AUDIO_PACKET_CONTROL, hdmi0); + + /* posting read */ + RREG32(R_000040_GEN_INT_CNTL); + return 0; } @@ -890,6 +894,9 @@ void rs600_bandwidth_update(struct radeon_device *rdev) u32 d1mode_priority_a_cnt, d2mode_priority_a_cnt; /* FIXME: implement full support */ + if (!rdev->mode_info.mode_config_initialized) + return; + radeon_update_display_priority(rdev); if (rdev->mode_info.crtcs[0]->base.enabled) diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c index 3462b64369bf..0a2d36e81108 100644 --- a/drivers/gpu/drm/radeon/rs690.c +++ b/drivers/gpu/drm/radeon/rs690.c @@ -579,6 +579,9 @@ void rs690_bandwidth_update(struct radeon_device *rdev) u32 d1mode_priority_a_cnt, d1mode_priority_b_cnt; u32 d2mode_priority_a_cnt, d2mode_priority_b_cnt; + if (!rdev->mode_info.mode_config_initialized) + return; + radeon_update_display_priority(rdev); if (rdev->mode_info.crtcs[0]->base.enabled) diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c index 237dd29d9f1c..b49965a21a2d 100644 --- a/drivers/gpu/drm/radeon/rv515.c +++ b/drivers/gpu/drm/radeon/rv515.c @@ -1276,6 +1276,9 @@ void rv515_bandwidth_update(struct radeon_device *rdev) struct drm_display_mode *mode0 = NULL; struct drm_display_mode *mode1 = NULL; + if (!rdev->mode_info.mode_config_initialized) + return; + radeon_update_display_priority(rdev); if (rdev->mode_info.crtcs[0]->base.enabled) diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index ea93393374df..2f2deccb3b78 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -2227,6 +2227,9 @@ void dce6_bandwidth_update(struct radeon_device *rdev) u32 num_heads = 0, lb_size; int i; + if (!rdev->mode_info.mode_config_initialized) + return; + radeon_update_display_priority(rdev); for (i = 0; i < rdev->num_crtc; i++) { @@ -4810,7 +4813,7 @@ void si_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm) /* write new base address */ radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3)); - radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) | + radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(1) | WRITE_DATA_DST_SEL(0))); if (vm->id < 8) { @@ -5955,6 +5958,9 @@ int si_irq_set(struct radeon_device *rdev) WREG32(CG_THERMAL_INT, thermal_int); + /* posting read */ + RREG32(SRBM_STATUS); + return 0; } @@ -6872,8 +6878,7 @@ int si_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk) WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_BYPASS_EN_MASK, ~UPLL_BYPASS_EN_MASK); if (!vclk || !dclk) { - /* keep the Bypass mode, put PLL to sleep */ - WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_SLEEP_MASK, ~UPLL_SLEEP_MASK); + /* keep the Bypass mode */ return 0; } @@ -6889,8 +6894,7 @@ int si_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk) /* set VCO_MODE to 1 */ WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_VCO_MODE_MASK, ~UPLL_VCO_MODE_MASK); - /* toggle UPLL_SLEEP to 1 then back to 0 */ - WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_SLEEP_MASK, ~UPLL_SLEEP_MASK); + /* disable sleep mode */ WREG32_P(CG_UPLL_FUNC_CNTL, 0, ~UPLL_SLEEP_MASK); /* deassert UPLL_RESET */ diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index 0a2f5b4bca43..35bf2bba69bf 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -2900,6 +2900,22 @@ static int si_init_smc_spll_table(struct radeon_device *rdev) return ret; } +struct si_dpm_quirk { + u32 chip_vendor; + u32 chip_device; + u32 subsys_vendor; + u32 subsys_device; + u32 max_sclk; + u32 max_mclk; +}; + +/* cards with dpm stability problems */ +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 }, + { 0, 0, 0, 0 }, +}; + static void si_apply_state_adjust_rules(struct radeon_device *rdev, struct radeon_ps *rps) { @@ -2910,7 +2926,22 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev, u32 mclk, sclk; u16 vddc, vddci; u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc; + u32 max_sclk = 0, max_mclk = 0; int i; + struct si_dpm_quirk *p = si_dpm_quirk_list; + + /* Apply dpm quirks */ + while (p && p->chip_device != 0) { + if (rdev->pdev->vendor == p->chip_vendor && + rdev->pdev->device == p->chip_device && + rdev->pdev->subsystem_vendor == p->subsys_vendor && + rdev->pdev->subsystem_device == p->subsys_device) { + max_sclk = p->max_sclk; + max_mclk = p->max_mclk; + break; + } + ++p; + } if ((rdev->pm.dpm.new_active_crtc_count > 1) || ni_dpm_vblank_too_short(rdev)) @@ -2964,6 +2995,14 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev, if (ps->performance_levels[i].mclk > max_mclk_vddc) ps->performance_levels[i].mclk = max_mclk_vddc; } + if (max_mclk) { + if (ps->performance_levels[i].mclk > max_mclk) + ps->performance_levels[i].mclk = max_mclk; + } + if (max_sclk) { + if (ps->performance_levels[i].sclk > max_sclk) + ps->performance_levels[i].sclk = max_sclk; + } } /* XXX validate the min clocks required for display */ @@ -6200,7 +6239,7 @@ static void si_parse_pplib_clock_info(struct radeon_device *rdev, if ((rps->class2 & ATOM_PPLIB_CLASSIFICATION2_ULV) && index == 0) { /* XXX disable for A0 tahiti */ - si_pi->ulv.supported = true; + si_pi->ulv.supported = false; si_pi->ulv.pl = *pl; si_pi->ulv.one_pcie_lane_in_ulv = false; si_pi->ulv.volt_change_delay = SISLANDS_ULVVOLTAGECHANGEDELAY_DFLT; diff --git a/drivers/gpu/drm/radeon/trinity_dpm.c b/drivers/gpu/drm/radeon/trinity_dpm.c index 2da0e17eb960..d9cfa09b2e3f 100644 --- a/drivers/gpu/drm/radeon/trinity_dpm.c +++ b/drivers/gpu/drm/radeon/trinity_dpm.c @@ -1877,7 +1877,16 @@ int trinity_dpm_init(struct radeon_device *rdev) for (i = 0; i < SUMO_MAX_HARDWARE_POWERLEVELS; i++) pi->at[i] = TRINITY_AT_DFLT; - pi->enable_bapm = false; + /* There are stability issues reported on with + * bapm enabled when switching between AC and battery + * power. At the same time, some MSI boards hang + * if it's not enabled and dpm is enabled. Just enable + * it for MSI boards right now. + */ + if (rdev->pdev->subsystem_vendor == 0x1462) + pi->enable_bapm = true; + else + pi->enable_bapm = false; pi->enable_nbps_policy = true; pi->enable_sclk_ds = true; pi->enable_gfx_power_gating = true; diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c index 171a8203892c..52b47115b5cb 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c @@ -84,6 +84,7 @@ static int modeset_init(struct drm_device *dev) if ((priv->num_encoders == 0) || (priv->num_connectors == 0)) { /* oh nos! */ dev_err(dev->dev, "no encoders/connectors found\n"); + drm_mode_config_cleanup(dev); return -ENXIO; } @@ -122,6 +123,7 @@ static int tilcdc_unload(struct drm_device *dev) struct tilcdc_drm_private *priv = dev->dev_private; struct tilcdc_module *mod, *cur; + drm_fbdev_cma_fini(priv->fbdev); drm_kms_helper_poll_fini(dev); drm_mode_config_cleanup(dev); drm_vblank_cleanup(dev); @@ -177,33 +179,37 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags) dev->dev_private = priv; priv->wq = alloc_ordered_workqueue("tilcdc", 0); + if (!priv->wq) { + ret = -ENOMEM; + goto fail_free_priv; + } res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!res) { dev_err(dev->dev, "failed to get memory resource\n"); ret = -EINVAL; - goto fail; + goto fail_free_wq; } priv->mmio = ioremap_nocache(res->start, resource_size(res)); if (!priv->mmio) { dev_err(dev->dev, "failed to ioremap\n"); ret = -ENOMEM; - goto fail; + goto fail_free_wq; } priv->clk = clk_get(dev->dev, "fck"); if (IS_ERR(priv->clk)) { dev_err(dev->dev, "failed to get functional clock\n"); ret = -ENODEV; - goto fail; + goto fail_iounmap; } priv->disp_clk = clk_get(dev->dev, "dpll_disp_ck"); if (IS_ERR(priv->clk)) { dev_err(dev->dev, "failed to get display clock\n"); ret = -ENODEV; - goto fail; + goto fail_put_clk; } #ifdef CONFIG_CPU_FREQ @@ -213,7 +219,7 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags) CPUFREQ_TRANSITION_NOTIFIER); if (ret) { dev_err(dev->dev, "failed to register cpufreq notifier\n"); - goto fail; + goto fail_put_disp_clk; } #endif @@ -258,13 +264,13 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags) ret = modeset_init(dev); if (ret < 0) { dev_err(dev->dev, "failed to initialize mode setting\n"); - goto fail; + goto fail_cpufreq_unregister; } ret = drm_vblank_init(dev, 1); if (ret < 0) { dev_err(dev->dev, "failed to initialize vblank\n"); - goto fail; + goto fail_mode_config_cleanup; } pm_runtime_get_sync(dev->dev); @@ -272,7 +278,7 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags) pm_runtime_put_sync(dev->dev); if (ret < 0) { dev_err(dev->dev, "failed to install IRQ handler\n"); - goto fail; + goto fail_vblank_cleanup; } platform_set_drvdata(pdev, dev); @@ -288,13 +294,48 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags) priv->fbdev = drm_fbdev_cma_init(dev, bpp, dev->mode_config.num_crtc, dev->mode_config.num_connector); + if (IS_ERR(priv->fbdev)) { + ret = PTR_ERR(priv->fbdev); + goto fail_irq_uninstall; + } drm_kms_helper_poll_init(dev); return 0; -fail: - tilcdc_unload(dev); +fail_irq_uninstall: + pm_runtime_get_sync(dev->dev); + drm_irq_uninstall(dev); + pm_runtime_put_sync(dev->dev); + +fail_vblank_cleanup: + drm_vblank_cleanup(dev); + +fail_mode_config_cleanup: + drm_mode_config_cleanup(dev); + +fail_cpufreq_unregister: + pm_runtime_disable(dev->dev); +#ifdef CONFIG_CPU_FREQ + cpufreq_unregister_notifier(&priv->freq_transition, + CPUFREQ_TRANSITION_NOTIFIER); +fail_put_disp_clk: + clk_put(priv->disp_clk); +#endif + +fail_put_clk: + clk_put(priv->clk); + +fail_iounmap: + iounmap(priv->mmio); + +fail_free_wq: + flush_workqueue(priv->wq); + destroy_workqueue(priv->wq); + +fail_free_priv: + dev->dev_private = NULL; + kfree(priv); return ret; } @@ -628,10 +669,10 @@ static int __init tilcdc_drm_init(void) static void __exit tilcdc_drm_fini(void) { DBG("fini"); - tilcdc_tfp410_fini(); - tilcdc_slave_fini(); - tilcdc_panel_fini(); platform_driver_unregister(&tilcdc_platform_driver); + tilcdc_panel_fini(); + tilcdc_slave_fini(); + tilcdc_tfp410_fini(); } late_initcall(tilcdc_drm_init); diff --git a/drivers/gpu/drm/tilcdc/tilcdc_panel.c b/drivers/gpu/drm/tilcdc/tilcdc_panel.c index 86c67329b605..b085dcc54fb5 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_panel.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_panel.c @@ -151,6 +151,7 @@ struct panel_connector { static void panel_connector_destroy(struct drm_connector *connector) { struct panel_connector *panel_connector = to_panel_connector(connector); + drm_sysfs_connector_remove(connector); drm_connector_cleanup(connector); kfree(panel_connector); } @@ -285,10 +286,8 @@ static void panel_destroy(struct tilcdc_module *mod) { struct panel_module *panel_mod = to_panel_module(mod); - if (panel_mod->timings) { + if (panel_mod->timings) display_timings_release(panel_mod->timings); - kfree(panel_mod->timings); - } tilcdc_module_cleanup(mod); kfree(panel_mod->info); diff --git a/drivers/gpu/drm/tilcdc/tilcdc_slave.c b/drivers/gpu/drm/tilcdc/tilcdc_slave.c index 595068ba2d5e..2f83ffb7f37e 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_slave.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_slave.c @@ -166,6 +166,7 @@ struct slave_connector { static void slave_connector_destroy(struct drm_connector *connector) { struct slave_connector *slave_connector = to_slave_connector(connector); + drm_sysfs_connector_remove(connector); drm_connector_cleanup(connector); kfree(slave_connector); } diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c index c38b56b268ac..ce75ac8de4f8 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c @@ -167,6 +167,7 @@ struct tfp410_connector { static void tfp410_connector_destroy(struct drm_connector *connector) { struct tfp410_connector *tfp410_connector = to_tfp410_connector(connector); + drm_sysfs_connector_remove(connector); drm_connector_cleanup(connector); kfree(tfp410_connector); } diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c index 863bef9f9234..76329d27385b 100644 --- a/drivers/gpu/drm/ttm/ttm_page_alloc.c +++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c @@ -297,9 +297,12 @@ static void ttm_pool_update_free_locked(struct ttm_page_pool *pool, * * @pool: to free the pages from * @free_all: If set to true will free all pages in pool + * @use_static: Safe to use static buffer **/ -static int ttm_page_pool_free(struct ttm_page_pool *pool, unsigned nr_free) +static int ttm_page_pool_free(struct ttm_page_pool *pool, unsigned nr_free, + bool use_static) { + static struct page *static_buf[NUM_PAGES_TO_ALLOC]; unsigned long irq_flags; struct page *p; struct page **pages_to_free; @@ -309,8 +312,11 @@ static int ttm_page_pool_free(struct ttm_page_pool *pool, unsigned nr_free) if (NUM_PAGES_TO_ALLOC < nr_free) npages_to_free = NUM_PAGES_TO_ALLOC; - pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), - GFP_KERNEL); + if (use_static) + pages_to_free = static_buf; + else + pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), + GFP_KERNEL); if (!pages_to_free) { pr_err("Failed to allocate memory for pool free operation\n"); return 0; @@ -373,7 +379,8 @@ restart: if (freed_pages) ttm_pages_put(pages_to_free, freed_pages); out: - kfree(pages_to_free); + if (pages_to_free != static_buf) + kfree(pages_to_free); return nr_free; } @@ -382,32 +389,33 @@ out: * * XXX: (dchinner) Deadlock warning! * - * ttm_page_pool_free() does memory allocation using GFP_KERNEL. that means - * this can deadlock when called a sc->gfp_mask that is not equal to - * GFP_KERNEL. - * * This code is crying out for a shrinker per pool.... */ static unsigned long ttm_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { - static atomic_t start_pool = ATOMIC_INIT(0); + static DEFINE_MUTEX(lock); + static unsigned start_pool; unsigned i; - unsigned pool_offset = atomic_add_return(1, &start_pool); + unsigned pool_offset; struct ttm_page_pool *pool; int shrink_pages = sc->nr_to_scan; unsigned long freed = 0; - pool_offset = pool_offset % NUM_POOLS; + if (!mutex_trylock(&lock)) + return SHRINK_STOP; + pool_offset = ++start_pool % NUM_POOLS; /* select start pool in round robin fashion */ for (i = 0; i < NUM_POOLS; ++i) { unsigned nr_free = shrink_pages; if (shrink_pages == 0) break; pool = &_manager->pools[(i + pool_offset)%NUM_POOLS]; - shrink_pages = ttm_page_pool_free(pool, nr_free); + /* OK to use static buffer since global mutex is held. */ + shrink_pages = ttm_page_pool_free(pool, nr_free, true); freed += nr_free - shrink_pages; } + mutex_unlock(&lock); return freed; } @@ -706,7 +714,7 @@ static void ttm_put_pages(struct page **pages, unsigned npages, int flags, } spin_unlock_irqrestore(&pool->lock, irq_flags); if (npages) - ttm_page_pool_free(pool, npages); + ttm_page_pool_free(pool, npages, false); } /* @@ -845,8 +853,9 @@ void ttm_page_alloc_fini(void) pr_info("Finalizing pool allocator\n"); ttm_pool_mm_shrink_fini(_manager); + /* OK to use static buffer since global mutex is no longer used. */ for (i = 0; i < NUM_POOLS; ++i) - ttm_page_pool_free(&_manager->pools[i], FREE_ALL_PAGES); + ttm_page_pool_free(&_manager->pools[i], FREE_ALL_PAGES, true); kobject_put(&_manager->kobj); _manager = NULL; diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c index fb8259f69839..3dfa97d04e51 100644 --- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c +++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c @@ -411,9 +411,12 @@ static void ttm_dma_page_put(struct dma_pool *pool, struct dma_page *d_page) * * @pool: to free the pages from * @nr_free: If set to true will free all pages in pool + * @use_static: Safe to use static buffer **/ -static unsigned ttm_dma_page_pool_free(struct dma_pool *pool, unsigned nr_free) +static unsigned ttm_dma_page_pool_free(struct dma_pool *pool, unsigned nr_free, + bool use_static) { + static struct page *static_buf[NUM_PAGES_TO_ALLOC]; unsigned long irq_flags; struct dma_page *dma_p, *tmp; struct page **pages_to_free; @@ -430,8 +433,11 @@ static unsigned ttm_dma_page_pool_free(struct dma_pool *pool, unsigned nr_free) npages_to_free, nr_free); } #endif - pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), - GFP_KERNEL); + if (use_static) + pages_to_free = static_buf; + else + pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), + GFP_KERNEL); if (!pages_to_free) { pr_err("%s: Failed to allocate memory for pool free operation\n", @@ -501,7 +507,8 @@ restart: if (freed_pages) ttm_dma_pages_put(pool, &d_pages, pages_to_free, freed_pages); out: - kfree(pages_to_free); + if (pages_to_free != static_buf) + kfree(pages_to_free); return nr_free; } @@ -530,7 +537,8 @@ static void ttm_dma_free_pool(struct device *dev, enum pool_type type) if (pool->type != type) continue; /* Takes a spinlock.. */ - ttm_dma_page_pool_free(pool, FREE_ALL_PAGES); + /* OK to use static buffer since global mutex is held. */ + ttm_dma_page_pool_free(pool, FREE_ALL_PAGES, true); WARN_ON(((pool->npages_in_use + pool->npages_free) != 0)); /* This code path is called after _all_ references to the * struct device has been dropped - so nobody should be @@ -983,7 +991,7 @@ void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev) /* shrink pool if necessary (only on !is_cached pools)*/ if (npages) - ttm_dma_page_pool_free(pool, npages); + ttm_dma_page_pool_free(pool, npages, false); ttm->state = tt_unpopulated; } EXPORT_SYMBOL_GPL(ttm_dma_unpopulate); @@ -993,20 +1001,15 @@ EXPORT_SYMBOL_GPL(ttm_dma_unpopulate); * * XXX: (dchinner) Deadlock warning! * - * ttm_dma_page_pool_free() does GFP_KERNEL memory allocation, and so attention - * needs to be paid to sc->gfp_mask to determine if this can be done or not. - * GFP_KERNEL memory allocation in a GFP_ATOMIC reclaim context woul dbe really - * bad. - * * I'm getting sadder as I hear more pathetical whimpers about needing per-pool * shrinkers */ static unsigned long ttm_dma_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { - static atomic_t start_pool = ATOMIC_INIT(0); + static unsigned start_pool; unsigned idx = 0; - unsigned pool_offset = atomic_add_return(1, &start_pool); + unsigned pool_offset; unsigned shrink_pages = sc->nr_to_scan; struct device_pools *p; unsigned long freed = 0; @@ -1014,8 +1017,11 @@ ttm_dma_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) if (list_empty(&_manager->pools)) return SHRINK_STOP; - mutex_lock(&_manager->lock); - pool_offset = pool_offset % _manager->npools; + if (!mutex_trylock(&_manager->lock)) + return SHRINK_STOP; + if (!_manager->npools) + goto out; + pool_offset = ++start_pool % _manager->npools; list_for_each_entry(p, &_manager->pools, pools) { unsigned nr_free; @@ -1027,13 +1033,15 @@ ttm_dma_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) if (++idx < pool_offset) continue; nr_free = shrink_pages; - shrink_pages = ttm_dma_page_pool_free(p->pool, nr_free); + /* OK to use static buffer since global mutex is held. */ + shrink_pages = ttm_dma_page_pool_free(p->pool, nr_free, true); freed += nr_free - shrink_pages; pr_debug("%s: (%s:%d) Asked to shrink %d, have %d more to go\n", p->pool->dev_name, p->pool->name, current->pid, nr_free, shrink_pages); } +out: mutex_unlock(&_manager->lock); return freed; } @@ -1044,7 +1052,8 @@ ttm_dma_pool_shrink_count(struct shrinker *shrink, struct shrink_control *sc) struct device_pools *p; unsigned long count = 0; - mutex_lock(&_manager->lock); + if (!mutex_trylock(&_manager->lock)) + return 0; list_for_each_entry(p, &_manager->pools, pools) count += p->pool->npages_free; mutex_unlock(&_manager->lock); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 0083cbf99edf..0771dcbf9ed0 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -688,7 +688,11 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) goto out_err0; } - if (unlikely(dev_priv->prim_bb_mem < dev_priv->vram_size)) + /* + * Limit back buffer size to VRAM size. Remove this once + * screen targets are implemented. + */ + if (dev_priv->prim_bb_mem > dev_priv->vram_size) dev_priv->prim_bb_mem = dev_priv->vram_size; mutex_unlock(&dev_priv->hw_mutex); @@ -729,32 +733,6 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) goto out_err1; } - ret = ttm_bo_init_mm(&dev_priv->bdev, TTM_PL_VRAM, - (dev_priv->vram_size >> PAGE_SHIFT)); - if (unlikely(ret != 0)) { - DRM_ERROR("Failed initializing memory manager for VRAM.\n"); - goto out_err2; - } - - dev_priv->has_gmr = true; - if (((dev_priv->capabilities & (SVGA_CAP_GMR | SVGA_CAP_GMR2)) == 0) || - refuse_dma || ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_GMR, - VMW_PL_GMR) != 0) { - DRM_INFO("No GMR memory available. " - "Graphics memory resources are very limited.\n"); - dev_priv->has_gmr = false; - } - - if (dev_priv->capabilities & SVGA_CAP_GBOBJECTS) { - dev_priv->has_mob = true; - if (ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_MOB, - VMW_PL_MOB) != 0) { - DRM_INFO("No MOB memory available. " - "3D will be disabled.\n"); - dev_priv->has_mob = false; - } - } - dev_priv->mmio_mtrr = arch_phys_wc_add(dev_priv->mmio_start, dev_priv->mmio_size); @@ -817,6 +795,33 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) goto out_no_fman; } + + ret = ttm_bo_init_mm(&dev_priv->bdev, TTM_PL_VRAM, + (dev_priv->vram_size >> PAGE_SHIFT)); + if (unlikely(ret != 0)) { + DRM_ERROR("Failed initializing memory manager for VRAM.\n"); + goto out_no_vram; + } + + dev_priv->has_gmr = true; + if (((dev_priv->capabilities & (SVGA_CAP_GMR | SVGA_CAP_GMR2)) == 0) || + refuse_dma || ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_GMR, + VMW_PL_GMR) != 0) { + DRM_INFO("No GMR memory available. " + "Graphics memory resources are very limited.\n"); + dev_priv->has_gmr = false; + } + + if (dev_priv->capabilities & SVGA_CAP_GBOBJECTS) { + dev_priv->has_mob = true; + if (ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_MOB, + VMW_PL_MOB) != 0) { + DRM_INFO("No MOB memory available. " + "3D will be disabled.\n"); + dev_priv->has_mob = false; + } + } + vmw_kms_save_vga(dev_priv); /* Start kms and overlay systems, needs fifo. */ @@ -842,6 +847,12 @@ out_no_fifo: vmw_kms_close(dev_priv); out_no_kms: vmw_kms_restore_vga(dev_priv); + if (dev_priv->has_mob) + (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB); + if (dev_priv->has_gmr) + (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR); + (void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM); +out_no_vram: vmw_fence_manager_takedown(dev_priv->fman); out_no_fman: if (dev_priv->capabilities & SVGA_CAP_IRQMASK) @@ -857,12 +868,6 @@ out_err4: iounmap(dev_priv->mmio_virt); out_err3: arch_phys_wc_del(dev_priv->mmio_mtrr); - if (dev_priv->has_mob) - (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB); - if (dev_priv->has_gmr) - (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR); - (void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM); -out_err2: (void)ttm_bo_device_release(&dev_priv->bdev); out_err1: vmw_ttm_global_release(dev_priv); @@ -892,6 +897,13 @@ static int vmw_driver_unload(struct drm_device *dev) } vmw_kms_close(dev_priv); vmw_overlay_close(dev_priv); + + if (dev_priv->has_mob) + (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB); + if (dev_priv->has_gmr) + (void)ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR); + (void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM); + vmw_fence_manager_takedown(dev_priv->fman); if (dev_priv->capabilities & SVGA_CAP_IRQMASK) drm_irq_uninstall(dev_priv->dev); @@ -903,11 +915,6 @@ static int vmw_driver_unload(struct drm_device *dev) ttm_object_device_release(&dev_priv->tdev); iounmap(dev_priv->mmio_virt); arch_phys_wc_del(dev_priv->mmio_mtrr); - if (dev_priv->has_mob) - (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB); - if (dev_priv->has_gmr) - (void)ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR); - (void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM); (void)ttm_bo_device_release(&dev_priv->bdev); vmw_ttm_global_release(dev_priv); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c index 436b013b4231..b65272d7ea56 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c @@ -1049,6 +1049,8 @@ static int vmw_event_fence_action_create(struct drm_file *file_priv, if (ret != 0) goto out_no_queue; + return 0; + out_no_queue: event->base.destroy(&event->base); out_no_event: @@ -1124,17 +1126,10 @@ int vmw_fence_event_ioctl(struct drm_device *dev, void *data, BUG_ON(fence == NULL); - if (arg->flags & DRM_VMW_FE_FLAG_REQ_TIME) - ret = vmw_event_fence_action_create(file_priv, fence, - arg->flags, - arg->user_data, - true); - else - ret = vmw_event_fence_action_create(file_priv, fence, - arg->flags, - arg->user_data, - true); - + ret = vmw_event_fence_action_create(file_priv, fence, + arg->flags, + arg->user_data, + true); if (unlikely(ret != 0)) { if (ret != -ERESTARTSYS) DRM_ERROR("Failed to attach event to fence.\n"); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c index 6ccd993e26bf..6eae14d2a3f7 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c @@ -180,8 +180,9 @@ void vmw_fifo_release(struct vmw_private *dev_priv, struct vmw_fifo_state *fifo) mutex_lock(&dev_priv->hw_mutex); + vmw_write(dev_priv, SVGA_REG_SYNC, SVGA_SYNC_GENERIC); while (vmw_read(dev_priv, SVGA_REG_BUSY) != 0) - vmw_write(dev_priv, SVGA_REG_SYNC, SVGA_SYNC_GENERIC); + ; dev_priv->last_read_seqno = ioread32(fifo_mem + SVGA_FIFO_FENCE); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 8a650413dea5..c8f8ecf7b282 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1954,6 +1954,14 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector, DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }; int i; + u32 assumed_bpp = 2; + + /* + * If using screen objects, then assume 32-bpp because that's what the + * SVGA device is assuming + */ + if (dev_priv->sou_priv) + assumed_bpp = 4; /* Add preferred mode */ { @@ -1964,8 +1972,9 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector, mode->vdisplay = du->pref_height; vmw_guess_mode_timing(mode); - if (vmw_kms_validate_mode_vram(dev_priv, mode->hdisplay * 2, - mode->vdisplay)) { + if (vmw_kms_validate_mode_vram(dev_priv, + mode->hdisplay * assumed_bpp, + mode->vdisplay)) { drm_mode_probed_add(connector, mode); } else { drm_mode_destroy(dev, mode); @@ -1987,7 +1996,8 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector, bmode->vdisplay > max_height) continue; - if (!vmw_kms_validate_mode_vram(dev_priv, bmode->hdisplay * 2, + if (!vmw_kms_validate_mode_vram(dev_priv, + bmode->hdisplay * assumed_bpp, bmode->vdisplay)) continue; diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c index 6866448083b2..37ac7b5dbd06 100644 --- a/drivers/gpu/vga/vga_switcheroo.c +++ b/drivers/gpu/vga/vga_switcheroo.c @@ -660,6 +660,12 @@ int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain * } EXPORT_SYMBOL(vga_switcheroo_init_domain_pm_ops); +void vga_switcheroo_fini_domain_pm_ops(struct device *dev) +{ + dev->pm_domain = NULL; +} +EXPORT_SYMBOL(vga_switcheroo_fini_domain_pm_ops); + static int vga_switcheroo_runtime_resume_hdmi_audio(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 7cd42ea30d6d..d92c7d9b959a 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1743,6 +1743,7 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_ERGO_525V) }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_I405X) }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X) }, + { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2) }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X) }, { HID_USB_DEVICE(USB_VENDOR_ID_LABTEC, USB_DEVICE_ID_LABTEC_WIRELESS_KEYBOARD) }, { HID_USB_DEVICE(USB_VENDOR_ID_LCPOWER, USB_DEVICE_ID_LCPOWER_LC1000 ) }, diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 6e12cd0317f6..4850da34d3ef 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -292,6 +292,11 @@ #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_73F7 0x73f7 #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_A001 0xa001 +#define USB_VENDOR_ID_ELAN 0x04f3 +#define USB_DEVICE_ID_ELAN_TOUCHSCREEN 0x0089 +#define USB_DEVICE_ID_ELAN_TOUCHSCREEN_009B 0x009b +#define USB_DEVICE_ID_ELAN_TOUCHSCREEN_016F 0x016f + #define USB_VENDOR_ID_ELECOM 0x056e #define USB_DEVICE_ID_ELECOM_BM084 0x0061 @@ -506,6 +511,7 @@ #define USB_DEVICE_ID_KYE_GPEN_560 0x5003 #define USB_DEVICE_ID_KYE_EASYPEN_I405X 0x5010 #define USB_DEVICE_ID_KYE_MOUSEPEN_I608X 0x5011 +#define USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2 0x501a #define USB_DEVICE_ID_KYE_EASYPEN_M610X 0x5013 #define USB_VENDOR_ID_LABTEC 0x1020 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index a713e6211419..a413f76e84d4 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -312,6 +312,9 @@ static const struct hid_device_id hid_battery_quirks[] = { USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI), HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, + USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO), + HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_ANSI), HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE }, {} @@ -1063,6 +1066,23 @@ void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct return; } + /* + * Ignore reports for absolute data if the data didn't change. This is + * not only an optimization but also fixes 'dead' key reports. Some + * RollOver implementations for localized keys (like BACKSLASH/PIPE; HID + * 0x31 and 0x32) report multiple keys, even though a localized keyboard + * can only have one of them physically available. The 'dead' keys + * report constant 0. As all map to the same keycode, they'd confuse + * the input layer. If we filter the 'dead' keys on the HID level, we + * skip the keycode translation and only forward real events. + */ + if (!(field->flags & (HID_MAIN_ITEM_RELATIVE | + HID_MAIN_ITEM_BUFFERED_BYTE)) && + (field->flags & HID_MAIN_ITEM_VARIABLE) && + usage->usage_index < field->maxusage && + value == field->value[usage->usage_index]) + return; + /* report the usage code as scancode if the key status has changed */ if (usage->type == EV_KEY && !!test_bit(usage->code, input->key) != value) input_event(input, EV_MSC, MSC_SCAN, usage->hid); diff --git a/drivers/hid/hid-kye.c b/drivers/hid/hid-kye.c index b92bf01a1ae8..158fcf577fae 100644 --- a/drivers/hid/hid-kye.c +++ b/drivers/hid/hid-kye.c @@ -323,6 +323,7 @@ static __u8 *kye_report_fixup(struct hid_device *hdev, __u8 *rdesc, } break; case USB_DEVICE_ID_KYE_MOUSEPEN_I608X: + case USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2: if (*rsize == MOUSEPEN_I608X_RDESC_ORIG_SIZE) { rdesc = mousepen_i608x_rdesc_fixed; *rsize = sizeof(mousepen_i608x_rdesc_fixed); @@ -415,6 +416,7 @@ static int kye_probe(struct hid_device *hdev, const struct hid_device_id *id) switch (id->product) { case USB_DEVICE_ID_KYE_EASYPEN_I405X: case USB_DEVICE_ID_KYE_MOUSEPEN_I608X: + case USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2: case USB_DEVICE_ID_KYE_EASYPEN_M610X: ret = kye_tablet_enable(hdev); if (ret) { @@ -446,6 +448,8 @@ static const struct hid_device_id kye_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X) }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, + USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2) }, + { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X) }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_GENIUS_GILA_GAMING_MOUSE) }, diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index 0b14d3261531..5da115a6fd22 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -687,7 +687,6 @@ static int logi_dj_raw_event(struct hid_device *hdev, struct dj_receiver_dev *djrcv_dev = hid_get_drvdata(hdev); struct dj_report *dj_report = (struct dj_report *) data; unsigned long flags; - bool report_processed = false; dbg_hid("%s, size:%d\n", __func__, size); @@ -714,34 +713,42 @@ static int logi_dj_raw_event(struct hid_device *hdev, * device (via hid_input_report() ) and return 1 so hid-core does not do * anything else with it. */ + + /* case 1) */ + if (data[0] != REPORT_ID_DJ_SHORT) + return false; + if ((dj_report->device_index < DJ_DEVICE_INDEX_MIN) || (dj_report->device_index > DJ_DEVICE_INDEX_MAX)) { - dev_err(&hdev->dev, "%s: invalid device index:%d\n", + /* + * Device index is wrong, bail out. + * This driver can ignore safely the receiver notifications, + * so ignore those reports too. + */ + if (dj_report->device_index != DJ_RECEIVER_INDEX) + dev_err(&hdev->dev, "%s: invalid device index:%d\n", __func__, dj_report->device_index); return false; } spin_lock_irqsave(&djrcv_dev->lock, flags); - if (dj_report->report_id == REPORT_ID_DJ_SHORT) { - switch (dj_report->report_type) { - case REPORT_TYPE_NOTIF_DEVICE_PAIRED: - case REPORT_TYPE_NOTIF_DEVICE_UNPAIRED: - logi_dj_recv_queue_notification(djrcv_dev, dj_report); - break; - case REPORT_TYPE_NOTIF_CONNECTION_STATUS: - if (dj_report->report_params[CONNECTION_STATUS_PARAM_STATUS] == - STATUS_LINKLOSS) { - logi_dj_recv_forward_null_report(djrcv_dev, dj_report); - } - break; - default: - logi_dj_recv_forward_report(djrcv_dev, dj_report); + switch (dj_report->report_type) { + case REPORT_TYPE_NOTIF_DEVICE_PAIRED: + case REPORT_TYPE_NOTIF_DEVICE_UNPAIRED: + logi_dj_recv_queue_notification(djrcv_dev, dj_report); + break; + case REPORT_TYPE_NOTIF_CONNECTION_STATUS: + if (dj_report->report_params[CONNECTION_STATUS_PARAM_STATUS] == + STATUS_LINKLOSS) { + logi_dj_recv_forward_null_report(djrcv_dev, dj_report); } - report_processed = true; + break; + default: + logi_dj_recv_forward_report(djrcv_dev, dj_report); } spin_unlock_irqrestore(&djrcv_dev->lock, flags); - return report_processed; + return true; } static int logi_dj_probe(struct hid_device *hdev, diff --git a/drivers/hid/hid-logitech-dj.h b/drivers/hid/hid-logitech-dj.h index 4a4000340ce1..daeb0aa4bee9 100644 --- a/drivers/hid/hid-logitech-dj.h +++ b/drivers/hid/hid-logitech-dj.h @@ -27,6 +27,7 @@ #define DJ_MAX_PAIRED_DEVICES 6 #define DJ_MAX_NUMBER_NOTIFICATIONS 8 +#define DJ_RECEIVER_INDEX 0 #define DJ_DEVICE_INDEX_MIN 1 #define DJ_DEVICE_INDEX_MAX 6 diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c index 3b43d1cfa936..991ba79cfc72 100644 --- a/drivers/hid/hid-magicmouse.c +++ b/drivers/hid/hid-magicmouse.c @@ -290,6 +290,11 @@ static int magicmouse_raw_event(struct hid_device *hdev, if (size < 4 || ((size - 4) % 9) != 0) return 0; npoints = (size - 4) / 9; + if (npoints > 15) { + hid_warn(hdev, "invalid size value (%d) for TRACKPAD_REPORT_ID\n", + size); + return 0; + } msc->ntouches = 0; for (ii = 0; ii < npoints; ii++) magicmouse_emit_touch(msc, ii, data + ii * 9 + 4); @@ -307,6 +312,11 @@ static int magicmouse_raw_event(struct hid_device *hdev, if (size < 6 || ((size - 6) % 8) != 0) return 0; npoints = (size - 6) / 8; + if (npoints > 15) { + hid_warn(hdev, "invalid size value (%d) for MOUSE_REPORT_ID\n", + size); + return 0; + } msc->ntouches = 0; for (ii = 0; ii < npoints; ii++) magicmouse_emit_touch(msc, ii, data + ii * 8 + 6); diff --git a/drivers/hid/hid-picolcd_core.c b/drivers/hid/hid-picolcd_core.c index acbb021065ec..020df3c2e8b4 100644 --- a/drivers/hid/hid-picolcd_core.c +++ b/drivers/hid/hid-picolcd_core.c @@ -350,6 +350,12 @@ static int picolcd_raw_event(struct hid_device *hdev, if (!data) return 1; + if (size > 64) { + hid_warn(hdev, "invalid size value (%d) for picolcd raw event\n", + size); + return 0; + } + if (report->id == REPORT_KEY_STATE) { if (data->input_keys) ret = picolcd_raw_keypad(data, report, raw_data+1, size-1); diff --git a/drivers/hid/hid-roccat-pyra.c b/drivers/hid/hid-roccat-pyra.c index 1a07e07d99a0..47d7e74231e5 100644 --- a/drivers/hid/hid-roccat-pyra.c +++ b/drivers/hid/hid-roccat-pyra.c @@ -35,6 +35,8 @@ static struct class *pyra_class; static void profile_activated(struct pyra_device *pyra, unsigned int new_profile) { + if (new_profile >= ARRAY_SIZE(pyra->profile_settings)) + return; pyra->actual_profile = new_profile; pyra->actual_cpi = pyra->profile_settings[pyra->actual_profile].y_cpi; } @@ -257,9 +259,11 @@ static ssize_t pyra_sysfs_write_settings(struct file *fp, if (off != 0 || count != PYRA_SIZE_SETTINGS) return -EINVAL; - mutex_lock(&pyra->pyra_lock); - settings = (struct pyra_settings const *)buf; + if (settings->startup_profile >= ARRAY_SIZE(pyra->profile_settings)) + return -EINVAL; + + mutex_lock(&pyra->pyra_lock); retval = pyra_set_settings(usb_dev, settings); if (retval) { diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c index 42eebd14de1f..17be889d8a83 100644 --- a/drivers/hid/i2c-hid/i2c-hid.c +++ b/drivers/hid/i2c-hid/i2c-hid.c @@ -136,6 +136,7 @@ struct i2c_hid { * descriptor. */ unsigned int bufsize; /* i2c buffer size */ char *inbuf; /* Input buffer */ + char *rawbuf; /* Raw Input buffer */ char *cmdbuf; /* Command buffer */ char *argsbuf; /* Command arguments buffer */ @@ -357,6 +358,9 @@ static void i2c_hid_get_input(struct i2c_hid *ihid) int ret, ret_size; int size = le16_to_cpu(ihid->hdesc.wMaxInputLength); + if (size > ihid->bufsize) + size = ihid->bufsize; + ret = i2c_master_recv(ihid->client, ihid->inbuf, size); if (ret != size) { if (ret < 0) @@ -482,9 +486,11 @@ static void i2c_hid_find_max_report(struct hid_device *hid, unsigned int type, static void i2c_hid_free_buffers(struct i2c_hid *ihid) { kfree(ihid->inbuf); + kfree(ihid->rawbuf); kfree(ihid->argsbuf); kfree(ihid->cmdbuf); ihid->inbuf = NULL; + ihid->rawbuf = NULL; ihid->cmdbuf = NULL; ihid->argsbuf = NULL; ihid->bufsize = 0; @@ -500,10 +506,11 @@ static int i2c_hid_alloc_buffers(struct i2c_hid *ihid, size_t report_size) report_size; /* report */ ihid->inbuf = kzalloc(report_size, GFP_KERNEL); + ihid->rawbuf = kzalloc(report_size, GFP_KERNEL); ihid->argsbuf = kzalloc(args_len, GFP_KERNEL); ihid->cmdbuf = kzalloc(sizeof(union command) + args_len, GFP_KERNEL); - if (!ihid->inbuf || !ihid->argsbuf || !ihid->cmdbuf) { + if (!ihid->inbuf || !ihid->rawbuf || !ihid->argsbuf || !ihid->cmdbuf) { i2c_hid_free_buffers(ihid); return -ENOMEM; } @@ -530,12 +537,12 @@ static int i2c_hid_get_raw_report(struct hid_device *hid, ret = i2c_hid_get_report(client, report_type == HID_FEATURE_REPORT ? 0x03 : 0x01, - report_number, ihid->inbuf, ask_count); + report_number, ihid->rawbuf, ask_count); if (ret < 0) return ret; - ret_count = ihid->inbuf[0] | (ihid->inbuf[1] << 8); + ret_count = ihid->rawbuf[0] | (ihid->rawbuf[1] << 8); if (ret_count <= 2) return 0; @@ -544,7 +551,7 @@ static int i2c_hid_get_raw_report(struct hid_device *hid, /* The query buffer contains the size, dropping it in the reply */ count = min(count, ret_count - 2); - memcpy(buf, ihid->inbuf + 2, count); + memcpy(buf, ihid->rawbuf + 2, count); return count; } diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index 44df131d390a..617c47f9ebe6 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -82,7 +82,7 @@ static int hid_start_in(struct hid_device *hid) struct usbhid_device *usbhid = hid->driver_data; spin_lock_irqsave(&usbhid->lock, flags); - if (hid->open > 0 && + if ((hid->open > 0 || hid->quirks & HID_QUIRK_ALWAYS_POLL) && !test_bit(HID_DISCONNECTED, &usbhid->iofl) && !test_bit(HID_SUSPENDED, &usbhid->iofl) && !test_and_set_bit(HID_IN_RUNNING, &usbhid->iofl)) { @@ -292,6 +292,8 @@ static void hid_irq_in(struct urb *urb) case 0: /* success */ usbhid_mark_busy(usbhid); usbhid->retry_delay = 0; + if ((hid->quirks & HID_QUIRK_ALWAYS_POLL) && !hid->open) + break; hid_input_report(urb->context, HID_INPUT_REPORT, urb->transfer_buffer, urb->actual_length, 1); @@ -734,8 +736,10 @@ void usbhid_close(struct hid_device *hid) if (!--hid->open) { spin_unlock_irq(&usbhid->lock); hid_cancel_delayed_stuff(usbhid); - usb_kill_urb(usbhid->urbin); - usbhid->intf->needs_remote_wakeup = 0; + if (!(hid->quirks & HID_QUIRK_ALWAYS_POLL)) { + usb_kill_urb(usbhid->urbin); + usbhid->intf->needs_remote_wakeup = 0; + } } else { spin_unlock_irq(&usbhid->lock); } @@ -1119,6 +1123,19 @@ static int usbhid_start(struct hid_device *hid) set_bit(HID_STARTED, &usbhid->iofl); + if (hid->quirks & HID_QUIRK_ALWAYS_POLL) { + ret = usb_autopm_get_interface(usbhid->intf); + if (ret) + goto fail; + usbhid->intf->needs_remote_wakeup = 1; + ret = hid_start_in(hid); + if (ret) { + dev_err(&hid->dev, + "failed to start in urb: %d\n", ret); + } + usb_autopm_put_interface(usbhid->intf); + } + /* Some keyboards don't work until their LEDs have been set. * Since BIOSes do set the LEDs, it must be safe for any device * that supports the keyboard boot protocol. @@ -1151,6 +1168,9 @@ static void usbhid_stop(struct hid_device *hid) if (WARN_ON(!usbhid)) return; + if (hid->quirks & HID_QUIRK_ALWAYS_POLL) + usbhid->intf->needs_remote_wakeup = 0; + clear_bit(HID_STARTED, &usbhid->iofl); spin_lock_irq(&usbhid->lock); /* Sync with error and led handlers */ set_bit(HID_DISCONNECTED, &usbhid->iofl); diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c index 8e4ddb369883..473c0c43af52 100644 --- a/drivers/hid/usbhid/hid-quirks.c +++ b/drivers/hid/usbhid/hid-quirks.c @@ -69,6 +69,9 @@ 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_DMI, USB_DEVICE_ID_DMI_ENC, HID_QUIRK_NOGET }, + { USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN, HID_QUIRK_ALWAYS_POLL }, + { USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_009B, HID_QUIRK_ALWAYS_POLL }, + { USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_016F, HID_QUIRK_ALWAYS_POLL }, { USB_VENDOR_ID_ELO, USB_DEVICE_ID_ELO_TS2700, HID_QUIRK_NOGET }, { USB_VENDOR_ID_FORMOSA, USB_DEVICE_ID_FORMOSA_IR_RECEIVER, HID_QUIRK_NO_INIT_REPORTS }, { USB_VENDOR_ID_FREESCALE, USB_DEVICE_ID_FREESCALE_MX28, HID_QUIRK_NOGET }, @@ -113,6 +116,7 @@ static const struct hid_blacklist { { USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_WIRELESS, HID_QUIRK_MULTI_INPUT }, { USB_VENDOR_ID_SIGMA_MICRO, USB_DEVICE_ID_SIGMA_MICRO_KEYBOARD, HID_QUIRK_NO_INIT_REPORTS }, { USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X, HID_QUIRK_MULTI_INPUT }, + { USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2, HID_QUIRK_MULTI_INPUT }, { USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X, HID_QUIRK_MULTI_INPUT }, { USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_DUOSENSE, HID_QUIRK_NO_INIT_REPORTS }, { USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_LTS1, HID_QUIRK_NO_INIT_REPORTS }, diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index 69ea36f07b4d..e99e71a6ea59 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -164,8 +164,10 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size, ret = vmbus_post_msg(open_msg, sizeof(struct vmbus_channel_open_channel)); - if (ret != 0) + if (ret != 0) { + err = ret; goto error1; + } t = wait_for_completion_timeout(&open_info->waitevent, 5*HZ); if (t == 0) { @@ -362,7 +364,6 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer, u32 next_gpadl_handle; unsigned long flags; int ret = 0; - int t; next_gpadl_handle = atomic_read(&vmbus_connection.next_gpadl_handle); atomic_inc(&vmbus_connection.next_gpadl_handle); @@ -409,9 +410,7 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer, } } - t = wait_for_completion_timeout(&msginfo->waitevent, 5*HZ); - BUG_ON(t == 0); - + wait_for_completion(&msginfo->waitevent); /* At this point, we received the gpadl created msg */ *gpadl_handle = gpadlmsg->gpadl; @@ -434,7 +433,7 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle) struct vmbus_channel_gpadl_teardown *msg; struct vmbus_channel_msginfo *info; unsigned long flags; - int ret, t; + int ret; info = kmalloc(sizeof(*info) + sizeof(struct vmbus_channel_gpadl_teardown), GFP_KERNEL); @@ -456,11 +455,12 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle) ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_gpadl_teardown)); - BUG_ON(ret != 0); - t = wait_for_completion_timeout(&info->waitevent, 5*HZ); - BUG_ON(t == 0); + if (ret) + goto post_msg_err; + + wait_for_completion(&info->waitevent); - /* Received a torndown response */ +post_msg_err: spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags); list_del(&info->msglistentry); spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags); @@ -470,7 +470,7 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle) } EXPORT_SYMBOL_GPL(vmbus_teardown_gpadl); -static void vmbus_close_internal(struct vmbus_channel *channel) +static int vmbus_close_internal(struct vmbus_channel *channel) { struct vmbus_channel_close_channel *msg; int ret; @@ -492,11 +492,28 @@ static void vmbus_close_internal(struct vmbus_channel *channel) ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_close_channel)); - BUG_ON(ret != 0); + if (ret) { + pr_err("Close failed: close post msg return is %d\n", ret); + /* + * If we failed to post the close msg, + * it is perhaps better to leak memory. + */ + return ret; + } + /* Tear down the gpadl for the channel's ring buffer */ - if (channel->ringbuffer_gpadlhandle) - vmbus_teardown_gpadl(channel, - channel->ringbuffer_gpadlhandle); + if (channel->ringbuffer_gpadlhandle) { + ret = vmbus_teardown_gpadl(channel, + channel->ringbuffer_gpadlhandle); + if (ret) { + pr_err("Close failed: teardown gpadl return %d\n", ret); + /* + * If we failed to teardown gpadl, + * it is perhaps better to leak memory. + */ + return ret; + } + } /* Cleanup the ring buffers for this channel */ hv_ringbuffer_cleanup(&channel->outbound); @@ -505,7 +522,7 @@ static void vmbus_close_internal(struct vmbus_channel *channel) free_pages((unsigned long)channel->ringbuffer_pages, get_order(channel->ringbuffer_pagecount * PAGE_SIZE)); - + return ret; } /* diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index fa920469bf10..505fe29c75b0 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -202,9 +202,16 @@ static void vmbus_process_rescind_offer(struct work_struct *work) unsigned long flags; struct vmbus_channel *primary_channel; struct vmbus_channel_relid_released msg; + struct device *dev; + + if (channel->device_obj) { + dev = get_device(&channel->device_obj->device); + if (dev) { + vmbus_device_unregister(channel->device_obj); + put_device(dev); + } + } - if (channel->device_obj) - vmbus_device_unregister(channel->device_obj); memset(&msg, 0, sizeof(struct vmbus_channel_relid_released)); msg.child_relid = channel->offermsg.child_relid; msg.header.msgtype = CHANNELMSG_RELID_RELEASED; diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index ce5a9f2584f3..d8fd95cb0456 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -408,10 +408,21 @@ int vmbus_post_msg(void *buffer, size_t buflen) * insufficient resources. Retry the operation a couple of * times before giving up. */ - while (retries < 3) { - ret = hv_post_message(conn_id, 1, buffer, buflen); - if (ret != HV_STATUS_INSUFFICIENT_BUFFERS) + while (retries < 10) { + ret = hv_post_message(conn_id, 1, buffer, buflen); + + switch (ret) { + case HV_STATUS_INSUFFICIENT_BUFFERS: + ret = -ENOMEM; + case -ENOMEM: + break; + case HV_STATUS_SUCCESS: return ret; + default: + pr_err("hv_post_msg() failed; error code:%d\n", ret); + return -EINVAL; + } + retries++; msleep(100); } diff --git a/drivers/hwmon/ds1621.c b/drivers/hwmon/ds1621.c index fc6f5d54e7f7..8890870309e4 100644 --- a/drivers/hwmon/ds1621.c +++ b/drivers/hwmon/ds1621.c @@ -309,6 +309,7 @@ static ssize_t set_convrate(struct device *dev, struct device_attribute *da, data->conf |= (resol << DS1621_REG_CONFIG_RESOL_SHIFT); i2c_smbus_write_byte_data(client, DS1621_REG_CONF, data->conf); data->update_interval = ds1721_convrates[resol]; + data->zbits = 7 - resol; mutex_unlock(&data->update_lock); return count; diff --git a/drivers/i2c/busses/i2c-at91.c b/drivers/i2c/busses/i2c-at91.c index c56be739006b..8873d84e1d4f 100644 --- a/drivers/i2c/busses/i2c-at91.c +++ b/drivers/i2c/busses/i2c-at91.c @@ -101,6 +101,7 @@ struct at91_twi_dev { unsigned twi_cwgr_reg; struct at91_twi_pdata *pdata; bool use_dma; + bool recv_len_abort; struct at91_twi_dma dma; }; @@ -267,12 +268,24 @@ static void at91_twi_read_next_byte(struct at91_twi_dev *dev) *dev->buf = at91_twi_read(dev, AT91_TWI_RHR) & 0xff; --dev->buf_len; + /* return if aborting, we only needed to read RHR to clear RXRDY*/ + if (dev->recv_len_abort) + return; + /* handle I2C_SMBUS_BLOCK_DATA */ if (unlikely(dev->msg->flags & I2C_M_RECV_LEN)) { - dev->msg->flags &= ~I2C_M_RECV_LEN; - dev->buf_len += *dev->buf; - dev->msg->len = dev->buf_len + 1; - dev_dbg(dev->dev, "received block length %d\n", dev->buf_len); + /* ensure length byte is a valid value */ + if (*dev->buf <= I2C_SMBUS_BLOCK_MAX && *dev->buf > 0) { + dev->msg->flags &= ~I2C_M_RECV_LEN; + dev->buf_len += *dev->buf; + dev->msg->len = dev->buf_len + 1; + dev_dbg(dev->dev, "received block length %d\n", + dev->buf_len); + } else { + /* abort and send the stop by reading one more byte */ + dev->recv_len_abort = true; + dev->buf_len = 1; + } } /* send stop if second but last byte has been read */ @@ -421,8 +434,8 @@ static int at91_do_twi_transfer(struct at91_twi_dev *dev) } } - ret = wait_for_completion_interruptible_timeout(&dev->cmd_complete, - dev->adapter.timeout); + ret = wait_for_completion_timeout(&dev->cmd_complete, + dev->adapter.timeout); if (ret == 0) { dev_err(dev->dev, "controller timed out\n"); at91_init_twi_bus(dev); @@ -444,6 +457,12 @@ static int at91_do_twi_transfer(struct at91_twi_dev *dev) ret = -EIO; goto error; } + if (dev->recv_len_abort) { + dev_err(dev->dev, "invalid smbus block length recvd\n"); + ret = -EPROTO; + goto error; + } + dev_dbg(dev->dev, "transfer complete\n"); return 0; @@ -500,6 +519,7 @@ static int at91_twi_xfer(struct i2c_adapter *adap, struct i2c_msg *msg, int num) dev->buf_len = m_start->len; dev->buf = m_start->buf; dev->msg = m_start; + dev->recv_len_abort = false; ret = at91_do_twi_transfer(dev); diff --git a/drivers/i2c/busses/i2c-davinci.c b/drivers/i2c/busses/i2c-davinci.c index af0b5830303d..e3c6a96717fc 100644 --- a/drivers/i2c/busses/i2c-davinci.c +++ b/drivers/i2c/busses/i2c-davinci.c @@ -411,11 +411,9 @@ i2c_davinci_xfer_msg(struct i2c_adapter *adap, struct i2c_msg *msg, int stop) if (dev->cmd_err & DAVINCI_I2C_STR_NACK) { if (msg->flags & I2C_M_IGNORE_NAK) return msg->len; - if (stop) { - w = davinci_i2c_read_reg(dev, DAVINCI_I2C_MDR_REG); - w |= DAVINCI_I2C_MDR_STP; - davinci_i2c_write_reg(dev, DAVINCI_I2C_MDR_REG, w); - } + w = davinci_i2c_read_reg(dev, DAVINCI_I2C_MDR_REG); + w |= DAVINCI_I2C_MDR_STP; + davinci_i2c_write_reg(dev, DAVINCI_I2C_MDR_REG, w); return -EREMOTEIO; } return -EIO; diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c index 8ce4f517fc56..6e932d140573 100644 --- a/drivers/i2c/busses/i2c-ismt.c +++ b/drivers/i2c/busses/i2c-ismt.c @@ -497,7 +497,7 @@ static int ismt_access(struct i2c_adapter *adap, u16 addr, desc->wr_len_cmd = dma_size; desc->control |= ISMT_DESC_BLK; priv->dma_buffer[0] = command; - memcpy(&priv->dma_buffer[1], &data->block[1], dma_size); + memcpy(&priv->dma_buffer[1], &data->block[1], dma_size - 1); } else { /* Block Read */ dev_dbg(dev, "I2C_SMBUS_BLOCK_DATA: READ\n"); @@ -525,7 +525,7 @@ static int ismt_access(struct i2c_adapter *adap, u16 addr, desc->wr_len_cmd = dma_size; desc->control |= ISMT_DESC_I2C; priv->dma_buffer[0] = command; - memcpy(&priv->dma_buffer[1], &data->block[1], dma_size); + memcpy(&priv->dma_buffer[1], &data->block[1], dma_size - 1); } else { /* i2c Block Read */ dev_dbg(dev, "I2C_SMBUS_I2C_BLOCK_DATA: READ\n"); diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c index d52d84937ad3..cf891752cc73 100644 --- a/drivers/i2c/busses/i2c-mv64xxx.c +++ b/drivers/i2c/busses/i2c-mv64xxx.c @@ -748,8 +748,7 @@ mv64xxx_of_config(struct mv64xxx_i2c_data *drv_data, } tclk = clk_get_rate(drv_data->clk); - rc = of_property_read_u32(np, "clock-frequency", &bus_freq); - if (rc) + if (of_property_read_u32(np, "clock-frequency", &bus_freq)) bus_freq = 100000; /* 100kHz by default */ if (!mv64xxx_find_baud_factors(bus_freq, tclk, diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index 90dcc2eaac5f..a6860570391f 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -926,14 +926,12 @@ omap_i2c_isr_thread(int this_irq, void *dev_id) if (stat & OMAP_I2C_STAT_NACK) { err |= OMAP_I2C_STAT_NACK; omap_i2c_ack_stat(dev, OMAP_I2C_STAT_NACK); - break; } if (stat & OMAP_I2C_STAT_AL) { dev_err(dev->dev, "Arbitration lost\n"); err |= OMAP_I2C_STAT_AL; omap_i2c_ack_stat(dev, OMAP_I2C_STAT_AL); - break; } /* @@ -958,11 +956,13 @@ omap_i2c_isr_thread(int this_irq, void *dev_id) if (dev->fifo_size) num_bytes = dev->buf_len; - omap_i2c_receive_data(dev, num_bytes, true); - - if (dev->errata & I2C_OMAP_ERRATA_I207) + if (dev->errata & I2C_OMAP_ERRATA_I207) { i2c_omap_errata_i207(dev, stat); + num_bytes = (omap_i2c_read_reg(dev, + OMAP_I2C_BUFSTAT_REG) >> 8) & 0x3F; + } + omap_i2c_receive_data(dev, num_bytes, true); omap_i2c_ack_stat(dev, OMAP_I2C_STAT_RDR); continue; } diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c index 93ec37649346..79a211782766 100644 --- a/drivers/i2c/busses/i2c-s3c2410.c +++ b/drivers/i2c/busses/i2c-s3c2410.c @@ -753,14 +753,16 @@ static int s3c24xx_i2c_xfer(struct i2c_adapter *adap, int ret; pm_runtime_get_sync(&adap->dev); - clk_prepare_enable(i2c->clk); + ret = clk_enable(i2c->clk); + if (ret) + return ret; for (retry = 0; retry < adap->retries; retry++) { ret = s3c24xx_i2c_doxfer(i2c, msgs, num); if (ret != -EAGAIN) { - clk_disable_unprepare(i2c->clk); + clk_disable(i2c->clk); pm_runtime_put(&adap->dev); return ret; } @@ -770,7 +772,7 @@ static int s3c24xx_i2c_xfer(struct i2c_adapter *adap, udelay(100); } - clk_disable_unprepare(i2c->clk); + clk_disable(i2c->clk); pm_runtime_put(&adap->dev); return -EREMOTEIO; } @@ -1153,7 +1155,7 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev) clk_prepare_enable(i2c->clk); ret = s3c24xx_i2c_init(i2c); - clk_disable_unprepare(i2c->clk); + clk_disable(i2c->clk); if (ret != 0) { dev_err(&pdev->dev, "I2C controller init failed\n"); return ret; @@ -1166,6 +1168,7 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev) i2c->irq = ret = platform_get_irq(pdev, 0); if (ret <= 0) { dev_err(&pdev->dev, "cannot find IRQ\n"); + clk_unprepare(i2c->clk); return ret; } @@ -1174,6 +1177,7 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev) if (ret != 0) { dev_err(&pdev->dev, "cannot claim IRQ %d\n", i2c->irq); + clk_unprepare(i2c->clk); return ret; } } @@ -1181,6 +1185,7 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev) ret = s3c24xx_i2c_register_cpufreq(i2c); if (ret < 0) { dev_err(&pdev->dev, "failed to register cpufreq notifier\n"); + clk_unprepare(i2c->clk); return ret; } @@ -1197,6 +1202,7 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev) if (ret < 0) { dev_err(&pdev->dev, "failed to add bus to i2c core\n"); s3c24xx_i2c_deregister_cpufreq(i2c); + clk_unprepare(i2c->clk); return ret; } @@ -1218,6 +1224,8 @@ static int s3c24xx_i2c_remove(struct platform_device *pdev) { struct s3c24xx_i2c *i2c = platform_get_drvdata(pdev); + clk_unprepare(i2c->clk); + pm_runtime_disable(&i2c->adap.dev); pm_runtime_disable(&pdev->dev); @@ -1246,10 +1254,13 @@ static int s3c24xx_i2c_resume(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); struct s3c24xx_i2c *i2c = platform_get_drvdata(pdev); + int ret; - clk_prepare_enable(i2c->clk); + ret = clk_enable(i2c->clk); + if (ret) + return ret; s3c24xx_i2c_init(i2c); - clk_disable_unprepare(i2c->clk); + clk_disable(i2c->clk); i2c->suspended = 0; return 0; diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c index 5fb80b8962a2..435403c85b1b 100644 --- a/drivers/i2c/i2c-core.c +++ b/drivers/i2c/i2c-core.c @@ -49,6 +49,7 @@ #include <linux/pm_runtime.h> #include <linux/acpi.h> #include <asm/uaccess.h> +#include <linux/err.h> #include "i2c-core.h" @@ -722,6 +723,10 @@ EXPORT_SYMBOL_GPL(i2c_new_device); */ void i2c_unregister_device(struct i2c_client *client) { +#if IS_ENABLED(CONFIG_OF_DYNAMIC) + if (client->dev.of_node) + of_node_clear_flag(client->dev.of_node, OF_POPULATED); +#endif device_unregister(&client->dev); } EXPORT_SYMBOL_GPL(i2c_unregister_device); @@ -982,62 +987,71 @@ static void i2c_scan_static_board_info(struct i2c_adapter *adapter) /* OF support code */ #if IS_ENABLED(CONFIG_OF) -static void of_i2c_register_devices(struct i2c_adapter *adap) +static struct i2c_client *of_i2c_register_device(struct i2c_adapter *adap, + struct device_node *node) { - void *result; - struct device_node *node; + struct i2c_client *result; + struct i2c_board_info info = {}; + struct dev_archdata dev_ad = {}; + const __be32 *addr; + int len; - /* Only register child devices if the adapter has a node pointer set */ - if (!adap->dev.of_node) - return; + dev_dbg(&adap->dev, "of_i2c: register %s\n", node->full_name); - dev_dbg(&adap->dev, "of_i2c: walking child nodes\n"); + if (of_modalias_node(node, info.type, sizeof(info.type)) < 0) { + dev_err(&adap->dev, "of_i2c: modalias failure on %s\n", + node->full_name); + return ERR_PTR(-EINVAL); + } - for_each_available_child_of_node(adap->dev.of_node, node) { - struct i2c_board_info info = {}; - struct dev_archdata dev_ad = {}; - const __be32 *addr; - int len; + addr = of_get_property(node, "reg", &len); + if (!addr || (len < sizeof(int))) { + dev_err(&adap->dev, "of_i2c: invalid reg on %s\n", + node->full_name); + return ERR_PTR(-EINVAL); + } - dev_dbg(&adap->dev, "of_i2c: register %s\n", node->full_name); + info.addr = be32_to_cpup(addr); + if (info.addr > (1 << 10) - 1) { + dev_err(&adap->dev, "of_i2c: invalid addr=%x on %s\n", + info.addr, node->full_name); + return ERR_PTR(-EINVAL); + } - if (of_modalias_node(node, info.type, sizeof(info.type)) < 0) { - dev_err(&adap->dev, "of_i2c: modalias failure on %s\n", - node->full_name); - continue; - } + info.irq = irq_of_parse_and_map(node, 0); + info.of_node = of_node_get(node); + info.archdata = &dev_ad; - addr = of_get_property(node, "reg", &len); - if (!addr || (len < sizeof(int))) { - dev_err(&adap->dev, "of_i2c: invalid reg on %s\n", - node->full_name); - continue; - } + if (of_get_property(node, "wakeup-source", NULL)) + info.flags |= I2C_CLIENT_WAKE; - info.addr = be32_to_cpup(addr); - if (info.addr > (1 << 10) - 1) { - dev_err(&adap->dev, "of_i2c: invalid addr=%x on %s\n", - info.addr, node->full_name); - continue; - } + request_module("%s%s", I2C_MODULE_PREFIX, info.type); - info.irq = irq_of_parse_and_map(node, 0); - info.of_node = of_node_get(node); - info.archdata = &dev_ad; + result = i2c_new_device(adap, &info); + if (result == NULL) { + dev_err(&adap->dev, "of_i2c: Failure registering %s\n", + node->full_name); + of_node_put(node); + irq_dispose_mapping(info.irq); + return ERR_PTR(-EINVAL); + } + return result; +} - if (of_get_property(node, "wakeup-source", NULL)) - info.flags |= I2C_CLIENT_WAKE; +static void of_i2c_register_devices(struct i2c_adapter *adap) +{ + struct device_node *node; + + /* Only register child devices if the adapter has a node pointer set */ + if (!adap->dev.of_node) + return; - request_module("%s%s", I2C_MODULE_PREFIX, info.type); + dev_dbg(&adap->dev, "of_i2c: walking child nodes\n"); - result = i2c_new_device(adap, &info); - if (result == NULL) { - dev_err(&adap->dev, "of_i2c: Failure registering %s\n", - node->full_name); - of_node_put(node); - irq_dispose_mapping(info.irq); + for_each_available_child_of_node(adap->dev.of_node, node) { + if (of_node_test_and_set_flag(node, OF_POPULATED)) continue; - } + of_i2c_register_device(adap, node); } } @@ -1651,6 +1665,61 @@ void i2c_clients_command(struct i2c_adapter *adap, unsigned int cmd, void *arg) } EXPORT_SYMBOL(i2c_clients_command); +#if IS_ENABLED(CONFIG_OF_DYNAMIC) +static int of_i2c_notify(struct notifier_block *nb, unsigned long action, + void *arg) +{ + struct of_reconfig_data *rd = arg; + struct i2c_adapter *adap; + struct i2c_client *client; + + switch (of_reconfig_get_state_change(action, rd)) { + case OF_RECONFIG_CHANGE_ADD: + adap = of_find_i2c_adapter_by_node(rd->dn->parent); + if (adap == NULL) + return NOTIFY_OK; /* not for us */ + + if (of_node_test_and_set_flag(rd->dn, OF_POPULATED)) { + put_device(&adap->dev); + return NOTIFY_OK; + } + + client = of_i2c_register_device(adap, rd->dn); + put_device(&adap->dev); + + if (IS_ERR(client)) { + pr_err("%s: failed to create for '%s'\n", + __func__, rd->dn->full_name); + return notifier_from_errno(PTR_ERR(client)); + } + break; + case OF_RECONFIG_CHANGE_REMOVE: + /* already depopulated? */ + if (!of_node_check_flag(rd->dn, OF_POPULATED)) + return NOTIFY_OK; + + /* find our device by node */ + client = of_find_i2c_device_by_node(rd->dn); + if (client == NULL) + return NOTIFY_OK; /* no? not meant for us */ + + /* unregister takes one ref away */ + i2c_unregister_device(client); + + /* and put the reference of the find */ + put_device(&client->dev); + break; + } + + return NOTIFY_OK; +} +static struct notifier_block i2c_of_notifier = { + .notifier_call = of_i2c_notify, +}; +#else +extern struct notifier_block i2c_of_notifier; +#endif /* CONFIG_OF_DYNAMIC */ + static int __init i2c_init(void) { int retval; @@ -1668,6 +1737,10 @@ static int __init i2c_init(void) retval = i2c_add_driver(&dummy_driver); if (retval) goto class_err; + + if (IS_ENABLED(CONFIG_OF_DYNAMIC)) + WARN_ON(of_reconfig_notifier_register(&i2c_of_notifier)); + return 0; class_err: @@ -1681,6 +1754,8 @@ bus_err: static void __exit i2c_exit(void) { + if (IS_ENABLED(CONFIG_OF_DYNAMIC)) + WARN_ON(of_reconfig_notifier_unregister(&i2c_of_notifier)); i2c_del_driver(&dummy_driver); #ifdef CONFIG_I2C_COMPAT class_compat_unregister(i2c_adapter_compat_class); diff --git a/drivers/iio/accel/bma180.c b/drivers/iio/accel/bma180.c index fe83d04784c8..6f039c300141 100644 --- a/drivers/iio/accel/bma180.c +++ b/drivers/iio/accel/bma180.c @@ -571,7 +571,7 @@ static int bma180_probe(struct i2c_client *client, trig->ops = &bma180_trigger_ops; iio_trigger_set_drvdata(trig, indio_dev); data->trig = trig; - indio_dev->trig = trig; + indio_dev->trig = iio_trigger_get(trig); ret = iio_trigger_register(trig); if (ret) diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c index 9a4e0e32a771..eb799a43aef0 100644 --- a/drivers/iio/adc/ad_sigma_delta.c +++ b/drivers/iio/adc/ad_sigma_delta.c @@ -472,7 +472,7 @@ static int ad_sd_probe_trigger(struct iio_dev *indio_dev) goto error_free_irq; /* select default trigger */ - indio_dev->trig = sigma_delta->trig; + indio_dev->trig = iio_trigger_get(sigma_delta->trig); return 0; diff --git a/drivers/iio/adc/mcp3422.c b/drivers/iio/adc/mcp3422.c index 47dcb34ff44c..3a615f3b5d80 100644 --- a/drivers/iio/adc/mcp3422.c +++ b/drivers/iio/adc/mcp3422.c @@ -57,20 +57,11 @@ .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SAMP_FREQ), \ } -/* LSB is in nV to eliminate floating point */ -static const u32 rates_to_lsb[] = {1000000, 250000, 62500, 15625}; - -/* - * scales calculated as: - * rates_to_lsb[sample_rate] / (1 << pga); - * pga is 1 for 0, 2 - */ - static const int mcp3422_scales[4][4] = { - { 1000000, 250000, 62500, 15625 }, - { 500000 , 125000, 31250, 7812 }, - { 250000 , 62500 , 15625, 3906 }, - { 125000 , 31250 , 7812 , 1953 } }; + { 1000000, 500000, 250000, 125000 }, + { 250000 , 125000, 62500 , 31250 }, + { 62500 , 31250 , 15625 , 7812 }, + { 15625 , 7812 , 3906 , 1953 } }; /* Constant msleep times for data acquisitions */ static const int mcp3422_read_times[4] = { diff --git a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c index 7dcf83998e6f..1be235b01934 100644 --- a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c +++ b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c @@ -99,7 +99,8 @@ int hid_sensor_setup_trigger(struct iio_dev *indio_dev, const char *name, dev_err(&indio_dev->dev, "Trigger Register Failed\n"); goto error_free_trig; } - indio_dev->trig = attrb->trigger = trig; + attrb->trigger = trig; + indio_dev->trig = iio_trigger_get(trig); return ret; diff --git a/drivers/iio/common/st_sensors/st_sensors_buffer.c b/drivers/iio/common/st_sensors/st_sensors_buffer.c index 1665c8e4b62b..e18bc6782256 100644 --- a/drivers/iio/common/st_sensors/st_sensors_buffer.c +++ b/drivers/iio/common/st_sensors/st_sensors_buffer.c @@ -71,7 +71,7 @@ int st_sensors_get_buffer_element(struct iio_dev *indio_dev, u8 *buf) goto st_sensors_free_memory; } - for (i = 0; i < n * num_data_channels; i++) { + for (i = 0; i < n * byte_for_channel; i++) { if (i < n) buf[i] = rx_array[i]; else diff --git a/drivers/iio/common/st_sensors/st_sensors_trigger.c b/drivers/iio/common/st_sensors/st_sensors_trigger.c index 8fc3a97eb266..8d8ca6f1e16a 100644 --- a/drivers/iio/common/st_sensors/st_sensors_trigger.c +++ b/drivers/iio/common/st_sensors/st_sensors_trigger.c @@ -49,7 +49,7 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, dev_err(&indio_dev->dev, "failed to register iio trigger.\n"); goto iio_trigger_register_error; } - indio_dev->trig = sdata->trig; + indio_dev->trig = iio_trigger_get(sdata->trig); return 0; diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c index 17aca4d9bd06..861ba3d60163 100644 --- a/drivers/iio/dac/ad5686.c +++ b/drivers/iio/dac/ad5686.c @@ -322,7 +322,7 @@ static int ad5686_probe(struct spi_device *spi) st = iio_priv(indio_dev); spi_set_drvdata(spi, indio_dev); - st->reg = devm_regulator_get(&spi->dev, "vcc"); + st->reg = devm_regulator_get_optional(&spi->dev, "vcc"); if (!IS_ERR(st->reg)) { ret = regulator_enable(st->reg); if (ret) diff --git a/drivers/iio/gyro/itg3200_buffer.c b/drivers/iio/gyro/itg3200_buffer.c index e3b3c5084070..eef50e91f17c 100644 --- a/drivers/iio/gyro/itg3200_buffer.c +++ b/drivers/iio/gyro/itg3200_buffer.c @@ -132,7 +132,7 @@ int itg3200_probe_trigger(struct iio_dev *indio_dev) goto error_free_irq; /* select default trigger */ - indio_dev->trig = st->trig; + indio_dev->trig = iio_trigger_get(st->trig); return 0; diff --git a/drivers/iio/imu/adis16400_core.c b/drivers/iio/imu/adis16400_core.c index 7c582f7ae34e..70753bf23a86 100644 --- a/drivers/iio/imu/adis16400_core.c +++ b/drivers/iio/imu/adis16400_core.c @@ -26,6 +26,7 @@ #include <linux/list.h> #include <linux/module.h> #include <linux/debugfs.h> +#include <linux/bitops.h> #include <linux/iio/iio.h> #include <linux/iio/sysfs.h> @@ -447,7 +448,7 @@ static int adis16400_read_raw(struct iio_dev *indio_dev, mutex_unlock(&indio_dev->mlock); if (ret) return ret; - val16 = ((val16 & 0xFFF) << 4) >> 4; + val16 = sign_extend32(val16, 11); *val = val16; return IIO_VAL_INT; case IIO_CHAN_INFO_OFFSET: diff --git a/drivers/iio/imu/adis_trigger.c b/drivers/iio/imu/adis_trigger.c index e0017c22bb9c..f53e9a803a0e 100644 --- a/drivers/iio/imu/adis_trigger.c +++ b/drivers/iio/imu/adis_trigger.c @@ -60,7 +60,7 @@ int adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev) iio_trigger_set_drvdata(adis->trig, adis); ret = iio_trigger_register(adis->trig); - indio_dev->trig = adis->trig; + indio_dev->trig = iio_trigger_get(adis->trig); if (ret) goto error_free_irq; diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c index 429517117eff..30fce6723e61 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c @@ -25,6 +25,16 @@ #include <linux/poll.h> #include "inv_mpu_iio.h" +static void inv_clear_kfifo(struct inv_mpu6050_state *st) +{ + unsigned long flags; + + /* take the spin lock sem to avoid interrupt kick in */ + spin_lock_irqsave(&st->time_stamp_lock, flags); + kfifo_reset(&st->timestamps); + spin_unlock_irqrestore(&st->time_stamp_lock, flags); +} + int inv_reset_fifo(struct iio_dev *indio_dev) { int result; @@ -51,6 +61,10 @@ int inv_reset_fifo(struct iio_dev *indio_dev) INV_MPU6050_BIT_FIFO_RST); if (result) goto reset_fifo_fail; + + /* clear timestamps fifo */ + inv_clear_kfifo(st); + /* enable interrupt */ if (st->chip_config.accl_fifo_enable || st->chip_config.gyro_fifo_enable) { @@ -84,16 +98,6 @@ reset_fifo_fail: return result; } -static void inv_clear_kfifo(struct inv_mpu6050_state *st) -{ - unsigned long flags; - - /* take the spin lock sem to avoid interrupt kick in */ - spin_lock_irqsave(&st->time_stamp_lock, flags); - kfifo_reset(&st->timestamps); - spin_unlock_irqrestore(&st->time_stamp_lock, flags); -} - /** * inv_mpu6050_irq_handler() - Cache a timestamp at each data ready interrupt. */ @@ -185,7 +189,6 @@ end_session: flush_fifo: /* Flush HW and SW FIFOs. */ inv_reset_fifo(indio_dev); - inv_clear_kfifo(st); mutex_unlock(&indio_dev->mlock); iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c index 03b9372c1212..926fccea8de0 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c @@ -135,7 +135,7 @@ int inv_mpu6050_probe_trigger(struct iio_dev *indio_dev) ret = iio_trigger_register(st->trig); if (ret) goto error_free_irq; - indio_dev->trig = st->trig; + indio_dev->trig = iio_trigger_get(st->trig); return 0; diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c index 1e8e94d4db7d..4fc88e617acf 100644 --- a/drivers/iio/inkern.c +++ b/drivers/iio/inkern.c @@ -178,7 +178,7 @@ static struct iio_channel *of_iio_channel_get_by_name(struct device_node *np, index = of_property_match_string(np, "io-channel-names", name); chan = of_iio_channel_get(np, index); - if (!IS_ERR(chan)) + if (!IS_ERR(chan) || PTR_ERR(chan) == -EPROBE_DEFER) break; else if (name && index >= 0) { pr_err("ERROR: could not get IIO channel %s:%s(%i)\n", diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c index 52bbcfa1e077..476aa132a192 100644 --- a/drivers/iio/magnetometer/st_magn_core.c +++ b/drivers/iio/magnetometer/st_magn_core.c @@ -42,7 +42,8 @@ #define ST_MAGN_FS_AVL_5600MG 5600 #define ST_MAGN_FS_AVL_8000MG 8000 #define ST_MAGN_FS_AVL_8100MG 8100 -#define ST_MAGN_FS_AVL_10000MG 10000 +#define ST_MAGN_FS_AVL_12000MG 12000 +#define ST_MAGN_FS_AVL_16000MG 16000 /* CUSTOM VALUES FOR SENSOR 1 */ #define ST_MAGN_1_WAI_EXP 0x3c @@ -69,20 +70,20 @@ #define ST_MAGN_1_FS_AVL_4700_VAL 0x05 #define ST_MAGN_1_FS_AVL_5600_VAL 0x06 #define ST_MAGN_1_FS_AVL_8100_VAL 0x07 -#define ST_MAGN_1_FS_AVL_1300_GAIN_XY 1100 -#define ST_MAGN_1_FS_AVL_1900_GAIN_XY 855 -#define ST_MAGN_1_FS_AVL_2500_GAIN_XY 670 -#define ST_MAGN_1_FS_AVL_4000_GAIN_XY 450 -#define ST_MAGN_1_FS_AVL_4700_GAIN_XY 400 -#define ST_MAGN_1_FS_AVL_5600_GAIN_XY 330 -#define ST_MAGN_1_FS_AVL_8100_GAIN_XY 230 -#define ST_MAGN_1_FS_AVL_1300_GAIN_Z 980 -#define ST_MAGN_1_FS_AVL_1900_GAIN_Z 760 -#define ST_MAGN_1_FS_AVL_2500_GAIN_Z 600 -#define ST_MAGN_1_FS_AVL_4000_GAIN_Z 400 -#define ST_MAGN_1_FS_AVL_4700_GAIN_Z 355 -#define ST_MAGN_1_FS_AVL_5600_GAIN_Z 295 -#define ST_MAGN_1_FS_AVL_8100_GAIN_Z 205 +#define ST_MAGN_1_FS_AVL_1300_GAIN_XY 909 +#define ST_MAGN_1_FS_AVL_1900_GAIN_XY 1169 +#define ST_MAGN_1_FS_AVL_2500_GAIN_XY 1492 +#define ST_MAGN_1_FS_AVL_4000_GAIN_XY 2222 +#define ST_MAGN_1_FS_AVL_4700_GAIN_XY 2500 +#define ST_MAGN_1_FS_AVL_5600_GAIN_XY 3030 +#define ST_MAGN_1_FS_AVL_8100_GAIN_XY 4347 +#define ST_MAGN_1_FS_AVL_1300_GAIN_Z 1020 +#define ST_MAGN_1_FS_AVL_1900_GAIN_Z 1315 +#define ST_MAGN_1_FS_AVL_2500_GAIN_Z 1666 +#define ST_MAGN_1_FS_AVL_4000_GAIN_Z 2500 +#define ST_MAGN_1_FS_AVL_4700_GAIN_Z 2816 +#define ST_MAGN_1_FS_AVL_5600_GAIN_Z 3389 +#define ST_MAGN_1_FS_AVL_8100_GAIN_Z 4878 #define ST_MAGN_1_MULTIREAD_BIT false /* CUSTOM VALUES FOR SENSOR 2 */ @@ -105,10 +106,12 @@ #define ST_MAGN_2_FS_MASK 0x60 #define ST_MAGN_2_FS_AVL_4000_VAL 0x00 #define ST_MAGN_2_FS_AVL_8000_VAL 0x01 -#define ST_MAGN_2_FS_AVL_10000_VAL 0x02 -#define ST_MAGN_2_FS_AVL_4000_GAIN 430 -#define ST_MAGN_2_FS_AVL_8000_GAIN 230 -#define ST_MAGN_2_FS_AVL_10000_GAIN 230 +#define ST_MAGN_2_FS_AVL_12000_VAL 0x02 +#define ST_MAGN_2_FS_AVL_16000_VAL 0x03 +#define ST_MAGN_2_FS_AVL_4000_GAIN 146 +#define ST_MAGN_2_FS_AVL_8000_GAIN 292 +#define ST_MAGN_2_FS_AVL_12000_GAIN 438 +#define ST_MAGN_2_FS_AVL_16000_GAIN 584 #define ST_MAGN_2_MULTIREAD_BIT false #define ST_MAGN_2_OUT_X_L_ADDR 0x28 #define ST_MAGN_2_OUT_Y_L_ADDR 0x2a @@ -266,9 +269,14 @@ static const struct st_sensors st_magn_sensors[] = { .gain = ST_MAGN_2_FS_AVL_8000_GAIN, }, [2] = { - .num = ST_MAGN_FS_AVL_10000MG, - .value = ST_MAGN_2_FS_AVL_10000_VAL, - .gain = ST_MAGN_2_FS_AVL_10000_GAIN, + .num = ST_MAGN_FS_AVL_12000MG, + .value = ST_MAGN_2_FS_AVL_12000_VAL, + .gain = ST_MAGN_2_FS_AVL_12000_GAIN, + }, + [3] = { + .num = ST_MAGN_FS_AVL_16000MG, + .value = ST_MAGN_2_FS_AVL_16000_VAL, + .gain = ST_MAGN_2_FS_AVL_16000_GAIN, }, }, }, diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index 56a4b7ca7ee3..45d67e9228d7 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -1124,6 +1124,9 @@ static int ucma_set_ib_path(struct ucma_context *ctx, if (!optlen) return -EINVAL; + memset(&sa_path, 0, sizeof(sa_path)); + sa_path.vlan_id = 0xffff; + ib_sa_unpack_path(path_data->path_rec, &sa_path); ret = rdma_set_ib_paths(ctx->cm_id, &sa_path, 1); if (ret) diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index a84112322071..055ebebc07dd 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -94,6 +94,14 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, if (dmasync) dma_set_attr(DMA_ATTR_WRITE_BARRIER, &attrs); + /* + * If the combination of the addr and size requested for this memory + * region causes an integer overflow, return error. + */ + if ((PAGE_ALIGN(addr + size) <= size) || + (PAGE_ALIGN(addr + size) <= addr)) + return ERR_PTR(-EINVAL); + if (!can_do_mlock()) return ERR_PTR(-EPERM); diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index ea6203ee7bcc..2adc14372b94 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -1964,20 +1964,21 @@ ssize_t ib_uverbs_modify_qp(struct ib_uverbs_file *file, if (qp->real_qp == qp) { ret = ib_resolve_eth_l2_attrs(qp, attr, &cmd.attr_mask); if (ret) - goto out; + goto release_qp; ret = qp->device->modify_qp(qp, attr, modify_qp_mask(qp->qp_type, cmd.attr_mask), &udata); } else { ret = ib_modify_qp(qp, attr, modify_qp_mask(qp->qp_type, cmd.attr_mask)); } - put_qp_read(qp); - if (ret) - goto out; + goto release_qp; ret = in_len; +release_qp: + put_qp_read(qp); + out: kfree(attr); @@ -2425,6 +2426,8 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file, attr.grh.sgid_index = cmd.attr.grh.sgid_index; attr.grh.hop_limit = cmd.attr.grh.hop_limit; attr.grh.traffic_class = cmd.attr.grh.traffic_class; + attr.vlan_id = 0; + memset(&attr.dmac, 0, sizeof(attr.dmac)); memcpy(attr.grh.dgid.raw, cmd.attr.grh.dgid, 16); ah = ib_create_ah(pd, &attr); diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 08219fb3338b..7a515c867674 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -476,6 +476,7 @@ static void ib_uverbs_async_handler(struct ib_uverbs_file *file, entry->desc.async.element = element; entry->desc.async.event_type = event; + entry->desc.async.reserved = 0; entry->counter = counter; list_add_tail(&entry->list, &file->async_file->event_list); diff --git a/drivers/infiniband/core/uverbs_marshall.c b/drivers/infiniband/core/uverbs_marshall.c index e7bee46868d1..abd97247443e 100644 --- a/drivers/infiniband/core/uverbs_marshall.c +++ b/drivers/infiniband/core/uverbs_marshall.c @@ -140,5 +140,9 @@ void ib_copy_path_rec_from_user(struct ib_sa_path_rec *dst, dst->packet_life_time = src->packet_life_time; dst->preference = src->preference; dst->packet_life_time_selector = src->packet_life_time_selector; + + memset(dst->smac, 0, sizeof(dst->smac)); + memset(dst->dmac, 0, sizeof(dst->dmac)); + dst->vlan_id = 0xffff; } EXPORT_SYMBOL(ib_copy_path_rec_from_user); diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index f2a3f48107e7..2592ab5f21b1 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -64,6 +64,14 @@ enum { #define GUID_TBL_BLK_NUM_ENTRIES 8 #define GUID_TBL_BLK_SIZE (GUID_TBL_ENTRY_SIZE * GUID_TBL_BLK_NUM_ENTRIES) +/* Counters should be saturate once they reach their maximum value */ +#define ASSIGN_32BIT_COUNTER(counter, value) do {\ + if ((value) > U32_MAX) \ + counter = cpu_to_be32(U32_MAX); \ + else \ + counter = cpu_to_be32(value); \ +} while (0) + struct mlx4_mad_rcv_buf { struct ib_grh grh; u8 payload[256]; @@ -730,10 +738,14 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, static void edit_counter(struct mlx4_counter *cnt, struct ib_pma_portcounters *pma_cnt) { - pma_cnt->port_xmit_data = cpu_to_be32((be64_to_cpu(cnt->tx_bytes)>>2)); - pma_cnt->port_rcv_data = cpu_to_be32((be64_to_cpu(cnt->rx_bytes)>>2)); - pma_cnt->port_xmit_packets = cpu_to_be32(be64_to_cpu(cnt->tx_frames)); - pma_cnt->port_rcv_packets = cpu_to_be32(be64_to_cpu(cnt->rx_frames)); + ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_data, + (be64_to_cpu(cnt->tx_bytes) >> 2)); + ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_data, + (be64_to_cpu(cnt->rx_bytes) >> 2)); + ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_packets, + be64_to_cpu(cnt->tx_frames)); + ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_packets, + be64_to_cpu(cnt->rx_frames)); } static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index f9c12e92fdd6..1a3d924744cc 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -1161,8 +1161,7 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) struct mlx4_ib_qp *mqp = to_mqp(ibqp); u64 reg_id; struct mlx4_ib_steering *ib_steering = NULL; - enum mlx4_protocol prot = (gid->raw[1] == 0x0e) ? - MLX4_PROT_IB_IPV4 : MLX4_PROT_IB_IPV6; + enum mlx4_protocol prot = MLX4_PROT_IB_IPV6; if (mdev->dev->caps.steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED) { @@ -1175,8 +1174,10 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) !!(mqp->flags & MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK), prot, ®_id); - if (err) + if (err) { + pr_err("multicast attach op failed, err %d\n", err); goto err_malloc; + } err = add_gid_entry(ibqp, gid); if (err) @@ -1224,8 +1225,7 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) struct net_device *ndev; struct mlx4_ib_gid_entry *ge; u64 reg_id = 0; - enum mlx4_protocol prot = (gid->raw[1] == 0x0e) ? - MLX4_PROT_IB_IPV4 : MLX4_PROT_IB_IPV6; + enum mlx4_protocol prot = MLX4_PROT_IB_IPV6; if (mdev->dev->caps.steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED) { @@ -1622,6 +1622,7 @@ static void mlx4_ib_get_dev_addr(struct net_device *dev, struct inet6_dev *in6_dev; union ib_gid *pgid; struct inet6_ifaddr *ifp; + union ib_gid default_gid; #endif union ib_gid gid; @@ -1642,12 +1643,15 @@ static void mlx4_ib_get_dev_addr(struct net_device *dev, in_dev_put(in_dev); } #if IS_ENABLED(CONFIG_IPV6) + mlx4_make_default_gid(dev, &default_gid); /* IPv6 gids */ in6_dev = in6_dev_get(dev); if (in6_dev) { read_lock_bh(&in6_dev->lock); list_for_each_entry(ifp, &in6_dev->addr_list, if_list) { pgid = (union ib_gid *)&ifp->addr; + if (!memcmp(pgid, &default_gid, sizeof(*pgid))) + continue; update_gid_table(ibdev, port, pgid, 0, 0); } read_unlock_bh(&in6_dev->lock); @@ -1723,31 +1727,34 @@ static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev) port_state = (netif_running(curr_netdev) && netif_carrier_ok(curr_netdev)) ? IB_PORT_ACTIVE : IB_PORT_DOWN; mlx4_ib_set_default_gid(ibdev, curr_netdev, port); - } else { - reset_gid_table(ibdev, port); - } - /* if using bonding/team and a slave port is down, we don't the bond IP - * based gids in the table since flows that select port by gid may get - * the down port. - */ - if (curr_master && (port_state == IB_PORT_DOWN)) { - reset_gid_table(ibdev, port); - mlx4_ib_set_default_gid(ibdev, curr_netdev, port); - } - /* if bonding is used it is possible that we add it to masters - * only after IP address is assigned to the net bonding - * interface. - */ - if (curr_master && (old_master != curr_master)) { - reset_gid_table(ibdev, port); - mlx4_ib_set_default_gid(ibdev, curr_netdev, port); - mlx4_ib_get_dev_addr(curr_master, ibdev, port); - } + /* if using bonding/team and a slave port is down, we + * don't the bond IP based gids in the table since + * flows that select port by gid may get the down port. + */ + if (curr_master && (port_state == IB_PORT_DOWN)) { + reset_gid_table(ibdev, port); + mlx4_ib_set_default_gid(ibdev, + curr_netdev, port); + } + /* if bonding is used it is possible that we add it to + * masters only after IP address is assigned to the + * net bonding interface. + */ + if (curr_master && (old_master != curr_master)) { + reset_gid_table(ibdev, port); + mlx4_ib_set_default_gid(ibdev, + curr_netdev, port); + mlx4_ib_get_dev_addr(curr_master, ibdev, port); + } - if (!curr_master && (old_master != curr_master)) { + if (!curr_master && (old_master != curr_master)) { + reset_gid_table(ibdev, port); + mlx4_ib_set_default_gid(ibdev, + curr_netdev, port); + mlx4_ib_get_dev_addr(curr_netdev, ibdev, port); + } + } else { reset_gid_table(ibdev, port); - mlx4_ib_set_default_gid(ibdev, curr_netdev, port); - mlx4_ib_get_dev_addr(curr_netdev, ibdev, port); } } diff --git a/drivers/infiniband/hw/qib/qib.h b/drivers/infiniband/hw/qib/qib.h index 1946101419a3..675d3c796b9f 100644 --- a/drivers/infiniband/hw/qib/qib.h +++ b/drivers/infiniband/hw/qib/qib.h @@ -1080,12 +1080,6 @@ struct qib_devdata { /* control high-level access to EEPROM */ struct mutex eep_lock; uint64_t traffic_wds; - /* active time is kept in seconds, but logged in hours */ - atomic_t active_time; - /* Below are nominal shadow of EEPROM, new since last EEPROM update */ - uint8_t eep_st_errs[QIB_EEP_LOG_CNT]; - uint8_t eep_st_new_errs[QIB_EEP_LOG_CNT]; - uint16_t eep_hrs; /* * masks for which bits of errs, hwerrs that cause * each of the counters to increment. @@ -1307,8 +1301,7 @@ int qib_twsi_blk_rd(struct qib_devdata *dd, int dev, int addr, void *buffer, int qib_twsi_blk_wr(struct qib_devdata *dd, int dev, int addr, const void *buffer, int len); void qib_get_eeprom_info(struct qib_devdata *); -int qib_update_eeprom_log(struct qib_devdata *dd); -void qib_inc_eeprom_err(struct qib_devdata *dd, u32 eidx, u32 incr); +#define qib_inc_eeprom_err(dd, eidx, incr) void qib_dump_lookup_output_queue(struct qib_devdata *); void qib_force_pio_avail_update(struct qib_devdata *); void qib_clear_symerror_on_linkup(unsigned long opaque); diff --git a/drivers/infiniband/hw/qib/qib_debugfs.c b/drivers/infiniband/hw/qib/qib_debugfs.c index 799a0c3bffc4..6abd3ed3cd51 100644 --- a/drivers/infiniband/hw/qib/qib_debugfs.c +++ b/drivers/infiniband/hw/qib/qib_debugfs.c @@ -193,6 +193,7 @@ static void *_qp_stats_seq_start(struct seq_file *s, loff_t *pos) struct qib_qp_iter *iter; loff_t n = *pos; + rcu_read_lock(); iter = qib_qp_iter_init(s->private); if (!iter) return NULL; @@ -224,7 +225,7 @@ static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr, static void _qp_stats_seq_stop(struct seq_file *s, void *iter_ptr) { - /* nothing for now */ + rcu_read_unlock(); } static int _qp_stats_seq_show(struct seq_file *s, void *iter_ptr) diff --git a/drivers/infiniband/hw/qib/qib_eeprom.c b/drivers/infiniband/hw/qib/qib_eeprom.c index 4d5d71aaa2b4..e2280b07df02 100644 --- a/drivers/infiniband/hw/qib/qib_eeprom.c +++ b/drivers/infiniband/hw/qib/qib_eeprom.c @@ -267,190 +267,9 @@ void qib_get_eeprom_info(struct qib_devdata *dd) "Board SN %s did not pass functional test: %s\n", dd->serial, ifp->if_comment); - memcpy(&dd->eep_st_errs, &ifp->if_errcntp, QIB_EEP_LOG_CNT); - /* - * Power-on (actually "active") hours are kept as little-endian value - * in EEPROM, but as seconds in a (possibly as small as 24-bit) - * atomic_t while running. - */ - atomic_set(&dd->active_time, 0); - dd->eep_hrs = ifp->if_powerhour[0] | (ifp->if_powerhour[1] << 8); - done: vfree(buf); bail:; } -/** - * qib_update_eeprom_log - copy active-time and error counters to eeprom - * @dd: the qlogic_ib device - * - * Although the time is kept as seconds in the qib_devdata struct, it is - * rounded to hours for re-write, as we have only 16 bits in EEPROM. - * First-cut code reads whole (expected) struct qib_flash, modifies, - * re-writes. Future direction: read/write only what we need, assuming - * that the EEPROM had to have been "good enough" for driver init, and - * if not, we aren't making it worse. - * - */ -int qib_update_eeprom_log(struct qib_devdata *dd) -{ - void *buf; - struct qib_flash *ifp; - int len, hi_water; - uint32_t new_time, new_hrs; - u8 csum; - int ret, idx; - unsigned long flags; - - /* first, check if we actually need to do anything. */ - ret = 0; - for (idx = 0; idx < QIB_EEP_LOG_CNT; ++idx) { - if (dd->eep_st_new_errs[idx]) { - ret = 1; - break; - } - } - new_time = atomic_read(&dd->active_time); - - if (ret == 0 && new_time < 3600) - goto bail; - - /* - * The quick-check above determined that there is something worthy - * of logging, so get current contents and do a more detailed idea. - * read full flash, not just currently used part, since it may have - * been written with a newer definition - */ - len = sizeof(struct qib_flash); - buf = vmalloc(len); - ret = 1; - if (!buf) { - qib_dev_err(dd, - "Couldn't allocate memory to read %u bytes from eeprom for logging\n", - len); - goto bail; - } - - /* Grab semaphore and read current EEPROM. If we get an - * error, let go, but if not, keep it until we finish write. - */ - ret = mutex_lock_interruptible(&dd->eep_lock); - if (ret) { - qib_dev_err(dd, "Unable to acquire EEPROM for logging\n"); - goto free_bail; - } - ret = qib_twsi_blk_rd(dd, dd->twsi_eeprom_dev, 0, buf, len); - if (ret) { - mutex_unlock(&dd->eep_lock); - qib_dev_err(dd, "Unable read EEPROM for logging\n"); - goto free_bail; - } - ifp = (struct qib_flash *)buf; - - csum = flash_csum(ifp, 0); - if (csum != ifp->if_csum) { - mutex_unlock(&dd->eep_lock); - qib_dev_err(dd, "EEPROM cks err (0x%02X, S/B 0x%02X)\n", - csum, ifp->if_csum); - ret = 1; - goto free_bail; - } - hi_water = 0; - spin_lock_irqsave(&dd->eep_st_lock, flags); - for (idx = 0; idx < QIB_EEP_LOG_CNT; ++idx) { - int new_val = dd->eep_st_new_errs[idx]; - if (new_val) { - /* - * If we have seen any errors, add to EEPROM values - * We need to saturate at 0xFF (255) and we also - * would need to adjust the checksum if we were - * trying to minimize EEPROM traffic - * Note that we add to actual current count in EEPROM, - * in case it was altered while we were running. - */ - new_val += ifp->if_errcntp[idx]; - if (new_val > 0xFF) - new_val = 0xFF; - if (ifp->if_errcntp[idx] != new_val) { - ifp->if_errcntp[idx] = new_val; - hi_water = offsetof(struct qib_flash, - if_errcntp) + idx; - } - /* - * update our shadow (used to minimize EEPROM - * traffic), to match what we are about to write. - */ - dd->eep_st_errs[idx] = new_val; - dd->eep_st_new_errs[idx] = 0; - } - } - /* - * Now update active-time. We would like to round to the nearest hour - * but unless atomic_t are sure to be proper signed ints we cannot, - * because we need to account for what we "transfer" to EEPROM and - * if we log an hour at 31 minutes, then we would need to set - * active_time to -29 to accurately count the _next_ hour. - */ - if (new_time >= 3600) { - new_hrs = new_time / 3600; - atomic_sub((new_hrs * 3600), &dd->active_time); - new_hrs += dd->eep_hrs; - if (new_hrs > 0xFFFF) - new_hrs = 0xFFFF; - dd->eep_hrs = new_hrs; - if ((new_hrs & 0xFF) != ifp->if_powerhour[0]) { - ifp->if_powerhour[0] = new_hrs & 0xFF; - hi_water = offsetof(struct qib_flash, if_powerhour); - } - if ((new_hrs >> 8) != ifp->if_powerhour[1]) { - ifp->if_powerhour[1] = new_hrs >> 8; - hi_water = offsetof(struct qib_flash, if_powerhour) + 1; - } - } - /* - * There is a tiny possibility that we could somehow fail to write - * the EEPROM after updating our shadows, but problems from holding - * the spinlock too long are a much bigger issue. - */ - spin_unlock_irqrestore(&dd->eep_st_lock, flags); - if (hi_water) { - /* we made some change to the data, uopdate cksum and write */ - csum = flash_csum(ifp, 1); - ret = eeprom_write_with_enable(dd, 0, buf, hi_water + 1); - } - mutex_unlock(&dd->eep_lock); - if (ret) - qib_dev_err(dd, "Failed updating EEPROM\n"); - -free_bail: - vfree(buf); -bail: - return ret; -} - -/** - * qib_inc_eeprom_err - increment one of the four error counters - * that are logged to EEPROM. - * @dd: the qlogic_ib device - * @eidx: 0..3, the counter to increment - * @incr: how much to add - * - * Each counter is 8-bits, and saturates at 255 (0xFF). They - * are copied to the EEPROM (aka flash) whenever qib_update_eeprom_log() - * is called, but it can only be called in a context that allows sleep. - * This function can be called even at interrupt level. - */ -void qib_inc_eeprom_err(struct qib_devdata *dd, u32 eidx, u32 incr) -{ - uint new_val; - unsigned long flags; - - spin_lock_irqsave(&dd->eep_st_lock, flags); - new_val = dd->eep_st_new_errs[eidx] + incr; - if (new_val > 255) - new_val = 255; - dd->eep_st_new_errs[eidx] = new_val; - spin_unlock_irqrestore(&dd->eep_st_lock, flags); -} diff --git a/drivers/infiniband/hw/qib/qib_iba6120.c b/drivers/infiniband/hw/qib/qib_iba6120.c index 84e593d6007b..295f6312e6a9 100644 --- a/drivers/infiniband/hw/qib/qib_iba6120.c +++ b/drivers/infiniband/hw/qib/qib_iba6120.c @@ -2682,8 +2682,6 @@ static void qib_get_6120_faststats(unsigned long opaque) spin_lock_irqsave(&dd->eep_st_lock, flags); traffic_wds -= dd->traffic_wds; dd->traffic_wds += traffic_wds; - if (traffic_wds >= QIB_TRAFFIC_ACTIVE_THRESHOLD) - atomic_add(5, &dd->active_time); /* S/B #define */ spin_unlock_irqrestore(&dd->eep_st_lock, flags); qib_chk_6120_errormask(dd); diff --git a/drivers/infiniband/hw/qib/qib_iba7220.c b/drivers/infiniband/hw/qib/qib_iba7220.c index 454c2e7668fe..c86e71b9e160 100644 --- a/drivers/infiniband/hw/qib/qib_iba7220.c +++ b/drivers/infiniband/hw/qib/qib_iba7220.c @@ -3299,8 +3299,6 @@ static void qib_get_7220_faststats(unsigned long opaque) spin_lock_irqsave(&dd->eep_st_lock, flags); traffic_wds -= dd->traffic_wds; dd->traffic_wds += traffic_wds; - if (traffic_wds >= QIB_TRAFFIC_ACTIVE_THRESHOLD) - atomic_add(5, &dd->active_time); /* S/B #define */ spin_unlock_irqrestore(&dd->eep_st_lock, flags); done: mod_timer(&dd->stats_timer, jiffies + HZ * ACTIVITY_TIMER); diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c index d1bd21319d7d..0f8d1f0bd929 100644 --- a/drivers/infiniband/hw/qib/qib_iba7322.c +++ b/drivers/infiniband/hw/qib/qib_iba7322.c @@ -5191,8 +5191,6 @@ static void qib_get_7322_faststats(unsigned long opaque) spin_lock_irqsave(&ppd->dd->eep_st_lock, flags); traffic_wds -= ppd->dd->traffic_wds; ppd->dd->traffic_wds += traffic_wds; - if (traffic_wds >= QIB_TRAFFIC_ACTIVE_THRESHOLD) - atomic_add(ACTIVITY_TIMER, &ppd->dd->active_time); spin_unlock_irqrestore(&ppd->dd->eep_st_lock, flags); if (ppd->cpspec->qdr_dfe_on && (ppd->link_speed_active & QIB_IB_QDR) && diff --git a/drivers/infiniband/hw/qib/qib_init.c b/drivers/infiniband/hw/qib/qib_init.c index 76c3e177164d..8c9bb6c35838 100644 --- a/drivers/infiniband/hw/qib/qib_init.c +++ b/drivers/infiniband/hw/qib/qib_init.c @@ -922,7 +922,6 @@ static void qib_shutdown_device(struct qib_devdata *dd) } } - qib_update_eeprom_log(dd); } /** diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c index 0cad0c40d742..6a71b2b41b27 100644 --- a/drivers/infiniband/hw/qib/qib_qp.c +++ b/drivers/infiniband/hw/qib/qib_qp.c @@ -1324,7 +1324,6 @@ int qib_qp_iter_next(struct qib_qp_iter *iter) struct qib_qp *pqp = iter->qp; struct qib_qp *qp; - rcu_read_lock(); for (; n < dev->qp_table_size; n++) { if (pqp) qp = rcu_dereference(pqp->next); @@ -1332,18 +1331,11 @@ int qib_qp_iter_next(struct qib_qp_iter *iter) qp = rcu_dereference(dev->qp_table[n]); pqp = qp; if (qp) { - if (iter->qp) - atomic_dec(&iter->qp->refcount); - atomic_inc(&qp->refcount); - rcu_read_unlock(); iter->qp = qp; iter->n = n; return 0; } } - rcu_read_unlock(); - if (iter->qp) - atomic_dec(&iter->qp->refcount); return ret; } diff --git a/drivers/infiniband/hw/qib/qib_sysfs.c b/drivers/infiniband/hw/qib/qib_sysfs.c index 3c8e4e3caca6..b9ccbda7817d 100644 --- a/drivers/infiniband/hw/qib/qib_sysfs.c +++ b/drivers/infiniband/hw/qib/qib_sysfs.c @@ -611,28 +611,6 @@ bail: return ret < 0 ? ret : count; } -static ssize_t show_logged_errs(struct device *device, - struct device_attribute *attr, char *buf) -{ - struct qib_ibdev *dev = - container_of(device, struct qib_ibdev, ibdev.dev); - struct qib_devdata *dd = dd_from_dev(dev); - int idx, count; - - /* force consistency with actual EEPROM */ - if (qib_update_eeprom_log(dd) != 0) - return -ENXIO; - - count = 0; - for (idx = 0; idx < QIB_EEP_LOG_CNT; ++idx) { - count += scnprintf(buf + count, PAGE_SIZE - count, "%d%c", - dd->eep_st_errs[idx], - idx == (QIB_EEP_LOG_CNT - 1) ? '\n' : ' '); - } - - return count; -} - /* * Dump tempsense regs. in decimal, to ease shell-scripts. */ @@ -679,7 +657,6 @@ static DEVICE_ATTR(nctxts, S_IRUGO, show_nctxts, NULL); static DEVICE_ATTR(nfreectxts, S_IRUGO, show_nfreectxts, NULL); static DEVICE_ATTR(serial, S_IRUGO, show_serial, NULL); static DEVICE_ATTR(boardversion, S_IRUGO, show_boardversion, NULL); -static DEVICE_ATTR(logged_errors, S_IRUGO, show_logged_errs, NULL); static DEVICE_ATTR(tempsense, S_IRUGO, show_tempsense, NULL); static DEVICE_ATTR(localbus_info, S_IRUGO, show_localbus_info, NULL); static DEVICE_ATTR(chip_reset, S_IWUSR, NULL, store_chip_reset); @@ -693,7 +670,6 @@ static struct device_attribute *qib_attributes[] = { &dev_attr_nfreectxts, &dev_attr_serial, &dev_attr_boardversion, - &dev_attr_logged_errors, &dev_attr_tempsense, &dev_attr_localbus_info, &dev_attr_chip_reset, diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 156205a81523..60142274fe4b 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -41,6 +41,7 @@ static DEFINE_MUTEX(device_list_mutex); static LIST_HEAD(device_list); static struct workqueue_struct *isert_rx_wq; static struct workqueue_struct *isert_comp_wq; +static struct workqueue_struct *isert_release_wq; static void isert_unmap_cmd(struct isert_cmd *isert_cmd, struct isert_conn *isert_conn); @@ -52,6 +53,11 @@ isert_unreg_rdma(struct isert_cmd *isert_cmd, struct isert_conn *isert_conn); static int isert_reg_rdma(struct iscsi_conn *conn, struct iscsi_cmd *cmd, struct isert_rdma_wr *wr); +static int +isert_rdma_post_recvl(struct isert_conn *isert_conn); +static int +isert_rdma_accept(struct isert_conn *isert_conn); +struct rdma_cm_id *isert_setup_id(struct isert_np *isert_np); static void isert_qp_event_callback(struct ib_event *e, void *context) @@ -112,9 +118,12 @@ isert_conn_setup_qp(struct isert_conn *isert_conn, struct rdma_cm_id *cma_id) attr.cap.max_recv_wr = ISERT_QP_MAX_RECV_DTOS; /* * FIXME: Use devattr.max_sge - 2 for max_send_sge as - * work-around for RDMA_READ.. + * work-around for RDMA_READs with ConnectX-2. + * + * Also, still make sure to have at least two SGEs for + * outgoing control PDU responses. */ - attr.cap.max_send_sge = device->dev_attr.max_sge - 2; + attr.cap.max_send_sge = max(2, device->dev_attr.max_sge - 2); isert_conn->max_sge = attr.cap.max_send_sge; attr.cap.max_recv_sge = 1; @@ -129,12 +138,18 @@ isert_conn_setup_qp(struct isert_conn *isert_conn, struct rdma_cm_id *cma_id) ret = rdma_create_qp(cma_id, isert_conn->conn_pd, &attr); if (ret) { pr_err("rdma_create_qp failed for cma_id %d\n", ret); - return ret; + goto err; } isert_conn->conn_qp = cma_id->qp; pr_debug("rdma_create_qp() returned success >>>>>>>>>>>>>>>>>>>>>>>>>.\n"); return 0; +err: + mutex_lock(&device_list_mutex); + device->cq_active_qps[min_index]--; + mutex_unlock(&device_list_mutex); + + return ret; } static void @@ -220,12 +235,16 @@ isert_create_device_ib_res(struct isert_device *device) struct isert_cq_desc *cq_desc; struct ib_device_attr *dev_attr; int ret = 0, i, j; + int max_rx_cqe, max_tx_cqe; dev_attr = &device->dev_attr; ret = isert_query_device(ib_dev, dev_attr); if (ret) return ret; + max_rx_cqe = min(ISER_MAX_RX_CQ_LEN, dev_attr->max_cqe); + max_tx_cqe = min(ISER_MAX_TX_CQ_LEN, dev_attr->max_cqe); + /* asign function handlers */ if (dev_attr->device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) { device->use_fastreg = 1; @@ -261,7 +280,7 @@ isert_create_device_ib_res(struct isert_device *device) isert_cq_rx_callback, isert_cq_event_callback, (void *)&cq_desc[i], - ISER_MAX_RX_CQ_LEN, i); + max_rx_cqe, i); if (IS_ERR(device->dev_rx_cq[i])) { ret = PTR_ERR(device->dev_rx_cq[i]); device->dev_rx_cq[i] = NULL; @@ -273,7 +292,7 @@ isert_create_device_ib_res(struct isert_device *device) isert_cq_tx_callback, isert_cq_event_callback, (void *)&cq_desc[i], - ISER_MAX_TX_CQ_LEN, i); + max_tx_cqe, i); if (IS_ERR(device->dev_tx_cq[i])) { ret = PTR_ERR(device->dev_tx_cq[i]); device->dev_tx_cq[i] = NULL; @@ -482,8 +501,8 @@ err: static int isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) { - struct iscsi_np *np = cma_id->context; - struct isert_np *isert_np = np->np_context; + struct isert_np *isert_np = cma_id->context; + struct iscsi_np *np = isert_np->np; struct isert_conn *isert_conn; struct isert_device *device; struct ib_device *ib_dev = cma_id->device; @@ -508,15 +527,14 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) isert_conn->state = ISER_CONN_INIT; INIT_LIST_HEAD(&isert_conn->conn_accept_node); init_completion(&isert_conn->conn_login_comp); + init_completion(&isert_conn->login_req_comp); init_completion(&isert_conn->conn_wait); init_completion(&isert_conn->conn_wait_comp_err); kref_init(&isert_conn->conn_kref); - kref_get(&isert_conn->conn_kref); mutex_init(&isert_conn->conn_mutex); spin_lock_init(&isert_conn->conn_lock); INIT_LIST_HEAD(&isert_conn->conn_fr_pool); - cma_id->context = isert_conn; isert_conn->conn_cm_id = cma_id; isert_conn->responder_resources = event->param.conn.responder_resources; isert_conn->initiator_depth = event->param.conn.initiator_depth; @@ -590,6 +608,14 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) if (ret) goto out_conn_dev; + ret = isert_rdma_post_recvl(isert_conn); + if (ret) + goto out_conn_dev; + + ret = isert_rdma_accept(isert_conn); + if (ret) + goto out_conn_dev; + mutex_lock(&isert_np->np_accept_mutex); list_add_tail(&isert_conn->conn_accept_node, &isert_np->np_accept_list); mutex_unlock(&isert_np->np_accept_mutex); @@ -614,6 +640,7 @@ out_login_buf: kfree(isert_conn->login_buf); out: kfree(isert_conn); + rdma_reject(cma_id, NULL, 0); return ret; } @@ -629,18 +656,20 @@ isert_connect_release(struct isert_conn *isert_conn) if (device && device->use_fastreg) isert_conn_free_fastreg_pool(isert_conn); + isert_free_rx_descriptors(isert_conn); + rdma_destroy_id(isert_conn->conn_cm_id); + if (isert_conn->conn_qp) { cq_index = ((struct isert_cq_desc *) isert_conn->conn_qp->recv_cq->cq_context)->cq_index; pr_debug("isert_connect_release: cq_index: %d\n", cq_index); + mutex_lock(&device_list_mutex); isert_conn->conn_device->cq_active_qps[cq_index]--; + mutex_unlock(&device_list_mutex); - rdma_destroy_qp(isert_conn->conn_cm_id); + ib_destroy_qp(isert_conn->conn_qp); } - isert_free_rx_descriptors(isert_conn); - rdma_destroy_id(isert_conn->conn_cm_id); - ib_dereg_mr(isert_conn->conn_mr); ib_dealloc_pd(isert_conn->conn_pd); @@ -663,7 +692,19 @@ isert_connect_release(struct isert_conn *isert_conn) static void isert_connected_handler(struct rdma_cm_id *cma_id) { - return; + struct isert_conn *isert_conn = cma_id->qp->qp_context; + + pr_info("conn %p\n", isert_conn); + + if (!kref_get_unless_zero(&isert_conn->conn_kref)) { + pr_warn("conn %p connect_release is running\n", isert_conn); + return; + } + + mutex_lock(&isert_conn->conn_mutex); + if (isert_conn->state != ISER_CONN_FULL_FEATURE) + isert_conn->state = ISER_CONN_UP; + mutex_unlock(&isert_conn->conn_mutex); } static void @@ -684,55 +725,108 @@ isert_put_conn(struct isert_conn *isert_conn) kref_put(&isert_conn->conn_kref, isert_release_conn_kref); } +/** + * isert_conn_terminate() - Initiate connection termination + * @isert_conn: isert connection struct + * + * Notes: + * In case the connection state is FULL_FEATURE, move state + * to TEMINATING and start teardown sequence (rdma_disconnect). + * In case the connection state is UP, complete flush as well. + * + * This routine must be called with conn_mutex held. Thus it is + * safe to call multiple times. + */ static void -isert_disconnect_work(struct work_struct *work) +isert_conn_terminate(struct isert_conn *isert_conn) { - struct isert_conn *isert_conn = container_of(work, - struct isert_conn, conn_logout_work); + int err; - pr_debug("isert_disconnect_work(): >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n"); - mutex_lock(&isert_conn->conn_mutex); - if (isert_conn->state == ISER_CONN_UP) + switch (isert_conn->state) { + case ISER_CONN_TERMINATING: + break; + case ISER_CONN_UP: + /* + * No flush completions will occur as we didn't + * get to ISER_CONN_FULL_FEATURE yet, complete + * to allow teardown progress. + */ + complete(&isert_conn->conn_wait_comp_err); + case ISER_CONN_FULL_FEATURE: /* FALLTHRU */ + pr_info("Terminating conn %p state %d\n", + isert_conn, isert_conn->state); isert_conn->state = ISER_CONN_TERMINATING; - - if (isert_conn->post_recv_buf_count == 0 && - atomic_read(&isert_conn->post_send_buf_count) == 0) { - mutex_unlock(&isert_conn->conn_mutex); - goto wake_up; - } - if (!isert_conn->conn_cm_id) { - mutex_unlock(&isert_conn->conn_mutex); - isert_put_conn(isert_conn); - return; + err = rdma_disconnect(isert_conn->conn_cm_id); + if (err) + pr_warn("Failed rdma_disconnect isert_conn %p\n", + isert_conn); + break; + default: + pr_warn("conn %p teminating in state %d\n", + isert_conn, isert_conn->state); } +} - if (isert_conn->disconnect) { - /* Send DREQ/DREP towards our initiator */ - rdma_disconnect(isert_conn->conn_cm_id); +static int +isert_np_cma_handler(struct isert_np *isert_np, + enum rdma_cm_event_type event) +{ + pr_debug("isert np %p, handling event %d\n", isert_np, event); + + switch (event) { + case RDMA_CM_EVENT_DEVICE_REMOVAL: + isert_np->np_cm_id = NULL; + break; + case RDMA_CM_EVENT_ADDR_CHANGE: + isert_np->np_cm_id = isert_setup_id(isert_np); + if (IS_ERR(isert_np->np_cm_id)) { + pr_err("isert np %p setup id failed: %ld\n", + isert_np, PTR_ERR(isert_np->np_cm_id)); + isert_np->np_cm_id = NULL; + } + break; + default: + pr_err("isert np %p Unexpected event %d\n", + isert_np, event); } + return -1; +} + +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; + + if (isert_np->np_cm_id == cma_id) + return isert_np_cma_handler(cma_id->context, event); + + isert_conn = cma_id->qp->qp_context; + + mutex_lock(&isert_conn->conn_mutex); + isert_conn_terminate(isert_conn); mutex_unlock(&isert_conn->conn_mutex); -wake_up: + pr_info("conn %p completing conn_wait\n", isert_conn); complete(&isert_conn->conn_wait); - isert_put_conn(isert_conn); + + return 0; } static void -isert_disconnected_handler(struct rdma_cm_id *cma_id, bool disconnect) +isert_connect_error(struct rdma_cm_id *cma_id) { - struct isert_conn *isert_conn = (struct isert_conn *)cma_id->context; + struct isert_conn *isert_conn = cma_id->qp->qp_context; - isert_conn->disconnect = disconnect; - INIT_WORK(&isert_conn->conn_logout_work, isert_disconnect_work); - schedule_work(&isert_conn->conn_logout_work); + isert_put_conn(isert_conn); } static int isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) { int ret = 0; - bool disconnect = false; pr_debug("isert_cma_handler: event %d status %d conn %p id %p\n", event->event, event->status, cma_id->context, cma_id); @@ -740,6 +834,9 @@ isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) switch (event->event) { case RDMA_CM_EVENT_CONNECT_REQUEST: ret = isert_connect_request(cma_id, event); + if (ret) + pr_err("isert_cma_handler failed RDMA_CM_EVENT: 0x%08x %d\n", + event->event, ret); break; case RDMA_CM_EVENT_ESTABLISHED: isert_connected_handler(cma_id); @@ -747,22 +844,19 @@ isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) case RDMA_CM_EVENT_ADDR_CHANGE: /* FALLTHRU */ case RDMA_CM_EVENT_DISCONNECTED: /* FALLTHRU */ case RDMA_CM_EVENT_DEVICE_REMOVAL: /* FALLTHRU */ - disconnect = true; case RDMA_CM_EVENT_TIMEWAIT_EXIT: /* FALLTHRU */ - isert_disconnected_handler(cma_id, disconnect); + ret = isert_disconnected_handler(cma_id, event->event); break; + case RDMA_CM_EVENT_REJECTED: /* FALLTHRU */ + case RDMA_CM_EVENT_UNREACHABLE: /* FALLTHRU */ case RDMA_CM_EVENT_CONNECT_ERROR: + isert_connect_error(cma_id); + break; default: pr_err("Unhandled RDMA CMA event: %d\n", event->event); break; } - if (ret != 0) { - pr_err("isert_cma_handler failed RDMA_CM_EVENT: 0x%08x %d\n", - event->event, ret); - dump_stack(); - } - return ret; } @@ -891,7 +985,7 @@ isert_init_send_wr(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd, * bit for every ISERT_COMP_BATCH_COUNT number of ib_post_send() calls. */ mutex_lock(&isert_conn->conn_mutex); - if (coalesce && isert_conn->state == ISER_CONN_UP && + if (coalesce && isert_conn->state == ISER_CONN_FULL_FEATURE && ++isert_conn->conn_comp_batch < ISERT_COMP_BATCH_COUNT) { tx_desc->llnode_active = true; llist_add(&tx_desc->comp_llnode, &isert_conn->conn_comp_llist); @@ -970,7 +1064,8 @@ isert_put_login_tx(struct iscsi_conn *conn, struct iscsi_login *login, } if (!login->login_failed) { if (login->login_complete) { - if (isert_conn->conn_device->use_fastreg) { + if (!conn->sess->sess_ops->SessionType && + isert_conn->conn_device->use_fastreg) { ret = isert_conn_create_fastreg_pool(isert_conn); if (ret) { pr_err("Conn: %p failed to create" @@ -987,7 +1082,10 @@ isert_put_login_tx(struct iscsi_conn *conn, struct iscsi_login *login, if (ret) return ret; - isert_conn->state = ISER_CONN_UP; + /* Now we are in FULL_FEATURE phase */ + mutex_lock(&isert_conn->conn_mutex); + isert_conn->state = ISER_CONN_FULL_FEATURE; + mutex_unlock(&isert_conn->conn_mutex); goto post_send; } @@ -1004,18 +1102,17 @@ post_send: } static void -isert_rx_login_req(struct iser_rx_desc *rx_desc, int rx_buflen, - struct isert_conn *isert_conn) +isert_rx_login_req(struct isert_conn *isert_conn) { + struct iser_rx_desc *rx_desc = (void *)isert_conn->login_req_buf; + int rx_buflen = isert_conn->login_req_len; struct iscsi_conn *conn = isert_conn->conn; struct iscsi_login *login = conn->conn_login; int size; - if (!login) { - pr_err("conn->conn_login is NULL\n"); - dump_stack(); - return; - } + pr_info("conn %p\n", isert_conn); + + WARN_ON_ONCE(!login); if (login->first_request) { struct iscsi_login_req *login_req = @@ -1378,11 +1475,20 @@ isert_rx_completion(struct iser_rx_desc *desc, struct isert_conn *isert_conn, hdr->opcode, hdr->itt, hdr->flags, (int)(xfer_len - ISER_HEADERS_LEN)); - if ((char *)desc == isert_conn->login_req_buf) - isert_rx_login_req(desc, xfer_len - ISER_HEADERS_LEN, - isert_conn); - else + if ((char *)desc == isert_conn->login_req_buf) { + isert_conn->login_req_len = xfer_len - ISER_HEADERS_LEN; + if (isert_conn->conn) { + struct iscsi_login *login = isert_conn->conn->conn_login; + + if (login && !login->first_request) + isert_rx_login_req(isert_conn); + } + mutex_lock(&isert_conn->conn_mutex); + complete(&isert_conn->login_req_comp); + mutex_unlock(&isert_conn->conn_mutex); + } else { isert_rx_do_work(desc, isert_conn); + } ib_dma_sync_single_for_device(ib_dev, rx_dma, rx_buflen, DMA_FROM_DEVICE); @@ -1783,7 +1889,7 @@ isert_cq_rx_comp_err(struct isert_conn *isert_conn) msleep(3000); mutex_lock(&isert_conn->conn_mutex); - isert_conn->state = ISER_CONN_DOWN; + isert_conn_terminate(isert_conn); mutex_unlock(&isert_conn->conn_mutex); iscsit_cause_connection_reinstatement(isert_conn->conn, 0); @@ -1937,7 +2043,7 @@ isert_put_response(struct iscsi_conn *conn, struct iscsi_cmd *cmd) isert_cmd->tx_desc.num_sge = 2; } - isert_init_send_wr(isert_conn, isert_cmd, send_wr, true); + isert_init_send_wr(isert_conn, isert_cmd, send_wr, false); pr_debug("Posting SCSI Response IB_WR_SEND >>>>>>>>>>>>>>>>>>>>>>\n"); @@ -2456,7 +2562,7 @@ isert_put_datain(struct iscsi_conn *conn, struct iscsi_cmd *cmd) &isert_cmd->tx_desc.iscsi_header); isert_init_tx_hdrs(isert_conn, &isert_cmd->tx_desc); isert_init_send_wr(isert_conn, isert_cmd, - &isert_cmd->tx_desc.send_wr, true); + &isert_cmd->tx_desc.send_wr, false); atomic_add(wr->send_wr_num + 1, &isert_conn->post_send_buf_count); @@ -2563,13 +2669,51 @@ isert_response_queue(struct iscsi_conn *conn, struct iscsi_cmd *cmd, int state) return ret; } +struct rdma_cm_id * +isert_setup_id(struct isert_np *isert_np) +{ + struct iscsi_np *np = isert_np->np; + struct rdma_cm_id *id; + struct sockaddr *sa; + int ret; + + sa = (struct sockaddr *)&np->np_sockaddr; + pr_debug("ksockaddr: %p, sa: %p\n", &np->np_sockaddr, sa); + + id = rdma_create_id(isert_cma_handler, isert_np, + RDMA_PS_TCP, IB_QPT_RC); + if (IS_ERR(id)) { + pr_err("rdma_create_id() failed: %ld\n", PTR_ERR(id)); + ret = PTR_ERR(id); + goto out; + } + pr_debug("id %p context %p\n", id, id->context); + + ret = rdma_bind_addr(id, sa); + if (ret) { + pr_err("rdma_bind_addr() failed: %d\n", ret); + goto out_id; + } + + ret = rdma_listen(id, ISERT_RDMA_LISTEN_BACKLOG); + if (ret) { + pr_err("rdma_listen() failed: %d\n", ret); + goto out_id; + } + + return id; +out_id: + rdma_destroy_id(id); +out: + return ERR_PTR(ret); +} + static int isert_setup_np(struct iscsi_np *np, struct __kernel_sockaddr_storage *ksockaddr) { struct isert_np *isert_np; struct rdma_cm_id *isert_lid; - struct sockaddr *sa; int ret; isert_np = kzalloc(sizeof(struct isert_np), GFP_KERNEL); @@ -2581,9 +2725,8 @@ isert_setup_np(struct iscsi_np *np, mutex_init(&isert_np->np_accept_mutex); INIT_LIST_HEAD(&isert_np->np_accept_list); init_completion(&isert_np->np_login_comp); + isert_np->np = np; - sa = (struct sockaddr *)ksockaddr; - pr_debug("ksockaddr: %p, sa: %p\n", ksockaddr, sa); /* * Setup the np->np_sockaddr from the passed sockaddr setup * in iscsi_target_configfs.c code.. @@ -2591,37 +2734,20 @@ isert_setup_np(struct iscsi_np *np, memcpy(&np->np_sockaddr, ksockaddr, sizeof(struct __kernel_sockaddr_storage)); - isert_lid = rdma_create_id(isert_cma_handler, np, RDMA_PS_TCP, - IB_QPT_RC); + isert_lid = isert_setup_id(isert_np); if (IS_ERR(isert_lid)) { - pr_err("rdma_create_id() for isert_listen_handler failed: %ld\n", - PTR_ERR(isert_lid)); ret = PTR_ERR(isert_lid); goto out; } - ret = rdma_bind_addr(isert_lid, sa); - if (ret) { - pr_err("rdma_bind_addr() for isert_lid failed: %d\n", ret); - goto out_lid; - } - - ret = rdma_listen(isert_lid, ISERT_RDMA_LISTEN_BACKLOG); - if (ret) { - pr_err("rdma_listen() for isert_lid failed: %d\n", ret); - goto out_lid; - } - isert_np->np_cm_id = isert_lid; np->np_context = isert_np; - pr_debug("Setup isert_lid->context: %p\n", isert_lid->context); return 0; -out_lid: - rdma_destroy_id(isert_lid); out: kfree(isert_np); + return ret; } @@ -2657,7 +2783,15 @@ isert_get_login_rx(struct iscsi_conn *conn, struct iscsi_login *login) struct isert_conn *isert_conn = (struct isert_conn *)conn->context; int ret; - pr_debug("isert_get_login_rx before conn_login_comp conn: %p\n", conn); + pr_info("before login_req comp conn: %p\n", isert_conn); + ret = wait_for_completion_interruptible(&isert_conn->login_req_comp); + if (ret) { + pr_err("isert_conn %p interrupted before got login req\n", + isert_conn); + return ret; + } + reinit_completion(&isert_conn->login_req_comp); + /* * For login requests after the first PDU, isert_rx_login_req() will * kick schedule_delayed_work(&conn->login_work) as the packet is @@ -2667,11 +2801,15 @@ isert_get_login_rx(struct iscsi_conn *conn, struct iscsi_login *login) if (!login->first_request) return 0; + isert_rx_login_req(isert_conn); + + pr_info("before conn_login_comp conn: %p\n", conn); ret = wait_for_completion_interruptible(&isert_conn->conn_login_comp); if (ret) return ret; - pr_debug("isert_get_login_rx processing login->req: %p\n", login->req); + pr_info("processing login->req: %p\n", login->req); + return 0; } @@ -2749,17 +2887,10 @@ accept_wait: isert_conn->conn = conn; max_accept = 0; - ret = isert_rdma_post_recvl(isert_conn); - if (ret) - return ret; - - ret = isert_rdma_accept(isert_conn); - if (ret) - return ret; - isert_set_conn_info(np, conn, isert_conn); - pr_debug("Processing isert_accept_np: isert_conn: %p\n", isert_conn); + pr_debug("Processing isert_conn: %p\n", isert_conn); + return 0; } @@ -2768,12 +2899,31 @@ isert_free_np(struct iscsi_np *np) { struct isert_np *isert_np = (struct isert_np *)np->np_context; - rdma_destroy_id(isert_np->np_cm_id); + if (isert_np->np_cm_id) + rdma_destroy_id(isert_np->np_cm_id); np->np_context = NULL; kfree(isert_np); } +static void isert_release_work(struct work_struct *work) +{ + struct isert_conn *isert_conn = container_of(work, + struct isert_conn, + release_work); + + pr_info("Starting release conn %p\n", isert_conn); + + wait_for_completion(&isert_conn->conn_wait); + + mutex_lock(&isert_conn->conn_mutex); + isert_conn->state = ISER_CONN_DOWN; + mutex_unlock(&isert_conn->conn_mutex); + + pr_info("Destroying conn %p\n", isert_conn); + isert_put_conn(isert_conn); +} + static void isert_wait_conn(struct iscsi_conn *conn) { struct isert_conn *isert_conn = conn->context; @@ -2781,10 +2931,6 @@ static void isert_wait_conn(struct iscsi_conn *conn) pr_debug("isert_wait_conn: Starting \n"); mutex_lock(&isert_conn->conn_mutex); - if (isert_conn->conn_cm_id) { - pr_debug("Calling rdma_disconnect from isert_wait_conn\n"); - rdma_disconnect(isert_conn->conn_cm_id); - } /* * Only wait for conn_wait_comp_err if the isert_conn made it * into full feature phase.. @@ -2793,13 +2939,13 @@ static void isert_wait_conn(struct iscsi_conn *conn) mutex_unlock(&isert_conn->conn_mutex); return; } - if (isert_conn->state == ISER_CONN_UP) - isert_conn->state = ISER_CONN_TERMINATING; + isert_conn_terminate(isert_conn); mutex_unlock(&isert_conn->conn_mutex); wait_for_completion(&isert_conn->conn_wait_comp_err); - wait_for_completion(&isert_conn->conn_wait); + INIT_WORK(&isert_conn->release_work, isert_release_work); + queue_work(isert_release_wq, &isert_conn->release_work); } static void isert_free_conn(struct iscsi_conn *conn) @@ -2845,10 +2991,21 @@ static int __init isert_init(void) goto destroy_rx_wq; } + isert_release_wq = alloc_workqueue("isert_release_wq", WQ_UNBOUND, + WQ_UNBOUND_MAX_ACTIVE); + if (!isert_release_wq) { + pr_err("Unable to allocate isert_release_wq\n"); + ret = -ENOMEM; + goto destroy_comp_wq; + } + iscsit_register_transport(&iser_target_transport); - pr_debug("iSER_TARGET[0] - Loaded iser_target_transport\n"); + pr_info("iSER_TARGET[0] - Loaded iser_target_transport\n"); + return 0; +destroy_comp_wq: + destroy_workqueue(isert_comp_wq); destroy_rx_wq: destroy_workqueue(isert_rx_wq); return ret; @@ -2857,6 +3014,7 @@ destroy_rx_wq: static void __exit isert_exit(void) { flush_scheduled_work(); + destroy_workqueue(isert_release_wq); destroy_workqueue(isert_comp_wq); destroy_workqueue(isert_rx_wq); iscsit_unregister_transport(&iser_target_transport); diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h index cbecaabe90b9..1178c5b6800c 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.h +++ b/drivers/infiniband/ulp/isert/ib_isert.h @@ -23,6 +23,7 @@ enum iser_ib_op_code { enum iser_conn_state { ISER_CONN_INIT, ISER_CONN_UP, + ISER_CONN_FULL_FEATURE, ISER_CONN_TERMINATING, ISER_CONN_DOWN, }; @@ -102,6 +103,7 @@ struct isert_conn { char *login_req_buf; char *login_rsp_buf; u64 login_req_dma; + int login_req_len; u64 login_rsp_dma; unsigned int conn_rx_desc_head; struct iser_rx_desc *conn_rx_descs; @@ -109,13 +111,13 @@ struct isert_conn { struct iscsi_conn *conn; struct list_head conn_accept_node; struct completion conn_login_comp; + struct completion login_req_comp; struct iser_tx_desc conn_login_tx_desc; struct rdma_cm_id *conn_cm_id; struct ib_pd *conn_pd; struct ib_mr *conn_mr; struct ib_qp *conn_qp; struct isert_device *conn_device; - struct work_struct conn_logout_work; struct mutex conn_mutex; struct completion conn_wait; struct completion conn_wait_comp_err; @@ -124,10 +126,10 @@ struct isert_conn { int conn_fr_pool_size; /* lock to protect fastreg pool */ spinlock_t conn_lock; + struct work_struct release_work; #define ISERT_COMP_BATCH_COUNT 8 int conn_comp_batch; struct llist_head conn_comp_llist; - bool disconnect; }; #define ISERT_MAX_CQ 64 @@ -158,6 +160,7 @@ struct isert_device { }; struct isert_np { + struct iscsi_np *np; struct semaphore np_sem; struct rdma_cm_id *np_cm_id; struct mutex np_accept_mutex; diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index d1078ce73095..0097b8dae5bc 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -2091,6 +2091,7 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch) if (!qp_init) goto out; +retry: ch->cq = ib_create_cq(sdev->device, srpt_completion, NULL, ch, ch->rq_size + srp_sq_size, 0); if (IS_ERR(ch->cq)) { @@ -2114,6 +2115,13 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch) ch->qp = ib_create_qp(sdev->pd, qp_init); if (IS_ERR(ch->qp)) { ret = PTR_ERR(ch->qp); + if (ret == -ENOMEM) { + srp_sq_size /= 2; + if (srp_sq_size >= MIN_SRPT_SQ_SIZE) { + ib_destroy_cq(ch->cq); + goto retry; + } + } printk(KERN_ERR "failed to create_qp ret= %d\n", ret); goto err_destroy_cq; } diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index ce953d895f5b..fb787c3e88d9 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -757,20 +757,23 @@ static int evdev_handle_set_keycode_v2(struct input_dev *dev, void __user *p) */ static int evdev_handle_get_val(struct evdev_client *client, struct input_dev *dev, unsigned int type, - unsigned long *bits, unsigned int max, - unsigned int size, void __user *p, int compat) + unsigned long *bits, unsigned int maxbit, + unsigned int maxlen, void __user *p, + int compat) { int ret; unsigned long *mem; + size_t len; - mem = kmalloc(sizeof(unsigned long) * max, GFP_KERNEL); + len = BITS_TO_LONGS(maxbit) * sizeof(unsigned long); + mem = kmalloc(len, GFP_KERNEL); if (!mem) return -ENOMEM; spin_lock_irq(&dev->event_lock); spin_lock(&client->buffer_lock); - memcpy(mem, bits, sizeof(unsigned long) * max); + memcpy(mem, bits, len); spin_unlock(&dev->event_lock); @@ -778,7 +781,7 @@ static int evdev_handle_get_val(struct evdev_client *client, spin_unlock_irq(&client->buffer_lock); - ret = bits_to_user(mem, max, size, p, compat); + ret = bits_to_user(mem, maxbit, maxlen, p, compat); if (ret < 0) evdev_queue_syn_dropped(client); diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 603fe0dd3682..517829f6a58b 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -1003,9 +1003,19 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id } ep_irq_in = &intf->cur_altsetting->endpoint[1].desc; - usb_fill_bulk_urb(xpad->bulk_out, udev, - usb_sndbulkpipe(udev, ep_irq_in->bEndpointAddress), - xpad->bdata, XPAD_PKT_LEN, xpad_bulk_out, xpad); + if (usb_endpoint_is_bulk_out(ep_irq_in)) { + usb_fill_bulk_urb(xpad->bulk_out, udev, + usb_sndbulkpipe(udev, + ep_irq_in->bEndpointAddress), + xpad->bdata, XPAD_PKT_LEN, + xpad_bulk_out, xpad); + } else { + usb_fill_int_urb(xpad->bulk_out, udev, + usb_sndintpipe(udev, + ep_irq_in->bEndpointAddress), + xpad->bdata, XPAD_PKT_LEN, + xpad_bulk_out, xpad, 0); + } /* * Submit the int URB immediately rather than waiting for open diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c index 2dd1d0dd4f7d..6f5d79569136 100644 --- a/drivers/input/keyboard/atkbd.c +++ b/drivers/input/keyboard/atkbd.c @@ -1791,14 +1791,6 @@ static const struct dmi_system_id atkbd_dmi_quirk_table[] __initconst = { { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LG Electronics"), - DMI_MATCH(DMI_PRODUCT_NAME, "LW25-B7HV"), - }, - .callback = atkbd_deactivate_fixup, - }, - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LG Electronics"), - DMI_MATCH(DMI_PRODUCT_NAME, "P1-J273B"), }, .callback = atkbd_deactivate_fixup, }, diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c index fb15c64ffb95..4979b00fbf04 100644 --- a/drivers/input/mouse/alps.c +++ b/drivers/input/mouse/alps.c @@ -1047,7 +1047,13 @@ static psmouse_ret_t alps_process_byte(struct psmouse *psmouse) { struct alps_data *priv = psmouse->private; - if ((psmouse->packet[0] & 0xc8) == 0x08) { /* PS/2 packet */ + /* + * Check if we are dealing with a bare PS/2 packet, presumably from + * a device connected to the external PS/2 port. Because bare PS/2 + * protocol does not have enough constant bits to self-synchronize + * properly we only do this if the device is fully synchronized. + */ + if (!psmouse->out_of_sync_cnt && (psmouse->packet[0] & 0xc8) == 0x08) { if (psmouse->pktcnt == 3) { alps_report_bare_ps2_packet(psmouse, psmouse->packet, true); @@ -1071,12 +1077,27 @@ static psmouse_ret_t alps_process_byte(struct psmouse *psmouse) } /* Bytes 2 - pktsize should have 0 in the highest bit */ - if ((priv->proto_version < ALPS_PROTO_V5) && + if (priv->proto_version < ALPS_PROTO_V5 && psmouse->pktcnt >= 2 && psmouse->pktcnt <= psmouse->pktsize && (psmouse->packet[psmouse->pktcnt - 1] & 0x80)) { psmouse_dbg(psmouse, "refusing packet[%i] = %x\n", psmouse->pktcnt - 1, psmouse->packet[psmouse->pktcnt - 1]); + + if (priv->proto_version == ALPS_PROTO_V3 && + psmouse->pktcnt == psmouse->pktsize) { + /* + * Some Dell boxes, such as Latitude E6440 or E7440 + * with closed lid, quite often smash last byte of + * otherwise valid packet with 0xff. Given that the + * next packet is very likely to be valid let's + * report PSMOUSE_FULL_PACKET but not process data, + * rather than reporting PSMOUSE_BAD_DATA and + * filling the logs. + */ + return PSMOUSE_FULL_PACKET; + } + return PSMOUSE_BAD_DATA; } @@ -2148,6 +2169,9 @@ int alps_init(struct psmouse *psmouse) /* We are having trouble resyncing ALPS touchpads so disable it for now */ psmouse->resync_time = 0; + /* Allow 2 invalid packets without resetting device */ + psmouse->resetafter = psmouse->pktsize * 2; + return 0; init_fail: diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index 233516aff595..0b75b5764f31 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -1253,6 +1253,13 @@ static bool elantech_is_signature_valid(const unsigned char *param) if (param[1] == 0) return true; + /* + * Some models have a revision higher then 20. Meaning param[2] may + * be 10 or 20, skip the rates check for these. + */ + if (param[0] == 0x46 && (param[1] & 0xef) == 0x0f && param[2] < 40) + return true; + for (i = 0; i < ARRAY_SIZE(rates); i++) if (param[2] == rates[i]) return false; diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index ef9e0b8a9aa7..b00e282ef166 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -132,14 +132,19 @@ static const struct min_max_quirk min_max_pnpid_table[] = { 1232, 5710, 1156, 4696 }, { - (const char * const []){"LEN0034", "LEN0036", "LEN2002", - "LEN2004", NULL}, + (const char * const []){"LEN0034", "LEN0036", "LEN0037", + "LEN0039", "LEN2002", "LEN2004", + NULL}, 1024, 5112, 2024, 4832 }, { (const char * const []){"LEN2001", NULL}, 1024, 5022, 2508, 4832 }, + { + (const char * const []){"LEN2006", NULL}, + 1264, 5675, 1171, 4688 + }, { } }; @@ -158,8 +163,9 @@ static const char * const topbuttonpad_pnp_ids[] = { "LEN0034", /* T431s, L440, L540, T540, W540, X1 Carbon 2nd */ "LEN0035", /* X240 */ "LEN0036", /* T440 */ - "LEN0037", + "LEN0037", /* X1 Carbon 2nd */ "LEN0038", + "LEN0039", /* T440s */ "LEN0041", "LEN0042", /* Yoga */ "LEN0045", @@ -626,10 +632,61 @@ static int synaptics_parse_hw_state(const unsigned char buf[], ((buf[0] & 0x04) >> 1) | ((buf[3] & 0x04) >> 2)); + if ((SYN_CAP_ADV_GESTURE(priv->ext_cap_0c) || + SYN_CAP_IMAGE_SENSOR(priv->ext_cap_0c)) && + hw->w == 2) { + synaptics_parse_agm(buf, priv, hw); + return 1; + } + + hw->x = (((buf[3] & 0x10) << 8) | + ((buf[1] & 0x0f) << 8) | + buf[4]); + hw->y = (((buf[3] & 0x20) << 7) | + ((buf[1] & 0xf0) << 4) | + buf[5]); + hw->z = buf[2]; + hw->left = (buf[0] & 0x01) ? 1 : 0; hw->right = (buf[0] & 0x02) ? 1 : 0; - if (SYN_CAP_CLICKPAD(priv->ext_cap_0c)) { + if (SYN_CAP_FORCEPAD(priv->ext_cap_0c)) { + /* + * ForcePads, like Clickpads, use middle button + * bits to report primary button clicks. + * Unfortunately they report primary button not + * only when user presses on the pad above certain + * threshold, but also when there are more than one + * finger on the touchpad, which interferes with + * out multi-finger gestures. + */ + if (hw->z == 0) { + /* No contacts */ + priv->press = priv->report_press = false; + } else if (hw->w >= 4 && ((buf[0] ^ buf[3]) & 0x01)) { + /* + * Single-finger touch with pressure above + * the threshold. If pressure stays long + * enough, we'll start reporting primary + * button. We rely on the device continuing + * sending data even if finger does not + * move. + */ + if (!priv->press) { + priv->press_start = jiffies; + priv->press = true; + } else if (time_after(jiffies, + priv->press_start + + msecs_to_jiffies(50))) { + priv->report_press = true; + } + } else { + priv->press = false; + } + + hw->left = priv->report_press; + + } else if (SYN_CAP_CLICKPAD(priv->ext_cap_0c)) { /* * Clickpad's button is transmitted as middle button, * however, since it is primary button, we will report @@ -648,21 +705,6 @@ static int synaptics_parse_hw_state(const unsigned char buf[], hw->down = ((buf[0] ^ buf[3]) & 0x02) ? 1 : 0; } - if ((SYN_CAP_ADV_GESTURE(priv->ext_cap_0c) || - SYN_CAP_IMAGE_SENSOR(priv->ext_cap_0c)) && - hw->w == 2) { - synaptics_parse_agm(buf, priv, hw); - return 1; - } - - hw->x = (((buf[3] & 0x10) << 8) | - ((buf[1] & 0x0f) << 8) | - buf[4]); - hw->y = (((buf[3] & 0x20) << 7) | - ((buf[1] & 0xf0) << 4) | - buf[5]); - hw->z = buf[2]; - if (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) && ((buf[0] ^ buf[3]) & 0x02)) { switch (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) & ~0x01) { diff --git a/drivers/input/mouse/synaptics.h b/drivers/input/mouse/synaptics.h index e594af0b264b..fb2e076738ae 100644 --- a/drivers/input/mouse/synaptics.h +++ b/drivers/input/mouse/synaptics.h @@ -78,6 +78,11 @@ * 2 0x08 image sensor image sensor tracks 5 fingers, but only * reports 2. * 2 0x20 report min query 0x0f gives min coord reported + * 2 0x80 forcepad forcepad is a variant of clickpad that + * does not have physical buttons but rather + * uses pressure above certain threshold to + * report primary clicks. Forcepads also have + * clickpad bit set. */ #define SYN_CAP_CLICKPAD(ex0c) ((ex0c) & 0x100000) /* 1-button ClickPad */ #define SYN_CAP_CLICKPAD2BTN(ex0c) ((ex0c) & 0x000100) /* 2-button ClickPad */ @@ -86,6 +91,7 @@ #define SYN_CAP_ADV_GESTURE(ex0c) ((ex0c) & 0x080000) #define SYN_CAP_REDUCED_FILTERING(ex0c) ((ex0c) & 0x000400) #define SYN_CAP_IMAGE_SENSOR(ex0c) ((ex0c) & 0x000800) +#define SYN_CAP_FORCEPAD(ex0c) ((ex0c) & 0x008000) /* synaptics modes query bits */ #define SYN_MODE_ABSOLUTE(m) ((m) & (1 << 7)) @@ -177,6 +183,11 @@ struct synaptics_data { */ struct synaptics_hw_state agm; bool agm_pending; /* new AGM packet received */ + + /* ForcePad handling */ + unsigned long press_start; + bool press; + bool report_press; }; void synaptics_module_init(void); diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 381b20d4c561..dd6d14d2337f 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -101,6 +101,12 @@ static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = { }, { .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "X750LN"), + }, + }, + { + .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Compaq"), DMI_MATCH(DMI_PRODUCT_NAME , "ProLiant"), DMI_MATCH(DMI_PRODUCT_VERSION, "8500"), @@ -146,6 +152,14 @@ static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = { }, }, { + /* Medion Akoya E7225 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Medion"), + DMI_MATCH(DMI_PRODUCT_NAME, "Akoya E7225"), + DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), + }, + }, + { /* Blue FB5601 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "blue"), @@ -402,6 +416,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { }, }, { + /* Acer Aspire 7738 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 7738"), + }, + }, + { /* Gericom Bellagio */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Gericom"), @@ -458,6 +479,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"), }, }, + { + /* Avatar AVIU-145A6 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Intel"), + DMI_MATCH(DMI_PRODUCT_NAME, "IC4I"), + }, + }, { } }; @@ -601,6 +629,30 @@ static const struct dmi_system_id __initconst i8042_dmi_notimeout_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"), }, }, + { + /* Fujitsu A544 laptop */ + /* https://bugzilla.redhat.com/show_bug.cgi?id=1111138 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK A544"), + }, + }, + { + /* Fujitsu AH544 laptop */ + /* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK AH544"), + }, + }, + { + /* Fujitsu U574 laptop */ + /* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U574"), + }, + }, { } }; @@ -684,6 +736,35 @@ static const struct dmi_system_id __initconst i8042_dmi_dritek_table[] = { { } }; +/* + * Some laptops need keyboard reset before probing for the trackpad to get + * it detected, initialised & finally work. + */ +static const struct dmi_system_id __initconst i8042_dmi_kbdreset_table[] = { + { + /* Gigabyte P35 v2 - Elantech touchpad */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "P35V2"), + }, + }, + { + /* Aorus branded Gigabyte X3 Plus - Elantech touchpad */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "X3"), + }, + }, + { + /* Gigabyte P34 - Elantech touchpad */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "P34"), + }, + }, + { } +}; + #endif /* CONFIG_X86 */ #ifdef CONFIG_PNP @@ -979,6 +1060,9 @@ static int __init i8042_platform_init(void) if (dmi_check_system(i8042_dmi_dritek_table)) i8042_dritek = true; + if (dmi_check_system(i8042_dmi_kbdreset_table)) + i8042_kbdreset = true; + /* * A20 was already enabled during early kernel init. But some buggy * BIOSes (in MSI Laptops) require A20 to be enabled using 8042 to diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index 3807c3e971cc..eb796fff9e62 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -67,6 +67,10 @@ static bool i8042_notimeout; module_param_named(notimeout, i8042_notimeout, bool, 0); MODULE_PARM_DESC(notimeout, "Ignore timeouts signalled by i8042"); +static bool i8042_kbdreset; +module_param_named(kbdreset, i8042_kbdreset, bool, 0); +MODULE_PARM_DESC(kbdreset, "Reset device connected to KBD port"); + #ifdef CONFIG_X86 static bool i8042_dritek; module_param_named(dritek, i8042_dritek, bool, 0); @@ -790,6 +794,16 @@ static int __init i8042_check_aux(void) return -1; /* + * Reset keyboard (needed on some laptops to successfully detect + * touchpad, e.g., some Gigabyte laptop models with Elantech + * touchpads). + */ + if (i8042_kbdreset) { + pr_warn("Attempting to reset device connected to KBD port\n"); + i8042_kbd_write(NULL, (unsigned char) 0xff); + } + +/* * Test AUX IRQ delivery to make sure BIOS did not grab the IRQ and * used it for a PCI card or somethig else. */ diff --git a/drivers/input/serio/serport.c b/drivers/input/serio/serport.c index 0cb7ef59071b..69175b825346 100644 --- a/drivers/input/serio/serport.c +++ b/drivers/input/serio/serport.c @@ -21,6 +21,7 @@ #include <linux/init.h> #include <linux/serio.h> #include <linux/tty.h> +#include <linux/compat.h> MODULE_AUTHOR("Vojtech Pavlik <vojtech@ucw.cz>"); MODULE_DESCRIPTION("Input device TTY line discipline"); @@ -198,28 +199,55 @@ static ssize_t serport_ldisc_read(struct tty_struct * tty, struct file * file, u return 0; } +static void serport_set_type(struct tty_struct *tty, unsigned long type) +{ + struct serport *serport = tty->disc_data; + + serport->id.proto = type & 0x000000ff; + serport->id.id = (type & 0x0000ff00) >> 8; + serport->id.extra = (type & 0x00ff0000) >> 16; +} + /* * serport_ldisc_ioctl() allows to set the port protocol, and device ID */ -static int serport_ldisc_ioctl(struct tty_struct * tty, struct file * file, unsigned int cmd, unsigned long arg) +static int serport_ldisc_ioctl(struct tty_struct *tty, struct file *file, + unsigned int cmd, unsigned long arg) { - struct serport *serport = (struct serport*) tty->disc_data; - unsigned long type; - if (cmd == SPIOCSTYPE) { + unsigned long type; + if (get_user(type, (unsigned long __user *) arg)) return -EFAULT; - serport->id.proto = type & 0x000000ff; - serport->id.id = (type & 0x0000ff00) >> 8; - serport->id.extra = (type & 0x00ff0000) >> 16; + serport_set_type(tty, type); + return 0; + } + + return -EINVAL; +} + +#ifdef CONFIG_COMPAT +#define COMPAT_SPIOCSTYPE _IOW('q', 0x01, compat_ulong_t) +static long serport_ldisc_compat_ioctl(struct tty_struct *tty, + struct file *file, + unsigned int cmd, unsigned long arg) +{ + if (cmd == COMPAT_SPIOCSTYPE) { + void __user *uarg = compat_ptr(arg); + compat_ulong_t compat_type; + + if (get_user(compat_type, (compat_ulong_t __user *)uarg)) + return -EFAULT; + serport_set_type(tty, compat_type); return 0; } return -EINVAL; } +#endif static void serport_ldisc_write_wakeup(struct tty_struct * tty) { @@ -243,6 +271,9 @@ static struct tty_ldisc_ops serport_ldisc = { .close = serport_ldisc_close, .read = serport_ldisc_read, .ioctl = serport_ldisc_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = serport_ldisc_compat_ioctl, +#endif .receive_buf = serport_ldisc_receive, .write_wakeup = serport_ldisc_write_wakeup }; diff --git a/drivers/input/tablet/wacom_wac.c b/drivers/input/tablet/wacom_wac.c index 05f371df6c40..d4b0a31ab66b 100644 --- a/drivers/input/tablet/wacom_wac.c +++ b/drivers/input/tablet/wacom_wac.c @@ -700,6 +700,12 @@ static int wacom_intuos_irq(struct wacom_wac *wacom) input_report_key(input, BTN_7, (data[4] & 0x40)); /* Left */ input_report_key(input, BTN_8, (data[4] & 0x80)); /* Down */ input_report_key(input, BTN_0, (data[3] & 0x01)); /* Center */ + + if (data[4] | (data[3] & 0x01)) { + input_report_abs(input, ABS_MISC, PAD_DEVICE_ID); + } else { + input_report_abs(input, ABS_MISC, 0); + } } else if (features->type >= INTUOS5S && features->type <= INTUOSPL) { int i; diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 1d9ab39af29f..2ecac467f78f 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -794,8 +794,11 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain) reg |= TTBCR_EAE | (TTBCR_SH_IS << TTBCR_SH0_SHIFT) | (TTBCR_RGN_WBWA << TTBCR_ORGN0_SHIFT) | - (TTBCR_RGN_WBWA << TTBCR_IRGN0_SHIFT) | - (TTBCR_SL0_LVL_1 << TTBCR_SL0_SHIFT); + (TTBCR_RGN_WBWA << TTBCR_IRGN0_SHIFT); + + if (!stage1) + reg |= (TTBCR_SL0_LVL_1 << TTBCR_SL0_SHIFT); + writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR); /* MAIR0 (stage-1 only) */ diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 40f6b47c28f6..8855ecbc36be 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -1768,7 +1768,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, struct dma_pte *first_pte = NULL, *pte = NULL; phys_addr_t uninitialized_var(pteval); int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT; - unsigned long sg_res; + unsigned long sg_res = 0; unsigned int largepage_lvl = 0; unsigned long lvl_pages = 0; @@ -1779,10 +1779,8 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, prot &= DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP; - if (sg) - sg_res = 0; - else { - sg_res = nr_pages + 1; + if (!sg) { + sg_res = nr_pages; pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | prot; } diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c index 63ecc1723466..afcb430508ec 100644 --- a/drivers/mailbox/mailbox.c +++ b/drivers/mailbox/mailbox.c @@ -126,7 +126,7 @@ static void poll_txdone(unsigned long data) if (resched) mod_timer(&mbox->poll, jiffies + - msecs_to_jiffies(mbox->period)); + msecs_to_jiffies(mbox->txpoll_period)); } /** @@ -252,8 +252,6 @@ int mbox_send_message(struct mbox_chan *chan, void *mssg) msg_submit(chan); - reinit_completion(&chan->tx_complete); - if (chan->txdone_method == TXDONE_BY_POLL) poll_txdone((unsigned long)chan->mbox); diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 5f9c2a665ca5..fbcb6225f794 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -199,7 +199,7 @@ void bch_btree_node_read_done(struct btree *b) struct bset *i = btree_bset_first(b); struct btree_iter *iter; - iter = mempool_alloc(b->c->fill_iter, GFP_NOWAIT); + iter = mempool_alloc(b->c->fill_iter, GFP_NOIO); iter->size = b->c->sb.bucket_size / b->c->sb.block_size; iter->used = 0; diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 4195a01b1535..8e51b3a3e7b9 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -883,7 +883,6 @@ void bitmap_unplug(struct bitmap *bitmap) { unsigned long i; int dirty, need_write; - int wait = 0; if (!bitmap || !bitmap->storage.filemap || test_bit(BITMAP_STALE, &bitmap->flags)) @@ -901,16 +900,13 @@ void bitmap_unplug(struct bitmap *bitmap) clear_page_attr(bitmap, i, BITMAP_PAGE_PENDING); write_page(bitmap, bitmap->storage.filemap[i], 0); } - if (dirty) - wait = 1; - } - if (wait) { /* if any writes were performed, we need to wait on them */ - if (bitmap->storage.file) - wait_event(bitmap->write_wait, - atomic_read(&bitmap->pending_writes)==0); - else - md_super_wait(bitmap->mddev); } + if (bitmap->storage.file) + wait_event(bitmap->write_wait, + atomic_read(&bitmap->pending_writes)==0); + else + md_super_wait(bitmap->mddev); + if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags)) bitmap_file_kick(bitmap); } diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 0e722c103562..03c872fd5d5c 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -465,6 +465,7 @@ static void __relink_lru(struct dm_buffer *b, int dirty) c->n_buffers[dirty]++; b->list_mode = dirty; list_move(&b->lru_list, &c->lru[dirty]); + b->last_accessed = jiffies; } /*---------------------------------------------------------------- @@ -531,6 +532,19 @@ static void use_dmio(struct dm_buffer *b, int rw, sector_t block, end_io(&b->bio, r); } +static void inline_endio(struct bio *bio, int error) +{ + bio_end_io_t *end_fn = bio->bi_private; + + /* + * Reset the bio to free any attached resources + * (e.g. bio integrity profiles). + */ + bio_reset(bio); + + end_fn(bio, error); +} + static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block, bio_end_io_t *end_io) { @@ -542,7 +556,12 @@ static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block, b->bio.bi_max_vecs = DM_BUFIO_INLINE_VECS; b->bio.bi_iter.bi_sector = block << b->c->sectors_per_block_bits; b->bio.bi_bdev = b->c->bdev; - b->bio.bi_end_io = end_io; + b->bio.bi_end_io = inline_endio; + /* + * Use of .bi_private isn't a problem here because + * the dm_buffer's inline bio is local to bufio. + */ + b->bio.bi_private = end_io; /* * We assume that if len >= PAGE_SIZE ptr is page-aligned. @@ -1447,9 +1466,9 @@ static void drop_buffers(struct dm_bufio_client *c) /* * Test if the buffer is unused and too old, and commit it. - * At if noio is set, we must not do any I/O because we hold - * dm_bufio_clients_lock and we would risk deadlock if the I/O gets rerouted to - * different bufio client. + * And if GFP_NOFS is used, we must not do any I/O because we hold + * dm_bufio_clients_lock and we would risk deadlock if the I/O gets + * rerouted to different bufio client. */ static int __cleanup_old_buffer(struct dm_buffer *b, gfp_t gfp, unsigned long max_jiffies) @@ -1457,7 +1476,7 @@ static int __cleanup_old_buffer(struct dm_buffer *b, gfp_t gfp, if (jiffies - b->last_accessed < max_jiffies) return 0; - if (!(gfp & __GFP_IO)) { + if (!(gfp & __GFP_FS)) { if (test_bit(B_READING, &b->state) || test_bit(B_WRITING, &b->state) || test_bit(B_DIRTY, &b->state)) @@ -1485,9 +1504,9 @@ static long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan, list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) { freed += __cleanup_old_buffer(b, gfp_mask, 0); if (!--nr_to_scan) - break; + return freed; + dm_bufio_cond_resched(); } - dm_bufio_cond_resched(); } return freed; } @@ -1499,7 +1518,7 @@ dm_bufio_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) unsigned long freed; c = container_of(shrink, struct dm_bufio_client, shrinker); - if (sc->gfp_mask & __GFP_IO) + if (sc->gfp_mask & __GFP_FS) dm_bufio_lock(c); else if (!dm_bufio_trylock(c)) return SHRINK_STOP; @@ -1516,7 +1535,7 @@ dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc) unsigned long count; c = container_of(shrink, struct dm_bufio_client, shrinker); - if (sc->gfp_mask & __GFP_IO) + if (sc->gfp_mask & __GFP_FS) dm_bufio_lock(c); else if (!dm_bufio_trylock(c)) return 0; diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index a87d3fab0271..b950a803bae8 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -94,6 +94,9 @@ struct cache_disk_superblock { } __packed; struct dm_cache_metadata { + atomic_t ref_count; + struct list_head list; + struct block_device *bdev; struct dm_block_manager *bm; struct dm_space_map *metadata_sm; @@ -669,10 +672,10 @@ static void unpack_value(__le64 value_le, dm_oblock_t *block, unsigned *flags) /*----------------------------------------------------------------*/ -struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev, - sector_t data_block_size, - bool may_format_device, - size_t policy_hint_size) +static struct dm_cache_metadata *metadata_open(struct block_device *bdev, + sector_t data_block_size, + bool may_format_device, + size_t policy_hint_size) { int r; struct dm_cache_metadata *cmd; @@ -680,9 +683,10 @@ struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev, cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); if (!cmd) { DMERR("could not allocate metadata struct"); - return NULL; + return ERR_PTR(-ENOMEM); } + atomic_set(&cmd->ref_count, 1); init_rwsem(&cmd->root_lock); cmd->bdev = bdev; cmd->data_block_size = data_block_size; @@ -705,10 +709,96 @@ struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev, return cmd; } +/* + * We keep a little list of ref counted metadata objects to prevent two + * different target instances creating separate bufio instances. This is + * an issue if a table is reloaded before the suspend. + */ +static DEFINE_MUTEX(table_lock); +static LIST_HEAD(table); + +static struct dm_cache_metadata *lookup(struct block_device *bdev) +{ + struct dm_cache_metadata *cmd; + + list_for_each_entry(cmd, &table, list) + if (cmd->bdev == bdev) { + atomic_inc(&cmd->ref_count); + return cmd; + } + + return NULL; +} + +static struct dm_cache_metadata *lookup_or_open(struct block_device *bdev, + sector_t data_block_size, + bool may_format_device, + size_t policy_hint_size) +{ + struct dm_cache_metadata *cmd, *cmd2; + + mutex_lock(&table_lock); + cmd = lookup(bdev); + mutex_unlock(&table_lock); + + if (cmd) + return cmd; + + cmd = metadata_open(bdev, data_block_size, may_format_device, policy_hint_size); + if (!IS_ERR(cmd)) { + mutex_lock(&table_lock); + cmd2 = lookup(bdev); + if (cmd2) { + mutex_unlock(&table_lock); + __destroy_persistent_data_objects(cmd); + kfree(cmd); + return cmd2; + } + list_add(&cmd->list, &table); + mutex_unlock(&table_lock); + } + + return cmd; +} + +static bool same_params(struct dm_cache_metadata *cmd, sector_t data_block_size) +{ + if (cmd->data_block_size != data_block_size) { + DMERR("data_block_size (%llu) different from that in metadata (%llu)\n", + (unsigned long long) data_block_size, + (unsigned long long) cmd->data_block_size); + return false; + } + + return true; +} + +struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev, + sector_t data_block_size, + bool may_format_device, + size_t policy_hint_size) +{ + struct dm_cache_metadata *cmd = lookup_or_open(bdev, data_block_size, + may_format_device, policy_hint_size); + + if (!IS_ERR(cmd) && !same_params(cmd, data_block_size)) { + dm_cache_metadata_close(cmd); + return ERR_PTR(-EINVAL); + } + + return cmd; +} + void dm_cache_metadata_close(struct dm_cache_metadata *cmd) { - __destroy_persistent_data_objects(cmd); - kfree(cmd); + if (atomic_dec_and_test(&cmd->ref_count)) { + mutex_lock(&table_lock); + list_del(&cmd->list); + mutex_unlock(&table_lock); + + __destroy_persistent_data_objects(cmd); + kfree(cmd); + } } /* diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 735e939a846d..c10dec0f6e9d 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -222,7 +222,13 @@ struct cache { struct list_head need_commit_migrations; sector_t migration_threshold; wait_queue_head_t migration_wait; - atomic_t nr_migrations; + atomic_t nr_allocated_migrations; + + /* + * The number of in flight migrations that are performing + * background io. eg, promotion, writeback. + */ + atomic_t nr_io_migrations; wait_queue_head_t quiescing_wait; atomic_t quiescing; @@ -259,7 +265,6 @@ struct cache { struct dm_deferred_set *all_io_ds; mempool_t *migration_pool; - struct dm_cache_migration *next_migration; struct dm_cache_policy *policy; unsigned policy_nr_args; @@ -350,10 +355,31 @@ static void free_prison_cell(struct cache *cache, struct dm_bio_prison_cell *cel dm_bio_prison_free_cell(cache->prison, cell); } +static struct dm_cache_migration *alloc_migration(struct cache *cache) +{ + struct dm_cache_migration *mg; + + mg = mempool_alloc(cache->migration_pool, GFP_NOWAIT); + if (mg) { + mg->cache = cache; + atomic_inc(&mg->cache->nr_allocated_migrations); + } + + return mg; +} + +static void free_migration(struct dm_cache_migration *mg) +{ + if (atomic_dec_and_test(&mg->cache->nr_allocated_migrations)) + wake_up(&mg->cache->migration_wait); + + mempool_free(mg, mg->cache->migration_pool); +} + static int prealloc_data_structs(struct cache *cache, struct prealloc *p) { if (!p->mg) { - p->mg = mempool_alloc(cache->migration_pool, GFP_NOWAIT); + p->mg = alloc_migration(cache); if (!p->mg) return -ENOMEM; } @@ -382,7 +408,7 @@ static void prealloc_free_structs(struct cache *cache, struct prealloc *p) free_prison_cell(cache, p->cell1); if (p->mg) - mempool_free(p->mg, cache->migration_pool); + free_migration(p->mg); } static struct dm_cache_migration *prealloc_get_migration(struct prealloc *p) @@ -812,24 +838,14 @@ static void remap_to_origin_then_cache(struct cache *cache, struct bio *bio, * Migration covers moving data from the origin device to the cache, or * vice versa. *--------------------------------------------------------------*/ -static void free_migration(struct dm_cache_migration *mg) +static void inc_io_migrations(struct cache *cache) { - mempool_free(mg, mg->cache->migration_pool); + atomic_inc(&cache->nr_io_migrations); } -static void inc_nr_migrations(struct cache *cache) +static void dec_io_migrations(struct cache *cache) { - atomic_inc(&cache->nr_migrations); -} - -static void dec_nr_migrations(struct cache *cache) -{ - atomic_dec(&cache->nr_migrations); - - /* - * Wake the worker in case we're suspending the target. - */ - wake_up(&cache->migration_wait); + atomic_dec(&cache->nr_io_migrations); } static void __cell_defer(struct cache *cache, struct dm_bio_prison_cell *cell, @@ -852,11 +868,10 @@ static void cell_defer(struct cache *cache, struct dm_bio_prison_cell *cell, wake_worker(cache); } -static void cleanup_migration(struct dm_cache_migration *mg) +static void free_io_migration(struct dm_cache_migration *mg) { - struct cache *cache = mg->cache; + dec_io_migrations(mg->cache); free_migration(mg); - dec_nr_migrations(cache); } static void migration_failure(struct dm_cache_migration *mg) @@ -881,7 +896,7 @@ static void migration_failure(struct dm_cache_migration *mg) cell_defer(cache, mg->new_ocell, true); } - cleanup_migration(mg); + free_io_migration(mg); } static void migration_success_pre_commit(struct dm_cache_migration *mg) @@ -890,9 +905,9 @@ static void migration_success_pre_commit(struct dm_cache_migration *mg) struct cache *cache = mg->cache; if (mg->writeback) { - cell_defer(cache, mg->old_ocell, false); clear_dirty(cache, mg->old_oblock, mg->cblock); - cleanup_migration(mg); + cell_defer(cache, mg->old_ocell, false); + free_io_migration(mg); return; } else if (mg->demote) { @@ -902,14 +917,14 @@ static void migration_success_pre_commit(struct dm_cache_migration *mg) mg->old_oblock); if (mg->promote) cell_defer(cache, mg->new_ocell, true); - cleanup_migration(mg); + free_io_migration(mg); return; } } else { if (dm_cache_insert_mapping(cache->cmd, mg->cblock, mg->new_oblock)) { DMWARN_LIMIT("promotion failed; couldn't update on disk metadata"); policy_remove_mapping(cache->policy, mg->new_oblock); - cleanup_migration(mg); + free_io_migration(mg); return; } } @@ -942,18 +957,22 @@ static void migration_success_post_commit(struct dm_cache_migration *mg) } else { if (mg->invalidate) policy_remove_mapping(cache->policy, mg->old_oblock); - cleanup_migration(mg); + free_io_migration(mg); } } else { - if (mg->requeue_holder) + if (mg->requeue_holder) { + clear_dirty(cache, mg->new_oblock, mg->cblock); cell_defer(cache, mg->new_ocell, true); - else { + } else { + /* + * The block was promoted via an overwrite, so it's dirty. + */ + set_dirty(cache, mg->new_oblock, mg->cblock); bio_endio(mg->new_ocell->holder, 0); cell_defer(cache, mg->new_ocell, false); } - clear_dirty(cache, mg->new_oblock, mg->cblock); - cleanup_migration(mg); + free_io_migration(mg); } } @@ -1060,7 +1079,8 @@ static void issue_copy(struct dm_cache_migration *mg) avoid = is_discarded_oblock(cache, mg->new_oblock); - if (!avoid && bio_writes_complete_block(cache, bio)) { + if (writeback_mode(&cache->features) && + !avoid && bio_writes_complete_block(cache, bio)) { issue_overwrite(mg, bio); return; } @@ -1164,7 +1184,7 @@ static void promote(struct cache *cache, struct prealloc *structs, mg->new_ocell = cell; mg->start_jiffies = jiffies; - inc_nr_migrations(cache); + inc_io_migrations(cache); quiesce_migration(mg); } @@ -1187,7 +1207,7 @@ static void writeback(struct cache *cache, struct prealloc *structs, mg->new_ocell = NULL; mg->start_jiffies = jiffies; - inc_nr_migrations(cache); + inc_io_migrations(cache); quiesce_migration(mg); } @@ -1213,7 +1233,7 @@ static void demote_then_promote(struct cache *cache, struct prealloc *structs, mg->new_ocell = new_ocell; mg->start_jiffies = jiffies; - inc_nr_migrations(cache); + inc_io_migrations(cache); quiesce_migration(mg); } @@ -1240,7 +1260,7 @@ static void invalidate(struct cache *cache, struct prealloc *structs, mg->new_ocell = NULL; mg->start_jiffies = jiffies; - inc_nr_migrations(cache); + inc_io_migrations(cache); quiesce_migration(mg); } @@ -1301,7 +1321,7 @@ static void process_discard_bio(struct cache *cache, struct bio *bio) static bool spare_migration_bandwidth(struct cache *cache) { - sector_t current_volume = (atomic_read(&cache->nr_migrations) + 1) * + sector_t current_volume = (atomic_read(&cache->nr_io_migrations) + 1) * cache->sectors_per_block; return current_volume < cache->migration_threshold; } @@ -1656,7 +1676,7 @@ static void stop_quiescing(struct cache *cache) static void wait_for_migrations(struct cache *cache) { - wait_event(cache->migration_wait, !atomic_read(&cache->nr_migrations)); + wait_event(cache->migration_wait, !atomic_read(&cache->nr_allocated_migrations)); } static void stop_worker(struct cache *cache) @@ -1767,9 +1787,6 @@ static void destroy(struct cache *cache) { unsigned i; - if (cache->next_migration) - mempool_free(cache->next_migration, cache->migration_pool); - if (cache->migration_pool) mempool_destroy(cache->migration_pool); @@ -2277,7 +2294,8 @@ static int cache_create(struct cache_args *ca, struct cache **result) INIT_LIST_HEAD(&cache->quiesced_migrations); INIT_LIST_HEAD(&cache->completed_migrations); INIT_LIST_HEAD(&cache->need_commit_migrations); - atomic_set(&cache->nr_migrations, 0); + atomic_set(&cache->nr_allocated_migrations, 0); + atomic_set(&cache->nr_io_migrations, 0); init_waitqueue_head(&cache->migration_wait); init_waitqueue_head(&cache->quiescing_wait); @@ -2337,8 +2355,6 @@ static int cache_create(struct cache_args *ca, struct cache **result) goto bad; } - cache->next_migration = NULL; - cache->need_tick_bio = true; cache->sized = false; cache->invalidate = false; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 53b213226c01..4a8d19d0a5a4 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -709,7 +709,7 @@ static int crypt_iv_tcw_whitening(struct crypt_config *cc, for (i = 0; i < ((1 << SECTOR_SHIFT) / 8); i++) crypto_xor(data + i * 8, buf, 8); out: - memset(buf, 0, sizeof(buf)); + memzero_explicit(buf, sizeof(buf)); return r; } @@ -1681,6 +1681,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) unsigned int key_size, opt_params; unsigned long long tmpll; int ret; + size_t iv_size_padding; struct dm_arg_set as; const char *opt_string; char dummy; @@ -1717,12 +1718,23 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) cc->dmreq_start = sizeof(struct ablkcipher_request); cc->dmreq_start += crypto_ablkcipher_reqsize(any_tfm(cc)); - cc->dmreq_start = ALIGN(cc->dmreq_start, crypto_tfm_ctx_alignment()); - cc->dmreq_start += crypto_ablkcipher_alignmask(any_tfm(cc)) & - ~(crypto_tfm_ctx_alignment() - 1); + cc->dmreq_start = ALIGN(cc->dmreq_start, __alignof__(struct dm_crypt_request)); + + if (crypto_ablkcipher_alignmask(any_tfm(cc)) < CRYPTO_MINALIGN) { + /* Allocate the padding exactly */ + iv_size_padding = -(cc->dmreq_start + sizeof(struct dm_crypt_request)) + & crypto_ablkcipher_alignmask(any_tfm(cc)); + } else { + /* + * If the cipher requires greater alignment than kmalloc + * alignment, we don't know the exact position of the + * initialization vector. We must assume worst case. + */ + iv_size_padding = crypto_ablkcipher_alignmask(any_tfm(cc)); + } cc->req_pool = mempool_create_kmalloc_pool(MIN_IOS, cc->dmreq_start + - sizeof(struct dm_crypt_request) + cc->iv_size); + sizeof(struct dm_crypt_request) + iv_size_padding + cc->iv_size); if (!cc->req_pool) { ti->error = "Cannot allocate crypt request mempool"; goto bad; diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index db404a0f7e2c..080e767250d3 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -291,6 +291,19 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where, struct request_queue *q = bdev_get_queue(where->bdev); unsigned short logical_block_size = queue_logical_block_size(q); sector_t num_sectors; + unsigned int uninitialized_var(special_cmd_max_sectors); + + /* + * Reject unsupported discard and write same requests. + */ + if (rw & REQ_DISCARD) + special_cmd_max_sectors = q->limits.max_discard_sectors; + else if (rw & REQ_WRITE_SAME) + special_cmd_max_sectors = q->limits.max_write_same_sectors; + if ((rw & (REQ_DISCARD | REQ_WRITE_SAME)) && special_cmd_max_sectors == 0) { + dec_count(io, region, -EOPNOTSUPP); + return; + } /* * where->count may be zero if rw holds a flush and we need to @@ -313,7 +326,7 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where, store_io_and_region_in_bio(bio, io, region); if (rw & REQ_DISCARD) { - num_sectors = min_t(sector_t, q->limits.max_discard_sectors, remaining); + num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining); bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT; remaining -= num_sectors; } else if (rw & REQ_WRITE_SAME) { @@ -322,7 +335,7 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where, */ dp->get_page(dp, &page, &len, &offset); bio_add_page(bio, page, logical_block_size, offset); - num_sectors = min_t(sector_t, q->limits.max_write_same_sectors, remaining); + num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining); bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT; offset = 0; diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c index 08d9a207259a..c69d0b787746 100644 --- a/drivers/md/dm-log-userspace-transfer.c +++ b/drivers/md/dm-log-userspace-transfer.c @@ -272,7 +272,7 @@ int dm_ulog_tfr_init(void) r = cn_add_callback(&ulog_cn_id, "dmlogusr", cn_ulog_callback); if (r) { - cn_del_callback(&ulog_cn_id); + kfree(prealloced_cn_msg); return r; } diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 4880b69e2e9e..59715389b3cf 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -785,8 +785,7 @@ struct dm_raid_superblock { __le32 layout; __le32 stripe_sectors; - __u8 pad[452]; /* Round struct to 512 bytes. */ - /* Always set to 0 when writing. */ + /* Remainder of a logical block is zero-filled when writing (see super_sync()). */ } __packed; static int read_disk_sb(struct md_rdev *rdev, int size) @@ -823,7 +822,7 @@ static void super_sync(struct mddev *mddev, struct md_rdev *rdev) test_bit(Faulty, &(rs->dev[i].rdev.flags))) failed_devices |= (1ULL << i); - memset(sb, 0, sizeof(*sb)); + memset(sb + 1, 0, rdev->sb_size - sizeof(*sb)); sb->magic = cpu_to_le32(DM_RAID_MAGIC); sb->features = cpu_to_le32(0); /* No features yet */ @@ -858,7 +857,11 @@ static int super_load(struct md_rdev *rdev, struct md_rdev *refdev) uint64_t events_sb, events_refsb; rdev->sb_start = 0; - rdev->sb_size = sizeof(*sb); + rdev->sb_size = bdev_logical_block_size(rdev->meta_bdev); + if (rdev->sb_size < sizeof(*sb) || rdev->sb_size > PAGE_SIZE) { + DMERR("superblock size of a logical block is no longer valid"); + return -EINVAL; + } ret = read_disk_sb(rdev, rdev->sb_size); if (ret) diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index 7dfdb5c746d6..089d62751f7f 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -604,6 +604,15 @@ static void write_callback(unsigned long error, void *context) return; } + /* + * If the bio is discard, return an error, but do not + * degrade the array. + */ + if (bio->bi_rw & REQ_DISCARD) { + bio_endio(bio, -EOPNOTSUPP); + return; + } + for (i = 0; i < ms->nr_mirrors; i++) if (test_bit(i, &error)) fail_mirror(ms->mirror + i, DM_RAID1_WRITE_ERROR); diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index ebddef5237e4..c356a10b9ba5 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -1440,8 +1440,6 @@ out: full_bio->bi_private = pe->full_bio_private; atomic_inc(&full_bio->bi_remaining); } - free_pending_exception(pe); - increment_pending_exceptions_done_count(); up_write(&s->lock); @@ -1458,6 +1456,8 @@ out: } retry_origin_bios(s, origin_bios); + + free_pending_exception(pe); } static void commit_callback(void *context, int success) diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 359af3a519b5..c1120eb96d86 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -916,6 +916,24 @@ static void schedule_zero(struct thin_c *tc, dm_block_t virt_block, } } +static void set_pool_mode(struct pool *pool, enum pool_mode new_mode); + +static void check_for_space(struct pool *pool) +{ + int r; + dm_block_t nr_free; + + if (get_pool_mode(pool) != PM_OUT_OF_DATA_SPACE) + return; + + r = dm_pool_get_free_block_count(pool->pmd, &nr_free); + if (r) + return; + + if (nr_free) + set_pool_mode(pool, PM_WRITE); +} + /* * A non-zero return indicates read_only or fail_io mode. * Many callers don't care about the return value. @@ -930,6 +948,8 @@ static int commit(struct pool *pool) r = dm_pool_commit_metadata(pool->pmd); if (r) metadata_operation_failed(pool, "dm_pool_commit_metadata", r); + else + check_for_space(pool); return r; } @@ -948,8 +968,6 @@ static void check_low_water_mark(struct pool *pool, dm_block_t free_blocks) } } -static void set_pool_mode(struct pool *pool, enum pool_mode new_mode); - static int alloc_data_block(struct thin_c *tc, dm_block_t *result) { int r; @@ -1592,7 +1610,7 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) pool->process_bio = process_bio_read_only; pool->process_discard = process_discard; pool->process_prepared_mapping = process_prepared_mapping; - pool->process_prepared_discard = process_prepared_discard_passdown; + pool->process_prepared_discard = process_prepared_discard; if (!pool->pf.error_if_no_space && no_space_timeout) queue_delayed_work(pool->wq, &pool->no_space_timeout, no_space_timeout); @@ -1704,6 +1722,14 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_SUBMITTED; } + /* + * We must hold the virtual cell before doing the lookup, otherwise + * there's a race with discard. + */ + build_virtual_key(tc->td, block, &key); + if (dm_bio_detain(tc->pool->prison, &key, bio, &cell1, &cell_result)) + return DM_MAPIO_SUBMITTED; + r = dm_thin_find_block(td, block, 0, &result); /* @@ -1727,13 +1753,10 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) * shared flag will be set in their case. */ thin_defer_bio(tc, bio); + cell_defer_no_holder_no_free(tc, &cell1); return DM_MAPIO_SUBMITTED; } - build_virtual_key(tc->td, block, &key); - if (dm_bio_detain(tc->pool->prison, &key, bio, &cell1, &cell_result)) - return DM_MAPIO_SUBMITTED; - build_data_key(tc->td, result.block, &key); if (dm_bio_detain(tc->pool->prison, &key, bio, &cell2, &cell_result)) { cell_defer_no_holder_no_free(tc, &cell1); @@ -1754,6 +1777,7 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) * of doing so. */ handle_unserviceable_bio(tc->pool, bio); + cell_defer_no_holder_no_free(tc, &cell1); return DM_MAPIO_SUBMITTED; } /* fall through */ @@ -1764,6 +1788,7 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) * provide the hint to load the metadata into cache. */ thin_defer_bio(tc, bio); + cell_defer_no_holder_no_free(tc, &cell1); return DM_MAPIO_SUBMITTED; default: @@ -1773,6 +1798,7 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) * pool is switched to fail-io mode. */ bio_io_error(bio); + cell_defer_no_holder_no_free(tc, &cell1); return DM_MAPIO_SUBMITTED; } } @@ -2718,6 +2744,12 @@ static int pool_message(struct dm_target *ti, unsigned argc, char **argv) struct pool_c *pt = ti->private; struct pool *pool = pt->pool; + if (get_pool_mode(pool) >= PM_READ_ONLY) { + DMERR("%s: unable to service pool target messages in READ_ONLY or FAIL mode", + dm_device_name(pool->pool_md)); + return -EINVAL; + } + if (!strcasecmp(argv[0], "create_thin")) r = process_create_thin_mesg(argc, argv, pool); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 65ee3a0d4683..e40059143272 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2288,7 +2288,7 @@ int dm_setup_md_queue(struct mapped_device *md) return 0; } -static struct mapped_device *dm_find_md(dev_t dev) +struct mapped_device *dm_get_md(dev_t dev) { struct mapped_device *md; unsigned minor = MINOR(dev); @@ -2299,12 +2299,15 @@ static struct mapped_device *dm_find_md(dev_t dev) spin_lock(&_minor_lock); md = idr_find(&_minor_idr, minor); - if (md && (md == MINOR_ALLOCED || - (MINOR(disk_devt(dm_disk(md))) != minor) || - dm_deleting_md(md) || - test_bit(DMF_FREEING, &md->flags))) { - md = NULL; - goto out; + if (md) { + if ((md == MINOR_ALLOCED || + (MINOR(disk_devt(dm_disk(md))) != minor) || + dm_deleting_md(md) || + test_bit(DMF_FREEING, &md->flags))) { + md = NULL; + goto out; + } + dm_get(md); } out: @@ -2312,16 +2315,6 @@ out: return md; } - -struct mapped_device *dm_get_md(dev_t dev) -{ - struct mapped_device *md = dm_find_md(dev); - - if (md) - dm_get(md); - - return md; -} EXPORT_SYMBOL_GPL(dm_get_md); void *dm_get_mdptr(struct mapped_device *md) @@ -2359,10 +2352,16 @@ static void __dm_destroy(struct mapped_device *md, bool wait) set_bit(DMF_FREEING, &md->flags); spin_unlock(&_minor_lock); + /* + * Take suspend_lock so that presuspend and postsuspend methods + * do not race with internal suspend. + */ + mutex_lock(&md->suspend_lock); if (!dm_suspended_md(md)) { dm_table_presuspend_targets(map); dm_table_postsuspend_targets(map); } + mutex_unlock(&md->suspend_lock); /* dm_put_live_table must be before msleep, otherwise deadlock is possible */ dm_put_live_table(md, srcu_idx); diff --git a/drivers/md/md.c b/drivers/md/md.c index 73aedcb639c0..40959ee73583 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5333,6 +5333,7 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev) printk("md: %s still in use.\n",mdname(mddev)); if (did_freeze) { clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); } err = -EBUSY; @@ -5347,6 +5348,8 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev) mddev->ro = 1; set_disk_ro(mddev->gendisk, 1); clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + md_wakeup_thread(mddev->thread); sysfs_notify_dirent_safe(mddev->sysfs_state); err = 0; } @@ -5390,6 +5393,7 @@ static int do_md_stop(struct mddev * mddev, int mode, mutex_unlock(&mddev->open_mutex); if (did_freeze) { clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); } return -EBUSY; diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h index 37d367bb9aa8..bf2b80d5c470 100644 --- a/drivers/md/persistent-data/dm-btree-internal.h +++ b/drivers/md/persistent-data/dm-btree-internal.h @@ -42,6 +42,12 @@ struct btree_node { } __packed; +/* + * Locks a block using the btree node validator. + */ +int bn_read_lock(struct dm_btree_info *info, dm_block_t b, + struct dm_block **result); + void inc_children(struct dm_transaction_manager *tm, struct btree_node *n, struct dm_btree_value_type *vt); diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c index cf9fd676ae44..1b5e13ec7f96 100644 --- a/drivers/md/persistent-data/dm-btree-spine.c +++ b/drivers/md/persistent-data/dm-btree-spine.c @@ -92,7 +92,7 @@ struct dm_block_validator btree_node_validator = { /*----------------------------------------------------------------*/ -static int bn_read_lock(struct dm_btree_info *info, dm_block_t b, +int bn_read_lock(struct dm_btree_info *info, dm_block_t b, struct dm_block **result) { return dm_tm_read_lock(info->tm, b, &btree_node_validator, result); diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c index 416060c25709..200ac12a1d40 100644 --- a/drivers/md/persistent-data/dm-btree.c +++ b/drivers/md/persistent-data/dm-btree.c @@ -847,22 +847,26 @@ EXPORT_SYMBOL_GPL(dm_btree_find_lowest_key); * FIXME: We shouldn't use a recursive algorithm when we have limited stack * space. Also this only works for single level trees. */ -static int walk_node(struct ro_spine *s, dm_block_t block, +static int walk_node(struct dm_btree_info *info, dm_block_t block, int (*fn)(void *context, uint64_t *keys, void *leaf), void *context) { int r; unsigned i, nr; + struct dm_block *node; struct btree_node *n; uint64_t keys; - r = ro_step(s, block); - n = ro_node(s); + r = bn_read_lock(info, block, &node); + if (r) + return r; + + n = dm_block_data(node); nr = le32_to_cpu(n->header.nr_entries); for (i = 0; i < nr; i++) { if (le32_to_cpu(n->header.flags) & INTERNAL_NODE) { - r = walk_node(s, value64(n, i), fn, context); + r = walk_node(info, value64(n, i), fn, context); if (r) goto out; } else { @@ -874,7 +878,7 @@ static int walk_node(struct ro_spine *s, dm_block_t block, } out: - ro_pop(s); + dm_tm_unlock(info->tm, node); return r; } @@ -882,15 +886,7 @@ int dm_btree_walk(struct dm_btree_info *info, dm_block_t root, int (*fn)(void *context, uint64_t *keys, void *leaf), void *context) { - int r; - struct ro_spine spine; - BUG_ON(info->levels > 1); - - init_ro_spine(&spine, info); - r = walk_node(&spine, root, fn, context); - exit_ro_spine(&spine); - - return r; + return walk_node(info, root, fn, context); } EXPORT_SYMBOL_GPL(dm_btree_walk); diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c index 786b689bdfc7..f4e22bcc7fb8 100644 --- a/drivers/md/persistent-data/dm-space-map-metadata.c +++ b/drivers/md/persistent-data/dm-space-map-metadata.c @@ -564,7 +564,9 @@ static int sm_bootstrap_get_nr_blocks(struct dm_space_map *sm, dm_block_t *count { struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); - return smm->ll.nr_blocks; + *count = smm->ll.nr_blocks; + + return 0; } static int sm_bootstrap_get_nr_free(struct dm_space_map *sm, dm_block_t *count) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index d7690f86fdb9..b96ee9d78aa3 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -540,11 +540,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect has_nonrot_disk = 0; choose_next_idle = 0; - if (conf->mddev->recovery_cp < MaxSector && - (this_sector + sectors >= conf->next_resync)) - choose_first = 1; - else - choose_first = 0; + choose_first = (conf->mddev->recovery_cp < this_sector + sectors); for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) { sector_t dist; @@ -565,7 +561,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect if (test_bit(WriteMostly, &rdev->flags)) { /* Don't balance among write-mostly, just * use the first as a last resort */ - if (best_disk < 0) { + if (best_dist_disk < 0) { if (is_badblock(rdev, this_sector, sectors, &first_bad, &bad_sectors)) { if (first_bad < this_sector) @@ -574,7 +570,8 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect best_good_sectors = first_bad - this_sector; } else best_good_sectors = sectors; - best_disk = disk; + best_dist_disk = disk; + best_pending_disk = disk; } continue; } @@ -831,7 +828,7 @@ static void flush_pending_writes(struct r1conf *conf) * there is no normal IO happeing. It must arrange to call * lower_barrier when the particular background IO completes. */ -static void raise_barrier(struct r1conf *conf) +static void raise_barrier(struct r1conf *conf, sector_t sector_nr) { spin_lock_irq(&conf->resync_lock); @@ -841,6 +838,7 @@ static void raise_barrier(struct r1conf *conf) /* block any new IO from starting */ conf->barrier++; + conf->next_resync = sector_nr; /* For these conditions we must wait: * A: while the array is in frozen state @@ -849,14 +847,17 @@ static void raise_barrier(struct r1conf *conf) * C: next_resync + RESYNC_SECTORS > start_next_window, meaning * next resync will reach to the window which normal bios are * handling. + * D: while there are any active requests in the current window. */ wait_event_lock_irq(conf->wait_barrier, !conf->array_frozen && conf->barrier < RESYNC_DEPTH && + conf->current_window_requests == 0 && (conf->start_next_window >= conf->next_resync + RESYNC_SECTORS), conf->resync_lock); + conf->nr_pending++; spin_unlock_irq(&conf->resync_lock); } @@ -866,6 +867,7 @@ static void lower_barrier(struct r1conf *conf) BUG_ON(conf->barrier <= 0); spin_lock_irqsave(&conf->resync_lock, flags); conf->barrier--; + conf->nr_pending--; spin_unlock_irqrestore(&conf->resync_lock, flags); wake_up(&conf->wait_barrier); } @@ -877,12 +879,10 @@ static bool need_to_wait_for_sync(struct r1conf *conf, struct bio *bio) if (conf->array_frozen || !bio) wait = true; else if (conf->barrier && bio_data_dir(bio) == WRITE) { - if (conf->next_resync < RESYNC_WINDOW_SECTORS) - wait = true; - else if ((conf->next_resync - RESYNC_WINDOW_SECTORS - >= bio_end_sector(bio)) || - (conf->next_resync + NEXT_NORMALIO_DISTANCE - <= bio->bi_iter.bi_sector)) + if ((conf->mddev->curr_resync_completed + >= bio_end_sector(bio)) || + (conf->next_resync + NEXT_NORMALIO_DISTANCE + <= bio->bi_iter.bi_sector)) wait = false; else wait = true; @@ -919,8 +919,8 @@ static sector_t wait_barrier(struct r1conf *conf, struct bio *bio) } if (bio && bio_data_dir(bio) == WRITE) { - if (conf->next_resync + NEXT_NORMALIO_DISTANCE - <= bio->bi_iter.bi_sector) { + if (bio->bi_iter.bi_sector >= + conf->mddev->curr_resync_completed) { if (conf->start_next_window == MaxSector) conf->start_next_window = conf->next_resync + @@ -1186,6 +1186,7 @@ read_again: atomic_read(&bitmap->behind_writes) == 0); } r1_bio->read_disk = rdisk; + r1_bio->start_next_window = 0; read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev); bio_trim(read_bio, r1_bio->sector - bio->bi_iter.bi_sector, @@ -1548,8 +1549,13 @@ static void close_sync(struct r1conf *conf) mempool_destroy(conf->r1buf_pool); conf->r1buf_pool = NULL; + spin_lock_irq(&conf->resync_lock); conf->next_resync = 0; conf->start_next_window = MaxSector; + conf->current_window_requests += + conf->next_window_requests; + conf->next_window_requests = 0; + spin_unlock_irq(&conf->resync_lock); } static int raid1_spare_active(struct mddev *mddev) @@ -2150,7 +2156,7 @@ static void fix_read_error(struct r1conf *conf, int read_disk, d--; rdev = conf->mirrors[d].rdev; if (rdev && - test_bit(In_sync, &rdev->flags)) + !test_bit(Faulty, &rdev->flags)) r1_sync_page_io(rdev, sect, s, conf->tmppage, WRITE); } @@ -2162,7 +2168,7 @@ static void fix_read_error(struct r1conf *conf, int read_disk, d--; rdev = conf->mirrors[d].rdev; if (rdev && - test_bit(In_sync, &rdev->flags)) { + !test_bit(Faulty, &rdev->flags)) { if (r1_sync_page_io(rdev, sect, s, conf->tmppage, READ)) { atomic_add(s, &rdev->corrected_errors); @@ -2541,9 +2547,8 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp bitmap_cond_end_sync(mddev->bitmap, sector_nr); r1_bio = mempool_alloc(conf->r1buf_pool, GFP_NOIO); - raise_barrier(conf); - conf->next_resync = sector_nr; + raise_barrier(conf, sector_nr); rcu_read_lock(); /* diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 18cda77b4f79..3545fafe2027 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -64,6 +64,10 @@ #define cpu_to_group(cpu) cpu_to_node(cpu) #define ANY_GROUP NUMA_NO_NODE +static bool devices_handle_discard_safely = false; +module_param(devices_handle_discard_safely, bool, 0644); +MODULE_PARM_DESC(devices_handle_discard_safely, + "Set to Y if all devices in each array reliably return zeroes on reads from discarded regions"); static struct workqueue_struct *raid5_wq; /* * Stripe cache @@ -2892,7 +2896,8 @@ static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s, (s->failed >= 2 && fdev[1]->toread) || (sh->raid_conf->level <= 5 && s->failed && fdev[0]->towrite && !test_bit(R5_OVERWRITE, &fdev[0]->flags)) || - (sh->raid_conf->level == 6 && s->failed && s->to_write))) { + ((sh->raid_conf->level == 6 || sh->sector >= sh->raid_conf->mddev->recovery_cp) + && s->failed && s->to_write))) { /* we would like to get this block, possibly by computing it, * otherwise read it if the backing disk is insync */ @@ -3066,7 +3071,8 @@ static void handle_stripe_dirtying(struct r5conf *conf, * generate correct data from the parity. */ if (conf->max_degraded == 2 || - (recovery_cp < MaxSector && sh->sector >= recovery_cp)) { + (recovery_cp < MaxSector && sh->sector >= recovery_cp && + s->failed == 0)) { /* Calculate the real rcw later - for now make it * look like rcw is cheaper */ @@ -6117,7 +6123,7 @@ static int run(struct mddev *mddev) mddev->queue->limits.discard_granularity = stripe; /* * unaligned part of discard request will be ignored, so can't - * guarantee discard_zerors_data + * guarantee discard_zeroes_data */ mddev->queue->limits.discard_zeroes_data = 0; @@ -6142,6 +6148,18 @@ static int run(struct mddev *mddev) !bdev_get_queue(rdev->bdev)-> limits.discard_zeroes_data) discard_supported = false; + /* Unfortunately, discard_zeroes_data is not currently + * a guarantee - just a hint. So we only allow DISCARD + * if the sysadmin has confirmed that only safe devices + * are in use by setting a module parameter. + */ + if (!devices_handle_discard_safely) { + if (discard_supported) { + pr_info("md/raid456: discard support disabled due to uncertainty.\n"); + pr_info("Set raid456.devices_handle_discard_safely=Y to override.\n"); + } + discard_supported = false; + } } if (discard_supported && diff --git a/drivers/media/dvb-core/dvb-usb-ids.h b/drivers/media/dvb-core/dvb-usb-ids.h index 80643ef9183f..fabe2fce9bc5 100644 --- a/drivers/media/dvb-core/dvb-usb-ids.h +++ b/drivers/media/dvb-core/dvb-usb-ids.h @@ -279,6 +279,8 @@ #define USB_PID_PCTV_400E 0x020f #define USB_PID_PCTV_450E 0x0222 #define USB_PID_PCTV_452E 0x021f +#define USB_PID_PCTV_78E 0x025a +#define USB_PID_PCTV_79E 0x0262 #define USB_PID_REALTEK_RTL2831U 0x2831 #define USB_PID_REALTEK_RTL2832U 0x2832 #define USB_PID_TECHNOTREND_CONNECT_S2_3600 0x3007 diff --git a/drivers/media/dvb-frontends/ds3000.c b/drivers/media/dvb-frontends/ds3000.c index 1e344b033277..22e8c2032f6d 100644 --- a/drivers/media/dvb-frontends/ds3000.c +++ b/drivers/media/dvb-frontends/ds3000.c @@ -864,6 +864,13 @@ struct dvb_frontend *ds3000_attach(const struct ds3000_config *config, memcpy(&state->frontend.ops, &ds3000_ops, sizeof(struct dvb_frontend_ops)); state->frontend.demodulator_priv = state; + + /* + * Some devices like T480 starts with voltage on. Be sure + * to turn voltage off during init, as this can otherwise + * interfere with Unicable SCR systems. + */ + ds3000_set_voltage(&state->frontend, SEC_VOLTAGE_OFF); return &state->frontend; error3: diff --git a/drivers/media/i2c/adv7604.c b/drivers/media/i2c/adv7604.c index 71c8570bd9ea..112394d138c9 100644 --- a/drivers/media/i2c/adv7604.c +++ b/drivers/media/i2c/adv7604.c @@ -1984,7 +1984,7 @@ static int adv7604_log_status(struct v4l2_subdev *sd) v4l2_info(sd, "HDCP keys read: %s%s\n", (hdmi_read(sd, 0x04) & 0x20) ? "yes" : "no", (hdmi_read(sd, 0x04) & 0x10) ? "ERROR" : ""); - if (!is_hdmi(sd)) { + if (is_hdmi(sd)) { bool audio_pll_locked = hdmi_read(sd, 0x04) & 0x01; bool audio_sample_packet_detect = hdmi_read(sd, 0x18) & 0x01; bool audio_mute = io_read(sd, 0x65) & 0x40; diff --git a/drivers/media/i2c/smiapp-pll.c b/drivers/media/i2c/smiapp-pll.c index 2335529b195c..ab5d9a3adebf 100644 --- a/drivers/media/i2c/smiapp-pll.c +++ b/drivers/media/i2c/smiapp-pll.c @@ -67,7 +67,7 @@ static void print_pll(struct device *dev, struct smiapp_pll *pll) { dev_dbg(dev, "pre_pll_clk_div\t%d\n", pll->pre_pll_clk_div); dev_dbg(dev, "pll_multiplier \t%d\n", pll->pll_multiplier); - if (pll->flags != SMIAPP_PLL_FLAG_NO_OP_CLOCKS) { + if (!(pll->flags & SMIAPP_PLL_FLAG_NO_OP_CLOCKS)) { dev_dbg(dev, "op_sys_clk_div \t%d\n", pll->op_sys_clk_div); dev_dbg(dev, "op_pix_clk_div \t%d\n", pll->op_pix_clk_div); } @@ -77,7 +77,7 @@ static void print_pll(struct device *dev, struct smiapp_pll *pll) dev_dbg(dev, "ext_clk_freq_hz \t%d\n", pll->ext_clk_freq_hz); dev_dbg(dev, "pll_ip_clk_freq_hz \t%d\n", pll->pll_ip_clk_freq_hz); dev_dbg(dev, "pll_op_clk_freq_hz \t%d\n", pll->pll_op_clk_freq_hz); - if (pll->flags & SMIAPP_PLL_FLAG_NO_OP_CLOCKS) { + if (!(pll->flags & SMIAPP_PLL_FLAG_NO_OP_CLOCKS)) { dev_dbg(dev, "op_sys_clk_freq_hz \t%d\n", pll->op_sys_clk_freq_hz); dev_dbg(dev, "op_pix_clk_freq_hz \t%d\n", diff --git a/drivers/media/i2c/smiapp/smiapp-core.c b/drivers/media/i2c/smiapp/smiapp-core.c index 8741cae9c9f2..873d0627a75b 100644 --- a/drivers/media/i2c/smiapp/smiapp-core.c +++ b/drivers/media/i2c/smiapp/smiapp-core.c @@ -2138,7 +2138,7 @@ static int smiapp_set_selection(struct v4l2_subdev *subdev, ret = smiapp_set_compose(subdev, fh, sel); break; default: - BUG(); + ret = -EINVAL; } mutex_unlock(&sensor->mutex); @@ -2624,7 +2624,9 @@ static int smiapp_registered(struct v4l2_subdev *subdev) pll->flags |= SMIAPP_PLL_FLAG_OP_PIX_CLOCK_PER_LANE; pll->scale_n = sensor->limits[SMIAPP_LIMIT_SCALER_N_MIN]; + mutex_lock(&sensor->mutex); rval = smiapp_update_mode(sensor); + mutex_unlock(&sensor->mutex); if (rval) { dev_err(&client->dev, "update mode failed\n"); goto out_nvm_release; diff --git a/drivers/media/i2c/tda7432.c b/drivers/media/i2c/tda7432.c index 72af644fa051..cf93021a6500 100644 --- a/drivers/media/i2c/tda7432.c +++ b/drivers/media/i2c/tda7432.c @@ -293,7 +293,7 @@ static int tda7432_s_ctrl(struct v4l2_ctrl *ctrl) if (t->mute->val) { lf |= TDA7432_MUTE; lr |= TDA7432_MUTE; - lf |= TDA7432_MUTE; + rf |= TDA7432_MUTE; rr |= TDA7432_MUTE; } /* Mute & update balance*/ diff --git a/drivers/media/pci/cx18/cx18-driver.c b/drivers/media/pci/cx18/cx18-driver.c index 716bdc57fac6..83f5074706f9 100644 --- a/drivers/media/pci/cx18/cx18-driver.c +++ b/drivers/media/pci/cx18/cx18-driver.c @@ -1091,6 +1091,7 @@ static int cx18_probe(struct pci_dev *pci_dev, setup.addr = ADDR_UNSET; setup.type = cx->options.tuner; setup.mode_mask = T_ANALOG_TV; /* matches TV tuners */ + setup.config = NULL; if (cx->options.radio > 0) setup.mode_mask |= T_RADIO; setup.tuner_callback = (setup.type == TUNER_XC2028) ? diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_common.h b/drivers/media/platform/s5p-mfc/s5p_mfc_common.h index f723f1f2f578..ab851278d9d0 100644 --- a/drivers/media/platform/s5p-mfc/s5p_mfc_common.h +++ b/drivers/media/platform/s5p-mfc/s5p_mfc_common.h @@ -30,7 +30,7 @@ /* Offset base used to differentiate between CAPTURE and OUTPUT * while mmaping */ -#define DST_QUEUE_OFF_BASE (TASK_SIZE / 2) +#define DST_QUEUE_OFF_BASE (1 << 30) #define MFC_BANK1_ALLOC_CTX 0 #define MFC_BANK2_ALLOC_CTX 1 diff --git a/drivers/media/platform/sh_veu.c b/drivers/media/platform/sh_veu.c index 744e43b480bc..f698e322a1cd 100644 --- a/drivers/media/platform/sh_veu.c +++ b/drivers/media/platform/sh_veu.c @@ -1183,6 +1183,7 @@ static int sh_veu_probe(struct platform_device *pdev) } *vdev = sh_veu_videodev; + vdev->v4l2_dev = &veu->v4l2_dev; spin_lock_init(&veu->lock); mutex_init(&veu->fop_lock); vdev->lock = &veu->fop_lock; diff --git a/drivers/media/rc/ir-lirc-codec.c b/drivers/media/rc/ir-lirc-codec.c index ed2c8a1ed8ca..98893a8332c7 100644 --- a/drivers/media/rc/ir-lirc-codec.c +++ b/drivers/media/rc/ir-lirc-codec.c @@ -42,11 +42,17 @@ static int ir_lirc_decode(struct rc_dev *dev, struct ir_raw_event ev) return -EINVAL; /* Packet start */ - if (ev.reset) - return 0; + if (ev.reset) { + /* Userspace expects a long space event before the start of + * the signal to use as a sync. This may be done with repeat + * packets and normal samples. But if a reset has been sent + * then we assume that a long time has passed, so we send a + * space with the maximum time value. */ + sample = LIRC_SPACE(LIRC_VALUE_MASK); + IR_dprintk(2, "delivering reset sync space to lirc_dev\n"); /* Carrier reports */ - if (ev.carrier_report) { + } else if (ev.carrier_report) { sample = LIRC_FREQUENCY(ev.carrier); IR_dprintk(2, "carrier report (freq: %d)\n", sample); diff --git a/drivers/media/tuners/m88ts2022.c b/drivers/media/tuners/m88ts2022.c index 40c42dec721b..7a62097aa9ea 100644 --- a/drivers/media/tuners/m88ts2022.c +++ b/drivers/media/tuners/m88ts2022.c @@ -314,7 +314,7 @@ static int m88ts2022_set_params(struct dvb_frontend *fe) div_min = gdiv28 * 78 / 100; div_max = clamp_val(div_max, 0U, 63U); - f_3db_hz = c->symbol_rate * 135UL / 200UL; + f_3db_hz = mult_frac(c->symbol_rate, 135, 200); f_3db_hz += 2000000U + (frequency_offset_khz * 1000U); f_3db_hz = clamp(f_3db_hz, 7000000U, 40000000U); diff --git a/drivers/media/usb/au0828/au0828-cards.c b/drivers/media/usb/au0828/au0828-cards.c index dd32decb237d..1d4b11038958 100644 --- a/drivers/media/usb/au0828/au0828-cards.c +++ b/drivers/media/usb/au0828/au0828-cards.c @@ -36,6 +36,11 @@ static void hvr950q_cs5340_audio(void *priv, int enable) au0828_clear(dev, REG_000, 0x10); } +/* + * WARNING: There's a quirks table at sound/usb/quirks-table.h + * that should also be updated every time a new device with V4L2 support + * is added here. + */ struct au0828_board au0828_boards[] = { [AU0828_BOARD_UNKNOWN] = { .name = "Unknown board", diff --git a/drivers/media/usb/dvb-usb-v2/af9035.c b/drivers/media/usb/dvb-usb-v2/af9035.c index 8ede8ea762e6..88228f735342 100644 --- a/drivers/media/usb/dvb-usb-v2/af9035.c +++ b/drivers/media/usb/dvb-usb-v2/af9035.c @@ -1541,6 +1541,10 @@ static const struct usb_device_id af9035_id_table[] = { &af9035_props, "Leadtek WinFast DTV Dongle Dual", NULL) }, { DVB_USB_DEVICE(USB_VID_HAUPPAUGE, 0xf900, &af9035_props, "Hauppauge WinTV-MiniStick 2", NULL) }, + { DVB_USB_DEVICE(USB_VID_PCTV, USB_PID_PCTV_78E, + &af9035_props, "PCTV 78e", RC_MAP_IT913X_V1) }, + { DVB_USB_DEVICE(USB_VID_PCTV, USB_PID_PCTV_79E, + &af9035_props, "PCTV 79e", RC_MAP_IT913X_V2) }, { } }; MODULE_DEVICE_TABLE(usb, af9035_id_table); diff --git a/drivers/media/usb/dvb-usb-v2/lmedm04.c b/drivers/media/usb/dvb-usb-v2/lmedm04.c index f674dc024d06..d2a4e6d40bf0 100644 --- a/drivers/media/usb/dvb-usb-v2/lmedm04.c +++ b/drivers/media/usb/dvb-usb-v2/lmedm04.c @@ -350,6 +350,7 @@ static int lme2510_int_read(struct dvb_usb_adapter *adap) { struct dvb_usb_device *d = adap_to_d(adap); struct lme2510_state *lme_int = adap_to_priv(adap); + struct usb_host_endpoint *ep; lme_int->lme_urb = usb_alloc_urb(0, GFP_ATOMIC); @@ -371,6 +372,12 @@ static int lme2510_int_read(struct dvb_usb_adapter *adap) adap, 8); + /* Quirk of pipe reporting PIPE_BULK but behaves as interrupt */ + ep = usb_pipe_endpoint(d->udev, lme_int->lme_urb->pipe); + + if (usb_endpoint_type(&ep->desc) == USB_ENDPOINT_XFER_BULK) + lme_int->lme_urb->pipe = usb_rcvbulkpipe(d->udev, 0xa), + lme_int->lme_urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; usb_submit_urb(lme_int->lme_urb, GFP_ATOMIC); diff --git a/drivers/media/usb/dvb-usb/af9005.c b/drivers/media/usb/dvb-usb/af9005.c index af176b6ce738..e6d3561eea47 100644 --- a/drivers/media/usb/dvb-usb/af9005.c +++ b/drivers/media/usb/dvb-usb/af9005.c @@ -1081,9 +1081,12 @@ static int __init af9005_usb_module_init(void) err("usb_register failed. (%d)", result); return result; } +#if IS_MODULE(CONFIG_DVB_USB_AF9005) || defined(CONFIG_DVB_USB_AF9005_REMOTE) + /* FIXME: convert to todays kernel IR infrastructure */ rc_decode = symbol_request(af9005_rc_decode); rc_keys = symbol_request(rc_map_af9005_table); rc_keys_size = symbol_request(rc_map_af9005_table_size); +#endif if (rc_decode == NULL || rc_keys == NULL || rc_keys_size == NULL) { err("af9005_rc_decode function not found, disabling remote"); af9005_properties.rc.legacy.rc_query = NULL; diff --git a/drivers/media/usb/em28xx/em28xx-audio.c b/drivers/media/usb/em28xx/em28xx-audio.c index dfdfa772eb1e..c39f7d329ee2 100644 --- a/drivers/media/usb/em28xx/em28xx-audio.c +++ b/drivers/media/usb/em28xx/em28xx-audio.c @@ -814,7 +814,7 @@ static int em28xx_audio_urb_init(struct em28xx *dev) if (urb_size > ep_size * npackets) npackets = DIV_ROUND_UP(urb_size, ep_size); - em28xx_info("Number of URBs: %d, with %d packets and %d size", + em28xx_info("Number of URBs: %d, with %d packets and %d size\n", num_urb, npackets, urb_size); /* Estimate the bytes per period */ @@ -974,7 +974,7 @@ static int em28xx_audio_fini(struct em28xx *dev) return 0; } - em28xx_info("Closing audio extension"); + em28xx_info("Closing audio extension\n"); if (dev->adev.sndcard) { snd_card_disconnect(dev->adev.sndcard); diff --git a/drivers/media/usb/em28xx/em28xx-cards.c b/drivers/media/usb/em28xx/em28xx-cards.c index 4d97a76cc3b0..c1a3f8f95750 100644 --- a/drivers/media/usb/em28xx/em28xx-cards.c +++ b/drivers/media/usb/em28xx/em28xx-cards.c @@ -2993,16 +2993,6 @@ static int em28xx_init_dev(struct em28xx *dev, struct usb_device *udev, } } - if (dev->chip_id == CHIP_ID_EM2870 || - dev->chip_id == CHIP_ID_EM2874 || - dev->chip_id == CHIP_ID_EM28174 || - dev->chip_id == CHIP_ID_EM28178) { - /* Digital only device - don't load any alsa module */ - dev->audio_mode.has_audio = false; - dev->has_audio_class = false; - dev->has_alsa_audio = false; - } - if (chip_name != default_chip_name) printk(KERN_INFO DRIVER_NAME ": chip ID is %s\n", chip_name); @@ -3272,7 +3262,6 @@ static int em28xx_usb_probe(struct usb_interface *interface, dev->alt = -1; dev->is_audio_only = has_audio && !(has_video || has_dvb); dev->has_alsa_audio = has_audio; - dev->audio_mode.has_audio = has_audio; dev->has_video = has_video; dev->ifnum = ifnum; diff --git a/drivers/media/usb/em28xx/em28xx-core.c b/drivers/media/usb/em28xx/em28xx-core.c index 898fb9bd88a2..97fd881a4e7b 100644 --- a/drivers/media/usb/em28xx/em28xx-core.c +++ b/drivers/media/usb/em28xx/em28xx-core.c @@ -506,8 +506,18 @@ int em28xx_audio_setup(struct em28xx *dev) int vid1, vid2, feat, cfg; u32 vid; - if (!dev->audio_mode.has_audio) + if (dev->chip_id == CHIP_ID_EM2870 || + dev->chip_id == CHIP_ID_EM2874 || + dev->chip_id == CHIP_ID_EM28174 || + dev->chip_id == CHIP_ID_EM28178) { + /* Digital only device - don't load any alsa module */ + dev->audio_mode.has_audio = false; + dev->has_audio_class = false; + dev->has_alsa_audio = false; return 0; + } + + dev->audio_mode.has_audio = true; /* See how this device is configured */ cfg = em28xx_read_reg(dev, EM28XX_R00_CHIPCFG); diff --git a/drivers/media/usb/em28xx/em28xx-dvb.c b/drivers/media/usb/em28xx/em28xx-dvb.c index 1373cfa4e974..ec2ebe9b89fb 100644 --- a/drivers/media/usb/em28xx/em28xx-dvb.c +++ b/drivers/media/usb/em28xx/em28xx-dvb.c @@ -1468,7 +1468,7 @@ static int em28xx_dvb_fini(struct em28xx *dev) return 0; } - em28xx_info("Closing DVB extension"); + em28xx_info("Closing DVB extension\n"); if (dev->dvb) { struct em28xx_dvb *dvb = dev->dvb; diff --git a/drivers/media/usb/em28xx/em28xx-input.c b/drivers/media/usb/em28xx/em28xx-input.c index 18f65d89d4bc..dd59c005cbcc 100644 --- a/drivers/media/usb/em28xx/em28xx-input.c +++ b/drivers/media/usb/em28xx/em28xx-input.c @@ -810,7 +810,7 @@ static int em28xx_ir_fini(struct em28xx *dev) return 0; } - em28xx_info("Closing input extension"); + em28xx_info("Closing input extension\n"); em28xx_shutdown_buttons(dev); diff --git a/drivers/media/usb/em28xx/em28xx-video.c b/drivers/media/usb/em28xx/em28xx-video.c index c3c928937dcd..0e8d0856b89a 100644 --- a/drivers/media/usb/em28xx/em28xx-video.c +++ b/drivers/media/usb/em28xx/em28xx-video.c @@ -953,13 +953,16 @@ static int em28xx_stop_streaming(struct vb2_queue *vq) } spin_lock_irqsave(&dev->slock, flags); + if (dev->usb_ctl.vid_buf != NULL) { + vb2_buffer_done(&dev->usb_ctl.vid_buf->vb, VB2_BUF_STATE_ERROR); + dev->usb_ctl.vid_buf = NULL; + } while (!list_empty(&vidq->active)) { struct em28xx_buffer *buf; buf = list_entry(vidq->active.next, struct em28xx_buffer, list); list_del(&buf->list); vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR); } - dev->usb_ctl.vid_buf = NULL; spin_unlock_irqrestore(&dev->slock, flags); return 0; @@ -981,13 +984,16 @@ int em28xx_stop_vbi_streaming(struct vb2_queue *vq) } spin_lock_irqsave(&dev->slock, flags); + if (dev->usb_ctl.vbi_buf != NULL) { + vb2_buffer_done(&dev->usb_ctl.vbi_buf->vb, VB2_BUF_STATE_ERROR); + dev->usb_ctl.vbi_buf = NULL; + } while (!list_empty(&vbiq->active)) { struct em28xx_buffer *buf; buf = list_entry(vbiq->active.next, struct em28xx_buffer, list); list_del(&buf->list); vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR); } - dev->usb_ctl.vbi_buf = NULL; spin_unlock_irqrestore(&dev->slock, flags); return 0; @@ -1894,7 +1900,7 @@ static int em28xx_v4l2_fini(struct em28xx *dev) return 0; } - em28xx_info("Closing video extension"); + em28xx_info("Closing video extension\n"); mutex_lock(&dev->lock); diff --git a/drivers/media/usb/ttusb-dec/ttusbdecfe.c b/drivers/media/usb/ttusb-dec/ttusbdecfe.c index 5c45c9d0712d..9c29552aedec 100644 --- a/drivers/media/usb/ttusb-dec/ttusbdecfe.c +++ b/drivers/media/usb/ttusb-dec/ttusbdecfe.c @@ -156,6 +156,9 @@ static int ttusbdecfe_dvbs_diseqc_send_master_cmd(struct dvb_frontend* fe, struc 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }; + if (cmd->msg_len > sizeof(b) - 4) + return -EINVAL; + memcpy(&b[4], cmd->msg, cmd->msg_len); state->config->send_command(fe, 0x72, diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index c3bb2502225b..45314412b4a3 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -1603,12 +1603,12 @@ static void uvc_delete(struct uvc_device *dev) { struct list_head *p, *n; - usb_put_intf(dev->intf); - usb_put_dev(dev->udev); - uvc_status_cleanup(dev); uvc_ctrl_cleanup_device(dev); + usb_put_intf(dev->intf); + usb_put_dev(dev->udev); + if (dev->vdev.dev) v4l2_device_unregister(&dev->vdev); #ifdef CONFIG_MEDIA_CONTROLLER @@ -2210,6 +2210,15 @@ static struct usb_device_id uvc_ids[] = { .bInterfaceSubClass = 1, .bInterfaceProtocol = 0, .driver_info = UVC_QUIRK_PROBE_DEF }, + /* Dell XPS M1330 (OmniVision OV7670 webcam) */ + { .match_flags = USB_DEVICE_ID_MATCH_DEVICE + | USB_DEVICE_ID_MATCH_INT_INFO, + .idVendor = 0x05a9, + .idProduct = 0x7670, + .bInterfaceClass = USB_CLASS_VIDEO, + .bInterfaceSubClass = 1, + .bInterfaceProtocol = 0, + .driver_info = UVC_QUIRK_PROBE_DEF }, /* Apple Built-In iSight */ { .match_flags = USB_DEVICE_ID_MATCH_DEVICE | USB_DEVICE_ID_MATCH_INT_INFO, diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c index 433d6d77942e..c5521cec933b 100644 --- a/drivers/media/v4l2-core/v4l2-common.c +++ b/drivers/media/v4l2-core/v4l2-common.c @@ -431,16 +431,13 @@ static unsigned int clamp_align(unsigned int x, unsigned int min, /* Bits that must be zero to be aligned */ unsigned int mask = ~((1 << align) - 1); + /* Clamp to aligned min and max */ + x = clamp(x, (min + ~mask) & mask, max & mask); + /* Round to nearest aligned value */ if (align) x = (x + (1 << (align - 1))) & mask; - /* Clamp to aligned value of min and max */ - if (x < min) - x = (min + ~mask) & mask; - else if (x > max) - x = max & mask; - return x; } diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c index a127925c9d61..06faea4d60ee 100644 --- a/drivers/media/v4l2-core/videobuf2-core.c +++ b/drivers/media/v4l2-core/videobuf2-core.c @@ -745,6 +745,7 @@ static int __reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req) * to the userspace. */ req->count = allocated_buffers; + q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type); return 0; } @@ -793,6 +794,7 @@ static int __create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create memset(q->plane_sizes, 0, sizeof(q->plane_sizes)); memset(q->alloc_ctx, 0, sizeof(q->alloc_ctx)); q->memory = create->memory; + q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type); } num_buffers = min(create->count, VIDEO_MAX_FRAME - q->num_buffers); @@ -1447,6 +1449,7 @@ static int vb2_internal_qbuf(struct vb2_queue *q, struct v4l2_buffer *b) * dequeued in dqbuf. */ list_add_tail(&vb->queued_entry, &q->queued_list); + q->waiting_for_buffers = false; vb->state = VB2_BUF_STATE_QUEUED; /* @@ -1841,6 +1844,7 @@ static int vb2_internal_streamoff(struct vb2_queue *q, enum v4l2_buf_type type) * and videobuf, effectively returning control over them to userspace. */ __vb2_queue_cancel(q); + q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type); dprintk(3, "Streamoff successful\n"); return 0; @@ -2150,9 +2154,16 @@ unsigned int vb2_poll(struct vb2_queue *q, struct file *file, poll_table *wait) } /* - * There is nothing to wait for if no buffers have already been queued. + * There is nothing to wait for if the queue isn't streaming. */ - if (list_empty(&q->queued_list)) + if (!vb2_is_streaming(q)) + return res | POLLERR; + /* + * For compatibility with vb1: if QBUF hasn't been called yet, then + * return POLLERR as well. This only affects capture queues, output + * queues will always initialize waiting_for_buffers to false. + */ + if (q->waiting_for_buffers) return res | POLLERR; if (list_empty(&q->done_list)) diff --git a/drivers/message/fusion/mptspi.c b/drivers/message/fusion/mptspi.c index 5653e505f91f..424f51d1e2ce 100644 --- a/drivers/message/fusion/mptspi.c +++ b/drivers/message/fusion/mptspi.c @@ -1422,6 +1422,11 @@ mptspi_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto out_mptspi_probe; } + /* VMWare emulation doesn't properly implement WRITE_SAME + */ + if (pdev->subsystem_vendor == 0x15AD) + sh->no_write_same = 1; + spin_lock_irqsave(&ioc->FreeQlock, flags); /* Attach the SCSI Host to the IOC structure diff --git a/drivers/mfd/kempld-core.c b/drivers/mfd/kempld-core.c index 38917a822335..2df3cbc968d1 100644 --- a/drivers/mfd/kempld-core.c +++ b/drivers/mfd/kempld-core.c @@ -629,7 +629,7 @@ static int __init kempld_init(void) if (force_device_id[0]) { for (id = kempld_dmi_table; id->matches[0].slot != DMI_NONE; id++) if (strstr(id->ident, force_device_id)) - if (id->callback && id->callback(id)) + if (id->callback && !id->callback(id)) break; if (id->matches[0].slot == DMI_NONE) return -ENODEV; diff --git a/drivers/mfd/rtsx_pcr.c b/drivers/mfd/rtsx_pcr.c index 1d15735f9ef9..89b4c4216d0c 100644 --- a/drivers/mfd/rtsx_pcr.c +++ b/drivers/mfd/rtsx_pcr.c @@ -1177,7 +1177,7 @@ static int rtsx_pci_probe(struct pci_dev *pcidev, pcr->msi_en = msi_en; if (pcr->msi_en) { ret = pci_enable_msi(pcidev); - if (ret < 0) + if (ret) pcr->msi_en = false; } diff --git a/drivers/mfd/tc6393xb.c b/drivers/mfd/tc6393xb.c index 11c19e538551..48579e5ef02c 100644 --- a/drivers/mfd/tc6393xb.c +++ b/drivers/mfd/tc6393xb.c @@ -263,6 +263,17 @@ static int tc6393xb_ohci_disable(struct platform_device *dev) return 0; } +static int tc6393xb_ohci_suspend(struct platform_device *dev) +{ + struct tc6393xb_platform_data *tcpd = dev_get_platdata(dev->dev.parent); + + /* We can't properly store/restore OHCI state, so fail here */ + if (tcpd->resume_restore) + return -EBUSY; + + return tc6393xb_ohci_disable(dev); +} + static int tc6393xb_fb_enable(struct platform_device *dev) { struct tc6393xb *tc6393xb = dev_get_drvdata(dev->dev.parent); @@ -403,7 +414,7 @@ static struct mfd_cell tc6393xb_cells[] = { .num_resources = ARRAY_SIZE(tc6393xb_ohci_resources), .resources = tc6393xb_ohci_resources, .enable = tc6393xb_ohci_enable, - .suspend = tc6393xb_ohci_disable, + .suspend = tc6393xb_ohci_suspend, .resume = tc6393xb_ohci_enable, .disable = tc6393xb_ohci_disable, }, diff --git a/drivers/mfd/ti_am335x_tscadc.c b/drivers/mfd/ti_am335x_tscadc.c index d4e860413bb5..e87a2485468f 100644 --- a/drivers/mfd/ti_am335x_tscadc.c +++ b/drivers/mfd/ti_am335x_tscadc.c @@ -54,11 +54,11 @@ void am335x_tsc_se_set_cache(struct ti_tscadc_dev *tsadc, u32 val) unsigned long flags; spin_lock_irqsave(&tsadc->reg_lock, flags); - tsadc->reg_se_cache = val; + tsadc->reg_se_cache |= val; if (tsadc->adc_waiting) wake_up(&tsadc->reg_se_wait); else if (!tsadc->adc_in_use) - tscadc_writel(tsadc, REG_SE, val); + tscadc_writel(tsadc, REG_SE, tsadc->reg_se_cache); spin_unlock_irqrestore(&tsadc->reg_lock, flags); } @@ -97,6 +97,7 @@ static void am335x_tscadc_need_adc(struct ti_tscadc_dev *tsadc) void am335x_tsc_se_set_once(struct ti_tscadc_dev *tsadc, u32 val) { spin_lock_irq(&tsadc->reg_lock); + tsadc->reg_se_cache |= val; am335x_tscadc_need_adc(tsadc); tscadc_writel(tsadc, REG_SE, val); diff --git a/drivers/misc/genwqe/card_utils.c b/drivers/misc/genwqe/card_utils.c index 6b1a6ef9f1a8..0c3a64708409 100644 --- a/drivers/misc/genwqe/card_utils.c +++ b/drivers/misc/genwqe/card_utils.c @@ -490,6 +490,8 @@ int genwqe_user_vmap(struct genwqe_dev *cd, struct dma_mapping *m, void *uaddr, m->nr_pages, 1, /* write by caller */ m->page_list); /* ptrs to pages */ + if (rc < 0) + goto fail_get_user_pages; /* assumption: get_user_pages can be killed by signals. */ if (rc < m->nr_pages) { diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index 4bc7d620d695..9a07bba3ade4 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -71,7 +71,7 @@ static int mei_cl_device_probe(struct device *dev) dev_dbg(dev, "Device probe\n"); - strncpy(id.name, dev_name(dev), sizeof(id.name)); + strlcpy(id.name, dev_name(dev), sizeof(id.name)); return driver->probe(device, &id); } diff --git a/drivers/misc/mei/init.c b/drivers/misc/mei/init.c index cdd31c2a2a2b..b2965382d0ec 100644 --- a/drivers/misc/mei/init.c +++ b/drivers/misc/mei/init.c @@ -275,6 +275,8 @@ void mei_stop(struct mei_device *dev) dev->dev_state = MEI_DEV_POWER_DOWN; mei_reset(dev); + /* move device to disabled state unconditionally */ + dev->dev_state = MEI_DEV_DISABLED; mutex_unlock(&dev->device_lock); diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index 7b5424f398ac..df72c478c5a2 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -260,7 +260,7 @@ static ssize_t force_ro_show(struct device *dev, struct device_attribute *attr, int ret; struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev)); - ret = snprintf(buf, PAGE_SIZE, "%d", + ret = snprintf(buf, PAGE_SIZE, "%d\n", get_disk_ro(dev_to_disk(dev)) ^ md->read_only); mmc_blk_put(md); diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c index 55cd110a49c4..caed9d53e8fa 100644 --- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -632,6 +632,13 @@ static void dw_mci_ctrl_rd_thld(struct dw_mci *host, struct mmc_data *data) WARN_ON(!(data->flags & MMC_DATA_READ)); + /* + * CDTHRCTL doesn't exist prior to 240A (in fact that register offset is + * in the FIFO region, so we really shouldn't access it). + */ + if (host->verid < DW_MMC_240A) + return; + if (host->timing != MMC_TIMING_MMC_HS200 && host->timing != MMC_TIMING_UHS_SDR104) goto disable; diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c index 7e1866175e7b..ca297d741207 100644 --- a/drivers/mmc/host/rtsx_pci_sdmmc.c +++ b/drivers/mmc/host/rtsx_pci_sdmmc.c @@ -342,6 +342,13 @@ static void sd_send_cmd_get_rsp(struct realtek_pci_sdmmc *host, } if (rsp_type == SD_RSP_TYPE_R2) { + /* + * The controller offloads the last byte {CRC-7, end bit 1'b1} + * of response type R2. Assign dummy CRC, 0, and end bit to the + * byte(ptr[16], goes into the LSB of resp[3] later). + */ + ptr[16] = 1; + for (i = 0; i < 4; i++) { cmd->resp[i] = get_unaligned_be32(ptr + 1 + i * 4); dev_dbg(sdmmc_dev(host), "cmd->resp[%d] = 0x%08x\n", diff --git a/drivers/mmc/host/sdhci-pci-o2micro.c b/drivers/mmc/host/sdhci-pci-o2micro.c index f49666bcc52a..257e9ca30166 100644 --- a/drivers/mmc/host/sdhci-pci-o2micro.c +++ b/drivers/mmc/host/sdhci-pci-o2micro.c @@ -88,8 +88,6 @@ void sdhci_pci_o2_fujin2_pci_init(struct sdhci_pci_chip *chip) return; scratch_32 &= ~((1 << 21) | (1 << 30)); - /* Set RTD3 function disabled */ - scratch_32 |= ((1 << 29) | (1 << 28)); pci_write_config_dword(chip->pdev, O2_SD_FUNC_REG3, scratch_32); /* Set L1 Entrance Timer */ diff --git a/drivers/mmc/host/sdhci-pci.c b/drivers/mmc/host/sdhci-pci.c index 0955777b6c7e..19bfa0ad70c4 100644 --- a/drivers/mmc/host/sdhci-pci.c +++ b/drivers/mmc/host/sdhci-pci.c @@ -103,6 +103,10 @@ static const struct sdhci_pci_fixes sdhci_cafe = { SDHCI_QUIRK_BROKEN_TIMEOUT_VAL, }; +static const struct sdhci_pci_fixes sdhci_intel_qrk = { + .quirks = SDHCI_QUIRK_NO_HISPD_BIT, +}; + static int mrst_hc_probe_slot(struct sdhci_pci_slot *slot) { slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA; @@ -733,6 +737,14 @@ static const struct pci_device_id pci_ids[] = { { .vendor = PCI_VENDOR_ID_INTEL, + .device = PCI_DEVICE_ID_INTEL_QRK_SD, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .driver_data = (kernel_ulong_t)&sdhci_intel_qrk, + }, + + { + .vendor = PCI_VENDOR_ID_INTEL, .device = PCI_DEVICE_ID_INTEL_MRST_SD0, .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 6d718719659e..c101477ef3be 100644 --- a/drivers/mmc/host/sdhci-pci.h +++ b/drivers/mmc/host/sdhci-pci.h @@ -17,6 +17,7 @@ #define PCI_DEVICE_ID_INTEL_CLV_SDIO2 0x08fb #define PCI_DEVICE_ID_INTEL_CLV_EMMC0 0x08e5 #define PCI_DEVICE_ID_INTEL_CLV_EMMC1 0x08e6 +#define PCI_DEVICE_ID_INTEL_QRK_SD 0x08A7 /* * PCI registers diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c index 793dacd3b841..561c6b4907a1 100644 --- a/drivers/mmc/host/sdhci-pxav3.c +++ b/drivers/mmc/host/sdhci-pxav3.c @@ -201,8 +201,8 @@ static struct sdhci_pxa_platdata *pxav3_get_mmc_pdata(struct device *dev) if (!pdata) return NULL; - of_property_read_u32(np, "mrvl,clk-delay-cycles", &clk_delay_cycles); - if (clk_delay_cycles > 0) + if (!of_property_read_u32(np, "mrvl,clk-delay-cycles", + &clk_delay_cycles)) pdata->clk_delay_cycles = clk_delay_cycles; return pdata; diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 9ddef4763541..881bf89acfcc 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -1343,6 +1343,8 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq) sdhci_runtime_pm_get(host); + present = mmc_gpio_get_cd(host->mmc); + spin_lock_irqsave(&host->lock, flags); WARN_ON(host->mrq != NULL); @@ -1371,7 +1373,6 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq) * zero: cd-gpio is used, and card is removed * one: cd-gpio is used, and card is present */ - present = mmc_gpio_get_cd(host->mmc); if (present < 0) { /* If polling, assume that the card is always present. */ if (host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION) @@ -2082,15 +2083,18 @@ static void sdhci_card_event(struct mmc_host *mmc) { struct sdhci_host *host = mmc_priv(mmc); unsigned long flags; + int present; /* First check if client has provided their own card event */ if (host->ops->card_event) host->ops->card_event(host); + present = sdhci_do_get_cd(host); + spin_lock_irqsave(&host->lock, flags); /* Check host->mrq first in case we are runtime suspended */ - if (host->mrq && !sdhci_do_get_cd(host)) { + if (host->mrq && !present) { pr_err("%s: Card removed during transfer!\n", mmc_hostname(host->mmc)); pr_err("%s: Resetting controller.\n", @@ -2533,7 +2537,7 @@ out: /* * We have to delay this as it calls back into the driver. */ - if (cardint) + if (cardint && host->mmc->sdio_irqs) mmc_signal_sdio_irq(host->mmc); return result; diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c index 51e15fd53108..d058b00ba218 100644 --- a/drivers/mtd/nand/pxa3xx_nand.c +++ b/drivers/mtd/nand/pxa3xx_nand.c @@ -481,6 +481,42 @@ static void disable_int(struct pxa3xx_nand_info *info, uint32_t int_mask) nand_writel(info, NDCR, ndcr | int_mask); } +static void drain_fifo(struct pxa3xx_nand_info *info, void *data, int len) +{ + if (info->ecc_bch) { + int timeout; + + /* + * According to the datasheet, when reading from NDDB + * with BCH enabled, after each 32 bytes reads, we + * have to make sure that the NDSR.RDDREQ bit is set. + * + * Drain the FIFO 8 32 bits reads at a time, and skip + * the polling on the last read. + */ + while (len > 8) { + __raw_readsl(info->mmio_base + NDDB, data, 8); + + for (timeout = 0; + !(nand_readl(info, NDSR) & NDSR_RDDREQ); + timeout++) { + if (timeout >= 5) { + dev_err(&info->pdev->dev, + "Timeout on RDDREQ while draining the FIFO\n"); + return; + } + + mdelay(1); + } + + data += 32; + len -= 8; + } + } + + __raw_readsl(info->mmio_base + NDDB, data, len); +} + static void handle_data_pio(struct pxa3xx_nand_info *info) { unsigned int do_bytes = min(info->data_size, info->chunk_size); @@ -497,14 +533,14 @@ static void handle_data_pio(struct pxa3xx_nand_info *info) DIV_ROUND_UP(info->oob_size, 4)); break; case STATE_PIO_READING: - __raw_readsl(info->mmio_base + NDDB, - info->data_buff + info->data_buff_pos, - DIV_ROUND_UP(do_bytes, 4)); + drain_fifo(info, + info->data_buff + info->data_buff_pos, + DIV_ROUND_UP(do_bytes, 4)); if (info->oob_size > 0) - __raw_readsl(info->mmio_base + NDDB, - info->oob_buff + info->oob_buff_pos, - DIV_ROUND_UP(info->oob_size, 4)); + drain_fifo(info, + info->oob_buff + info->oob_buff_pos, + DIV_ROUND_UP(info->oob_size, 4)); break; default: dev_err(&info->pdev->dev, "%s: invalid state %d\n", __func__, diff --git a/drivers/mtd/tests/torturetest.c b/drivers/mtd/tests/torturetest.c index eeab96973cf0..b55bc52a1340 100644 --- a/drivers/mtd/tests/torturetest.c +++ b/drivers/mtd/tests/torturetest.c @@ -264,7 +264,9 @@ static int __init tort_init(void) int i; void *patt; - mtdtest_erase_good_eraseblocks(mtd, bad_ebs, eb, ebcnt); + err = mtdtest_erase_good_eraseblocks(mtd, bad_ebs, eb, ebcnt); + if (err) + goto out; /* Check if the eraseblocks contain only 0xFF bytes */ if (check) { diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c index c5dad652614d..904b4517fc1e 100644 --- a/drivers/mtd/ubi/fastmap.c +++ b/drivers/mtd/ubi/fastmap.c @@ -330,6 +330,7 @@ static int process_pool_aeb(struct ubi_device *ubi, struct ubi_attach_info *ai, av = tmp_av; else { ubi_err("orphaned volume in fastmap pool!"); + kmem_cache_free(ai->aeb_slab_cache, new_aeb); return UBI_BAD_FASTMAP; } diff --git a/drivers/mtd/ubi/upd.c b/drivers/mtd/ubi/upd.c index ec2c2dc1c1ca..2a1b6e037e1a 100644 --- a/drivers/mtd/ubi/upd.c +++ b/drivers/mtd/ubi/upd.c @@ -133,6 +133,10 @@ int ubi_start_update(struct ubi_device *ubi, struct ubi_volume *vol, ubi_assert(!vol->updating && !vol->changing_leb); vol->updating = 1; + vol->upd_buf = vmalloc(ubi->leb_size); + if (!vol->upd_buf) + return -ENOMEM; + err = set_update_marker(ubi, vol); if (err) return err; @@ -152,14 +156,12 @@ int ubi_start_update(struct ubi_device *ubi, struct ubi_volume *vol, err = clear_update_marker(ubi, vol, 0); if (err) return err; + + vfree(vol->upd_buf); vol->updating = 0; return 0; } - vol->upd_buf = vmalloc(ubi->leb_size); - if (!vol->upd_buf) - return -ENOMEM; - vol->upd_ebs = div_u64(bytes + vol->usable_leb_size - 1, vol->usable_leb_size); vol->upd_bytes = bytes; diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c index 02317c1c0238..68b924ec222e 100644 --- a/drivers/mtd/ubi/wl.c +++ b/drivers/mtd/ubi/wl.c @@ -1205,7 +1205,6 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, err = do_sync_erase(ubi, e1, vol_id, lnum, 0); if (err) { - kmem_cache_free(ubi_wl_entry_slab, e1); if (e2) kmem_cache_free(ubi_wl_entry_slab, e2); goto out_ro; @@ -1219,10 +1218,8 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, dbg_wl("PEB %d (LEB %d:%d) was put meanwhile, erase", e2->pnum, vol_id, lnum); err = do_sync_erase(ubi, e2, vol_id, lnum, 0); - if (err) { - kmem_cache_free(ubi_wl_entry_slab, e2); + if (err) goto out_ro; - } } dbg_wl("done"); @@ -1258,10 +1255,9 @@ out_not_moved: ubi_free_vid_hdr(ubi, vid_hdr); err = do_sync_erase(ubi, e2, vol_id, lnum, torture); - if (err) { - kmem_cache_free(ubi_wl_entry_slab, e2); + if (err) goto out_ro; - } + mutex_unlock(&ubi->move_mutex); return 0; diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 494b888a6568..7e5c6a8b89e7 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -135,6 +135,7 @@ config MACVLAN config MACVTAP tristate "MAC-VLAN based tap driver" depends on MACVLAN + depends on INET help This adds a specialized tap character device driver that is based on the MAC-VLAN network interface, called macvtap. A macvtap device @@ -205,6 +206,7 @@ config RIONET_RX_SIZE config TUN tristate "Universal TUN/TAP device driver support" + depends on INET select CRC32 ---help--- TUN/TAP provides packet reception and transmission for user space diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index a95b322f0924..15379824d77d 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2450,9 +2450,9 @@ static void bond_loadbalance_arp_mon(struct work_struct *work) if (!rtnl_trylock()) goto re_arm; - if (slave_state_changed) { + if (slave_state_changed) bond_slave_state_change(bond); - } else if (do_failover) { + if (do_failover) { /* the bond_select_active_slave must hold RTNL * and curr_slave_lock for write. */ @@ -3624,8 +3624,14 @@ static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev else bond_xmit_slave_id(bond, skb, 0); } else { - slave_id = bond_rr_gen_slave_id(bond); - bond_xmit_slave_id(bond, skb, slave_id % bond->slave_cnt); + int slave_cnt = ACCESS_ONCE(bond->slave_cnt); + + if (likely(slave_cnt)) { + slave_id = bond_rr_gen_slave_id(bond); + bond_xmit_slave_id(bond, skb, slave_id % slave_cnt); + } else { + dev_kfree_skb_any(skb); + } } return NETDEV_TX_OK; @@ -3656,8 +3662,13 @@ static int bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_d static int bond_xmit_xor(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); + int slave_cnt = ACCESS_ONCE(bond->slave_cnt); - bond_xmit_slave_id(bond, skb, bond_xmit_hash(bond, skb, bond->slave_cnt)); + if (likely(slave_cnt)) + bond_xmit_slave_id(bond, skb, + bond_xmit_hash(bond, skb, bond->slave_cnt)); + else + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index fc59bc6f040b..84ad2b44377c 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -384,7 +384,7 @@ void can_free_echo_skb(struct net_device *dev, unsigned int idx) BUG_ON(idx >= priv->echo_skb_max); if (priv->echo_skb[idx]) { - kfree_skb(priv->echo_skb[idx]); + dev_kfree_skb_any(priv->echo_skb[idx]); priv->echo_skb[idx] = NULL; } } @@ -502,6 +502,14 @@ struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf) skb->pkt_type = PACKET_BROADCAST; skb->ip_summed = CHECKSUM_UNNECESSARY; + skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + + skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + can_skb_reserve(skb); can_skb_prv(skb)->ifindex = dev->ifindex; @@ -664,10 +672,14 @@ static int can_changelink(struct net_device *dev, if (dev->flags & IFF_UP) return -EBUSY; cm = nla_data(data[IFLA_CAN_CTRLMODE]); - if (cm->flags & ~priv->ctrlmode_supported) + + /* check whether changed bits are allowed to be modified */ + if (cm->mask & ~priv->ctrlmode_supported) return -EOPNOTSUPP; + + /* clear bits to be modified and copy the flag values */ priv->ctrlmode &= ~cm->mask; - priv->ctrlmode |= cm->flags; + priv->ctrlmode |= (cm->flags & cm->mask); } if (data[IFLA_CAN_RESTART_MS]) { diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 61376abdab39..dbd8d21a8f10 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -1095,12 +1095,19 @@ static int flexcan_probe(struct platform_device *pdev) const struct flexcan_devtype_data *devtype_data; struct net_device *dev; struct flexcan_priv *priv; + struct regulator *reg_xceiver; struct resource *mem; struct clk *clk_ipg = NULL, *clk_per = NULL; void __iomem *base; int err, irq; u32 clock_freq = 0; + reg_xceiver = devm_regulator_get(&pdev->dev, "xceiver"); + if (PTR_ERR(reg_xceiver) == -EPROBE_DEFER) + return -EPROBE_DEFER; + else if (IS_ERR(reg_xceiver)) + reg_xceiver = NULL; + if (pdev->dev.of_node) of_property_read_u32(pdev->dev.of_node, "clock-frequency", &clock_freq); @@ -1162,9 +1169,7 @@ static int flexcan_probe(struct platform_device *pdev) priv->pdata = dev_get_platdata(&pdev->dev); priv->devtype_data = devtype_data; - priv->reg_xceiver = devm_regulator_get(&pdev->dev, "xceiver"); - if (IS_ERR(priv->reg_xceiver)) - priv->reg_xceiver = NULL; + priv->reg_xceiver = reg_xceiver; netif_napi_add(dev, &priv->napi, flexcan_poll, FLEXCAN_NAPI_WEIGHT); diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c index 7fbe85935f1d..f34f7fa1f901 100644 --- a/drivers/net/can/usb/esd_usb2.c +++ b/drivers/net/can/usb/esd_usb2.c @@ -1141,6 +1141,7 @@ static void esd_usb2_disconnect(struct usb_interface *intf) } } unlink_all_urbs(dev); + kfree(dev); } } diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c index e77d11049747..3d198679510b 100644 --- a/drivers/net/can/usb/kvaser_usb.c +++ b/drivers/net/can/usb/kvaser_usb.c @@ -578,7 +578,7 @@ static int kvaser_usb_simple_msg_async(struct kvaser_usb_net_priv *priv, usb_sndbulkpipe(dev->udev, dev->bulk_out->bEndpointAddress), buf, msg->len, - kvaser_usb_simple_msg_callback, priv); + kvaser_usb_simple_msg_callback, netdev); usb_anchor_urb(urb, &priv->tx_submitted); err = usb_submit_urb(urb, GFP_ATOMIC); @@ -653,11 +653,6 @@ static void kvaser_usb_rx_error(const struct kvaser_usb *dev, priv = dev->nets[channel]; stats = &priv->netdev->stats; - if (status & M16C_STATE_BUS_RESET) { - kvaser_usb_unlink_tx_urbs(priv); - return; - } - skb = alloc_can_err_skb(priv->netdev, &cf); if (!skb) { stats->rx_dropped++; @@ -668,7 +663,7 @@ static void kvaser_usb_rx_error(const struct kvaser_usb *dev, netdev_dbg(priv->netdev, "Error status: 0x%02x\n", status); - if (status & M16C_STATE_BUS_OFF) { + if (status & (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET)) { cf->can_id |= CAN_ERR_BUSOFF; priv->can.can_stats.bus_off++; @@ -694,9 +689,7 @@ static void kvaser_usb_rx_error(const struct kvaser_usb *dev, } new_state = CAN_STATE_ERROR_PASSIVE; - } - - if (status == M16C_STATE_BUS_ERROR) { + } else if (status & M16C_STATE_BUS_ERROR) { if ((priv->can.state < CAN_STATE_ERROR_WARNING) && ((txerr >= 96) || (rxerr >= 96))) { cf->can_id |= CAN_ERR_CRTL; @@ -706,7 +699,8 @@ static void kvaser_usb_rx_error(const struct kvaser_usb *dev, priv->can.can_stats.error_warning++; new_state = CAN_STATE_ERROR_WARNING; - } else if (priv->can.state > CAN_STATE_ERROR_ACTIVE) { + } else if ((priv->can.state > CAN_STATE_ERROR_ACTIVE) && + ((txerr < 96) && (rxerr < 96))) { cf->can_id |= CAN_ERR_PROT; cf->data[2] = CAN_ERR_PROT_ACTIVE; @@ -1237,6 +1231,9 @@ static int kvaser_usb_close(struct net_device *netdev) if (err) netdev_warn(netdev, "Cannot stop device, error %d\n", err); + /* reset tx contexts */ + kvaser_usb_unlink_tx_urbs(priv); + priv->can.state = CAN_STATE_STOPPED; close_candev(priv->netdev); @@ -1285,12 +1282,14 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb, if (!urb) { netdev_err(netdev, "No memory left for URBs\n"); stats->tx_dropped++; - goto nourbmem; + dev_kfree_skb(skb); + return NETDEV_TX_OK; } buf = kmalloc(sizeof(struct kvaser_msg), GFP_ATOMIC); if (!buf) { stats->tx_dropped++; + dev_kfree_skb(skb); goto nobufmem; } @@ -1325,6 +1324,7 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb, } } + /* This should never happen; it implies a flow control bug */ if (!context) { netdev_warn(netdev, "cannot find free context\n"); ret = NETDEV_TX_BUSY; @@ -1355,9 +1355,6 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb, if (unlikely(err)) { can_free_echo_skb(netdev, context->echo_index); - skb = NULL; /* set to NULL to avoid double free in - * dev_kfree_skb(skb) */ - atomic_dec(&priv->active_tx_urbs); usb_unanchor_urb(urb); @@ -1379,8 +1376,6 @@ releasebuf: kfree(buf); nobufmem: usb_free_urb(urb); -nourbmem: - dev_kfree_skb(skb); return ret; } @@ -1492,6 +1487,10 @@ static int kvaser_usb_init_one(struct usb_interface *intf, struct kvaser_usb_net_priv *priv; int i, err; + err = kvaser_usb_send_simple_msg(dev, CMD_RESET_CHIP, channel); + if (err) + return err; + netdev = alloc_candev(sizeof(*priv), MAX_TX_URBS); if (!netdev) { dev_err(&intf->dev, "Cannot alloc candev\n"); @@ -1577,7 +1576,7 @@ static int kvaser_usb_probe(struct usb_interface *intf, { struct kvaser_usb *dev; int err = -ENOMEM; - int i; + int i, retry = 3; dev = devm_kzalloc(&intf->dev, sizeof(*dev), GFP_KERNEL); if (!dev) @@ -1595,10 +1594,15 @@ static int kvaser_usb_probe(struct usb_interface *intf, usb_set_intfdata(intf, dev); - for (i = 0; i < MAX_NET_DEVICES; i++) - kvaser_usb_send_simple_msg(dev, CMD_RESET_CHIP, i); + /* On some x86 laptops, plugging a Kvaser device again after + * an unplug makes the firmware always ignore the very first + * command. For such a case, provide some room for retries + * instead of completely exiting the driver. + */ + do { + err = kvaser_usb_get_software_info(dev); + } while (--retry && err == -ETIMEDOUT); - err = kvaser_usb_get_software_info(dev); if (err) { dev_err(&intf->dev, "Cannot get software infos, error %d\n", err); diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index 0b7a4c3b01a2..03e7f0cbda8c 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -734,7 +734,7 @@ static int peak_usb_create_dev(struct peak_usb_adapter *peak_usb_adapter, dev->cmd_buf = kmalloc(PCAN_USB_MAX_CMD_LEN, GFP_KERNEL); if (!dev->cmd_buf) { err = -ENOMEM; - goto lbl_set_intf_data; + goto lbl_free_candev; } dev->udev = usb_dev; @@ -773,7 +773,7 @@ static int peak_usb_create_dev(struct peak_usb_adapter *peak_usb_adapter, err = register_candev(netdev); if (err) { dev_err(&intf->dev, "couldn't register CAN device: %d\n", err); - goto lbl_free_cmd_buf; + goto lbl_restore_intf_data; } if (dev->prev_siblings) @@ -786,14 +786,14 @@ static int peak_usb_create_dev(struct peak_usb_adapter *peak_usb_adapter, if (dev->adapter->dev_init) { err = dev->adapter->dev_init(dev); if (err) - goto lbl_free_cmd_buf; + goto lbl_unregister_candev; } /* set bus off */ if (dev->adapter->dev_set_bus) { err = dev->adapter->dev_set_bus(dev, 0); if (err) - goto lbl_free_cmd_buf; + goto lbl_unregister_candev; } /* get device number early */ @@ -805,11 +805,14 @@ static int peak_usb_create_dev(struct peak_usb_adapter *peak_usb_adapter, return 0; -lbl_free_cmd_buf: - kfree(dev->cmd_buf); +lbl_unregister_candev: + unregister_candev(netdev); -lbl_set_intf_data: +lbl_restore_intf_data: usb_set_intfdata(intf, dev->prev_siblings); + kfree(dev->cmd_buf); + +lbl_free_candev: free_candev(netdev); return err; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c index 263dd921edc4..f7f796a2c50b 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c @@ -333,8 +333,6 @@ static int pcan_usb_pro_send_req(struct peak_usb_device *dev, int req_id, if (!(dev->state & PCAN_USB_STATE_CONNECTED)) return 0; - memset(req_addr, '\0', req_size); - req_type = USB_TYPE_VENDOR | USB_RECIP_OTHER; switch (req_id) { @@ -345,6 +343,7 @@ static int pcan_usb_pro_send_req(struct peak_usb_device *dev, int req_id, default: p = usb_rcvctrlpipe(dev->udev, 0); req_type |= USB_DIR_IN; + memset(req_addr, '\0', req_size); break; } diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c index 9339cccfe05a..ad0e71c7a607 100644 --- a/drivers/net/ethernet/amd/pcnet32.c +++ b/drivers/net/ethernet/amd/pcnet32.c @@ -1516,7 +1516,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) { struct pcnet32_private *lp; int i, media; - int fdx, mii, fset, dxsuflo; + int fdx, mii, fset, dxsuflo, sram; int chip_version; char *chipname; struct net_device *dev; @@ -1553,7 +1553,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) } /* initialize variables */ - fdx = mii = fset = dxsuflo = 0; + fdx = mii = fset = dxsuflo = sram = 0; chip_version = (chip_version >> 12) & 0xffff; switch (chip_version) { @@ -1586,6 +1586,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) chipname = "PCnet/FAST III 79C973"; /* PCI */ fdx = 1; mii = 1; + sram = 1; break; case 0x2626: chipname = "PCnet/Home 79C978"; /* PCI */ @@ -1609,6 +1610,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) chipname = "PCnet/FAST III 79C975"; /* PCI */ fdx = 1; mii = 1; + sram = 1; break; case 0x2628: chipname = "PCnet/PRO 79C976"; @@ -1637,6 +1639,31 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) dxsuflo = 1; } + /* + * The Am79C973/Am79C975 controllers come with 12K of SRAM + * which we can use for the Tx/Rx buffers but most importantly, + * the use of SRAM allow us to use the BCR18:NOUFLO bit to avoid + * Tx fifo underflows. + */ + if (sram) { + /* + * The SRAM is being configured in two steps. First we + * set the SRAM size in the BCR25:SRAM_SIZE bits. According + * to the datasheet, each bit corresponds to a 512-byte + * page so we can have at most 24 pages. The SRAM_SIZE + * holds the value of the upper 8 bits of the 16-bit SRAM size. + * The low 8-bits start at 0x00 and end at 0xff. So the + * address range is from 0x0000 up to 0x17ff. Therefore, + * the SRAM_SIZE is set to 0x17. The next step is to set + * the BCR26:SRAM_BND midway through so the Tx and Rx + * buffers can share the SRAM equally. + */ + a->write_bcr(ioaddr, 25, 0x17); + a->write_bcr(ioaddr, 26, 0xc); + /* And finally enable the NOUFLO bit */ + a->write_bcr(ioaddr, 18, a->read_bcr(ioaddr, 18) | (1 << 11)); + } + dev = alloc_etherdev(sizeof(*lp)); if (!dev) { ret = -ENOMEM; diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index 380d24922049..3e1d7d29b4ec 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -184,15 +184,16 @@ static void alx_schedule_reset(struct alx_priv *alx) schedule_work(&alx->reset_wk); } -static bool alx_clean_rx_irq(struct alx_priv *alx, int budget) +static int alx_clean_rx_irq(struct alx_priv *alx, int budget) { struct alx_rx_queue *rxq = &alx->rxq; struct alx_rrd *rrd; struct alx_buffer *rxb; struct sk_buff *skb; u16 length, rfd_cleaned = 0; + int work = 0; - while (budget > 0) { + while (work < budget) { rrd = &rxq->rrd[rxq->rrd_read_idx]; if (!(rrd->word3 & cpu_to_le32(1 << RRD_UPDATED_SHIFT))) break; @@ -203,7 +204,7 @@ static bool alx_clean_rx_irq(struct alx_priv *alx, int budget) ALX_GET_FIELD(le32_to_cpu(rrd->word0), RRD_NOR) != 1) { alx_schedule_reset(alx); - return 0; + return work; } rxb = &rxq->bufs[rxq->read_idx]; @@ -243,7 +244,7 @@ static bool alx_clean_rx_irq(struct alx_priv *alx, int budget) } napi_gro_receive(&alx->napi, skb); - budget--; + work++; next_pkt: if (++rxq->read_idx == alx->rx_ringsz) @@ -258,21 +259,22 @@ next_pkt: if (rfd_cleaned) alx_refill_rx_ring(alx, GFP_ATOMIC); - return budget > 0; + return work; } static int alx_poll(struct napi_struct *napi, int budget) { struct alx_priv *alx = container_of(napi, struct alx_priv, napi); struct alx_hw *hw = &alx->hw; - bool complete = true; unsigned long flags; + bool tx_complete; + int work; - complete = alx_clean_tx_irq(alx) && - alx_clean_rx_irq(alx, budget); + tx_complete = alx_clean_tx_irq(alx); + work = alx_clean_rx_irq(alx, budget); - if (!complete) - return 1; + if (!tx_complete || work == budget) + return budget; napi_complete(&alx->napi); @@ -284,7 +286,7 @@ static int alx_poll(struct napi_struct *napi, int budget) alx_post_write(hw); - return 0; + return work; } static irqreturn_t alx_intr_handle(struct alx_priv *alx, u32 intr) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index afa4a1f63270..a830d42e3d9b 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -3131,7 +3131,7 @@ static int bnx2x_poll(struct napi_struct *napi, int budget) } #endif if (!bnx2x_fp_lock_napi(fp)) - return work_done; + return budget; for_each_cos_in_tx_queue(fp, cos) if (bnx2x_tx_queue_has_work(fp->txdata_ptr[cos])) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 7d4382286457..242874041ba4 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -12395,6 +12395,9 @@ static int bnx2x_init_dev(struct bnx2x *bp, struct pci_dev *pdev, pci_write_config_dword(bp->pdev, PCICFG_GRC_ADDRESS, PCICFG_VENDOR_ID_OFFSET); + /* Set PCIe reset type to fundamental for EEH recovery */ + pdev->needs_freset = 1; + /* AER (Advanced Error reporting) configuration */ rc = pci_enable_pcie_error_reporting(pdev); if (!rc) diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index a210766279d3..82061139b215 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -6923,7 +6923,8 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget) skb->protocol = eth_type_trans(skb, tp->dev); if (len > (tp->dev->mtu + ETH_HLEN) && - skb->protocol != htons(ETH_P_8021Q)) { + skb->protocol != htons(ETH_P_8021Q) && + skb->protocol != htons(ETH_P_8021AD)) { dev_kfree_skb(skb); goto drop_it_no_recycle; } @@ -7915,8 +7916,6 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) entry = tnapi->tx_prod; base_flags = 0; - if (skb->ip_summed == CHECKSUM_PARTIAL) - base_flags |= TXD_FLAG_TCPUDP_CSUM; mss = skb_shinfo(skb)->gso_size; if (mss) { @@ -7932,6 +7931,13 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb) - ETH_HLEN; + /* HW/FW can not correctly segment packets that have been + * vlan encapsulated. + */ + if (skb->protocol == htons(ETH_P_8021Q) || + skb->protocol == htons(ETH_P_8021AD)) + return tg3_tso_bug(tp, skb); + if (!skb_is_gso_v6(skb)) { iph->check = 0; iph->tot_len = htons(mss + hdr_len); @@ -7978,6 +7984,17 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) base_flags |= tsflags << 12; } } + } else if (skb->ip_summed == CHECKSUM_PARTIAL) { + /* HW/FW can not correctly checksum packets that have been + * vlan encapsulated. + */ + if (skb->protocol == htons(ETH_P_8021Q) || + skb->protocol == htons(ETH_P_8021AD)) { + if (skb_checksum_help(skb)) + goto drop; + } else { + base_flags |= TXD_FLAG_TCPUDP_CSUM; + } } if (tg3_flag(tp, USE_JUMBO_BDFLAG) && @@ -8531,7 +8548,8 @@ static int tg3_init_rings(struct tg3 *tp) if (tnapi->rx_rcb) memset(tnapi->rx_rcb, 0, TG3_RX_RCB_RING_BYTES(tp)); - if (tg3_rx_prodring_alloc(tp, &tnapi->prodring)) { + if (tnapi->prodring.rx_std && + tg3_rx_prodring_alloc(tp, &tnapi->prodring)) { tg3_free_rings(tp); return -ENOMEM; } @@ -17713,23 +17731,6 @@ static int tg3_init_one(struct pci_dev *pdev, goto err_out_apeunmap; } - /* - * Reset chip in case UNDI or EFI driver did not shutdown - * DMA self test will enable WDMAC and we'll see (spurious) - * pending DMA on the PCI bus at that point. - */ - if ((tr32(HOSTCC_MODE) & HOSTCC_MODE_ENABLE) || - (tr32(WDMAC_MODE) & WDMAC_MODE_ENABLE)) { - tw32(MEMARB_MODE, MEMARB_MODE_ENABLE); - tg3_halt(tp, RESET_KIND_SHUTDOWN, 1); - } - - err = tg3_test_dma(tp); - if (err) { - dev_err(&pdev->dev, "DMA engine test failed, aborting\n"); - goto err_out_apeunmap; - } - intmbx = MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW; rcvmbx = MAILBOX_RCVRET_CON_IDX_0 + TG3_64BIT_REG_LOW; sndmbx = MAILBOX_SNDHOST_PROD_IDX_0 + TG3_64BIT_REG_LOW; @@ -17774,6 +17775,23 @@ static int tg3_init_one(struct pci_dev *pdev, sndmbx += 0xc; } + /* + * Reset chip in case UNDI or EFI driver did not shutdown + * DMA self test will enable WDMAC and we'll see (spurious) + * pending DMA on the PCI bus at that point. + */ + if ((tr32(HOSTCC_MODE) & HOSTCC_MODE_ENABLE) || + (tr32(WDMAC_MODE) & WDMAC_MODE_ENABLE)) { + tw32(MEMARB_MODE, MEMARB_MODE_ENABLE); + tg3_halt(tp, RESET_KIND_SHUTDOWN, 1); + } + + err = tg3_test_dma(tp); + if (err) { + dev_err(&pdev->dev, "DMA engine test failed, aborting\n"); + goto err_out_apeunmap; + } + tg3_init_coal(tp); pci_set_drvdata(pdev, dev); diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index d0c38e01e99f..0085476a0258 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -30,7 +30,6 @@ #include <linux/of_device.h> #include <linux/of_mdio.h> #include <linux/of_net.h> -#include <linux/pinctrl/consumer.h> #include "macb.h" @@ -1810,7 +1809,6 @@ static int __init macb_probe(struct platform_device *pdev) struct phy_device *phydev; u32 config; int err = -ENXIO; - struct pinctrl *pinctrl; const char *mac; regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -1819,15 +1817,6 @@ static int __init macb_probe(struct platform_device *pdev) goto err_out; } - pinctrl = devm_pinctrl_get_select_default(&pdev->dev); - if (IS_ERR(pinctrl)) { - err = PTR_ERR(pinctrl); - if (err == -EPROBE_DEFER) - goto err_out; - - dev_warn(&pdev->dev, "No pinctrl provided\n"); - } - err = -ENOMEM; dev = alloc_etherdev(sizeof(*bp)); if (!dev) diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index b740bfce72ef..ff9b423805a0 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -1044,10 +1044,14 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq, PKT_HASH_TYPE_L4 : PKT_HASH_TYPE_L3); } - if ((netdev->features & NETIF_F_RXCSUM) && !csum_not_calc) { - skb->csum = htons(checksum); - skb->ip_summed = CHECKSUM_COMPLETE; - } + /* Hardware does not provide whole packet checksum. It only + * provides pseudo checksum. Since hw validates the packet + * checksum but not provide us the checksum value. use + * CHECSUM_UNNECESSARY. + */ + if ((netdev->features & NETIF_F_RXCSUM) && tcp_udp_csum_ok && + ipv4_csum_ok) + skb->ip_summed = CHECKSUM_UNNECESSARY; if (vlan_stripped) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci); diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 1fc8334fc181..55e3075492da 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -292,6 +292,18 @@ failure: atomic_add(buffers_added, &(pool->available)); } +/* + * The final 8 bytes of the buffer list is a counter of frames dropped + * because there was not a buffer in the buffer list capable of holding + * the frame. + */ +static void ibmveth_update_rx_no_buffer(struct ibmveth_adapter *adapter) +{ + __be64 *p = adapter->buffer_list_addr + 4096 - 8; + + adapter->rx_no_buffer = be64_to_cpup(p); +} + /* replenish routine */ static void ibmveth_replenish_task(struct ibmveth_adapter *adapter) { @@ -307,8 +319,7 @@ static void ibmveth_replenish_task(struct ibmveth_adapter *adapter) ibmveth_replenish_buffer_pool(adapter, pool); } - adapter->rx_no_buffer = *(u64 *)(((char*)adapter->buffer_list_addr) + - 4096 - 8); + ibmveth_update_rx_no_buffer(adapter); } /* empty and free ana buffer pool - also used to do cleanup in error paths */ @@ -698,8 +709,7 @@ static int ibmveth_close(struct net_device *netdev) free_irq(netdev->irq, netdev); - adapter->rx_no_buffer = *(u64 *)(((char *)adapter->buffer_list_addr) + - 4096 - 8); + ibmveth_update_rx_no_buffer(adapter); ibmveth_cleanup(adapter); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index b901371ca361..5d3206d5cb07 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -4024,6 +4024,9 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf) DCB_CAP_DCBX_VER_IEEE; pf->flags |= I40E_FLAG_DCB_ENABLED; } + } else { + dev_info(&pf->pdev->dev, "AQ Querying DCB configuration failed: %d\n", + pf->hw.aq.asq_last_status); } out: @@ -8003,7 +8006,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) { dev_info(&pdev->dev, "init_pf_dcb failed: %d\n", err); pf->flags &= ~I40E_FLAG_DCB_ENABLED; - goto err_init_dcb; + /* Continue without DCB enabled */ } #endif /* CONFIG_I40E_DCB */ @@ -8119,9 +8122,6 @@ err_vsis: err_switch_setup: i40e_reset_interrupt_capability(pf); del_timer_sync(&pf->service_timer); -#ifdef CONFIG_I40E_DCB -err_init_dcb: -#endif /* CONFIG_I40E_DCB */ err_mac_addr: err_configure_lan_hmc: (void)i40e_shutdown_lan_hmc(hw); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 5ca8c479666e..206e79d29c79 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -1613,6 +1613,8 @@ void igb_power_up_link(struct igb_adapter *adapter) igb_power_up_phy_copper(&adapter->hw); else igb_power_up_serdes_link_82575(&adapter->hw); + + igb_setup_link(&adapter->hw); } /** diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index c4c00d9f2c04..96fc7fe8519f 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -213,7 +213,7 @@ /* Various constants */ /* Coalescing */ -#define MVNETA_TXDONE_COAL_PKTS 16 +#define MVNETA_TXDONE_COAL_PKTS 1 #define MVNETA_RX_COAL_PKTS 32 #define MVNETA_RX_COAL_USEC 100 @@ -1612,6 +1612,7 @@ static int mvneta_tx(struct sk_buff *skb, struct net_device *dev) u16 txq_id = skb_get_queue_mapping(skb); struct mvneta_tx_queue *txq = &pp->txqs[txq_id]; struct mvneta_tx_desc *tx_desc; + int len = skb->len; struct netdev_queue *nq; int frags = 0; u32 tx_cmd; @@ -1675,7 +1676,7 @@ out: u64_stats_update_begin(&stats->syncp); stats->tx_packets++; - stats->tx_bytes += skb->len; + stats->tx_bytes += len; u64_stats_update_end(&stats->syncp); } else { dev->stats.tx_dropped++; diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 57428a0cb9dd..1e8a4b411dc6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -1456,7 +1456,7 @@ static int qp_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd, switch (op) { case RES_OP_RESERVE: - count = get_param_l(&in_param); + count = get_param_l(&in_param) & 0xffffff; align = get_param_h(&in_param); err = mlx4_grant_resource(dev, slave, RES_QP, count, 0); if (err) diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 68026f7e8ba3..4a474dd9c910 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -872,6 +872,10 @@ static int myri10ge_dma_test(struct myri10ge_priv *mgp, int test_type) return -ENOMEM; dmatest_bus = pci_map_page(mgp->pdev, dmatest_page, 0, PAGE_SIZE, DMA_BIDIRECTIONAL); + if (unlikely(pci_dma_mapping_error(mgp->pdev, dmatest_bus))) { + __free_page(dmatest_page); + return -ENOMEM; + } /* Run a small DMA test. * The magic multipliers to the length tell the firmware @@ -1293,6 +1297,7 @@ myri10ge_alloc_rx_pages(struct myri10ge_priv *mgp, struct myri10ge_rx_buf *rx, int bytes, int watchdog) { struct page *page; + dma_addr_t bus; int idx; #if MYRI10GE_ALLOC_SIZE > 4096 int end_offset; @@ -1317,11 +1322,21 @@ myri10ge_alloc_rx_pages(struct myri10ge_priv *mgp, struct myri10ge_rx_buf *rx, rx->watchdog_needed = 1; return; } + + bus = pci_map_page(mgp->pdev, page, 0, + MYRI10GE_ALLOC_SIZE, + PCI_DMA_FROMDEVICE); + if (unlikely(pci_dma_mapping_error(mgp->pdev, bus))) { + __free_pages(page, MYRI10GE_ALLOC_ORDER); + if (rx->fill_cnt - rx->cnt < 16) + rx->watchdog_needed = 1; + return; + } + rx->page = page; rx->page_offset = 0; - rx->bus = pci_map_page(mgp->pdev, page, 0, - MYRI10GE_ALLOC_SIZE, - PCI_DMA_FROMDEVICE); + rx->bus = bus; + } rx->info[idx].page = rx->page; rx->info[idx].page_offset = rx->page_offset; @@ -2765,6 +2780,35 @@ myri10ge_submit_req(struct myri10ge_tx_buf *tx, struct mcp_kreq_ether_send *src, mb(); } +static void myri10ge_unmap_tx_dma(struct myri10ge_priv *mgp, + struct myri10ge_tx_buf *tx, int idx) +{ + unsigned int len; + int last_idx; + + /* Free any DMA resources we've alloced and clear out the skb slot */ + last_idx = (idx + 1) & tx->mask; + idx = tx->req & tx->mask; + do { + len = dma_unmap_len(&tx->info[idx], len); + if (len) { + if (tx->info[idx].skb != NULL) + pci_unmap_single(mgp->pdev, + dma_unmap_addr(&tx->info[idx], + bus), len, + PCI_DMA_TODEVICE); + else + pci_unmap_page(mgp->pdev, + dma_unmap_addr(&tx->info[idx], + bus), len, + PCI_DMA_TODEVICE); + dma_unmap_len_set(&tx->info[idx], len, 0); + tx->info[idx].skb = NULL; + } + idx = (idx + 1) & tx->mask; + } while (idx != last_idx); +} + /* * Transmit a packet. We need to split the packet so that a single * segment does not cross myri10ge->tx_boundary, so this makes segment @@ -2788,7 +2832,7 @@ static netdev_tx_t myri10ge_xmit(struct sk_buff *skb, u32 low; __be32 high_swapped; unsigned int len; - int idx, last_idx, avail, frag_cnt, frag_idx, count, mss, max_segments; + int idx, avail, frag_cnt, frag_idx, count, mss, max_segments; u16 pseudo_hdr_offset, cksum_offset, queue; int cum_len, seglen, boundary, rdma_count; u8 flags, odd_flag; @@ -2885,9 +2929,12 @@ again: /* map the skb for DMA */ len = skb_headlen(skb); + bus = pci_map_single(mgp->pdev, skb->data, len, PCI_DMA_TODEVICE); + if (unlikely(pci_dma_mapping_error(mgp->pdev, bus))) + goto drop; + idx = tx->req & tx->mask; tx->info[idx].skb = skb; - bus = pci_map_single(mgp->pdev, skb->data, len, PCI_DMA_TODEVICE); dma_unmap_addr_set(&tx->info[idx], bus, bus); dma_unmap_len_set(&tx->info[idx], len, len); @@ -2986,12 +3033,16 @@ again: break; /* map next fragment for DMA */ - idx = (count + tx->req) & tx->mask; frag = &skb_shinfo(skb)->frags[frag_idx]; frag_idx++; len = skb_frag_size(frag); bus = skb_frag_dma_map(&mgp->pdev->dev, frag, 0, len, DMA_TO_DEVICE); + if (unlikely(pci_dma_mapping_error(mgp->pdev, bus))) { + myri10ge_unmap_tx_dma(mgp, tx, idx); + goto drop; + } + idx = (count + tx->req) & tx->mask; dma_unmap_addr_set(&tx->info[idx], bus, bus); dma_unmap_len_set(&tx->info[idx], len, len); } @@ -3022,31 +3073,8 @@ again: return NETDEV_TX_OK; abort_linearize: - /* Free any DMA resources we've alloced and clear out the skb - * slot so as to not trip up assertions, and to avoid a - * double-free if linearizing fails */ + myri10ge_unmap_tx_dma(mgp, tx, idx); - last_idx = (idx + 1) & tx->mask; - idx = tx->req & tx->mask; - tx->info[idx].skb = NULL; - do { - len = dma_unmap_len(&tx->info[idx], len); - if (len) { - if (tx->info[idx].skb != NULL) - pci_unmap_single(mgp->pdev, - dma_unmap_addr(&tx->info[idx], - bus), len, - PCI_DMA_TODEVICE); - else - pci_unmap_page(mgp->pdev, - dma_unmap_addr(&tx->info[idx], - bus), len, - PCI_DMA_TODEVICE); - dma_unmap_len_set(&tx->info[idx], len, 0); - tx->info[idx].skb = NULL; - } - idx = (idx + 1) & tx->mask; - } while (idx != last_idx); if (skb_is_gso(skb)) { netdev_err(mgp->dev, "TSO but wanted to linearize?!?!?\n"); goto drop; diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index 70849dea32b1..5fa076fd439e 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -2390,7 +2390,10 @@ static int netxen_nic_poll(struct napi_struct *napi, int budget) work_done = netxen_process_rcv_ring(sds_ring, budget); - if ((work_done < budget) && tx_complete) { + if (!tx_complete) + work_done = budget; + + if (work_done < budget) { napi_complete(&sds_ring->napi); if (test_bit(__NX_DEV_UP, &adapter->state)) netxen_nic_enable_int(sds_ring); diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c index 6382b7c416f4..e10f5ed26181 100644 --- a/drivers/net/ethernet/smsc/smsc911x.c +++ b/drivers/net/ethernet/smsc/smsc911x.c @@ -1341,6 +1341,42 @@ static void smsc911x_rx_multicast_update_workaround(struct smsc911x_data *pdata) spin_unlock(&pdata->mac_lock); } +static int smsc911x_phy_general_power_up(struct smsc911x_data *pdata) +{ + int rc = 0; + + if (!pdata->phy_dev) + return rc; + + /* If the internal PHY is in General Power-Down mode, all, except the + * management interface, is powered-down and stays in that condition as + * long as Phy register bit 0.11 is HIGH. + * + * In that case, clear the bit 0.11, so the PHY powers up and we can + * access to the phy registers. + */ + rc = phy_read(pdata->phy_dev, MII_BMCR); + if (rc < 0) { + SMSC_WARN(pdata, drv, "Failed reading PHY control reg"); + return rc; + } + + /* If the PHY general power-down bit is not set is not necessary to + * disable the general power down-mode. + */ + if (rc & BMCR_PDOWN) { + rc = phy_write(pdata->phy_dev, MII_BMCR, rc & ~BMCR_PDOWN); + if (rc < 0) { + SMSC_WARN(pdata, drv, "Failed writing PHY control reg"); + return rc; + } + + usleep_range(1000, 1500); + } + + return 0; +} + static int smsc911x_phy_disable_energy_detect(struct smsc911x_data *pdata) { int rc = 0; @@ -1414,6 +1450,16 @@ static int smsc911x_soft_reset(struct smsc911x_data *pdata) int ret; /* + * Make sure to power-up the PHY chip before doing a reset, otherwise + * the reset fails. + */ + ret = smsc911x_phy_general_power_up(pdata); + if (ret) { + SMSC_WARN(pdata, drv, "Failed to power-up the PHY chip"); + return ret; + } + + /* * LAN9210/LAN9211/LAN9220/LAN9221 chips have an internal PHY that * are initialized in a Energy Detect Power-Down mode that prevents * the MAC chip to be software reseted. So we have to wakeup the PHY diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index fd411d6e19a2..03ae9def0e0c 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -656,7 +656,7 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev) spin_lock_irqsave(&port->vio.lock, flags); dr = &port->vio.drings[VIO_DRIVER_TX_RING]; - if (unlikely(vnet_tx_dring_avail(dr) < 2)) { + if (unlikely(vnet_tx_dring_avail(dr) < 1)) { if (!netif_queue_stopped(dev)) { netif_stop_queue(dev); @@ -704,7 +704,7 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev) dev->stats.tx_bytes += skb->len; dr->prod = (dr->prod + 1) & (VNET_TX_RING_SIZE - 1); - if (unlikely(vnet_tx_dring_avail(dr) < 2)) { + if (unlikely(vnet_tx_dring_avail(dr) < 1)) { netif_stop_queue(dev); if (vnet_tx_dring_avail(dr) > VNET_TX_WAKEUP_THRESH(dr)) netif_wake_queue(dev); diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 921b9df2faca..4eb091da7fb6 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -596,7 +596,7 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable) /* Clear all mcast from ALE */ cpsw_ale_flush_multicast(ale, ALE_ALL_PORTS << - priv->host_port); + priv->host_port, -1); /* Flood All Unicast Packets to Host port */ cpsw_ale_control_set(ale, 0, ALE_P0_UNI_FLOOD, 1); @@ -620,6 +620,12 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable) static void cpsw_ndo_set_rx_mode(struct net_device *ndev) { struct cpsw_priv *priv = netdev_priv(ndev); + int vid; + + if (priv->data.dual_emac) + vid = priv->slaves[priv->emac_port].port_vlan; + else + vid = priv->data.default_vlan; if (ndev->flags & IFF_PROMISC) { /* Enable promiscuous mode */ @@ -631,7 +637,8 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev) } /* Clear all mcast from ALE */ - cpsw_ale_flush_multicast(priv->ale, ALE_ALL_PORTS << priv->host_port); + cpsw_ale_flush_multicast(priv->ale, ALE_ALL_PORTS << priv->host_port, + vid); if (!netdev_mc_empty(ndev)) { struct netdev_hw_addr *ha; @@ -716,6 +723,14 @@ static void cpsw_rx_handler(void *token, int len, int status) static irqreturn_t cpsw_interrupt(int irq, void *dev_id) { struct cpsw_priv *priv = dev_id; + int value = irq - priv->irqs_table[0]; + + /* NOTICE: Ending IRQ here. The trick with the 'value' variable above + * is to make sure we will always write the correct value to the EOI + * register. Namely 0 for RX_THRESH Interrupt, 1 for RX Interrupt, 2 + * for TX Interrupt and 3 for MISC Interrupt. + */ + cpdma_ctlr_eoi(priv->dma, value); cpsw_intr_disable(priv); if (priv->irq_enabled == true) { @@ -745,8 +760,6 @@ static int cpsw_poll(struct napi_struct *napi, int budget) int num_tx, num_rx; num_tx = cpdma_chan_process(priv->txch, 128); - if (num_tx) - cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_TX); num_rx = cpdma_chan_process(priv->rxch, budget); if (num_rx < budget) { @@ -754,7 +767,6 @@ static int cpsw_poll(struct napi_struct *napi, int budget) napi_complete(napi); cpsw_intr_enable(priv); - cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_RX); prim_cpsw = cpsw_get_slave_priv(priv, 0); if (prim_cpsw->irq_enabled == false) { prim_cpsw->irq_enabled = true; @@ -1265,8 +1277,6 @@ static int cpsw_ndo_open(struct net_device *ndev) napi_enable(&priv->napi); cpdma_ctlr_start(priv->dma); cpsw_intr_enable(priv); - cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_RX); - cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_TX); if (priv->data.dual_emac) priv->slaves[priv->emac_port].open_stat = true; @@ -1512,9 +1522,6 @@ static void cpsw_ndo_tx_timeout(struct net_device *ndev) cpdma_chan_start(priv->txch); cpdma_ctlr_int_ctrl(priv->dma, true); cpsw_intr_enable(priv); - cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_RX); - cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_TX); - } static int cpsw_ndo_set_mac_address(struct net_device *ndev, void *p) @@ -1560,9 +1567,6 @@ static void cpsw_ndo_poll_controller(struct net_device *ndev) cpsw_interrupt(ndev->irq, priv); cpdma_ctlr_int_ctrl(priv->dma, true); cpsw_intr_enable(priv); - cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_RX); - cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_TX); - } #endif @@ -1606,6 +1610,19 @@ static int cpsw_ndo_vlan_rx_add_vid(struct net_device *ndev, if (vid == priv->data.default_vlan) return 0; + if (priv->data.dual_emac) { + /* In dual EMAC, reserved VLAN id should not be used for + * creating VLAN interfaces as this can break the dual + * EMAC port separation + */ + int i; + + for (i = 0; i < priv->data.slaves; i++) { + if (vid == priv->slaves[i].port_vlan) + return -EINVAL; + } + } + dev_info(priv->dev, "Adding vlanid %d to vlan filter\n", vid); return cpsw_add_vlan_ale_entry(priv, vid); } @@ -1619,6 +1636,15 @@ static int cpsw_ndo_vlan_rx_kill_vid(struct net_device *ndev, if (vid == priv->data.default_vlan) return 0; + if (priv->data.dual_emac) { + int i; + + for (i = 0; i < priv->data.slaves; i++) { + if (vid == priv->slaves[i].port_vlan) + return -EINVAL; + } + } + dev_info(priv->dev, "removing vlanid %d from vlan filter\n", vid); ret = cpsw_ale_del_vlan(priv->ale, vid, 0); if (ret != 0) diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index 7f893069c418..4eceb7e42c80 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -236,7 +236,7 @@ static void cpsw_ale_flush_mcast(struct cpsw_ale *ale, u32 *ale_entry, cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE); } -int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask) +int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid) { u32 ale_entry[ALE_ENTRY_WORDS]; int ret, idx; @@ -247,6 +247,14 @@ int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask) if (ret != ALE_TYPE_ADDR && ret != ALE_TYPE_VLAN_ADDR) continue; + /* if vid passed is -1 then remove all multicast entry from + * the table irrespective of vlan id, if a valid vlan id is + * passed then remove only multicast added to that vlan id. + * if vlan id doesn't match then move on to next entry. + */ + if (vid != -1 && cpsw_ale_get_vlan_id(ale_entry) != vid) + continue; + if (cpsw_ale_get_mcast(ale_entry)) { u8 addr[6]; diff --git a/drivers/net/ethernet/ti/cpsw_ale.h b/drivers/net/ethernet/ti/cpsw_ale.h index de409c33b250..e701358fd00b 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.h +++ b/drivers/net/ethernet/ti/cpsw_ale.h @@ -88,7 +88,7 @@ void cpsw_ale_stop(struct cpsw_ale *ale); int cpsw_ale_set_ageout(struct cpsw_ale *ale, int ageout); int cpsw_ale_flush(struct cpsw_ale *ale, int port_mask); -int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask); +int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid); int cpsw_ale_add_ucast(struct cpsw_ale *ale, u8 *addr, int port, int flags, u16 vid); int cpsw_ale_del_ucast(struct cpsw_ale *ale, u8 *addr, int port, diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index d6fce9750b95..3c1c33ceffba 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -146,6 +146,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net) struct hv_netvsc_packet *packet; int ret; unsigned int i, num_pages, npg_data; + u32 skb_length = skb->len; /* Add multipages for skb->data and additional 2 for RNDIS */ npg_data = (((unsigned long)skb->data + skb_headlen(skb) - 1) @@ -216,7 +217,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net) ret = rndis_filter_send(net_device_ctx->device_ctx, packet); if (ret == 0) { - net->stats.tx_bytes += skb->len; + net->stats.tx_bytes += skb_length; net->stats.tx_packets++; } else { kfree(packet); diff --git a/drivers/net/ieee802154/fakehard.c b/drivers/net/ieee802154/fakehard.c index bf0d55e2dd63..6adbef89c4b0 100644 --- a/drivers/net/ieee802154/fakehard.c +++ b/drivers/net/ieee802154/fakehard.c @@ -376,17 +376,20 @@ static int ieee802154fake_probe(struct platform_device *pdev) err = wpan_phy_register(phy); if (err) - goto out; + goto err_phy_reg; err = register_netdev(dev); - if (err < 0) - goto out; + if (err) + goto err_netdev_reg; dev_info(&pdev->dev, "Added ieee802154 HardMAC hardware\n"); return 0; -out: - unregister_netdev(dev); +err_netdev_reg: + wpan_phy_unregister(phy); +err_phy_reg: + free_netdev(dev); + wpan_phy_free(phy); return err; } diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 7f1abb7c18f2..fbf7dcdc22b0 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -709,6 +709,7 @@ static netdev_features_t macvlan_fix_features(struct net_device *dev, features, mask); features |= ALWAYS_ON_FEATURES; + features &= ~NETIF_F_NETNS_LOCAL; return features; } diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 3381c4f91a8c..e8c21f911b6f 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -16,6 +16,7 @@ #include <linux/idr.h> #include <linux/fs.h> +#include <net/ipv6.h> #include <net/net_namespace.h> #include <net/rtnetlink.h> #include <net/sock.h> @@ -112,17 +113,15 @@ out: return err; } +/* Requires RTNL */ static int macvtap_set_queue(struct net_device *dev, struct file *file, struct macvtap_queue *q) { struct macvlan_dev *vlan = netdev_priv(dev); - int err = -EBUSY; - rtnl_lock(); if (vlan->numqueues == MAX_MACVTAP_QUEUES) - goto out; + return -EBUSY; - err = 0; rcu_assign_pointer(q->vlan, vlan); rcu_assign_pointer(vlan->taps[vlan->numvtaps], q); sock_hold(&q->sk); @@ -136,9 +135,7 @@ static int macvtap_set_queue(struct net_device *dev, struct file *file, vlan->numvtaps++; vlan->numqueues++; -out: - rtnl_unlock(); - return err; + return 0; } static int macvtap_disable_queue(struct macvtap_queue *q) @@ -454,11 +451,12 @@ static void macvtap_sock_destruct(struct sock *sk) static int macvtap_open(struct inode *inode, struct file *file) { struct net *net = current->nsproxy->net_ns; - struct net_device *dev = dev_get_by_macvtap_minor(iminor(inode)); + struct net_device *dev; struct macvtap_queue *q; - int err; + int err = -ENODEV; - err = -ENODEV; + rtnl_lock(); + dev = dev_get_by_macvtap_minor(iminor(inode)); if (!dev) goto out; @@ -498,6 +496,7 @@ out: if (dev) dev_put(dev); + rtnl_unlock(); return err; } @@ -572,6 +571,8 @@ static int macvtap_skb_from_vnet_hdr(struct sk_buff *skb, break; case VIRTIO_NET_HDR_GSO_UDP: gso_type = SKB_GSO_UDP; + if (skb->protocol == htons(ETH_P_IPV6)) + ipv6_proxy_select_ident(skb); break; default: return -EINVAL; @@ -628,18 +629,23 @@ static void macvtap_skb_to_vnet_hdr(const struct sk_buff *skb, if (skb->ip_summed == CHECKSUM_PARTIAL) { vnet_hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; vnet_hdr->csum_start = skb_checksum_start_offset(skb); + if (vlan_tx_tag_present(skb)) + vnet_hdr->csum_start += VLAN_HLEN; vnet_hdr->csum_offset = skb->csum_offset; } else if (skb->ip_summed == CHECKSUM_UNNECESSARY) { vnet_hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID; } /* else everything is zero */ } +/* Neighbour code has some assumptions on HH_DATA_MOD alignment */ +#define MACVTAP_RESERVE HH_DATA_OFF(ETH_HLEN) + /* Get packet from user space buffer */ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, const struct iovec *iv, unsigned long total_len, size_t count, int noblock) { - int good_linear = SKB_MAX_HEAD(NET_IP_ALIGN); + int good_linear = SKB_MAX_HEAD(MACVTAP_RESERVE); struct sk_buff *skb; struct macvlan_dev *vlan; unsigned long len = total_len; @@ -698,7 +704,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, linear = vnet_hdr.hdr_len; } - skb = macvtap_alloc_skb(&q->sk, NET_IP_ALIGN, copylen, + skb = macvtap_alloc_skb(&q->sk, MACVTAP_RESERVE, copylen, linear, noblock, &err); if (!skb) goto err; diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 76d96b9ebcdb..1d568788c3e3 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -194,6 +194,25 @@ static inline unsigned int phy_find_valid(unsigned int idx, u32 features) } /** + * phy_check_valid - check if there is a valid PHY setting which matches + * speed, duplex, and feature mask + * @speed: speed to match + * @duplex: duplex to match + * @features: A mask of the valid settings + * + * Description: Returns true if there is a valid setting, false otherwise. + */ +static inline bool phy_check_valid(int speed, int duplex, u32 features) +{ + unsigned int idx; + + idx = phy_find_valid(phy_find_setting(speed, duplex), features); + + return settings[idx].speed == speed && settings[idx].duplex == duplex && + (settings[idx].setting & features); +} + +/** * phy_sanitize_settings - make sure the PHY is set to supported speed and duplex * @phydev: the target phy_device struct * @@ -955,7 +974,6 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable) int eee_lp, eee_cap, eee_adv; u32 lp, cap, adv; int status; - unsigned int idx; /* Read phy status to properly get the right settings */ status = phy_read_status(phydev); @@ -987,8 +1005,7 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable) adv = mmd_eee_adv_to_ethtool_adv_t(eee_adv); lp = mmd_eee_adv_to_ethtool_adv_t(eee_lp); - idx = phy_find_setting(phydev->speed, phydev->duplex); - if (!(lp & adv & settings[idx].setting)) + if (!phy_check_valid(phydev->speed, phydev->duplex, lp & adv)) return -EPROTONOSUPPORT; if (clk_stop_enable) { diff --git a/drivers/net/ppp/ppp_deflate.c b/drivers/net/ppp/ppp_deflate.c index 602c625d95d5..b5edc7f96a39 100644 --- a/drivers/net/ppp/ppp_deflate.c +++ b/drivers/net/ppp/ppp_deflate.c @@ -246,7 +246,7 @@ static int z_compress(void *arg, unsigned char *rptr, unsigned char *obuf, /* * See if we managed to reduce the size of the packet. */ - if (olen < isize) { + if (olen < isize && olen <= osize) { state->stats.comp_bytes += olen; state->stats.comp_packets++; } else { diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 72ff14b811c6..5a1897d86e94 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -601,7 +601,7 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (file == ppp->owner) ppp_shutdown_interface(ppp); } - if (atomic_long_read(&file->f_count) <= 2) { + if (atomic_long_read(&file->f_count) < 2) { ppp_release(NULL, file); err = 0; } else diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index 1aff970be33e..1dc628ffce2b 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -506,7 +506,9 @@ static int pptp_getname(struct socket *sock, struct sockaddr *uaddr, int len = sizeof(struct sockaddr_pppox); struct sockaddr_pppox sp; - sp.sa_family = AF_PPPOX; + memset(&sp.sa_addr, 0, sizeof(sp.sa_addr)); + + sp.sa_family = AF_PPPOX; sp.sa_protocol = PX_PROTO_PPTP; sp.sa_addr.pptp = pppox_sk(sock->sk)->proto.pptp.src_addr; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 26d8c29b59de..c28e2dafb3f0 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -42,9 +42,7 @@ static struct team_port *team_port_get_rcu(const struct net_device *dev) { - struct team_port *port = rcu_dereference(dev->rx_handler_data); - - return team_port_exists(dev) ? port : NULL; + return rcu_dereference(dev->rx_handler_data); } static struct team_port *team_port_get_rtnl(const struct net_device *dev) @@ -629,6 +627,7 @@ static int team_change_mode(struct team *team, const char *kind) static void team_notify_peers_work(struct work_struct *work) { struct team *team; + int val; team = container_of(work, struct team, notify_peers.dw.work); @@ -636,9 +635,14 @@ static void team_notify_peers_work(struct work_struct *work) schedule_delayed_work(&team->notify_peers.dw, 0); return; } + val = atomic_dec_if_positive(&team->notify_peers.count_pending); + if (val < 0) { + rtnl_unlock(); + return; + } call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, team->dev); rtnl_unlock(); - if (!atomic_dec_and_test(&team->notify_peers.count_pending)) + if (val) schedule_delayed_work(&team->notify_peers.dw, msecs_to_jiffies(team->notify_peers.interval)); } @@ -647,7 +651,7 @@ static void team_notify_peers(struct team *team) { if (!team->notify_peers.count || !netif_running(team->dev)) return; - atomic_set(&team->notify_peers.count_pending, team->notify_peers.count); + atomic_add(team->notify_peers.count, &team->notify_peers.count_pending); schedule_delayed_work(&team->notify_peers.dw, 0); } @@ -669,6 +673,7 @@ static void team_notify_peers_fini(struct team *team) static void team_mcast_rejoin_work(struct work_struct *work) { struct team *team; + int val; team = container_of(work, struct team, mcast_rejoin.dw.work); @@ -676,9 +681,14 @@ static void team_mcast_rejoin_work(struct work_struct *work) schedule_delayed_work(&team->mcast_rejoin.dw, 0); return; } + val = atomic_dec_if_positive(&team->mcast_rejoin.count_pending); + if (val < 0) { + rtnl_unlock(); + return; + } call_netdevice_notifiers(NETDEV_RESEND_IGMP, team->dev); rtnl_unlock(); - if (!atomic_dec_and_test(&team->mcast_rejoin.count_pending)) + if (val) schedule_delayed_work(&team->mcast_rejoin.dw, msecs_to_jiffies(team->mcast_rejoin.interval)); } @@ -687,7 +697,7 @@ static void team_mcast_rejoin(struct team *team) { if (!team->mcast_rejoin.count || !netif_running(team->dev)) return; - atomic_set(&team->mcast_rejoin.count_pending, team->mcast_rejoin.count); + atomic_add(team->mcast_rejoin.count, &team->mcast_rejoin.count_pending); schedule_delayed_work(&team->mcast_rejoin.dw, 0); } @@ -1713,11 +1723,11 @@ static int team_set_mac_address(struct net_device *dev, void *p) if (dev->type == ARPHRD_ETHER && !is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); - rcu_read_lock(); - list_for_each_entry_rcu(port, &team->port_list, list) + mutex_lock(&team->lock); + list_for_each_entry(port, &team->port_list, list) if (team->ops.port_change_dev_addr) team->ops.port_change_dev_addr(team, port); - rcu_read_unlock(); + mutex_unlock(&team->lock); return 0; } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 26f8635b027d..ec63314d6480 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -65,6 +65,7 @@ #include <linux/nsproxy.h> #include <linux/virtio_net.h> #include <linux/rcupdate.h> +#include <net/ipv6.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> @@ -1140,6 +1141,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, break; } + skb_reset_network_header(skb); + if (gso.gso_type != VIRTIO_NET_HDR_GSO_NONE) { pr_debug("GSO!\n"); switch (gso.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { @@ -1151,6 +1154,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, break; case VIRTIO_NET_HDR_GSO_UDP: skb_shinfo(skb)->gso_type = SKB_GSO_UDP; + if (skb->protocol == htons(ETH_P_IPV6)) + ipv6_proxy_select_ident(skb); break; default: tun->dev->stats.rx_frame_errors++; @@ -1180,7 +1185,6 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; } - skb_reset_network_header(skb); skb_probe_transport_header(skb, 0); rxhash = skb_get_hash(skb); @@ -1222,6 +1226,10 @@ static ssize_t tun_put_user(struct tun_struct *tun, struct tun_pi pi = { 0, skb->protocol }; ssize_t total = 0; int vlan_offset = 0, copied; + int vlan_hlen = 0; + + if (vlan_tx_tag_present(skb)) + vlan_hlen = VLAN_HLEN; if (!(tun->flags & TUN_NO_PI)) { if ((len -= sizeof(pi)) < 0) @@ -1273,7 +1281,8 @@ static ssize_t tun_put_user(struct tun_struct *tun, if (skb->ip_summed == CHECKSUM_PARTIAL) { gso.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; - gso.csum_start = skb_checksum_start_offset(skb); + gso.csum_start = skb_checksum_start_offset(skb) + + vlan_hlen; gso.csum_offset = skb->csum_offset; } else if (skb->ip_summed == CHECKSUM_UNNECESSARY) { gso.flags = VIRTIO_NET_HDR_F_DATA_VALID; @@ -1286,10 +1295,9 @@ static ssize_t tun_put_user(struct tun_struct *tun, } copied = total; - total += skb->len; - if (!vlan_tx_tag_present(skb)) { - len = min_t(int, skb->len, len); - } else { + len = min_t(int, skb->len + vlan_hlen, len); + total += skb->len + vlan_hlen; + if (vlan_hlen) { int copy, ret; struct { __be16 h_vlan_proto; @@ -1300,8 +1308,6 @@ static ssize_t tun_put_user(struct tun_struct *tun, veth.h_vlan_TCI = htons(vlan_tx_tag_get(skb)); vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto); - len = min_t(int, skb->len + VLAN_HLEN, len); - total += VLAN_HLEN; copy = min_t(int, vlan_offset, len); ret = skb_copy_datagram_const_iovec(skb, 0, iv, copied, copy); diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 054e59ca6946..8cee173eefb2 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -696,6 +696,7 @@ static int ax88179_set_mac_addr(struct net_device *net, void *p) { struct usbnet *dev = netdev_priv(net); struct sockaddr *addr = p; + int ret; if (netif_running(net)) return -EBUSY; @@ -705,8 +706,12 @@ static int ax88179_set_mac_addr(struct net_device *net, void *p) memcpy(net->dev_addr, addr->sa_data, ETH_ALEN); /* Set the MAC address */ - return ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_NODE_ID, ETH_ALEN, + ret = ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_NODE_ID, ETH_ALEN, ETH_ALEN, net->dev_addr); + if (ret < 0) + return ret; + + return 0; } static const struct net_device_ops ax88179_netdev_ops = { diff --git a/drivers/net/usb/cx82310_eth.c b/drivers/net/usb/cx82310_eth.c index 3eed708a6182..fe48f4c51373 100644 --- a/drivers/net/usb/cx82310_eth.c +++ b/drivers/net/usb/cx82310_eth.c @@ -300,9 +300,18 @@ static const struct driver_info cx82310_info = { .tx_fixup = cx82310_tx_fixup, }; +#define USB_DEVICE_CLASS(vend, prod, cl, sc, pr) \ + .match_flags = USB_DEVICE_ID_MATCH_DEVICE | \ + USB_DEVICE_ID_MATCH_DEV_INFO, \ + .idVendor = (vend), \ + .idProduct = (prod), \ + .bDeviceClass = (cl), \ + .bDeviceSubClass = (sc), \ + .bDeviceProtocol = (pr) + static const struct usb_device_id products[] = { { - USB_DEVICE_AND_INTERFACE_INFO(0x0572, 0xcb01, 0xff, 0, 0), + USB_DEVICE_CLASS(0x0572, 0xcb01, 0xff, 0, 0), .driver_info = (unsigned long) &cx82310_info }, { }, diff --git a/drivers/net/usb/plusb.c b/drivers/net/usb/plusb.c index 3d18bb0eee85..1bfe0fcaccf5 100644 --- a/drivers/net/usb/plusb.c +++ b/drivers/net/usb/plusb.c @@ -134,6 +134,11 @@ static const struct usb_device_id products [] = { }, { USB_DEVICE(0x050d, 0x258a), /* Belkin F5U258/F5U279 (PL-25A1) */ .driver_info = (unsigned long) &prolific_info, +}, { + USB_DEVICE(0x3923, 0x7825), /* National Instruments USB + * Host-to-Host Cable + */ + .driver_info = (unsigned long) &prolific_info, }, { }, // END diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index d510f1d41bae..db21af8de9f6 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -769,6 +769,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81a4, 8)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */ {QMI_FIXED_INTF(0x413c, 0x81a8, 8)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */ {QMI_FIXED_INTF(0x413c, 0x81a9, 8)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */ + {QMI_FIXED_INTF(0x03f0, 0x581d, 4)}, /* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 40ad25d7f28b..5988910db23e 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -279,13 +279,15 @@ static inline struct vxlan_rdst *first_remote_rtnl(struct vxlan_fdb *fdb) return list_first_entry(&fdb->remotes, struct vxlan_rdst, list); } -/* Find VXLAN socket based on network namespace and UDP port */ -static struct vxlan_sock *vxlan_find_sock(struct net *net, __be16 port) +/* Find VXLAN socket based on network namespace, address family and UDP port */ +static struct vxlan_sock *vxlan_find_sock(struct net *net, + sa_family_t family, __be16 port) { struct vxlan_sock *vs; hlist_for_each_entry_rcu(vs, vs_head(net, port), hlist) { - if (inet_sk(vs->sock->sk)->inet_sport == port) + if (inet_sk(vs->sock->sk)->inet_sport == port && + inet_sk(vs->sock->sk)->sk.sk_family == family) return vs; } return NULL; @@ -304,11 +306,12 @@ static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, u32 id) } /* Look up VNI in a per net namespace table */ -static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id, __be16 port) +static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id, + sa_family_t family, __be16 port) { struct vxlan_sock *vs; - vs = vxlan_find_sock(net, port); + vs = vxlan_find_sock(net, family, port); if (!vs) return NULL; @@ -1334,7 +1337,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb) } else if (vxlan->flags & VXLAN_F_L3MISS) { union vxlan_addr ipa = { .sin.sin_addr.s_addr = tip, - .sa.sa_family = AF_INET, + .sin.sin_family = AF_INET, }; vxlan_ip_miss(dev, &ipa); @@ -1447,9 +1450,6 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb) if (!in6_dev) goto out; - if (!pskb_may_pull(skb, skb->len)) - goto out; - iphdr = ipv6_hdr(skb); saddr = &iphdr->saddr; daddr = &iphdr->daddr; @@ -1495,7 +1495,7 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb) } else if (vxlan->flags & VXLAN_F_L3MISS) { union vxlan_addr ipa = { .sin6.sin6_addr = msg->target, - .sa.sa_family = AF_INET6, + .sin6.sin6_family = AF_INET6, }; vxlan_ip_miss(dev, &ipa); @@ -1528,7 +1528,7 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) if (!n && (vxlan->flags & VXLAN_F_L3MISS)) { union vxlan_addr ipa = { .sin.sin_addr.s_addr = pip->daddr, - .sa.sa_family = AF_INET, + .sin.sin_family = AF_INET, }; vxlan_ip_miss(dev, &ipa); @@ -1549,7 +1549,7 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) if (!n && (vxlan->flags & VXLAN_F_L3MISS)) { union vxlan_addr ipa = { .sin6.sin6_addr = pip6->daddr, - .sa.sa_family = AF_INET6, + .sin6.sin6_family = AF_INET6, }; vxlan_ip_miss(dev, &ipa); @@ -1770,6 +1770,8 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, struct pcpu_sw_netstats *tx_stats, *rx_stats; union vxlan_addr loopback; union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip; + struct net_device *dev = skb->dev; + int len = skb->len; tx_stats = this_cpu_ptr(src_vxlan->dev->tstats); rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats); @@ -1793,16 +1795,16 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, u64_stats_update_begin(&tx_stats->syncp); tx_stats->tx_packets++; - tx_stats->tx_bytes += skb->len; + tx_stats->tx_bytes += len; u64_stats_update_end(&tx_stats->syncp); if (netif_rx(skb) == NET_RX_SUCCESS) { u64_stats_update_begin(&rx_stats->syncp); rx_stats->rx_packets++; - rx_stats->rx_bytes += skb->len; + rx_stats->rx_bytes += len; u64_stats_update_end(&rx_stats->syncp); } else { - skb->dev->stats.rx_dropped++; + dev->stats.rx_dropped++; } } @@ -1873,7 +1875,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, struct vxlan_dev *dst_vxlan; ip_rt_put(rt); - dst_vxlan = vxlan_find_vni(dev_net(dev), vni, dst_port); + dst_vxlan = vxlan_find_vni(dev_net(dev), vni, + dst->sa.sa_family, dst_port); if (!dst_vxlan) goto tx_error; vxlan_encap_bypass(skb, vxlan, dst_vxlan); @@ -1926,7 +1929,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, struct vxlan_dev *dst_vxlan; dst_release(ndst); - dst_vxlan = vxlan_find_vni(dev_net(dev), vni, dst_port); + dst_vxlan = vxlan_find_vni(dev_net(dev), vni, + dst->sa.sa_family, dst_port); if (!dst_vxlan) goto tx_error; vxlan_encap_bypass(skb, vxlan, dst_vxlan); @@ -1977,7 +1981,8 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) return arp_reduce(dev, skb); #if IS_ENABLED(CONFIG_IPV6) else if (ntohs(eth->h_proto) == ETH_P_IPV6 && - skb->len >= sizeof(struct ipv6hdr) + sizeof(struct nd_msg) && + pskb_may_pull(skb, sizeof(struct ipv6hdr) + + sizeof(struct nd_msg)) && ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) { struct nd_msg *msg; @@ -1986,6 +1991,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) msg->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION) return neigh_reduce(dev, skb); } + eth = eth_hdr(skb); #endif } @@ -2082,6 +2088,7 @@ static int vxlan_init(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id); + bool ipv6 = vxlan->flags & VXLAN_F_IPV6; struct vxlan_sock *vs; int i; @@ -2097,10 +2104,10 @@ static int vxlan_init(struct net_device *dev) spin_lock(&vn->sock_lock); - vs = vxlan_find_sock(dev_net(dev), vxlan->dst_port); - if (vs) { + vs = vxlan_find_sock(dev_net(dev), ipv6 ? AF_INET6 : AF_INET, + vxlan->dst_port); + if (vs && atomic_add_unless(&vs->refcnt, 1, 0)) { /* If we have a socket with same port already, reuse it */ - atomic_inc(&vs->refcnt); vxlan_vs_add_dev(vs, vxlan); } else { /* otherwise make new socket outside of RTNL */ @@ -2565,13 +2572,10 @@ struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port, return vs; spin_lock(&vn->sock_lock); - vs = vxlan_find_sock(net, port); - if (vs) { - if (vs->rcv == rcv) - atomic_inc(&vs->refcnt); - else + vs = vxlan_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port); + if (vs && ((vs->rcv != rcv) || + !atomic_add_unless(&vs->refcnt, 1, 0))) vs = ERR_PTR(-EBUSY); - } spin_unlock(&vn->sock_lock); if (!vs) @@ -2711,7 +2715,8 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, if (data[IFLA_VXLAN_PORT]) vxlan->dst_port = nla_get_be16(data[IFLA_VXLAN_PORT]); - if (vxlan_find_vni(net, vni, vxlan->dst_port)) { + if (vxlan_find_vni(net, vni, use_ipv6 ? AF_INET6 : AF_INET, + vxlan->dst_port)) { pr_info("duplicate VNI %u\n", vni); return -EEXIST; } diff --git a/drivers/net/wireless/ath/ath5k/qcu.c b/drivers/net/wireless/ath/ath5k/qcu.c index 0583c69d26db..ddaad712c59a 100644 --- a/drivers/net/wireless/ath/ath5k/qcu.c +++ b/drivers/net/wireless/ath/ath5k/qcu.c @@ -225,13 +225,7 @@ ath5k_hw_setup_tx_queue(struct ath5k_hw *ah, enum ath5k_tx_queue queue_type, } else { switch (queue_type) { case AR5K_TX_QUEUE_DATA: - for (queue = AR5K_TX_QUEUE_ID_DATA_MIN; - ah->ah_txq[queue].tqi_type != - AR5K_TX_QUEUE_INACTIVE; queue++) { - - if (queue > AR5K_TX_QUEUE_ID_DATA_MAX) - return -EINVAL; - } + queue = queue_info->tqi_subtype; break; case AR5K_TX_QUEUE_UAPSD: queue = AR5K_TX_QUEUE_ID_UAPSD; diff --git a/drivers/net/wireless/ath/ath5k/reset.c b/drivers/net/wireless/ath/ath5k/reset.c index a3399c4f13a9..b9b651ea9851 100644 --- a/drivers/net/wireless/ath/ath5k/reset.c +++ b/drivers/net/wireless/ath/ath5k/reset.c @@ -478,7 +478,7 @@ ath5k_hw_wisoc_reset(struct ath5k_hw *ah, u32 flags) regval = ioread32(reg); iowrite32(regval | val, reg); regval = ioread32(reg); - usleep_range(100, 150); + udelay(100); /* NB: should be atomic */ /* Bring BB/MAC out of reset */ iowrite32(regval & ~val, reg); diff --git a/drivers/net/wireless/ath/ath6kl/hif.h b/drivers/net/wireless/ath/ath6kl/hif.h index 61f6b21fb0ae..dc6bd8cd9b83 100644 --- a/drivers/net/wireless/ath/ath6kl/hif.h +++ b/drivers/net/wireless/ath/ath6kl/hif.h @@ -197,9 +197,9 @@ struct hif_scatter_req { /* bounce buffer for upper layers to copy to/from */ u8 *virt_dma_buf; - struct hif_scatter_item scat_list[1]; - u32 scat_q_depth; + + struct hif_scatter_item scat_list[0]; }; struct ath6kl_irq_proc_registers { diff --git a/drivers/net/wireless/ath/ath6kl/sdio.c b/drivers/net/wireless/ath/ath6kl/sdio.c index 7126bdd4236c..6bf15a331714 100644 --- a/drivers/net/wireless/ath/ath6kl/sdio.c +++ b/drivers/net/wireless/ath/ath6kl/sdio.c @@ -348,7 +348,7 @@ static int ath6kl_sdio_alloc_prep_scat_req(struct ath6kl_sdio *ar_sdio, int i, scat_req_sz, scat_list_sz, size; u8 *virt_buf; - scat_list_sz = (n_scat_entry - 1) * sizeof(struct hif_scatter_item); + scat_list_sz = n_scat_entry * sizeof(struct hif_scatter_item); scat_req_sz = sizeof(*s_req) + scat_list_sz; if (!virt_scat) diff --git a/drivers/net/wireless/ath/ath9k/ar9003_phy.c b/drivers/net/wireless/ath/ath9k/ar9003_phy.c index 09facba1dc6d..390c2de5a73e 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_phy.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_phy.c @@ -647,6 +647,19 @@ static void ar9003_hw_override_ini(struct ath_hw *ah) ah->enabled_cals |= TX_CL_CAL; else ah->enabled_cals &= ~TX_CL_CAL; + + if (AR_SREV_9340(ah) || AR_SREV_9531(ah) || AR_SREV_9550(ah)) { + if (ah->is_clk_25mhz) { + REG_WRITE(ah, AR_RTC_DERIVED_CLK, 0x17c << 1); + REG_WRITE(ah, AR_SLP32_MODE, 0x0010f3d7); + REG_WRITE(ah, AR_SLP32_INC, 0x0001e7ae); + } else { + REG_WRITE(ah, AR_RTC_DERIVED_CLK, 0x261 << 1); + REG_WRITE(ah, AR_SLP32_MODE, 0x0010f400); + REG_WRITE(ah, AR_SLP32_INC, 0x0001e800); + } + udelay(100); + } } static void ar9003_hw_prog_ini(struct ath_hw *ah, diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c index 9078a6c5a74e..dcc14940c9df 100644 --- a/drivers/net/wireless/ath/ath9k/hw.c +++ b/drivers/net/wireless/ath/ath9k/hw.c @@ -858,19 +858,6 @@ static void ath9k_hw_init_pll(struct ath_hw *ah, udelay(RTC_PLL_SETTLE_DELAY); REG_WRITE(ah, AR_RTC_SLEEP_CLK, AR_RTC_FORCE_DERIVED_CLK); - - if (AR_SREV_9340(ah) || AR_SREV_9550(ah)) { - if (ah->is_clk_25mhz) { - REG_WRITE(ah, AR_RTC_DERIVED_CLK, 0x17c << 1); - REG_WRITE(ah, AR_SLP32_MODE, 0x0010f3d7); - REG_WRITE(ah, AR_SLP32_INC, 0x0001e7ae); - } else { - REG_WRITE(ah, AR_RTC_DERIVED_CLK, 0x261 << 1); - REG_WRITE(ah, AR_SLP32_MODE, 0x0010f400); - REG_WRITE(ah, AR_SLP32_INC, 0x0001e800); - } - udelay(100); - } } static void ath9k_hw_init_interrupt_masks(struct ath_hw *ah, diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h index 0acd4b5a4892..32ae0a47fed0 100644 --- a/drivers/net/wireless/ath/ath9k/hw.h +++ b/drivers/net/wireless/ath/ath9k/hw.h @@ -216,8 +216,8 @@ #define AH_WOW_BEACON_MISS BIT(3) enum ath_hw_txq_subtype { - ATH_TXQ_AC_BE = 0, - ATH_TXQ_AC_BK = 1, + ATH_TXQ_AC_BK = 0, + ATH_TXQ_AC_BE = 1, ATH_TXQ_AC_VI = 2, ATH_TXQ_AC_VO = 3, }; diff --git a/drivers/net/wireless/ath/ath9k/mac.c b/drivers/net/wireless/ath/ath9k/mac.c index 5f727588ca27..8f93ed373fb5 100644 --- a/drivers/net/wireless/ath/ath9k/mac.c +++ b/drivers/net/wireless/ath/ath9k/mac.c @@ -311,14 +311,7 @@ int ath9k_hw_setuptxqueue(struct ath_hw *ah, enum ath9k_tx_queue type, q = ATH9K_NUM_TX_QUEUES - 3; break; case ATH9K_TX_QUEUE_DATA: - for (q = 0; q < ATH9K_NUM_TX_QUEUES; q++) - if (ah->txq[q].tqi_type == - ATH9K_TX_QUEUE_INACTIVE) - break; - if (q == ATH9K_NUM_TX_QUEUES) { - ath_err(common, "No available TX queue\n"); - return -1; - } + q = qinfo->tqi_subtype; break; default: ath_err(common, "Invalid TX queue type: %u\n", type); diff --git a/drivers/net/wireless/ath/carl9170/carl9170.h b/drivers/net/wireless/ath/carl9170/carl9170.h index 8596aba34f96..237d0cda1bcb 100644 --- a/drivers/net/wireless/ath/carl9170/carl9170.h +++ b/drivers/net/wireless/ath/carl9170/carl9170.h @@ -256,6 +256,7 @@ struct ar9170 { atomic_t rx_work_urbs; atomic_t rx_pool_urbs; kernel_ulong_t features; + bool usb_ep_cmd_is_bulk; /* firmware settings */ struct completion fw_load_wait; diff --git a/drivers/net/wireless/ath/carl9170/usb.c b/drivers/net/wireless/ath/carl9170/usb.c index ca115f33746f..bc931f6f1f0f 100644 --- a/drivers/net/wireless/ath/carl9170/usb.c +++ b/drivers/net/wireless/ath/carl9170/usb.c @@ -621,9 +621,16 @@ int __carl9170_exec_cmd(struct ar9170 *ar, struct carl9170_cmd *cmd, goto err_free; } - usb_fill_int_urb(urb, ar->udev, usb_sndintpipe(ar->udev, - AR9170_USB_EP_CMD), cmd, cmd->hdr.len + 4, - carl9170_usb_cmd_complete, ar, 1); + if (ar->usb_ep_cmd_is_bulk) + usb_fill_bulk_urb(urb, ar->udev, + usb_sndbulkpipe(ar->udev, AR9170_USB_EP_CMD), + cmd, cmd->hdr.len + 4, + carl9170_usb_cmd_complete, ar); + else + usb_fill_int_urb(urb, ar->udev, + usb_sndintpipe(ar->udev, AR9170_USB_EP_CMD), + cmd, cmd->hdr.len + 4, + carl9170_usb_cmd_complete, ar, 1); if (free_buf) urb->transfer_flags |= URB_FREE_BUFFER; @@ -1032,9 +1039,10 @@ static void carl9170_usb_firmware_step2(const struct firmware *fw, static int carl9170_usb_probe(struct usb_interface *intf, const struct usb_device_id *id) { + struct usb_endpoint_descriptor *ep; struct ar9170 *ar; struct usb_device *udev; - int err; + int i, err; err = usb_reset_device(interface_to_usbdev(intf)); if (err) @@ -1050,6 +1058,21 @@ static int carl9170_usb_probe(struct usb_interface *intf, ar->intf = intf; ar->features = id->driver_info; + /* We need to remember the type of endpoint 4 because it differs + * between high- and full-speed configuration. The high-speed + * configuration specifies it as interrupt and the full-speed + * configuration as bulk endpoint. This information is required + * later when sending urbs to that endpoint. + */ + for (i = 0; i < intf->cur_altsetting->desc.bNumEndpoints; ++i) { + ep = &intf->cur_altsetting->endpoint[i].desc; + + if (usb_endpoint_num(ep) == AR9170_USB_EP_CMD && + usb_endpoint_dir_out(ep) && + usb_endpoint_type(ep) == USB_ENDPOINT_XFER_BULK) + ar->usb_ep_cmd_is_bulk = true; + } + usb_set_intfdata(intf, ar); SET_IEEE80211_DEV(ar->hw, &intf->dev); diff --git a/drivers/net/wireless/brcm80211/brcmfmac/fweh.c b/drivers/net/wireless/brcm80211/brcmfmac/fweh.c index fad77dd2a3a5..3f9cb894d001 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/fweh.c +++ b/drivers/net/wireless/brcm80211/brcmfmac/fweh.c @@ -185,7 +185,13 @@ static void brcmf_fweh_handle_if_event(struct brcmf_pub *drvr, ifevent->action, ifevent->ifidx, ifevent->bssidx, ifevent->flags, ifevent->role); - if (ifevent->flags & BRCMF_E_IF_FLAG_NOIF) { + /* The P2P Device interface event must not be ignored + * contrary to what firmware tells us. The only way to + * distinguish the P2P Device is by looking at the ifidx + * and bssidx received. + */ + if (!(ifevent->ifidx == 0 && ifevent->bssidx == 1) && + (ifevent->flags & BRCMF_E_IF_FLAG_NOIF)) { brcmf_dbg(EVENT, "event can be ignored\n"); return; } @@ -210,12 +216,12 @@ static void brcmf_fweh_handle_if_event(struct brcmf_pub *drvr, return; } - if (ifevent->action == BRCMF_E_IF_CHANGE) + if (ifp && ifevent->action == BRCMF_E_IF_CHANGE) brcmf_fws_reset_interface(ifp); err = brcmf_fweh_call_event_handler(ifp, emsg->event_code, emsg, data); - if (ifevent->action == BRCMF_E_IF_DEL) { + if (ifp && ifevent->action == BRCMF_E_IF_DEL) { brcmf_fws_del_interface(ifp); brcmf_del_if(drvr, ifevent->bssidx); } diff --git a/drivers/net/wireless/brcm80211/brcmfmac/fweh.h b/drivers/net/wireless/brcm80211/brcmfmac/fweh.h index 51b53a73d074..d26b47698f68 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/fweh.h +++ b/drivers/net/wireless/brcm80211/brcmfmac/fweh.h @@ -167,6 +167,8 @@ enum brcmf_fweh_event_code { #define BRCMF_E_IF_ROLE_STA 0 #define BRCMF_E_IF_ROLE_AP 1 #define BRCMF_E_IF_ROLE_WDS 2 +#define BRCMF_E_IF_ROLE_P2P_GO 3 +#define BRCMF_E_IF_ROLE_P2P_CLIENT 4 /** * definitions for event packet validation. diff --git a/drivers/net/wireless/iwlwifi/dvm/dev.h b/drivers/net/wireless/iwlwifi/dvm/dev.h index 3441f70d0ff9..6e8cdb8a0cc5 100644 --- a/drivers/net/wireless/iwlwifi/dvm/dev.h +++ b/drivers/net/wireless/iwlwifi/dvm/dev.h @@ -708,7 +708,6 @@ struct iwl_priv { unsigned long reload_jiffies; int reload_count; bool ucode_loaded; - bool init_ucode_run; /* Don't run init uCode again */ u8 plcp_delta_threshold; diff --git a/drivers/net/wireless/iwlwifi/dvm/rxon.c b/drivers/net/wireless/iwlwifi/dvm/rxon.c index c1e311341b74..503a81e58185 100644 --- a/drivers/net/wireless/iwlwifi/dvm/rxon.c +++ b/drivers/net/wireless/iwlwifi/dvm/rxon.c @@ -1068,6 +1068,13 @@ int iwlagn_commit_rxon(struct iwl_priv *priv, struct iwl_rxon_context *ctx) /* recalculate basic rates */ iwl_calc_basic_rates(priv, ctx); + /* + * force CTS-to-self frames protection if RTS-CTS is not preferred + * one aggregation protection method + */ + if (!priv->hw_params.use_rts_for_aggregation) + ctx->staging.flags |= RXON_FLG_SELF_CTS_EN; + if ((ctx->vif && ctx->vif->bss_conf.use_short_slot) || !(ctx->staging.flags & RXON_FLG_BAND_24G_MSK)) ctx->staging.flags |= RXON_FLG_SHORT_SLOT_MSK; @@ -1473,6 +1480,11 @@ void iwlagn_bss_info_changed(struct ieee80211_hw *hw, else ctx->staging.flags &= ~RXON_FLG_TGG_PROTECT_MSK; + if (bss_conf->use_cts_prot) + ctx->staging.flags |= RXON_FLG_SELF_CTS_EN; + else + ctx->staging.flags &= ~RXON_FLG_SELF_CTS_EN; + memcpy(ctx->staging.bssid_addr, bss_conf->bssid, ETH_ALEN); if (vif->type == NL80211_IFTYPE_AP || diff --git a/drivers/net/wireless/iwlwifi/dvm/ucode.c b/drivers/net/wireless/iwlwifi/dvm/ucode.c index cf03ef5619d9..8b2dedc30159 100644 --- a/drivers/net/wireless/iwlwifi/dvm/ucode.c +++ b/drivers/net/wireless/iwlwifi/dvm/ucode.c @@ -418,9 +418,6 @@ int iwl_run_init_ucode(struct iwl_priv *priv) if (!priv->fw->img[IWL_UCODE_INIT].sec[0].len) return 0; - if (priv->init_ucode_run) - return 0; - iwl_init_notification_wait(&priv->notif_wait, &calib_wait, calib_complete, ARRAY_SIZE(calib_complete), iwlagn_wait_calib, priv); @@ -440,8 +437,6 @@ int iwl_run_init_ucode(struct iwl_priv *priv) */ ret = iwl_wait_notification(&priv->notif_wait, &calib_wait, UCODE_CALIB_TIMEOUT); - if (!ret) - priv->init_ucode_run = true; goto out; diff --git a/drivers/net/wireless/iwlwifi/iwl-config.h b/drivers/net/wireless/iwlwifi/iwl-config.h index 1ced525157dc..b45d78f53f08 100644 --- a/drivers/net/wireless/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/iwlwifi/iwl-config.h @@ -119,6 +119,8 @@ enum iwl_led_mode { #define IWL_LONG_WD_TIMEOUT 10000 #define IWL_MAX_WD_TIMEOUT 120000 +#define IWL_DEFAULT_MAX_TX_POWER 22 + /* Antenna presence definitions */ #define ANT_NONE 0x0 #define ANT_A BIT(0) diff --git a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c index 725e954d8475..3c3eb7842c62 100644 --- a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c +++ b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c @@ -118,8 +118,6 @@ static const u8 iwl_nvm_channels[] = { #define LAST_2GHZ_HT_PLUS 9 #define LAST_5GHZ_HT 161 -#define DEFAULT_MAX_TX_POWER 16 - /* rate data (static) */ static struct ieee80211_rate iwl_cfg80211_rates[] = { { .bitrate = 1 * 10, .hw_value = 0, .hw_value_short = 0, }, @@ -242,7 +240,7 @@ static int iwl_init_channel_map(struct device *dev, const struct iwl_cfg *cfg, * Default value - highest tx power value. max_power * is not used in mvm, and is used for backwards compatibility */ - channel->max_power = DEFAULT_MAX_TX_POWER; + channel->max_power = IWL_DEFAULT_MAX_TX_POWER; is_5ghz = channel->band == IEEE80211_BAND_5GHZ; IWL_DEBUG_EEPROM(dev, "Ch. %d [%sGHz] %s%s%s%s%s%s(0x%02x %ddBm): Ad-Hoc %ssupported\n", diff --git a/drivers/net/wireless/iwlwifi/iwl-trans.h b/drivers/net/wireless/iwlwifi/iwl-trans.h index 1f065cf4a4ba..d090ed79ada0 100644 --- a/drivers/net/wireless/iwlwifi/iwl-trans.h +++ b/drivers/net/wireless/iwlwifi/iwl-trans.h @@ -514,6 +514,7 @@ enum iwl_trans_state { * Set during transport allocation. * @hw_id_str: a string with info about HW ID. Set during transport allocation. * @pm_support: set to true in start_hw if link pm is supported + * @ltr_enabled: set to true if the LTR is enabled * @dev_cmd_pool: pool for Tx cmd allocation - for internal use only. * The user should use iwl_trans_{alloc,free}_tx_cmd. * @dev_cmd_headroom: room needed for the transport's private use before the @@ -539,6 +540,7 @@ struct iwl_trans { u8 rx_mpdu_cmd, rx_mpdu_cmd_hdr_size; bool pm_support; + bool ltr_enabled; /* The following fields are internal only */ struct kmem_cache *dev_cmd_pool; diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h index 884c08725308..fa66471283d9 100644 --- a/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h +++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h @@ -66,13 +66,46 @@ /* Power Management Commands, Responses, Notifications */ +/** + * enum iwl_ltr_config_flags - masks for LTR config command flags + * @LTR_CFG_FLAG_FEATURE_ENABLE: Feature operational status + * @LTR_CFG_FLAG_HW_DIS_ON_SHADOW_REG_ACCESS: allow LTR change on shadow + * memory access + * @LTR_CFG_FLAG_HW_EN_SHRT_WR_THROUGH: allow LTR msg send on ANY LTR + * reg change + * @LTR_CFG_FLAG_HW_DIS_ON_D0_2_D3: allow LTR msg send on transition from + * D0 to D3 + * @LTR_CFG_FLAG_SW_SET_SHORT: fixed static short LTR register + * @LTR_CFG_FLAG_SW_SET_LONG: fixed static short LONG register + * @LTR_CFG_FLAG_DENIE_C10_ON_PD: allow going into C10 on PD + */ +enum iwl_ltr_config_flags { + LTR_CFG_FLAG_FEATURE_ENABLE = BIT(0), + LTR_CFG_FLAG_HW_DIS_ON_SHADOW_REG_ACCESS = BIT(1), + LTR_CFG_FLAG_HW_EN_SHRT_WR_THROUGH = BIT(2), + LTR_CFG_FLAG_HW_DIS_ON_D0_2_D3 = BIT(3), + LTR_CFG_FLAG_SW_SET_SHORT = BIT(4), + LTR_CFG_FLAG_SW_SET_LONG = BIT(5), + LTR_CFG_FLAG_DENIE_C10_ON_PD = BIT(6), +}; + +/** + * struct iwl_ltr_config_cmd - configures the LTR + * @flags: See %enum iwl_ltr_config_flags + */ +struct iwl_ltr_config_cmd { + __le32 flags; + __le32 static_long; + __le32 static_short; +} __packed; + /* Radio LP RX Energy Threshold measured in dBm */ #define POWER_LPRX_RSSI_THRESHOLD 75 #define POWER_LPRX_RSSI_THRESHOLD_MAX 94 #define POWER_LPRX_RSSI_THRESHOLD_MIN 30 /** - * enum iwl_scan_flags - masks for power table command flags + * enum iwl_power_flags - masks for power table command flags * @POWER_FLAGS_POWER_SAVE_ENA_MSK: '1' Allow to save power by turning off * receiver and transmitter. '0' - does not allow. * @POWER_FLAGS_POWER_MANAGEMENT_ENA_MSK: '0' Driver disables power management, diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api.h b/drivers/net/wireless/iwlwifi/mvm/fw-api.h index 989d7dbdca6c..60dc387cc554 100644 --- a/drivers/net/wireless/iwlwifi/mvm/fw-api.h +++ b/drivers/net/wireless/iwlwifi/mvm/fw-api.h @@ -142,6 +142,7 @@ enum { /* Power - legacy power table command */ POWER_TABLE_CMD = 0x77, PSM_UAPSD_AP_MISBEHAVING_NOTIFICATION = 0x78, + LTR_CONFIG = 0xee, /* Thermal Throttling*/ REPLY_THERMAL_MNG_BACKOFF = 0x7e, @@ -1393,7 +1394,7 @@ enum iwl_sf_scenario { #define SF_NUM_TIMEOUT_TYPES 2 /* Aging timer and Idle timer */ /* smart FIFO default values */ -#define SF_W_MARK_SISO 4096 +#define SF_W_MARK_SISO 6144 #define SF_W_MARK_MIMO2 8192 #define SF_W_MARK_MIMO3 6144 #define SF_W_MARK_LEGACY 4096 @@ -1415,14 +1416,14 @@ enum iwl_sf_scenario { /** * Smart Fifo configuration command. - * @state: smart fifo state, types listed in iwl_sf_sate. + * @state: smart fifo state, types listed in enum %iwl_sf_sate. * @watermark: Minimum allowed availabe free space in RXF for transient state. * @long_delay_timeouts: aging and idle timer values for each scenario * in long delay state. * @full_on_timeouts: timer values for each scenario in full on state. */ struct iwl_sf_cfg_cmd { - enum iwl_sf_state state; + __le32 state; __le32 watermark[SF_TRANSIENT_STATES_NUMBER]; __le32 long_delay_timeouts[SF_NUM_SCENARIO][SF_NUM_TIMEOUT_TYPES]; __le32 full_on_timeouts[SF_NUM_SCENARIO][SF_NUM_TIMEOUT_TYPES]; diff --git a/drivers/net/wireless/iwlwifi/mvm/fw.c b/drivers/net/wireless/iwlwifi/mvm/fw.c index c03d39541f9e..2ef344fc0acb 100644 --- a/drivers/net/wireless/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/iwlwifi/mvm/fw.c @@ -439,6 +439,15 @@ int iwl_mvm_up(struct iwl_mvm *mvm) goto error; } + if (mvm->trans->ltr_enabled) { + struct iwl_ltr_config_cmd cmd = { + .flags = cpu_to_le32(LTR_CFG_FLAG_FEATURE_ENABLE), + }; + + WARN_ON(iwl_mvm_send_cmd_pdu(mvm, LTR_CONFIG, 0, + sizeof(cmd), &cmd)); + } + ret = iwl_mvm_power_update_device_mode(mvm); if (ret) goto error; diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c index d06414ef15c5..4a3b8b72c8af 100644 --- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c @@ -410,9 +410,6 @@ static void iwl_mvm_cleanup_iterator(void *data, u8 *mac, mvmvif->uploaded = false; mvmvif->ap_sta_id = IWL_MVM_STATION_COUNT; - /* does this make sense at all? */ - mvmvif->color++; - spin_lock_bh(&mvm->time_event_lock); iwl_mvm_te_clear_data(mvm, &mvmvif->time_event_data); spin_unlock_bh(&mvm->time_event_lock); diff --git a/drivers/net/wireless/iwlwifi/mvm/ops.c b/drivers/net/wireless/iwlwifi/mvm/ops.c index a3d43de342d7..dbff7f0bc6a8 100644 --- a/drivers/net/wireless/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/iwlwifi/mvm/ops.c @@ -313,6 +313,7 @@ static const char *iwl_mvm_cmd_strings[REPLY_MAX] = { CMD(REPLY_BEACON_FILTERING_CMD), CMD(REPLY_THERMAL_MNG_BACKOFF), CMD(MAC_PM_POWER_TABLE), + CMD(LTR_CONFIG), CMD(BT_COEX_CI), CMD(PSM_UAPSD_AP_MISBEHAVING_NOTIFICATION), }; diff --git a/drivers/net/wireless/iwlwifi/mvm/sf.c b/drivers/net/wireless/iwlwifi/mvm/sf.c index 88809b2d1654..dab8fd13857a 100644 --- a/drivers/net/wireless/iwlwifi/mvm/sf.c +++ b/drivers/net/wireless/iwlwifi/mvm/sf.c @@ -172,7 +172,7 @@ 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 = new_state, + .state = cpu_to_le32(new_state), }; struct ieee80211_sta *sta; int ret = 0; diff --git a/drivers/net/wireless/iwlwifi/mvm/tx.c b/drivers/net/wireless/iwlwifi/mvm/tx.c index 76ee486039d7..4efcb2869379 100644 --- a/drivers/net/wireless/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/iwlwifi/mvm/tx.c @@ -835,6 +835,11 @@ int iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb, sta_id = ba_notif->sta_id; tid = ba_notif->tid; + if (WARN_ONCE(sta_id >= IWL_MVM_STATION_COUNT || + tid >= IWL_MAX_TID_COUNT, + "sta_id %d tid %d", sta_id, tid)) + return 0; + rcu_read_lock(); sta = rcu_dereference(mvm->fw_id_to_mac_id[sta_id]); diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c index df1f5e732ab5..1ac33d9cd396 100644 --- a/drivers/net/wireless/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/iwlwifi/pcie/drv.c @@ -272,6 +272,8 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = { {IWL_PCI_DEVICE(0x08B1, 0x4070, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4072, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4170, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0x4C60, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0x4C70, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4060, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x406A, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4160, iwl7260_2n_cfg)}, @@ -315,6 +317,8 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = { {IWL_PCI_DEVICE(0x08B1, 0xC770, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0xC760, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B2, 0xC270, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0xCC70, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0xCC60, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B2, 0xC272, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B2, 0xC260, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B2, 0xC26A, iwl7260_n_cfg)}, diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c index 16be0c07c64a..fb62927ca44d 100644 --- a/drivers/net/wireless/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/iwlwifi/pcie/trans.c @@ -94,6 +94,7 @@ static void iwl_pcie_apm_config(struct iwl_trans *trans) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); u16 lctl; + u16 cap; /* * HW bug W/A for instability in PCIe bus L0S->L1 transition. @@ -104,16 +105,17 @@ static void iwl_pcie_apm_config(struct iwl_trans *trans) * power savings, even without L1. */ pcie_capability_read_word(trans_pcie->pci_dev, PCI_EXP_LNKCTL, &lctl); - if (lctl & PCI_EXP_LNKCTL_ASPM_L1) { - /* L1-ASPM enabled; disable(!) L0S */ + if (lctl & PCI_EXP_LNKCTL_ASPM_L1) iwl_set_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_ENABLED); - dev_info(trans->dev, "L1 Enabled; Disabling L0S\n"); - } else { - /* L1-ASPM disabled; enable(!) L0S */ + else iwl_clear_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_ENABLED); - dev_info(trans->dev, "L1 Disabled; Enabling L0S\n"); - } trans->pm_support = !(lctl & PCI_EXP_LNKCTL_ASPM_L0S); + + pcie_capability_read_word(trans_pcie->pci_dev, PCI_EXP_DEVCTL2, &cap); + trans->ltr_enabled = cap & PCI_EXP_DEVCTL2_LTR_EN; + dev_info(trans->dev, "L1 %sabled - LTR %sabled\n", + (lctl & PCI_EXP_LNKCTL_ASPM_L1) ? "En" : "Dis", + trans->ltr_enabled ? "En" : "Dis"); } /* diff --git a/drivers/net/wireless/iwlwifi/pcie/tx.c b/drivers/net/wireless/iwlwifi/pcie/tx.c index 3d549008b3e2..52427fba22cd 100644 --- a/drivers/net/wireless/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/iwlwifi/pcie/tx.c @@ -729,7 +729,12 @@ void iwl_trans_pcie_tx_reset(struct iwl_trans *trans) iwl_write_direct32(trans, FH_KW_MEM_ADDR_REG, trans_pcie->kw.dma >> 4); - iwl_pcie_tx_start(trans, trans_pcie->scd_base_addr); + /* + * Send 0 as the scd_base_addr since the device may have be reset + * while we were in WoWLAN in which case SCD_SRAM_BASE_ADDR will + * contain garbage. + */ + iwl_pcie_tx_start(trans, 0); } /* diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 69d4c3179d04..505ff601d9f4 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -1974,7 +1974,7 @@ static int mac80211_hwsim_create_radio(int channels, const char *reg_alpha2, if (err != 0) { printk(KERN_DEBUG "mac80211_hwsim: device_bind_driver failed (%d)\n", err); - goto failed_hw; + goto failed_bind; } skb_queue_head_init(&data->pending); @@ -2157,6 +2157,8 @@ static int mac80211_hwsim_create_radio(int channels, const char *reg_alpha2, return idx; failed_hw: + device_release_driver(data->dev); +failed_bind: device_unregister(data->dev); failed_drvdata: ieee80211_free_hw(hw); diff --git a/drivers/net/wireless/rt2x00/rt2800.h b/drivers/net/wireless/rt2x00/rt2800.h index a394a9a95919..ebd5625d13f1 100644 --- a/drivers/net/wireless/rt2x00/rt2800.h +++ b/drivers/net/wireless/rt2x00/rt2800.h @@ -52,6 +52,7 @@ * RF5592 2.4G/5G 2T2R * RF3070 2.4G 1T1R * RF5360 2.4G 1T1R + * RF5362 2.4G 1T1R * RF5370 2.4G 1T1R * RF5390 2.4G 1T1R */ @@ -72,6 +73,7 @@ #define RF3070 0x3070 #define RF3290 0x3290 #define RF5360 0x5360 +#define RF5362 0x5362 #define RF5370 0x5370 #define RF5372 0x5372 #define RF5390 0x5390 @@ -2039,7 +2041,7 @@ struct mac_iveiv_entry { * 2 - drop tx power by 12dBm, * 3 - increase tx power by 6dBm */ -#define BBP1_TX_POWER_CTRL FIELD8(0x07) +#define BBP1_TX_POWER_CTRL FIELD8(0x03) #define BBP1_TX_ANTENNA FIELD8(0x18) /* @@ -2145,7 +2147,7 @@ struct mac_iveiv_entry { /* Bits [7-4] for RF3320 (RT3370/RT3390), on other chipsets reserved */ #define RFCSR3_PA1_BIAS_CCK FIELD8(0x70) #define RFCSR3_PA2_CASCODE_BIAS_CCKK FIELD8(0x80) -/* Bits for RF3290/RF5360/RF5370/RF5372/RF5390/RF5392 */ +/* Bits for RF3290/RF5360/RF5362/RF5370/RF5372/RF5390/RF5392 */ #define RFCSR3_VCOCAL_EN FIELD8(0x80) /* Bits for RF3050 */ #define RFCSR3_BIT1 FIELD8(0x02) diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c index 41d4a8167dc3..4e16d4da9d82 100644 --- a/drivers/net/wireless/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/rt2x00/rt2800lib.c @@ -3142,6 +3142,7 @@ static void rt2800_config_channel(struct rt2x00_dev *rt2x00dev, break; case RF3070: case RF5360: + case RF5362: case RF5370: case RF5372: case RF5390: @@ -3159,6 +3160,7 @@ static void rt2800_config_channel(struct rt2x00_dev *rt2x00dev, rt2x00_rf(rt2x00dev, RF3290) || rt2x00_rf(rt2x00dev, RF3322) || rt2x00_rf(rt2x00dev, RF5360) || + rt2x00_rf(rt2x00dev, RF5362) || rt2x00_rf(rt2x00dev, RF5370) || rt2x00_rf(rt2x00dev, RF5372) || rt2x00_rf(rt2x00dev, RF5390) || @@ -4273,6 +4275,7 @@ void rt2800_vco_calibration(struct rt2x00_dev *rt2x00dev) case RF3070: case RF3290: case RF5360: + case RF5362: case RF5370: case RF5372: case RF5390: @@ -7073,6 +7076,7 @@ static int rt2800_init_eeprom(struct rt2x00_dev *rt2x00dev) case RF3320: case RF3322: case RF5360: + case RF5362: case RF5370: case RF5372: case RF5390: @@ -7529,6 +7533,7 @@ static int rt2800_probe_hw_mode(struct rt2x00_dev *rt2x00dev) case RF3320: case RF3322: case RF5360: + case RF5362: case RF5370: case RF5372: case RF5390: @@ -7658,6 +7663,7 @@ static int rt2800_probe_hw_mode(struct rt2x00_dev *rt2x00dev) case RF3070: case RF3290: case RF5360: + case RF5362: case RF5370: case RF5372: case RF5390: diff --git a/drivers/net/wireless/rt2x00/rt2800usb.c b/drivers/net/wireless/rt2x00/rt2800usb.c index caddc1b427a9..57d3967de32f 100644 --- a/drivers/net/wireless/rt2x00/rt2800usb.c +++ b/drivers/net/wireless/rt2x00/rt2800usb.c @@ -1062,6 +1062,7 @@ static struct usb_device_id rt2800usb_device_table[] = { /* Ovislink */ { USB_DEVICE(0x1b75, 0x3071) }, { USB_DEVICE(0x1b75, 0x3072) }, + { USB_DEVICE(0x1b75, 0xa200) }, /* Para */ { USB_DEVICE(0x20b8, 0x8888) }, /* Pegatron */ @@ -1235,6 +1236,8 @@ static struct usb_device_id rt2800usb_device_table[] = { /* Arcadyan */ { USB_DEVICE(0x043e, 0x7a12) }, { USB_DEVICE(0x043e, 0x7a32) }, + /* ASUS */ + { USB_DEVICE(0x0b05, 0x17e8) }, /* Azurewave */ { USB_DEVICE(0x13d3, 0x3329) }, { USB_DEVICE(0x13d3, 0x3365) }, @@ -1271,6 +1274,7 @@ static struct usb_device_id rt2800usb_device_table[] = { { USB_DEVICE(0x057c, 0x8501) }, /* Buffalo */ { USB_DEVICE(0x0411, 0x0241) }, + { USB_DEVICE(0x0411, 0x0253) }, /* D-Link */ { USB_DEVICE(0x2001, 0x3c1a) }, { USB_DEVICE(0x2001, 0x3c21) }, @@ -1361,6 +1365,7 @@ static struct usb_device_id rt2800usb_device_table[] = { { USB_DEVICE(0x0df6, 0x0053) }, { USB_DEVICE(0x0df6, 0x0069) }, { USB_DEVICE(0x0df6, 0x006f) }, + { USB_DEVICE(0x0df6, 0x0078) }, /* SMC */ { USB_DEVICE(0x083a, 0xa512) }, { USB_DEVICE(0x083a, 0xc522) }, diff --git a/drivers/net/wireless/rt2x00/rt2x00queue.c b/drivers/net/wireless/rt2x00/rt2x00queue.c index 5642ccceca7c..22d49d575d3f 100644 --- a/drivers/net/wireless/rt2x00/rt2x00queue.c +++ b/drivers/net/wireless/rt2x00/rt2x00queue.c @@ -158,55 +158,29 @@ void rt2x00queue_align_frame(struct sk_buff *skb) skb_trim(skb, frame_length); } -void rt2x00queue_insert_l2pad(struct sk_buff *skb, unsigned int header_length) +/* + * H/W needs L2 padding between the header and the paylod if header size + * is not 4 bytes aligned. + */ +void rt2x00queue_insert_l2pad(struct sk_buff *skb, unsigned int hdr_len) { - unsigned int payload_length = skb->len - header_length; - unsigned int header_align = ALIGN_SIZE(skb, 0); - unsigned int payload_align = ALIGN_SIZE(skb, header_length); - unsigned int l2pad = payload_length ? L2PAD_SIZE(header_length) : 0; + unsigned int l2pad = (skb->len > hdr_len) ? L2PAD_SIZE(hdr_len) : 0; - /* - * Adjust the header alignment if the payload needs to be moved more - * than the header. - */ - if (payload_align > header_align) - header_align += 4; - - /* There is nothing to do if no alignment is needed */ - if (!header_align) + if (!l2pad) return; - /* Reserve the amount of space needed in front of the frame */ - skb_push(skb, header_align); - - /* - * Move the header. - */ - memmove(skb->data, skb->data + header_align, header_length); - - /* Move the payload, if present and if required */ - if (payload_length && payload_align) - memmove(skb->data + header_length + l2pad, - skb->data + header_length + l2pad + payload_align, - payload_length); - - /* Trim the skb to the correct size */ - skb_trim(skb, header_length + l2pad + payload_length); + skb_push(skb, l2pad); + memmove(skb->data, skb->data + l2pad, hdr_len); } -void rt2x00queue_remove_l2pad(struct sk_buff *skb, unsigned int header_length) +void rt2x00queue_remove_l2pad(struct sk_buff *skb, unsigned int hdr_len) { - /* - * L2 padding is only present if the skb contains more than just the - * IEEE 802.11 header. - */ - unsigned int l2pad = (skb->len > header_length) ? - L2PAD_SIZE(header_length) : 0; + unsigned int l2pad = (skb->len > hdr_len) ? L2PAD_SIZE(hdr_len) : 0; if (!l2pad) return; - memmove(skb->data + l2pad, skb->data, header_length); + memmove(skb->data + l2pad, skb->data, hdr_len); skb_pull(skb, l2pad); } diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c index c61311084d7e..f58316769159 100644 --- a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c +++ b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c @@ -317,6 +317,7 @@ static struct usb_device_id rtl8192c_usb_ids[] = { {RTL_USB_DEVICE(0x0bda, 0x5088, rtl92cu_hal_cfg)}, /*Thinkware-CC&C*/ {RTL_USB_DEVICE(0x0df6, 0x0052, rtl92cu_hal_cfg)}, /*Sitecom - Edimax*/ {RTL_USB_DEVICE(0x0df6, 0x005c, rtl92cu_hal_cfg)}, /*Sitecom - Edimax*/ + {RTL_USB_DEVICE(0x0df6, 0x0070, rtl92cu_hal_cfg)}, /*Sitecom - 150N */ {RTL_USB_DEVICE(0x0df6, 0x0077, rtl92cu_hal_cfg)}, /*Sitecom-WLA2100V2*/ {RTL_USB_DEVICE(0x0eb0, 0x9071, rtl92cu_hal_cfg)}, /*NO Brand - Etop*/ {RTL_USB_DEVICE(0x4856, 0x0091, rtl92cu_hal_cfg)}, /*NetweeN - Feixun*/ diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index e30d80033cbc..19db057658c5 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -469,9 +469,6 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev, len = skb_frag_size(frag); offset = frag->page_offset; - /* Data must not cross a page boundary. */ - BUG_ON(len + offset > PAGE_SIZE<<compound_order(page)); - /* Skip unused frames from start of page */ page += offset >> PAGE_SHIFT; offset &= ~PAGE_MASK; @@ -479,8 +476,6 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev, while (len > 0) { unsigned long bytes; - BUG_ON(offset >= PAGE_SIZE); - bytes = PAGE_SIZE - offset; if (bytes > len) bytes = len; diff --git a/drivers/nfc/microread/microread.c b/drivers/nfc/microread/microread.c index f868333271aa..963a4a5dc88e 100644 --- a/drivers/nfc/microread/microread.c +++ b/drivers/nfc/microread/microread.c @@ -501,9 +501,13 @@ static void microread_target_discovered(struct nfc_hci_dev *hdev, u8 gate, targets->sens_res = be16_to_cpu(*(u16 *)&skb->data[MICROREAD_EMCF_A_ATQA]); targets->sel_res = skb->data[MICROREAD_EMCF_A_SAK]; - memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A_UID], - skb->data[MICROREAD_EMCF_A_LEN]); targets->nfcid1_len = skb->data[MICROREAD_EMCF_A_LEN]; + if (targets->nfcid1_len > sizeof(targets->nfcid1)) { + r = -EINVAL; + goto exit_free; + } + memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A_UID], + targets->nfcid1_len); break; case MICROREAD_GATE_ID_MREAD_ISO_A_3: targets->supported_protocols = @@ -511,9 +515,13 @@ static void microread_target_discovered(struct nfc_hci_dev *hdev, u8 gate, targets->sens_res = be16_to_cpu(*(u16 *)&skb->data[MICROREAD_EMCF_A3_ATQA]); targets->sel_res = skb->data[MICROREAD_EMCF_A3_SAK]; - memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A3_UID], - skb->data[MICROREAD_EMCF_A3_LEN]); targets->nfcid1_len = skb->data[MICROREAD_EMCF_A3_LEN]; + if (targets->nfcid1_len > sizeof(targets->nfcid1)) { + r = -EINVAL; + goto exit_free; + } + memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A3_UID], + targets->nfcid1_len); break; case MICROREAD_GATE_ID_MREAD_ISO_B: targets->supported_protocols = NFC_PROTO_ISO14443_B_MASK; diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig index ec919a9160a5..99e8345b31ef 100644 --- a/drivers/of/Kconfig +++ b/drivers/of/Kconfig @@ -7,17 +7,11 @@ config OF menu "Device Tree and Open Firmware support" depends on OF -config PROC_DEVICETREE - bool "Support for device tree in /proc" - depends on PROC_FS && !SPARC - help - This option adds a device-tree directory under /proc which contains - an image of the device tree that the kernel copies from Open - Firmware or other boot firmware. If unsure, say Y here. - -config OF_SELFTEST - bool "Device Tree Runtime self tests" - depends on OF_IRQ +config OF_UNITTEST + bool "Device Tree runtime unit tests" + depends on OF_IRQ && OF_EARLY_FLATTREE + select OF_DYNAMIC + select OF_RESOLVE help This option builds in test cases for the device tree infrastructure that are executed once at boot time, and the results dumped to the @@ -82,4 +76,14 @@ config OF_RESERVED_MEM help Helpers to allow for reservation of memory regions +config OF_RESOLVE + bool + +config OF_OVERLAY + bool + depends on OF + select OF_DYNAMIC + select OF_DEVICE + select OF_RESOLVE + endmenu # OF diff --git a/drivers/of/Makefile b/drivers/of/Makefile index 9891232f999e..c60969c748dd 100644 --- a/drivers/of/Makefile +++ b/drivers/of/Makefile @@ -1,14 +1,18 @@ obj-y = base.o device.o platform.o +obj-$(CONFIG_OF_DYNAMIC) += dynamic.o obj-$(CONFIG_OF_FLATTREE) += fdt.o obj-$(CONFIG_OF_PROMTREE) += pdt.o obj-$(CONFIG_OF_ADDRESS) += address.o obj-$(CONFIG_OF_IRQ) += irq.o obj-$(CONFIG_OF_NET) += of_net.o -obj-$(CONFIG_OF_SELFTEST) += selftest.o +obj-$(CONFIG_OF_UNITTEST) += of_unittest.o +of_unittest-objs := unittest.o unittest-data/testcases.dtb.o obj-$(CONFIG_OF_MDIO) += of_mdio.o obj-$(CONFIG_OF_PCI) += of_pci.o obj-$(CONFIG_OF_PCI_IRQ) += of_pci_irq.o obj-$(CONFIG_OF_MTD) += of_mtd.o obj-$(CONFIG_OF_RESERVED_MEM) += of_reserved_mem.o +obj-$(CONFIG_OF_RESOLVE) += resolver.o +obj-$(CONFIG_OF_OVERLAY) += overlay.o CFLAGS_fdt.o = -I$(src)/../../scripts/dtc/libfdt diff --git a/drivers/of/address.c b/drivers/of/address.c index 1a54f1ffaadb..0f66f9b41011 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -401,6 +401,21 @@ static struct of_bus *of_match_bus(struct device_node *np) return NULL; } +static int of_empty_ranges_quirk(void) +{ + if (IS_ENABLED(CONFIG_PPC)) { + /* To save cycles, we cache the result */ + static int quirk_state = -1; + + if (quirk_state < 0) + quirk_state = + of_machine_is_compatible("Power Macintosh") || + of_machine_is_compatible("MacRISC"); + return quirk_state; + } + return false; +} + static int of_translate_one(struct device_node *parent, struct of_bus *bus, struct of_bus *pbus, __be32 *addr, int na, int ns, int pna, const char *rprop) @@ -426,12 +441,10 @@ static int of_translate_one(struct device_node *parent, struct of_bus *bus, * This code is only enabled on powerpc. --gcl */ ranges = of_get_property(parent, rprop, &rlen); -#if !defined(CONFIG_PPC) - if (ranges == NULL) { - pr_err("OF: no ranges; cannot translate\n"); + if (ranges == NULL && !of_empty_ranges_quirk()) { + pr_debug("OF: no ranges; cannot translate\n"); return 1; } -#endif /* !defined(CONFIG_PPC) */ if (ranges == NULL || rlen == 0) { offset = of_read_number(addr, na); memset(addr, 0, pna * 4); @@ -496,8 +509,7 @@ static u64 __of_translate_address(struct device_node *dev, /* Count address cells & copy address locally */ bus->count_cells(dev, &na, &ns); if (!OF_CHECK_COUNTS(na, ns)) { - printk(KERN_ERR "prom_parse: Bad cell count for %s\n", - of_node_full_name(dev)); + pr_debug("OF: Bad cell count for %s\n", of_node_full_name(dev)); goto bail; } memcpy(addr, in_addr, na * 4); @@ -562,25 +574,6 @@ u64 of_translate_dma_address(struct device_node *dev, const __be32 *in_addr) } EXPORT_SYMBOL(of_translate_dma_address); -bool of_can_translate_address(struct device_node *dev) -{ - struct device_node *parent; - struct of_bus *bus; - int na, ns; - - parent = of_get_parent(dev); - if (parent == NULL) - return false; - - bus = of_match_bus(parent); - bus->count_cells(dev, &na, &ns); - - of_node_put(parent); - - return OF_CHECK_COUNTS(na, ns); -} -EXPORT_SYMBOL(of_can_translate_address); - const __be32 *of_get_address(struct device_node *dev, int index, u64 *size, unsigned int *flags) { diff --git a/drivers/of/base.c b/drivers/of/base.c index 89e888a78899..87eaf8e75ebe 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -21,8 +21,10 @@ #include <linux/cpu.h> #include <linux/module.h> #include <linux/of.h> +#include <linux/of_graph.h> #include <linux/spinlock.h> #include <linux/slab.h> +#include <linux/string.h> #include <linux/proc_fs.h> #include "of_private.h" @@ -35,7 +37,15 @@ struct device_node *of_chosen; struct device_node *of_aliases; static struct device_node *of_stdout; -DEFINE_MUTEX(of_aliases_mutex); +struct kset *of_kset; + +/* + * Used to protect the of_aliases, to hold off addition of nodes to sysfs. + * This mutex must be held whenever modifications are being made to the + * device tree. The of_{attach,detach}_node() and + * of_{add,remove,update}_property() helpers make sure this happens. + */ +DEFINE_MUTEX(of_mutex); /* use when traversing tree through the allnext, child, sibling, * or parent members of struct device_node. @@ -81,80 +91,123 @@ int __weak of_node_to_nid(struct device_node *np) } #endif -#if defined(CONFIG_OF_DYNAMIC) -/** - * of_node_get - Increment refcount of a node - * @node: Node to inc refcount, NULL is supported to - * simplify writing of callers - * - * Returns node. - */ -struct device_node *of_node_get(struct device_node *node) +#ifndef CONFIG_OF_DYNAMIC +static void of_node_release(struct kobject *kobj) { - if (node) - kref_get(&node->kref); - return node; + /* Without CONFIG_OF_DYNAMIC, no nodes gets freed */ } -EXPORT_SYMBOL(of_node_get); +#endif /* CONFIG_OF_DYNAMIC */ + +struct kobj_type of_node_ktype = { + .release = of_node_release, +}; -static inline struct device_node *kref_to_device_node(struct kref *kref) +static ssize_t of_node_property_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, + loff_t offset, size_t count) { - return container_of(kref, struct device_node, kref); + struct property *pp = container_of(bin_attr, struct property, attr); + return memory_read_from_buffer(buf, count, &offset, pp->value, pp->length); } -/** - * of_node_release - release a dynamically allocated node - * @kref: kref element of the node to be released - * - * In of_node_put() this function is passed to kref_put() - * as the destructor. - */ -static void of_node_release(struct kref *kref) +static const char *safe_name(struct kobject *kobj, const char *orig_name) { - struct device_node *node = kref_to_device_node(kref); - struct property *prop = node->properties; + const char *name = orig_name; + struct kernfs_node *kn; + int i = 0; - /* We should never be releasing nodes that haven't been detached. */ - if (!of_node_check_flag(node, OF_DETACHED)) { - pr_err("ERROR: Bad of_node_put() on %s\n", node->full_name); - dump_stack(); - kref_init(&node->kref); - return; + /* don't be a hero. After 16 tries give up */ + while (i < 16 && (kn = sysfs_get_dirent(kobj->sd, name))) { + sysfs_put(kn); + if (name != orig_name) + kfree(name); + name = kasprintf(GFP_KERNEL, "%s#%i", orig_name, ++i); } - if (!of_node_check_flag(node, OF_DYNAMIC)) - return; + if (name != orig_name) + pr_warn("device-tree: Duplicate name in %s, renamed to \"%s\"\n", + kobject_name(kobj), name); + return name; +} - while (prop) { - struct property *next = prop->next; - kfree(prop->name); - kfree(prop->value); - kfree(prop); - prop = next; +int __of_add_property_sysfs(struct device_node *np, struct property *pp) +{ + int rc; - if (!prop) { - prop = node->deadprops; - node->deadprops = NULL; - } + /* Important: Don't leak passwords */ + bool secure = strncmp(pp->name, "security-", 9) == 0; + + if (!IS_ENABLED(CONFIG_SYSFS)) + return 0; + + if (!of_kset || !of_node_is_attached(np)) + return 0; + + sysfs_bin_attr_init(&pp->attr); + pp->attr.attr.name = safe_name(&np->kobj, pp->name); + pp->attr.attr.mode = secure ? S_IRUSR : S_IRUGO; + pp->attr.size = secure ? 0 : pp->length; + pp->attr.read = of_node_property_read; + + rc = sysfs_create_bin_file(&np->kobj, &pp->attr); + WARN(rc, "error adding attribute %s to node %s\n", pp->name, np->full_name); + return rc; +} + +int __of_attach_node_sysfs(struct device_node *np) +{ + const char *name; + struct property *pp; + int rc; + + if (!IS_ENABLED(CONFIG_SYSFS)) + return 0; + + if (!of_kset) + return 0; + + np->kobj.kset = of_kset; + if (!np->parent) { + /* Nodes without parents are new top level trees */ + rc = kobject_add(&np->kobj, NULL, safe_name(&of_kset->kobj, "base")); + } 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); } - kfree(node->full_name); - kfree(node->data); - kfree(node); + if (rc) + return rc; + + for_each_property_of_node(np, pp) + __of_add_property_sysfs(np, pp); + + return 0; } -/** - * of_node_put - Decrement refcount of a node - * @node: Node to dec refcount, NULL is supported to - * simplify writing of callers - * - */ -void of_node_put(struct device_node *node) +static int __init of_init(void) { - if (node) - kref_put(&node->kref, of_node_release); + struct device_node *np; + + /* Create the kset, and register existing nodes */ + mutex_lock(&of_mutex); + of_kset = kset_create_and_add("devicetree", NULL, firmware_kobj); + if (!of_kset) { + mutex_unlock(&of_mutex); + return -ENOMEM; + } + for_each_of_allnodes(np) + __of_attach_node_sysfs(np); + mutex_unlock(&of_mutex); + + /* Symlink in /proc as required by userspace ABI */ + if (of_allnodes) + proc_symlink("device-tree", NULL, "/sys/firmware/devicetree/base"); + + return 0; } -EXPORT_SYMBOL(of_node_put); -#endif /* CONFIG_OF_DYNAMIC */ +core_initcall(of_init); static struct property *__of_find_property(const struct device_node *np, const char *name, int *lenp) @@ -218,8 +271,8 @@ EXPORT_SYMBOL(of_find_all_nodes); * Find a property with a given name for a given node * and return the value. */ -static const void *__of_get_property(const struct device_node *np, - const char *name, int *lenp) +const void *__of_get_property(const struct device_node *np, + const char *name, int *lenp) { struct property *pp = __of_find_property(np, name, lenp); @@ -904,6 +957,38 @@ struct device_node *of_find_node_by_phandle(phandle handle) EXPORT_SYMBOL(of_find_node_by_phandle); /** + * of_property_count_elems_of_size - Count the number of elements in a property + * + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * @elem_size: size of the individual element + * + * Search for a property in a device node and count the number of elements of + * size elem_size in it. Returns number of elements on sucess, -EINVAL if the + * property does not exist or its length does not match a multiple of elem_size + * and -ENODATA if the property does not have a value. + */ +int of_property_count_elems_of_size(const struct device_node *np, + const char *propname, int elem_size) +{ + struct property *prop = of_find_property(np, propname, NULL); + + if (!prop) + return -EINVAL; + if (!prop->value) + return -ENODATA; + + if (prop->length % elem_size != 0) { + pr_err("size of %s in node %s is not a multiple of %d\n", + propname, np->full_name, elem_size); + return -EINVAL; + } + + return prop->length / elem_size; +} +EXPORT_SYMBOL_GPL(of_property_count_elems_of_size); + +/** * of_find_property_value_of_size * * @np: device node from which the property value is to be read. @@ -1117,52 +1202,6 @@ int of_property_read_string(struct device_node *np, const char *propname, EXPORT_SYMBOL_GPL(of_property_read_string); /** - * of_property_read_string_index - Find and read a string from a multiple - * strings property. - * @np: device node from which the property value is to be read. - * @propname: name of the property to be searched. - * @index: index of the string in the list of strings - * @out_string: pointer to null terminated return string, modified only if - * return value is 0. - * - * Search for a property in a device tree node and retrieve a null - * terminated string value (pointer to data, not a copy) in the list of strings - * contained in that property. - * Returns 0 on success, -EINVAL if the property does not exist, -ENODATA if - * property does not have a value, and -EILSEQ if the string is not - * null-terminated within the length of the property data. - * - * The out_string pointer is modified only if a valid string can be decoded. - */ -int of_property_read_string_index(struct device_node *np, const char *propname, - int index, const char **output) -{ - struct property *prop = of_find_property(np, propname, NULL); - int i = 0; - size_t l = 0, total = 0; - const char *p; - - if (!prop) - return -EINVAL; - if (!prop->value) - return -ENODATA; - if (strnlen(prop->value, prop->length) >= prop->length) - return -EILSEQ; - - p = prop->value; - - for (i = 0; total < prop->length; total += l, p += l) { - l = strlen(p) + 1; - if (i++ == index) { - *output = p; - return 0; - } - } - return -ENODATA; -} -EXPORT_SYMBOL_GPL(of_property_read_string_index); - -/** * of_property_match_string() - Find string in a list and return index * @np: pointer to node containing string list property * @propname: string list property name @@ -1188,7 +1227,7 @@ int of_property_match_string(struct device_node *np, const char *propname, end = p + prop->length; for (i = 0; p < end; i++, p += l) { - l = strlen(p) + 1; + l = strnlen(p, end - p) + 1; if (p + l > end) return -EILSEQ; pr_debug("comparing %s with %s\n", string, p); @@ -1200,39 +1239,41 @@ int of_property_match_string(struct device_node *np, const char *propname, EXPORT_SYMBOL_GPL(of_property_match_string); /** - * of_property_count_strings - Find and return the number of strings from a - * multiple strings property. + * of_property_read_string_util() - Utility helper for parsing string properties * @np: device node from which the property value is to be read. * @propname: name of the property to be searched. + * @out_strs: output array of string pointers. + * @sz: number of array elements to read. + * @skip: Number of strings to skip over at beginning of list. * - * Search for a property in a device tree node and retrieve the number of null - * terminated string contain in it. Returns the number of strings on - * success, -EINVAL if the property does not exist, -ENODATA if property - * does not have a value, and -EILSEQ if the string is not null-terminated - * within the length of the property data. + * Don't call this function directly. It is a utility helper for the + * of_property_read_string*() family of functions. */ -int of_property_count_strings(struct device_node *np, const char *propname) +int of_property_read_string_helper(struct device_node *np, const char *propname, + const char **out_strs, size_t sz, int skip) { struct property *prop = of_find_property(np, propname, NULL); - int i = 0; - size_t l = 0, total = 0; - const char *p; + int l = 0, i = 0; + const char *p, *end; if (!prop) return -EINVAL; if (!prop->value) return -ENODATA; - if (strnlen(prop->value, prop->length) >= prop->length) - return -EILSEQ; - p = prop->value; + end = p + prop->length; - for (i = 0; total < prop->length; total += l, p += l, i++) - l = strlen(p) + 1; - - return i; + for (i = 0; p < end && (!out_strs || i < skip + sz); i++, p += l) { + l = strnlen(p, end - p) + 1; + if (p + l > end) + return -EILSEQ; + if (out_strs && i >= skip) + *out_strs++ = p; + } + i -= skip; + return i <= 0 ? -ENODATA : i; } -EXPORT_SYMBOL_GPL(of_property_count_strings); +EXPORT_SYMBOL_GPL(of_property_read_string_helper); void of_print_phandle_args(const char *msg, const struct of_phandle_args *args) { @@ -1492,301 +1533,186 @@ int of_count_phandle_with_args(const struct device_node *np, const char *list_na } EXPORT_SYMBOL(of_count_phandle_with_args); -#if defined(CONFIG_OF_DYNAMIC) -static int of_property_notify(int action, struct device_node *np, - struct property *prop) -{ - struct of_prop_reconfig pr; - - pr.dn = np; - pr.prop = prop; - return of_reconfig_notify(action, &pr); -} -#else -static int of_property_notify(int action, struct device_node *np, - struct property *prop) -{ - return 0; -} -#endif - /** - * of_add_property - Add a property to a node + * __of_add_property - Add a property to a node without lock operations */ -int of_add_property(struct device_node *np, struct property *prop) +int __of_add_property(struct device_node *np, struct property *prop) { struct property **next; - unsigned long flags; - int rc; - - rc = of_property_notify(OF_RECONFIG_ADD_PROPERTY, np, prop); - if (rc) - return rc; prop->next = NULL; - raw_spin_lock_irqsave(&devtree_lock, flags); next = &np->properties; while (*next) { - if (strcmp(prop->name, (*next)->name) == 0) { + if (strcmp(prop->name, (*next)->name) == 0) /* duplicate ! don't insert it */ - raw_spin_unlock_irqrestore(&devtree_lock, flags); - return -1; - } + return -EEXIST; + next = &(*next)->next; } *next = prop; - raw_spin_unlock_irqrestore(&devtree_lock, flags); - -#ifdef CONFIG_PROC_DEVICETREE - /* try to add to proc as well if it was initialized */ - if (np->pde) - proc_device_tree_add_prop(np->pde, prop); -#endif /* CONFIG_PROC_DEVICETREE */ return 0; } /** - * of_remove_property - Remove a property from a node. - * - * Note that we don't actually remove it, since we have given out - * who-knows-how-many pointers to the data using get-property. - * Instead we just move the property to the "dead properties" - * list, so it won't be found any more. + * of_add_property - Add a property to a node */ -int of_remove_property(struct device_node *np, struct property *prop) +int of_add_property(struct device_node *np, struct property *prop) { - struct property **next; unsigned long flags; - int found = 0; int rc; - rc = of_property_notify(OF_RECONFIG_REMOVE_PROPERTY, np, prop); - if (rc) - return rc; + mutex_lock(&of_mutex); raw_spin_lock_irqsave(&devtree_lock, flags); - next = &np->properties; - while (*next) { - if (*next == prop) { - /* found the node */ - *next = prop->next; - prop->next = np->deadprops; - np->deadprops = prop; - found = 1; - break; - } - next = &(*next)->next; - } + rc = __of_add_property(np, prop); raw_spin_unlock_irqrestore(&devtree_lock, flags); - if (!found) - return -ENODEV; + if (!rc) + __of_add_property_sysfs(np, prop); -#ifdef CONFIG_PROC_DEVICETREE - /* try to remove the proc node as well */ - if (np->pde) - proc_device_tree_remove_prop(np->pde, prop); -#endif /* CONFIG_PROC_DEVICETREE */ + mutex_unlock(&of_mutex); - return 0; + if (!rc) + of_property_notify(OF_RECONFIG_ADD_PROPERTY, np, prop, NULL); + + return rc; } -/* - * of_update_property - Update a property in a node, if the property does - * not exist, add it. - * - * Note that we don't actually remove it, since we have given out - * who-knows-how-many pointers to the data using get-property. - * Instead we just move the property to the "dead properties" list, - * and add the new property to the property list - */ -int of_update_property(struct device_node *np, struct property *newprop) +int __of_remove_property(struct device_node *np, struct property *prop) { - struct property **next, *oldprop; - unsigned long flags; - int rc, found = 0; - - rc = of_property_notify(OF_RECONFIG_UPDATE_PROPERTY, np, newprop); - if (rc) - return rc; - - if (!newprop->name) - return -EINVAL; - - oldprop = of_find_property(np, newprop->name, NULL); - if (!oldprop) - return of_add_property(np, newprop); + struct property **next; - raw_spin_lock_irqsave(&devtree_lock, flags); - next = &np->properties; - while (*next) { - if (*next == oldprop) { - /* found the node */ - newprop->next = oldprop->next; - *next = newprop; - oldprop->next = np->deadprops; - np->deadprops = oldprop; - found = 1; + for (next = &np->properties; *next; next = &(*next)->next) { + if (*next == prop) break; - } - next = &(*next)->next; } - raw_spin_unlock_irqrestore(&devtree_lock, flags); - - if (!found) + if (*next == NULL) return -ENODEV; -#ifdef CONFIG_PROC_DEVICETREE - /* try to add to proc as well if it was initialized */ - if (np->pde) - proc_device_tree_update_prop(np->pde, newprop, oldprop); -#endif /* CONFIG_PROC_DEVICETREE */ + /* found the node */ + *next = prop->next; + prop->next = np->deadprops; + np->deadprops = prop; return 0; } -#if defined(CONFIG_OF_DYNAMIC) -/* - * Support for dynamic device trees. - * - * On some platforms, the device tree can be manipulated at runtime. - * The routines in this section support adding, removing and changing - * device tree nodes. - */ - -static BLOCKING_NOTIFIER_HEAD(of_reconfig_chain); - -int of_reconfig_notifier_register(struct notifier_block *nb) -{ - return blocking_notifier_chain_register(&of_reconfig_chain, nb); -} -EXPORT_SYMBOL_GPL(of_reconfig_notifier_register); - -int of_reconfig_notifier_unregister(struct notifier_block *nb) +void __of_remove_property_sysfs(struct device_node *np, struct property *prop) { - return blocking_notifier_chain_unregister(&of_reconfig_chain, nb); -} -EXPORT_SYMBOL_GPL(of_reconfig_notifier_unregister); - -int of_reconfig_notify(unsigned long action, void *p) -{ - int rc; - - rc = blocking_notifier_call_chain(&of_reconfig_chain, action, p); - return notifier_to_errno(rc); -} - -#ifdef CONFIG_PROC_DEVICETREE -static void of_add_proc_dt_entry(struct device_node *dn) -{ - struct proc_dir_entry *ent; + if (!IS_ENABLED(CONFIG_SYSFS)) + return; - ent = proc_mkdir(strrchr(dn->full_name, '/') + 1, dn->parent->pde); - if (ent) - proc_device_tree_add_node(dn, ent); -} -#else -static void of_add_proc_dt_entry(struct device_node *dn) -{ - return; + /* 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); } -#endif /** - * of_attach_node - Plug a device node into the tree and global list. + * of_remove_property - Remove a property from a node. + * + * Note that we don't actually remove it, since we have given out + * who-knows-how-many pointers to the data using get-property. + * Instead we just move the property to the "dead properties" + * list, so it won't be found any more. */ -int of_attach_node(struct device_node *np) +int of_remove_property(struct device_node *np, struct property *prop) { unsigned long flags; int rc; - rc = of_reconfig_notify(OF_RECONFIG_ATTACH_NODE, np); - if (rc) - return rc; + mutex_lock(&of_mutex); raw_spin_lock_irqsave(&devtree_lock, flags); - np->sibling = np->parent->child; - np->allnext = of_allnodes; - np->parent->child = np; - of_allnodes = np; + rc = __of_remove_property(np, prop); raw_spin_unlock_irqrestore(&devtree_lock, flags); - of_add_proc_dt_entry(np); - return 0; + if (!rc) + __of_remove_property_sysfs(np, prop); + + mutex_unlock(&of_mutex); + + if (!rc) + of_property_notify(OF_RECONFIG_REMOVE_PROPERTY, np, prop, NULL); + + return rc; } -#ifdef CONFIG_PROC_DEVICETREE -static void of_remove_proc_dt_entry(struct device_node *dn) +int __of_update_property(struct device_node *np, struct property *newprop, + struct property **oldpropp) { - proc_remove(dn->pde); + struct property **next, *oldprop; + + for (next = &np->properties; *next; next = &(*next)->next) { + if (of_prop_cmp((*next)->name, newprop->name) == 0) + break; + } + *oldpropp = oldprop = *next; + + if (oldprop) { + /* replace the node */ + newprop->next = oldprop->next; + *next = newprop; + oldprop->next = np->deadprops; + np->deadprops = oldprop; + } else { + /* new node */ + newprop->next = NULL; + *next = newprop; + } + + return 0; } -#else -static void of_remove_proc_dt_entry(struct device_node *dn) + +void __of_update_property_sysfs(struct device_node *np, struct property *newprop, + struct property *oldprop) { - return; + if (!IS_ENABLED(CONFIG_SYSFS)) + return; + + /* At early boot, bail out and defer setup to of_init() */ + if (!of_kset) + return; + + if (oldprop) + sysfs_remove_bin_file(&np->kobj, &oldprop->attr); + __of_add_property_sysfs(np, newprop); } -#endif -/** - * of_detach_node - "Unplug" a node from the device tree. +/* + * of_update_property - Update a property in a node, if the property does + * not exist, add it. * - * The caller must hold a reference to the node. The memory associated with - * the node is not freed until its refcount goes to zero. + * Note that we don't actually remove it, since we have given out + * who-knows-how-many pointers to the data using get-property. + * Instead we just move the property to the "dead properties" list, + * and add the new property to the property list */ -int of_detach_node(struct device_node *np) +int of_update_property(struct device_node *np, struct property *newprop) { - struct device_node *parent; + struct property *oldprop; unsigned long flags; - int rc = 0; - - rc = of_reconfig_notify(OF_RECONFIG_DETACH_NODE, np); - if (rc) - return rc; + int rc; - raw_spin_lock_irqsave(&devtree_lock, flags); + if (!newprop->name) + return -EINVAL; - if (of_node_check_flag(np, OF_DETACHED)) { - /* someone already detached it */ - raw_spin_unlock_irqrestore(&devtree_lock, flags); - return rc; - } + mutex_lock(&of_mutex); - parent = np->parent; - if (!parent) { - raw_spin_unlock_irqrestore(&devtree_lock, flags); - return rc; - } + raw_spin_lock_irqsave(&devtree_lock, flags); + rc = __of_update_property(np, newprop, &oldprop); + raw_spin_unlock_irqrestore(&devtree_lock, flags); - if (of_allnodes == np) - of_allnodes = np->allnext; - else { - struct device_node *prev; - for (prev = of_allnodes; - prev->allnext != np; - prev = prev->allnext) - ; - prev->allnext = np->allnext; - } + if (!rc) + __of_update_property_sysfs(np, newprop, oldprop); - if (parent->child == np) - parent->child = np->sibling; - else { - struct device_node *prevsib; - for (prevsib = np->parent->child; - prevsib->sibling != np; - prevsib = prevsib->sibling) - ; - prevsib->sibling = np->sibling; - } + mutex_unlock(&of_mutex); - of_node_set_flag(np, OF_DETACHED); - raw_spin_unlock_irqrestore(&devtree_lock, flags); + if (!rc) + of_property_notify(OF_RECONFIG_UPDATE_PROPERTY, np, newprop, oldprop); - of_remove_proc_dt_entry(np); return rc; } -#endif /* defined(CONFIG_OF_DYNAMIC) */ static void of_alias_add(struct alias_prop *ap, struct device_node *np, int id, const char *stem, int stem_len) @@ -1879,7 +1805,7 @@ int of_alias_get_id(struct device_node *np, const char *stem) struct alias_prop *app; int id = -ENODEV; - mutex_lock(&of_aliases_mutex); + mutex_lock(&of_mutex); list_for_each_entry(app, &aliases_lookup, link) { if (strcmp(app->stem, stem) != 0) continue; @@ -1889,7 +1815,7 @@ int of_alias_get_id(struct device_node *np, const char *stem) break; } } - mutex_unlock(&of_aliases_mutex); + mutex_unlock(&of_mutex); return id; } @@ -1982,3 +1908,154 @@ struct device_node *of_find_next_cache_node(const struct device_node *np) return NULL; } + +/** + * of_graph_parse_endpoint() - parse common endpoint node properties + * @node: pointer to endpoint device_node + * @endpoint: pointer to the OF endpoint data structure + * + * The caller should hold a reference to @node. + */ +int of_graph_parse_endpoint(const struct device_node *node, + struct of_endpoint *endpoint) +{ + struct device_node *port_node = of_get_parent(node); + + WARN_ONCE(!port_node, "%s(): endpoint %s has no parent node\n", + __func__, node->full_name); + + memset(endpoint, 0, sizeof(*endpoint)); + + endpoint->local_node = node; + /* + * It doesn't matter whether the two calls below succeed. + * If they don't then the default value 0 is used. + */ + of_property_read_u32(port_node, "reg", &endpoint->port); + of_property_read_u32(node, "reg", &endpoint->id); + + of_node_put(port_node); + + return 0; +} +EXPORT_SYMBOL(of_graph_parse_endpoint); + +/** + * of_graph_get_next_endpoint() - get next endpoint node + * @parent: pointer to the parent device node + * @prev: previous endpoint node, or NULL to get first + * + * Return: An 'endpoint' node pointer with refcount incremented. Refcount + * of the passed @prev node is not decremented, the caller have to use + * of_node_put() on it when done. + */ +struct device_node *of_graph_get_next_endpoint(const struct device_node *parent, + struct device_node *prev) +{ + struct device_node *endpoint; + struct device_node *port; + + if (!parent) + return NULL; + + /* + * Start by locating the port node. If no previous endpoint is specified + * search for the first port node, otherwise get the previous endpoint + * parent port node. + */ + if (!prev) { + struct device_node *node; + + node = of_get_child_by_name(parent, "ports"); + if (node) + parent = node; + + port = of_get_child_by_name(parent, "port"); + of_node_put(node); + + if (!port) { + pr_err("%s(): no port node found in %s\n", + __func__, parent->full_name); + return NULL; + } + } else { + port = of_get_parent(prev); + if (WARN_ONCE(!port, "%s(): endpoint %s has no parent node\n", + __func__, prev->full_name)) + return NULL; + + /* + * Avoid dropping prev node refcount to 0 when getting the next + * child below. + */ + of_node_get(prev); + } + + while (1) { + /* + * Now that we have a port node, get the next endpoint by + * getting the next child. If the previous endpoint is NULL this + * will return the first child. + */ + endpoint = of_get_next_child(port, prev); + if (endpoint) { + of_node_put(port); + return endpoint; + } + + /* No more endpoints under this port, try the next one. */ + prev = NULL; + + do { + port = of_get_next_child(parent, port); + if (!port) + return NULL; + } while (of_node_cmp(port->name, "port")); + } +} +EXPORT_SYMBOL(of_graph_get_next_endpoint); + +/** + * of_graph_get_remote_port_parent() - get remote port's parent node + * @node: pointer to a local endpoint device_node + * + * Return: Remote device node associated with remote endpoint node linked + * to @node. Use of_node_put() on it when done. + */ +struct device_node *of_graph_get_remote_port_parent( + const struct device_node *node) +{ + struct device_node *np; + unsigned int depth; + + /* Get remote endpoint node. */ + np = of_parse_phandle(node, "remote-endpoint", 0); + + /* Walk 3 levels up only if there is 'ports' node. */ + for (depth = 3; depth && np; depth--) { + np = of_get_next_parent(np); + if (depth == 2 && of_node_cmp(np->name, "ports")) + break; + } + return np; +} +EXPORT_SYMBOL(of_graph_get_remote_port_parent); + +/** + * of_graph_get_remote_port() - get remote port node + * @node: pointer to a local endpoint device_node + * + * Return: Remote port node associated with remote endpoint node linked + * to @node. Use of_node_put() on it when done. + */ +struct device_node *of_graph_get_remote_port(const struct device_node *node) +{ + struct device_node *np; + + /* Get remote endpoint node. */ + np = of_parse_phandle(node, "remote-endpoint", 0); + if (!np) + return NULL; + return of_get_next_parent(np); +} +EXPORT_SYMBOL(of_graph_get_remote_port); diff --git a/drivers/of/device.c b/drivers/of/device.c index dafb9736ab9b..46d6c75c1404 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -160,7 +160,7 @@ void of_device_uevent(struct device *dev, struct kobj_uevent_env *env) add_uevent_var(env, "OF_COMPATIBLE_N=%d", seen); seen = 0; - mutex_lock(&of_aliases_mutex); + mutex_lock(&of_mutex); list_for_each_entry(app, &aliases_lookup, link) { if (dev->of_node == app->np) { add_uevent_var(env, "OF_ALIAS_%d=%s", seen, @@ -168,7 +168,7 @@ void of_device_uevent(struct device *dev, struct kobj_uevent_env *env) seen++; } } - mutex_unlock(&of_aliases_mutex); + mutex_unlock(&of_mutex); } int of_device_uevent_modalias(struct device *dev, struct kobj_uevent_env *env) diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c new file mode 100644 index 000000000000..87887de81cd3 --- /dev/null +++ b/drivers/of/dynamic.c @@ -0,0 +1,794 @@ +/* + * Support for dynamic device trees. + * + * On some platforms, the device tree can be manipulated at runtime. + * The routines in this section support adding, removing and changing + * device tree nodes. + */ + +#include <linux/of.h> +#include <linux/spinlock.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/proc_fs.h> + +#include "of_private.h" + +/** + * of_node_get() - Increment refcount of a node + * @node: Node to inc refcount, NULL is supported to simplify writing of + * callers + * + * Returns node. + */ +struct device_node *of_node_get(struct device_node *node) +{ + if (node) + kobject_get(&node->kobj); + return node; +} +EXPORT_SYMBOL(of_node_get); + +/** + * of_node_put() - Decrement refcount of a node + * @node: Node to dec refcount, NULL is supported to simplify writing of + * callers + */ +void of_node_put(struct device_node *node) +{ + if (node) + kobject_put(&node->kobj); +} +EXPORT_SYMBOL(of_node_put); + +void __of_detach_node_sysfs(struct device_node *np) +{ + struct property *pp; + + if (!IS_ENABLED(CONFIG_SYSFS)) + return; + + BUG_ON(!of_node_is_initialized(np)); + if (!of_kset) + return; + + /* 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); + kobject_del(&np->kobj); + } + + /* finally remove the kobj_init ref */ + of_node_put(np); +} + +static BLOCKING_NOTIFIER_HEAD(of_reconfig_chain); + +int of_reconfig_notifier_register(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&of_reconfig_chain, nb); +} +EXPORT_SYMBOL_GPL(of_reconfig_notifier_register); + +int of_reconfig_notifier_unregister(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&of_reconfig_chain, nb); +} +EXPORT_SYMBOL_GPL(of_reconfig_notifier_unregister); + +#ifdef DEBUG +const char *action_names[] = { + [OF_RECONFIG_ATTACH_NODE] = "ATTACH_NODE", + [OF_RECONFIG_DETACH_NODE] = "DETACH_NODE", + [OF_RECONFIG_ADD_PROPERTY] = "ADD_PROPERTY", + [OF_RECONFIG_REMOVE_PROPERTY] = "REMOVE_PROPERTY", + [OF_RECONFIG_UPDATE_PROPERTY] = "UPDATE_PROPERTY", +}; +#endif + +int of_reconfig_notify(unsigned long action, struct of_reconfig_data *p) +{ + int rc; +#ifdef DEBUG + struct of_reconfig_data *pr = p; + + switch (action) { + case OF_RECONFIG_ATTACH_NODE: + case OF_RECONFIG_DETACH_NODE: + pr_debug("of/notify %-15s %s\n", action_names[action], + pr->dn->full_name); + break; + case OF_RECONFIG_ADD_PROPERTY: + case OF_RECONFIG_REMOVE_PROPERTY: + case OF_RECONFIG_UPDATE_PROPERTY: + pr_debug("of/notify %-15s %s:%s\n", action_names[action], + pr->dn->full_name, pr->prop->name); + break; + + } +#endif + rc = blocking_notifier_call_chain(&of_reconfig_chain, action, p); + return notifier_to_errno(rc); +} + +/* + * of_reconfig_get_state_change() - Returns new state of device + * @action - action of the of notifier + * @arg - argument of the of notifier + * + * Returns the new state of a device based on the notifier used. + * Returns 0 on device going from enabled to disabled, 1 on device + * going from disabled to enabled and -1 on no change. + */ +int of_reconfig_get_state_change(unsigned long action, struct of_reconfig_data *pr) +{ + struct property *prop, *old_prop = NULL; + int is_status, status_state, old_status_state, prev_state, new_state; + + /* figure out if a device should be created or destroyed */ + switch (action) { + case OF_RECONFIG_ATTACH_NODE: + case OF_RECONFIG_DETACH_NODE: + prop = of_find_property(pr->dn, "status", NULL); + break; + case OF_RECONFIG_ADD_PROPERTY: + case OF_RECONFIG_REMOVE_PROPERTY: + prop = pr->prop; + break; + case OF_RECONFIG_UPDATE_PROPERTY: + prop = pr->prop; + old_prop = pr->old_prop; + break; + default: + return OF_RECONFIG_NO_CHANGE; + } + + is_status = 0; + status_state = -1; + old_status_state = -1; + prev_state = -1; + new_state = -1; + + if (prop && !strcmp(prop->name, "status")) { + is_status = 1; + status_state = !strcmp(prop->value, "okay") || + !strcmp(prop->value, "ok"); + if (old_prop) + old_status_state = !strcmp(old_prop->value, "okay") || + !strcmp(old_prop->value, "ok"); + } + + switch (action) { + case OF_RECONFIG_ATTACH_NODE: + prev_state = 0; + /* -1 & 0 status either missing or okay */ + new_state = status_state != 0; + break; + case OF_RECONFIG_DETACH_NODE: + /* -1 & 0 status either missing or okay */ + prev_state = status_state != 0; + new_state = 0; + break; + case OF_RECONFIG_ADD_PROPERTY: + if (is_status) { + /* no status property -> enabled (legacy) */ + prev_state = 1; + new_state = status_state; + } + break; + case OF_RECONFIG_REMOVE_PROPERTY: + if (is_status) { + prev_state = status_state; + /* no status property -> enabled (legacy) */ + new_state = 1; + } + break; + case OF_RECONFIG_UPDATE_PROPERTY: + if (is_status) { + prev_state = old_status_state != 0; + new_state = status_state != 0; + } + break; + } + + if (prev_state == new_state) + return OF_RECONFIG_NO_CHANGE; + + return new_state ? OF_RECONFIG_CHANGE_ADD : OF_RECONFIG_CHANGE_REMOVE; +} +EXPORT_SYMBOL_GPL(of_reconfig_get_state_change); + +int of_property_notify(int action, struct device_node *np, + struct property *prop, struct property *oldprop) +{ + struct of_reconfig_data pr; + + /* only call notifiers if the node is attached */ + if (!of_node_is_attached(np)) + return 0; + + pr.dn = np; + pr.prop = prop; + pr.old_prop = oldprop; + return of_reconfig_notify(action, &pr); +} + +void __of_attach_node(struct device_node *np) +{ + const __be32 *phandle; + int sz; + + np->name = __of_get_property(np, "name", NULL) ? : "<NULL>"; + np->type = __of_get_property(np, "device_type", NULL) ? : "<NULL>"; + + phandle = __of_get_property(np, "phandle", &sz); + if (!phandle) + phandle = __of_get_property(np, "linux,phandle", &sz); + if (IS_ENABLED(PPC_PSERIES) && !phandle) + phandle = __of_get_property(np, "ibm,phandle", &sz); + np->phandle = (phandle && (sz >= 4)) ? be32_to_cpup(phandle) : 0; + + np->child = NULL; + np->sibling = np->parent->child; + np->allnext = np->parent->allnext; + np->parent->allnext = np; + np->parent->child = np; + of_node_clear_flag(np, OF_DETACHED); +} + +/** + * of_attach_node() - Plug a device node into the tree and global list. + */ +int of_attach_node(struct device_node *np) +{ + struct of_reconfig_data rd; + unsigned long flags; + + memset(&rd, 0, sizeof(rd)); + rd.dn = np; + + mutex_lock(&of_mutex); + raw_spin_lock_irqsave(&devtree_lock, flags); + __of_attach_node(np); + raw_spin_unlock_irqrestore(&devtree_lock, flags); + + __of_attach_node_sysfs(np); + mutex_unlock(&of_mutex); + + of_reconfig_notify(OF_RECONFIG_ATTACH_NODE, &rd); + + return 0; +} + +void __of_detach_node(struct device_node *np) +{ + struct device_node *parent; + + if (WARN_ON(of_node_check_flag(np, OF_DETACHED))) + return; + + parent = np->parent; + if (WARN_ON(!parent)) + return; + + if (of_allnodes == np) + of_allnodes = np->allnext; + else { + struct device_node *prev; + for (prev = of_allnodes; + prev->allnext != np; + prev = prev->allnext) + ; + prev->allnext = np->allnext; + } + + if (parent->child == np) + parent->child = np->sibling; + else { + struct device_node *prevsib; + for (prevsib = np->parent->child; + prevsib->sibling != np; + prevsib = prevsib->sibling) + ; + prevsib->sibling = np->sibling; + } + + of_node_set_flag(np, OF_DETACHED); +} + +/** + * of_detach_node() - "Unplug" a node from the device tree. + * + * The caller must hold a reference to the node. The memory associated with + * the node is not freed until its refcount goes to zero. + */ +int of_detach_node(struct device_node *np) +{ + struct of_reconfig_data rd; + unsigned long flags; + int rc = 0; + + memset(&rd, 0, sizeof(rd)); + rd.dn = np; + + mutex_lock(&of_mutex); + raw_spin_lock_irqsave(&devtree_lock, flags); + __of_detach_node(np); + raw_spin_unlock_irqrestore(&devtree_lock, flags); + + __of_detach_node_sysfs(np); + mutex_unlock(&of_mutex); + + of_reconfig_notify(OF_RECONFIG_DETACH_NODE, &rd); + + return rc; +} + +/** + * of_node_release() - release a dynamically allocated node + * @kref: kref element of the node to be released + * + * In of_node_put() this function is passed to kref_put() as the destructor. + */ +void of_node_release(struct kobject *kobj) +{ + struct device_node *node = kobj_to_device_node(kobj); + struct property *prop = node->properties; + + /* We should never be releasing nodes that haven't been detached. */ + if (!of_node_check_flag(node, OF_DETACHED)) { + pr_err("ERROR: Bad of_node_put() on %s\n", node->full_name); + dump_stack(); + return; + } + + if (!of_node_check_flag(node, OF_DYNAMIC)) + return; + + while (prop) { + struct property *next = prop->next; + kfree(prop->name); + kfree(prop->value); + kfree(prop); + prop = next; + + if (!prop) { + prop = node->deadprops; + node->deadprops = NULL; + } + } + kfree(node->full_name); + kfree(node->data); + kfree(node); +} + +/** + * __of_prop_dup - Copy a property dynamically. + * @prop: Property to copy + * @allocflags: Allocation flags (typically pass GFP_KERNEL) + * + * Copy a property by dynamically allocating the memory of both the + * property stucture and the property name & contents. The property's + * flags have the OF_DYNAMIC bit set so that we can differentiate between + * dynamically allocated properties and not. + * Returns the newly allocated property or NULL on out of memory error. + */ +struct property *__of_prop_dup(const struct property *prop, gfp_t allocflags) +{ + struct property *new; + + new = kzalloc(sizeof(*new), allocflags); + if (!new) + return NULL; + + /* + * NOTE: There is no check for zero length value. + * In case of a boolean property, this will allocate a value + * of zero bytes. We do this to work around the use + * of of_get_property() calls on boolean values. + */ + new->name = kstrdup(prop->name, allocflags); + new->value = kmemdup(prop->value, prop->length, allocflags); + new->length = prop->length; + if (!new->name || !new->value) + goto err_free; + + /* mark the property as dynamic */ + of_property_set_flag(new, OF_DYNAMIC); + + return new; + + err_free: + kfree(new->name); + kfree(new->value); + kfree(new); + return NULL; +} + +/** + * __of_node_dup() - Duplicate or create an empty device node dynamically. + * @fmt: Format string (plus vargs) for new full name of the device node + * + * Create an device tree node, either by duplicating an empty node or by allocating + * an empty one suitable for further modification. The node data are + * dynamically allocated and all the node flags have the OF_DYNAMIC & + * OF_DETACHED bits set. Returns the newly allocated node or NULL on out of + * memory error. + */ +struct device_node *__of_node_dup(const struct device_node *np, const char *fmt, ...) +{ + va_list vargs; + struct device_node *node; + + node = kzalloc(sizeof(*node), GFP_KERNEL); + if (!node) + return NULL; + va_start(vargs, fmt); + node->full_name = kvasprintf(GFP_KERNEL, fmt, vargs); + va_end(vargs); + if (!node->full_name) { + kfree(node); + return NULL; + } + + of_node_set_flag(node, OF_DYNAMIC); + of_node_set_flag(node, OF_DETACHED); + of_node_init(node); + + /* Iterate over and duplicate all properties */ + if (np) { + struct property *pp, *new_pp; + for_each_property_of_node(np, pp) { + new_pp = __of_prop_dup(pp, GFP_KERNEL); + if (!new_pp) + goto err_prop; + if (__of_add_property(node, new_pp)) { + kfree(new_pp->name); + kfree(new_pp->value); + kfree(new_pp); + goto err_prop; + } + } + } + return node; + + err_prop: + of_node_put(node); /* Frees the node and properties */ + return NULL; +} + +static void __of_changeset_entry_destroy(struct of_changeset_entry *ce) +{ + of_node_put(ce->np); + list_del(&ce->node); + kfree(ce); +} + +#ifdef DEBUG +static void __of_changeset_entry_dump(struct of_changeset_entry *ce) +{ + switch (ce->action) { + case OF_RECONFIG_ADD_PROPERTY: + case OF_RECONFIG_REMOVE_PROPERTY: + case OF_RECONFIG_UPDATE_PROPERTY: + pr_debug("of/cset<%p> %-15s %s/%s\n", ce, action_names[ce->action], + ce->np->full_name, ce->prop->name); + break; + case OF_RECONFIG_ATTACH_NODE: + case OF_RECONFIG_DETACH_NODE: + pr_debug("of/cset<%p> %-15s %s\n", ce, action_names[ce->action], + ce->np->full_name); + break; + } +} +#else +static inline void __of_changeset_entry_dump(struct of_changeset_entry *ce) +{ + /* empty */ +} +#endif + +static void __of_changeset_entry_invert(struct of_changeset_entry *ce, + struct of_changeset_entry *rce) +{ + memcpy(rce, ce, sizeof(*rce)); + + switch (ce->action) { + case OF_RECONFIG_ATTACH_NODE: + rce->action = OF_RECONFIG_DETACH_NODE; + break; + case OF_RECONFIG_DETACH_NODE: + rce->action = OF_RECONFIG_ATTACH_NODE; + break; + case OF_RECONFIG_ADD_PROPERTY: + rce->action = OF_RECONFIG_REMOVE_PROPERTY; + break; + case OF_RECONFIG_REMOVE_PROPERTY: + rce->action = OF_RECONFIG_ADD_PROPERTY; + break; + case OF_RECONFIG_UPDATE_PROPERTY: + rce->old_prop = ce->prop; + rce->prop = ce->old_prop; + break; + } +} + +static void __of_changeset_entry_notify(struct of_changeset_entry *ce, bool revert) +{ + struct of_reconfig_data rd; + struct of_changeset_entry ce_inverted; + int ret; + + if (revert) { + __of_changeset_entry_invert(ce, &ce_inverted); + ce = &ce_inverted; + } + + switch (ce->action) { + case OF_RECONFIG_ATTACH_NODE: + case OF_RECONFIG_DETACH_NODE: + memset(&rd, 0, sizeof(rd)); + rd.dn = ce->np; + ret = of_reconfig_notify(ce->action, &rd); + break; + case OF_RECONFIG_ADD_PROPERTY: + case OF_RECONFIG_REMOVE_PROPERTY: + case OF_RECONFIG_UPDATE_PROPERTY: + ret = of_property_notify(ce->action, ce->np, ce->prop, ce->old_prop); + break; + default: + pr_err("%s: invalid devicetree changeset action: %i\n", __func__, + (int)ce->action); + return; + } + + if (ret) + pr_err("%s: notifier error @%s\n", __func__, ce->np->full_name); +} + +static int __of_changeset_entry_apply(struct of_changeset_entry *ce) +{ + struct property *old_prop, **propp; + unsigned long flags; + int ret = 0; + + __of_changeset_entry_dump(ce); + + raw_spin_lock_irqsave(&devtree_lock, flags); + switch (ce->action) { + case OF_RECONFIG_ATTACH_NODE: + __of_attach_node(ce->np); + break; + case OF_RECONFIG_DETACH_NODE: + __of_detach_node(ce->np); + break; + case OF_RECONFIG_ADD_PROPERTY: + /* If the property is in deadprops then it must be removed */ + for (propp = &ce->np->deadprops; *propp; propp = &(*propp)->next) { + if (*propp == ce->prop) { + *propp = ce->prop->next; + ce->prop->next = NULL; + break; + } + } + + ret = __of_add_property(ce->np, ce->prop); + if (ret) { + pr_err("%s: add_property failed @%s/%s\n", + __func__, ce->np->full_name, + ce->prop->name); + break; + } + break; + case OF_RECONFIG_REMOVE_PROPERTY: + ret = __of_remove_property(ce->np, ce->prop); + if (ret) { + pr_err("%s: remove_property failed @%s/%s\n", + __func__, ce->np->full_name, + ce->prop->name); + break; + } + break; + + case OF_RECONFIG_UPDATE_PROPERTY: + /* If the property is in deadprops then it must be removed */ + for (propp = &ce->np->deadprops; *propp; propp = &(*propp)->next) { + if (*propp == ce->prop) { + *propp = ce->prop->next; + ce->prop->next = NULL; + break; + } + } + + ret = __of_update_property(ce->np, ce->prop, &old_prop); + if (ret) { + pr_err("%s: update_property failed @%s/%s\n", + __func__, ce->np->full_name, + ce->prop->name); + break; + } + break; + default: + ret = -EINVAL; + } + raw_spin_unlock_irqrestore(&devtree_lock, flags); + + if (ret) + return ret; + + switch (ce->action) { + case OF_RECONFIG_ATTACH_NODE: + __of_attach_node_sysfs(ce->np); + break; + case OF_RECONFIG_DETACH_NODE: + __of_detach_node_sysfs(ce->np); + break; + case OF_RECONFIG_ADD_PROPERTY: + /* ignore duplicate names */ + __of_add_property_sysfs(ce->np, ce->prop); + break; + case OF_RECONFIG_REMOVE_PROPERTY: + __of_remove_property_sysfs(ce->np, ce->prop); + break; + case OF_RECONFIG_UPDATE_PROPERTY: + __of_update_property_sysfs(ce->np, ce->prop, ce->old_prop); + break; + } + + return 0; +} + +static inline int __of_changeset_entry_revert(struct of_changeset_entry *ce) +{ + struct of_changeset_entry ce_inverted; + + __of_changeset_entry_invert(ce, &ce_inverted); + return __of_changeset_entry_apply(&ce_inverted); +} + +/** + * of_changeset_init - Initialize a changeset for use + * + * @ocs: changeset pointer + * + * Initialize a changeset structure + */ +void of_changeset_init(struct of_changeset *ocs) +{ + memset(ocs, 0, sizeof(*ocs)); + INIT_LIST_HEAD(&ocs->entries); +} + +/** + * of_changeset_destroy - Destroy a changeset + * + * @ocs: changeset pointer + * + * Destroys a changeset. Note that if a changeset is applied, + * its changes to the tree cannot be reverted. + */ +void of_changeset_destroy(struct of_changeset *ocs) +{ + struct of_changeset_entry *ce, *cen; + + list_for_each_entry_safe_reverse(ce, cen, &ocs->entries, node) + __of_changeset_entry_destroy(ce); +} + +/** + * of_changeset_apply - Applies a changeset + * + * @ocs: changeset pointer + * + * Applies a changeset to the live tree. + * Any side-effects of live tree state changes are applied here on + * sucess, like creation/destruction of devices and side-effects + * like creation of sysfs properties and directories. + * Returns 0 on success, a negative error value in case of an error. + * On error the partially applied effects are reverted. + */ +int of_changeset_apply(struct of_changeset *ocs) +{ + struct of_changeset_entry *ce; + int ret; + + /* perform the rest of the work */ + pr_debug("of_changeset: applying...\n"); + list_for_each_entry(ce, &ocs->entries, node) { + ret = __of_changeset_entry_apply(ce); + if (ret) { + pr_err("%s: Error applying changeset (%d)\n", __func__, ret); + list_for_each_entry_continue_reverse(ce, &ocs->entries, node) + __of_changeset_entry_revert(ce); + return ret; + } + } + pr_debug("of_changeset: applied, emitting notifiers.\n"); + + /* drop the global lock while emitting notifiers */ + mutex_unlock(&of_mutex); + list_for_each_entry(ce, &ocs->entries, node) + __of_changeset_entry_notify(ce, 0); + mutex_lock(&of_mutex); + pr_debug("of_changeset: notifiers sent.\n"); + + return 0; +} + +/** + * of_changeset_revert - Reverts an applied changeset + * + * @ocs: changeset pointer + * + * Reverts a changeset returning the state of the tree to what it + * was before the application. + * Any side-effects like creation/destruction of devices and + * removal of sysfs properties and directories are applied. + * Returns 0 on success, a negative error value in case of an error. + */ +int of_changeset_revert(struct of_changeset *ocs) +{ + struct of_changeset_entry *ce; + int ret; + + pr_debug("of_changeset: reverting...\n"); + list_for_each_entry_reverse(ce, &ocs->entries, node) { + ret = __of_changeset_entry_revert(ce); + if (ret) { + pr_err("%s: Error reverting changeset (%d)\n", __func__, ret); + list_for_each_entry_continue(ce, &ocs->entries, node) + __of_changeset_entry_apply(ce); + return ret; + } + } + pr_debug("of_changeset: reverted, emitting notifiers.\n"); + + /* drop the global lock while emitting notifiers */ + mutex_unlock(&of_mutex); + list_for_each_entry_reverse(ce, &ocs->entries, node) + __of_changeset_entry_notify(ce, 1); + mutex_lock(&of_mutex); + pr_debug("of_changeset: notifiers sent.\n"); + + return 0; +} + +/** + * of_changeset_action - Perform a changeset action + * + * @ocs: changeset pointer + * @action: action to perform + * @np: Pointer to device node + * @prop: Pointer to property + * + * On action being one of: + * + OF_RECONFIG_ATTACH_NODE + * + OF_RECONFIG_DETACH_NODE, + * + OF_RECONFIG_ADD_PROPERTY + * + OF_RECONFIG_REMOVE_PROPERTY, + * + OF_RECONFIG_UPDATE_PROPERTY + * Returns 0 on success, a negative error value in case of an error. + */ +int of_changeset_action(struct of_changeset *ocs, unsigned long action, + struct device_node *np, struct property *prop) +{ + struct of_changeset_entry *ce; + + ce = kzalloc(sizeof(*ce), GFP_KERNEL); + if (!ce) { + pr_err("%s: Failed to allocate\n", __func__); + return -ENOMEM; + } + /* get a reference to the node */ + ce->action = action; + ce->np = of_node_get(np); + ce->prop = prop; + + if (action == OF_RECONFIG_UPDATE_PROPERTY && prop) + ce->old_prop = of_find_property(np, prop->name, NULL); + + /* add it to the list */ + list_add_tail(&ce->node, &ocs->entries); + return 0; +} diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 024b8f99d480..69f78cf203e5 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -157,6 +157,7 @@ static void * unflatten_dt_node(struct boot_param_header *blob, __alignof__(struct device_node)); if (allnextpp) { char *fn; + of_node_init(np); np->full_name = fn = ((char *)np) + sizeof(*np); if (new_format) { /* rebuild full path for new format */ @@ -187,7 +188,6 @@ static void * unflatten_dt_node(struct boot_param_header *blob, dad->next->sibling = np; dad->next = np; } - kref_init(&np->kref); } /* process properties */ for (offset = fdt_first_property_offset(blob, *poffset); diff --git a/drivers/of/irq.c b/drivers/of/irq.c index ca0189308d72..bbff99dcbaea 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -290,7 +290,7 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar struct device_node *p; const __be32 *intspec, *tmp, *addr; u32 intsize, intlen; - int i, res = -EINVAL; + int i, res; pr_debug("of_irq_parse_one: dev=%s, index=%d\n", of_node_full_name(device), index); @@ -301,16 +301,17 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar /* Get the reg property (if any) */ addr = of_get_property(device, "reg", NULL); + /* Try the new-style interrupts-extended first */ + res = of_parse_phandle_with_args(device, "interrupts-extended", + "#interrupt-cells", index, out_irq); + if (!res) + return of_irq_parse_raw(addr, out_irq); + /* Get the interrupts property */ intspec = of_get_property(device, "interrupts", &intlen); - if (intspec == NULL) { - /* Try the new-style interrupts-extended */ - res = of_parse_phandle_with_args(device, "interrupts-extended", - "#interrupt-cells", index, out_irq); - if (res) - return -EINVAL; - return of_irq_parse_raw(addr, out_irq); - } + if (intspec == NULL) + return -EINVAL; + intlen /= sizeof(*intspec); pr_debug(" intspec=%d intlen=%d\n", be32_to_cpup(intspec), intlen); @@ -322,15 +323,19 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar /* Get size of interrupt specifier */ tmp = of_get_property(p, "#interrupt-cells", NULL); - if (tmp == NULL) + if (tmp == NULL) { + res = -EINVAL; goto out; + } intsize = be32_to_cpu(*tmp); pr_debug(" intsize=%d intlen=%d\n", intsize, intlen); /* Check index */ - if ((index + 1) * intsize > intlen) + if ((index + 1) * intsize > intlen) { + res = -EINVAL; goto out; + } /* Copy intspec into irq structure */ intspec += index * intsize; diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h index ff350c8fa7ac..8e882e706cd8 100644 --- a/drivers/of/of_private.h +++ b/drivers/of/of_private.h @@ -31,6 +31,63 @@ struct alias_prop { char stem[0]; }; -extern struct mutex of_aliases_mutex; +extern struct mutex of_mutex; extern struct list_head aliases_lookup; +extern struct kset *of_kset; + + +static inline struct device_node *kobj_to_device_node(struct kobject *kobj) +{ + return container_of(kobj, struct device_node, kobj); +} + +#if defined(CONFIG_OF_DYNAMIC) +extern int of_property_notify(int action, struct device_node *np, + struct property *prop, struct property *old_prop); +extern void of_node_release(struct kobject *kobj); +#else /* CONFIG_OF_DYNAMIC */ +static inline int of_property_notify(int action, struct device_node *np, + struct property *prop, struct property *old_prop) +{ + return 0; +} +#endif /* CONFIG_OF_DYNAMIC */ + +/** + * General utilities for working with live trees. + * + * All functions with two leading underscores operate + * without taking node references, so you either have to + * own the devtree lock or work on detached trees only. + */ +struct property *__of_prop_dup(const struct property *prop, gfp_t allocflags); +__printf(2, 3) struct device_node *__of_node_dup(const struct device_node *np, const char *fmt, ...); + +extern const void *__of_get_property(const struct device_node *np, + const char *name, int *lenp); +extern int __of_add_property(struct device_node *np, struct property *prop); +extern int __of_add_property_sysfs(struct device_node *np, + struct property *prop); +extern int __of_remove_property(struct device_node *np, struct property *prop); +extern void __of_remove_property_sysfs(struct device_node *np, + struct property *prop); +extern int __of_update_property(struct device_node *np, + struct property *newprop, struct property **oldprop); +extern void __of_update_property_sysfs(struct device_node *np, + struct property *newprop, struct property *oldprop); + +extern void __of_attach_node(struct device_node *np); +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); + +/* iterators for transactions, used for overlays */ +/* forward iterator */ +#define for_each_transaction_entry(_oft, _te) \ + list_for_each_entry(_te, &(_oft)->te_list, node) + +/* reverse iterator */ +#define for_each_transaction_entry_reverse(_oft, _te) \ + list_for_each_entry_reverse(_te, &(_oft)->te_list, node) + #endif /* _LINUX_OF_PRIVATE_H */ diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c new file mode 100644 index 000000000000..406664801cb5 --- /dev/null +++ b/drivers/of/overlay.c @@ -0,0 +1,552 @@ +/* + * Functions for working with device tree overlays + * + * Copyright (C) 2012 Pantelis Antoniou <panto@antoniou-consulting.com> + * Copyright (C) 2012 Texas Instruments Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + */ +#undef DEBUG +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/string.h> +#include <linux/ctype.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/slab.h> +#include <linux/err.h> +#include <linux/idr.h> + +#include "of_private.h" + +/** + * struct of_overlay_info - Holds a single overlay info + * @target: target of the overlay operation + * @overlay: pointer to the overlay contents node + * + * Holds a single overlay state, including all the overlay logs & + * records. + */ +struct of_overlay_info { + struct device_node *target; + struct device_node *overlay; +}; + +/** + * struct of_overlay - Holds a complete overlay transaction + * @node: List on which we are located + * @count: Count of ovinfo structures + * @ovinfo_tab: Overlay info table (count sized) + * @cset: Changeset to be used + * + * Holds a complete overlay transaction + */ +struct of_overlay { + int id; + struct list_head node; + int count; + struct of_overlay_info *ovinfo_tab; + struct of_changeset cset; +}; + +static int of_overlay_apply_one(struct of_overlay *ov, + struct device_node *target, const struct device_node *overlay); + +static int of_overlay_apply_single_property(struct of_overlay *ov, + struct device_node *target, struct property *prop) +{ + struct property *propn, *tprop; + + /* NOTE: Multiple changes of single properties not supported */ + tprop = of_find_property(target, prop->name, NULL); + + /* special properties are not meant to be updated (silent NOP) */ + if (of_prop_cmp(prop->name, "name") == 0 || + of_prop_cmp(prop->name, "phandle") == 0 || + of_prop_cmp(prop->name, "linux,phandle") == 0) + return 0; + + propn = __of_prop_dup(prop, GFP_KERNEL); + if (propn == NULL) + return -ENOMEM; + + /* not found? add */ + if (tprop == NULL) + return of_changeset_add_property(&ov->cset, target, propn); + + /* found? update */ + return of_changeset_update_property(&ov->cset, target, propn); +} + +static int of_overlay_apply_single_device_node(struct of_overlay *ov, + struct device_node *target, struct device_node *child) +{ + const char *cname; + struct device_node *tchild, *grandchild; + int ret = 0; + + cname = kbasename(child->full_name); + if (cname == NULL) + return -ENOMEM; + + /* NOTE: Multiple mods of created nodes not supported */ + tchild = of_get_child_by_name(target, cname); + if (tchild != NULL) { + /* apply overlay recursively */ + ret = of_overlay_apply_one(ov, tchild, child); + of_node_put(tchild); + } else { + /* create empty tree as a target */ + tchild = __of_node_dup(child, "%s/%s", target->full_name, cname); + if (!tchild) + return -ENOMEM; + + /* point to parent */ + tchild->parent = target; + + ret = of_changeset_attach_node(&ov->cset, tchild); + if (ret) + return ret; + + ret = of_overlay_apply_one(ov, tchild, child); + if (ret) + return ret; + } + + return ret; +} + +/* + * Apply a single overlay node recursively. + * + * Note that the in case of an error the target node is left + * in a inconsistent state. Error recovery should be performed + * by using the changeset. + */ +static int of_overlay_apply_one(struct of_overlay *ov, + struct device_node *target, const struct device_node *overlay) +{ + struct device_node *child; + struct property *prop; + int ret; + + for_each_property_of_node(overlay, prop) { + ret = of_overlay_apply_single_property(ov, target, prop); + if (ret) { + pr_err("%s: Failed to apply prop @%s/%s\n", + __func__, target->full_name, prop->name); + return ret; + } + } + + for_each_child_of_node(overlay, child) { + ret = of_overlay_apply_single_device_node(ov, target, child); + if (ret != 0) { + pr_err("%s: Failed to apply single node @%s/%s\n", + __func__, target->full_name, + child->name); + return ret; + } + } + + return 0; +} + +/** + * of_overlay_apply() - Apply @count overlays pointed at by @ovinfo_tab + * @ov: Overlay to apply + * + * Applies the overlays given, while handling all error conditions + * appropriately. Either the operation succeeds, or if it fails the + * live tree is reverted to the state before the attempt. + * Returns 0, or an error if the overlay attempt failed. + */ +static int of_overlay_apply(struct of_overlay *ov) +{ + int i, err; + + /* first we apply the overlays atomically */ + for (i = 0; i < ov->count; i++) { + struct of_overlay_info *ovinfo = &ov->ovinfo_tab[i]; + + err = of_overlay_apply_one(ov, ovinfo->target, ovinfo->overlay); + if (err != 0) { + pr_err("%s: overlay failed '%s'\n", + __func__, ovinfo->target->full_name); + return err; + } + } + + return 0; +} + +/* + * Find the target node using a number of different strategies + * in order of preference + * + * "target" property containing the phandle of the target + * "target-path" property containing the path of the target + */ +static struct device_node *find_target_node(struct device_node *info_node) +{ + const char *path; + u32 val; + int ret; + + /* first try to go by using the target as a phandle */ + ret = of_property_read_u32(info_node, "target", &val); + if (ret == 0) + return of_find_node_by_phandle(val); + + /* now try to locate by path */ + ret = of_property_read_string(info_node, "target-path", &path); + if (ret == 0) + return of_find_node_by_path(path); + + pr_err("%s: Failed to find target for node %p (%s)\n", __func__, + info_node, info_node->name); + + return NULL; +} + +/** + * of_fill_overlay_info() - Fill an overlay info structure + * @ov Overlay to fill + * @info_node: Device node containing the overlay + * @ovinfo: Pointer to the overlay info structure to fill + * + * Fills an overlay info structure with the overlay information + * from a device node. This device node must have a target property + * which contains a phandle of the overlay target node, and an + * __overlay__ child node which has the overlay contents. + * Both ovinfo->target & ovinfo->overlay have their references taken. + * + * Returns 0 on success, or a negative error value. + */ +static int of_fill_overlay_info(struct of_overlay *ov, + struct device_node *info_node, struct of_overlay_info *ovinfo) +{ + ovinfo->overlay = of_get_child_by_name(info_node, "__overlay__"); + if (ovinfo->overlay == NULL) + goto err_fail; + + ovinfo->target = find_target_node(info_node); + if (ovinfo->target == NULL) + goto err_fail; + + return 0; + +err_fail: + of_node_put(ovinfo->target); + of_node_put(ovinfo->overlay); + + memset(ovinfo, 0, sizeof(*ovinfo)); + return -EINVAL; +} + +/** + * of_build_overlay_info() - Build an overlay info array + * @ov Overlay to build + * @tree: Device node containing all the overlays + * + * Helper function that given a tree containing overlay information, + * allocates and builds an overlay info array containing it, ready + * for use using of_overlay_apply. + * + * Returns 0 on success with the @cntp @ovinfop pointers valid, + * while on error a negative error value is returned. + */ +static int of_build_overlay_info(struct of_overlay *ov, + struct device_node *tree) +{ + struct device_node *node; + struct of_overlay_info *ovinfo; + int cnt, err; + + /* worst case; every child is a node */ + cnt = 0; + for_each_child_of_node(tree, node) + cnt++; + + ovinfo = kcalloc(cnt, sizeof(*ovinfo), GFP_KERNEL); + if (ovinfo == NULL) + return -ENOMEM; + + cnt = 0; + for_each_child_of_node(tree, node) { + memset(&ovinfo[cnt], 0, sizeof(*ovinfo)); + err = of_fill_overlay_info(ov, node, &ovinfo[cnt]); + if (err == 0) + cnt++; + } + + /* if nothing filled, return error */ + if (cnt == 0) { + kfree(ovinfo); + return -ENODEV; + } + + ov->count = cnt; + ov->ovinfo_tab = ovinfo; + + return 0; +} + +/** + * of_free_overlay_info() - Free an overlay info array + * @ov Overlay to free the overlay info from + * @ovinfo_tab: Array of overlay_info's to free + * + * Releases the memory of a previously allocated ovinfo array + * by of_build_overlay_info. + * Returns 0, or an error if the arguments are bogus. + */ +static int of_free_overlay_info(struct of_overlay *ov) +{ + struct of_overlay_info *ovinfo; + int i; + + /* do it in reverse */ + for (i = ov->count - 1; i >= 0; i--) { + ovinfo = &ov->ovinfo_tab[i]; + + of_node_put(ovinfo->target); + of_node_put(ovinfo->overlay); + } + kfree(ov->ovinfo_tab); + + return 0; +} + +static LIST_HEAD(ov_list); +static DEFINE_IDR(ov_idr); + +/** + * of_overlay_create() - Create and apply an overlay + * @tree: Device node containing all the overlays + * + * Creates and applies an overlay while also keeping track + * of the overlay in a list. This list can be used to prevent + * illegal overlay removals. + * + * Returns the id of the created overlay, or an negative error number + */ +int of_overlay_create(struct device_node *tree) +{ + struct of_overlay *ov; + int err, id; + + /* allocate the overlay structure */ + ov = kzalloc(sizeof(*ov), GFP_KERNEL); + if (ov == NULL) + return -ENOMEM; + ov->id = -1; + + INIT_LIST_HEAD(&ov->node); + + of_changeset_init(&ov->cset); + + mutex_lock(&of_mutex); + + id = idr_alloc(&ov_idr, ov, 0, 0, GFP_KERNEL); + if (id < 0) { + pr_err("%s: idr_alloc() failed for tree@%s\n", + __func__, tree->full_name); + err = id; + goto err_destroy_trans; + } + ov->id = id; + + /* build the overlay info structures */ + err = of_build_overlay_info(ov, tree); + if (err) { + pr_err("%s: of_build_overlay_info() failed for tree@%s\n", + __func__, tree->full_name); + goto err_free_idr; + } + + /* apply the overlay */ + err = of_overlay_apply(ov); + if (err) { + pr_err("%s: of_overlay_apply() failed for tree@%s\n", + __func__, tree->full_name); + goto err_abort_trans; + } + + /* apply the changeset */ + err = of_changeset_apply(&ov->cset); + if (err) { + pr_err("%s: of_changeset_apply() failed for tree@%s\n", + __func__, tree->full_name); + goto err_revert_overlay; + } + + /* add to the tail of the overlay list */ + list_add_tail(&ov->node, &ov_list); + + mutex_unlock(&of_mutex); + + return id; + +err_revert_overlay: +err_abort_trans: + of_free_overlay_info(ov); +err_free_idr: + idr_remove(&ov_idr, ov->id); +err_destroy_trans: + of_changeset_destroy(&ov->cset); + kfree(ov); + mutex_unlock(&of_mutex); + + return err; +} +EXPORT_SYMBOL_GPL(of_overlay_create); + +/* check whether the given node, lies under the given tree */ +static int overlay_subtree_check(struct device_node *tree, + struct device_node *dn) +{ + struct device_node *child; + + /* match? */ + if (tree == dn) + return 1; + + for_each_child_of_node(tree, child) { + if (overlay_subtree_check(child, dn)) + return 1; + } + + return 0; +} + +/* check whether this overlay is the topmost */ +static int overlay_is_topmost(struct of_overlay *ov, struct device_node *dn) +{ + struct of_overlay *ovt; + struct of_changeset_entry *ce; + + list_for_each_entry_reverse(ovt, &ov_list, node) { + /* if we hit ourselves, we're done */ + if (ovt == ov) + break; + + /* check against each subtree affected by this overlay */ + list_for_each_entry(ce, &ovt->cset.entries, node) { + if (overlay_subtree_check(ce->np, dn)) { + pr_err("%s: #%d clashes #%d @%s\n", + __func__, ov->id, ovt->id, + dn->full_name); + return 0; + } + } + } + + /* overlay is topmost */ + return 1; +} + +/* + * We can safely remove the overlay only if it's the top-most one. + * Newly applied overlays are inserted at the tail of the overlay list, + * so a top most overlay is the one that is closest to the tail. + * + * The topmost check is done by exploiting this property. For each + * affected device node in the log list we check if this overlay is + * the one closest to the tail. If another overlay has affected this + * device node and is closest to the tail, then removal is not permited. + */ +static int overlay_removal_is_ok(struct of_overlay *ov) +{ + struct of_changeset_entry *ce; + + list_for_each_entry(ce, &ov->cset.entries, node) { + if (!overlay_is_topmost(ov, ce->np)) { + pr_err("%s: overlay #%d is not topmost\n", + __func__, ov->id); + return 0; + } + } + + return 1; +} + +/** + * of_overlay_destroy() - Removes an overlay + * @id: Overlay id number returned by a previous call to of_overlay_create + * + * Removes an overlay if it is permissible. + * + * Returns 0 on success, or an negative error number + */ +int of_overlay_destroy(int id) +{ + struct of_overlay *ov; + int err; + + mutex_lock(&of_mutex); + + ov = idr_find(&ov_idr, id); + if (ov == NULL) { + err = -ENODEV; + pr_err("%s: Could not find overlay #%d\n", + __func__, id); + goto out; + } + + /* check whether the overlay is safe to remove */ + if (!overlay_removal_is_ok(ov)) { + err = -EBUSY; + pr_err("%s: removal check failed for overlay #%d\n", + __func__, id); + goto out; + } + + + list_del(&ov->node); + of_changeset_revert(&ov->cset); + of_free_overlay_info(ov); + idr_remove(&ov_idr, id); + of_changeset_destroy(&ov->cset); + kfree(ov); + + err = 0; + +out: + mutex_unlock(&of_mutex); + + return err; +} +EXPORT_SYMBOL_GPL(of_overlay_destroy); + +/** + * of_overlay_destroy_all() - Removes all overlays from the system + * + * Removes all overlays from the system in the correct order. + * + * Returns 0 on success, or an negative error number + */ +int of_overlay_destroy_all(void) +{ + struct of_overlay *ov, *ovn; + + mutex_lock(&of_mutex); + + /* the tail of list is guaranteed to be safe to remove */ + list_for_each_entry_safe_reverse(ov, ovn, &ov_list, node) { + list_del(&ov->node); + of_changeset_revert(&ov->cset); + of_free_overlay_info(ov); + idr_remove(&ov_idr, ov->id); + kfree(ov); + } + + mutex_unlock(&of_mutex); + + return 0; +} +EXPORT_SYMBOL_GPL(of_overlay_destroy_all); diff --git a/drivers/of/pdt.c b/drivers/of/pdt.c index 7b666736c168..36b4035881b0 100644 --- a/drivers/of/pdt.c +++ b/drivers/of/pdt.c @@ -176,11 +176,10 @@ static struct device_node * __init of_pdt_create_node(phandle node, return NULL; dp = prom_early_alloc(sizeof(*dp)); + of_node_init(dp); of_pdt_incr_unique_id(dp); dp->parent = parent; - kref_init(&dp->kref); - dp->name = of_pdt_get_one_property(node, "name"); dp->type = of_pdt_get_one_property(node, "device_type"); dp->phandle = node; diff --git a/drivers/of/platform.c b/drivers/of/platform.c index bd47fbc53dc9..e7a3635ddcdf 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -51,10 +51,6 @@ struct platform_device *of_find_device_by_node(struct device_node *np) } EXPORT_SYMBOL(of_find_device_by_node); -#if defined(CONFIG_PPC_DCR) -#include <asm/dcr.h> -#endif - #ifdef CONFIG_OF_ADDRESS /* * The following routines scan a subtree and registers a device for @@ -68,66 +64,35 @@ EXPORT_SYMBOL(of_find_device_by_node); * of_device_make_bus_id - Use the device node data to assign a unique name * @dev: pointer to device structure that is linked to a device tree node * - * This routine will first try using either the dcr-reg or the reg property - * value to derive a unique name. As a last resort it will use the node - * name followed by a unique number. + * This routine will first try using the translated bus address to + * derive a unique name. If it cannot, then it will prepend names from + * parent nodes until a unique name can be derived. */ void of_device_make_bus_id(struct device *dev) { - static atomic_t bus_no_reg_magic; struct device_node *node = dev->of_node; const __be32 *reg; u64 addr; - const __be32 *addrp; - int magic; -#ifdef CONFIG_PPC_DCR - /* - * If it's a DCR based device, use 'd' for native DCRs - * and 'D' for MMIO DCRs. - */ - reg = of_get_property(node, "dcr-reg", NULL); - if (reg) { -#ifdef CONFIG_PPC_DCR_NATIVE - dev_set_name(dev, "d%x.%s", *reg, node->name); -#else /* CONFIG_PPC_DCR_NATIVE */ - u64 addr = of_translate_dcr_address(node, *reg, NULL); - if (addr != OF_BAD_ADDR) { - dev_set_name(dev, "D%llx.%s", - (unsigned long long)addr, node->name); + /* Construct the name, using parent nodes if necessary to ensure uniqueness */ + while (node->parent) { + /* + * If the address can be translated, then that is as much + * uniqueness as we need. Make it the first component and return + */ + reg = of_get_property(node, "reg", NULL); + if (reg && (addr = of_translate_address(node, reg)) != OF_BAD_ADDR) { + dev_set_name(dev, dev_name(dev) ? "%llx.%s:%s" : "%llx.%s", + (unsigned long long)addr, node->name, + dev_name(dev)); return; } -#endif /* !CONFIG_PPC_DCR_NATIVE */ - } -#endif /* CONFIG_PPC_DCR */ - /* - * For MMIO, get the physical address - */ - reg = of_get_property(node, "reg", NULL); - if (reg) { - if (of_can_translate_address(node)) { - addr = of_translate_address(node, reg); - } else { - addrp = of_get_address(node, 0, NULL, NULL); - if (addrp) - addr = of_read_number(addrp, 1); - else - addr = OF_BAD_ADDR; - } - if (addr != OF_BAD_ADDR) { - dev_set_name(dev, "%llx.%s", - (unsigned long long)addr, node->name); - return; - } + /* format arguments only used if dev_name() resolves to NULL */ + dev_set_name(dev, dev_name(dev) ? "%s:%s" : "%s", + strrchr(node->full_name, '/') + 1, dev_name(dev)); + node = node->parent; } - - /* - * No BusID, use the node name and add a globally incremented - * counter (and pray...) - */ - magic = atomic_add_return(1, &bus_no_reg_magic); - dev_set_name(dev, "%s.%d", node->name, magic - 1); } /** @@ -149,9 +114,8 @@ struct platform_device *of_device_alloc(struct device_node *np, return NULL; /* count the io and irq resources */ - if (of_can_translate_address(np)) - while (of_address_to_resource(np, num_reg, &temp_res) == 0) - num_reg++; + while (of_address_to_resource(np, num_reg, &temp_res) == 0) + num_reg++; num_irq = of_irq_count(np); /* Populate the resource table */ @@ -174,10 +138,7 @@ struct platform_device *of_device_alloc(struct device_node *np, } dev->dev.of_node = of_node_get(np); -#if defined(CONFIG_MICROBLAZE) - dev->dev.dma_mask = &dev->archdata.dma_mask; -#endif - dev->dev.parent = parent; + dev->dev.parent = parent ? : &platform_bus; if (bus_id) dev_set_name(&dev->dev, "%s", bus_id); @@ -206,12 +167,13 @@ static struct platform_device *of_platform_device_create_pdata( { struct platform_device *dev; - if (!of_device_is_available(np)) + if (!of_device_is_available(np) || + of_node_test_and_set_flag(np, OF_POPULATED)) return NULL; dev = of_device_alloc(np, bus_id, parent); if (!dev) - return NULL; + goto err_clear_flag; #if defined(CONFIG_MICROBLAZE) dev->archdata.dma_mask = 0xffffffffUL; @@ -229,10 +191,14 @@ static struct platform_device *of_platform_device_create_pdata( if (of_device_add(dev) != 0) { platform_device_put(dev); - return NULL; + goto err_clear_flag; } return dev; + +err_clear_flag: + of_node_clear_flag(np, OF_POPULATED); + return NULL; } /** @@ -264,20 +230,21 @@ static struct amba_device *of_amba_device_create(struct device_node *node, pr_debug("Creating amba device %s\n", node->full_name); - if (!of_device_is_available(node)) + if (!of_device_is_available(node) || + of_node_test_and_set_flag(node, OF_POPULATED)) return NULL; dev = amba_device_alloc(NULL, 0, 0); if (!dev) { pr_err("%s(): amba_device_alloc() failed for %s\n", __func__, node->full_name); - return NULL; + goto err_clear_flag; } /* setup generic device info */ dev->dev.coherent_dma_mask = ~0; dev->dev.of_node = of_node_get(node); - dev->dev.parent = parent; + dev->dev.parent = parent ? : &platform_bus; dev->dev.platform_data = platform_data; if (bus_id) dev_set_name(&dev->dev, "%s", bus_id); @@ -311,6 +278,8 @@ static struct amba_device *of_amba_device_create(struct device_node *node, err_free: amba_device_put(dev); +err_clear_flag: + of_node_clear_flag(node, OF_POPULATED); return NULL; } #else /* CONFIG_ARM_AMBA */ @@ -404,6 +373,7 @@ static int of_platform_bus_create(struct device_node *bus, break; } } + of_node_set_flag(bus, OF_POPULATED_BUS); return rc; } @@ -487,4 +457,109 @@ int of_platform_populate(struct device_node *root, return rc; } EXPORT_SYMBOL_GPL(of_platform_populate); + +static int of_platform_device_destroy(struct device *dev, void *data) +{ + /* Do not touch devices not populated from the device tree */ + if (!dev->of_node || !of_node_check_flag(dev->of_node, OF_POPULATED)) + return 0; + + /* Recurse for any nodes that were treated as busses */ + if (of_node_check_flag(dev->of_node, OF_POPULATED_BUS)) + device_for_each_child(dev, NULL, of_platform_device_destroy); + + if (dev->bus == &platform_bus_type) + platform_device_unregister(to_platform_device(dev)); +#ifdef CONFIG_ARM_AMBA + else if (dev->bus == &amba_bustype) + amba_device_unregister(to_amba_device(dev)); +#endif + + of_node_clear_flag(dev->of_node, OF_POPULATED); + of_node_clear_flag(dev->of_node, OF_POPULATED_BUS); + return 0; +} + +/** + * of_platform_depopulate() - Remove devices populated from device tree + * @parent: device which children will be removed + * + * Complementary to of_platform_populate(), this function removes children + * of the given device (and, recurrently, their children) that have been + * created from their respective device tree nodes (and only those, + * leaving others - eg. manually created - unharmed). + * + * Returns 0 when all children devices have been removed or + * -EBUSY when some children remained. + */ +void of_platform_depopulate(struct device *parent) +{ + device_for_each_child(parent, NULL, of_platform_device_destroy); +} +EXPORT_SYMBOL_GPL(of_platform_depopulate); + +#ifdef CONFIG_OF_DYNAMIC +static int of_platform_notify(struct notifier_block *nb, + unsigned long action, void *arg) +{ + struct of_reconfig_data *rd = arg; + struct platform_device *pdev_parent, *pdev; + bool children_left; + + switch (of_reconfig_get_state_change(action, rd)) { + case OF_RECONFIG_CHANGE_ADD: + /* verify that the parent is a bus */ + if (!of_node_check_flag(rd->dn->parent, OF_POPULATED_BUS)) + return NOTIFY_OK; /* not for us */ + + /* already populated? (driver using of_populate manually) */ + if (of_node_check_flag(rd->dn, OF_POPULATED)) + return NOTIFY_OK; + + /* pdev_parent may be NULL when no bus platform device */ + pdev_parent = of_find_device_by_node(rd->dn->parent); + pdev = of_platform_device_create(rd->dn, NULL, + pdev_parent ? &pdev_parent->dev : NULL); + of_dev_put(pdev_parent); + + if (pdev == NULL) { + pr_err("%s: failed to create for '%s'\n", + __func__, rd->dn->full_name); + /* of_platform_device_create tosses the error code */ + return notifier_from_errno(-EINVAL); + } + break; + + case OF_RECONFIG_CHANGE_REMOVE: + + /* already depopulated? */ + if (!of_node_check_flag(rd->dn, OF_POPULATED)) + return NOTIFY_OK; + + /* find our device by node */ + pdev = of_find_device_by_node(rd->dn); + if (pdev == NULL) + return NOTIFY_OK; /* no? not meant for us */ + + /* unregister takes one ref away */ + of_platform_device_destroy(&pdev->dev, &children_left); + + /* and put the reference of the find */ + of_dev_put(pdev); + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block platform_of_notifier = { + .notifier_call = of_platform_notify, +}; + +void of_platform_register_reconfig_notifier(void) +{ + WARN_ON(of_reconfig_notifier_register(&platform_of_notifier)); +} +#endif /* CONFIG_OF_DYNAMIC */ + #endif /* CONFIG_OF_ADDRESS */ diff --git a/drivers/of/resolver.c b/drivers/of/resolver.c new file mode 100644 index 000000000000..640eb4cb46e3 --- /dev/null +++ b/drivers/of/resolver.c @@ -0,0 +1,412 @@ +/* + * Functions for dealing with DT resolution + * + * Copyright (C) 2012 Pantelis Antoniou <panto@antoniou-consulting.com> + * Copyright (C) 2012 Texas Instruments Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/string.h> +#include <linux/ctype.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/slab.h> + +/* illegal phandle value (set when unresolved) */ +#define OF_PHANDLE_ILLEGAL 0xdeadbeef + +/** + * Find a node with the give full name by recursively following any of + * the child node links. + */ +static struct device_node *__of_find_node_by_full_name(struct device_node *node, + const char *full_name) +{ + struct device_node *child, *found; + + if (node == NULL) + return NULL; + + /* check */ + if (of_node_cmp(node->full_name, full_name) == 0) + return node; + + for_each_child_of_node(node, child) { + found = __of_find_node_by_full_name(child, full_name); + if (found != NULL) + return found; + } + + return NULL; +} + +/* + * Find live tree's maximum phandle value. + */ +static phandle of_get_tree_max_phandle(void) +{ + struct device_node *node; + phandle phandle; + unsigned long flags; + + /* now search recursively */ + raw_spin_lock_irqsave(&devtree_lock, flags); + phandle = 0; + for_each_of_allnodes(node) { + if (node->phandle != OF_PHANDLE_ILLEGAL && + node->phandle > phandle) + phandle = node->phandle; + } + raw_spin_unlock_irqrestore(&devtree_lock, flags); + + return phandle; +} + +/* + * Adjust a subtree's phandle values by a given delta. + * Makes sure not to just adjust the device node's phandle value, + * but modify the phandle properties values as well. + */ +static void __of_adjust_tree_phandles(struct device_node *node, + int phandle_delta) +{ + struct device_node *child; + struct property *prop; + phandle phandle; + + /* first adjust the node's phandle direct value */ + if (node->phandle != 0 && node->phandle != OF_PHANDLE_ILLEGAL) + node->phandle += phandle_delta; + + /* now adjust phandle & linux,phandle values */ + for_each_property_of_node(node, prop) { + + /* only look for these two */ + if (of_prop_cmp(prop->name, "phandle") != 0 && + of_prop_cmp(prop->name, "linux,phandle") != 0) + continue; + + /* must be big enough */ + if (prop->length < 4) + continue; + + /* read phandle value */ + phandle = be32_to_cpup(prop->value); + if (phandle == OF_PHANDLE_ILLEGAL) /* unresolved */ + continue; + + /* adjust */ + *(uint32_t *)prop->value = cpu_to_be32(node->phandle); + } + + /* now do the children recursively */ + for_each_child_of_node(node, child) + __of_adjust_tree_phandles(child, phandle_delta); +} + +static int __of_adjust_phandle_ref(struct device_node *node, + struct property *rprop, int value) +{ + phandle phandle; + struct device_node *refnode; + struct property *sprop; + char *propval, *propcur, *propend, *nodestr, *propstr, *s; + int offset, propcurlen; + int err = 0; + + /* make a copy */ + propval = kmalloc(rprop->length, GFP_KERNEL); + if (!propval) { + pr_err("%s: Could not copy value of '%s'\n", + __func__, rprop->name); + return -ENOMEM; + } + memcpy(propval, rprop->value, rprop->length); + + propend = propval + rprop->length; + for (propcur = propval; propcur < propend; propcur += propcurlen + 1) { + propcurlen = strlen(propcur); + + nodestr = propcur; + s = strchr(propcur, ':'); + if (!s) { + pr_err("%s: Illegal symbol entry '%s' (1)\n", + __func__, propcur); + err = -EINVAL; + goto err_fail; + } + *s++ = '\0'; + + propstr = s; + s = strchr(s, ':'); + if (!s) { + pr_err("%s: Illegal symbol entry '%s' (2)\n", + __func__, (char *)rprop->value); + err = -EINVAL; + goto err_fail; + } + + *s++ = '\0'; + err = kstrtoint(s, 10, &offset); + if (err != 0) { + pr_err("%s: Could get offset '%s'\n", + __func__, (char *)rprop->value); + goto err_fail; + } + + /* look into the resolve node for the full path */ + refnode = __of_find_node_by_full_name(node, nodestr); + if (!refnode) { + pr_warn("%s: Could not find refnode '%s'\n", + __func__, (char *)rprop->value); + continue; + } + + /* now find the property */ + for_each_property_of_node(refnode, sprop) { + if (of_prop_cmp(sprop->name, propstr) == 0) + break; + } + + if (!sprop) { + pr_err("%s: Could not find property '%s'\n", + __func__, (char *)rprop->value); + err = -ENOENT; + goto err_fail; + } + + phandle = value; + *(__be32 *)(sprop->value + offset) = cpu_to_be32(phandle); + } + +err_fail: + kfree(propval); + return err; +} + +/* compare nodes taking into account that 'name' strips out the @ part */ +static int __of_node_name_cmp(const struct device_node *dn1, + const struct device_node *dn2) +{ + const char *n1 = strrchr(dn1->full_name, '/') ? : "/"; + const char *n2 = strrchr(dn2->full_name, '/') ? : "/"; + + return of_node_cmp(n1, n2); +} + +/* + * Adjust the local phandle references by the given phandle delta. + * Assumes the existances of a __local_fixups__ node at the root. + * Assumes that __of_verify_tree_phandle_references has been called. + * Does not take any devtree locks so make sure you call this on a tree + * which is at the detached state. + */ +static int __of_adjust_tree_phandle_references(struct device_node *node, + struct device_node *target, int phandle_delta) +{ + struct device_node *child, *childtarget; + struct property *rprop, *sprop; + int err, i, count; + unsigned int off; + phandle phandle; + + if (node == NULL) + return 0; + + for_each_property_of_node(node, rprop) { + + /* skip properties added automatically */ + if (of_prop_cmp(rprop->name, "name") == 0 || + of_prop_cmp(rprop->name, "phandle") == 0 || + of_prop_cmp(rprop->name, "linux,phandle") == 0) + continue; + + if ((rprop->length % 4) != 0 || rprop->length == 0) { + pr_err("%s: Illegal property (size) '%s' @%s\n", + __func__, rprop->name, node->full_name); + return -EINVAL; + } + count = rprop->length / sizeof(__be32); + + /* now find the target property */ + for_each_property_of_node(target, sprop) { + if (of_prop_cmp(sprop->name, rprop->name) == 0) + break; + } + + if (sprop == NULL) { + pr_err("%s: Could not find target property '%s' @%s\n", + __func__, rprop->name, node->full_name); + return -EINVAL; + } + + for (i = 0; i < count; i++) { + off = be32_to_cpu(((__be32 *)rprop->value)[i]); + /* make sure the offset doesn't overstep (even wrap) */ + if (off >= sprop->length || + (off + 4) > sprop->length) { + pr_err("%s: Illegal property '%s' @%s\n", + __func__, rprop->name, + node->full_name); + return -EINVAL; + } + + if (phandle_delta) { + /* adjust */ + phandle = be32_to_cpu(*(__be32 *)(sprop->value + off)); + phandle += phandle_delta; + *(__be32 *)(sprop->value + off) = cpu_to_be32(phandle); + } + } + } + + for_each_child_of_node(node, child) { + + for_each_child_of_node(target, childtarget) + if (__of_node_name_cmp(child, childtarget) == 0) + break; + + if (!childtarget) { + pr_err("%s: Could not find target child '%s' @%s\n", + __func__, child->name, node->full_name); + return -EINVAL; + } + + err = __of_adjust_tree_phandle_references(child, childtarget, + phandle_delta); + if (err != 0) + return err; + } + + return 0; +} + +/** + * of_resolve - Resolve the given node against the live tree. + * + * @resolve: Node to resolve + * + * Perform dynamic Device Tree resolution against the live tree + * to the given node to resolve. This depends on the live tree + * having a __symbols__ node, and the resolve node the __fixups__ & + * __local_fixups__ nodes (if needed). + * The result of the operation is a resolve node that it's contents + * are fit to be inserted or operate upon the live tree. + * Returns 0 on success or a negative error value on error. + */ +int of_resolve_phandles(struct device_node *resolve) +{ + struct device_node *child, *childroot, *refnode; + struct device_node *root_sym, *resolve_sym, *resolve_fix; + struct property *rprop; + const char *refpath; + phandle phandle, phandle_delta; + int err; + + /* the resolve node must exist, and be detached */ + if (!resolve || !of_node_check_flag(resolve, OF_DETACHED)) + return -EINVAL; + + /* first we need to adjust the phandles */ + phandle_delta = of_get_tree_max_phandle() + 1; + __of_adjust_tree_phandles(resolve, phandle_delta); + + /* locate the local fixups */ + childroot = NULL; + for_each_child_of_node(resolve, childroot) + if (of_node_cmp(childroot->name, "__local_fixups__") == 0) + break; + + if (childroot != NULL) { + /* resolve root is guaranteed to be the '/' */ + err = __of_adjust_tree_phandle_references(childroot, + resolve, 0); + if (err != 0) + return err; + + BUG_ON(__of_adjust_tree_phandle_references(childroot, + resolve, phandle_delta)); + } + + root_sym = NULL; + resolve_sym = NULL; + resolve_fix = NULL; + + /* this may fail (if no fixups are required) */ + root_sym = of_find_node_by_path("/__symbols__"); + + /* locate the symbols & fixups nodes on resolve */ + for_each_child_of_node(resolve, child) { + + if (!resolve_sym && + of_node_cmp(child->name, "__symbols__") == 0) + resolve_sym = child; + + if (!resolve_fix && + of_node_cmp(child->name, "__fixups__") == 0) + resolve_fix = child; + + /* both found, don't bother anymore */ + if (resolve_sym && resolve_fix) + break; + } + + /* we do allow for the case where no fixups are needed */ + if (!resolve_fix) { + err = 0; /* no error */ + goto out; + } + + /* we need to fixup, but no root symbols... */ + if (!root_sym) { + err = -EINVAL; + goto out; + } + + for_each_property_of_node(resolve_fix, rprop) { + + /* skip properties added automatically */ + if (of_prop_cmp(rprop->name, "name") == 0) + continue; + + err = of_property_read_string(root_sym, + rprop->name, &refpath); + if (err != 0) { + pr_err("%s: Could not find symbol '%s'\n", + __func__, rprop->name); + goto out; + } + + refnode = of_find_node_by_path(refpath); + if (!refnode) { + pr_err("%s: Could not find node by path '%s'\n", + __func__, refpath); + err = -ENOENT; + goto out; + } + + phandle = refnode->phandle; + of_node_put(refnode); + + pr_debug("%s: %s phandle is 0x%08x\n", + __func__, rprop->name, phandle); + + err = __of_adjust_phandle_ref(resolve, rprop, phandle); + if (err) + break; + } + +out: + /* NULL is handled by of_node_put as NOP */ + of_node_put(root_sym); + + return err; +} +EXPORT_SYMBOL_GPL(of_resolve_phandles); diff --git a/drivers/of/selftest.c b/drivers/of/selftest.c index 6643d1920985..70c61d75b75e 100644 --- a/drivers/of/selftest.c +++ b/drivers/of/selftest.c @@ -132,8 +132,9 @@ static void __init of_selftest_parse_phandle_with_args(void) selftest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); } -static void __init of_selftest_property_match_string(void) +static void __init of_selftest_property_string(void) { + const char *strings[4]; struct device_node *np; int rc; @@ -150,13 +151,66 @@ static void __init of_selftest_property_match_string(void) rc = of_property_match_string(np, "phandle-list-names", "third"); selftest(rc == 2, "third expected:0 got:%i\n", rc); rc = of_property_match_string(np, "phandle-list-names", "fourth"); - selftest(rc == -ENODATA, "unmatched string; rc=%i", rc); + selftest(rc == -ENODATA, "unmatched string; rc=%i\n", rc); rc = of_property_match_string(np, "missing-property", "blah"); - selftest(rc == -EINVAL, "missing property; rc=%i", rc); + selftest(rc == -EINVAL, "missing property; rc=%i\n", rc); rc = of_property_match_string(np, "empty-property", "blah"); - selftest(rc == -ENODATA, "empty property; rc=%i", rc); + selftest(rc == -ENODATA, "empty property; rc=%i\n", rc); rc = of_property_match_string(np, "unterminated-string", "blah"); - selftest(rc == -EILSEQ, "unterminated string; rc=%i", rc); + selftest(rc == -EILSEQ, "unterminated string; rc=%i\n", rc); + + /* of_property_count_strings() tests */ + rc = of_property_count_strings(np, "string-property"); + selftest(rc == 1, "Incorrect string count; rc=%i\n", rc); + rc = of_property_count_strings(np, "phandle-list-names"); + selftest(rc == 3, "Incorrect string count; rc=%i\n", rc); + rc = of_property_count_strings(np, "unterminated-string"); + selftest(rc == -EILSEQ, "unterminated string; rc=%i\n", rc); + rc = of_property_count_strings(np, "unterminated-string-list"); + selftest(rc == -EILSEQ, "unterminated string array; rc=%i\n", rc); + + /* of_property_read_string_index() tests */ + rc = of_property_read_string_index(np, "string-property", 0, strings); + selftest(rc == 0 && !strcmp(strings[0], "foobar"), "of_property_read_string_index() failure; rc=%i\n", rc); + strings[0] = NULL; + rc = of_property_read_string_index(np, "string-property", 1, strings); + selftest(rc == -ENODATA && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc); + rc = of_property_read_string_index(np, "phandle-list-names", 0, strings); + selftest(rc == 0 && !strcmp(strings[0], "first"), "of_property_read_string_index() failure; rc=%i\n", rc); + rc = of_property_read_string_index(np, "phandle-list-names", 1, strings); + selftest(rc == 0 && !strcmp(strings[0], "second"), "of_property_read_string_index() failure; rc=%i\n", rc); + rc = of_property_read_string_index(np, "phandle-list-names", 2, strings); + selftest(rc == 0 && !strcmp(strings[0], "third"), "of_property_read_string_index() failure; rc=%i\n", rc); + strings[0] = NULL; + rc = of_property_read_string_index(np, "phandle-list-names", 3, strings); + selftest(rc == -ENODATA && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc); + strings[0] = NULL; + rc = of_property_read_string_index(np, "unterminated-string", 0, strings); + selftest(rc == -EILSEQ && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc); + rc = of_property_read_string_index(np, "unterminated-string-list", 0, strings); + selftest(rc == 0 && !strcmp(strings[0], "first"), "of_property_read_string_index() failure; rc=%i\n", rc); + strings[0] = NULL; + rc = of_property_read_string_index(np, "unterminated-string-list", 2, strings); /* should fail */ + selftest(rc == -EILSEQ && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc); + strings[1] = NULL; + + /* of_property_read_string_array() tests */ + rc = of_property_read_string_array(np, "string-property", strings, 4); + selftest(rc == 1, "Incorrect string count; rc=%i\n", rc); + rc = of_property_read_string_array(np, "phandle-list-names", strings, 4); + selftest(rc == 3, "Incorrect string count; rc=%i\n", rc); + rc = of_property_read_string_array(np, "unterminated-string", strings, 4); + selftest(rc == -EILSEQ, "unterminated string; rc=%i\n", rc); + /* -- An incorrectly formed string should cause a failure */ + rc = of_property_read_string_array(np, "unterminated-string-list", strings, 4); + selftest(rc == -EILSEQ, "unterminated string array; rc=%i\n", rc); + /* -- parsing the correctly formed strings should still work: */ + strings[2] = NULL; + rc = of_property_read_string_array(np, "unterminated-string-list", strings, 2); + selftest(rc == 2 && strings[2] == NULL, "of_property_read_string_array() failure; rc=%i\n", rc); + strings[1] = NULL; + rc = of_property_read_string_array(np, "phandle-list-names", strings, 1); + selftest(rc == 1 && strings[1] == NULL, "Overwrote end of string array; rc=%i, str='%s'\n", rc, strings[1]); } static void __init of_selftest_parse_interrupts(void) @@ -379,7 +433,7 @@ static int __init of_selftest(void) pr_info("start of selftest - you will see error messages\n"); of_selftest_parse_phandle_with_args(); - of_selftest_property_match_string(); + of_selftest_property_string(); of_selftest_parse_interrupts(); of_selftest_parse_interrupts_extended(); of_selftest_match_node(); diff --git a/drivers/of/testcase-data/testcases.dtsi b/drivers/of/testcase-data/testcases.dtsi deleted file mode 100644 index 3a5b75a8e4d7..000000000000 --- a/drivers/of/testcase-data/testcases.dtsi +++ /dev/null @@ -1,3 +0,0 @@ -#include "tests-phandle.dtsi" -#include "tests-interrupts.dtsi" -#include "tests-match.dtsi" diff --git a/drivers/of/unittest-data/testcases.dts b/drivers/of/unittest-data/testcases.dts new file mode 100644 index 000000000000..16c9c8775a5c --- /dev/null +++ b/drivers/of/unittest-data/testcases.dts @@ -0,0 +1,79 @@ +/dts-v1/; +/ { + testcase-data { + changeset { + prop-update = "hello"; + prop-remove = "world"; + node-remove { + }; + }; + }; +}; +#include "tests-phandle.dtsi" +#include "tests-interrupts.dtsi" +#include "tests-match.dtsi" +#include "tests-platform.dtsi" +#include "tests-overlay.dtsi" + +/* + * phandle fixup data - generated by dtc patches that aren't upstream. + * This data must be regenerated whenever phandle references are modified in + * the testdata tree. + * + * The format of this data may be subject to change. For the time being consider + * this a kernel-internal data format. + */ +/ { __local_fixups__ { + testcase-data { + phandle-tests { + consumer-a { + phandle-list = <0x00000000 0x00000008 + 0x00000018 0x00000028 + 0x00000034 0x00000038>; + phandle-list-bad-args = <0x00000000 0x0000000c>; + }; + }; + interrupts { + intmap0 { + interrupt-map = <0x00000004 0x00000010 + 0x00000024 0x00000034>; + }; + intmap1 { + interrupt-map = <0x0000000c>; + }; + interrupts0 { + interrupt-parent = <0x00000000>; + }; + interrupts1 { + interrupt-parent = <0x00000000>; + }; + interrupts-extended0 { + interrupts-extended = <0x00000000 0x00000008 + 0x00000018 0x00000024 + 0x0000002c 0x00000034 + 0x0000003c>; + }; + }; + testcase-device1 { + interrupt-parent = <0x00000000>; + }; + testcase-device2 { + interrupt-parent = <0x00000000>; + }; + overlay2 { + fragment@0 { + target = <0x00000000>; + }; + }; + overlay3 { + fragment@0 { + target = <0x00000000>; + }; + }; + overlay4 { + fragment@0 { + target = <0x00000000>; + }; + }; + }; +}; }; diff --git a/drivers/of/testcase-data/tests-interrupts.dtsi b/drivers/of/unittest-data/tests-interrupts.dtsi index c843720bd3e5..da4695f60351 100644 --- a/drivers/of/testcase-data/tests-interrupts.dtsi +++ b/drivers/of/unittest-data/tests-interrupts.dtsi @@ -54,5 +54,18 @@ <&test_intmap1 1 2>; }; }; + + testcase-device1 { + compatible = "testcase-device"; + interrupt-parent = <&test_intc0>; + interrupts = <1>; + }; + + testcase-device2 { + compatible = "testcase-device"; + interrupt-parent = <&test_intc2>; + interrupts = <1>; /* invalid specifier - too short */ + }; }; + }; diff --git a/drivers/of/testcase-data/tests-match.dtsi b/drivers/of/unittest-data/tests-match.dtsi index c9e541129534..c9e541129534 100644 --- a/drivers/of/testcase-data/tests-match.dtsi +++ b/drivers/of/unittest-data/tests-match.dtsi diff --git a/drivers/of/unittest-data/tests-overlay.dtsi b/drivers/of/unittest-data/tests-overlay.dtsi new file mode 100644 index 000000000000..244226cbb5a3 --- /dev/null +++ b/drivers/of/unittest-data/tests-overlay.dtsi @@ -0,0 +1,329 @@ + +/ { + testcase-data { + overlay-node { + + /* test bus */ + selftestbus: test-bus { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <0>; + + selftest100: test-selftest100 { + compatible = "selftest"; + status = "okay"; + reg = <100>; + }; + + selftest101: test-selftest101 { + compatible = "selftest"; + status = "disabled"; + reg = <101>; + }; + + selftest0: test-selftest0 { + compatible = "selftest"; + status = "disabled"; + reg = <0>; + }; + + selftest1: test-selftest1 { + compatible = "selftest"; + status = "okay"; + reg = <1>; + }; + + selftest2: test-selftest2 { + compatible = "selftest"; + status = "disabled"; + reg = <2>; + }; + + selftest3: test-selftest3 { + compatible = "selftest"; + status = "okay"; + reg = <3>; + }; + + selftest5: test-selftest5 { + compatible = "selftest"; + status = "disabled"; + reg = <5>; + }; + + selftest6: test-selftest6 { + compatible = "selftest"; + status = "disabled"; + reg = <6>; + }; + + selftest7: test-selftest7 { + compatible = "selftest"; + status = "disabled"; + reg = <7>; + }; + + selftest8: test-selftest8 { + compatible = "selftest"; + status = "disabled"; + reg = <8>; + }; + + i2c-test-bus { + compatible = "selftest-i2c-bus"; + status = "okay"; + reg = <50>; + + #address-cells = <1>; + #size-cells = <0>; + + test-selftest12 { + reg = <8>; + compatible = "selftest-i2c-dev"; + status = "disabled"; + }; + + test-selftest13 { + reg = <9>; + compatible = "selftest-i2c-dev"; + status = "okay"; + }; + + test-selftest14 { + reg = <10>; + compatible = "selftest-i2c-mux"; + status = "okay"; + + #address-cells = <1>; + #size-cells = <0>; + + i2c@0 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0>; + + test-mux-dev { + reg = <32>; + compatible = "selftest-i2c-dev"; + status = "okay"; + }; + }; + }; + }; + }; + }; + + /* test enable using absolute target path */ + overlay0 { + fragment@0 { + target-path = "/testcase-data/overlay-node/test-bus/test-selftest0"; + __overlay__ { + status = "okay"; + }; + }; + }; + + /* test disable using absolute target path */ + overlay1 { + fragment@0 { + target-path = "/testcase-data/overlay-node/test-bus/test-selftest1"; + __overlay__ { + status = "disabled"; + }; + }; + }; + + /* test enable using label */ + overlay2 { + fragment@0 { + target = <&selftest2>; + __overlay__ { + status = "okay"; + }; + }; + }; + + /* test disable using label */ + overlay3 { + fragment@0 { + target = <&selftest3>; + __overlay__ { + status = "disabled"; + }; + }; + }; + + /* test insertion of a full node */ + overlay4 { + fragment@0 { + target = <&selftestbus>; + __overlay__ { + + /* suppress DTC warning */ + #address-cells = <1>; + #size-cells = <0>; + + test-selftest4 { + compatible = "selftest"; + status = "okay"; + reg = <4>; + }; + }; + }; + }; + + /* test overlay apply revert */ + overlay5 { + fragment@0 { + target-path = "/testcase-data/overlay-node/test-bus/test-selftest5"; + __overlay__ { + status = "okay"; + }; + }; + }; + + /* test overlays application and removal in sequence */ + overlay6 { + fragment@0 { + target-path = "/testcase-data/overlay-node/test-bus/test-selftest6"; + __overlay__ { + status = "okay"; + }; + }; + }; + overlay7 { + fragment@0 { + target-path = "/testcase-data/overlay-node/test-bus/test-selftest7"; + __overlay__ { + status = "okay"; + }; + }; + }; + + /* test overlays application and removal in bad sequence */ + overlay8 { + fragment@0 { + target-path = "/testcase-data/overlay-node/test-bus/test-selftest8"; + __overlay__ { + status = "okay"; + }; + }; + }; + overlay9 { + fragment@0 { + target-path = "/testcase-data/overlay-node/test-bus/test-selftest8"; + __overlay__ { + property-foo = "bar"; + }; + }; + }; + + overlay10 { + fragment@0 { + target-path = "/testcase-data/overlay-node/test-bus"; + __overlay__ { + + /* suppress DTC warning */ + #address-cells = <1>; + #size-cells = <0>; + + test-selftest10 { + compatible = "selftest"; + status = "okay"; + reg = <10>; + + #address-cells = <1>; + #size-cells = <0>; + + test-selftest101 { + compatible = "selftest"; + status = "okay"; + reg = <1>; + }; + + }; + }; + }; + }; + + overlay11 { + fragment@0 { + target-path = "/testcase-data/overlay-node/test-bus"; + __overlay__ { + + /* suppress DTC warning */ + #address-cells = <1>; + #size-cells = <0>; + + test-selftest11 { + compatible = "selftest"; + status = "okay"; + reg = <11>; + + #address-cells = <1>; + #size-cells = <0>; + + test-selftest111 { + compatible = "selftest"; + status = "okay"; + reg = <1>; + }; + + }; + }; + }; + }; + + /* test enable using absolute target path (i2c) */ + overlay12 { + fragment@0 { + target-path = "/testcase-data/overlay-node/test-bus/i2c-test-bus/test-selftest12"; + __overlay__ { + status = "okay"; + }; + }; + }; + + /* test disable using absolute target path (i2c) */ + overlay13 { + fragment@0 { + target-path = "/testcase-data/overlay-node/test-bus/i2c-test-bus/test-selftest13"; + __overlay__ { + status = "disabled"; + }; + }; + }; + + /* test mux overlay */ + overlay15 { + fragment@0 { + target-path = "/testcase-data/overlay-node/test-bus/i2c-test-bus"; + __overlay__ { + #address-cells = <1>; + #size-cells = <0>; + test-selftest15 { + reg = <11>; + compatible = "selftest-i2c-mux"; + status = "okay"; + + #address-cells = <1>; + #size-cells = <0>; + + i2c@0 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0>; + + test-mux-dev { + reg = <32>; + compatible = "selftest-i2c-dev"; + status = "okay"; + }; + }; + }; + }; + }; + }; + + }; +}; diff --git a/drivers/of/testcase-data/tests-phandle.dtsi b/drivers/of/unittest-data/tests-phandle.dtsi index 0007d3cd7dc2..5b1527e8a7fb 100644 --- a/drivers/of/testcase-data/tests-phandle.dtsi +++ b/drivers/of/unittest-data/tests-phandle.dtsi @@ -1,6 +1,13 @@ / { - testcase-data { + aliases { + testcase-alias = &testcase; + }; + + testcase: testcase-data { + security-password = "password"; + duplicate-name = "duplicate"; + duplicate-name { }; phandle-tests { provider0: provider0 { #phandle-cells = <0>; @@ -32,7 +39,9 @@ phandle-list-bad-args = <&provider2 1 0>, <&provider3 0>; empty-property; + string-property = "foobar"; unterminated-string = [40 41 42 43]; + unterminated-string-list = "first", "second", [40 41 42 43]; }; }; }; diff --git a/drivers/of/unittest-data/tests-platform.dtsi b/drivers/of/unittest-data/tests-platform.dtsi new file mode 100644 index 000000000000..eb20eeb2b062 --- /dev/null +++ b/drivers/of/unittest-data/tests-platform.dtsi @@ -0,0 +1,35 @@ + +/ { + testcase-data { + platform-tests { + #address-cells = <1>; + #size-cells = <0>; + + test-device@0 { + compatible = "test-device"; + reg = <0x0>; + + #address-cells = <1>; + #size-cells = <0>; + + dev@100 { + compatible = "test-sub-device"; + reg = <0x100>; + }; + }; + + test-device@1 { + compatible = "test-device"; + reg = <0x1>; + + #address-cells = <1>; + #size-cells = <0>; + + dev@100 { + compatible = "test-sub-device"; + reg = <0x100>; + }; + }; + }; + }; +}; diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c new file mode 100644 index 000000000000..23249591d2e8 --- /dev/null +++ b/drivers/of/unittest.c @@ -0,0 +1,1858 @@ +/* + * Self tests for device tree subsystem + */ + +#define pr_fmt(fmt) "### dt-test ### " fmt + +#include <linux/clk.h> +#include <linux/err.h> +#include <linux/errno.h> +#include <linux/hashtable.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_fdt.h> +#include <linux/of_irq.h> +#include <linux/of_platform.h> +#include <linux/list.h> +#include <linux/mutex.h> +#include <linux/slab.h> +#include <linux/device.h> +#include <linux/platform_device.h> +#include <linux/of_platform.h> + +#include <linux/i2c.h> +#include <linux/i2c-mux.h> + +#include "of_private.h" + +static struct selftest_results { + int passed; + int failed; +} selftest_results; + +#define NO_OF_NODES 3 +static struct device_node *nodes[NO_OF_NODES]; +static int last_node_index; +static bool selftest_live_tree; + +#define selftest(result, fmt, ...) ({ \ + bool failed = !(result); \ + if (failed) { \ + selftest_results.failed++; \ + pr_err("FAIL %s():%i " fmt, __func__, __LINE__, ##__VA_ARGS__); \ + } else { \ + selftest_results.passed++; \ + pr_debug("pass %s():%i\n", __func__, __LINE__); \ + } \ + failed; \ +}) + +static void __init of_selftest_find_node_by_name(void) +{ + struct device_node *np; + + np = of_find_node_by_path("/testcase-data"); + selftest(np && !strcmp("/testcase-data", np->full_name), + "find /testcase-data failed\n"); + of_node_put(np); + + /* Test if trailing '/' works */ + np = of_find_node_by_path("/testcase-data/"); + selftest(!np, "trailing '/' on /testcase-data/ should fail\n"); + + np = of_find_node_by_path("/testcase-data/phandle-tests/consumer-a"); + selftest(np && !strcmp("/testcase-data/phandle-tests/consumer-a", np->full_name), + "find /testcase-data/phandle-tests/consumer-a failed\n"); + of_node_put(np); + + np = of_find_node_by_path("testcase-alias"); + selftest(np && !strcmp("/testcase-data", np->full_name), + "find testcase-alias failed\n"); + of_node_put(np); + + /* Test if trailing '/' works on aliases */ + np = of_find_node_by_path("testcase-alias/"); + selftest(!np, "trailing '/' on testcase-alias/ should fail\n"); + + np = of_find_node_by_path("testcase-alias/phandle-tests/consumer-a"); + selftest(np && !strcmp("/testcase-data/phandle-tests/consumer-a", np->full_name), + "find testcase-alias/phandle-tests/consumer-a failed\n"); + of_node_put(np); + + np = of_find_node_by_path("/testcase-data/missing-path"); + selftest(!np, "non-existent path returned node %s\n", np->full_name); + of_node_put(np); + + np = of_find_node_by_path("missing-alias"); + selftest(!np, "non-existent alias returned node %s\n", np->full_name); + of_node_put(np); + + np = of_find_node_by_path("testcase-alias/missing-path"); + selftest(!np, "non-existent alias with relative path returned node %s\n", np->full_name); + of_node_put(np); +} + +static void __init of_selftest_dynamic(void) +{ + struct device_node *np; + struct property *prop; + + np = of_find_node_by_path("/testcase-data"); + if (!np) { + pr_err("missing testcase data\n"); + return; + } + + /* Array of 4 properties for the purpose of testing */ + prop = kzalloc(sizeof(*prop) * 4, GFP_KERNEL); + if (!prop) { + selftest(0, "kzalloc() failed\n"); + return; + } + + /* Add a new property - should pass*/ + prop->name = "new-property"; + prop->value = "new-property-data"; + prop->length = strlen(prop->value); + selftest(of_add_property(np, prop) == 0, "Adding a new property failed\n"); + + /* Try to add an existing property - should fail */ + prop++; + prop->name = "new-property"; + prop->value = "new-property-data-should-fail"; + prop->length = strlen(prop->value); + selftest(of_add_property(np, prop) != 0, + "Adding an existing property should have failed\n"); + + /* Try to modify an existing property - should pass */ + prop->value = "modify-property-data-should-pass"; + prop->length = strlen(prop->value); + selftest(of_update_property(np, prop) == 0, + "Updating an existing property should have passed\n"); + + /* Try to modify non-existent property - should pass*/ + prop++; + prop->name = "modify-property"; + prop->value = "modify-missing-property-data-should-pass"; + prop->length = strlen(prop->value); + selftest(of_update_property(np, prop) == 0, + "Updating a missing property should have passed\n"); + + /* Remove property - should pass */ + selftest(of_remove_property(np, prop) == 0, + "Removing a property should have passed\n"); + + /* Adding very large property - should pass */ + prop++; + prop->name = "large-property-PAGE_SIZEx8"; + prop->length = PAGE_SIZE * 8; + prop->value = kzalloc(prop->length, GFP_KERNEL); + selftest(prop->value != NULL, "Unable to allocate large buffer\n"); + if (prop->value) + selftest(of_add_property(np, prop) == 0, + "Adding a large property should have passed\n"); +} + +static int __init of_selftest_check_node_linkage(struct device_node *np) +{ + struct device_node *child, *allnext_index = np; + int count = 0, rc; + + for_each_child_of_node(np, child) { + if (child->parent != np) { + pr_err("Child node %s links to wrong parent %s\n", + child->name, np->name); + return -EINVAL; + } + + while (allnext_index && allnext_index != child) + allnext_index = allnext_index->allnext; + if (allnext_index != child) { + pr_err("Node %s is ordered differently in sibling and allnode lists\n", + child->name); + return -EINVAL; + } + + rc = of_selftest_check_node_linkage(child); + if (rc < 0) + return rc; + count += rc; + } + + return count + 1; +} + +static void __init of_selftest_check_tree_linkage(void) +{ + struct device_node *np; + int allnode_count = 0, child_count; + + if (!of_allnodes) + return; + + for_each_of_allnodes(np) + allnode_count++; + child_count = of_selftest_check_node_linkage(of_allnodes); + + selftest(child_count > 0, "Device node data structure is corrupted\n"); + selftest(child_count == allnode_count, "allnodes list size (%i) doesn't match" + "sibling lists size (%i)\n", allnode_count, child_count); + pr_debug("allnodes list size (%i); sibling lists size (%i)\n", allnode_count, child_count); +} + +struct node_hash { + struct hlist_node node; + struct device_node *np; +}; + +static DEFINE_HASHTABLE(phandle_ht, 8); +static void __init of_selftest_check_phandles(void) +{ + struct device_node *np; + struct node_hash *nh; + struct hlist_node *tmp; + int i, dup_count = 0, phandle_count = 0; + + for_each_of_allnodes(np) { + if (!np->phandle) + continue; + + hash_for_each_possible(phandle_ht, nh, node, np->phandle) { + if (nh->np->phandle == np->phandle) { + pr_info("Duplicate phandle! %i used by %s and %s\n", + np->phandle, nh->np->full_name, np->full_name); + dup_count++; + break; + } + } + + nh = kzalloc(sizeof(*nh), GFP_KERNEL); + if (WARN_ON(!nh)) + return; + + nh->np = np; + hash_add(phandle_ht, &nh->node, np->phandle); + phandle_count++; + } + selftest(dup_count == 0, "Found %i duplicates in %i phandles\n", + dup_count, phandle_count); + + /* Clean up */ + hash_for_each_safe(phandle_ht, i, tmp, nh, node) { + hash_del(&nh->node); + kfree(nh); + } +} + +static void __init of_selftest_parse_phandle_with_args(void) +{ + struct device_node *np; + struct of_phandle_args args; + int i, rc; + + np = of_find_node_by_path("/testcase-data/phandle-tests/consumer-a"); + if (!np) { + pr_err("missing testcase data\n"); + return; + } + + rc = of_count_phandle_with_args(np, "phandle-list", "#phandle-cells"); + selftest(rc == 7, "of_count_phandle_with_args() returned %i, expected 7\n", rc); + + for (i = 0; i < 8; i++) { + bool passed = true; + rc = of_parse_phandle_with_args(np, "phandle-list", + "#phandle-cells", i, &args); + + /* Test the values from tests-phandle.dtsi */ + switch (i) { + case 0: + passed &= !rc; + passed &= (args.args_count == 1); + passed &= (args.args[0] == (i + 1)); + break; + case 1: + passed &= !rc; + passed &= (args.args_count == 2); + passed &= (args.args[0] == (i + 1)); + passed &= (args.args[1] == 0); + break; + case 2: + passed &= (rc == -ENOENT); + break; + case 3: + passed &= !rc; + passed &= (args.args_count == 3); + passed &= (args.args[0] == (i + 1)); + passed &= (args.args[1] == 4); + passed &= (args.args[2] == 3); + break; + case 4: + passed &= !rc; + passed &= (args.args_count == 2); + passed &= (args.args[0] == (i + 1)); + passed &= (args.args[1] == 100); + break; + case 5: + passed &= !rc; + passed &= (args.args_count == 0); + break; + case 6: + passed &= !rc; + passed &= (args.args_count == 1); + passed &= (args.args[0] == (i + 1)); + break; + case 7: + passed &= (rc == -ENOENT); + break; + default: + passed = false; + } + + selftest(passed, "index %i - data error on node %s rc=%i\n", + i, args.np->full_name, rc); + } + + /* Check for missing list property */ + rc = of_parse_phandle_with_args(np, "phandle-list-missing", + "#phandle-cells", 0, &args); + selftest(rc == -ENOENT, "expected:%i got:%i\n", -ENOENT, rc); + rc = of_count_phandle_with_args(np, "phandle-list-missing", + "#phandle-cells"); + selftest(rc == -ENOENT, "expected:%i got:%i\n", -ENOENT, rc); + + /* Check for missing cells property */ + rc = of_parse_phandle_with_args(np, "phandle-list", + "#phandle-cells-missing", 0, &args); + selftest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); + rc = of_count_phandle_with_args(np, "phandle-list", + "#phandle-cells-missing"); + selftest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); + + /* Check for bad phandle in list */ + rc = of_parse_phandle_with_args(np, "phandle-list-bad-phandle", + "#phandle-cells", 0, &args); + selftest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); + rc = of_count_phandle_with_args(np, "phandle-list-bad-phandle", + "#phandle-cells"); + selftest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); + + /* Check for incorrectly formed argument list */ + rc = of_parse_phandle_with_args(np, "phandle-list-bad-args", + "#phandle-cells", 1, &args); + selftest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); + rc = of_count_phandle_with_args(np, "phandle-list-bad-args", + "#phandle-cells"); + selftest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); +} + +static void __init of_selftest_property_match_string(void) +{ + struct device_node *np; + int rc; + + np = of_find_node_by_path("/testcase-data/phandle-tests/consumer-a"); + if (!np) { + pr_err("No testcase data in device tree\n"); + return; + } + + rc = of_property_match_string(np, "phandle-list-names", "first"); + selftest(rc == 0, "first expected:0 got:%i\n", rc); + rc = of_property_match_string(np, "phandle-list-names", "second"); + selftest(rc == 1, "second expected:0 got:%i\n", rc); + rc = of_property_match_string(np, "phandle-list-names", "third"); + selftest(rc == 2, "third expected:0 got:%i\n", rc); + rc = of_property_match_string(np, "phandle-list-names", "fourth"); + selftest(rc == -ENODATA, "unmatched string; rc=%i", rc); + rc = of_property_match_string(np, "missing-property", "blah"); + selftest(rc == -EINVAL, "missing property; rc=%i", rc); + rc = of_property_match_string(np, "empty-property", "blah"); + selftest(rc == -ENODATA, "empty property; rc=%i", rc); + rc = of_property_match_string(np, "unterminated-string", "blah"); + selftest(rc == -EILSEQ, "unterminated string; rc=%i", rc); +} + +#define propcmp(p1, p2) (((p1)->length == (p2)->length) && \ + (p1)->value && (p2)->value && \ + !memcmp((p1)->value, (p2)->value, (p1)->length) && \ + !strcmp((p1)->name, (p2)->name)) +static void __init of_selftest_property_copy(void) +{ +#ifdef CONFIG_OF_DYNAMIC + struct property p1 = { .name = "p1", .length = 0, .value = "" }; + struct property p2 = { .name = "p2", .length = 5, .value = "abcd" }; + struct property *new; + + new = __of_prop_dup(&p1, GFP_KERNEL); + selftest(new && propcmp(&p1, new), "empty property didn't copy correctly\n"); + kfree(new->value); + kfree(new->name); + kfree(new); + + new = __of_prop_dup(&p2, GFP_KERNEL); + selftest(new && propcmp(&p2, new), "non-empty property didn't copy correctly\n"); + kfree(new->value); + kfree(new->name); + kfree(new); +#endif +} + +static void __init of_selftest_changeset(void) +{ +#ifdef CONFIG_OF_DYNAMIC + struct property *ppadd, padd = { .name = "prop-add", .length = 0, .value = "" }; + struct property *ppupdate, pupdate = { .name = "prop-update", .length = 5, .value = "abcd" }; + struct property *ppremove; + struct device_node *n1, *n2, *n21, *nremove, *parent, *np; + struct of_changeset chgset; + + of_changeset_init(&chgset); + n1 = __of_node_dup(NULL, "/testcase-data/changeset/n1"); + selftest(n1, "testcase setup failure\n"); + n2 = __of_node_dup(NULL, "/testcase-data/changeset/n2"); + selftest(n2, "testcase setup failure\n"); + n21 = __of_node_dup(NULL, "%s/%s", "/testcase-data/changeset/n2", "n21"); + selftest(n21, "testcase setup failure %p\n", n21); + nremove = of_find_node_by_path("/testcase-data/changeset/node-remove"); + selftest(nremove, "testcase setup failure\n"); + ppadd = __of_prop_dup(&padd, GFP_KERNEL); + selftest(ppadd, "testcase setup failure\n"); + ppupdate = __of_prop_dup(&pupdate, GFP_KERNEL); + selftest(ppupdate, "testcase setup failure\n"); + parent = nremove->parent; + n1->parent = parent; + n2->parent = parent; + n21->parent = n2; + n2->child = n21; + ppremove = of_find_property(parent, "prop-remove", NULL); + selftest(ppremove, "failed to find removal prop"); + + of_changeset_init(&chgset); + selftest(!of_changeset_attach_node(&chgset, n1), "fail attach n1\n"); + selftest(!of_changeset_attach_node(&chgset, n2), "fail attach n2\n"); + selftest(!of_changeset_detach_node(&chgset, nremove), "fail remove node\n"); + selftest(!of_changeset_attach_node(&chgset, n21), "fail attach n21\n"); + selftest(!of_changeset_add_property(&chgset, parent, ppadd), "fail add prop\n"); + selftest(!of_changeset_update_property(&chgset, parent, ppupdate), "fail update prop\n"); + selftest(!of_changeset_remove_property(&chgset, parent, ppremove), "fail remove prop\n"); + mutex_lock(&of_mutex); + selftest(!of_changeset_apply(&chgset), "apply failed\n"); + mutex_unlock(&of_mutex); + + /* Make sure node names are constructed correctly */ + selftest((np = of_find_node_by_path("/testcase-data/changeset/n2/n21")), + "'%s' not added\n", n21->full_name); + if (np) + of_node_put(np); + + mutex_lock(&of_mutex); + selftest(!of_changeset_revert(&chgset), "revert failed\n"); + mutex_unlock(&of_mutex); + + of_changeset_destroy(&chgset); +#endif +} + +static void __init of_selftest_parse_interrupts(void) +{ + struct device_node *np; + struct of_phandle_args args; + int i, rc; + + np = of_find_node_by_path("/testcase-data/interrupts/interrupts0"); + if (!np) { + pr_err("missing testcase data\n"); + return; + } + + for (i = 0; i < 4; i++) { + bool passed = true; + args.args_count = 0; + rc = of_irq_parse_one(np, i, &args); + + passed &= !rc; + passed &= (args.args_count == 1); + passed &= (args.args[0] == (i + 1)); + + selftest(passed, "index %i - data error on node %s rc=%i\n", + i, args.np->full_name, rc); + } + of_node_put(np); + + np = of_find_node_by_path("/testcase-data/interrupts/interrupts1"); + if (!np) { + pr_err("missing testcase data\n"); + return; + } + + for (i = 0; i < 4; i++) { + bool passed = true; + args.args_count = 0; + rc = of_irq_parse_one(np, i, &args); + + /* Test the values from tests-phandle.dtsi */ + switch (i) { + case 0: + passed &= !rc; + passed &= (args.args_count == 1); + passed &= (args.args[0] == 9); + break; + case 1: + passed &= !rc; + passed &= (args.args_count == 3); + passed &= (args.args[0] == 10); + passed &= (args.args[1] == 11); + passed &= (args.args[2] == 12); + break; + case 2: + passed &= !rc; + passed &= (args.args_count == 2); + passed &= (args.args[0] == 13); + passed &= (args.args[1] == 14); + break; + case 3: + passed &= !rc; + passed &= (args.args_count == 2); + passed &= (args.args[0] == 15); + passed &= (args.args[1] == 16); + break; + default: + passed = false; + } + selftest(passed, "index %i - data error on node %s rc=%i\n", + i, args.np->full_name, rc); + } + of_node_put(np); +} + +static void __init of_selftest_parse_interrupts_extended(void) +{ + struct device_node *np; + struct of_phandle_args args; + int i, rc; + + np = of_find_node_by_path("/testcase-data/interrupts/interrupts-extended0"); + if (!np) { + pr_err("missing testcase data\n"); + return; + } + + for (i = 0; i < 7; i++) { + bool passed = true; + rc = of_irq_parse_one(np, i, &args); + + /* Test the values from tests-phandle.dtsi */ + switch (i) { + case 0: + passed &= !rc; + passed &= (args.args_count == 1); + passed &= (args.args[0] == 1); + break; + case 1: + passed &= !rc; + passed &= (args.args_count == 3); + passed &= (args.args[0] == 2); + passed &= (args.args[1] == 3); + passed &= (args.args[2] == 4); + break; + case 2: + passed &= !rc; + passed &= (args.args_count == 2); + passed &= (args.args[0] == 5); + passed &= (args.args[1] == 6); + break; + case 3: + passed &= !rc; + passed &= (args.args_count == 1); + passed &= (args.args[0] == 9); + break; + case 4: + passed &= !rc; + passed &= (args.args_count == 3); + passed &= (args.args[0] == 10); + passed &= (args.args[1] == 11); + passed &= (args.args[2] == 12); + break; + case 5: + passed &= !rc; + passed &= (args.args_count == 2); + passed &= (args.args[0] == 13); + passed &= (args.args[1] == 14); + break; + case 6: + passed &= !rc; + passed &= (args.args_count == 1); + passed &= (args.args[0] == 15); + break; + default: + passed = false; + } + + selftest(passed, "index %i - data error on node %s rc=%i\n", + i, args.np->full_name, rc); + } + of_node_put(np); +} + +static struct of_device_id match_node_table[] = { + { .data = "A", .name = "name0", }, /* Name alone is lowest priority */ + { .data = "B", .type = "type1", }, /* followed by type alone */ + + { .data = "Ca", .name = "name2", .type = "type1", }, /* followed by both together */ + { .data = "Cb", .name = "name2", }, /* Only match when type doesn't match */ + { .data = "Cc", .name = "name2", .type = "type2", }, + + { .data = "E", .compatible = "compat3" }, + { .data = "G", .compatible = "compat2", }, + { .data = "H", .compatible = "compat2", .name = "name5", }, + { .data = "I", .compatible = "compat2", .type = "type1", }, + { .data = "J", .compatible = "compat2", .type = "type1", .name = "name8", }, + { .data = "K", .compatible = "compat2", .name = "name9", }, + {} +}; + +static struct { + const char *path; + const char *data; +} match_node_tests[] = { + { .path = "/testcase-data/match-node/name0", .data = "A", }, + { .path = "/testcase-data/match-node/name1", .data = "B", }, + { .path = "/testcase-data/match-node/a/name2", .data = "Ca", }, + { .path = "/testcase-data/match-node/b/name2", .data = "Cb", }, + { .path = "/testcase-data/match-node/c/name2", .data = "Cc", }, + { .path = "/testcase-data/match-node/name3", .data = "E", }, + { .path = "/testcase-data/match-node/name4", .data = "G", }, + { .path = "/testcase-data/match-node/name5", .data = "H", }, + { .path = "/testcase-data/match-node/name6", .data = "G", }, + { .path = "/testcase-data/match-node/name7", .data = "I", }, + { .path = "/testcase-data/match-node/name8", .data = "J", }, + { .path = "/testcase-data/match-node/name9", .data = "K", }, +}; + +static void __init of_selftest_match_node(void) +{ + struct device_node *np; + const struct of_device_id *match; + int i; + + for (i = 0; i < ARRAY_SIZE(match_node_tests); i++) { + np = of_find_node_by_path(match_node_tests[i].path); + if (!np) { + selftest(0, "missing testcase node %s\n", + match_node_tests[i].path); + continue; + } + + match = of_match_node(match_node_table, np); + if (!match) { + selftest(0, "%s didn't match anything\n", + match_node_tests[i].path); + continue; + } + + if (strcmp(match->data, match_node_tests[i].data) != 0) { + selftest(0, "%s got wrong match. expected %s, got %s\n", + match_node_tests[i].path, match_node_tests[i].data, + (const char *)match->data); + continue; + } + selftest(1, "passed"); + } +} + +struct device test_bus = { + .init_name = "unittest-bus", +}; +static void __init of_selftest_platform_populate(void) +{ + int irq, rc; + struct device_node *np, *child, *grandchild; + struct platform_device *pdev; + struct of_device_id match[] = { + { .compatible = "test-device", }, + {} + }; + + np = of_find_node_by_path("/testcase-data"); + of_platform_populate(np, of_default_bus_match_table, NULL, NULL); + + /* Test that a missing irq domain returns -EPROBE_DEFER */ + np = of_find_node_by_path("/testcase-data/testcase-device1"); + pdev = of_find_device_by_node(np); + selftest(pdev, "device 1 creation failed\n"); + + irq = platform_get_irq(pdev, 0); + selftest(irq == -EPROBE_DEFER, "device deferred probe failed - %d\n", irq); + + /* Test that a parsing failure does not return -EPROBE_DEFER */ + np = of_find_node_by_path("/testcase-data/testcase-device2"); + pdev = of_find_device_by_node(np); + selftest(pdev, "device 2 creation failed\n"); + irq = platform_get_irq(pdev, 0); + selftest(irq < 0 && irq != -EPROBE_DEFER, "device parsing error failed - %d\n", irq); + + if (selftest(np = of_find_node_by_path("/testcase-data/platform-tests"), + "No testcase data in device tree\n")); + return; + + if (selftest(!(rc = device_register(&test_bus)), + "testbus registration failed; rc=%i\n", rc)); + return; + + for_each_child_of_node(np, child) { + of_platform_populate(child, match, NULL, &test_bus); + for_each_child_of_node(child, grandchild) + selftest(of_find_device_by_node(grandchild), + "Could not create device for node '%s'\n", + grandchild->name); + } + + of_platform_depopulate(&test_bus); + for_each_child_of_node(np, child) { + for_each_child_of_node(child, grandchild) + selftest(!of_find_device_by_node(grandchild), + "device didn't get destroyed '%s'\n", + grandchild->name); + } + + device_unregister(&test_bus); + of_node_put(np); +} + +/** + * update_node_properties - adds the properties + * of np into dup node (present in live tree) and + * updates parent of children of np to dup. + * + * @np: node already present in live tree + * @dup: node present in live tree to be updated + */ +static void update_node_properties(struct device_node *np, + struct device_node *dup) +{ + struct property *prop; + struct device_node *child; + + for_each_property_of_node(np, prop) + of_add_property(dup, prop); + + for_each_child_of_node(np, child) + child->parent = dup; +} + +/** + * attach_node_and_children - attaches nodes + * and its children to live tree + * + * @np: Node to attach to live tree + */ +static int attach_node_and_children(struct device_node *np) +{ + struct device_node *next, *root = np, *dup; + + /* skip root node */ + np = np->child; + /* storing a copy in temporary node */ + dup = np; + + while (dup) { + if (WARN_ON(last_node_index >= NO_OF_NODES)) + return -EINVAL; + nodes[last_node_index++] = dup; + dup = dup->sibling; + } + dup = NULL; + + while (np) { + next = np->allnext; + dup = of_find_node_by_path(np->full_name); + if (dup) + update_node_properties(np, dup); + else { + np->child = NULL; + if (np->parent == root) + np->parent = of_allnodes; + of_attach_node(np); + } + np = next; + } + + return 0; +} + +/** + * selftest_data_add - Reads, copies data from + * linked tree and attaches it to the live tree + */ +static int __init selftest_data_add(void) +{ + void *selftest_data; + struct device_node *selftest_data_node, *np; + extern uint8_t __dtb_testcases_begin[]; + extern uint8_t __dtb_testcases_end[]; + const int size = __dtb_testcases_end - __dtb_testcases_begin; + int rc; + + if (!size) { + pr_warn("%s: No testcase data to attach; not running tests\n", + __func__); + return -ENODATA; + } + + /* creating copy */ + selftest_data = kmemdup(__dtb_testcases_begin, size, GFP_KERNEL); + + if (!selftest_data) { + pr_warn("%s: Failed to allocate memory for selftest_data; " + "not running tests\n", __func__); + return -ENOMEM; + } + of_fdt_unflatten_tree(selftest_data, &selftest_data_node); + if (!selftest_data_node) { + pr_warn("%s: No tree to attach; not running tests\n", __func__); + return -ENODATA; + } + of_node_set_flag(selftest_data_node, OF_DETACHED); + rc = of_resolve_phandles(selftest_data_node); + if (rc) { + pr_err("%s: Failed to resolve phandles (rc=%i)\n", __func__, rc); + return -EINVAL; + } + + if (!of_allnodes) { + /* enabling flag for removing nodes */ + selftest_live_tree = true; + of_allnodes = selftest_data_node; + + for_each_of_allnodes(np) + __of_attach_node_sysfs(np); + of_aliases = of_find_node_by_path("/aliases"); + of_chosen = of_find_node_by_path("/chosen"); + return 0; + } + + /* attach the sub-tree to live tree */ + return attach_node_and_children(selftest_data_node); +} + +/** + * detach_node_and_children - detaches node + * and its children from live tree + * + * @np: Node to detach from live tree + */ +static void detach_node_and_children(struct device_node *np) +{ + while (np->child) + detach_node_and_children(np->child); + of_detach_node(np); +} + +/** + * selftest_data_remove - removes the selftest data + * nodes from the live tree + */ +static void selftest_data_remove(void) +{ + struct device_node *np; + struct property *prop; + + if (selftest_live_tree) { + of_node_put(of_aliases); + of_node_put(of_chosen); + of_aliases = NULL; + of_chosen = NULL; + for_each_child_of_node(of_allnodes, np) + detach_node_and_children(np); + __of_detach_node_sysfs(of_allnodes); + of_allnodes = NULL; + return; + } + + while (last_node_index >= 0) { + if (nodes[last_node_index]) { + np = of_find_node_by_path(nodes[last_node_index]->full_name); + if (strcmp(np->full_name, "/aliases") != 0) { + detach_node_and_children(np); + } else { + for_each_property_of_node(np, prop) { + if (strcmp(prop->name, "testcase-alias") == 0) + of_remove_property(np, prop); + } + } + } + last_node_index--; + } +} + +#ifdef CONFIG_OF_OVERLAY + +static int selftest_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + + if (np == NULL) { + dev_err(dev, "No OF data for device\n"); + return -EINVAL; + + } + + dev_dbg(dev, "%s for node @%s\n", __func__, np->full_name); + + of_platform_populate(np, NULL, NULL, &pdev->dev); + + return 0; +} + +static int selftest_remove(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + + dev_dbg(dev, "%s for node @%s\n", __func__, np->full_name); + return 0; +} + +static struct of_device_id selftest_match[] = { + { .compatible = "selftest", }, + {}, +}; +MODULE_DEVICE_TABLE(of, altera_jtaguart_match); + +static struct platform_driver selftest_driver = { + .probe = selftest_probe, + .remove = selftest_remove, + .driver = { + .name = "selftest", + .owner = THIS_MODULE, + .of_match_table = of_match_ptr(selftest_match), + }, +}; + +/* get the platform device instantiated at the path */ +static struct platform_device *of_path_to_platform_device(const char *path) +{ + struct device_node *np; + struct platform_device *pdev; + + np = of_find_node_by_path(path); + if (np == NULL) + return NULL; + + pdev = of_find_device_by_node(np); + of_node_put(np); + + return pdev; +} + +/* find out if a platform device exists at that path */ +static int of_path_platform_device_exists(const char *path) +{ + struct platform_device *pdev; + + pdev = of_path_to_platform_device(path); + platform_device_put(pdev); + return pdev != NULL; +} + +#if IS_ENABLED(CONFIG_I2C) + +/* get the i2c client device instantiated at the path */ +static struct i2c_client *of_path_to_i2c_client(const char *path) +{ + struct device_node *np; + struct i2c_client *client; + + np = of_find_node_by_path(path); + if (np == NULL) + return NULL; + + client = of_find_i2c_device_by_node(np); + of_node_put(np); + + return client; +} + +/* find out if a i2c client device exists at that path */ +static int of_path_i2c_client_exists(const char *path) +{ + struct i2c_client *client; + + client = of_path_to_i2c_client(path); + if (client) + put_device(&client->dev); + return client != NULL; +} +#else +static int of_path_i2c_client_exists(const char *path) +{ + return 0; +} +#endif + +enum overlay_type { + PDEV_OVERLAY, + I2C_OVERLAY +}; + +static int of_path_device_type_exists(const char *path, + enum overlay_type ovtype) +{ + switch (ovtype) { + case PDEV_OVERLAY: + return of_path_platform_device_exists(path); + case I2C_OVERLAY: + return of_path_i2c_client_exists(path); + } + return 0; +} + +static const char *selftest_path(int nr, enum overlay_type ovtype) +{ + const char *base; + static char buf[256]; + + switch (ovtype) { + case PDEV_OVERLAY: + base = "/testcase-data/overlay-node/test-bus"; + break; + case I2C_OVERLAY: + base = "/testcase-data/overlay-node/test-bus/i2c-test-bus"; + break; + default: + buf[0] = '\0'; + return buf; + } + snprintf(buf, sizeof(buf) - 1, "%s/test-selftest%d", base, nr); + buf[sizeof(buf) - 1] = '\0'; + return buf; +} + +static int of_selftest_device_exists(int selftest_nr, enum overlay_type ovtype) +{ + const char *path; + + path = selftest_path(selftest_nr, ovtype); + + switch (ovtype) { + case PDEV_OVERLAY: + return of_path_platform_device_exists(path); + case I2C_OVERLAY: + return of_path_i2c_client_exists(path); + } + return 0; +} + +static const char *overlay_path(int nr) +{ + static char buf[256]; + + snprintf(buf, sizeof(buf) - 1, + "/testcase-data/overlay%d", nr); + buf[sizeof(buf) - 1] = '\0'; + + return buf; +} + +static const char *bus_path = "/testcase-data/overlay-node/test-bus"; + +static int of_selftest_apply_overlay(int selftest_nr, int overlay_nr, + int *overlay_id) +{ + struct device_node *np = NULL; + int ret, id = -1; + + np = of_find_node_by_path(overlay_path(overlay_nr)); + if (np == NULL) { + selftest(0, "could not find overlay node @\"%s\"\n", + overlay_path(overlay_nr)); + ret = -EINVAL; + goto out; + } + + ret = of_overlay_create(np); + if (ret < 0) { + selftest(0, "could not create overlay from \"%s\"\n", + overlay_path(overlay_nr)); + goto out; + } + id = ret; + + ret = 0; + +out: + of_node_put(np); + + if (overlay_id) + *overlay_id = id; + + return ret; +} + +/* apply an overlay while checking before and after states */ +static int of_selftest_apply_overlay_check(int overlay_nr, int selftest_nr, + int before, int after, enum overlay_type ovtype) +{ + int ret; + + /* selftest device must not be in before state */ + if (of_selftest_device_exists(selftest_nr, ovtype) != before) { + selftest(0, "overlay @\"%s\" with device @\"%s\" %s\n", + overlay_path(overlay_nr), + selftest_path(selftest_nr, ovtype), + !before ? "enabled" : "disabled"); + return -EINVAL; + } + + ret = of_selftest_apply_overlay(overlay_nr, selftest_nr, NULL); + if (ret != 0) { + /* of_selftest_apply_overlay already called selftest() */ + return ret; + } + + /* selftest device must be to set to after state */ + if (of_selftest_device_exists(selftest_nr, ovtype) != after) { + selftest(0, "overlay @\"%s\" failed to create @\"%s\" %s\n", + overlay_path(overlay_nr), + selftest_path(selftest_nr, ovtype), + !after ? "enabled" : "disabled"); + return -EINVAL; + } + + return 0; +} + +/* apply an overlay and then revert it while checking before, after states */ +static int of_selftest_apply_revert_overlay_check(int overlay_nr, + int selftest_nr, int before, int after, + enum overlay_type ovtype) +{ + int ret, ov_id; + + /* selftest device must be in before state */ + if (of_selftest_device_exists(selftest_nr, ovtype) != before) { + selftest(0, "overlay @\"%s\" with device @\"%s\" %s\n", + overlay_path(overlay_nr), + selftest_path(selftest_nr, ovtype), + !before ? "enabled" : "disabled"); + return -EINVAL; + } + + /* apply the overlay */ + ret = of_selftest_apply_overlay(overlay_nr, selftest_nr, &ov_id); + if (ret != 0) { + /* of_selftest_apply_overlay already called selftest() */ + return ret; + } + + /* selftest device must be in after state */ + if (of_selftest_device_exists(selftest_nr, ovtype) != after) { + selftest(0, "overlay @\"%s\" failed to create @\"%s\" %s\n", + overlay_path(overlay_nr), + selftest_path(selftest_nr, ovtype), + !after ? "enabled" : "disabled"); + return -EINVAL; + } + + ret = of_overlay_destroy(ov_id); + if (ret != 0) { + selftest(0, "overlay @\"%s\" failed to be destroyed @\"%s\"\n", + overlay_path(overlay_nr), + selftest_path(selftest_nr, ovtype)); + return ret; + } + + /* selftest device must be again in before state */ + if (of_selftest_device_exists(selftest_nr, PDEV_OVERLAY) != before) { + selftest(0, "overlay @\"%s\" with device @\"%s\" %s\n", + overlay_path(overlay_nr), + selftest_path(selftest_nr, ovtype), + !before ? "enabled" : "disabled"); + return -EINVAL; + } + + return 0; +} + +/* test activation of device */ +static void of_selftest_overlay_0(void) +{ + int ret; + + /* device should enable */ + ret = of_selftest_apply_overlay_check(0, 0, 0, 1, PDEV_OVERLAY); + if (ret != 0) + return; + + selftest(1, "overlay test %d passed\n", 0); +} + +/* test deactivation of device */ +static void of_selftest_overlay_1(void) +{ + int ret; + + /* device should disable */ + ret = of_selftest_apply_overlay_check(1, 1, 1, 0, PDEV_OVERLAY); + if (ret != 0) + return; + + selftest(1, "overlay test %d passed\n", 1); +} + +/* test activation of device */ +static void of_selftest_overlay_2(void) +{ + int ret; + + /* device should enable */ + ret = of_selftest_apply_overlay_check(2, 2, 0, 1, PDEV_OVERLAY); + if (ret != 0) + return; + + selftest(1, "overlay test %d passed\n", 2); +} + +/* test deactivation of device */ +static void of_selftest_overlay_3(void) +{ + int ret; + + /* device should disable */ + ret = of_selftest_apply_overlay_check(3, 3, 1, 0, PDEV_OVERLAY); + if (ret != 0) + return; + + selftest(1, "overlay test %d passed\n", 3); +} + +/* test activation of a full device node */ +static void of_selftest_overlay_4(void) +{ + int ret; + + /* device should disable */ + ret = of_selftest_apply_overlay_check(4, 4, 0, 1, PDEV_OVERLAY); + if (ret != 0) + return; + + selftest(1, "overlay test %d passed\n", 4); +} + +/* test overlay apply/revert sequence */ +static void of_selftest_overlay_5(void) +{ + int ret; + + /* device should disable */ + ret = of_selftest_apply_revert_overlay_check(5, 5, 0, 1, PDEV_OVERLAY); + if (ret != 0) + return; + + selftest(1, "overlay test %d passed\n", 5); +} + +/* test overlay application in sequence */ +static void of_selftest_overlay_6(void) +{ + struct device_node *np; + int ret, i, ov_id[2]; + int overlay_nr = 6, selftest_nr = 6; + int before = 0, after = 1; + + /* selftest device must be in before state */ + for (i = 0; i < 2; i++) { + if (of_selftest_device_exists(selftest_nr + i, PDEV_OVERLAY) + != before) { + selftest(0, "overlay @\"%s\" with device @\"%s\" %s\n", + overlay_path(overlay_nr + i), + selftest_path(selftest_nr + i, + PDEV_OVERLAY), + !before ? "enabled" : "disabled"); + return; + } + } + + /* apply the overlays */ + for (i = 0; i < 2; i++) { + + np = of_find_node_by_path(overlay_path(overlay_nr + i)); + if (np == NULL) { + selftest(0, "could not find overlay node @\"%s\"\n", + overlay_path(overlay_nr + i)); + return; + } + + ret = of_overlay_create(np); + if (ret < 0) { + selftest(0, "could not create overlay from \"%s\"\n", + overlay_path(overlay_nr + i)); + return; + } + ov_id[i] = ret; + } + + for (i = 0; i < 2; i++) { + /* selftest device must be in after state */ + if (of_selftest_device_exists(selftest_nr + i, PDEV_OVERLAY) + != after) { + selftest(0, "overlay @\"%s\" failed @\"%s\" %s\n", + overlay_path(overlay_nr + i), + selftest_path(selftest_nr + i, + PDEV_OVERLAY), + !after ? "enabled" : "disabled"); + return; + } + } + + for (i = 1; i >= 0; i--) { + ret = of_overlay_destroy(ov_id[i]); + if (ret != 0) { + selftest(0, "overlay @\"%s\" failed destroy @\"%s\"\n", + overlay_path(overlay_nr + i), + selftest_path(selftest_nr + i, + PDEV_OVERLAY)); + return; + } + } + + for (i = 0; i < 2; i++) { + /* selftest device must be again in before state */ + if (of_selftest_device_exists(selftest_nr + i, PDEV_OVERLAY) + != before) { + selftest(0, "overlay @\"%s\" with device @\"%s\" %s\n", + overlay_path(overlay_nr + i), + selftest_path(selftest_nr + i, + PDEV_OVERLAY), + !before ? "enabled" : "disabled"); + return; + } + } + + selftest(1, "overlay test %d passed\n", 6); +} + +/* test overlay application in sequence */ +static void of_selftest_overlay_8(void) +{ + struct device_node *np; + int ret, i, ov_id[2]; + int overlay_nr = 8, selftest_nr = 8; + + /* we don't care about device state in this test */ + + /* apply the overlays */ + for (i = 0; i < 2; i++) { + + np = of_find_node_by_path(overlay_path(overlay_nr + i)); + if (np == NULL) { + selftest(0, "could not find overlay node @\"%s\"\n", + overlay_path(overlay_nr + i)); + return; + } + + ret = of_overlay_create(np); + if (ret < 0) { + selftest(0, "could not create overlay from \"%s\"\n", + overlay_path(overlay_nr + i)); + return; + } + ov_id[i] = ret; + } + + /* now try to remove first overlay (it should fail) */ + ret = of_overlay_destroy(ov_id[0]); + if (ret == 0) { + selftest(0, "overlay @\"%s\" was destroyed @\"%s\"\n", + overlay_path(overlay_nr + 0), + selftest_path(selftest_nr, + PDEV_OVERLAY)); + return; + } + + /* removing them in order should work */ + for (i = 1; i >= 0; i--) { + ret = of_overlay_destroy(ov_id[i]); + if (ret != 0) { + selftest(0, "overlay @\"%s\" not destroyed @\"%s\"\n", + overlay_path(overlay_nr + i), + selftest_path(selftest_nr, + PDEV_OVERLAY)); + return; + } + } + + selftest(1, "overlay test %d passed\n", 8); +} + +/* test insertion of a bus with parent devices */ +static void of_selftest_overlay_10(void) +{ + int ret; + char *child_path; + + /* device should disable */ + ret = of_selftest_apply_overlay_check(10, 10, 0, 1, PDEV_OVERLAY); + if (selftest(ret == 0, + "overlay test %d failed; overlay application\n", 10)) + return; + + child_path = kasprintf(GFP_KERNEL, "%s/test-selftest101", + selftest_path(10, PDEV_OVERLAY)); + if (selftest(child_path, "overlay test %d failed; kasprintf\n", 10)) + return; + + ret = of_path_device_type_exists(child_path, PDEV_OVERLAY); + kfree(child_path); + if (selftest(ret, "overlay test %d failed; no child device\n", 10)) + return; +} + +/* test insertion of a bus with parent devices (and revert) */ +static void of_selftest_overlay_11(void) +{ + int ret; + + /* device should disable */ + ret = of_selftest_apply_revert_overlay_check(11, 11, 0, 1, + PDEV_OVERLAY); + if (selftest(ret == 0, + "overlay test %d failed; overlay application\n", 11)) + return; +} + +#if IS_ENABLED(CONFIG_I2C) && IS_ENABLED(CONFIG_OF_OVERLAY) + +struct selftest_i2c_bus_data { + struct platform_device *pdev; + struct i2c_adapter adap; +}; + +static int selftest_i2c_master_xfer(struct i2c_adapter *adap, + struct i2c_msg *msgs, int num) +{ + struct selftest_i2c_bus_data *std = i2c_get_adapdata(adap); + + (void)std; + + return num; +} + +static u32 selftest_i2c_functionality(struct i2c_adapter *adap) +{ + return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL; +} + +static const struct i2c_algorithm selftest_i2c_algo = { + .master_xfer = selftest_i2c_master_xfer, + .functionality = selftest_i2c_functionality, +}; + +static int selftest_i2c_bus_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + struct selftest_i2c_bus_data *std; + struct i2c_adapter *adap; + int ret; + + if (np == NULL) { + dev_err(dev, "No OF data for device\n"); + return -EINVAL; + + } + + dev_dbg(dev, "%s for node @%s\n", __func__, np->full_name); + + std = devm_kzalloc(dev, sizeof(*std), GFP_KERNEL); + if (!std) { + dev_err(dev, "Failed to allocate selftest i2c data\n"); + return -ENOMEM; + } + + /* link them together */ + std->pdev = pdev; + platform_set_drvdata(pdev, std); + + adap = &std->adap; + i2c_set_adapdata(adap, std); + adap->nr = -1; + strlcpy(adap->name, pdev->name, sizeof(adap->name)); + adap->class = I2C_CLASS_DEPRECATED; + adap->algo = &selftest_i2c_algo; + adap->dev.parent = dev; + adap->dev.of_node = dev->of_node; + adap->timeout = 5 * HZ; + adap->retries = 3; + + ret = i2c_add_numbered_adapter(adap); + if (ret != 0) { + dev_err(dev, "Failed to add I2C adapter\n"); + return ret; + } + + return 0; +} + +static int selftest_i2c_bus_remove(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + struct selftest_i2c_bus_data *std = platform_get_drvdata(pdev); + + dev_dbg(dev, "%s for node @%s\n", __func__, np->full_name); + i2c_del_adapter(&std->adap); + + return 0; +} + +static struct of_device_id selftest_i2c_bus_match[] = { + { .compatible = "selftest-i2c-bus", }, + {}, +}; + +static struct platform_driver selftest_i2c_bus_driver = { + .probe = selftest_i2c_bus_probe, + .remove = selftest_i2c_bus_remove, + .driver = { + .name = "selftest-i2c-bus", + .of_match_table = of_match_ptr(selftest_i2c_bus_match), + }, +}; + +static int selftest_i2c_dev_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct device *dev = &client->dev; + struct device_node *np = client->dev.of_node; + + if (!np) { + dev_err(dev, "No OF node\n"); + return -EINVAL; + } + + dev_dbg(dev, "%s for node @%s\n", __func__, np->full_name); + + return 0; +}; + +static int selftest_i2c_dev_remove(struct i2c_client *client) +{ + struct device *dev = &client->dev; + struct device_node *np = client->dev.of_node; + + dev_dbg(dev, "%s for node @%s\n", __func__, np->full_name); + return 0; +} + +static const struct i2c_device_id selftest_i2c_dev_id[] = { + { .name = "selftest-i2c-dev" }, + { } +}; + +static struct i2c_driver selftest_i2c_dev_driver = { + .driver = { + .name = "selftest-i2c-dev", + .owner = THIS_MODULE, + }, + .probe = selftest_i2c_dev_probe, + .remove = selftest_i2c_dev_remove, + .id_table = selftest_i2c_dev_id, +}; + +#if IS_ENABLED(CONFIG_I2C_MUX) + +struct selftest_i2c_mux_data { + int nchans; + struct i2c_adapter *adap[]; +}; + +static int selftest_i2c_mux_select_chan(struct i2c_adapter *adap, + void *client, u32 chan) +{ + return 0; +} + +static int selftest_i2c_mux_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + int ret, i, nchans, size; + struct device *dev = &client->dev; + struct i2c_adapter *adap = to_i2c_adapter(dev->parent); + struct device_node *np = client->dev.of_node, *child; + struct selftest_i2c_mux_data *stm; + u32 reg, max_reg; + + dev_dbg(dev, "%s for node @%s\n", __func__, np->full_name); + + if (!np) { + dev_err(dev, "No OF node\n"); + return -EINVAL; + } + + max_reg = (u32)-1; + for_each_child_of_node(np, child) { + ret = of_property_read_u32(child, "reg", ®); + if (ret) + continue; + if (max_reg == (u32)-1 || reg > max_reg) + max_reg = reg; + } + nchans = max_reg == (u32)-1 ? 0 : max_reg + 1; + if (nchans == 0) { + dev_err(dev, "No channels\n"); + return -EINVAL; + } + + size = offsetof(struct selftest_i2c_mux_data, adap[nchans]); + stm = devm_kzalloc(dev, size, GFP_KERNEL); + if (!stm) { + dev_err(dev, "Out of memory\n"); + return -ENOMEM; + } + stm->nchans = nchans; + for (i = 0; i < nchans; i++) { + stm->adap[i] = i2c_add_mux_adapter(adap, dev, client, + 0, i, 0, selftest_i2c_mux_select_chan, NULL); + if (!stm->adap[i]) { + dev_err(dev, "Failed to register mux #%d\n", i); + for (i--; i >= 0; i--) + i2c_del_mux_adapter(stm->adap[i]); + return -ENODEV; + } + } + + i2c_set_clientdata(client, stm); + + return 0; +}; + +static int selftest_i2c_mux_remove(struct i2c_client *client) +{ + struct device *dev = &client->dev; + struct device_node *np = client->dev.of_node; + struct selftest_i2c_mux_data *stm = i2c_get_clientdata(client); + int i; + + dev_dbg(dev, "%s for node @%s\n", __func__, np->full_name); + for (i = stm->nchans - 1; i >= 0; i--) + i2c_del_mux_adapter(stm->adap[i]); + return 0; +} + +static const struct i2c_device_id selftest_i2c_mux_id[] = { + { .name = "selftest-i2c-mux" }, + { } +}; + +static struct i2c_driver selftest_i2c_mux_driver = { + .driver = { + .name = "selftest-i2c-mux", + .owner = THIS_MODULE, + }, + .probe = selftest_i2c_mux_probe, + .remove = selftest_i2c_mux_remove, + .id_table = selftest_i2c_mux_id, +}; + +#endif + +static int of_selftest_overlay_i2c_init(void) +{ + int ret; + + ret = i2c_add_driver(&selftest_i2c_dev_driver); + if (selftest(ret == 0, + "could not register selftest i2c device driver\n")) + return ret; + + ret = platform_driver_register(&selftest_i2c_bus_driver); + if (selftest(ret == 0, + "could not register selftest i2c bus driver\n")) + return ret; + +#if IS_ENABLED(CONFIG_I2C_MUX) + ret = i2c_add_driver(&selftest_i2c_mux_driver); + if (selftest(ret == 0, + "could not register selftest i2c mux driver\n")) + return ret; +#endif + + return 0; +} + +static void of_selftest_overlay_i2c_cleanup(void) +{ +#if IS_ENABLED(CONFIG_I2C_MUX) + i2c_del_driver(&selftest_i2c_mux_driver); +#endif + platform_driver_unregister(&selftest_i2c_bus_driver); + i2c_del_driver(&selftest_i2c_dev_driver); +} + +static void of_selftest_overlay_i2c_12(void) +{ + int ret; + + /* device should enable */ + ret = of_selftest_apply_overlay_check(12, 12, 0, 1, I2C_OVERLAY); + if (ret != 0) + return; + + selftest(1, "overlay test %d passed\n", 12); +} + +/* test deactivation of device */ +static void of_selftest_overlay_i2c_13(void) +{ + int ret; + + /* device should disable */ + ret = of_selftest_apply_overlay_check(13, 13, 1, 0, I2C_OVERLAY); + if (ret != 0) + return; + + selftest(1, "overlay test %d passed\n", 13); +} + +/* just check for i2c mux existence */ +static void of_selftest_overlay_i2c_14(void) +{ +} + +static void of_selftest_overlay_i2c_15(void) +{ + int ret; + + /* device should enable */ + ret = of_selftest_apply_overlay_check(16, 15, 0, 1, I2C_OVERLAY); + if (ret != 0) + return; + + selftest(1, "overlay test %d passed\n", 15); +} + +#else + +static inline void of_selftest_overlay_i2c_14(void) { } +static inline void of_selftest_overlay_i2c_15(void) { } + +#endif + +static void __init of_selftest_overlay(void) +{ + struct device_node *bus_np = NULL; + int ret; + + ret = platform_driver_register(&selftest_driver); + if (ret != 0) { + selftest(0, "could not register selftest driver\n"); + goto out; + } + + bus_np = of_find_node_by_path(bus_path); + if (bus_np == NULL) { + selftest(0, "could not find bus_path \"%s\"\n", bus_path); + goto out; + } + + ret = of_platform_populate(bus_np, of_default_bus_match_table, + NULL, NULL); + if (ret != 0) { + selftest(0, "could not populate bus @ \"%s\"\n", bus_path); + goto out; + } + + if (!of_selftest_device_exists(100, PDEV_OVERLAY)) { + selftest(0, "could not find selftest0 @ \"%s\"\n", + selftest_path(100, PDEV_OVERLAY)); + goto out; + } + + if (of_selftest_device_exists(101, PDEV_OVERLAY)) { + selftest(0, "selftest1 @ \"%s\" should not exist\n", + selftest_path(101, PDEV_OVERLAY)); + goto out; + } + + selftest(1, "basic infrastructure of overlays passed"); + + /* tests in sequence */ + of_selftest_overlay_0(); + of_selftest_overlay_1(); + of_selftest_overlay_2(); + of_selftest_overlay_3(); + of_selftest_overlay_4(); + of_selftest_overlay_5(); + of_selftest_overlay_6(); + of_selftest_overlay_8(); + + of_selftest_overlay_10(); + of_selftest_overlay_11(); + +#if IS_ENABLED(CONFIG_I2C) + if (selftest(of_selftest_overlay_i2c_init() == 0, "i2c init failed\n")) + goto out; + + of_selftest_overlay_i2c_12(); + of_selftest_overlay_i2c_13(); + of_selftest_overlay_i2c_14(); + of_selftest_overlay_i2c_15(); + + of_selftest_overlay_i2c_cleanup(); +#endif + +out: + of_node_put(bus_np); +} + +#else +static inline void __init of_selftest_overlay(void) { } +#endif + +static int __init of_selftest(void) +{ + struct device_node *np; + int res; + + /* adding data for selftest */ + res = selftest_data_add(); + if (res) + return res; + + np = of_find_node_by_path("/testcase-data/phandle-tests/consumer-a"); + if (!np) { + pr_info("No testcase data in device tree; not running tests\n"); + return 0; + } + of_node_put(np); + + pr_info("start of selftest - you will see error messages\n"); + of_selftest_check_tree_linkage(); + of_selftest_check_phandles(); + of_selftest_find_node_by_name(); + of_selftest_dynamic(); + of_selftest_parse_phandle_with_args(); + of_selftest_property_match_string(); + of_selftest_property_copy(); + of_selftest_changeset(); + of_selftest_parse_interrupts(); + of_selftest_parse_interrupts_extended(); + of_selftest_match_node(); + of_selftest_platform_populate(); + of_selftest_overlay(); + + /* removing selftest data from live tree */ + selftest_data_remove(); + + /* Double check linkage after removing testcase data */ + of_selftest_check_tree_linkage(); + + pr_info("end of selftest - %i passed, %i failed\n", + selftest_results.passed, selftest_results.failed); + + return 0; +} +late_initcall(of_selftest); diff --git a/drivers/pci/host/pci-mvebu.c b/drivers/pci/host/pci-mvebu.c index 483d9ad89705..97736674ddcd 100644 --- a/drivers/pci/host/pci-mvebu.c +++ b/drivers/pci/host/pci-mvebu.c @@ -855,7 +855,7 @@ static int mvebu_get_tgt_attr(struct device_node *np, int devfn, rangesz = pna + na + ns; nranges = rlen / sizeof(__be32) / rangesz; - for (i = 0; i < nranges; i++) { + for (i = 0; i < nranges; i++, range += rangesz) { u32 flags = of_read_number(range, 1); u32 slot = of_read_number(range + 1, 1); u64 cpuaddr = of_read_number(range + na, pna); @@ -865,14 +865,14 @@ static int mvebu_get_tgt_attr(struct device_node *np, int devfn, rtype = IORESOURCE_IO; else if (DT_FLAGS_TO_TYPE(flags) == DT_TYPE_MEM32) rtype = IORESOURCE_MEM; + else + continue; if (slot == PCI_SLOT(devfn) && type == rtype) { *tgt = DT_CPUADDR_TO_TARGET(cpuaddr); *attr = DT_CPUADDR_TO_ATTR(cpuaddr); return 0; } - - range += rangesz; } return -ENOENT; diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index fb02fc2fb034..ced17f2ac782 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -599,6 +599,20 @@ error_attrs: return ret; } +static int msi_verify_entries(struct pci_dev *dev) +{ + struct msi_desc *entry; + + list_for_each_entry(entry, &dev->msi_list, list) { + if (!dev->no_64bit_msi || !entry->msg.address_hi) + continue; + dev_err(&dev->dev, "Device has broken 64-bit MSI but arch" + " tried to assign one above 4G\n"); + return -EIO; + } + return 0; +} + /** * msi_capability_init - configure device's MSI capability structure * @dev: pointer to the pci_dev data structure of MSI device function @@ -652,6 +666,13 @@ static int msi_capability_init(struct pci_dev *dev, int nvec) return ret; } + ret = msi_verify_entries(dev); + if (ret) { + msi_mask_irq(entry, mask, ~mask); + free_msi_irqs(dev); + return ret; + } + ret = populate_msi_sysfs(dev); if (ret) { msi_mask_irq(entry, mask, ~mask); @@ -767,6 +788,11 @@ static int msix_capability_init(struct pci_dev *dev, if (ret) goto out_avail; + /* Check if all MSI entries honor device restrictions */ + ret = msi_verify_entries(dev); + if (ret) + goto out_free; + /* * Some devices require MSI-X to be enabled before we can touch the * MSI-X registers. We need to mask all the vectors to prevent diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 25f0bc659164..7f4155116cc9 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -1324,7 +1324,7 @@ static int pci_uevent(struct device *dev, struct kobj_uevent_env *env) if (add_uevent_var(env, "PCI_SLOT_NAME=%s", pci_name(pdev))) return -ENOMEM; - if (add_uevent_var(env, "MODALIAS=pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02x", + if (add_uevent_var(env, "MODALIAS=pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02X", pdev->vendor, pdev->device, pdev->subsystem_vendor, pdev->subsystem_device, (u8)(pdev->class >> 16), (u8)(pdev->class >> 8), diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 276ef9c18802..a943c6c0f206 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -178,7 +178,7 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, { struct pci_dev *pci_dev = to_pci_dev(dev); - return sprintf(buf, "pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02x\n", + return sprintf(buf, "pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02X\n", pci_dev->vendor, pci_dev->device, pci_dev->subsystem_vendor, pci_dev->subsystem_device, (u8)(pci_dev->class >> 16), (u8)(pci_dev->class >> 8), @@ -186,9 +186,9 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(modalias); -static ssize_t enabled_store(struct device *dev, - struct device_attribute *attr, const char *buf, - size_t count) +static ssize_t enable_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) { struct pci_dev *pdev = to_pci_dev(dev); unsigned long val; @@ -212,15 +212,15 @@ static ssize_t enabled_store(struct device *dev, return result < 0 ? result : count; } -static ssize_t enabled_show(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t enable_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct pci_dev *pdev; pdev = to_pci_dev (dev); return sprintf (buf, "%u\n", atomic_read(&pdev->enable_cnt)); } -static DEVICE_ATTR_RW(enabled); +static DEVICE_ATTR_RW(enable); #ifdef CONFIG_NUMA static ssize_t @@ -526,7 +526,7 @@ static struct attribute *pci_dev_attrs[] = { #endif &dev_attr_dma_mask_bits.attr, &dev_attr_consistent_dma_mask_bits.attr, - &dev_attr_enabled.attr, + &dev_attr_enable.attr, &dev_attr_broken_parity_status.attr, &dev_attr_msi_bus.attr, #if defined(CONFIG_PM_RUNTIME) && defined(CONFIG_ACPI) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index dae70d216762..78c65d327e33 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3187,7 +3187,8 @@ static int pci_parent_bus_reset(struct pci_dev *dev, int probe) { struct pci_dev *pdev; - if (pci_is_root_bus(dev->bus) || dev->subordinate || !dev->bus->self) + if (pci_is_root_bus(dev->bus) || dev->subordinate || + !dev->bus->self || dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET) return -ENOTTY; list_for_each_entry(pdev, &dev->bus->devices, bus_list) @@ -3221,7 +3222,8 @@ static int pci_dev_reset_slot_function(struct pci_dev *dev, int probe) { struct pci_dev *pdev; - if (dev->subordinate || !dev->slot) + if (dev->subordinate || !dev->slot || + dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET) return -ENOTTY; list_for_each_entry(pdev, &dev->bus->devices, bus_list) @@ -3452,6 +3454,20 @@ int pci_try_reset_function(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(pci_try_reset_function); +/* Do any devices on or below this bus prevent a bus reset? */ +static bool pci_bus_resetable(struct pci_bus *bus) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &bus->devices, bus_list) { + if (dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET || + (dev->subordinate && !pci_bus_resetable(dev->subordinate))) + return false; + } + + return true; +} + /* Lock devices from the top of the tree down */ static void pci_bus_lock(struct pci_bus *bus) { @@ -3502,6 +3518,22 @@ unlock: return 0; } +/* Do any devices on or below this slot prevent a bus reset? */ +static bool pci_slot_resetable(struct pci_slot *slot) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &slot->bus->devices, bus_list) { + if (!dev->slot || dev->slot != slot) + continue; + if (dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET || + (dev->subordinate && !pci_bus_resetable(dev->subordinate))) + return false; + } + + return true; +} + /* Lock devices from the top of the tree down */ static void pci_slot_lock(struct pci_slot *slot) { @@ -3623,7 +3655,7 @@ static int pci_slot_reset(struct pci_slot *slot, int probe) { int rc; - if (!slot) + if (!slot || !pci_slot_resetable(slot)) return -ENOTTY; if (!probe) @@ -3715,7 +3747,7 @@ EXPORT_SYMBOL_GPL(pci_try_reset_slot); static int pci_bus_reset(struct pci_bus *bus, int probe) { - if (!bus->self) + if (!bus->self || !pci_bus_resetable(bus)) return -ENOTTY; if (probe) diff --git a/drivers/pci/pcie/aer/aerdrv_errprint.c b/drivers/pci/pcie/aer/aerdrv_errprint.c index 34ff7026440c..5d3b45640181 100644 --- a/drivers/pci/pcie/aer/aerdrv_errprint.c +++ b/drivers/pci/pcie/aer/aerdrv_errprint.c @@ -127,16 +127,8 @@ static const char *aer_agent_string[] = { static void __print_tlp_header(struct pci_dev *dev, struct aer_header_log_regs *t) { - unsigned char *tlp = (unsigned char *)&t; - - dev_err(&dev->dev, " TLP Header:" - " %02x%02x%02x%02x %02x%02x%02x%02x" - " %02x%02x%02x%02x %02x%02x%02x%02x\n", - *(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp, - *(tlp + 7), *(tlp + 6), *(tlp + 5), *(tlp + 4), - *(tlp + 11), *(tlp + 10), *(tlp + 9), - *(tlp + 8), *(tlp + 15), *(tlp + 14), - *(tlp + 13), *(tlp + 12)); + dev_err(&dev->dev, " TLP Header: %08x %08x %08x %08x\n", + t->dw0, t->dw1, t->dw2, t->dw3); } static void __aer_print_error(struct pci_dev *dev, diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 6e34498ec9f0..5b428db6a150 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -214,14 +214,17 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, res->flags |= IORESOURCE_SIZEALIGN; if (res->flags & IORESOURCE_IO) { l &= PCI_BASE_ADDRESS_IO_MASK; + sz &= PCI_BASE_ADDRESS_IO_MASK; mask = PCI_BASE_ADDRESS_IO_MASK & (u32) IO_SPACE_LIMIT; } else { l &= PCI_BASE_ADDRESS_MEM_MASK; + sz &= PCI_BASE_ADDRESS_MEM_MASK; mask = (u32)PCI_BASE_ADDRESS_MEM_MASK; } } else { res->flags |= (l & IORESOURCE_ROM_ENABLE); l &= PCI_ROM_ADDRESS_MASK; + sz &= PCI_ROM_ADDRESS_MASK; mask = (u32)PCI_ROM_ADDRESS_MASK; } @@ -395,15 +398,16 @@ static void pci_read_bridge_mmio_pref(struct pci_bus *child) { struct pci_dev *dev = child->self; u16 mem_base_lo, mem_limit_lo; - unsigned long base, limit; + u64 base64, limit64; + dma_addr_t base, limit; struct pci_bus_region region; struct resource *res; res = child->resource[2]; pci_read_config_word(dev, PCI_PREF_MEMORY_BASE, &mem_base_lo); pci_read_config_word(dev, PCI_PREF_MEMORY_LIMIT, &mem_limit_lo); - base = ((unsigned long) mem_base_lo & PCI_PREF_RANGE_MASK) << 16; - limit = ((unsigned long) mem_limit_lo & PCI_PREF_RANGE_MASK) << 16; + base64 = (mem_base_lo & PCI_PREF_RANGE_MASK) << 16; + limit64 = (mem_limit_lo & PCI_PREF_RANGE_MASK) << 16; if ((mem_base_lo & PCI_PREF_RANGE_TYPE_MASK) == PCI_PREF_RANGE_TYPE_64) { u32 mem_base_hi, mem_limit_hi; @@ -417,18 +421,20 @@ static void pci_read_bridge_mmio_pref(struct pci_bus *child) * this, just assume they are not being used. */ if (mem_base_hi <= mem_limit_hi) { -#if BITS_PER_LONG == 64 - base |= ((unsigned long) mem_base_hi) << 32; - limit |= ((unsigned long) mem_limit_hi) << 32; -#else - if (mem_base_hi || mem_limit_hi) { - dev_err(&dev->dev, "can't handle 64-bit " - "address space for bridge\n"); - return; - } -#endif + base64 |= (u64) mem_base_hi << 32; + limit64 |= (u64) mem_limit_hi << 32; } } + + base = (dma_addr_t) base64; + limit = (dma_addr_t) limit64; + + if (base != base64) { + dev_err(&dev->dev, "can't handle bridge window above 4GB (bus address %#010llx)\n", + (unsigned long long) base64); + return; + } + if (base <= limit) { res->flags = (mem_base_lo & PCI_PREF_RANGE_TYPE_MASK) | IORESOURCE_MEM | IORESOURCE_PREFETCH; diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 813f437f3ee8..27abeb40dfab 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -24,6 +24,7 @@ #include <linux/ioport.h> #include <linux/sched.h> #include <linux/ktime.h> +#include <linux/mm.h> #include <asm/dma.h> /* isa_dma_bridge_buggy */ #include "pci.h" @@ -287,6 +288,25 @@ static void quirk_citrine(struct pci_dev *dev) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CITRINE, quirk_citrine); +/* On IBM Crocodile ipr SAS adapters, expand BAR to system page size */ +static void quirk_extend_bar_to_page(struct pci_dev *dev) +{ + int i; + + for (i = 0; i < PCI_STD_RESOURCE_END; i++) { + struct resource *r = &dev->resource[i]; + + if (r->flags & IORESOURCE_MEM && resource_size(r) < PAGE_SIZE) { + r->end = PAGE_SIZE - 1; + r->start = 0; + r->flags |= IORESOURCE_UNSET; + dev_info(&dev->dev, "expanded BAR %d to page size: %pR\n", + i, r); + } + } +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM, 0x034a, quirk_extend_bar_to_page); + /* * S3 868 and 968 chips report region size equal to 32M, but they decode 64M. * If it's needed, re-allocate the region. @@ -2988,6 +3008,20 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_CHELSIO, 0x0030, DECLARE_PCI_FIXUP_HEADER(0x1814, 0x0601, /* Ralink RT2800 802.11n PCI */ quirk_broken_intx_masking); +static void quirk_no_bus_reset(struct pci_dev *dev) +{ + dev->dev_flags |= PCI_DEV_FLAGS_NO_BUS_RESET; +} + +/* + * 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. + * http://www.spinics.net/lists/linux-pci/msg34797.html + */ +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATHEROS, 0x0030, quirk_no_bus_reset); + static void pci_do_fixups(struct pci_dev *dev, struct pci_fixup *f, struct pci_fixup *end) { diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c index 5d595724e5f4..5510c88b5044 100644 --- a/drivers/pci/rom.c +++ b/drivers/pci/rom.c @@ -69,6 +69,7 @@ size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size) { void __iomem *image; int last_image; + unsigned length; image = rom; do { @@ -91,9 +92,9 @@ size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size) if (readb(pds + 3) != 'R') break; last_image = readb(pds + 21) & 0x80; - /* this length is reliable */ - image += readw(pds + 16) * 512; - } while (!last_image); + length = readw(pds + 16); + image += length * 512; + } while (length && !last_image); /* never return a size larger than the PCI resource window */ /* there are known ROMs that get the size wrong */ diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index 34d56f7864d6..86592dd24da5 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -50,7 +50,9 @@ static void devm_phy_consume(struct device *dev, void *res) static int devm_phy_match(struct device *dev, void *res, void *match_data) { - return res == match_data; + struct phy **phy = res; + + return *phy == match_data; } static struct phy *phy_lookup(struct device *device, const char *port) diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c index c3ace1db8136..aaac3594f83b 100644 --- a/drivers/phy/phy-twl4030-usb.c +++ b/drivers/phy/phy-twl4030-usb.c @@ -34,6 +34,7 @@ #include <linux/delay.h> #include <linux/usb/otg.h> #include <linux/phy/phy.h> +#include <linux/pm_runtime.h> #include <linux/usb/musb-omap.h> #include <linux/usb/ulpi.h> #include <linux/i2c/twl.h> @@ -422,37 +423,55 @@ static void twl4030_phy_power(struct twl4030_usb *twl, int on) } } -static int twl4030_phy_power_off(struct phy *phy) +static int twl4030_usb_runtime_suspend(struct device *dev) { - struct twl4030_usb *twl = phy_get_drvdata(phy); + struct twl4030_usb *twl = dev_get_drvdata(dev); + dev_dbg(twl->dev, "%s\n", __func__); if (twl->asleep) return 0; twl4030_phy_power(twl, 0); twl->asleep = 1; - dev_dbg(twl->dev, "%s\n", __func__); + return 0; } -static void __twl4030_phy_power_on(struct twl4030_usb *twl) +static int twl4030_usb_runtime_resume(struct device *dev) { + struct twl4030_usb *twl = dev_get_drvdata(dev); + + dev_dbg(twl->dev, "%s\n", __func__); + if (!twl->asleep) + return 0; + twl4030_phy_power(twl, 1); - twl4030_i2c_access(twl, 1); - twl4030_usb_set_mode(twl, twl->usb_mode); - if (twl->usb_mode == T2_USB_MODE_ULPI) - twl4030_i2c_access(twl, 0); + twl->asleep = 0; + + return 0; +} + +static int twl4030_phy_power_off(struct phy *phy) +{ + struct twl4030_usb *twl = phy_get_drvdata(phy); + + dev_dbg(twl->dev, "%s\n", __func__); + pm_runtime_mark_last_busy(twl->dev); + pm_runtime_put_autosuspend(twl->dev); + + return 0; } static int twl4030_phy_power_on(struct phy *phy) { struct twl4030_usb *twl = phy_get_drvdata(phy); - if (!twl->asleep) - return 0; - __twl4030_phy_power_on(twl); - twl->asleep = 0; dev_dbg(twl->dev, "%s\n", __func__); + pm_runtime_get_sync(twl->dev); + twl4030_i2c_access(twl, 1); + twl4030_usb_set_mode(twl, twl->usb_mode); + if (twl->usb_mode == T2_USB_MODE_ULPI) + twl4030_i2c_access(twl, 0); /* * XXX When VBUS gets driven after musb goes to A mode, @@ -558,9 +577,27 @@ static irqreturn_t twl4030_usb_irq(int irq, void *_twl) * USB_LINK_VBUS state. musb_hdrc won't care until it * starts to handle softconnect right. */ + if ((status == OMAP_MUSB_VBUS_VALID) || + (status == OMAP_MUSB_ID_GROUND)) { + if (twl->asleep) + pm_runtime_get_sync(twl->dev); + } else { + if (!twl->asleep) { + pm_runtime_mark_last_busy(twl->dev); + pm_runtime_put_autosuspend(twl->dev); + } + } omap_musb_mailbox(status); } - sysfs_notify(&twl->dev->kobj, NULL, "vbus"); + + /* don't schedule during sleep - irq works right then */ + if (status == OMAP_MUSB_ID_GROUND && !twl->asleep) { + cancel_delayed_work(&twl->id_workaround_work); + schedule_delayed_work(&twl->id_workaround_work, HZ); + } + + if (irq) + sysfs_notify(&twl->dev->kobj, NULL, "vbus"); return IRQ_HANDLED; } @@ -569,29 +606,8 @@ static void twl4030_id_workaround_work(struct work_struct *work) { struct twl4030_usb *twl = container_of(work, struct twl4030_usb, id_workaround_work.work); - enum omap_musb_vbus_id_status status; - bool status_changed = false; - - status = twl4030_usb_linkstat(twl); - - spin_lock_irq(&twl->lock); - if (status >= 0 && status != twl->linkstat) { - twl->linkstat = status; - status_changed = true; - } - spin_unlock_irq(&twl->lock); - - if (status_changed) { - dev_dbg(twl->dev, "handle missing status change to %d\n", - status); - omap_musb_mailbox(status); - } - /* don't schedule during sleep - irq works right then */ - if (status == OMAP_MUSB_ID_GROUND && !twl->asleep) { - cancel_delayed_work(&twl->id_workaround_work); - schedule_delayed_work(&twl->id_workaround_work, HZ); - } + twl4030_usb_irq(0, twl); } static int twl4030_phy_init(struct phy *phy) @@ -599,22 +615,17 @@ static int twl4030_phy_init(struct phy *phy) struct twl4030_usb *twl = phy_get_drvdata(phy); enum omap_musb_vbus_id_status status; - /* - * Start in sleep state, we'll get called through set_suspend() - * callback when musb is runtime resumed and it's time to start. - */ - __twl4030_phy_power(twl, 0); - twl->asleep = 1; - + pm_runtime_get_sync(twl->dev); status = twl4030_usb_linkstat(twl); twl->linkstat = status; - if (status == OMAP_MUSB_ID_GROUND || status == OMAP_MUSB_VBUS_VALID) { + if (status == OMAP_MUSB_ID_GROUND || status == OMAP_MUSB_VBUS_VALID) omap_musb_mailbox(twl->linkstat); - twl4030_phy_power_on(phy); - } sysfs_notify(&twl->dev->kobj, NULL, "vbus"); + pm_runtime_mark_last_busy(twl->dev); + pm_runtime_put_autosuspend(twl->dev); + return 0; } @@ -650,6 +661,11 @@ static const struct phy_ops ops = { .owner = THIS_MODULE, }; +static const struct dev_pm_ops twl4030_usb_pm_ops = { + SET_RUNTIME_PM_OPS(twl4030_usb_runtime_suspend, + twl4030_usb_runtime_resume, NULL) +}; + static int twl4030_usb_probe(struct platform_device *pdev) { struct twl4030_usb_data *pdata = dev_get_platdata(&pdev->dev); @@ -726,6 +742,11 @@ static int twl4030_usb_probe(struct platform_device *pdev) ATOMIC_INIT_NOTIFIER_HEAD(&twl->phy.notifier); + pm_runtime_use_autosuspend(&pdev->dev); + pm_runtime_set_autosuspend_delay(&pdev->dev, 2000); + pm_runtime_enable(&pdev->dev); + pm_runtime_get_sync(&pdev->dev); + /* Our job is to use irqs and status from the power module * to keep the transceiver disabled when nothing's connected. * @@ -744,6 +765,9 @@ static int twl4030_usb_probe(struct platform_device *pdev) return status; } + pm_runtime_mark_last_busy(&pdev->dev); + pm_runtime_put_autosuspend(twl->dev); + dev_info(&pdev->dev, "Initialized TWL4030 USB module\n"); return 0; } @@ -753,6 +777,7 @@ static int twl4030_usb_remove(struct platform_device *pdev) struct twl4030_usb *twl = platform_get_drvdata(pdev); int val; + pm_runtime_get_sync(twl->dev); cancel_delayed_work(&twl->id_workaround_work); device_remove_file(twl->dev, &dev_attr_vbus); @@ -772,9 +797,8 @@ static int twl4030_usb_remove(struct platform_device *pdev) /* disable complete OTG block */ twl4030_usb_clear_bits(twl, POWER_CTRL, POWER_CTRL_OTG_ENAB); - - if (!twl->asleep) - twl4030_phy_power(twl, 0); + pm_runtime_mark_last_busy(twl->dev); + pm_runtime_put(twl->dev); return 0; } @@ -792,6 +816,7 @@ static struct platform_driver twl4030_usb_driver = { .remove = twl4030_usb_remove, .driver = { .name = "twl4030_usb", + .pm = &twl4030_usb_pm_ops, .owner = THIS_MODULE, .of_match_table = of_match_ptr(twl4030_usb_id_table), }, diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c index c0fe6091566a..988f5e18763a 100644 --- a/drivers/pinctrl/core.c +++ b/drivers/pinctrl/core.c @@ -1812,14 +1812,15 @@ void pinctrl_unregister(struct pinctrl_dev *pctldev) if (pctldev == NULL) return; - mutex_lock(&pinctrldev_list_mutex); mutex_lock(&pctldev->mutex); - pinctrl_remove_device_debugfs(pctldev); + mutex_unlock(&pctldev->mutex); if (!IS_ERR(pctldev->p)) pinctrl_put(pctldev->p); + mutex_lock(&pinctrldev_list_mutex); + mutex_lock(&pctldev->mutex); /* TODO: check that no pinmuxes are still active? */ list_del(&pctldev->node); /* Destroy descriptor tree */ diff --git a/drivers/pinctrl/pinctrl-baytrail.c b/drivers/pinctrl/pinctrl-baytrail.c index 665b96bc0c3a..eb9f1906952a 100644 --- a/drivers/pinctrl/pinctrl-baytrail.c +++ b/drivers/pinctrl/pinctrl-baytrail.c @@ -263,7 +263,7 @@ static int byt_gpio_direction_output(struct gpio_chip *chip, spin_lock_irqsave(&vg->lock, flags); reg_val = readl(reg) | BYT_DIR_MASK; - reg_val &= ~BYT_OUTPUT_EN; + reg_val &= ~(BYT_OUTPUT_EN | BYT_INPUT_EN); if (value) writel(reg_val | BYT_LEVEL, reg); diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c index c91f69b39db4..dcfcaea76048 100644 --- a/drivers/platform/x86/acer-wmi.c +++ b/drivers/platform/x86/acer-wmi.c @@ -570,6 +570,17 @@ static const struct dmi_system_id video_vendor_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5750"), }, }, + { + /* + * Note no video_set_backlight_video_vendor, we must use the + * acer interface, as there is no native backlight interface. + */ + .ident = "Acer KAV80", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "KAV80"), + }, + }, {} }; diff --git a/drivers/platform/x86/dell-wmi.c b/drivers/platform/x86/dell-wmi.c index 390e8e33d5e3..25721bf20092 100644 --- a/drivers/platform/x86/dell-wmi.c +++ b/drivers/platform/x86/dell-wmi.c @@ -163,18 +163,24 @@ static void dell_wmi_notify(u32 value, void *context) const struct key_entry *key; int reported_key; u16 *buffer_entry = (u16 *)obj->buffer.pointer; + int buffer_size = obj->buffer.length/2; - if (dell_new_hk_type && (buffer_entry[1] != 0x10)) { + if (buffer_size >= 2 && dell_new_hk_type && buffer_entry[1] != 0x10) { pr_info("Received unknown WMI event (0x%x)\n", buffer_entry[1]); kfree(obj); return; } - if (dell_new_hk_type || buffer_entry[1] == 0x0) + if (buffer_size >= 3 && (dell_new_hk_type || buffer_entry[1] == 0x0)) reported_key = (int)buffer_entry[2]; - else + else if (buffer_size >= 2) reported_key = (int)buffer_entry[1] & 0xffff; + else { + pr_info("Received unknown WMI event\n"); + kfree(obj); + return; + } key = sparse_keymap_entry_from_scancode(dell_wmi_input_dev, reported_key); diff --git a/drivers/platform/x86/hp_accel.c b/drivers/platform/x86/hp_accel.c index 3dc934438c28..07fbcb0fb646 100644 --- a/drivers/platform/x86/hp_accel.c +++ b/drivers/platform/x86/hp_accel.c @@ -237,6 +237,7 @@ static struct dmi_system_id lis3lv02d_dmi_ids[] = { AXIS_DMI_MATCH("HPB64xx", "HP ProBook 64", xy_swap), AXIS_DMI_MATCH("HPB64xx", "HP EliteBook 84", xy_swap), AXIS_DMI_MATCH("HPB65xx", "HP ProBook 65", x_inverted), + AXIS_DMI_MATCH("HPZBook15", "HP ZBook 15", x_inverted), { NULL, } /* Laptop models without axis info (yet): * "NC6910" "HP Compaq 6910" diff --git a/drivers/power/88pm860x_charger.c b/drivers/power/88pm860x_charger.c index de029bbc1cc1..5ccca8743ce6 100644 --- a/drivers/power/88pm860x_charger.c +++ b/drivers/power/88pm860x_charger.c @@ -711,6 +711,7 @@ static int pm860x_charger_probe(struct platform_device *pdev) return 0; out_irq: + power_supply_unregister(&info->usb); while (--i >= 0) free_irq(info->irq[i], info); out: diff --git a/drivers/power/bq2415x_charger.c b/drivers/power/bq2415x_charger.c index e384844a1ae1..1f49986fc605 100644 --- a/drivers/power/bq2415x_charger.c +++ b/drivers/power/bq2415x_charger.c @@ -1579,8 +1579,15 @@ static int bq2415x_probe(struct i2c_client *client, if (np) { bq->notify_psy = power_supply_get_by_phandle(np, "ti,usb-charger-detection"); - if (!bq->notify_psy) - return -EPROBE_DEFER; + if (IS_ERR(bq->notify_psy)) { + dev_info(&client->dev, + "no 'ti,usb-charger-detection' property (err=%ld)\n", + PTR_ERR(bq->notify_psy)); + bq->notify_psy = NULL; + } else if (!bq->notify_psy) { + ret = -EPROBE_DEFER; + goto error_2; + } } else if (pdata->notify_device) bq->notify_psy = power_supply_get_by_name(pdata->notify_device); @@ -1602,27 +1609,27 @@ static int bq2415x_probe(struct i2c_client *client, ret = of_property_read_u32(np, "ti,current-limit", &bq->init_data.current_limit); if (ret) - return ret; + goto error_2; ret = of_property_read_u32(np, "ti,weak-battery-voltage", &bq->init_data.weak_battery_voltage); if (ret) - return ret; + goto error_2; ret = of_property_read_u32(np, "ti,battery-regulation-voltage", &bq->init_data.battery_regulation_voltage); if (ret) - return ret; + goto error_2; ret = of_property_read_u32(np, "ti,charge-current", &bq->init_data.charge_current); if (ret) - return ret; + goto error_2; ret = of_property_read_u32(np, "ti,termination-current", &bq->init_data.termination_current); if (ret) - return ret; + goto error_2; ret = of_property_read_u32(np, "ti,resistor-sense", &bq->init_data.resistor_sense); if (ret) - return ret; + goto error_2; } else { memcpy(&bq->init_data, pdata, sizeof(bq->init_data)); } diff --git a/drivers/power/bq24190_charger.c b/drivers/power/bq24190_charger.c index ad3ff8fbfbbb..e4c95e1a6733 100644 --- a/drivers/power/bq24190_charger.c +++ b/drivers/power/bq24190_charger.c @@ -929,7 +929,7 @@ static void bq24190_charger_init(struct power_supply *charger) charger->properties = bq24190_charger_properties; charger->num_properties = ARRAY_SIZE(bq24190_charger_properties); charger->supplied_to = bq24190_charger_supplied_to; - charger->num_supplies = ARRAY_SIZE(bq24190_charger_supplied_to); + charger->num_supplicants = ARRAY_SIZE(bq24190_charger_supplied_to); charger->get_property = bq24190_charger_get_property; charger->set_property = bq24190_charger_set_property; charger->property_is_writeable = bq24190_charger_property_is_writeable; diff --git a/drivers/power/charger-manager.c b/drivers/power/charger-manager.c index 9e4dab46eefd..03bfac3655ef 100644 --- a/drivers/power/charger-manager.c +++ b/drivers/power/charger-manager.c @@ -97,6 +97,7 @@ static struct charger_global_desc *g_desc; /* init with setup_charger_manager */ static bool is_batt_present(struct charger_manager *cm) { union power_supply_propval val; + struct power_supply *psy; bool present = false; int i, ret; @@ -107,16 +108,27 @@ static bool is_batt_present(struct charger_manager *cm) case CM_NO_BATTERY: break; case CM_FUEL_GAUGE: - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + psy = power_supply_get_by_name(cm->desc->psy_fuel_gauge); + if (!psy) + break; + + ret = psy->get_property(psy, POWER_SUPPLY_PROP_PRESENT, &val); if (ret == 0 && val.intval) present = true; break; case CM_CHARGER_STAT: - for (i = 0; cm->charger_stat[i]; i++) { - ret = cm->charger_stat[i]->get_property( - cm->charger_stat[i], - POWER_SUPPLY_PROP_PRESENT, &val); + for (i = 0; cm->desc->psy_charger_stat[i]; i++) { + psy = power_supply_get_by_name( + cm->desc->psy_charger_stat[i]); + if (!psy) { + dev_err(cm->dev, "Cannot find power supply \"%s\"\n", + cm->desc->psy_charger_stat[i]); + continue; + } + + ret = psy->get_property(psy, POWER_SUPPLY_PROP_PRESENT, + &val); if (ret == 0 && val.intval) { present = true; break; @@ -139,14 +151,20 @@ static bool is_batt_present(struct charger_manager *cm) static bool is_ext_pwr_online(struct charger_manager *cm) { union power_supply_propval val; + struct power_supply *psy; bool online = false; int i, ret; /* If at least one of them has one, it's yes. */ - for (i = 0; cm->charger_stat[i]; i++) { - ret = cm->charger_stat[i]->get_property( - cm->charger_stat[i], - POWER_SUPPLY_PROP_ONLINE, &val); + for (i = 0; cm->desc->psy_charger_stat[i]; i++) { + psy = power_supply_get_by_name(cm->desc->psy_charger_stat[i]); + if (!psy) { + dev_err(cm->dev, "Cannot find power supply \"%s\"\n", + cm->desc->psy_charger_stat[i]); + continue; + } + + ret = psy->get_property(psy, POWER_SUPPLY_PROP_ONLINE, &val); if (ret == 0 && val.intval) { online = true; break; @@ -167,12 +185,14 @@ static bool is_ext_pwr_online(struct charger_manager *cm) static int get_batt_uV(struct charger_manager *cm, int *uV) { union power_supply_propval val; + struct power_supply *fuel_gauge; int ret; - if (!cm->fuel_gauge) + fuel_gauge = power_supply_get_by_name(cm->desc->psy_fuel_gauge); + if (!fuel_gauge) return -ENODEV; - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + ret = fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_VOLTAGE_NOW, &val); if (ret) return ret; @@ -189,6 +209,7 @@ static bool is_charging(struct charger_manager *cm) { int i, ret; bool charging = false; + struct power_supply *psy; union power_supply_propval val; /* If there is no battery, it cannot be charged */ @@ -196,17 +217,22 @@ static bool is_charging(struct charger_manager *cm) return false; /* If at least one of the charger is charging, return yes */ - for (i = 0; cm->charger_stat[i]; i++) { + for (i = 0; cm->desc->psy_charger_stat[i]; i++) { /* 1. The charger sholuld not be DISABLED */ if (cm->emergency_stop) continue; if (!cm->charger_enabled) continue; + psy = power_supply_get_by_name(cm->desc->psy_charger_stat[i]); + if (!psy) { + dev_err(cm->dev, "Cannot find power supply \"%s\"\n", + cm->desc->psy_charger_stat[i]); + continue; + } + /* 2. The charger should be online (ext-power) */ - ret = cm->charger_stat[i]->get_property( - cm->charger_stat[i], - POWER_SUPPLY_PROP_ONLINE, &val); + ret = psy->get_property(psy, POWER_SUPPLY_PROP_ONLINE, &val); if (ret) { dev_warn(cm->dev, "Cannot read ONLINE value from %s\n", cm->desc->psy_charger_stat[i]); @@ -219,9 +245,7 @@ static bool is_charging(struct charger_manager *cm) * 3. The charger should not be FULL, DISCHARGING, * or NOT_CHARGING. */ - ret = cm->charger_stat[i]->get_property( - cm->charger_stat[i], - POWER_SUPPLY_PROP_STATUS, &val); + ret = psy->get_property(psy, POWER_SUPPLY_PROP_STATUS, &val); if (ret) { dev_warn(cm->dev, "Cannot read STATUS value from %s\n", cm->desc->psy_charger_stat[i]); @@ -248,6 +272,7 @@ static bool is_full_charged(struct charger_manager *cm) { struct charger_desc *desc = cm->desc; union power_supply_propval val; + struct power_supply *fuel_gauge; int ret = 0; int uV; @@ -255,11 +280,15 @@ static bool is_full_charged(struct charger_manager *cm) if (!is_batt_present(cm)) return false; - if (cm->fuel_gauge && desc->fullbatt_full_capacity > 0) { + fuel_gauge = power_supply_get_by_name(cm->desc->psy_fuel_gauge); + if (!fuel_gauge) + return false; + + if (desc->fullbatt_full_capacity > 0) { val.intval = 0; /* Not full if capacity of fuel gauge isn't full */ - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + ret = fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_CHARGE_FULL, &val); if (!ret && val.intval > desc->fullbatt_full_capacity) return true; @@ -273,10 +302,10 @@ static bool is_full_charged(struct charger_manager *cm) } /* Full, if the capacity is more than fullbatt_soc */ - if (cm->fuel_gauge && desc->fullbatt_soc > 0) { + if (desc->fullbatt_soc > 0) { val.intval = 0; - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + ret = fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_CAPACITY, &val); if (!ret && val.intval >= desc->fullbatt_soc) return true; @@ -551,6 +580,20 @@ static int check_charging_duration(struct charger_manager *cm) return ret; } +static int cm_get_battery_temperature_by_psy(struct charger_manager *cm, + int *temp) +{ + struct power_supply *fuel_gauge; + + fuel_gauge = power_supply_get_by_name(cm->desc->psy_fuel_gauge); + if (!fuel_gauge) + return -ENODEV; + + return fuel_gauge->get_property(fuel_gauge, + POWER_SUPPLY_PROP_TEMP, + (union power_supply_propval *)temp); +} + static int cm_get_battery_temperature(struct charger_manager *cm, int *temp) { @@ -560,15 +603,18 @@ static int cm_get_battery_temperature(struct charger_manager *cm, return -ENODEV; #ifdef CONFIG_THERMAL - ret = thermal_zone_get_temp(cm->tzd_batt, (unsigned long *)temp); - if (!ret) - /* Calibrate temperature unit */ - *temp /= 100; -#else - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, - POWER_SUPPLY_PROP_TEMP, - (union power_supply_propval *)temp); + if (cm->tzd_batt) { + ret = thermal_zone_get_temp(cm->tzd_batt, (unsigned long *)temp); + if (!ret) + /* Calibrate temperature unit */ + *temp /= 100; + } else #endif + { + /* if-else continued from CONFIG_THERMAL */ + ret = cm_get_battery_temperature_by_psy(cm, temp); + } + return ret; } @@ -827,6 +873,7 @@ static int charger_get_property(struct power_supply *psy, struct charger_manager *cm = container_of(psy, struct charger_manager, charger_psy); struct charger_desc *desc = cm->desc; + struct power_supply *fuel_gauge; int ret = 0; int uV; @@ -857,14 +904,20 @@ static int charger_get_property(struct power_supply *psy, ret = get_batt_uV(cm, &val->intval); break; case POWER_SUPPLY_PROP_CURRENT_NOW: - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + fuel_gauge = power_supply_get_by_name(cm->desc->psy_fuel_gauge); + if (!fuel_gauge) { + ret = -ENODEV; + break; + } + ret = fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_CURRENT_NOW, val); break; case POWER_SUPPLY_PROP_TEMP: case POWER_SUPPLY_PROP_TEMP_AMBIENT: return cm_get_battery_temperature(cm, &val->intval); case POWER_SUPPLY_PROP_CAPACITY: - if (!cm->fuel_gauge) { + fuel_gauge = power_supply_get_by_name(cm->desc->psy_fuel_gauge); + if (!fuel_gauge) { ret = -ENODEV; break; } @@ -875,7 +928,7 @@ static int charger_get_property(struct power_supply *psy, break; } - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + ret = fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_CAPACITY, val); if (ret) break; @@ -924,7 +977,14 @@ static int charger_get_property(struct power_supply *psy, break; case POWER_SUPPLY_PROP_CHARGE_NOW: if (is_charging(cm)) { - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + fuel_gauge = power_supply_get_by_name( + cm->desc->psy_fuel_gauge); + if (!fuel_gauge) { + ret = -ENODEV; + break; + } + + ret = fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_CHARGE_NOW, val); if (ret) { @@ -1485,14 +1545,15 @@ err: return ret; } -static int cm_init_thermal_data(struct charger_manager *cm) +static int cm_init_thermal_data(struct charger_manager *cm, + struct power_supply *fuel_gauge) { struct charger_desc *desc = cm->desc; union power_supply_propval val; int ret; /* Verify whether fuel gauge provides battery temperature */ - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + ret = fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_TEMP, &val); if (!ret) { @@ -1502,8 +1563,6 @@ static int cm_init_thermal_data(struct charger_manager *cm) cm->desc->measure_battery_temp = true; } #ifdef CONFIG_THERMAL - cm->tzd_batt = cm->fuel_gauge->tzd; - if (ret && desc->thermal_zone) { cm->tzd_batt = thermal_zone_get_zone_by_name(desc->thermal_zone); @@ -1666,6 +1725,7 @@ static int charger_manager_probe(struct platform_device *pdev) int ret = 0, i = 0; int j = 0; union power_supply_propval val; + struct power_supply *fuel_gauge; if (g_desc && !rtc_dev && g_desc->rtc_name) { rtc_dev = rtc_class_open(g_desc->rtc_name); @@ -1720,27 +1780,29 @@ static int charger_manager_probe(struct platform_device *pdev) return -EINVAL; } + if (!desc->psy_fuel_gauge) { + dev_err(&pdev->dev, "No fuel gauge power supply defined\n"); + return -EINVAL; + } + /* Counting index only */ while (desc->psy_charger_stat[i]) i++; - cm->charger_stat = devm_kzalloc(&pdev->dev, - sizeof(struct power_supply *) * i, GFP_KERNEL); - if (!cm->charger_stat) - return -ENOMEM; - + /* Check if charger's supplies are present at probe */ for (i = 0; desc->psy_charger_stat[i]; i++) { - cm->charger_stat[i] = power_supply_get_by_name( - desc->psy_charger_stat[i]); - if (!cm->charger_stat[i]) { + struct power_supply *psy; + + psy = power_supply_get_by_name(desc->psy_charger_stat[i]); + if (!psy) { dev_err(&pdev->dev, "Cannot find power supply \"%s\"\n", desc->psy_charger_stat[i]); return -ENODEV; } } - cm->fuel_gauge = power_supply_get_by_name(desc->psy_fuel_gauge); - if (!cm->fuel_gauge) { + fuel_gauge = power_supply_get_by_name(desc->psy_fuel_gauge); + if (!fuel_gauge) { dev_err(&pdev->dev, "Cannot find power supply \"%s\"\n", desc->psy_fuel_gauge); return -ENODEV; @@ -1783,13 +1845,13 @@ static int charger_manager_probe(struct platform_device *pdev) cm->charger_psy.num_properties = psy_default.num_properties; /* Find which optional psy-properties are available */ - if (!cm->fuel_gauge->get_property(cm->fuel_gauge, + if (!fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_CHARGE_NOW, &val)) { cm->charger_psy.properties[cm->charger_psy.num_properties] = POWER_SUPPLY_PROP_CHARGE_NOW; cm->charger_psy.num_properties++; } - if (!cm->fuel_gauge->get_property(cm->fuel_gauge, + if (!fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_CURRENT_NOW, &val)) { cm->charger_psy.properties[cm->charger_psy.num_properties] = @@ -1797,7 +1859,7 @@ static int charger_manager_probe(struct platform_device *pdev) cm->charger_psy.num_properties++; } - ret = cm_init_thermal_data(cm); + ret = cm_init_thermal_data(cm, fuel_gauge); if (ret) { dev_err(&pdev->dev, "Failed to initialize thermal data\n"); cm->desc->measure_battery_temp = false; @@ -2054,8 +2116,8 @@ static bool find_power_supply(struct charger_manager *cm, int i; bool found = false; - for (i = 0; cm->charger_stat[i]; i++) { - if (psy == cm->charger_stat[i]) { + for (i = 0; cm->desc->psy_charger_stat[i]; i++) { + if (!strcmp(psy->name, cm->desc->psy_charger_stat[i])) { found = true; break; } diff --git a/drivers/power/gpio-charger.c b/drivers/power/gpio-charger.c index a0024b252197..86e03c6d28f3 100644 --- a/drivers/power/gpio-charger.c +++ b/drivers/power/gpio-charger.c @@ -168,7 +168,7 @@ static int gpio_charger_suspend(struct device *dev) if (device_may_wakeup(dev)) gpio_charger->wakeup_enabled = - enable_irq_wake(gpio_charger->irq); + !enable_irq_wake(gpio_charger->irq); return 0; } @@ -178,7 +178,7 @@ static int gpio_charger_resume(struct device *dev) struct platform_device *pdev = to_platform_device(dev); struct gpio_charger *gpio_charger = platform_get_drvdata(pdev); - if (gpio_charger->wakeup_enabled) + if (device_may_wakeup(dev) && gpio_charger->wakeup_enabled) disable_irq_wake(gpio_charger->irq); power_supply_changed(&gpio_charger->charger); diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index afca1bc24f26..5d8d2dcd975e 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1479,7 +1479,7 @@ struct regulator *regulator_get_optional(struct device *dev, const char *id) } EXPORT_SYMBOL_GPL(regulator_get_optional); -/* Locks held by regulator_put() */ +/* regulator_list_mutex lock held by regulator_put() */ static void _regulator_put(struct regulator *regulator) { struct regulator_dev *rdev; @@ -1494,12 +1494,14 @@ static void _regulator_put(struct regulator *regulator) /* remove any sysfs entries */ if (regulator->dev) sysfs_remove_link(&rdev->dev.kobj, regulator->supply_name); + mutex_lock(&rdev->mutex); kfree(regulator->supply_name); list_del(®ulator->list); kfree(regulator); rdev->open_count--; rdev->exclusive = 0; + mutex_unlock(&rdev->mutex); module_put(rdev->owner); } @@ -1762,10 +1764,12 @@ static int _regulator_do_enable(struct regulator_dev *rdev) trace_regulator_enable(rdev_get_name(rdev)); if (rdev->ena_pin) { - ret = regulator_ena_gpio_ctrl(rdev, true); - if (ret < 0) - return ret; - rdev->ena_gpio_state = 1; + if (!rdev->ena_gpio_state) { + ret = regulator_ena_gpio_ctrl(rdev, true); + if (ret < 0) + return ret; + rdev->ena_gpio_state = 1; + } } else if (rdev->desc->ops->enable) { ret = rdev->desc->ops->enable(rdev); if (ret < 0) @@ -1895,10 +1899,12 @@ static int _regulator_do_disable(struct regulator_dev *rdev) trace_regulator_disable(rdev_get_name(rdev)); if (rdev->ena_pin) { - ret = regulator_ena_gpio_ctrl(rdev, false); - if (ret < 0) - return ret; - rdev->ena_gpio_state = 0; + if (rdev->ena_gpio_state) { + ret = regulator_ena_gpio_ctrl(rdev, false); + if (ret < 0) + return ret; + rdev->ena_gpio_state = 0; + } } else if (rdev->desc->ops->disable) { ret = rdev->desc->ops->disable(rdev); @@ -3452,12 +3458,6 @@ regulator_register(const struct regulator_desc *regulator_desc, config->ena_gpio, ret); goto wash; } - - if (config->ena_gpio_flags & GPIOF_OUT_INIT_HIGH) - rdev->ena_gpio_state = 1; - - if (config->ena_gpio_invert) - rdev->ena_gpio_state = !rdev->ena_gpio_state; } /* set regulator constraints */ @@ -3629,9 +3629,11 @@ int regulator_suspend_finish(void) list_for_each_entry(rdev, ®ulator_list, list) { mutex_lock(&rdev->mutex); if (rdev->use_count > 0 || rdev->constraints->always_on) { - error = _regulator_do_enable(rdev); - if (error) - ret = error; + if (!_regulator_is_enabled(rdev)) { + error = _regulator_do_enable(rdev); + if (error) + ret = error; + } } else { if (!have_full_constraints()) goto unlock; diff --git a/drivers/regulator/max77693.c b/drivers/regulator/max77693.c index 5fb899f461d0..24c926bfe6d4 100644 --- a/drivers/regulator/max77693.c +++ b/drivers/regulator/max77693.c @@ -232,7 +232,7 @@ static int max77693_pmic_probe(struct platform_device *pdev) struct max77693_pmic_dev *max77693_pmic; struct max77693_regulator_data *rdata = NULL; int num_rdata, i; - struct regulator_config config; + struct regulator_config config = { }; num_rdata = max77693_pmic_init_rdata(&pdev->dev, &rdata); if (!rdata || num_rdata <= 0) { diff --git a/drivers/rtc/rtc-isl12057.c b/drivers/rtc/rtc-isl12057.c index 7854a656628f..110eab817a4f 100644 --- a/drivers/rtc/rtc-isl12057.c +++ b/drivers/rtc/rtc-isl12057.c @@ -89,7 +89,7 @@ static void isl12057_rtc_regs_to_tm(struct rtc_time *tm, u8 *regs) tm->tm_min = bcd2bin(regs[ISL12057_REG_RTC_MN]); if (regs[ISL12057_REG_RTC_HR] & ISL12057_REG_RTC_HR_MIL) { /* AM/PM */ - tm->tm_hour = bcd2bin(regs[ISL12057_REG_RTC_HR] & 0x0f); + tm->tm_hour = bcd2bin(regs[ISL12057_REG_RTC_HR] & 0x1f); if (regs[ISL12057_REG_RTC_HR] & ISL12057_REG_RTC_HR_PM) tm->tm_hour += 12; } else { /* 24 hour mode */ @@ -98,7 +98,7 @@ static void isl12057_rtc_regs_to_tm(struct rtc_time *tm, u8 *regs) tm->tm_mday = bcd2bin(regs[ISL12057_REG_RTC_DT]); tm->tm_wday = bcd2bin(regs[ISL12057_REG_RTC_DW]) - 1; /* starts at 1 */ - tm->tm_mon = bcd2bin(regs[ISL12057_REG_RTC_MO]) - 1; /* starts at 1 */ + tm->tm_mon = bcd2bin(regs[ISL12057_REG_RTC_MO] & 0x1f) - 1; /* ditto */ tm->tm_year = bcd2bin(regs[ISL12057_REG_RTC_YR]) + 100; } diff --git a/drivers/rtc/rtc-sirfsoc.c b/drivers/rtc/rtc-sirfsoc.c index 3eb3642ae299..d2b1ab3162c2 100644 --- a/drivers/rtc/rtc-sirfsoc.c +++ b/drivers/rtc/rtc-sirfsoc.c @@ -290,14 +290,6 @@ static int sirfsoc_rtc_probe(struct platform_device *pdev) rtc_div = ((32768 / RTC_HZ) / 2) - 1; sirfsoc_rtc_iobrg_writel(rtc_div, rtcdrv->rtc_base + RTC_DIV); - rtcdrv->rtc = devm_rtc_device_register(&pdev->dev, pdev->name, - &sirfsoc_rtc_ops, THIS_MODULE); - if (IS_ERR(rtcdrv->rtc)) { - err = PTR_ERR(rtcdrv->rtc); - dev_err(&pdev->dev, "can't register RTC device\n"); - return err; - } - /* 0x3 -> RTC_CLK */ sirfsoc_rtc_iobrg_writel(SIRFSOC_RTC_CLK, rtcdrv->rtc_base + RTC_CLOCK_SWITCH); @@ -312,6 +304,14 @@ static int sirfsoc_rtc_probe(struct platform_device *pdev) rtcdrv->overflow_rtc = sirfsoc_rtc_iobrg_readl(rtcdrv->rtc_base + RTC_SW_VALUE); + rtcdrv->rtc = devm_rtc_device_register(&pdev->dev, pdev->name, + &sirfsoc_rtc_ops, THIS_MODULE); + if (IS_ERR(rtcdrv->rtc)) { + err = PTR_ERR(rtcdrv->rtc); + dev_err(&pdev->dev, "can't register RTC device\n"); + return err; + } + rtcdrv->irq = platform_get_irq(pdev, 0); err = devm_request_irq( &pdev->dev, diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c index bb86494e2b7b..19915c5b256f 100644 --- a/drivers/s390/char/con3215.c +++ b/drivers/s390/char/con3215.c @@ -288,12 +288,16 @@ static void raw3215_timeout(unsigned long __data) unsigned long flags; spin_lock_irqsave(get_ccwdev_lock(raw->cdev), flags); - if (raw->flags & RAW3215_TIMER_RUNS) { - del_timer(&raw->timer); - raw->flags &= ~RAW3215_TIMER_RUNS; - if (!(raw->port.flags & ASYNC_SUSPENDED)) { - raw3215_mk_write_req(raw); - raw3215_start_io(raw); + raw->flags &= ~RAW3215_TIMER_RUNS; + if (!(raw->port.flags & ASYNC_SUSPENDED)) { + raw3215_mk_write_req(raw); + raw3215_start_io(raw); + if ((raw->queued_read || raw->queued_write) && + !(raw->flags & RAW3215_WORKING) && + !(raw->flags & RAW3215_TIMER_RUNS)) { + raw->timer.expires = RAW3215_TIMEOUT + jiffies; + add_timer(&raw->timer); + raw->flags |= RAW3215_TIMER_RUNS; } } spin_unlock_irqrestore(get_ccwdev_lock(raw->cdev), flags); @@ -317,17 +321,15 @@ static inline void raw3215_try_io(struct raw3215_info *raw) (raw->flags & RAW3215_FLUSHING)) { /* execute write requests bigger than minimum size */ raw3215_start_io(raw); - if (raw->flags & RAW3215_TIMER_RUNS) { - del_timer(&raw->timer); - raw->flags &= ~RAW3215_TIMER_RUNS; - } - } else if (!(raw->flags & RAW3215_TIMER_RUNS)) { - /* delay small writes */ - raw->timer.expires = RAW3215_TIMEOUT + jiffies; - add_timer(&raw->timer); - raw->flags |= RAW3215_TIMER_RUNS; } } + if ((raw->queued_read || raw->queued_write) && + !(raw->flags & RAW3215_WORKING) && + !(raw->flags & RAW3215_TIMER_RUNS)) { + raw->timer.expires = RAW3215_TIMEOUT + jiffies; + add_timer(&raw->timer); + raw->flags |= RAW3215_TIMER_RUNS; + } } /* @@ -1027,12 +1029,26 @@ static int tty3215_write(struct tty_struct * tty, const unsigned char *buf, int count) { struct raw3215_info *raw; + int i, written; if (!tty) return 0; raw = (struct raw3215_info *) tty->driver_data; - raw3215_write(raw, buf, count); - return count; + written = count; + while (count > 0) { + for (i = 0; i < count; i++) + if (buf[i] == '\t' || buf[i] == '\n') + break; + raw3215_write(raw, buf, i); + count -= i; + buf += i; + if (count > 0) { + raw3215_putchar(raw, *buf); + count--; + buf++; + } + } + return written; } /* @@ -1180,7 +1196,7 @@ static int __init tty3215_init(void) driver->subtype = SYSTEM_TYPE_TTY; driver->init_termios = tty_std_termios; driver->init_termios.c_iflag = IGNBRK | IGNPAR; - driver->init_termios.c_oflag = ONLCR | XTABS; + driver->init_termios.c_oflag = ONLCR; driver->init_termios.c_lflag = ISIG; driver->flags = TTY_DRIVER_REAL_RAW; tty_set_operations(driver, &tty3215_ops); diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index ab3baa7f9508..86ade85481bd 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -44,6 +44,7 @@ #include <linux/hrtimer.h> #include <linux/ktime.h> #include <asm/facility.h> +#include <linux/crypto.h> #include "ap_bus.h" @@ -71,7 +72,7 @@ MODULE_AUTHOR("IBM Corporation"); MODULE_DESCRIPTION("Adjunct Processor Bus driver, " \ "Copyright IBM Corp. 2006, 2012"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("z90crypt"); +MODULE_ALIAS_CRYPTO("z90crypt"); /* * Module parameter diff --git a/drivers/scsi/NCR5380.c b/drivers/scsi/NCR5380.c index 1e9d6ad9302b..7563b3d9cc76 100644 --- a/drivers/scsi/NCR5380.c +++ b/drivers/scsi/NCR5380.c @@ -2655,14 +2655,14 @@ static void NCR5380_dma_complete(NCR5380_instance * instance) { * * Purpose : abort a command * - * Inputs : cmd - the Scsi_Cmnd to abort, code - code to set the - * host byte of the result field to, if zero DID_ABORTED is + * Inputs : cmd - the Scsi_Cmnd to abort, code - code to set the + * host byte of the result field to, if zero DID_ABORTED is * used. * - * Returns : 0 - success, -1 on failure. + * Returns : SUCCESS - success, FAILED on failure. * - * XXX - there is no way to abort the command that is currently - * connected, you have to wait for it to complete. If this is + * XXX - there is no way to abort the command that is currently + * connected, you have to wait for it to complete. If this is * a problem, we could implement longjmp() / setjmp(), setjmp() * called where the loop started in NCR5380_main(). * @@ -2712,7 +2712,7 @@ static int NCR5380_abort(Scsi_Cmnd * cmd) { * aborted flag and get back into our main loop. */ - return 0; + return SUCCESS; } #endif diff --git a/drivers/scsi/aha1740.c b/drivers/scsi/aha1740.c index 5f3101797c93..31ace4bef8fe 100644 --- a/drivers/scsi/aha1740.c +++ b/drivers/scsi/aha1740.c @@ -531,7 +531,7 @@ static int aha1740_eh_abort_handler (Scsi_Cmnd *dummy) * quiet as possible... */ - return 0; + return SUCCESS; } static struct scsi_host_template aha1740_template = { diff --git a/drivers/scsi/atari_NCR5380.c b/drivers/scsi/atari_NCR5380.c index 0f3cdbc80ba6..30073d43d87b 100644 --- a/drivers/scsi/atari_NCR5380.c +++ b/drivers/scsi/atari_NCR5380.c @@ -2613,7 +2613,7 @@ static void NCR5380_reselect(struct Scsi_Host *instance) * host byte of the result field to, if zero DID_ABORTED is * used. * - * Returns : 0 - success, -1 on failure. + * Returns : SUCCESS - success, FAILED on failure. * * XXX - there is no way to abort the command that is currently * connected, you have to wait for it to complete. If this is diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c index 5642a9b250c2..19ddd43a00cf 100644 --- a/drivers/scsi/be2iscsi/be_main.c +++ b/drivers/scsi/be2iscsi/be_main.c @@ -581,7 +581,6 @@ static struct beiscsi_hba *beiscsi_hba_alloc(struct pci_dev *pcidev) "beiscsi_hba_alloc - iscsi_host_alloc failed\n"); return NULL; } - shost->dma_boundary = pcidev->dma_mask; shost->max_id = BE2_MAX_SESSIONS; shost->max_channel = 0; shost->max_cmd_len = BEISCSI_MAX_CMD_LEN; @@ -5685,9 +5684,9 @@ free_port: hba_free: if (phba->msix_enabled) pci_disable_msix(phba->pcidev); - iscsi_host_remove(phba->shost); pci_dev_put(phba->pcidev); iscsi_host_free(phba->shost); + pci_set_drvdata(pcidev, NULL); disable_pci: pci_disable_device(pcidev); return ret; diff --git a/drivers/scsi/be2iscsi/be_mgmt.c b/drivers/scsi/be2iscsi/be_mgmt.c index b2fcac78feaa..5bb9406688c9 100644 --- a/drivers/scsi/be2iscsi/be_mgmt.c +++ b/drivers/scsi/be2iscsi/be_mgmt.c @@ -897,17 +897,20 @@ mgmt_static_ip_modify(struct beiscsi_hba *phba, if (ip_action == IP_ACTION_ADD) { memcpy(req->ip_params.ip_record.ip_addr.addr, ip_param->value, - ip_param->len); + sizeof(req->ip_params.ip_record.ip_addr.addr)); if (subnet_param) memcpy(req->ip_params.ip_record.ip_addr.subnet_mask, - subnet_param->value, subnet_param->len); + subnet_param->value, + sizeof(req->ip_params.ip_record.ip_addr.subnet_mask)); } else { memcpy(req->ip_params.ip_record.ip_addr.addr, - if_info->ip_addr.addr, ip_param->len); + if_info->ip_addr.addr, + sizeof(req->ip_params.ip_record.ip_addr.addr)); memcpy(req->ip_params.ip_record.ip_addr.subnet_mask, - if_info->ip_addr.subnet_mask, ip_param->len); + if_info->ip_addr.subnet_mask, + sizeof(req->ip_params.ip_record.ip_addr.subnet_mask)); } rc = mgmt_exec_nonemb_cmd(phba, &nonemb_cmd, NULL, 0); @@ -935,7 +938,7 @@ static int mgmt_modify_gateway(struct beiscsi_hba *phba, uint8_t *gt_addr, req->action = gtway_action; req->ip_addr.ip_type = BE2_IPV4; - memcpy(req->ip_addr.addr, gt_addr, param_len); + memcpy(req->ip_addr.addr, gt_addr, sizeof(req->ip_addr.addr)); return mgmt_exec_nonemb_cmd(phba, &nonemb_cmd, NULL, 0); } diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c index 9b948505d118..cc6b13b81c53 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c +++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c @@ -411,6 +411,7 @@ static int bnx2fc_rcv(struct sk_buff *skb, struct net_device *dev, struct fc_frame_header *fh; struct fcoe_rcv_info *fr; struct fcoe_percpu_s *bg; + struct sk_buff *tmp_skb; unsigned short oxid; interface = container_of(ptype, struct bnx2fc_interface, @@ -423,6 +424,12 @@ static int bnx2fc_rcv(struct sk_buff *skb, struct net_device *dev, goto err; } + tmp_skb = skb_share_check(skb, GFP_ATOMIC); + if (!tmp_skb) + goto err; + + skb = tmp_skb; + if (unlikely(eth_hdr(skb)->h_proto != htons(ETH_P_FCOE))) { printk(KERN_ERR PFX "bnx2fc_rcv: Wrong FC type frame\n"); goto err; diff --git a/drivers/scsi/esas2r/esas2r_main.c b/drivers/scsi/esas2r/esas2r_main.c index f37f3e3dd5d5..28fe6feae44c 100644 --- a/drivers/scsi/esas2r/esas2r_main.c +++ b/drivers/scsi/esas2r/esas2r_main.c @@ -1057,7 +1057,7 @@ int esas2r_eh_abort(struct scsi_cmnd *cmd) cmd->scsi_done(cmd); - return 0; + return SUCCESS; } spin_lock_irqsave(&a->queue_lock, flags); diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 3f5b56a99892..b4ddb7310e36 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -683,6 +683,7 @@ static void ipr_init_ipr_cmnd(struct ipr_cmnd *ipr_cmd, ipr_reinit_ipr_cmnd(ipr_cmd); ipr_cmd->u.scratch = 0; ipr_cmd->sibling = NULL; + ipr_cmd->eh_comp = NULL; ipr_cmd->fast_done = fast_done; init_timer(&ipr_cmd->timer); } @@ -848,6 +849,8 @@ static void ipr_scsi_eh_done(struct ipr_cmnd *ipr_cmd) scsi_dma_unmap(ipr_cmd->scsi_cmd); scsi_cmd->scsi_done(scsi_cmd); + if (ipr_cmd->eh_comp) + complete(ipr_cmd->eh_comp); list_add_tail(&ipr_cmd->queue, &ipr_cmd->hrrq->hrrq_free_q); } @@ -4805,6 +4808,84 @@ static int ipr_slave_alloc(struct scsi_device *sdev) return rc; } +/** + * ipr_match_lun - Match function for specified LUN + * @ipr_cmd: ipr command struct + * @device: device to match (sdev) + * + * Returns: + * 1 if command matches sdev / 0 if command does not match sdev + **/ +static int ipr_match_lun(struct ipr_cmnd *ipr_cmd, void *device) +{ + if (ipr_cmd->scsi_cmd && ipr_cmd->scsi_cmd->device == device) + return 1; + return 0; +} + +/** + * ipr_wait_for_ops - Wait for matching commands to complete + * @ipr_cmd: ipr command struct + * @device: device to match (sdev) + * @match: match function to use + * + * Returns: + * SUCCESS / FAILED + **/ +static int ipr_wait_for_ops(struct ipr_ioa_cfg *ioa_cfg, void *device, + int (*match)(struct ipr_cmnd *, void *)) +{ + struct ipr_cmnd *ipr_cmd; + int wait; + unsigned long flags; + struct ipr_hrr_queue *hrrq; + signed long timeout = IPR_ABORT_TASK_TIMEOUT; + DECLARE_COMPLETION_ONSTACK(comp); + + ENTER; + do { + wait = 0; + + for_each_hrrq(hrrq, ioa_cfg) { + spin_lock_irqsave(hrrq->lock, flags); + list_for_each_entry(ipr_cmd, &hrrq->hrrq_pending_q, queue) { + if (match(ipr_cmd, device)) { + ipr_cmd->eh_comp = ∁ + wait++; + } + } + spin_unlock_irqrestore(hrrq->lock, flags); + } + + if (wait) { + timeout = wait_for_completion_timeout(&comp, timeout); + + if (!timeout) { + wait = 0; + + for_each_hrrq(hrrq, ioa_cfg) { + spin_lock_irqsave(hrrq->lock, flags); + list_for_each_entry(ipr_cmd, &hrrq->hrrq_pending_q, queue) { + if (match(ipr_cmd, device)) { + ipr_cmd->eh_comp = NULL; + wait++; + } + } + spin_unlock_irqrestore(hrrq->lock, flags); + } + + if (wait) + dev_err(&ioa_cfg->pdev->dev, "Timed out waiting for aborted commands\n"); + LEAVE; + return wait ? FAILED : SUCCESS; + } + } + } while (wait); + + LEAVE; + return SUCCESS; +} + static int ipr_eh_host_reset(struct scsi_cmnd *cmd) { struct ipr_ioa_cfg *ioa_cfg; @@ -5023,11 +5104,17 @@ static int __ipr_eh_dev_reset(struct scsi_cmnd *scsi_cmd) static int ipr_eh_dev_reset(struct scsi_cmnd *cmd) { int rc; + struct ipr_ioa_cfg *ioa_cfg; + + ioa_cfg = (struct ipr_ioa_cfg *) cmd->device->host->hostdata; spin_lock_irq(cmd->device->host->host_lock); rc = __ipr_eh_dev_reset(cmd); spin_unlock_irq(cmd->device->host->host_lock); + if (rc == SUCCESS) + rc = ipr_wait_for_ops(ioa_cfg, cmd->device, ipr_match_lun); + return rc; } @@ -5205,13 +5292,18 @@ static int ipr_eh_abort(struct scsi_cmnd *scsi_cmd) { unsigned long flags; int rc; + struct ipr_ioa_cfg *ioa_cfg; ENTER; + ioa_cfg = (struct ipr_ioa_cfg *) scsi_cmd->device->host->hostdata; + spin_lock_irqsave(scsi_cmd->device->host->host_lock, flags); rc = ipr_cancel_op(scsi_cmd); spin_unlock_irqrestore(scsi_cmd->device->host->host_lock, flags); + if (rc == SUCCESS) + rc = ipr_wait_for_ops(ioa_cfg, scsi_cmd->device, ipr_match_lun); LEAVE; return rc; } diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h index 9ce38a22647e..0801f3df4b27 100644 --- a/drivers/scsi/ipr.h +++ b/drivers/scsi/ipr.h @@ -1585,6 +1585,7 @@ struct ipr_cmnd { struct scsi_device *sdev; } u; + struct completion *eh_comp; struct ipr_hrr_queue *hrrq; struct ipr_ioa_cfg *ioa_cfg; }; diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 40462415291e..454998669c2a 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -717,11 +717,21 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr, return NULL; } + if (data_size > ISCSI_DEF_MAX_RECV_SEG_LEN) { + iscsi_conn_printk(KERN_ERR, conn, "Invalid buffer len of %u for login task. Max len is %u\n", data_size, ISCSI_DEF_MAX_RECV_SEG_LEN); + return NULL; + } + task = conn->login_task; } else { if (session->state != ISCSI_STATE_LOGGED_IN) return NULL; + if (data_size != 0) { + iscsi_conn_printk(KERN_ERR, conn, "Can not send data buffer of len %u for op 0x%x\n", data_size, opcode); + return NULL; + } + BUG_ON(conn->c_stage == ISCSI_CONN_INITIAL_STAGE); BUG_ON(conn->c_stage == ISCSI_CONN_STOPPED); diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c index 62b58d38ce2e..60de66252fa2 100644 --- a/drivers/scsi/libsas/sas_discover.c +++ b/drivers/scsi/libsas/sas_discover.c @@ -500,6 +500,7 @@ static void sas_revalidate_domain(struct work_struct *work) struct sas_discovery_event *ev = to_sas_discovery_event(work); struct asd_sas_port *port = ev->port; struct sas_ha_struct *ha = port->ha; + struct domain_device *ddev = port->port_dev; /* prevent revalidation from finding sata links in recovery */ mutex_lock(&ha->disco_mutex); @@ -514,8 +515,9 @@ static void sas_revalidate_domain(struct work_struct *work) SAS_DPRINTK("REVALIDATING DOMAIN on port %d, pid:%d\n", port->id, task_pid_nr(current)); - if (port->port_dev) - res = sas_ex_revalidate_domain(port->port_dev); + if (ddev && (ddev->dev_type == SAS_FANOUT_EXPANDER_DEVICE || + ddev->dev_type == SAS_EDGE_EXPANDER_DEVICE)) + res = sas_ex_revalidate_domain(ddev); SAS_DPRINTK("done REVALIDATING DOMAIN on port %d, pid:%d, res 0x%x\n", port->id, task_pid_nr(current), res); diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c index 816db12ef5d5..52587ceac099 100644 --- a/drivers/scsi/megaraid.c +++ b/drivers/scsi/megaraid.c @@ -1967,7 +1967,7 @@ megaraid_abort_and_reset(adapter_t *adapter, Scsi_Cmnd *cmd, int aor) cmd->device->id, cmd->device->lun); if(list_empty(&adapter->pending_list)) - return FALSE; + return FAILED; list_for_each_safe(pos, next, &adapter->pending_list) { @@ -1990,7 +1990,7 @@ megaraid_abort_and_reset(adapter_t *adapter, Scsi_Cmnd *cmd, int aor) (aor==SCB_ABORT) ? "ABORTING":"RESET", scb->idx); - return FALSE; + return FAILED; } else { @@ -2015,12 +2015,12 @@ megaraid_abort_and_reset(adapter_t *adapter, Scsi_Cmnd *cmd, int aor) list_add_tail(SCSI_LIST(cmd), &adapter->completed_list); - return TRUE; + return SUCCESS; } } } - return FALSE; + return FAILED; } static inline int diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 3b7ad10497fe..c80afde97e96 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -953,7 +953,7 @@ megasas_issue_blocked_abort_cmd(struct megasas_instance *instance, cpu_to_le32(upper_32_bits(cmd_to_abort->frame_phys_addr)); cmd->sync_cmd = 1; - cmd->cmd_status = 0xFF; + cmd->cmd_status = ENODATA; instance->instancet->issue_dcmd(instance, cmd); diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c index f6555921fd7a..a1f04e3b2a8f 100644 --- a/drivers/scsi/megaraid/megaraid_sas_fusion.c +++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c @@ -92,6 +92,8 @@ megasas_enable_intr_fusion(struct megasas_instance *instance) { struct megasas_register_set __iomem *regs; regs = instance->reg_set; + + instance->mask_interrupts = 0; /* For Thunderbolt/Invader also clear intr on enable */ writel(~0, ®s->outbound_intr_status); readl(®s->outbound_intr_status); @@ -100,7 +102,6 @@ megasas_enable_intr_fusion(struct megasas_instance *instance) /* Dummy readl to force pci flush */ readl(®s->outbound_intr_mask); - instance->mask_interrupts = 0; } /** diff --git a/drivers/scsi/mpt2sas/mpt2sas_transport.c b/drivers/scsi/mpt2sas/mpt2sas_transport.c index 410f4a3e8888..72f9c55d0e00 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_transport.c +++ b/drivers/scsi/mpt2sas/mpt2sas_transport.c @@ -1006,12 +1006,9 @@ mpt2sas_transport_update_links(struct MPT2SAS_ADAPTER *ioc, &mpt2sas_phy->remote_identify); _transport_add_phy_to_an_existing_port(ioc, sas_node, mpt2sas_phy, mpt2sas_phy->remote_identify.sas_address); - } else { + } else memset(&mpt2sas_phy->remote_identify, 0 , sizeof(struct sas_identify)); - _transport_del_phy_from_an_existing_port(ioc, sas_node, - mpt2sas_phy); - } if (mpt2sas_phy->phy) mpt2sas_phy->phy->negotiated_linkrate = diff --git a/drivers/scsi/mpt3sas/mpt3sas_transport.c b/drivers/scsi/mpt3sas/mpt3sas_transport.c index 65170cb1a00f..55aa597eb229 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_transport.c +++ b/drivers/scsi/mpt3sas/mpt3sas_transport.c @@ -1003,12 +1003,9 @@ mpt3sas_transport_update_links(struct MPT3SAS_ADAPTER *ioc, &mpt3sas_phy->remote_identify); _transport_add_phy_to_an_existing_port(ioc, sas_node, mpt3sas_phy, mpt3sas_phy->remote_identify.sas_address); - } else { + } else memset(&mpt3sas_phy->remote_identify, 0 , sizeof(struct sas_identify)); - _transport_del_phy_from_an_existing_port(ioc, sas_node, - mpt3sas_phy); - } if (mpt3sas_phy->phy) mpt3sas_phy->phy->negotiated_linkrate = diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 83cb61266979..23c1b0cd3074 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -3039,10 +3039,8 @@ qla2x00_unmap_iobases(struct qla_hw_data *ha) } static void -qla2x00_clear_drv_active(scsi_qla_host_t *vha) +qla2x00_clear_drv_active(struct qla_hw_data *ha) { - struct qla_hw_data *ha = vha->hw; - if (IS_QLA8044(ha)) { qla8044_idc_lock(ha); qla8044_clear_drv_active(ha); @@ -3111,7 +3109,7 @@ qla2x00_remove_one(struct pci_dev *pdev) scsi_host_put(base_vha->host); - qla2x00_clear_drv_active(base_vha); + qla2x00_clear_drv_active(ha); qla2x00_unmap_iobases(ha); diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 0cb73074c199..2f264ac79546 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1382,12 +1382,10 @@ static inline void qlt_unmap_sg(struct scsi_qla_host *vha, static int qlt_check_reserve_free_req(struct scsi_qla_host *vha, uint32_t req_cnt) { - struct qla_hw_data *ha = vha->hw; - device_reg_t __iomem *reg = ha->iobase; uint32_t cnt; if (vha->req->cnt < (req_cnt + 2)) { - cnt = (uint16_t)RD_REG_DWORD(®->isp24.req_q_out); + cnt = (uint16_t)RD_REG_DWORD(vha->req->req_q_out); ql_dbg(ql_dbg_tgt, vha, 0xe00a, "Request ring circled: cnt=%d, vha->->ring_index=%d, " diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index 788c4fe2b0c9..1817f3f2b02d 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -707,7 +707,16 @@ static void tcm_qla2xxx_clear_nacl_from_fcport_map(struct qla_tgt_sess *sess) pr_debug("fc_rport domain: port_id 0x%06x\n", nacl->nport_id); node = btree_remove32(&lport->lport_fcport_map, nacl->nport_id); - WARN_ON(node && (node != se_nacl)); + if (WARN_ON(node && (node != se_nacl))) { + /* + * The nacl no longer matches what we think it should be. + * Most likely a new dynamic acl has been added while + * someone dropped the hardware lock. It clearly is a + * bug elsewhere, but this bit can't make things worse. + */ + btree_insert32(&lport->lport_fcport_map, nacl->nport_id, + node, GFP_ATOMIC); + } pr_debug("Removed from fcport_map: %p for WWNN: 0x%016LX, port_id: 0x%06x\n", se_nacl, nacl->nport_wwnn, nacl->nport_id); @@ -1506,7 +1515,7 @@ static int tcm_qla2xxx_check_initiator_node_acl( /* * Finally register the new FC Nexus with TCM */ - __transport_register_session(se_nacl->se_tpg, se_nacl, se_sess, sess); + transport_register_session(se_nacl->se_tpg, se_nacl, se_sess, sess); return 0; } diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index 49014a143c6a..262ab837a704 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -202,6 +202,7 @@ static struct { {"IOMEGA", "Io20S *F", NULL, BLIST_KEY}, {"INSITE", "Floptical F*8I", NULL, BLIST_KEY}, {"INSITE", "I325VM", NULL, BLIST_KEY}, + {"Intel", "Multi-Flex", NULL, BLIST_NO_RSOC}, {"iRiver", "iFP Mass Driver", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36}, {"LASOUND", "CDX7405", "3.10", BLIST_MAX5LUN | BLIST_SINGLELUN}, {"MATSHITA", "PD-1", NULL, BLIST_FORCELUN | BLIST_SINGLELUN}, @@ -210,6 +211,7 @@ static struct { {"Medion", "Flash XL MMC/SD", "2.6D", BLIST_FORCELUN}, {"MegaRAID", "LD", NULL, BLIST_FORCELUN}, {"MICROP", "4110", NULL, BLIST_NOTQ}, + {"MSFT", "Virtual HD", NULL, BLIST_NO_RSOC}, {"MYLEX", "DACARMRB", "*", BLIST_REPORTLUN2}, {"nCipher", "Fastness Crypto", NULL, BLIST_FORCELUN}, {"NAKAMICH", "MJ-4.8S", NULL, BLIST_FORCELUN | BLIST_SINGLELUN}, diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index edb4d46fa874..96b6664bb1cf 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -1984,8 +1984,10 @@ static void scsi_restart_operations(struct Scsi_Host *shost) * is no point trying to lock the door of an off-line device. */ shost_for_each_device(sdev, shost) { - if (scsi_device_online(sdev) && sdev->locked) + if (scsi_device_online(sdev) && sdev->was_reset && sdev->locked) { scsi_eh_lock_door(sdev); + sdev->was_reset = 0; + } } /* diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 64e487a8bf59..719bd8257520 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1258,9 +1258,11 @@ int scsi_prep_state_check(struct scsi_device *sdev, struct request *req) "rejecting I/O to dead device\n"); ret = BLKPREP_KILL; break; - case SDEV_QUIESCE: case SDEV_BLOCK: case SDEV_CREATED_BLOCK: + ret = BLKPREP_DEFER; + break; + case SDEV_QUIESCE: /* * If the devices is blocked we defer normal commands. */ diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index df5e961484e1..eb81c98386b9 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -522,7 +522,7 @@ static ssize_t sg_new_read(Sg_fd * sfp, char __user *buf, size_t count, Sg_request * srp) { sg_io_hdr_t *hp = &srp->header; - int err = 0; + int err = 0, err2; int len; if (count < SZ_SG_IO_HDR) { @@ -551,8 +551,8 @@ sg_new_read(Sg_fd * sfp, char __user *buf, size_t count, Sg_request * srp) goto err_out; } err_out: - err = sg_finish_rem_req(srp); - return (0 == err) ? count : err; + err2 = sg_finish_rem_req(srp); + return err ? : err2 ? : count; } static ssize_t diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index ed0f899e8aa5..86b05151fdab 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1690,13 +1690,12 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) if (ret == -EAGAIN) { /* no more space */ - if (cmd_request->bounce_sgl_count) { + if (cmd_request->bounce_sgl_count) destroy_bounce_buffer(cmd_request->bounce_sgl, cmd_request->bounce_sgl_count); - ret = SCSI_MLQUEUE_DEVICE_BUSY; - goto queue_error; - } + ret = SCSI_MLQUEUE_DEVICE_BUSY; + goto queue_error; } return 0; diff --git a/drivers/scsi/sun3_NCR5380.c b/drivers/scsi/sun3_NCR5380.c index 636bbe0ea84c..fc57c8aec2b3 100644 --- a/drivers/scsi/sun3_NCR5380.c +++ b/drivers/scsi/sun3_NCR5380.c @@ -2597,15 +2597,15 @@ static void NCR5380_reselect (struct Scsi_Host *instance) * Purpose : abort a command * * Inputs : cmd - the struct scsi_cmnd to abort, code - code to set the - * host byte of the result field to, if zero DID_ABORTED is + * host byte of the result field to, if zero DID_ABORTED is * used. * - * Returns : 0 - success, -1 on failure. + * Returns : SUCCESS - success, FAILED on failure. * - * XXX - there is no way to abort the command that is currently - * connected, you have to wait for it to complete. If this is + * XXX - there is no way to abort the command that is currently + * connected, you have to wait for it to complete. If this is * a problem, we could implement longjmp() / setjmp(), setjmp() - * called where the loop started in NCR5380_main(). + * called where the loop started in NCR5380_main(). */ static int NCR5380_abort(struct scsi_cmnd *cmd) diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c index 5d7b07f08326..5f8c6d2f4df7 100644 --- a/drivers/spi/spi-atmel.c +++ b/drivers/spi/spi-atmel.c @@ -781,17 +781,17 @@ static void atmel_spi_pdc_next_xfer(struct spi_master *master, (unsigned long long)xfer->rx_dma); } - /* REVISIT: We're waiting for ENDRX before we start the next + /* REVISIT: We're waiting for RXBUFF before we start the next * transfer because we need to handle some difficult timing - * issues otherwise. If we wait for ENDTX in one transfer and - * then starts waiting for ENDRX in the next, it's difficult - * to tell the difference between the ENDRX interrupt we're - * actually waiting for and the ENDRX interrupt of the + * issues otherwise. If we wait for TXBUFE in one transfer and + * then starts waiting for RXBUFF in the next, it's difficult + * to tell the difference between the RXBUFF interrupt we're + * actually waiting for and the RXBUFF interrupt of the * previous transfer. * * It should be doable, though. Just not now... */ - spi_writel(as, IER, SPI_BIT(ENDRX) | SPI_BIT(OVRES)); + spi_writel(as, IER, SPI_BIT(RXBUFF) | SPI_BIT(OVRES)); spi_writel(as, PTCR, SPI_BIT(TXTEN) | SPI_BIT(RXTEN)); } diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c index 6d207afec8cb..996e16d12cd4 100644 --- a/drivers/spi/spi-dw-mid.c +++ b/drivers/spi/spi-dw-mid.c @@ -89,7 +89,13 @@ err_exit: static void mid_spi_dma_exit(struct dw_spi *dws) { + if (!dws->dma_inited) + return; + + dmaengine_terminate_all(dws->txchan); dma_release_channel(dws->txchan); + + dmaengine_terminate_all(dws->rxchan); dma_release_channel(dws->rxchan); } @@ -136,7 +142,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change) txconf.dst_addr = dws->dma_addr; txconf.dst_maxburst = LNW_DMA_MSIZE_16; txconf.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; - txconf.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES; + txconf.dst_addr_width = dws->dma_width; txconf.device_fc = false; txchan->device->device_control(txchan, DMA_SLAVE_CONFIG, @@ -159,7 +165,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change) rxconf.src_addr = dws->dma_addr; rxconf.src_maxburst = LNW_DMA_MSIZE_16; rxconf.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; - rxconf.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES; + rxconf.src_addr_width = dws->dma_width; rxconf.device_fc = false; rxchan->device->device_control(rxchan, DMA_SLAVE_CONFIG, @@ -216,7 +222,6 @@ int dw_spi_mid_init(struct dw_spi *dws) iounmap(clk_reg); dws->num_cs = 16; - dws->fifo_len = 40; /* FIFO has 40 words buffer */ #ifdef CONFIG_SPI_DW_MID_DMA dws->dma_priv = kzalloc(sizeof(struct mid_dma), GFP_KERNEL); diff --git a/drivers/spi/spi-dw-pci.c b/drivers/spi/spi-dw-pci.c index 3f3dc1226edf..e14960470d8d 100644 --- a/drivers/spi/spi-dw-pci.c +++ b/drivers/spi/spi-dw-pci.c @@ -62,6 +62,8 @@ static int spi_pci_probe(struct pci_dev *pdev, if (ret) return ret; + dws->regs = pcim_iomap_table(pdev)[pci_bar]; + dws->bus_num = 0; dws->num_cs = 4; dws->irq = pdev->irq; diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c index e63d27013142..e543b80d610e 100644 --- a/drivers/spi/spi-dw.c +++ b/drivers/spi/spi-dw.c @@ -394,9 +394,6 @@ static void pump_transfers(unsigned long data) chip = dws->cur_chip; spi = message->spi; - if (unlikely(!chip->clk_div)) - chip->clk_div = dws->max_freq / chip->speed_hz; - if (message->state == ERROR_STATE) { message->status = -EIO; goto early_exit; @@ -437,7 +434,7 @@ static void pump_transfers(unsigned long data) if (transfer->speed_hz) { speed = chip->speed_hz; - if (transfer->speed_hz != speed) { + if ((transfer->speed_hz != speed) || (!chip->clk_div)) { speed = transfer->speed_hz; if (speed > dws->max_freq) { printk(KERN_ERR "MRST SPI0: unsupported" @@ -659,7 +656,6 @@ static int dw_spi_setup(struct spi_device *spi) dev_err(&spi->dev, "No max speed HZ parameter\n"); return -EINVAL; } - chip->speed_hz = spi->max_speed_hz; chip->tmode = 0; /* Tx & Rx */ /* Default SPI mode is SCPOL = 0, SCPH = 0 */ diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index a25392065d9b..a5db6f930fa3 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -45,7 +45,7 @@ #define SPI_TCR 0x08 -#define SPI_CTAR(x) (0x0c + (x * 4)) +#define SPI_CTAR(x) (0x0c + (((x) & 0x3) * 4)) #define SPI_CTAR_FMSZ(x) (((x) & 0x0000000f) << 27) #define SPI_CTAR_CPOL(x) ((x) << 26) #define SPI_CTAR_CPHA(x) ((x) << 25) @@ -69,7 +69,7 @@ #define SPI_PUSHR 0x34 #define SPI_PUSHR_CONT (1 << 31) -#define SPI_PUSHR_CTAS(x) (((x) & 0x00000007) << 28) +#define SPI_PUSHR_CTAS(x) (((x) & 0x00000003) << 28) #define SPI_PUSHR_EOQ (1 << 27) #define SPI_PUSHR_CTCNT (1 << 26) #define SPI_PUSHR_PCS(x) (((1 << x) & 0x0000003f) << 16) diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c index 119f7af94537..4dcb2929c01f 100644 --- a/drivers/spi/spi-fsl-spi.c +++ b/drivers/spi/spi-fsl-spi.c @@ -362,18 +362,28 @@ static int fsl_spi_bufs(struct spi_device *spi, struct spi_transfer *t, static void fsl_spi_do_one_msg(struct spi_message *m) { struct spi_device *spi = m->spi; - struct spi_transfer *t; + struct spi_transfer *t, *first; unsigned int cs_change; const int nsecs = 50; int status; - cs_change = 1; - status = 0; + /* Don't allow changes if CS is active */ + first = list_first_entry(&m->transfers, struct spi_transfer, + transfer_list); list_for_each_entry(t, &m->transfers, transfer_list) { - if (t->bits_per_word || t->speed_hz) { - /* Don't allow changes if CS is active */ + if ((first->bits_per_word != t->bits_per_word) || + (first->speed_hz != t->speed_hz)) { status = -EINVAL; + dev_err(&spi->dev, + "bits_per_word/speed_hz should be same for the same SPI transfer\n"); + return; + } + } + cs_change = 1; + status = -EINVAL; + list_for_each_entry(t, &m->transfers, transfer_list) { + if (t->bits_per_word || t->speed_hz) { if (cs_change) status = fsl_spi_setup_transfer(spi, t); if (status < 0) diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c index a64f1557c156..b0059e7552b0 100644 --- a/drivers/spi/spi-omap2-mcspi.c +++ b/drivers/spi/spi-omap2-mcspi.c @@ -321,7 +321,8 @@ static void omap2_mcspi_set_fifo(const struct spi_device *spi, disable_fifo: if (t->rx_buf != NULL) chconf &= ~OMAP2_MCSPI_CHCONF_FFER; - else + + if (t->tx_buf != NULL) chconf &= ~OMAP2_MCSPI_CHCONF_FFET; mcspi_write_chconf0(spi, chconf); diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c index 2789b452e711..fe091a87fd6d 100644 --- a/drivers/spi/spi-pl022.c +++ b/drivers/spi/spi-pl022.c @@ -503,12 +503,12 @@ static void giveback(struct pl022 *pl022) pl022->cur_msg = NULL; pl022->cur_transfer = NULL; pl022->cur_chip = NULL; - spi_finalize_current_message(pl022->master); /* disable the SPI/SSP operation */ writew((readw(SSP_CR1(pl022->virtbase)) & (~SSP_CR1_MASK_SSE)), SSP_CR1(pl022->virtbase)); + spi_finalize_current_message(pl022->master); } /** @@ -1075,7 +1075,7 @@ err_rxdesc: pl022->sgt_tx.nents, DMA_TO_DEVICE); err_tx_sgmap: dma_unmap_sg(rxchan->device->dev, pl022->sgt_rx.sgl, - pl022->sgt_tx.nents, DMA_FROM_DEVICE); + pl022->sgt_rx.nents, DMA_FROM_DEVICE); err_rx_sgmap: sg_free_table(&pl022->sgt_tx); err_alloc_tx_sg: diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index ced9ecffa163..458a1480dc07 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -400,8 +400,8 @@ static void giveback(struct driver_data *drv_data) cs_deassert(drv_data); } - spi_finalize_current_message(drv_data->master); drv_data->cur_chip = NULL; + spi_finalize_current_message(drv_data->master); } static void reset_sccr1(struct driver_data *drv_data) @@ -1280,7 +1280,9 @@ static int pxa2xx_spi_suspend(struct device *dev) if (status != 0) return status; write_SSCR0(0, drv_data->ioaddr); - clk_disable_unprepare(ssp->clk); + + if (!pm_runtime_suspended(dev)) + clk_disable_unprepare(ssp->clk); return 0; } @@ -1294,7 +1296,8 @@ static int pxa2xx_spi_resume(struct device *dev) pxa2xx_spi_dma_resume(drv_data); /* Enable the SSP clock */ - clk_prepare_enable(ssp->clk); + if (!pm_runtime_suspended(dev)) + clk_prepare_enable(ssp->clk); /* Restore LPSS private register bits */ lpss_ssp_setup(drv_data); diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index fbf3b22efe5a..d6563ec700d4 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -846,13 +846,14 @@ void spi_finalize_current_message(struct spi_master *master) "failed to unprepare message: %d\n", ret); } } + + trace_spi_message_done(mesg); + master->cur_msg_prepared = false; mesg->state = NULL; if (mesg->complete) mesg->complete(mesg->context); - - trace_spi_message_done(mesg); } EXPORT_SYMBOL_GPL(spi_finalize_current_message); diff --git a/drivers/staging/comedi/comedi_compat32.c b/drivers/staging/comedi/comedi_compat32.c index 1e9da405d833..528781049ad5 100644 --- a/drivers/staging/comedi/comedi_compat32.c +++ b/drivers/staging/comedi/comedi_compat32.c @@ -262,7 +262,7 @@ static int compat_cmd(struct file *file, unsigned long arg) { struct comedi_cmd __user *cmd; struct comedi32_cmd_struct __user *cmd32; - int rc; + int rc, err; cmd32 = compat_ptr(arg); cmd = compat_alloc_user_space(sizeof(*cmd)); @@ -271,7 +271,15 @@ static int compat_cmd(struct file *file, unsigned long arg) if (rc) return rc; - return translated_ioctl(file, COMEDI_CMD, (unsigned long)cmd); + rc = translated_ioctl(file, COMEDI_CMD, (unsigned long)cmd); + if (rc == -EAGAIN) { + /* Special case: copy cmd back to user. */ + err = put_compat_cmd(cmd32, cmd); + if (err) + rc = err; + } + + return rc; } /* Handle 32-bit COMEDI_CMDTEST ioctl. */ diff --git a/drivers/staging/comedi/drivers/cb_pcidas64.c b/drivers/staging/comedi/drivers/cb_pcidas64.c index 4fff1738e3f8..3d1cb5b0a956 100644 --- a/drivers/staging/comedi/drivers/cb_pcidas64.c +++ b/drivers/staging/comedi/drivers/cb_pcidas64.c @@ -441,6 +441,29 @@ static const struct comedi_lrange ai_ranges_64xx = { } }; +static const uint8_t ai_range_code_64xx[8] = { + 0x0, 0x1, 0x2, 0x3, /* bipolar 10, 5, 2,5, 1.25 */ + 0x8, 0x9, 0xa, 0xb /* unipolar 10, 5, 2.5, 1.25 */ +}; + +/* analog input ranges for 64-Mx boards */ +static const struct comedi_lrange ai_ranges_64_mx = { + 7, { + BIP_RANGE(5), + BIP_RANGE(2.5), + BIP_RANGE(1.25), + BIP_RANGE(0.625), + UNI_RANGE(5), + UNI_RANGE(2.5), + UNI_RANGE(1.25) + } +}; + +static const uint8_t ai_range_code_64_mx[7] = { + 0x0, 0x1, 0x2, 0x3, /* bipolar 5, 2.5, 1.25, 0.625 */ + 0x9, 0xa, 0xb /* unipolar 5, 2.5, 1.25 */ +}; + /* analog input ranges for 60xx boards */ static const struct comedi_lrange ai_ranges_60xx = { 4, { @@ -451,6 +474,10 @@ static const struct comedi_lrange ai_ranges_60xx = { } }; +static const uint8_t ai_range_code_60xx[4] = { + 0x0, 0x1, 0x4, 0x7 /* bipolar 10, 5, 0.5, 0.05 */ +}; + /* analog input ranges for 6030, etc boards */ static const struct comedi_lrange ai_ranges_6030 = { 14, { @@ -471,6 +498,11 @@ static const struct comedi_lrange ai_ranges_6030 = { } }; +static const uint8_t ai_range_code_6030[14] = { + 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, /* bip 10, 5, 2, 1, 0.5, 0.2, 0.1 */ + 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf /* uni 10, 5, 2, 1, 0.5, 0.2, 0.1 */ +}; + /* analog input ranges for 6052, etc boards */ static const struct comedi_lrange ai_ranges_6052 = { 15, { @@ -492,6 +524,11 @@ static const struct comedi_lrange ai_ranges_6052 = { } }; +static const uint8_t ai_range_code_6052[15] = { + 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, /* bipolar 10 ... 0.05 */ + 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf /* unipolar 10 ... 0.1 */ +}; + /* analog input ranges for 4020 board */ static const struct comedi_lrange ai_ranges_4020 = { 2, { @@ -595,6 +632,7 @@ struct pcidas64_board { int ai_bits; /* analog input resolution */ int ai_speed; /* fastest conversion period in ns */ const struct comedi_lrange *ai_range_table; + const uint8_t *ai_range_code; int ao_nchan; /* number of analog out channels */ int ao_bits; /* analog output resolution */ int ao_scan_speed; /* analog output scan speed */ @@ -653,6 +691,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 10000, .layout = LAYOUT_64XX, .ai_range_table = &ai_ranges_64xx, + .ai_range_code = ai_range_code_64xx, .ao_range_table = &ao_ranges_64xx, .ao_range_code = ao_range_code_64xx, .ai_fifo = &ai_fifo_64xx, @@ -668,6 +707,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 10000, .layout = LAYOUT_64XX, .ai_range_table = &ai_ranges_64xx, + .ai_range_code = ai_range_code_64xx, .ao_range_table = &ao_ranges_64xx, .ao_range_code = ao_range_code_64xx, .ai_fifo = &ai_fifo_64xx, @@ -682,7 +722,8 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_bits = 16, .ao_scan_speed = 10000, .layout = LAYOUT_64XX, - .ai_range_table = &ai_ranges_64xx, + .ai_range_table = &ai_ranges_64_mx, + .ai_range_code = ai_range_code_64_mx, .ao_range_table = &ao_ranges_64xx, .ao_range_code = ao_range_code_64xx, .ai_fifo = &ai_fifo_64xx, @@ -697,7 +738,8 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_bits = 16, .ao_scan_speed = 10000, .layout = LAYOUT_64XX, - .ai_range_table = &ai_ranges_64xx, + .ai_range_table = &ai_ranges_64_mx, + .ai_range_code = ai_range_code_64_mx, .ao_range_table = &ao_ranges_64xx, .ao_range_code = ao_range_code_64xx, .ai_fifo = &ai_fifo_64xx, @@ -712,7 +754,8 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_bits = 16, .ao_scan_speed = 10000, .layout = LAYOUT_64XX, - .ai_range_table = &ai_ranges_64xx, + .ai_range_table = &ai_ranges_64_mx, + .ai_range_code = ai_range_code_64_mx, .ao_range_table = &ao_ranges_64xx, .ao_range_code = ao_range_code_64xx, .ai_fifo = &ai_fifo_64xx, @@ -727,6 +770,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_bits = 16, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_60xx, + .ai_range_code = ai_range_code_60xx, .ao_range_table = &range_bipolar10, .ao_range_code = ao_range_code_60xx, .ai_fifo = &ai_fifo_60xx, @@ -742,6 +786,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 100000, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_60xx, + .ai_range_code = ai_range_code_60xx, .ao_range_table = &range_bipolar10, .ao_range_code = ao_range_code_60xx, .ai_fifo = &ai_fifo_60xx, @@ -756,6 +801,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 100000, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_60xx, + .ai_range_code = ai_range_code_60xx, .ao_range_table = &range_bipolar10, .ao_range_code = ao_range_code_60xx, .ai_fifo = &ai_fifo_60xx, @@ -771,6 +817,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 100000, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_60xx, + .ai_range_code = ai_range_code_60xx, .ao_range_table = &range_bipolar10, .ao_range_code = ao_range_code_60xx, .ai_fifo = &ai_fifo_60xx, @@ -786,6 +833,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 10000, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_6030, + .ai_range_code = ai_range_code_6030, .ao_range_table = &ao_ranges_6030, .ao_range_code = ao_range_code_6030, .ai_fifo = &ai_fifo_60xx, @@ -801,6 +849,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 10000, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_6030, + .ai_range_code = ai_range_code_6030, .ao_range_table = &ao_ranges_6030, .ao_range_code = ao_range_code_6030, .ai_fifo = &ai_fifo_60xx, @@ -814,6 +863,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_nchan = 0, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_6030, + .ai_range_code = ai_range_code_6030, .ai_fifo = &ai_fifo_60xx, .has_8255 = 0, }, @@ -825,6 +875,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_nchan = 0, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_6030, + .ai_range_code = ai_range_code_6030, .ai_fifo = &ai_fifo_60xx, .has_8255 = 0, }, @@ -837,6 +888,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 0, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_60xx, + .ai_range_code = ai_range_code_60xx, .ai_fifo = &ai_fifo_60xx, .has_8255 = 0, }, @@ -850,6 +902,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 100000, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_60xx, + .ai_range_code = ai_range_code_60xx, .ao_range_table = &range_bipolar10, .ao_range_code = ao_range_code_60xx, .ai_fifo = &ai_fifo_60xx, @@ -865,6 +918,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 100000, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_60xx, + .ai_range_code = ai_range_code_60xx, .ao_range_table = &range_bipolar10, .ao_range_code = ao_range_code_60xx, .ai_fifo = &ai_fifo_60xx, @@ -880,6 +934,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 1000, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_6052, + .ai_range_code = ai_range_code_6052, .ao_range_table = &ao_ranges_6030, .ao_range_code = ao_range_code_6030, .ai_fifo = &ai_fifo_60xx, @@ -895,6 +950,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 3333, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_6052, + .ai_range_code = ai_range_code_6052, .ao_range_table = &ao_ranges_6030, .ao_range_code = ao_range_code_6030, .ai_fifo = &ai_fifo_60xx, @@ -910,6 +966,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 1000, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_6052, + .ai_range_code = ai_range_code_6052, .ao_range_table = &ao_ranges_6030, .ao_range_code = ao_range_code_6030, .ai_fifo = &ai_fifo_60xx, @@ -925,6 +982,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 1000, .layout = LAYOUT_60XX, .ai_range_table = &ai_ranges_6052, + .ai_range_code = ai_range_code_6052, .ao_range_table = &ao_ranges_6030, .ao_range_code = ao_range_code_6030, .ai_fifo = &ai_fifo_60xx, @@ -959,6 +1017,7 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_scan_speed = 10000, .layout = LAYOUT_64XX, .ai_range_table = &ai_ranges_64xx, + .ai_range_code = ai_range_code_64xx, .ai_fifo = ai_fifo_64xx, .has_8255 = 1, }, @@ -970,7 +1029,8 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_nchan = 0, .ao_scan_speed = 10000, .layout = LAYOUT_64XX, - .ai_range_table = &ai_ranges_64xx, + .ai_range_table = &ai_ranges_64_mx, + .ai_range_code = ai_range_code_64_mx, .ai_fifo = ai_fifo_64xx, .has_8255 = 1, }, @@ -982,7 +1042,8 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_nchan = 0, .ao_scan_speed = 10000, .layout = LAYOUT_64XX, - .ai_range_table = &ai_ranges_64xx, + .ai_range_table = &ai_ranges_64_mx, + .ai_range_code = ai_range_code_64_mx, .ai_fifo = ai_fifo_64xx, .has_8255 = 1, }, @@ -994,7 +1055,8 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_nchan = 0, .ao_scan_speed = 10000, .layout = LAYOUT_64XX, - .ai_range_table = &ai_ranges_64xx, + .ai_range_table = &ai_ranges_64_mx, + .ai_range_code = ai_range_code_64_mx, .ai_fifo = ai_fifo_64xx, .has_8255 = 1, }, @@ -1006,7 +1068,8 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_nchan = 2, .ao_scan_speed = 10000, .layout = LAYOUT_64XX, - .ai_range_table = &ai_ranges_64xx, + .ai_range_table = &ai_ranges_64_mx, + .ai_range_code = ai_range_code_64_mx, .ai_fifo = ai_fifo_64xx, .has_8255 = 1, }, @@ -1018,7 +1081,8 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_nchan = 2, .ao_scan_speed = 10000, .layout = LAYOUT_64XX, - .ai_range_table = &ai_ranges_64xx, + .ai_range_table = &ai_ranges_64_mx, + .ai_range_code = ai_range_code_64_mx, .ai_fifo = ai_fifo_64xx, .has_8255 = 1, }, @@ -1030,7 +1094,8 @@ static const struct pcidas64_board pcidas64_boards[] = { .ao_nchan = 2, .ao_scan_speed = 10000, .layout = LAYOUT_64XX, - .ai_range_table = &ai_ranges_64xx, + .ai_range_table = &ai_ranges_64_mx, + .ai_range_code = ai_range_code_64_mx, .ai_fifo = ai_fifo_64xx, .has_8255 = 1, }, @@ -1127,45 +1192,8 @@ static unsigned int ai_range_bits_6xxx(const struct comedi_device *dev, unsigned int range_index) { const struct pcidas64_board *thisboard = comedi_board(dev); - const struct comedi_krange *range = - &thisboard->ai_range_table->range[range_index]; - unsigned int bits = 0; - switch (range->max) { - case 10000000: - bits = 0x000; - break; - case 5000000: - bits = 0x100; - break; - case 2000000: - case 2500000: - bits = 0x200; - break; - case 1000000: - case 1250000: - bits = 0x300; - break; - case 500000: - bits = 0x400; - break; - case 200000: - case 250000: - bits = 0x500; - break; - case 100000: - bits = 0x600; - break; - case 50000: - bits = 0x700; - break; - default: - comedi_error(dev, "bug! in ai_range_bits_6xxx"); - break; - } - if (range->min == 0) - bits += 0x900; - return bits; + return thisboard->ai_range_code[range_index] << 8; } static unsigned int hw_revision(const struct comedi_device *dev, diff --git a/drivers/staging/iio/adc/mxs-lradc.c b/drivers/staging/iio/adc/mxs-lradc.c index 9ec1df9cff95..27e1a6e62d06 100644 --- a/drivers/staging/iio/adc/mxs-lradc.c +++ b/drivers/staging/iio/adc/mxs-lradc.c @@ -214,11 +214,17 @@ struct mxs_lradc { unsigned long is_divided; /* - * Touchscreen LRADC channels receives a private slot in the CTRL4 - * register, the slot #7. Therefore only 7 slots instead of 8 in the - * CTRL4 register can be mapped to LRADC channels when using the - * touchscreen. - * + * When the touchscreen is enabled, we give it two private virtual + * channels: #6 and #7. This means that only 6 virtual channels (instead + * of 8) will be available for buffered capture. + */ +#define TOUCHSCREEN_VCHANNEL1 7 +#define TOUCHSCREEN_VCHANNEL2 6 +#define BUFFER_VCHANS_LIMITED 0x3f +#define BUFFER_VCHANS_ALL 0xff + u8 buffer_vchans; + + /* * Furthermore, certain LRADC channels are shared between touchscreen * and/or touch-buttons and generic LRADC block. Therefore when using * either of these, these channels are not available for the regular @@ -342,6 +348,9 @@ struct mxs_lradc { #define LRADC_CTRL4 0x140 #define LRADC_CTRL4_LRADCSELECT_MASK(n) (0xf << ((n) * 4)) #define LRADC_CTRL4_LRADCSELECT_OFFSET(n) ((n) * 4) +#define LRADC_CTRL4_LRADCSELECT(n, x) \ + (((x) << LRADC_CTRL4_LRADCSELECT_OFFSET(n)) & \ + LRADC_CTRL4_LRADCSELECT_MASK(n)) #define LRADC_RESOLUTION 12 #define LRADC_SINGLE_SAMPLE_MASK ((1 << LRADC_RESOLUTION) - 1) @@ -423,6 +432,14 @@ static bool mxs_lradc_check_touch_event(struct mxs_lradc *lradc) LRADC_STATUS_TOUCH_DETECT_RAW); } +static void mxs_lradc_map_channel(struct mxs_lradc *lradc, unsigned vch, + unsigned ch) +{ + mxs_lradc_reg_clear(lradc, LRADC_CTRL4_LRADCSELECT_MASK(vch), + LRADC_CTRL4); + mxs_lradc_reg_set(lradc, LRADC_CTRL4_LRADCSELECT(vch, ch), LRADC_CTRL4); +} + static void mxs_lradc_setup_ts_channel(struct mxs_lradc *lradc, unsigned ch) { /* @@ -450,12 +467,8 @@ static void mxs_lradc_setup_ts_channel(struct mxs_lradc *lradc, unsigned ch) LRADC_DELAY_DELAY(lradc->over_sample_delay - 1), LRADC_DELAY(3)); - mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ(2) | - LRADC_CTRL1_LRADC_IRQ(3) | LRADC_CTRL1_LRADC_IRQ(4) | - LRADC_CTRL1_LRADC_IRQ(5), LRADC_CTRL1); + mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ(ch), LRADC_CTRL1); - /* wake us again, when the complete conversion is done */ - mxs_lradc_reg_set(lradc, LRADC_CTRL1_LRADC_IRQ_EN(ch), LRADC_CTRL1); /* * after changing the touchscreen plates setting * the signals need some initial time to settle. Start the @@ -508,12 +521,8 @@ static void mxs_lradc_setup_ts_pressure(struct mxs_lradc *lradc, unsigned ch1, LRADC_DELAY_DELAY(lradc->over_sample_delay - 1), LRADC_DELAY(3)); - mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ(2) | - LRADC_CTRL1_LRADC_IRQ(3) | LRADC_CTRL1_LRADC_IRQ(4) | - LRADC_CTRL1_LRADC_IRQ(5), LRADC_CTRL1); + mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ(ch2), LRADC_CTRL1); - /* wake us again, when the conversions are done */ - mxs_lradc_reg_set(lradc, LRADC_CTRL1_LRADC_IRQ_EN(ch2), LRADC_CTRL1); /* * after changing the touchscreen plates setting * the signals need some initial time to settle. Start the @@ -578,36 +587,6 @@ static unsigned mxs_lradc_read_ts_pressure(struct mxs_lradc *lradc, #define TS_CH_XM 4 #define TS_CH_YM 5 -static int mxs_lradc_read_ts_channel(struct mxs_lradc *lradc) -{ - u32 reg; - int val; - - reg = readl(lradc->base + LRADC_CTRL1); - - /* only channels 3 to 5 are of interest here */ - if (reg & LRADC_CTRL1_LRADC_IRQ(TS_CH_YP)) { - mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ_EN(TS_CH_YP) | - LRADC_CTRL1_LRADC_IRQ(TS_CH_YP), LRADC_CTRL1); - val = mxs_lradc_read_raw_channel(lradc, TS_CH_YP); - } else if (reg & LRADC_CTRL1_LRADC_IRQ(TS_CH_XM)) { - mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ_EN(TS_CH_XM) | - LRADC_CTRL1_LRADC_IRQ(TS_CH_XM), LRADC_CTRL1); - val = mxs_lradc_read_raw_channel(lradc, TS_CH_XM); - } else if (reg & LRADC_CTRL1_LRADC_IRQ(TS_CH_YM)) { - mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ_EN(TS_CH_YM) | - LRADC_CTRL1_LRADC_IRQ(TS_CH_YM), LRADC_CTRL1); - val = mxs_lradc_read_raw_channel(lradc, TS_CH_YM); - } else { - return -EIO; - } - - mxs_lradc_reg_wrt(lradc, 0, LRADC_DELAY(2)); - mxs_lradc_reg_wrt(lradc, 0, LRADC_DELAY(3)); - - return val; -} - /* * YP(open)--+-------------+ * | |--+ @@ -651,7 +630,8 @@ static void mxs_lradc_prepare_x_pos(struct mxs_lradc *lradc) mxs_lradc_reg_set(lradc, mxs_lradc_drive_x_plate(lradc), LRADC_CTRL0); lradc->cur_plate = LRADC_SAMPLE_X; - mxs_lradc_setup_ts_channel(lradc, TS_CH_YP); + mxs_lradc_map_channel(lradc, TOUCHSCREEN_VCHANNEL1, TS_CH_YP); + mxs_lradc_setup_ts_channel(lradc, TOUCHSCREEN_VCHANNEL1); } /* @@ -672,7 +652,8 @@ static void mxs_lradc_prepare_y_pos(struct mxs_lradc *lradc) mxs_lradc_reg_set(lradc, mxs_lradc_drive_y_plate(lradc), LRADC_CTRL0); lradc->cur_plate = LRADC_SAMPLE_Y; - mxs_lradc_setup_ts_channel(lradc, TS_CH_XM); + mxs_lradc_map_channel(lradc, TOUCHSCREEN_VCHANNEL1, TS_CH_XM); + mxs_lradc_setup_ts_channel(lradc, TOUCHSCREEN_VCHANNEL1); } /* @@ -693,7 +674,10 @@ static void mxs_lradc_prepare_pressure(struct mxs_lradc *lradc) mxs_lradc_reg_set(lradc, mxs_lradc_drive_pressure(lradc), LRADC_CTRL0); lradc->cur_plate = LRADC_SAMPLE_PRESSURE; - mxs_lradc_setup_ts_pressure(lradc, TS_CH_XP, TS_CH_YM); + mxs_lradc_map_channel(lradc, TOUCHSCREEN_VCHANNEL1, TS_CH_YM); + mxs_lradc_map_channel(lradc, TOUCHSCREEN_VCHANNEL2, TS_CH_XP); + mxs_lradc_setup_ts_pressure(lradc, TOUCHSCREEN_VCHANNEL2, + TOUCHSCREEN_VCHANNEL1); } static void mxs_lradc_enable_touch_detection(struct mxs_lradc *lradc) @@ -706,6 +690,19 @@ static void mxs_lradc_enable_touch_detection(struct mxs_lradc *lradc) mxs_lradc_reg_set(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ_EN, LRADC_CTRL1); } +static void mxs_lradc_start_touch_event(struct mxs_lradc *lradc) +{ + mxs_lradc_reg_clear(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ_EN, + LRADC_CTRL1); + mxs_lradc_reg_set(lradc, + LRADC_CTRL1_LRADC_IRQ_EN(TOUCHSCREEN_VCHANNEL1), LRADC_CTRL1); + /* + * start with the Y-pos, because it uses nearly the same plate + * settings like the touch detection + */ + mxs_lradc_prepare_y_pos(lradc); +} + static void mxs_lradc_report_ts_event(struct mxs_lradc *lradc) { input_report_abs(lradc->ts_input, ABS_X, lradc->ts_x_pos); @@ -723,10 +720,12 @@ static void mxs_lradc_complete_touch_event(struct mxs_lradc *lradc) * start a dummy conversion to burn time to settle the signals * note: we are not interested in the conversion's value */ - mxs_lradc_reg_wrt(lradc, 0, LRADC_CH(5)); - mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ(5), LRADC_CTRL1); - mxs_lradc_reg_set(lradc, LRADC_CTRL1_LRADC_IRQ_EN(5), LRADC_CTRL1); - mxs_lradc_reg_wrt(lradc, LRADC_DELAY_TRIGGER(1 << 5) | + mxs_lradc_reg_wrt(lradc, 0, LRADC_CH(TOUCHSCREEN_VCHANNEL1)); + mxs_lradc_reg_clear(lradc, + LRADC_CTRL1_LRADC_IRQ(TOUCHSCREEN_VCHANNEL1) | + LRADC_CTRL1_LRADC_IRQ(TOUCHSCREEN_VCHANNEL2), LRADC_CTRL1); + mxs_lradc_reg_wrt(lradc, + LRADC_DELAY_TRIGGER(1 << TOUCHSCREEN_VCHANNEL1) | LRADC_DELAY_KICK | LRADC_DELAY_DELAY(10), /* waste 5 ms */ LRADC_DELAY(2)); } @@ -758,59 +757,45 @@ static void mxs_lradc_finish_touch_event(struct mxs_lradc *lradc, bool valid) /* if it is released, wait for the next touch via IRQ */ lradc->cur_plate = LRADC_TOUCH; - mxs_lradc_reg_clear(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ, LRADC_CTRL1); + mxs_lradc_reg_wrt(lradc, 0, LRADC_DELAY(2)); + mxs_lradc_reg_wrt(lradc, 0, LRADC_DELAY(3)); + mxs_lradc_reg_clear(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ | + LRADC_CTRL1_LRADC_IRQ_EN(TOUCHSCREEN_VCHANNEL1) | + LRADC_CTRL1_LRADC_IRQ(TOUCHSCREEN_VCHANNEL1), LRADC_CTRL1); mxs_lradc_reg_set(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ_EN, LRADC_CTRL1); } /* touchscreen's state machine */ static void mxs_lradc_handle_touch(struct mxs_lradc *lradc) { - int val; - switch (lradc->cur_plate) { case LRADC_TOUCH: - /* - * start with the Y-pos, because it uses nearly the same plate - * settings like the touch detection - */ - if (mxs_lradc_check_touch_event(lradc)) { - mxs_lradc_reg_clear(lradc, - LRADC_CTRL1_TOUCH_DETECT_IRQ_EN, - LRADC_CTRL1); - mxs_lradc_prepare_y_pos(lradc); - } + if (mxs_lradc_check_touch_event(lradc)) + mxs_lradc_start_touch_event(lradc); mxs_lradc_reg_clear(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ, LRADC_CTRL1); return; case LRADC_SAMPLE_Y: - val = mxs_lradc_read_ts_channel(lradc); - if (val < 0) { - mxs_lradc_enable_touch_detection(lradc); /* re-start */ - return; - } - lradc->ts_y_pos = val; + lradc->ts_y_pos = mxs_lradc_read_raw_channel(lradc, + TOUCHSCREEN_VCHANNEL1); mxs_lradc_prepare_x_pos(lradc); return; case LRADC_SAMPLE_X: - val = mxs_lradc_read_ts_channel(lradc); - if (val < 0) { - mxs_lradc_enable_touch_detection(lradc); /* re-start */ - return; - } - lradc->ts_x_pos = val; + lradc->ts_x_pos = mxs_lradc_read_raw_channel(lradc, + TOUCHSCREEN_VCHANNEL1); mxs_lradc_prepare_pressure(lradc); return; case LRADC_SAMPLE_PRESSURE: - lradc->ts_pressure = - mxs_lradc_read_ts_pressure(lradc, TS_CH_XP, TS_CH_YM); + lradc->ts_pressure = mxs_lradc_read_ts_pressure(lradc, + TOUCHSCREEN_VCHANNEL2, + TOUCHSCREEN_VCHANNEL1); mxs_lradc_complete_touch_event(lradc); return; case LRADC_SAMPLE_VALID: - val = mxs_lradc_read_ts_channel(lradc); /* ignore the value */ mxs_lradc_finish_touch_event(lradc, 1); break; } @@ -842,9 +827,9 @@ static int mxs_lradc_read_single(struct iio_dev *iio_dev, int chan, int *val) * used if doing raw sampling. */ if (lradc->soc == IMX28_LRADC) - mxs_lradc_reg_clear(lradc, LRADC_CTRL1_MX28_LRADC_IRQ_EN_MASK, + mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ_EN(0), LRADC_CTRL1); - mxs_lradc_reg_clear(lradc, 0xff, LRADC_CTRL0); + mxs_lradc_reg_clear(lradc, 0x1, LRADC_CTRL0); /* Enable / disable the divider per requirement */ if (test_bit(chan, &lradc->is_divided)) @@ -1091,9 +1076,8 @@ static void mxs_lradc_disable_ts(struct mxs_lradc *lradc) { /* stop all interrupts from firing */ mxs_lradc_reg_clear(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ_EN | - LRADC_CTRL1_LRADC_IRQ_EN(2) | LRADC_CTRL1_LRADC_IRQ_EN(3) | - LRADC_CTRL1_LRADC_IRQ_EN(4) | LRADC_CTRL1_LRADC_IRQ_EN(5), - LRADC_CTRL1); + LRADC_CTRL1_LRADC_IRQ_EN(TOUCHSCREEN_VCHANNEL1) | + LRADC_CTRL1_LRADC_IRQ_EN(TOUCHSCREEN_VCHANNEL2), LRADC_CTRL1); /* Power-down touchscreen touch-detect circuitry. */ mxs_lradc_reg_clear(lradc, mxs_lradc_plate_mask(lradc), LRADC_CTRL0); @@ -1159,25 +1143,30 @@ static irqreturn_t mxs_lradc_handle_irq(int irq, void *data) struct iio_dev *iio = data; struct mxs_lradc *lradc = iio_priv(iio); unsigned long reg = readl(lradc->base + LRADC_CTRL1); + uint32_t clr_irq = mxs_lradc_irq_mask(lradc); const uint32_t ts_irq_mask = LRADC_CTRL1_TOUCH_DETECT_IRQ | - LRADC_CTRL1_LRADC_IRQ(2) | - LRADC_CTRL1_LRADC_IRQ(3) | - LRADC_CTRL1_LRADC_IRQ(4) | - LRADC_CTRL1_LRADC_IRQ(5); + LRADC_CTRL1_LRADC_IRQ(TOUCHSCREEN_VCHANNEL1) | + LRADC_CTRL1_LRADC_IRQ(TOUCHSCREEN_VCHANNEL2); if (!(reg & mxs_lradc_irq_mask(lradc))) return IRQ_NONE; - if (lradc->use_touchscreen && (reg & ts_irq_mask)) + if (lradc->use_touchscreen && (reg & ts_irq_mask)) { mxs_lradc_handle_touch(lradc); + /* Make sure we don't clear the next conversion's interrupt. */ + clr_irq &= ~(LRADC_CTRL1_LRADC_IRQ(TOUCHSCREEN_VCHANNEL1) | + LRADC_CTRL1_LRADC_IRQ(TOUCHSCREEN_VCHANNEL2)); + } - if (iio_buffer_enabled(iio)) - iio_trigger_poll(iio->trig, iio_get_time_ns()); - else if (reg & LRADC_CTRL1_LRADC_IRQ(0)) + if (iio_buffer_enabled(iio)) { + if (reg & lradc->buffer_vchans) + iio_trigger_poll(iio->trig, iio_get_time_ns()); + } else if (reg & LRADC_CTRL1_LRADC_IRQ(0)) { complete(&lradc->completion); + } - mxs_lradc_reg_clear(lradc, reg & mxs_lradc_irq_mask(lradc), LRADC_CTRL1); + mxs_lradc_reg_clear(lradc, reg & clr_irq, LRADC_CTRL1); return IRQ_HANDLED; } @@ -1288,9 +1277,10 @@ static int mxs_lradc_buffer_preenable(struct iio_dev *iio) } if (lradc->soc == IMX28_LRADC) - mxs_lradc_reg_clear(lradc, LRADC_CTRL1_MX28_LRADC_IRQ_EN_MASK, - LRADC_CTRL1); - mxs_lradc_reg_clear(lradc, 0xff, LRADC_CTRL0); + mxs_lradc_reg_clear(lradc, + lradc->buffer_vchans << LRADC_CTRL1_LRADC_IRQ_EN_OFFSET, + LRADC_CTRL1); + mxs_lradc_reg_clear(lradc, lradc->buffer_vchans, LRADC_CTRL0); for_each_set_bit(chan, iio->active_scan_mask, LRADC_MAX_TOTAL_CHANS) { ctrl4_set |= chan << LRADC_CTRL4_LRADCSELECT_OFFSET(ofs); @@ -1323,10 +1313,11 @@ static int mxs_lradc_buffer_postdisable(struct iio_dev *iio) mxs_lradc_reg_clear(lradc, LRADC_DELAY_TRIGGER_LRADCS_MASK | LRADC_DELAY_KICK, LRADC_DELAY(0)); - mxs_lradc_reg_clear(lradc, 0xff, LRADC_CTRL0); + mxs_lradc_reg_clear(lradc, lradc->buffer_vchans, LRADC_CTRL0); if (lradc->soc == IMX28_LRADC) - mxs_lradc_reg_clear(lradc, LRADC_CTRL1_MX28_LRADC_IRQ_EN_MASK, - LRADC_CTRL1); + mxs_lradc_reg_clear(lradc, + lradc->buffer_vchans << LRADC_CTRL1_LRADC_IRQ_EN_OFFSET, + LRADC_CTRL1); kfree(lradc->buffer); mutex_unlock(&lradc->lock); @@ -1352,7 +1343,7 @@ static bool mxs_lradc_validate_scan_mask(struct iio_dev *iio, if (lradc->use_touchbutton) rsvd_chans++; if (lradc->use_touchscreen) - rsvd_chans++; + rsvd_chans += 2; /* Test for attempts to map channels with special mode of operation. */ if (bitmap_intersects(mask, &rsvd_mask, LRADC_MAX_TOTAL_CHANS)) @@ -1412,6 +1403,13 @@ static const struct iio_chan_spec mxs_lradc_chan_spec[] = { .channel = 8, .scan_type = {.sign = 'u', .realbits = 18, .storagebits = 32,}, }, + /* Hidden channel to keep indexes */ + { + .type = IIO_TEMP, + .indexed = 1, + .scan_index = -1, + .channel = 9, + }, MXS_ADC_CHAN(10, IIO_VOLTAGE), /* VDDIO */ MXS_ADC_CHAN(11, IIO_VOLTAGE), /* VTH */ MXS_ADC_CHAN(12, IIO_VOLTAGE), /* VDDA */ @@ -1563,6 +1561,11 @@ static int mxs_lradc_probe(struct platform_device *pdev) touch_ret = mxs_lradc_probe_touchscreen(lradc, node); + if (touch_ret == 0) + lradc->buffer_vchans = BUFFER_VCHANS_LIMITED; + else + lradc->buffer_vchans = BUFFER_VCHANS_ALL; + /* Grab all IRQ sources */ for (i = 0; i < of_cfg->irq_count; i++) { lradc->irq[i] = platform_get_irq(pdev, i); diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c index 2b96665da8a2..97d4b3fb7e95 100644 --- a/drivers/staging/iio/impedance-analyzer/ad5933.c +++ b/drivers/staging/iio/impedance-analyzer/ad5933.c @@ -115,6 +115,7 @@ static const struct iio_chan_spec ad5933_channels[] = { .channel = 0, .info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED), .address = AD5933_REG_TEMP_DATA, + .scan_index = -1, .scan_type = { .sign = 's', .realbits = 14, @@ -124,9 +125,7 @@ static const struct iio_chan_spec ad5933_channels[] = { .type = IIO_VOLTAGE, .indexed = 1, .channel = 0, - .extend_name = "real_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | - BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "real", .address = AD5933_REG_REAL_DATA, .scan_index = 0, .scan_type = { @@ -138,9 +137,7 @@ static const struct iio_chan_spec ad5933_channels[] = { .type = IIO_VOLTAGE, .indexed = 1, .channel = 0, - .extend_name = "imag_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | - BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "imag", .address = AD5933_REG_IMAG_DATA, .scan_index = 1, .scan_type = { @@ -748,14 +745,14 @@ static int ad5933_probe(struct i2c_client *client, indio_dev->name = id->name; indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->channels = ad5933_channels; - indio_dev->num_channels = 1; /* only register temp0_input */ + indio_dev->num_channels = ARRAY_SIZE(ad5933_channels); ret = ad5933_register_ring_funcs_and_init(indio_dev); if (ret) goto error_disable_reg; - /* skip temp0_input, register in0_(real|imag)_raw */ - ret = iio_buffer_register(indio_dev, &ad5933_channels[1], 2); + ret = iio_buffer_register(indio_dev, ad5933_channels, + ARRAY_SIZE(ad5933_channels)); if (ret) goto error_unreg_ring; diff --git a/drivers/staging/iio/meter/ade7758.h b/drivers/staging/iio/meter/ade7758.h index 07318203a836..e8c98cf57070 100644 --- a/drivers/staging/iio/meter/ade7758.h +++ b/drivers/staging/iio/meter/ade7758.h @@ -119,7 +119,6 @@ struct ade7758_state { u8 *tx; u8 *rx; struct mutex buf_lock; - const struct iio_chan_spec *ade7758_ring_channels; struct spi_transfer ring_xfer[4]; struct spi_message ring_msg; /* diff --git a/drivers/staging/iio/meter/ade7758_core.c b/drivers/staging/iio/meter/ade7758_core.c index cba183e24838..94d9914a602c 100644 --- a/drivers/staging/iio/meter/ade7758_core.c +++ b/drivers/staging/iio/meter/ade7758_core.c @@ -630,9 +630,6 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_VOLTAGE, .indexed = 1, .channel = 0, - .extend_name = "raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .address = AD7758_WT(AD7758_PHASE_A, AD7758_VOLTAGE), .scan_index = 0, .scan_type = { @@ -644,9 +641,6 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_CURRENT, .indexed = 1, .channel = 0, - .extend_name = "raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .address = AD7758_WT(AD7758_PHASE_A, AD7758_CURRENT), .scan_index = 1, .scan_type = { @@ -658,9 +652,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 0, - .extend_name = "apparent_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "apparent", .address = AD7758_WT(AD7758_PHASE_A, AD7758_APP_PWR), .scan_index = 2, .scan_type = { @@ -672,9 +664,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 0, - .extend_name = "active_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "active", .address = AD7758_WT(AD7758_PHASE_A, AD7758_ACT_PWR), .scan_index = 3, .scan_type = { @@ -686,9 +676,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 0, - .extend_name = "reactive_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "reactive", .address = AD7758_WT(AD7758_PHASE_A, AD7758_REACT_PWR), .scan_index = 4, .scan_type = { @@ -700,9 +688,6 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_VOLTAGE, .indexed = 1, .channel = 1, - .extend_name = "raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .address = AD7758_WT(AD7758_PHASE_B, AD7758_VOLTAGE), .scan_index = 5, .scan_type = { @@ -714,9 +699,6 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_CURRENT, .indexed = 1, .channel = 1, - .extend_name = "raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .address = AD7758_WT(AD7758_PHASE_B, AD7758_CURRENT), .scan_index = 6, .scan_type = { @@ -728,9 +710,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 1, - .extend_name = "apparent_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "apparent", .address = AD7758_WT(AD7758_PHASE_B, AD7758_APP_PWR), .scan_index = 7, .scan_type = { @@ -742,9 +722,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 1, - .extend_name = "active_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "active", .address = AD7758_WT(AD7758_PHASE_B, AD7758_ACT_PWR), .scan_index = 8, .scan_type = { @@ -756,9 +734,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 1, - .extend_name = "reactive_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "reactive", .address = AD7758_WT(AD7758_PHASE_B, AD7758_REACT_PWR), .scan_index = 9, .scan_type = { @@ -770,9 +746,6 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_VOLTAGE, .indexed = 1, .channel = 2, - .extend_name = "raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .address = AD7758_WT(AD7758_PHASE_C, AD7758_VOLTAGE), .scan_index = 10, .scan_type = { @@ -784,9 +757,6 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_CURRENT, .indexed = 1, .channel = 2, - .extend_name = "raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .address = AD7758_WT(AD7758_PHASE_C, AD7758_CURRENT), .scan_index = 11, .scan_type = { @@ -798,9 +768,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 2, - .extend_name = "apparent_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "apparent", .address = AD7758_WT(AD7758_PHASE_C, AD7758_APP_PWR), .scan_index = 12, .scan_type = { @@ -812,9 +780,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 2, - .extend_name = "active_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "active", .address = AD7758_WT(AD7758_PHASE_C, AD7758_ACT_PWR), .scan_index = 13, .scan_type = { @@ -826,9 +792,7 @@ static const struct iio_chan_spec ade7758_channels[] = { .type = IIO_POWER, .indexed = 1, .channel = 2, - .extend_name = "reactive_raw", - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), + .extend_name = "reactive", .address = AD7758_WT(AD7758_PHASE_C, AD7758_REACT_PWR), .scan_index = 14, .scan_type = { @@ -869,13 +833,14 @@ static int ade7758_probe(struct spi_device *spi) goto error_free_rx; } st->us = spi; - st->ade7758_ring_channels = &ade7758_channels[0]; mutex_init(&st->buf_lock); indio_dev->name = spi->dev.driver->name; indio_dev->dev.parent = &spi->dev; indio_dev->info = &ade7758_info; indio_dev->modes = INDIO_DIRECT_MODE; + indio_dev->channels = ade7758_channels; + indio_dev->num_channels = ARRAY_SIZE(ade7758_channels); ret = ade7758_configure_ring(indio_dev); if (ret) diff --git a/drivers/staging/iio/meter/ade7758_ring.c b/drivers/staging/iio/meter/ade7758_ring.c index c0accf8cce93..6e9006490742 100644 --- a/drivers/staging/iio/meter/ade7758_ring.c +++ b/drivers/staging/iio/meter/ade7758_ring.c @@ -85,17 +85,16 @@ static irqreturn_t ade7758_trigger_handler(int irq, void *p) **/ static int ade7758_ring_preenable(struct iio_dev *indio_dev) { - struct ade7758_state *st = iio_priv(indio_dev); unsigned channel; - if (!bitmap_empty(indio_dev->active_scan_mask, indio_dev->masklength)) + if (bitmap_empty(indio_dev->active_scan_mask, indio_dev->masklength)) return -EINVAL; channel = find_first_bit(indio_dev->active_scan_mask, indio_dev->masklength); ade7758_write_waveform_type(&indio_dev->dev, - st->ade7758_ring_channels[channel].address); + indio_dev->channels[channel].address); return 0; } diff --git a/drivers/staging/iio/meter/ade7758_trigger.c b/drivers/staging/iio/meter/ade7758_trigger.c index 7a94ddd42f59..8c4f2896cd0d 100644 --- a/drivers/staging/iio/meter/ade7758_trigger.c +++ b/drivers/staging/iio/meter/ade7758_trigger.c @@ -85,7 +85,7 @@ int ade7758_probe_trigger(struct iio_dev *indio_dev) ret = iio_trigger_register(st->trig); /* select default trigger */ - indio_dev->trig = st->trig; + indio_dev->trig = iio_trigger_get(st->trig); if (ret) goto error_free_irq; diff --git a/drivers/staging/imx-drm/ipuv3-plane.c b/drivers/staging/imx-drm/ipuv3-plane.c index 34b642a12f8b..c70f1734b274 100644 --- a/drivers/staging/imx-drm/ipuv3-plane.c +++ b/drivers/staging/imx-drm/ipuv3-plane.c @@ -277,7 +277,8 @@ static void ipu_plane_dpms(struct ipu_plane *ipu_plane, int mode) ipu_idmac_put(ipu_plane->ipu_ch); ipu_dmfc_put(ipu_plane->dmfc); - ipu_dp_put(ipu_plane->dp); + if (ipu_plane->dp) + ipu_dp_put(ipu_plane->dp); } } diff --git a/drivers/staging/lustre/lustre/Kconfig b/drivers/staging/lustre/lustre/Kconfig index 209e4c7e6f8a..4f65ba1158bf 100644 --- a/drivers/staging/lustre/lustre/Kconfig +++ b/drivers/staging/lustre/lustre/Kconfig @@ -57,4 +57,5 @@ config LUSTRE_TRANSLATE_ERRNOS config LUSTRE_LLITE_LLOOP tristate "Lustre virtual block device" depends on LUSTRE_FS && BLOCK + depends on !PPC_64K_PAGES && !ARM64_64K_PAGES default m diff --git a/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h b/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h index eefdb8d061b1..81cc7a0134bb 100644 --- a/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h +++ b/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h @@ -105,8 +105,8 @@ static inline void ll_set_fs_pwd(struct fs_struct *fs, struct vfsmount *mnt, #define ll_vfs_unlink(inode,entry,mnt) vfs_unlink(inode,entry) #define ll_vfs_mknod(dir,entry,mnt,mode,dev) vfs_mknod(dir,entry,mode,dev) #define ll_security_inode_unlink(dir,entry,mnt) security_inode_unlink(dir,entry) -#define ll_vfs_rename(old,old_dir,mnt,new,new_dir,mnt1,delegated_inode) \ - vfs_rename(old,old_dir,new,new_dir,delegated_inode) +#define ll_vfs_rename(old, old_dir, mnt, new, new_dir, mnt1) \ + vfs_rename(old, old_dir, new, new_dir, NULL, 0) #define cfs_bio_io_error(a,b) bio_io_error((a)) #define cfs_bio_endio(a,b,c) bio_endio((a),(c)) diff --git a/drivers/staging/lustre/lustre/llite/llite_nfs.c b/drivers/staging/lustre/lustre/llite/llite_nfs.c index 1767c741fb72..ed35a88c6dd9 100644 --- a/drivers/staging/lustre/lustre/llite/llite_nfs.c +++ b/drivers/staging/lustre/lustre/llite/llite_nfs.c @@ -205,13 +205,15 @@ static int ll_encode_fh(struct inode *inode, __u32 *fh, int *plen, return LUSTRE_NFS_FID; } -static int ll_nfs_get_name_filldir(void *cookie, const char *name, int namelen, - loff_t hash, u64 ino, unsigned type) +static int ll_nfs_get_name_filldir(struct dir_context *ctx, const char *name, + int namelen, loff_t hash, u64 ino, + unsigned type) { /* It is hack to access lde_fid for comparison with lgd_fid. * So the input 'name' must be part of the 'lu_dirent'. */ struct lu_dirent *lde = container_of0(name, struct lu_dirent, lde_name); - struct ll_getname_data *lgd = cookie; + struct ll_getname_data *lgd = + container_of(ctx, struct ll_getname_data, ctx); struct lu_fid fid; fid_le_to_cpu(&fid, &lde->lde_fid); diff --git a/drivers/staging/lustre/lustre/llite/symlink.c b/drivers/staging/lustre/lustre/llite/symlink.c index ab06891f7fc7..80d48b5ae247 100644 --- a/drivers/staging/lustre/lustre/llite/symlink.c +++ b/drivers/staging/lustre/lustre/llite/symlink.c @@ -115,27 +115,6 @@ failed: return rc; } -static int ll_readlink(struct dentry *dentry, char *buffer, int buflen) -{ - struct inode *inode = dentry->d_inode; - struct ptlrpc_request *request; - char *symname; - int rc; - - CDEBUG(D_VFSTRACE, "VFS Op\n"); - - ll_inode_size_lock(inode); - rc = ll_readlink_internal(inode, &request, &symname); - if (rc) - GOTO(out, rc); - - rc = vfs_readlink(dentry, buffer, buflen, symname); - out: - ptlrpc_req_finished(request); - ll_inode_size_unlock(inode); - return rc; -} - static void *ll_follow_link(struct dentry *dentry, struct nameidata *nd) { struct inode *inode = dentry->d_inode; @@ -175,7 +154,7 @@ static void ll_put_link(struct dentry *dentry, struct nameidata *nd, void *cooki } struct inode_operations ll_fast_symlink_inode_operations = { - .readlink = ll_readlink, + .readlink = generic_readlink, .setattr = ll_setattr, .follow_link = ll_follow_link, .put_link = ll_put_link, diff --git a/drivers/staging/lustre/lustre/lvfs/lvfs_linux.c b/drivers/staging/lustre/lustre/lvfs/lvfs_linux.c index 428ffd8c37b7..d50822be3230 100644 --- a/drivers/staging/lustre/lustre/lvfs/lvfs_linux.c +++ b/drivers/staging/lustre/lustre/lvfs/lvfs_linux.c @@ -223,7 +223,7 @@ int lustre_rename(struct dentry *dir, struct vfsmount *mnt, GOTO(put_old, err = PTR_ERR(dchild_new)); err = ll_vfs_rename(dir->d_inode, dchild_old, mnt, - dir->d_inode, dchild_new, mnt, NULL); + dir->d_inode, dchild_new, mnt); dput(dchild_new); put_old: diff --git a/drivers/staging/rtl8188eu/os_dep/usb_intf.c b/drivers/staging/rtl8188eu/os_dep/usb_intf.c index fed699fc5918..2185a71055f2 100644 --- a/drivers/staging/rtl8188eu/os_dep/usb_intf.c +++ b/drivers/staging/rtl8188eu/os_dep/usb_intf.c @@ -57,6 +57,7 @@ static struct usb_device_id rtw_usb_id_tbl[] = { {USB_DEVICE(0x07b8, 0x8179)}, /* Abocom - Abocom */ {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(0x0df6, 0x0076)}, /* Sitecom N150 v2 */ {} /* Terminating entry */ }; diff --git a/drivers/staging/vt6655/rf.c b/drivers/staging/vt6655/rf.c index edb1b2768b17..dbd9d44919ac 100644 --- a/drivers/staging/vt6655/rf.c +++ b/drivers/staging/vt6655/rf.c @@ -936,6 +936,7 @@ bool RFbSetPower( break; case RATE_6M: case RATE_9M: + case RATE_12M: case RATE_18M: byPwr = pDevice->abyOFDMPwrTbl[uCH]; if (pDevice->byRFType == RF_UW2452) { diff --git a/drivers/staging/vt6656/rf.c b/drivers/staging/vt6656/rf.c index 1e8f64bff03c..2dc48d4ff433 100644 --- a/drivers/staging/vt6656/rf.c +++ b/drivers/staging/vt6656/rf.c @@ -752,6 +752,7 @@ int RFbSetPower(struct vnt_private *priv, u32 rate, u32 channel) break; case RATE_6M: case RATE_9M: + case RATE_12M: case RATE_18M: case RATE_24M: case RATE_36M: diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index f329ad294fc0..b61c555a5a8f 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -1165,7 +1165,7 @@ iscsit_handle_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, * traditional iSCSI block I/O. */ if (iscsit_allocate_iovecs(cmd) < 0) { - return iscsit_add_reject_cmd(cmd, + return iscsit_reject_cmd(cmd, ISCSI_REASON_BOOKMARK_NO_RESOURCES, buf); } immed_data = cmd->immediate_data; @@ -4196,11 +4196,17 @@ int iscsit_close_connection( pr_debug("Closing iSCSI connection CID %hu on SID:" " %u\n", conn->cid, sess->sid); /* - * Always up conn_logout_comp just in case the RX Thread is sleeping - * and the logout response never got sent because the connection - * failed. + * Always up conn_logout_comp for the traditional TCP case just in case + * the RX Thread in iscsi_target_rx_opcode() is sleeping and the logout + * response never got sent because the connection failed. + * + * However for iser-target, isert_wait4logout() is using conn_logout_comp + * to signal logout response TX interrupt completion. Go ahead and skip + * this for iser since isert_rx_opcode() does not wait on logout failure, + * and to avoid iscsi_conn pointer dereference in iser-target code. */ - complete(&conn->conn_logout_comp); + if (conn->conn_transport->transport_type == ISCSI_TCP) + complete(&conn->conn_logout_comp); iscsi_release_thread_set(conn); @@ -4513,6 +4519,7 @@ static void iscsit_logout_post_handler_diffcid( { struct iscsi_conn *l_conn; struct iscsi_session *sess = conn->sess; + bool conn_found = false; if (!sess) return; @@ -4521,12 +4528,13 @@ static void iscsit_logout_post_handler_diffcid( list_for_each_entry(l_conn, &sess->sess_conn_list, conn_list) { if (l_conn->cid == cid) { iscsit_inc_conn_usage_count(l_conn); + conn_found = true; break; } } spin_unlock_bh(&sess->conn_lock); - if (!l_conn) + if (!conn_found) return; if (l_conn->sock) diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index d509aa74cfa1..c5d3811a7b8c 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -1186,6 +1186,9 @@ old_sess_out: conn->sock = NULL; } + if (conn->conn_transport->iscsit_wait_conn) + conn->conn_transport->iscsit_wait_conn(conn); + if (conn->conn_transport->iscsit_free_conn) conn->conn_transport->iscsit_free_conn(conn); diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c index 4d2e23fc76fd..43b7e6a616b8 100644 --- a/drivers/target/iscsi/iscsi_target_parameters.c +++ b/drivers/target/iscsi/iscsi_target_parameters.c @@ -601,7 +601,7 @@ int iscsi_copy_param_list( param_list = kzalloc(sizeof(struct iscsi_param_list), GFP_KERNEL); if (!param_list) { pr_err("Unable to allocate memory for struct iscsi_param_list.\n"); - goto err_out; + return -1; } INIT_LIST_HEAD(¶m_list->param_list); INIT_LIST_HEAD(¶m_list->extra_response_list); diff --git a/drivers/target/iscsi/iscsi_target_tq.c b/drivers/target/iscsi/iscsi_target_tq.c index 601e9cc61e98..bb2890e79ca0 100644 --- a/drivers/target/iscsi/iscsi_target_tq.c +++ b/drivers/target/iscsi/iscsi_target_tq.c @@ -24,36 +24,22 @@ #include "iscsi_target_tq.h" #include "iscsi_target.h" -static LIST_HEAD(active_ts_list); static LIST_HEAD(inactive_ts_list); -static DEFINE_SPINLOCK(active_ts_lock); static DEFINE_SPINLOCK(inactive_ts_lock); static DEFINE_SPINLOCK(ts_bitmap_lock); -static void iscsi_add_ts_to_active_list(struct iscsi_thread_set *ts) -{ - spin_lock(&active_ts_lock); - list_add_tail(&ts->ts_list, &active_ts_list); - iscsit_global->active_ts++; - spin_unlock(&active_ts_lock); -} - static void iscsi_add_ts_to_inactive_list(struct iscsi_thread_set *ts) { + if (!list_empty(&ts->ts_list)) { + WARN_ON(1); + return; + } spin_lock(&inactive_ts_lock); list_add_tail(&ts->ts_list, &inactive_ts_list); iscsit_global->inactive_ts++; spin_unlock(&inactive_ts_lock); } -static void iscsi_del_ts_from_active_list(struct iscsi_thread_set *ts) -{ - spin_lock(&active_ts_lock); - list_del(&ts->ts_list); - iscsit_global->active_ts--; - spin_unlock(&active_ts_lock); -} - static struct iscsi_thread_set *iscsi_get_ts_from_inactive_list(void) { struct iscsi_thread_set *ts; @@ -66,7 +52,7 @@ static struct iscsi_thread_set *iscsi_get_ts_from_inactive_list(void) ts = list_first_entry(&inactive_ts_list, struct iscsi_thread_set, ts_list); - list_del(&ts->ts_list); + list_del_init(&ts->ts_list); iscsit_global->inactive_ts--; spin_unlock(&inactive_ts_lock); @@ -204,8 +190,6 @@ static void iscsi_deallocate_extra_thread_sets(void) void iscsi_activate_thread_set(struct iscsi_conn *conn, struct iscsi_thread_set *ts) { - iscsi_add_ts_to_active_list(ts); - spin_lock_bh(&ts->ts_state_lock); conn->thread_set = ts; ts->conn = conn; @@ -397,7 +381,6 @@ struct iscsi_conn *iscsi_rx_thread_pre_handler(struct iscsi_thread_set *ts) if (ts->delay_inactive && (--ts->thread_count == 0)) { spin_unlock_bh(&ts->ts_state_lock); - iscsi_del_ts_from_active_list(ts); if (!iscsit_global->in_shutdown) iscsi_deallocate_extra_thread_sets(); @@ -452,7 +435,6 @@ struct iscsi_conn *iscsi_tx_thread_pre_handler(struct iscsi_thread_set *ts) if (ts->delay_inactive && (--ts->thread_count == 0)) { spin_unlock_bh(&ts->ts_state_lock); - iscsi_del_ts_from_active_list(ts); if (!iscsit_global->in_shutdown) iscsi_deallocate_extra_thread_sets(); diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index ab77f80ead2b..1e406af4ee47 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -1356,15 +1356,15 @@ static int iscsit_do_tx_data( struct iscsi_conn *conn, struct iscsi_data_count *count) { - int data = count->data_length, total_tx = 0, tx_loop = 0, iov_len; + int ret, iov_len; struct kvec *iov_p; struct msghdr msg; if (!conn || !conn->sock || !conn->conn_ops) return -1; - if (data <= 0) { - pr_err("Data length is: %d\n", data); + if (count->data_length <= 0) { + pr_err("Data length is: %d\n", count->data_length); return -1; } @@ -1373,20 +1373,16 @@ static int iscsit_do_tx_data( iov_p = count->iov; iov_len = count->iov_count; - while (total_tx < data) { - tx_loop = kernel_sendmsg(conn->sock, &msg, iov_p, iov_len, - (data - total_tx)); - if (tx_loop <= 0) { - pr_debug("tx_loop: %d total_tx %d\n", - tx_loop, total_tx); - return tx_loop; - } - total_tx += tx_loop; - pr_debug("tx_loop: %d, total_tx: %d, data: %d\n", - tx_loop, total_tx, data); + ret = kernel_sendmsg(conn->sock, &msg, iov_p, iov_len, + count->data_length); + if (ret != count->data_length) { + pr_err("Unexpected ret: %d send data %d\n", + ret, count->data_length); + return -EPIPE; } + pr_debug("ret: %d, sent data: %d\n", ret, count->data_length); - return total_tx; + return ret; } int rx_data( diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index fadad7c5f635..67c802c93ef3 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -153,18 +153,11 @@ static int tcm_loop_change_queue_type(struct scsi_device *sdev, int tag) /* * Locate the SAM Task Attr from struct scsi_cmnd * */ -static int tcm_loop_sam_attr(struct scsi_cmnd *sc) -{ - if (sc->device->tagged_supported) { - switch (sc->tag) { - case HEAD_OF_QUEUE_TAG: - return MSG_HEAD_TAG; - case ORDERED_QUEUE_TAG: - return MSG_ORDERED_TAG; - default: - break; - } - } +static int tcm_loop_sam_attr(struct scsi_cmnd *sc, int tag) +{ + if (sc->device->tagged_supported && + sc->device->ordered_tags && tag >= 0) + return MSG_ORDERED_TAG; return MSG_SIMPLE_TAG; } @@ -197,7 +190,7 @@ static void tcm_loop_submission_work(struct work_struct *work) set_host_byte(sc, DID_TRANSPORT_DISRUPTED); goto out_done; } - tl_nexus = tl_hba->tl_nexus; + tl_nexus = tl_tpg->tl_nexus; if (!tl_nexus) { scmd_printk(KERN_ERR, sc, "TCM_Loop I_T Nexus" " does not exist\n"); @@ -214,7 +207,7 @@ static void tcm_loop_submission_work(struct work_struct *work) } rc = target_submit_cmd_map_sgls(se_cmd, tl_nexus->se_sess, sc->cmnd, &tl_cmd->tl_sense_buf[0], tl_cmd->sc->device->lun, - scsi_bufflen(sc), tcm_loop_sam_attr(sc), + scsi_bufflen(sc), tcm_loop_sam_attr(sc, tl_cmd->sc_cmd_tag), sc->sc_data_direction, 0, scsi_sglist(sc), scsi_sg_count(sc), sgl_bidi, sgl_bidi_count, @@ -252,7 +245,7 @@ static int tcm_loop_queuecommand(struct Scsi_Host *sh, struct scsi_cmnd *sc) } tl_cmd->sc = sc; - tl_cmd->sc_cmd_tag = sc->tag; + tl_cmd->sc_cmd_tag = sc->request->tag; INIT_WORK(&tl_cmd->work, tcm_loop_submission_work); queue_work(tcm_loop_workqueue, &tl_cmd->work); return 0; @@ -263,16 +256,26 @@ static int tcm_loop_queuecommand(struct Scsi_Host *sh, struct scsi_cmnd *sc) * to struct scsi_device */ static int tcm_loop_issue_tmr(struct tcm_loop_tpg *tl_tpg, - struct tcm_loop_nexus *tl_nexus, int lun, int task, enum tcm_tmreq_table tmr) { struct se_cmd *se_cmd = NULL; struct se_session *se_sess; struct se_portal_group *se_tpg; + struct tcm_loop_nexus *tl_nexus; struct tcm_loop_cmd *tl_cmd = NULL; struct tcm_loop_tmr *tl_tmr = NULL; int ret = TMR_FUNCTION_FAILED, rc; + /* + * Locate the tl_nexus and se_sess pointers + */ + tl_nexus = tl_tpg->tl_nexus; + if (!tl_nexus) { + pr_err("Unable to perform device reset without" + " active I_T Nexus\n"); + return ret; + } + tl_cmd = kmem_cache_zalloc(tcm_loop_cmd_cache, GFP_KERNEL); if (!tl_cmd) { pr_err("Unable to allocate memory for tl_cmd\n"); @@ -288,7 +291,7 @@ static int tcm_loop_issue_tmr(struct tcm_loop_tpg *tl_tpg, se_cmd = &tl_cmd->tl_se_cmd; se_tpg = &tl_tpg->tl_se_tpg; - se_sess = tl_nexus->se_sess; + se_sess = tl_tpg->tl_nexus->se_sess; /* * Initialize struct se_cmd descriptor from target_core_mod infrastructure */ @@ -333,7 +336,6 @@ release: static int tcm_loop_abort_task(struct scsi_cmnd *sc) { struct tcm_loop_hba *tl_hba; - struct tcm_loop_nexus *tl_nexus; struct tcm_loop_tpg *tl_tpg; int ret = FAILED; @@ -341,22 +343,9 @@ static int tcm_loop_abort_task(struct scsi_cmnd *sc) * Locate the tcm_loop_hba_t pointer */ tl_hba = *(struct tcm_loop_hba **)shost_priv(sc->device->host); - /* - * Locate the tl_nexus and se_sess pointers - */ - tl_nexus = tl_hba->tl_nexus; - if (!tl_nexus) { - pr_err("Unable to perform device reset without" - " active I_T Nexus\n"); - return FAILED; - } - - /* - * Locate the tl_tpg pointer from TargetID in sc->device->id - */ tl_tpg = &tl_hba->tl_hba_tpgs[sc->device->id]; - ret = tcm_loop_issue_tmr(tl_tpg, tl_nexus, sc->device->lun, - sc->tag, TMR_ABORT_TASK); + ret = tcm_loop_issue_tmr(tl_tpg, sc->device->lun, + sc->request->tag, TMR_ABORT_TASK); return (ret == TMR_FUNCTION_COMPLETE) ? SUCCESS : FAILED; } @@ -367,7 +356,6 @@ static int tcm_loop_abort_task(struct scsi_cmnd *sc) static int tcm_loop_device_reset(struct scsi_cmnd *sc) { struct tcm_loop_hba *tl_hba; - struct tcm_loop_nexus *tl_nexus; struct tcm_loop_tpg *tl_tpg; int ret = FAILED; @@ -375,20 +363,9 @@ static int tcm_loop_device_reset(struct scsi_cmnd *sc) * Locate the tcm_loop_hba_t pointer */ tl_hba = *(struct tcm_loop_hba **)shost_priv(sc->device->host); - /* - * Locate the tl_nexus and se_sess pointers - */ - tl_nexus = tl_hba->tl_nexus; - if (!tl_nexus) { - pr_err("Unable to perform device reset without" - " active I_T Nexus\n"); - return FAILED; - } - /* - * Locate the tl_tpg pointer from TargetID in sc->device->id - */ tl_tpg = &tl_hba->tl_hba_tpgs[sc->device->id]; - ret = tcm_loop_issue_tmr(tl_tpg, tl_nexus, sc->device->lun, + + ret = tcm_loop_issue_tmr(tl_tpg, sc->device->lun, 0, TMR_LUN_RESET); return (ret == TMR_FUNCTION_COMPLETE) ? SUCCESS : FAILED; } @@ -995,8 +972,8 @@ static int tcm_loop_make_nexus( struct tcm_loop_nexus *tl_nexus; int ret = -ENOMEM; - if (tl_tpg->tl_hba->tl_nexus) { - pr_debug("tl_tpg->tl_hba->tl_nexus already exists\n"); + if (tl_tpg->tl_nexus) { + pr_debug("tl_tpg->tl_nexus already exists\n"); return -EEXIST; } se_tpg = &tl_tpg->tl_se_tpg; @@ -1031,7 +1008,7 @@ static int tcm_loop_make_nexus( */ __transport_register_session(se_tpg, tl_nexus->se_sess->se_node_acl, tl_nexus->se_sess, tl_nexus); - tl_tpg->tl_hba->tl_nexus = tl_nexus; + tl_tpg->tl_nexus = tl_nexus; pr_debug("TCM_Loop_ConfigFS: Established I_T Nexus to emulated" " %s Initiator Port: %s\n", tcm_loop_dump_proto_id(tl_hba), name); @@ -1047,12 +1024,8 @@ static int tcm_loop_drop_nexus( { struct se_session *se_sess; struct tcm_loop_nexus *tl_nexus; - struct tcm_loop_hba *tl_hba = tpg->tl_hba; - if (!tl_hba) - return -ENODEV; - - tl_nexus = tl_hba->tl_nexus; + tl_nexus = tpg->tl_nexus; if (!tl_nexus) return -ENODEV; @@ -1068,13 +1041,13 @@ static int tcm_loop_drop_nexus( } pr_debug("TCM_Loop_ConfigFS: Removing I_T Nexus to emulated" - " %s Initiator Port: %s\n", tcm_loop_dump_proto_id(tl_hba), + " %s Initiator Port: %s\n", tcm_loop_dump_proto_id(tpg->tl_hba), tl_nexus->se_sess->se_node_acl->initiatorname); /* * Release the SCSI I_T Nexus to the emulated SAS Target Port */ transport_deregister_session(tl_nexus->se_sess); - tpg->tl_hba->tl_nexus = NULL; + tpg->tl_nexus = NULL; kfree(tl_nexus); return 0; } @@ -1090,7 +1063,7 @@ static ssize_t tcm_loop_tpg_show_nexus( struct tcm_loop_nexus *tl_nexus; ssize_t ret; - tl_nexus = tl_tpg->tl_hba->tl_nexus; + tl_nexus = tl_tpg->tl_nexus; if (!tl_nexus) return -ENODEV; diff --git a/drivers/target/loopback/tcm_loop.h b/drivers/target/loopback/tcm_loop.h index 54c59d0b6608..6ae49f272ba6 100644 --- a/drivers/target/loopback/tcm_loop.h +++ b/drivers/target/loopback/tcm_loop.h @@ -27,11 +27,6 @@ struct tcm_loop_tmr { }; struct tcm_loop_nexus { - int it_nexus_active; - /* - * Pointer to Linux/SCSI HBA from linux/include/scsi_host.h - */ - struct scsi_host *sh; /* * Pointer to TCM session for I_T Nexus */ @@ -51,6 +46,7 @@ struct tcm_loop_tpg { atomic_t tl_tpg_port_count; struct se_portal_group tl_se_tpg; struct tcm_loop_hba *tl_hba; + struct tcm_loop_nexus *tl_nexus; }; struct tcm_loop_hba { @@ -59,7 +55,6 @@ struct tcm_loop_hba { struct se_hba_s *se_hba; struct se_lun *tl_hba_lun; struct se_port *tl_hba_lun_sep; - struct tcm_loop_nexus *tl_nexus; struct device dev; struct Scsi_Host *sh; struct tcm_loop_tpg tl_hba_tpgs[TL_TPGS_PER_HBA]; diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index 483d324020a6..f30385385544 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -2359,7 +2359,7 @@ static ssize_t target_core_alua_tg_pt_gp_store_attr_alua_support_##_name(\ pr_err("Invalid value '%ld', must be '0' or '1'\n", tmp); \ return -EINVAL; \ } \ - if (!tmp) \ + if (tmp) \ t->_var |= _bit; \ else \ t->_var &= ~_bit; \ diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 6ea95d216eb8..093b8cb85de7 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -1153,10 +1153,10 @@ int se_dev_set_optimal_sectors(struct se_device *dev, u32 optimal_sectors) " changed for TCM/pSCSI\n", dev); return -EINVAL; } - if (optimal_sectors > dev->dev_attrib.fabric_max_sectors) { + if (optimal_sectors > dev->dev_attrib.hw_max_sectors) { pr_err("dev[%p]: Passed optimal_sectors %u cannot be" - " greater than fabric_max_sectors: %u\n", dev, - optimal_sectors, dev->dev_attrib.fabric_max_sectors); + " greater than hw_max_sectors: %u\n", dev, + optimal_sectors, dev->dev_attrib.hw_max_sectors); return -EINVAL; } @@ -1409,7 +1409,8 @@ int core_dev_add_initiator_node_lun_acl( * Check to see if there are any existing persistent reservation APTPL * pre-registrations that need to be enabled for this LUN ACL.. */ - core_scsi3_check_aptpl_registration(lun->lun_se_dev, tpg, lun, lacl); + core_scsi3_check_aptpl_registration(lun->lun_se_dev, tpg, lun, nacl, + lacl->mapped_lun); return 0; } @@ -1564,7 +1565,6 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name) DA_UNMAP_GRANULARITY_ALIGNMENT_DEFAULT; dev->dev_attrib.max_write_same_len = DA_MAX_WRITE_SAME_LEN; dev->dev_attrib.fabric_max_sectors = DA_FABRIC_MAX_SECTORS; - dev->dev_attrib.optimal_sectors = DA_FABRIC_MAX_SECTORS; xcopy_lun = &dev->xcopy_lun; xcopy_lun->lun_se_dev = dev; @@ -1591,8 +1591,6 @@ int target_configure_device(struct se_device *dev) ret = dev->transport->configure_device(dev); if (ret) goto out; - dev->dev_flags |= DF_CONFIGURED; - /* * XXX: there is not much point to have two different values here.. */ @@ -1605,6 +1603,7 @@ int target_configure_device(struct se_device *dev) dev->dev_attrib.hw_max_sectors = se_dev_align_max_sectors(dev->dev_attrib.hw_max_sectors, dev->dev_attrib.hw_block_size); + dev->dev_attrib.optimal_sectors = dev->dev_attrib.hw_max_sectors; dev->dev_index = scsi_get_new_index(SCSI_DEVICE_INDEX); dev->creation_time = get_jiffies_64(); @@ -1653,6 +1652,8 @@ int target_configure_device(struct se_device *dev) list_add_tail(&dev->g_dev_node, &g_device_list); mutex_unlock(&g_device_mutex); + dev->dev_flags |= DF_CONFIGURED; + return 0; out_free_alua: diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index cf991a91a8a9..41eff7d64cb8 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -620,7 +620,16 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, struct fd_prot fd_prot; sense_reason_t rc; int ret = 0; - + /* + * We are currently limited by the number of iovecs (2048) per + * single vfs_[writev,readv] call. + */ + if (cmd->data_length > FD_MAX_BYTES) { + pr_err("FILEIO: Not able to process I/O of %u bytes due to" + "FD_MAX_BYTES: %u iovec count limitiation\n", + cmd->data_length, FD_MAX_BYTES); + return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; + } /* * Call vectorized fileio functions to map struct scatterlist * physical memory addresses to struct iovec virtual memory. diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index 9e0232cca92e..feefe24a88f7 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -123,7 +123,7 @@ static int iblock_configure_device(struct se_device *dev) q = bdev_get_queue(bd); dev->dev_attrib.hw_block_size = bdev_logical_block_size(bd); - dev->dev_attrib.hw_max_sectors = UINT_MAX; + dev->dev_attrib.hw_max_sectors = queue_max_hw_sectors(q); dev->dev_attrib.hw_queue_depth = q->nr_requests; /* diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index 3013287a2aaa..70cb37516d40 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -76,7 +76,7 @@ enum preempt_type { }; static void __core_scsi3_complete_pro_release(struct se_device *, struct se_node_acl *, - struct t10_pr_registration *, int); + struct t10_pr_registration *, int, int); static sense_reason_t target_scsi2_reservation_check(struct se_cmd *cmd) @@ -528,6 +528,18 @@ static int core_scsi3_pr_seq_non_holder( return 0; } + } else if (we && registered_nexus) { + /* + * Reads are allowed for Write Exclusive locks + * from all registrants. + */ + if (cmd->data_direction == DMA_FROM_DEVICE) { + pr_debug("Allowing READ CDB: 0x%02x for %s" + " reservation\n", cdb[0], + core_scsi3_pr_dump_type(pr_reg_type)); + + return 0; + } } pr_debug("%s Conflict for %sregistered nexus %s CDB: 0x%2x" " for %s reservation\n", transport_dump_cmd_direction(cmd), @@ -944,10 +956,10 @@ int core_scsi3_check_aptpl_registration( struct se_device *dev, struct se_portal_group *tpg, struct se_lun *lun, - struct se_lun_acl *lun_acl) + struct se_node_acl *nacl, + u32 mapped_lun) { - struct se_node_acl *nacl = lun_acl->se_lun_nacl; - struct se_dev_entry *deve = nacl->device_list[lun_acl->mapped_lun]; + struct se_dev_entry *deve = nacl->device_list[mapped_lun]; if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS) return 0; @@ -1186,7 +1198,7 @@ static int core_scsi3_check_implicit_release( * service action with the SERVICE ACTION RESERVATION KEY * field set to zero (see 5.7.11.3). */ - __core_scsi3_complete_pro_release(dev, nacl, pr_reg, 0); + __core_scsi3_complete_pro_release(dev, nacl, pr_reg, 0, 1); ret = 1; /* * For 'All Registrants' reservation types, all existing @@ -1228,7 +1240,8 @@ static void __core_scsi3_free_registration( pr_reg->pr_reg_deve->def_pr_registered = 0; pr_reg->pr_reg_deve->pr_res_key = 0; - list_del(&pr_reg->pr_reg_list); + if (!list_empty(&pr_reg->pr_reg_list)) + list_del(&pr_reg->pr_reg_list); /* * Caller accessing *pr_reg using core_scsi3_locate_pr_reg(), * so call core_scsi3_put_pr_reg() to decrement our reference. @@ -1280,6 +1293,7 @@ void core_scsi3_free_pr_reg_from_nacl( { struct t10_reservation *pr_tmpl = &dev->t10_pr; struct t10_pr_registration *pr_reg, *pr_reg_tmp, *pr_res_holder; + bool free_reg = false; /* * If the passed se_node_acl matches the reservation holder, * release the reservation. @@ -1287,13 +1301,18 @@ void core_scsi3_free_pr_reg_from_nacl( spin_lock(&dev->dev_reservation_lock); pr_res_holder = dev->dev_pr_res_holder; if ((pr_res_holder != NULL) && - (pr_res_holder->pr_reg_nacl == nacl)) - __core_scsi3_complete_pro_release(dev, nacl, pr_res_holder, 0); + (pr_res_holder->pr_reg_nacl == nacl)) { + __core_scsi3_complete_pro_release(dev, nacl, pr_res_holder, 0, 1); + free_reg = true; + } spin_unlock(&dev->dev_reservation_lock); /* * Release any registration associated with the struct se_node_acl. */ spin_lock(&pr_tmpl->registration_lock); + if (pr_res_holder && free_reg) + __core_scsi3_free_registration(dev, pr_res_holder, NULL, 0); + list_for_each_entry_safe(pr_reg, pr_reg_tmp, &pr_tmpl->registration_list, pr_reg_list) { @@ -1316,7 +1335,7 @@ void core_scsi3_free_all_registrations( if (pr_res_holder != NULL) { struct se_node_acl *pr_res_nacl = pr_res_holder->pr_reg_nacl; __core_scsi3_complete_pro_release(dev, pr_res_nacl, - pr_res_holder, 0); + pr_res_holder, 0, 0); } spin_unlock(&dev->dev_reservation_lock); @@ -1877,8 +1896,8 @@ static int core_scsi3_update_aptpl_buf( } if ((len + strlen(tmp) >= pr_aptpl_buf_len)) { - pr_err("Unable to update renaming" - " APTPL metadata\n"); + pr_err("Unable to update renaming APTPL metadata," + " reallocating larger buffer\n"); ret = -EMSGSIZE; goto out; } @@ -1895,8 +1914,8 @@ static int core_scsi3_update_aptpl_buf( lun->lun_sep->sep_rtpi, lun->unpacked_lun, reg_count); if ((len + strlen(tmp) >= pr_aptpl_buf_len)) { - pr_err("Unable to update renaming" - " APTPL metadata\n"); + pr_err("Unable to update renaming APTPL metadata," + " reallocating larger buffer\n"); ret = -EMSGSIZE; goto out; } @@ -1959,7 +1978,7 @@ static int __core_scsi3_write_aptpl_to_file( static sense_reason_t core_scsi3_update_and_write_aptpl(struct se_device *dev, bool aptpl) { unsigned char *buf; - int rc; + int rc, len = PR_APTPL_BUF_LEN; if (!aptpl) { char *null_buf = "No Registrations or Reservations\n"; @@ -1973,25 +1992,26 @@ static sense_reason_t core_scsi3_update_and_write_aptpl(struct se_device *dev, b return 0; } - - buf = kzalloc(PR_APTPL_BUF_LEN, GFP_KERNEL); +retry: + buf = vzalloc(len); if (!buf) return TCM_OUT_OF_RESOURCES; - rc = core_scsi3_update_aptpl_buf(dev, buf, PR_APTPL_BUF_LEN); + rc = core_scsi3_update_aptpl_buf(dev, buf, len); if (rc < 0) { - kfree(buf); - return TCM_OUT_OF_RESOURCES; + vfree(buf); + len *= 2; + goto retry; } rc = __core_scsi3_write_aptpl_to_file(dev, buf); if (rc != 0) { pr_err("SPC-3 PR: Could not update APTPL\n"); - kfree(buf); + vfree(buf); return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; } dev->t10_pr.pr_aptpl_active = 1; - kfree(buf); + vfree(buf); pr_debug("SPC-3 PR: Set APTPL Bit Activated\n"); return 0; } @@ -2125,13 +2145,13 @@ core_scsi3_emulate_pro_register(struct se_cmd *cmd, u64 res_key, u64 sa_res_key, /* * sa_res_key=0 Unregister Reservation Key for registered I_T Nexus. */ - pr_holder = core_scsi3_check_implicit_release( - cmd->se_dev, pr_reg); + type = pr_reg->pr_res_type; + pr_holder = core_scsi3_check_implicit_release(cmd->se_dev, + pr_reg); if (pr_holder < 0) { ret = TCM_RESERVATION_CONFLICT; goto out; } - type = pr_reg->pr_res_type; spin_lock(&pr_tmpl->registration_lock); /* @@ -2289,6 +2309,7 @@ core_scsi3_pro_reserve(struct se_cmd *cmd, int type, int scope, u64 res_key) spin_lock(&dev->dev_reservation_lock); pr_res_holder = dev->dev_pr_res_holder; if (pr_res_holder) { + int pr_res_type = pr_res_holder->pr_res_type; /* * From spc4r17 Section 5.7.9: Reserving: * @@ -2299,7 +2320,9 @@ core_scsi3_pro_reserve(struct se_cmd *cmd, int type, int scope, u64 res_key) * the logical unit, then the command shall be completed with * RESERVATION CONFLICT status. */ - if (pr_res_holder != pr_reg) { + if ((pr_res_holder != pr_reg) && + (pr_res_type != PR_TYPE_WRITE_EXCLUSIVE_ALLREG) && + (pr_res_type != PR_TYPE_EXCLUSIVE_ACCESS_ALLREG)) { struct se_node_acl *pr_res_nacl = pr_res_holder->pr_reg_nacl; pr_err("SPC-3 PR: Attempted RESERVE from" " [%s]: %s while reservation already held by" @@ -2405,23 +2428,59 @@ static void __core_scsi3_complete_pro_release( struct se_device *dev, struct se_node_acl *se_nacl, struct t10_pr_registration *pr_reg, - int explicit) + int explicit, + int unreg) { struct target_core_fabric_ops *tfo = se_nacl->se_tpg->se_tpg_tfo; char i_buf[PR_REG_ISID_ID_LEN]; + int pr_res_type = 0, pr_res_scope = 0; memset(i_buf, 0, PR_REG_ISID_ID_LEN); core_pr_dump_initiator_port(pr_reg, i_buf, PR_REG_ISID_ID_LEN); /* * Go ahead and release the current PR reservation holder. + * If an All Registrants reservation is currently active and + * a unregister operation is requested, replace the current + * dev_pr_res_holder with another active registration. */ - dev->dev_pr_res_holder = NULL; + if (dev->dev_pr_res_holder) { + pr_res_type = dev->dev_pr_res_holder->pr_res_type; + pr_res_scope = dev->dev_pr_res_holder->pr_res_scope; + dev->dev_pr_res_holder->pr_res_type = 0; + dev->dev_pr_res_holder->pr_res_scope = 0; + dev->dev_pr_res_holder->pr_res_holder = 0; + dev->dev_pr_res_holder = NULL; + } + if (!unreg) + goto out; - pr_debug("SPC-3 PR [%s] Service Action: %s RELEASE cleared" - " reservation holder TYPE: %s ALL_TG_PT: %d\n", - tfo->get_fabric_name(), (explicit) ? "explicit" : "implicit", - core_scsi3_pr_dump_type(pr_reg->pr_res_type), - (pr_reg->pr_reg_all_tg_pt) ? 1 : 0); + spin_lock(&dev->t10_pr.registration_lock); + list_del_init(&pr_reg->pr_reg_list); + /* + * If the I_T nexus is a reservation holder, the persistent reservation + * is of an all registrants type, and the I_T nexus is the last remaining + * registered I_T nexus, then the device server shall also release the + * persistent reservation. + */ + if (!list_empty(&dev->t10_pr.registration_list) && + ((pr_res_type == PR_TYPE_WRITE_EXCLUSIVE_ALLREG) || + (pr_res_type == PR_TYPE_EXCLUSIVE_ACCESS_ALLREG))) { + dev->dev_pr_res_holder = + list_entry(dev->t10_pr.registration_list.next, + struct t10_pr_registration, pr_reg_list); + dev->dev_pr_res_holder->pr_res_type = pr_res_type; + dev->dev_pr_res_holder->pr_res_scope = pr_res_scope; + dev->dev_pr_res_holder->pr_res_holder = 1; + } + spin_unlock(&dev->t10_pr.registration_lock); +out: + if (!dev->dev_pr_res_holder) { + pr_debug("SPC-3 PR [%s] Service Action: %s RELEASE cleared" + " reservation holder TYPE: %s ALL_TG_PT: %d\n", + tfo->get_fabric_name(), (explicit) ? "explicit" : + "implicit", core_scsi3_pr_dump_type(pr_res_type), + (pr_reg->pr_reg_all_tg_pt) ? 1 : 0); + } pr_debug("SPC-3 PR [%s] RELEASE Node: %s%s\n", tfo->get_fabric_name(), se_nacl->initiatorname, i_buf); @@ -2552,7 +2611,7 @@ core_scsi3_emulate_pro_release(struct se_cmd *cmd, int type, int scope, * server shall not establish a unit attention condition. */ __core_scsi3_complete_pro_release(dev, se_sess->se_node_acl, - pr_reg, 1); + pr_reg, 1, 0); spin_unlock(&dev->dev_reservation_lock); @@ -2640,7 +2699,7 @@ core_scsi3_emulate_pro_clear(struct se_cmd *cmd, u64 res_key) if (pr_res_holder) { struct se_node_acl *pr_res_nacl = pr_res_holder->pr_reg_nacl; __core_scsi3_complete_pro_release(dev, pr_res_nacl, - pr_res_holder, 0); + pr_res_holder, 0, 0); } spin_unlock(&dev->dev_reservation_lock); /* @@ -2699,7 +2758,7 @@ static void __core_scsi3_complete_pro_preempt( */ if (dev->dev_pr_res_holder) __core_scsi3_complete_pro_release(dev, nacl, - dev->dev_pr_res_holder, 0); + dev->dev_pr_res_holder, 0, 0); dev->dev_pr_res_holder = pr_reg; pr_reg->pr_res_holder = 1; @@ -2943,8 +3002,8 @@ core_scsi3_pro_preempt(struct se_cmd *cmd, int type, int scope, u64 res_key, */ if (pr_reg_n != pr_res_holder) __core_scsi3_complete_pro_release(dev, - pr_res_holder->pr_reg_nacl, - dev->dev_pr_res_holder, 0); + pr_res_holder->pr_reg_nacl, + dev->dev_pr_res_holder, 0, 0); /* * b) Remove the registrations for all I_T nexuses identified * by the SERVICE ACTION RESERVATION KEY field, except the @@ -3414,7 +3473,7 @@ after_iport_check: * holder (i.e., the I_T nexus on which the */ __core_scsi3_complete_pro_release(dev, pr_res_nacl, - dev->dev_pr_res_holder, 0); + dev->dev_pr_res_holder, 0, 0); /* * g) Move the persistent reservation to the specified I_T nexus using * the same scope and type as the persistent reservation released in @@ -3854,7 +3913,8 @@ core_scsi3_pri_read_full_status(struct se_cmd *cmd) unsigned char *buf; u32 add_desc_len = 0, add_len = 0, desc_len, exp_desc_len; u32 off = 8; /* off into first Full Status descriptor */ - int format_code = 0; + int format_code = 0, pr_res_type = 0, pr_res_scope = 0; + bool all_reg = false; if (cmd->data_length < 8) { pr_err("PRIN SA READ_FULL_STATUS SCSI Data Length: %u" @@ -3871,6 +3931,19 @@ core_scsi3_pri_read_full_status(struct se_cmd *cmd) buf[2] = ((dev->t10_pr.pr_generation >> 8) & 0xff); buf[3] = (dev->t10_pr.pr_generation & 0xff); + spin_lock(&dev->dev_reservation_lock); + if (dev->dev_pr_res_holder) { + struct t10_pr_registration *pr_holder = dev->dev_pr_res_holder; + + if (pr_holder->pr_res_type == PR_TYPE_WRITE_EXCLUSIVE_ALLREG || + pr_holder->pr_res_type == PR_TYPE_EXCLUSIVE_ACCESS_ALLREG) { + all_reg = true; + pr_res_type = pr_holder->pr_res_type; + pr_res_scope = pr_holder->pr_res_scope; + } + } + spin_unlock(&dev->dev_reservation_lock); + spin_lock(&pr_tmpl->registration_lock); list_for_each_entry_safe(pr_reg, pr_reg_tmp, &pr_tmpl->registration_list, pr_reg_list) { @@ -3920,14 +3993,20 @@ core_scsi3_pri_read_full_status(struct se_cmd *cmd) * reservation holder for PR_HOLDER bit. * * Also, if this registration is the reservation - * holder, fill in SCOPE and TYPE in the next byte. + * holder or there is an All Registrants reservation + * active, fill in SCOPE and TYPE in the next byte. */ if (pr_reg->pr_res_holder) { buf[off++] |= 0x01; buf[off++] = (pr_reg->pr_res_scope & 0xf0) | (pr_reg->pr_res_type & 0x0f); - } else + } else if (all_reg) { + buf[off++] |= 0x01; + buf[off++] = (pr_res_scope & 0xf0) | + (pr_res_type & 0x0f); + } else { off += 2; + } off += 4; /* Skip over reserved area */ /* diff --git a/drivers/target/target_core_pr.h b/drivers/target/target_core_pr.h index 2ee2936fa0bd..749fd7bb7510 100644 --- a/drivers/target/target_core_pr.h +++ b/drivers/target/target_core_pr.h @@ -60,7 +60,7 @@ extern int core_scsi3_alloc_aptpl_registration( unsigned char *, u16, u32, int, int, u8); extern int core_scsi3_check_aptpl_registration(struct se_device *, struct se_portal_group *, struct se_lun *, - struct se_lun_acl *); + struct se_node_acl *, u32); extern void core_scsi3_free_pr_reg_from_nacl(struct se_device *, struct se_node_acl *); extern void core_scsi3_free_all_registrations(struct se_device *); diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 0f199f6a0738..29f28808fc03 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -1111,7 +1111,7 @@ static u32 pscsi_get_device_type(struct se_device *dev) struct pscsi_dev_virt *pdv = PSCSI_DEV(dev); struct scsi_device *sd = pdv->pdv_sd; - return sd->type; + return (sd) ? sd->type : TYPE_NO_LUN; } static sector_t pscsi_get_blocks(struct se_device *dev) diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index 379033f5903b..68511e83486b 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -266,6 +266,8 @@ static inline unsigned long long transport_lba_64_ext(unsigned char *cdb) static sense_reason_t sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *ops) { + struct se_device *dev = cmd->se_dev; + sector_t end_lba = dev->transport->get_blocks(dev) + 1; unsigned int sectors = sbc_get_write_same_sectors(cmd); if ((flags[0] & 0x04) || (flags[0] & 0x02)) { @@ -279,6 +281,16 @@ sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *o sectors, cmd->se_dev->dev_attrib.max_write_same_len); return TCM_INVALID_CDB_FIELD; } + /* + * Sanity check for LBA wrap and request past end of device. + */ + if (((cmd->t_task_lba + sectors) < cmd->t_task_lba) || + ((cmd->t_task_lba + sectors) > end_lba)) { + pr_err("WRITE_SAME exceeds last lba %llu (lba %llu, sectors %u)\n", + (unsigned long long)end_lba, cmd->t_task_lba, sectors); + return TCM_ADDRESS_OUT_OF_RANGE; + } + /* We always have ANC_SUP == 0 so setting ANCHOR is always an error */ if (flags[0] & 0x10) { pr_warn("WRITE SAME with ANCHOR not supported\n"); @@ -910,23 +922,9 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) if (cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) { unsigned long long end_lba; - if (sectors > dev->dev_attrib.fabric_max_sectors) { - printk_ratelimited(KERN_ERR "SCSI OP %02xh with too" - " big sectors %u exceeds fabric_max_sectors:" - " %u\n", cdb[0], sectors, - dev->dev_attrib.fabric_max_sectors); - return TCM_INVALID_CDB_FIELD; - } - if (sectors > dev->dev_attrib.hw_max_sectors) { - printk_ratelimited(KERN_ERR "SCSI OP %02xh with too" - " big sectors %u exceeds backend hw_max_sectors:" - " %u\n", cdb[0], sectors, - dev->dev_attrib.hw_max_sectors); - return TCM_INVALID_CDB_FIELD; - } - end_lba = dev->transport->get_blocks(dev) + 1; - if (cmd->t_task_lba + sectors > end_lba) { + if (((cmd->t_task_lba + sectors) < cmd->t_task_lba) || + ((cmd->t_task_lba + sectors) > end_lba)) { pr_err("cmd exceeds last lba %llu " "(lba %llu, sectors %u)\n", end_lba, cmd->t_task_lba, sectors); diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c index fcdf98fc947c..12a74f646d38 100644 --- a/drivers/target/target_core_spc.c +++ b/drivers/target/target_core_spc.c @@ -503,7 +503,6 @@ static sense_reason_t spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf) { struct se_device *dev = cmd->se_dev; - u32 max_sectors; int have_tp = 0; int opt, min; @@ -537,9 +536,7 @@ spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf) /* * Set MAXIMUM TRANSFER LENGTH */ - max_sectors = min(dev->dev_attrib.fabric_max_sectors, - dev->dev_attrib.hw_max_sectors); - put_unaligned_be32(max_sectors, &buf[8]); + put_unaligned_be32(dev->dev_attrib.hw_max_sectors, &buf[8]); /* * Set OPTIMAL TRANSFER LENGTH diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c index c036595b17cf..fb8a1a12dda9 100644 --- a/drivers/target/target_core_tpg.c +++ b/drivers/target/target_core_tpg.c @@ -40,6 +40,7 @@ #include <target/target_core_fabric.h> #include "target_core_internal.h" +#include "target_core_pr.h" extern struct se_device *g_lun0_dev; @@ -166,6 +167,13 @@ void core_tpg_add_node_to_devs( core_enable_device_list_for_node(lun, NULL, lun->unpacked_lun, lun_access, acl, tpg); + /* + * Check to see if there are any existing persistent reservation + * APTPL pre-registrations that need to be enabled for this dynamic + * LUN ACL now.. + */ + core_scsi3_check_aptpl_registration(dev, tpg, lun, acl, + lun->unpacked_lun); spin_lock(&tpg->tpg_lun_lock); } spin_unlock(&tpg->tpg_lun_lock); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 24f527977ddb..9e54c0fe718d 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1855,8 +1855,7 @@ static void transport_complete_qf(struct se_cmd *cmd) if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) { trace_target_cmd_complete(cmd); ret = cmd->se_tfo->queue_status(cmd); - if (ret) - goto out; + goto out; } switch (cmd->data_direction) { @@ -2231,7 +2230,7 @@ transport_generic_new_cmd(struct se_cmd *cmd) * and let it call back once the write buffers are ready. */ target_add_to_state_list(cmd); - if (cmd->data_direction != DMA_TO_DEVICE) { + if (cmd->data_direction != DMA_TO_DEVICE || cmd->data_length == 0) { target_execute_cmd(cmd); return 0; } @@ -2328,6 +2327,10 @@ int target_get_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd, list_add_tail(&se_cmd->se_cmd_list, &se_sess->sess_cmd_list); out: spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); + + if (ret && ack_kref) + target_put_sess_cmd(se_sess, se_cmd); + return ret; } EXPORT_SYMBOL(target_get_sess_cmd); diff --git a/drivers/target/tcm_fc/tfc_io.c b/drivers/target/tcm_fc/tfc_io.c index e415af32115a..c67d3795db4a 100644 --- a/drivers/target/tcm_fc/tfc_io.c +++ b/drivers/target/tcm_fc/tfc_io.c @@ -346,7 +346,7 @@ void ft_invl_hw_context(struct ft_cmd *cmd) ep = fc_seq_exch(seq); if (ep) { lport = ep->lp; - if (lport && (ep->xid <= lport->lro_xid)) + if (lport && (ep->xid <= lport->lro_xid)) { /* * "ddp_done" trigger invalidation of HW * specific DDP context @@ -361,6 +361,7 @@ void ft_invl_hw_context(struct ft_cmd *cmd) * identified using ep->xid) */ cmd->was_ddp_setup = 0; + } } } } diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c index a084325f1386..6e75177915fa 100644 --- a/drivers/thermal/intel_powerclamp.c +++ b/drivers/thermal/intel_powerclamp.c @@ -435,7 +435,6 @@ static int clamp_thread(void *arg) * allowed. thus jiffies are updated properly. */ preempt_disable(); - tick_nohz_idle_enter(); /* mwait until target jiffies is reached */ while (time_before(jiffies, target_jiffies)) { unsigned long ecx = 1; @@ -451,7 +450,6 @@ static int clamp_thread(void *arg) start_critical_timings(); atomic_inc(&idle_wakeup_counter); } - tick_nohz_idle_exit(); preempt_enable(); } del_timer_sync(&wakeup_timer); diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c index 04b1be7fa018..4b2b999b7611 100644 --- a/drivers/thermal/of-thermal.c +++ b/drivers/thermal/of-thermal.c @@ -156,8 +156,8 @@ static int of_thermal_bind(struct thermal_zone_device *thermal, ret = thermal_zone_bind_cooling_device(thermal, tbp->trip_id, cdev, - tbp->min, - tbp->max); + tbp->max, + tbp->min); if (ret) return ret; } @@ -712,11 +712,12 @@ thermal_of_build_thermal_zone(struct device_node *np) } i = 0; - for_each_child_of_node(child, gchild) + for_each_child_of_node(child, gchild) { ret = thermal_of_populate_bind_params(gchild, &tz->tbps[i++], tz->trips, tz->ntrips); if (ret) goto free_tbps; + } finish: of_node_put(child); diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 71b0ec0c370d..284733e1fb6f 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -1824,10 +1824,10 @@ static int __init thermal_init(void) exit_netlink: genetlink_exit(); -unregister_governors: - thermal_unregister_governors(); unregister_class: class_unregister(&thermal_class); +unregister_governors: + thermal_unregister_governors(); error: idr_destroy(&thermal_tz_idr); idr_destroy(&thermal_cdev_idr); diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index 28ac3f3b7ec3..8ab46ad40f28 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -247,8 +247,6 @@ static void n_tty_write_wakeup(struct tty_struct *tty) static void n_tty_check_throttle(struct tty_struct *tty) { - if (tty->driver->type == TTY_DRIVER_TYPE_PTY) - return; /* * Check the remaining room for the input canonicalization * mode. We don't want to throttle the driver if we're in @@ -321,7 +319,8 @@ static void n_tty_check_unthrottle(struct tty_struct *tty) static inline void put_tty_queue(unsigned char c, struct n_tty_data *ldata) { - *read_buf_addr(ldata, ldata->read_head++) = c; + *read_buf_addr(ldata, ldata->read_head) = c; + ldata->read_head++; } /** @@ -1511,23 +1510,6 @@ n_tty_receive_char_lnext(struct tty_struct *tty, unsigned char c, char flag) n_tty_receive_char_flagged(tty, c, flag); } -/** - * n_tty_receive_buf - data receive - * @tty: terminal device - * @cp: buffer - * @fp: flag buffer - * @count: characters - * - * Called by the terminal driver when a block of characters has - * been received. This function must be called from soft contexts - * not from interrupt context. The driver is responsible for making - * calls one at a time and in order (or using flush_to_ldisc) - * - * n_tty_receive_buf()/producer path: - * claims non-exclusive termios_rwsem - * publishes read_head and canon_head - */ - static void n_tty_receive_buf_real_raw(struct tty_struct *tty, const unsigned char *cp, char *fp, int count) @@ -1683,24 +1665,85 @@ static void __receive_buf(struct tty_struct *tty, const unsigned char *cp, } } +/** + * n_tty_receive_buf_common - process input + * @tty: device to receive input + * @cp: input chars + * @fp: flags for each char (if NULL, all chars are TTY_NORMAL) + * @count: number of input chars in @cp + * + * Called by the terminal driver when a block of characters has + * been received. This function must be called from soft contexts + * not from interrupt context. The driver is responsible for making + * calls one at a time and in order (or using flush_to_ldisc) + * + * Returns the # of input chars from @cp which were processed. + * + * In canonical mode, the maximum line length is 4096 chars (including + * the line termination char); lines longer than 4096 chars are + * truncated. After 4095 chars, input data is still processed but + * not stored. Overflow processing ensures the tty can always + * receive more input until at least one line can be read. + * + * In non-canonical mode, the read buffer will only accept 4095 chars; + * this provides the necessary space for a newline char if the input + * mode is switched to canonical. + * + * Note it is possible for the read buffer to _contain_ 4096 chars + * in non-canonical mode: the read buffer could already contain the + * maximum canon line of 4096 chars when the mode is switched to + * non-canonical. + * + * n_tty_receive_buf()/producer path: + * claims non-exclusive termios_rwsem + * publishes commit_head or canon_head + */ static int n_tty_receive_buf_common(struct tty_struct *tty, const unsigned char *cp, char *fp, int count, int flow) { struct n_tty_data *ldata = tty->disc_data; - int room, n, rcvd = 0; + int room, n, rcvd = 0, overflow; down_read(&tty->termios_rwsem); while (1) { - room = receive_room(tty); + /* + * When PARMRK is set, each input char may take up to 3 chars + * in the read buf; reduce the buffer space avail by 3x + * + * If we are doing input canonicalization, and there are no + * pending newlines, let characters through without limit, so + * that erase characters will be handled. Other excess + * characters will be beeped. + * + * paired with store in *_copy_from_read_buf() -- guarantees + * the consumer has loaded the data in read_buf up to the new + * read_tail (so this producer will not overwrite unread data) + */ + size_t tail = ldata->read_tail; + + room = N_TTY_BUF_SIZE - (ldata->read_head - tail); + if (I_PARMRK(tty)) + room = (room + 2) / 3; + room--; + if (room <= 0) { + overflow = ldata->icanon && ldata->canon_head == tail; + if (overflow && room < 0) + ldata->read_head--; + room = overflow; + ldata->no_room = flow && !room; + } else + overflow = 0; + n = min(count, room); - if (!n) { - if (flow && !room) - ldata->no_room = 1; + if (!n) break; - } - __receive_buf(tty, cp, fp, n); + + /* ignore parity errors if handling overflow */ + if (!overflow || !fp || *fp != TTY_PARITY) + __receive_buf(tty, cp, fp, n); + cp += n; if (fp) fp += n; @@ -1709,7 +1752,17 @@ n_tty_receive_buf_common(struct tty_struct *tty, const unsigned char *cp, } tty->receive_room = room; - n_tty_check_throttle(tty); + + /* Unthrottle if handling overflow on pty */ + if (tty->driver->type == TTY_DRIVER_TYPE_PTY) { + if (overflow) { + tty_set_flow_change(tty, TTY_UNTHROTTLE_SAFE); + tty_unthrottle_safe(tty); + __tty_set_flow_change(tty, 0); + } + } else + n_tty_check_throttle(tty); + up_read(&tty->termios_rwsem); return rcvd; @@ -2416,12 +2469,17 @@ 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 (test_bit(TTY_OTHER_CLOSED, &tty->flags)) + mask |= POLLHUP; if (input_available_p(tty, 1)) mask |= POLLIN | POLLRDNORM; + else if (mask & POLLHUP) { + tty_flush_to_ldisc(tty); + 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/pty.c b/drivers/tty/pty.c index 25c9bc783722..e49616eeb1cc 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -209,6 +209,9 @@ static int pty_signal(struct tty_struct *tty, int sig) unsigned long flags; struct pid *pgrp; + if (sig != SIGINT && sig != SIGQUIT && sig != SIGTSTP) + return -EINVAL; + if (tty->link) { spin_lock_irqsave(&tty->link->ctrl_lock, flags); pgrp = get_pid(tty->link->pgrp); diff --git a/drivers/tty/serial/8250/8250_dma.c b/drivers/tty/serial/8250/8250_dma.c index ab9096dc3849..148ffe4c232f 100644 --- a/drivers/tty/serial/8250/8250_dma.c +++ b/drivers/tty/serial/8250/8250_dma.c @@ -192,21 +192,28 @@ int serial8250_request_dma(struct uart_8250_port *p) dma->rx_buf = dma_alloc_coherent(dma->rxchan->device->dev, dma->rx_size, &dma->rx_addr, GFP_KERNEL); - if (!dma->rx_buf) { - dma_release_channel(dma->rxchan); - dma_release_channel(dma->txchan); - return -ENOMEM; - } + if (!dma->rx_buf) + goto err; /* TX buffer */ dma->tx_addr = dma_map_single(dma->txchan->device->dev, p->port.state->xmit.buf, UART_XMIT_SIZE, DMA_TO_DEVICE); + if (dma_mapping_error(dma->txchan->device->dev, dma->tx_addr)) { + dma_free_coherent(dma->rxchan->device->dev, dma->rx_size, + dma->rx_buf, dma->rx_addr); + goto err; + } dev_dbg_ratelimited(p->port.dev, "got both dma channels\n"); return 0; +err: + dma_release_channel(dma->rxchan); + dma_release_channel(dma->txchan); + + return -ENOMEM; } EXPORT_SYMBOL_GPL(serial8250_request_dma); diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 0ff3e3624d4c..5892eab03874 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -66,7 +66,7 @@ static void moan_device(const char *str, struct pci_dev *dev) "Please send the output of lspci -vv, this\n" "message (0x%04x,0x%04x,0x%04x,0x%04x), the\n" "manufacturer and name of serial board or\n" - "modem board to rmk+serial@arm.linux.org.uk.\n", + "modem board to <linux-serial@vger.kernel.org>.\n", pci_name(dev), str, dev->vendor, dev->device, dev->subsystem_vendor, dev->subsystem_device); } @@ -1766,6 +1766,7 @@ pci_wch_ch353_setup(struct serial_private *priv, #define PCI_DEVICE_ID_COMMTECH_4222PCIE 0x0022 #define PCI_DEVICE_ID_BROADCOM_TRUMANAGE 0x160a #define PCI_DEVICE_ID_AMCC_ADDIDATA_APCI7800 0x818e +#define PCI_DEVICE_ID_INTEL_QRK_UART 0x0936 #define PCI_VENDOR_ID_SUNIX 0x1fd4 #define PCI_DEVICE_ID_SUNIX_1999 0x1999 @@ -1876,6 +1877,13 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = { .subdevice = PCI_ANY_ID, .setup = byt_serial_setup, }, + { + .vendor = PCI_VENDOR_ID_INTEL, + .device = PCI_DEVICE_ID_INTEL_QRK_UART, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = pci_default_setup, + }, /* * ITE */ @@ -2710,6 +2718,7 @@ enum pci_board_num_t { pbn_ADDIDATA_PCIe_8_3906250, pbn_ce4100_1_115200, pbn_byt, + pbn_qrk, pbn_omegapci, pbn_NETMOS9900_2s_115200, pbn_brcm_trumanage, @@ -3456,6 +3465,12 @@ static struct pciserial_board pci_boards[] = { .uart_offset = 0x80, .reg_shift = 2, }, + [pbn_qrk] = { + .flags = FL_BASE0, + .num_ports = 1, + .base_baud = 2764800, + .reg_shift = 2, + }, [pbn_omegapci] = { .flags = FL_BASE0, .num_ports = 8, @@ -5150,6 +5165,12 @@ static struct pci_device_id serial_pci_tbl[] = { pbn_byt }, /* + * Intel Quark x1000 + */ + { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_QRK_UART, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, + pbn_qrk }, + /* * Cronyx Omega PCI */ { PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_CRONYX_OMEGA, diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index ce352b81e230..0d3e6cb36748 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -2392,7 +2392,7 @@ static int atmel_serial_probe(struct platform_device *pdev) ret = atmel_init_port(port, pdev); if (ret) - goto err; + goto err_clear_bit; if (!atmel_use_pdc_rx(&port->uart)) { ret = -ENOMEM; @@ -2441,6 +2441,8 @@ err_alloc_ring: clk_put(port->clk); port->clk = NULL; } +err_clear_bit: + clear_bit(port->uart.line, atmel_ports_in_use); err: return ret; } diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 175f123f4f09..501c465feb59 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -362,6 +362,9 @@ static void lpuart_setup_watermark(struct lpuart_port *sport) writeb(val | UARTPFIFO_TXFE | UARTPFIFO_RXFE, sport->port.membase + UARTPFIFO); + /* explicitly clear RDRF */ + readb(sport->port.membase + UARTSR1); + /* flush Tx and Rx FIFO */ writeb(UARTCFIFO_TXFLUSH | UARTCFIFO_RXFLUSH, sport->port.membase + UARTCFIFO); diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c index db8434d3def9..f4e68b3fc39d 100644 --- a/drivers/tty/serial/omap-serial.c +++ b/drivers/tty/serial/omap-serial.c @@ -260,8 +260,16 @@ serial_omap_baud_is_mode16(struct uart_port *port, unsigned int baud) { unsigned int n13 = port->uartclk / (13 * baud); unsigned int n16 = port->uartclk / (16 * baud); - int baudAbsDiff13 = baud - (port->uartclk / (13 * n13)); - int baudAbsDiff16 = baud - (port->uartclk / (16 * n16)); + int baudAbsDiff13; + int baudAbsDiff16; + + if (n13 == 0) + n13 = 1; + if (n16 == 0) + n16 = 1; + + baudAbsDiff13 = baud - (port->uartclk / (13 * n13)); + baudAbsDiff16 = baud - (port->uartclk / (16 * n16)); if (baudAbsDiff13 < 0) baudAbsDiff13 = -baudAbsDiff13; if (baudAbsDiff16 < 0) diff --git a/drivers/tty/serial/samsung.c b/drivers/tty/serial/samsung.c index 9cd706df3b33..7d3a3f5cb5ba 100644 --- a/drivers/tty/serial/samsung.c +++ b/drivers/tty/serial/samsung.c @@ -544,11 +544,15 @@ static void s3c24xx_serial_pm(struct uart_port *port, unsigned int level, unsigned int old) { struct s3c24xx_uart_port *ourport = to_ourport(port); + int timeout = 10000; ourport->pm_level = level; switch (level) { case 3: + while (--timeout && !s3c24xx_serial_txempty_nofifo(port)) + udelay(100); + if (!IS_ERR(ourport->baudclk)) clk_disable_unprepare(ourport->baudclk); diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 25b8f6868788..27b5554e20d9 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -353,7 +353,7 @@ uart_get_baud_rate(struct uart_port *port, struct ktermios *termios, * The spd_hi, spd_vhi, spd_shi, spd_warp kludge... * Die! Die! Die! */ - if (baud == 38400) + if (try == 0 && baud == 38400) baud = altbaud; /* diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index d3448a90f0f9..39988fa91294 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -996,8 +996,8 @@ EXPORT_SYMBOL(start_tty); /* We limit tty time update visibility to every 8 seconds or so. */ static void tty_update_time(struct timespec *time) { - unsigned long sec = get_seconds() & ~7; - if ((long)(sec - time->tv_sec) > 0) + unsigned long sec = get_seconds(); + if (abs(sec - time->tv_sec) & ~7) time->tv_sec = sec; } @@ -1701,6 +1701,7 @@ int tty_release(struct inode *inode, struct file *filp) int pty_master, tty_closing, o_tty_closing, do_sleep; int idx; char buf[64]; + long timeout = 0; if (tty_paranoia_check(tty, inode, __func__)) return 0; @@ -1785,7 +1786,11 @@ int tty_release(struct inode *inode, struct file *filp) __func__, tty_name(tty, buf)); tty_unlock_pair(tty, o_tty); mutex_unlock(&tty_mutex); - schedule(); + schedule_timeout_killable(timeout); + if (timeout < 120 * HZ) + timeout = 2 * timeout + 1; + else + timeout = MAX_SCHEDULE_TIMEOUT; } /* diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c index 6fd60fece6b4..22da05d27009 100644 --- a/drivers/tty/tty_ioctl.c +++ b/drivers/tty/tty_ioctl.c @@ -217,11 +217,17 @@ void tty_wait_until_sent(struct tty_struct *tty, long timeout) #endif if (!timeout) timeout = MAX_SCHEDULE_TIMEOUT; + if (wait_event_interruptible_timeout(tty->write_wait, - !tty_chars_in_buffer(tty), timeout) >= 0) { - if (tty->ops->wait_until_sent) - tty->ops->wait_until_sent(tty, timeout); + !tty_chars_in_buffer(tty), timeout) < 0) { + return; } + + if (timeout == MAX_SCHEDULE_TIMEOUT) + timeout = 0; + + if (tty->ops->wait_until_sent) + tty->ops->wait_until_sent(tty, timeout); } EXPORT_SYMBOL(tty_wait_until_sent); diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 23b5d32954bf..693091ab726b 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -498,6 +498,7 @@ void invert_screen(struct vc_data *vc, int offset, int count, int viewed) #endif if (DO_UPDATE(vc)) do_update_region(vc, (unsigned long) p, count); + notify_update(vc); } /* used by selection: complement pointer position */ @@ -514,6 +515,7 @@ void complement_pos(struct vc_data *vc, int offset) scr_writew(old, screenpos(vc, old_offset, 1)); if (DO_UPDATE(vc)) vc->vc_sw->con_putc(vc, old, oldy, oldx); + notify_update(vc); } old_offset = offset; @@ -531,8 +533,8 @@ void complement_pos(struct vc_data *vc, int offset) oldy = (offset >> 1) / vc->vc_cols; vc->vc_sw->con_putc(vc, new, oldy, oldx); } + notify_update(vc); } - } static void insert_char(struct vc_data *vc, unsigned int nr) diff --git a/drivers/usb/chipidea/ci_hdrc_msm.c b/drivers/usb/chipidea/ci_hdrc_msm.c index 2d51d852b474..ca1123d415c5 100644 --- a/drivers/usb/chipidea/ci_hdrc_msm.c +++ b/drivers/usb/chipidea/ci_hdrc_msm.c @@ -20,13 +20,13 @@ static void ci_hdrc_msm_notify_event(struct ci_hdrc *ci, unsigned event) { struct device *dev = ci->gadget.dev.parent; - int val; switch (event) { case CI_HDRC_CONTROLLER_RESET_EVENT: dev_dbg(dev, "CI_HDRC_CONTROLLER_RESET_EVENT received\n"); writel(0, USB_AHBBURST); writel(0, USB_AHBMODE); + usb_phy_init(ci->transceiver); break; case CI_HDRC_CONTROLLER_STOPPED_EVENT: dev_dbg(dev, "CI_HDRC_CONTROLLER_STOPPED_EVENT received\n"); @@ -34,10 +34,7 @@ static void ci_hdrc_msm_notify_event(struct ci_hdrc *ci, unsigned event) * Put the transceiver in non-driving mode. Otherwise host * may not detect soft-disconnection. */ - val = usb_phy_io_read(ci->transceiver, ULPI_FUNC_CTRL); - val &= ~ULPI_FUNC_CTRL_OPMODE_MASK; - val |= ULPI_FUNC_CTRL_OPMODE_NONDRIVING; - usb_phy_io_write(ci->transceiver, val, ULPI_FUNC_CTRL); + usb_phy_notify_disconnect(ci->transceiver, USB_SPEED_UNKNOWN); break; default: dev_dbg(dev, "unknown ci_hdrc event\n"); diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index eabccd45f4e8..d7049c393a33 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -965,11 +965,12 @@ static void acm_tty_set_termios(struct tty_struct *tty, /* FIXME: Needs to clear unsupported bits in the termios */ acm->clocal = ((termios->c_cflag & CLOCAL) != 0); - if (!newline.dwDTERate) { + if (C_BAUD(tty) == B0) { newline.dwDTERate = acm->line.dwDTERate; newctrl &= ~ACM_CTRL_DTR; - } else + } else if (termios_old && (termios_old->c_cflag & CBAUD) == B0) { newctrl |= ACM_CTRL_DTR; + } if (newctrl != acm->ctrlout) acm_set_control(acm, acm->ctrlout = newctrl); @@ -1168,10 +1169,11 @@ next_desc: } else { control_interface = usb_ifnum_to_if(usb_dev, union_header->bMasterInterface0); data_interface = usb_ifnum_to_if(usb_dev, (data_interface_num = union_header->bSlaveInterface0)); - if (!control_interface || !data_interface) { - dev_dbg(&intf->dev, "no interfaces\n"); - return -ENODEV; - } + } + + if (!control_interface || !data_interface) { + dev_dbg(&intf->dev, "no interfaces\n"); + return -ENODEV; } if (data_interface_num != call_interface_num) @@ -1447,6 +1449,7 @@ alloc_fail8: &dev_attr_wCountryCodes); device_remove_file(&acm->control->dev, &dev_attr_iCountryCodeRelDate); + kfree(acm->country_codes); } device_remove_file(&acm->control->dev, &dev_attr_bmCapabilities); alloc_fail7: @@ -1672,6 +1675,7 @@ static const struct usb_device_id acm_ids[] = { { USB_DEVICE(0x0572, 0x1328), /* Shiro / Aztech USB MODEM UM-3100 */ .driver_info = NO_UNION_NORMAL, /* has no union descriptor */ }, + { USB_DEVICE(0x2184, 0x001c) }, /* GW Instek AFG-2225 */ { USB_DEVICE(0x22b8, 0x6425), /* Motorola MOTOMAGX phones */ }, /* Motorola H24 HSPA module: */ diff --git a/drivers/usb/core/buffer.c b/drivers/usb/core/buffer.c index 684ef70dc09d..506b969ea7fd 100644 --- a/drivers/usb/core/buffer.c +++ b/drivers/usb/core/buffer.c @@ -22,17 +22,25 @@ */ /* FIXME tune these based on pool statistics ... */ -static const size_t pool_max[HCD_BUFFER_POOLS] = { - /* platforms without dma-friendly caches might need to - * prevent cacheline sharing... - */ - 32, - 128, - 512, - PAGE_SIZE / 2 - /* bigger --> allocate pages */ +static size_t pool_max[HCD_BUFFER_POOLS] = { + 32, 128, 512, 2048, }; +void __init usb_init_pool_max(void) +{ + /* + * The pool_max values must never be smaller than + * ARCH_KMALLOC_MINALIGN. + */ + if (ARCH_KMALLOC_MINALIGN <= 32) + ; /* Original value is okay */ + else if (ARCH_KMALLOC_MINALIGN <= 64) + pool_max[0] = 64; + else if (ARCH_KMALLOC_MINALIGN <= 128) + pool_max[0] = 0; /* Don't use this pool */ + else + BUILD_BUG(); /* We don't allow this */ +} /* SETUP primitives */ diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 9ca77166d37e..45b7b96f9ed3 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -501,6 +501,7 @@ static void async_completed(struct urb *urb) as->status = urb->status; signr = as->signr; if (signr) { + memset(&sinfo, 0, sizeof(sinfo)); sinfo.si_signo = as->signr; sinfo.si_errno = as->status; sinfo.si_code = SI_ASYNCIO; @@ -2227,6 +2228,7 @@ static void usbdev_remove(struct usb_device *udev) wake_up_all(&ps->wait); list_del_init(&ps->list); if (ps->discsignr) { + memset(&sinfo, 0, sizeof(sinfo)); sinfo.si_signo = ps->discsignr; sinfo.si_errno = EPIPE; sinfo.si_code = SI_ASYNCIO; diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 2518c3250750..ee6c5562d296 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -1617,6 +1617,7 @@ static int unlink1(struct usb_hcd *hcd, struct urb *urb, int status) int usb_hcd_unlink_urb (struct urb *urb, int status) { struct usb_hcd *hcd; + struct usb_device *udev = urb->dev; int retval = -EIDRM; unsigned long flags; @@ -1628,20 +1629,19 @@ int usb_hcd_unlink_urb (struct urb *urb, int status) spin_lock_irqsave(&hcd_urb_unlink_lock, flags); if (atomic_read(&urb->use_count) > 0) { retval = 0; - usb_get_dev(urb->dev); + usb_get_dev(udev); } spin_unlock_irqrestore(&hcd_urb_unlink_lock, flags); if (retval == 0) { hcd = bus_to_hcd(urb->dev->bus); retval = unlink1(hcd, urb, status); - usb_put_dev(urb->dev); + if (retval == 0) + retval = -EINPROGRESS; + else if (retval != -EIDRM && retval != -EBUSY) + dev_dbg(&udev->dev, "hcd_unlink_urb %p fail %d\n", + urb, retval); + usb_put_dev(udev); } - - if (retval == 0) - retval = -EINPROGRESS; - else if (retval != -EIDRM && retval != -EBUSY) - dev_dbg(&urb->dev->dev, "hcd_unlink_urb %p fail %d\n", - urb, retval); return retval; } @@ -2057,6 +2057,8 @@ int usb_alloc_streams(struct usb_interface *interface, return -EINVAL; if (dev->speed != USB_SPEED_SUPER) return -EINVAL; + if (dev->state < USB_STATE_CONFIGURED) + return -ENODEV; /* Streams only apply to bulk endpoints. */ for (i = 0; i < num_eps; i++) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 6650df70bb35..d2bd9d7c8f4b 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -1948,8 +1948,10 @@ void usb_set_device_state(struct usb_device *udev, || new_state == USB_STATE_SUSPENDED) ; /* No change to wakeup settings */ else if (new_state == USB_STATE_CONFIGURED) - wakeup = udev->actconfig->desc.bmAttributes - & USB_CONFIG_ATT_WAKEUP; + wakeup = (udev->quirks & + USB_QUIRK_IGNORE_REMOTE_WAKEUP) ? 0 : + udev->actconfig->desc.bmAttributes & + USB_CONFIG_ATT_WAKEUP; else wakeup = 0; } @@ -4376,6 +4378,9 @@ check_highspeed (struct usb_hub *hub, struct usb_device *udev, int port1) struct usb_qualifier_descriptor *qual; int status; + if (udev->quirks & USB_QUIRK_DEVICE_QUALIFIER) + return; + qual = kmalloc (sizeof *qual, GFP_KERNEL); if (qual == NULL) return; @@ -4764,9 +4769,10 @@ static void hub_events(void) hub = list_entry(tmp, struct usb_hub, event_list); kref_get(&hub->kref); + hdev = hub->hdev; + usb_get_dev(hdev); spin_unlock_irq(&hub_event_lock); - hdev = hub->hdev; hub_dev = hub->intfdev; intf = to_usb_interface(hub_dev); dev_dbg(hub_dev, "state %d ports %d chg %04x evt %04x\n", @@ -4979,6 +4985,7 @@ static void hub_events(void) usb_autopm_put_interface(intf); loop_disconnected: usb_unlock_device(hdev); + usb_put_dev(hdev); kref_put(&hub->kref, hub_release); } /* end while (1) */ diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 739ee8e8bdfd..b195fdb1effc 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -44,6 +44,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* Creative SB Audigy 2 NX */ { USB_DEVICE(0x041e, 0x3020), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Microsoft Wireless Laser Mouse 6000 Receiver */ + { USB_DEVICE(0x045e, 0x00e1), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Microsoft LifeCam-VX700 v2.0 */ { USB_DEVICE(0x045e, 0x0770), .driver_info = USB_QUIRK_RESET_RESUME }, @@ -93,6 +96,16 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x04e8, 0x6601), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, + /* Elan Touchscreen */ + { USB_DEVICE(0x04f3, 0x0089), .driver_info = + USB_QUIRK_DEVICE_QUALIFIER }, + + { USB_DEVICE(0x04f3, 0x009b), .driver_info = + USB_QUIRK_DEVICE_QUALIFIER }, + + { USB_DEVICE(0x04f3, 0x016f), .driver_info = + USB_QUIRK_DEVICE_QUALIFIER }, + /* Roland SC-8820 */ { USB_DEVICE(0x0582, 0x0007), .driver_info = USB_QUIRK_RESET_RESUME }, @@ -160,6 +173,10 @@ static const struct usb_device_id usb_interface_quirk_list[] = { { USB_VENDOR_AND_INTERFACE_INFO(0x046d, USB_CLASS_VIDEO, 1, 0), .driver_info = USB_QUIRK_RESET_RESUME }, + /* ASUS Base Station(T100) */ + { USB_DEVICE(0x0b05, 0x17e0), .driver_info = + USB_QUIRK_IGNORE_REMOTE_WAKEUP }, + { } /* terminating entry must be last */ }; diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c index 4d1144990d4c..a92273026ecc 100644 --- a/drivers/usb/core/usb.c +++ b/drivers/usb/core/usb.c @@ -1050,6 +1050,7 @@ static int __init usb_init(void) pr_info("%s: USB support disabled\n", usbcore_name); return 0; } + usb_init_pool_max(); retval = usb_debugfs_init(); if (retval) diff --git a/drivers/usb/dwc3/Kconfig b/drivers/usb/dwc3/Kconfig index e2c730fc9a90..b78ffc281d36 100644 --- a/drivers/usb/dwc3/Kconfig +++ b/drivers/usb/dwc3/Kconfig @@ -90,4 +90,11 @@ config USB_DWC3_VERBOSE help Say Y here to enable verbose debugging messages on DWC3 Driver. +config DWC3_HOST_USB3_LPM_ENABLE + bool "Enable USB3 LPM Capability" + depends on USB_DWC3_HOST=y || USB_DWC3_DUAL_ROLE=y + default n + help + Select this when you want to enable USB3 LPM with dwc3 xhci host. + endif diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index a49217ae3533..fc06c52ecc7e 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -61,9 +61,10 @@ void dwc3_set_mode(struct dwc3 *dwc, u32 mode) * dwc3_core_soft_reset - Issues core soft reset and PHY reset * @dwc: pointer to our context structure */ -static void dwc3_core_soft_reset(struct dwc3 *dwc) +static int dwc3_core_soft_reset(struct dwc3 *dwc) { u32 reg; + int ret; /* Before Resetting PHY, put Core in Reset */ reg = dwc3_readl(dwc->regs, DWC3_GCTL); @@ -82,6 +83,15 @@ static void dwc3_core_soft_reset(struct dwc3 *dwc) usb_phy_init(dwc->usb2_phy); usb_phy_init(dwc->usb3_phy); + ret = phy_init(dwc->usb2_generic_phy); + if (ret < 0) + return ret; + + ret = phy_init(dwc->usb3_generic_phy); + if (ret < 0) { + phy_exit(dwc->usb2_generic_phy); + return ret; + } mdelay(100); /* Clear USB3 PHY reset */ @@ -100,6 +110,8 @@ static void dwc3_core_soft_reset(struct dwc3 *dwc) reg = dwc3_readl(dwc->regs, DWC3_GCTL); reg &= ~DWC3_GCTL_CORESOFTRESET; dwc3_writel(dwc->regs, DWC3_GCTL, reg); + + return 0; } /** @@ -242,6 +254,90 @@ static void dwc3_event_buffers_cleanup(struct dwc3 *dwc) } } +static int dwc3_alloc_scratch_buffers(struct dwc3 *dwc) +{ + if (!dwc->has_hibernation) + return 0; + + if (!dwc->nr_scratch) + return 0; + + dwc->scratchbuf = kmalloc_array(dwc->nr_scratch, + DWC3_SCRATCHBUF_SIZE, GFP_KERNEL); + if (!dwc->scratchbuf) + return -ENOMEM; + + return 0; +} + +static int dwc3_setup_scratch_buffers(struct dwc3 *dwc) +{ + dma_addr_t scratch_addr; + u32 param; + int ret; + + if (!dwc->has_hibernation) + return 0; + + if (!dwc->nr_scratch) + return 0; + + /* should never fall here */ + if (!WARN_ON(dwc->scratchbuf)) + return 0; + + scratch_addr = dma_map_single(dwc->dev, dwc->scratchbuf, + dwc->nr_scratch * DWC3_SCRATCHBUF_SIZE, + DMA_BIDIRECTIONAL); + if (dma_mapping_error(dwc->dev, scratch_addr)) { + dev_err(dwc->dev, "failed to map scratch buffer\n"); + ret = -EFAULT; + goto err0; + } + + dwc->scratch_addr = scratch_addr; + + param = lower_32_bits(scratch_addr); + + ret = dwc3_send_gadget_generic_command(dwc, + DWC3_DGCMD_SET_SCRATCHPAD_ADDR_LO, param); + if (ret < 0) + goto err1; + + param = upper_32_bits(scratch_addr); + + ret = dwc3_send_gadget_generic_command(dwc, + DWC3_DGCMD_SET_SCRATCHPAD_ADDR_HI, param); + if (ret < 0) + goto err1; + + return 0; + +err1: + dma_unmap_single(dwc->dev, dwc->scratch_addr, dwc->nr_scratch * + DWC3_SCRATCHBUF_SIZE, DMA_BIDIRECTIONAL); + +err0: + return ret; +} + +static void dwc3_free_scratch_buffers(struct dwc3 *dwc) +{ + if (!dwc->has_hibernation) + return; + + if (!dwc->nr_scratch) + return; + + /* should never fall here */ + if (!WARN_ON(dwc->scratchbuf)) + return; + + dma_unmap_single(dwc->dev, dwc->scratch_addr, dwc->nr_scratch * + DWC3_SCRATCHBUF_SIZE, DMA_BIDIRECTIONAL); + kfree(dwc->scratchbuf); +} + static void dwc3_core_num_eps(struct dwc3 *dwc) { struct dwc3_hwparams *parms = &dwc->hwparams; @@ -277,6 +373,7 @@ static void dwc3_cache_hwparams(struct dwc3 *dwc) static int dwc3_core_init(struct dwc3 *dwc) { unsigned long timeout; + u32 hwparams4 = dwc->hwparams.hwparams4; u32 reg; int ret; @@ -306,7 +403,9 @@ static int dwc3_core_init(struct dwc3 *dwc) cpu_relax(); } while (true); - dwc3_core_soft_reset(dwc); + ret = dwc3_core_soft_reset(dwc); + if (ret) + goto err0; reg = dwc3_readl(dwc->regs, DWC3_GCTL); reg &= ~DWC3_GCTL_SCALEDOWN_MASK; @@ -314,7 +413,29 @@ static int dwc3_core_init(struct dwc3 *dwc) switch (DWC3_GHWPARAMS1_EN_PWROPT(dwc->hwparams.hwparams1)) { case DWC3_GHWPARAMS1_EN_PWROPT_CLK: - reg &= ~DWC3_GCTL_DSBLCLKGTNG; + /** + * WORKAROUND: DWC3 revisions between 2.10a and 2.50a have an + * issue which would cause xHCI compliance tests to fail. + * + * Because of that we cannot enable clock gating on such + * configurations. + * + * Refers to: + * + * STAR#9000588375: Clock Gating, SOF Issues when ref_clk-Based + * SOF/ITP Mode Used + */ + if ((dwc->dr_mode == USB_DR_MODE_HOST || + dwc->dr_mode == USB_DR_MODE_OTG) && + (dwc->revision >= DWC3_REVISION_210A && + dwc->revision <= DWC3_REVISION_250A)) + reg |= DWC3_GCTL_DSBLCLKGTNG | DWC3_GCTL_SOFITPSYNC; + else + reg &= ~DWC3_GCTL_DSBLCLKGTNG; + break; + case DWC3_GHWPARAMS1_EN_PWROPT_HIB: + /* enable hibernation here */ + dwc->nr_scratch = DWC3_GHWPARAMS4_HIBER_SCRATCHBUFS(hwparams4); break; default: dev_dbg(dwc->dev, "No power optimization available\n"); @@ -333,16 +454,34 @@ static int dwc3_core_init(struct dwc3 *dwc) dwc3_writel(dwc->regs, DWC3_GCTL, reg); + ret = dwc3_alloc_scratch_buffers(dwc); + if (ret) + goto err1; + + ret = dwc3_setup_scratch_buffers(dwc); + if (ret) + goto err2; + return 0; +err2: + dwc3_free_scratch_buffers(dwc); + +err1: + usb_phy_shutdown(dwc->usb2_phy); + usb_phy_shutdown(dwc->usb3_phy); + err0: return ret; } static void dwc3_core_exit(struct dwc3 *dwc) { + dwc3_free_scratch_buffers(dwc); usb_phy_shutdown(dwc->usb2_phy); usb_phy_shutdown(dwc->usb3_phy); + phy_exit(dwc->usb2_generic_phy); + phy_exit(dwc->usb3_generic_phy); } #define DWC3_ALIGN_MASK (16 - 1) @@ -411,32 +550,52 @@ static int dwc3_probe(struct platform_device *pdev) if (IS_ERR(dwc->usb2_phy)) { ret = PTR_ERR(dwc->usb2_phy); - - /* - * if -ENXIO is returned, it means PHY layer wasn't - * enabled, so it makes no sense to return -EPROBE_DEFER - * in that case, since no PHY driver will ever probe. - */ - if (ret == -ENXIO) + if (ret == -ENXIO || ret == -ENODEV) { + dwc->usb2_phy = NULL; + } else if (ret == -EPROBE_DEFER) { return ret; - - dev_err(dev, "no usb2 phy configured\n"); - return -EPROBE_DEFER; + } else { + dev_err(dev, "no usb2 phy configured\n"); + return ret; + } } if (IS_ERR(dwc->usb3_phy)) { ret = PTR_ERR(dwc->usb3_phy); + if (ret == -ENXIO || ret == -ENODEV) { + dwc->usb3_phy = NULL; + } else if (ret == -EPROBE_DEFER) { + return ret; + } else { + dev_err(dev, "no usb3 phy configured\n"); + return ret; + } + } - /* - * if -ENXIO is returned, it means PHY layer wasn't - * enabled, so it makes no sense to return -EPROBE_DEFER - * in that case, since no PHY driver will ever probe. - */ - if (ret == -ENXIO) + dwc->usb2_generic_phy = devm_phy_get(dev, "usb2-phy"); + if (IS_ERR(dwc->usb2_generic_phy)) { + ret = PTR_ERR(dwc->usb2_generic_phy); + if (ret == -ENOSYS || ret == -ENODEV) { + dwc->usb2_generic_phy = NULL; + } else if (ret == -EPROBE_DEFER) { return ret; + } else { + dev_err(dev, "no usb2 phy configured\n"); + return ret; + } + } - dev_err(dev, "no usb3 phy configured\n"); - return -EPROBE_DEFER; + dwc->usb3_generic_phy = devm_phy_get(dev, "usb3-phy"); + if (IS_ERR(dwc->usb3_generic_phy)) { + ret = PTR_ERR(dwc->usb3_generic_phy); + if (ret == -ENOSYS || ret == -ENODEV) { + dwc->usb3_generic_phy = NULL; + } else if (ret == -EPROBE_DEFER) { + return ret; + } else { + dev_err(dev, "no usb3 phy configured\n"); + return ret; + } } dwc->xhci_resources[0].start = res->start; @@ -479,6 +638,14 @@ static int dwc3_probe(struct platform_device *pdev) goto err0; } + if (IS_ENABLED(CONFIG_USB_DWC3_HOST)) + dwc->dr_mode = USB_DR_MODE_HOST; + else if (IS_ENABLED(CONFIG_USB_DWC3_GADGET)) + dwc->dr_mode = USB_DR_MODE_PERIPHERAL; + + if (dwc->dr_mode == USB_DR_MODE_UNKNOWN) + dwc->dr_mode = USB_DR_MODE_OTG; + ret = dwc3_core_init(dwc); if (ret) { dev_err(dev, "failed to initialize core\n"); @@ -487,21 +654,20 @@ static int dwc3_probe(struct platform_device *pdev) usb_phy_set_suspend(dwc->usb2_phy, 0); usb_phy_set_suspend(dwc->usb3_phy, 0); + ret = phy_power_on(dwc->usb2_generic_phy); + if (ret < 0) + goto err1; + + ret = phy_power_on(dwc->usb3_generic_phy); + if (ret < 0) + goto err_usb2phy_power; ret = dwc3_event_buffers_setup(dwc); if (ret) { dev_err(dwc->dev, "failed to setup event buffers\n"); - goto err1; + goto err_usb3phy_power; } - if (IS_ENABLED(CONFIG_USB_DWC3_HOST)) - dwc->dr_mode = USB_DR_MODE_HOST; - else if (IS_ENABLED(CONFIG_USB_DWC3_GADGET)) - dwc->dr_mode = USB_DR_MODE_PERIPHERAL; - - if (dwc->dr_mode == USB_DR_MODE_UNKNOWN) - dwc->dr_mode = USB_DR_MODE_OTG; - switch (dwc->dr_mode) { case USB_DR_MODE_PERIPHERAL: dwc3_set_mode(dwc, DWC3_GCTL_PRTCAP_DEVICE); @@ -568,6 +734,12 @@ err3: err2: dwc3_event_buffers_cleanup(dwc); +err_usb3phy_power: + phy_power_off(dwc->usb3_generic_phy); + +err_usb2phy_power: + phy_power_off(dwc->usb2_generic_phy); + err1: usb_phy_set_suspend(dwc->usb2_phy, 1); usb_phy_set_suspend(dwc->usb3_phy, 1); @@ -583,12 +755,6 @@ static int dwc3_remove(struct platform_device *pdev) { struct dwc3 *dwc = platform_get_drvdata(pdev); - usb_phy_set_suspend(dwc->usb2_phy, 1); - usb_phy_set_suspend(dwc->usb3_phy, 1); - - pm_runtime_put_sync(&pdev->dev); - pm_runtime_disable(&pdev->dev); - dwc3_debugfs_exit(dwc); switch (dwc->dr_mode) { @@ -609,8 +775,18 @@ static int dwc3_remove(struct platform_device *pdev) dwc3_event_buffers_cleanup(dwc); dwc3_free_event_buffers(dwc); + + usb_phy_set_suspend(dwc->usb2_phy, 1); + usb_phy_set_suspend(dwc->usb3_phy, 1); + + phy_power_off(dwc->usb2_generic_phy); + phy_power_off(dwc->usb3_generic_phy); + dwc3_core_exit(dwc); + pm_runtime_put_sync(&pdev->dev); + pm_runtime_disable(&pdev->dev); + return 0; } @@ -645,6 +821,7 @@ static void dwc3_complete(struct device *dev) spin_lock_irqsave(&dwc->lock, flags); + dwc3_event_buffers_setup(dwc); switch (dwc->dr_mode) { case USB_DR_MODE_PERIPHERAL: case USB_DR_MODE_OTG: @@ -652,7 +829,6 @@ static void dwc3_complete(struct device *dev) /* FALLTHROUGH */ case USB_DR_MODE_HOST: default: - dwc3_event_buffers_setup(dwc); break; } @@ -682,6 +858,8 @@ static int dwc3_suspend(struct device *dev) usb_phy_shutdown(dwc->usb3_phy); usb_phy_shutdown(dwc->usb2_phy); + phy_exit(dwc->usb2_generic_phy); + phy_exit(dwc->usb3_generic_phy); return 0; } @@ -690,9 +868,17 @@ static int dwc3_resume(struct device *dev) { struct dwc3 *dwc = dev_get_drvdata(dev); unsigned long flags; + int ret; usb_phy_init(dwc->usb3_phy); usb_phy_init(dwc->usb2_phy); + ret = phy_init(dwc->usb2_generic_phy); + if (ret < 0) + return ret; + + ret = phy_init(dwc->usb3_generic_phy); + if (ret < 0) + goto err_usb2phy_init; spin_lock_irqsave(&dwc->lock, flags); @@ -716,6 +902,11 @@ static int dwc3_resume(struct device *dev) pm_runtime_enable(dev); return 0; + +err_usb2phy_init: + phy_exit(dwc->usb2_generic_phy); + + return ret; } static const struct dev_pm_ops dwc3_dev_pm_ops = { diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 546e67a2e4cd..b451900ad5c7 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -31,11 +31,14 @@ #include <linux/usb/gadget.h> #include <linux/usb/otg.h> +#include <linux/phy/phy.h> + /* Global constants */ #define DWC3_EP0_BOUNCE_SIZE 512 #define DWC3_ENDPOINTS_NUM 32 #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) @@ -157,6 +160,7 @@ #define DWC3_GCTL_PRTCAP_OTG 3 #define DWC3_GCTL_CORESOFTRESET (1 << 11) +#define DWC3_GCTL_SOFITPSYNC (1 << 10) #define DWC3_GCTL_SCALEDOWN(n) ((n) << 4) #define DWC3_GCTL_SCALEDOWN_MASK DWC3_GCTL_SCALEDOWN(3) #define DWC3_GCTL_DISSCRAMBLE (1 << 3) @@ -598,6 +602,7 @@ struct dwc3_scratchpad_array { * @ep0_trb: dma address of ep0_trb * @ep0_usb_req: dummy req used while handling STD USB requests * @ep0_bounce_addr: dma address of ep0_bounce + * @scratch_addr: dma address of scratchbuf * @lock: for synchronizing * @dev: pointer to our struct device * @xhci: pointer to our xHCI child @@ -606,6 +611,7 @@ struct dwc3_scratchpad_array { * @gadget_driver: pointer to the gadget driver * @regs: base address for our registers * @regs_size: address space size + * @nr_scratch: number of scratch buffers * @num_event_buffers: calculated number of event buffers * @u1u2: only used on revisions <1.83a for workaround * @maximum_speed: maximum speed requested (mainly for testing purposes) @@ -613,16 +619,10 @@ struct dwc3_scratchpad_array { * @dr_mode: requested mode of operation * @usb2_phy: pointer to USB2 PHY * @usb3_phy: pointer to USB3 PHY + * @usb2_generic_phy: pointer to USB2 PHY + * @usb3_generic_phy: pointer to USB3 PHY * @dcfg: saved contents of DCFG register * @gctl: saved contents of GCTL register - * @is_selfpowered: true when we are selfpowered - * @three_stage_setup: set if we perform a three phase setup - * @ep0_bounced: true when we used bounce buffer - * @ep0_expect_in: true when we expect a DATA IN transfer - * @start_config_issued: true when StartConfig command has been issued - * @setup_packet_pending: true when there's a Setup Packet in FIFO. Workaround - * @needs_fifo_resize: not all users might want fifo resizing, flag it - * @resize_fifos: tells us it's ok to reconfigure our TxFIFO sizes. * @isoch_delay: wValue from Set Isochronous Delay request; * @u2sel: parameter from Set SEL request. * @u2pel: parameter from Set SEL request. @@ -637,15 +637,31 @@ struct dwc3_scratchpad_array { * @mem: points to start of memory which is used for this struct. * @hwparams: copy of hwparams registers * @root: debugfs root folder pointer + * @regset: debugfs pointer to regdump file + * @test_mode: true when we're entering a USB test mode + * @test_mode_nr: test feature selector + * @delayed_status: true when gadget driver asks for delayed status + * @ep0_bounced: true when we used bounce buffer + * @ep0_expect_in: true when we expect a DATA IN transfer + * @has_hibernation: true when dwc3 was configured with Hibernation + * @is_selfpowered: true when we are selfpowered + * @needs_fifo_resize: not all users might want fifo resizing, flag it + * @pullups_connected: true when Run/Stop bit is set + * @resize_fifos: tells us it's ok to reconfigure our TxFIFO sizes. + * @setup_packet_pending: true when there's a Setup Packet in FIFO. Workaround + * @start_config_issued: true when StartConfig command has been issued + * @three_stage_setup: set if we perform a three phase setup */ struct dwc3 { struct usb_ctrlrequest *ctrl_req; struct dwc3_trb *ep0_trb; void *ep0_bounce; + void *scratchbuf; u8 *setup_buf; dma_addr_t ctrl_req_addr; dma_addr_t ep0_trb_addr; dma_addr_t ep0_bounce_addr; + dma_addr_t scratch_addr; struct dwc3_request ep0_usb_req; /* device lock */ @@ -665,6 +681,9 @@ struct dwc3 { struct usb_phy *usb2_phy; struct usb_phy *usb3_phy; + struct phy *usb2_generic_phy; + struct phy *usb3_generic_phy; + void __iomem *regs; size_t regs_size; @@ -674,6 +693,7 @@ struct dwc3 { u32 dcfg; u32 gctl; + u32 nr_scratch; u32 num_event_buffers; u32 u1u2; u32 maximum_speed; @@ -696,17 +716,6 @@ struct dwc3 { #define DWC3_REVISION_240A 0x5533240a #define DWC3_REVISION_250A 0x5533250a - unsigned is_selfpowered:1; - unsigned three_stage_setup:1; - unsigned ep0_bounced:1; - unsigned ep0_expect_in:1; - unsigned start_config_issued:1; - unsigned setup_packet_pending:1; - unsigned delayed_status:1; - unsigned needs_fifo_resize:1; - unsigned resize_fifos:1; - unsigned pullups_connected:1; - enum dwc3_ep0_next ep0_next_event; enum dwc3_ep0_state ep0state; enum dwc3_link_state link_state; @@ -730,6 +739,18 @@ struct dwc3 { u8 test_mode; u8 test_mode_nr; + + unsigned delayed_status:1; + unsigned ep0_bounced:1; + unsigned ep0_expect_in:1; + unsigned has_hibernation:1; + unsigned is_selfpowered:1; + unsigned needs_fifo_resize:1; + unsigned pullups_connected:1; + unsigned resize_fifos:1; + unsigned setup_packet_pending:1; + unsigned start_config_issued:1; + unsigned three_stage_setup:1; }; /* -------------------------------------------------------------------------- */ diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c index b269dbd47fc4..cfca302d3d88 100644 --- a/drivers/usb/dwc3/dwc3-omap.c +++ b/drivers/usb/dwc3/dwc3-omap.c @@ -211,6 +211,18 @@ static void dwc3_omap_write_irq0_set(struct dwc3_omap *omap, u32 value) omap->irq0_offset, value); } +static void dwc3_omap_write_irqmisc_clr(struct dwc3_omap *omap, u32 value) +{ + dwc3_omap_writel(omap->base, USBOTGSS_IRQENABLE_CLR_MISC + + omap->irqmisc_offset, value); +} + +static void dwc3_omap_write_irq0_clr(struct dwc3_omap *omap, u32 value) +{ + dwc3_omap_writel(omap->base, USBOTGSS_IRQENABLE_CLR_0 - + omap->irq0_offset, value); +} + static void dwc3_omap_set_mailbox(struct dwc3_omap *omap, enum omap_dwc3_vbus_id_status status) { @@ -351,9 +363,23 @@ static void dwc3_omap_enable_irqs(struct dwc3_omap *omap) static void dwc3_omap_disable_irqs(struct dwc3_omap *omap) { + u32 reg; + /* disable all IRQs */ - dwc3_omap_write_irqmisc_set(omap, 0x00); - dwc3_omap_write_irq0_set(omap, 0x00); + reg = USBOTGSS_IRQO_COREIRQ_ST; + dwc3_omap_write_irq0_clr(omap, reg); + + reg = (USBOTGSS_IRQMISC_OEVT | + USBOTGSS_IRQMISC_DRVVBUS_RISE | + USBOTGSS_IRQMISC_CHRGVBUS_RISE | + USBOTGSS_IRQMISC_DISCHRGVBUS_RISE | + USBOTGSS_IRQMISC_IDPULLUP_RISE | + USBOTGSS_IRQMISC_DRVVBUS_FALL | + USBOTGSS_IRQMISC_CHRGVBUS_FALL | + USBOTGSS_IRQMISC_DISCHRGVBUS_FALL | + USBOTGSS_IRQMISC_IDPULLUP_FALL); + + dwc3_omap_write_irqmisc_clr(omap, reg); } static u64 dwc3_omap_dma_mask = DMA_BIT_MASK(32); @@ -582,9 +608,9 @@ static int dwc3_omap_remove(struct platform_device *pdev) if (omap->extcon_id_dev.edev) extcon_unregister_interest(&omap->extcon_id_dev); dwc3_omap_disable_irqs(omap); + device_for_each_child(&pdev->dev, NULL, dwc3_omap_remove_core); pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); - device_for_each_child(&pdev->dev, NULL, dwc3_omap_remove_core); return 0; } diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index 21a352079bc2..0985ff715c0c 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -251,7 +251,7 @@ static void dwc3_ep0_stall_and_restart(struct dwc3 *dwc) /* stall is always issued on EP0 */ dep = dwc->eps[0]; - __dwc3_gadget_ep_set_halt(dep, 1); + __dwc3_gadget_ep_set_halt(dep, 1, false); dep->flags = DWC3_EP_ENABLED; dwc->delayed_status = false; @@ -461,7 +461,7 @@ static int dwc3_ep0_handle_feature(struct dwc3 *dwc, return -EINVAL; if (set == 0 && (dep->flags & DWC3_EP_WEDGE)) break; - ret = __dwc3_gadget_ep_set_halt(dep, set); + ret = __dwc3_gadget_ep_set_halt(dep, set, true); if (ret) return -EINVAL; break; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 09e9619ae381..e99a6986cab6 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -532,12 +532,11 @@ static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep, if (!usb_endpoint_xfer_isoc(desc)) return 0; - memset(&trb_link, 0, sizeof(trb_link)); - /* Link TRB for ISOC. The HWO bit is never reset */ trb_st_hw = &dep->trb_pool[0]; trb_link = &dep->trb_pool[DWC3_TRB_NUM - 1]; + memset(trb_link, 0, sizeof(*trb_link)); trb_link->bpl = lower_32_bits(dwc3_trb_dma_offset(dep, trb_st_hw)); trb_link->bph = upper_32_bits(dwc3_trb_dma_offset(dep, trb_st_hw)); @@ -588,7 +587,7 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep) /* make sure HW endpoint isn't stalled */ if (dep->flags & DWC3_EP_STALL) - __dwc3_gadget_ep_set_halt(dep, 0); + __dwc3_gadget_ep_set_halt(dep, 0, false); reg = dwc3_readl(dwc->regs, DWC3_DALEPENA); reg &= ~DWC3_DALEPENA_EP(dep->number); @@ -888,8 +887,7 @@ static void dwc3_prepare_trbs(struct dwc3_ep *dep, bool starting) if (i == (request->num_mapped_sgs - 1) || sg_is_last(s)) { - if (list_is_last(&req->list, - &dep->request_list)) + if (list_empty(&dep->request_list)) last_one = true; chain = false; } @@ -907,6 +905,9 @@ static void dwc3_prepare_trbs(struct dwc3_ep *dep, bool starting) if (last_one) break; } + + if (last_one) + break; } else { dma = req->request.dma; length = req->request.length; @@ -1186,7 +1187,7 @@ out0: return ret; } -int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value) +int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol) { struct dwc3_gadget_ep_cmd_params params; struct dwc3 *dwc = dep->dwc; @@ -1195,6 +1196,14 @@ int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value) memset(¶ms, 0x00, sizeof(params)); if (value) { + if (!protocol && ((dep->direction && dep->flags & DWC3_EP_BUSY) || + (!list_empty(&dep->req_queued) || + !list_empty(&dep->request_list)))) { + dev_dbg(dwc->dev, "%s: pending request, cannot halt\n", + dep->name); + return -EAGAIN; + } + ret = dwc3_send_gadget_ep_cmd(dwc, dep->number, DWC3_DEPCMD_SETSTALL, ¶ms); if (ret) @@ -1234,7 +1243,7 @@ static int dwc3_gadget_ep_set_halt(struct usb_ep *ep, int value) goto out; } - ret = __dwc3_gadget_ep_set_halt(dep, value); + ret = __dwc3_gadget_ep_set_halt(dep, value, false); out: spin_unlock_irqrestore(&dwc->lock, flags); @@ -1254,7 +1263,7 @@ static int dwc3_gadget_ep_set_wedge(struct usb_ep *ep) if (dep->number == 0 || dep->number == 1) return dwc3_gadget_ep0_set_halt(ep, 1); else - return dwc3_gadget_ep_set_halt(ep, 1); + return __dwc3_gadget_ep_set_halt(dep, 1, false); } /* -------------------------------------------------------------------------- */ @@ -2385,6 +2394,30 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc, dev_vdbg(dwc->dev, "%s link %d\n", __func__, dwc->link_state); } +static void dwc3_gadget_hibernation_interrupt(struct dwc3 *dwc, + unsigned int evtinfo) +{ + unsigned int is_ss = evtinfo & BIT(4); + + /** + * WORKAROUND: DWC3 revison 2.20a with hibernation support + * have a known issue which can cause USB CV TD.9.23 to fail + * randomly. + * + * Because of this issue, core could generate bogus hibernation + * events which SW needs to ignore. + * + * Refers to: + * + * STAR#9000546576: Device Mode Hibernation: Issue in USB 2.0 + * Device Fallback from SuperSpeed + */ + if (is_ss ^ (dwc->speed == USB_SPEED_SUPER)) + return; + + /* enter hibernation here */ +} + static void dwc3_gadget_interrupt(struct dwc3 *dwc, const struct dwc3_event_devt *event) { @@ -2401,6 +2434,13 @@ static void dwc3_gadget_interrupt(struct dwc3 *dwc, case DWC3_DEVICE_EVENT_WAKEUP: dwc3_gadget_wakeup_interrupt(dwc); break; + case DWC3_DEVICE_EVENT_HIBER_REQ: + if (dev_WARN_ONCE(dwc->dev, !dwc->has_hibernation, + "unexpected hibernation event\n")) + break; + + dwc3_gadget_hibernation_interrupt(dwc, event->event_info); + break; case DWC3_DEVICE_EVENT_LINK_STATUS_CHANGE: dwc3_gadget_linksts_change_interrupt(dwc, event->event_info); break; diff --git a/drivers/usb/dwc3/gadget.h b/drivers/usb/dwc3/gadget.h index a0ee75b68a80..ac62558231be 100644 --- a/drivers/usb/dwc3/gadget.h +++ b/drivers/usb/dwc3/gadget.h @@ -85,7 +85,7 @@ void dwc3_ep0_out_start(struct dwc3 *dwc); int dwc3_gadget_ep0_set_halt(struct usb_ep *ep, int value); int dwc3_gadget_ep0_queue(struct usb_ep *ep, struct usb_request *request, gfp_t gfp_flags); -int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value); +int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol); /** * dwc3_gadget_ep_get_transfer_index - Gets transfer index from HW diff --git a/drivers/usb/dwc3/host.c b/drivers/usb/dwc3/host.c index 32db328cc769..dcb8ca084598 100644 --- a/drivers/usb/dwc3/host.c +++ b/drivers/usb/dwc3/host.c @@ -16,12 +16,14 @@ */ #include <linux/platform_device.h> +#include <linux/usb/xhci_pdriver.h> #include "core.h" int dwc3_host_init(struct dwc3 *dwc) { struct platform_device *xhci; + struct usb_xhci_pdata pdata; int ret; xhci = platform_device_alloc("xhci-hcd", PLATFORM_DEVID_AUTO); @@ -46,6 +48,18 @@ int dwc3_host_init(struct dwc3 *dwc) goto err1; } + memset(&pdata, 0, sizeof(pdata)); + +#ifdef CONFIG_DWC3_HOST_USB3_LPM_ENABLE + pdata.usb3_lpm_capable = 1; +#endif + + ret = platform_device_add_data(xhci, &pdata, sizeof(pdata)); + if (ret) { + dev_err(dwc->dev, "couldn't add platform data to xHCI device\n"); + goto err1; + } + ret = platform_device_add(xhci); if (ret) { dev_err(dwc->dev, "failed to register xHCI device\n"); diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig index 8154165aa601..fd13ef0a96c9 100644 --- a/drivers/usb/gadget/Kconfig +++ b/drivers/usb/gadget/Kconfig @@ -445,7 +445,7 @@ config USB_GOKU gadget drivers to also be dynamically linked. config USB_EG20T - tristate "Intel EG20T PCH/LAPIS Semiconductor IOH(ML7213/ML7831) UDC" + tristate "Intel QUARK X1000/EG20T PCH/LAPIS Semiconductor IOH(ML7213/ML7831) UDC" depends on PCI help This is a USB device driver for EG20T PCH. @@ -466,6 +466,7 @@ config USB_EG20T ML7213/ML7831 is companion chip for Intel Atom E6xx series. ML7213/ML7831 is completely compatible for Intel EG20T PCH. + This driver can be used with Intel's Quark X1000 SOC platform # # LAST -- dummy/emulated controller # diff --git a/drivers/usb/gadget/f_acm.c b/drivers/usb/gadget/f_acm.c index ab1065afbbd0..3384486c2884 100644 --- a/drivers/usb/gadget/f_acm.c +++ b/drivers/usb/gadget/f_acm.c @@ -430,11 +430,12 @@ static int acm_set_alt(struct usb_function *f, unsigned intf, unsigned alt) if (acm->notify->driver_data) { VDBG(cdev, "reset acm control interface %d\n", intf); usb_ep_disable(acm->notify); - } else { - VDBG(cdev, "init acm ctrl interface %d\n", intf); + } + + if (!acm->notify->desc) if (config_ep_by_speed(cdev->gadget, f, acm->notify)) return -EINVAL; - } + usb_ep_enable(acm->notify); acm->notify->driver_data = acm; diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c index 5bcf7d001259..afd0a159fe61 100644 --- a/drivers/usb/gadget/f_fs.c +++ b/drivers/usb/gadget/f_fs.c @@ -1995,8 +1995,6 @@ static inline struct f_fs_opts *ffs_do_functionfs_bind(struct usb_function *f, func->conf = c; func->gadget = c->cdev->gadget; - ffs_data_get(func->ffs); - /* * in drivers/usb/gadget/configfs.c:configfs_composite_bind() * configurations are bound in sequence with list_for_each_entry, diff --git a/drivers/usb/gadget/pch_udc.c b/drivers/usb/gadget/pch_udc.c index eb8c3bedb57a..460d953c91b6 100644 --- a/drivers/usb/gadget/pch_udc.c +++ b/drivers/usb/gadget/pch_udc.c @@ -343,6 +343,7 @@ struct pch_vbus_gpio_data { * @setup_data: Received setup data * @phys_addr: of device memory * @base_addr: for mapped device memory + * @bar: Indicates which PCI BAR for USB regs * @irq: IRQ line for the device * @cfg_data: current cfg, intf, and alt in use * @vbus_gpio: GPIO informaton for detecting VBUS @@ -370,14 +371,17 @@ struct pch_udc_dev { struct usb_ctrlrequest setup_data; unsigned long phys_addr; void __iomem *base_addr; + unsigned bar; unsigned irq; struct pch_udc_cfg_data cfg_data; struct pch_vbus_gpio_data vbus_gpio; }; #define to_pch_udc(g) (container_of((g), struct pch_udc_dev, gadget)) +#define PCH_UDC_PCI_BAR_QUARK_X1000 0 #define PCH_UDC_PCI_BAR 1 #define PCI_DEVICE_ID_INTEL_EG20T_UDC 0x8808 +#define PCI_DEVICE_ID_INTEL_QUARK_X1000_UDC 0x0939 #define PCI_VENDOR_ID_ROHM 0x10DB #define PCI_DEVICE_ID_ML7213_IOH_UDC 0x801D #define PCI_DEVICE_ID_ML7831_IOH_UDC 0x8808 @@ -3076,7 +3080,7 @@ static void pch_udc_remove(struct pci_dev *pdev) iounmap(dev->base_addr); if (dev->mem_region) release_mem_region(dev->phys_addr, - pci_resource_len(pdev, PCH_UDC_PCI_BAR)); + pci_resource_len(pdev, dev->bar)); if (dev->active) pci_disable_device(pdev); kfree(dev); @@ -3144,9 +3148,15 @@ static int pch_udc_probe(struct pci_dev *pdev, dev->active = 1; pci_set_drvdata(pdev, dev); + /* Determine BAR based on PCI ID */ + if (id->device == PCI_DEVICE_ID_INTEL_QUARK_X1000_UDC) + dev->bar = PCH_UDC_PCI_BAR_QUARK_X1000; + else + dev->bar = PCH_UDC_PCI_BAR; + /* PCI resource allocation */ - resource = pci_resource_start(pdev, 1); - len = pci_resource_len(pdev, 1); + resource = pci_resource_start(pdev, dev->bar); + len = pci_resource_len(pdev, dev->bar); if (!request_mem_region(resource, len, KBUILD_MODNAME)) { dev_err(&pdev->dev, "%s: pci device used already\n", __func__); @@ -3212,6 +3222,12 @@ finished: static const struct pci_device_id pch_udc_pcidev_id[] = { { + PCI_DEVICE(PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_QUARK_X1000_UDC), + .class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe, + .class_mask = 0xffffffff, + }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_EG20T_UDC), .class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe, .class_mask = 0xffffffff, diff --git a/drivers/usb/gadget/udc-core.c b/drivers/usb/gadget/udc-core.c index 27768a7d986a..9ce0b135c8c8 100644 --- a/drivers/usb/gadget/udc-core.c +++ b/drivers/usb/gadget/udc-core.c @@ -456,6 +456,11 @@ static ssize_t usb_udc_softconn_store(struct device *dev, { struct usb_udc *udc = container_of(dev, struct usb_udc, dev); + if (!udc->driver) { + dev_err(dev, "soft-connect without a gadget driver\n"); + return -EOPNOTSUPP; + } + if (sysfs_streq(buf, "connect")) { usb_gadget_udc_start(udc->gadget, udc->driver); usb_gadget_connect(udc->gadget); diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index 142ebd8a29c5..992ca7d2f14d 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -970,8 +970,6 @@ rescan: } qh->exception = 1; - if (ehci->rh_state < EHCI_RH_RUNNING) - qh->qh_state = QH_STATE_IDLE; switch (qh->qh_state) { case QH_STATE_LINKED: WARN_ON(!list_empty(&qh->qtd_list)); diff --git a/drivers/usb/host/ehci-sched.c b/drivers/usb/host/ehci-sched.c index e113fd73aeae..c399606f154e 100644 --- a/drivers/usb/host/ehci-sched.c +++ b/drivers/usb/host/ehci-sched.c @@ -1581,6 +1581,10 @@ iso_stream_schedule ( else next = (now + 2 + 7) & ~0x07; /* full frame cache */ + /* If needed, initialize last_iso_frame so that this URB will be seen */ + if (ehci->isoc_count == 0) + ehci->last_iso_frame = now >> 3; + /* * Use ehci->last_iso_frame as the base. There can't be any * TDs scheduled for earlier than that. @@ -1671,10 +1675,6 @@ iso_stream_schedule ( urb->start_frame = start & (mod - 1); if (!stream->highspeed) urb->start_frame >>= 3; - - /* Make sure scan_isoc() sees these */ - if (ehci->isoc_count == 0) - ehci->last_iso_frame = now >> 3; return status; fail: diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index 2f3acebb577a..f4e6b945136c 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -571,7 +571,8 @@ static void quirk_usb_handoff_ohci(struct pci_dev *pdev) { void __iomem *base; u32 control; - u32 fminterval; + u32 fminterval = 0; + bool no_fminterval = false; int cnt; if (!mmio_resource_enabled(pdev, 0)) @@ -581,6 +582,13 @@ static void quirk_usb_handoff_ohci(struct pci_dev *pdev) if (base == NULL) return; + /* + * ULi M5237 OHCI controller locks the whole system when accessing + * the OHCI_FMINTERVAL offset. + */ + if (pdev->vendor == PCI_VENDOR_ID_AL && pdev->device == 0x5237) + no_fminterval = true; + control = readl(base + OHCI_CONTROL); /* On PA-RISC, PDC can leave IR set incorrectly; ignore it there. */ @@ -619,7 +627,9 @@ static void quirk_usb_handoff_ohci(struct pci_dev *pdev) } /* software reset of the controller, preserving HcFmInterval */ - fminterval = readl(base + OHCI_FMINTERVAL); + if (!no_fminterval) + fminterval = readl(base + OHCI_FMINTERVAL); + writel(OHCI_HCR, base + OHCI_CMDSTATUS); /* reset requires max 10 us delay */ @@ -628,7 +638,9 @@ static void quirk_usb_handoff_ohci(struct pci_dev *pdev) break; udelay(1); } - writel(fminterval, base + OHCI_FMINTERVAL); + + if (!no_fminterval) + writel(fminterval, base + OHCI_FMINTERVAL); /* Now the controller is safely in SUSPEND and nothing can wake it up */ iounmap(base); diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index 9992fbfec85f..b9e16abb0fab 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -383,6 +383,10 @@ static void xhci_clear_port_change_bit(struct xhci_hcd *xhci, u16 wValue, status = PORT_PLC; port_change_bit = "link state"; break; + case USB_PORT_FEAT_C_PORT_CONFIG_ERROR: + status = PORT_CEC; + port_change_bit = "config error"; + break; default: /* Should never happen */ return; @@ -470,7 +474,8 @@ static void xhci_hub_report_usb2_link_state(u32 *status, u32 status_reg) } /* Updates Link Status for super Speed port */ -static void xhci_hub_report_usb3_link_state(u32 *status, u32 status_reg) +static void xhci_hub_report_usb3_link_state(struct xhci_hcd *xhci, + u32 *status, u32 status_reg) { u32 pls = status_reg & PORT_PLS_MASK; @@ -509,7 +514,8 @@ static void xhci_hub_report_usb3_link_state(u32 *status, u32 status_reg) * in which sometimes the port enters compliance mode * caused by a delay on the host-device negotiation. */ - if (pls == USB_SS_PORT_LS_COMP_MOD) + if ((xhci->quirks & XHCI_COMP_MODE_QUIRK) && + (pls == USB_SS_PORT_LS_COMP_MOD)) pls |= USB_PORT_STAT_CONNECTION; } @@ -582,6 +588,8 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd, status |= USB_PORT_STAT_C_LINK_STATE << 16; if ((raw_port_status & PORT_WRC)) status |= USB_PORT_STAT_C_BH_RESET << 16; + if ((raw_port_status & PORT_CEC)) + status |= USB_PORT_STAT_C_CONFIG_ERROR << 16; } if (hcd->speed != HCD_USB3) { @@ -668,7 +676,7 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd, } /* Update Port Link State */ if (hcd->speed == HCD_USB3) { - xhci_hub_report_usb3_link_state(&status, raw_port_status); + xhci_hub_report_usb3_link_state(xhci, &status, raw_port_status); /* * Verify if all USB3 Ports Have entered U0 already. * Delete Compliance Mode Timer if so. @@ -997,6 +1005,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, case USB_PORT_FEAT_C_OVER_CURRENT: case USB_PORT_FEAT_C_ENABLE: case USB_PORT_FEAT_C_PORT_LINK_STATE: + case USB_PORT_FEAT_C_PORT_CONFIG_ERROR: xhci_clear_port_change_bit(xhci, wValue, wIndex, port_array[wIndex], temp); break; @@ -1061,7 +1070,7 @@ int xhci_hub_status_data(struct usb_hcd *hcd, char *buf) */ status = bus_state->resuming_ports; - mask = PORT_CSC | PORT_PEC | PORT_OCC | PORT_PLC | PORT_WRC; + mask = PORT_CSC | PORT_PEC | PORT_OCC | PORT_PLC | PORT_WRC | PORT_CEC; spin_lock_irqsave(&xhci->lock, flags); /* For each port, did anything change? If so, set that bit in buf. */ diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 4133a00461b1..9bce4f0e99be 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1723,7 +1723,7 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci) } num_ports = HCS_MAX_PORTS(xhci->hcs_params1); - for (i = 0; i < num_ports; i++) { + for (i = 0; i < num_ports && xhci->rh_bw; i++) { struct xhci_interval_bw_table *bwt = &xhci->rh_bw[i].bw_table; for (j = 0; j < XHCI_MAX_INTERVAL; j++) { struct list_head *ep = &bwt->interval_bw[j].endpoints; diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 75cb1ff9d26b..eb3399f4c1ed 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -108,6 +108,7 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_INTEL) { xhci->quirks |= XHCI_LPM_SUPPORT; xhci->quirks |= XHCI_INTEL_HOST; + xhci->quirks |= XHCI_AVOID_BEI; } if (pdev->vendor == PCI_VENDOR_ID_INTEL && pdev->device == PCI_DEVICE_ID_INTEL_PANTHERPOINT_XHCI) { @@ -123,7 +124,6 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) * PPT chipsets. */ xhci->quirks |= XHCI_SPURIOUS_REBOOT; - xhci->quirks |= XHCI_AVOID_BEI; } if (pdev->vendor == PCI_VENDOR_ID_INTEL && (pdev->device == PCI_DEVICE_ID_INTEL_LYNXPOINT_XHCI || @@ -281,7 +281,7 @@ static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup) if (xhci_compliance_mode_recovery_timer_quirk_check()) pdev->no_d3cold = true; - return xhci_suspend(xhci); + return xhci_suspend(xhci, do_wakeup); } static int xhci_pci_resume(struct usb_hcd *hcd, bool hibernated) diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index 8abda5c73ca1..d6f70a223a43 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -11,11 +11,12 @@ * version 2 as published by the Free Software Foundation. */ -#include <linux/platform_device.h> +#include <linux/dma-mapping.h> #include <linux/module.h> -#include <linux/slab.h> #include <linux/of.h> -#include <linux/dma-mapping.h> +#include <linux/platform_device.h> +#include <linux/slab.h> +#include <linux/usb/xhci_pdriver.h> #include "xhci.h" @@ -87,6 +88,8 @@ static const struct hc_driver xhci_plat_xhci_driver = { static int xhci_plat_probe(struct platform_device *pdev) { + struct device_node *node = pdev->dev.of_node; + struct usb_xhci_pdata *pdata = dev_get_platdata(&pdev->dev); const struct hc_driver *driver; struct xhci_hcd *xhci; struct resource *res; @@ -152,6 +155,9 @@ static int xhci_plat_probe(struct platform_device *pdev) goto dealloc_usb2_hcd; } + if ((node && of_property_read_bool(node, "usb3-lpm-capable")) || + (pdata && pdata->usb3_lpm_capable)) + xhci->quirks |= XHCI_LPM_SUPPORT; /* * Set the xHCI pointer before xhci_plat_setup() (aka hcd_driver.reset) * is called by usb_add_hcd(). @@ -205,7 +211,15 @@ static int xhci_plat_suspend(struct device *dev) struct usb_hcd *hcd = dev_get_drvdata(dev); struct xhci_hcd *xhci = hcd_to_xhci(hcd); - return xhci_suspend(xhci); + /* + * xhci_suspend() needs `do_wakeup` to know whether host is allowed + * to do wakeup during suspend. Since xhci_plat_suspend is currently + * only designed for system suspend, device_may_wakeup() is enough + * to dertermine whether host is allowed to do wakeup. Need to + * reconsider this when xhci_plat_suspend enlarges its scope, e.g., + * also applies to runtime suspend. + */ + return xhci_suspend(xhci, device_may_wakeup(dev)); } static int xhci_plat_resume(struct device *dev) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 0e6665a82e88..a95eee8ddc38 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1180,9 +1180,8 @@ static void xhci_handle_cmd_reset_ep(struct xhci_hcd *xhci, int slot_id, false); xhci_ring_cmd_db(xhci); } else { - /* Clear our internal halted state and restart the ring(s) */ + /* Clear our internal halted state */ xhci->devs[slot_id]->eps[ep_index].ep_state &= ~EP_HALTED; - ring_doorbell_for_active_rings(xhci, slot_id, ep_index); } } @@ -1999,22 +1998,13 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_td *td, ep->stopped_td = td; return 0; } else { - if (trb_comp_code == COMP_STALL) { - /* The transfer is completed from the driver's - * perspective, but we need to issue a set dequeue - * command for this stalled endpoint to move the dequeue - * pointer past the TD. We can't do that here because - * the halt condition must be cleared first. Let the - * USB class driver clear the stall later. - */ - ep->stopped_td = td; - ep->stopped_stream = ep_ring->stream_id; - } else if (xhci_requires_manual_halt_cleanup(xhci, - ep_ctx, trb_comp_code)) { - /* Other types of errors halt the endpoint, but the - * class driver doesn't call usb_reset_endpoint() unless - * the error is -EPIPE. Clear the halted status in the - * xHCI hardware manually. + if (trb_comp_code == COMP_STALL || + xhci_requires_manual_halt_cleanup(xhci, ep_ctx, + trb_comp_code)) { + /* Issue a reset endpoint command to clear the host side + * halt, followed by a set dequeue command to move the + * dequeue pointer past the TD. + * The class driver clears the device side halt later. */ xhci_cleanup_halted_endpoint(xhci, slot_id, ep_index, ep_ring->stream_id, @@ -2134,9 +2124,7 @@ static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td, else td->urb->actual_length = 0; - xhci_cleanup_halted_endpoint(xhci, - slot_id, ep_index, 0, td, event_trb); - return finish_td(xhci, td, event_trb, event, ep, status, true); + return finish_td(xhci, td, event_trb, event, ep, status, false); } /* * Did we transfer any data, despite the errors that might have @@ -2145,7 +2133,7 @@ static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td, if (event_trb != ep_ring->dequeue) { /* The event was for the status stage */ if (event_trb == td->last_trb) { - if (td->urb->actual_length != 0) { + if (td->urb_length_set) { /* Don't overwrite a previously set error code */ if ((*status == -EINPROGRESS || *status == 0) && @@ -2159,7 +2147,13 @@ static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td, td->urb->transfer_buffer_length; } } else { - /* Maybe the event was for the data stage? */ + /* + * Maybe the event was for the data stage? If so, update + * already the actual_length of the URB and flag it as + * set, so that it is not overwritten in the event for + * the last TRB. + */ + td->urb_length_set = true; td->urb->actual_length = td->urb->transfer_buffer_length - EVENT_TRB_LEN(le32_to_cpu(event->transfer_len)); @@ -2690,17 +2684,8 @@ cleanup: if (ret) { urb = td->urb; urb_priv = urb->hcpriv; - /* Leave the TD around for the reset endpoint function - * to use(but only if it's not a control endpoint, - * since we already queued the Set TR dequeue pointer - * command for stalled control endpoints). - */ - if (usb_endpoint_xfer_control(&urb->ep->desc) || - (trb_comp_code != COMP_STALL && - trb_comp_code != COMP_BABBLE)) - xhci_urb_free_priv(xhci, urb_priv); - else - kfree(urb_priv); + + xhci_urb_free_priv(xhci, urb_priv); usb_hcd_unlink_urb_from_ep(bus_to_hcd(urb->dev->bus), urb); if ((urb->actual_length != urb->transfer_buffer_length && diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index ab831048e8a4..16f4f8dc1ae9 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -35,6 +35,8 @@ #define DRIVER_AUTHOR "Sarah Sharp" #define DRIVER_DESC "'eXtensible' Host Controller (xHC) Driver" +#define PORT_WAKE_BITS (PORT_WKOC_E | PORT_WKDISC_E | PORT_WKCONN_E) + /* Some 0.95 hardware can't handle the chain bit on a Link TRB being cleared */ static int link_quirk; module_param(link_quirk, int, S_IRUGO | S_IWUSR); @@ -842,13 +844,47 @@ static void xhci_clear_command_ring(struct xhci_hcd *xhci) xhci_set_cmd_ring_deq(xhci); } +static void xhci_disable_port_wake_on_bits(struct xhci_hcd *xhci) +{ + int port_index; + __le32 __iomem **port_array; + unsigned long flags; + u32 t1, t2; + + spin_lock_irqsave(&xhci->lock, flags); + + /* disble usb3 ports Wake bits*/ + port_index = xhci->num_usb3_ports; + port_array = xhci->usb3_ports; + while (port_index--) { + t1 = readl(port_array[port_index]); + t1 = xhci_port_state_to_neutral(t1); + t2 = t1 & ~PORT_WAKE_BITS; + if (t1 != t2) + writel(t2, port_array[port_index]); + } + + /* disble usb2 ports Wake bits*/ + port_index = xhci->num_usb2_ports; + port_array = xhci->usb2_ports; + while (port_index--) { + t1 = readl(port_array[port_index]); + t1 = xhci_port_state_to_neutral(t1); + t2 = t1 & ~PORT_WAKE_BITS; + if (t1 != t2) + writel(t2, port_array[port_index]); + } + + spin_unlock_irqrestore(&xhci->lock, flags); +} + /* * Stop HC (not bus-specific) * * This is called when the machine transition into S3/S4 mode. * */ -int xhci_suspend(struct xhci_hcd *xhci) +int xhci_suspend(struct xhci_hcd *xhci, bool do_wakeup) { int rc = 0; unsigned int delay = XHCI_MAX_HALT_USEC; @@ -859,6 +895,10 @@ int xhci_suspend(struct xhci_hcd *xhci) xhci->shared_hcd->state != HC_STATE_SUSPENDED) return -EINVAL; + /* Clear root port wake on bits if wakeup not allowed. */ + if (!do_wakeup) + xhci_disable_port_wake_on_bits(xhci); + /* Don't poll the roothubs on bus suspend. */ xhci_dbg(xhci, "%s: stopping port polling.\n", __func__); clear_bit(HCD_FLAG_POLL_RH, &hcd->flags); @@ -2885,63 +2925,33 @@ void xhci_cleanup_stalled_ring(struct xhci_hcd *xhci, } } -/* Deal with stalled endpoints. The core should have sent the control message - * to clear the halt condition. However, we need to make the xHCI hardware - * reset its sequence number, since a device will expect a sequence number of - * zero after the halt condition is cleared. +/* Called when clearing halted device. The core should have sent the control + * message to clear the device halt condition. The host side of the halt should + * already be cleared with a reset endpoint command issued when the STALL tx + * event was received. + * * Context: in_interrupt */ + void xhci_endpoint_reset(struct usb_hcd *hcd, struct usb_host_endpoint *ep) { struct xhci_hcd *xhci; - struct usb_device *udev; - unsigned int ep_index; - unsigned long flags; - int ret; - struct xhci_virt_ep *virt_ep; xhci = hcd_to_xhci(hcd); - udev = (struct usb_device *) ep->hcpriv; - /* Called with a root hub endpoint (or an endpoint that wasn't added - * with xhci_add_endpoint() - */ - if (!ep->hcpriv) - return; - ep_index = xhci_get_endpoint_index(&ep->desc); - virt_ep = &xhci->devs[udev->slot_id]->eps[ep_index]; - if (!virt_ep->stopped_td) { - xhci_dbg_trace(xhci, trace_xhci_dbg_reset_ep, - "Endpoint 0x%x not halted, refusing to reset.", - ep->desc.bEndpointAddress); - return; - } - if (usb_endpoint_xfer_control(&ep->desc)) { - xhci_dbg_trace(xhci, trace_xhci_dbg_reset_ep, - "Control endpoint stall already handled."); - return; - } - xhci_dbg_trace(xhci, trace_xhci_dbg_reset_ep, - "Queueing reset endpoint command"); - spin_lock_irqsave(&xhci->lock, flags); - ret = xhci_queue_reset_ep(xhci, udev->slot_id, ep_index); /* - * Can't change the ring dequeue pointer until it's transitioned to the - * stopped state, which is only upon a successful reset endpoint - * command. Better hope that last command worked! + * We might need to implement the config ep cmd in xhci 4.8.1 note: + * The Reset Endpoint Command may only be issued to endpoints in the + * Halted state. If software wishes reset the Data Toggle or Sequence + * Number of an endpoint that isn't in the Halted state, then software + * may issue a Configure Endpoint Command with the Drop and Add bits set + * for the target endpoint. that is in the Stopped state. */ - if (!ret) { - xhci_cleanup_stalled_ring(xhci, udev, ep_index); - kfree(virt_ep->stopped_td); - xhci_ring_cmd_db(xhci); - } - virt_ep->stopped_td = NULL; - virt_ep->stopped_stream = 0; - spin_unlock_irqrestore(&xhci->lock, flags); - if (ret) - xhci_warn(xhci, "FIXME allocate a new ring segment\n"); + /* For now just print debug to follow the situation */ + xhci_dbg(xhci, "Endpoint 0x%x ep reset callback called\n", + ep->desc.bEndpointAddress); } static int xhci_check_streams_endpoint(struct xhci_hcd *xhci, @@ -3928,13 +3938,21 @@ static int __maybe_unused xhci_change_max_exit_latency(struct xhci_hcd *xhci, int ret; spin_lock_irqsave(&xhci->lock, flags); - if (max_exit_latency == xhci->devs[udev->slot_id]->current_mel) { + + virt_dev = xhci->devs[udev->slot_id]; + + /* + * virt_dev might not exists yet if xHC resumed from hibernate (S4) and + * xHC was re-initialized. Exit latency will be set later after + * hub_port_finish_reset() is done and xhci->devs[] are re-allocated + */ + + if (!virt_dev || max_exit_latency == virt_dev->current_mel) { spin_unlock_irqrestore(&xhci->lock, flags); return 0; } /* Attempt to issue an Evaluate Context command to change the MEL. */ - virt_dev = xhci->devs[udev->slot_id]; command = xhci->lpm_command; ctrl_ctx = xhci_get_input_control_ctx(xhci, command->in_ctx); if (!ctrl_ctx) { diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 8faef64371c6..7225dd242bfa 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1,3 +1,4 @@ + /* * xHCI host controller driver * @@ -88,9 +89,10 @@ struct xhci_cap_regs { #define HCS_IST(p) (((p) >> 0) & 0xf) /* bits 4:7, max number of Event Ring segments */ #define HCS_ERST_MAX(p) (((p) >> 4) & 0xf) +/* bits 21:25 Hi 5 bits of Scratchpad buffers SW must allocate for the HW */ /* bit 26 Scratchpad restore - for save/restore HW state - not used yet */ -/* bits 27:31 number of Scratchpad buffers SW must allocate for the HW */ -#define HCS_MAX_SCRATCHPAD(p) (((p) >> 27) & 0x1f) +/* bits 27:31 Lo 5 bits of Scratchpad buffers SW must allocate for the HW */ +#define HCS_MAX_SCRATCHPAD(p) ((((p) >> 16) & 0x3e0) | (((p) >> 27) & 0x1f)) /* HCSPARAMS3 - hcs_params3 - bitmasks */ /* bits 0:7, Max U1 to U0 latency for the roothub ports */ @@ -1289,6 +1291,8 @@ struct xhci_td { struct xhci_segment *start_seg; union xhci_trb *first_trb; union xhci_trb *last_trb; + /* actual_length of the URB has already been set */ + bool urb_length_set; }; /* xHCI command default timeout value */ @@ -1760,7 +1764,7 @@ void xhci_shutdown(struct usb_hcd *hcd); int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks); #ifdef CONFIG_PM -int xhci_suspend(struct xhci_hcd *xhci); +int xhci_suspend(struct xhci_hcd *xhci, bool do_wakeup); int xhci_resume(struct xhci_hcd *xhci, bool hibernated); #else #define xhci_suspend NULL diff --git a/drivers/usb/misc/sisusbvga/sisusb.c b/drivers/usb/misc/sisusbvga/sisusb.c index de98906f786d..0aef801edbc1 100644 --- a/drivers/usb/misc/sisusbvga/sisusb.c +++ b/drivers/usb/misc/sisusbvga/sisusb.c @@ -3248,6 +3248,7 @@ static const struct usb_device_id sisusb_table[] = { { USB_DEVICE(0x0711, 0x0918) }, { USB_DEVICE(0x0711, 0x0920) }, { USB_DEVICE(0x0711, 0x0950) }, + { USB_DEVICE(0x0711, 0x5200) }, { USB_DEVICE(0x182d, 0x021c) }, { USB_DEVICE(0x182d, 0x0269) }, { } diff --git a/drivers/usb/musb/musb_cppi41.c b/drivers/usb/musb/musb_cppi41.c index c2d5afc57e22..1d29bbfeb9d5 100644 --- a/drivers/usb/musb/musb_cppi41.c +++ b/drivers/usb/musb/musb_cppi41.c @@ -190,7 +190,8 @@ static enum hrtimer_restart cppi41_recheck_tx_req(struct hrtimer *timer) } } - if (!list_empty(&controller->early_tx_list)) { + if (!list_empty(&controller->early_tx_list) && + !hrtimer_is_queued(&controller->early_tx)) { ret = HRTIMER_RESTART; hrtimer_forward_now(&controller->early_tx, ktime_set(0, 150 * NSEC_PER_USEC)); diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c index 7a109eae9b9a..865243e818b7 100644 --- a/drivers/usb/musb/musb_dsps.c +++ b/drivers/usb/musb/musb_dsps.c @@ -707,6 +707,7 @@ static int dsps_suspend(struct device *dev) struct musb *musb = platform_get_drvdata(glue->musb); void __iomem *mbase = musb->ctrl_base; + del_timer_sync(&glue->timer); glue->context.control = dsps_readl(mbase, wrp->control); glue->context.epintr = dsps_readl(mbase, wrp->epintr_set); glue->context.coreintr = dsps_readl(mbase, wrp->coreintr_set); @@ -732,6 +733,9 @@ static int dsps_resume(struct device *dev) dsps_writel(mbase, wrp->mode, glue->context.mode); dsps_writel(mbase, wrp->tx_mode, glue->context.tx_mode); dsps_writel(mbase, wrp->rx_mode, glue->context.rx_mode); + if (musb->xceiv->state == OTG_STATE_B_IDLE && + musb->port_mode == MUSB_PORT_MODE_DUAL_ROLE) + mod_timer(&glue->timer, jiffies + wrp->poll_seconds * HZ); return 0; } diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index abb38c3833ef..6b0fb6af6815 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -2640,7 +2640,6 @@ void musb_host_cleanup(struct musb *musb) if (musb->port_mode == MUSB_PORT_MODE_GADGET) return; usb_remove_hcd(musb->hcd); - musb->hcd = NULL; } void musb_host_free(struct musb *musb) diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c index bbe4f8e6e8d7..8834b70c868c 100644 --- a/drivers/usb/phy/phy-tegra-usb.c +++ b/drivers/usb/phy/phy-tegra-usb.c @@ -881,8 +881,8 @@ static int utmi_phy_probe(struct tegra_usb_phy *tegra_phy, return -ENOMEM; } - tegra_phy->config = devm_kzalloc(&pdev->dev, - sizeof(*tegra_phy->config), GFP_KERNEL); + tegra_phy->config = devm_kzalloc(&pdev->dev, sizeof(*config), + GFP_KERNEL); if (!tegra_phy->config) { dev_err(&pdev->dev, "unable to allocate memory for USB UTMIP config\n"); diff --git a/drivers/usb/phy/phy.c b/drivers/usb/phy/phy.c index 8afa813d690b..0180eef05656 100644 --- a/drivers/usb/phy/phy.c +++ b/drivers/usb/phy/phy.c @@ -229,6 +229,9 @@ struct usb_phy *usb_get_phy_dev(struct device *dev, u8 index) phy = __usb_find_phy_dev(dev, &phy_bind_list, index); if (IS_ERR(phy) || !try_module_get(phy->dev->driver->owner)) { dev_dbg(dev, "unable to find transceiver\n"); + if (!IS_ERR(phy)) + phy = ERR_PTR(-ENODEV); + goto err0; } diff --git a/drivers/usb/serial/bus.c b/drivers/usb/serial/bus.c index 9374bd2aba20..6f91eb9ae81a 100644 --- a/drivers/usb/serial/bus.c +++ b/drivers/usb/serial/bus.c @@ -51,6 +51,7 @@ static int usb_serial_device_probe(struct device *dev) { struct usb_serial_driver *driver; struct usb_serial_port *port; + struct device *tty_dev; int retval = 0; int minor; @@ -75,12 +76,20 @@ static int usb_serial_device_probe(struct device *dev) retval = device_create_file(dev, &dev_attr_port_number); if (retval) { if (driver->port_remove) - retval = driver->port_remove(port); + driver->port_remove(port); goto exit_with_autopm; } minor = port->minor; - tty_register_device(usb_serial_tty_driver, minor, dev); + tty_dev = tty_register_device(usb_serial_tty_driver, minor, dev); + if (IS_ERR(tty_dev)) { + retval = PTR_ERR(tty_dev); + device_remove_file(dev, &dev_attr_port_number); + if (driver->port_remove) + driver->port_remove(port); + goto exit_with_autopm; + } + dev_info(&port->serial->dev->dev, "%s converter now attached to ttyUSB%d\n", driver->description, minor); diff --git a/drivers/usb/serial/console.c b/drivers/usb/serial/console.c index 8d7fc48b1f30..29fa1c3d0089 100644 --- a/drivers/usb/serial/console.c +++ b/drivers/usb/serial/console.c @@ -46,6 +46,8 @@ static struct console usbcons; * ------------------------------------------------------------ */ +static const struct tty_operations usb_console_fake_tty_ops = { +}; /* * The parsing of the command line works exactly like the @@ -137,13 +139,17 @@ static int usb_console_setup(struct console *co, char *options) goto reset_open_count; } kref_init(&tty->kref); - tty_port_tty_set(&port->port, tty); tty->driver = usb_serial_tty_driver; tty->index = co->index; + init_ldsem(&tty->ldisc_sem); + INIT_LIST_HEAD(&tty->tty_files); + kref_get(&tty->driver->kref); + tty->ops = &usb_console_fake_tty_ops; if (tty_init_termios(tty)) { retval = -ENOMEM; - goto free_tty; + goto put_tty; } + tty_port_tty_set(&port->port, tty); } /* only call the device specific open if this @@ -161,7 +167,7 @@ static int usb_console_setup(struct console *co, char *options) serial->type->set_termios(tty, port, &dummy); tty_port_tty_set(&port->port, NULL); - kfree(tty); + tty_kref_put(tty); } set_bit(ASYNCB_INITIALIZED, &port->port.flags); } @@ -177,8 +183,8 @@ static int usb_console_setup(struct console *co, char *options) fail: tty_port_tty_set(&port->port, NULL); - free_tty: - kfree(tty); + put_tty: + tty_kref_put(tty); reset_open_count: port->port.count = 0; usb_autopm_put_interface(serial->interface); diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 330df5ce435b..8d114b9733ed 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -56,6 +56,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x0846, 0x1100) }, /* NetGear Managed Switch M4100 series, M5300 series, M7100 series */ { USB_DEVICE(0x08e6, 0x5501) }, /* Gemalto Prox-PU/CU contactless smartcard reader */ { USB_DEVICE(0x08FD, 0x000A) }, /* Digianswer A/S , ZigBee/802.15.4 MAC Device */ + { USB_DEVICE(0x0908, 0x01FF) }, /* Siemens RUGGEDCOM USB Serial Console */ { USB_DEVICE(0x0BED, 0x1100) }, /* MEI (TM) Cashflow-SC Bill/Voucher Acceptor */ { USB_DEVICE(0x0BED, 0x1101) }, /* MEI series 2000 Combo Acceptor */ { USB_DEVICE(0x0FCF, 0x1003) }, /* Dynastream ANT development board */ @@ -120,8 +121,12 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */ { USB_DEVICE(0x10C4, 0x8664) }, /* AC-Services CAN-IF */ { USB_DEVICE(0x10C4, 0x8665) }, /* AC-Services OBD-IF */ + { USB_DEVICE(0x10C4, 0x8856) }, /* CEL EM357 ZigBee USB Stick - LR */ + { USB_DEVICE(0x10C4, 0x8857) }, /* CEL EM357 ZigBee USB Stick */ { USB_DEVICE(0x10C4, 0x88A4) }, /* MMB Networks ZigBee USB Device */ { USB_DEVICE(0x10C4, 0x88A5) }, /* Planet Innovation Ingeni ZigBee USB Device */ + { USB_DEVICE(0x10C4, 0x8946) }, /* Ketra N1 Wireless Interface */ + { USB_DEVICE(0x10C4, 0x8977) }, /* CEL MeshWorks DevKit Device */ { USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */ { USB_DEVICE(0x10C4, 0xEA61) }, /* Silicon Labs factory default */ { USB_DEVICE(0x10C4, 0xEA70) }, /* Silicon Labs factory default */ @@ -142,6 +147,8 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x166A, 0x0305) }, /* Clipsal C-5000CT2 C-Bus Spectrum Colour Touchscreen */ { USB_DEVICE(0x166A, 0x0401) }, /* Clipsal L51xx C-Bus Architectural Dimmer */ { USB_DEVICE(0x166A, 0x0101) }, /* Clipsal 5560884 C-Bus Multi-room Audio Matrix Switcher */ + { USB_DEVICE(0x16C0, 0x09B0) }, /* Lunatico Seletek */ + { USB_DEVICE(0x16C0, 0x09B1) }, /* Lunatico Seletek */ { USB_DEVICE(0x16D6, 0x0001) }, /* Jablotron serial interface */ { USB_DEVICE(0x16DC, 0x0010) }, /* W-IE-NE-R Plein & Baus GmbH PL512 Power Supply */ { USB_DEVICE(0x16DC, 0x0011) }, /* W-IE-NE-R Plein & Baus GmbH RCM Remote Control for MARATON Power Supply */ @@ -154,7 +161,9 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */ { USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */ { USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */ + { USB_DEVICE(0x1BA4, 0x0002) }, /* Silicon Labs 358x factory default */ { USB_DEVICE(0x1BE3, 0x07A6) }, /* WAGO 750-923 USB Service Cable */ + { USB_DEVICE(0x1D6F, 0x0010) }, /* Seluxit ApS RF Dongle */ { USB_DEVICE(0x1E29, 0x0102) }, /* Festo CPX-USB */ { USB_DEVICE(0x1E29, 0x0501) }, /* Festo CMSP */ { USB_DEVICE(0x1FB9, 0x0100) }, /* Lake Shore Model 121 Current Source */ diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 8b0f517abb6b..2d858f81ab33 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -145,6 +145,7 @@ static struct ftdi_sio_quirk ftdi_8u2232c_quirk = { * /sys/bus/usb-serial/drivers/ftdi_sio/new_id and send a patch or report. */ static const struct usb_device_id id_table_combined[] = { + { USB_DEVICE(FTDI_VID, FTDI_BRICK_PID) }, { USB_DEVICE(FTDI_VID, FTDI_ZEITCONTROL_TAGTRACE_MIFARE_PID) }, { USB_DEVICE(FTDI_VID, FTDI_CTI_MINI_PID) }, { USB_DEVICE(FTDI_VID, FTDI_CTI_NANO_PID) }, @@ -482,6 +483,39 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_01FD_PID) }, { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_01FE_PID) }, { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_01FF_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_4701_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9300_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9301_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9302_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9303_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9304_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9305_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9306_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9307_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9308_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9309_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930A_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930B_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930C_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930D_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930E_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930F_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9310_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9311_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9312_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9313_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9314_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9315_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9316_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9317_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9318_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9319_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931A_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931B_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931C_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931D_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931E_PID) }, + { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931F_PID) }, { USB_DEVICE(FTDI_VID, FTDI_PERLE_ULTRAPORT_PID) }, { USB_DEVICE(FTDI_VID, FTDI_PIEGROUP_PID) }, { USB_DEVICE(FTDI_VID, FTDI_TNC_X_PID) }, @@ -583,6 +617,7 @@ static const struct usb_device_id id_table_combined[] = { .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, { USB_DEVICE(FTDI_VID, FTDI_NT_ORIONLXM_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE(FTDI_VID, FTDI_SYNAPSE_SS200_PID) }, /* * ELV devices: */ @@ -674,6 +709,8 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, XSENS_CONVERTER_5_PID) }, { USB_DEVICE(FTDI_VID, XSENS_CONVERTER_6_PID) }, { USB_DEVICE(FTDI_VID, XSENS_CONVERTER_7_PID) }, + { USB_DEVICE(XSENS_VID, XSENS_AWINDA_DONGLE_PID) }, + { USB_DEVICE(XSENS_VID, XSENS_AWINDA_STATION_PID) }, { USB_DEVICE(XSENS_VID, XSENS_CONVERTER_PID) }, { USB_DEVICE(XSENS_VID, XSENS_MTW_PID) }, { USB_DEVICE(FTDI_VID, FTDI_OMNI1509) }, @@ -741,6 +778,7 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, FTDI_NDI_AURORA_SCU_PID), .driver_info = (kernel_ulong_t)&ftdi_NDI_device_quirk }, { USB_DEVICE(TELLDUS_VID, TELLDUS_TELLSTICK_PID) }, + { USB_DEVICE(NOVITUS_VID, NOVITUS_BONO_E_PID) }, { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_S03_PID) }, { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_59_PID) }, { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_57A_PID) }, @@ -775,6 +813,8 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, FTDI_ELSTER_UNICOM_PID) }, { USB_DEVICE(FTDI_VID, FTDI_PROPOX_JTAGCABLEII_PID) }, { 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), @@ -952,6 +992,25 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, FTDI_EKEY_CONV_USB_PID) }, /* Infineon Devices */ { USB_DEVICE_INTERFACE_NUMBER(INFINEON_VID, INFINEON_TRIBOARD_PID, 1) }, + /* GE Healthcare devices */ + { USB_DEVICE(GE_HEALTHCARE_VID, GE_HEALTHCARE_NEMO_TRACKER_PID) }, + /* Active Research (Actisense) devices */ + { USB_DEVICE(FTDI_VID, ACTISENSE_NDC_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_USG_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_NGT_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_NGW_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_D9AC_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_D9AD_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_D9AE_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_D9AF_PID) }, + { USB_DEVICE(FTDI_VID, CHETCO_SEAGAUGE_PID) }, + { USB_DEVICE(FTDI_VID, CHETCO_SEASWITCH_PID) }, + { USB_DEVICE(FTDI_VID, CHETCO_SEASMART_NMEA2000_PID) }, + { USB_DEVICE(FTDI_VID, CHETCO_SEASMART_ETHERNET_PID) }, + { USB_DEVICE(FTDI_VID, CHETCO_SEASMART_WIFI_PID) }, + { USB_DEVICE(FTDI_VID, CHETCO_SEASMART_DISPLAY_PID) }, + { USB_DEVICE(FTDI_VID, CHETCO_SEASMART_LITE_PID) }, + { USB_DEVICE(FTDI_VID, CHETCO_SEASMART_ANALOG_PID) }, { } /* Terminating entry */ }; @@ -1843,8 +1902,12 @@ static int ftdi_8u2232c_probe(struct usb_serial *serial) { struct usb_device *udev = serial->dev; - if ((udev->manufacturer && !strcmp(udev->manufacturer, "CALAO Systems")) || - (udev->product && !strcmp(udev->product, "BeagleBone/XDS100V2"))) + if (udev->manufacturer && !strcmp(udev->manufacturer, "CALAO Systems")) + return ftdi_jtag_probe(serial); + + if (udev->product && + (!strcmp(udev->product, "BeagleBone/XDS100V2") || + !strcmp(udev->product, "SNAP Connect E10"))) return ftdi_jtag_probe(serial); return 0; diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 70b0b1d88ae9..4e4f46f3c89c 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -30,8 +30,17 @@ /*** third-party PIDs (using FTDI_VID) ***/ +/* + * Certain versions of the official Windows FTDI driver reprogrammed + * counterfeit FTDI devices to PID 0. Support these devices anyway. + */ +#define FTDI_BRICK_PID 0x0000 + #define FTDI_LUMEL_PD12_PID 0x6002 +/* Cyber Cortex AV by Fabulous Silicon (http://fabuloussilicon.com) */ +#define CYBER_CORTEX_AV_PID 0x8698 + /* * Marvell OpenRD Base, Client * http://www.open-rd.org @@ -143,8 +152,12 @@ * Xsens Technologies BV products (http://www.xsens.com). */ #define XSENS_VID 0x2639 -#define XSENS_CONVERTER_PID 0xD00D /* Xsens USB-serial converter */ +#define XSENS_AWINDA_STATION_PID 0x0101 +#define XSENS_AWINDA_DONGLE_PID 0x0102 #define XSENS_MTW_PID 0x0200 /* Xsens MTw */ +#define XSENS_CONVERTER_PID 0xD00D /* Xsens USB-serial converter */ + +/* Xsens devices using FTDI VID */ #define XSENS_CONVERTER_0_PID 0xD388 /* Xsens USB converter */ #define XSENS_CONVERTER_1_PID 0xD389 /* Xsens Wireless Receiver */ #define XSENS_CONVERTER_2_PID 0xD38A @@ -548,6 +561,12 @@ */ #define FTDI_NT_ORIONLXM_PID 0x7c90 /* OrionLXm Substation Automation Platform */ +/* + * Synapse Wireless product ids (FTDI_VID) + * http://www.synapse-wireless.com + */ +#define FTDI_SYNAPSE_SS200_PID 0x9090 /* SS200 - SNAP Stick 200 */ + /********************************/ /** third-party VID/PID combos **/ @@ -837,6 +856,12 @@ #define TELLDUS_TELLSTICK_PID 0x0C30 /* RF control dongle 433 MHz using FT232RL */ /* + * NOVITUS printers + */ +#define NOVITUS_VID 0x1a28 +#define NOVITUS_BONO_E_PID 0x6010 + +/* * RT Systems programming cables for various ham radios */ #define RTSYSTEMS_VID 0x2100 /* Vendor ID */ @@ -910,8 +935,8 @@ #define BAYER_CONTOUR_CABLE_PID 0x6001 /* - * The following are the values for the Matrix Orbital FTDI Range - * Anything in this range will use an FT232RL. + * Matrix Orbital Intelligent USB displays. + * http://www.matrixorbital.com */ #define MTXORB_VID 0x1B3D #define MTXORB_FTDI_RANGE_0100_PID 0x0100 @@ -1170,8 +1195,39 @@ #define MTXORB_FTDI_RANGE_01FD_PID 0x01FD #define MTXORB_FTDI_RANGE_01FE_PID 0x01FE #define MTXORB_FTDI_RANGE_01FF_PID 0x01FF - - +#define MTXORB_FTDI_RANGE_4701_PID 0x4701 +#define MTXORB_FTDI_RANGE_9300_PID 0x9300 +#define MTXORB_FTDI_RANGE_9301_PID 0x9301 +#define MTXORB_FTDI_RANGE_9302_PID 0x9302 +#define MTXORB_FTDI_RANGE_9303_PID 0x9303 +#define MTXORB_FTDI_RANGE_9304_PID 0x9304 +#define MTXORB_FTDI_RANGE_9305_PID 0x9305 +#define MTXORB_FTDI_RANGE_9306_PID 0x9306 +#define MTXORB_FTDI_RANGE_9307_PID 0x9307 +#define MTXORB_FTDI_RANGE_9308_PID 0x9308 +#define MTXORB_FTDI_RANGE_9309_PID 0x9309 +#define MTXORB_FTDI_RANGE_930A_PID 0x930A +#define MTXORB_FTDI_RANGE_930B_PID 0x930B +#define MTXORB_FTDI_RANGE_930C_PID 0x930C +#define MTXORB_FTDI_RANGE_930D_PID 0x930D +#define MTXORB_FTDI_RANGE_930E_PID 0x930E +#define MTXORB_FTDI_RANGE_930F_PID 0x930F +#define MTXORB_FTDI_RANGE_9310_PID 0x9310 +#define MTXORB_FTDI_RANGE_9311_PID 0x9311 +#define MTXORB_FTDI_RANGE_9312_PID 0x9312 +#define MTXORB_FTDI_RANGE_9313_PID 0x9313 +#define MTXORB_FTDI_RANGE_9314_PID 0x9314 +#define MTXORB_FTDI_RANGE_9315_PID 0x9315 +#define MTXORB_FTDI_RANGE_9316_PID 0x9316 +#define MTXORB_FTDI_RANGE_9317_PID 0x9317 +#define MTXORB_FTDI_RANGE_9318_PID 0x9318 +#define MTXORB_FTDI_RANGE_9319_PID 0x9319 +#define MTXORB_FTDI_RANGE_931A_PID 0x931A +#define MTXORB_FTDI_RANGE_931B_PID 0x931B +#define MTXORB_FTDI_RANGE_931C_PID 0x931C +#define MTXORB_FTDI_RANGE_931D_PID 0x931D +#define MTXORB_FTDI_RANGE_931E_PID 0x931E +#define MTXORB_FTDI_RANGE_931F_PID 0x931F /* * The Mobility Lab (TML) @@ -1385,3 +1441,29 @@ * ekey biometric systems GmbH (http://ekey.net/) */ #define FTDI_EKEY_CONV_USB_PID 0xCB08 /* Converter USB */ + +/* + * GE Healthcare devices + */ +#define GE_HEALTHCARE_VID 0x1901 +#define GE_HEALTHCARE_NEMO_TRACKER_PID 0x0015 + +/* + * Active Research (Actisense) devices + */ +#define ACTISENSE_NDC_PID 0xD9A8 /* NDC USB Serial Adapter */ +#define ACTISENSE_USG_PID 0xD9A9 /* USG USB Serial Adapter */ +#define ACTISENSE_NGT_PID 0xD9AA /* NGT NMEA2000 Interface */ +#define ACTISENSE_NGW_PID 0xD9AB /* NGW NMEA2000 Gateway */ +#define ACTISENSE_D9AC_PID 0xD9AC /* Actisense Reserved */ +#define ACTISENSE_D9AD_PID 0xD9AD /* Actisense Reserved */ +#define ACTISENSE_D9AE_PID 0xD9AE /* Actisense Reserved */ +#define ACTISENSE_D9AF_PID 0xD9AF /* Actisense Reserved */ +#define CHETCO_SEAGAUGE_PID 0xA548 /* SeaGauge USB Adapter */ +#define CHETCO_SEASWITCH_PID 0xA549 /* SeaSwitch USB Adapter */ +#define CHETCO_SEASMART_NMEA2000_PID 0xA54A /* SeaSmart NMEA2000 Gateway */ +#define CHETCO_SEASMART_ETHERNET_PID 0xA54B /* SeaSmart Ethernet Gateway */ +#define CHETCO_SEASMART_WIFI_PID 0xA5AC /* SeaSmart Wifi Gateway */ +#define CHETCO_SEASMART_DISPLAY_PID 0xA5AD /* SeaSmart NMEA2000 Display */ +#define CHETCO_SEASMART_LITE_PID 0xA5AE /* SeaSmart Lite USB Adapter */ +#define CHETCO_SEASMART_ANALOG_PID 0xA5AF /* SeaSmart Analog Adapter */ diff --git a/drivers/usb/serial/generic.c b/drivers/usb/serial/generic.c index b63ce023f96f..d6a197917ebd 100644 --- a/drivers/usb/serial/generic.c +++ b/drivers/usb/serial/generic.c @@ -258,7 +258,8 @@ void usb_serial_generic_wait_until_sent(struct tty_struct *tty, long timeout) * character or at least one jiffy. */ period = max_t(unsigned long, (10 * HZ / bps), 1); - period = min_t(unsigned long, period, timeout); + if (timeout) + period = min_t(unsigned long, period, timeout); dev_dbg(&port->dev, "%s - timeout = %u ms, period = %u ms\n", __func__, jiffies_to_msecs(timeout), @@ -268,7 +269,7 @@ void usb_serial_generic_wait_until_sent(struct tty_struct *tty, long timeout) schedule_timeout_interruptible(period); if (signal_pending(current)) break; - if (time_after(jiffies, expire)) + if (timeout && time_after(jiffies, expire)) break; } } diff --git a/drivers/usb/serial/keyspan.c b/drivers/usb/serial/keyspan.c index 265c6776b081..35297a845a63 100644 --- a/drivers/usb/serial/keyspan.c +++ b/drivers/usb/serial/keyspan.c @@ -311,24 +311,30 @@ static void usa26_indat_callback(struct urb *urb) if ((data[0] & 0x80) == 0) { /* no errors on individual bytes, only possible overrun err */ - if (data[0] & RXERROR_OVERRUN) - err = TTY_OVERRUN; - else - err = 0; + if (data[0] & RXERROR_OVERRUN) { + tty_insert_flip_char(&port->port, 0, + TTY_OVERRUN); + } for (i = 1; i < urb->actual_length ; ++i) - tty_insert_flip_char(&port->port, data[i], err); + tty_insert_flip_char(&port->port, data[i], + TTY_NORMAL); } else { /* some bytes had errors, every byte has status */ dev_dbg(&port->dev, "%s - RX error!!!!\n", __func__); for (i = 0; i + 1 < urb->actual_length; i += 2) { - int stat = data[i], flag = 0; - if (stat & RXERROR_OVERRUN) - flag |= TTY_OVERRUN; - if (stat & RXERROR_FRAMING) - flag |= TTY_FRAME; - if (stat & RXERROR_PARITY) - flag |= TTY_PARITY; + int stat = data[i]; + int flag = TTY_NORMAL; + + if (stat & RXERROR_OVERRUN) { + tty_insert_flip_char(&port->port, 0, + TTY_OVERRUN); + } /* XXX should handle break (0x10) */ + if (stat & RXERROR_PARITY) + flag = TTY_PARITY; + else if (stat & RXERROR_FRAMING) + flag = TTY_FRAME; + tty_insert_flip_char(&port->port, data[i+1], flag); } @@ -415,6 +421,8 @@ static void usa26_instat_callback(struct urb *urb) } port = serial->port[msg->port]; p_priv = usb_get_serial_port_data(port); + if (!p_priv) + goto resubmit; /* Update handshaking pin state information */ old_dcd_state = p_priv->dcd_state; @@ -425,7 +433,7 @@ static void usa26_instat_callback(struct urb *urb) if (old_dcd_state != p_priv->dcd_state) tty_port_tty_hangup(&port->port, true); - +resubmit: /* Resubmit urb so we continue receiving */ err = usb_submit_urb(urb, GFP_ATOMIC); if (err != 0) @@ -535,6 +543,8 @@ static void usa28_instat_callback(struct urb *urb) } port = serial->port[msg->port]; p_priv = usb_get_serial_port_data(port); + if (!p_priv) + goto resubmit; /* Update handshaking pin state information */ old_dcd_state = p_priv->dcd_state; @@ -545,7 +555,7 @@ static void usa28_instat_callback(struct urb *urb) if (old_dcd_state != p_priv->dcd_state && old_dcd_state) tty_port_tty_hangup(&port->port, true); - +resubmit: /* Resubmit urb so we continue receiving */ err = usb_submit_urb(urb, GFP_ATOMIC); if (err != 0) @@ -618,6 +628,8 @@ static void usa49_instat_callback(struct urb *urb) } port = serial->port[msg->portNumber]; p_priv = usb_get_serial_port_data(port); + if (!p_priv) + goto resubmit; /* Update handshaking pin state information */ old_dcd_state = p_priv->dcd_state; @@ -628,7 +640,7 @@ static void usa49_instat_callback(struct urb *urb) if (old_dcd_state != p_priv->dcd_state && old_dcd_state) tty_port_tty_hangup(&port->port, true); - +resubmit: /* Resubmit urb so we continue receiving */ err = usb_submit_urb(urb, GFP_ATOMIC); if (err != 0) @@ -666,14 +678,19 @@ static void usa49_indat_callback(struct urb *urb) } else { /* some bytes had errors, every byte has status */ for (i = 0; i + 1 < urb->actual_length; i += 2) { - int stat = data[i], flag = 0; - if (stat & RXERROR_OVERRUN) - flag |= TTY_OVERRUN; - if (stat & RXERROR_FRAMING) - flag |= TTY_FRAME; - if (stat & RXERROR_PARITY) - flag |= TTY_PARITY; + int stat = data[i]; + int flag = TTY_NORMAL; + + if (stat & RXERROR_OVERRUN) { + tty_insert_flip_char(&port->port, 0, + TTY_OVERRUN); + } /* XXX should handle break (0x10) */ + if (stat & RXERROR_PARITY) + flag = TTY_PARITY; + else if (stat & RXERROR_FRAMING) + flag = TTY_FRAME; + tty_insert_flip_char(&port->port, data[i+1], flag); } @@ -730,15 +747,19 @@ static void usa49wg_indat_callback(struct urb *urb) */ for (x = 0; x + 1 < len && i + 1 < urb->actual_length; x += 2) { - int stat = data[i], flag = 0; + int stat = data[i]; + int flag = TTY_NORMAL; - if (stat & RXERROR_OVERRUN) - flag |= TTY_OVERRUN; - if (stat & RXERROR_FRAMING) - flag |= TTY_FRAME; - if (stat & RXERROR_PARITY) - flag |= TTY_PARITY; + if (stat & RXERROR_OVERRUN) { + tty_insert_flip_char(&port->port, 0, + TTY_OVERRUN); + } /* XXX should handle break (0x10) */ + if (stat & RXERROR_PARITY) + flag = TTY_PARITY; + else if (stat & RXERROR_FRAMING) + flag = TTY_FRAME; + tty_insert_flip_char(&port->port, data[i+1], flag); i += 2; @@ -790,25 +811,31 @@ static void usa90_indat_callback(struct urb *urb) if ((data[0] & 0x80) == 0) { /* no errors on individual bytes, only possible overrun err*/ - if (data[0] & RXERROR_OVERRUN) - err = TTY_OVERRUN; - else - err = 0; + if (data[0] & RXERROR_OVERRUN) { + tty_insert_flip_char(&port->port, 0, + TTY_OVERRUN); + } for (i = 1; i < urb->actual_length ; ++i) tty_insert_flip_char(&port->port, - data[i], err); + data[i], TTY_NORMAL); } else { /* some bytes had errors, every byte has status */ dev_dbg(&port->dev, "%s - RX error!!!!\n", __func__); for (i = 0; i + 1 < urb->actual_length; i += 2) { - int stat = data[i], flag = 0; - if (stat & RXERROR_OVERRUN) - flag |= TTY_OVERRUN; - if (stat & RXERROR_FRAMING) - flag |= TTY_FRAME; - if (stat & RXERROR_PARITY) - flag |= TTY_PARITY; + int stat = data[i]; + int flag = TTY_NORMAL; + + if (stat & RXERROR_OVERRUN) { + tty_insert_flip_char( + &port->port, 0, + TTY_OVERRUN); + } /* XXX should handle break (0x10) */ + if (stat & RXERROR_PARITY) + flag = TTY_PARITY; + else if (stat & RXERROR_FRAMING) + flag = TTY_FRAME; + tty_insert_flip_char(&port->port, data[i+1], flag); } @@ -851,6 +878,8 @@ static void usa90_instat_callback(struct urb *urb) port = serial->port[0]; p_priv = usb_get_serial_port_data(port); + if (!p_priv) + goto resubmit; /* Update handshaking pin state information */ old_dcd_state = p_priv->dcd_state; @@ -861,7 +890,7 @@ static void usa90_instat_callback(struct urb *urb) if (old_dcd_state != p_priv->dcd_state && old_dcd_state) tty_port_tty_hangup(&port->port, true); - +resubmit: /* Resubmit urb so we continue receiving */ err = usb_submit_urb(urb, GFP_ATOMIC); if (err != 0) @@ -922,6 +951,8 @@ static void usa67_instat_callback(struct urb *urb) port = serial->port[msg->port]; p_priv = usb_get_serial_port_data(port); + if (!p_priv) + goto resubmit; /* Update handshaking pin state information */ old_dcd_state = p_priv->dcd_state; @@ -930,7 +961,7 @@ static void usa67_instat_callback(struct urb *urb) if (old_dcd_state != p_priv->dcd_state && old_dcd_state) tty_port_tty_hangup(&port->port, true); - +resubmit: /* Resubmit urb so we continue receiving */ err = usb_submit_urb(urb, GFP_ATOMIC); if (err != 0) diff --git a/drivers/usb/serial/kobil_sct.c b/drivers/usb/serial/kobil_sct.c index 618c1c1f227e..5cdb32b37e85 100644 --- a/drivers/usb/serial/kobil_sct.c +++ b/drivers/usb/serial/kobil_sct.c @@ -335,7 +335,8 @@ static int kobil_write(struct tty_struct *tty, struct usb_serial_port *port, port->interrupt_out_urb->transfer_buffer_length = length; priv->cur_pos = priv->cur_pos + length; - result = usb_submit_urb(port->interrupt_out_urb, GFP_NOIO); + result = usb_submit_urb(port->interrupt_out_urb, + GFP_ATOMIC); dev_dbg(&port->dev, "%s - Send write URB returns: %i\n", __func__, result); todo = priv->filled - priv->cur_pos; @@ -350,7 +351,7 @@ static int kobil_write(struct tty_struct *tty, struct usb_serial_port *port, if (priv->device_type == KOBIL_ADAPTER_B_PRODUCT_ID || priv->device_type == KOBIL_ADAPTER_K_PRODUCT_ID) { result = usb_submit_urb(port->interrupt_in_urb, - GFP_NOIO); + GFP_ATOMIC); dev_dbg(&port->dev, "%s - Send read URB returns: %i\n", __func__, result); } } diff --git a/drivers/usb/serial/mxuport.c b/drivers/usb/serial/mxuport.c index ab1d690274ae..460a40669967 100644 --- a/drivers/usb/serial/mxuport.c +++ b/drivers/usb/serial/mxuport.c @@ -1284,7 +1284,8 @@ static int mxuport_open(struct tty_struct *tty, struct usb_serial_port *port) } /* Initial port termios */ - mxuport_set_termios(tty, port, NULL); + if (tty) + mxuport_set_termios(tty, port, NULL); /* * TODO: use RQ_VENDOR_GET_MSR, once we know what it diff --git a/drivers/usb/serial/opticon.c b/drivers/usb/serial/opticon.c index 4856fb7e637e..4b7bfb394a32 100644 --- a/drivers/usb/serial/opticon.c +++ b/drivers/usb/serial/opticon.c @@ -215,7 +215,7 @@ static int opticon_write(struct tty_struct *tty, struct usb_serial_port *port, /* The connected devices do not have a bulk write endpoint, * to transmit data to de barcode device the control endpoint is used */ - dr = kmalloc(sizeof(struct usb_ctrlrequest), GFP_NOIO); + dr = kmalloc(sizeof(struct usb_ctrlrequest), GFP_ATOMIC); if (!dr) { count = -ENOMEM; goto error_no_dr; diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 9da566a3f5c8..8b3484134ab0 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -269,14 +269,19 @@ static void option_instat_callback(struct urb *urb); #define TELIT_PRODUCT_DE910_DUAL 0x1010 #define TELIT_PRODUCT_UE910_V2 0x1012 #define TELIT_PRODUCT_LE920 0x1200 +#define TELIT_PRODUCT_LE910 0x1201 /* ZTE PRODUCTS */ #define ZTE_VENDOR_ID 0x19d2 #define ZTE_PRODUCT_MF622 0x0001 #define ZTE_PRODUCT_MF628 0x0015 #define ZTE_PRODUCT_MF626 0x0031 -#define ZTE_PRODUCT_MC2718 0xffe8 #define ZTE_PRODUCT_AC2726 0xfff1 +#define ZTE_PRODUCT_CDMA_TECH 0xfffe +#define ZTE_PRODUCT_AC8710T 0xffff +#define ZTE_PRODUCT_MC2718 0xffe8 +#define ZTE_PRODUCT_AD3812 0xffeb +#define ZTE_PRODUCT_MC2716 0xffed #define BENQ_VENDOR_ID 0x04a5 #define BENQ_PRODUCT_H10 0x4068 @@ -357,6 +362,7 @@ static void option_instat_callback(struct urb *urb); /* Haier products */ #define HAIER_VENDOR_ID 0x201e +#define HAIER_PRODUCT_CE81B 0x10f8 #define HAIER_PRODUCT_CE100 0x2009 /* Cinterion (formerly Siemens) products */ @@ -494,6 +500,10 @@ static void option_instat_callback(struct urb *urb); #define INOVIA_VENDOR_ID 0x20a6 #define INOVIA_SEW858 0x1105 +/* VIA Telecom */ +#define VIATELECOM_VENDOR_ID 0x15eb +#define VIATELECOM_PRODUCT_CDS7 0x0001 + /* some devices interfaces need special handling due to a number of reasons */ enum option_blacklist_reason { OPTION_BLACKLIST_NONE = 0, @@ -527,10 +537,18 @@ static const struct option_blacklist_info zte_k3765_z_blacklist = { .reserved = BIT(4), }; +static const struct option_blacklist_info zte_ad3812_z_blacklist = { + .sendsetup = BIT(0) | BIT(1) | BIT(2), +}; + static const struct option_blacklist_info zte_mc2718_z_blacklist = { .sendsetup = BIT(1) | BIT(2) | BIT(3) | BIT(4), }; +static const struct option_blacklist_info zte_mc2716_z_blacklist = { + .sendsetup = BIT(1) | BIT(2) | BIT(3), +}; + static const struct option_blacklist_info huawei_cdc12_blacklist = { .reserved = BIT(1) | BIT(2), }; @@ -572,6 +590,11 @@ static const struct option_blacklist_info zte_1255_blacklist = { .reserved = BIT(3) | BIT(4), }; +static const struct option_blacklist_info telit_le910_blacklist = { + .sendsetup = BIT(0), + .reserved = BIT(1) | BIT(2), +}; + static const struct option_blacklist_info telit_le920_blacklist = { .sendsetup = BIT(0), .reserved = BIT(1) | BIT(5), @@ -1070,6 +1093,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(BANDRICH_VENDOR_ID, BANDRICH_PRODUCT_1012, 0xff) }, { USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC650) }, { USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC680) }, + { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6000)}, /* ZTE AC8700 */ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x0023)}, /* ONYX 3G device */ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */ @@ -1120,6 +1144,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_CC864_SINGLE) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_DE910_DUAL) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UE910_V2) }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910), + .driver_info = (kernel_ulong_t)&telit_le910_blacklist }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920), .driver_info = (kernel_ulong_t)&telit_le920_blacklist }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */ @@ -1544,13 +1570,18 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff93, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff94, 0xff, 0xff, 0xff) }, - /* NOTE: most ZTE CDMA devices should be driven by zte_ev, not option */ + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_CDMA_TECH, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC2726, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC8710T, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MC2718, 0xff, 0xff, 0xff), .driver_info = (kernel_ulong_t)&zte_mc2718_z_blacklist }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AD3812, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&zte_ad3812_z_blacklist }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MC2716, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&zte_mc2716_z_blacklist }, { USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x01) }, { USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x05) }, { USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x86, 0x10) }, - { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC2726, 0xff, 0xff, 0xff) }, { USB_DEVICE(BENQ_VENDOR_ID, BENQ_PRODUCT_H10) }, { USB_DEVICE(DLINK_VENDOR_ID, DLINK_PRODUCT_DWM_652) }, @@ -1590,6 +1621,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(LONGCHEER_VENDOR_ID, ZOOM_PRODUCT_4597) }, { USB_DEVICE(LONGCHEER_VENDOR_ID, IBALL_3_5G_CONNECT) }, { USB_DEVICE(HAIER_VENDOR_ID, HAIER_PRODUCT_CE100) }, + { USB_DEVICE_AND_INTERFACE_INFO(HAIER_VENDOR_ID, HAIER_PRODUCT_CE81B, 0xff, 0xff, 0xff) }, /* Pirelli */ { USB_DEVICE_INTERFACE_CLASS(PIRELLI_VENDOR_ID, PIRELLI_PRODUCT_C100_1, 0xff) }, { USB_DEVICE_INTERFACE_CLASS(PIRELLI_VENDOR_ID, PIRELLI_PRODUCT_C100_2, 0xff) }, @@ -1724,6 +1756,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */ { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */ { USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) }, + { USB_DEVICE(VIATELECOM_VENDOR_ID, VIATELECOM_PRODUCT_CDS7) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); @@ -1917,6 +1950,8 @@ static void option_instat_callback(struct urb *urb) dev_dbg(dev, "%s: type %x req %x\n", __func__, req_pkt->bRequestType, req_pkt->bRequest); } + } else if (status == -ENOENT || status == -ESHUTDOWN) { + dev_dbg(dev, "%s: urb stopped: %d\n", __func__, status); } else dev_err(dev, "%s: error %d\n", __func__, status); diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c index b3d5a35c0d4b..e9bad928039f 100644 --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -45,6 +45,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_GPRS) }, { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_HCR331) }, { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_MOTOROLA) }, + { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_ZTEK) }, { USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID) }, { USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID_RSAQ5) }, { USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_ID) }, diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h index 42bc082896ac..71fd9da1d6e7 100644 --- a/drivers/usb/serial/pl2303.h +++ b/drivers/usb/serial/pl2303.h @@ -22,6 +22,7 @@ #define PL2303_PRODUCT_ID_GPRS 0x0609 #define PL2303_PRODUCT_ID_HCR331 0x331a #define PL2303_PRODUCT_ID_MOTOROLA 0x0307 +#define PL2303_PRODUCT_ID_ZTEK 0xe1f1 #define ATEN_VENDOR_ID 0x0557 #define ATEN_VENDOR_ID2 0x0547 diff --git a/drivers/usb/serial/sierra.c b/drivers/usb/serial/sierra.c index 37480348e39b..74a9375a9bb5 100644 --- a/drivers/usb/serial/sierra.c +++ b/drivers/usb/serial/sierra.c @@ -282,14 +282,19 @@ static const struct usb_device_id id_table[] = { /* Sierra Wireless HSPA Non-Composite Device */ { USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x6892, 0xFF, 0xFF, 0xFF)}, { USB_DEVICE(0x1199, 0x6893) }, /* Sierra Wireless Device */ - { USB_DEVICE(0x1199, 0x68A3), /* Sierra Wireless Direct IP modems */ + /* Sierra Wireless Direct IP modems */ + { USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x68A3, 0xFF, 0xFF, 0xFF), + .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist + }, + { USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x68AA, 0xFF, 0xFF, 0xFF), .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist }, /* AT&T Direct IP LTE modems */ { USB_DEVICE_AND_INTERFACE_INFO(0x0F3D, 0x68AA, 0xFF, 0xFF, 0xFF), .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist }, - { USB_DEVICE(0x0f3d, 0x68A3), /* Airprime/Sierra Wireless Direct IP modems */ + /* Airprime/Sierra Wireless Direct IP modems */ + { USB_DEVICE_AND_INTERFACE_INFO(0x0F3D, 0x68A3, 0xFF, 0xFF, 0xFF), .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist }, diff --git a/drivers/usb/serial/ssu100.c b/drivers/usb/serial/ssu100.c index a7fe664b6b7d..70a098de429f 100644 --- a/drivers/usb/serial/ssu100.c +++ b/drivers/usb/serial/ssu100.c @@ -490,10 +490,9 @@ static void ssu100_update_lsr(struct usb_serial_port *port, u8 lsr, if (*tty_flag == TTY_NORMAL) *tty_flag = TTY_FRAME; } - if (lsr & UART_LSR_OE){ + if (lsr & UART_LSR_OE) { port->icount.overrun++; - if (*tty_flag == TTY_NORMAL) - *tty_flag = TTY_OVERRUN; + tty_insert_flip_char(&port->port, 0, TTY_OVERRUN); } } @@ -511,12 +510,8 @@ static void ssu100_process_read_urb(struct urb *urb) if ((len >= 4) && (packet[0] == 0x1b) && (packet[1] == 0x1b) && ((packet[2] == 0x00) || (packet[2] == 0x01))) { - if (packet[2] == 0x00) { + if (packet[2] == 0x00) ssu100_update_lsr(port, packet[3], &flag); - if (flag == TTY_OVERRUN) - tty_insert_flip_char(&port->port, 0, - TTY_OVERRUN); - } if (packet[2] == 0x01) ssu100_update_msr(port, packet[3]); diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c index b169b0f9b3a2..9a08e18e09b9 100644 --- a/drivers/usb/serial/usb-serial.c +++ b/drivers/usb/serial/usb-serial.c @@ -764,29 +764,39 @@ static int usb_serial_probe(struct usb_interface *interface, if (usb_endpoint_is_bulk_in(endpoint)) { /* we found a bulk in endpoint */ dev_dbg(ddev, "found bulk in on endpoint %d\n", i); - bulk_in_endpoint[num_bulk_in] = endpoint; - ++num_bulk_in; + if (num_bulk_in < MAX_NUM_PORTS) { + bulk_in_endpoint[num_bulk_in] = endpoint; + ++num_bulk_in; + } } if (usb_endpoint_is_bulk_out(endpoint)) { /* we found a bulk out endpoint */ dev_dbg(ddev, "found bulk out on endpoint %d\n", i); - bulk_out_endpoint[num_bulk_out] = endpoint; - ++num_bulk_out; + if (num_bulk_out < MAX_NUM_PORTS) { + bulk_out_endpoint[num_bulk_out] = endpoint; + ++num_bulk_out; + } } if (usb_endpoint_is_int_in(endpoint)) { /* we found a interrupt in endpoint */ dev_dbg(ddev, "found interrupt in on endpoint %d\n", i); - interrupt_in_endpoint[num_interrupt_in] = endpoint; - ++num_interrupt_in; + if (num_interrupt_in < MAX_NUM_PORTS) { + interrupt_in_endpoint[num_interrupt_in] = + endpoint; + ++num_interrupt_in; + } } if (usb_endpoint_is_int_out(endpoint)) { /* we found an interrupt out endpoint */ dev_dbg(ddev, "found interrupt out on endpoint %d\n", i); - interrupt_out_endpoint[num_interrupt_out] = endpoint; - ++num_interrupt_out; + if (num_interrupt_out < MAX_NUM_PORTS) { + interrupt_out_endpoint[num_interrupt_out] = + endpoint; + ++num_interrupt_out; + } } } @@ -809,8 +819,10 @@ static int usb_serial_probe(struct usb_interface *interface, if (usb_endpoint_is_int_in(endpoint)) { /* we found a interrupt in endpoint */ dev_dbg(ddev, "found interrupt in for Prolific device on separate interface\n"); - interrupt_in_endpoint[num_interrupt_in] = endpoint; - ++num_interrupt_in; + if (num_interrupt_in < MAX_NUM_PORTS) { + interrupt_in_endpoint[num_interrupt_in] = endpoint; + ++num_interrupt_in; + } } } } @@ -850,6 +862,11 @@ static int usb_serial_probe(struct usb_interface *interface, num_ports = type->num_ports; } + if (num_ports > MAX_NUM_PORTS) { + dev_warn(ddev, "too many ports requested: %d\n", num_ports); + num_ports = MAX_NUM_PORTS; + } + serial->num_ports = num_ports; serial->num_bulk_in = num_bulk_in; serial->num_bulk_out = num_bulk_out; diff --git a/drivers/usb/serial/zte_ev.c b/drivers/usb/serial/zte_ev.c index e40ab739c4a6..c9bb107d5e5c 100644 --- a/drivers/usb/serial/zte_ev.c +++ b/drivers/usb/serial/zte_ev.c @@ -272,28 +272,16 @@ static void zte_ev_usb_serial_close(struct usb_serial_port *port) } static const struct usb_device_id id_table[] = { - /* AC8710, AC8710T */ - { USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xffff, 0xff, 0xff, 0xff) }, - /* AC8700 */ - { USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xfffe, 0xff, 0xff, 0xff) }, - /* MG880 */ - { USB_DEVICE(0x19d2, 0xfffd) }, - { USB_DEVICE(0x19d2, 0xfffc) }, - { USB_DEVICE(0x19d2, 0xfffb) }, - /* AC8710_V3 */ + { USB_DEVICE(0x19d2, 0xffec) }, + { USB_DEVICE(0x19d2, 0xffee) }, { USB_DEVICE(0x19d2, 0xfff6) }, { USB_DEVICE(0x19d2, 0xfff7) }, { USB_DEVICE(0x19d2, 0xfff8) }, { USB_DEVICE(0x19d2, 0xfff9) }, - { USB_DEVICE(0x19d2, 0xffee) }, - /* AC2716, MC2716 */ - { USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xffed, 0xff, 0xff, 0xff) }, - /* AD3812 */ - { USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xffeb, 0xff, 0xff, 0xff) }, - { USB_DEVICE(0x19d2, 0xffec) }, - { USB_DEVICE(0x05C6, 0x3197) }, - { USB_DEVICE(0x05C6, 0x6000) }, - { USB_DEVICE(0x05C6, 0x9008) }, + { USB_DEVICE(0x19d2, 0xfffb) }, + { USB_DEVICE(0x19d2, 0xfffc) }, + /* MG880 */ + { USB_DEVICE(0x19d2, 0xfffd) }, { }, }; MODULE_DEVICE_TABLE(usb, id_table); diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c index 22c7d4360fa2..b1d815eb6d0b 100644 --- a/drivers/usb/storage/transport.c +++ b/drivers/usb/storage/transport.c @@ -1118,6 +1118,31 @@ int usb_stor_Bulk_transport(struct scsi_cmnd *srb, struct us_data *us) */ if (result == USB_STOR_XFER_LONG) fake_sense = 1; + + /* + * Sometimes a device will mistakenly skip the data phase + * and go directly to the status phase without sending a + * zero-length packet. If we get a 13-byte response here, + * check whether it really is a CSW. + */ + if (result == USB_STOR_XFER_SHORT && + srb->sc_data_direction == DMA_FROM_DEVICE && + transfer_length - scsi_get_resid(srb) == + US_BULK_CS_WRAP_LEN) { + struct scatterlist *sg = NULL; + unsigned int offset = 0; + + if (usb_stor_access_xfer_buf((unsigned char *) bcs, + US_BULK_CS_WRAP_LEN, srb, &sg, + &offset, FROM_XFER_BUF) == + US_BULK_CS_WRAP_LEN && + bcs->Signature == + cpu_to_le32(US_BULK_CS_SIGN)) { + usb_stor_dbg(us, "Device skipped data phase\n"); + scsi_set_resid(srb, transfer_length); + goto skipped_data_phase; + } + } } /* See flow chart on pg 15 of the Bulk Only Transport spec for @@ -1153,6 +1178,7 @@ int usb_stor_Bulk_transport(struct scsi_cmnd *srb, struct us_data *us) if (result != USB_STOR_XFER_GOOD) return USB_STOR_TRANSPORT_ERROR; + skipped_data_phase: /* check bulk status */ residue = le32_to_cpu(bcs->Residue); usb_stor_dbg(us, "Bulk Status S 0x%x T 0x%x R %u Stat 0x%x\n", diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 042c83b01046..7f625306ea80 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -101,6 +101,12 @@ UNUSUAL_DEV( 0x03f0, 0x4002, 0x0001, 0x0001, "PhotoSmart R707", USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_FIX_CAPACITY), +UNUSUAL_DEV( 0x03f3, 0x0001, 0x0000, 0x9999, + "Adaptec", + "USBConnect 2000", + USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init, + US_FL_SCM_MULT_TARG ), + /* Reported by Sebastian Kapfer <sebastian_kapfer@gmx.net> * and Olaf Hering <olh@suse.de> (different bcd's, same vendor/product) * for USB floppies that need the SINGLE_LUN enforcement. @@ -741,6 +747,12 @@ UNUSUAL_DEV( 0x059b, 0x0001, 0x0100, 0x0100, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_SINGLE_LUN ), +UNUSUAL_DEV( 0x059b, 0x0040, 0x0100, 0x0100, + "Iomega", + "Jaz USB Adapter", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_SINGLE_LUN ), + /* Reported by <Hendryk.Pfeiffer@gmx.de> */ UNUSUAL_DEV( 0x059f, 0x0643, 0x0000, 0x0000, "LaCie", @@ -1113,6 +1125,18 @@ UNUSUAL_DEV( 0x0851, 0x1543, 0x0200, 0x0200, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_NOT_LOCKABLE), +UNUSUAL_DEV( 0x085a, 0x0026, 0x0100, 0x0133, + "Xircom", + "PortGear USB-SCSI (Mac USB Dock)", + USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init, + US_FL_SCM_MULT_TARG ), + +UNUSUAL_DEV( 0x085a, 0x0028, 0x0100, 0x0133, + "Xircom", + "PortGear USB to SCSI Converter", + USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init, + US_FL_SCM_MULT_TARG ), + /* Submitted by Jan De Luyck <lkml@kcore.org> */ UNUSUAL_DEV( 0x08bd, 0x1100, 0x0000, 0x0000, "CITIZEN", @@ -1945,6 +1969,14 @@ UNUSUAL_DEV( 0x152d, 0x2329, 0x0100, 0x0100, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_IGNORE_RESIDUE | US_FL_SANE_SENSE ), +/* Entrega Technologies U1-SC25 (later Xircom PortGear PGSCSI) + * and Mac USB Dock USB-SCSI */ +UNUSUAL_DEV( 0x1645, 0x0007, 0x0100, 0x0133, + "Entrega Technologies", + "USB to SCSI Converter", + USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init, + US_FL_SCM_MULT_TARG ), + /* Reported by Robert Schedel <r.schedel@yahoo.de> * Note: this is a 'super top' device like the above 14cd/6600 device */ UNUSUAL_DEV( 0x1652, 0x6600, 0x0201, 0x0201, @@ -1967,6 +1999,12 @@ UNUSUAL_DEV( 0x177f, 0x0400, 0x0000, 0x0000, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_BULK_IGNORE_TAG | US_FL_MAX_SECTORS_64 ), +UNUSUAL_DEV( 0x1822, 0x0001, 0x0000, 0x9999, + "Ariston Technologies", + "iConnect USB to SCSI adapter", + USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init, + US_FL_SCM_MULT_TARG ), + /* Reported by Hans de Goede <hdegoede@redhat.com> * These Appotech controllers are found in Picture Frames, they provide a * (buggy) emulation of a cdrom drive which contains the windows software diff --git a/drivers/uwb/lc-dev.c b/drivers/uwb/lc-dev.c index 80079b8fed15..d0303f0dbe15 100644 --- a/drivers/uwb/lc-dev.c +++ b/drivers/uwb/lc-dev.c @@ -431,16 +431,19 @@ void uwbd_dev_onair(struct uwb_rc *rc, struct uwb_beca_e *bce) uwb_dev->mac_addr = *bce->mac_addr; uwb_dev->dev_addr = bce->dev_addr; dev_set_name(&uwb_dev->dev, "%s", macbuf); + + /* plug the beacon cache */ + bce->uwb_dev = uwb_dev; + uwb_dev->bce = bce; + uwb_bce_get(bce); /* released in uwb_dev_sys_release() */ + result = uwb_dev_add(uwb_dev, &rc->uwb_dev.dev, rc); if (result < 0) { dev_err(dev, "new device %s: cannot instantiate device\n", macbuf); goto error_dev_add; } - /* plug the beacon cache */ - bce->uwb_dev = uwb_dev; - uwb_dev->bce = bce; - uwb_bce_get(bce); /* released in uwb_dev_sys_release() */ + dev_info(dev, "uwb device (mac %s dev %s) connected to %s %s\n", macbuf, devbuf, rc->uwb_dev.dev.parent->bus->name, dev_name(rc->uwb_dev.dev.parent)); @@ -448,6 +451,8 @@ void uwbd_dev_onair(struct uwb_rc *rc, struct uwb_beca_e *bce) return; error_dev_add: + bce->uwb_dev = NULL; + uwb_bce_put(bce); kfree(uwb_dev); return; } diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 7ba042498857..75e1d03b8da3 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -810,13 +810,11 @@ static const struct vfio_device_ops vfio_pci_ops = { static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { - u8 type; struct vfio_pci_device *vdev; struct iommu_group *group; int ret; - pci_read_config_byte(pdev, PCI_HEADER_TYPE, &type); - if ((type & PCI_HEADER_TYPE) != PCI_HEADER_TYPE_NORMAL) + if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL) return -EINVAL; group = iommu_group_get(&pdev->dev); diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index e48d4a672580..486d710a5293 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -861,6 +861,23 @@ vhost_scsi_map_iov_to_sgl(struct tcm_vhost_cmd *cmd, return 0; } +static int vhost_scsi_to_tcm_attr(int attr) +{ + switch (attr) { + case VIRTIO_SCSI_S_SIMPLE: + return MSG_SIMPLE_TAG; + case VIRTIO_SCSI_S_ORDERED: + return MSG_ORDERED_TAG; + case VIRTIO_SCSI_S_HEAD: + return MSG_HEAD_TAG; + case VIRTIO_SCSI_S_ACA: + return MSG_ACA_TAG; + default: + break; + } + return MSG_SIMPLE_TAG; +} + static void tcm_vhost_submission_work(struct work_struct *work) { struct tcm_vhost_cmd *cmd = @@ -887,9 +904,10 @@ static void tcm_vhost_submission_work(struct work_struct *work) rc = target_submit_cmd_map_sgls(se_cmd, tv_nexus->tvn_se_sess, cmd->tvc_cdb, &cmd->tvc_sense_buf[0], cmd->tvc_lun, cmd->tvc_exp_data_len, - cmd->tvc_task_attr, cmd->tvc_data_direction, - TARGET_SCF_ACK_KREF, sg_ptr, cmd->tvc_sgl_count, - sg_bidi_ptr, sg_no_bidi, NULL, 0); + vhost_scsi_to_tcm_attr(cmd->tvc_task_attr), + cmd->tvc_data_direction, TARGET_SCF_ACK_KREF, + sg_ptr, cmd->tvc_sgl_count, sg_bidi_ptr, sg_no_bidi, + NULL, 0); if (rc < 0) { transport_send_check_condition_and_sense(se_cmd, TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE, 0); @@ -1200,6 +1218,7 @@ static int vhost_scsi_set_endpoint(struct vhost_scsi *vs, struct vhost_scsi_target *t) { + struct se_portal_group *se_tpg; struct tcm_vhost_tport *tv_tport; struct tcm_vhost_tpg *tpg; struct tcm_vhost_tpg **vs_tpg; @@ -1247,6 +1266,21 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, ret = -EEXIST; goto out; } + /* + * In order to ensure individual vhost-scsi configfs + * groups cannot be removed while in use by vhost ioctl, + * go ahead and take an explicit se_tpg->tpg_group.cg_item + * dependency now. + */ + se_tpg = &tpg->se_tpg; + ret = configfs_depend_item(se_tpg->se_tpg_tfo->tf_subsys, + &se_tpg->tpg_group.cg_item); + if (ret) { + pr_warn("configfs_depend_item() failed: %d\n", ret); + kfree(vs_tpg); + mutex_unlock(&tpg->tv_tpg_mutex); + goto out; + } tpg->tv_tpg_vhost_count++; tpg->vhost_scsi = vs; vs_tpg[tpg->tport_tpgt] = tpg; @@ -1289,6 +1323,7 @@ static int vhost_scsi_clear_endpoint(struct vhost_scsi *vs, struct vhost_scsi_target *t) { + struct se_portal_group *se_tpg; struct tcm_vhost_tport *tv_tport; struct tcm_vhost_tpg *tpg; struct vhost_virtqueue *vq; @@ -1337,6 +1372,13 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs, vs->vs_tpg[target] = NULL; match = true; mutex_unlock(&tpg->tv_tpg_mutex); + /* + * Release se_tpg->tpg_group.cg_item configfs dependency now + * to allow vhost-scsi WWPN se_tpg->tpg_group shutdown to occur. + */ + se_tpg = &tpg->se_tpg; + configfs_undepend_item(se_tpg->se_tpg_tfo->tf_subsys, + &se_tpg->tpg_group.cg_item); } if (match) { for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) { diff --git a/drivers/video/console/bitblit.c b/drivers/video/console/bitblit.c index 61b182bf32a2..dbfe4eecf12e 100644 --- a/drivers/video/console/bitblit.c +++ b/drivers/video/console/bitblit.c @@ -205,7 +205,6 @@ static void bit_putcs(struct vc_data *vc, struct fb_info *info, static void bit_clear_margins(struct vc_data *vc, struct fb_info *info, int bottom_only) { - int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; unsigned int cw = vc->vc_font.width; unsigned int ch = vc->vc_font.height; unsigned int rw = info->var.xres - (vc->vc_cols*cw); @@ -214,7 +213,7 @@ static void bit_clear_margins(struct vc_data *vc, struct fb_info *info, unsigned int bs = info->var.yres - bh; struct fb_fillrect region; - region.color = attr_bgcol_ec(bgshift, vc, info); + region.color = 0; region.rop = ROP_COPY; if (rw && !bottom_only) { diff --git a/drivers/video/console/fbcon_ccw.c b/drivers/video/console/fbcon_ccw.c index 41b32ae23dac..5a3cbf6dff4d 100644 --- a/drivers/video/console/fbcon_ccw.c +++ b/drivers/video/console/fbcon_ccw.c @@ -197,9 +197,8 @@ static void ccw_clear_margins(struct vc_data *vc, struct fb_info *info, unsigned int bh = info->var.xres - (vc->vc_rows*ch); unsigned int bs = vc->vc_rows*ch; struct fb_fillrect region; - int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; - region.color = attr_bgcol_ec(bgshift,vc,info); + region.color = 0; region.rop = ROP_COPY; if (rw && !bottom_only) { diff --git a/drivers/video/console/fbcon_cw.c b/drivers/video/console/fbcon_cw.c index a93670ef7f89..e7ee44db4e98 100644 --- a/drivers/video/console/fbcon_cw.c +++ b/drivers/video/console/fbcon_cw.c @@ -180,9 +180,8 @@ static void cw_clear_margins(struct vc_data *vc, struct fb_info *info, unsigned int bh = info->var.xres - (vc->vc_rows*ch); unsigned int rs = info->var.yres - rw; struct fb_fillrect region; - int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; - region.color = attr_bgcol_ec(bgshift,vc,info); + region.color = 0; region.rop = ROP_COPY; if (rw && !bottom_only) { diff --git a/drivers/video/console/fbcon_ud.c b/drivers/video/console/fbcon_ud.c index ff0872c0498b..19e3714abfe8 100644 --- a/drivers/video/console/fbcon_ud.c +++ b/drivers/video/console/fbcon_ud.c @@ -227,9 +227,8 @@ static void ud_clear_margins(struct vc_data *vc, struct fb_info *info, unsigned int rw = info->var.xres - (vc->vc_cols*cw); unsigned int bh = info->var.yres - (vc->vc_rows*ch); struct fb_fillrect region; - int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; - region.color = attr_bgcol_ec(bgshift,vc,info); + region.color = 0; region.rop = ROP_COPY; if (rw && !bottom_only) { diff --git a/drivers/video/logo/logo.c b/drivers/video/logo/logo.c index b670cbda38e3..ffe024b830fc 100644 --- a/drivers/video/logo/logo.c +++ b/drivers/video/logo/logo.c @@ -21,6 +21,21 @@ static bool nologo; module_param(nologo, bool, 0); MODULE_PARM_DESC(nologo, "Disables startup logo"); +/* + * Logos are located in the initdata, and will be freed in kernel_init. + * Use late_init to mark the logos as freed to prevent any further use. + */ + +static bool logos_freed; + +static int __init fb_logo_late_init(void) +{ + logos_freed = true; + return 0; +} + +late_initcall(fb_logo_late_init); + /* logo's are marked __initdata. Use __init_refok to tell * modpost that it is intended that this function uses data * marked __initdata. @@ -29,7 +44,7 @@ const struct linux_logo * __init_refok fb_find_logo(int depth) { const struct linux_logo *logo = NULL; - if (nologo) + if (nologo || logos_freed) return NULL; if (depth >= 1) { diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c index a416f9b2a7f6..827b5f8e6297 100644 --- a/drivers/virtio/virtio_pci.c +++ b/drivers/virtio/virtio_pci.c @@ -791,6 +791,7 @@ static int virtio_pci_restore(struct device *dev) struct pci_dev *pci_dev = to_pci_dev(dev); struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); struct virtio_driver *drv; + unsigned status = 0; int ret; drv = container_of(vp_dev->vdev.dev.driver, @@ -801,14 +802,40 @@ static int virtio_pci_restore(struct device *dev) return ret; pci_set_master(pci_dev); + /* We always start by resetting the device, in case a previous + * driver messed it up. */ + vp_reset(&vp_dev->vdev); + + /* Acknowledge that we've seen the device. */ + status |= VIRTIO_CONFIG_S_ACKNOWLEDGE; + vp_set_status(&vp_dev->vdev, status); + + /* Maybe driver failed before freeze. + * Restore the failed status, for debugging. */ + status |= vp_dev->saved_status & VIRTIO_CONFIG_S_FAILED; + vp_set_status(&vp_dev->vdev, status); + + if (!drv) + return 0; + + /* We have a driver! */ + status |= VIRTIO_CONFIG_S_DRIVER; + vp_set_status(&vp_dev->vdev, status); + vp_finalize_features(&vp_dev->vdev); - if (drv && drv->restore) + if (drv->restore) { ret = drv->restore(&vp_dev->vdev); + if (ret) { + status |= VIRTIO_CONFIG_S_FAILED; + vp_set_status(&vp_dev->vdev, status); + return ret; + } + } /* Finally, tell the device we're all set */ - if (!ret) - vp_set_status(&vp_dev->vdev, vp_dev->saved_status); + status |= VIRTIO_CONFIG_S_DRIVER_OK; + vp_set_status(&vp_dev->vdev, status); return ret; } diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index f4a9e3311297..c8860a8757ac 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -547,20 +547,26 @@ static unsigned int __startup_pirq(unsigned int irq) pirq_query_unmask(irq); rc = set_evtchn_to_irq(evtchn, irq); - if (rc != 0) { - pr_err("irq%d: Failed to set port to irq mapping (%d)\n", - irq, rc); - xen_evtchn_close(evtchn); - return 0; - } + if (rc) + goto err; + bind_evtchn_to_cpu(evtchn, 0); info->evtchn = evtchn; + rc = xen_evtchn_port_setup(info); + if (rc) + goto err; + out: unmask_evtchn(evtchn); eoi_pirq(irq_get_irq_data(irq)); return 0; + +err: + pr_err("irq%d: Failed to set port to irq mapping (%d)\n", irq, rc); + xen_evtchn_close(evtchn); + return 0; } static unsigned int startup_pirq(struct irq_data *data) diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index 624e8dc24532..edfd797db341 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -111,16 +111,17 @@ static void do_suspend(void) shutting_down = SHUTDOWN_SUSPEND; -#ifdef CONFIG_PREEMPT - /* If the kernel is preemptible, we need to freeze all the processes - to prevent them from being in the middle of a pagetable update - during suspend. */ err = freeze_processes(); if (err) { - pr_err("%s: freeze failed %d\n", __func__, err); + pr_err("%s: freeze processes failed %d\n", __func__, err); goto out; } -#endif + + err = freeze_kernel_threads(); + if (err) { + pr_err("%s: freeze kernel threads failed %d\n", __func__, err); + goto out_thaw; + } err = dpm_suspend_start(PMSG_FREEZE); if (err) { @@ -169,10 +170,8 @@ out_resume: dpm_resume_end(si.cancelled ? PMSG_THAW : PMSG_RESTORE); out_thaw: -#ifdef CONFIG_PREEMPT thaw_processes(); out: -#endif shutting_down = SHUTDOWN_INVALID; } #endif /* CONFIG_HIBERNATE_CALLBACKS */ diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index ebd8f218a788..f3a9d831d0f9 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -96,8 +96,6 @@ static inline phys_addr_t xen_bus_to_phys(dma_addr_t baddr) dma_addr_t dma = (dma_addr_t)pfn << PAGE_SHIFT; phys_addr_t paddr = dma; - BUG_ON(paddr != dma); /* truncation has occurred, should never happen */ - paddr |= baddr & ~PAGE_MASK; return paddr; @@ -447,7 +445,7 @@ static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr, BUG_ON(dir == DMA_NONE); - xen_dma_unmap_page(hwdev, paddr, size, dir, attrs); + xen_dma_unmap_page(hwdev, dev_addr, size, dir, attrs); /* NOTE: We use dev_addr here, not paddr! */ if (is_xen_swiotlb_buffer(dev_addr)) { @@ -495,14 +493,14 @@ xen_swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr, BUG_ON(dir == DMA_NONE); if (target == SYNC_FOR_CPU) - xen_dma_sync_single_for_cpu(hwdev, paddr, size, dir); + xen_dma_sync_single_for_cpu(hwdev, dev_addr, size, dir); /* NOTE: We use dev_addr here, not paddr! */ if (is_xen_swiotlb_buffer(dev_addr)) swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target); if (target == SYNC_FOR_DEVICE) - xen_dma_sync_single_for_cpu(hwdev, paddr, size, dir); + xen_dma_sync_single_for_device(hwdev, dev_addr, size, dir); if (dir != DMA_FROM_DEVICE) return; diff --git a/drivers/xen/xen-pciback/conf_space.c b/drivers/xen/xen-pciback/conf_space.c index 46ae0f9f02ad..75fe3d466515 100644 --- a/drivers/xen/xen-pciback/conf_space.c +++ b/drivers/xen/xen-pciback/conf_space.c @@ -16,7 +16,7 @@ #include "conf_space.h" #include "conf_space_quirks.h" -static bool permissive; +bool permissive; module_param(permissive, bool, 0644); /* This is where xen_pcibk_read_config_byte, xen_pcibk_read_config_word, diff --git a/drivers/xen/xen-pciback/conf_space.h b/drivers/xen/xen-pciback/conf_space.h index e56c934ad137..2e1d73d1d5d0 100644 --- a/drivers/xen/xen-pciback/conf_space.h +++ b/drivers/xen/xen-pciback/conf_space.h @@ -64,6 +64,8 @@ struct config_field_entry { void *data; }; +extern bool permissive; + #define OFFSET(cfg_entry) ((cfg_entry)->base_offset+(cfg_entry)->field->offset) /* Add fields to a device - the add_fields macro expects to get a pointer to diff --git a/drivers/xen/xen-pciback/conf_space_header.c b/drivers/xen/xen-pciback/conf_space_header.c index c5ee82587e8c..2d7369391472 100644 --- a/drivers/xen/xen-pciback/conf_space_header.c +++ b/drivers/xen/xen-pciback/conf_space_header.c @@ -11,6 +11,10 @@ #include "pciback.h" #include "conf_space.h" +struct pci_cmd_info { + u16 val; +}; + struct pci_bar_info { u32 val; u32 len_val; @@ -20,22 +24,36 @@ struct pci_bar_info { #define is_enable_cmd(value) ((value)&(PCI_COMMAND_MEMORY|PCI_COMMAND_IO)) #define is_master_cmd(value) ((value)&PCI_COMMAND_MASTER) -static int command_read(struct pci_dev *dev, int offset, u16 *value, void *data) +/* Bits guests are allowed to control in permissive mode. */ +#define PCI_COMMAND_GUEST (PCI_COMMAND_MASTER|PCI_COMMAND_SPECIAL| \ + PCI_COMMAND_INVALIDATE|PCI_COMMAND_VGA_PALETTE| \ + PCI_COMMAND_WAIT|PCI_COMMAND_FAST_BACK) + +static void *command_init(struct pci_dev *dev, int offset) { - int i; - int ret; - - ret = xen_pcibk_read_config_word(dev, offset, value, data); - if (!pci_is_enabled(dev)) - return ret; - - for (i = 0; i < PCI_ROM_RESOURCE; i++) { - if (dev->resource[i].flags & IORESOURCE_IO) - *value |= PCI_COMMAND_IO; - if (dev->resource[i].flags & IORESOURCE_MEM) - *value |= PCI_COMMAND_MEMORY; + struct pci_cmd_info *cmd = kmalloc(sizeof(*cmd), GFP_KERNEL); + int err; + + if (!cmd) + return ERR_PTR(-ENOMEM); + + err = pci_read_config_word(dev, PCI_COMMAND, &cmd->val); + if (err) { + kfree(cmd); + return ERR_PTR(err); } + return cmd; +} + +static int command_read(struct pci_dev *dev, int offset, u16 *value, void *data) +{ + int ret = pci_read_config_word(dev, offset, value); + const struct pci_cmd_info *cmd = data; + + *value &= PCI_COMMAND_GUEST; + *value |= cmd->val & ~PCI_COMMAND_GUEST; + return ret; } @@ -43,6 +61,8 @@ static int command_write(struct pci_dev *dev, int offset, u16 value, void *data) { struct xen_pcibk_dev_data *dev_data; int err; + u16 val; + struct pci_cmd_info *cmd = data; dev_data = pci_get_drvdata(dev); if (!pci_is_enabled(dev) && is_enable_cmd(value)) { @@ -83,6 +103,19 @@ static int command_write(struct pci_dev *dev, int offset, u16 value, void *data) } } + cmd->val = value; + + if (!permissive && (!dev_data || !dev_data->permissive)) + return 0; + + /* Only allow the guest to control certain bits. */ + err = pci_read_config_word(dev, offset, &val); + if (err || val == value) + return err; + + value &= PCI_COMMAND_GUEST; + value |= val & ~PCI_COMMAND_GUEST; + return pci_write_config_word(dev, offset, value); } @@ -282,6 +315,8 @@ static const struct config_field header_common[] = { { .offset = PCI_COMMAND, .size = 2, + .init = command_init, + .release = bar_release, .u.w.read = command_read, .u.w.write = command_write, }, diff --git a/fs/Kconfig b/fs/Kconfig index 7385e54be4b9..6b40fd8d719e 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -67,6 +67,7 @@ source "fs/quota/Kconfig" source "fs/autofs4/Kconfig" source "fs/fuse/Kconfig" +source "fs/overlayfs/Kconfig" menu "Caches" diff --git a/fs/Makefile b/fs/Makefile index 47ac07bb4acc..b5954404e02d 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -104,6 +104,7 @@ obj-$(CONFIG_QNX6FS_FS) += qnx6/ obj-$(CONFIG_AUTOFS4_FS) += autofs4/ obj-$(CONFIG_ADFS_FS) += adfs/ obj-$(CONFIG_FUSE_FS) += fuse/ +obj-$(CONFIG_OVERLAY_FS) += overlayfs/ obj-$(CONFIG_UDF_FS) += udf/ obj-$(CONFIG_SUN_OPENPROMFS) += openpromfs/ obj-$(CONFIG_OMFS_FS) += omfs/ diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 529300327f45..5479af6de6ce 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -26,7 +26,7 @@ static int afs_readdir(struct file *file, struct dir_context *ctx); static int afs_d_revalidate(struct dentry *dentry, unsigned int flags); static int afs_d_delete(const struct dentry *dentry); static void afs_d_release(struct dentry *dentry); -static int afs_lookup_filldir(void *_cookie, const char *name, int nlen, +static int afs_lookup_filldir(struct dir_context *ctx, const char *name, int nlen, loff_t fpos, u64 ino, unsigned dtype); static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl); @@ -391,10 +391,11 @@ static int afs_readdir(struct file *file, struct dir_context *ctx) * - if afs_dir_iterate_block() spots this function, it'll pass the FID * uniquifier through dtype */ -static int afs_lookup_filldir(void *_cookie, const char *name, int nlen, - loff_t fpos, u64 ino, unsigned dtype) +static int afs_lookup_filldir(struct dir_context *ctx, const char *name, + int nlen, loff_t fpos, u64 ino, unsigned dtype) { - struct afs_lookup_cookie *cookie = _cookie; + struct afs_lookup_cookie *cookie = + container_of(ctx, struct afs_lookup_cookie, ctx); _enter("{%s,%u},%s,%u,,%llu,%u", cookie->name.name, cookie->name.len, name, nlen, @@ -141,6 +141,7 @@ struct kioctx { struct { unsigned tail; + unsigned completed_events; spinlock_t completion_lock; } ____cacheline_aligned_in_smp; @@ -164,6 +165,15 @@ static struct vfsmount *aio_mnt; static const struct file_operations aio_ring_fops; static const struct address_space_operations aio_ctx_aops; +/* Backing dev info for aio fs. + * -no dirty page accounting or writeback happens + */ +static struct backing_dev_info aio_fs_backing_dev_info = { + .name = "aiofs", + .state = 0, + .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_MAP_COPY, +}; + static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages) { struct qstr this = QSTR_INIT("[aio]", 5); @@ -175,6 +185,7 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages) inode->i_mapping->a_ops = &aio_ctx_aops; inode->i_mapping->private_data = ctx; + inode->i_mapping->backing_dev_info = &aio_fs_backing_dev_info; inode->i_size = PAGE_SIZE * nr_pages; path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this); @@ -220,6 +231,9 @@ static int __init aio_setup(void) if (IS_ERR(aio_mnt)) panic("Failed to create aio fs mount."); + if (bdi_init(&aio_fs_backing_dev_info)) + panic("Failed to init aio fs backing dev info."); + kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC); kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC); @@ -281,11 +295,6 @@ static const struct file_operations aio_ring_fops = { .mmap = aio_ring_mmap, }; -static int aio_set_page_dirty(struct page *page) -{ - return 0; -} - #if IS_ENABLED(CONFIG_MIGRATION) static int aio_migratepage(struct address_space *mapping, struct page *new, struct page *old, enum migrate_mode mode) @@ -357,7 +366,7 @@ out: #endif static const struct address_space_operations aio_ctx_aops = { - .set_page_dirty = aio_set_page_dirty, + .set_page_dirty = __set_page_dirty_no_writeback, #if IS_ENABLED(CONFIG_MIGRATION) .migratepage = aio_migratepage, #endif @@ -412,7 +421,6 @@ static int aio_setup_ring(struct kioctx *ctx) pr_debug("pid(%d) page[%d]->count=%d\n", current->pid, i, page_count(page)); SetPageUptodate(page); - SetPageDirty(page); unlock_page(page); ctx->ring_pages[i] = page; @@ -711,6 +719,9 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) err_cleanup: aio_nr_sub(ctx->max_reqs); err_ctx: + atomic_set(&ctx->dead, 1); + if (ctx->mmap_size) + vm_munmap(ctx->mmap_base, ctx->mmap_size); aio_free_ring(ctx); err: mutex_unlock(&ctx->ring_lock); @@ -796,6 +807,9 @@ void exit_aio(struct mm_struct *mm) unsigned i = 0; while (1) { + struct completion requests_done = + COMPLETION_INITIALIZER_ONSTACK(requests_done); + rcu_read_lock(); table = rcu_dereference(mm->ioctx_table); @@ -823,7 +837,10 @@ void exit_aio(struct mm_struct *mm) */ ctx->mmap_size = 0; - kill_ioctx(mm, ctx, NULL); + kill_ioctx(mm, ctx, &requests_done); + + /* Wait until all IO for the context are done. */ + wait_for_completion(&requests_done); } } @@ -880,6 +897,68 @@ out: return ret; } +/* refill_reqs_available + * Updates the reqs_available reference counts used for tracking the + * number of free slots in the completion ring. This can be called + * from aio_complete() (to optimistically update reqs_available) or + * from aio_get_req() (the we're out of events case). It must be + * called holding ctx->completion_lock. + */ +static void refill_reqs_available(struct kioctx *ctx, unsigned head, + unsigned tail) +{ + unsigned events_in_ring, completed; + + /* Clamp head since userland can write to it. */ + head %= ctx->nr_events; + if (head <= tail) + events_in_ring = tail - head; + else + events_in_ring = ctx->nr_events - (head - tail); + + completed = ctx->completed_events; + if (events_in_ring < completed) + completed -= events_in_ring; + else + completed = 0; + + if (!completed) + return; + + ctx->completed_events -= completed; + put_reqs_available(ctx, completed); +} + +/* user_refill_reqs_available + * Called to refill reqs_available when aio_get_req() encounters an + * out of space in the completion ring. + */ +static void user_refill_reqs_available(struct kioctx *ctx) +{ + spin_lock_irq(&ctx->completion_lock); + if (ctx->completed_events) { + struct aio_ring *ring; + unsigned head; + + /* Access of ring->head may race with aio_read_events_ring() + * here, but that's okay since whether we read the old version + * or the new version, and either will be valid. The important + * part is that head cannot pass tail since we prevent + * aio_complete() from updating tail by holding + * ctx->completion_lock. Even if head is invalid, the check + * against ctx->completed_events below will make sure we do the + * safe/right thing. + */ + ring = kmap_atomic(ctx->ring_pages[0]); + head = ring->head; + kunmap_atomic(ring); + + refill_reqs_available(ctx, head, ctx->tail); + } + + spin_unlock_irq(&ctx->completion_lock); +} + /* aio_get_req * Allocate a slot for an aio request. * Returns NULL if no requests are free. @@ -888,8 +967,11 @@ static inline struct kiocb *aio_get_req(struct kioctx *ctx) { struct kiocb *req; - if (!get_reqs_available(ctx)) - return NULL; + if (!get_reqs_available(ctx)) { + user_refill_reqs_available(ctx); + if (!get_reqs_available(ctx)) + return NULL; + } req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL|__GFP_ZERO); if (unlikely(!req)) @@ -948,8 +1030,8 @@ void aio_complete(struct kiocb *iocb, long res, long res2) struct kioctx *ctx = iocb->ki_ctx; struct aio_ring *ring; struct io_event *ev_page, *event; + unsigned tail, pos, head; unsigned long flags; - unsigned tail, pos; /* * Special case handling for sync iocbs: @@ -1010,10 +1092,14 @@ void aio_complete(struct kiocb *iocb, long res, long res2) ctx->tail = tail; ring = kmap_atomic(ctx->ring_pages[0]); + head = ring->head; ring->tail = tail; kunmap_atomic(ring); flush_dcache_page(ctx->ring_pages[0]); + ctx->completed_events++; + if (ctx->completed_events > 1) + refill_reqs_available(ctx, head, tail); spin_unlock_irqrestore(&ctx->completion_lock, flags); pr_debug("added to ring %p at [%u]\n", iocb, tail); @@ -1028,7 +1114,6 @@ void aio_complete(struct kiocb *iocb, long res, long res2) /* everything turned out well, dispose of the aiocb. */ kiocb_free(iocb); - put_reqs_available(ctx, 1); /* * We have to order our ring_info tail store above and test @@ -1065,6 +1150,12 @@ static long aio_read_events_ring(struct kioctx *ctx, tail = ring->tail; kunmap_atomic(ring); + /* + * Ensure that once we've read the current tail pointer, that + * we also see the events that were stored up to the tail. + */ + smp_rmb(); + pr_debug("h%u t%u m%u\n", head, tail, ctx->nr_events); if (head == tail) diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c index 3182c0e68b42..e3399dc2453b 100644 --- a/fs/autofs4/dev-ioctl.c +++ b/fs/autofs4/dev-ioctl.c @@ -95,7 +95,7 @@ static int check_dev_ioctl_version(int cmd, struct autofs_dev_ioctl *param) */ static struct autofs_dev_ioctl *copy_dev_ioctl(struct autofs_dev_ioctl __user *in) { - struct autofs_dev_ioctl tmp; + struct autofs_dev_ioctl tmp, *res; if (copy_from_user(&tmp, in, sizeof(tmp))) return ERR_PTR(-EFAULT); @@ -103,7 +103,11 @@ static struct autofs_dev_ioctl *copy_dev_ioctl(struct autofs_dev_ioctl __user *i if (tmp.size < sizeof(tmp)) return ERR_PTR(-EINVAL); - return memdup_user(in, tmp.size); + res = memdup_user(in, tmp.size); + if (!IS_ERR(res)) + res->size = tmp.size; + + return res; } static inline void free_dev_ioctl(struct autofs_dev_ioctl *param) diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 67be2951b98a..f4d7b2fc9ffb 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -549,11 +549,12 @@ out: static unsigned long randomize_stack_top(unsigned long stack_top) { - unsigned int random_variable = 0; + unsigned long random_variable = 0; if ((current->flags & PF_RANDOMIZE) && !(current->personality & ADDR_NO_RANDOMIZE)) { - random_variable = get_random_int() & STACK_RND_MASK; + random_variable = (unsigned long) get_random_int(); + random_variable &= STACK_RND_MASK; random_variable <<= PAGE_SHIFT; } #ifdef CONFIG_STACK_GROWSUP diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index b01fb6c527e3..d43c544d3b68 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -472,7 +472,7 @@ static noinline int add_ra_bio_pages(struct inode *inode, rcu_read_lock(); page = radix_tree_lookup(&mapping->page_tree, pg_index); rcu_read_unlock(); - if (page) { + if (page && !radix_tree_exceptional_entry(page)) { misses++; if (misses > 4) break; diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index cbd3a7d6fa68..93de3ba994e7 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -2655,32 +2655,23 @@ static int key_search(struct extent_buffer *b, struct btrfs_key *key, return 0; } -int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *found_path, +int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *path, u64 iobjectid, u64 ioff, u8 key_type, struct btrfs_key *found_key) { int ret; struct btrfs_key key; struct extent_buffer *eb; - struct btrfs_path *path; + + ASSERT(path); key.type = key_type; key.objectid = iobjectid; key.offset = ioff; - if (found_path == NULL) { - path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; - } else - path = found_path; - ret = btrfs_search_slot(NULL, fs_root, &key, path, 0, 0); - if ((ret < 0) || (found_key == NULL)) { - if (path != found_path) - btrfs_free_path(path); + if ((ret < 0) || (found_key == NULL)) return ret; - } eb = path->nodes[0]; if (ret && path->slots[0] >= btrfs_header_nritems(eb)) { diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 451b00c86f6c..12e35566d2fc 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1854,6 +1854,14 @@ int btrfs_delayed_delete_inode_ref(struct inode *inode) { struct btrfs_delayed_node *delayed_node; + /* + * we don't do delayed inode updates during log recovery because it + * leads to enospc problems. This means we also can't do + * delayed inode refs + */ + if (BTRFS_I(inode)->root->fs_info->log_root_recovering) + return -EAGAIN; + delayed_node = btrfs_get_or_create_delayed_node(inode); if (IS_ERR(delayed_node)) return PTR_ERR(delayed_node); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 370ef7450157..f48d5fc352a9 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1560,6 +1560,7 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, bool check_ref) { struct btrfs_root *root; + struct btrfs_path *path; int ret; if (location->objectid == BTRFS_ROOT_TREE_OBJECTID) @@ -1599,8 +1600,14 @@ again: if (ret) goto fail; - ret = btrfs_find_item(fs_info->tree_root, NULL, BTRFS_ORPHAN_OBJECTID, + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto fail; + } + ret = btrfs_find_item(fs_info->tree_root, path, BTRFS_ORPHAN_OBJECTID, location->objectid, BTRFS_ORPHAN_ITEM_KEY, NULL); + btrfs_free_path(path); if (ret < 0) goto fail; if (ret == 0) @@ -2411,7 +2418,7 @@ int open_ctree(struct super_block *sb, features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO; if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA) - printk(KERN_ERR "BTRFS: has skinny extents\n"); + printk(KERN_INFO "BTRFS: has skinny extents\n"); /* * flag our filesystem as having big metadata blocks if @@ -3978,12 +3985,6 @@ again: if (ret) break; - /* opt_discard */ - if (btrfs_test_opt(root, DISCARD)) - ret = btrfs_error_discard_extent(root, start, - end + 1 - start, - NULL); - clear_extent_dirty(unpin, start, end, GFP_NOFS); btrfs_error_unpin_extent_range(root, start, end); cond_resched(); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 3ff98e23f651..d2f1c011d73a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5503,7 +5503,8 @@ void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans, update_global_block_rsv(fs_info); } -static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end) +static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end, + const bool return_free_space) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_block_group_cache *cache = NULL; @@ -5527,7 +5528,8 @@ static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end) if (start < cache->last_byte_to_unpin) { len = min(len, cache->last_byte_to_unpin - start); - btrfs_add_free_space(cache, start, len); + if (return_free_space) + btrfs_add_free_space(cache, start, len); } start += len; @@ -5590,7 +5592,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans, end + 1 - start, NULL); clear_extent_dirty(unpin, start, end, GFP_NOFS); - unpin_extent_range(root, start, end); + unpin_extent_range(root, start, end, true); cond_resched(); } @@ -8886,7 +8888,7 @@ out: int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end) { - return unpin_extent_range(root, start, end); + return unpin_extent_range(root, start, end, false); } int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr, diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 1a858947006e..fa9f90049099 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4507,7 +4507,8 @@ static void check_buffer_tree_ref(struct extent_buffer *eb) spin_unlock(&eb->refs_lock); } -static void mark_extent_buffer_accessed(struct extent_buffer *eb) +static void mark_extent_buffer_accessed(struct extent_buffer *eb, + struct page *accessed) { unsigned long num_pages, i; @@ -4516,7 +4517,8 @@ static void mark_extent_buffer_accessed(struct extent_buffer *eb) num_pages = num_extent_pages(eb->start, eb->len); for (i = 0; i < num_pages; i++) { struct page *p = extent_buffer_page(eb, i); - mark_page_accessed(p); + if (p != accessed) + mark_page_accessed(p); } } @@ -4530,7 +4532,7 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info, start >> PAGE_CACHE_SHIFT); if (eb && atomic_inc_not_zero(&eb->refs)) { rcu_read_unlock(); - mark_extent_buffer_accessed(eb); + mark_extent_buffer_accessed(eb, NULL); return eb; } rcu_read_unlock(); @@ -4578,7 +4580,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, spin_unlock(&mapping->private_lock); unlock_page(p); page_cache_release(p); - mark_extent_buffer_accessed(exists); + mark_extent_buffer_accessed(exists, p); goto free_eb; } @@ -4593,7 +4595,6 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, attach_extent_buffer_page(eb, p); spin_unlock(&mapping->private_lock); WARN_ON(PageDirty(p)); - mark_page_accessed(p); eb->pages[i] = p; if (!PageUptodate(p)) uptodate = 0; diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 996ad56b57db..82845a6c63c2 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -290,8 +290,6 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len, if (!em) goto out; - if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags)) - list_move(&em->list, &tree->modified_extents); em->generation = gen; clear_bit(EXTENT_FLAG_PINNED, &em->flags); em->mod_start = em->start; diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index ca248b0687f4..196b089b0052 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -423,7 +423,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end, ret = 0; fail: while (ret < 0 && !list_empty(&tmplist)) { - sums = list_entry(&tmplist, struct btrfs_ordered_sum, list); + sums = list_entry(tmplist.next, struct btrfs_ordered_sum, list); list_del(&sums->list); kfree(sums); } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 0165b8672f09..0a841ddd6843 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -425,13 +425,8 @@ static noinline int btrfs_copy_from_user(loff_t pos, int num_pages, struct page *page = prepared_pages[pg]; /* * Copy data from userspace to the current page - * - * Disable pagefault to avoid recursive lock since - * the pages are already locked */ - pagefault_disable(); copied = iov_iter_copy_from_user_atomic(page, i, offset, count); - pagefault_enable(); /* Flush processor's dcache for this page */ flush_dcache_page(page); @@ -475,11 +470,12 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages) for (i = 0; i < num_pages; i++) { /* page checked is some magic around finding pages that * have been modified without going through btrfs_set_page_dirty - * clear it here + * clear it here. There should be no need to mark the pages + * accessed as prepare_pages should have marked them accessed + * in prepare_pages via find_or_create_page() */ ClearPageChecked(pages[i]); unlock_page(pages[i]); - mark_page_accessed(pages[i]); page_cache_release(pages[i]); } } @@ -1778,22 +1774,10 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, mutex_unlock(&inode->i_mutex); /* - * we want to make sure fsync finds this change - * but we haven't joined a transaction running right now. - * - * Later on, someone is sure to update the inode and get the - * real transid recorded. - * - * We set last_trans now to the fs_info generation + 1, - * this will either be one more than the running transaction - * or the generation used for the next transaction if there isn't - * one running right now. - * * We also have to set last_sub_trans to the current log transid, * otherwise subsequent syncs to a file that's been synced in this * transaction will appear to have already occured. */ - BTRFS_I(inode)->last_trans = root->fs_info->generation + 1; BTRFS_I(inode)->last_sub_trans = root->log_transid; if (num_written > 0) { err = generic_write_sync(file, pos, num_written); @@ -1896,25 +1880,37 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) atomic_inc(&root->log_batch); /* - * check the transaction that last modified this inode - * and see if its already been committed - */ - if (!BTRFS_I(inode)->last_trans) { - mutex_unlock(&inode->i_mutex); - goto out; - } - - /* - * if the last transaction that changed this file was before - * the current transaction, we can bail out now without any - * syncing + * If the last transaction that changed this file was before the current + * transaction and we have the full sync flag set in our inode, we can + * bail out now without any syncing. + * + * Note that we can't bail out if the full sync flag isn't set. This is + * because when the full sync flag is set we start all ordered extents + * and wait for them to fully complete - when they complete they update + * the inode's last_trans field through: + * + * btrfs_finish_ordered_io() -> + * btrfs_update_inode_fallback() -> + * btrfs_update_inode() -> + * btrfs_set_inode_last_trans() + * + * So we are sure that last_trans is up to date and can do this check to + * bail out safely. For the fast path, when the full sync flag is not + * set in our inode, we can not do it because we start only our ordered + * extents and don't wait for them to complete (that is when + * btrfs_finish_ordered_io runs), so here at this point their last_trans + * value might be less than or equals to fs_info->last_trans_committed, + * and setting a speculative last_trans for an inode when a buffered + * write is made (such as fs_info->generation + 1 for example) would not + * be reliable since after setting the value and before fsync is called + * any number of transactions can start and commit (transaction kthread + * commits the current transaction periodically), and a transaction + * commit does not start nor waits for ordered extents to complete. */ smp_mb(); if (btrfs_inode_in_log(inode, root->fs_info->generation) || - BTRFS_I(inode)->last_trans <= - root->fs_info->last_trans_committed) { - BTRFS_I(inode)->last_trans = 0; - + (full_sync && BTRFS_I(inode)->last_trans <= + root->fs_info->last_trans_committed)) { /* * We'v had everything committed since the last time we were * modified so clear this flag in case it was set for whatever @@ -2510,23 +2506,28 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence) struct btrfs_root *root = BTRFS_I(inode)->root; struct extent_map *em = NULL; struct extent_state *cached_state = NULL; - u64 lockstart = *offset; - u64 lockend = i_size_read(inode); - u64 start = *offset; - u64 len = i_size_read(inode); + u64 lockstart; + u64 lockend; + u64 start; + u64 len; int ret = 0; - lockend = max_t(u64, root->sectorsize, lockend); + if (inode->i_size == 0) + return -ENXIO; + + /* + * *offset can be negative, in this case we start finding DATA/HOLE from + * the very start of the file. + */ + start = max_t(loff_t, 0, *offset); + + lockstart = round_down(start, root->sectorsize); + lockend = round_up(i_size_read(inode), root->sectorsize); if (lockend <= lockstart) lockend = lockstart + root->sectorsize; - lockend--; len = lockend - lockstart + 1; - len = max_t(u64, len, root->sectorsize); - if (inode->i_size == 0) - return -ENXIO; - lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend, 0, &cached_state); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c69c76351f12..653cdd85e0f2 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3596,7 +3596,8 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans, * without delay */ if (!btrfs_is_free_space_inode(inode) - && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) { + && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID + && !root->fs_info->log_root_recovering) { btrfs_update_root_times(trans, root); ret = btrfs_delayed_update_inode(trans, root, inode); @@ -6869,7 +6870,6 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) && em->block_start != EXTENT_MAP_HOLE)) { int type; - int ret; u64 block_start, orig_start, orig_block_len, ram_bytes; if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a6d8efa46bfe..96b95e6f9f91 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -302,6 +302,9 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) goto out_drop; } else { + ret = btrfs_set_prop(inode, "btrfs.compression", NULL, 0, 0); + if (ret && ret != -ENODATA) + goto out_drop; ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS); } @@ -679,23 +682,6 @@ out: return ret; } -/* copy of check_sticky in fs/namei.c() -* It's inline, so penalty for filesystems that don't use sticky bit is -* minimal. -*/ -static inline int btrfs_check_sticky(struct inode *dir, struct inode *inode) -{ - kuid_t fsuid = current_fsuid(); - - if (!(dir->i_mode & S_ISVTX)) - return 0; - if (uid_eq(inode->i_uid, fsuid)) - return 0; - if (uid_eq(dir->i_uid, fsuid)) - return 0; - return !capable(CAP_FOWNER); -} - /* copy of may_delete in fs/namei.c() * Check whether we can remove a link victim from directory dir, check * whether the type of victim is right. @@ -731,8 +717,7 @@ static int btrfs_may_delete(struct inode *dir, struct dentry *victim, int isdir) return error; if (IS_APPEND(dir)) return -EPERM; - if (btrfs_check_sticky(dir, victim->d_inode)|| - IS_APPEND(victim->d_inode)|| + if (check_sticky(dir, victim->d_inode) || IS_APPEND(victim->d_inode) || IS_IMMUTABLE(victim->d_inode) || IS_SWAPFILE(victim->d_inode)) return -EPERM; if (isdir) { @@ -4750,6 +4735,12 @@ long btrfs_ioctl(struct file *file, unsigned int if (ret) return ret; ret = btrfs_sync_fs(file->f_dentry->d_sb, 1); + /* + * The transaction thread may want to do more work, + * namely it pokes the cleaner ktread that will start + * processing uncleaned subvols. + */ + wake_up_process(root->fs_info->transaction_kthread); return ret; } case BTRFS_IOC_START_SYNC: diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 07b3b36f40ee..01f977e3ce09 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -736,7 +736,8 @@ again: err = ret; goto out; } - BUG_ON(!ret || !path1->slots[0]); + ASSERT(ret); + ASSERT(path1->slots[0]); path1->slots[0]--; @@ -746,10 +747,10 @@ again: * the backref was added previously when processing * backref of type BTRFS_TREE_BLOCK_REF_KEY */ - BUG_ON(!list_is_singular(&cur->upper)); + ASSERT(list_is_singular(&cur->upper)); edge = list_entry(cur->upper.next, struct backref_edge, list[LOWER]); - BUG_ON(!list_empty(&edge->list[UPPER])); + ASSERT(list_empty(&edge->list[UPPER])); exist = edge->node[UPPER]; /* * add the upper level block to pending list if we need @@ -831,7 +832,7 @@ again: cur->cowonly = 1; } #else - BUG_ON(key.type == BTRFS_EXTENT_REF_V0_KEY); + ASSERT(key.type != BTRFS_EXTENT_REF_V0_KEY); if (key.type == BTRFS_SHARED_BLOCK_REF_KEY) { #endif if (key.objectid == key.offset) { @@ -840,7 +841,7 @@ again: * backref of this type. */ root = find_reloc_root(rc, cur->bytenr); - BUG_ON(!root); + ASSERT(root); cur->root = root; break; } @@ -868,7 +869,7 @@ again: } else { upper = rb_entry(rb_node, struct backref_node, rb_node); - BUG_ON(!upper->checked); + ASSERT(upper->checked); INIT_LIST_HEAD(&edge->list[UPPER]); } list_add_tail(&edge->list[LOWER], &cur->upper); @@ -892,7 +893,7 @@ again: if (btrfs_root_level(&root->root_item) == cur->level) { /* tree root */ - BUG_ON(btrfs_root_bytenr(&root->root_item) != + ASSERT(btrfs_root_bytenr(&root->root_item) == cur->bytenr); if (should_ignore_root(root)) list_add(&cur->list, &useless); @@ -927,7 +928,7 @@ again: need_check = true; for (; level < BTRFS_MAX_LEVEL; level++) { if (!path2->nodes[level]) { - BUG_ON(btrfs_root_bytenr(&root->root_item) != + ASSERT(btrfs_root_bytenr(&root->root_item) == lower->bytenr); if (should_ignore_root(root)) list_add(&lower->list, &useless); @@ -976,12 +977,15 @@ again: need_check = false; list_add_tail(&edge->list[UPPER], &list); - } else + } else { + if (upper->checked) + need_check = true; INIT_LIST_HEAD(&edge->list[UPPER]); + } } else { upper = rb_entry(rb_node, struct backref_node, rb_node); - BUG_ON(!upper->checked); + ASSERT(upper->checked); INIT_LIST_HEAD(&edge->list[UPPER]); if (!upper->owner) upper->owner = btrfs_header_owner(eb); @@ -1025,7 +1029,7 @@ next: * everything goes well, connect backref nodes and insert backref nodes * into the cache. */ - BUG_ON(!node->checked); + ASSERT(node->checked); cowonly = node->cowonly; if (!cowonly) { rb_node = tree_insert(&cache->rb_root, node->bytenr, @@ -1061,8 +1065,21 @@ next: continue; } - BUG_ON(!upper->checked); - BUG_ON(cowonly != upper->cowonly); + if (!upper->checked) { + /* + * Still want to blow up for developers since this is a + * logic bug. + */ + ASSERT(0); + err = -EINVAL; + goto out; + } + if (cowonly != upper->cowonly) { + ASSERT(0); + err = -EINVAL; + goto out; + } + if (!cowonly) { rb_node = tree_insert(&cache->rb_root, upper->bytenr, &upper->rb_node); @@ -1085,7 +1102,7 @@ next: while (!list_empty(&useless)) { upper = list_entry(useless.next, struct backref_node, list); list_del_init(&upper->list); - BUG_ON(!list_empty(&upper->upper)); + ASSERT(list_empty(&upper->upper)); if (upper == node) node = NULL; if (upper->lowest) { @@ -1118,29 +1135,45 @@ out: if (err) { while (!list_empty(&useless)) { lower = list_entry(useless.next, - struct backref_node, upper); - list_del_init(&lower->upper); + struct backref_node, list); + list_del_init(&lower->list); } - upper = node; - INIT_LIST_HEAD(&list); - while (upper) { - if (RB_EMPTY_NODE(&upper->rb_node)) { - list_splice_tail(&upper->upper, &list); - free_backref_node(cache, upper); - } - - if (list_empty(&list)) - break; - - edge = list_entry(list.next, struct backref_edge, - list[LOWER]); + while (!list_empty(&list)) { + edge = list_first_entry(&list, struct backref_edge, + list[UPPER]); + list_del(&edge->list[UPPER]); list_del(&edge->list[LOWER]); + lower = edge->node[LOWER]; upper = edge->node[UPPER]; free_backref_edge(cache, edge); + + /* + * Lower is no longer linked to any upper backref nodes + * and isn't in the cache, we can free it ourselves. + */ + if (list_empty(&lower->upper) && + RB_EMPTY_NODE(&lower->rb_node)) + list_add(&lower->list, &useless); + + if (!RB_EMPTY_NODE(&upper->rb_node)) + continue; + + /* Add this guy's upper edges to the list to proces */ + list_for_each_entry(edge, &upper->upper, list[LOWER]) + list_add_tail(&edge->list[UPPER], &list); + if (list_empty(&upper->upper)) + list_add(&upper->list, &useless); + } + + while (!list_empty(&useless)) { + lower = list_entry(useless.next, + struct backref_node, list); + list_del_init(&lower->list); + free_backref_node(cache, lower); } return ERR_PTR(err); } - BUG_ON(node && node->detached); + ASSERT(!node || !node->detached); return node; } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index a65ed4cb436b..20d793542096 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -4728,7 +4728,9 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end) if (S_ISREG(sctx->cur_inode_mode)) { if (need_send_hole(sctx)) { - if (sctx->cur_inode_last_extent == (u64)-1) { + if (sctx->cur_inode_last_extent == (u64)-1 || + sctx->cur_inode_last_extent < + sctx->cur_inode_size) { ret = get_last_extent(sctx, (u64)-1); if (ret) goto out; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index b05bf58b9395..a0b65a01fed7 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -592,7 +592,6 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid) if (transid <= root->fs_info->last_trans_committed) goto out; - ret = -EINVAL; /* find specified transaction */ spin_lock(&root->fs_info->trans_lock); list_for_each_entry(t, &root->fs_info->trans_list, list) { @@ -608,9 +607,16 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid) } } spin_unlock(&root->fs_info->trans_lock); - /* The specified transaction doesn't exist */ - if (!cur_trans) + + /* + * The specified transaction doesn't exist, or we + * raced with btrfs_commit_transaction + */ + if (!cur_trans) { + if (transid > root->fs_info->last_trans_committed) + ret = -EINVAL; goto out; + } } else { /* find newest transaction that is committing | committed */ spin_lock(&root->fs_info->trans_lock); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 39d83da03e03..ec8b6542c8bd 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -979,7 +979,7 @@ again: base = btrfs_item_ptr_offset(leaf, path->slots[0]); while (cur_offset < item_size) { - extref = (struct btrfs_inode_extref *)base + cur_offset; + extref = (struct btrfs_inode_extref *)(base + cur_offset); victim_name_len = btrfs_inode_extref_name_len(leaf, extref); @@ -1235,13 +1235,14 @@ out: } static int insert_orphan_item(struct btrfs_trans_handle *trans, - struct btrfs_root *root, u64 offset) + struct btrfs_root *root, u64 ino) { int ret; - ret = btrfs_find_item(root, NULL, BTRFS_ORPHAN_OBJECTID, - offset, BTRFS_ORPHAN_ITEM_KEY, NULL); - if (ret > 0) - ret = btrfs_insert_orphan_item(trans, root, offset); + + ret = btrfs_insert_orphan_item(trans, root, ino); + if (ret == -EEXIST) + ret = 0; + return ret; } diff --git a/fs/buffer.c b/fs/buffer.c index 27265a8b43c1..eef21c69f2d7 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -227,7 +227,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) int all_mapped = 1; index = block >> (PAGE_CACHE_SHIFT - bd_inode->i_blkbits); - page = find_get_page(bd_mapping, index); + page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED); if (!page) goto out; @@ -1029,7 +1029,8 @@ grow_dev_page(struct block_device *bdev, sector_t block, bh = page_buffers(page); if (bh->b_size == size) { end_block = init_page_buffers(page, bdev, - index << sizebits, size); + (sector_t)index << sizebits, + size); goto done; } if (!try_to_free_buffers(page)) @@ -1050,7 +1051,8 @@ grow_dev_page(struct block_device *bdev, sector_t block, */ spin_lock(&inode->i_mapping->private_lock); link_dev_buffers(page, bh); - end_block = init_page_buffers(page, bdev, index << sizebits, size); + end_block = init_page_buffers(page, bdev, (sector_t)index << sizebits, + size); spin_unlock(&inode->i_mapping->private_lock); done: ret = (block < end_block) ? 1 : -ENXIO; @@ -1366,12 +1368,13 @@ __find_get_block(struct block_device *bdev, sector_t block, unsigned size) struct buffer_head *bh = lookup_bh_lru(bdev, block, size); if (bh == NULL) { + /* __find_get_block_slow will mark the page accessed */ bh = __find_get_block_slow(bdev, block); if (bh) bh_lru_install(bh); - } - if (bh) + } else touch_buffer(bh); + return bh; } EXPORT_SYMBOL(__find_get_block); @@ -1483,16 +1486,27 @@ EXPORT_SYMBOL(set_bh_page); /* * Called when truncating a buffer on a page completely. */ + +/* Bits that are cleared during an invalidate */ +#define BUFFER_FLAGS_DISCARD \ + (1 << BH_Mapped | 1 << BH_New | 1 << BH_Req | \ + 1 << BH_Delay | 1 << BH_Unwritten) + static void discard_buffer(struct buffer_head * bh) { + unsigned long b_state, b_state_old; + lock_buffer(bh); clear_buffer_dirty(bh); bh->b_bdev = NULL; - clear_buffer_mapped(bh); - clear_buffer_req(bh); - clear_buffer_new(bh); - clear_buffer_delay(bh); - clear_buffer_unwritten(bh); + b_state = bh->b_state; + for (;;) { + b_state_old = cmpxchg(&bh->b_state, b_state, + (b_state & ~BUFFER_FLAGS_DISCARD)); + if (b_state_old == b_state) + break; + b_state = b_state_old; + } unlock_buffer(bh); } @@ -2075,6 +2089,7 @@ int generic_write_end(struct file *file, struct address_space *mapping, struct page *page, void *fsdata) { struct inode *inode = mapping->host; + loff_t old_size = inode->i_size; int i_size_changed = 0; copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); @@ -2094,6 +2109,8 @@ int generic_write_end(struct file *file, struct address_space *mapping, unlock_page(page); page_cache_release(page); + if (old_size < pos) + pagecache_isize_extended(inode, old_size, pos); /* * Don't mark the inode dirty under page lock. First, it unnecessarily * makes the holding time of page lock longer. Second, it forces lock @@ -2311,6 +2328,11 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, err = 0; balance_dirty_pages_ratelimited(mapping); + + if (unlikely(fatal_signal_pending(current))) { + err = -EINTR; + goto out; + } } /* page covers the boundary, find the boundary offset */ diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c index 622f4696e484..5b99bafc31d1 100644 --- a/fs/cachefiles/bind.c +++ b/fs/cachefiles/bind.c @@ -124,7 +124,6 @@ static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache) /* check parameters */ ret = -EOPNOTSUPP; if (!root->d_inode || - !root->d_inode->i_op || !root->d_inode->i_op->lookup || !root->d_inode->i_op->mkdir || !root->d_inode->i_op->setxattr || diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index ca65f39dc8dc..c0a681705104 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -391,12 +391,12 @@ try_again: path.dentry = dir; path_to_graveyard.mnt = cache->mnt; path_to_graveyard.dentry = cache->graveyard; - ret = security_path_rename(&path, rep, &path_to_graveyard, grave); + ret = security_path_rename(&path, rep, &path_to_graveyard, grave, 0); if (ret < 0) { cachefiles_io_error(cache, "Rename security error %d", ret); } else { ret = vfs_rename(dir->d_inode, rep, - cache->graveyard->d_inode, grave, NULL); + cache->graveyard->d_inode, grave, NULL, 0); if (ret != 0 && ret != -ENOMEM) cachefiles_io_error(cache, "Rename failed with error %d", ret); @@ -779,8 +779,7 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache, } ret = -EPERM; - if (!subdir->d_inode->i_op || - !subdir->d_inode->i_op->setxattr || + if (!subdir->d_inode->i_op->setxattr || !subdir->d_inode->i_op->getxattr || !subdir->d_inode->i_op->lookup || !subdir->d_inode->i_op->mkdir || diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index b53278c9fd97..94a85ee5b990 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -676,7 +676,7 @@ static int ceph_writepages_start(struct address_space *mapping, int rc = 0; unsigned wsize = 1 << inode->i_blkbits; struct ceph_osd_request *req = NULL; - int do_sync; + int do_sync = 0; u64 truncate_size, snap_size; u32 truncate_seq; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index f4f050a69a48..339c41216d14 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1461,15 +1461,18 @@ static void discard_cap_releases(struct ceph_mds_client *mdsc, dout("discard_cap_releases mds%d\n", session->s_mds); - /* zero out the in-progress message */ - msg = list_first_entry(&session->s_cap_releases, - struct ceph_msg, list_head); - head = msg->front.iov_base; - num = le32_to_cpu(head->num); - dout("discard_cap_releases mds%d %p %u\n", session->s_mds, msg, num); - head->num = cpu_to_le32(0); - msg->front.iov_len = sizeof(*head); - session->s_num_cap_releases += num; + if (!list_empty(&session->s_cap_releases)) { + /* zero out the in-progress message */ + msg = list_first_entry(&session->s_cap_releases, + struct ceph_msg, list_head); + head = msg->front.iov_base; + num = le32_to_cpu(head->num); + dout("discard_cap_releases mds%d %p %u\n", + session->s_mds, msg, num); + head->num = cpu_to_le32(0); + msg->front.iov_len = sizeof(*head); + session->s_num_cap_releases += num; + } /* requeue completed messages */ while (!list_empty(&session->s_cap_releases_done)) { diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index f15d4353f30f..5d12d69e2045 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -399,6 +399,8 @@ struct smb_version_operations { const struct cifs_fid *, u32 *); int (*set_acl)(struct cifs_ntsd *, __u32, struct inode *, const char *, int); + /* check if we need to issue closedir */ + bool (*dir_needs_close)(struct cifsFileInfo *); }; struct smb_version_values { diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 8175b18df819..40ddb6e93912 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -366,6 +366,7 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) struct cifsLockInfo *li, *tmp; struct cifs_fid fid; struct cifs_pending_open open; + bool oplock_break_cancelled; spin_lock(&cifs_file_list_lock); if (--cifs_file->count > 0) { @@ -397,7 +398,7 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) } spin_unlock(&cifs_file_list_lock); - cancel_work_sync(&cifs_file->oplock_break); + oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break); if (!tcon->need_reconnect && !cifs_file->invalidHandle) { struct TCP_Server_Info *server = tcon->ses->server; @@ -409,6 +410,9 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) _free_xid(xid); } + if (oplock_break_cancelled) + cifs_done_oplock_break(cifsi); + cifs_del_pending_open(&open); /* @@ -762,7 +766,7 @@ int cifs_closedir(struct inode *inode, struct file *file) cifs_dbg(FYI, "Freeing private data in close dir\n"); spin_lock(&cifs_file_list_lock); - if (!cfile->srch_inf.endOfSearch && !cfile->invalidHandle) { + if (server->ops->dir_needs_close(cfile)) { cfile->invalidHandle = true; spin_unlock(&cifs_file_list_lock); if (server->ops->close_dir) @@ -1817,6 +1821,7 @@ refind_writable: cifsFileInfo_put(inv_file); spin_lock(&cifs_file_list_lock); ++refind; + inv_file = NULL; goto refind_writable; } } diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 77492301cc2b..dfc95646b88c 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -86,21 +86,16 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, } src_inode = src_file.file->f_dentry->d_inode; + rc = -EINVAL; + if (S_ISDIR(src_inode->i_mode)) + goto out_fput; /* * Note: cifs case is easier than btrfs since server responsible for * checks for proper open modes and file type and if it wants * server could even support copy of range where source = target */ - - /* so we do not deadlock racing two ioctls on same files */ - if (target_inode < src_inode) { - mutex_lock_nested(&target_inode->i_mutex, I_MUTEX_PARENT); - mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_CHILD); - } else { - mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_PARENT); - mutex_lock_nested(&target_inode->i_mutex, I_MUTEX_CHILD); - } + lock_two_nondirectories(target_inode, src_inode); /* determine range to clone */ rc = -EINVAL; @@ -124,13 +119,7 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, out_unlock: /* although unlocking in the reverse order from locking is not strictly necessary here it is a little cleaner to be consistent */ - if (target_inode < src_inode) { - mutex_unlock(&src_inode->i_mutex); - mutex_unlock(&target_inode->i_mutex); - } else { - mutex_unlock(&target_inode->i_mutex); - mutex_unlock(&src_inode->i_mutex); - } + unlock_two_nondirectories(src_inode, target_inode); out_fput: fdput(src_file); out_drop_write: diff --git a/fs/cifs/link.c b/fs/cifs/link.c index 68559fd557fb..a5c2812ead68 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -213,8 +213,12 @@ create_mf_symlink(const unsigned int xid, struct cifs_tcon *tcon, if (rc) goto out; - rc = tcon->ses->server->ops->create_mf_symlink(xid, tcon, cifs_sb, - fromName, buf, &bytes_written); + if (tcon->ses->server->ops->create_mf_symlink) + rc = tcon->ses->server->ops->create_mf_symlink(xid, tcon, + cifs_sb, fromName, buf, &bytes_written); + else + rc = -EOPNOTSUPP; + if (rc) goto out; diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 2bbf11b09214..b334a89d6a66 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -593,7 +593,7 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos, /* close and restart search */ cifs_dbg(FYI, "search backing up - close and restart search\n"); spin_lock(&cifs_file_list_lock); - if (!cfile->srch_inf.endOfSearch && !cfile->invalidHandle) { + if (server->ops->dir_needs_close(cfile)) { cfile->invalidHandle = true; spin_unlock(&cifs_file_list_lock); if (server->ops->close_dir) diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index d1fdfa848703..e9ad8d37bb00 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -586,7 +586,7 @@ cifs_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, tmprc = CIFS_open(xid, &oparms, &oplock, NULL); if (tmprc == -EOPNOTSUPP) *symlink = true; - else + else if (tmprc == 0) CIFSSMBClose(xid, tcon, fid.netfid); } @@ -1009,6 +1009,12 @@ cifs_is_read_op(__u32 oplock) return oplock == OPLOCK_READ; } +static bool +cifs_dir_needs_close(struct cifsFileInfo *cfile) +{ + return !cfile->srch_inf.endOfSearch && !cfile->invalidHandle; +} + struct smb_version_operations smb1_operations = { .send_cancel = send_nt_cancel, .compare_fids = cifs_compare_fids, @@ -1078,6 +1084,7 @@ struct smb_version_operations smb1_operations = { .query_mf_symlink = cifs_query_mf_symlink, .create_mf_symlink = cifs_create_mf_symlink, .is_read_op = cifs_is_read_op, + .dir_needs_close = cifs_dir_needs_close, #ifdef CONFIG_CIFS_XATTR .query_all_EAs = CIFSSMBQAllEAs, .set_EA = CIFSSMBSetEA, diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c index e31a9dfdcd39..a491814cb2c0 100644 --- a/fs/cifs/smb2maperror.c +++ b/fs/cifs/smb2maperror.c @@ -214,7 +214,7 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_BREAKPOINT, -EIO, "STATUS_BREAKPOINT"}, {STATUS_SINGLE_STEP, -EIO, "STATUS_SINGLE_STEP"}, {STATUS_BUFFER_OVERFLOW, -EIO, "STATUS_BUFFER_OVERFLOW"}, - {STATUS_NO_MORE_FILES, -EIO, "STATUS_NO_MORE_FILES"}, + {STATUS_NO_MORE_FILES, -ENODATA, "STATUS_NO_MORE_FILES"}, {STATUS_WAKE_SYSTEM_DEBUGGER, -EIO, "STATUS_WAKE_SYSTEM_DEBUGGER"}, {STATUS_HANDLES_CLOSED, -EIO, "STATUS_HANDLES_CLOSED"}, {STATUS_NO_INHERITANCE, -EIO, "STATUS_NO_INHERITANCE"}, @@ -256,6 +256,8 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_DLL_MIGHT_BE_INCOMPATIBLE, -EIO, "STATUS_DLL_MIGHT_BE_INCOMPATIBLE"}, {STATUS_STOPPED_ON_SYMLINK, -EOPNOTSUPP, "STATUS_STOPPED_ON_SYMLINK"}, + {STATUS_IO_REPARSE_TAG_NOT_HANDLED, -EOPNOTSUPP, + "STATUS_REPARSE_NOT_HANDLED"}, {STATUS_DEVICE_REQUIRES_CLEANING, -EIO, "STATUS_DEVICE_REQUIRES_CLEANING"}, {STATUS_DEVICE_DOOR_OPEN, -EIO, "STATUS_DEVICE_DOOR_OPEN"}, diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index f8977b2d9187..30f3eb5bc022 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -630,7 +630,8 @@ smb2_clone_range(const unsigned int xid, /* No need to change MaxChunks since already set to 1 */ chunk_sizes_updated = true; - } + } else + goto cchunk_out; } cchunk_out: @@ -1102,6 +1103,12 @@ smb3_parse_lease_buf(void *buf, unsigned int *epoch) return le32_to_cpu(lc->lcontext.LeaseState); } +static bool +smb2_dir_needs_close(struct cifsFileInfo *cfile) +{ + return !cfile->invalidHandle; +} + struct smb_version_operations smb20_operations = { .compare_fids = smb2_compare_fids, .setup_request = smb2_setup_request, @@ -1175,6 +1182,7 @@ struct smb_version_operations smb20_operations = { .create_lease_buf = smb2_create_lease_buf, .parse_lease_buf = smb2_parse_lease_buf, .clone_range = smb2_clone_range, + .dir_needs_close = smb2_dir_needs_close, }; struct smb_version_operations smb21_operations = { @@ -1250,6 +1258,7 @@ struct smb_version_operations smb21_operations = { .create_lease_buf = smb2_create_lease_buf, .parse_lease_buf = smb2_parse_lease_buf, .clone_range = smb2_clone_range, + .dir_needs_close = smb2_dir_needs_close, }; struct smb_version_operations smb30_operations = { @@ -1328,6 +1337,7 @@ struct smb_version_operations smb30_operations = { .parse_lease_buf = smb3_parse_lease_buf, .clone_range = smb2_clone_range, .validate_negotiate = smb3_validate_negotiate, + .dir_needs_close = smb2_dir_needs_close, }; struct smb_version_values smb20_values = { diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 9aab8fe0e508..348792911e1f 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2136,6 +2136,10 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon, rsp = (struct smb2_query_directory_rsp *)iov[0].iov_base; if (rc) { + if (rc == -ENODATA && rsp->hdr.Status == STATUS_NO_MORE_FILES) { + srch_inf->endOfSearch = true; + rc = 0; + } cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE); goto qdir_exit; } @@ -2173,11 +2177,6 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon, else cifs_dbg(VFS, "illegal search buffer type\n"); - if (rsp->hdr.Status == STATUS_NO_MORE_FILES) - srch_inf->endOfSearch = 1; - else - srch_inf->endOfSearch = 0; - return rc; qdir_exit: diff --git a/fs/compat.c b/fs/compat.c index 6af20de2c1a3..14da9b327ffa 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -837,10 +837,12 @@ struct compat_readdir_callback { int result; }; -static int compat_fillonedir(void *__buf, const char *name, int namlen, - loff_t offset, u64 ino, unsigned int d_type) +static int compat_fillonedir(struct dir_context *ctx, const char *name, + int namlen, loff_t offset, u64 ino, + unsigned int d_type) { - struct compat_readdir_callback *buf = __buf; + struct compat_readdir_callback *buf = + container_of(ctx, struct compat_readdir_callback, ctx); struct compat_old_linux_dirent __user *dirent; compat_ulong_t d_ino; @@ -905,11 +907,12 @@ struct compat_getdents_callback { int error; }; -static int compat_filldir(void *__buf, const char *name, int namlen, +static int compat_filldir(struct dir_context *ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { struct compat_linux_dirent __user * dirent; - struct compat_getdents_callback *buf = __buf; + struct compat_getdents_callback *buf = + container_of(ctx, struct compat_getdents_callback, ctx); compat_ulong_t d_ino; int reclen = ALIGN(offsetof(struct compat_linux_dirent, d_name) + namlen + 2, sizeof(compat_long_t)); @@ -991,11 +994,13 @@ struct compat_getdents_callback64 { int error; }; -static int compat_filldir64(void * __buf, const char * name, int namlen, loff_t offset, - u64 ino, unsigned int d_type) +static int compat_filldir64(struct dir_context *ctx, const char *name, + int namlen, loff_t offset, u64 ino, + unsigned int d_type) { struct linux_dirent64 __user *dirent; - struct compat_getdents_callback64 *buf = __buf; + struct compat_getdents_callback64 *buf = + container_of(ctx, struct compat_getdents_callback64, ctx); int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1, sizeof(u64)); u64 off; diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 06610cf94d57..a1f801c14fbc 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -195,8 +195,7 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i struct page *page = NULL; if (blocknr + i < devsize) { - page = read_mapping_page_async(mapping, blocknr + i, - NULL); + page = read_mapping_page(mapping, blocknr + i, NULL); /* synchronous error? */ if (IS_ERR(page)) page = NULL; diff --git a/fs/dcache.c b/fs/dcache.c index 58d57da91d2a..e3c556351810 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2481,12 +2481,14 @@ static void switch_names(struct dentry *dentry, struct dentry *target) dentry->d_name.name = dentry->d_iname; } else { /* - * Both are internal. Just copy target to dentry + * Both are internal. */ - memcpy(dentry->d_iname, target->d_name.name, - target->d_name.len + 1); - dentry->d_name.len = target->d_name.len; - return; + unsigned int i; + BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long))); + for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) { + swap(((long *) &dentry->d_iname)[i], + ((long *) &target->d_iname)[i]); + } } } swap(dentry->d_name.len, target->d_name.len); @@ -2543,13 +2545,15 @@ static void dentry_unlock_parents_for_move(struct dentry *dentry, * __d_move - move a dentry * @dentry: entry to move * @target: new dentry + * @exchange: exchange the two dentries * * Update the dcache to reflect the move of a file name. Negative * dcache entries should not be moved in this way. Caller must hold * rename_lock, the i_mutex of the source and target directories, * and the sb->s_vfs_rename_mutex if they differ. See lock_rename(). */ -static void __d_move(struct dentry * dentry, struct dentry * target) +static void __d_move(struct dentry *dentry, struct dentry *target, + bool exchange) { if (!dentry->d_inode) printk(KERN_WARNING "VFS: moving negative dcache entry\n"); @@ -2571,8 +2575,15 @@ static void __d_move(struct dentry * dentry, struct dentry * target) __d_drop(dentry); __d_rehash(dentry, d_hash(target->d_parent, target->d_name.hash)); - /* Unhash the target: dput() will then get rid of it */ + /* + * Unhash the target (d_delete() is not usable here). If exchanging + * the two dentries, then rehash onto the other's hash queue. + */ __d_drop(target); + if (exchange) { + __d_rehash(target, + d_hash(dentry->d_parent, dentry->d_name.hash)); + } list_del(&dentry->d_u.d_child); list_del(&target->d_u.d_child); @@ -2599,6 +2610,8 @@ static void __d_move(struct dentry * dentry, struct dentry * target) write_seqcount_end(&dentry->d_seq); dentry_unlock_parents_for_move(dentry, target); + if (exchange) + fsnotify_d_move(target); spin_unlock(&target->d_lock); fsnotify_d_move(dentry); spin_unlock(&dentry->d_lock); @@ -2616,11 +2629,30 @@ static void __d_move(struct dentry * dentry, struct dentry * target) void d_move(struct dentry *dentry, struct dentry *target) { write_seqlock(&rename_lock); - __d_move(dentry, target); + __d_move(dentry, target, false); write_sequnlock(&rename_lock); } EXPORT_SYMBOL(d_move); +/* + * d_exchange - exchange two dentries + * @dentry1: first dentry + * @dentry2: second dentry + */ +void d_exchange(struct dentry *dentry1, struct dentry *dentry2) +{ + write_seqlock(&rename_lock); + + WARN_ON(!dentry1->d_inode); + WARN_ON(!dentry2->d_inode); + WARN_ON(IS_ROOT(dentry1)); + WARN_ON(IS_ROOT(dentry2)); + + __d_move(dentry1, dentry2, true); + + write_sequnlock(&rename_lock); +} + /** * d_ancestor - search for an ancestor * @p1: ancestor dentry @@ -2668,7 +2700,7 @@ static struct dentry *__d_unalias(struct inode *inode, m2 = &alias->d_parent->d_inode->i_mutex; out_unalias: if (likely(!d_mountpoint(alias))) { - __d_move(alias, dentry); + __d_move(alias, dentry, false); ret = alias; } out_err: @@ -2824,6 +2856,9 @@ static int prepend(char **buffer, int *buflen, const char *str, int namelen) * the beginning of the name. The sequence number check at the caller will * retry it again when a d_move() does happen. So any garbage in the buffer * due to mismatched pointer and length will be discarded. + * + * Data dependency barrier is needed to make sure that we see that terminating + * NUL. Alpha strikes again, film at 11... */ static int prepend_name(char **buffer, int *buflen, struct qstr *name) { @@ -2831,6 +2866,8 @@ static int prepend_name(char **buffer, int *buflen, struct qstr *name) u32 dlen = ACCESS_ONCE(name->len); char *p; + smp_read_barrier_depends(); + *buflen -= dlen + 1; if (*buflen < 0) return -ENAMETOOLONG; diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 15761957cc3f..1ff8fe5dab0d 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -245,10 +245,19 @@ static int debugfs_show_options(struct seq_file *m, struct dentry *root) return 0; } +static void debugfs_evict_inode(struct inode *inode) +{ + truncate_inode_pages(&inode->i_data, 0); + clear_inode(inode); + if (S_ISLNK(inode->i_mode)) + kfree(inode->i_private); +} + static const struct super_operations debugfs_super_operations = { .statfs = simple_statfs, .remount_fs = debugfs_remount, .show_options = debugfs_show_options, + .evict_inode = debugfs_evict_inode, }; static int debug_fill_super(struct super_block *sb, void *data, int silent) @@ -465,23 +474,14 @@ static int __debugfs_remove(struct dentry *dentry, struct dentry *parent) int ret = 0; if (debugfs_positive(dentry)) { - if (dentry->d_inode) { - dget(dentry); - switch (dentry->d_inode->i_mode & S_IFMT) { - case S_IFDIR: - ret = simple_rmdir(parent->d_inode, dentry); - break; - case S_IFLNK: - kfree(dentry->d_inode->i_private); - /* fall through */ - default: - simple_unlink(parent->d_inode, dentry); - break; - } - if (!ret) - d_delete(dentry); - dput(dentry); - } + dget(dentry); + if (S_ISDIR(dentry->d_inode->i_mode)) + ret = simple_rmdir(parent->d_inode, dentry); + else + simple_unlink(parent->d_inode, dentry); + if (!ret) + d_delete(dentry); + dput(dentry); } return ret; } diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index 2f6735dbf1a9..31b148f3e772 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -1917,7 +1917,6 @@ ecryptfs_decode_from_filename(unsigned char *dst, size_t *dst_size, break; case 2: dst[dst_byte_offset++] |= (src_byte); - dst[dst_byte_offset] = 0; current_bit_offset = 0; break; } diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index b1eaa7a1f82c..121a94876d40 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -76,11 +76,11 @@ struct ecryptfs_getdents_callback { /* Inspired by generic filldir in fs/readdir.c */ static int -ecryptfs_filldir(void *dirent, const char *lower_name, int lower_namelen, - loff_t offset, u64 ino, unsigned int d_type) +ecryptfs_filldir(struct dir_context *ctx, const char *lower_name, + int lower_namelen, loff_t offset, u64 ino, unsigned int d_type) { struct ecryptfs_getdents_callback *buf = - (struct ecryptfs_getdents_callback *)dirent; + container_of(ctx, struct ecryptfs_getdents_callback, ctx); size_t name_size; char *name; int rc; @@ -191,23 +191,11 @@ static int ecryptfs_open(struct inode *inode, struct file *file) { int rc = 0; struct ecryptfs_crypt_stat *crypt_stat = NULL; - struct ecryptfs_mount_crypt_stat *mount_crypt_stat; struct dentry *ecryptfs_dentry = file->f_path.dentry; /* Private value of ecryptfs_dentry allocated in * ecryptfs_lookup() */ struct ecryptfs_file_info *file_info; - mount_crypt_stat = &ecryptfs_superblock_to_private( - ecryptfs_dentry->d_sb)->mount_crypt_stat; - if ((mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED) - && ((file->f_flags & O_WRONLY) || (file->f_flags & O_RDWR) - || (file->f_flags & O_CREAT) || (file->f_flags & O_TRUNC) - || (file->f_flags & O_APPEND))) { - printk(KERN_WARNING "Mount has encrypted view enabled; " - "files may only be read\n"); - rc = -EPERM; - goto out; - } /* Released in ecryptfs_release or end of function if failure */ file_info = kmem_cache_zalloc(ecryptfs_file_info_cache, GFP_KERNEL); ecryptfs_set_file_private(file, file_info); diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index b167ca48b8ee..57ee4c53b4f8 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -641,7 +641,7 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry, } rc = vfs_rename(lower_old_dir_dentry->d_inode, lower_old_dentry, lower_new_dir_dentry->d_inode, lower_new_dentry, - NULL); + NULL, 0); if (rc) goto out_lock; if (target_inode) @@ -1039,7 +1039,7 @@ ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value, } rc = vfs_setxattr(lower_dentry, name, value, size, flags); - if (!rc) + if (!rc && dentry->d_inode) fsstack_copy_attr_all(dentry->d_inode, lower_dentry->d_inode); out: return rc; diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 1b119d3bf924..d9eb84bda559 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -493,6 +493,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags { struct super_block *s; struct ecryptfs_sb_info *sbi; + struct ecryptfs_mount_crypt_stat *mount_crypt_stat; struct ecryptfs_dentry_info *root_info; const char *err = "Getting sb failed"; struct inode *inode; @@ -511,6 +512,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags err = "Error parsing options"; goto out; } + mount_crypt_stat = &sbi->mount_crypt_stat; s = sget(fs_type, NULL, set_anon_super, flags, NULL); if (IS_ERR(s)) { @@ -557,15 +559,30 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags /** * Set the POSIX ACL flag based on whether they're enabled in the lower - * mount. Force a read-only eCryptfs mount if the lower mount is ro. - * Allow a ro eCryptfs mount even when the lower mount is rw. + * mount. */ s->s_flags = flags & ~MS_POSIXACL; - s->s_flags |= path.dentry->d_sb->s_flags & (MS_RDONLY | MS_POSIXACL); + s->s_flags |= path.dentry->d_sb->s_flags & MS_POSIXACL; + + /** + * Force a read-only eCryptfs mount when: + * 1) The lower mount is ro + * 2) The ecryptfs_encrypted_view mount option is specified + */ + if (path.dentry->d_sb->s_flags & MS_RDONLY || + mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED) + s->s_flags |= MS_RDONLY; s->s_maxbytes = path.dentry->d_sb->s_maxbytes; s->s_blocksize = path.dentry->d_sb->s_blocksize; s->s_magic = ECRYPTFS_SUPER_MAGIC; + s->s_stack_depth = path.dentry->d_sb->s_stack_depth + 1; + + rc = -EINVAL; + if (s->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) { + pr_err("eCryptfs: maximum fs stacking depth exceeded\n"); + goto out_free; + } inode = ecryptfs_get_inode(path.dentry->d_inode, s); rc = PTR_ERR(inode); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index ead00467282d..f50d79eb52db 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1852,7 +1852,8 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, goto error_tgt_fput; /* Check if EPOLLWAKEUP is allowed */ - ep_take_care_of_epollwakeup(&epds); + if (ep_op_has_event(op)) + ep_take_care_of_epollwakeup(&epds); /* * We have to check that the file structure underneath the file descriptor diff --git a/fs/exec.c b/fs/exec.c index 31e46b1b358b..ea4449d0536a 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -26,6 +26,7 @@ #include <linux/file.h> #include <linux/fdtable.h> #include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/stat.h> #include <linux/fcntl.h> #include <linux/swap.h> @@ -820,7 +821,7 @@ EXPORT_SYMBOL(read_code); static int exec_mmap(struct mm_struct *mm) { struct task_struct *tsk; - struct mm_struct * old_mm, *active_mm; + struct mm_struct *old_mm, *active_mm; /* Notify parent that we're no longer interested in the old VM */ tsk = current; @@ -846,6 +847,8 @@ static int exec_mmap(struct mm_struct *mm) tsk->mm = mm; tsk->active_mm = mm; activate_mm(active_mm, mm); + tsk->mm->vmacache_seqnum = 0; + vmacache_flush(tsk); task_unlock(tsk); if (old_mm) { up_read(&old_mm->mmap_sem); diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 48a359dd286e..59d339c417c9 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -241,10 +241,11 @@ struct getdents_callback { * A rather strange filldir function to capture * the name matching the specified inode number. */ -static int filldir_one(void * __buf, const char * name, int len, +static int filldir_one(struct dir_context *ctx, const char *name, int len, loff_t pos, u64 ino, unsigned int d_type) { - struct getdents_callback *buf = __buf; + struct getdents_callback *buf = + container_of(ctx, struct getdents_callback, ctx); int result = 0; buf->sequence++; diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 37fd31ed16e7..0498390f309e 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -1354,13 +1354,6 @@ set_qf_format: "not specified."); return 0; } - } else { - if (sbi->s_jquota_fmt) { - ext3_msg(sb, KERN_ERR, "error: journaled quota format " - "specified with no journaling " - "enabled."); - return 0; - } } #endif return 1; diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c index 3285aa5a706a..b610779a958c 100644 --- a/fs/ext4/bitmap.c +++ b/fs/ext4/bitmap.c @@ -24,8 +24,7 @@ int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, __u32 provided, calculated; struct ext4_sb_info *sbi = EXT4_SB(sb); - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return 1; provided = le16_to_cpu(gdp->bg_inode_bitmap_csum_lo); @@ -46,8 +45,7 @@ void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group, __u32 csum; struct ext4_sb_info *sbi = EXT4_SB(sb); - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return; csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); @@ -65,8 +63,7 @@ int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, struct ext4_sb_info *sbi = EXT4_SB(sb); int sz = EXT4_CLUSTERS_PER_GROUP(sb) / 8; - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return 1; provided = le16_to_cpu(gdp->bg_block_bitmap_csum_lo); @@ -91,8 +88,7 @@ void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group, __u32 csum; struct ext4_sb_info *sbi = EXT4_SB(sb); - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return; csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 62f024c051ce..2a6830a7af33 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2110,6 +2110,7 @@ int do_journal_get_write_access(handle_t *handle, #define CONVERT_INLINE_DATA 2 extern struct inode *ext4_iget(struct super_block *, unsigned long); +extern struct inode *ext4_iget_normal(struct super_block *, unsigned long); extern int ext4_write_inode(struct inode *, struct writeback_control *); extern int ext4_setattr(struct dentry *, struct iattr *); extern int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry, @@ -2340,10 +2341,18 @@ extern int ext4_register_li_request(struct super_block *sb, static inline int ext4_has_group_desc_csum(struct super_block *sb) { return EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_GDT_CSUM | - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM); + EXT4_FEATURE_RO_COMPAT_GDT_CSUM) || + (EXT4_SB(sb)->s_chksum_driver != NULL); } +static inline int ext4_has_metadata_csum(struct super_block *sb) +{ + WARN_ON_ONCE(EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) && + !EXT4_SB(sb)->s_chksum_driver); + + return (EXT4_SB(sb)->s_chksum_driver != NULL); +} static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es) { return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) | diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 47188916dd8d..96a1ce159f51 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -74,8 +74,7 @@ static int ext4_extent_block_csum_verify(struct inode *inode, { struct ext4_extent_tail *et; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return 1; et = find_ext4_extent_tail(eh); @@ -89,8 +88,7 @@ static void ext4_extent_block_csum_set(struct inode *inode, { struct ext4_extent_tail *et; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return; et = find_ext4_extent_tail(eh); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 2a8b2e15dcc4..589117e9e9be 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -100,7 +100,7 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov, struct blk_plug plug; int unaligned_aio = 0; ssize_t ret; - int overwrite = 0; + int *overwrite = iocb->private; size_t length = iov_length(iov, nr_segs); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) && @@ -118,8 +118,6 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov, mutex_lock(&inode->i_mutex); blk_start_plug(&plug); - iocb->private = &overwrite; - /* check whether we do a DIO overwrite or not */ if (ext4_should_dioread_nolock(inode) && !unaligned_aio && !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) { @@ -143,7 +141,7 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov, * So we should check these two conditions. */ if (err == len && (map.m_flags & EXT4_MAP_MAPPED)) - overwrite = 1; + *overwrite = 1; } ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); @@ -170,6 +168,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, { struct inode *inode = file_inode(iocb->ki_filp); ssize_t ret; + int overwrite = 0; /* * If we have encountered a bitmap-format file, the size limit @@ -190,6 +189,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, } } + iocb->private = &overwrite; if (unlikely(iocb->ki_filp->f_flags & O_DIRECT)) ret = ext4_file_dio_write(iocb, iov, nr_segs, pos); else diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 64bb32f17903..a8d1a64d8cb0 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -864,6 +864,10 @@ got: struct buffer_head *block_bitmap_bh; block_bitmap_bh = ext4_read_block_bitmap(sb, group); + if (!block_bitmap_bh) { + err = -EIO; + goto out; + } BUFFER_TRACE(block_bitmap_bh, "get block bitmap access"); err = ext4_journal_get_write_access(handle, block_bitmap_bh); if (err) { @@ -988,8 +992,7 @@ got: spin_unlock(&sbi->s_next_gen_lock); /* Precompute checksum seed for inode metadata */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { + if (ext4_has_metadata_csum(sb)) { __u32 csum; __le32 inum = cpu_to_le32(inode->i_ino); __le32 gen = cpu_to_le32(inode->i_generation); diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 82edf5b93352..8c03b747021b 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1128,8 +1128,7 @@ static int ext4_finish_convert_inline_dir(handle_t *handle, memcpy((void *)de, buf + EXT4_INLINE_DOTDOT_SIZE, inline_size - EXT4_INLINE_DOTDOT_SIZE); - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); inode->i_size = inode->i_sb->s_blocksize; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index b56062dc8b62..3a7e0341447f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -83,8 +83,7 @@ static int ext4_inode_csum_verify(struct inode *inode, struct ext4_inode *raw, if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != cpu_to_le32(EXT4_OS_LINUX) || - !EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + !ext4_has_metadata_csum(inode->i_sb)) return 1; provided = le16_to_cpu(raw->i_checksum_lo); @@ -105,8 +104,7 @@ static void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw, if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != cpu_to_le32(EXT4_OS_LINUX) || - !EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + !ext4_has_metadata_csum(inode->i_sb)) return; csum = ext4_inode_csum(inode, raw, ei); @@ -2633,6 +2631,20 @@ static int ext4_nonda_switch(struct super_block *sb) return 0; } +/* We always reserve for an inode update; the superblock could be there too */ +static int ext4_da_write_credits(struct inode *inode, loff_t pos, unsigned len) +{ + if (likely(EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_LARGE_FILE))) + return 1; + + if (pos + len <= 0x7fffffffULL) + return 1; + + /* We might need to update the superblock to set LARGE_FILE */ + return 2; +} + static int ext4_da_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) @@ -2683,7 +2695,8 @@ retry_grab: * of file which has an already mapped buffer. */ retry_journal: - handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, 1); + handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, + ext4_da_write_credits(inode, pos, len)); if (IS_ERR(handle)) { page_cache_release(page); return PTR_ERR(handle); @@ -4061,8 +4074,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) ei->i_extra_isize = 0; /* Precompute checksum seed for inode metadata */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { + if (ext4_has_metadata_csum(sb)) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); __u32 csum; __le32 inum = cpu_to_le32(inode->i_ino); @@ -4250,6 +4262,13 @@ bad_inode: return ERR_PTR(ret); } +struct inode *ext4_iget_normal(struct super_block *sb, unsigned long ino) +{ + if (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO) + return ERR_PTR(-EIO); + return ext4_iget(sb, ino); +} + static int ext4_inode_blocks_set(handle_t *handle, struct ext4_inode *raw_inode, struct ext4_inode_info *ei) @@ -4645,8 +4664,12 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) ext4_orphan_del(NULL, inode); goto err_out; } - } else + } else { + loff_t oldsize = inode->i_size; + i_size_write(inode, attr->ia_size); + pagecache_isize_extended(inode, oldsize, inode->i_size); + } /* * Blocks are going to be removed from the inode. Wait diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index a2a837f00407..dfe982dee0b3 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -343,8 +343,7 @@ flags_out: if (!inode_owner_or_capable(inode)) return -EPERM; - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { + if (ext4_has_metadata_csum(inode->i_sb)) { ext4_warning(sb, "Setting inode version is not " "supported with metadata_csum enabled."); return -ENOTTY; @@ -544,9 +543,17 @@ group_add_out: } case EXT4_IOC_SWAP_BOOT: + { + int err; if (!(filp->f_mode & FMODE_WRITE)) return -EBADF; - return swap_inode_boot_loader(sb, inode); + err = mnt_want_write_file(filp); + if (err) + return err; + err = swap_inode_boot_loader(sb, inode); + mnt_drop_write_file(filp); + return err; + } case EXT4_IOC_RESIZE_FS: { ext4_fsblk_t n_blocks_count; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 242226a87be7..7620133f78bf 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1044,6 +1044,8 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) * allocating. If we are looking at the buddy cache we would * have taken a reference using ext4_mb_load_buddy and that * would have pinned buddy page to page cache. + * The call to ext4_mb_get_buddy_page_lock will mark the + * page accessed. */ ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b); if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) { @@ -1062,7 +1064,6 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) ret = -EIO; goto err; } - mark_page_accessed(page); if (e4b.bd_buddy_page == NULL) { /* @@ -1082,7 +1083,6 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) ret = -EIO; goto err; } - mark_page_accessed(page); err: ext4_mb_put_buddy_page_lock(&e4b); return ret; @@ -1141,7 +1141,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, /* we could use find_or_create_page(), but it locks page * what we'd like to avoid in fast path ... */ - page = find_get_page(inode->i_mapping, pnum); + page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED); if (page == NULL || !PageUptodate(page)) { if (page) /* @@ -1172,15 +1172,16 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, ret = -EIO; goto err; } + + /* Pages marked accessed already */ e4b->bd_bitmap_page = page; e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize); - mark_page_accessed(page); block++; pnum = block / blocks_per_page; poff = block % blocks_per_page; - page = find_get_page(inode->i_mapping, pnum); + page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED); if (page == NULL || !PageUptodate(page)) { if (page) page_cache_release(page); @@ -1201,9 +1202,10 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, ret = -EIO; goto err; } + + /* Pages marked accessed already */ e4b->bd_buddy_page = page; e4b->bd_buddy = page_address(page) + (poff * sb->s_blocksize); - mark_page_accessed(page); BUG_ON(e4b->bd_bitmap_page == NULL); BUG_ON(e4b->bd_buddy_page == NULL); diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 04434ad3e8e0..1268a1b5afa9 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -20,8 +20,7 @@ static __le32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp) int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp) { - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return 1; return mmp->mmp_checksum == ext4_mmp_csum(sb, mmp); @@ -29,8 +28,7 @@ int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp) void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp) { - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return; mmp->mmp_checksum = ext4_mmp_csum(sb, mmp); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index d050e043e884..98de4b391e79 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -123,8 +123,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, "directory leaf block found instead of index block"); return ERR_PTR(-EIO); } - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) || + if (!ext4_has_metadata_csum(inode->i_sb) || buffer_verified(bh)) return bh; @@ -339,8 +338,7 @@ int ext4_dirent_csum_verify(struct inode *inode, struct ext4_dir_entry *dirent) { struct ext4_dir_entry_tail *t; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return 1; t = get_dirent_tail(inode, dirent); @@ -361,8 +359,7 @@ static void ext4_dirent_csum_set(struct inode *inode, { struct ext4_dir_entry_tail *t; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return; t = get_dirent_tail(inode, dirent); @@ -437,8 +434,7 @@ static int ext4_dx_csum_verify(struct inode *inode, struct dx_tail *t; int count_offset, limit, count; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return 1; c = get_dx_countlimit(inode, dirent, &count_offset); @@ -467,8 +463,7 @@ static void ext4_dx_csum_set(struct inode *inode, struct ext4_dir_entry *dirent) struct dx_tail *t; int count_offset, limit, count; - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return; c = get_dx_countlimit(inode, dirent, &count_offset); @@ -556,8 +551,7 @@ static inline unsigned dx_root_limit(struct inode *dir, unsigned infosize) unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(1) - EXT4_DIR_REC_LEN(2) - infosize; - if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(dir->i_sb)) entry_space -= sizeof(struct dx_tail); return entry_space / sizeof(struct dx_entry); } @@ -566,8 +560,7 @@ static inline unsigned dx_node_limit(struct inode *dir) { unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0); - if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(dir->i_sb)) entry_space -= sizeof(struct dx_tail); return entry_space / sizeof(struct dx_entry); } @@ -1429,7 +1422,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi dentry); return ERR_PTR(-EIO); } - inode = ext4_iget(dir->i_sb, ino); + inode = ext4_iget_normal(dir->i_sb, ino); if (inode == ERR_PTR(-ESTALE)) { EXT4_ERROR_INODE(dir, "deleted inode referenced: %u", @@ -1460,7 +1453,7 @@ struct dentry *ext4_get_parent(struct dentry *child) return ERR_PTR(-EIO); } - return d_obtain_alias(ext4_iget(child->d_inode->i_sb, ino)); + return d_obtain_alias(ext4_iget_normal(child->d_inode->i_sb, ino)); } /* @@ -1534,8 +1527,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, int csum_size = 0; int err = 0, i; - if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(dir->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); bh2 = ext4_append(handle, dir, &newblock); @@ -1704,8 +1696,7 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry, int csum_size = 0; int err; - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); if (!de) { @@ -1772,8 +1763,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, struct fake_dirent *fde; int csum_size = 0; - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); blocksize = dir->i_sb->s_blocksize; @@ -1889,8 +1879,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, ext4_lblk_t block, blocks; int csum_size = 0; - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); sb = dir->i_sb; @@ -2152,8 +2141,7 @@ static int ext4_delete_entry(handle_t *handle, return err; } - if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(dir->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); BUFFER_TRACE(bh, "get_write_access"); @@ -2372,8 +2360,7 @@ static int ext4_init_new_dir(handle_t *handle, struct inode *dir, int csum_size = 0; int err; - if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(dir->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { @@ -3204,6 +3191,16 @@ end_rename: return retval; } +static int ext4_rename2(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags) +{ + if (flags & ~RENAME_NOREPLACE) + return -EINVAL; + + return ext4_rename(old_dir, old_dentry, new_dir, new_dentry); +} + /* * directories can handle most operations... */ @@ -3217,7 +3214,7 @@ const struct inode_operations ext4_dir_inode_operations = { .rmdir = ext4_rmdir, .mknod = ext4_mknod, .tmpfile = ext4_tmpfile, - .rename = ext4_rename, + .rename2 = ext4_rename2, .setattr = ext4_setattr, .setxattr = generic_setxattr, .getxattr = generic_getxattr, diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index f3b84cd9de56..2400ad1c3d12 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1071,7 +1071,7 @@ static void update_backups(struct super_block *sb, int blk_off, char *data, break; if (meta_bg == 0) - backup_block = group * bpg + blk_off; + backup_block = ((ext4_fsblk_t)group) * bpg + blk_off; else backup_block = (ext4_group_first_block_no(sb, group) + ext4_bg_has_super(sb, group)); @@ -1200,8 +1200,7 @@ static int ext4_set_bitmap_checksums(struct super_block *sb, { struct buffer_head *bh; - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return 0; bh = ext4_get_bitmap(sb, group_data->inode_bitmap); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index a46030d6b4af..9fb3e6c0c578 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -140,8 +140,7 @@ static __le32 ext4_superblock_csum(struct super_block *sb, int ext4_superblock_csum_verify(struct super_block *sb, struct ext4_super_block *es) { - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return 1; return es->s_checksum == ext4_superblock_csum(sb, es); @@ -151,8 +150,7 @@ void ext4_superblock_csum_set(struct super_block *sb) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(sb)) return; es->s_checksum = ext4_superblock_csum(sb, es); @@ -996,7 +994,7 @@ static struct inode *ext4_nfs_get_inode(struct super_block *sb, * Currently we don't know the generation for parent directory, so * a generation of 0 means "accept any" */ - inode = ext4_iget(sb, ino); + inode = ext4_iget_normal(sb, ino); if (IS_ERR(inode)) return ERR_CAST(inode); if (generation && inode->i_generation != generation) { @@ -1706,13 +1704,6 @@ static int parse_options(char *options, struct super_block *sb, "not specified"); return 0; } - } else { - if (sbi->s_jquota_fmt) { - ext4_msg(sb, KERN_ERR, "journaled quota format " - "specified with no journaling " - "enabled"); - return 0; - } } #endif if (test_opt(sb, DIOREAD_NOLOCK)) { @@ -2010,8 +2001,7 @@ static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group, __u16 crc = 0; __le32 le_group = cpu_to_le32(block_group); - if ((sbi->s_es->s_feature_ro_compat & - cpu_to_le32(EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))) { + if (ext4_has_metadata_csum(sbi->s_sb)) { /* Use new metadata_csum algorithm */ __le16 save_csum; __u32 csum32; @@ -2029,6 +2019,10 @@ static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group, } /* old crc16 code */ + if (!(sbi->s_es->s_feature_ro_compat & + cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM))) + return 0; + offset = offsetof(struct ext4_group_desc, bg_checksum); crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid)); @@ -3167,8 +3161,7 @@ static int set_journal_csum_feature_set(struct super_block *sb) int compat, incompat; struct ext4_sb_info *sbi = EXT4_SB(sb); - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { + if (ext4_has_metadata_csum(sb)) { /* journal checksum v3 */ compat = 0; incompat = JBD2_FEATURE_INCOMPAT_CSUM_V3; @@ -3475,8 +3468,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } /* Precompute checksum seed for all metadata */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (ext4_has_metadata_csum(sb)) sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid, sizeof(es->s_uuid)); @@ -3494,6 +3486,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) #ifdef CONFIG_EXT4_FS_POSIX_ACL set_opt(sb, POSIX_ACL); #endif + /* don't forget to enable journal_csum when metadata_csum is enabled. */ + if (ext4_has_metadata_csum(sb)) + set_opt(sb, JOURNAL_CHECKSUM); + if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA) set_opt(sb, JOURNAL_DATA); else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 55e611c1513c..8825154b20b6 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -141,8 +141,7 @@ static int ext4_xattr_block_csum_verify(struct inode *inode, sector_t block_nr, struct ext4_xattr_header *hdr) { - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) && + if (ext4_has_metadata_csum(inode->i_sb) && (hdr->h_checksum != ext4_xattr_block_csum(inode, block_nr, hdr))) return 0; return 1; @@ -152,8 +151,7 @@ static void ext4_xattr_block_csum_set(struct inode *inode, sector_t block_nr, struct ext4_xattr_header *hdr) { - if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_metadata_csum(inode->i_sb)) return; hdr->h_checksum = ext4_xattr_block_csum(inode, block_nr, hdr); @@ -189,14 +187,28 @@ ext4_listxattr(struct dentry *dentry, char *buffer, size_t size) } static int -ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end) +ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end, + void *value_start) { - while (!IS_LAST_ENTRY(entry)) { - struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(entry); + struct ext4_xattr_entry *e = entry; + + while (!IS_LAST_ENTRY(e)) { + struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(e); if ((void *)next >= end) return -EIO; - entry = next; + e = next; } + + while (!IS_LAST_ENTRY(entry)) { + if (entry->e_value_size != 0 && + (value_start + le16_to_cpu(entry->e_value_offs) < + (void *)e + sizeof(__u32) || + value_start + le16_to_cpu(entry->e_value_offs) + + le32_to_cpu(entry->e_value_size) > end)) + return -EIO; + entry = EXT4_XATTR_NEXT(entry); + } + return 0; } @@ -213,7 +225,8 @@ ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh) return -EIO; if (!ext4_xattr_block_csum_verify(inode, bh->b_blocknr, BHDR(bh))) return -EIO; - error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size); + error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size, + bh->b_data); if (!error) set_buffer_verified(bh); return error; @@ -329,7 +342,7 @@ ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name, header = IHDR(inode, raw_inode); entry = IFIRST(header); end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; - error = ext4_xattr_check_names(entry, end); + error = ext4_xattr_check_names(entry, end, entry); if (error) goto cleanup; error = ext4_xattr_find_entry(&entry, name_index, name, @@ -457,7 +470,7 @@ ext4_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size) raw_inode = ext4_raw_inode(&iloc); header = IHDR(inode, raw_inode); end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; - error = ext4_xattr_check_names(IFIRST(header), end); + error = ext4_xattr_check_names(IFIRST(header), end, IFIRST(header)); if (error) goto cleanup; error = ext4_xattr_list_entries(dentry, IFIRST(header), @@ -972,7 +985,8 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, is->s.here = is->s.first; is->s.end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { - error = ext4_xattr_check_names(IFIRST(header), is->s.end); + error = ext4_xattr_check_names(IFIRST(header), is->s.end, + IFIRST(header)); if (error) return error; /* Find the named attribute. */ diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 293d0486a40f..5c6fe278fb63 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -71,7 +71,6 @@ repeat: goto repeat; } out: - mark_page_accessed(page); return page; } diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index b0649b76eb4f..bb6478acb369 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -969,7 +969,6 @@ repeat: } got_it: f2fs_bug_on(nid != nid_of_node(page)); - mark_page_accessed(page); return page; } @@ -1024,7 +1023,6 @@ page_hit: f2fs_put_page(page, 1); return ERR_PTR(-EIO); } - mark_page_accessed(page); return page; } diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 3963ede84eb0..c5d6bb939d19 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -702,10 +702,11 @@ static int fat_readdir(struct file *file, struct dir_context *ctx) } #define FAT_IOCTL_FILLDIR_FUNC(func, dirent_type) \ -static int func(void *__buf, const char *name, int name_len, \ +static int func(struct dir_context *ctx, const char *name, int name_len, \ loff_t offset, u64 ino, unsigned int d_type) \ { \ - struct fat_ioctl_filldir_callback *buf = __buf; \ + struct fat_ioctl_filldir_callback *buf = \ + container_of(ctx, struct fat_ioctl_filldir_callback, ctx); \ struct dirent_type __user *d1 = buf->dirent; \ struct dirent_type __user *d2 = d1 + 1; \ \ diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index a16315957ef3..23a51f08e3b5 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -476,12 +476,28 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) * write_inode() */ spin_lock(&inode->i_lock); - /* Clear I_DIRTY_PAGES if we've written out all dirty pages */ - if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) - inode->i_state &= ~I_DIRTY_PAGES; + dirty = inode->i_state & I_DIRTY; - inode->i_state &= ~(I_DIRTY_SYNC | I_DIRTY_DATASYNC); + inode->i_state &= ~I_DIRTY; + + /* + * Paired with smp_mb() in __mark_inode_dirty(). This allows + * __mark_inode_dirty() to test i_state without grabbing i_lock - + * either they see the I_DIRTY bits cleared or we see the dirtied + * inode. + * + * I_DIRTY_PAGES is always cleared together above even if @mapping + * still has dirty pages. The flag is reinstated after smp_mb() if + * necessary. This guarantees that either __mark_inode_dirty() + * sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY. + */ + smp_mb(); + + if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) + inode->i_state |= I_DIRTY_PAGES; + spin_unlock(&inode->i_lock); + /* Don't write the inode if only I_DIRTY_PAGES was set */ if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) { int err = write_inode(inode, wbc); @@ -1145,12 +1161,11 @@ void __mark_inode_dirty(struct inode *inode, int flags) } /* - * make sure that changes are seen by all cpus before we test i_state - * -- mikulas + * Paired with smp_mb() in __writeback_single_inode() for the + * following lockless i_state test. See there for details. */ smp_mb(); - /* avoid the locking if we can */ if ((inode->i_state & flags) == flags) return; diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 0a648bb455ae..499155ca3e84 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -819,8 +819,8 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) newpage = buf->page; - if (WARN_ON(!PageUptodate(newpage))) - return -EIO; + if (!PageUptodate(newpage)) + SetPageUptodate(newpage); ClearPageMappedToDisk(newpage); @@ -1614,7 +1614,7 @@ out_finish: static void fuse_retrieve_end(struct fuse_conn *fc, struct fuse_req *req) { - release_pages(req->pages, req->num_pages, 0); + release_pages(req->pages, req->num_pages, false); } static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, @@ -1726,6 +1726,9 @@ copy_finish: static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code, unsigned int size, struct fuse_copy_state *cs) { + /* Don't try to move pages (yet) */ + cs->move_pages = 0; + switch (code) { case FUSE_NOTIFY_POLL: return fuse_notify_poll(fc, size, cs); diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 342f0239fcbf..33dec83eccfb 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -680,6 +680,14 @@ static int fuse_symlink(struct inode *dir, struct dentry *entry, return create_new_entry(fc, req, dir, entry, S_IFLNK); } +static inline void fuse_update_ctime(struct inode *inode) +{ + if (!IS_NOCMTIME(inode)) { + inode->i_ctime = current_fs_time(inode->i_sb); + mark_inode_dirty_sync(inode); + } +} + static int fuse_unlink(struct inode *dir, struct dentry *entry) { int err; @@ -714,6 +722,7 @@ static int fuse_unlink(struct inode *dir, struct dentry *entry) fuse_invalidate_attr(inode); fuse_invalidate_attr(dir); fuse_invalidate_entry_cache(entry); + fuse_update_ctime(inode); } else if (err == -EINTR) fuse_invalidate_entry(entry); return err; @@ -744,23 +753,26 @@ static int fuse_rmdir(struct inode *dir, struct dentry *entry) return err; } -static int fuse_rename(struct inode *olddir, struct dentry *oldent, - struct inode *newdir, struct dentry *newent) +static int fuse_rename_common(struct inode *olddir, struct dentry *oldent, + struct inode *newdir, struct dentry *newent, + unsigned int flags, int opcode, size_t argsize) { int err; - struct fuse_rename_in inarg; + struct fuse_rename2_in inarg; struct fuse_conn *fc = get_fuse_conn(olddir); - struct fuse_req *req = fuse_get_req_nopages(fc); + struct fuse_req *req; + req = fuse_get_req_nopages(fc); if (IS_ERR(req)) return PTR_ERR(req); - memset(&inarg, 0, sizeof(inarg)); + memset(&inarg, 0, argsize); inarg.newdir = get_node_id(newdir); - req->in.h.opcode = FUSE_RENAME; + inarg.flags = flags; + req->in.h.opcode = opcode; req->in.h.nodeid = get_node_id(olddir); req->in.numargs = 3; - req->in.args[0].size = sizeof(inarg); + req->in.args[0].size = argsize; req->in.args[0].value = &inarg; req->in.args[1].size = oldent->d_name.len + 1; req->in.args[1].value = oldent->d_name.name; @@ -772,15 +784,22 @@ static int fuse_rename(struct inode *olddir, struct dentry *oldent, if (!err) { /* ctime changes */ fuse_invalidate_attr(oldent->d_inode); + fuse_update_ctime(oldent->d_inode); + + if (flags & RENAME_EXCHANGE) { + fuse_invalidate_attr(newent->d_inode); + fuse_update_ctime(newent->d_inode); + } fuse_invalidate_attr(olddir); if (olddir != newdir) fuse_invalidate_attr(newdir); /* newent will end up negative */ - if (newent->d_inode) { + if (!(flags & RENAME_EXCHANGE) && newent->d_inode) { fuse_invalidate_attr(newent->d_inode); fuse_invalidate_entry_cache(newent); + fuse_update_ctime(newent->d_inode); } } else if (err == -EINTR) { /* If request was interrupted, DEITY only knows if the @@ -796,6 +815,36 @@ static int fuse_rename(struct inode *olddir, struct dentry *oldent, return err; } +static int fuse_rename2(struct inode *olddir, struct dentry *oldent, + struct inode *newdir, struct dentry *newent, + unsigned int flags) +{ + struct fuse_conn *fc = get_fuse_conn(olddir); + int err; + + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) + return -EINVAL; + + if (flags) { + if (fc->no_rename2 || fc->minor < 23) + return -EINVAL; + + err = fuse_rename_common(olddir, oldent, newdir, newent, flags, + FUSE_RENAME2, + sizeof(struct fuse_rename2_in)); + if (err == -ENOSYS) { + fc->no_rename2 = 1; + err = -EINVAL; + } + } else { + err = fuse_rename_common(olddir, oldent, newdir, newent, 0, + FUSE_RENAME, + sizeof(struct fuse_rename_in)); + } + + return err; +} + static int fuse_link(struct dentry *entry, struct inode *newdir, struct dentry *newent) { @@ -830,6 +879,7 @@ static int fuse_link(struct dentry *entry, struct inode *newdir, inc_nlink(inode); spin_unlock(&fc->lock); fuse_invalidate_attr(inode); + fuse_update_ctime(inode); } else if (err == -EINTR) { fuse_invalidate_attr(inode); } @@ -840,6 +890,16 @@ static void fuse_fillattr(struct inode *inode, struct fuse_attr *attr, struct kstat *stat) { unsigned int blkbits; + struct fuse_conn *fc = get_fuse_conn(inode); + + /* see the comment in fuse_change_attributes() */ + if (fc->writeback_cache && S_ISREG(inode->i_mode)) { + attr->size = i_size_read(inode); + attr->mtime = inode->i_mtime.tv_sec; + attr->mtimensec = inode->i_mtime.tv_nsec; + attr->ctime = inode->i_ctime.tv_sec; + attr->ctimensec = inode->i_ctime.tv_nsec; + } stat->dev = inode->i_sb->s_dev; stat->ino = attr->ino; @@ -1478,12 +1538,16 @@ static long fuse_dir_compat_ioctl(struct file *file, unsigned int cmd, FUSE_IOCTL_COMPAT | FUSE_IOCTL_DIR); } -static bool update_mtime(unsigned ivalid) +static bool update_mtime(unsigned ivalid, bool trust_local_mtime) { /* Always update if mtime is explicitly set */ if (ivalid & ATTR_MTIME_SET) return true; + /* Or if kernel i_mtime is the official one */ + if (trust_local_mtime) + return true; + /* If it's an open(O_TRUNC) or an ftruncate(), don't update */ if ((ivalid & ATTR_SIZE) && (ivalid & (ATTR_OPEN | ATTR_FILE))) return false; @@ -1492,7 +1556,8 @@ static bool update_mtime(unsigned ivalid) return true; } -static void iattr_to_fattr(struct iattr *iattr, struct fuse_setattr_in *arg) +static void iattr_to_fattr(struct iattr *iattr, struct fuse_setattr_in *arg, + bool trust_local_mtime) { unsigned ivalid = iattr->ia_valid; @@ -1511,11 +1576,11 @@ static void iattr_to_fattr(struct iattr *iattr, struct fuse_setattr_in *arg) if (!(ivalid & ATTR_ATIME_SET)) arg->valid |= FATTR_ATIME_NOW; } - if ((ivalid & ATTR_MTIME) && update_mtime(ivalid)) { + if ((ivalid & ATTR_MTIME) && update_mtime(ivalid, trust_local_mtime)) { arg->valid |= FATTR_MTIME; arg->mtime = iattr->ia_mtime.tv_sec; arg->mtimensec = iattr->ia_mtime.tv_nsec; - if (!(ivalid & ATTR_MTIME_SET)) + if (!(ivalid & ATTR_MTIME_SET) && !trust_local_mtime) arg->valid |= FATTR_MTIME_NOW; } } @@ -1564,6 +1629,63 @@ void fuse_release_nowrite(struct inode *inode) spin_unlock(&fc->lock); } +static void fuse_setattr_fill(struct fuse_conn *fc, struct fuse_req *req, + struct inode *inode, + struct fuse_setattr_in *inarg_p, + struct fuse_attr_out *outarg_p) +{ + req->in.h.opcode = FUSE_SETATTR; + req->in.h.nodeid = get_node_id(inode); + req->in.numargs = 1; + req->in.args[0].size = sizeof(*inarg_p); + req->in.args[0].value = inarg_p; + req->out.numargs = 1; + if (fc->minor < 9) + req->out.args[0].size = FUSE_COMPAT_ATTR_OUT_SIZE; + else + req->out.args[0].size = sizeof(*outarg_p); + req->out.args[0].value = outarg_p; +} + +/* + * Flush inode->i_mtime to the server + */ +int fuse_flush_mtime(struct file *file, bool nofail) +{ + struct inode *inode = file->f_mapping->host; + struct fuse_inode *fi = get_fuse_inode(inode); + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_req *req = NULL; + struct fuse_setattr_in inarg; + struct fuse_attr_out outarg; + int err; + + if (nofail) { + req = fuse_get_req_nofail_nopages(fc, file); + } else { + req = fuse_get_req_nopages(fc); + if (IS_ERR(req)) + return PTR_ERR(req); + } + + memset(&inarg, 0, sizeof(inarg)); + memset(&outarg, 0, sizeof(outarg)); + + inarg.valid |= FATTR_MTIME; + inarg.mtime = inode->i_mtime.tv_sec; + inarg.mtimensec = inode->i_mtime.tv_nsec; + + fuse_setattr_fill(fc, req, inode, &inarg, &outarg); + fuse_request_send(fc, req); + err = req->out.h.error; + fuse_put_request(fc, req); + + if (!err) + clear_bit(FUSE_I_MTIME_DIRTY, &fi->state); + + return err; +} + /* * Set attributes, and at the same time refresh them. * @@ -1581,8 +1703,10 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr, struct fuse_setattr_in inarg; struct fuse_attr_out outarg; bool is_truncate = false; + bool is_wb = fc->writeback_cache; loff_t oldsize; int err; + bool trust_local_mtime = is_wb && S_ISREG(inode->i_mode); if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS)) attr->ia_valid |= ATTR_FORCE; @@ -1611,7 +1735,7 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr, memset(&inarg, 0, sizeof(inarg)); memset(&outarg, 0, sizeof(outarg)); - iattr_to_fattr(attr, &inarg); + iattr_to_fattr(attr, &inarg, trust_local_mtime); if (file) { struct fuse_file *ff = file->private_data; inarg.valid |= FATTR_FH; @@ -1622,17 +1746,7 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr, inarg.valid |= FATTR_LOCKOWNER; inarg.lock_owner = fuse_lock_owner_id(fc, current->files); } - req->in.h.opcode = FUSE_SETATTR; - req->in.h.nodeid = get_node_id(inode); - req->in.numargs = 1; - req->in.args[0].size = sizeof(inarg); - req->in.args[0].value = &inarg; - req->out.numargs = 1; - if (fc->minor < 9) - req->out.args[0].size = FUSE_COMPAT_ATTR_OUT_SIZE; - else - req->out.args[0].size = sizeof(outarg); - req->out.args[0].value = &outarg; + fuse_setattr_fill(fc, req, inode, &inarg, &outarg); fuse_request_send(fc, req); err = req->out.h.error; fuse_put_request(fc, req); @@ -1649,10 +1763,18 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr, } spin_lock(&fc->lock); + /* the kernel maintains i_mtime locally */ + if (trust_local_mtime && (attr->ia_valid & ATTR_MTIME)) { + inode->i_mtime = attr->ia_mtime; + clear_bit(FUSE_I_MTIME_DIRTY, &fi->state); + } + fuse_change_attributes_common(inode, &outarg.attr, attr_timeout(&outarg)); oldsize = inode->i_size; - i_size_write(inode, outarg.attr.size); + /* see the comment in fuse_change_attributes() */ + if (!is_wb || is_truncate || !S_ISREG(inode->i_mode)) + i_size_write(inode, outarg.attr.size); if (is_truncate) { /* NOTE: this may release/reacquire fc->lock */ @@ -1664,7 +1786,8 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr, * Only call invalidate_inode_pages2() after removing * FUSE_NOWRITE, otherwise fuse_launder_page() would deadlock. */ - if (S_ISREG(inode->i_mode) && oldsize != outarg.attr.size) { + if ((is_truncate || !is_wb) && + S_ISREG(inode->i_mode) && oldsize != outarg.attr.size) { truncate_pagecache(inode, outarg.attr.size); invalidate_inode_pages2(inode->i_mapping); } @@ -1740,8 +1863,10 @@ static int fuse_setxattr(struct dentry *entry, const char *name, fc->no_setxattr = 1; err = -EOPNOTSUPP; } - if (!err) + if (!err) { fuse_invalidate_attr(inode); + fuse_update_ctime(inode); + } return err; } @@ -1871,18 +1996,31 @@ static int fuse_removexattr(struct dentry *entry, const char *name) fc->no_removexattr = 1; err = -EOPNOTSUPP; } - if (!err) + if (!err) { fuse_invalidate_attr(inode); + fuse_update_ctime(inode); + } return err; } +static int fuse_update_time(struct inode *inode, struct timespec *now, + int flags) +{ + if (flags & S_MTIME) { + inode->i_mtime = *now; + set_bit(FUSE_I_MTIME_DIRTY, &get_fuse_inode(inode)->state); + BUG_ON(!S_ISREG(inode->i_mode)); + } + return 0; +} + static const struct inode_operations fuse_dir_inode_operations = { .lookup = fuse_lookup, .mkdir = fuse_mkdir, .symlink = fuse_symlink, .unlink = fuse_unlink, .rmdir = fuse_rmdir, - .rename = fuse_rename, + .rename2 = fuse_rename2, .link = fuse_link, .setattr = fuse_setattr, .create = fuse_create, @@ -1915,6 +2053,7 @@ static const struct inode_operations fuse_common_inode_operations = { .getxattr = fuse_getxattr, .listxattr = fuse_listxattr, .removexattr = fuse_removexattr, + .update_time = fuse_update_time, }; static const struct inode_operations fuse_symlink_inode_operations = { diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 77bcc303c3ae..5916dc51599b 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -188,6 +188,22 @@ int fuse_do_open(struct fuse_conn *fc, u64 nodeid, struct file *file, } EXPORT_SYMBOL_GPL(fuse_do_open); +static void fuse_link_write_file(struct file *file) +{ + struct inode *inode = file_inode(file); + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_inode *fi = get_fuse_inode(inode); + struct fuse_file *ff = file->private_data; + /* + * file may be written through mmap, so chain it onto the + * inodes's write_file list + */ + spin_lock(&fc->lock); + if (list_empty(&ff->write_entry)) + list_add(&ff->write_entry, &fi->write_files); + spin_unlock(&fc->lock); +} + void fuse_finish_open(struct inode *inode, struct file *file) { struct fuse_file *ff = file->private_data; @@ -292,6 +308,9 @@ static int fuse_open(struct inode *inode, struct file *file) static int fuse_release(struct inode *inode, struct file *file) { + if (test_bit(FUSE_I_MTIME_DIRTY, &get_fuse_inode(inode)->state)) + fuse_flush_mtime(file, true); + fuse_release_common(file, FUSE_RELEASE); /* return value is ignored by VFS */ @@ -459,6 +478,12 @@ int fuse_fsync_common(struct file *file, loff_t start, loff_t end, fuse_sync_writes(inode); + if (test_bit(FUSE_I_MTIME_DIRTY, &get_fuse_inode(inode)->state)) { + int err = fuse_flush_mtime(file, false); + if (err) + goto out; + } + req = fuse_get_req_nopages(fc); if (IS_ERR(req)) { err = PTR_ERR(req); @@ -655,6 +680,32 @@ static void fuse_read_update_size(struct inode *inode, loff_t size, spin_unlock(&fc->lock); } +static void fuse_short_read(struct fuse_req *req, struct inode *inode, + u64 attr_ver) +{ + size_t num_read = req->out.args[0].size; + struct fuse_conn *fc = get_fuse_conn(inode); + + if (fc->writeback_cache) { + /* + * A hole in a file. Some data after the hole are in page cache, + * but have not reached the client fs yet. So, the hole is not + * present there. + */ + int i; + int start_idx = num_read >> PAGE_CACHE_SHIFT; + size_t off = num_read & (PAGE_CACHE_SIZE - 1); + + for (i = start_idx; i < req->num_pages; i++) { + zero_user_segment(req->pages[i], off, PAGE_CACHE_SIZE); + off = 0; + } + } else { + loff_t pos = page_offset(req->pages[0]) + num_read; + fuse_read_update_size(inode, pos, attr_ver); + } +} + static int fuse_readpage(struct file *file, struct page *page) { struct fuse_io_priv io = { .async = 0, .file = file }; @@ -692,18 +743,18 @@ static int fuse_readpage(struct file *file, struct page *page) req->page_descs[0].length = count; num_read = fuse_send_read(req, &io, pos, count, NULL); err = req->out.h.error; - fuse_put_request(fc, req); if (!err) { /* * Short read means EOF. If file size is larger, truncate it */ if (num_read < count) - fuse_read_update_size(inode, pos + num_read, attr_ver); + fuse_short_read(req, inode, attr_ver); SetPageUptodate(page); } + fuse_put_request(fc, req); fuse_invalidate_atime(inode); out: unlock_page(page); @@ -726,13 +777,9 @@ static void fuse_readpages_end(struct fuse_conn *fc, struct fuse_req *req) /* * Short read means EOF. If file size is larger, truncate it */ - if (!req->out.h.error && num_read < count) { - loff_t pos; + if (!req->out.h.error && num_read < count) + fuse_short_read(req, inode, req->misc.read.attr_ver); - pos = page_offset(req->pages[0]) + num_read; - fuse_read_update_size(inode, pos, - req->misc.read.attr_ver); - } fuse_invalidate_atime(inode); } @@ -922,16 +969,21 @@ static size_t fuse_send_write(struct fuse_req *req, struct fuse_io_priv *io, return req->misc.write.out.size; } -void fuse_write_update_size(struct inode *inode, loff_t pos) +bool fuse_write_update_size(struct inode *inode, loff_t pos) { struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); + bool ret = false; spin_lock(&fc->lock); fi->attr_version = ++fc->attr_version; - if (pos > inode->i_size) + if (pos > inode->i_size) { i_size_write(inode, pos); + ret = true; + } spin_unlock(&fc->lock); + + return ret; } static size_t fuse_send_write_pages(struct fuse_req *req, struct file *file, @@ -1003,13 +1055,9 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req, if (mapping_writably_mapped(mapping)) flush_dcache_page(page); - pagefault_disable(); tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes); - pagefault_enable(); flush_dcache_page(page); - mark_page_accessed(page); - if (!tmp) { unlock_page(page); page_cache_release(page); @@ -1946,20 +1994,9 @@ static const struct vm_operations_struct fuse_file_vm_ops = { static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) { - if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE)) { - struct inode *inode = file_inode(file); - struct fuse_conn *fc = get_fuse_conn(inode); - struct fuse_inode *fi = get_fuse_inode(inode); - struct fuse_file *ff = file->private_data; - /* - * file may be written through mmap, so chain it onto the - * inodes's write_file list - */ - spin_lock(&fc->lock); - if (list_empty(&ff->write_entry)) - list_add(&ff->write_entry, &fi->write_files); - spin_unlock(&fc->lock); - } + if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE)) + fuse_link_write_file(file); + file_accessed(file); vma->vm_ops = &fuse_file_vm_ops; return 0; @@ -2850,8 +2887,16 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, goto out; /* we could have extended the file */ - if (!(mode & FALLOC_FL_KEEP_SIZE)) - fuse_write_update_size(inode, offset + length); + if (!(mode & FALLOC_FL_KEEP_SIZE)) { + bool changed = fuse_write_update_size(inode, offset + length); + + if (changed && fc->writeback_cache) { + struct fuse_inode *fi = get_fuse_inode(inode); + + inode->i_mtime = current_fs_time(inode->i_sb); + set_bit(FUSE_I_MTIME_DIRTY, &fi->state); + } + } if (mode & FALLOC_FL_PUNCH_HOLE) truncate_pagecache_range(inode, offset, offset + length - 1); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 2da5db2c8bdb..7cc58c976780 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -119,6 +119,8 @@ enum { FUSE_I_INIT_RDPLUS, /** An operation changing file size is in progress */ FUSE_I_SIZE_UNSTABLE, + /** i_mtime has been updated locally; a flush to userspace needed */ + FUSE_I_MTIME_DIRTY, }; struct fuse_conn; @@ -480,6 +482,9 @@ struct fuse_conn { /** Set if bdi is valid */ unsigned bdi_initialized:1; + /** write-back cache policy (default is write-through) */ + unsigned writeback_cache:1; + /* * The following bitfields are only for optimization purposes * and hence races in setting them will not cause malfunction @@ -539,6 +544,9 @@ struct fuse_conn { /** Is fallocate not implemented by fs? */ unsigned no_fallocate:1; + /** Is rename with flags implemented by fs? */ + unsigned no_rename2:1; + /** Use enhanced/automatic page cache invalidation. */ unsigned auto_inval_data:1; @@ -873,7 +881,9 @@ long fuse_ioctl_common(struct file *file, unsigned int cmd, unsigned fuse_file_poll(struct file *file, poll_table *wait); int fuse_dev_release(struct inode *inode, struct file *file); -void fuse_write_update_size(struct inode *inode, loff_t pos); +bool fuse_write_update_size(struct inode *inode, loff_t pos); + +int fuse_flush_mtime(struct file *file, bool nofail); int fuse_do_setattr(struct inode *inode, struct iattr *attr, struct file *file); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 73f6bcb44ea8..8fe0b485908c 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -170,10 +170,13 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, inode->i_blocks = attr->blocks; inode->i_atime.tv_sec = attr->atime; inode->i_atime.tv_nsec = attr->atimensec; - inode->i_mtime.tv_sec = attr->mtime; - inode->i_mtime.tv_nsec = attr->mtimensec; - inode->i_ctime.tv_sec = attr->ctime; - inode->i_ctime.tv_nsec = attr->ctimensec; + /* mtime from server may be stale due to local buffered write */ + if (!fc->writeback_cache || !S_ISREG(inode->i_mode)) { + inode->i_mtime.tv_sec = attr->mtime; + inode->i_mtime.tv_nsec = attr->mtimensec; + inode->i_ctime.tv_sec = attr->ctime; + inode->i_ctime.tv_nsec = attr->ctimensec; + } if (attr->blksize != 0) inode->i_blkbits = ilog2(attr->blksize); @@ -197,6 +200,7 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, { struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); + bool is_wb = fc->writeback_cache; loff_t oldsize; struct timespec old_mtime; @@ -211,10 +215,16 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, fuse_change_attributes_common(inode, attr, attr_valid); oldsize = inode->i_size; - i_size_write(inode, attr->size); + /* + * In case of writeback_cache enabled, the cached writes beyond EOF + * extend local i_size without keeping userspace server in sync. So, + * attr->size coming from server can be stale. We cannot trust it. + */ + if (!is_wb || !S_ISREG(inode->i_mode)) + i_size_write(inode, attr->size); spin_unlock(&fc->lock); - if (S_ISREG(inode->i_mode)) { + if (!is_wb && S_ISREG(inode->i_mode)) { bool inval = false; if (oldsize != attr->size) { @@ -243,6 +253,10 @@ static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr) { inode->i_mode = attr->mode & S_IFMT; inode->i_size = attr->size; + inode->i_mtime.tv_sec = attr->mtime; + inode->i_mtime.tv_nsec = attr->mtimensec; + inode->i_ctime.tv_sec = attr->ctime; + inode->i_ctime.tv_nsec = attr->ctimensec; if (S_ISREG(inode->i_mode)) { fuse_init_common(inode); fuse_init_file_inode(inode); @@ -289,7 +303,9 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid, return NULL; if ((inode->i_state & I_NEW)) { - inode->i_flags |= S_NOATIME|S_NOCMTIME; + inode->i_flags |= S_NOATIME; + if (!fc->writeback_cache || !S_ISREG(inode->i_mode)) + inode->i_flags |= S_NOCMTIME; inode->i_generation = generation; inode->i_data.backing_dev_info = &fc->bdi; fuse_init_inode(inode, attr); diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 49436fa7cd4f..4ccb60d943bb 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -517,7 +517,6 @@ int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos, p = kmap_atomic(page); memcpy(buf + copied, p + offset, amt); kunmap_atomic(p); - mark_page_accessed(page); page_cache_release(page); copied += amt; index++; diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c index 8b9b3775e2e7..c41d255b6a7b 100644 --- a/fs/gfs2/export.c +++ b/fs/gfs2/export.c @@ -69,10 +69,12 @@ struct get_name_filldir { char *name; }; -static int get_name_filldir(void *opaque, const char *name, int length, - loff_t offset, u64 inum, unsigned int type) +static int get_name_filldir(struct dir_context *ctx, const char *name, + int length, loff_t offset, u64 inum, + unsigned int type) { - struct get_name_filldir *gnfd = opaque; + struct get_name_filldir *gnfd = + container_of(ctx, struct get_name_filldir, ctx); if (inum != gnfd->inum.no_addr) return 0; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 5c524180c98e..bc643b97423c 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -606,8 +606,10 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, if (!IS_ERR(inode)) { d = d_splice_alias(inode, dentry); error = PTR_ERR(d); - if (IS_ERR(d)) + if (IS_ERR(d)) { + inode = ERR_CAST(d); goto fail_gunlock; + } error = 0; if (file) { if (S_ISREG(inode->i_mode)) { @@ -823,7 +825,6 @@ static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry, d = d_splice_alias(inode, dentry); if (IS_ERR(d)) { - iput(inode); gfs2_glock_dq_uninit(&gh); return d; } diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index c7f24690ed05..e7b149614f5e 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -97,6 +97,11 @@ const struct address_space_operations gfs2_meta_aops = { .releasepage = gfs2_releasepage, }; +const struct address_space_operations gfs2_rgrp_aops = { + .writepage = gfs2_aspace_writepage, + .releasepage = gfs2_releasepage, +}; + /** * gfs2_getbuf - Get a buffer with a given address space * @gl: the glock @@ -131,7 +136,8 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create) yield(); } } else { - page = find_lock_page(mapping, index); + page = find_get_page_flags(mapping, index, + FGP_LOCK|FGP_ACCESSED); if (!page) return NULL; } @@ -148,7 +154,6 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create) map_bh(bh, sdp->sd_vfs, blkno); unlock_page(page); - mark_page_accessed(page); page_cache_release(page); return bh; diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h index 4823b934208a..ac5d8027d335 100644 --- a/fs/gfs2/meta_io.h +++ b/fs/gfs2/meta_io.h @@ -38,12 +38,15 @@ static inline void gfs2_buffer_copy_tail(struct buffer_head *to_bh, } extern const struct address_space_operations gfs2_meta_aops; +extern const struct address_space_operations gfs2_rgrp_aops; static inline struct gfs2_sbd *gfs2_mapping2sbd(struct address_space *mapping) { struct inode *inode = mapping->host; if (mapping->a_ops == &gfs2_meta_aops) return (((struct gfs2_glock *)mapping) - 1)->gl_sbd; + else if (mapping->a_ops == &gfs2_rgrp_aops) + return container_of(mapping, struct gfs2_sbd, sd_aspace); else return inode->i_sb->s_fs_info; } diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index c6872d09561a..f6c9d83aa39b 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -104,7 +104,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) mapping = &sdp->sd_aspace; address_space_init_once(mapping); - mapping->a_ops = &gfs2_meta_aops; + mapping->a_ops = &gfs2_rgrp_aops; mapping->host = sb->s_bdev->bd_inode; mapping->flags = 0; mapping_set_gfp_mask(mapping, GFP_NOFS); diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c index 6e560d56094b..754fdf8c6356 100644 --- a/fs/hfsplus/brec.c +++ b/fs/hfsplus/brec.c @@ -131,13 +131,16 @@ skip: hfs_bnode_write(node, entry, data_off + key_len, entry_len); hfs_bnode_dump(node); - if (new_node) { - /* update parent key if we inserted a key - * at the start of the first node - */ - if (!rec && new_node != node) - hfs_brec_update_parent(fd); + /* + * update parent key if we inserted a key + * at the start of the node and it is not the new node + */ + if (!rec && new_node != node) { + hfs_bnode_read_key(node, fd->search_key, data_off + size); + hfs_brec_update_parent(fd); + } + if (new_node) { hfs_bnode_put(fd->bnode); if (!new_node->parent) { hfs_btree_inc_height(tree); @@ -168,9 +171,6 @@ skip: goto again; } - if (!rec) - hfs_brec_update_parent(fd); - return 0; } @@ -370,6 +370,8 @@ again: if (IS_ERR(parent)) return PTR_ERR(parent); __hfs_brec_find(parent, fd, hfs_find_rec_by_key); + if (fd->record < 0) + return -ENOENT; hfs_bnode_dump(parent); rec = fd->record; diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c index 4338ff32959d..5f2755117ce7 100644 --- a/fs/hppfs/hppfs.c +++ b/fs/hppfs/hppfs.c @@ -548,10 +548,11 @@ struct hppfs_dirent { struct dentry *dentry; }; -static int hppfs_filldir(void *d, const char *name, int size, +static int hppfs_filldir(struct dir_context *ctx, const char *name, int size, loff_t offset, u64 inode, unsigned int type) { - struct hppfs_dirent *dirent = d; + struct hppfs_dirent *dirent = + container_of(ctx, struct hppfs_dirent, ctx); if (file_removed(dirent->dentry, name)) return 0; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index d19b30ababf1..a4a8ed56e438 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -1017,6 +1017,11 @@ static int __init init_hugetlbfs_fs(void) int error; int i; + if (!hugepages_supported()) { + pr_info("hugetlbfs: disabling because there are no supported hugepage sizes\n"); + return -ENOTSUPP; + } + error = bdi_init(&hugetlbfs_backing_dev_info); if (error) return error; diff --git a/fs/internal.h b/fs/internal.h index 465742407466..dd41b12c13f1 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -42,7 +42,6 @@ extern void __init chrdev_init(void); /* * namei.c */ -extern int __inode_permission(struct inode *, int); extern int user_path_mountpoint_at(int, const char __user *, unsigned int, struct path *); extern int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); @@ -135,12 +134,6 @@ extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *); extern int rw_verify_area(int, struct file *, const loff_t *, size_t); /* - * splice.c - */ -extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, - loff_t *opos, size_t len, unsigned int flags); - -/* * pipe.c */ extern const struct file_operations pipefifo_fops; diff --git a/fs/ioprio.c b/fs/ioprio.c index e50170ca7c33..31666c92b46a 100644 --- a/fs/ioprio.c +++ b/fs/ioprio.c @@ -157,14 +157,16 @@ out: int ioprio_best(unsigned short aprio, unsigned short bprio) { - unsigned short aclass = IOPRIO_PRIO_CLASS(aprio); - unsigned short bclass = IOPRIO_PRIO_CLASS(bprio); + unsigned short aclass; + unsigned short bclass; - if (aclass == IOPRIO_CLASS_NONE) - aclass = IOPRIO_CLASS_BE; - if (bclass == IOPRIO_CLASS_NONE) - bclass = IOPRIO_CLASS_BE; + if (!ioprio_valid(aprio)) + aprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM); + if (!ioprio_valid(bprio)) + bprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM); + aclass = IOPRIO_PRIO_CLASS(aprio); + bclass = IOPRIO_PRIO_CLASS(bprio); if (aclass == bclass) return min(aprio, bprio); if (aclass > bclass) diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c index f488bbae541a..735d7522a3a9 100644 --- a/fs/isofs/rock.c +++ b/fs/isofs/rock.c @@ -30,6 +30,7 @@ struct rock_state { int cont_size; int cont_extent; int cont_offset; + int cont_loops; struct inode *inode; }; @@ -73,6 +74,9 @@ static void init_rock_state(struct rock_state *rs, struct inode *inode) rs->inode = inode; } +/* Maximum number of Rock Ridge continuation entries */ +#define RR_MAX_CE_ENTRIES 32 + /* * Returns 0 if the caller should continue scanning, 1 if the scan must end * and -ve on error. @@ -105,6 +109,8 @@ static int rock_continue(struct rock_state *rs) goto out; } ret = -EIO; + if (++rs->cont_loops >= RR_MAX_CE_ENTRIES) + goto out; bh = sb_bread(rs->inode->i_sb, rs->cont_extent); if (bh) { memcpy(rs->buffer, bh->b_data + rs->cont_offset, @@ -356,6 +362,9 @@ repeat: rs.cont_size = isonum_733(rr->u.CE.size); break; case SIG('E', 'R'): + /* Invalid length of ER tag id? */ + if (rr->u.ER.len_id + offsetof(struct rock_ridge, u.ER.data) > rr->len) + goto out; ISOFS_SB(inode->i_sb)->s_rock = 1; printk(KERN_DEBUG "ISO 9660 Extensions: "); { diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 9b329b55ffe3..bcbef08a4d8f 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -525,6 +525,7 @@ static int do_one_pass(journal_t *journal, !jbd2_descr_block_csum_verify(journal, bh->b_data)) { err = -EIO; + brelse(bh); goto failed; } diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index a69e426435dd..5b234db85854 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -687,7 +687,7 @@ unsigned char *jffs2_gc_fetch_page(struct jffs2_sb_info *c, struct inode *inode = OFNI_EDONI_2SFFJ(f); struct page *pg; - pg = read_cache_page_async(inode->i_mapping, offset >> PAGE_CACHE_SHIFT, + pg = read_cache_page(inode->i_mapping, offset >> PAGE_CACHE_SHIFT, (void *)jffs2_do_readpage_unlock, inode); if (IS_ERR(pg)) return (void *)pg; diff --git a/fs/jffs2/jffs2_fs_sb.h b/fs/jffs2/jffs2_fs_sb.h index 413ef89c2d1b..046fee8b6e9b 100644 --- a/fs/jffs2/jffs2_fs_sb.h +++ b/fs/jffs2/jffs2_fs_sb.h @@ -134,8 +134,6 @@ struct jffs2_sb_info { struct rw_semaphore wbuf_sem; /* Protects the write buffer */ struct delayed_work wbuf_dwork; /* write-buffer write-out work */ - int wbuf_queued; /* non-zero delayed work is queued */ - spinlock_t wbuf_dwork_lock; /* protects wbuf_dwork and and wbuf_queued */ unsigned char *oobbuf; int oobavail; /* How many bytes are available for JFFS2 in OOB */ diff --git a/fs/jffs2/scan.c b/fs/jffs2/scan.c index 7654e87b0428..9ad5ba4b299b 100644 --- a/fs/jffs2/scan.c +++ b/fs/jffs2/scan.c @@ -510,6 +510,10 @@ static int jffs2_scan_eraseblock (struct jffs2_sb_info *c, struct jffs2_eraseblo sumlen = c->sector_size - je32_to_cpu(sm->offset); sumptr = buf + buf_size - sumlen; + /* sm->offset maybe wrong but MAGIC maybe right */ + if (sumlen > c->sector_size) + goto full_scan; + /* Now, make sure the summary itself is available */ if (sumlen > buf_size) { /* Need to kmalloc for this. */ @@ -544,6 +548,7 @@ static int jffs2_scan_eraseblock (struct jffs2_sb_info *c, struct jffs2_eraseblo } } +full_scan: buf_ofs = jeb->offset; if (!buf_size) { diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c index a6597d60d76d..09ed55190ee2 100644 --- a/fs/jffs2/wbuf.c +++ b/fs/jffs2/wbuf.c @@ -1162,10 +1162,6 @@ static void delayed_wbuf_sync(struct work_struct *work) struct jffs2_sb_info *c = work_to_sb(work); struct super_block *sb = OFNI_BS_2SFFJ(c); - spin_lock(&c->wbuf_dwork_lock); - c->wbuf_queued = 0; - spin_unlock(&c->wbuf_dwork_lock); - if (!(sb->s_flags & MS_RDONLY)) { jffs2_dbg(1, "%s()\n", __func__); jffs2_flush_wbuf_gc(c, 0); @@ -1180,14 +1176,9 @@ void jffs2_dirty_trigger(struct jffs2_sb_info *c) if (sb->s_flags & MS_RDONLY) return; - spin_lock(&c->wbuf_dwork_lock); - if (!c->wbuf_queued) { + delay = msecs_to_jiffies(dirty_writeback_interval * 10); + if (queue_delayed_work(system_long_wq, &c->wbuf_dwork, delay)) jffs2_dbg(1, "%s()\n", __func__); - delay = msecs_to_jiffies(dirty_writeback_interval * 10); - queue_delayed_work(system_long_wq, &c->wbuf_dwork, delay); - c->wbuf_queued = 1; - } - spin_unlock(&c->wbuf_dwork_lock); } int jffs2_nand_flash_setup(struct jffs2_sb_info *c) @@ -1211,7 +1202,6 @@ int jffs2_nand_flash_setup(struct jffs2_sb_info *c) /* Initialise write buffer */ init_rwsem(&c->wbuf_sem); - spin_lock_init(&c->wbuf_dwork_lock); INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync); c->wbuf_pagesize = c->mtd->writesize; c->wbuf_ofs = 0xFFFFFFFF; @@ -1251,7 +1241,6 @@ int jffs2_dataflash_setup(struct jffs2_sb_info *c) { /* Initialize write buffer */ init_rwsem(&c->wbuf_sem); - spin_lock_init(&c->wbuf_dwork_lock); INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync); c->wbuf_pagesize = c->mtd->erasesize; @@ -1311,7 +1300,6 @@ int jffs2_nor_wbuf_flash_setup(struct jffs2_sb_info *c) { /* Initialize write buffer */ init_rwsem(&c->wbuf_sem); - spin_lock_init(&c->wbuf_dwork_lock); INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync); c->wbuf_pagesize = c->mtd->writesize; @@ -1346,7 +1334,6 @@ int jffs2_ubivol_setup(struct jffs2_sb_info *c) { return 0; init_rwsem(&c->wbuf_sem); - spin_lock_init(&c->wbuf_dwork_lock); INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync); c->wbuf_pagesize = c->mtd->writesize; diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 1812f026960c..6ae664b489af 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -159,6 +159,12 @@ static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res, msg.rpc_proc = &clnt->cl_procinfo[proc]; status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN); + if (status == -ECONNREFUSED) { + dprintk("lockd: NSM upcall RPC failed, status=%d, forcing rebind\n", + status); + rpc_force_rebind(clnt); + status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN); + } if (status < 0) dprintk("lockd: NSM upcall RPC failed, status=%d\n", status); diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 6bf06a07f3e0..59a53f664005 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -137,10 +137,6 @@ lockd(void *vrqstp) dprintk("NFS locking service started (ver " LOCKD_VERSION ").\n"); - if (!nlm_timeout) - nlm_timeout = LOCKD_DFLT_TIMEO; - nlmsvc_timeout = nlm_timeout * HZ; - /* * The main request loop. We don't terminate until the last * NFS mount or NFS daemon has gone away. @@ -253,13 +249,11 @@ static int lockd_up_net(struct svc_serv *serv, struct net *net) error = make_socks(serv, net); if (error < 0) - goto err_socks; + goto err_bind; set_grace_period(net); dprintk("lockd_up_net: per-net data created; net=%p\n", net); return 0; -err_socks: - svc_rpcb_cleanup(serv, net); err_bind: ln->nlmsvc_users--; return error; @@ -348,6 +342,10 @@ static struct svc_serv *lockd_create_svc(void) printk(KERN_WARNING "lockd_up: no pid, %d users??\n", nlmsvc_users); + if (!nlm_timeout) + nlm_timeout = LOCKD_DFLT_TIMEO; + nlmsvc_timeout = nlm_timeout * HZ; + serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, NULL); if (!serv) { printk(KERN_WARNING "lockd_up: create service failed\n"); diff --git a/fs/locks.c b/fs/locks.c index 4dd39b98a6a3..2c61c4e9368c 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2235,16 +2235,28 @@ void locks_remove_flock(struct file *filp) while ((fl = *before) != NULL) { if (fl->fl_file == filp) { - if (IS_FLOCK(fl)) { - locks_delete_lock(before); - continue; - } if (IS_LEASE(fl)) { lease_modify(before, F_UNLCK); continue; } - /* What? */ - BUG(); + + /* + * There's a leftover lock on the list of a type that + * we didn't expect to see. Most likely a classic + * POSIX lock that ended up not getting released + * properly, or that raced onto the list somehow. Log + * some info about it and then just remove it from + * the list. + */ + WARN(!IS_FLOCK(fl), + "leftover lock: dev=%u:%u ino=%lu type=%hhd flags=0x%x start=%lld end=%lld\n", + MAJOR(inode->i_sb->s_dev), + MINOR(inode->i_sb->s_dev), inode->i_ino, + fl->fl_type, fl->fl_flags, + fl->fl_start, fl->fl_end); + + locks_delete_lock(before); + continue; } before = &fl->fl_next; } diff --git a/fs/namei.c b/fs/namei.c index d5a4faeb39a5..0fbf1504fb63 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -415,6 +415,7 @@ int __inode_permission(struct inode *inode, int mask) return security_inode_permission(inode, mask); } +EXPORT_SYMBOL(__inode_permission); /** * sb_permission - Check superblock-level permissions @@ -642,24 +643,22 @@ static int complete_walk(struct nameidata *nd) static __always_inline void set_root(struct nameidata *nd) { - if (!nd->root.mnt) - get_fs_root(current->fs, &nd->root); + get_fs_root(current->fs, &nd->root); } static int link_path_walk(const char *, struct nameidata *); -static __always_inline void set_root_rcu(struct nameidata *nd) +static __always_inline unsigned set_root_rcu(struct nameidata *nd) { - if (!nd->root.mnt) { - struct fs_struct *fs = current->fs; - unsigned seq; + struct fs_struct *fs = current->fs; + unsigned seq, res; - do { - seq = read_seqcount_begin(&fs->seq); - nd->root = fs->root; - nd->seq = __read_seqcount_begin(&nd->root.dentry->d_seq); - } while (read_seqcount_retry(&fs->seq, seq)); - } + do { + seq = read_seqcount_begin(&fs->seq); + nd->root = fs->root; + res = __read_seqcount_begin(&nd->root.dentry->d_seq); + } while (read_seqcount_retry(&fs->seq, seq)); + return res; } static void path_put_conditional(struct path *path, struct nameidata *nd) @@ -859,7 +858,8 @@ follow_link(struct path *link, struct nameidata *nd, void **p) return PTR_ERR(s); } if (*s == '/') { - set_root(nd); + if (!nd->root.mnt) + set_root(nd); path_put(&nd->path); nd->path = nd->root; path_get(&nd->root); @@ -1132,7 +1132,8 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path, static int follow_dotdot_rcu(struct nameidata *nd) { - set_root_rcu(nd); + if (!nd->root.mnt) + set_root_rcu(nd); while (1) { if (nd->path.dentry == nd->root.dentry && @@ -1244,7 +1245,8 @@ static void follow_mount(struct path *path) static void follow_dotdot(struct nameidata *nd) { - set_root(nd); + if (!nd->root.mnt) + set_root(nd); while(1) { struct dentry *old = nd->path.dentry; @@ -1842,7 +1844,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, if (*name=='/') { if (flags & LOOKUP_RCU) { rcu_read_lock(); - set_root_rcu(nd); + nd->seq = set_root_rcu(nd); } else { set_root(nd); path_get(&nd->root); @@ -2358,22 +2360,17 @@ kern_path_mountpoint(int dfd, const char *name, struct path *path, } EXPORT_SYMBOL(kern_path_mountpoint); -/* - * It's inline, so penalty for filesystems that don't use sticky bit is - * minimal. - */ -static inline int check_sticky(struct inode *dir, struct inode *inode) +int __check_sticky(struct inode *dir, struct inode *inode) { kuid_t fsuid = current_fsuid(); - if (!(dir->i_mode & S_ISVTX)) - return 0; if (uid_eq(inode->i_uid, fsuid)) return 0; if (uid_eq(dir->i_uid, fsuid)) return 0; return !capable_wrt_inode_uidgid(inode, CAP_FOWNER); } +EXPORT_SYMBOL(__check_sticky); /* * Check whether we can remove a link victim from directory dir, check @@ -2476,7 +2473,7 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) } mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT); - mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD); + mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_PARENT2); return NULL; } @@ -3036,9 +3033,12 @@ finish_open_created: error = may_open(&nd->path, acc_mode, open_flag); if (error) goto out; - file->f_path.mnt = nd->path.mnt; - error = finish_open(file, nd->path.dentry, NULL, opened); - if (error) { + + BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */ + error = vfs_open(&nd->path, file, current_cred()); + if (!error) { + *opened |= FILE_OPENED; + } else { if (error == -EOPENSTALE) goto stale_open; goto out; @@ -3127,7 +3127,8 @@ static int do_tmpfile(int dfd, struct filename *pathname, if (error) goto out2; audit_inode(pathname, nd->path.dentry, 0); - error = may_open(&nd->path, op->acc_mode, op->open_flag); + /* Don't check for other permissions, the inode was just created */ + error = may_open(&nd->path, MAY_OPEN, op->open_flag); if (error) goto out2; file->f_path.mnt = nd->path.mnt; @@ -3975,7 +3976,28 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname return sys_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0); } -/* +/** + * vfs_rename - rename a filesystem object + * @old_dir: parent of source + * @old_dentry: source + * @new_dir: parent of destination + * @new_dentry: destination + * @delegated_inode: returns an inode needing a delegation break + * @flags: rename flags + * + * The caller must hold multiple mutexes--see lock_rename()). + * + * If vfs_rename discovers a delegation in need of breaking at either + * the source or destination, it will return -EWOULDBLOCK and return a + * reference to the inode in delegated_inode. The caller should then + * break the delegation and retry. Because breaking a delegation may + * take a long time, the caller should drop all locks before doing + * so. + * + * Alternatively, a caller may pass NULL for delegated_inode. This may + * be appropriate for callers that expect the underlying filesystem not + * to be NFS exported. + * * The worst of all namespace operations - renaming directory. "Perverted" * doesn't even start to describe it. Somebody in UCB had a heck of a trip... * Problems: @@ -4003,163 +4025,140 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname * ->i_mutex on parents, which works but leads to some truly excessive * locking]. */ -static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry) +int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + struct inode **delegated_inode, unsigned int flags) { - int error = 0; + 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; + if (source == target) + return 0; + + error = may_delete(old_dir, old_dentry, is_dir); + if (error) + return error; + + if (!target) { + error = may_create(new_dir, new_dentry); + } else { + new_is_dir = d_is_dir(new_dentry); + + if (!(flags & RENAME_EXCHANGE)) + error = may_delete(new_dir, new_dentry, is_dir); + else + error = may_delete(new_dir, new_dentry, new_is_dir); + } + if (error) + return error; + + if (!old_dir->i_op->rename && !old_dir->i_op->rename2) + return -EPERM; + + if (flags && !old_dir->i_op->rename2) + return -EINVAL; + /* * If we are going to change the parent - check write permissions, * we'll need to flip '..'. */ if (new_dir != old_dir) { - error = inode_permission(old_dentry->d_inode, MAY_WRITE); - if (error) - return error; + if (is_dir) { + error = inode_permission(source, MAY_WRITE); + if (error) + return error; + } + if ((flags & RENAME_EXCHANGE) && new_is_dir) { + error = inode_permission(target, MAY_WRITE); + if (error) + return error; + } } - error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry); + error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry, + flags); if (error) return error; + old_name = fsnotify_oldname_init(old_dentry->d_name.name); dget(new_dentry); - if (target) + if (!is_dir || (flags & RENAME_EXCHANGE)) + lock_two_nondirectories(source, target); + else if (target) mutex_lock(&target->i_mutex); error = -EBUSY; if (d_mountpoint(old_dentry) || d_mountpoint(new_dentry)) goto out; - error = -EMLINK; - if (max_links && !target && new_dir != old_dir && - new_dir->i_nlink >= max_links) - goto out; - - if (target) + if (max_links && new_dir != old_dir) { + error = -EMLINK; + if (is_dir && !new_is_dir && new_dir->i_nlink >= max_links) + goto out; + if ((flags & RENAME_EXCHANGE) && !is_dir && new_is_dir && + old_dir->i_nlink >= max_links) + goto out; + } + if (is_dir && !(flags & RENAME_EXCHANGE) && target) shrink_dcache_parent(new_dentry); - error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry); - if (error) - goto out; - - if (target) { - target->i_flags |= S_DEAD; - dont_mount(new_dentry); + if (!is_dir) { + error = try_break_deleg(source, delegated_inode); + if (error) + goto out; } -out: - if (target) - mutex_unlock(&target->i_mutex); - dput(new_dentry); - if (!error) - if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) - d_move(old_dentry,new_dentry); - return error; -} - -static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - struct inode **delegated_inode) -{ - struct inode *target = new_dentry->d_inode; - struct inode *source = old_dentry->d_inode; - int error; - - error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry); - if (error) - return error; - - dget(new_dentry); - lock_two_nondirectories(source, target); - - error = -EBUSY; - if (d_mountpoint(old_dentry)||d_mountpoint(new_dentry)) - goto out; - - error = try_break_deleg(source, delegated_inode); - if (error) - goto out; - if (target) { + if (target && !new_is_dir) { error = try_break_deleg(target, delegated_inode); if (error) goto out; } - error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry); + if (!old_dir->i_op->rename2) { + error = old_dir->i_op->rename(old_dir, old_dentry, + new_dir, new_dentry); + } else { + WARN_ON(old_dir->i_op->rename != NULL); + error = old_dir->i_op->rename2(old_dir, old_dentry, + new_dir, new_dentry, flags); + } if (error) goto out; - if (target) + if (!(flags & RENAME_EXCHANGE) && target) { + if (is_dir) + target->i_flags |= S_DEAD; dont_mount(new_dentry); - if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) - d_move(old_dentry, new_dentry); + } + if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) { + if (!(flags & RENAME_EXCHANGE)) + d_move(old_dentry, new_dentry); + else + d_exchange(old_dentry, new_dentry); + } out: - unlock_two_nondirectories(source, target); + if (!is_dir || (flags & RENAME_EXCHANGE)) + unlock_two_nondirectories(source, target); + else if (target) + mutex_unlock(&target->i_mutex); dput(new_dentry); - return error; -} - -/** - * vfs_rename - rename a filesystem object - * @old_dir: parent of source - * @old_dentry: source - * @new_dir: parent of destination - * @new_dentry: destination - * @delegated_inode: returns an inode needing a delegation break - * - * The caller must hold multiple mutexes--see lock_rename()). - * - * If vfs_rename discovers a delegation in need of breaking at either - * the source or destination, it will return -EWOULDBLOCK and return a - * reference to the inode in delegated_inode. The caller should then - * break the delegation and retry. Because breaking a delegation may - * take a long time, the caller should drop all locks before doing - * so. - * - * Alternatively, a caller may pass NULL for delegated_inode. This may - * be appropriate for callers that expect the underlying filesystem not - * to be NFS exported. - */ -int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - struct inode **delegated_inode) -{ - int error; - int is_dir = d_is_dir(old_dentry); - const unsigned char *old_name; - - if (old_dentry->d_inode == new_dentry->d_inode) - return 0; - - error = may_delete(old_dir, old_dentry, is_dir); - if (error) - return error; - - if (!new_dentry->d_inode) - error = may_create(new_dir, new_dentry); - else - error = may_delete(new_dir, new_dentry, is_dir); - if (error) - return error; - - if (!old_dir->i_op->rename) - return -EPERM; - - old_name = fsnotify_oldname_init(old_dentry->d_name.name); - - if (is_dir) - error = vfs_rename_dir(old_dir,old_dentry,new_dir,new_dentry); - else - error = vfs_rename_other(old_dir,old_dentry,new_dir,new_dentry,delegated_inode); - if (!error) + if (!error) { fsnotify_move(old_dir, new_dir, old_name, is_dir, - new_dentry->d_inode, old_dentry); + !(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); return error; } -SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, - int, newdfd, const char __user *, newname) +SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname, + int, newdfd, const char __user *, newname, unsigned int, flags) { struct dentry *old_dir, *new_dir; struct dentry *old_dentry, *new_dentry; @@ -4171,6 +4170,17 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, unsigned int lookup_flags = 0; bool should_retry = false; int error; + + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) + return -EINVAL; + + if ((flags & (RENAME_NOREPLACE | RENAME_WHITEOUT)) && + (flags & RENAME_EXCHANGE)) + return -EINVAL; + + if ((flags & RENAME_WHITEOUT) && !capable(CAP_MKNOD)) + return -EPERM; + retry: from = user_path_parent(olddfd, oldname, &oldnd, lookup_flags); if (IS_ERR(from)) { @@ -4194,6 +4204,8 @@ retry: goto exit2; new_dir = newnd.path.dentry; + if (flags & RENAME_NOREPLACE) + error = -EEXIST; if (newnd.last_type != LAST_NORM) goto exit2; @@ -4203,7 +4215,8 @@ retry: oldnd.flags &= ~LOOKUP_PARENT; newnd.flags &= ~LOOKUP_PARENT; - newnd.flags |= LOOKUP_RENAME_TARGET; + if (!(flags & RENAME_EXCHANGE)) + newnd.flags |= LOOKUP_RENAME_TARGET; retry_deleg: trap = lock_rename(new_dir, old_dir); @@ -4216,34 +4229,49 @@ retry_deleg: error = -ENOENT; if (d_is_negative(old_dentry)) goto exit4; + new_dentry = lookup_hash(&newnd); + error = PTR_ERR(new_dentry); + if (IS_ERR(new_dentry)) + goto exit4; + error = -EEXIST; + if ((flags & RENAME_NOREPLACE) && d_is_positive(new_dentry)) + goto exit5; + if (flags & RENAME_EXCHANGE) { + error = -ENOENT; + if (d_is_negative(new_dentry)) + goto exit5; + + if (!d_is_dir(new_dentry)) { + error = -ENOTDIR; + if (newnd.last.name[newnd.last.len]) + goto exit5; + } + } /* unless the source is a directory trailing slashes give -ENOTDIR */ if (!d_is_dir(old_dentry)) { error = -ENOTDIR; if (oldnd.last.name[oldnd.last.len]) - goto exit4; - if (newnd.last.name[newnd.last.len]) - goto exit4; + goto exit5; + if (!(flags & RENAME_EXCHANGE) && newnd.last.name[newnd.last.len]) + goto exit5; } /* source should not be ancestor of target */ error = -EINVAL; if (old_dentry == trap) - goto exit4; - new_dentry = lookup_hash(&newnd); - error = PTR_ERR(new_dentry); - if (IS_ERR(new_dentry)) - goto exit4; + goto exit5; /* target should not be an ancestor of source */ - error = -ENOTEMPTY; + if (!(flags & RENAME_EXCHANGE)) + error = -ENOTEMPTY; if (new_dentry == trap) goto exit5; error = security_path_rename(&oldnd.path, old_dentry, - &newnd.path, new_dentry); + &newnd.path, new_dentry, flags); if (error) goto exit5; error = vfs_rename(old_dir->d_inode, old_dentry, - new_dir->d_inode, new_dentry, - &delegated_inode); + new_dir->d_inode, new_dentry, + &delegated_inode, flags); exit5: dput(new_dentry); exit4: @@ -4273,16 +4301,34 @@ exit: return error; } +SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, + int, newdfd, const char __user *, newname) +{ + return sys_renameat2(olddfd, oldname, newdfd, newname, 0); +} + SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname) { - return sys_renameat(AT_FDCWD, oldname, AT_FDCWD, newname); + return sys_renameat2(AT_FDCWD, oldname, AT_FDCWD, newname, 0); } -int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen, const char *link) +int vfs_whiteout(struct inode *dir, struct dentry *dentry) { - int len; + int error = may_create(dir, dentry); + if (error) + return error; - len = PTR_ERR(link); + if (!dir->i_op->mknod) + return -EPERM; + + return dir->i_op->mknod(dir, dentry, + S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); +} +EXPORT_SYMBOL(vfs_whiteout); + +int readlink_copy(char __user *buffer, int buflen, const char *link) +{ + int len = PTR_ERR(link); if (IS_ERR(link)) goto out; @@ -4311,7 +4357,7 @@ int generic_readlink(struct dentry *dentry, char __user *buffer, int buflen) if (IS_ERR(cookie)) return PTR_ERR(cookie); - res = vfs_readlink(dentry, buffer, buflen, nd_get_link(&nd)); + res = readlink_copy(buffer, buflen, nd_get_link(&nd)); if (dentry->d_inode->i_op->put_link) dentry->d_inode->i_op->put_link(dentry, &nd, cookie); return res; @@ -4335,8 +4381,7 @@ static char *page_getlink(struct dentry * dentry, struct page **ppage) int page_readlink(struct dentry *dentry, char __user *buffer, int buflen) { struct page *page = NULL; - char *s = page_getlink(dentry, &page); - int res = vfs_readlink(dentry,buffer,buflen,s); + int res = readlink_copy(buffer, buflen, page_getlink(dentry, &page)); if (page) { kunmap(page); page_cache_release(page); @@ -4432,7 +4477,6 @@ EXPORT_SYMBOL(vfs_link); EXPORT_SYMBOL(vfs_mkdir); EXPORT_SYMBOL(vfs_mknod); EXPORT_SYMBOL(generic_permission); -EXPORT_SYMBOL(vfs_readlink); EXPORT_SYMBOL(vfs_rename); EXPORT_SYMBOL(vfs_rmdir); EXPORT_SYMBOL(vfs_symlink); diff --git a/fs/namespace.c b/fs/namespace.c index 75536db4b69b..c6533ce9cdee 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1295,6 +1295,8 @@ void umount_tree(struct mount *mnt, int how) } if (last) { last->mnt_hash.next = unmounted.first; + if (unmounted.first) + unmounted.first->pprev = &last->mnt_hash.next; unmounted.first = tmp_list.first; unmounted.first->pprev = &unmounted.first; } @@ -1365,6 +1367,8 @@ static int do_umount(struct mount *mnt, int flags) * Special case for "unmounting" root ... * we just try to remount it readonly. */ + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; down_write(&sb->s_umount); if (!(sb->s_flags & MS_RDONLY)) retval = do_remount_sb(sb, MS_RDONLY, NULL, 0); @@ -1437,6 +1441,9 @@ SYSCALL_DEFINE2(umount, char __user *, name, int, flags) goto dput_and_out; if (mnt->mnt.mnt_flags & MNT_LOCKED) goto dput_and_out; + retval = -EPERM; + if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN)) + goto dput_and_out; retval = do_umount(mnt, flags); dput_and_out: @@ -1579,6 +1586,33 @@ void drop_collected_mounts(struct vfsmount *mnt) namespace_unlock(); } +/** + * clone_private_mount - create a private clone of a path + * + * This creates a new vfsmount, which will be the clone of @path. The new will + * not be attached anywhere in the namespace and will be private (i.e. changes + * to the originating mount won't be propagated into this). + * + * Release with mntput(). + */ +struct vfsmount *clone_private_mount(struct path *path) +{ + struct mount *old_mnt = real_mount(path->mnt); + struct mount *new_mnt; + + if (IS_MNT_UNBINDABLE(old_mnt)) + return ERR_PTR(-EINVAL); + + down_read(&namespace_sem); + new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE); + up_read(&namespace_sem); + if (IS_ERR(new_mnt)) + return ERR_CAST(new_mnt); + + return &new_mnt->mnt; +} +EXPORT_SYMBOL_GPL(clone_private_mount); + int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg, struct vfsmount *root) { @@ -1962,7 +1996,13 @@ static int do_remount(struct path *path, int flags, int mnt_flags, } if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) && !(mnt_flags & MNT_NODEV)) { - return -EPERM; + /* Was the nodev implicitly added in mount? */ + if ((mnt->mnt_ns->user_ns != &init_user_ns) && + !(sb->s_type->fs_flags & FS_USERNS_DEV_MOUNT)) { + mnt_flags |= MNT_NODEV; + } else { + return -EPERM; + } } if ((mnt->mnt.mnt_flags & MNT_LOCK_NOSUID) && !(mnt_flags & MNT_NOSUID)) { @@ -2829,6 +2869,9 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, /* make sure we can reach put_old from new_root */ if (!is_path_reachable(old_mnt, old.dentry, &new)) goto out4; + /* make certain new is below the root */ + if (!is_path_reachable(new_mnt, new.dentry, &root)) + goto out4; root_mp->m_count++; /* pin it so it won't go away */ lock_mount_hash(); detach_mnt(new_mnt, &parent_path); diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c index 60426ccb3b65..2f970de02b16 100644 --- a/fs/ncpfs/ioctl.c +++ b/fs/ncpfs/ioctl.c @@ -448,7 +448,6 @@ static long __ncp_ioctl(struct inode *inode, unsigned int cmd, unsigned long arg result = -EIO; } } - result = 0; } mutex_unlock(&server->root_setup_lock); diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 56ff823ca82e..65d849bdf77a 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -1213,7 +1213,7 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx) end = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE); if (end != NFS_I(inode)->npages) { rcu_read_lock(); - end = radix_tree_next_hole(&mapping->page_tree, idx + 1, ULONG_MAX); + end = page_cache_next_hole(mapping, idx + 1, ULONG_MAX); rcu_read_unlock(); } diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 073b4cf67ed9..0a2016bd6e58 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -128,22 +128,24 @@ nfs41_callback_svc(void *vrqstp) if (try_to_freeze()) continue; - prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE); + prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_UNINTERRUPTIBLE); spin_lock_bh(&serv->sv_cb_lock); if (!list_empty(&serv->sv_cb_list)) { req = list_first_entry(&serv->sv_cb_list, struct rpc_rqst, rq_bc_list); list_del(&req->rq_bc_list); spin_unlock_bh(&serv->sv_cb_lock); + finish_wait(&serv->sv_cb_waitq, &wq); dprintk("Invoking bc_svc_process()\n"); error = bc_svc_process(serv, req, rqstp); dprintk("bc_svc_process() returned w/ error code= %d\n", error); } else { spin_unlock_bh(&serv->sv_cb_lock); - schedule(); + /* schedule_timeout to game the hung task watchdog */ + schedule_timeout(60 * HZ); + finish_wait(&serv->sv_cb_waitq, &wq); } - finish_wait(&serv->sv_cb_waitq, &wq); } return 0; } diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index f4ccfe6521ec..02f8d09e119f 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -464,8 +464,10 @@ static __be32 decode_cb_sequence_args(struct svc_rqst *rqstp, for (i = 0; i < args->csa_nrclists; i++) { status = decode_rc_list(xdr, &args->csa_rclists[i]); - if (status) + if (status) { + args->csa_nrclists = i; goto out_free; + } } } status = 0; diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 5d8ccecf5f5c..2ea3537b8bde 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -109,6 +109,8 @@ again: continue; if (!test_bit(NFS_DELEGATED_STATE, &state->flags)) continue; + if (!nfs4_valid_open_stateid(state)) + continue; if (!nfs4_stateid_match(&state->stateid, stateid)) continue; get_nfs_open_context(ctx); @@ -159,8 +161,8 @@ void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, &delegation->flags); NFS_I(inode)->delegation_state = delegation->type; spin_unlock(&delegation->lock); - put_rpccred(oldcred); rcu_read_unlock(); + put_rpccred(oldcred); trace_nfs4_reclaim_delegation(inode, res->delegation_type); } else { /* We appear to have raced with a delegation return. */ @@ -177,7 +179,11 @@ static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation * { int res = 0; - res = nfs4_proc_delegreturn(inode, delegation->cred, &delegation->stateid, issync); + if (!test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) + res = nfs4_proc_delegreturn(inode, + delegation->cred, + &delegation->stateid, + issync); nfs_free_delegation(delegation); return res; } @@ -364,11 +370,13 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation { struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; struct nfs_inode *nfsi = NFS_I(inode); - int err; + int err = 0; if (delegation == NULL) return 0; do { + if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) + break; err = nfs_delegation_claim_opens(inode, &delegation->stateid); if (!issync || err != -EAGAIN) break; @@ -589,10 +597,23 @@ static void nfs_client_mark_return_unused_delegation_types(struct nfs_client *cl rcu_read_unlock(); } +static void nfs_revoke_delegation(struct inode *inode) +{ + struct nfs_delegation *delegation; + rcu_read_lock(); + delegation = rcu_dereference(NFS_I(inode)->delegation); + if (delegation != NULL) { + set_bit(NFS_DELEGATION_REVOKED, &delegation->flags); + nfs_mark_return_delegation(NFS_SERVER(inode), delegation); + } + rcu_read_unlock(); +} + void nfs_remove_bad_delegation(struct inode *inode) { struct nfs_delegation *delegation; + nfs_revoke_delegation(inode); delegation = nfs_inode_detach_delegation(inode); if (delegation) { nfs_inode_find_state_and_recover(inode, &delegation->stateid); diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index 9a79c7a99d6d..e02b090ab9da 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -31,6 +31,7 @@ enum { NFS_DELEGATION_RETURN_IF_CLOSED, NFS_DELEGATION_REFERENCED, NFS_DELEGATION_RETURNING, + NFS_DELEGATION_REVOKED, }; int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index b8797ae6831f..7ececa1c6c4f 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -123,6 +123,12 @@ static inline int put_dreq(struct nfs_direct_req *dreq) */ ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t pos, unsigned long nr_segs) { + struct inode *inode = iocb->ki_filp->f_mapping->host; + + /* we only support swap file calling nfs_direct_IO */ + if (!IS_SWAPFILE(inode)) + return 0; + #ifndef CONFIG_NFS_SWAP dprintk("NFS: nfs_direct_IO (%pD) off/no(%Ld/%lu) EINVAL\n", iocb->ki_filp, (long long) pos, nr_segs); @@ -178,6 +184,7 @@ static void nfs_direct_req_free(struct kref *kref) { struct nfs_direct_req *dreq = container_of(kref, struct nfs_direct_req, kref); + nfs_free_pnfs_ds_cinfo(&dreq->ds_cinfo); if (dreq->l_ctx != NULL) nfs_put_lock_context(dreq->l_ctx); if (dreq->ctx != NULL) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 15f9d98627a4..6659ce545f15 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -592,7 +592,7 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) { struct inode *inode = dentry->d_inode; int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME; - int err; + int err = 0; trace_nfs_getattr_enter(inode); /* Flush out writes to the server in order to update c/mtime. */ diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 0e46d3d1b6cc..d3f606255b99 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -482,6 +482,16 @@ int nfs40_walk_client_list(struct nfs_client *new, spin_lock(&nn->nfs_client_lock); list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) { + + if (pos->rpc_ops != new->rpc_ops) + continue; + + if (pos->cl_proto != new->cl_proto) + continue; + + if (pos->cl_minorversion != new->cl_minorversion) + continue; + /* If "pos" isn't marked ready, we can't trust the * remaining fields in "pos" */ if (pos->cl_cons_state > NFS_CS_READY) { @@ -501,15 +511,6 @@ int nfs40_walk_client_list(struct nfs_client *new, if (pos->cl_cons_state != NFS_CS_READY) continue; - if (pos->rpc_ops != new->rpc_ops) - continue; - - if (pos->cl_proto != new->cl_proto) - continue; - - if (pos->cl_minorversion != new->cl_minorversion) - continue; - if (pos->cl_clientid != new->cl_clientid) continue; @@ -564,20 +565,14 @@ static bool nfs4_match_clientids(struct nfs_client *a, struct nfs_client *b) } /* - * Returns true if the server owners match + * Returns true if the server major ids match */ static bool -nfs4_match_serverowners(struct nfs_client *a, struct nfs_client *b) +nfs4_check_clientid_trunking(struct nfs_client *a, struct nfs_client *b) { struct nfs41_server_owner *o1 = a->cl_serverowner; struct nfs41_server_owner *o2 = b->cl_serverowner; - if (o1->minor_id != o2->minor_id) { - dprintk("NFS: --> %s server owner minor IDs do not match\n", - __func__); - return false; - } - if (o1->major_id_sz != o2->major_id_sz) goto out_major_mismatch; if (memcmp(o1->major_id, o2->major_id, o1->major_id_sz) != 0) @@ -615,6 +610,16 @@ int nfs41_walk_client_list(struct nfs_client *new, spin_lock(&nn->nfs_client_lock); list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) { + + if (pos->rpc_ops != new->rpc_ops) + continue; + + if (pos->cl_proto != new->cl_proto) + continue; + + if (pos->cl_minorversion != new->cl_minorversion) + continue; + /* If "pos" isn't marked ready, we can't trust the * remaining fields in "pos", especially the client * ID and serverowner fields. Wait for CREATE_SESSION @@ -628,7 +633,7 @@ int nfs41_walk_client_list(struct nfs_client *new, prev = pos; status = nfs_wait_client_init_complete(pos); - if (status == 0) { + if (pos->cl_cons_state == NFS_CS_SESSION_INITING) { nfs4_schedule_lease_recovery(pos); status = nfs4_wait_clnt_recover(pos); } @@ -640,19 +645,15 @@ int nfs41_walk_client_list(struct nfs_client *new, if (pos->cl_cons_state != NFS_CS_READY) continue; - if (pos->rpc_ops != new->rpc_ops) - continue; - - if (pos->cl_proto != new->cl_proto) - continue; - - if (pos->cl_minorversion != new->cl_minorversion) - continue; - if (!nfs4_match_clientids(pos, new)) continue; - if (!nfs4_match_serverowners(pos, new)) + /* + * Note that session trunking is just a special subcase of + * client id trunking. In either case, we want to fall back + * to using the existing nfs_client. + */ + if (!nfs4_check_clientid_trunking(pos, new)) continue; atomic_inc(&pos->cl_count); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 17f91a72840b..58258ad50d5f 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1587,7 +1587,7 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct nfs_inode_find_state_and_recover(state->inode, stateid); nfs4_schedule_stateid_recovery(server, state); - return 0; + return -EAGAIN; case -NFS4ERR_DELAY: case -NFS4ERR_GRACE: set_bit(NFS_DELEGATED_STATE, &state->flags); @@ -2034,46 +2034,60 @@ static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *sta return ret; } +static void nfs_finish_clear_delegation_stateid(struct nfs4_state *state) +{ + nfs_remove_bad_delegation(state->inode); + write_seqlock(&state->seqlock); + nfs4_stateid_copy(&state->stateid, &state->open_stateid); + write_sequnlock(&state->seqlock); + clear_bit(NFS_DELEGATED_STATE, &state->flags); +} + +static void nfs40_clear_delegation_stateid(struct nfs4_state *state) +{ + if (rcu_access_pointer(NFS_I(state->inode)->delegation) != NULL) + nfs_finish_clear_delegation_stateid(state); +} + +static int nfs40_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state) +{ + /* NFSv4.0 doesn't allow for delegation recovery on open expire */ + nfs40_clear_delegation_stateid(state); + return nfs4_open_expired(sp, state); +} + #if defined(CONFIG_NFS_V4_1) -static void nfs41_clear_delegation_stateid(struct nfs4_state *state) +static void nfs41_check_delegation_stateid(struct nfs4_state *state) { struct nfs_server *server = NFS_SERVER(state->inode); - nfs4_stateid *stateid = &state->stateid; + nfs4_stateid stateid; struct nfs_delegation *delegation; - struct rpc_cred *cred = NULL; - int status = -NFS4ERR_BAD_STATEID; - - /* If a state reset has been done, test_stateid is unneeded */ - if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0) - return; + struct rpc_cred *cred; + int status; /* Get the delegation credential for use by test/free_stateid */ rcu_read_lock(); delegation = rcu_dereference(NFS_I(state->inode)->delegation); - if (delegation != NULL && - nfs4_stateid_match(&delegation->stateid, stateid)) { - cred = get_rpccred(delegation->cred); - rcu_read_unlock(); - status = nfs41_test_stateid(server, stateid, cred); - trace_nfs4_test_delegation_stateid(state, NULL, status); - } else + if (delegation == NULL) { rcu_read_unlock(); + return; + } + + nfs4_stateid_copy(&stateid, &delegation->stateid); + cred = get_rpccred(delegation->cred); + rcu_read_unlock(); + status = nfs41_test_stateid(server, &stateid, cred); + trace_nfs4_test_delegation_stateid(state, NULL, status); if (status != NFS_OK) { /* Free the stateid unless the server explicitly * informs us the stateid is unrecognized. */ if (status != -NFS4ERR_BAD_STATEID) - nfs41_free_stateid(server, stateid, cred); - nfs_remove_bad_delegation(state->inode); - - write_seqlock(&state->seqlock); - nfs4_stateid_copy(&state->stateid, &state->open_stateid); - write_sequnlock(&state->seqlock); - clear_bit(NFS_DELEGATED_STATE, &state->flags); + nfs41_free_stateid(server, &stateid, cred); + nfs_finish_clear_delegation_stateid(state); } - if (cred != NULL) - put_rpccred(cred); + put_rpccred(cred); } /** @@ -2117,7 +2131,7 @@ static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *st { int status; - nfs41_clear_delegation_stateid(state); + nfs41_check_delegation_stateid(state); status = nfs41_check_open_stateid(state); if (status != NFS_OK) status = nfs4_open_expired(sp, state); @@ -2558,23 +2572,23 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) is_rdwr = test_bit(NFS_O_RDWR_STATE, &state->flags); is_rdonly = test_bit(NFS_O_RDONLY_STATE, &state->flags); is_wronly = test_bit(NFS_O_WRONLY_STATE, &state->flags); - /* Calculate the current open share mode */ - calldata->arg.fmode = 0; - if (is_rdonly || is_rdwr) - calldata->arg.fmode |= FMODE_READ; - if (is_wronly || is_rdwr) - calldata->arg.fmode |= FMODE_WRITE; /* Calculate the change in open mode */ + calldata->arg.fmode = 0; if (state->n_rdwr == 0) { - if (state->n_rdonly == 0) { - call_close |= is_rdonly || is_rdwr; - calldata->arg.fmode &= ~FMODE_READ; - } - if (state->n_wronly == 0) { - call_close |= is_wronly || is_rdwr; - calldata->arg.fmode &= ~FMODE_WRITE; - } - } + if (state->n_rdonly == 0) + call_close |= is_rdonly; + else if (is_rdonly) + calldata->arg.fmode |= FMODE_READ; + if (state->n_wronly == 0) + call_close |= is_wronly; + else if (is_wronly) + calldata->arg.fmode |= FMODE_WRITE; + } else if (is_rdwr) + calldata->arg.fmode |= FMODE_READ|FMODE_WRITE; + + if (calldata->arg.fmode == 0) + call_close |= is_rdwr; + if (!nfs4_valid_open_stateid(state)) call_close = 0; spin_unlock(&state->owner->so_lock); @@ -7242,7 +7256,7 @@ static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cr int ret = 0; if ((renew_flags & NFS4_RENEW_TIMEOUT) == 0) - return 0; + return -EAGAIN; task = _nfs41_proc_sequence(clp, cred, false); if (IS_ERR(task)) ret = PTR_ERR(task); @@ -7575,6 +7589,9 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) dprintk("--> %s\n", __func__); + /* nfs4_layoutget_release calls pnfs_put_layout_hdr */ + pnfs_get_layout_hdr(NFS_I(inode)->layout); + lgp->args.layout.pages = nfs4_alloc_pages(max_pages, gfp_flags); if (!lgp->args.layout.pages) { nfs4_layoutget_release(lgp); @@ -7587,9 +7604,6 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) lgp->res.seq_res.sr_slot = NULL; nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0); - /* nfs4_layoutget_release calls pnfs_put_layout_hdr */ - pnfs_get_layout_hdr(NFS_I(inode)->layout); - task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return ERR_CAST(task); @@ -8255,7 +8269,7 @@ static const struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = { static const struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = { .owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE, .state_flag_bit = NFS_STATE_RECLAIM_NOGRACE, - .recover_open = nfs4_open_expired, + .recover_open = nfs40_open_expired, .recover_lock = nfs4_lock_expired, .establish_clid = nfs4_init_clientid, }; diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c index 1720d32ffa54..e1ba58c3d1ad 100644 --- a/fs/nfs/nfs4renewd.c +++ b/fs/nfs/nfs4renewd.c @@ -88,10 +88,18 @@ nfs4_renew_state(struct work_struct *work) } nfs_expire_all_delegations(clp); } else { + int ret; + /* Queue an asynchronous RENEW. */ - ops->sched_state_renewal(clp, cred, renew_flags); + ret = ops->sched_state_renewal(clp, cred, renew_flags); put_rpccred(cred); - goto out_exp; + switch (ret) { + default: + goto out_exp; + case -EAGAIN: + case -ENOMEM: + break; + } } } else { dprintk("%s: failed to call renewd. Reason: lease not expired \n", diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 27f5f858502b..b4f177f1d405 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1732,7 +1732,8 @@ restart: if (status < 0) { set_bit(ops->owner_flag_bit, &sp->so_flags); nfs4_put_state_owner(sp); - return nfs4_recovery_handle_error(clp, status); + status = nfs4_recovery_handle_error(clp, status); + return (status != 0) ? status : -EAGAIN; } nfs4_put_state_owner(sp); @@ -1741,7 +1742,7 @@ restart: spin_unlock(&clp->cl_lock); } rcu_read_unlock(); - return status; + return 0; } static int nfs4_check_lease(struct nfs_client *clp) @@ -1788,7 +1789,6 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status) break; case -NFS4ERR_STALE_CLIENTID: clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); - nfs4_state_clear_reclaim_reboot(clp); nfs4_state_start_reclaim_reboot(clp); break; case -NFS4ERR_CLID_INUSE: @@ -2370,6 +2370,7 @@ static void nfs4_state_manager(struct nfs_client *clp) status = nfs4_check_lease(clp); if (status < 0) goto out_error; + continue; } if (test_and_clear_bit(NFS4CLNT_MOVED, &clp->cl_state)) { @@ -2391,14 +2392,11 @@ static void nfs4_state_manager(struct nfs_client *clp) section = "reclaim reboot"; status = nfs4_do_reclaim(clp, clp->cl_mvops->reboot_recovery_ops); - if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) || - test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state)) - continue; - nfs4_state_end_reclaim_reboot(clp); - if (test_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state)) + if (status == -EAGAIN) continue; if (status < 0) goto out_error; + nfs4_state_end_reclaim_reboot(clp); } /* Now recover expired state... */ @@ -2406,9 +2404,7 @@ static void nfs4_state_manager(struct nfs_client *clp) section = "reclaim nograce"; status = nfs4_do_reclaim(clp, clp->cl_mvops->nograce_recovery_ops); - if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) || - test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) || - test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state)) + if (status == -EAGAIN) continue; if (status < 0) goto out_error; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 2ffebf2081ce..27d7f2742592 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -113,7 +113,7 @@ __nfs_iocounter_wait(struct nfs_io_counter *c) if (atomic_read(&c->io_count) == 0) break; ret = nfs_wait_bit_killable(&c->flags); - } while (atomic_read(&c->io_count) != 0); + } while (atomic_read(&c->io_count) != 0 && !ret); finish_wait(wq, &q.wait); return ret; } diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index cc8c5b32043c..f42bbe5fbc0a 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -784,8 +784,12 @@ static bool nfsd41_cb_get_slot(struct nfs4_client *clp, struct rpc_task *task) { if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) { rpc_sleep_on(&clp->cl_cb_waitq, task, NULL); - dprintk("%s slot is busy\n", __func__); - return false; + /* Race breaker */ + if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) { + dprintk("%s slot is busy\n", __func__); + return false; + } + rpc_wake_up_queued_task(&clp->cl_cb_waitq, task); } return true; } diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index f23a6ca37504..86f5d3e474bf 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1243,7 +1243,8 @@ static bool need_wrongsec_check(struct svc_rqst *rqstp) */ if (argp->opcnt == resp->opcnt) return false; - + if (next->opnum == OP_ILLEGAL) + return false; nextd = OPDESC(next); /* * Rest of 2.6.3.1.1: certain operations will return WRONGSEC diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 9c271f42604a..674a5d529e09 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -244,10 +244,11 @@ struct nfs4_dir_ctx { }; static int -nfsd4_build_namelist(void *arg, const char *name, int namlen, +nfsd4_build_namelist(struct dir_context *__ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { - struct nfs4_dir_ctx *ctx = arg; + struct nfs4_dir_ctx *ctx = + container_of(__ctx, struct nfs4_dir_ctx, ctx); struct name_list *entry; if (namlen != HEXDIR_LEN - 1) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 34d2a1f2f400..daa53da1d286 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1209,15 +1209,14 @@ static int copy_cred(struct svc_cred *target, struct svc_cred *source) return 0; } -static long long +static int compare_blob(const struct xdr_netobj *o1, const struct xdr_netobj *o2) { - long long res; - - res = o1->len - o2->len; - if (res) - return res; - return (long long)memcmp(o1->data, o2->data, o1->len); + if (o1->len < o2->len) + return -1; + if (o1->len > o2->len) + return 1; + return memcmp(o1->data, o2->data, o1->len); } static int same_name(const char *n1, const char *n2) @@ -1401,7 +1400,7 @@ add_clp_to_name_tree(struct nfs4_client *new_clp, struct rb_root *root) static struct nfs4_client * find_clp_in_name_tree(struct xdr_netobj *name, struct rb_root *root) { - long long cmp; + int cmp; struct rb_node *node = root->rb_node; struct nfs4_client *clp; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 86573350350e..dd1afa38f2ae 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1809,6 +1809,9 @@ static __be32 nfsd4_encode_components_esc(char sep, char *components, } else end++; + if (found_esc) + end = next; + str = end; } *pp = p; diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index f8f060ffbf4f..6040da8830ff 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -224,13 +224,6 @@ hash_refile(struct svc_cacherep *rp) hlist_add_head(&rp->c_hash, cache_hash + hash_32(rp->c_xid, maskbits)); } -static inline bool -nfsd_cache_entry_expired(struct svc_cacherep *rp) -{ - return rp->c_state != RC_INPROG && - time_after(jiffies, rp->c_timestamp + RC_EXPIRE); -} - /* * Walk the LRU list and prune off entries that are older than RC_EXPIRE. * Also prune the oldest ones when the total exceeds the max number of entries. @@ -242,8 +235,14 @@ prune_cache_entries(void) long freed = 0; list_for_each_entry_safe(rp, tmp, &lru_head, c_lru) { - if (!nfsd_cache_entry_expired(rp) && - num_drc_entries <= max_drc_entries) + /* + * Don't free entries attached to calls that are still + * in-progress, but do keep scanning the list. + */ + if (rp->c_state == RC_INPROG) + continue; + if (num_drc_entries <= max_drc_entries && + time_before(jiffies, rp->c_timestamp + RC_EXPIRE)) break; nfsd_reply_cache_free_locked(rp); freed++; diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 479eb681c27c..f417fef17118 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -328,12 +328,15 @@ void nfsd_lockd_shutdown(void); (NFSD4_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SUPPATTR_EXCLCREAT) #ifdef CONFIG_NFSD_V4_SECURITY_LABEL -#define NFSD4_2_SUPPORTED_ATTRS_WORD2 \ - (NFSD4_1_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SECURITY_LABEL) +#define NFSD4_2_SECURITY_ATTRS FATTR4_WORD2_SECURITY_LABEL #else -#define NFSD4_2_SUPPORTED_ATTRS_WORD2 0 +#define NFSD4_2_SECURITY_ATTRS 0 #endif +#define NFSD4_2_SUPPORTED_ATTRS_WORD2 \ + (NFSD4_1_SUPPORTED_ATTRS_WORD2 | \ + NFSD4_2_SECURITY_ATTRS) + static inline u32 nfsd_suppattrs0(u32 minorversion) { return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD0 diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index eea5ad188984..3953a20db16d 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1703,7 +1703,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry) goto out_dput_new; - host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL); + host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL, 0); if (!host_err) { host_err = commit_metadata(tfhp); if (!host_err) @@ -1808,10 +1808,12 @@ struct readdir_data { int full; }; -static int nfsd_buffered_filldir(void *__buf, const char *name, int namlen, - loff_t offset, u64 ino, unsigned int d_type) +static int nfsd_buffered_filldir(struct dir_context *ctx, const char *name, + int namlen, loff_t offset, u64 ino, + unsigned int d_type) { - struct readdir_data *buf = __buf; + struct readdir_data *buf = + container_of(ctx, struct readdir_data, ctx); struct buffered_dirent *de = (void *)(buf->dirent + buf->used); unsigned int reclen; @@ -1831,7 +1833,7 @@ static int nfsd_buffered_filldir(void *__buf, const char *name, int namlen, return 0; } -static __be32 nfsd_buffered_readdir(struct file *file, filldir_t func, +static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func, struct readdir_cd *cdp, loff_t *offsetp) { struct buffered_dirent *de; @@ -1915,7 +1917,7 @@ static __be32 nfsd_buffered_readdir(struct file *file, filldir_t func, */ __be32 nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, - struct readdir_cd *cdp, filldir_t func) + struct readdir_cd *cdp, nfsd_filldir_t func) { __be32 err; struct file *file; diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index fbe90bdb2214..ea760b17ecbd 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -36,7 +36,7 @@ /* * Callback function for readdir */ -typedef int (*nfsd_dirop_t)(struct inode *, struct dentry *, int, int); +typedef int (*nfsd_filldir_t)(void *, const char *, int, loff_t, u64, unsigned); /* nfsd/vfs.c */ int nfsd_racache_init(int); @@ -89,7 +89,7 @@ __be32 nfsd_rename(struct svc_rqst *, __be32 nfsd_unlink(struct svc_rqst *, struct svc_fh *, int type, char *name, int len); __be32 nfsd_readdir(struct svc_rqst *, struct svc_fh *, - loff_t *, struct readdir_cd *, filldir_t); + loff_t *, struct readdir_cd *, nfsd_filldir_t); __be32 nfsd_statfs(struct svc_rqst *, struct svc_fh *, struct kstatfs *, int access); diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index b2e3ff347620..ecdbae19a766 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -31,6 +31,8 @@ #include "alloc.h" #include "dat.h" +static void __nilfs_btree_init(struct nilfs_bmap *bmap); + static struct nilfs_btree_path *nilfs_btree_alloc_path(void) { struct nilfs_btree_path *path; @@ -368,6 +370,34 @@ static int nilfs_btree_node_broken(const struct nilfs_btree_node *node, return ret; } +/** + * nilfs_btree_root_broken - verify consistency of btree root node + * @node: btree root node to be examined + * @ino: inode number + * + * Return Value: If node is broken, 1 is returned. Otherwise, 0 is returned. + */ +static int nilfs_btree_root_broken(const struct nilfs_btree_node *node, + unsigned long ino) +{ + int level, flags, nchildren; + int ret = 0; + + level = nilfs_btree_node_get_level(node); + flags = nilfs_btree_node_get_flags(node); + nchildren = nilfs_btree_node_get_nchildren(node); + + if (unlikely(level < NILFS_BTREE_LEVEL_NODE_MIN || + level > NILFS_BTREE_LEVEL_MAX || + nchildren < 0 || + nchildren > NILFS_BTREE_ROOT_NCHILDREN_MAX)) { + pr_crit("NILFS: bad btree root (inode number=%lu): level = %d, flags = 0x%x, nchildren = %d\n", + ino, level, flags, nchildren); + ret = 1; + } + return ret; +} + int nilfs_btree_broken_node_block(struct buffer_head *bh) { int ret; @@ -1713,7 +1743,7 @@ nilfs_btree_commit_convert_and_insert(struct nilfs_bmap *btree, /* convert and insert */ dat = NILFS_BMAP_USE_VBN(btree) ? nilfs_bmap_get_dat(btree) : NULL; - nilfs_btree_init(btree); + __nilfs_btree_init(btree); if (nreq != NULL) { nilfs_bmap_commit_alloc_ptr(btree, dreq, dat); nilfs_bmap_commit_alloc_ptr(btree, nreq, dat); @@ -2294,12 +2324,23 @@ static const struct nilfs_bmap_operations nilfs_btree_ops_gc = { .bop_gather_data = NULL, }; -int nilfs_btree_init(struct nilfs_bmap *bmap) +static void __nilfs_btree_init(struct nilfs_bmap *bmap) { bmap->b_ops = &nilfs_btree_ops; bmap->b_nchildren_per_block = NILFS_BTREE_NODE_NCHILDREN_MAX(nilfs_btree_node_size(bmap)); - return 0; +} + +int nilfs_btree_init(struct nilfs_bmap *bmap) +{ + int ret = 0; + + __nilfs_btree_init(bmap); + + if (nilfs_btree_root_broken(nilfs_btree_get_root(bmap), + bmap->b_inode->i_ino)) + ret = -EIO; + return ret; } void nilfs_btree_init_gc(struct nilfs_bmap *bmap) diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 7e350c562e0e..09480c53fd74 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -24,6 +24,7 @@ #include <linux/buffer_head.h> #include <linux/gfp.h> #include <linux/mpage.h> +#include <linux/pagemap.h> #include <linux/writeback.h> #include <linux/aio.h> #include "nilfs.h" @@ -48,6 +49,8 @@ struct nilfs_iget_args { int for_gc; }; +static int nilfs_iget_test(struct inode *inode, void *opaque); + void nilfs_inode_add_blocks(struct inode *inode, int n) { struct nilfs_root *root = NILFS_I(inode)->i_root; @@ -219,10 +222,10 @@ static int nilfs_writepage(struct page *page, struct writeback_control *wbc) static int nilfs_set_page_dirty(struct page *page) { + struct inode *inode = page->mapping->host; int ret = __set_page_dirty_nobuffers(page); if (page_has_buffers(page)) { - struct inode *inode = page->mapping->host; unsigned nr_dirty = 0; struct buffer_head *bh, *head; @@ -245,6 +248,10 @@ static int nilfs_set_page_dirty(struct page *page) if (nr_dirty) nilfs_set_file_dirty(inode, nr_dirty); + } else if (ret) { + unsigned nr_dirty = 1 << (PAGE_CACHE_SHIFT - inode->i_blkbits); + + nilfs_set_file_dirty(inode, nr_dirty); } return ret; } @@ -342,6 +349,17 @@ const struct address_space_operations nilfs_aops = { .is_partially_uptodate = block_is_partially_uptodate, }; +static int nilfs_insert_inode_locked(struct inode *inode, + struct nilfs_root *root, + unsigned long ino) +{ + struct nilfs_iget_args args = { + .ino = ino, .root = root, .cno = 0, .for_gc = 0 + }; + + return insert_inode_locked4(inode, ino, nilfs_iget_test, &args); +} + struct inode *nilfs_new_inode(struct inode *dir, umode_t mode) { struct super_block *sb = dir->i_sb; @@ -377,7 +395,7 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode) if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) { err = nilfs_bmap_read(ii->i_bmap, NULL); if (err < 0) - goto failed_bmap; + goto failed_after_creation; set_bit(NILFS_I_BMAP, &ii->i_state); /* No lock is needed; iget() ensures it. */ @@ -393,21 +411,24 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode) spin_lock(&nilfs->ns_next_gen_lock); inode->i_generation = nilfs->ns_next_generation++; spin_unlock(&nilfs->ns_next_gen_lock); - insert_inode_hash(inode); + if (nilfs_insert_inode_locked(inode, root, ino) < 0) { + err = -EIO; + goto failed_after_creation; + } err = nilfs_init_acl(inode, dir); if (unlikely(err)) - goto failed_acl; /* never occur. When supporting + goto failed_after_creation; /* never occur. When supporting nilfs_init_acl(), proper cancellation of above jobs should be considered */ return inode; - failed_acl: - failed_bmap: + failed_after_creation: clear_nlink(inode); + unlock_new_inode(inode); iput(inode); /* raw_inode will be deleted through - generic_delete_inode() */ + nilfs_evict_inode() */ goto failed; failed_ifile_create_inode: @@ -455,8 +476,8 @@ int nilfs_read_inode_common(struct inode *inode, inode->i_atime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec); inode->i_ctime.tv_nsec = le32_to_cpu(raw_inode->i_ctime_nsec); inode->i_mtime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec); - if (inode->i_nlink == 0 && inode->i_mode == 0) - return -EINVAL; /* this inode is deleted */ + if (inode->i_nlink == 0) + return -ESTALE; /* this inode is deleted */ inode->i_blocks = le64_to_cpu(raw_inode->i_blocks); ii->i_flags = le32_to_cpu(raw_inode->i_flags); diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index 9de78f08989e..0f84b257932c 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -51,9 +51,11 @@ static inline int nilfs_add_nondir(struct dentry *dentry, struct inode *inode) int err = nilfs_add_link(dentry, inode); if (!err) { d_instantiate(dentry, inode); + unlock_new_inode(inode); return 0; } inode_dec_link_count(inode); + unlock_new_inode(inode); iput(inode); return err; } @@ -182,6 +184,7 @@ out: out_fail: drop_nlink(inode); nilfs_mark_inode_dirty(inode); + unlock_new_inode(inode); iput(inode); goto out; } @@ -201,11 +204,15 @@ static int nilfs_link(struct dentry *old_dentry, struct inode *dir, inode_inc_link_count(inode); ihold(inode); - err = nilfs_add_nondir(dentry, inode); - if (!err) + err = nilfs_add_link(dentry, inode); + if (!err) { + d_instantiate(dentry, inode); err = nilfs_transaction_commit(dir->i_sb); - else + } else { + inode_dec_link_count(inode); + iput(inode); nilfs_transaction_abort(dir->i_sb); + } return err; } @@ -243,6 +250,7 @@ static int nilfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) nilfs_mark_inode_dirty(inode); d_instantiate(dentry, inode); + unlock_new_inode(inode); out: if (!err) err = nilfs_transaction_commit(dir->i_sb); @@ -255,6 +263,7 @@ out_fail: drop_nlink(inode); drop_nlink(inode); nilfs_mark_inode_dirty(inode); + unlock_new_inode(inode); iput(inode); out_dir: drop_nlink(dir); diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 9bc72dec3fa6..b02c202223a6 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -141,7 +141,6 @@ enum { * @ti_save: Backup of journal_info field of task_struct * @ti_flags: Flags * @ti_count: Nest level - * @ti_garbage: List of inode to be put when releasing semaphore */ struct nilfs_transaction_info { u32 ti_magic; @@ -150,7 +149,6 @@ struct nilfs_transaction_info { one of other filesystems has a bug. */ unsigned short ti_flags; unsigned short ti_count; - struct list_head ti_garbage; }; /* ti_magic */ diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index a1a191634abc..14538a865102 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -305,7 +305,6 @@ static void nilfs_transaction_lock(struct super_block *sb, ti->ti_count = 0; ti->ti_save = cur_ti; ti->ti_magic = NILFS_TI_MAGIC; - INIT_LIST_HEAD(&ti->ti_garbage); current->journal_info = ti; for (;;) { @@ -332,8 +331,6 @@ static void nilfs_transaction_unlock(struct super_block *sb) up_write(&nilfs->ns_segctor_sem); current->journal_info = ti->ti_save; - if (!list_empty(&ti->ti_garbage)) - nilfs_dispose_list(nilfs, &ti->ti_garbage, 0); } static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci, @@ -746,6 +743,15 @@ static void nilfs_dispose_list(struct the_nilfs *nilfs, } } +static void nilfs_iput_work_func(struct work_struct *work) +{ + struct nilfs_sc_info *sci = container_of(work, struct nilfs_sc_info, + sc_iput_work); + struct the_nilfs *nilfs = sci->sc_super->s_fs_info; + + nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 0); +} + static int nilfs_test_metadata_dirty(struct the_nilfs *nilfs, struct nilfs_root *root) { @@ -1899,8 +1905,9 @@ static int nilfs_segctor_collect_dirty_files(struct nilfs_sc_info *sci, static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci, struct the_nilfs *nilfs) { - struct nilfs_transaction_info *ti = current->journal_info; struct nilfs_inode_info *ii, *n; + int during_mount = !(sci->sc_super->s_flags & MS_ACTIVE); + int defer_iput = false; spin_lock(&nilfs->ns_inode_lock); list_for_each_entry_safe(ii, n, &sci->sc_dirty_files, i_dirty) { @@ -1911,9 +1918,24 @@ static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci, clear_bit(NILFS_I_BUSY, &ii->i_state); brelse(ii->i_bh); ii->i_bh = NULL; - list_move_tail(&ii->i_dirty, &ti->ti_garbage); + list_del_init(&ii->i_dirty); + if (!ii->vfs_inode.i_nlink || during_mount) { + /* + * Defer calling iput() to avoid deadlocks if + * i_nlink == 0 or mount is not yet finished. + */ + list_add_tail(&ii->i_dirty, &sci->sc_iput_queue); + defer_iput = true; + } else { + spin_unlock(&nilfs->ns_inode_lock); + iput(&ii->vfs_inode); + spin_lock(&nilfs->ns_inode_lock); + } } spin_unlock(&nilfs->ns_inode_lock); + + if (defer_iput) + schedule_work(&sci->sc_iput_work); } /* @@ -2580,6 +2602,8 @@ static struct nilfs_sc_info *nilfs_segctor_new(struct super_block *sb, INIT_LIST_HEAD(&sci->sc_segbufs); INIT_LIST_HEAD(&sci->sc_write_logs); INIT_LIST_HEAD(&sci->sc_gc_inodes); + INIT_LIST_HEAD(&sci->sc_iput_queue); + INIT_WORK(&sci->sc_iput_work, nilfs_iput_work_func); init_timer(&sci->sc_timer); sci->sc_interval = HZ * NILFS_SC_DEFAULT_TIMEOUT; @@ -2606,6 +2630,8 @@ static void nilfs_segctor_write_out(struct nilfs_sc_info *sci) ret = nilfs_segctor_construct(sci, SC_LSEG_SR); nilfs_transaction_unlock(sci->sc_super); + flush_work(&sci->sc_iput_work); + } while (ret && retrycount-- > 0); } @@ -2630,6 +2656,9 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) || sci->sc_seq_request != sci->sc_seq_done); spin_unlock(&sci->sc_state_lock); + if (flush_work(&sci->sc_iput_work)) + flag = true; + if (flag || !nilfs_segctor_confirm(sci)) nilfs_segctor_write_out(sci); @@ -2639,6 +2668,12 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) nilfs_dispose_list(nilfs, &sci->sc_dirty_files, 1); } + if (!list_empty(&sci->sc_iput_queue)) { + nilfs_warning(sci->sc_super, __func__, + "iput queue is not empty\n"); + nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 1); + } + WARN_ON(!list_empty(&sci->sc_segbufs)); WARN_ON(!list_empty(&sci->sc_write_logs)); diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h index 38a1d0013314..a48d6de1e02c 100644 --- a/fs/nilfs2/segment.h +++ b/fs/nilfs2/segment.h @@ -26,6 +26,7 @@ #include <linux/types.h> #include <linux/fs.h> #include <linux/buffer_head.h> +#include <linux/workqueue.h> #include <linux/nilfs2_fs.h> #include "nilfs.h" @@ -92,6 +93,8 @@ struct nilfs_segsum_pointer { * @sc_nblk_inc: Block count of current generation * @sc_dirty_files: List of files to be written * @sc_gc_inodes: List of GC inodes having blocks to be written + * @sc_iput_queue: list of inodes for which iput should be done + * @sc_iput_work: work struct to defer iput call * @sc_freesegs: array of segment numbers to be freed * @sc_nfreesegs: number of segments on @sc_freesegs * @sc_dsync_inode: inode whose data pages are written for a sync operation @@ -135,6 +138,8 @@ struct nilfs_sc_info { struct list_head sc_dirty_files; struct list_head sc_gc_inodes; + struct list_head sc_iput_queue; + struct work_struct sc_iput_work; __u64 *sc_freesegs; size_t sc_nfreesegs; diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 287a22c04149..de6323eb0113 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -71,7 +71,7 @@ static int create_fd(struct fsnotify_group *group, pr_debug("%s: group=%p event=%p\n", __func__, group, event); - client_fd = get_unused_fd(); + client_fd = get_unused_fd_flags(group->fanotify_data.f_flags); if (client_fd < 0) return client_fd; diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c index 238a5930cb3c..9d7e2b9659cb 100644 --- a/fs/notify/fdinfo.c +++ b/fs/notify/fdinfo.c @@ -42,7 +42,7 @@ static int show_mark_fhandle(struct seq_file *m, struct inode *inode) { struct { struct file_handle handle; - u8 pad[64]; + u8 pad[MAX_HANDLE_SZ]; } f; int size, ret, i; @@ -50,7 +50,7 @@ static int show_mark_fhandle(struct seq_file *m, struct inode *inode) size = f.handle.handle_bytes >> 2; ret = exportfs_encode_inode_fh(inode, (struct fid *)f.handle.f_handle, &size, 0); - if ((ret == 255) || (ret == -ENOSPC)) { + if ((ret == FILEID_INVALID) || (ret < 0)) { WARN_ONCE(1, "Can't encode file handler for inotify: %d\n", ret); return 0; } diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c index 74825be65b7b..fbb9dfb7b1d2 100644 --- a/fs/notify/inode_mark.c +++ b/fs/notify/inode_mark.c @@ -288,20 +288,25 @@ void fsnotify_unmount_inodes(struct list_head *list) spin_unlock(&inode->i_lock); /* In case the dropping of a reference would nuke next_i. */ - if ((&next_i->i_sb_list != list) && - atomic_read(&next_i->i_count)) { + while (&next_i->i_sb_list != list) { spin_lock(&next_i->i_lock); - if (!(next_i->i_state & (I_FREEING | I_WILL_FREE))) { + if (!(next_i->i_state & (I_FREEING | I_WILL_FREE)) && + atomic_read(&next_i->i_count)) { __iget(next_i); need_iput = next_i; + spin_unlock(&next_i->i_lock); + break; } spin_unlock(&next_i->i_lock); + next_i = list_entry(next_i->i_sb_list.next, + struct inode, i_sb_list); } /* - * We can safely drop inode_sb_list_lock here because we hold - * references on both inode and next_i. Also no new inodes - * will be added since the umount has begun. + * We can safely drop inode_sb_list_lock here because either + * we actually hold references on both inode and next_i or + * end of list. Also no new inodes will be added since the + * umount has begun. */ spin_unlock(&inode_sb_list_lock); diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index a27e3fecefaf..250ed5b20c8f 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -1748,7 +1748,6 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size) if (page) { set_page_dirty(page); unlock_page(page); - mark_page_accessed(page); page_cache_release(page); } ntfs_debug("Done."); diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index db9bd8a31725..86ddab916b66 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2060,7 +2060,6 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, } do { unlock_page(pages[--do_pages]); - mark_page_accessed(pages[do_pages]); page_cache_release(pages[do_pages]); } while (do_pages); if (unlikely(status)) diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index aeb44e879c51..bb6ee06118ca 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -899,7 +899,7 @@ void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages) } } -static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc) +static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc) { int i; @@ -920,7 +920,11 @@ static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc) page_cache_release(wc->w_target_page); } ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages); +} +static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc) +{ + ocfs2_unlock_pages(wc); brelse(wc->w_di_bh); kfree(wc); } @@ -2045,11 +2049,19 @@ out_write_size: di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); ocfs2_journal_dirty(handle, wc->w_di_bh); + /* unlock pages before dealloc since it needs acquiring j_trans_barrier + * lock, or it will cause a deadlock since journal commit threads holds + * this lock and will ask for the page lock when flushing the data. + * put it here to preserve the unlock order. + */ + ocfs2_unlock_pages(wc); + ocfs2_commit_trans(osb, handle); ocfs2_run_deallocs(osb, &wc->w_dealloc); - ocfs2_free_write_ctxt(wc); + brelse(wc->w_di_bh); + kfree(wc); return copied; } diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 91a7e85ac8fd..478e14d7be54 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -2073,10 +2073,12 @@ struct ocfs2_empty_dir_priv { unsigned seen_other; unsigned dx_dir; }; -static int ocfs2_empty_dir_filldir(void *priv, const char *name, int name_len, - loff_t pos, u64 ino, unsigned type) +static int ocfs2_empty_dir_filldir(struct dir_context *ctx, const char *name, + int name_len, loff_t pos, u64 ino, + unsigned type) { - struct ocfs2_empty_dir_priv *p = priv; + struct ocfs2_empty_dir_priv *p = + container_of(ctx, struct ocfs2_empty_dir_priv, ctx); /* * Check the positions of "." and ".." records to be sure diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index af3f7aa73e13..1be3398c96f6 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -650,12 +650,9 @@ void dlm_lockres_clear_refmap_bit(struct dlm_ctxt *dlm, clear_bit(bit, res->refmap); } - -void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm, +static void __dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm, struct dlm_lock_resource *res) { - assert_spin_locked(&res->spinlock); - res->inflight_locks++; mlog(0, "%s: res %.*s, inflight++: now %u, %ps()\n", dlm->name, @@ -663,6 +660,13 @@ void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm, __builtin_return_address(0)); } +void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm, + struct dlm_lock_resource *res) +{ + assert_spin_locked(&res->spinlock); + __dlm_lockres_grab_inflight_ref(dlm, res); +} + void dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm, struct dlm_lock_resource *res) { @@ -852,10 +856,8 @@ lookup: /* finally add the lockres to its hash bucket */ __dlm_insert_lockres(dlm, res); - /* Grab inflight ref to pin the resource */ - spin_lock(&res->spinlock); - dlm_lockres_grab_inflight_ref(dlm, res); - spin_unlock(&res->spinlock); + /* since this lockres is new it doesn't not require the spinlock */ + __dlm_lockres_grab_inflight_ref(dlm, res); /* get an extra ref on the mle in case this is a BLOCK * if so, the creator of the BLOCK may try to put the last diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 51632c40e896..7fe30f655aa5 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2391,10 +2391,14 @@ out_dio: /* buffered aio wouldn't have proper lock coverage today */ BUG_ON(ret == -EIOCBQUEUED && !(file->f_flags & O_DIRECT)); + if (unlikely(written <= 0)) + goto no_sync; + if (((file->f_flags & O_DSYNC) && !direct_io) || IS_SYNC(inode) || ((file->f_flags & O_DIRECT) && !direct_io)) { - ret = filemap_fdatawrite_range(file->f_mapping, *ppos, - *ppos + count - 1); + ret = filemap_fdatawrite_range(file->f_mapping, + iocb->ki_pos - written, + iocb->ki_pos - 1); if (ret < 0) written = ret; @@ -2407,10 +2411,12 @@ out_dio: } if (!ret) - ret = filemap_fdatawait_range(file->f_mapping, *ppos, - *ppos + count - 1); + ret = filemap_fdatawait_range(file->f_mapping, + iocb->ki_pos - written, + iocb->ki_pos - 1); } +no_sync: /* * deep in g_f_a_w_n()->ocfs2_direct_IO we pass in a ocfs2_dio_end_io * function pointer which is called when o_direct io completes so that diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 44fc3e530c3d..a1b7dca075dd 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -1981,10 +1981,12 @@ struct ocfs2_orphan_filldir_priv { struct ocfs2_super *osb; }; -static int ocfs2_orphan_filldir(void *priv, const char *name, int name_len, - loff_t pos, u64 ino, unsigned type) +static int ocfs2_orphan_filldir(struct dir_context *ctx, const char *name, + int name_len, loff_t pos, u64 ino, + unsigned type) { - struct ocfs2_orphan_filldir_priv *p = priv; + struct ocfs2_orphan_filldir_priv *p = + container_of(ctx, struct ocfs2_orphan_filldir_priv, ctx); struct inode *iter; if (name_len == 1 && !strncmp(".", name, 1)) diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index feed025fe064..b2427623dd6c 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -94,6 +94,14 @@ static int ocfs2_create_symlink_data(struct ocfs2_super *osb, struct inode *inode, const char *symname); +static int ocfs2_double_lock(struct ocfs2_super *osb, + struct buffer_head **bh1, + struct inode *inode1, + struct buffer_head **bh2, + struct inode *inode2, + int rename); + +static void ocfs2_double_unlock(struct inode *inode1, struct inode *inode2); /* An orphan dir name is an 8 byte value, printed as a hex string */ #define OCFS2_ORPHAN_NAMELEN ((int)(2 * sizeof(u64))) @@ -656,8 +664,10 @@ static int ocfs2_link(struct dentry *old_dentry, { handle_t *handle; struct inode *inode = old_dentry->d_inode; + struct inode *old_dir = old_dentry->d_parent->d_inode; int err; struct buffer_head *fe_bh = NULL; + struct buffer_head *old_dir_bh = NULL; struct buffer_head *parent_fe_bh = NULL; struct ocfs2_dinode *fe = NULL; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); @@ -674,19 +684,33 @@ static int ocfs2_link(struct dentry *old_dentry, dquot_initialize(dir); - err = ocfs2_inode_lock_nested(dir, &parent_fe_bh, 1, OI_LS_PARENT); + err = ocfs2_double_lock(osb, &old_dir_bh, old_dir, + &parent_fe_bh, dir, 0); if (err < 0) { if (err != -ENOENT) mlog_errno(err); return err; } + /* make sure both dirs have bhs + * get an extra ref on old_dir_bh if old==new */ + if (!parent_fe_bh) { + if (old_dir_bh) { + parent_fe_bh = old_dir_bh; + get_bh(parent_fe_bh); + } else { + mlog(ML_ERROR, "%s: no old_dir_bh!\n", osb->uuid_str); + err = -EIO; + goto out; + } + } + if (!dir->i_nlink) { err = -ENOENT; goto out; } - err = ocfs2_lookup_ino_from_name(dir, old_dentry->d_name.name, + err = ocfs2_lookup_ino_from_name(old_dir, old_dentry->d_name.name, old_dentry->d_name.len, &old_de_ino); if (err) { err = -ENOENT; @@ -779,10 +803,11 @@ out_unlock_inode: ocfs2_inode_unlock(inode, 1); out: - ocfs2_inode_unlock(dir, 1); + ocfs2_double_unlock(old_dir, dir); brelse(fe_bh); brelse(parent_fe_bh); + brelse(old_dir_bh); ocfs2_free_dir_lookup_result(&lookup); @@ -991,14 +1016,15 @@ leave: } /* - * The only place this should be used is rename! + * The only place this should be used is rename and link! * if they have the same id, then the 1st one is the only one locked. */ static int ocfs2_double_lock(struct ocfs2_super *osb, struct buffer_head **bh1, struct inode *inode1, struct buffer_head **bh2, - struct inode *inode2) + struct inode *inode2, + int rename) { int status; struct ocfs2_inode_info *oi1 = OCFS2_I(inode1); @@ -1028,7 +1054,7 @@ static int ocfs2_double_lock(struct ocfs2_super *osb, } /* lock id2 */ status = ocfs2_inode_lock_nested(inode2, bh2, 1, - OI_LS_RENAME1); + rename == 1 ? OI_LS_RENAME1 : OI_LS_PARENT); if (status < 0) { if (status != -ENOENT) mlog_errno(status); @@ -1037,7 +1063,8 @@ static int ocfs2_double_lock(struct ocfs2_super *osb, } /* lock id1 */ - status = ocfs2_inode_lock_nested(inode1, bh1, 1, OI_LS_RENAME2); + status = ocfs2_inode_lock_nested(inode1, bh1, 1, + rename == 1 ? OI_LS_RENAME2 : OI_LS_PARENT); if (status < 0) { /* * An error return must mean that no cluster locks @@ -1137,7 +1164,7 @@ static int ocfs2_rename(struct inode *old_dir, /* if old and new are the same, this'll just do one lock. */ status = ocfs2_double_lock(osb, &old_dir_bh, old_dir, - &new_dir_bh, new_dir); + &new_dir_bh, new_dir, 1); if (status < 0) { mlog_errno(status); goto bail; diff --git a/fs/open.c b/fs/open.c index 2ed7325f713e..c92c6ef8bf6d 100644 --- a/fs/open.c +++ b/fs/open.c @@ -822,8 +822,7 @@ struct file *dentry_open(const struct path *path, int flags, f = get_empty_filp(); if (!IS_ERR(f)) { f->f_flags = flags; - f->f_path = *path; - error = do_dentry_open(f, NULL, cred); + error = vfs_open(path, f, cred); if (!error) { /* from now on we need fput() to dispose of f */ error = open_check_o_direct(f); @@ -840,6 +839,26 @@ struct file *dentry_open(const struct path *path, int flags, } EXPORT_SYMBOL(dentry_open); +/** + * vfs_open - open the file at the given path + * @path: path to open + * @filp: newly allocated file with f_flag initialized + * @cred: credentials to use + */ +int vfs_open(const struct path *path, struct file *filp, + const struct cred *cred) +{ + struct inode *inode = path->dentry->d_inode; + + if (inode->i_op->dentry_open) + return inode->i_op->dentry_open(path->dentry, filp, cred); + else { + filp->f_path = *path; + return do_dentry_open(filp, NULL, cred); + } +} +EXPORT_SYMBOL(vfs_open); + static inline int build_open_flags(int flags, umode_t mode, struct open_flags *op) { int lookup_flags = 0; diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig new file mode 100644 index 000000000000..34355818a2e0 --- /dev/null +++ b/fs/overlayfs/Kconfig @@ -0,0 +1,10 @@ +config OVERLAY_FS + tristate "Overlay filesystem support" + help + An overlay filesystem combines two filesystems - an 'upper' filesystem + and a 'lower' filesystem. When a name exists in both filesystems, the + object in the 'upper' filesystem is visible while the object in the + 'lower' filesystem is either hidden or, in the case of directories, + merged with the 'upper' object. + + For more information see Documentation/filesystems/overlayfs.txt diff --git a/fs/overlayfs/Makefile b/fs/overlayfs/Makefile new file mode 100644 index 000000000000..900daed3e91d --- /dev/null +++ b/fs/overlayfs/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for the overlay filesystem. +# + +obj-$(CONFIG_OVERLAY_FS) += overlay.o + +overlay-objs := super.o inode.o dir.o readdir.o copy_up.o diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c new file mode 100644 index 000000000000..24f640441bd9 --- /dev/null +++ b/fs/overlayfs/copy_up.c @@ -0,0 +1,413 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <linux/fs.h> +#include <linux/slab.h> +#include <linux/file.h> +#include <linux/splice.h> +#include <linux/xattr.h> +#include <linux/security.h> +#include <linux/uaccess.h> +#include <linux/sched.h> +#include <linux/namei.h> +#include "overlayfs.h" + +#define OVL_COPY_UP_CHUNK_SIZE (1 << 20) + +int ovl_copy_xattr(struct dentry *old, struct dentry *new) +{ + ssize_t list_size, size; + char *buf, *name, *value; + int error; + + if (!old->d_inode->i_op->getxattr || + !new->d_inode->i_op->getxattr) + return 0; + + list_size = vfs_listxattr(old, NULL, 0); + if (list_size <= 0) { + if (list_size == -EOPNOTSUPP) + return 0; + return list_size; + } + + buf = kzalloc(list_size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + error = -ENOMEM; + value = kmalloc(XATTR_SIZE_MAX, GFP_KERNEL); + if (!value) + goto out; + + list_size = vfs_listxattr(old, buf, list_size); + if (list_size <= 0) { + error = list_size; + goto out_free_value; + } + + for (name = buf; name < (buf + list_size); name += strlen(name) + 1) { + size = vfs_getxattr(old, name, value, XATTR_SIZE_MAX); + if (size <= 0) { + error = size; + goto out_free_value; + } + error = vfs_setxattr(new, name, value, size, 0); + if (error) + goto out_free_value; + } + +out_free_value: + kfree(value); +out: + kfree(buf); + return error; +} + +static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) +{ + struct file *old_file; + struct file *new_file; + loff_t old_pos = 0; + loff_t new_pos = 0; + int error = 0; + + if (len == 0) + return 0; + + old_file = ovl_path_open(old, O_RDONLY); + if (IS_ERR(old_file)) + return PTR_ERR(old_file); + + new_file = ovl_path_open(new, O_WRONLY); + if (IS_ERR(new_file)) { + error = PTR_ERR(new_file); + goto out_fput; + } + + /* FIXME: copy up sparse files efficiently */ + while (len) { + size_t this_len = OVL_COPY_UP_CHUNK_SIZE; + long bytes; + + if (len < this_len) + this_len = len; + + if (signal_pending_state(TASK_KILLABLE, current)) { + error = -EINTR; + break; + } + + bytes = do_splice_direct(old_file, &old_pos, + new_file, &new_pos, + this_len, SPLICE_F_MOVE); + if (bytes <= 0) { + error = bytes; + break; + } + WARN_ON(old_pos != new_pos); + + len -= bytes; + } + + fput(new_file); +out_fput: + fput(old_file); + return error; +} + +static char *ovl_read_symlink(struct dentry *realdentry) +{ + int res; + char *buf; + struct inode *inode = realdentry->d_inode; + mm_segment_t old_fs; + + res = -EINVAL; + if (!inode->i_op->readlink) + goto err; + + res = -ENOMEM; + buf = (char *) __get_free_page(GFP_KERNEL); + if (!buf) + goto err; + + old_fs = get_fs(); + set_fs(get_ds()); + /* The cast to a user pointer is valid due to the set_fs() */ + res = inode->i_op->readlink(realdentry, + (char __user *)buf, PAGE_SIZE - 1); + set_fs(old_fs); + if (res < 0) { + free_page((unsigned long) buf); + goto err; + } + buf[res] = '\0'; + + return buf; + +err: + return ERR_PTR(res); +} + +static int ovl_set_timestamps(struct dentry *upperdentry, struct kstat *stat) +{ + struct iattr attr = { + .ia_valid = + ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET, + .ia_atime = stat->atime, + .ia_mtime = stat->mtime, + }; + + return notify_change(upperdentry, &attr, NULL); +} + +int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat) +{ + int err = 0; + + if (!S_ISLNK(stat->mode)) { + struct iattr attr = { + .ia_valid = ATTR_MODE, + .ia_mode = stat->mode, + }; + err = notify_change(upperdentry, &attr, NULL); + } + if (!err) { + struct iattr attr = { + .ia_valid = ATTR_UID | ATTR_GID, + .ia_uid = stat->uid, + .ia_gid = stat->gid, + }; + err = notify_change(upperdentry, &attr, NULL); + } + if (!err) + ovl_set_timestamps(upperdentry, stat); + + return err; +} + +static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir, + struct dentry *dentry, struct path *lowerpath, + struct kstat *stat, struct iattr *attr, + const char *link) +{ + struct inode *wdir = workdir->d_inode; + struct inode *udir = upperdir->d_inode; + struct dentry *newdentry = NULL; + struct dentry *upper = NULL; + umode_t mode = stat->mode; + int err; + + newdentry = ovl_lookup_temp(workdir, dentry); + err = PTR_ERR(newdentry); + if (IS_ERR(newdentry)) + goto out; + + upper = lookup_one_len(dentry->d_name.name, upperdir, + dentry->d_name.len); + err = PTR_ERR(upper); + if (IS_ERR(upper)) + goto out1; + + /* Can't properly set mode on creation because of the umask */ + stat->mode &= S_IFMT; + err = ovl_create_real(wdir, newdentry, stat, link, NULL, true); + stat->mode = mode; + if (err) + goto out2; + + if (S_ISREG(stat->mode)) { + struct path upperpath; + ovl_path_upper(dentry, &upperpath); + BUG_ON(upperpath.dentry != NULL); + upperpath.dentry = newdentry; + + err = ovl_copy_up_data(lowerpath, &upperpath, stat->size); + if (err) + goto out_cleanup; + } + + err = ovl_copy_xattr(lowerpath->dentry, newdentry); + if (err) + goto out_cleanup; + + mutex_lock(&newdentry->d_inode->i_mutex); + err = ovl_set_attr(newdentry, stat); + if (!err && attr) + err = notify_change(newdentry, attr, NULL); + mutex_unlock(&newdentry->d_inode->i_mutex); + if (err) + goto out_cleanup; + + err = ovl_do_rename(wdir, newdentry, udir, upper, 0); + if (err) + goto out_cleanup; + + ovl_dentry_update(dentry, newdentry); + newdentry = NULL; + + /* + * Non-directores become opaque when copied up. + */ + if (!S_ISDIR(stat->mode)) + ovl_dentry_set_opaque(dentry, true); +out2: + dput(upper); +out1: + dput(newdentry); +out: + return err; + +out_cleanup: + ovl_cleanup(wdir, newdentry); + goto out; +} + +/* + * Copy up a single dentry + * + * Directory renames only allowed on "pure upper" (already created on + * upper filesystem, never copied up). Directories which are on lower or + * are merged may not be renamed. For these -EXDEV is returned and + * userspace has to deal with it. This means, when copying up a + * directory we can rely on it and ancestors being stable. + * + * Non-directory renames start with copy up of source if necessary. The + * actual rename will only proceed once the copy up was successful. Copy + * up uses upper parent i_mutex for exclusion. Since rename can change + * d_parent it is possible that the copy up will lock the old parent. At + * that point the file will have already been copied up anyway. + */ +int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, + struct path *lowerpath, struct kstat *stat, + struct iattr *attr) +{ + struct dentry *workdir = ovl_workdir(dentry); + int err; + struct kstat pstat; + struct path parentpath; + struct dentry *upperdir; + struct dentry *upperdentry; + const struct cred *old_cred; + struct cred *override_cred; + char *link = NULL; + + ovl_path_upper(parent, &parentpath); + upperdir = parentpath.dentry; + + err = vfs_getattr(&parentpath, &pstat); + if (err) + return err; + + if (S_ISLNK(stat->mode)) { + link = ovl_read_symlink(lowerpath->dentry); + if (IS_ERR(link)) + return PTR_ERR(link); + } + + err = -ENOMEM; + override_cred = prepare_creds(); + if (!override_cred) + goto out_free_link; + + override_cred->fsuid = stat->uid; + override_cred->fsgid = stat->gid; + /* + * CAP_SYS_ADMIN for copying up extended attributes + * CAP_DAC_OVERRIDE for create + * CAP_FOWNER for chmod, timestamp update + * CAP_FSETID for chmod + * CAP_CHOWN for chown + * CAP_MKNOD for mknod + */ + cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN); + cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE); + cap_raise(override_cred->cap_effective, CAP_FOWNER); + cap_raise(override_cred->cap_effective, CAP_FSETID); + cap_raise(override_cred->cap_effective, CAP_CHOWN); + cap_raise(override_cred->cap_effective, CAP_MKNOD); + old_cred = override_creds(override_cred); + + err = -EIO; + if (lock_rename(workdir, upperdir) != NULL) { + pr_err("overlayfs: failed to lock workdir+upperdir\n"); + goto out_unlock; + } + upperdentry = ovl_dentry_upper(dentry); + if (upperdentry) { + unlock_rename(workdir, upperdir); + err = 0; + /* Raced with another copy-up? Do the setattr here */ + if (attr) { + mutex_lock(&upperdentry->d_inode->i_mutex); + err = notify_change(upperdentry, attr, NULL); + mutex_unlock(&upperdentry->d_inode->i_mutex); + } + goto out_put_cred; + } + + err = ovl_copy_up_locked(workdir, upperdir, dentry, lowerpath, + stat, attr, link); + if (!err) { + /* Restore timestamps on parent (best effort) */ + ovl_set_timestamps(upperdir, &pstat); + } +out_unlock: + unlock_rename(workdir, upperdir); +out_put_cred: + revert_creds(old_cred); + put_cred(override_cred); + +out_free_link: + if (link) + free_page((unsigned long) link); + + return err; +} + +int ovl_copy_up(struct dentry *dentry) +{ + int err; + + err = 0; + while (!err) { + struct dentry *next; + struct dentry *parent; + struct path lowerpath; + struct kstat stat; + enum ovl_path_type type = ovl_path_type(dentry); + + if (OVL_TYPE_UPPER(type)) + break; + + next = dget(dentry); + /* find the topmost dentry not yet copied up */ + for (;;) { + parent = dget_parent(next); + + type = ovl_path_type(parent); + if (OVL_TYPE_UPPER(type)) + break; + + dput(next); + next = parent; + } + + ovl_path_lower(next, &lowerpath); + err = vfs_getattr(&lowerpath, &stat); + if (!err) + err = ovl_copy_up_one(parent, next, &lowerpath, &stat, NULL); + + dput(parent); + dput(next); + } + + return err; +} diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c new file mode 100644 index 000000000000..0dc4c33a0a1b --- /dev/null +++ b/fs/overlayfs/dir.c @@ -0,0 +1,928 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <linux/fs.h> +#include <linux/namei.h> +#include <linux/xattr.h> +#include <linux/security.h> +#include <linux/cred.h> +#include "overlayfs.h" + +void ovl_cleanup(struct inode *wdir, struct dentry *wdentry) +{ + int err; + + dget(wdentry); + if (S_ISDIR(wdentry->d_inode->i_mode)) + err = ovl_do_rmdir(wdir, wdentry); + else + err = ovl_do_unlink(wdir, wdentry); + dput(wdentry); + + if (err) { + pr_err("overlayfs: cleanup of '%pd2' failed (%i)\n", + wdentry, err); + } +} + +struct dentry *ovl_lookup_temp(struct dentry *workdir, struct dentry *dentry) +{ + struct dentry *temp; + char name[20]; + + snprintf(name, sizeof(name), "#%lx", (unsigned long) dentry); + + temp = lookup_one_len(name, workdir, strlen(name)); + if (!IS_ERR(temp) && temp->d_inode) { + pr_err("overlayfs: workdir/%s already exists\n", name); + dput(temp); + temp = ERR_PTR(-EIO); + } + + return temp; +} + +/* caller holds i_mutex on workdir */ +static struct dentry *ovl_whiteout(struct dentry *workdir, + struct dentry *dentry) +{ + int err; + struct dentry *whiteout; + struct inode *wdir = workdir->d_inode; + + whiteout = ovl_lookup_temp(workdir, dentry); + if (IS_ERR(whiteout)) + return whiteout; + + err = ovl_do_whiteout(wdir, whiteout); + if (err) { + dput(whiteout); + whiteout = ERR_PTR(err); + } + + return whiteout; +} + +int ovl_create_real(struct inode *dir, struct dentry *newdentry, + struct kstat *stat, const char *link, + struct dentry *hardlink, bool debug) +{ + int err; + + if (newdentry->d_inode) + return -ESTALE; + + if (hardlink) { + err = ovl_do_link(hardlink, dir, newdentry, debug); + } else { + switch (stat->mode & S_IFMT) { + case S_IFREG: + err = ovl_do_create(dir, newdentry, stat->mode, debug); + break; + + case S_IFDIR: + err = ovl_do_mkdir(dir, newdentry, stat->mode, debug); + break; + + case S_IFCHR: + case S_IFBLK: + case S_IFIFO: + case S_IFSOCK: + err = ovl_do_mknod(dir, newdentry, + stat->mode, stat->rdev, debug); + break; + + case S_IFLNK: + err = ovl_do_symlink(dir, newdentry, link, debug); + break; + + default: + err = -EPERM; + } + } + if (!err && WARN_ON(!newdentry->d_inode)) { + /* + * Not quite sure if non-instantiated dentry is legal or not. + * VFS doesn't seem to care so check and warn here. + */ + err = -ENOENT; + } + return err; +} + +static int ovl_set_opaque(struct dentry *upperdentry) +{ + return ovl_do_setxattr(upperdentry, OVL_XATTR_OPAQUE, "y", 1, 0); +} + +static void ovl_remove_opaque(struct dentry *upperdentry) +{ + int err; + + err = ovl_do_removexattr(upperdentry, OVL_XATTR_OPAQUE); + if (err) { + pr_warn("overlayfs: failed to remove opaque from '%s' (%i)\n", + upperdentry->d_name.name, err); + } +} + +static int ovl_dir_getattr(struct vfsmount *mnt, struct dentry *dentry, + struct kstat *stat) +{ + int err; + enum ovl_path_type type; + struct path realpath; + + type = ovl_path_real(dentry, &realpath); + err = vfs_getattr(&realpath, stat); + if (err) + return err; + + stat->dev = dentry->d_sb->s_dev; + stat->ino = dentry->d_inode->i_ino; + + /* + * It's probably not worth it to count subdirs to get the + * correct link count. nlink=1 seems to pacify 'find' and + * other utilities. + */ + if (OVL_TYPE_MERGE(type)) + stat->nlink = 1; + + return 0; +} + +static int ovl_create_upper(struct dentry *dentry, struct inode *inode, + struct kstat *stat, const char *link, + struct dentry *hardlink) +{ + struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent); + struct inode *udir = upperdir->d_inode; + struct dentry *newdentry; + int err; + + mutex_lock_nested(&udir->i_mutex, I_MUTEX_PARENT); + newdentry = lookup_one_len(dentry->d_name.name, upperdir, + dentry->d_name.len); + err = PTR_ERR(newdentry); + if (IS_ERR(newdentry)) + goto out_unlock; + err = ovl_create_real(udir, newdentry, stat, link, hardlink, false); + if (err) + goto out_dput; + + ovl_dentry_version_inc(dentry->d_parent); + ovl_dentry_update(dentry, newdentry); + ovl_copyattr(newdentry->d_inode, inode); + d_instantiate(dentry, inode); + newdentry = NULL; +out_dput: + dput(newdentry); +out_unlock: + mutex_unlock(&udir->i_mutex); + return err; +} + +static int ovl_lock_rename_workdir(struct dentry *workdir, + struct dentry *upperdir) +{ + /* Workdir should not be the same as upperdir */ + if (workdir == upperdir) + goto err; + + /* Workdir should not be subdir of upperdir and vice versa */ + if (lock_rename(workdir, upperdir) != NULL) + goto err_unlock; + + return 0; + +err_unlock: + unlock_rename(workdir, upperdir); +err: + pr_err("overlayfs: failed to lock workdir+upperdir\n"); + return -EIO; +} + +static struct dentry *ovl_clear_empty(struct dentry *dentry, + struct list_head *list) +{ + struct dentry *workdir = ovl_workdir(dentry); + struct inode *wdir = workdir->d_inode; + struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent); + struct inode *udir = upperdir->d_inode; + struct path upperpath; + struct dentry *upper; + struct dentry *opaquedir; + struct kstat stat; + int err; + + err = ovl_lock_rename_workdir(workdir, upperdir); + if (err) + goto out; + + ovl_path_upper(dentry, &upperpath); + err = vfs_getattr(&upperpath, &stat); + if (err) + goto out_unlock; + + err = -ESTALE; + if (!S_ISDIR(stat.mode)) + goto out_unlock; + upper = upperpath.dentry; + if (upper->d_parent->d_inode != udir) + goto out_unlock; + + opaquedir = ovl_lookup_temp(workdir, dentry); + err = PTR_ERR(opaquedir); + if (IS_ERR(opaquedir)) + goto out_unlock; + + err = ovl_create_real(wdir, opaquedir, &stat, NULL, NULL, true); + if (err) + goto out_dput; + + err = ovl_copy_xattr(upper, opaquedir); + if (err) + goto out_cleanup; + + err = ovl_set_opaque(opaquedir); + if (err) + goto out_cleanup; + + mutex_lock(&opaquedir->d_inode->i_mutex); + err = ovl_set_attr(opaquedir, &stat); + mutex_unlock(&opaquedir->d_inode->i_mutex); + if (err) + goto out_cleanup; + + err = ovl_do_rename(wdir, opaquedir, udir, upper, RENAME_EXCHANGE); + if (err) + goto out_cleanup; + + ovl_cleanup_whiteouts(upper, list); + ovl_cleanup(wdir, upper); + unlock_rename(workdir, upperdir); + + /* dentry's upper doesn't match now, get rid of it */ + d_drop(dentry); + + return opaquedir; + +out_cleanup: + ovl_cleanup(wdir, opaquedir); +out_dput: + dput(opaquedir); +out_unlock: + unlock_rename(workdir, upperdir); +out: + return ERR_PTR(err); +} + +static struct dentry *ovl_check_empty_and_clear(struct dentry *dentry) +{ + int err; + struct dentry *ret = NULL; + LIST_HEAD(list); + + err = ovl_check_empty_dir(dentry, &list); + if (err) + ret = ERR_PTR(err); + else { + /* + * If no upperdentry then skip clearing whiteouts. + * + * Can race with copy-up, since we don't hold the upperdir + * mutex. Doesn't matter, since copy-up can't create a + * non-empty directory from an empty one. + */ + if (ovl_dentry_upper(dentry)) + ret = ovl_clear_empty(dentry, &list); + } + + ovl_cache_free(&list); + + return ret; +} + +static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode, + struct kstat *stat, const char *link, + struct dentry *hardlink) +{ + struct dentry *workdir = ovl_workdir(dentry); + struct inode *wdir = workdir->d_inode; + struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent); + struct inode *udir = upperdir->d_inode; + struct dentry *upper; + struct dentry *newdentry; + int err; + + err = ovl_lock_rename_workdir(workdir, upperdir); + if (err) + goto out; + + newdentry = ovl_lookup_temp(workdir, dentry); + err = PTR_ERR(newdentry); + if (IS_ERR(newdentry)) + goto out_unlock; + + upper = lookup_one_len(dentry->d_name.name, upperdir, + dentry->d_name.len); + err = PTR_ERR(upper); + if (IS_ERR(upper)) + goto out_dput; + + err = ovl_create_real(wdir, newdentry, stat, link, hardlink, true); + if (err) + goto out_dput2; + + if (S_ISDIR(stat->mode)) { + err = ovl_set_opaque(newdentry); + if (err) + goto out_cleanup; + + err = ovl_do_rename(wdir, newdentry, udir, upper, + RENAME_EXCHANGE); + if (err) + goto out_cleanup; + + ovl_cleanup(wdir, upper); + } else { + err = ovl_do_rename(wdir, newdentry, udir, upper, 0); + if (err) + goto out_cleanup; + } + ovl_dentry_version_inc(dentry->d_parent); + ovl_dentry_update(dentry, newdentry); + ovl_copyattr(newdentry->d_inode, inode); + d_instantiate(dentry, inode); + newdentry = NULL; +out_dput2: + dput(upper); +out_dput: + dput(newdentry); +out_unlock: + unlock_rename(workdir, upperdir); +out: + return err; + +out_cleanup: + ovl_cleanup(wdir, newdentry); + goto out_dput2; +} + +static int ovl_create_or_link(struct dentry *dentry, int mode, dev_t rdev, + const char *link, struct dentry *hardlink) +{ + int err; + struct inode *inode; + struct kstat stat = { + .mode = mode, + .rdev = rdev, + }; + + err = -ENOMEM; + inode = ovl_new_inode(dentry->d_sb, mode, dentry->d_fsdata); + if (!inode) + goto out; + + err = ovl_copy_up(dentry->d_parent); + if (err) + goto out_iput; + + if (!ovl_dentry_is_opaque(dentry)) { + err = ovl_create_upper(dentry, inode, &stat, link, hardlink); + } else { + const struct cred *old_cred; + struct cred *override_cred; + + err = -ENOMEM; + override_cred = prepare_creds(); + if (!override_cred) + goto out_iput; + + /* + * CAP_SYS_ADMIN for setting opaque xattr + * CAP_DAC_OVERRIDE for create in workdir, rename + * CAP_FOWNER for removing whiteout from sticky dir + */ + cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN); + cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE); + cap_raise(override_cred->cap_effective, CAP_FOWNER); + old_cred = override_creds(override_cred); + + err = ovl_create_over_whiteout(dentry, inode, &stat, link, + hardlink); + + revert_creds(old_cred); + put_cred(override_cred); + } + + if (!err) + inode = NULL; +out_iput: + iput(inode); +out: + return err; +} + +static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev, + const char *link) +{ + int err; + + err = ovl_want_write(dentry); + if (!err) { + err = ovl_create_or_link(dentry, mode, rdev, link, NULL); + ovl_drop_write(dentry); + } + + return err; +} + +static int ovl_create(struct inode *dir, struct dentry *dentry, umode_t mode, + bool excl) +{ + return ovl_create_object(dentry, (mode & 07777) | S_IFREG, 0, NULL); +} + +static int ovl_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + return ovl_create_object(dentry, (mode & 07777) | S_IFDIR, 0, NULL); +} + +static int ovl_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, + dev_t rdev) +{ + /* Don't allow creation of "whiteout" on overlay */ + if (S_ISCHR(mode) && rdev == WHITEOUT_DEV) + return -EPERM; + + return ovl_create_object(dentry, mode, rdev, NULL); +} + +static int ovl_symlink(struct inode *dir, struct dentry *dentry, + const char *link) +{ + return ovl_create_object(dentry, S_IFLNK, 0, link); +} + +static int ovl_link(struct dentry *old, struct inode *newdir, + struct dentry *new) +{ + int err; + struct dentry *upper; + + err = ovl_want_write(old); + if (err) + goto out; + + err = ovl_copy_up(old); + if (err) + goto out_drop_write; + + upper = ovl_dentry_upper(old); + err = ovl_create_or_link(new, upper->d_inode->i_mode, 0, NULL, upper); + +out_drop_write: + ovl_drop_write(old); +out: + return err; +} + +static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir) +{ + struct dentry *workdir = ovl_workdir(dentry); + struct inode *wdir = workdir->d_inode; + struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent); + struct inode *udir = upperdir->d_inode; + struct dentry *whiteout; + struct dentry *upper; + struct dentry *opaquedir = NULL; + int err; + + if (is_dir && OVL_TYPE_MERGE_OR_LOWER(ovl_path_type(dentry))) { + opaquedir = ovl_check_empty_and_clear(dentry); + err = PTR_ERR(opaquedir); + if (IS_ERR(opaquedir)) + goto out; + } + + err = ovl_lock_rename_workdir(workdir, upperdir); + if (err) + goto out_dput; + + whiteout = ovl_whiteout(workdir, dentry); + err = PTR_ERR(whiteout); + if (IS_ERR(whiteout)) + 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; + + if (opaquedir) + upper = opaquedir; + err = -ESTALE; + if (upper->d_parent != upperdir) + goto kill_whiteout; + + if (is_dir) + flags |= RENAME_EXCHANGE; + + err = ovl_do_rename(wdir, whiteout, udir, upper, flags); + if (err) + goto kill_whiteout; + + if (is_dir) + ovl_cleanup(wdir, upper); + } + ovl_dentry_version_inc(dentry->d_parent); +out_d_drop: + d_drop(dentry); + dput(whiteout); +out_unlock: + unlock_rename(workdir, upperdir); +out_dput: + dput(opaquedir); +out: + return err; + +kill_whiteout: + ovl_cleanup(wdir, whiteout); + goto out_d_drop; +} + +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); + int err; + + mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); + err = -ESTALE; + if (upper->d_parent == upperdir) { + /* Don't let d_delete() think it can reset d_inode */ + dget(upper); + if (is_dir) + err = vfs_rmdir(dir, upper); + else + err = vfs_unlink(dir, upper, NULL); + dput(upper); + ovl_dentry_version_inc(dentry->d_parent); + } + + /* + * Keeping this dentry hashed would mean having to release + * upperpath/lowerpath, which could only be done if we are the + * sole user of this dentry. Too tricky... Just unhash for + * now. + */ + d_drop(dentry); + mutex_unlock(&dir->i_mutex); + + return err; +} + +static inline int ovl_check_sticky(struct dentry *dentry) +{ + struct inode *dir = ovl_dentry_real(dentry->d_parent)->d_inode; + struct inode *inode = ovl_dentry_real(dentry)->d_inode; + + if (check_sticky(dir, inode)) + return -EPERM; + + return 0; +} + +static int ovl_do_remove(struct dentry *dentry, bool is_dir) +{ + enum ovl_path_type type; + int err; + + err = ovl_check_sticky(dentry); + if (err) + goto out; + + err = ovl_want_write(dentry); + if (err) + goto out; + + err = ovl_copy_up(dentry->d_parent); + if (err) + goto out_drop_write; + + type = ovl_path_type(dentry); + if (OVL_TYPE_PURE_UPPER(type)) { + err = ovl_remove_upper(dentry, is_dir); + } else { + const struct cred *old_cred; + struct cred *override_cred; + + err = -ENOMEM; + override_cred = prepare_creds(); + if (!override_cred) + goto out_drop_write; + + /* + * CAP_SYS_ADMIN for setting xattr on whiteout, opaque dir + * CAP_DAC_OVERRIDE for create in workdir, rename + * CAP_FOWNER for removing whiteout from sticky dir + * CAP_FSETID for chmod of opaque dir + * CAP_CHOWN for chown of opaque dir + */ + cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN); + cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE); + cap_raise(override_cred->cap_effective, CAP_FOWNER); + cap_raise(override_cred->cap_effective, CAP_FSETID); + cap_raise(override_cred->cap_effective, CAP_CHOWN); + old_cred = override_creds(override_cred); + + err = ovl_remove_and_whiteout(dentry, is_dir); + + revert_creds(old_cred); + put_cred(override_cred); + } +out_drop_write: + ovl_drop_write(dentry); +out: + return err; +} + +static int ovl_unlink(struct inode *dir, struct dentry *dentry) +{ + return ovl_do_remove(dentry, false); +} + +static int ovl_rmdir(struct inode *dir, struct dentry *dentry) +{ + return ovl_do_remove(dentry, true); +} + +static int ovl_rename2(struct inode *olddir, struct dentry *old, + struct inode *newdir, struct dentry *new, + unsigned int flags) +{ + int err; + enum ovl_path_type old_type; + enum ovl_path_type new_type; + struct dentry *old_upperdir; + struct dentry *new_upperdir; + struct dentry *olddentry; + struct dentry *newdentry; + struct dentry *trap; + bool old_opaque; + bool new_opaque; + bool new_create = false; + bool cleanup_whiteout = false; + bool overwrite = !(flags & RENAME_EXCHANGE); + bool is_dir = S_ISDIR(old->d_inode->i_mode); + bool new_is_dir = false; + struct dentry *opaquedir = NULL; + const struct cred *old_cred = NULL; + struct cred *override_cred = NULL; + + err = -EINVAL; + if (flags & ~(RENAME_EXCHANGE | RENAME_NOREPLACE)) + goto out; + + flags &= ~RENAME_NOREPLACE; + + err = ovl_check_sticky(old); + if (err) + goto out; + + /* Don't copy up directory trees */ + old_type = ovl_path_type(old); + err = -EXDEV; + if (OVL_TYPE_MERGE_OR_LOWER(old_type) && is_dir) + goto out; + + if (new->d_inode) { + err = ovl_check_sticky(new); + if (err) + goto out; + + if (S_ISDIR(new->d_inode->i_mode)) + new_is_dir = true; + + new_type = ovl_path_type(new); + err = -EXDEV; + if (!overwrite && OVL_TYPE_MERGE_OR_LOWER(new_type) && new_is_dir) + goto out; + + err = 0; + if (!OVL_TYPE_UPPER(new_type) && !OVL_TYPE_UPPER(old_type)) { + if (ovl_dentry_lower(old)->d_inode == + ovl_dentry_lower(new)->d_inode) + goto out; + } + if (OVL_TYPE_UPPER(new_type) && OVL_TYPE_UPPER(old_type)) { + if (ovl_dentry_upper(old)->d_inode == + ovl_dentry_upper(new)->d_inode) + goto out; + } + } else { + if (ovl_dentry_is_opaque(new)) + new_type = __OVL_PATH_UPPER; + else + new_type = __OVL_PATH_UPPER | __OVL_PATH_PURE; + } + + err = ovl_want_write(old); + if (err) + goto out; + + err = ovl_copy_up(old); + if (err) + goto out_drop_write; + + err = ovl_copy_up(new->d_parent); + if (err) + goto out_drop_write; + if (!overwrite) { + err = ovl_copy_up(new); + if (err) + goto out_drop_write; + } + + old_opaque = !OVL_TYPE_PURE_UPPER(old_type); + new_opaque = !OVL_TYPE_PURE_UPPER(new_type); + + if (old_opaque || new_opaque) { + err = -ENOMEM; + override_cred = prepare_creds(); + if (!override_cred) + goto out_drop_write; + + /* + * CAP_SYS_ADMIN for setting xattr on whiteout, opaque dir + * CAP_DAC_OVERRIDE for create in workdir + * CAP_FOWNER for removing whiteout from sticky dir + * CAP_FSETID for chmod of opaque dir + * CAP_CHOWN for chown of opaque dir + */ + cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN); + cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE); + cap_raise(override_cred->cap_effective, CAP_FOWNER); + cap_raise(override_cred->cap_effective, CAP_FSETID); + cap_raise(override_cred->cap_effective, CAP_CHOWN); + old_cred = override_creds(override_cred); + } + + if (overwrite && OVL_TYPE_MERGE_OR_LOWER(new_type) && new_is_dir) { + opaquedir = ovl_check_empty_and_clear(new); + err = PTR_ERR(opaquedir); + if (IS_ERR(opaquedir)) { + opaquedir = NULL; + goto out_revert_creds; + } + } + + if (overwrite) { + if (old_opaque) { + if (new->d_inode || !new_opaque) { + /* Whiteout source */ + flags |= RENAME_WHITEOUT; + } else { + /* Switch whiteouts */ + flags |= RENAME_EXCHANGE; + } + } else if (is_dir && !new->d_inode && new_opaque) { + flags |= RENAME_EXCHANGE; + cleanup_whiteout = true; + } + } + + old_upperdir = ovl_dentry_upper(old->d_parent); + new_upperdir = ovl_dentry_upper(new->d_parent); + + trap = lock_rename(new_upperdir, old_upperdir); + + olddentry = ovl_dentry_upper(old); + newdentry = ovl_dentry_upper(new); + if (newdentry) { + if (opaquedir) { + newdentry = opaquedir; + opaquedir = NULL; + } else { + dget(newdentry); + } + } 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; + } + + 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) + goto out_dput; + + if (is_dir && !old_opaque && new_opaque) { + err = ovl_set_opaque(olddentry); + if (err) + goto out_dput; + } + if (!overwrite && new_is_dir && old_opaque && !new_opaque) { + err = ovl_set_opaque(newdentry); + if (err) + goto out_dput; + } + + if (old_opaque || new_opaque) { + err = ovl_do_rename(old_upperdir->d_inode, olddentry, + new_upperdir->d_inode, newdentry, + flags); + } else { + /* No debug for the plain case */ + BUG_ON(flags & ~RENAME_EXCHANGE); + err = vfs_rename(old_upperdir->d_inode, olddentry, + new_upperdir->d_inode, newdentry, + NULL, flags); + } + + if (err) { + if (is_dir && !old_opaque && new_opaque) + ovl_remove_opaque(olddentry); + if (!overwrite && new_is_dir && old_opaque && !new_opaque) + ovl_remove_opaque(newdentry); + goto out_dput; + } + + if (is_dir && old_opaque && !new_opaque) + ovl_remove_opaque(olddentry); + if (!overwrite && new_is_dir && !old_opaque && new_opaque) + ovl_remove_opaque(newdentry); + + if (old_opaque != new_opaque) { + ovl_dentry_set_opaque(old, new_opaque); + if (!overwrite) + ovl_dentry_set_opaque(new, old_opaque); + } + + if (cleanup_whiteout) + ovl_cleanup(old_upperdir->d_inode, newdentry); + + ovl_dentry_version_inc(old->d_parent); + ovl_dentry_version_inc(new->d_parent); + +out_dput: + dput(newdentry); +out_unlock: + unlock_rename(new_upperdir, old_upperdir); +out_revert_creds: + if (old_opaque || new_opaque) { + revert_creds(old_cred); + put_cred(override_cred); + } +out_drop_write: + ovl_drop_write(old); +out: + dput(opaquedir); + return err; +} + +const struct inode_operations ovl_dir_inode_operations = { + .lookup = ovl_lookup, + .mkdir = ovl_mkdir, + .symlink = ovl_symlink, + .unlink = ovl_unlink, + .rmdir = ovl_rmdir, + .rename2 = ovl_rename2, + .link = ovl_link, + .setattr = ovl_setattr, + .create = ovl_create, + .mknod = ovl_mknod, + .permission = ovl_permission, + .getattr = ovl_dir_getattr, + .setxattr = ovl_setxattr, + .getxattr = ovl_getxattr, + .listxattr = ovl_listxattr, + .removexattr = ovl_removexattr, +}; diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c new file mode 100644 index 000000000000..04f124884687 --- /dev/null +++ b/fs/overlayfs/inode.c @@ -0,0 +1,436 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <linux/fs.h> +#include <linux/slab.h> +#include <linux/xattr.h> +#include "overlayfs.h" + +static int ovl_copy_up_last(struct dentry *dentry, struct iattr *attr, + bool no_data) +{ + int err; + struct dentry *parent; + struct kstat stat; + struct path lowerpath; + + parent = dget_parent(dentry); + err = ovl_copy_up(parent); + if (err) + goto out_dput_parent; + + ovl_path_lower(dentry, &lowerpath); + err = vfs_getattr(&lowerpath, &stat); + if (err) + goto out_dput_parent; + + if (no_data) + stat.size = 0; + + err = ovl_copy_up_one(parent, dentry, &lowerpath, &stat, attr); + +out_dput_parent: + dput(parent); + return err; +} + +int ovl_setattr(struct dentry *dentry, struct iattr *attr) +{ + int err; + struct dentry *upperdentry; + + err = ovl_want_write(dentry); + if (err) + goto out; + + upperdentry = ovl_dentry_upper(dentry); + if (upperdentry) { + mutex_lock(&upperdentry->d_inode->i_mutex); + err = notify_change(upperdentry, attr, NULL); + mutex_unlock(&upperdentry->d_inode->i_mutex); + } else { + err = ovl_copy_up_last(dentry, attr, false); + } + ovl_drop_write(dentry); +out: + return err; +} + +static int ovl_getattr(struct vfsmount *mnt, struct dentry *dentry, + struct kstat *stat) +{ + struct path realpath; + + ovl_path_real(dentry, &realpath); + return vfs_getattr(&realpath, stat); +} + +int ovl_permission(struct inode *inode, int mask) +{ + struct ovl_entry *oe; + struct dentry *alias = NULL; + struct inode *realinode; + struct dentry *realdentry; + bool is_upper; + int err; + + if (S_ISDIR(inode->i_mode)) { + oe = inode->i_private; + } else if (mask & MAY_NOT_BLOCK) { + return -ECHILD; + } else { + /* + * For non-directories find an alias and get the info + * from there. + */ + alias = d_find_any_alias(inode); + if (WARN_ON(!alias)) + return -ENOENT; + + oe = alias->d_fsdata; + } + + realdentry = ovl_entry_real(oe, &is_upper); + + /* Careful in RCU walk mode */ + realinode = ACCESS_ONCE(realdentry->d_inode); + if (!realinode) { + WARN_ON(!(mask & MAY_NOT_BLOCK)); + err = -ENOENT; + goto out_dput; + } + + if (mask & MAY_WRITE) { + umode_t mode = realinode->i_mode; + + /* + * Writes will always be redirected to upper layer, so + * ignore lower layer being read-only. + * + * If the overlay itself is read-only then proceed + * with the permission check, don't return EROFS. + * This will only happen if this is the lower layer of + * another overlayfs. + * + * If upper fs becomes read-only after the overlay was + * constructed return EROFS to prevent modification of + * upper layer. + */ + err = -EROFS; + if (is_upper && !IS_RDONLY(inode) && IS_RDONLY(realinode) && + (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) + goto out_dput; + } + + err = __inode_permission(realinode, mask); +out_dput: + dput(alias); + return err; +} + + +struct ovl_link_data { + struct dentry *realdentry; + void *cookie; +}; + +static void *ovl_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + void *ret; + struct dentry *realdentry; + struct inode *realinode; + + realdentry = ovl_dentry_real(dentry); + realinode = realdentry->d_inode; + + if (WARN_ON(!realinode->i_op->follow_link)) + return ERR_PTR(-EPERM); + + ret = realinode->i_op->follow_link(realdentry, nd); + if (IS_ERR(ret)) + return ret; + + if (realinode->i_op->put_link) { + struct ovl_link_data *data; + + data = kmalloc(sizeof(struct ovl_link_data), GFP_KERNEL); + if (!data) { + realinode->i_op->put_link(realdentry, nd, ret); + return ERR_PTR(-ENOMEM); + } + data->realdentry = realdentry; + data->cookie = ret; + + return data; + } else { + return NULL; + } +} + +static void ovl_put_link(struct dentry *dentry, struct nameidata *nd, void *c) +{ + struct inode *realinode; + struct ovl_link_data *data = c; + + if (!data) + return; + + realinode = data->realdentry->d_inode; + realinode->i_op->put_link(data->realdentry, nd, data->cookie); + kfree(data); +} + +static int ovl_readlink(struct dentry *dentry, char __user *buf, int bufsiz) +{ + struct path realpath; + struct inode *realinode; + + ovl_path_real(dentry, &realpath); + realinode = realpath.dentry->d_inode; + + if (!realinode->i_op->readlink) + return -EINVAL; + + touch_atime(&realpath); + + return realinode->i_op->readlink(realpath.dentry, buf, bufsiz); +} + + +static bool ovl_is_private_xattr(const char *name) +{ + return strncmp(name, OVL_XATTR_PRE_NAME, OVL_XATTR_PRE_LEN) == 0; +} + +int ovl_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) +{ + int err; + struct dentry *upperdentry; + + err = ovl_want_write(dentry); + if (err) + goto out; + + err = -EPERM; + if (ovl_is_private_xattr(name)) + goto out_drop_write; + + err = ovl_copy_up(dentry); + if (err) + goto out_drop_write; + + upperdentry = ovl_dentry_upper(dentry); + err = vfs_setxattr(upperdentry, name, value, size, flags); + +out_drop_write: + ovl_drop_write(dentry); +out: + return err; +} + +static bool ovl_need_xattr_filter(struct dentry *dentry, + enum ovl_path_type type) +{ + if ((type & (__OVL_PATH_PURE | __OVL_PATH_UPPER)) == __OVL_PATH_UPPER) + return S_ISDIR(dentry->d_inode->i_mode); + else + return false; +} + +ssize_t ovl_getxattr(struct dentry *dentry, const char *name, + void *value, size_t size) +{ + struct path realpath; + enum ovl_path_type type = ovl_path_real(dentry, &realpath); + + if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name)) + return -ENODATA; + + return vfs_getxattr(realpath.dentry, name, value, size); +} + +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; + + res = vfs_listxattr(realpath.dentry, list, size); + if (res <= 0 || size == 0) + return res; + + if (!ovl_need_xattr_filter(dentry, type)) + return res; + + /* filter out private xattrs */ + for (off = 0; off < res;) { + char *s = list + off; + size_t slen = strlen(s) + 1; + + BUG_ON(off + slen > res); + + if (ovl_is_private_xattr(s)) { + res -= slen; + memmove(s, s + slen, res - off); + } else { + off += slen; + } + } + + return res; +} + +int ovl_removexattr(struct dentry *dentry, const char *name) +{ + int err; + struct path realpath; + enum ovl_path_type type = ovl_path_real(dentry, &realpath); + + err = ovl_want_write(dentry); + if (err) + goto out; + + err = -ENODATA; + if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name)) + goto out_drop_write; + + if (!OVL_TYPE_UPPER(type)) { + err = vfs_getxattr(realpath.dentry, name, NULL, 0); + if (err < 0) + goto out_drop_write; + + err = ovl_copy_up(dentry); + if (err) + goto out_drop_write; + + ovl_path_upper(dentry, &realpath); + } + + err = vfs_removexattr(realpath.dentry, name); +out_drop_write: + ovl_drop_write(dentry); +out: + return err; +} + +static bool ovl_open_need_copy_up(int flags, enum ovl_path_type type, + struct dentry *realdentry) +{ + if (OVL_TYPE_UPPER(type)) + return false; + + if (special_file(realdentry->d_inode->i_mode)) + return false; + + if (!(OPEN_FMODE(flags) & FMODE_WRITE) && !(flags & O_TRUNC)) + return false; + + return true; +} + +static int ovl_dentry_open(struct dentry *dentry, struct file *file, + const struct cred *cred) +{ + int err; + struct path realpath; + enum ovl_path_type type; + bool want_write = false; + + type = ovl_path_real(dentry, &realpath); + if (ovl_open_need_copy_up(file->f_flags, type, realpath.dentry)) { + want_write = true; + err = ovl_want_write(dentry); + if (err) + goto out; + + if (file->f_flags & O_TRUNC) + err = ovl_copy_up_last(dentry, NULL, true); + else + err = ovl_copy_up(dentry); + if (err) + goto out_drop_write; + + ovl_path_upper(dentry, &realpath); + } + + err = vfs_open(&realpath, file, cred); +out_drop_write: + if (want_write) + ovl_drop_write(dentry); +out: + return err; +} + +static const struct inode_operations ovl_file_inode_operations = { + .setattr = ovl_setattr, + .permission = ovl_permission, + .getattr = ovl_getattr, + .setxattr = ovl_setxattr, + .getxattr = ovl_getxattr, + .listxattr = ovl_listxattr, + .removexattr = ovl_removexattr, + .dentry_open = ovl_dentry_open, +}; + +static const struct inode_operations ovl_symlink_inode_operations = { + .setattr = ovl_setattr, + .follow_link = ovl_follow_link, + .put_link = ovl_put_link, + .readlink = ovl_readlink, + .getattr = ovl_getattr, + .setxattr = ovl_setxattr, + .getxattr = ovl_getxattr, + .listxattr = ovl_listxattr, + .removexattr = ovl_removexattr, +}; + +struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, + struct ovl_entry *oe) +{ + struct inode *inode; + + inode = new_inode(sb); + if (!inode) + return NULL; + + mode &= S_IFMT; + + inode->i_ino = get_next_ino(); + inode->i_mode = mode; + inode->i_flags |= S_NOATIME | S_NOCMTIME; + + switch (mode) { + case S_IFDIR: + inode->i_private = oe; + inode->i_op = &ovl_dir_inode_operations; + inode->i_fop = &ovl_dir_operations; + break; + + case S_IFLNK: + inode->i_op = &ovl_symlink_inode_operations; + break; + + case S_IFREG: + case S_IFSOCK: + case S_IFBLK: + case S_IFCHR: + case S_IFIFO: + inode->i_op = &ovl_file_inode_operations; + break; + + default: + WARN(1, "illegal file type: %i\n", mode); + iput(inode); + inode = NULL; + } + + return inode; +} diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h new file mode 100644 index 000000000000..17ac5afc9ffb --- /dev/null +++ b/fs/overlayfs/overlayfs.h @@ -0,0 +1,199 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <linux/kernel.h> + +struct ovl_entry; + +enum ovl_path_type { + __OVL_PATH_PURE = (1 << 0), + __OVL_PATH_UPPER = (1 << 1), + __OVL_PATH_MERGE = (1 << 2), +}; + +#define OVL_TYPE_UPPER(type) ((type) & __OVL_PATH_UPPER) +#define OVL_TYPE_MERGE(type) ((type) & __OVL_PATH_MERGE) +#define OVL_TYPE_PURE_UPPER(type) ((type) & __OVL_PATH_PURE) +#define OVL_TYPE_MERGE_OR_LOWER(type) \ + (OVL_TYPE_MERGE(type) || !OVL_TYPE_UPPER(type)) + +#define OVL_XATTR_PRE_NAME "trusted.overlay." +#define OVL_XATTR_PRE_LEN 16 +#define OVL_XATTR_OPAQUE OVL_XATTR_PRE_NAME"opaque" + +static inline int ovl_do_rmdir(struct inode *dir, struct dentry *dentry) +{ + int err = vfs_rmdir(dir, dentry); + pr_debug("rmdir(%pd2) = %i\n", dentry, err); + return err; +} + +static inline int ovl_do_unlink(struct inode *dir, struct dentry *dentry) +{ + int err = vfs_unlink(dir, dentry, NULL); + pr_debug("unlink(%pd2) = %i\n", dentry, err); + return err; +} + +static inline int ovl_do_link(struct dentry *old_dentry, struct inode *dir, + struct dentry *new_dentry, bool debug) +{ + int err = vfs_link(old_dentry, dir, new_dentry, NULL); + if (debug) { + pr_debug("link(%pd2, %pd2) = %i\n", + old_dentry, new_dentry, err); + } + return err; +} + +static inline int ovl_do_create(struct inode *dir, struct dentry *dentry, + umode_t mode, bool debug) +{ + int err = vfs_create(dir, dentry, mode, true); + if (debug) + pr_debug("create(%pd2, 0%o) = %i\n", dentry, mode, err); + return err; +} + +static inline int ovl_do_mkdir(struct inode *dir, struct dentry *dentry, + umode_t mode, bool debug) +{ + int err = vfs_mkdir(dir, dentry, mode); + if (debug) + pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, err); + return err; +} + +static inline int ovl_do_mknod(struct inode *dir, struct dentry *dentry, + umode_t mode, dev_t dev, bool debug) +{ + int err = vfs_mknod(dir, dentry, mode, dev); + if (debug) { + pr_debug("mknod(%pd2, 0%o, 0%o) = %i\n", + dentry, mode, dev, err); + } + return err; +} + +static inline int ovl_do_symlink(struct inode *dir, struct dentry *dentry, + const char *oldname, bool debug) +{ + int err = vfs_symlink(dir, dentry, oldname); + if (debug) + pr_debug("symlink(\"%s\", %pd2) = %i\n", oldname, dentry, err); + return err; +} + +static inline int ovl_do_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) +{ + int err = vfs_setxattr(dentry, name, value, size, flags); + pr_debug("setxattr(%pd2, \"%s\", \"%*s\", 0x%x) = %i\n", + dentry, name, (int) size, (char *) value, flags, err); + return err; +} + +static inline int ovl_do_removexattr(struct dentry *dentry, const char *name) +{ + int err = vfs_removexattr(dentry, name); + pr_debug("removexattr(%pd2, \"%s\") = %i\n", dentry, name, err); + return err; +} + +static inline int ovl_do_rename(struct inode *olddir, struct dentry *olddentry, + struct inode *newdir, struct dentry *newdentry, + unsigned int flags) +{ + int err; + + pr_debug("rename2(%pd2, %pd2, 0x%x)\n", + olddentry, newdentry, flags); + + err = vfs_rename(olddir, olddentry, newdir, newdentry, NULL, flags); + + if (err) { + pr_debug("...rename2(%pd2, %pd2, ...) = %i\n", + olddentry, newdentry, err); + } + return err; +} + +static inline int ovl_do_whiteout(struct inode *dir, struct dentry *dentry) +{ + int err = vfs_whiteout(dir, dentry); + pr_debug("whiteout(%pd2) = %i\n", dentry, err); + return err; +} + +enum ovl_path_type ovl_path_type(struct dentry *dentry); +u64 ovl_dentry_version_get(struct dentry *dentry); +void ovl_dentry_version_inc(struct dentry *dentry); +void ovl_path_upper(struct dentry *dentry, struct path *path); +void ovl_path_lower(struct dentry *dentry, struct path *path); +enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path); +int ovl_path_next(int idx, struct dentry *dentry, struct path *path); +struct dentry *ovl_dentry_upper(struct dentry *dentry); +struct dentry *ovl_dentry_lower(struct dentry *dentry); +struct dentry *ovl_dentry_real(struct dentry *dentry); +struct dentry *ovl_entry_real(struct ovl_entry *oe, bool *is_upper); +struct ovl_dir_cache *ovl_dir_cache(struct dentry *dentry); +void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache); +struct dentry *ovl_workdir(struct dentry *dentry); +int ovl_want_write(struct dentry *dentry); +void ovl_drop_write(struct dentry *dentry); +bool ovl_dentry_is_opaque(struct dentry *dentry); +void ovl_dentry_set_opaque(struct dentry *dentry, bool opaque); +bool ovl_is_whiteout(struct dentry *dentry); +void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry); +struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags); +struct file *ovl_path_open(struct path *path, int flags); + +struct dentry *ovl_upper_create(struct dentry *upperdir, struct dentry *dentry, + struct kstat *stat, const char *link); + +/* readdir.c */ +extern const struct file_operations ovl_dir_operations; +int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list); +void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list); +void ovl_cache_free(struct list_head *list); + +/* inode.c */ +int ovl_setattr(struct dentry *dentry, struct iattr *attr); +int ovl_permission(struct inode *inode, int mask); +int ovl_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags); +ssize_t ovl_getxattr(struct dentry *dentry, const char *name, + void *value, size_t size); +ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size); +int ovl_removexattr(struct dentry *dentry, const char *name); + +struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, + struct ovl_entry *oe); +static inline void ovl_copyattr(struct inode *from, struct inode *to) +{ + to->i_uid = from->i_uid; + to->i_gid = from->i_gid; +} + +/* dir.c */ +extern const struct inode_operations ovl_dir_inode_operations; +struct dentry *ovl_lookup_temp(struct dentry *workdir, struct dentry *dentry); +int ovl_create_real(struct inode *dir, struct dentry *newdentry, + struct kstat *stat, const char *link, + struct dentry *hardlink, bool debug); +void ovl_cleanup(struct inode *dir, struct dentry *dentry); + +/* copy_up.c */ +int ovl_copy_up(struct dentry *dentry); +int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, + struct path *lowerpath, struct kstat *stat, + struct iattr *attr); +int ovl_copy_xattr(struct dentry *old, struct dentry *new); +int ovl_set_attr(struct dentry *upper, struct kstat *stat); diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c new file mode 100644 index 000000000000..907870e81a72 --- /dev/null +++ b/fs/overlayfs/readdir.c @@ -0,0 +1,557 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <linux/fs.h> +#include <linux/slab.h> +#include <linux/namei.h> +#include <linux/file.h> +#include <linux/xattr.h> +#include <linux/rbtree.h> +#include <linux/security.h> +#include <linux/cred.h> +#include "overlayfs.h" + +struct ovl_cache_entry { + unsigned int len; + unsigned int type; + u64 ino; + struct list_head l_node; + struct rb_node node; + bool is_whiteout; + char name[]; +}; + +struct ovl_dir_cache { + long refcount; + u64 version; + struct list_head entries; +}; + +struct ovl_readdir_data { + struct dir_context ctx; + bool is_merge; + struct rb_root root; + struct list_head *list; + struct list_head middle; + struct dentry *dir; + int count; + int err; +}; + +struct ovl_dir_file { + bool is_real; + bool is_upper; + struct ovl_dir_cache *cache; + struct list_head *cursor; + struct file *realfile; + struct file *upperfile; +}; + +static struct ovl_cache_entry *ovl_cache_entry_from_node(struct rb_node *n) +{ + return container_of(n, struct ovl_cache_entry, node); +} + +static struct ovl_cache_entry *ovl_cache_entry_find(struct rb_root *root, + const char *name, int len) +{ + struct rb_node *node = root->rb_node; + int cmp; + + while (node) { + struct ovl_cache_entry *p = ovl_cache_entry_from_node(node); + + cmp = strncmp(name, p->name, len); + if (cmp > 0) + node = p->node.rb_right; + else if (cmp < 0 || len < p->len) + node = p->node.rb_left; + else + return p; + } + + return NULL; +} + +static struct ovl_cache_entry *ovl_cache_entry_new(struct dentry *dir, + const char *name, int len, + u64 ino, unsigned int d_type) +{ + struct ovl_cache_entry *p; + size_t size = offsetof(struct ovl_cache_entry, name[len + 1]); + + p = kmalloc(size, GFP_KERNEL); + if (!p) + return NULL; + + memcpy(p->name, name, len); + p->name[len] = '\0'; + p->len = len; + p->type = d_type; + p->ino = ino; + p->is_whiteout = false; + + if (d_type == DT_CHR) { + struct dentry *dentry; + const struct cred *old_cred; + struct cred *override_cred; + + override_cred = prepare_creds(); + if (!override_cred) { + kfree(p); + return NULL; + } + + /* + * CAP_DAC_OVERRIDE for lookup + */ + cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE); + old_cred = override_creds(override_cred); + + dentry = lookup_one_len(name, dir, len); + if (!IS_ERR(dentry)) { + p->is_whiteout = ovl_is_whiteout(dentry); + dput(dentry); + } + revert_creds(old_cred); + put_cred(override_cred); + } + return p; +} + +static int ovl_cache_entry_add_rb(struct ovl_readdir_data *rdd, + const char *name, int len, u64 ino, + unsigned int d_type) +{ + struct rb_node **newp = &rdd->root.rb_node; + struct rb_node *parent = NULL; + struct ovl_cache_entry *p; + + while (*newp) { + int cmp; + struct ovl_cache_entry *tmp; + + parent = *newp; + tmp = ovl_cache_entry_from_node(*newp); + cmp = strncmp(name, tmp->name, len); + if (cmp > 0) + newp = &tmp->node.rb_right; + else if (cmp < 0 || len < tmp->len) + newp = &tmp->node.rb_left; + else + return 0; + } + + p = ovl_cache_entry_new(rdd->dir, name, len, ino, d_type); + if (p == NULL) + return -ENOMEM; + + list_add_tail(&p->l_node, rdd->list); + rb_link_node(&p->node, parent, newp); + rb_insert_color(&p->node, &rdd->root); + + return 0; +} + +static int ovl_fill_lower(struct ovl_readdir_data *rdd, + const char *name, int namelen, + loff_t offset, u64 ino, unsigned int d_type) +{ + struct ovl_cache_entry *p; + + p = ovl_cache_entry_find(&rdd->root, name, namelen); + if (p) { + list_move_tail(&p->l_node, &rdd->middle); + } else { + p = ovl_cache_entry_new(rdd->dir, name, namelen, ino, d_type); + if (p == NULL) + rdd->err = -ENOMEM; + else + list_add_tail(&p->l_node, &rdd->middle); + } + + return rdd->err; +} + +void ovl_cache_free(struct list_head *list) +{ + struct ovl_cache_entry *p; + struct ovl_cache_entry *n; + + list_for_each_entry_safe(p, n, list, l_node) + kfree(p); + + INIT_LIST_HEAD(list); +} + +static void ovl_cache_put(struct ovl_dir_file *od, struct dentry *dentry) +{ + struct ovl_dir_cache *cache = od->cache; + + WARN_ON(cache->refcount <= 0); + cache->refcount--; + if (!cache->refcount) { + if (ovl_dir_cache(dentry) == cache) + ovl_set_dir_cache(dentry, NULL); + + ovl_cache_free(&cache->entries); + kfree(cache); + } +} + +static int ovl_fill_merge(struct dir_context *ctx, const char *name, + int namelen, loff_t offset, u64 ino, + unsigned int d_type) +{ + struct ovl_readdir_data *rdd = + container_of(ctx, struct ovl_readdir_data, ctx); + + rdd->count++; + if (!rdd->is_merge) + return ovl_cache_entry_add_rb(rdd, name, namelen, ino, d_type); + else + return ovl_fill_lower(rdd, name, namelen, offset, ino, d_type); +} + +static inline int ovl_dir_read(struct path *realpath, + struct ovl_readdir_data *rdd) +{ + struct file *realfile; + int err; + + realfile = ovl_path_open(realpath, O_RDONLY | O_DIRECTORY); + if (IS_ERR(realfile)) + return PTR_ERR(realfile); + + rdd->dir = realpath->dentry; + rdd->ctx.pos = 0; + do { + rdd->count = 0; + rdd->err = 0; + err = iterate_dir(realfile, &rdd->ctx); + if (err >= 0) + err = rdd->err; + } while (!err && rdd->count); + fput(realfile); + + return err; +} + +static void ovl_dir_reset(struct file *file) +{ + struct ovl_dir_file *od = file->private_data; + struct ovl_dir_cache *cache = od->cache; + struct dentry *dentry = file->f_path.dentry; + enum ovl_path_type type = ovl_path_type(dentry); + + if (cache && ovl_dentry_version_get(dentry) != cache->version) { + ovl_cache_put(od, dentry); + od->cache = NULL; + od->cursor = NULL; + } + WARN_ON(!od->is_real && !OVL_TYPE_MERGE(type)); + if (od->is_real && OVL_TYPE_MERGE(type)) + od->is_real = false; +} + +static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list) +{ + int err; + struct path realpath; + struct ovl_readdir_data rdd = { + .ctx.actor = ovl_fill_merge, + .list = list, + .root = RB_ROOT, + .is_merge = false, + }; + int idx, next; + + for (idx = 0; idx != -1; idx = next) { + next = ovl_path_next(idx, dentry, &realpath); + + if (next != -1) { + err = ovl_dir_read(&realpath, &rdd); + if (err) + break; + } else { + /* + * Insert lowest layer entries before upper ones, this + * allows offsets to be reasonably constant + */ + list_add(&rdd.middle, rdd.list); + rdd.is_merge = true; + err = ovl_dir_read(&realpath, &rdd); + list_del(&rdd.middle); + } + } + return err; +} + +static void ovl_seek_cursor(struct ovl_dir_file *od, loff_t pos) +{ + struct list_head *p; + loff_t off = 0; + + list_for_each(p, &od->cache->entries) { + if (off >= pos) + break; + off++; + } + /* Cursor is safe since the cache is stable */ + od->cursor = p; +} + +static struct ovl_dir_cache *ovl_cache_get(struct dentry *dentry) +{ + int res; + struct ovl_dir_cache *cache; + + cache = ovl_dir_cache(dentry); + if (cache && ovl_dentry_version_get(dentry) == cache->version) { + cache->refcount++; + return cache; + } + ovl_set_dir_cache(dentry, NULL); + + cache = kzalloc(sizeof(struct ovl_dir_cache), GFP_KERNEL); + if (!cache) + return ERR_PTR(-ENOMEM); + + cache->refcount = 1; + INIT_LIST_HEAD(&cache->entries); + + res = ovl_dir_read_merged(dentry, &cache->entries); + if (res) { + ovl_cache_free(&cache->entries); + kfree(cache); + return ERR_PTR(res); + } + + cache->version = ovl_dentry_version_get(dentry); + ovl_set_dir_cache(dentry, cache); + + return cache; +} + +static int ovl_iterate(struct file *file, struct dir_context *ctx) +{ + struct ovl_dir_file *od = file->private_data; + struct dentry *dentry = file->f_path.dentry; + struct ovl_cache_entry *p; + + if (!ctx->pos) + ovl_dir_reset(file); + + if (od->is_real) + return iterate_dir(od->realfile, ctx); + + if (!od->cache) { + struct ovl_dir_cache *cache; + + cache = ovl_cache_get(dentry); + if (IS_ERR(cache)) + return PTR_ERR(cache); + + od->cache = cache; + ovl_seek_cursor(od, ctx->pos); + } + + while (od->cursor != &od->cache->entries) { + p = list_entry(od->cursor, struct ovl_cache_entry, l_node); + if (!p->is_whiteout) + if (!dir_emit(ctx, p->name, p->len, p->ino, p->type)) + break; + od->cursor = p->l_node.next; + ctx->pos++; + } + return 0; +} + +static loff_t ovl_dir_llseek(struct file *file, loff_t offset, int origin) +{ + loff_t res; + struct ovl_dir_file *od = file->private_data; + + mutex_lock(&file_inode(file)->i_mutex); + if (!file->f_pos) + ovl_dir_reset(file); + + if (od->is_real) { + res = vfs_llseek(od->realfile, offset, origin); + file->f_pos = od->realfile->f_pos; + } else { + res = -EINVAL; + + switch (origin) { + case SEEK_CUR: + offset += file->f_pos; + break; + case SEEK_SET: + break; + default: + goto out_unlock; + } + if (offset < 0) + goto out_unlock; + + if (offset != file->f_pos) { + file->f_pos = offset; + if (od->cache) + ovl_seek_cursor(od, offset); + } + res = offset; + } +out_unlock: + mutex_unlock(&file_inode(file)->i_mutex); + + return res; +} + +static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end, + int datasync) +{ + struct ovl_dir_file *od = file->private_data; + struct dentry *dentry = file->f_path.dentry; + struct file *realfile = od->realfile; + + /* + * Need to check if we started out being a lower dir, but got copied up + */ + if (!od->is_upper && OVL_TYPE_UPPER(ovl_path_type(dentry))) { + struct inode *inode = file_inode(file); + + realfile = lockless_dereference(od->upperfile); + if (!realfile) { + struct path upperpath; + + ovl_path_upper(dentry, &upperpath); + realfile = ovl_path_open(&upperpath, O_RDONLY); + smp_mb__before_spinlock(); + mutex_lock(&inode->i_mutex); + if (!od->upperfile) { + if (IS_ERR(realfile)) { + mutex_unlock(&inode->i_mutex); + return PTR_ERR(realfile); + } + od->upperfile = realfile; + } else { + /* somebody has beaten us to it */ + if (!IS_ERR(realfile)) + fput(realfile); + realfile = od->upperfile; + } + mutex_unlock(&inode->i_mutex); + } + } + + return vfs_fsync_range(realfile, start, end, datasync); +} + +static int ovl_dir_release(struct inode *inode, struct file *file) +{ + struct ovl_dir_file *od = file->private_data; + + if (od->cache) { + mutex_lock(&inode->i_mutex); + ovl_cache_put(od, file->f_path.dentry); + mutex_unlock(&inode->i_mutex); + } + fput(od->realfile); + if (od->upperfile) + fput(od->upperfile); + kfree(od); + + return 0; +} + +static int ovl_dir_open(struct inode *inode, struct file *file) +{ + struct path realpath; + struct file *realfile; + struct ovl_dir_file *od; + enum ovl_path_type type; + + od = kzalloc(sizeof(struct ovl_dir_file), GFP_KERNEL); + if (!od) + return -ENOMEM; + + type = ovl_path_real(file->f_path.dentry, &realpath); + realfile = ovl_path_open(&realpath, file->f_flags); + if (IS_ERR(realfile)) { + kfree(od); + return PTR_ERR(realfile); + } + od->realfile = realfile; + od->is_real = !OVL_TYPE_MERGE(type); + od->is_upper = OVL_TYPE_UPPER(type); + file->private_data = od; + + return 0; +} + +const struct file_operations ovl_dir_operations = { + .read = generic_read_dir, + .open = ovl_dir_open, + .iterate = ovl_iterate, + .llseek = ovl_dir_llseek, + .fsync = ovl_dir_fsync, + .release = ovl_dir_release, +}; + +int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list) +{ + int err; + struct ovl_cache_entry *p; + + err = ovl_dir_read_merged(dentry, list); + if (err) + return err; + + err = 0; + + list_for_each_entry(p, list, l_node) { + if (p->is_whiteout) + continue; + + if (p->name[0] == '.') { + if (p->len == 1) + continue; + if (p->len == 2 && p->name[1] == '.') + continue; + } + err = -ENOTEMPTY; + break; + } + + return err; +} + +void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list) +{ + struct ovl_cache_entry *p; + + mutex_lock_nested(&upper->d_inode->i_mutex, I_MUTEX_CHILD); + list_for_each_entry(p, list, l_node) { + struct dentry *dentry; + + if (!p->is_whiteout) + continue; + + dentry = lookup_one_len(p->name, upper, p->len); + if (IS_ERR(dentry)) { + pr_err("overlayfs: lookup '%s/%.*s' failed (%i)\n", + upper->d_name.name, p->len, p->name, + (int) PTR_ERR(dentry)); + continue; + } + ovl_cleanup(upper->d_inode, dentry); + dput(dentry); + } + mutex_unlock(&upper->d_inode->i_mutex); +} diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c new file mode 100644 index 000000000000..5f0d1993e6e3 --- /dev/null +++ b/fs/overlayfs/super.c @@ -0,0 +1,1046 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <linux/fs.h> +#include <linux/namei.h> +#include <linux/xattr.h> +#include <linux/security.h> +#include <linux/mount.h> +#include <linux/slab.h> +#include <linux/parser.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/statfs.h> +#include <linux/seq_file.h> +#include "overlayfs.h" + +MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>"); +MODULE_DESCRIPTION("Overlay filesystem"); +MODULE_LICENSE("GPL"); + +#define OVERLAYFS_SUPER_MAGIC 0x794c7630 + +struct ovl_config { + char *lowerdir; + char *upperdir; + char *workdir; +}; + +/* private information held for overlayfs's superblock */ +struct ovl_fs { + struct vfsmount *upper_mnt; + unsigned numlower; + struct vfsmount **lower_mnt; + struct dentry *workdir; + long lower_namelen; + /* pathnames of lower and upper dirs, for show_options */ + struct ovl_config config; +}; + +struct ovl_dir_cache; + +/* private information held for every overlayfs dentry */ +struct ovl_entry { + struct dentry *__upperdentry; + struct ovl_dir_cache *cache; + union { + struct { + u64 version; + bool opaque; + }; + struct rcu_head rcu; + }; + unsigned numlower; + struct path lowerstack[]; +}; + +#define OVL_MAX_STACK 500 + +static struct dentry *__ovl_dentry_lower(struct ovl_entry *oe) +{ + return oe->numlower ? oe->lowerstack[0].dentry : NULL; +} + +enum ovl_path_type ovl_path_type(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + enum ovl_path_type type = 0; + + if (oe->__upperdentry) { + type = __OVL_PATH_UPPER; + + if (oe->numlower) { + if (S_ISDIR(dentry->d_inode->i_mode)) + type |= __OVL_PATH_MERGE; + } else if (!oe->opaque) { + type |= __OVL_PATH_PURE; + } + } else { + if (oe->numlower > 1) + type |= __OVL_PATH_MERGE; + } + return type; +} + +static struct dentry *ovl_upperdentry_dereference(struct ovl_entry *oe) +{ + return lockless_dereference(oe->__upperdentry); +} + +void ovl_path_upper(struct dentry *dentry, struct path *path) +{ + struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + struct ovl_entry *oe = dentry->d_fsdata; + + path->mnt = ofs->upper_mnt; + path->dentry = ovl_upperdentry_dereference(oe); +} + +enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path) +{ + enum ovl_path_type type = ovl_path_type(dentry); + + if (!OVL_TYPE_UPPER(type)) + ovl_path_lower(dentry, path); + else + ovl_path_upper(dentry, path); + + return type; +} + +struct dentry *ovl_dentry_upper(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + return ovl_upperdentry_dereference(oe); +} + +struct dentry *ovl_dentry_lower(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + return __ovl_dentry_lower(oe); +} + +struct dentry *ovl_dentry_real(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + struct dentry *realdentry; + + realdentry = ovl_upperdentry_dereference(oe); + if (!realdentry) + realdentry = __ovl_dentry_lower(oe); + + return realdentry; +} + +struct dentry *ovl_entry_real(struct ovl_entry *oe, bool *is_upper) +{ + struct dentry *realdentry; + + realdentry = ovl_upperdentry_dereference(oe); + if (realdentry) { + *is_upper = true; + } else { + realdentry = __ovl_dentry_lower(oe); + *is_upper = false; + } + return realdentry; +} + +struct ovl_dir_cache *ovl_dir_cache(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + return oe->cache; +} + +void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + oe->cache = cache; +} + +void ovl_path_lower(struct dentry *dentry, struct path *path) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + *path = oe->numlower ? oe->lowerstack[0] : (struct path) { NULL, NULL }; +} + +int ovl_want_write(struct dentry *dentry) +{ + struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + return mnt_want_write(ofs->upper_mnt); +} + +void ovl_drop_write(struct dentry *dentry) +{ + struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + mnt_drop_write(ofs->upper_mnt); +} + +struct dentry *ovl_workdir(struct dentry *dentry) +{ + struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + return ofs->workdir; +} + +bool ovl_dentry_is_opaque(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + return oe->opaque; +} + +void ovl_dentry_set_opaque(struct dentry *dentry, bool opaque) +{ + struct ovl_entry *oe = dentry->d_fsdata; + oe->opaque = opaque; +} + +void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + WARN_ON(!mutex_is_locked(&upperdentry->d_parent->d_inode->i_mutex)); + WARN_ON(oe->__upperdentry); + BUG_ON(!upperdentry->d_inode); + /* + * Make sure upperdentry is consistent before making it visible to + * ovl_upperdentry_dereference(). + */ + smp_wmb(); + oe->__upperdentry = upperdentry; +} + +void ovl_dentry_version_inc(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + WARN_ON(!mutex_is_locked(&dentry->d_inode->i_mutex)); + oe->version++; +} + +u64 ovl_dentry_version_get(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + WARN_ON(!mutex_is_locked(&dentry->d_inode->i_mutex)); + return oe->version; +} + +bool ovl_is_whiteout(struct dentry *dentry) +{ + struct inode *inode = dentry->d_inode; + + return inode && IS_WHITEOUT(inode); +} + +static bool ovl_is_opaquedir(struct dentry *dentry) +{ + int res; + char val; + struct inode *inode = dentry->d_inode; + + if (!S_ISDIR(inode->i_mode) || !inode->i_op->getxattr) + return false; + + res = inode->i_op->getxattr(dentry, OVL_XATTR_OPAQUE, &val, 1); + if (res == 1 && val == 'y') + return true; + + return false; +} + +static void ovl_dentry_release(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + if (oe) { + unsigned int i; + + dput(oe->__upperdentry); + for (i = 0; i < oe->numlower; i++) + dput(oe->lowerstack[i].dentry); + kfree_rcu(oe, rcu); + } +} + +static const struct dentry_operations ovl_dentry_operations = { + .d_release = ovl_dentry_release, +}; + +static struct ovl_entry *ovl_alloc_entry(unsigned int numlower) +{ + size_t size = offsetof(struct ovl_entry, lowerstack[numlower]); + struct ovl_entry *oe = kzalloc(size, GFP_KERNEL); + + if (oe) + oe->numlower = numlower; + + return oe; +} + +static inline struct dentry *ovl_lookup_real(struct dentry *dir, + struct qstr *name) +{ + struct dentry *dentry; + + mutex_lock(&dir->d_inode->i_mutex); + dentry = lookup_one_len(name->name, dir, name->len); + mutex_unlock(&dir->d_inode->i_mutex); + + if (IS_ERR(dentry)) { + if (PTR_ERR(dentry) == -ENOENT) + dentry = NULL; + } else if (!dentry->d_inode) { + dput(dentry); + dentry = NULL; + } + return dentry; +} + +/* + * Returns next layer in stack starting from top. + * Returns -1 if this is the last layer. + */ +int ovl_path_next(int idx, struct dentry *dentry, struct path *path) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + BUG_ON(idx < 0); + if (idx == 0) { + ovl_path_upper(dentry, path); + if (path->dentry) + return oe->numlower ? 1 : -1; + idx++; + } + BUG_ON(idx > oe->numlower); + *path = oe->lowerstack[idx - 1]; + + return (idx < oe->numlower) ? idx + 1 : -1; +} + +struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags) +{ + struct ovl_entry *oe; + struct ovl_entry *poe = dentry->d_parent->d_fsdata; + struct path *stack = NULL; + struct dentry *upperdir, *upperdentry = NULL; + unsigned int ctr = 0; + struct inode *inode = NULL; + bool upperopaque = false; + struct dentry *this, *prev = NULL; + unsigned int i; + int err; + + upperdir = ovl_upperdentry_dereference(poe); + if (upperdir) { + this = ovl_lookup_real(upperdir, &dentry->d_name); + err = PTR_ERR(this); + if (IS_ERR(this)) + goto out; + + if (this) { + if (ovl_is_whiteout(this)) { + dput(this); + this = NULL; + upperopaque = true; + } else if (poe->numlower && ovl_is_opaquedir(this)) { + upperopaque = true; + } + } + upperdentry = prev = this; + } + + if (!upperopaque && poe->numlower) { + err = -ENOMEM; + stack = kcalloc(poe->numlower, sizeof(struct path), GFP_KERNEL); + if (!stack) + goto out_put_upper; + } + + for (i = 0; !upperopaque && i < poe->numlower; i++) { + bool opaque = false; + struct path lowerpath = poe->lowerstack[i]; + + this = ovl_lookup_real(lowerpath.dentry, &dentry->d_name); + err = PTR_ERR(this); + if (IS_ERR(this)) { + /* + * If it's positive, then treat ENAMETOOLONG as ENOENT. + */ + if (err == -ENAMETOOLONG && (upperdentry || ctr)) + continue; + goto out_put; + } + if (!this) + continue; + if (ovl_is_whiteout(this)) { + dput(this); + break; + } + /* + * Only makes sense to check opaque dir if this is not the + * lowermost layer. + */ + if (i < poe->numlower - 1 && ovl_is_opaquedir(this)) + opaque = true; + + if (prev && (!S_ISDIR(prev->d_inode->i_mode) || + !S_ISDIR(this->d_inode->i_mode))) { + /* + * FIXME: check for upper-opaqueness maybe better done + * in remove code. + */ + if (prev == upperdentry) + upperopaque = true; + dput(this); + break; + } + /* + * If this is a non-directory then stop here. + */ + if (!S_ISDIR(this->d_inode->i_mode)) + opaque = true; + + stack[ctr].dentry = this; + stack[ctr].mnt = lowerpath.mnt; + ctr++; + prev = this; + if (opaque) + break; + } + + oe = ovl_alloc_entry(ctr); + err = -ENOMEM; + if (!oe) + goto out_put; + + if (upperdentry || ctr) { + struct dentry *realdentry; + + realdentry = upperdentry ? upperdentry : stack[0].dentry; + + err = -ENOMEM; + inode = ovl_new_inode(dentry->d_sb, realdentry->d_inode->i_mode, + oe); + if (!inode) + goto out_free_oe; + ovl_copyattr(realdentry->d_inode, inode); + } + + oe->opaque = upperopaque; + oe->__upperdentry = upperdentry; + memcpy(oe->lowerstack, stack, sizeof(struct path) * ctr); + kfree(stack); + dentry->d_fsdata = oe; + d_add(dentry, inode); + + return NULL; + +out_free_oe: + kfree(oe); +out_put: + for (i = 0; i < ctr; i++) + dput(stack[i].dentry); + kfree(stack); +out_put_upper: + dput(upperdentry); +out: + return ERR_PTR(err); +} + +struct file *ovl_path_open(struct path *path, int flags) +{ + return dentry_open(path, flags, current_cred()); +} + +static void ovl_put_super(struct super_block *sb) +{ + struct ovl_fs *ufs = sb->s_fs_info; + unsigned i; + + dput(ufs->workdir); + mntput(ufs->upper_mnt); + for (i = 0; i < ufs->numlower; i++) + mntput(ufs->lower_mnt[i]); + + kfree(ufs->config.lowerdir); + kfree(ufs->config.upperdir); + kfree(ufs->config.workdir); + kfree(ufs); +} + +/** + * ovl_statfs + * @sb: The overlayfs super block + * @buf: The struct kstatfs to fill in with stats + * + * Get the filesystem statistics. As writes always target the upper layer + * filesystem pass the statfs to the upper filesystem (if it exists) + */ +static int ovl_statfs(struct dentry *dentry, struct kstatfs *buf) +{ + struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + struct dentry *root_dentry = dentry->d_sb->s_root; + struct path path; + int err; + + ovl_path_real(root_dentry, &path); + + err = vfs_statfs(&path, buf); + if (!err) { + buf->f_namelen = max(buf->f_namelen, ofs->lower_namelen); + buf->f_type = OVERLAYFS_SUPER_MAGIC; + } + + return err; +} + +/** + * ovl_show_options + * + * Prints the mount options for a given superblock. + * Returns zero; does not fail. + */ +static int ovl_show_options(struct seq_file *m, struct dentry *dentry) +{ + struct super_block *sb = dentry->d_sb; + struct ovl_fs *ufs = sb->s_fs_info; + + seq_printf(m, ",lowerdir=%s", ufs->config.lowerdir); + if (ufs->config.upperdir) { + seq_printf(m, ",upperdir=%s", ufs->config.upperdir); + seq_printf(m, ",workdir=%s", ufs->config.workdir); + } + return 0; +} + +static int ovl_remount(struct super_block *sb, int *flags, char *data) +{ + struct ovl_fs *ufs = sb->s_fs_info; + + if (!(*flags & MS_RDONLY) && !ufs->upper_mnt) + return -EROFS; + + return 0; +} + +static const struct super_operations ovl_super_operations = { + .put_super = ovl_put_super, + .statfs = ovl_statfs, + .show_options = ovl_show_options, + .remount_fs = ovl_remount, +}; + +enum { + OPT_LOWERDIR, + OPT_UPPERDIR, + OPT_WORKDIR, + OPT_ERR, +}; + +static const match_table_t ovl_tokens = { + {OPT_LOWERDIR, "lowerdir=%s"}, + {OPT_UPPERDIR, "upperdir=%s"}, + {OPT_WORKDIR, "workdir=%s"}, + {OPT_ERR, NULL} +}; + +static char *ovl_next_opt(char **s) +{ + char *sbegin = *s; + char *p; + + if (sbegin == NULL) + return NULL; + + for (p = sbegin; *p; p++) { + if (*p == '\\') { + p++; + if (!*p) + break; + } else if (*p == ',') { + *p = '\0'; + *s = p + 1; + return sbegin; + } + } + *s = NULL; + return sbegin; +} + +static int ovl_parse_opt(char *opt, struct ovl_config *config) +{ + char *p; + + while ((p = ovl_next_opt(&opt)) != NULL) { + int token; + substring_t args[MAX_OPT_ARGS]; + + if (!*p) + continue; + + token = match_token(p, ovl_tokens, args); + switch (token) { + case OPT_UPPERDIR: + kfree(config->upperdir); + config->upperdir = match_strdup(&args[0]); + if (!config->upperdir) + return -ENOMEM; + break; + + case OPT_LOWERDIR: + kfree(config->lowerdir); + config->lowerdir = match_strdup(&args[0]); + if (!config->lowerdir) + return -ENOMEM; + break; + + case OPT_WORKDIR: + kfree(config->workdir); + config->workdir = match_strdup(&args[0]); + if (!config->workdir) + return -ENOMEM; + break; + + default: + pr_err("overlayfs: unrecognized mount option \"%s\" or missing value\n", p); + return -EINVAL; + } + } + + /* Workdir is useless in non-upper mount */ + if (!config->upperdir && config->workdir) { + pr_info("overlayfs: option \"workdir=%s\" is useless in a non-upper mount, ignore\n", + config->workdir); + kfree(config->workdir); + config->workdir = NULL; + } + + return 0; +} + +#define OVL_WORKDIR_NAME "work" + +static struct dentry *ovl_workdir_create(struct vfsmount *mnt, + struct dentry *dentry) +{ + struct inode *dir = dentry->d_inode; + struct dentry *work; + int err; + bool retried = false; + + err = mnt_want_write(mnt); + if (err) + return ERR_PTR(err); + + mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); +retry: + work = lookup_one_len(OVL_WORKDIR_NAME, dentry, + strlen(OVL_WORKDIR_NAME)); + + if (!IS_ERR(work)) { + struct kstat stat = { + .mode = S_IFDIR | 0, + }; + + if (work->d_inode) { + err = -EEXIST; + if (retried) + goto out_dput; + + retried = true; + ovl_cleanup(dir, work); + dput(work); + goto retry; + } + + err = ovl_create_real(dir, work, &stat, NULL, NULL, true); + if (err) + goto out_dput; + } +out_unlock: + mutex_unlock(&dir->i_mutex); + mnt_drop_write(mnt); + + return work; + +out_dput: + dput(work); + work = ERR_PTR(err); + goto out_unlock; +} + +static void ovl_unescape(char *s) +{ + char *d = s; + + for (;; s++, d++) { + if (*s == '\\') + s++; + *d = *s; + if (!*s) + break; + } +} + +static bool ovl_is_allowed_fs_type(struct dentry *root) +{ + const struct dentry_operations *dop = root->d_op; + + /* + * We don't support: + * - automount filesystems + * - filesystems with revalidate (FIXME for lower layer) + * - filesystems with case insensitive names + */ + if (dop && + (dop->d_manage || dop->d_automount || + dop->d_revalidate || dop->d_weak_revalidate || + dop->d_compare || dop->d_hash)) { + return false; + } + return true; +} + +static int ovl_mount_dir_noesc(const char *name, struct path *path) +{ + int err = -EINVAL; + + if (!*name) { + pr_err("overlayfs: empty lowerdir\n"); + goto out; + } + err = kern_path(name, LOOKUP_FOLLOW, path); + if (err) { + pr_err("overlayfs: failed to resolve '%s': %i\n", name, err); + goto out; + } + err = -EINVAL; + if (!ovl_is_allowed_fs_type(path->dentry)) { + pr_err("overlayfs: filesystem on '%s' not supported\n", name); + goto out_put; + } + if (!S_ISDIR(path->dentry->d_inode->i_mode)) { + pr_err("overlayfs: '%s' not a directory\n", name); + goto out_put; + } + return 0; + +out_put: + path_put(path); +out: + return err; +} + +static int ovl_mount_dir(const char *name, struct path *path) +{ + int err = -ENOMEM; + char *tmp = kstrdup(name, GFP_KERNEL); + + if (tmp) { + ovl_unescape(tmp); + err = ovl_mount_dir_noesc(tmp, path); + kfree(tmp); + } + return err; +} + +static int ovl_lower_dir(const char *name, struct path *path, long *namelen, + int *stack_depth) +{ + int err; + struct kstatfs statfs; + + err = ovl_mount_dir_noesc(name, path); + if (err) + goto out; + + err = vfs_statfs(path, &statfs); + if (err) { + pr_err("overlayfs: statfs failed on '%s'\n", name); + goto out_put; + } + *namelen = max(*namelen, statfs.f_namelen); + *stack_depth = max(*stack_depth, path->mnt->mnt_sb->s_stack_depth); + + return 0; + +out_put: + path_put(path); +out: + return err; +} + +/* Workdir should not be subdir of upperdir and vice versa */ +static bool ovl_workdir_ok(struct dentry *workdir, struct dentry *upperdir) +{ + bool ok = false; + + if (workdir != upperdir) { + ok = (lock_rename(workdir, upperdir) == NULL); + unlock_rename(workdir, upperdir); + } + return ok; +} + +static unsigned int ovl_split_lowerdirs(char *str) +{ + unsigned int ctr = 1; + char *s, *d; + + for (s = d = str;; s++, d++) { + if (*s == '\\') { + s++; + } else if (*s == ':') { + *d = '\0'; + ctr++; + continue; + } + *d = *s; + if (!*s) + break; + } + return ctr; +} + +static int ovl_fill_super(struct super_block *sb, void *data, int silent) +{ + struct path upperpath = { NULL, NULL }; + struct path workpath = { NULL, NULL }; + struct dentry *root_dentry; + struct ovl_entry *oe; + struct ovl_fs *ufs; + struct path *stack = NULL; + char *lowertmp; + char *lower; + unsigned int numlower; + unsigned int stacklen = 0; + unsigned int i; + int err; + + err = -ENOMEM; + ufs = kzalloc(sizeof(struct ovl_fs), GFP_KERNEL); + if (!ufs) + goto out; + + err = ovl_parse_opt((char *) data, &ufs->config); + if (err) + goto out_free_config; + + err = -EINVAL; + if (!ufs->config.lowerdir) { + pr_err("overlayfs: missing 'lowerdir'\n"); + goto out_free_config; + } + + sb->s_stack_depth = 0; + if (ufs->config.upperdir) { + if (!ufs->config.workdir) { + pr_err("overlayfs: missing 'workdir'\n"); + goto out_free_config; + } + + err = ovl_mount_dir(ufs->config.upperdir, &upperpath); + if (err) + goto out_free_config; + + /* Upper fs should not be r/o */ + if (upperpath.mnt->mnt_sb->s_flags & MS_RDONLY) { + pr_err("overlayfs: upper fs is r/o, try multi-lower layers mount\n"); + err = -EINVAL; + goto out_put_upperpath; + } + + err = ovl_mount_dir(ufs->config.workdir, &workpath); + if (err) + goto out_put_upperpath; + + err = -EINVAL; + if (upperpath.mnt != workpath.mnt) { + pr_err("overlayfs: workdir and upperdir must reside under the same mount\n"); + goto out_put_workpath; + } + if (!ovl_workdir_ok(workpath.dentry, upperpath.dentry)) { + pr_err("overlayfs: workdir and upperdir must be separate subtrees\n"); + goto out_put_workpath; + } + sb->s_stack_depth = upperpath.mnt->mnt_sb->s_stack_depth; + } + err = -ENOMEM; + lowertmp = kstrdup(ufs->config.lowerdir, GFP_KERNEL); + if (!lowertmp) + goto out_put_workpath; + + err = -EINVAL; + stacklen = ovl_split_lowerdirs(lowertmp); + if (stacklen > OVL_MAX_STACK) { + pr_err("overlayfs: too many lower directries, limit is %d\n", + OVL_MAX_STACK); + goto out_free_lowertmp; + } else if (!ufs->config.upperdir && stacklen == 1) { + pr_err("overlayfs: at least 2 lowerdir are needed while upperdir nonexistent\n"); + goto out_free_lowertmp; + } + + stack = kcalloc(stacklen, sizeof(struct path), GFP_KERNEL); + if (!stack) + goto out_free_lowertmp; + + lower = lowertmp; + for (numlower = 0; numlower < stacklen; numlower++) { + err = ovl_lower_dir(lower, &stack[numlower], + &ufs->lower_namelen, &sb->s_stack_depth); + if (err) + goto out_put_lowerpath; + + lower = strchr(lower, '\0') + 1; + } + + err = -EINVAL; + sb->s_stack_depth++; + if (sb->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) { + pr_err("overlayfs: maximum fs stacking depth exceeded\n"); + goto out_put_lowerpath; + } + + if (ufs->config.upperdir) { + ufs->upper_mnt = clone_private_mount(&upperpath); + err = PTR_ERR(ufs->upper_mnt); + if (IS_ERR(ufs->upper_mnt)) { + pr_err("overlayfs: failed to clone upperpath\n"); + goto out_put_lowerpath; + } + + ufs->workdir = ovl_workdir_create(ufs->upper_mnt, workpath.dentry); + err = PTR_ERR(ufs->workdir); + if (IS_ERR(ufs->workdir)) { + pr_err("overlayfs: failed to create directory %s/%s\n", + ufs->config.workdir, OVL_WORKDIR_NAME); + goto out_put_upper_mnt; + } + } + + err = -ENOMEM; + ufs->lower_mnt = kcalloc(numlower, sizeof(struct vfsmount *), GFP_KERNEL); + if (ufs->lower_mnt == NULL) + goto out_put_workdir; + for (i = 0; i < numlower; i++) { + struct vfsmount *mnt = clone_private_mount(&stack[i]); + + err = PTR_ERR(mnt); + if (IS_ERR(mnt)) { + pr_err("overlayfs: failed to clone lowerpath\n"); + goto out_put_lower_mnt; + } + /* + * Make lower_mnt R/O. That way fchmod/fchown on lower file + * will fail instead of modifying lower fs. + */ + mnt->mnt_flags |= MNT_READONLY; + + ufs->lower_mnt[ufs->numlower] = mnt; + ufs->numlower++; + } + + /* If the upper fs is nonexistent, we mark overlayfs r/o too */ + if (!ufs->upper_mnt) + sb->s_flags |= MS_RDONLY; + + sb->s_d_op = &ovl_dentry_operations; + + err = -ENOMEM; + oe = ovl_alloc_entry(numlower); + if (!oe) + goto out_put_lower_mnt; + + root_dentry = d_make_root(ovl_new_inode(sb, S_IFDIR, oe)); + if (!root_dentry) + goto out_free_oe; + + mntput(upperpath.mnt); + for (i = 0; i < numlower; i++) + mntput(stack[i].mnt); + path_put(&workpath); + kfree(lowertmp); + + oe->__upperdentry = upperpath.dentry; + for (i = 0; i < numlower; i++) { + oe->lowerstack[i].dentry = stack[i].dentry; + oe->lowerstack[i].mnt = ufs->lower_mnt[i]; + } + + root_dentry->d_fsdata = oe; + + sb->s_magic = OVERLAYFS_SUPER_MAGIC; + sb->s_op = &ovl_super_operations; + sb->s_root = root_dentry; + sb->s_fs_info = ufs; + + return 0; + +out_free_oe: + kfree(oe); +out_put_lower_mnt: + for (i = 0; i < ufs->numlower; i++) + mntput(ufs->lower_mnt[i]); + kfree(ufs->lower_mnt); +out_put_workdir: + dput(ufs->workdir); +out_put_upper_mnt: + mntput(ufs->upper_mnt); +out_put_lowerpath: + for (i = 0; i < numlower; i++) + path_put(&stack[i]); + kfree(stack); +out_free_lowertmp: + kfree(lowertmp); +out_put_workpath: + path_put(&workpath); +out_put_upperpath: + path_put(&upperpath); +out_free_config: + kfree(ufs->config.lowerdir); + kfree(ufs->config.upperdir); + kfree(ufs->config.workdir); + kfree(ufs); +out: + return err; +} + +static struct dentry *ovl_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *raw_data) +{ + return mount_nodev(fs_type, flags, raw_data, ovl_fill_super); +} + +static struct file_system_type ovl_fs_type = { + .owner = THIS_MODULE, + .name = "overlay", + .mount = ovl_mount, + .kill_sb = kill_anon_super, +}; +MODULE_ALIAS_FS("overlay"); + +static int __init ovl_init(void) +{ + return register_filesystem(&ovl_fs_type); +} + +static void __exit ovl_exit(void) +{ + unregister_filesystem(&ovl_fs_type); +} + +module_init(ovl_init); +module_exit(ovl_exit); diff --git a/fs/proc/Makefile b/fs/proc/Makefile index ab30716584f5..239493ec718e 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -27,6 +27,5 @@ proc-$(CONFIG_PROC_SYSCTL) += proc_sysctl.o proc-$(CONFIG_NET) += proc_net.o proc-$(CONFIG_PROC_KCORE) += kcore.o proc-$(CONFIG_PROC_VMCORE) += vmcore.o -proc-$(CONFIG_PROC_DEVICETREE) += proc_devtree.o proc-$(CONFIG_PRINTK) += kmsg.o proc-$(CONFIG_PROC_PAGE_MONITOR) += page.o diff --git a/fs/proc/base.c b/fs/proc/base.c index b9760628e1fd..489ba8caafc0 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2555,6 +2555,57 @@ static const struct file_operations proc_projid_map_operations = { .llseek = seq_lseek, .release = proc_id_map_release, }; + +static int proc_setgroups_open(struct inode *inode, struct file *file) +{ + struct user_namespace *ns = NULL; + struct task_struct *task; + int ret; + + ret = -ESRCH; + task = get_proc_task(inode); + if (task) { + rcu_read_lock(); + ns = get_user_ns(task_cred_xxx(task, user_ns)); + rcu_read_unlock(); + put_task_struct(task); + } + if (!ns) + goto err; + + if (file->f_mode & FMODE_WRITE) { + ret = -EACCES; + if (!ns_capable(ns, CAP_SYS_ADMIN)) + goto err_put_ns; + } + + ret = single_open(file, &proc_setgroups_show, ns); + if (ret) + goto err_put_ns; + + return 0; +err_put_ns: + put_user_ns(ns); +err: + return ret; +} + +static int proc_setgroups_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq = file->private_data; + struct user_namespace *ns = seq->private; + int ret = single_release(inode, file); + put_user_ns(ns); + return ret; +} + +static const struct file_operations proc_setgroups_operations = { + .open = proc_setgroups_open, + .write = proc_setgroups_write, + .read = seq_read, + .llseek = seq_lseek, + .release = proc_setgroups_release, +}; #endif /* CONFIG_USER_NS */ static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns, @@ -2663,6 +2714,7 @@ static const struct pid_entry tgid_base_stuff[] = { REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations), + REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations), #endif #ifdef CONFIG_CHECKPOINT_RESTORE REG("timers", S_IRUGO, proc_timers_operations), @@ -2998,6 +3050,7 @@ static const struct pid_entry tid_base_stuff[] = { REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations), + REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations), #endif }; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index b7f268eb5f45..2e2d9d5d78d9 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -19,7 +19,6 @@ #include <linux/mount.h> #include <linux/init.h> #include <linux/idr.h> -#include <linux/namei.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/completion.h> @@ -162,17 +161,6 @@ void proc_free_inum(unsigned int inum) spin_unlock_irqrestore(&proc_inum_lock, flags); } -static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd) -{ - nd_set_link(nd, __PDE_DATA(dentry->d_inode)); - return NULL; -} - -static const struct inode_operations proc_link_inode_operations = { - .readlink = generic_readlink, - .follow_link = proc_follow_link, -}; - /* * Don't create negative dentries here, return -ENOENT by hand * instead. diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 124fc43c7090..2f2815f3176e 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -23,6 +23,7 @@ #include <linux/slab.h> #include <linux/mount.h> #include <linux/magic.h> +#include <linux/namei.h> #include <asm/uaccess.h> @@ -401,6 +402,26 @@ static const struct file_operations proc_reg_file_ops_no_compat = { }; #endif +static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + struct proc_dir_entry *pde = PDE(dentry->d_inode); + if (unlikely(!use_pde(pde))) + return ERR_PTR(-EINVAL); + nd_set_link(nd, pde->data); + return pde; +} + +static void proc_put_link(struct dentry *dentry, struct nameidata *nd, void *p) +{ + unuse_pde(p); +} + +const struct inode_operations proc_link_inode_operations = { + .readlink = generic_readlink, + .follow_link = proc_follow_link, + .put_link = proc_put_link, +}; + struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) { struct inode *inode = new_inode_pseudo(sb); diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 651d09a11dde..8b24f3640cd9 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -202,6 +202,7 @@ struct pde_opener { int closing; struct completion *c; }; +extern const struct inode_operations proc_link_inode_operations; extern const struct inode_operations proc_pid_link_inode_operations; @@ -211,13 +212,6 @@ extern int proc_fill_super(struct super_block *); extern void proc_entry_rundown(struct proc_dir_entry *); /* - * proc_devtree.c - */ -#ifdef CONFIG_PROC_DEVICETREE -extern void proc_device_tree_init(void); -#endif - -/* * proc_namespaces.c */ extern const struct inode_operations proc_ns_dir_inode_operations; diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c index 9ae46b87470d..89026095f2b5 100644 --- a/fs/proc/namespaces.c +++ b/fs/proc/namespaces.c @@ -146,7 +146,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl struct task_struct *task; void *ns; char name[50]; - int len = -EACCES; + int res = -EACCES; task = get_proc_task(inode); if (!task) @@ -155,24 +155,18 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl if (!ptrace_may_access(task, PTRACE_MODE_READ)) goto out_put_task; - len = -ENOENT; + res = -ENOENT; ns = ns_ops->get(task); if (!ns) goto out_put_task; snprintf(name, sizeof(name), "%s:[%u]", ns_ops->name, ns_ops->inum(ns)); - len = strlen(name); - - if (len > buflen) - len = buflen; - if (copy_to_user(buffer, name, len)) - len = -EFAULT; - + res = readlink_copy(buffer, buflen, name); ns_ops->put(ns); out_put_task: put_task_struct(task); out: - return len; + return res; } static const struct inode_operations proc_ns_link_inode_operations = { diff --git a/fs/proc/proc_devtree.c b/fs/proc/proc_devtree.c deleted file mode 100644 index c82dd5147845..000000000000 --- a/fs/proc/proc_devtree.c +++ /dev/null @@ -1,241 +0,0 @@ -/* - * proc_devtree.c - handles /proc/device-tree - * - * Copyright 1997 Paul Mackerras - */ -#include <linux/errno.h> -#include <linux/init.h> -#include <linux/time.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/printk.h> -#include <linux/stat.h> -#include <linux/string.h> -#include <linux/of.h> -#include <linux/export.h> -#include <linux/slab.h> -#include <asm/uaccess.h> -#include "internal.h" - -static inline void set_node_proc_entry(struct device_node *np, - struct proc_dir_entry *de) -{ - np->pde = de; -} - -static struct proc_dir_entry *proc_device_tree; - -/* - * Supply data on a read from /proc/device-tree/node/property. - */ -static int property_proc_show(struct seq_file *m, void *v) -{ - struct property *pp = m->private; - - seq_write(m, pp->value, pp->length); - return 0; -} - -static int property_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, property_proc_show, __PDE_DATA(inode)); -} - -static const struct file_operations property_proc_fops = { - .owner = THIS_MODULE, - .open = property_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -/* - * For a node with a name like "gc@10", we make symlinks called "gc" - * and "@10" to it. - */ - -/* - * Add a property to a node - */ -static struct proc_dir_entry * -__proc_device_tree_add_prop(struct proc_dir_entry *de, struct property *pp, - const char *name) -{ - struct proc_dir_entry *ent; - - /* - * Unfortunately proc_register puts each new entry - * at the beginning of the list. So we rearrange them. - */ - ent = proc_create_data(name, - strncmp(name, "security-", 9) ? S_IRUGO : S_IRUSR, - de, &property_proc_fops, pp); - if (ent == NULL) - return NULL; - - if (!strncmp(name, "security-", 9)) - proc_set_size(ent, 0); /* don't leak number of password chars */ - else - proc_set_size(ent, pp->length); - - return ent; -} - - -void proc_device_tree_add_prop(struct proc_dir_entry *pde, struct property *prop) -{ - __proc_device_tree_add_prop(pde, prop, prop->name); -} - -void proc_device_tree_remove_prop(struct proc_dir_entry *pde, - struct property *prop) -{ - remove_proc_entry(prop->name, pde); -} - -void proc_device_tree_update_prop(struct proc_dir_entry *pde, - struct property *newprop, - struct property *oldprop) -{ - struct proc_dir_entry *ent; - - if (!oldprop) { - proc_device_tree_add_prop(pde, newprop); - return; - } - - for (ent = pde->subdir; ent != NULL; ent = ent->next) - if (ent->data == oldprop) - break; - if (ent == NULL) { - pr_warn("device-tree: property \"%s\" does not exist\n", - oldprop->name); - } else { - ent->data = newprop; - ent->size = newprop->length; - } -} - -/* - * Various dodgy firmware might give us nodes and/or properties with - * conflicting names. That's generally ok, except for exporting via /proc, - * so munge names here to ensure they're unique. - */ - -static int duplicate_name(struct proc_dir_entry *de, const char *name) -{ - struct proc_dir_entry *ent; - int found = 0; - - spin_lock(&proc_subdir_lock); - - for (ent = de->subdir; ent != NULL; ent = ent->next) { - if (strcmp(ent->name, name) == 0) { - found = 1; - break; - } - } - - spin_unlock(&proc_subdir_lock); - - return found; -} - -static const char *fixup_name(struct device_node *np, struct proc_dir_entry *de, - const char *name) -{ - char *fixed_name; - int fixup_len = strlen(name) + 2 + 1; /* name + #x + \0 */ - int i = 1, size; - -realloc: - fixed_name = kmalloc(fixup_len, GFP_KERNEL); - if (fixed_name == NULL) { - pr_err("device-tree: Out of memory trying to fixup " - "name \"%s\"\n", name); - return name; - } - -retry: - size = snprintf(fixed_name, fixup_len, "%s#%d", name, i); - size++; /* account for NULL */ - - if (size > fixup_len) { - /* We ran out of space, free and reallocate. */ - kfree(fixed_name); - fixup_len = size; - goto realloc; - } - - if (duplicate_name(de, fixed_name)) { - /* Multiple duplicates. Retry with a different offset. */ - i++; - goto retry; - } - - pr_warn("device-tree: Duplicate name in %s, renamed to \"%s\"\n", - np->full_name, fixed_name); - - return fixed_name; -} - -/* - * Process a node, adding entries for its children and its properties. - */ -void proc_device_tree_add_node(struct device_node *np, - struct proc_dir_entry *de) -{ - struct property *pp; - struct proc_dir_entry *ent; - struct device_node *child; - const char *p; - - set_node_proc_entry(np, de); - for (child = NULL; (child = of_get_next_child(np, child));) { - /* Use everything after the last slash, or the full name */ - p = kbasename(child->full_name); - - if (duplicate_name(de, p)) - p = fixup_name(np, de, p); - - ent = proc_mkdir(p, de); - if (ent == NULL) - break; - proc_device_tree_add_node(child, ent); - } - of_node_put(child); - - for (pp = np->properties; pp != NULL; pp = pp->next) { - p = pp->name; - - if (strchr(p, '/')) - continue; - - if (duplicate_name(de, p)) - p = fixup_name(np, de, p); - - ent = __proc_device_tree_add_prop(de, pp, p); - if (ent == NULL) - break; - } -} - -/* - * Called on initialization to set up the /proc/device-tree subtree - */ -void __init proc_device_tree_init(void) -{ - struct device_node *root; - - proc_device_tree = proc_mkdir("device-tree", NULL); - if (proc_device_tree == NULL) - return; - root = of_find_node_by_path("/"); - if (root == NULL) { - remove_proc_entry("device-tree", NULL); - pr_debug("/proc/device-tree: can't find root\n"); - return; - } - proc_device_tree_add_node(root, proc_device_tree); - of_node_put(root); -} diff --git a/fs/proc/root.c b/fs/proc/root.c index 87dbcbef7fe4..7bbeb5257af1 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -183,9 +183,6 @@ void __init proc_root_init(void) proc_mkdir("openprom", NULL); #endif proc_tty_init(); -#ifdef CONFIG_PROC_DEVICETREE - proc_device_tree_init(); -#endif proc_mkdir("bus", NULL); proc_sys_init(); } diff --git a/fs/proc/self.c b/fs/proc/self.c index ffeb202ec942..4348bb8907c2 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -16,7 +16,7 @@ static int proc_self_readlink(struct dentry *dentry, char __user *buffer, if (!tgid) return -ENOENT; sprintf(tmp, "%d", tgid); - return vfs_readlink(dentry,buffer,buflen,tmp); + return readlink_copy(buffer, buflen, tmp); } static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd) diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 6f599c62f0cc..dbd027235440 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -159,7 +159,7 @@ static int show_stat(struct seq_file *p, void *v) /* sum again ? it could be updated? */ for_each_irq_nr(j) - seq_put_decimal_ull(p, ' ', kstat_irqs(j)); + seq_put_decimal_ull(p, ' ', kstat_irqs_usr(j)); seq_printf(p, "\nctxt %llu\n" diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 8f788193e3d4..c2546717fc2b 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1,4 +1,5 @@ #include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/hugetlb.h> #include <linux/huge_mm.h> #include <linux/mount.h> @@ -152,7 +153,7 @@ static void *m_start(struct seq_file *m, loff_t *pos) /* * We remember last_addr rather than next_addr to hit with - * mmap_cache most of the time. We have zero last_addr at + * vmacache most of the time. We have zero last_addr at * the beginning and also after lseek. We will have -1 last_addr * after the end of the vmas. */ @@ -1226,6 +1227,9 @@ out: static int pagemap_open(struct inode *inode, struct file *file) { + /* do not disclose physical addresses: attack vector */ + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; pr_warn_once("Bits 55-60 of /proc/PID/pagemap entries are about " "to stop being page-shift some time soon. See the " "linux/Documentation/vm/pagemap.txt for details.\n"); diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index 12823845d324..14120a3c6195 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -319,10 +319,10 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count, compressed ? ".enc.z" : ""); break; case PSTORE_TYPE_CONSOLE: - sprintf(name, "console-%s", psname); + sprintf(name, "console-%s-%lld", psname, id); break; case PSTORE_TYPE_FTRACE: - sprintf(name, "ftrace-%s", psname); + sprintf(name, "ftrace-%s-%lld", psname, id); break; case PSTORE_TYPE_MCE: sprintf(name, "mce-%s-%lld", psname, id); diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index fa8cef2cca3a..fe68d8ac4d3d 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -61,6 +61,11 @@ module_param(mem_size, ulong, 0400); MODULE_PARM_DESC(mem_size, "size of reserved RAM used to store oops/panic logs"); +static unsigned int mem_type; +module_param(mem_type, uint, 0600); +MODULE_PARM_DESC(mem_type, + "set to 1 to try to use unbuffered memory (default 0)"); + static int dump_oops = 1; module_param(dump_oops, int, 0600); MODULE_PARM_DESC(dump_oops, @@ -79,6 +84,7 @@ struct ramoops_context { struct persistent_ram_zone *fprz; phys_addr_t phys_addr; unsigned long size; + unsigned int memtype; size_t record_size; size_t console_size; size_t ftrace_size; @@ -86,6 +92,7 @@ struct ramoops_context { struct persistent_ram_ecc_info ecc_info; unsigned int max_dump_cnt; unsigned int dump_write_cnt; + /* _read_cnt need clear on ramoops_pstore_open */ unsigned int dump_read_cnt; unsigned int console_read_cnt; unsigned int ftrace_read_cnt; @@ -101,6 +108,7 @@ static int ramoops_pstore_open(struct pstore_info *psi) cxt->dump_read_cnt = 0; cxt->console_read_cnt = 0; + cxt->ftrace_read_cnt = 0; return 0; } @@ -117,13 +125,15 @@ ramoops_get_next_prz(struct persistent_ram_zone *przs[], uint *c, uint max, return NULL; prz = przs[i]; + if (!prz) + return NULL; - if (update) { - /* Update old/shadowed buffer. */ + /* Update old/shadowed buffer. */ + if (update) persistent_ram_save_old(prz); - if (!persistent_ram_old_size(prz)) - return NULL; - } + + if (!persistent_ram_old_size(prz)) + return NULL; *typep = type; *id = i; @@ -353,7 +363,8 @@ static int ramoops_init_przs(struct device *dev, struct ramoops_context *cxt, size_t sz = cxt->record_size; cxt->przs[i] = persistent_ram_new(*paddr, sz, 0, - &cxt->ecc_info); + &cxt->ecc_info, + cxt->memtype); if (IS_ERR(cxt->przs[i])) { err = PTR_ERR(cxt->przs[i]); dev_err(dev, "failed to request mem region (0x%zx@0x%llx): %d\n", @@ -383,7 +394,7 @@ static int ramoops_init_prz(struct device *dev, struct ramoops_context *cxt, return -ENOMEM; } - *prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info); + *prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info, cxt->memtype); if (IS_ERR(*prz)) { int err = PTR_ERR(*prz); @@ -428,9 +439,9 @@ static int ramoops_probe(struct platform_device *pdev) if (pdata->ftrace_size && !is_power_of_2(pdata->ftrace_size)) pdata->ftrace_size = rounddown_pow_of_two(pdata->ftrace_size); - cxt->dump_read_cnt = 0; cxt->size = pdata->mem_size; cxt->phys_addr = pdata->mem_address; + cxt->memtype = pdata->mem_type; cxt->record_size = pdata->record_size; cxt->console_size = pdata->console_size; cxt->ftrace_size = pdata->ftrace_size; @@ -561,6 +572,7 @@ static void ramoops_register_dummy(void) dummy_data->mem_size = mem_size; dummy_data->mem_address = mem_address; + dummy_data->mem_type = 0; dummy_data->record_size = record_size; dummy_data->console_size = ramoops_console_size; dummy_data->ftrace_size = ramoops_ftrace_size; diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index de272d426763..bda61a759b68 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -380,7 +380,8 @@ void persistent_ram_zap(struct persistent_ram_zone *prz) persistent_ram_update_header_ecc(prz); } -static void *persistent_ram_vmap(phys_addr_t start, size_t size) +static void *persistent_ram_vmap(phys_addr_t start, size_t size, + unsigned int memtype) { struct page **pages; phys_addr_t page_start; @@ -392,7 +393,10 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size) page_start = start - offset_in_page(start); page_count = DIV_ROUND_UP(size + offset_in_page(start), PAGE_SIZE); - prot = pgprot_noncached(PAGE_KERNEL); + if (memtype) + prot = pgprot_noncached(PAGE_KERNEL); + else + prot = pgprot_writecombine(PAGE_KERNEL); pages = kmalloc(sizeof(struct page *) * page_count, GFP_KERNEL); if (!pages) { @@ -411,8 +415,11 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size) return vaddr; } -static void *persistent_ram_iomap(phys_addr_t start, size_t size) +static void *persistent_ram_iomap(phys_addr_t start, size_t size, + unsigned int memtype) { + void *va; + if (!request_mem_region(start, size, "persistent_ram")) { pr_err("request mem region (0x%llx@0x%llx) failed\n", (unsigned long long)size, (unsigned long long)start); @@ -422,19 +429,24 @@ static void *persistent_ram_iomap(phys_addr_t start, size_t size) buffer_start_add = buffer_start_add_locked; buffer_size_add = buffer_size_add_locked; - return ioremap(start, size); + if (memtype) + va = ioremap(start, size); + else + va = ioremap_wc(start, size); + + return va; } static int persistent_ram_buffer_map(phys_addr_t start, phys_addr_t size, - struct persistent_ram_zone *prz) + struct persistent_ram_zone *prz, int memtype) { prz->paddr = start; prz->size = size; if (pfn_valid(start >> PAGE_SHIFT)) - prz->vaddr = persistent_ram_vmap(start, size); + prz->vaddr = persistent_ram_vmap(start, size, memtype); else - prz->vaddr = persistent_ram_iomap(start, size); + prz->vaddr = persistent_ram_iomap(start, size, memtype); if (!prz->vaddr) { pr_err("%s: Failed to map 0x%llx pages at 0x%llx\n", __func__, @@ -502,7 +514,8 @@ void persistent_ram_free(struct persistent_ram_zone *prz) } struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, - u32 sig, struct persistent_ram_ecc_info *ecc_info) + u32 sig, struct persistent_ram_ecc_info *ecc_info, + unsigned int memtype) { struct persistent_ram_zone *prz; int ret = -ENOMEM; @@ -513,7 +526,7 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, goto err; } - ret = persistent_ram_buffer_map(start, size, prz); + ret = persistent_ram_buffer_map(start, size, prz, memtype); if (ret) goto err; diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index ce87c9007b0f..89da95700c69 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -637,7 +637,7 @@ int dquot_writeback_dquots(struct super_block *sb, int type) dqstats_inc(DQST_LOOKUPS); err = sb->dq_op->write_dquot(dquot); if (!ret && err) - err = ret; + ret = err; dqput(dquot); spin_lock(&dq_list_lock); } diff --git a/fs/readdir.c b/fs/readdir.c index 5b53d995cae6..e21af53ec24e 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -72,10 +72,11 @@ struct readdir_callback { int result; }; -static int fillonedir(void * __buf, const char * name, int namlen, loff_t offset, - u64 ino, unsigned int d_type) +static int fillonedir(struct dir_context *ctx, const char *name, int namlen, + loff_t offset, u64 ino, unsigned int d_type) { - struct readdir_callback *buf = (struct readdir_callback *) __buf; + struct readdir_callback *buf = + container_of(ctx, struct readdir_callback, ctx); struct old_linux_dirent __user * dirent; unsigned long d_ino; @@ -146,11 +147,12 @@ struct getdents_callback { int error; }; -static int filldir(void * __buf, const char * name, int namlen, loff_t offset, - u64 ino, unsigned int d_type) +static int filldir(struct dir_context *ctx, const char *name, int namlen, + loff_t offset, u64 ino, unsigned int d_type) { struct linux_dirent __user * dirent; - struct getdents_callback * buf = (struct getdents_callback *) __buf; + struct getdents_callback *buf = + container_of(ctx, struct getdents_callback, ctx); unsigned long d_ino; int reclen = ALIGN(offsetof(struct linux_dirent, d_name) + namlen + 2, sizeof(long)); @@ -230,11 +232,12 @@ struct getdents_callback64 { int error; }; -static int filldir64(void * __buf, const char * name, int namlen, loff_t offset, - u64 ino, unsigned int d_type) +static int filldir64(struct dir_context *ctx, const char *name, int namlen, + loff_t offset, u64 ino, unsigned int d_type) { struct linux_dirent64 __user *dirent; - struct getdents_callback64 * buf = (struct getdents_callback64 *) __buf; + struct getdents_callback64 *buf = + container_of(ctx, struct getdents_callback64, ctx); int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1, sizeof(u64)); diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 5cdfbd638b5c..d8b7acfd5066 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -177,10 +177,11 @@ struct reiserfs_dentry_buf { }; static int -fill_with_dentries(void *buf, const char *name, int namelen, loff_t offset, - u64 ino, unsigned int d_type) +fill_with_dentries(struct dir_context *ctx, const char *name, int namelen, + loff_t offset, u64 ino, unsigned int d_type) { - struct reiserfs_dentry_buf *dbuf = buf; + struct reiserfs_dentry_buf *dbuf = + container_of(ctx, struct reiserfs_dentry_buf, ctx); struct dentry *dentry; WARN_ON_ONCE(!mutex_is_locked(&dbuf->xadir->d_inode->i_mutex)); @@ -794,10 +795,12 @@ struct listxattr_buf { struct dentry *dentry; }; -static int listxattr_filler(void *buf, const char *name, int namelen, - loff_t offset, u64 ino, unsigned int d_type) +static int listxattr_filler(struct dir_context *ctx, const char *name, + int namelen, loff_t offset, u64 ino, + unsigned int d_type) { - struct listxattr_buf *b = (struct listxattr_buf *)buf; + struct listxattr_buf *b = + container_of(ctx, struct listxattr_buf, ctx); size_t size; if (name[0] != '.' || (namelen != 1 && (name[1] != '.' || namelen != 2))) { diff --git a/fs/splice.c b/fs/splice.c index 12028fa41def..ffb92b9d34ba 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1327,6 +1327,7 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, return ret; } +EXPORT_SYMBOL(do_splice_direct); static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe, struct pipe_inode_info *opipe, diff --git a/fs/super.c b/fs/super.c index 7624267b2043..440ef51cd696 100644 --- a/fs/super.c +++ b/fs/super.c @@ -81,6 +81,8 @@ static unsigned long super_cache_scan(struct shrinker *shrink, inodes = list_lru_count_node(&sb->s_inode_lru, sc->nid); dentries = list_lru_count_node(&sb->s_dentry_lru, sc->nid); total_objects = dentries + inodes + fs_objects + 1; + if (!total_objects) + total_objects = 1; /* proportion the scan between the caches */ dentries = mult_frac(sc->nr_to_scan, dentries, total_objects); @@ -112,9 +114,14 @@ static unsigned long super_cache_count(struct shrinker *shrink, sb = container_of(shrink, struct super_block, s_shrink); - if (!grab_super_passive(sb)) - return 0; - + /* + * Don't call grab_super_passive as it is a potential + * scalability bottleneck. The counts could get updated + * between super_cache_count and super_cache_scan anyway. + * Call to super_cache_count with shrinker_rwsem held + * ensures the safety of call to list_lru_count_node() and + * s_op->nr_cached_objects(). + */ if (sb->s_op && sb->s_op->nr_cached_objects) total_objects = sb->s_op->nr_cached_objects(sb, sc->nid); @@ -125,7 +132,6 @@ static unsigned long super_cache_count(struct shrinker *shrink, sc->nid); total_objects = vfs_pressure_ratio(total_objects); - drop_super(sb); return total_objects; } @@ -276,10 +282,8 @@ void deactivate_locked_super(struct super_block *s) struct file_system_type *fs = s->s_type; if (atomic_dec_and_test(&s->s_active)) { cleancache_invalidate_fs(s); - fs->kill_sb(s); - - /* caches are now gone, we can safely kill the shrinker now */ unregister_shrinker(&s->s_shrink); + fs->kill_sb(s); put_filesystem(fs); put_super(s); diff --git a/fs/ubifs/commit.c b/fs/ubifs/commit.c index ff8229340cd5..26b69b2d4a45 100644 --- a/fs/ubifs/commit.c +++ b/fs/ubifs/commit.c @@ -166,15 +166,10 @@ static int do_commit(struct ubifs_info *c) err = ubifs_orphan_end_commit(c); if (err) goto out; - old_ltail_lnum = c->ltail_lnum; - err = ubifs_log_end_commit(c, new_ltail_lnum); - if (err) - goto out; err = dbg_check_old_index(c, &zroot); if (err) goto out; - mutex_lock(&c->mst_mutex); c->mst_node->cmt_no = cpu_to_le64(c->cmt_no); c->mst_node->log_lnum = cpu_to_le32(new_ltail_lnum); c->mst_node->root_lnum = cpu_to_le32(zroot.lnum); @@ -203,8 +198,9 @@ static int do_commit(struct ubifs_info *c) c->mst_node->flags |= cpu_to_le32(UBIFS_MST_NO_ORPHS); else c->mst_node->flags &= ~cpu_to_le32(UBIFS_MST_NO_ORPHS); - err = ubifs_write_master(c); - mutex_unlock(&c->mst_mutex); + + old_ltail_lnum = c->ltail_lnum; + err = ubifs_log_end_commit(c, new_ltail_lnum); if (err) goto out; diff --git a/fs/ubifs/log.c b/fs/ubifs/log.c index a902c5919e42..8d59de86dc9a 100644 --- a/fs/ubifs/log.c +++ b/fs/ubifs/log.c @@ -106,10 +106,14 @@ static inline long long empty_log_bytes(const struct ubifs_info *c) h = (long long)c->lhead_lnum * c->leb_size + c->lhead_offs; t = (long long)c->ltail_lnum * c->leb_size; - if (h >= t) + if (h > t) return c->log_bytes - h + t; - else + else if (h != t) return t - h; + else if (c->lhead_lnum != c->ltail_lnum) + return 0; + else + return c->log_bytes; } /** @@ -447,9 +451,9 @@ out: * @ltail_lnum: new log tail LEB number * * This function is called on when the commit operation was finished. It - * moves log tail to new position and unmaps LEBs which contain obsolete data. - * Returns zero in case of success and a negative error code in case of - * failure. + * moves log tail to new position and updates the master node so that it stores + * the new log tail LEB number. Returns zero in case of success and a negative + * error code in case of failure. */ int ubifs_log_end_commit(struct ubifs_info *c, int ltail_lnum) { @@ -477,7 +481,12 @@ int ubifs_log_end_commit(struct ubifs_info *c, int ltail_lnum) spin_unlock(&c->buds_lock); err = dbg_check_bud_bytes(c); + if (err) + goto out; + err = ubifs_write_master(c); + +out: mutex_unlock(&c->log_mutex); return err; } diff --git a/fs/ubifs/master.c b/fs/ubifs/master.c index ab83ace9910a..1a4bb9e8b3b8 100644 --- a/fs/ubifs/master.c +++ b/fs/ubifs/master.c @@ -352,10 +352,9 @@ int ubifs_read_master(struct ubifs_info *c) * ubifs_write_master - write master node. * @c: UBIFS file-system description object * - * This function writes the master node. The caller has to take the - * @c->mst_mutex lock before calling this function. Returns zero in case of - * success and a negative error code in case of failure. The master node is - * written twice to enable recovery. + * This function writes the master node. Returns zero in case of success and a + * negative error code in case of failure. The master node is written twice to + * enable recovery. */ int ubifs_write_master(struct ubifs_info *c) { diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 5ded8490c0c6..94d9a64287b7 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1957,7 +1957,6 @@ static struct ubifs_info *alloc_ubifs_info(struct ubi_volume_desc *ubi) mutex_init(&c->lp_mutex); mutex_init(&c->tnc_mutex); mutex_init(&c->log_mutex); - mutex_init(&c->mst_mutex); mutex_init(&c->umount_mutex); mutex_init(&c->bu_mutex); mutex_init(&c->write_reserve_mutex); diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index e8c8cfe1435c..7ab9c710c749 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -1042,7 +1042,6 @@ struct ubifs_debug_info; * * @mst_node: master node * @mst_offs: offset of valid master node - * @mst_mutex: protects the master node area, @mst_node, and @mst_offs * * @max_bu_buf_len: maximum bulk-read buffer length * @bu_mutex: protects the pre-allocated bulk-read buffer and @c->bu @@ -1282,7 +1281,6 @@ struct ubifs_info { struct ubifs_mst_node *mst_node; int mst_offs; - struct mutex mst_mutex; int max_bu_buf_len; struct mutex bu_mutex; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 982ce05c87ed..287cd5f23421 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1271,13 +1271,22 @@ update_time: return 0; } +/* + * Maximum length of linked list formed by ICB hierarchy. The chosen number is + * arbitrary - just that we hopefully don't limit any real use of rewritten + * inode on write-once media but avoid looping for too long on corrupted media. + */ +#define UDF_MAX_ICB_NESTING 1024 + static void __udf_read_inode(struct inode *inode) { struct buffer_head *bh = NULL; struct fileEntry *fe; uint16_t ident; struct udf_inode_info *iinfo = UDF_I(inode); + unsigned int indirections = 0; +reread: /* * Set defaults, but the inode is still incomplete! * Note: get_new_inode() sets the following on a new inode: @@ -1314,28 +1323,26 @@ static void __udf_read_inode(struct inode *inode) ibh = udf_read_ptagged(inode->i_sb, &iinfo->i_location, 1, &ident); if (ident == TAG_IDENT_IE && ibh) { - struct buffer_head *nbh = NULL; struct kernel_lb_addr loc; struct indirectEntry *ie; ie = (struct indirectEntry *)ibh->b_data; loc = lelb_to_cpu(ie->indirectICB.extLocation); - if (ie->indirectICB.extLength && - (nbh = udf_read_ptagged(inode->i_sb, &loc, 0, - &ident))) { - if (ident == TAG_IDENT_FE || - ident == TAG_IDENT_EFE) { - memcpy(&iinfo->i_location, - &loc, - sizeof(struct kernel_lb_addr)); - brelse(bh); - brelse(ibh); - brelse(nbh); - __udf_read_inode(inode); + if (ie->indirectICB.extLength) { + brelse(bh); + brelse(ibh); + memcpy(&iinfo->i_location, &loc, + sizeof(struct kernel_lb_addr)); + if (++indirections > UDF_MAX_ICB_NESTING) { + udf_err(inode->i_sb, + "too many ICBs in ICB hierarchy" + " (max %d supported)\n", + UDF_MAX_ICB_NESTING); + make_bad_inode(inode); return; } - brelse(nbh); + goto reread; } } brelse(ibh); diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c index d7c6dbe4194b..d89f324bc387 100644 --- a/fs/udf/symlink.c +++ b/fs/udf/symlink.c @@ -80,11 +80,17 @@ static int udf_symlink_filler(struct file *file, struct page *page) struct inode *inode = page->mapping->host; struct buffer_head *bh = NULL; unsigned char *symlink; - int err = -EIO; + int err; unsigned char *p = kmap(page); struct udf_inode_info *iinfo; uint32_t pos; + /* We don't support symlinks longer than one block */ + if (inode->i_size > inode->i_sb->s_blocksize) { + err = -ENAMETOOLONG; + goto out_unmap; + } + iinfo = UDF_I(inode); pos = udf_block_map(inode, 0); @@ -94,8 +100,10 @@ static int udf_symlink_filler(struct file *file, struct page *page) } else { bh = sb_bread(inode->i_sb, pos); - if (!bh) - goto out; + if (!bh) { + err = -EIO; + goto out_unlock_inode; + } symlink = bh->b_data; } @@ -109,9 +117,10 @@ static int udf_symlink_filler(struct file *file, struct page *page) unlock_page(page); return 0; -out: +out_unlock_inode: up_read(&iinfo->i_data_sem); SetPageError(page); +out_unmap: kunmap(page); unlock_page(page); return err; diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 5d2518b24cea..0461fbe405b7 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -434,10 +434,22 @@ xfs_start_page_writeback( { ASSERT(PageLocked(page)); ASSERT(!PageWriteback(page)); - if (clear_dirty) + + /* + * if the page was not fully cleaned, we need to ensure that the higher + * layers come back to it correctly. That means we need to keep the page + * dirty, and for WB_SYNC_ALL writeback we need to ensure the + * PAGECACHE_TAG_TOWRITE index mark is not removed so another attempt to + * write this page in this writeback sweep will be made. + */ + if (clear_dirty) { clear_page_dirty_for_io(page); - set_page_writeback(page); + set_page_writeback(page); + } else + set_page_writeback_keepwrite(page); + unlock_page(page); + /* If no buffers on the page are to be written, finish it here */ if (!buffers) end_page_writeback(page); diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 33149113e333..645f180f5960 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -319,6 +319,10 @@ xfs_buf_item_format( ASSERT(atomic_read(&bip->bli_refcount) > 0); ASSERT((bip->bli_flags & XFS_BLI_LOGGED) || (bip->bli_flags & XFS_BLI_STALE)); + ASSERT((bip->bli_flags & XFS_BLI_STALE) || + (xfs_blft_from_flags(&bip->__bli_format) > XFS_BLFT_UNKNOWN_BUF + && xfs_blft_from_flags(&bip->__bli_format) < XFS_BLFT_MAX_BUF)); + /* * If it is an inode buffer, transfer the in-memory state to the diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 3a137e9f9a7d..5d90b8db0ac7 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1946,6 +1946,7 @@ xfs_iunlink( agi->agi_unlinked[bucket_index] = cpu_to_be32(agino); offset = offsetof(xfs_agi_t, agi_unlinked) + (sizeof(xfs_agino_t) * bucket_index); + xfs_trans_buf_set_type(tp, agibp, XFS_BLFT_AGI_BUF); xfs_trans_log_buf(tp, agibp, offset, (offset + sizeof(xfs_agino_t) - 1)); return 0; @@ -2037,6 +2038,7 @@ xfs_iunlink_remove( agi->agi_unlinked[bucket_index] = cpu_to_be32(next_agino); offset = offsetof(xfs_agi_t, agi_unlinked) + (sizeof(xfs_agino_t) * bucket_index); + xfs_trans_buf_set_type(tp, agibp, XFS_BLFT_AGI_BUF); xfs_trans_log_buf(tp, agibp, offset, (offset + sizeof(xfs_agino_t) - 1)); } else { diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 78e62cc471c5..6152cbe353e8 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -271,32 +271,6 @@ xfs_open_by_handle( return error; } -/* - * This is a copy from fs/namei.c:vfs_readlink(), except for removing it's - * unused first argument. - */ -STATIC int -do_readlink( - char __user *buffer, - int buflen, - const char *link) -{ - int len; - - len = PTR_ERR(link); - if (IS_ERR(link)) - goto out; - - len = strlen(link); - if (len > (unsigned) buflen) - len = buflen; - if (copy_to_user(buffer, link, len)) - len = -EFAULT; - out: - return len; -} - - int xfs_readlink_by_handle( struct file *parfilp, @@ -334,7 +308,7 @@ xfs_readlink_by_handle( error = -xfs_readlink(XFS_I(dentry->d_inode), link); if (error) goto out_kfree; - error = do_readlink(hreq->ohandle, olen, link); + error = readlink_copy(hreq->ohandle, olen, link); if (error) goto out_kfree; diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index c6ff3cf5a5bb..0eaaa2d296f0 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -321,7 +321,6 @@ reread: * Initialize the mount structure from the superblock. */ xfs_sb_from_disk(sbp, XFS_BUF_TO_SBP(bp)); - xfs_sb_quota_from_disk(sbp); /* * If we haven't validated the superblock, do so now before we try diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 6d7d1de13403..1b271f59d518 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -1108,6 +1108,11 @@ xfs_qm_reset_dqcounts( */ xfs_dqcheck(mp, ddq, id+j, type, XFS_QMOPT_DQREPAIR, "xfs_quotacheck"); + /* + * Reset type in case we are reusing group quota file for + * project quotas or vice versa + */ + ddq->d_flags = type; ddq->d_bcount = 0; ddq->d_icount = 0; ddq->d_rtbcount = 0; diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c index 1e116794bb66..4afd393846d3 100644 --- a/fs/xfs/xfs_sb.c +++ b/fs/xfs/xfs_sb.c @@ -397,10 +397,11 @@ xfs_sb_quota_from_disk(struct xfs_sb *sbp) } } -void -xfs_sb_from_disk( +static void +__xfs_sb_from_disk( struct xfs_sb *to, - xfs_dsb_t *from) + xfs_dsb_t *from, + bool convert_xquota) { to->sb_magicnum = be32_to_cpu(from->sb_magicnum); to->sb_blocksize = be32_to_cpu(from->sb_blocksize); @@ -456,6 +457,17 @@ xfs_sb_from_disk( to->sb_pad = 0; to->sb_pquotino = be64_to_cpu(from->sb_pquotino); to->sb_lsn = be64_to_cpu(from->sb_lsn); + /* Convert on-disk flags to in-memory flags? */ + if (convert_xquota) + xfs_sb_quota_from_disk(to); +} + +void +xfs_sb_from_disk( + struct xfs_sb *to, + xfs_dsb_t *from) +{ + __xfs_sb_from_disk(to, from, true); } static inline void @@ -571,7 +583,11 @@ xfs_sb_verify( struct xfs_mount *mp = bp->b_target->bt_mount; struct xfs_sb sb; - xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp)); + /* + * Use call variant which doesn't convert quota flags from disk + * format, because xfs_mount_validate_sb checks the on-disk flags. + */ + __xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp), false); /* * Only check the in progress field for the primary superblock as diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index c812c5c060de..b626f3db67cb 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -474,6 +474,7 @@ xfs_trans_apply_sb_deltas( whole = 1; } + xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF); if (whole) /* * Log the whole thing, the fields are noncontiguous. diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index e9c4f190ffae..ac46782c10d3 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -118,6 +118,7 @@ struct acpi_device; struct acpi_hotplug_profile { struct kobject kobj; int (*scan_dependent)(struct acpi_device *adev); + void (*notify_online)(struct acpi_device *adev); bool enabled:1; bool demand_offline:1; }; diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h index bcec4c46cc2e..ca52de5a5c97 100644 --- a/include/drm/drm_pciids.h +++ b/include/drm/drm_pciids.h @@ -74,7 +74,6 @@ {0x1002, 0x4C64, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \ {0x1002, 0x4C66, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \ {0x1002, 0x4C67, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \ - {0x1002, 0x4C6E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280|RADEON_IS_MOBILITY}, \ {0x1002, 0x4E44, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \ {0x1002, 0x4E45, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \ {0x1002, 0x4E46, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \ diff --git a/include/dt-bindings/pinctrl/dra.h b/include/dt-bindings/pinctrl/dra.h index 3d33794e4f3e..7448edff4723 100644 --- a/include/dt-bindings/pinctrl/dra.h +++ b/include/dt-bindings/pinctrl/dra.h @@ -40,8 +40,8 @@ /* Active pin states */ #define PIN_OUTPUT (0 | PULL_DIS) -#define PIN_OUTPUT_PULLUP (PIN_OUTPUT | PULL_ENA | PULL_UP) -#define PIN_OUTPUT_PULLDOWN (PIN_OUTPUT | PULL_ENA) +#define PIN_OUTPUT_PULLUP (PULL_UP) +#define PIN_OUTPUT_PULLDOWN (0) #define PIN_INPUT (INPUT_EN | PULL_DIS) #define PIN_INPUT_SLEW (INPUT_EN | SLEWCONTROL) #define PIN_INPUT_PULLUP (PULL_ENA | INPUT_EN | PULL_UP) diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 63b5eff0a80f..c814346ba93c 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -23,6 +23,7 @@ #define AMBA_NR_IRQS 9 #define AMBA_CID 0xb105f00d +#define CORESIGHT_CID 0xb105900d struct clk; diff --git a/include/linux/audit.h b/include/linux/audit.h index ec1464df4c60..419b7d7d7a7f 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -47,6 +47,7 @@ struct sk_buff; struct audit_krule { int vers_ops; + u32 pflags; u32 flags; u32 listnr; u32 action; @@ -64,6 +65,9 @@ struct audit_krule { u64 prio; }; +/* Flag to indicate legacy AUDIT_LOGINUID unset usage */ +#define AUDIT_LOGINUID_LEGACY 0x1 + struct audit_field { u32 type; u32 val; diff --git a/include/linux/bitops.h b/include/linux/bitops.h index be5fd38bd5a0..5d858e02997f 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -18,8 +18,11 @@ * position @h. For example * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. */ -#define GENMASK(h, l) (((U32_C(1) << ((h) - (l) + 1)) - 1) << (l)) -#define GENMASK_ULL(h, l) (((U64_C(1) << ((h) - (l) + 1)) - 1) << (l)) +#define GENMASK(h, l) \ + (((~0UL) << (l)) & (~0UL >> (BITS_PER_LONG - 1 - (h)))) + +#define GENMASK_ULL(h, l) \ + (((~0ULL) << (l)) & (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h)))) extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index bbc3a6c88fce..33fd7ff53a77 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -180,7 +180,9 @@ enum rq_flag_bits { __REQ_ELVPRIV, /* elevator private data attached */ __REQ_FAILED, /* set if the request failed */ __REQ_QUIET, /* don't worry about errors */ - __REQ_PREEMPT, /* set for "ide_preempt" requests */ + __REQ_PREEMPT, /* set for "ide_preempt" requests and also + for requests for which the SCSI "quiesce" + state must be ignored. */ __REQ_ALLOCED, /* request came from our alloc pool */ __REQ_COPY_USER, /* contains copies of user pages */ __REQ_FLUSH_SEQ, /* request for flush sequence */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4afa4f8f6090..a693c6d29328 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1232,10 +1232,9 @@ static inline int queue_alignment_offset(struct request_queue *q) static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector) { unsigned int granularity = max(lim->physical_block_size, lim->io_min); - unsigned int alignment = (sector << 9) & (granularity - 1); + unsigned int alignment = sector_div(sector, granularity >> 9) << 9; - return (granularity + lim->alignment_offset - alignment) - & (granularity - 1); + return (granularity + lim->alignment_offset - alignment) % granularity; } static inline int bdev_alignment_offset(struct block_device *bdev) diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 939533da93a7..2045a128c987 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -304,6 +304,8 @@ struct clk_div_table { * of this register, and mask of divider bits are in higher 16-bit of this * register. While setting the divider bits, higher 16-bit should also be * updated to indicate changing divider bits. + * CLK_DIVIDER_ROUND_CLOSEST - Makes the best calculated divider to be rounded + * to the closest integer instead of the up one. */ struct clk_divider { struct clk_hw hw; @@ -319,6 +321,7 @@ struct clk_divider { #define CLK_DIVIDER_POWER_OF_TWO BIT(1) #define CLK_DIVIDER_ALLOW_ZERO BIT(2) #define CLK_DIVIDER_HIWORD_MASK BIT(3) +#define CLK_DIVIDER_ROUND_CLOSEST BIT(4) extern const struct clk_ops clk_divider_ops; struct clk *clk_register_divider(struct device *dev, const char *name, diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 67301a405712..879065d8d208 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -289,7 +289,7 @@ extern struct clocksource* clocksource_get_next(void); extern void clocksource_change_rating(struct clocksource *cs, int rating); extern void clocksource_suspend(void); extern void clocksource_resume(void); -extern struct clocksource * __init __weak clocksource_default_clock(void); +extern struct clocksource * __init clocksource_default_clock(void); extern void clocksource_mark_unstable(struct clocksource *cs); extern u64 diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 7e1c76e3cd68..01e3132820da 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -22,7 +22,7 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write, extern int fragmentation_index(struct zone *zone, unsigned int order); extern unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask, - bool sync, bool *contended); + enum migrate_mode mode, bool *contended); extern void compact_pgdat(pg_data_t *pgdat, int order); extern void reset_isolation_suitable(pg_data_t *pgdat); extern unsigned long compaction_suitable(struct zone *zone, int order); @@ -91,7 +91,7 @@ static inline bool compaction_restarting(struct zone *zone, int order) #else static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask, - bool sync, bool *contended) + enum migrate_mode mode, bool *contended) { return COMPACT_CONTINUE; } diff --git a/include/linux/compiler-gcc5.h b/include/linux/compiler-gcc5.h new file mode 100644 index 000000000000..cdd1cc202d51 --- /dev/null +++ b/include/linux/compiler-gcc5.h @@ -0,0 +1,66 @@ +#ifndef __LINUX_COMPILER_H +#error "Please don't include <linux/compiler-gcc5.h> directly, include <linux/compiler.h> instead." +#endif + +#define __used __attribute__((__used__)) +#define __must_check __attribute__((warn_unused_result)) +#define __compiler_offsetof(a, b) __builtin_offsetof(a, b) + +/* Mark functions as cold. gcc will assume any path leading to a call + to them will be unlikely. This means a lot of manual unlikely()s + are unnecessary now for any paths leading to the usual suspects + like BUG(), printk(), panic() etc. [but let's keep them for now for + older compilers] + + Early snapshots of gcc 4.3 don't support this and we can't detect this + in the preprocessor, but we can live with this because they're unreleased. + Maketime probing would be overkill here. + + gcc also has a __attribute__((__hot__)) to move hot functions into + a special section, but I don't see any sense in this right now in + the kernel context */ +#define __cold __attribute__((__cold__)) + +#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) + +#ifndef __CHECKER__ +# define __compiletime_warning(message) __attribute__((warning(message))) +# define __compiletime_error(message) __attribute__((error(message))) +#endif /* __CHECKER__ */ + +/* + * Mark a position in code as unreachable. This can be used to + * suppress control flow warnings after asm blocks that transfer + * control elsewhere. + * + * Early snapshots of gcc 4.5 don't support this and we can't detect + * this in the preprocessor, but we can live with this because they're + * unreleased. Really, we need to have autoconf for the kernel. + */ +#define unreachable() __builtin_unreachable() + +/* Mark a function definition as prohibited from being cloned. */ +#define __noclone __attribute__((__noclone__)) + +/* + * Tell the optimizer that something else uses this function or variable. + */ +#define __visible __attribute__((externally_visible)) + +/* + * GCC 'asm goto' miscompiles certain code sequences: + * + * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670 + * + * Work it around via a compiler barrier quirk suggested by Jakub Jelinek. + * Fixed in GCC 4.8.2 and later versions. + * + * (asm goto is automatically volatile - the naming reflects this.) + */ +#define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0) + +#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP +#define __HAVE_BUILTIN_BSWAP32__ +#define __HAVE_BUILTIN_BSWAP64__ +#define __HAVE_BUILTIN_BSWAP16__ +#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ diff --git a/include/linux/coresight.h b/include/linux/coresight.h new file mode 100644 index 000000000000..44c1597a738a --- /dev/null +++ b/include/linux/coresight.h @@ -0,0 +1,251 @@ +/* Copyright (c) 2012, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _LINUX_CORESIGHT_H +#define _LINUX_CORESIGHT_H + +#include <linux/device.h> + +/* Peripheral id registers (0xFD0-0xFEC) */ +#define CORESIGHT_PERIPHIDR4 0xfd0 +#define CORESIGHT_PERIPHIDR5 0xfd4 +#define CORESIGHT_PERIPHIDR6 0xfd8 +#define CORESIGHT_PERIPHIDR7 0xfdC +#define CORESIGHT_PERIPHIDR0 0xfe0 +#define CORESIGHT_PERIPHIDR1 0xfe4 +#define CORESIGHT_PERIPHIDR2 0xfe8 +#define CORESIGHT_PERIPHIDR3 0xfeC +/* Component id registers (0xFF0-0xFFC) */ +#define CORESIGHT_COMPIDR0 0xff0 +#define CORESIGHT_COMPIDR1 0xff4 +#define CORESIGHT_COMPIDR2 0xff8 +#define CORESIGHT_COMPIDR3 0xffC + +#define ETM_ARCH_V3_3 0x23 +#define ETM_ARCH_V3_5 0x25 +#define PFT_ARCH_V1_0 0x30 +#define PFT_ARCH_V1_1 0x31 + +#define CORESIGHT_UNLOCK 0xc5acce55 + +extern struct bus_type coresight_bustype; + +enum coresight_dev_type { + CORESIGHT_DEV_TYPE_NONE, + CORESIGHT_DEV_TYPE_SINK, + CORESIGHT_DEV_TYPE_LINK, + CORESIGHT_DEV_TYPE_LINKSINK, + CORESIGHT_DEV_TYPE_SOURCE, +}; + +enum coresight_dev_subtype_sink { + CORESIGHT_DEV_SUBTYPE_SINK_NONE, + CORESIGHT_DEV_SUBTYPE_SINK_PORT, + CORESIGHT_DEV_SUBTYPE_SINK_BUFFER, +}; + +enum coresight_dev_subtype_link { + CORESIGHT_DEV_SUBTYPE_LINK_NONE, + CORESIGHT_DEV_SUBTYPE_LINK_MERG, + CORESIGHT_DEV_SUBTYPE_LINK_SPLIT, + CORESIGHT_DEV_SUBTYPE_LINK_FIFO, +}; + +enum coresight_dev_subtype_source { + CORESIGHT_DEV_SUBTYPE_SOURCE_NONE, + CORESIGHT_DEV_SUBTYPE_SOURCE_PROC, + CORESIGHT_DEV_SUBTYPE_SOURCE_BUS, + CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE, +}; + +/** + * struct coresight_dev_subtype - further characterisation of a type + * @sink_subtype: type of sink this component is, as defined + by @coresight_dev_subtype_sink. + * @link_subtype: type of link this component is, as defined + by @coresight_dev_subtype_link. + * @source_subtype: type of source this component is, as defined + by @coresight_dev_subtype_source. + */ +struct coresight_dev_subtype { + enum coresight_dev_subtype_sink sink_subtype; + enum coresight_dev_subtype_link link_subtype; + enum coresight_dev_subtype_source source_subtype; +}; + +/** + * struct coresight_platform_data - data harvested from the DT specification + * @cpu: the CPU a source belongs to. Only applicable for ETM/PTMs. + * @name: name of the component as shown under sysfs. + * @nr_inport: number of input ports for this component. + * @outports: list of remote enpoint port number. + * @child_names:name of all child components connected to this device. + * @child_ports:child component port number the current component is + connected to. + * @nr_outport: number of output ports for this component. + * @clk: The clock this component is associated to. + */ +struct coresight_platform_data { + int cpu; + const char *name; + int nr_inport; + int *outports; + const char **child_names; + int *child_ports; + int nr_outport; + struct clk *clk; +}; + +/** + * struct coresight_desc - description of a component required from drivers + * @type: as defined by @coresight_dev_type. + * @subtype: as defined by @coresight_dev_subtype. + * @ops: generic operations for this component, as defined + by @coresight_ops. + * @pdata: platform data collected from DT. + * @dev: The device entity associated to this component. + * @groups :operations specific to this component. These will end up + in the component's sysfs sub-directory. + */ +struct coresight_desc { + enum coresight_dev_type type; + struct coresight_dev_subtype subtype; + const struct coresight_ops *ops; + struct coresight_platform_data *pdata; + struct device *dev; + const struct attribute_group **groups; +}; + +/** + * struct coresight_connection - representation of a single connection + * @ref_count: keeping count a port' references. + * @outport: a connection's output port number. + * @chid_name: remote component's name. + * @child_port: remote component's port number @output is connected to. + * @child_dev: a @coresight_device representation of the component + connected to @outport. + */ +struct coresight_connection { + int outport; + const char *child_name; + int child_port; + struct coresight_device *child_dev; +}; + +/** + * struct coresight_device - representation of a device as used by the framework + * @nr_inport: number of input port associated to this component. + * @nr_outport: number of output port associated to this component. + * @type: as defined by @coresight_dev_type. + * @subtype: as defined by @coresight_dev_subtype. + * @ops: generic operations for this component, as defined + by @coresight_ops. + * @dev: The device entity associated to this component. + * @refcnt: keep track of what is in use. + * @path_link: link of current component into the path being enabled. + * @orphan: true if the component has connections that haven't been linked. + * @enable: 'true' if component is currently part of an active path. + * @activated: 'true' only if a _sink_ has been activated. A sink can be + activated but not yet enabled. Enabling for a _sink_ + happens when a source has been selected for that it. + */ +struct coresight_device { + struct coresight_connection *conns; + int nr_inport; + int nr_outport; + enum coresight_dev_type type; + struct coresight_dev_subtype subtype; + const struct coresight_ops *ops; + struct device dev; + atomic_t *refcnt; + struct list_head path_link; + bool orphan; + bool enable; /* true only if configured as part of a path */ + bool activated; /* true only if a sink is part of a path */ +}; + +#define to_coresight_device(d) container_of(d, struct coresight_device, dev) + +#define source_ops(csdev) csdev->ops->source_ops +#define sink_ops(csdev) csdev->ops->sink_ops +#define link_ops(csdev) csdev->ops->link_ops + +/** + * struct coresight_ops_sink - basic operations for a sink + * Operations available for sinks + * @enable: enables the sink. + * @disable: disables the sink. + */ +struct coresight_ops_sink { + int (*enable)(struct coresight_device *csdev); + void (*disable)(struct coresight_device *csdev); +}; + +/** + * struct coresight_ops_link - basic operations for a link + * Operations available for links. + * @enable: enables flow between iport and oport. + * @disable: disables flow between iport and oport. + */ +struct coresight_ops_link { + int (*enable)(struct coresight_device *csdev, int iport, int oport); + void (*disable)(struct coresight_device *csdev, int iport, int oport); +}; + +/** + * struct coresight_ops_source - basic operations for a source + * Operations available for sources. + * @trace_id: returns the value of the component's trace ID as known + to the HW. + * @enable: enables tracing from a source. + * @disable: disables tracing for a source. + */ +struct coresight_ops_source { + int (*trace_id)(struct coresight_device *csdev); + int (*enable)(struct coresight_device *csdev); + void (*disable)(struct coresight_device *csdev); +}; + +struct coresight_ops { + const struct coresight_ops_sink *sink_ops; + const struct coresight_ops_link *link_ops; + const struct coresight_ops_source *source_ops; +}; + +#ifdef CONFIG_CORESIGHT +extern struct coresight_device * +coresight_register(struct coresight_desc *desc); +extern void coresight_unregister(struct coresight_device *csdev); +extern int coresight_enable(struct coresight_device *csdev); +extern void coresight_disable(struct coresight_device *csdev); +extern int coresight_timeout(void __iomem *addr, u32 offset, + int position, int value); +#else +static inline struct coresight_device * +coresight_register(struct coresight_desc *desc) { return NULL; } +static inline void coresight_unregister(struct coresight_device *csdev) {} +static inline int +coresight_enable(struct coresight_device *csdev) { return -ENOSYS; } +static inline void coresight_disable(struct coresight_device *csdev) {} +static inline int coresight_timeout(void __iomem *addr, u32 offset, + int position, int value) { return 1; } +#endif + +#ifdef CONFIG_OF +extern struct coresight_platform_data *of_get_coresight_platform_data( + struct device *dev, struct device_node *node); +#else +static inline struct coresight_platform_data *of_get_coresight_platform_data( + struct device *dev, struct device_node *node) { return NULL; } +#endif + +#endif diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 50fcbb0ac4e7..d1338170b6b9 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -69,7 +69,6 @@ struct cpuidle_device { unsigned int cpu; int last_residency; - int state_count; struct cpuidle_state_usage states_usage[CPUIDLE_STATE_MAX]; struct cpuidle_state_kobj *kobjs[CPUIDLE_STATE_MAX]; struct cpuidle_driver_kobj *kobj_driver; diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 3fe661fe96d1..ade2390ffe92 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -12,10 +12,31 @@ #include <linux/cpumask.h> #include <linux/nodemask.h> #include <linux/mm.h> +#include <linux/jump_label.h> #ifdef CONFIG_CPUSETS -extern int number_of_cpusets; /* How many cpusets are defined in system? */ +extern struct static_key cpusets_enabled_key; +static inline bool cpusets_enabled(void) +{ + return static_key_false(&cpusets_enabled_key); +} + +static inline int nr_cpusets(void) +{ + /* jump label reference count + the top-level cpuset */ + return static_key_count(&cpusets_enabled_key) + 1; +} + +static inline void cpuset_inc(void) +{ + static_key_slow_inc(&cpusets_enabled_key); +} + +static inline void cpuset_dec(void) +{ + static_key_slow_dec(&cpusets_enabled_key); +} extern int cpuset_init(void); extern void cpuset_init_smp(void); @@ -32,13 +53,13 @@ extern int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask); static inline int cpuset_node_allowed_softwall(int node, gfp_t gfp_mask) { - return number_of_cpusets <= 1 || + return nr_cpusets() <= 1 || __cpuset_node_allowed_softwall(node, gfp_mask); } static inline int cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask) { - return number_of_cpusets <= 1 || + return nr_cpusets() <= 1 || __cpuset_node_allowed_hardwall(node, gfp_mask); } @@ -87,25 +108,26 @@ extern void rebuild_sched_domains(void); extern void cpuset_print_task_mems_allowed(struct task_struct *p); /* - * get_mems_allowed is required when making decisions involving mems_allowed - * such as during page allocation. mems_allowed can be updated in parallel - * and depending on the new value an operation can fail potentially causing - * process failure. A retry loop with get_mems_allowed and put_mems_allowed - * prevents these artificial failures. + * read_mems_allowed_begin is required when making decisions involving + * mems_allowed such as during page allocation. mems_allowed can be updated in + * parallel and depending on the new value an operation can fail potentially + * causing process failure. A retry loop with read_mems_allowed_begin and + * read_mems_allowed_retry prevents these artificial failures. */ -static inline unsigned int get_mems_allowed(void) +static inline unsigned int read_mems_allowed_begin(void) { return read_seqcount_begin(¤t->mems_allowed_seq); } /* - * If this returns false, the operation that took place after get_mems_allowed - * may have failed. It is up to the caller to retry the operation if + * If this returns true, the operation that took place after + * read_mems_allowed_begin may have failed artificially due to a concurrent + * update of mems_allowed. It is up to the caller to retry the operation if * appropriate. */ -static inline bool put_mems_allowed(unsigned int seq) +static inline bool read_mems_allowed_retry(unsigned int seq) { - return !read_seqcount_retry(¤t->mems_allowed_seq, seq); + return read_seqcount_retry(¤t->mems_allowed_seq, seq); } static inline void set_mems_allowed(nodemask_t nodemask) @@ -123,6 +145,8 @@ static inline void set_mems_allowed(nodemask_t nodemask) #else /* !CONFIG_CPUSETS */ +static inline bool cpusets_enabled(void) { return false; } + static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} @@ -225,14 +249,14 @@ static inline void set_mems_allowed(nodemask_t nodemask) { } -static inline unsigned int get_mems_allowed(void) +static inline unsigned int read_mems_allowed_begin(void) { return 0; } -static inline bool put_mems_allowed(unsigned int seq) +static inline bool read_mems_allowed_retry(unsigned int seq) { - return true; + return false; } #endif /* !CONFIG_CPUSETS */ diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 7032518f8542..60023e5d3169 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -14,14 +14,13 @@ extern unsigned long long elfcorehdr_addr; extern unsigned long long elfcorehdr_size; -extern int __weak elfcorehdr_alloc(unsigned long long *addr, - unsigned long long *size); -extern void __weak elfcorehdr_free(unsigned long long addr); -extern ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos); -extern ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos); -extern int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma, - unsigned long from, unsigned long pfn, - unsigned long size, pgprot_t prot); +extern int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size); +extern void elfcorehdr_free(unsigned long long addr); +extern ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos); +extern ssize_t elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos); +extern int remap_oldmem_pfn_range(struct vm_area_struct *vma, + unsigned long from, unsigned long pfn, + unsigned long size, pgprot_t prot); extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, unsigned long, int); diff --git a/include/linux/cred.h b/include/linux/cred.h index 04421e825365..6c58dd7cb9ac 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -68,6 +68,7 @@ extern void groups_free(struct group_info *); extern int set_current_groups(struct group_info *); extern int set_groups(struct cred *, struct group_info *); extern int groups_search(const struct group_info *, kgid_t); +extern bool may_setgroups(void); /* access the groups "array" with this macro */ #define GROUP_AT(gi, i) \ diff --git a/include/linux/crypto.h b/include/linux/crypto.h index b92eadf92d72..2b00d92a6e6f 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -26,6 +26,19 @@ #include <linux/uaccess.h> /* + * Autoloaded crypto modules should only use a prefixed name to avoid allowing + * arbitrary modules to be loaded. Loading from userspace may still need the + * unprefixed names, so retains those aliases as well. + * This uses __MODULE_INFO directly instead of MODULE_ALIAS because pre-4.3 + * gcc (e.g. avr32 toolchain) uses __LINE__ for uniqueness, and this macro + * expands twice on the same line. Instead, use a separate base name for the + * alias. + */ +#define MODULE_ALIAS_CRYPTO(name) \ + __MODULE_INFO(alias, alias_userspace, name); \ + __MODULE_INFO(alias, alias_crypto, "crypto-" name) + +/* * Algorithm masks and types. */ #define CRYPTO_ALG_TYPE_MASK 0x0000000f diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 3b50cac7ccb3..3b9bfdb83ba6 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -308,6 +308,7 @@ extern void dentry_update_name_case(struct dentry *, struct qstr *); /* used for rename() and baskets */ extern void d_move(struct dentry *, struct dentry *); +extern void d_exchange(struct dentry *, struct dentry *); extern struct dentry *d_ancestor(struct dentry *, struct dentry *); /* appendix may either be NULL or be used for transname suffixes */ diff --git a/include/linux/efi.h b/include/linux/efi.h index 0a819e7a60c9..2bcd8d23053a 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -153,6 +153,102 @@ typedef struct { u8 sets_to_zero; } efi_time_cap_t; +typedef struct { + efi_table_hdr_t hdr; + u32 raise_tpl; + u32 restore_tpl; + u32 allocate_pages; + u32 free_pages; + u32 get_memory_map; + u32 allocate_pool; + u32 free_pool; + u32 create_event; + u32 set_timer; + u32 wait_for_event; + u32 signal_event; + u32 close_event; + u32 check_event; + u32 install_protocol_interface; + u32 reinstall_protocol_interface; + u32 uninstall_protocol_interface; + u32 handle_protocol; + u32 __reserved; + u32 register_protocol_notify; + u32 locate_handle; + u32 locate_device_path; + u32 install_configuration_table; + u32 load_image; + u32 start_image; + u32 exit; + u32 unload_image; + u32 exit_boot_services; + u32 get_next_monotonic_count; + u32 stall; + u32 set_watchdog_timer; + u32 connect_controller; + u32 disconnect_controller; + u32 open_protocol; + u32 close_protocol; + u32 open_protocol_information; + u32 protocols_per_handle; + u32 locate_handle_buffer; + u32 locate_protocol; + u32 install_multiple_protocol_interfaces; + u32 uninstall_multiple_protocol_interfaces; + u32 calculate_crc32; + u32 copy_mem; + u32 set_mem; + u32 create_event_ex; +} __packed efi_boot_services_32_t; + +typedef struct { + efi_table_hdr_t hdr; + u64 raise_tpl; + u64 restore_tpl; + u64 allocate_pages; + u64 free_pages; + u64 get_memory_map; + u64 allocate_pool; + u64 free_pool; + u64 create_event; + u64 set_timer; + u64 wait_for_event; + u64 signal_event; + u64 close_event; + u64 check_event; + u64 install_protocol_interface; + u64 reinstall_protocol_interface; + u64 uninstall_protocol_interface; + u64 handle_protocol; + u64 __reserved; + u64 register_protocol_notify; + u64 locate_handle; + u64 locate_device_path; + u64 install_configuration_table; + u64 load_image; + u64 start_image; + u64 exit; + u64 unload_image; + u64 exit_boot_services; + u64 get_next_monotonic_count; + u64 stall; + u64 set_watchdog_timer; + u64 connect_controller; + u64 disconnect_controller; + u64 open_protocol; + u64 close_protocol; + u64 open_protocol_information; + u64 protocols_per_handle; + u64 locate_handle_buffer; + u64 locate_protocol; + u64 install_multiple_protocol_interfaces; + u64 uninstall_multiple_protocol_interfaces; + u64 calculate_crc32; + u64 copy_mem; + u64 set_mem; + u64 create_event_ex; +} __packed efi_boot_services_64_t; + /* * EFI Boot Services table */ @@ -231,6 +327,15 @@ typedef enum { EfiPciIoAttributeOperationMaximum } EFI_PCI_IO_PROTOCOL_ATTRIBUTE_OPERATION; +typedef struct { + u32 read; + u32 write; +} efi_pci_io_protocol_access_32_t; + +typedef struct { + u64 read; + u64 write; +} efi_pci_io_protocol_access_64_t; typedef struct { void *read; @@ -238,6 +343,46 @@ typedef struct { } efi_pci_io_protocol_access_t; typedef struct { + u32 poll_mem; + u32 poll_io; + efi_pci_io_protocol_access_32_t mem; + efi_pci_io_protocol_access_32_t io; + efi_pci_io_protocol_access_32_t pci; + u32 copy_mem; + u32 map; + u32 unmap; + u32 allocate_buffer; + u32 free_buffer; + u32 flush; + u32 get_location; + u32 attributes; + u32 get_bar_attributes; + u32 set_bar_attributes; + uint64_t romsize; + void *romimage; +} efi_pci_io_protocol_32; + +typedef struct { + u64 poll_mem; + u64 poll_io; + efi_pci_io_protocol_access_64_t mem; + efi_pci_io_protocol_access_64_t io; + efi_pci_io_protocol_access_64_t pci; + u64 copy_mem; + u64 map; + u64 unmap; + u64 allocate_buffer; + u64 free_buffer; + u64 flush; + u64 get_location; + u64 attributes; + u64 get_bar_attributes; + u64 set_bar_attributes; + uint64_t romsize; + void *romimage; +} efi_pci_io_protocol_64; + +typedef struct { void *poll_mem; void *poll_io; efi_pci_io_protocol_access_t mem; @@ -292,6 +437,42 @@ typedef struct { typedef struct { efi_table_hdr_t hdr; + u32 get_time; + u32 set_time; + u32 get_wakeup_time; + u32 set_wakeup_time; + u32 set_virtual_address_map; + u32 convert_pointer; + u32 get_variable; + u32 get_next_variable; + u32 set_variable; + u32 get_next_high_mono_count; + u32 reset_system; + u32 update_capsule; + u32 query_capsule_caps; + u32 query_variable_info; +} efi_runtime_services_32_t; + +typedef struct { + efi_table_hdr_t hdr; + u64 get_time; + u64 set_time; + u64 get_wakeup_time; + u64 set_wakeup_time; + u64 set_virtual_address_map; + u64 convert_pointer; + u64 get_variable; + u64 get_next_variable; + u64 set_variable; + u64 get_next_high_mono_count; + u64 reset_system; + u64 update_capsule; + u64 query_capsule_caps; + u64 query_variable_info; +} efi_runtime_services_64_t; + +typedef struct { + efi_table_hdr_t hdr; void *get_time; void *set_time; void *get_wakeup_time; @@ -394,6 +575,9 @@ typedef efi_status_t efi_query_variable_store_t(u32 attributes, unsigned long si #define EFI_FILE_SYSTEM_GUID \ EFI_GUID( 0x964e5b22, 0x6459, 0x11d2, 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b ) +#define DEVICE_TREE_GUID \ + EFI_GUID( 0xb1b621d5, 0xf19c, 0x41a5, 0x83, 0x0b, 0xd9, 0x15, 0x2c, 0x69, 0xaa, 0xe0 ) + typedef struct { efi_guid_t guid; u64 table; @@ -483,6 +667,46 @@ struct efi_memory_map { unsigned long desc_size; }; +struct efi_fdt_params { + u64 system_table; + u64 mmap; + u32 mmap_size; + u32 desc_size; + u32 desc_ver; +}; + +typedef struct { + u32 revision; + u32 parent_handle; + u32 system_table; + u32 device_handle; + u32 file_path; + u32 reserved; + u32 load_options_size; + u32 load_options; + u32 image_base; + __aligned_u64 image_size; + unsigned int image_code_type; + unsigned int image_data_type; + unsigned long unload; +} efi_loaded_image_32_t; + +typedef struct { + u32 revision; + u64 parent_handle; + u64 system_table; + u64 device_handle; + u64 file_path; + u64 reserved; + u32 load_options_size; + u64 load_options; + u64 image_base; + __aligned_u64 image_size; + unsigned int image_code_type; + unsigned int image_data_type; + unsigned long unload; +} efi_loaded_image_64_t; + typedef struct { u32 revision; void *parent_handle; @@ -511,6 +735,34 @@ typedef struct { efi_char16_t filename[1]; } efi_file_info_t; +typedef struct { + u64 revision; + u32 open; + u32 close; + u32 delete; + u32 read; + u32 write; + u32 get_position; + u32 set_position; + u32 get_info; + u32 set_info; + u32 flush; +} efi_file_handle_32_t; + +typedef struct { + u64 revision; + u64 open; + u64 close; + u64 delete; + u64 read; + u64 write; + u64 get_position; + u64 set_position; + u64 get_info; + u64 set_info; + u64 flush; +} efi_file_handle_64_t; + typedef struct _efi_file_handle { u64 revision; efi_status_t (*open)(struct _efi_file_handle *, @@ -573,6 +825,7 @@ extern struct efi { efi_reset_system_t *reset_system; efi_set_virtual_address_map_t *set_virtual_address_map; struct efi_memory_map *memmap; + unsigned long flags; } efi; static inline int @@ -619,8 +872,15 @@ extern void efi_initialize_iomem_resources(struct resource *code_resource, extern void efi_get_time(struct timespec *now); extern int efi_set_rtc_mmss(const struct timespec *now); extern void efi_reserve_boot_services(void); +extern int efi_get_fdt_params(struct efi_fdt_params *params, int verbose); extern struct efi_memory_map memmap; +/* Iterate through an efi_memory_map */ +#define for_each_efi_memory_desc(m, md) \ + for ((md) = (m)->map; \ + (md) <= (efi_memory_desc_t *)((m)->map_end - (m)->desc_size); \ + (md) = (void *)(md) + (m)->desc_size) + /** * efi_range_is_wc - check the WC bit on an address range * @start: starting kvirt address @@ -659,18 +919,17 @@ extern int __init efi_setup_pcdp_console(char *); #define EFI_ARCH_1 6 /* First arch-specific bit */ #ifdef CONFIG_EFI -# ifdef CONFIG_X86 -extern int efi_enabled(int facility); -# else -static inline int efi_enabled(int facility) +/* + * Test whether the above EFI_* bits are enabled. + */ +static inline bool efi_enabled(int feature) { - return 1; + return test_bit(feature, &efi.flags) != 0; } -# endif #else -static inline int efi_enabled(int facility) +static inline bool efi_enabled(int feature) { - return 0; + return false; } #endif @@ -792,8 +1051,10 @@ struct efivars { * and we use a page for reading/writing. */ +#define EFI_VAR_NAME_LEN 1024 + struct efi_variable { - efi_char16_t VariableName[1024/sizeof(efi_char16_t)]; + efi_char16_t VariableName[EFI_VAR_NAME_LEN/sizeof(efi_char16_t)]; efi_guid_t VendorGuid; unsigned long DataSize; __u8 Data[1024]; @@ -809,6 +1070,17 @@ struct efivar_entry { bool deleting; }; +struct efi_simple_text_output_protocol_32 { + u32 reset; + u32 output_string; + u32 test_string; +}; + +struct efi_simple_text_output_protocol_64 { + u64 reset; + u64 output_string; + u64 test_string; +}; struct efi_simple_text_output_protocol { void *reset; @@ -816,6 +1088,7 @@ struct efi_simple_text_output_protocol { void *test_string; }; + extern struct list_head efivar_sysfs_list; static inline void @@ -864,7 +1137,7 @@ int efivar_entry_iter(int (*func)(struct efivar_entry *, void *), struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid, struct list_head *head, bool remove); -bool efivar_validate(struct efi_variable *var, u8 *data, unsigned long len); +bool efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len); extern struct work_struct efivar_work; void efivar_run_worker(void); diff --git a/include/linux/fs.h b/include/linux/fs.h index 23b2a35d712e..e1cee8b12d1a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -218,6 +218,13 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define ATTR_TIMES_SET (1 << 16) /* + * Whiteout is represented by a char device. The following constants define the + * mode and device number to use. + */ +#define WHITEOUT_MODE 0 +#define WHITEOUT_DEV 0 + +/* * This is the Inode Attributes structure, used for notify_change(). It * uses the above definitions as flags, to know which values have changed. * Also, in this manner, a Filesystem can look at only the values it cares @@ -249,6 +256,12 @@ struct iattr { */ #include <linux/quota.h> +/* + * Maximum number of layers of fs stack. Needs to be limited to + * prevent kernel stack overflow + */ +#define FILESYSTEM_MAX_STACK_DEPTH 2 + /** * enum positive_aop_returns - aop return codes with specific semantics * @@ -628,11 +641,13 @@ static inline int inode_unhashed(struct inode *inode) * 2: child/target * 3: xattr * 4: second non-directory - * The last is for certain operations (such as rename) which lock two + * 5: second parent (when locking independent directories in rename) + * + * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two * non-directories at once. * * The locking order between these classes is - * parent -> child -> normal -> xattr -> second non-directory + * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory */ enum inode_i_mutex_lock_class { @@ -640,7 +655,8 @@ enum inode_i_mutex_lock_class I_MUTEX_PARENT, I_MUTEX_CHILD, I_MUTEX_XATTR, - I_MUTEX_NONDIR2 + I_MUTEX_NONDIR2, + I_MUTEX_PARENT2, }; void lock_two_nondirectories(struct inode *, struct inode*); @@ -1329,6 +1345,11 @@ struct super_block { struct list_lru s_dentry_lru ____cacheline_aligned_in_smp; struct list_lru s_inode_lru ____cacheline_aligned_in_smp; struct rcu_head rcu; + + /* + * Indicates how deep in a filesystem stack this SB is + */ + int s_stack_depth; }; extern struct timespec current_fs_time(struct super_block *sb); @@ -1460,7 +1481,8 @@ extern int vfs_symlink(struct inode *, struct dentry *, const char *); extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **); extern int vfs_rmdir(struct inode *, struct dentry *); extern int vfs_unlink(struct inode *, struct dentry *, struct inode **); -extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **); +extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int); +extern int vfs_whiteout(struct inode *, struct dentry *); /* * VFS dentry helper functions. @@ -1508,7 +1530,10 @@ int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); * This allows the kernel to read directories into kernel space or * to have different dirent layouts depending on the binary type. */ -typedef int (*filldir_t)(void *, const char *, int, loff_t, u64, unsigned); +struct dir_context; +typedef int (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, + unsigned); + struct dir_context { const filldir_t actor; loff_t pos; @@ -1571,6 +1596,8 @@ struct inode_operations { int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t); int (*rename) (struct inode *, struct dentry *, struct inode *, struct dentry *); + int (*rename2) (struct inode *, struct dentry *, + struct inode *, struct dentry *, unsigned int); int (*setattr) (struct dentry *, struct iattr *); int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *); int (*setxattr) (struct dentry *, const char *,const void *,size_t,int); @@ -1585,6 +1612,9 @@ struct inode_operations { umode_t create_mode, int *opened); int (*tmpfile) (struct inode *, struct dentry *, umode_t); int (*set_acl)(struct inode *, struct posix_acl *, int); + + /* WARNING: probably going away soon, do not use! */ + int (*dentry_open)(struct dentry *, struct file *, const struct cred *); } ____cacheline_aligned; ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, @@ -1682,6 +1712,9 @@ struct super_operations { #define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT) #define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC) +#define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ + (inode)->i_rdev == WHITEOUT_DEV) + /* * Inode state bits. Protected by inode->i_lock * @@ -2079,6 +2112,7 @@ 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); +extern int vfs_open(const struct path *, struct file *, const struct cred *); extern struct file * dentry_open(const struct path *, int, const struct cred *); extern int filp_close(struct file *, fl_owner_t id); @@ -2292,7 +2326,9 @@ extern sector_t bmap(struct inode *, sector_t); #endif extern int notify_change(struct dentry *, struct iattr *, struct inode **); extern int inode_permission(struct inode *, int); +extern int __inode_permission(struct inode *, int); extern int generic_permission(struct inode *, int); +extern int __check_sticky(struct inode *dir, struct inode *inode); static inline bool execute_ok(struct inode *inode) { @@ -2500,6 +2536,9 @@ extern ssize_t generic_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out, loff_t *, size_t len, unsigned int flags); +extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, + loff_t *opos, size_t len, unsigned int flags); + extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); @@ -2564,7 +2603,7 @@ extern const struct file_operations generic_ro_fops; #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m)) -extern int vfs_readlink(struct dentry *, char __user *, int, const char *); +extern int readlink_copy(char __user *, int, const char *); extern int page_readlink(struct dentry *, char __user *, int); extern void *page_follow_link_light(struct dentry *, struct nameidata *); extern void page_put_link(struct dentry *, struct nameidata *, void *); @@ -2777,6 +2816,14 @@ static inline int is_sxid(umode_t mode) return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP)); } +static inline int check_sticky(struct inode *dir, struct inode *inode) +{ + if (!(dir->i_mode & S_ISVTX)) + return 0; + + return __check_sticky(dir, inode); +} + static inline void inode_has_no_xattr(struct inode *inode) { if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & MS_NOSEC)) diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 1c804b057fb1..7ee1774edee5 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -101,8 +101,10 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, new_dir_mask |= FS_ISDIR; } - fsnotify(old_dir, old_dir_mask, old_dir, FSNOTIFY_EVENT_INODE, old_name, fs_cookie); - fsnotify(new_dir, new_dir_mask, new_dir, FSNOTIFY_EVENT_INODE, new_name, fs_cookie); + fsnotify(old_dir, old_dir_mask, source, FSNOTIFY_EVENT_INODE, old_name, + fs_cookie); + fsnotify(new_dir, new_dir_mask, source, FSNOTIFY_EVENT_INODE, new_name, + fs_cookie); if (target) fsnotify_link_count(target); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 39b81dc7d01a..3824ac62f395 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -369,8 +369,8 @@ void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask); extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); -extern void free_hot_cold_page(struct page *page, int cold); -extern void free_hot_cold_page_list(struct list_head *list, int cold); +extern void free_hot_cold_page(struct page *page, bool cold); +extern void free_hot_cold_page_list(struct list_head *list, bool cold); extern void __free_memcg_kmem_pages(struct page *page, unsigned int order); extern void free_memcg_kmem_pages(unsigned long addr, unsigned int order); diff --git a/include/linux/hid.h b/include/linux/hid.h index 31b9d299ef6c..00c88fccd162 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -286,6 +286,7 @@ struct hid_item { #define HID_QUIRK_HIDINPUT_FORCE 0x00000080 #define HID_QUIRK_NO_EMPTY_INPUT 0x00000100 #define HID_QUIRK_NO_INIT_INPUT_REPORTS 0x00000200 +#define HID_QUIRK_ALWAYS_POLL 0x00000400 #define HID_QUIRK_SKIP_OUTPUT_REPORTS 0x00010000 #define HID_QUIRK_FULLSPEED_INTERVAL 0x10000000 #define HID_QUIRK_NO_INIT_REPORTS 0x20000000 diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index b826239bdce0..63579cb8d3dc 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -93,10 +93,6 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma); #endif /* CONFIG_DEBUG_VM */ extern unsigned long transparent_hugepage_flags; -extern int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pmd_t *dst_pmd, pmd_t *src_pmd, - struct vm_area_struct *vma, - unsigned long addr, unsigned long end); extern int split_huge_page_to_list(struct page *page, struct list_head *list); static inline int split_huge_page(struct page *page) { diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index bd1e9bcec547..42b05c4c53e5 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -400,6 +400,16 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h, return &mm->page_table_lock; } +static inline bool hugepages_supported(void) +{ + /* + * Some platform decide whether they support huge pages at boot + * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when + * there is no such support + */ + return HPAGE_SHIFT != 0; +} + #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; #define alloc_huge_page_node(h, nid) NULL diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 72ba6f5cbc8d..2abe67bd4df8 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -186,7 +186,6 @@ vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio) } extern bool vlan_do_receive(struct sk_buff **skb); -extern struct sk_buff *vlan_untag(struct sk_buff *skb); extern int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid); extern void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid); @@ -228,11 +227,6 @@ static inline bool vlan_do_receive(struct sk_buff **skb) return false; } -static inline struct sk_buff *vlan_untag(struct sk_buff *skb) -{ - return skb; -} - static inline int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid) { return 0; diff --git a/include/linux/iio/events.h b/include/linux/iio/events.h index 8bbd7bc1043d..03fa332ad2a8 100644 --- a/include/linux/iio/events.h +++ b/include/linux/iio/events.h @@ -72,7 +72,7 @@ struct iio_event_data { #define IIO_EVENT_CODE_EXTRACT_TYPE(mask) ((mask >> 56) & 0xFF) -#define IIO_EVENT_CODE_EXTRACT_DIR(mask) ((mask >> 48) & 0xCF) +#define IIO_EVENT_CODE_EXTRACT_DIR(mask) ((mask >> 48) & 0x7F) #define IIO_EVENT_CODE_EXTRACT_CHAN_TYPE(mask) ((mask >> 32) & 0xFF) diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index 369cf2cd5144..68f46cd5d514 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -84,10 +84,12 @@ static inline void iio_trigger_put(struct iio_trigger *trig) put_device(&trig->dev); } -static inline void iio_trigger_get(struct iio_trigger *trig) +static inline struct iio_trigger *iio_trigger_get(struct iio_trigger *trig) { get_device(&trig->dev); __module_get(trig->ops->owner); + + return trig; } /** diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 0068708161ff..0a21fbefdfbe 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -242,7 +242,7 @@ static inline void in_dev_put(struct in_device *idev) static __inline__ __be32 inet_make_mask(int logmask) { if (logmask) - return htonl(~((1<<(32-logmask))-1)); + return htonl(~((1U<<(32-logmask))-1)); return 0; } diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 1f44466c1e9d..c367cbdf73ab 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -258,23 +258,11 @@ extern unsigned long preset_lpj; #define SEC_JIFFIE_SC (32 - SHIFT_HZ) #endif #define NSEC_JIFFIE_SC (SEC_JIFFIE_SC + 29) -#define USEC_JIFFIE_SC (SEC_JIFFIE_SC + 19) #define SEC_CONVERSION ((unsigned long)((((u64)NSEC_PER_SEC << SEC_JIFFIE_SC) +\ TICK_NSEC -1) / (u64)TICK_NSEC)) #define NSEC_CONVERSION ((unsigned long)((((u64)1 << NSEC_JIFFIE_SC) +\ TICK_NSEC -1) / (u64)TICK_NSEC)) -#define USEC_CONVERSION \ - ((unsigned long)((((u64)NSEC_PER_USEC << USEC_JIFFIE_SC) +\ - TICK_NSEC -1) / (u64)TICK_NSEC)) -/* - * USEC_ROUND is used in the timeval to jiffie conversion. See there - * for more details. It is the scaled resolution rounding value. Note - * that it is a 64-bit value. Since, when it is applied, we are already - * in jiffies (albit scaled), it is nothing but the bits we will shift - * off. - */ -#define USEC_ROUND (u64)(((u64)1 << USEC_JIFFIE_SC) - 1) /* * The maximum jiffie value is (MAX_INT >> 1). Here we translate that * into seconds. The 64-bit case will overflow if we are not careful, diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 5c1dfb2a9e73..784304b222b3 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -69,6 +69,10 @@ struct static_key { # include <asm/jump_label.h> # define HAVE_JUMP_LABEL +#else +struct static_key { + atomic_t enabled; +}; #endif /* CC_HAVE_ASM_GOTO && CONFIG_JUMP_LABEL */ enum jump_label_type { @@ -79,6 +83,12 @@ enum jump_label_type { struct module; #include <linux/atomic.h> + +static inline int static_key_count(struct static_key *key) +{ + return atomic_read(&key->enabled); +} + #ifdef HAVE_JUMP_LABEL #define JUMP_LABEL_TYPE_FALSE_BRANCH 0UL @@ -134,10 +144,6 @@ extern void jump_label_apply_nops(struct module *mod); #else /* !HAVE_JUMP_LABEL */ -struct static_key { - atomic_t enabled; -}; - static __always_inline void jump_label_init(void) { static_key_initialized = true; @@ -145,14 +151,14 @@ static __always_inline void jump_label_init(void) static __always_inline bool static_key_false(struct static_key *key) { - if (unlikely(atomic_read(&key->enabled) > 0)) + if (unlikely(static_key_count(key) > 0)) return true; return false; } static __always_inline bool static_key_true(struct static_key *key) { - if (likely(atomic_read(&key->enabled) > 0)) + if (likely(static_key_count(key) > 0)) return true; return false; } @@ -194,7 +200,7 @@ static inline int jump_label_apply_nops(struct module *mod) static inline bool static_key_enabled(struct static_key *key) { - return (atomic_read(&key->enabled) > 0); + return static_key_count(key) > 0; } #endif /* _LINUX_JUMP_LABEL_H */ diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 51c72be4a7c3..4b2053a232c9 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -74,6 +74,7 @@ static inline unsigned int kstat_softirqs_cpu(unsigned int irq, int cpu) * Number of interrupts per specific IRQ source, since bootup */ extern unsigned int kstat_irqs(unsigned int irq); +extern unsigned int kstat_irqs_usr(unsigned int irq); /* * Number of interrupts per cpu, since bootup diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 6b06d378f3df..e465bb15912d 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -283,7 +283,7 @@ struct kgdb_io { extern struct kgdb_arch arch_kgdb_ops; -extern unsigned long __weak kgdb_arch_pc(int exception, struct pt_regs *regs); +extern unsigned long kgdb_arch_pc(int exception, struct pt_regs *regs); #ifdef CONFIG_SERIAL_KGDB_NMI extern int kgdb_register_nmi_console(void); diff --git a/include/linux/mailbox_controller.h b/include/linux/mailbox_controller.h index 9ee195b02444..d4cf96f07cfc 100644 --- a/include/linux/mailbox_controller.h +++ b/include/linux/mailbox_controller.h @@ -68,7 +68,6 @@ struct mbox_chan_ops { * last TX's status after these many millisecs * @of_xlate: Controller driver specific mapping of channel via DT * @poll: API private. Used to poll for TXDONE on all channels. - * @period: API private. Polling period. * @node: API private. To hook into list of controllers. */ struct mbox_controller { @@ -83,7 +82,6 @@ struct mbox_controller { const struct of_phandle_args *sp); /* Internal to API */ struct timer_list poll; - unsigned period; struct list_head node; }; diff --git a/include/linux/memory.h b/include/linux/memory.h index bb7384e3c3d8..8b8d8d12348e 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -35,7 +35,7 @@ struct memory_block { }; int arch_get_memory_phys_device(unsigned long start_pfn); -unsigned long __weak memory_block_size_bytes(void); +unsigned long memory_block_size_bytes(void); /* These states are exposed to userspace as text strings in sysfs */ #define MEM_ONLINE (1<<0) /* exposed to userspace */ diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 84a31ad0b791..a2901c414664 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -5,7 +5,9 @@ #include <linux/mempolicy.h> #include <linux/migrate_mode.h> -typedef struct page *new_page_t(struct page *, unsigned long private, int **); +typedef struct page *new_page_t(struct page *page, unsigned long private, + int **reason); +typedef void free_page_t(struct page *page, unsigned long private); /* * Return values from addresss_space_operations.migratepage(): @@ -38,7 +40,7 @@ enum migrate_reason { extern void putback_movable_pages(struct list_head *l); extern int migrate_page(struct address_space *, struct page *, struct page *, enum migrate_mode); -extern int migrate_pages(struct list_head *l, new_page_t x, +extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, unsigned long private, enum migrate_mode mode, int reason); extern int migrate_prep(void); @@ -56,8 +58,9 @@ extern int migrate_page_move_mapping(struct address_space *mapping, #else static inline void putback_movable_pages(struct list_head *l) {} -static inline int migrate_pages(struct list_head *l, new_page_t x, - unsigned long private, enum migrate_mode mode, int reason) +static inline int migrate_pages(struct list_head *l, new_page_t new, + free_page_t free, unsigned long private, enum migrate_mode mode, + int reason) { return -ENOSYS; } static inline int migrate_prep(void) { return -ENOSYS; } diff --git a/include/linux/mm.h b/include/linux/mm.h index c1b7414c7bef..46b8ab56b9db 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1041,6 +1041,14 @@ extern void show_free_areas(unsigned int flags); extern bool skip_free_areas_node(unsigned int flags, int nid); int shmem_zero_setup(struct vm_area_struct *); +#ifdef CONFIG_SHMEM +bool shmem_mapping(struct address_space *mapping); +#else +static inline bool shmem_mapping(struct address_space *mapping) +{ + return false; +} +#endif extern int can_do_mlock(void); extern int user_shm_lock(size_t, struct user_struct *); @@ -1123,6 +1131,7 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping, extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); +void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to); void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); int truncate_inode_page(struct address_space *mapping, struct page *page); int generic_error_remove_page(struct address_space *mapping, struct page *page); @@ -1847,9 +1856,6 @@ void page_cache_async_readahead(struct address_space *mapping, unsigned long size); unsigned long max_sane_readahead(unsigned long nr); -unsigned long ra_submit(struct file_ra_state *ra, - struct address_space *mapping, - struct file *filp); /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); @@ -1860,7 +1866,7 @@ extern int expand_downwards(struct vm_area_struct *vma, #if VM_GROWSUP extern int expand_upwards(struct vm_area_struct *vma, unsigned long address); #else - #define expand_upwards(vma, address) do { } while (0) + #define expand_upwards(vma, address) (0) #endif /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 290901a8c1de..2b58d192ea24 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -342,9 +342,9 @@ struct mm_rss_stat { struct kioctx_table; struct mm_struct { - struct vm_area_struct * mmap; /* list of VMAs */ + struct vm_area_struct *mmap; /* list of VMAs */ struct rb_root mm_rb; - struct vm_area_struct * mmap_cache; /* last find_vma result */ + u32 vmacache_seqnum; /* per-thread vmacache */ #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index e6800f0c0d7b..ac819bf9522c 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -78,10 +78,15 @@ extern int page_group_by_mobility_disabled; #define NR_MIGRATETYPE_BITS (PB_migrate_end - PB_migrate + 1) #define MIGRATETYPE_MASK ((1UL << NR_MIGRATETYPE_BITS) - 1) -static inline int get_pageblock_migratetype(struct page *page) +#define get_pageblock_migratetype(page) \ + get_pfnblock_flags_mask(page, page_to_pfn(page), \ + PB_migrate_end, MIGRATETYPE_MASK) + +static inline int get_pfnblock_migratetype(struct page *page, unsigned long pfn) { BUILD_BUG_ON(PB_migrate_end - PB_migrate != 2); - return get_pageblock_flags_mask(page, PB_migrate_end, MIGRATETYPE_MASK); + return get_pfnblock_flags_mask(page, pfn, PB_migrate_end, + MIGRATETYPE_MASK); } struct free_area { @@ -138,6 +143,7 @@ enum zone_stat_item { NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ + NR_PAGES_SCANNED, /* pages scanned since last reclaim */ #ifdef CONFIG_NUMA NUMA_HIT, /* allocated in intended node */ NUMA_MISS, /* allocated in non intended node */ @@ -316,19 +322,12 @@ enum zone_type { #ifndef __GENERATING_BOUNDS_H struct zone { - /* Fields commonly accessed by the page allocator */ + /* Read-mostly fields */ /* zone watermarks, access with *_wmark_pages(zone) macros */ unsigned long watermark[NR_WMARK]; /* - * When free pages are below this point, additional steps are taken - * when reading the number of free pages to avoid per-cpu counter - * drift allowing watermarks to be breached - */ - unsigned long percpu_drift_mark; - - /* * We don't know if the memory that we're going to allocate will be freeable * or/and it will be released eventually, so to avoid totally wasting several * GB of ram we must reserve some of the lower zone memory (otherwise we risk @@ -336,40 +335,26 @@ struct zone { * on the higher zones). This array is recalculated at runtime if the * sysctl_lowmem_reserve_ratio sysctl changes. */ - unsigned long lowmem_reserve[MAX_NR_ZONES]; - - /* - * This is a per-zone reserve of pages that should not be - * considered dirtyable memory. - */ - unsigned long dirty_balance_reserve; + long lowmem_reserve[MAX_NR_ZONES]; #ifdef CONFIG_NUMA int node; +#endif + /* - * zone reclaim becomes active if more unmapped pages exist. + * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on + * this zone's LRU. Maintained by the pageout code. */ - unsigned long min_unmapped_pages; - unsigned long min_slab_pages; -#endif + unsigned int inactive_ratio; + + struct pglist_data *zone_pgdat; struct per_cpu_pageset __percpu *pageset; + /* - * free areas of different sizes + * This is a per-zone reserve of pages that should not be + * considered dirtyable memory. */ - spinlock_t lock; -#if defined CONFIG_COMPACTION || defined CONFIG_CMA - /* Set to true when the PG_migrate_skip bits should be cleared */ - bool compact_blockskip_flush; - - /* pfns where compaction scanners should start */ - unsigned long compact_cached_free_pfn; - unsigned long compact_cached_migrate_pfn; -#endif -#ifdef CONFIG_MEMORY_HOTPLUG - /* see spanned/present_pages for more description */ - seqlock_t span_seqlock; -#endif - struct free_area free_area[MAX_ORDER]; + unsigned long dirty_balance_reserve; #ifndef CONFIG_SPARSEMEM /* @@ -379,71 +364,14 @@ struct zone { unsigned long *pageblock_flags; #endif /* CONFIG_SPARSEMEM */ -#ifdef CONFIG_COMPACTION - /* - * On compaction failure, 1<<compact_defer_shift compactions - * are skipped before trying again. The number attempted since - * last failure is tracked with compact_considered. - */ - unsigned int compact_considered; - unsigned int compact_defer_shift; - int compact_order_failed; -#endif - - ZONE_PADDING(_pad1_) - - /* Fields commonly accessed by the page reclaim scanner */ - spinlock_t lru_lock; - struct lruvec lruvec; - - unsigned long pages_scanned; /* since last reclaim */ - unsigned long flags; /* zone flags, see below */ - - /* Zone statistics */ - atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; - - /* - * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on - * this zone's LRU. Maintained by the pageout code. - */ - unsigned int inactive_ratio; - - - ZONE_PADDING(_pad2_) - /* Rarely used or read-mostly fields */ - +#ifdef CONFIG_NUMA /* - * wait_table -- the array holding the hash table - * wait_table_hash_nr_entries -- the size of the hash table array - * wait_table_bits -- wait_table_size == (1 << wait_table_bits) - * - * The purpose of all these is to keep track of the people - * waiting for a page to become available and make them - * runnable again when possible. The trouble is that this - * consumes a lot of space, especially when so few things - * wait on pages at a given time. So instead of using - * per-page waitqueues, we use a waitqueue hash table. - * - * The bucket discipline is to sleep on the same queue when - * colliding and wake all in that wait queue when removing. - * When something wakes, it must check to be sure its page is - * truly available, a la thundering herd. The cost of a - * collision is great, but given the expected load of the - * table, they should be so rare as to be outweighed by the - * benefits from the saved space. - * - * __wait_on_page_locked() and unlock_page() in mm/filemap.c, are the - * primary users of these fields, and in mm/page_alloc.c - * free_area_init_core() performs the initialization of them. + * zone reclaim becomes active if more unmapped pages exist. */ - wait_queue_head_t * wait_table; - unsigned long wait_table_hash_nr_entries; - unsigned long wait_table_bits; + unsigned long min_unmapped_pages; + unsigned long min_slab_pages; +#endif /* CONFIG_NUMA */ - /* - * Discontig memory support fields. - */ - struct pglist_data *zone_pgdat; /* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */ unsigned long zone_start_pfn; @@ -489,9 +417,11 @@ struct zone { * adjust_managed_page_count() should be used instead of directly * touching zone->managed_pages and totalram_pages. */ + unsigned long managed_pages; unsigned long spanned_pages; unsigned long present_pages; - unsigned long managed_pages; + + const char *name; /* * Number of MIGRATE_RESEVE page block. To maintain for just @@ -499,10 +429,91 @@ struct zone { */ int nr_migrate_reserve_block; +#ifdef CONFIG_MEMORY_HOTPLUG + /* see spanned/present_pages for more description */ + seqlock_t span_seqlock; +#endif + /* - * rarely used fields: + * wait_table -- the array holding the hash table + * wait_table_hash_nr_entries -- the size of the hash table array + * wait_table_bits -- wait_table_size == (1 << wait_table_bits) + * + * The purpose of all these is to keep track of the people + * waiting for a page to become available and make them + * runnable again when possible. The trouble is that this + * consumes a lot of space, especially when so few things + * wait on pages at a given time. So instead of using + * per-page waitqueues, we use a waitqueue hash table. + * + * The bucket discipline is to sleep on the same queue when + * colliding and wake all in that wait queue when removing. + * When something wakes, it must check to be sure its page is + * truly available, a la thundering herd. The cost of a + * collision is great, but given the expected load of the + * table, they should be so rare as to be outweighed by the + * benefits from the saved space. + * + * __wait_on_page_locked() and unlock_page() in mm/filemap.c, are the + * primary users of these fields, and in mm/page_alloc.c + * free_area_init_core() performs the initialization of them. */ - const char *name; + wait_queue_head_t *wait_table; + unsigned long wait_table_hash_nr_entries; + unsigned long wait_table_bits; + + ZONE_PADDING(_pad1_) + + /* Write-intensive fields used from the page allocator */ + spinlock_t lock; + + /* free areas of different sizes */ + struct free_area free_area[MAX_ORDER]; + + /* zone flags, see below */ + unsigned long flags; + + ZONE_PADDING(_pad2_) + + /* Write-intensive fields used by page reclaim */ + + /* Fields commonly accessed by the page reclaim scanner */ + spinlock_t lru_lock; + struct lruvec lruvec; + + /* + * When free pages are below this point, additional steps are taken + * when reading the number of free pages to avoid per-cpu counter + * drift allowing watermarks to be breached + */ + unsigned long percpu_drift_mark; + +#if defined CONFIG_COMPACTION || defined CONFIG_CMA + /* pfn where compaction free scanner should start */ + unsigned long compact_cached_free_pfn; + /* pfn where async and sync compaction migration scanner should start */ + unsigned long compact_cached_migrate_pfn[2]; +#endif + +#ifdef CONFIG_COMPACTION + /* + * On compaction failure, 1<<compact_defer_shift compactions + * are skipped before trying again. The number attempted since + * last failure is tracked with compact_considered. + */ + unsigned int compact_considered; + unsigned int compact_defer_shift; + int compact_order_failed; +#endif + +#if defined CONFIG_COMPACTION || defined CONFIG_CMA + /* Set to true when the PG_migrate_skip bits should be cleared */ + bool compact_blockskip_flush; +#endif + + ZONE_PADDING(_pad3_) + /* Zone statistics */ + atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; } ____cacheline_internodealigned_in_smp; typedef enum { @@ -518,6 +529,7 @@ typedef enum { ZONE_WRITEBACK, /* reclaim scanning has recently found * many pages under writeback */ + ZONE_FAIR_DEPLETED, /* fair zone policy batch depleted */ } zone_flags_t; static inline void zone_set_flag(struct zone *zone, zone_flags_t flag) @@ -555,6 +567,11 @@ static inline int zone_is_reclaim_locked(const struct zone *zone) return test_bit(ZONE_RECLAIM_LOCKED, &zone->flags); } +static inline int zone_is_fair_depleted(const struct zone *zone) +{ + return test_bit(ZONE_FAIR_DEPLETED, &zone->flags); +} + static inline int zone_is_oom_locked(const struct zone *zone) { return test_bit(ZONE_OOM_LOCKED, &zone->flags); @@ -806,10 +823,10 @@ static inline bool pgdat_is_empty(pg_data_t *pgdat) extern struct mutex zonelists_mutex; void build_all_zonelists(pg_data_t *pgdat, struct zone *zone); void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx); -bool zone_watermark_ok(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags); -bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags); +bool zone_watermark_ok(struct zone *z, unsigned int order, + unsigned long mark, int classzone_idx, int alloc_flags); +bool zone_watermark_ok_safe(struct zone *z, unsigned int order, + unsigned long mark, int classzone_idx, int alloc_flags); enum memmap_context { MEMMAP_EARLY, MEMMAP_HOTPLUG, diff --git a/include/linux/mount.h b/include/linux/mount.h index b0c1e6574e7f..fff78cb99fa1 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -81,6 +81,9 @@ extern void mnt_pin(struct vfsmount *mnt); extern void mnt_unpin(struct vfsmount *mnt); extern int __mnt_is_readonly(struct vfsmount *mnt); +struct path; +extern struct vfsmount *clone_private_mount(struct path *path); + struct file_system_type; extern struct vfsmount *vfs_kern_mount(struct file_system_type *type, int flags, const char *name, diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 5624e4e2763c..53988cb3c05a 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1247,11 +1247,22 @@ struct nfs41_free_stateid_res { unsigned int status; }; +static inline void +nfs_free_pnfs_ds_cinfo(struct pnfs_ds_commit_info *cinfo) +{ + kfree(cinfo->buckets); +} + #else struct pnfs_ds_commit_info { }; +static inline void +nfs_free_pnfs_ds_cinfo(struct pnfs_ds_commit_info *cinfo) +{ +} + #endif /* CONFIG_NFS_V4_1 */ struct nfs_page; diff --git a/include/linux/of.h b/include/linux/of.h index 435cb995904d..6f821dc62b8d 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -18,11 +18,12 @@ #include <linux/types.h> #include <linux/bitops.h> #include <linux/errno.h> -#include <linux/kref.h> +#include <linux/kobject.h> #include <linux/mod_devicetable.h> #include <linux/spinlock.h> #include <linux/topology.h> #include <linux/notifier.h> +#include <linux/list.h> #include <asm/byteorder.h> #include <asm/errno.h> @@ -37,6 +38,7 @@ struct property { struct property *next; unsigned long _flags; unsigned int unique_id; + struct bin_attribute attr; }; #if defined(CONFIG_SPARC) @@ -56,8 +58,7 @@ struct device_node { struct device_node *sibling; struct device_node *next; /* next device of same type */ struct device_node *allnext; /* next in list of all nodes */ - struct proc_dir_entry *pde; /* this node's proc directory */ - struct kref kref; + struct kobject kobj; unsigned long _flags; void *data; #if defined(CONFIG_SPARC) @@ -74,6 +75,31 @@ struct of_phandle_args { uint32_t args[MAX_PHANDLE_ARGS]; }; +struct of_reconfig_data { + struct device_node *dn; + struct property *prop; + struct property *old_prop; +}; + +/* initialize a node */ +extern struct kobj_type of_node_ktype; +static inline void of_node_init(struct device_node *node) +{ + kobject_init(&node->kobj, &of_node_ktype); +} + +/* true when node is initialized */ +static inline int of_node_is_initialized(struct device_node *node) +{ + return node && node->kobj.state_initialized; +} + +/* true when node is attached (i.e. present on sysfs) */ +static inline int of_node_is_attached(struct device_node *node) +{ + return node && node->kobj.state_in_sysfs; +} + #ifdef CONFIG_OF_DYNAMIC extern struct device_node *of_node_get(struct device_node *node); extern void of_node_put(struct device_node *node); @@ -109,11 +135,37 @@ static inline int of_node_check_flag(struct device_node *n, unsigned long flag) return test_bit(flag, &n->_flags); } +static inline int of_node_test_and_set_flag(struct device_node *n, + unsigned long flag) +{ + return test_and_set_bit(flag, &n->_flags); +} + static inline void of_node_set_flag(struct device_node *n, unsigned long flag) { set_bit(flag, &n->_flags); } +static inline void of_node_clear_flag(struct device_node *n, unsigned long flag) +{ + clear_bit(flag, &n->_flags); +} + +static inline int of_property_check_flag(struct property *p, unsigned long flag) +{ + return test_bit(flag, &p->_flags); +} + +static inline void of_property_set_flag(struct property *p, unsigned long flag) +{ + set_bit(flag, &p->_flags); +} + +static inline void of_property_clear_flag(struct property *p, unsigned long flag) +{ + clear_bit(flag, &p->_flags); +} + extern struct device_node *of_find_all_nodes(struct device_node *prev); /* @@ -156,6 +208,8 @@ static inline unsigned long of_read_ulong(const __be32 *cell, int size) /* flag descriptions */ #define OF_DYNAMIC 1 /* node and properties were allocated via kmalloc */ #define OF_DETACHED 2 /* node has been detached from the device tree */ +#define OF_POPULATED 3 /* device already created for the node */ +#define OF_POPULATED_BUS 4 /* of_platform_populate recursed to children of this node */ #define OF_IS_DYNAMIC(x) test_bit(OF_DYNAMIC, &x->_flags) #define OF_MARK_DYNAMIC(x) set_bit(OF_DYNAMIC, &x->_flags) @@ -167,6 +221,8 @@ static inline const char *of_node_full_name(const struct device_node *np) return np ? np->full_name : "<no-node>"; } +#define for_each_of_allnodes(dn) \ + for (dn = of_allnodes; dn; dn = dn->allnext) extern struct device_node *of_find_node_by_name(struct device_node *from, const char *name); extern struct device_node *of_find_node_by_type(struct device_node *from, @@ -198,6 +254,8 @@ extern struct device_node *of_find_node_with_property( extern struct property *of_find_property(const struct device_node *np, const char *name, int *lenp); +extern int of_property_count_elems_of_size(const struct device_node *np, + const char *propname, int elem_size); extern int of_property_read_u32_index(const struct device_node *np, const char *propname, u32 index, u32 *out_value); @@ -215,14 +273,12 @@ extern int of_property_read_u64(const struct device_node *np, extern int of_property_read_string(struct device_node *np, const char *propname, const char **out_string); -extern int of_property_read_string_index(struct device_node *np, - const char *propname, - int index, const char **output); extern int of_property_match_string(struct device_node *np, const char *propname, const char *string); -extern int of_property_count_strings(struct device_node *np, - const char *propname); +extern int of_property_read_string_helper(struct device_node *np, + const char *propname, + const char **out_strs, size_t sz, int index); extern int of_device_is_compatible(const struct device_node *device, const char *); extern int of_device_is_available(const struct device_node *device); @@ -267,15 +323,6 @@ extern int of_update_property(struct device_node *np, struct property *newprop); #define OF_RECONFIG_REMOVE_PROPERTY 0x0004 #define OF_RECONFIG_UPDATE_PROPERTY 0x0005 -struct of_prop_reconfig { - struct device_node *dn; - struct property *prop; -}; - -extern int of_reconfig_notifier_register(struct notifier_block *); -extern int of_reconfig_notifier_unregister(struct notifier_block *); -extern int of_reconfig_notify(unsigned long, void *); - extern int of_attach_node(struct device_node *); extern int of_detach_node(struct device_node *); @@ -390,6 +437,12 @@ static inline struct device_node *of_find_compatible_node( return NULL; } +static inline int of_property_count_elems_of_size(const struct device_node *np, + const char *propname, int elem_size) +{ + return -ENOSYS; +} + static inline int of_property_read_u32_index(const struct device_node *np, const char *propname, u32 index, u32 *out_value) { @@ -422,15 +475,9 @@ static inline int of_property_read_string(struct device_node *np, return -ENOSYS; } -static inline int of_property_read_string_index(struct device_node *np, - const char *propname, int index, - const char **out_string) -{ - return -ENOSYS; -} - -static inline int of_property_count_strings(struct device_node *np, - const char *propname) +static inline int of_property_read_string_helper(struct device_node *np, + const char *propname, + const char **out_strs, size_t sz, int index) { return -ENOSYS; } @@ -536,6 +583,138 @@ static inline struct device_node *of_find_matching_node( } /** + * of_property_read_string_array() - Read an array of strings from a multiple + * strings property. + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * @out_strs: output array of string pointers. + * @sz: number of array elements to read. + * + * Search for a property in a device tree node and retrieve a list of + * terminated string values (pointer to data, not a copy) in that property. + * + * If @out_strs is NULL, the number of strings in the property is returned. + */ +static inline int of_property_read_string_array(struct device_node *np, + const char *propname, const char **out_strs, + size_t sz) +{ + return of_property_read_string_helper(np, propname, out_strs, sz, 0); +} + +/** + * of_property_count_strings() - Find and return the number of strings from a + * multiple strings property. + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * + * Search for a property in a device tree node and retrieve the number of null + * terminated string contain in it. Returns the number of strings on + * success, -EINVAL if the property does not exist, -ENODATA if property + * does not have a value, and -EILSEQ if the string is not null-terminated + * within the length of the property data. + */ +static inline int of_property_count_strings(struct device_node *np, + const char *propname) +{ + return of_property_read_string_helper(np, propname, NULL, 0, 0); +} + +/** + * of_property_read_string_index() - Find and read a string from a multiple + * strings property. + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * @index: index of the string in the list of strings + * @out_string: pointer to null terminated return string, modified only if + * return value is 0. + * + * Search for a property in a device tree node and retrieve a null + * terminated string value (pointer to data, not a copy) in the list of strings + * contained in that property. + * Returns 0 on success, -EINVAL if the property does not exist, -ENODATA if + * property does not have a value, and -EILSEQ if the string is not + * null-terminated within the length of the property data. + * + * The out_string pointer is modified only if a valid string can be decoded. + */ +static inline int of_property_read_string_index(struct device_node *np, + const char *propname, + int index, const char **output) +{ + int rc = of_property_read_string_helper(np, propname, output, 1, index); + return rc < 0 ? rc : 0; +} + +/* + * of_property_count_u8_elems - Count the number of u8 elements in a property + * + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * + * Search for a property in a device node and count the number of u8 elements + * in it. Returns number of elements on sucess, -EINVAL if the property does + * not exist or its length does not match a multiple of u8 and -ENODATA if the + * property does not have a value. + */ +static inline int of_property_count_u8_elems(const struct device_node *np, + const char *propname) +{ + return of_property_count_elems_of_size(np, propname, sizeof(u8)); +} + +/** + * of_property_count_u16_elems - Count the number of u16 elements in a property + * + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * + * Search for a property in a device node and count the number of u16 elements + * in it. Returns number of elements on sucess, -EINVAL if the property does + * not exist or its length does not match a multiple of u16 and -ENODATA if the + * property does not have a value. + */ +static inline int of_property_count_u16_elems(const struct device_node *np, + const char *propname) +{ + return of_property_count_elems_of_size(np, propname, sizeof(u16)); +} + +/** + * of_property_count_u32_elems - Count the number of u32 elements in a property + * + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * + * Search for a property in a device node and count the number of u32 elements + * in it. Returns number of elements on sucess, -EINVAL if the property does + * not exist or its length does not match a multiple of u32 and -ENODATA if the + * property does not have a value. + */ +static inline int of_property_count_u32_elems(const struct device_node *np, + const char *propname) +{ + return of_property_count_elems_of_size(np, propname, sizeof(u32)); +} + +/** + * of_property_count_u64_elems - Count the number of u64 elements in a property + * + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * + * Search for a property in a device node and count the number of u64 elements + * in it. Returns number of elements on sucess, -EINVAL if the property does + * not exist or its length does not match a multiple of u64 and -ENODATA if the + * property does not have a value. + */ +static inline int of_property_count_u64_elems(const struct device_node *np, + const char *propname) +{ + return of_property_count_elems_of_size(np, propname, sizeof(u64)); +} + +/** * of_property_read_bool - Findfrom a property * @np: device node from which the property value is to be read. * @propname: name of the property to be searched. @@ -633,14 +812,166 @@ static inline int of_get_available_child_count(const struct device_node *np) return num; } -#if defined(CONFIG_PROC_FS) && defined(CONFIG_PROC_DEVICETREE) -extern void proc_device_tree_add_node(struct device_node *, struct proc_dir_entry *); -extern void proc_device_tree_add_prop(struct proc_dir_entry *pde, struct property *prop); -extern void proc_device_tree_remove_prop(struct proc_dir_entry *pde, - struct property *prop); -extern void proc_device_tree_update_prop(struct proc_dir_entry *pde, - struct property *newprop, - struct property *oldprop); +#ifdef CONFIG_OF +#define _OF_DECLARE(table, name, compat, fn, fn_type) \ + static const struct of_device_id __of_table_##name \ + __used __section(__##table##_of_table) \ + = { .compatible = compat, \ + .data = (fn == (fn_type)NULL) ? fn : fn } +#else +#define _OF_DECLARE(table, name, compat, fn, fn_type) \ + static const struct of_device_id __of_table_##name \ + __attribute__((unused)) \ + = { .compatible = compat, \ + .data = (fn == (fn_type)NULL) ? fn : fn } +#endif + +typedef int (*of_init_fn_2)(struct device_node *, struct device_node *); +typedef void (*of_init_fn_1)(struct device_node *); + +#define OF_DECLARE_1(table, name, compat, fn) \ + _OF_DECLARE(table, name, compat, fn, of_init_fn_1) +#define OF_DECLARE_2(table, name, compat, fn) \ + _OF_DECLARE(table, name, compat, fn, of_init_fn_2) + +/** + * struct of_changeset_entry - Holds a changeset entry + * + * @node: list_head for the log list + * @action: notifier action + * @np: pointer to the device node affected + * @prop: pointer to the property affected + * @old_prop: hold a pointer to the original property + * + * Every modification of the device tree during a changeset + * is held in a list of of_changeset_entry structures. + * That way we can recover from a partial application, or we can + * revert the changeset + */ +struct of_changeset_entry { + struct list_head node; + unsigned long action; + struct device_node *np; + struct property *prop; + struct property *old_prop; +}; + +/** + * struct of_changeset - changeset tracker structure + * + * @entries: list_head for the changeset entries + * + * changesets are a convenient way to apply bulk changes to the + * live tree. In case of an error, changes are rolled-back. + * changesets live on after initial application, and if not + * destroyed after use, they can be reverted in one single call. + */ +struct of_changeset { + struct list_head entries; +}; + +enum of_reconfig_change { + OF_RECONFIG_NO_CHANGE = 0, + OF_RECONFIG_CHANGE_ADD, + OF_RECONFIG_CHANGE_REMOVE, +}; + +#ifdef CONFIG_OF_DYNAMIC +extern int of_reconfig_notifier_register(struct notifier_block *); +extern int of_reconfig_notifier_unregister(struct notifier_block *); +extern int of_reconfig_notify(unsigned long, struct of_reconfig_data *rd); +extern int of_reconfig_get_state_change(unsigned long action, + struct of_reconfig_data *arg); + +extern void of_changeset_init(struct of_changeset *ocs); +extern void of_changeset_destroy(struct of_changeset *ocs); +extern int of_changeset_apply(struct of_changeset *ocs); +extern int of_changeset_revert(struct of_changeset *ocs); +extern int of_changeset_action(struct of_changeset *ocs, + unsigned long action, struct device_node *np, + struct property *prop); + +static inline int of_changeset_attach_node(struct of_changeset *ocs, + struct device_node *np) +{ + return of_changeset_action(ocs, OF_RECONFIG_ATTACH_NODE, np, NULL); +} + +static inline int of_changeset_detach_node(struct of_changeset *ocs, + struct device_node *np) +{ + return of_changeset_action(ocs, OF_RECONFIG_DETACH_NODE, np, NULL); +} + +static inline int of_changeset_add_property(struct of_changeset *ocs, + struct device_node *np, struct property *prop) +{ + return of_changeset_action(ocs, OF_RECONFIG_ADD_PROPERTY, np, prop); +} + +static inline int of_changeset_remove_property(struct of_changeset *ocs, + struct device_node *np, struct property *prop) +{ + return of_changeset_action(ocs, OF_RECONFIG_REMOVE_PROPERTY, np, prop); +} + +static inline int of_changeset_update_property(struct of_changeset *ocs, + struct device_node *np, struct property *prop) +{ + return of_changeset_action(ocs, OF_RECONFIG_UPDATE_PROPERTY, np, prop); +} +#else /* CONFIG_OF_DYNAMIC */ +static inline int of_reconfig_notifier_register(struct notifier_block *nb) +{ + return -EINVAL; +} +static inline int of_reconfig_notifier_unregister(struct notifier_block *nb) +{ + return -EINVAL; +} +static inline int of_reconfig_notify(unsigned long action, + struct of_reconfig_data *arg) +{ + return -EINVAL; +} +static inline int of_reconfig_get_state_change(unsigned long action, + struct of_reconfig_data *arg) +{ + return -EINVAL; +} +#endif /* CONFIG_OF_DYNAMIC */ + +/* CONFIG_OF_RESOLVE api */ +extern int of_resolve_phandles(struct device_node *tree); + +/** + * Overlay support + */ + +#ifdef CONFIG_OF_OVERLAY + +/* ID based overlays; the API for external users */ +int of_overlay_create(struct device_node *tree); +int of_overlay_destroy(int id); +int of_overlay_destroy_all(void); + +#else + +static inline int of_overlay_create(struct device_node *tree) +{ + return -ENOTSUPP; +} + +static inline int of_overlay_destroy(int id) +{ + return -ENOTSUPP; +} + +static inline int of_overlay_destroy_all(void) +{ + return -ENOTSUPP; +} + #endif #endif /* _LINUX_OF_H */ diff --git a/include/linux/of_address.h b/include/linux/of_address.h index 5f6ed6b182b8..906ca7681756 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -40,7 +40,6 @@ extern u64 of_translate_dma_address(struct device_node *dev, #ifdef CONFIG_OF_ADDRESS extern u64 of_translate_address(struct device_node *np, const __be32 *addr); -extern bool of_can_translate_address(struct device_node *dev); extern int of_address_to_resource(struct device_node *dev, int index, struct resource *r); extern struct device_node *of_find_matching_node_by_address( diff --git a/include/linux/of_graph.h b/include/linux/of_graph.h new file mode 100644 index 000000000000..56e0507a0d58 --- /dev/null +++ b/include/linux/of_graph.h @@ -0,0 +1,65 @@ +/* + * OF graph binding parsing helpers + * + * Copyright (C) 2012 - 2013 Samsung Electronics Co., Ltd. + * Author: Sylwester Nawrocki <s.nawrocki@samsung.com> + * + * Copyright (C) 2012 Renesas Electronics Corp. + * Author: Guennadi Liakhovetski <g.liakhovetski@gmx.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + */ +#ifndef __LINUX_OF_GRAPH_H +#define __LINUX_OF_GRAPH_H + +/** + * struct of_endpoint - the OF graph endpoint data structure + * @port: identifier (value of reg property) of a port this endpoint belongs to + * @id: identifier (value of reg property) of this endpoint + * @local_node: pointer to device_node of this endpoint + */ +struct of_endpoint { + unsigned int port; + unsigned int id; + const struct device_node *local_node; +}; + +#ifdef CONFIG_OF +int of_graph_parse_endpoint(const struct device_node *node, + struct of_endpoint *endpoint); +struct device_node *of_graph_get_next_endpoint(const struct device_node *parent, + struct device_node *previous); +struct device_node *of_graph_get_remote_port_parent( + const struct device_node *node); +struct device_node *of_graph_get_remote_port(const struct device_node *node); +#else + +static inline int of_graph_parse_endpoint(const struct device_node *node, + struct of_endpoint *endpoint) +{ + return -ENOSYS; +} +static inline struct device_node *of_graph_get_next_endpoint( + const struct device_node *parent, + struct device_node *previous) +{ + return NULL; +} + +static inline struct device_node *of_graph_get_remote_port_parent( + const struct device_node *node) +{ + return NULL; +} + +static inline struct device_node *of_graph_get_remote_port( + const struct device_node *node) +{ + return NULL; +} + +#endif /* CONFIG_OF */ + +#endif /* __LINUX_OF_GRAPH_H */ diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index 05cb4a928252..9142922871a7 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -72,6 +72,7 @@ extern int of_platform_populate(struct device_node *root, const struct of_device_id *matches, const struct of_dev_auxdata *lookup, struct device *parent); +extern void of_platform_depopulate(struct device *parent); #else static inline int of_platform_populate(struct device_node *root, const struct of_device_id *matches, @@ -80,6 +81,13 @@ static inline int of_platform_populate(struct device_node *root, { return -ENODEV; } +static inline void of_platform_depopulate(struct device *parent) { } +#endif + +#ifdef CONFIG_OF_DYNAMIC +extern void of_platform_register_reconfig_notifier(void); +#else +static inline void of_platform_register_reconfig_notifier(void) { } #endif #endif /* _LINUX_OF_PLATFORM_H */ diff --git a/include/linux/oom.h b/include/linux/oom.h index 4cd62677feb9..17f0949bd822 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -50,6 +50,9 @@ static inline bool oom_task_origin(const struct task_struct *p) extern unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, unsigned long totalpages); + +extern int oom_kills_count(void); +extern void note_oom_kill(void); extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, unsigned int points, unsigned long totalpages, struct mem_cgroup *memcg, nodemask_t *nodemask, diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index ca71a1d347a0..3c545b48aeab 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -198,6 +198,7 @@ struct page; /* forward declaration */ TESTPAGEFLAG(Locked, locked) PAGEFLAG(Error, error) TESTCLEARFLAG(Error, error) PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced) + __SETPAGEFLAG(Referenced, referenced) PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty) PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru) PAGEFLAG(Active, active) __CLEARPAGEFLAG(Active, active) @@ -208,6 +209,7 @@ PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned) /* Xen */ PAGEFLAG(SavePinned, savepinned); /* Xen */ PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved) PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked) + __SETPAGEFLAG(SwapBacked, swapbacked) __PAGEFLAG(SlobFree, slob_free) diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index c08730c10c7a..2baeee12f48e 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -65,33 +65,26 @@ extern int pageblock_order; /* Forward declaration */ struct page; -unsigned long get_pageblock_flags_mask(struct page *page, +unsigned long get_pfnblock_flags_mask(struct page *page, + unsigned long pfn, unsigned long end_bitidx, unsigned long mask); -void set_pageblock_flags_mask(struct page *page, + +void set_pfnblock_flags_mask(struct page *page, unsigned long flags, + unsigned long pfn, unsigned long end_bitidx, unsigned long mask); /* Declarations for getting and setting flags. See mm/page_alloc.c */ -static inline unsigned long get_pageblock_flags_group(struct page *page, - int start_bitidx, int end_bitidx) -{ - unsigned long nr_flag_bits = end_bitidx - start_bitidx + 1; - unsigned long mask = (1 << nr_flag_bits) - 1; - - return get_pageblock_flags_mask(page, end_bitidx, mask); -} - -static inline void set_pageblock_flags_group(struct page *page, - unsigned long flags, - int start_bitidx, int end_bitidx) -{ - unsigned long nr_flag_bits = end_bitidx - start_bitidx + 1; - unsigned long mask = (1 << nr_flag_bits) - 1; - - set_pageblock_flags_mask(page, flags, end_bitidx, mask); -} +#define get_pageblock_flags_group(page, start_bitidx, end_bitidx) \ + get_pfnblock_flags_mask(page, page_to_pfn(page), \ + end_bitidx, \ + (1 << (end_bitidx - start_bitidx + 1)) - 1) +#define set_pageblock_flags_group(page, flags, start_bitidx, end_bitidx) \ + set_pfnblock_flags_mask(page, flags, page_to_pfn(page), \ + end_bitidx, \ + (1 << (end_bitidx - start_bitidx + 1)) - 1) #ifdef CONFIG_COMPACTION #define get_pageblock_skip(page) \ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 1710d1b060ba..fcebdda3651c 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -99,7 +99,7 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) #define page_cache_get(page) get_page(page) #define page_cache_release(page) put_page(page) -void release_pages(struct page **pages, int nr, int cold); +void release_pages(struct page **pages, int nr, bool cold); /* * speculatively take a reference to a page. @@ -243,12 +243,116 @@ static inline struct page *page_cache_alloc_readahead(struct address_space *x) typedef int filler_t(void *, struct page *); -extern struct page * find_get_page(struct address_space *mapping, - pgoff_t index); -extern struct page * find_lock_page(struct address_space *mapping, - pgoff_t index); -extern struct page * find_or_create_page(struct address_space *mapping, - pgoff_t index, gfp_t gfp_mask); +pgoff_t page_cache_next_hole(struct address_space *mapping, + pgoff_t index, unsigned long max_scan); +pgoff_t page_cache_prev_hole(struct address_space *mapping, + pgoff_t index, unsigned long max_scan); + +#define FGP_ACCESSED 0x00000001 +#define FGP_LOCK 0x00000002 +#define FGP_CREAT 0x00000004 +#define FGP_WRITE 0x00000008 +#define FGP_NOFS 0x00000010 +#define FGP_NOWAIT 0x00000020 + +struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, + int fgp_flags, gfp_t cache_gfp_mask); + +/** + * find_get_page - find and get a page reference + * @mapping: the address_space to search + * @offset: the page index + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned with an increased refcount. + * + * Otherwise, %NULL is returned. + */ +static inline struct page *find_get_page(struct address_space *mapping, + pgoff_t offset) +{ + return pagecache_get_page(mapping, offset, 0, 0); +} + +static inline struct page *find_get_page_flags(struct address_space *mapping, + pgoff_t offset, int fgp_flags) +{ + return pagecache_get_page(mapping, offset, fgp_flags, 0); +} + +/** + * find_lock_page - locate, pin and lock a pagecache page + * pagecache_get_page - find and get a page reference + * @mapping: the address_space to search + * @offset: the page index + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. + * + * Otherwise, %NULL is returned. + * + * find_lock_page() may sleep. + */ +static inline struct page *find_lock_page(struct address_space *mapping, + pgoff_t offset) +{ + return pagecache_get_page(mapping, offset, FGP_LOCK, 0); +} + +/** + * find_or_create_page - locate or add a pagecache page + * @mapping: the page's address_space + * @index: the page's index into the mapping + * @gfp_mask: page allocation mode + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. + * + * If the page is not present, a new page is allocated using @gfp_mask + * and added to the page cache and the VM's LRU list. The page is + * returned locked and with an increased refcount. + * + * On memory exhaustion, %NULL is returned. + * + * find_or_create_page() may sleep, even if @gfp_flags specifies an + * atomic allocation! + */ +static inline struct page *find_or_create_page(struct address_space *mapping, + pgoff_t offset, gfp_t gfp_mask) +{ + return pagecache_get_page(mapping, offset, + FGP_LOCK|FGP_ACCESSED|FGP_CREAT, + gfp_mask); +} + +/** + * grab_cache_page_nowait - returns locked page at given index in given cache + * @mapping: target address_space + * @index: the page index + * + * Same as grab_cache_page(), but do not wait if the page is unavailable. + * This is intended for speculative data generators, where the data can + * be regenerated if the page couldn't be grabbed. This routine should + * be safe to call while holding the lock for another page. + * + * Clear __GFP_FS when allocating the page to avoid recursion into the fs + * and deadlock against the caller's locked page. + */ +static inline struct page *grab_cache_page_nowait(struct address_space *mapping, + pgoff_t index) +{ + return pagecache_get_page(mapping, index, + FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT, + mapping_gfp_mask(mapping)); +} + +struct page *find_get_entry(struct address_space *mapping, pgoff_t offset); +struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset); +unsigned find_get_entries(struct address_space *mapping, pgoff_t start, + unsigned int nr_entries, struct page **entries, + pgoff_t *indices); unsigned find_get_pages(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, @@ -268,10 +372,6 @@ static inline struct page *grab_cache_page(struct address_space *mapping, return find_or_create_page(mapping, index, mapping_gfp_mask(mapping)); } -extern struct page * grab_cache_page_nowait(struct address_space *mapping, - pgoff_t index); -extern struct page * read_cache_page_async(struct address_space *mapping, - pgoff_t index, filler_t *filler, void *data); extern struct page * read_cache_page(struct address_space *mapping, pgoff_t index, filler_t *filler, void *data); extern struct page * read_cache_page_gfp(struct address_space *mapping, @@ -279,14 +379,6 @@ extern struct page * read_cache_page_gfp(struct address_space *mapping, extern int read_cache_pages(struct address_space *mapping, struct list_head *pages, filler_t *filler, void *data); -static inline struct page *read_mapping_page_async( - struct address_space *mapping, - pgoff_t index, void *data) -{ - filler_t *filler = (filler_t *)mapping->a_ops->readpage; - return read_cache_page_async(mapping, index, filler, data); -} - static inline struct page *read_mapping_page(struct address_space *mapping, pgoff_t index, void *data) { diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index e4dbfab37729..b45d391b4540 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -22,6 +22,11 @@ struct pagevec { void __pagevec_release(struct pagevec *pvec); void __pagevec_lru_add(struct pagevec *pvec); +unsigned pagevec_lookup_entries(struct pagevec *pvec, + struct address_space *mapping, + pgoff_t start, unsigned nr_entries, + pgoff_t *indices); +void pagevec_remove_exceptionals(struct pagevec *pvec); unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping, pgoff_t start, unsigned nr_pages); unsigned pagevec_lookup_tag(struct pagevec *pvec, diff --git a/include/linux/pci.h b/include/linux/pci.h index 33aa2caf0f0c..d662546f77d8 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -170,6 +170,8 @@ enum pci_dev_flags { PCI_DEV_FLAGS_NO_D3 = (__force pci_dev_flags_t) 2, /* Provide indication device is assigned by a Virtual Machine Manager */ PCI_DEV_FLAGS_ASSIGNED = (__force pci_dev_flags_t) 4, + /* Do not use bus resets for device */ + PCI_DEV_FLAGS_NO_BUS_RESET = (__force pci_dev_flags_t) (1 << 6), }; enum pci_irq_reroute_variant { @@ -324,6 +326,7 @@ struct pci_dev { unsigned int is_added:1; unsigned int is_busmaster:1; /* device is busmaster */ unsigned int no_msi:1; /* device may not use msi */ + unsigned int no_64bit_msi:1; /* device may only use 32-bit MSIs */ unsigned int block_cfg_access:1; /* config space access is blocked */ unsigned int broken_parity_status:1; /* Device generates false positive parity */ unsigned int irq_reroute_variant:2; /* device needs IRQ rerouting variant */ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 97fbecdd7a40..057c1d8c77e5 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2551,6 +2551,7 @@ #define PCI_DEVICE_ID_INTEL_MFD_EMMC0 0x0823 #define PCI_DEVICE_ID_INTEL_MFD_EMMC1 0x0824 #define PCI_DEVICE_ID_INTEL_MRST_SD2 0x084F +#define PCI_DEVICE_ID_INTEL_QUARK_X1000_ILB 0x095E #define PCI_DEVICE_ID_INTEL_I960 0x0960 #define PCI_DEVICE_ID_INTEL_I960RM 0x0962 #define PCI_DEVICE_ID_INTEL_CENTERTON_ILB 0x0c60 diff --git a/include/linux/plist.h b/include/linux/plist.h index aa0fb390bd29..8b6c970cff6c 100644 --- a/include/linux/plist.h +++ b/include/linux/plist.h @@ -98,6 +98,13 @@ struct plist_node { } /** + * PLIST_HEAD - declare and init plist_head + * @head: name for struct plist_head variable + */ +#define PLIST_HEAD(head) \ + struct plist_head head = PLIST_HEAD_INIT(head) + +/** * PLIST_NODE_INIT - static struct plist_node initializer * @node: struct plist_node variable name * @__prio: initial node priority @@ -134,6 +141,8 @@ static inline void plist_node_init(struct plist_node *node, int prio) extern void plist_add(struct plist_node *node, struct plist_head *head); extern void plist_del(struct plist_node *node, struct plist_head *head); +extern void plist_requeue(struct plist_node *node, struct plist_head *head); + /** * plist_for_each - iterate over the plist * @pos: the type * to use as a loop counter @@ -143,6 +152,16 @@ extern void plist_del(struct plist_node *node, struct plist_head *head); list_for_each_entry(pos, &(head)->node_list, node_list) /** + * plist_for_each_continue - continue iteration over the plist + * @pos: the type * to use as a loop cursor + * @head: the head for your list + * + * Continue to iterate over plist, continuing after the current position. + */ +#define plist_for_each_continue(pos, head) \ + list_for_each_entry_continue(pos, &(head)->node_list, node_list) + +/** * plist_for_each_safe - iterate safely over a plist of given type * @pos: the type * to use as a loop counter * @n: another type * to use as temporary storage @@ -163,6 +182,18 @@ extern void plist_del(struct plist_node *node, struct plist_head *head); list_for_each_entry(pos, &(head)->node_list, mem.node_list) /** + * plist_for_each_entry_continue - continue iteration over list of given type + * @pos: the type * to use as a loop cursor + * @head: the head for your list + * @m: the name of the list_struct within the struct + * + * Continue to iterate over list of given type, continuing after + * the current position. + */ +#define plist_for_each_entry_continue(pos, head, m) \ + list_for_each_entry_continue(pos, &(head)->node_list, m.node_list) + +/** * plist_for_each_entry_safe - iterate safely over list of given type * @pos: the type * to use as a loop counter * @n: another type * to use as temporary storage @@ -229,6 +260,20 @@ static inline int plist_node_empty(const struct plist_node *node) #endif /** + * plist_next - get the next entry in list + * @pos: the type * to cursor + */ +#define plist_next(pos) \ + list_next_entry(pos, node_list) + +/** + * plist_prev - get the prev entry in list + * @pos: the type * to cursor + */ +#define plist_prev(pos) \ + list_prev_entry(pos, node_list) + +/** * plist_first - return the first node (and thus, highest priority) * @head: the &struct plist_head pointer * diff --git a/include/linux/pm.h b/include/linux/pm.h index 8c6583a53a06..ea05bc207c93 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -596,6 +596,7 @@ extern int dev_pm_put_subsys_data(struct device *dev); */ struct dev_pm_domain { struct dev_pm_ops ops; + void (*detach)(struct device *dev, bool power_off); }; /* diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 7c1d252b20c0..66cfa1a39d81 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -310,4 +310,56 @@ static inline void pm_genpd_syscore_poweron(struct device *dev) pm_genpd_syscore_switch(dev, false); } +/* OF PM domain providers */ +struct of_device_id; + +struct genpd_onecell_data { + struct generic_pm_domain **domains; + unsigned int num_domains; +}; + +typedef struct generic_pm_domain *(*genpd_xlate_t)(struct of_phandle_args *args, + void *data); + +#ifdef CONFIG_PM_GENERIC_DOMAINS_OF +int __of_genpd_add_provider(struct device_node *np, genpd_xlate_t xlate, + void *data); +void of_genpd_del_provider(struct device_node *np); + +struct generic_pm_domain *__of_genpd_xlate_simple( + struct of_phandle_args *genpdspec, + void *data); +struct generic_pm_domain *__of_genpd_xlate_onecell( + struct of_phandle_args *genpdspec, + void *data); + +int genpd_dev_pm_attach(struct device *dev); +#else /* !CONFIG_PM_GENERIC_DOMAINS_OF */ +static inline int __of_genpd_add_provider(struct device_node *np, + genpd_xlate_t xlate, void *data) +{ + return 0; +} +static inline void of_genpd_del_provider(struct device_node *np) {} + +#define __of_genpd_xlate_simple NULL +#define __of_genpd_xlate_onecell NULL + +static inline int genpd_dev_pm_attach(struct device *dev) +{ + return -ENODEV; +} +#endif /* CONFIG_PM_GENERIC_DOMAINS_OF */ + +static inline int of_genpd_add_provider_simple(struct device_node *np, + struct generic_pm_domain *genpd) +{ + return __of_genpd_add_provider(np, __of_genpd_xlate_simple, genpd); +} +static inline int of_genpd_add_provider_onecell(struct device_node *np, + struct genpd_onecell_data *data) +{ + return __of_genpd_add_provider(np, __of_genpd_xlate_onecell, data); +} + #endif /* _LINUX_PM_DOMAIN_H */ diff --git a/include/linux/power/charger-manager.h b/include/linux/power/charger-manager.h index 07e7945a1ff2..e97fc656a058 100644 --- a/include/linux/power/charger-manager.h +++ b/include/linux/power/charger-manager.h @@ -253,9 +253,6 @@ struct charger_manager { struct device *dev; struct charger_desc *desc; - struct power_supply *fuel_gauge; - struct power_supply **charger_stat; - #ifdef CONFIG_THERMAL struct thermal_zone_device *tzd_batt; #endif diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index 9974975d40db..4af3fdc85b01 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -53,7 +53,8 @@ struct persistent_ram_zone { }; struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, - u32 sig, struct persistent_ram_ecc_info *ecc_info); + u32 sig, struct persistent_ram_ecc_info *ecc_info, + unsigned int memtype); void persistent_ram_free(struct persistent_ram_zone *prz); void persistent_ram_zap(struct persistent_ram_zone *prz); @@ -76,6 +77,7 @@ ssize_t persistent_ram_ecc_string(struct persistent_ram_zone *prz, struct ramoops_platform_data { unsigned long mem_size; unsigned long mem_address; + unsigned int mem_type; unsigned long record_size; unsigned long console_size; unsigned long ftrace_size; diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 403940787be1..e8be53ecfc45 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -219,6 +219,7 @@ static inline void radix_tree_replace_slot(void **pslot, void *item) int radix_tree_insert(struct radix_tree_root *, unsigned long, void *); void *radix_tree_lookup(struct radix_tree_root *, unsigned long); void **radix_tree_lookup_slot(struct radix_tree_root *, unsigned long); +void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); void *radix_tree_delete(struct radix_tree_root *, unsigned long); unsigned int radix_tree_gang_lookup(struct radix_tree_root *root, void **results, @@ -226,10 +227,6 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results, unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results, unsigned long *indices, unsigned long first_index, unsigned int max_items); -unsigned long radix_tree_next_hole(struct radix_tree_root *root, - unsigned long index, unsigned long max_scan); -unsigned long radix_tree_prev_hole(struct radix_tree_root *root, - unsigned long index, unsigned long max_scan); int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); void radix_tree_init(void); diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 72bf3a01a4ee..a9a98ff6e339 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -555,6 +555,21 @@ static inline void rcu_preempt_sleep_check(void) #define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v) /** + * lockless_dereference() - safely load a pointer for later dereference + * @p: The pointer to load + * + * Similar to rcu_dereference(), but for situations where the pointed-to + * object's lifetime is managed by something other than RCU. That + * "something other" might be reference counting or simple immortality. + */ +#define lockless_dereference(p) \ +({ \ + typeof(p) _________p1 = ACCESS_ONCE(p); \ + smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ + (_________p1); \ +}) + +/** * rcu_assign_pointer() - assign to RCU-protected pointer * @p: pointer to assign to * @v: value to assign (publish) diff --git a/include/linux/sched.h b/include/linux/sched.h index ccd0c6f24f2c..218b058060f1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -59,6 +59,10 @@ struct sched_param { #define SCHED_ATTR_SIZE_VER0 48 /* sizeof first published struct */ +#define VMACACHE_BITS 2 +#define VMACACHE_SIZE (1U << VMACACHE_BITS) +#define VMACACHE_MASK (VMACACHE_SIZE - 1) + /* * Extended scheduling parameters data structure. * @@ -1228,6 +1232,9 @@ struct task_struct { #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; #endif + /* per-thread vma caching */ + u32 vmacache_seqnum; + struct vm_area_struct *vmacache[VMACACHE_SIZE]; #if defined(SPLIT_RSS_COUNTING) struct task_rss_stat rss_stat; #endif @@ -1869,11 +1876,13 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) -/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags */ +/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags + * __GFP_FS is also cleared as it implies __GFP_IO. + */ static inline gfp_t memalloc_noio_flags(gfp_t flags) { if (unlikely(current->flags & PF_MEMALLOC_NOIO)) - flags &= ~__GFP_IO; + flags &= ~(__GFP_IO | __GFP_FS); return flags; } diff --git a/include/linux/security.h b/include/linux/security.h index 2fc42d191f79..6478ce3252c7 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1793,7 +1793,8 @@ int security_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) int security_inode_rmdir(struct inode *dir, struct dentry *dentry); int security_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev); int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry); + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags); int security_inode_readlink(struct dentry *dentry); int security_inode_follow_link(struct dentry *dentry, struct nameidata *nd); int security_inode_permission(struct inode *inode, int mask); @@ -2161,7 +2162,8 @@ static inline int security_inode_mknod(struct inode *dir, static inline int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, - struct dentry *new_dentry) + struct dentry *new_dentry, + unsigned int flags) { return 0; } @@ -2955,7 +2957,8 @@ int security_path_symlink(struct path *dir, struct dentry *dentry, int security_path_link(struct dentry *old_dentry, struct path *new_dir, struct dentry *new_dentry); int security_path_rename(struct path *old_dir, struct dentry *old_dentry, - struct path *new_dir, struct dentry *new_dentry); + struct path *new_dir, struct dentry *new_dentry, + unsigned int flags); int security_path_chmod(struct path *path, umode_t mode); int security_path_chown(struct path *path, kuid_t uid, kgid_t gid); int security_path_chroot(struct path *path); @@ -3003,7 +3006,8 @@ static inline int security_path_link(struct dentry *old_dentry, static inline int security_path_rename(struct path *old_dir, struct dentry *old_dentry, struct path *new_dir, - struct dentry *new_dentry) + struct dentry *new_dentry, + unsigned int flags) { return 0; } diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 535f158977b9..8cf350325dc6 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -164,8 +164,6 @@ static inline unsigned read_seqcount_begin(const seqcount_t *s) static inline unsigned raw_seqcount_begin(const seqcount_t *s) { unsigned ret = ACCESS_ONCE(s->sequence); - - seqcount_lockdep_reader_access(s); smp_rmb(); return ret & ~1; } diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 9d55438bc4ad..4d1771c2d29f 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -51,6 +51,7 @@ extern struct file *shmem_kernel_file_setup(const char *name, loff_t size, unsigned long flags); extern int shmem_zero_setup(struct vm_area_struct *); extern int shmem_lock(struct file *file, int lock, struct user_struct *user); +extern bool shmem_mapping(struct address_space *mapping); extern void shmem_unlock_mapping(struct address_space *mapping); extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 15ede6a823a6..ad8f85908a56 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2458,6 +2458,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); void skb_scrub_packet(struct sk_buff *skb, bool xnet); unsigned int skb_gso_transport_seglen(const struct sk_buff *skb); struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); +struct sk_buff *skb_vlan_untag(struct sk_buff *skb); struct skb_checksum_ops { __wsum (*update)(const void *mem, int len, __wsum wsum); diff --git a/include/linux/string.h b/include/linux/string.h index ac889c5ea11b..0ed878d0465c 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -129,7 +129,7 @@ int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) __printf(3, 4); #endif extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, - const void *from, size_t available); + const void *from, size_t available); /** * strstarts - does @str start with @prefix? @@ -141,7 +141,8 @@ static inline bool strstarts(const char *str, const char *prefix) return strncmp(str, prefix, strlen(prefix)) == 0; } -extern size_t memweight(const void *ptr, size_t bytes); +size_t memweight(const void *ptr, size_t bytes); +void memzero_explicit(void *s, size_t count); /** * kbasename - return the last part of a pathname. diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 8097b9df6773..51009d280ac7 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -340,6 +340,7 @@ int xs_swapper(struct rpc_xprt *xprt, int enable); #define XPRT_CONNECTION_ABORT (7) #define XPRT_CONNECTION_CLOSE (8) #define XPRT_CONGESTED (9) +#define XPRT_CONNECTION_REUSE (10) static inline void xprt_set_connected(struct rpc_xprt *xprt) { diff --git a/include/linux/swap.h b/include/linux/swap.h index 46ba0c6c219f..241bf0922770 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -214,8 +214,9 @@ struct percpu_cluster { struct swap_info_struct { unsigned long flags; /* SWP_USED etc: see above */ signed short prio; /* swap priority of this type */ + struct plist_node list; /* entry in swap_active_head */ + struct plist_node avail_list; /* entry in swap_avail_head */ signed char type; /* strange name for an index */ - signed char next; /* next type on the swap list */ unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */ @@ -255,11 +256,6 @@ struct swap_info_struct { struct swap_cluster_info discard_cluster_tail; /* list tail of discard clusters */ }; -struct swap_list_t { - int head; /* head of priority-ordered swapfile list */ - int next; /* swapfile to be used next */ -}; - /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; extern unsigned long totalreserve_pages; @@ -272,12 +268,14 @@ extern unsigned long nr_free_pagecache_pages(void); /* linux/mm/swap.c */ -extern void __lru_cache_add(struct page *); extern void lru_cache_add(struct page *); +extern void lru_cache_add_anon(struct page *page); +extern void lru_cache_add_file(struct page *page); extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); extern void activate_page(struct page *); extern void mark_page_accessed(struct page *); +extern void init_page_accessed(struct page *page); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_all(void); @@ -287,22 +285,6 @@ extern void swap_setup(void); extern void add_page_to_unevictable_list(struct page *page); -/** - * lru_cache_add: add a page to the page lists - * @page: the page to add - */ -static inline void lru_cache_add_anon(struct page *page) -{ - ClearPageActive(page); - __lru_cache_add(page); -} - -static inline void lru_cache_add_file(struct page *page) -{ - ClearPageActive(page); - __lru_cache_add(page); -} - /* linux/mm/vmscan.c */ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); @@ -460,7 +442,7 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) #define free_page_and_swap_cache(page) \ page_cache_release(page) #define free_pages_and_swap_cache(pages, nr) \ - release_pages((pages), (nr), 0); + release_pages((pages), (nr), false); static inline void show_swap_cache_info(void) { diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h index e282624e8c10..388293a91e8c 100644 --- a/include/linux/swapfile.h +++ b/include/linux/swapfile.h @@ -6,7 +6,7 @@ * want to expose them to the dozens of source files that include swap.h */ extern spinlock_t swap_lock; -extern struct swap_list_t swap_list; +extern struct plist_head swap_active_head; extern struct swap_info_struct *swap_info[]; extern int try_to_unuse(unsigned int, bool, unsigned long); diff --git a/include/linux/time.h b/include/linux/time.h index d5d229b2e5af..7d532a32ff3a 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -173,6 +173,19 @@ extern void getboottime(struct timespec *ts); extern void monotonic_to_bootbased(struct timespec *ts); extern void get_monotonic_boottime(struct timespec *ts); +static inline bool timeval_valid(const struct timeval *tv) +{ + /* Dates before 1970 are bogus */ + if (tv->tv_sec < 0) + return false; + + /* Can't have more microseconds then a second */ + if (tv->tv_usec < 0 || tv->tv_usec >= USEC_PER_SEC) + return false; + + return true; +} + extern struct timespec timespec_trunc(struct timespec t, unsigned gran); extern int timekeeping_valid_for_hres(void); extern u64 timekeeping_max_deferment(void); diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index efe8d8a7c7ad..e34bce3781ee 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -447,6 +447,7 @@ extern const struct dev_pm_ops usb_hcd_pci_pm_ops; #endif /* CONFIG_PCI */ /* pci-ish (pdev null is ok) buffer alloc/mapping support */ +void usb_init_pool_max(void); int hcd_buffer_create(struct usb_hcd *hcd); void hcd_buffer_destroy(struct usb_hcd *hcd); diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 52f944dfe2fd..8b96ae2a38fe 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -30,4 +30,10 @@ descriptor */ #define USB_QUIRK_DELAY_INIT 0x00000040 +/* device generates spurious wakeup, ignore remote wakeup capability */ +#define USB_QUIRK_IGNORE_REMOTE_WAKEUP 0x00000200 + +/* device can't handle device_qualifier descriptor requests */ +#define USB_QUIRK_DEVICE_QUALIFIER 0x00000100 + #endif /* __LINUX_USB_QUIRKS_H */ diff --git a/include/linux/usb/xhci_pdriver.h b/include/linux/usb/xhci_pdriver.h new file mode 100644 index 000000000000..376654b5b0f7 --- /dev/null +++ b/include/linux/usb/xhci_pdriver.h @@ -0,0 +1,27 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY + * or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#ifndef __USB_CORE_XHCI_PDRIVER_H +#define __USB_CORE_XHCI_PDRIVER_H + +/** + * struct usb_xhci_pdata - platform_data for generic xhci platform driver + * + * @usb3_lpm_capable: determines if this xhci platform supports USB3 + * LPM capability + * + */ +struct usb_xhci_pdata { + unsigned usb3_lpm_capable:1; +}; + +#endif /* __USB_CORE_XHCI_PDRIVER_H */ diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 4836ba3c1cd8..e92abf9e796f 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -17,6 +17,10 @@ struct uid_gid_map { /* 64 bytes -- 1 cache line */ } extent[UID_GID_MAP_MAX_EXTENTS]; }; +#define USERNS_SETGROUPS_ALLOWED 1UL + +#define USERNS_INIT_FLAGS USERNS_SETGROUPS_ALLOWED + struct user_namespace { struct uid_gid_map uid_map; struct uid_gid_map gid_map; @@ -27,6 +31,7 @@ struct user_namespace { kuid_t owner; kgid_t group; unsigned int proc_inum; + unsigned long flags; /* Register of per-UID persistent keyrings for this namespace */ #ifdef CONFIG_PERSISTENT_KEYRINGS @@ -63,6 +68,9 @@ extern struct seq_operations proc_projid_seq_operations; extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, loff_t *); +extern ssize_t proc_setgroups_write(struct file *, const char __user *, size_t, loff_t *); +extern int proc_setgroups_show(struct seq_file *m, void *v); +extern bool userns_may_setgroups(const struct user_namespace *ns); #else static inline struct user_namespace *get_user_ns(struct user_namespace *ns) @@ -87,6 +95,10 @@ static inline void put_user_ns(struct user_namespace *ns) { } +static inline bool userns_may_setgroups(const struct user_namespace *ns) +{ + return true; +} #endif #endif /* _LINUX_USER_H */ diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h index 502073a53dd3..b483abd34493 100644 --- a/include/linux/vga_switcheroo.h +++ b/include/linux/vga_switcheroo.h @@ -64,6 +64,7 @@ int vga_switcheroo_get_client_state(struct pci_dev *dev); void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic); int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain *domain); +void vga_switcheroo_fini_domain_pm_ops(struct device *dev); int vga_switcheroo_init_domain_pm_optimus_hdmi_audio(struct device *dev, struct dev_pm_domain *domain); #else @@ -82,6 +83,7 @@ static inline int vga_switcheroo_get_client_state(struct pci_dev *dev) { return static inline void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic) {} static inline int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain *domain) { return -EINVAL; } +static inline void vga_switcheroo_fini_domain_pm_ops(struct device *dev) {} static inline int vga_switcheroo_init_domain_pm_optimus_hdmi_audio(struct device *dev, struct dev_pm_domain *domain) { return -EINVAL; } #endif diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h new file mode 100644 index 000000000000..c3fa0fd43949 --- /dev/null +++ b/include/linux/vmacache.h @@ -0,0 +1,38 @@ +#ifndef __LINUX_VMACACHE_H +#define __LINUX_VMACACHE_H + +#include <linux/sched.h> +#include <linux/mm.h> + +/* + * Hash based on the page number. Provides a good hit rate for + * workloads with good locality and those with random accesses as well. + */ +#define VMACACHE_HASH(addr) ((addr >> PAGE_SHIFT) & VMACACHE_MASK) + +static inline void vmacache_flush(struct task_struct *tsk) +{ + memset(tsk->vmacache, 0, sizeof(tsk->vmacache)); +} + +extern void vmacache_flush_all(struct mm_struct *mm); +extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma); +extern struct vm_area_struct *vmacache_find(struct mm_struct *mm, + unsigned long addr); + +#ifndef CONFIG_MMU +extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, + unsigned long start, + unsigned long end); +#endif + +static inline void vmacache_invalidate(struct mm_struct *mm) +{ + mm->vmacache_seqnum++; + + /* deal with overflows */ + if (unlikely(mm->vmacache_seqnum == 0)) + vmacache_flush_all(mm); +} + +#endif /* __LINUX_VMACACHE_H */ diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 704f4f652d0a..bc9d2c2ddf87 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -71,7 +71,8 @@ enum { /* data contains off-queue information when !WORK_STRUCT_PWQ */ WORK_OFFQ_FLAG_BASE = WORK_STRUCT_COLOR_SHIFT, - WORK_OFFQ_CANCELING = (1 << WORK_OFFQ_FLAG_BASE), + __WORK_OFFQ_CANCELING = WORK_OFFQ_FLAG_BASE, + WORK_OFFQ_CANCELING = (1 << __WORK_OFFQ_CANCELING), /* * When a work item is off queue, its high bits point to the last @@ -452,7 +453,7 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, alloc_workqueue("%s", WQ_FREEZABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, \ 1, (name)) #define create_singlethread_workqueue(name) \ - alloc_workqueue("%s", WQ_UNBOUND | WQ_MEM_RECLAIM, 1, (name)) + alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, name) extern void destroy_workqueue(struct workqueue_struct *wq); diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index bef53ce555d2..b10682cb138c 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -329,6 +329,9 @@ struct v4l2_fh; * @retry_start_streaming: start_streaming() was called, but there were not enough * buffers queued. If set, then retry calling start_streaming when * queuing a new buffer. + * @waiting_for_buffers: used in poll() to check if vb2 is still waiting for + * buffers. Only set for capture queues if qbuf has not yet been + * called since poll() needs to return POLLERR in that situation. * @fileio: file io emulator internal data, used only if emulator is active */ struct vb2_queue { @@ -362,6 +365,7 @@ struct vb2_queue { unsigned int streaming:1; unsigned int retry_start_streaming:1; + unsigned int waiting_for_buffers:1; struct vb2_fileio_data *fileio; }; diff --git a/include/net/dst.h b/include/net/dst.h index 77eb53fabfb0..909032821c37 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -466,6 +466,7 @@ void dst_init(void); /* Flags for xfrm_lookup flags argument. */ enum { XFRM_LOOKUP_ICMP = 1 << 0, + XFRM_LOOKUP_QUEUE = 1 << 1, }; struct flowi; @@ -476,7 +477,16 @@ static inline struct dst_entry *xfrm_lookup(struct net *net, int flags) { return dst_orig; -} +} + +static inline struct dst_entry *xfrm_lookup_route(struct net *net, + struct dst_entry *dst_orig, + const struct flowi *fl, + struct sock *sk, + int flags) +{ + return dst_orig; +} static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) { @@ -488,6 +498,10 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, struct sock *sk, int flags); +struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, + const struct flowi *fl, struct sock *sk, + int flags); + /* skb attached with this dst needs transformation if dst->xfrm is valid */ static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) { diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index c55aeed41ace..cf9272807788 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -62,6 +62,7 @@ struct inet_connection_sock_af_ops { void (*addr2sockaddr)(struct sock *sk, struct sockaddr *); int (*bind_conflict)(const struct sock *sk, const struct inet_bind_bucket *tb, bool relax); + void (*mtu_reduced)(struct sock *sk); }; /** inet_connection_sock - INET connection oriented sock diff --git a/include/net/ip.h b/include/net/ip.h index 937f19681426..3446cdd29608 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -38,11 +38,12 @@ struct inet_skb_parm { struct ip_options opt; /* Compiled IP options */ unsigned char flags; -#define IPSKB_FORWARDED 1 -#define IPSKB_XFRM_TUNNEL_SIZE 2 -#define IPSKB_XFRM_TRANSFORMED 4 -#define IPSKB_FRAG_COMPLETE 8 -#define IPSKB_REROUTED 16 +#define IPSKB_FORWARDED BIT(0) +#define IPSKB_XFRM_TUNNEL_SIZE BIT(1) +#define IPSKB_XFRM_TRANSFORMED BIT(2) +#define IPSKB_FRAG_COMPLETE BIT(3) +#define IPSKB_REROUTED BIT(4) +#define IPSKB_DOREDIRECT BIT(5) u16 frag_max_size; }; @@ -174,7 +175,7 @@ static inline __u8 ip_reply_arg_flowi_flags(const struct ip_reply_arg *arg) return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0; } -void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, +void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, unsigned int len); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 9ac65781d44b..a60948d7bcea 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -660,6 +660,8 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr)); } +void ipv6_proxy_select_ident(struct sk_buff *skb); + int ip6_dst_hoplimit(struct dst_entry *dst); /* diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 80f500a29498..57c2da922952 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -47,6 +47,7 @@ struct netns_ipv4 { struct inet_peer_base *peers; struct tcpm_hash_bucket *tcp_metrics_hash; unsigned int tcp_metrics_hash_log; + struct sock * __percpu *tcp_sk; struct netns_frags frags; #ifdef CONFIG_NETFILTER struct xt_table *iptable_filter; diff --git a/include/net/regulatory.h b/include/net/regulatory.h index b07cdc9fa454..f103f30122a1 100644 --- a/include/net/regulatory.h +++ b/include/net/regulatory.h @@ -160,7 +160,7 @@ struct ieee80211_reg_rule { struct ieee80211_regdomain { struct rcu_head rcu_head; u32 n_reg_rules; - char alpha2[2]; + char alpha2[3]; enum nl80211_dfs_regions dfs_region; struct ieee80211_reg_rule reg_rules[]; }; diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h index 4b7cd695e431..cfcbc3f627bd 100644 --- a/include/net/sctp/command.h +++ b/include/net/sctp/command.h @@ -115,7 +115,7 @@ typedef enum { * analysis of the state functions, but in reality just taken from * thin air in the hopes othat we don't trigger a kernel panic. */ -#define SCTP_MAX_NUM_COMMANDS 14 +#define SCTP_MAX_NUM_COMMANDS 20 typedef union { __s32 i32; diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index a3353f45ef94..ba41e01ebc54 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -433,6 +433,11 @@ static inline void sctp_assoc_pending_pmtu(struct sock *sk, struct sctp_associat asoc->pmtu_pending = 0; } +static inline bool sctp_chunk_pending(const struct sctp_chunk *chunk) +{ + return !list_empty(&chunk->list); +} + /* Walk through a list of TLV parameters. Don't trust the * individual parameter lengths and instead depend on * the chunk length to indicate when to stop. Make sure diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 7f4eeb340a54..72a31db47ded 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -248,9 +248,9 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *, int, __be16); struct sctp_chunk *sctp_make_asconf_set_prim(struct sctp_association *asoc, union sctp_addr *addr); -int sctp_verify_asconf(const struct sctp_association *asoc, - struct sctp_paramhdr *param_hdr, void *chunk_end, - struct sctp_paramhdr **errp); +bool sctp_verify_asconf(const struct sctp_association *asoc, + struct sctp_chunk *chunk, bool addr_param_needed, + struct sctp_paramhdr **errp); struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, struct sctp_chunk *asconf); int sctp_process_asconf_ack(struct sctp_association *asoc, diff --git a/include/net/sock.h b/include/net/sock.h index 2f7bc435c93d..f66b2b19a6e4 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -969,7 +969,6 @@ struct proto { struct sk_buff *skb); void (*release_cb)(struct sock *sk); - void (*mtu_reduced)(struct sock *sk); /* Keeping track of sk's, looking them up, and port selection methods. */ void (*hash)(struct sock *sk); diff --git a/include/net/tcp.h b/include/net/tcp.h index 743accec6c76..1f0d8479e15f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -453,6 +453,7 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th); */ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb); +void tcp_v4_mtu_reduced(struct sock *sk); int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb); struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, @@ -720,8 +721,10 @@ struct tcp_skb_cb { #define TCPCB_SACKED_RETRANS 0x02 /* SKB retransmitted */ #define TCPCB_LOST 0x04 /* SKB is lost */ #define TCPCB_TAGBITS 0x07 /* All tag bits */ +#define TCPCB_REPAIRED 0x10 /* SKB repaired (no skb_mstamp) */ #define TCPCB_EVER_RETRANS 0x80 /* Ever retransmitted frame */ -#define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS) +#define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \ + TCPCB_REPAIRED) __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */ /* 1 byte hole */ diff --git a/include/sound/ak4113.h b/include/sound/ak4113.h index 2609048c1d44..3a34f6edc2d1 100644 --- a/include/sound/ak4113.h +++ b/include/sound/ak4113.h @@ -286,7 +286,7 @@ struct ak4113 { ak4113_write_t *write; ak4113_read_t *read; void *private_data; - unsigned int init:1; + atomic_t wq_processing; spinlock_t lock; unsigned char regmap[AK4113_WRITABLE_REGS]; struct snd_kcontrol *kctls[AK4113_CONTROLS]; diff --git a/include/sound/ak4114.h b/include/sound/ak4114.h index 52f02a60dba7..069299a88915 100644 --- a/include/sound/ak4114.h +++ b/include/sound/ak4114.h @@ -168,7 +168,7 @@ struct ak4114 { ak4114_write_t * write; ak4114_read_t * read; void * private_data; - unsigned int init: 1; + atomic_t wq_processing; spinlock_t lock; unsigned char regmap[6]; unsigned char txcsb[5]; diff --git a/include/sound/soc-dpcm.h b/include/sound/soc-dpcm.h index 2883a7a6f9f3..98f2ade0266e 100644 --- a/include/sound/soc-dpcm.h +++ b/include/sound/soc-dpcm.h @@ -102,6 +102,8 @@ struct snd_soc_dpcm_runtime { /* state and update */ enum snd_soc_dpcm_update runtime_update; enum snd_soc_dpcm_state state; + + int trigger_pending; /* trigger cmd + 1 if pending, 0 if not */ }; /* can this BE stop and free */ diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 1772fadcff62..349325404add 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -407,7 +407,7 @@ struct t10_reservation { /* Activate Persistence across Target Power Loss enabled * for SCSI device */ int pr_aptpl_active; -#define PR_APTPL_BUF_LEN 8192 +#define PR_APTPL_BUF_LEN 262144 u32 pr_generation; spinlock_t registration_lock; spinlock_t aptpl_reg_lock; diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h index 06f544ef2f6f..c6814b917bdf 100644 --- a/include/trace/events/compaction.h +++ b/include/trace/events/compaction.h @@ -5,6 +5,7 @@ #define _TRACE_COMPACTION_H #include <linux/types.h> +#include <linux/list.h> #include <linux/tracepoint.h> #include <trace/events/gfpflags.h> @@ -47,10 +48,11 @@ DEFINE_EVENT(mm_compaction_isolate_template, mm_compaction_isolate_freepages, TRACE_EVENT(mm_compaction_migratepages, - TP_PROTO(unsigned long nr_migrated, - unsigned long nr_failed), + TP_PROTO(unsigned long nr_all, + int migrate_rc, + struct list_head *migratepages), - TP_ARGS(nr_migrated, nr_failed), + TP_ARGS(nr_all, migrate_rc, migratepages), TP_STRUCT__entry( __field(unsigned long, nr_migrated) @@ -58,7 +60,22 @@ TRACE_EVENT(mm_compaction_migratepages, ), TP_fast_assign( - __entry->nr_migrated = nr_migrated; + unsigned long nr_failed = 0; + struct list_head *page_lru; + + /* + * migrate_pages() returns either a non-negative number + * with the number of pages that failed migration, or an + * error code, in which case we need to count the remaining + * pages manually + */ + if (migrate_rc >= 0) + nr_failed = migrate_rc; + else + list_for_each(page_lru, migratepages) + nr_failed++; + + __entry->nr_migrated = nr_all - nr_failed; __entry->nr_failed = nr_failed; ), diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index aece1346ceb7..4ad10baecd4d 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -268,11 +268,11 @@ TRACE_EVENT(mm_page_alloc_extfrag, TP_PROTO(struct page *page, int alloc_order, int fallback_order, - int alloc_migratetype, int fallback_migratetype, int new_migratetype), + int alloc_migratetype, int fallback_migratetype), TP_ARGS(page, alloc_order, fallback_order, - alloc_migratetype, fallback_migratetype, new_migratetype), + alloc_migratetype, fallback_migratetype), TP_STRUCT__entry( __field( struct page *, page ) @@ -289,7 +289,8 @@ TRACE_EVENT(mm_page_alloc_extfrag, __entry->fallback_order = fallback_order; __entry->alloc_migratetype = alloc_migratetype; __entry->fallback_migratetype = fallback_migratetype; - __entry->change_ownership = (new_migratetype == alloc_migratetype); + __entry->change_ownership = (alloc_migratetype == + get_pageblock_migratetype(page)); ), TP_printk("page=%p pfn=%lu alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d", diff --git a/include/trace/events/pagemap.h b/include/trace/events/pagemap.h index 1c9fabde69e4..ce0803b8d05f 100644 --- a/include/trace/events/pagemap.h +++ b/include/trace/events/pagemap.h @@ -28,12 +28,10 @@ TRACE_EVENT(mm_lru_insertion, TP_PROTO( struct page *page, - unsigned long pfn, - int lru, - unsigned long flags + int lru ), - TP_ARGS(page, pfn, lru, flags), + TP_ARGS(page, lru), TP_STRUCT__entry( __field(struct page *, page ) @@ -44,9 +42,9 @@ TRACE_EVENT(mm_lru_insertion, TP_fast_assign( __entry->page = page; - __entry->pfn = pfn; + __entry->pfn = page_to_pfn(page); __entry->lru = lru; - __entry->flags = flags; + __entry->flags = trace_pagemap_flags(page); ), /* Flag format is based on page-types.c formatting for pagemap */ @@ -64,9 +62,9 @@ TRACE_EVENT(mm_lru_insertion, TRACE_EVENT(mm_lru_activate, - TP_PROTO(struct page *page, unsigned long pfn), + TP_PROTO(struct page *page), - TP_ARGS(page, pfn), + TP_ARGS(page), TP_STRUCT__entry( __field(struct page *, page ) @@ -75,7 +73,7 @@ TRACE_EVENT(mm_lru_activate, TP_fast_assign( __entry->page = page; - __entry->pfn = pfn; + __entry->pfn = page_to_pfn(page); ), /* Flag format is based on page-types.c formatting for pagemap */ diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 67e1bbf83695..dc7bb01f580f 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -100,7 +100,7 @@ static inline long __trace_sched_switch_state(struct task_struct *p) /* * For all intents and purposes a preempted task is a running task. */ - if (task_preempt_count(p) & PREEMPT_ACTIVE) + if (preempt_count() & PREEMPT_ACTIVE) state = TASK_RUNNING | TASK_STATE_MAX; #endif diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h index 87792a5fee3b..33b739522840 100644 --- a/include/uapi/drm/vmwgfx_drm.h +++ b/include/uapi/drm/vmwgfx_drm.h @@ -29,7 +29,7 @@ #define __VMWGFX_DRM_H__ #ifndef __KERNEL__ -#include <drm.h> +#include <drm/drm.h> #endif #define DRM_VMW_MAX_SURFACE_FACES 6 diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 6c28b61bb690..3735fa0a6784 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -35,6 +35,10 @@ #define SEEK_HOLE 4 /* seek to the next hole */ #define SEEK_MAX SEEK_HOLE +#define RENAME_NOREPLACE (1 << 0) /* Don't overwrite target */ +#define RENAME_EXCHANGE (1 << 1) /* Exchange source and dest */ +#define RENAME_WHITEOUT (1 << 2) /* Whiteout source */ + struct fstrim_range { __u64 start; __u64 len; diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 60bb2f9f7b74..b77cf381a44b 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -93,6 +93,9 @@ * * 7.22 * - add FUSE_ASYNC_DIO + * + * 7.23 + * - add FUSE_RENAME2 request */ #ifndef _LINUX_FUSE_H @@ -343,6 +346,7 @@ enum fuse_opcode { FUSE_BATCH_FORGET = 42, FUSE_FALLOCATE = 43, FUSE_READDIRPLUS = 44, + FUSE_RENAME2 = 45, /* CUSE specific operations */ CUSE_INIT = 4096, @@ -421,6 +425,12 @@ struct fuse_rename_in { uint64_t newdir; }; +struct fuse_rename2_in { + uint64_t newdir; + uint32_t flags; + uint32_t padding; +}; + struct fuse_link_in { uint64_t oldnodeid; }; diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h index e9a1d2d973b6..4c399ae04677 100644 --- a/include/uapi/linux/in6.h +++ b/include/uapi/linux/in6.h @@ -149,7 +149,7 @@ struct in6_flowlabel_req { /* * IPV6 socket options */ - +#if __UAPI_DEF_IPV6_OPTIONS #define IPV6_ADDRFORM 1 #define IPV6_2292PKTINFO 2 #define IPV6_2292HOPOPTS 3 @@ -192,6 +192,7 @@ struct in6_flowlabel_req { #define IPV6_IPSEC_POLICY 34 #define IPV6_XFRM_POLICY 35 +#endif /* * Multicast: diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h index c140620dad92..e28807ad17fa 100644 --- a/include/uapi/linux/libc-compat.h +++ b/include/uapi/linux/libc-compat.h @@ -69,6 +69,7 @@ #define __UAPI_DEF_SOCKADDR_IN6 0 #define __UAPI_DEF_IPV6_MREQ 0 #define __UAPI_DEF_IPPROTO_V6 0 +#define __UAPI_DEF_IPV6_OPTIONS 0 #else @@ -82,6 +83,7 @@ #define __UAPI_DEF_SOCKADDR_IN6 1 #define __UAPI_DEF_IPV6_MREQ 1 #define __UAPI_DEF_IPPROTO_V6 1 +#define __UAPI_DEF_IPV6_OPTIONS 1 #endif /* _NETINET_IN_H */ @@ -103,6 +105,7 @@ #define __UAPI_DEF_SOCKADDR_IN6 1 #define __UAPI_DEF_IPV6_MREQ 1 #define __UAPI_DEF_IPPROTO_V6 1 +#define __UAPI_DEF_IPV6_OPTIONS 1 /* Definitions for xattr.h */ #define __UAPI_DEF_XATTR 1 diff --git a/include/uapi/linux/netfilter/xt_bpf.h b/include/uapi/linux/netfilter/xt_bpf.h index 5dda450eb55b..2ec9fbcd06f9 100644 --- a/include/uapi/linux/netfilter/xt_bpf.h +++ b/include/uapi/linux/netfilter/xt_bpf.h @@ -6,6 +6,8 @@ #define XT_BPF_MAX_NUM_INSTR 64 +struct sk_filter; + struct xt_bpf_info { __u16 bpf_program_num_elem; struct sock_filter bpf_program[XT_BPF_MAX_NUM_INSTR]; diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h index 29e9c7aa9c66..f279394aafb0 100644 --- a/include/uapi/linux/usb/functionfs.h +++ b/include/uapi/linux/usb/functionfs.h @@ -27,24 +27,18 @@ struct usb_endpoint_descriptor_no_audio { __u8 bInterval; } __attribute__((packed)); -/* Legacy format, deprecated as of 3.14. */ -struct usb_functionfs_descs_head { - __le32 magic; - __le32 length; - __le32 fs_count; - __le32 hs_count; -} __attribute__((packed, deprecated)); /* * All numbers must be in little endian order. */ +/* Legacy format, deprecated as of 3.14. */ struct usb_functionfs_descs_head { __le32 magic; __le32 length; __le32 fs_count; __le32 hs_count; -} __attribute__((packed)); +} __attribute__((packed, deprecated)); /* * Descriptors format: diff --git a/include/uapi/linux/xattr.h b/include/uapi/linux/xattr.h index c38355c1f3c9..1590c49cae57 100644 --- a/include/uapi/linux/xattr.h +++ b/include/uapi/linux/xattr.h @@ -13,7 +13,7 @@ #ifndef _UAPI_LINUX_XATTR_H #define _UAPI_LINUX_XATTR_H -#ifdef __UAPI_DEF_XATTR +#if __UAPI_DEF_XATTR #define __USE_KERNEL_XATTR_DEFS #define XATTR_CREATE 0x1 /* set value, fail if attr already exists */ diff --git a/init/Kconfig b/init/Kconfig index 93c5ef0c5210..8b9521a2d2c1 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1389,6 +1389,7 @@ config FUTEX config HAVE_FUTEX_CMPXCHG bool + depends on FUTEX help Architectures should select this if futex_atomic_cmpxchg_inatomic() is implemented and always working. This removes a couple of runtime diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c index 17028648cfeb..cadddc8388f3 100644 --- a/ipc/ipc_sysctl.c +++ b/ipc/ipc_sysctl.c @@ -123,7 +123,6 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table ipc_table; - size_t lenp_bef = *lenp; int oldval; int rc; @@ -133,7 +132,7 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write, rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos); - if (write && !rc && lenp_bef == *lenp) { + if (write && !rc) { int newval = *((int *)(ipc_table.data)); /* * The file "auto_msgmni" has correctly been set. diff --git a/kernel/audit.c b/kernel/audit.c index 2c0ecd1753de..b45b2daa9f92 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -687,7 +687,7 @@ static int audit_get_feature(struct sk_buff *skb) seq = nlmsg_hdr(skb)->nlmsg_seq; - audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &af, sizeof(af)); + audit_send_reply(skb, seq, AUDIT_GET_FEATURE, 0, 0, &af, sizeof(af)); return 0; } @@ -702,7 +702,7 @@ static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_FEATURE_CHANGE); audit_log_task_info(ab, current); - audit_log_format(ab, "feature=%s old=%u new=%u old_lock=%u new_lock=%u res=%d", + audit_log_format(ab, " feature=%s old=%u new=%u old_lock=%u new_lock=%u res=%d", audit_feature_names[which], !!old_feature, !!new_feature, !!old_lock, !!new_lock, res); audit_log_end(ab); diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 135944a7b28a..a79db03990db 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -154,6 +154,7 @@ static struct audit_chunk *alloc_chunk(int count) chunk->owners[i].index = i; } fsnotify_init_mark(&chunk->mark, audit_tree_destroy_watch); + chunk->mark.mask = FS_IN_IGNORED; return chunk; } diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 92062fd6cc8c..598c1dcf26dd 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -429,6 +429,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, if ((f->type == AUDIT_LOGINUID) && (f->val == AUDIT_UID_UNSET)) { f->type = AUDIT_LOGINUID_SET; f->val = 0; + entry->rule.pflags |= AUDIT_LOGINUID_LEGACY; } err = audit_field_valid(entry, f); @@ -604,6 +605,13 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule) data->buflen += data->values[i] = audit_pack_string(&bufp, krule->filterkey); break; + case AUDIT_LOGINUID_SET: + if (krule->pflags & AUDIT_LOGINUID_LEGACY && !f->val) { + data->fields[i] = AUDIT_LOGINUID; + data->values[i] = AUDIT_UID_UNSET; + break; + } + /* fallthrough if set */ default: data->values[i] = f->val; } @@ -620,6 +628,7 @@ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b) int i; if (a->flags != b->flags || + a->pflags != b->pflags || a->listnr != b->listnr || a->action != b->action || a->field_count != b->field_count) @@ -738,6 +747,7 @@ struct audit_entry *audit_dupe_rule(struct audit_krule *old) new = &entry->rule; new->vers_ops = old->vers_ops; new->flags = old->flags; + new->pflags = old->pflags; new->listnr = old->listnr; new->action = old->action; for (i = 0; i < AUDIT_BITMASK_SIZE; i++) diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 0c753ddd223b..550e2050d778 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3663,7 +3663,6 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, l = cgroup_pidlist_find_create(cgrp, type); if (!l) { - mutex_unlock(&cgrp->pidlist_mutex); pidlist_free(array); return -ENOMEM; } diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 6b27e5c0cd86..7b4530b0b16b 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -61,12 +61,7 @@ #include <linux/cgroup.h> #include <linux/wait.h> -/* - * Tracks how many cpusets are currently defined in system. - * When there is only one cpuset (the root cpuset) we can - * short circuit some hooks. - */ -int number_of_cpusets __read_mostly; +struct static_key cpusets_enabled_key __read_mostly = STATIC_KEY_INIT_FALSE; /* See "Frequency meter" comments, below. */ @@ -508,9 +503,6 @@ static void update_domain_attr_tree(struct sched_domain_attr *dattr, rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, root_cs) { - if (cp == root_cs) - continue; - /* skip the whole subtree if @cp doesn't have any CPU */ if (cpumask_empty(cp->cpus_allowed)) { pos_css = css_rightmost_descendant(pos_css); @@ -611,7 +603,7 @@ static int generate_sched_domains(cpumask_var_t **domains, goto done; } - csa = kmalloc(number_of_cpusets * sizeof(cp), GFP_KERNEL); + csa = kmalloc(nr_cpusets() * sizeof(cp), GFP_KERNEL); if (!csa) goto done; csn = 0; @@ -1022,7 +1014,7 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk, task_lock(tsk); /* * Determine if a loop is necessary if another thread is doing - * get_mems_allowed(). If at least one node remains unchanged and + * read_mems_allowed_begin(). If at least one node remains unchanged and * tsk does not have a mempolicy, then an empty nodemask will not be * possible when mems_allowed is larger than a word. */ @@ -1961,7 +1953,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) if (is_spread_slab(parent)) set_bit(CS_SPREAD_SLAB, &cs->flags); - number_of_cpusets++; + cpuset_inc(); if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags)) goto out_unlock; @@ -2012,7 +2004,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css) if (is_sched_load_balance(cs)) update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); - number_of_cpusets--; + cpuset_dec(); clear_bit(CS_ONLINE, &cs->flags); mutex_unlock(&cpuset_mutex); @@ -2067,7 +2059,6 @@ int __init cpuset_init(void) if (!alloc_cpumask_var(&cpus_attach, GFP_KERNEL)) BUG(); - number_of_cpusets = 1; return 0; } diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 334b3980ffc1..8865caec45fb 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -49,6 +49,7 @@ #include <linux/pid.h> #include <linux/smp.h> #include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/rcupdate.h> #include <asm/cacheflush.h> @@ -224,10 +225,17 @@ static void kgdb_flush_swbreak_addr(unsigned long addr) if (!CACHE_FLUSH_IS_SAFE) return; - if (current->mm && current->mm->mmap_cache) { - flush_cache_range(current->mm->mmap_cache, - addr, addr + BREAK_INSTR_SIZE); + if (current->mm) { + int i; + + for (i = 0; i < VMACACHE_SIZE; i++) { + if (!current->vmacache[i]) + continue; + flush_cache_range(current->vmacache[i], + addr, addr + BREAK_INSTR_SIZE); + } } + /* Force flush instruction cache if it was outside the mm */ flush_icache_range(addr, addr + BREAK_INSTR_SIZE); } diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 0b097c8a1e50..449518eb85ce 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2535,7 +2535,7 @@ static int kdb_summary(int argc, const char **argv) #define K(x) ((x) << (PAGE_SHIFT - 10)) kdb_printf("\nMemTotal: %8lu kB\nMemFree: %8lu kB\n" "Buffers: %8lu kB\n", - val.totalram, val.freeram, val.bufferram); + K(val.totalram), K(val.freeram), K(val.bufferram)); return 0; } diff --git a/kernel/events/core.c b/kernel/events/core.c index f774e9365a03..60146febb9b3 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -39,6 +39,7 @@ #include <linux/hw_breakpoint.h> #include <linux/mm_types.h> #include <linux/cgroup.h> +#include <linux/compat.h> #include "internal.h" @@ -1516,6 +1517,11 @@ retry: */ if (ctx->is_active) { raw_spin_unlock_irq(&ctx->lock); + /* + * Reload the task pointer, it might have been changed by + * a concurrent perf_event_context_sched_out(). + */ + task = ctx->task; goto retry; } @@ -1957,6 +1963,11 @@ retry: */ if (ctx->is_active) { raw_spin_unlock_irq(&ctx->lock); + /* + * Reload the task pointer, it might have been changed by + * a concurrent perf_event_context_sched_out(). + */ + task = ctx->task; goto retry; } @@ -3683,6 +3694,26 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return 0; } +#ifdef CONFIG_COMPAT +static long perf_compat_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + switch (_IOC_NR(cmd)) { + case _IOC_NR(PERF_EVENT_IOC_SET_FILTER): + case _IOC_NR(PERF_EVENT_IOC_ID): + /* Fix up pointer size (usually 4 -> 8 in 32-on-64-bit case */ + if (_IOC_SIZE(cmd) == sizeof(compat_uptr_t)) { + cmd &= ~IOCSIZE_MASK; + cmd |= sizeof(void *) << IOCSIZE_SHIFT; + } + break; + } + return perf_ioctl(file, cmd, arg); +} +#else +# define perf_compat_ioctl NULL +#endif + int perf_event_task_enable(void) { struct perf_event *event; @@ -4175,7 +4206,7 @@ static const struct file_operations perf_fops = { .read = perf_read, .poll = perf_poll, .unlocked_ioctl = perf_ioctl, - .compat_ioctl = perf_ioctl, + .compat_ioctl = perf_compat_ioctl, .mmap = perf_mmap, .fasync = perf_fasync, }; @@ -4201,6 +4232,13 @@ static void perf_pending_event(struct irq_work *entry) { struct perf_event *event = container_of(entry, struct perf_event, pending); + int rctx; + + rctx = perf_swevent_get_recursion_context(); + /* + * If we 'fail' here, that's OK, it means recursion is already disabled + * and we won't recurse 'further'. + */ if (event->pending_disable) { event->pending_disable = 0; @@ -4211,6 +4249,9 @@ static void perf_pending_event(struct irq_work *entry) event->pending_wakeup = 0; perf_event_wakeup(event); } + + if (rctx >= 0) + perf_swevent_put_recursion_context(rctx); } /* @@ -7209,11 +7250,11 @@ SYSCALL_DEFINE5(perf_event_open, if (move_group) { synchronize_rcu(); - perf_install_in_context(ctx, group_leader, event->cpu); + perf_install_in_context(ctx, group_leader, group_leader->cpu); get_ctx(ctx); list_for_each_entry(sibling, &group_leader->sibling_list, group_entry) { - perf_install_in_context(ctx, sibling, event->cpu); + perf_install_in_context(ctx, sibling, sibling->cpu); get_ctx(ctx); } } @@ -7826,8 +7867,10 @@ int perf_event_init_task(struct task_struct *child) for_each_task_context_nr(ctxn) { ret = perf_event_init_context(child, ctxn); - if (ret) + if (ret) { + perf_event_free_task(child); return ret; + } } return 0; diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 307d87c0991a..1139b228befc 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1621,7 +1621,6 @@ bool uprobe_deny_signal(void) if (__fatal_signal_pending(t) || arch_uprobe_xol_was_trapped(t)) { utask->state = UTASK_SSTEP_TRAPPED; set_tsk_thread_flag(t, TIF_UPROBE); - set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); } } diff --git a/kernel/fork.c b/kernel/fork.c index c44bff8097f5..e2c685396295 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -28,6 +28,8 @@ #include <linux/mman.h> #include <linux/mmu_notifier.h> #include <linux/fs.h> +#include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/nsproxy.h> #include <linux/capability.h> #include <linux/cpu.h> @@ -363,7 +365,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) mm->locked_vm = 0; mm->mmap = NULL; - mm->mmap_cache = NULL; + mm->vmacache_seqnum = 0; mm->map_count = 0; cpumask_clear(mm_cpumask(mm)); mm->mm_rb = RB_ROOT; @@ -876,6 +878,9 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) if (!oldmm) return 0; + /* initialize the new vmacache entries */ + vmacache_flush(tsk); + if (clone_flags & CLONE_VM) { atomic_inc(&oldmm->mm_users); mm = oldmm; @@ -1323,7 +1328,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, goto bad_fork_cleanup_policy; retval = audit_alloc(p); if (retval) - goto bad_fork_cleanup_policy; + goto bad_fork_cleanup_perf; /* copy all the process information */ retval = copy_semundo(clone_flags, p); if (retval) @@ -1522,8 +1527,9 @@ bad_fork_cleanup_semundo: exit_sem(p); bad_fork_cleanup_audit: audit_free(p); -bad_fork_cleanup_policy: +bad_fork_cleanup_perf: perf_event_free_task(p); +bad_fork_cleanup_policy: #ifdef CONFIG_NUMA mpol_put(p->mempolicy); bad_fork_cleanup_cgroup: diff --git a/kernel/freezer.c b/kernel/freezer.c index aa6a8aadb911..8f9279b9c6d7 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -42,6 +42,9 @@ bool freezing_slow_path(struct task_struct *p) if (p->flags & (PF_NOFREEZE | PF_SUSPEND_TASK)) return false; + if (test_thread_flag(TIF_MEMDIE)) + return false; + if (pm_nosig_freezing || cgroup_freezing(p)) return true; diff --git a/kernel/futex.c b/kernel/futex.c index e3087afb7429..fda2950f2ce4 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -329,6 +329,8 @@ static void get_futex_key_refs(union futex_key *key) case FUT_OFF_MMSHARED: futex_get_mm(key); /* implies MB (B) */ break; + default: + smp_mb(); /* explicit MB (B) */ } } @@ -2614,6 +2616,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, * shared futexes. We need to compare the keys: */ if (match_futex(&q.key, &key2)) { + queue_unlock(hb); ret = -EINVAL; goto out_put_keys; } diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig index d04ce8ac4399..c92e44855ddd 100644 --- a/kernel/gcov/Kconfig +++ b/kernel/gcov/Kconfig @@ -32,10 +32,13 @@ config GCOV_KERNEL Note that the debugfs filesystem has to be mounted to access profiling data. +config ARCH_HAS_GCOV_PROFILE_ALL + def_bool n + config GCOV_PROFILE_ALL bool "Profile entire Kernel" depends on GCOV_KERNEL - depends on SUPERH || S390 || X86 || PPC || MICROBLAZE + depends on ARCH_HAS_GCOV_PROFILE_ALL default n ---help--- This options activates profiling for the entire kernel. diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c index f45b75b713c0..b358a802fd18 100644 --- a/kernel/gcov/base.c +++ b/kernel/gcov/base.c @@ -85,6 +85,12 @@ void __gcov_merge_ior(gcov_type *counters, unsigned int n_counters) } EXPORT_SYMBOL(__gcov_merge_ior); +void __gcov_merge_time_profile(gcov_type *counters, unsigned int n_counters) +{ + /* Unused. */ +} +EXPORT_SYMBOL(__gcov_merge_time_profile); + /** * 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 2c6e4631c814..826ba9fb5e32 100644 --- a/kernel/gcov/gcc_4_7.c +++ b/kernel/gcov/gcc_4_7.c @@ -18,7 +18,12 @@ #include <linux/vmalloc.h> #include "gcov.h" +#if __GNUC__ == 4 && __GNUC_MINOR__ >= 9 +#define GCOV_COUNTERS 9 +#else #define GCOV_COUNTERS 8 +#endif + #define GCOV_TAG_FUNCTION_LENGTH 3 static struct gcov_info *gcov_info_head; diff --git a/kernel/groups.c b/kernel/groups.c index 90cf1c38c8ea..67b4ba30475f 100644 --- a/kernel/groups.c +++ b/kernel/groups.c @@ -6,6 +6,7 @@ #include <linux/slab.h> #include <linux/security.h> #include <linux/syscalls.h> +#include <linux/user_namespace.h> #include <asm/uaccess.h> /* init to 2 - one for init_task, one to ensure it is never freed */ @@ -223,6 +224,14 @@ out: return i; } +bool may_setgroups(void) +{ + struct user_namespace *user_ns = current_user_ns(); + + return ns_capable(user_ns, CAP_SETGID) && + userns_may_setgroups(user_ns); +} + /* * SMP: Our groups are copy-on-write. We can set them safely * without another task interfering. @@ -233,7 +242,7 @@ SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist) struct group_info *group_info; int retval; - if (!ns_capable(current_user_ns(), CAP_SETGID)) + if (!may_setgroups()) return -EPERM; if ((unsigned)gidsetsize > NGROUPS_MAX) return -EINVAL; diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 001fa5bab490..8a160e8a44e8 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -74,6 +74,14 @@ extern void irq_percpu_disable(struct irq_desc *desc, unsigned int cpu); extern void mask_irq(struct irq_desc *desc); extern void unmask_irq(struct irq_desc *desc); +#ifdef CONFIG_SPARSE_IRQ +extern void irq_lock_sparse(void); +extern void irq_unlock_sparse(void); +#else +static inline void irq_lock_sparse(void) { } +static inline void irq_unlock_sparse(void) { } +#endif + extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr); irqreturn_t handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action); diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 8ab8e9390297..07d45516b540 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -131,6 +131,16 @@ static void free_masks(struct irq_desc *desc) static inline void free_masks(struct irq_desc *desc) { } #endif +void irq_lock_sparse(void) +{ + mutex_lock(&sparse_irq_lock); +} + +void irq_unlock_sparse(void) +{ + mutex_unlock(&sparse_irq_lock); +} + static struct irq_desc *alloc_desc(int irq, int node, struct module *owner) { struct irq_desc *desc; @@ -167,6 +177,12 @@ static void free_desc(unsigned int irq) unregister_irq_proc(irq, desc); + /* + * sparse_irq_lock protects also show_interrupts() and + * kstat_irq_usr(). Once we deleted the descriptor from the + * sparse tree we can free it. Access in proc will fail to + * lookup the descriptor. + */ mutex_lock(&sparse_irq_lock); delete_irq_desc(irq); mutex_unlock(&sparse_irq_lock); @@ -489,6 +505,15 @@ void dynamic_irq_cleanup(unsigned int irq) raw_spin_unlock_irqrestore(&desc->lock, flags); } +/** + * kstat_irqs_cpu - Get the statistics for an interrupt on a cpu + * @irq: The interrupt number + * @cpu: The cpu number + * + * Returns the sum of interrupt counts on @cpu since boot for + * @irq. The caller must ensure that the interrupt is not removed + * concurrently. + */ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) { struct irq_desc *desc = irq_to_desc(irq); @@ -497,6 +522,14 @@ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) *per_cpu_ptr(desc->kstat_irqs, cpu) : 0; } +/** + * kstat_irqs - Get the statistics for an interrupt + * @irq: The interrupt number + * + * Returns the sum of interrupt counts on all cpus since boot for + * @irq. The caller must ensure that the interrupt is not removed + * concurrently. + */ unsigned int kstat_irqs(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); @@ -509,3 +542,22 @@ unsigned int kstat_irqs(unsigned int irq) sum += *per_cpu_ptr(desc->kstat_irqs, cpu); return sum; } + +/** + * kstat_irqs_usr - Get the statistics for an interrupt + * @irq: The interrupt number + * + * Returns the sum of interrupt counts on all cpus since boot for + * @irq. Contrary to kstat_irqs() this can be called from any + * preemptible context. It's protected against concurrent removal of + * an interrupt descriptor when sparse irqs are enabled. + */ +unsigned int kstat_irqs_usr(unsigned int irq) +{ + int sum; + + irq_lock_sparse(); + sum = kstat_irqs(irq); + irq_unlock_sparse(); + return sum; +} diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 36f6ee181b0c..095cd7230aef 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -15,6 +15,23 @@ #include "internals.h" +/* + * Access rules: + * + * procfs protects read/write of /proc/irq/N/ files against a + * concurrent free of the interrupt descriptor. remove_proc_entry() + * immediately prevents new read/writes to happen and waits for + * already running read/write functions to complete. + * + * We remove the proc entries first and then delete the interrupt + * descriptor from the radix tree and free it. So it is guaranteed + * that irq_to_desc(N) is valid as long as the read/writes are + * permitted by procfs. + * + * The read from /proc/interrupts is a different problem because there + * is no protection. So the lookup and the access to irqdesc + * information must be protected by sparse_irq_lock. + */ static struct proc_dir_entry *root_irq_dir; #ifdef CONFIG_SMP @@ -437,9 +454,10 @@ int show_interrupts(struct seq_file *p, void *v) seq_putc(p, '\n'); } + irq_lock_sparse(); desc = irq_to_desc(i); if (!desc) - return 0; + goto outsparse; raw_spin_lock_irqsave(&desc->lock, flags); for_each_online_cpu(j) @@ -479,6 +497,8 @@ int show_interrupts(struct seq_file *p, void *v) seq_putc(p, '\n'); out: raw_spin_unlock_irqrestore(&desc->lock, flags); +outsparse: + irq_unlock_sparse(); return 0; } #endif diff --git a/kernel/kcmp.c b/kernel/kcmp.c index e30ac0fe61c3..0aa69ea1d8fd 100644 --- a/kernel/kcmp.c +++ b/kernel/kcmp.c @@ -44,11 +44,12 @@ static long kptr_obfuscate(long v, int type) */ static int kcmp_ptr(void *v1, void *v2, enum kcmp_type type) { - long ret; + long t1, t2; - ret = kptr_obfuscate((long)v1, type) - kptr_obfuscate((long)v2, type); + t1 = kptr_obfuscate((long)v1, type); + t2 = kptr_obfuscate((long)v2, type); - return (ret < 0) | ((ret > 0) << 1); + return (t1 < t2) | ((t1 > t2) << 1); } /* The caller must have pinned the task */ diff --git a/kernel/module.c b/kernel/module.c index 6716a1fa618b..1d679a6c942f 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1841,7 +1841,9 @@ static void free_module(struct module *mod) /* We leave it in list to prevent duplicate loads, but make sure * that noone uses it while it's being deconstructed. */ + mutex_lock(&module_mutex); mod->state = MODULE_STATE_UNFORMED; + mutex_unlock(&module_mutex); /* Remove dynamic debug info */ ddebug_remove_module(mod->name); diff --git a/kernel/pid.c b/kernel/pid.c index 9b9a26698144..82430c858d69 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -341,6 +341,8 @@ out: out_unlock: spin_unlock_irq(&pidmap_lock); + put_pid_ns(ns); + out_free: while (++i <= ns->level) free_pidmap(pid->numbers + i); diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 424c2d4265c9..77e6b83c0431 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -634,6 +634,7 @@ SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock, goto out; } } else { + memset(&event.sigev_value, 0, sizeof(event.sigev_value)); event.sigev_notify = SIGEV_SIGNAL; event.sigev_signo = SIGALRM; event.sigev_value.sival_int = new_timer->it_id; diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 2fac9cc79b3d..45aa98ee5a70 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -306,6 +306,10 @@ config PM_GENERIC_DOMAINS_RUNTIME def_bool y depends on PM_RUNTIME && PM_GENERIC_DOMAINS +config PM_GENERIC_DOMAINS_OF + def_bool y + depends on PM_GENERIC_DOMAINS && OF && !ARCH_EXYNOS + config CPU_PM bool depends on SUSPEND || CPU_IDLE diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 37170d4dd9a6..126586a31408 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -492,8 +492,14 @@ int hibernation_restore(int platform_mode) error = dpm_suspend_start(PMSG_QUIESCE); if (!error) { error = resume_target_kernel(platform_mode); - dpm_resume_end(PMSG_RECOVER); + /* + * The above should either succeed and jump to the new kernel, + * or return with an error. Otherwise things are just + * undefined, so let's be paranoid. + */ + BUG_ON(!error); } + dpm_resume_end(PMSG_RECOVER); pm_restore_gfp_mask(); ftrace_start(); resume_console(); diff --git a/kernel/power/main.c b/kernel/power/main.c index 1d1bf630e6e9..3ae41cdd804a 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -293,12 +293,12 @@ static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr, { char *s = buf; #ifdef CONFIG_SUSPEND - int i; + suspend_state_t i; + + for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++) + if (pm_states[i].state) + s += sprintf(s,"%s ", pm_states[i].label); - for (i = 0; i < PM_SUSPEND_MAX; i++) { - if (pm_states[i] && valid_state(i)) - s += sprintf(s,"%s ", pm_states[i]); - } #endif #ifdef CONFIG_HIBERNATION s += sprintf(s, "%s\n", "disk"); @@ -314,7 +314,7 @@ static suspend_state_t decode_state(const char *buf, size_t n) { #ifdef CONFIG_SUSPEND suspend_state_t state = PM_SUSPEND_MIN; - const char * const *s; + struct pm_sleep_state *s; #endif char *p; int len; @@ -328,8 +328,9 @@ static suspend_state_t decode_state(const char *buf, size_t n) #ifdef CONFIG_SUSPEND for (s = &pm_states[state]; state < PM_SUSPEND_MAX; s++, state++) - if (*s && len == strlen(*s) && !strncmp(buf, *s, len)) - return state; + if (s->state && len == strlen(s->label) + && !strncmp(buf, s->label, len)) + return s->state; #endif return PM_SUSPEND_ON; @@ -447,8 +448,8 @@ static ssize_t autosleep_show(struct kobject *kobj, #ifdef CONFIG_SUSPEND if (state < PM_SUSPEND_MAX) - return sprintf(buf, "%s\n", valid_state(state) ? - pm_states[state] : "error"); + return sprintf(buf, "%s\n", pm_states[state].state ? + pm_states[state].label : "error"); #endif #ifdef CONFIG_HIBERNATION return sprintf(buf, "disk\n"); diff --git a/kernel/power/power.h b/kernel/power/power.h index 7d4b7ffb3c1d..f770cad3666c 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -175,17 +175,20 @@ extern void swsusp_show_speed(struct timeval *, struct timeval *, unsigned int, char *); #ifdef CONFIG_SUSPEND +struct pm_sleep_state { + const char *label; + suspend_state_t state; +}; + /* kernel/power/suspend.c */ -extern const char *const pm_states[]; +extern struct pm_sleep_state pm_states[]; -extern bool valid_state(suspend_state_t state); extern int suspend_devices_and_enter(suspend_state_t state); #else /* !CONFIG_SUSPEND */ static inline int suspend_devices_and_enter(suspend_state_t state) { return -ENOSYS; } -static inline bool valid_state(suspend_state_t state) { return false; } #endif /* !CONFIG_SUSPEND */ #ifdef CONFIG_PM_TEST_SUSPEND diff --git a/kernel/power/process.c b/kernel/power/process.c index 14f9a8d4725d..f1fe7ec110bb 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -107,6 +107,28 @@ static int try_to_freeze_tasks(bool user_only) return todo ? -EBUSY : 0; } +/* + * Returns true if all freezable tasks (except for current) are frozen already + */ +static bool check_frozen_processes(void) +{ + struct task_struct *g, *p; + bool ret = true; + + read_lock(&tasklist_lock); + for_each_process_thread(g, p) { + if (p != current && !freezer_should_skip(p) && + !frozen(p)) { + ret = false; + goto done; + } + } +done: + read_unlock(&tasklist_lock); + + return ret; +} + /** * freeze_processes - Signal user space processes to enter the refrigerator. * The current thread will not be frozen. The same process that calls @@ -117,6 +139,7 @@ static int try_to_freeze_tasks(bool user_only) int freeze_processes(void) { int error; + int oom_kills_saved; error = __usermodehelper_disable(UMH_FREEZING); if (error) @@ -130,12 +153,27 @@ int freeze_processes(void) printk("Freezing user space processes ... "); pm_freezing = true; + oom_kills_saved = oom_kills_count(); error = try_to_freeze_tasks(true); if (!error) { - printk("done."); __usermodehelper_set_disable_depth(UMH_DISABLED); oom_killer_disable(); + + /* + * There might have been an OOM kill while we were + * freezing tasks and the killed task might be still + * on the way out so we have to double check for race. + */ + if (oom_kills_count() != oom_kills_saved && + !check_frozen_processes()) { + __usermodehelper_set_disable_depth(UMH_ENABLED); + printk("OOM in progress."); + error = -EBUSY; + goto done; + } + printk("done."); } +done: printk("\n"); BUG_ON(in_atomic()); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 62ee437b5c7e..5455d5c3c149 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -29,10 +29,10 @@ #include "power.h" -const char *const pm_states[PM_SUSPEND_MAX] = { - [PM_SUSPEND_FREEZE] = "freeze", - [PM_SUSPEND_STANDBY] = "standby", - [PM_SUSPEND_MEM] = "mem", +struct pm_sleep_state pm_states[PM_SUSPEND_MAX] = { + [PM_SUSPEND_FREEZE] = { .label = "freeze", .state = PM_SUSPEND_FREEZE }, + [PM_SUSPEND_STANDBY] = { .label = "standby", }, + [PM_SUSPEND_MEM] = { .label = "mem", }, }; static const struct platform_suspend_ops *suspend_ops; @@ -62,42 +62,34 @@ void freeze_wake(void) } EXPORT_SYMBOL_GPL(freeze_wake); +static bool valid_state(suspend_state_t state) +{ + /* + * PM_SUSPEND_STANDBY and PM_SUSPEND_MEM states need low level + * support and need to be valid to the low level + * implementation, no valid callback implies that none are valid. + */ + return suspend_ops && suspend_ops->valid && suspend_ops->valid(state); +} + /** * suspend_set_ops - Set the global suspend method table. * @ops: Suspend operations to use. */ void suspend_set_ops(const struct platform_suspend_ops *ops) { + suspend_state_t i; + lock_system_sleep(); + suspend_ops = ops; + for (i = PM_SUSPEND_STANDBY; i <= PM_SUSPEND_MEM; i++) + pm_states[i].state = valid_state(i) ? i : 0; + unlock_system_sleep(); } EXPORT_SYMBOL_GPL(suspend_set_ops); -bool valid_state(suspend_state_t state) -{ - if (state == PM_SUSPEND_FREEZE) { -#ifdef CONFIG_PM_DEBUG - if (pm_test_level != TEST_NONE && - pm_test_level != TEST_FREEZER && - pm_test_level != TEST_DEVICES && - pm_test_level != TEST_PLATFORM) { - printk(KERN_WARNING "Unsupported pm_test mode for " - "freeze state, please choose " - "none/freezer/devices/platform.\n"); - return false; - } -#endif - return true; - } - /* - * PM_SUSPEND_STANDBY and PM_SUSPEND_MEMORY states need lowlevel - * support and need to be valid to the lowlevel - * implementation, no valid callback implies that none are valid. - */ - return suspend_ops && suspend_ops->valid && suspend_ops->valid(state); -} - /** * suspend_valid_only_mem - Generic memory-only valid callback. * @@ -324,9 +316,17 @@ static int enter_state(suspend_state_t state) { int error; - if (!valid_state(state)) - return -ENODEV; - + if (state == PM_SUSPEND_FREEZE) { +#ifdef CONFIG_PM_DEBUG + if (pm_test_level != TEST_NONE && pm_test_level <= TEST_CPUS) { + pr_warning("PM: Unsupported test mode for freeze state," + "please choose none/freezer/devices/platform.\n"); + return -EAGAIN; + } +#endif + } else if (!valid_state(state)) { + return -EINVAL; + } if (!mutex_trylock(&pm_mutex)) return -EBUSY; @@ -337,7 +337,7 @@ static int enter_state(suspend_state_t state) sys_sync(); printk("done.\n"); - pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]); + pr_debug("PM: Preparing system for %s sleep\n", pm_states[state].label); error = suspend_prepare(state); if (error) goto Unlock; @@ -345,7 +345,7 @@ static int enter_state(suspend_state_t state) if (suspend_test(TEST_FREEZER)) goto Finish; - pr_debug("PM: Entering %s sleep\n", pm_states[state]); + pr_debug("PM: Entering %s sleep\n", pm_states[state].label); pm_restrict_gfp_mask(); error = suspend_devices_and_enter(state); pm_restore_gfp_mask(); diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c index 9b2a1d58558d..269b097e78ea 100644 --- a/kernel/power/suspend_test.c +++ b/kernel/power/suspend_test.c @@ -92,13 +92,13 @@ static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state) } if (state == PM_SUSPEND_MEM) { - printk(info_test, pm_states[state]); + printk(info_test, pm_states[state].label); status = pm_suspend(state); if (status == -ENODEV) state = PM_SUSPEND_STANDBY; } if (state == PM_SUSPEND_STANDBY) { - printk(info_test, pm_states[state]); + printk(info_test, pm_states[state].label); status = pm_suspend(state); } if (status < 0) @@ -136,18 +136,16 @@ static char warn_bad_state[] __initdata = static int __init setup_test_suspend(char *value) { - unsigned i; + suspend_state_t i; /* "=mem" ==> "mem" */ value++; - for (i = 0; i < PM_SUSPEND_MAX; i++) { - if (!pm_states[i]) - continue; - if (strcmp(pm_states[i], value) != 0) - continue; - test_state = (__force suspend_state_t) i; - return 0; - } + for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++) + if (!strcmp(pm_states[i].label, value)) { + test_state = pm_states[i].state; + return 0; + } + printk(warn_bad_state, value); return 0; } @@ -164,8 +162,8 @@ static int __init test_suspend(void) /* PM is initialized by now; is that state testable? */ if (test_state == PM_SUSPEND_ON) goto done; - if (!valid_state(test_state)) { - printk(warn_bad_state, pm_states[test_state]); + if (!pm_states[test_state].state) { + printk(warn_bad_state, pm_states[test_state].label); goto done; } diff --git a/kernel/printk/console_cmdline.h b/kernel/printk/console_cmdline.h index cbd69d842341..2ca4a8b5fe57 100644 --- a/kernel/printk/console_cmdline.h +++ b/kernel/printk/console_cmdline.h @@ -3,7 +3,7 @@ struct console_cmdline { - char name[8]; /* Name of the driver */ + char name[16]; /* Name of the driver */ int index; /* Minor dev. to use */ char *options; /* Options for the driver */ #ifdef CONFIG_A11Y_BRAILLE_CONSOLE diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 8c086e6049b9..a755ad70fe8f 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2280,6 +2280,7 @@ void register_console(struct console *newcon) for (i = 0, c = console_cmdline; i < MAX_CMDLINECONSOLES && c->name[0]; i++, c++) { + BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name)); if (strcmp(c->name, newcon->name) != 0) continue; if (newcon->index >= 0 && diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index b3d116cd072d..6705d947ef14 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1228,6 +1228,22 @@ static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) } /* + * Awaken the grace-period kthread for the specified flavor of RCU. + * Don't do a self-awaken, and don't bother awakening when there is + * nothing for the grace-period kthread to do (as in several CPUs + * raced to awaken, and we lost), and finally don't try to awaken + * a kthread that has not yet been created. + */ +static void rcu_gp_kthread_wake(struct rcu_state *rsp) +{ + if (current == rsp->gp_kthread || + !ACCESS_ONCE(rsp->gp_flags) || + !rsp->gp_kthread) + return; + wake_up(&rsp->gp_wq); +} + +/* * If there is room, assign a ->completed number to any callbacks on * this CPU that have not already been assigned. Also accelerate any * callbacks that were previously assigned a ->completed number that has @@ -1670,7 +1686,7 @@ static void rsp_wakeup(struct irq_work *work) struct rcu_state *rsp = container_of(work, struct rcu_state, wakeup_work); /* Wake up rcu_gp_kthread() to start the grace period. */ - wake_up(&rsp->gp_wq); + rcu_gp_kthread_wake(rsp); } /* @@ -1746,7 +1762,7 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) { WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags); - wake_up(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */ + rcu_gp_kthread_wake(rsp); } /* @@ -2322,7 +2338,7 @@ static void force_quiescent_state(struct rcu_state *rsp) } rsp->gp_flags |= RCU_GP_FLAG_FQS; raw_spin_unlock_irqrestore(&rnp_old->lock, flags); - wake_up(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */ + rcu_gp_kthread_wake(rsp); } /* diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 677ebad70ce1..5e973efc036e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1895,6 +1895,8 @@ unsigned long to_ratio(u64 period, u64 runtime) #ifdef CONFIG_SMP inline struct dl_bw *dl_bw_of(int i) { + rcu_lockdep_assert(rcu_read_lock_sched_held(), + "sched RCU must be held"); return &cpu_rq(i)->rd->dl_bw; } @@ -1903,6 +1905,8 @@ static inline int dl_bw_cpus(int i) struct root_domain *rd = cpu_rq(i)->rd; int cpus = 0; + rcu_lockdep_assert(rcu_read_lock_sched_held(), + "sched RCU must be held"); for_each_cpu_and(i, rd->span, cpu_active_mask) cpus++; @@ -2976,6 +2980,8 @@ void rt_mutex_setprio(struct task_struct *p, int prio) } else { if (dl_prio(oldprio)) p->dl.dl_boosted = 0; + if (rt_prio(oldprio)) + p->rt.timeout = 0; p->sched_class = &fair_sched_class; } @@ -3937,13 +3943,14 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) * root_domain. */ #ifdef CONFIG_SMP - if (task_has_dl_policy(p)) { - const struct cpumask *span = task_rq(p)->rd->span; - - if (dl_bandwidth_enabled() && !cpumask_subset(span, new_mask)) { + if (task_has_dl_policy(p) && dl_bandwidth_enabled()) { + rcu_read_lock(); + if (!cpumask_subset(task_rq(p)->rd->span, new_mask)) { retval = -EBUSY; + rcu_read_unlock(); goto out_unlock; } + rcu_read_unlock(); } #endif again: @@ -7458,6 +7465,8 @@ static int sched_dl_global_constraints(void) int cpu, ret = 0; unsigned long flags; + rcu_read_lock(); + /* * Here we want to check the bandwidth not being set to some * value smaller than the currently allocated bandwidth in @@ -7479,6 +7488,8 @@ static int sched_dl_global_constraints(void) break; } + rcu_read_unlock(); + return ret; } @@ -7494,6 +7505,7 @@ static void sched_dl_do_global(void) if (global_rt_runtime() != RUNTIME_INF) new_bw = to_ratio(global_rt_period(), global_rt_runtime()); + rcu_read_lock(); /* * FIXME: As above... */ @@ -7504,6 +7516,7 @@ static void sched_dl_do_global(void) dl_b->bw = new_bw; raw_spin_unlock_irqrestore(&dl_b->lock, flags); } + rcu_read_unlock(); } static int sched_rt_global_validate(void) diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 37dac98c0749..8d3c5ddfdfdd 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -550,24 +550,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se) static int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se) { - int dmiss = dl_time_before(dl_se->deadline, rq_clock(rq)); - int rorun = dl_se->runtime <= 0; - - if (!rorun && !dmiss) - return 0; - - /* - * If we are beyond our current deadline and we are still - * executing, then we have already used some of the runtime of - * the next instance. Thus, if we do not account that, we are - * stealing bandwidth from the system at each deadline miss! - */ - if (dmiss) { - dl_se->runtime = rorun ? dl_se->runtime : 0; - dl_se->runtime -= rq_clock(rq) - dl_se->deadline; - } - - return 1; + return (dl_se->runtime <= 0); } extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq); @@ -806,10 +789,10 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, * parameters of the task might need updating. Otherwise, * we want a replenishment of its runtime. */ - if (!dl_se->dl_new && flags & ENQUEUE_REPLENISH) - replenish_dl_entity(dl_se, pi_se); - else + if (dl_se->dl_new || flags & ENQUEUE_WAKEUP) update_dl_entity(dl_se, pi_se); + else if (flags & ENQUEUE_REPLENISH) + replenish_dl_entity(dl_se, pi_se); __enqueue_dl_entity(dl_se); } diff --git a/kernel/smpboot.c b/kernel/smpboot.c index eb89e1807408..60d35ac5d3f1 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -279,6 +279,7 @@ int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) unsigned int cpu; int ret = 0; + get_online_cpus(); mutex_lock(&smpboot_threads_lock); for_each_online_cpu(cpu) { ret = __smpboot_create_thread(plug_thread, cpu); @@ -291,6 +292,7 @@ int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) list_add(&plug_thread->list, &hotplug_threads); out: mutex_unlock(&smpboot_threads_lock); + put_online_cpus(); return ret; } EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread); diff --git a/kernel/time.c b/kernel/time.c index 7c7964c33ae7..3eb322e518a3 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -195,6 +195,10 @@ SYSCALL_DEFINE2(settimeofday, struct timeval __user *, tv, if (tv) { if (copy_from_user(&user_tv, tv, sizeof(*tv))) return -EFAULT; + + if (!timeval_valid(&user_tv)) + return -EINVAL; + new_ts.tv_sec = user_tv.tv_sec; new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC; } @@ -496,17 +500,20 @@ EXPORT_SYMBOL(usecs_to_jiffies); * that a remainder subtract here would not do the right thing as the * resolution values don't fall on second boundries. I.e. the line: * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding. + * Note that due to the small error in the multiplier here, this + * rounding is incorrect for sufficiently large values of tv_nsec, but + * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're + * OK. * * Rather, we just shift the bits off the right. * * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec * value to a scaled second value. */ -unsigned long -timespec_to_jiffies(const struct timespec *value) +static unsigned long +__timespec_to_jiffies(unsigned long sec, long nsec) { - unsigned long sec = value->tv_sec; - long nsec = value->tv_nsec + TICK_NSEC - 1; + nsec = nsec + TICK_NSEC - 1; if (sec >= MAX_SEC_IN_JIFFIES){ sec = MAX_SEC_IN_JIFFIES; @@ -517,6 +524,13 @@ timespec_to_jiffies(const struct timespec *value) (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; } + +unsigned long +timespec_to_jiffies(const struct timespec *value) +{ + return __timespec_to_jiffies(value->tv_sec, value->tv_nsec); +} + EXPORT_SYMBOL(timespec_to_jiffies); void @@ -533,31 +547,27 @@ jiffies_to_timespec(const unsigned long jiffies, struct timespec *value) } EXPORT_SYMBOL(jiffies_to_timespec); -/* Same for "timeval" +/* + * We could use a similar algorithm to timespec_to_jiffies (with a + * different multiplier for usec instead of nsec). But this has a + * problem with rounding: we can't exactly add TICK_NSEC - 1 to the + * usec value, since it's not necessarily integral. * - * Well, almost. The problem here is that the real system resolution is - * in nanoseconds and the value being converted is in micro seconds. - * Also for some machines (those that use HZ = 1024, in-particular), - * there is a LARGE error in the tick size in microseconds. - - * The solution we use is to do the rounding AFTER we convert the - * microsecond part. Thus the USEC_ROUND, the bits to be shifted off. - * Instruction wise, this should cost only an additional add with carry - * instruction above the way it was done above. + * We could instead round in the intermediate scaled representation + * (i.e. in units of 1/2^(large scale) jiffies) but that's also + * perilous: the scaling introduces a small positive error, which + * combined with a division-rounding-upward (i.e. adding 2^(scale) - 1 + * units to the intermediate before shifting) leads to accidental + * overflow and overestimates. + * + * At the cost of one additional multiplication by a constant, just + * use the timespec implementation. */ unsigned long timeval_to_jiffies(const struct timeval *value) { - unsigned long sec = value->tv_sec; - long usec = value->tv_usec; - - if (sec >= MAX_SEC_IN_JIFFIES){ - sec = MAX_SEC_IN_JIFFIES; - usec = 0; - } - return (((u64)sec * SEC_CONVERSION) + - (((u64)usec * USEC_CONVERSION + USEC_ROUND) >> - (USEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; + return __timespec_to_jiffies(value->tv_sec, + value->tv_usec * NSEC_PER_USEC); } EXPORT_SYMBOL(timeval_to_jiffies); diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index fe75444ae7ec..cd45a0727a16 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -464,18 +464,26 @@ static enum alarmtimer_type clock2alarm(clockid_t clockid) static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm, ktime_t now) { + unsigned long flags; struct k_itimer *ptr = container_of(alarm, struct k_itimer, it.alarm.alarmtimer); - if (posix_timer_event(ptr, 0) != 0) - ptr->it_overrun++; + enum alarmtimer_restart result = ALARMTIMER_NORESTART; + + spin_lock_irqsave(&ptr->it_lock, flags); + if ((ptr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) { + if (posix_timer_event(ptr, 0) != 0) + ptr->it_overrun++; + } /* Re-add periodic timers */ if (ptr->it.alarm.interval.tv64) { ptr->it_overrun += alarm_forward(alarm, now, ptr->it.alarm.interval); - return ALARMTIMER_RESTART; + result = ALARMTIMER_RESTART; } - return ALARMTIMER_NORESTART; + spin_unlock_irqrestore(&ptr->it_lock, flags); + + return result; } /** @@ -541,18 +549,22 @@ static int alarm_timer_create(struct k_itimer *new_timer) * @new_timer: k_itimer pointer * @cur_setting: itimerspec data to fill * - * Copies the itimerspec data out from the k_itimer + * Copies out the current itimerspec data */ static void alarm_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting) { - memset(cur_setting, 0, sizeof(struct itimerspec)); + ktime_t relative_expiry_time = + alarm_expires_remaining(&(timr->it.alarm.alarmtimer)); + + if (ktime_to_ns(relative_expiry_time) > 0) { + cur_setting->it_value = ktime_to_timespec(relative_expiry_time); + } else { + cur_setting->it_value.tv_sec = 0; + cur_setting->it_value.tv_nsec = 0; + } - cur_setting->it_interval = - ktime_to_timespec(timr->it.alarm.interval); - cur_setting->it_value = - ktime_to_timespec(timr->it.alarm.alarmtimer.node.expires); - return; + cur_setting->it_interval = ktime_to_timespec(timr->it.alarm.interval); } /** diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index af8d1d4f3d55..6211d5d6d465 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -631,6 +631,17 @@ int ntp_validate_timex(struct timex *txc) if ((txc->modes & ADJ_SETOFFSET) && (!capable(CAP_SYS_TIME))) return -EPERM; + /* + * Check for potential multiplication overflows that can + * only happen on 64-bit systems: + */ + if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) { + if (LLONG_MIN / PPM_SCALE > txc->freq) + return -EINVAL; + if (LLONG_MAX / PPM_SCALE < txc->freq) + return -EINVAL; + } + return 0; } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 6558b7ac112d..8c08a6f9cca0 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -807,7 +807,6 @@ void tick_nohz_idle_enter(void) local_irq_enable(); } -EXPORT_SYMBOL_GPL(tick_nohz_idle_enter); /** * tick_nohz_irq_exit - update next tick event from interrupt exit @@ -934,7 +933,6 @@ void tick_nohz_idle_exit(void) local_irq_enable(); } -EXPORT_SYMBOL_GPL(tick_nohz_idle_exit); static int tick_nohz_reprogram(struct tick_sched *ts, ktime_t now) { diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index a53f1bbc546b..774a0807fe81 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -626,8 +626,22 @@ int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, work = &cpu_buffer->irq_work; } - work->waiters_pending = true; poll_wait(filp, &work->waiters, poll_table); + work->waiters_pending = true; + /* + * There's a tight race between setting the waiters_pending and + * checking if the ring buffer is empty. Once the waiters_pending bit + * is set, the next event will wake the task up, but we can get stuck + * if there's only a single event in. + * + * FIXME: Ideally, we need a memory barrier on the writer side as well, + * but adding a memory barrier to all events will cause too much of a + * performance hit in the fast path. We only need a memory barrier when + * the buffer goes from empty to having content. But as this race is + * extremely small, and it's not a problem if another event comes in, we + * will fix it later. + */ + smp_mb(); if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) || (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu))) @@ -3358,7 +3372,7 @@ static void rb_iter_reset(struct ring_buffer_iter *iter) iter->head = cpu_buffer->reader_page->read; iter->cache_reader_page = iter->head_page; - iter->cache_read = iter->head; + iter->cache_read = cpu_buffer->read; if (iter->head) iter->read_stamp = cpu_buffer->read_stamp; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 71136720ffa1..813b021379f5 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4694,7 +4694,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, *fpos += written; out_unlock: - for (i = 0; i < nr_pages; i++){ + for (i = nr_pages - 1; i >= 0; i--) { kunmap_atomic(map_page[i]); put_page(pages[i]); } diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 759d5e004517..7e3cd7aaec83 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -313,7 +313,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) int size; syscall_nr = trace_get_syscall_nr(current, regs); - if (syscall_nr < 0) + if (syscall_nr < 0 || syscall_nr >= NR_syscalls) return; /* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE) */ @@ -360,7 +360,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) int syscall_nr; syscall_nr = trace_get_syscall_nr(current, regs); - if (syscall_nr < 0) + if (syscall_nr < 0 || syscall_nr >= NR_syscalls) return; /* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE()) */ @@ -567,7 +567,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) int size; syscall_nr = trace_get_syscall_nr(current, regs); - if (syscall_nr < 0) + if (syscall_nr < 0 || syscall_nr >= NR_syscalls) return; if (!test_bit(syscall_nr, enabled_perf_enter_syscalls)) return; @@ -641,7 +641,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) int size; syscall_nr = trace_get_syscall_nr(current, regs); - if (syscall_nr < 0) + if (syscall_nr < 0 || syscall_nr >= NR_syscalls) return; if (!test_bit(syscall_nr, enabled_perf_exit_syscalls)) return; diff --git a/kernel/uid16.c b/kernel/uid16.c index 602e5bbbceff..d58cc4d8f0d1 100644 --- a/kernel/uid16.c +++ b/kernel/uid16.c @@ -176,7 +176,7 @@ SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist) struct group_info *group_info; int retval; - if (!ns_capable(current_user_ns(), CAP_SETGID)) + if (!may_setgroups()) return -EPERM; if ((unsigned)gidsetsize > NGROUPS_MAX) return -EINVAL; diff --git a/kernel/user.c b/kernel/user.c index c006131beb77..c2bbb50f5a90 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -51,6 +51,7 @@ struct user_namespace init_user_ns = { .owner = GLOBAL_ROOT_UID, .group = GLOBAL_ROOT_GID, .proc_inum = PROC_USER_INIT_INO, + .flags = USERNS_INIT_FLAGS, #ifdef CONFIG_PERSISTENT_KEYRINGS .persistent_keyring_register_sem = __RWSEM_INITIALIZER(init_user_ns.persistent_keyring_register_sem), diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 80a57afd8647..153971e4798a 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -24,6 +24,7 @@ #include <linux/fs_struct.h> static struct kmem_cache *user_ns_cachep __read_mostly; +static DEFINE_MUTEX(userns_state_mutex); static bool new_idmap_permitted(const struct file *file, struct user_namespace *ns, int cap_setid, @@ -99,6 +100,11 @@ int create_user_ns(struct cred *new) ns->owner = owner; ns->group = group; + /* Inherit USERNS_SETGROUPS_ALLOWED from our parent */ + mutex_lock(&userns_state_mutex); + ns->flags = parent_ns->flags; + mutex_unlock(&userns_state_mutex); + set_cred_user_ns(new, ns); #ifdef CONFIG_PERSISTENT_KEYRINGS @@ -581,9 +587,6 @@ static bool mappings_overlap(struct uid_gid_map *new_map, struct uid_gid_extent return false; } - -static DEFINE_MUTEX(id_map_mutex); - static ssize_t map_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos, int cap_setid, @@ -600,7 +603,7 @@ static ssize_t map_write(struct file *file, const char __user *buf, ssize_t ret = -EINVAL; /* - * The id_map_mutex serializes all writes to any given map. + * The userns_state_mutex serializes all writes to any given map. * * Any map is only ever written once. * @@ -618,7 +621,7 @@ static ssize_t map_write(struct file *file, const char __user *buf, * order and smp_rmb() is guaranteed that we don't have crazy * architectures returning stale data. */ - mutex_lock(&id_map_mutex); + mutex_lock(&userns_state_mutex); ret = -EPERM; /* Only allow one successful write to the map */ @@ -745,7 +748,7 @@ static ssize_t map_write(struct file *file, const char __user *buf, *ppos = count; ret = count; out: - mutex_unlock(&id_map_mutex); + mutex_unlock(&userns_state_mutex); if (page) free_page(page); return ret; @@ -804,17 +807,21 @@ static bool new_idmap_permitted(const struct file *file, struct user_namespace *ns, int cap_setid, struct uid_gid_map *new_map) { - /* Allow mapping to your own filesystem ids */ - if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1)) { + const struct cred *cred = file->f_cred; + /* Don't allow mappings that would allow anything that wouldn't + * be allowed without the establishment of unprivileged mappings. + */ + if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1) && + uid_eq(ns->owner, cred->euid)) { u32 id = new_map->extent[0].lower_first; if (cap_setid == CAP_SETUID) { kuid_t uid = make_kuid(ns->parent, id); - if (uid_eq(uid, file->f_cred->fsuid)) + if (uid_eq(uid, cred->euid)) return true; - } - else if (cap_setid == CAP_SETGID) { + } else if (cap_setid == CAP_SETGID) { kgid_t gid = make_kgid(ns->parent, id); - if (gid_eq(gid, file->f_cred->fsgid)) + if (!(ns->flags & USERNS_SETGROUPS_ALLOWED) && + gid_eq(gid, cred->egid)) return true; } } @@ -834,6 +841,100 @@ static bool new_idmap_permitted(const struct file *file, return false; } +int proc_setgroups_show(struct seq_file *seq, void *v) +{ + struct user_namespace *ns = seq->private; + unsigned long userns_flags = ACCESS_ONCE(ns->flags); + + seq_printf(seq, "%s\n", + (userns_flags & USERNS_SETGROUPS_ALLOWED) ? + "allow" : "deny"); + return 0; +} + +ssize_t proc_setgroups_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct seq_file *seq = file->private_data; + struct user_namespace *ns = seq->private; + char kbuf[8], *pos; + bool setgroups_allowed; + ssize_t ret; + + /* Only allow a very narrow range of strings to be written */ + ret = -EINVAL; + if ((*ppos != 0) || (count >= sizeof(kbuf))) + goto out; + + /* What was written? */ + ret = -EFAULT; + if (copy_from_user(kbuf, buf, count)) + goto out; + kbuf[count] = '\0'; + pos = kbuf; + + /* What is being requested? */ + ret = -EINVAL; + if (strncmp(pos, "allow", 5) == 0) { + pos += 5; + setgroups_allowed = true; + } + else if (strncmp(pos, "deny", 4) == 0) { + pos += 4; + setgroups_allowed = false; + } + else + goto out; + + /* Verify there is not trailing junk on the line */ + pos = skip_spaces(pos); + if (*pos != '\0') + goto out; + + ret = -EPERM; + mutex_lock(&userns_state_mutex); + if (setgroups_allowed) { + /* Enabling setgroups after setgroups has been disabled + * is not allowed. + */ + if (!(ns->flags & USERNS_SETGROUPS_ALLOWED)) + goto out_unlock; + } else { + /* Permanently disabling setgroups after setgroups has + * been enabled by writing the gid_map is not allowed. + */ + if (ns->gid_map.nr_extents != 0) + goto out_unlock; + ns->flags &= ~USERNS_SETGROUPS_ALLOWED; + } + mutex_unlock(&userns_state_mutex); + + /* Report a successful write */ + *ppos = count; + ret = count; +out: + return ret; +out_unlock: + mutex_unlock(&userns_state_mutex); + goto out; +} + +bool userns_may_setgroups(const struct user_namespace *ns) +{ + bool allowed; + + mutex_lock(&userns_state_mutex); + /* It is not safe to use setgroups until a gid mapping in + * the user namespace has been established. + */ + allowed = ns->gid_map.nr_extents != 0; + /* Is setgroups allowed? */ + allowed = allowed && (ns->flags & USERNS_SETGROUPS_ALLOWED); + mutex_unlock(&userns_state_mutex); + + return allowed; +} + static void *userns_get(struct task_struct *task) { struct user_namespace *user_ns; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index b4defdecec8a..423c9e37a9e7 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1962,17 +1962,13 @@ static void pool_mayday_timeout(unsigned long __pool) * spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. Called only from * manager. - * - * Return: - * %false if no action was taken and pool->lock stayed locked, %true - * otherwise. */ -static bool maybe_create_worker(struct worker_pool *pool) +static void maybe_create_worker(struct worker_pool *pool) __releases(&pool->lock) __acquires(&pool->lock) { if (!need_to_create_worker(pool)) - return false; + return; restart: spin_unlock_irq(&pool->lock); @@ -1989,7 +1985,7 @@ restart: start_worker(worker); if (WARN_ON_ONCE(need_to_create_worker(pool))) goto restart; - return true; + return; } if (!need_to_create_worker(pool)) @@ -2006,7 +2002,7 @@ restart: spin_lock_irq(&pool->lock); if (need_to_create_worker(pool)) goto restart; - return true; + return; } /** @@ -2019,15 +2015,9 @@ restart: * LOCKING: * spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Called only from manager. - * - * Return: - * %false if no action was taken and pool->lock stayed locked, %true - * otherwise. */ -static bool maybe_destroy_workers(struct worker_pool *pool) +static void maybe_destroy_workers(struct worker_pool *pool) { - bool ret = false; - while (too_many_workers(pool)) { struct worker *worker; unsigned long expires; @@ -2041,10 +2031,7 @@ static bool maybe_destroy_workers(struct worker_pool *pool) } destroy_worker(worker); - ret = true; } - - return ret; } /** @@ -2064,16 +2051,14 @@ static bool maybe_destroy_workers(struct worker_pool *pool) * multiple times. Does GFP_KERNEL allocations. * * Return: - * %false if the pool don't need management and the caller can safely start - * processing works, %true indicates that the function released pool->lock - * and reacquired it to perform some management function and that the - * conditions that the caller verified while holding the lock before - * calling the function might no longer be true. + * %false if the pool doesn't need management and the caller can safely + * start processing works, %true if management function was performed and + * the conditions that the caller verified before calling the function may + * no longer be true. */ static bool manage_workers(struct worker *worker) { struct worker_pool *pool = worker->pool; - bool ret = false; /* * Managership is governed by two mutexes - manager_arb and @@ -2097,7 +2082,7 @@ static bool manage_workers(struct worker *worker) * manager_mutex. */ if (!mutex_trylock(&pool->manager_arb)) - return ret; + return false; /* * With manager arbitration won, manager_mutex would be free in @@ -2107,7 +2092,6 @@ static bool manage_workers(struct worker *worker) spin_unlock_irq(&pool->lock); mutex_lock(&pool->manager_mutex); spin_lock_irq(&pool->lock); - ret = true; } pool->flags &= ~POOL_MANAGE_WORKERS; @@ -2116,12 +2100,12 @@ static bool manage_workers(struct worker *worker) * Destroy and then create so that may_start_working() is true * on return. */ - ret |= maybe_destroy_workers(pool); - ret |= maybe_create_worker(pool); + maybe_destroy_workers(pool); + maybe_create_worker(pool); mutex_unlock(&pool->manager_mutex); mutex_unlock(&pool->manager_arb); - return ret; + return true; } /** @@ -2909,19 +2893,57 @@ bool flush_work(struct work_struct *work) } EXPORT_SYMBOL_GPL(flush_work); +struct cwt_wait { + wait_queue_t wait; + struct work_struct *work; +}; + +static int cwt_wakefn(wait_queue_t *wait, unsigned mode, int sync, void *key) +{ + struct cwt_wait *cwait = container_of(wait, struct cwt_wait, wait); + + if (cwait->work != key) + return 0; + return autoremove_wake_function(wait, mode, sync, key); +} + static bool __cancel_work_timer(struct work_struct *work, bool is_dwork) { + static DECLARE_WAIT_QUEUE_HEAD(cancel_waitq); unsigned long flags; int ret; do { ret = try_to_grab_pending(work, is_dwork, &flags); /* - * If someone else is canceling, wait for the same event it - * would be waiting for before retrying. + * If someone else is already canceling, wait for it to + * finish. flush_work() doesn't work for PREEMPT_NONE + * because we may get scheduled between @work's completion + * and the other canceling task resuming and clearing + * CANCELING - flush_work() will return false immediately + * as @work is no longer busy, try_to_grab_pending() will + * return -ENOENT as @work is still being canceled and the + * other canceling task won't be able to clear CANCELING as + * we're hogging the CPU. + * + * Let's wait for completion using a waitqueue. As this + * may lead to the thundering herd problem, use a custom + * wake function which matches @work along with exclusive + * wait and wakeup. */ - if (unlikely(ret == -ENOENT)) - flush_work(work); + if (unlikely(ret == -ENOENT)) { + struct cwt_wait cwait; + + init_wait(&cwait.wait); + cwait.wait.func = cwt_wakefn; + cwait.work = work; + + prepare_to_wait_exclusive(&cancel_waitq, &cwait.wait, + TASK_UNINTERRUPTIBLE); + if (work_is_canceling(work)) + schedule(); + finish_wait(&cancel_waitq, &cwait.wait); + } } while (unlikely(ret < 0)); /* tell other tasks trying to grab @work to back off */ @@ -2930,6 +2952,16 @@ static bool __cancel_work_timer(struct work_struct *work, bool is_dwork) flush_work(work); clear_work_data(work); + + /* + * Paired with prepare_to_wait() above so that either + * waitqueue_active() is visible here or !work_is_canceling() is + * visible there. + */ + smp_mb(); + if (waitqueue_active(&cancel_waitq)) + __wake_up(&cancel_waitq, TASK_NORMAL, 1, work); + return ret; } diff --git a/lib/bitmap.c b/lib/bitmap.c index 06f7e4fe8d2d..e5c4ebe586ba 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -131,7 +131,9 @@ void __bitmap_shift_right(unsigned long *dst, lower = src[off + k]; if (left && off + k == lim - 1) lower &= mask; - dst[k] = upper << (BITS_PER_LONG - rem) | lower >> rem; + dst[k] = lower >> rem; + if (rem) + dst[k] |= upper << (BITS_PER_LONG - rem); if (left && k == lim - 1) dst[k] &= mask; } @@ -172,7 +174,9 @@ void __bitmap_shift_left(unsigned long *dst, upper = src[k]; if (left && k == lim - 1) upper &= (1UL << left) - 1; - dst[k + off] = lower >> (BITS_PER_LONG - rem) | upper << rem; + dst[k + off] = upper << rem; + if (rem) + dst[k + off] |= lower >> (BITS_PER_LONG - rem); if (left && k + off == lim - 1) dst[k + off] &= (1UL << left) - 1; } diff --git a/lib/checksum.c b/lib/checksum.c index 129775eb6de6..8b39e86dbab5 100644 --- a/lib/checksum.c +++ b/lib/checksum.c @@ -181,6 +181,15 @@ csum_partial_copy(const void *src, void *dst, int len, __wsum sum) EXPORT_SYMBOL(csum_partial_copy); #ifndef csum_tcpudp_nofold +static inline u32 from64to32(u64 x) +{ + /* add up 32-bit and 32-bit for 32+c bit */ + x = (x & 0xffffffff) + (x >> 32); + /* add up carry.. */ + x = (x & 0xffffffff) + (x >> 32); + return (u32)x; +} + __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len, unsigned short proto, @@ -195,8 +204,7 @@ __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, #else s += (proto + len) << 8; #endif - s += (s >> 32); - return (__force __wsum)s; + return (__force __wsum)from64to32(s); } EXPORT_SYMBOL(csum_tcpudp_nofold); #endif diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c index 31c5f7675fbf..f504027d66a8 100644 --- a/lib/decompress_bunzip2.c +++ b/lib/decompress_bunzip2.c @@ -184,7 +184,7 @@ static int INIT get_next_block(struct bunzip_data *bd) if (get_bits(bd, 1)) return RETVAL_OBSOLETE_INPUT; origPtr = get_bits(bd, 24); - if (origPtr > dbufSize) + if (origPtr >= dbufSize) return RETVAL_DATA_ERROR; /* mapping table: if some byte values are never used (encoding things like ascii text), the compression code removes the gaps to have fewer diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c index 7a85967060a5..f0f5c5c3de12 100644 --- a/lib/lz4/lz4_decompress.c +++ b/lib/lz4/lz4_decompress.c @@ -139,6 +139,9 @@ static int lz4_uncompress(const char *source, char *dest, int osize) /* Error: request to write beyond destination buffer */ if (cpy > oend) goto _output_error; + if ((ref + COPYLENGTH) > oend || + (op + COPYLENGTH) > oend) + goto _output_error; LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH)); while (op < cpy) *op++ = *ref++; diff --git a/lib/lzo/lzo1x_decompress_safe.c b/lib/lzo/lzo1x_decompress_safe.c index 8563081e8da3..a1c387f6afba 100644 --- a/lib/lzo/lzo1x_decompress_safe.c +++ b/lib/lzo/lzo1x_decompress_safe.c @@ -19,31 +19,21 @@ #include <linux/lzo.h> #include "lzodefs.h" -#define HAVE_IP(t, x) \ - (((size_t)(ip_end - ip) >= (size_t)(t + x)) && \ - (((t + x) >= t) && ((t + x) >= x))) +#define HAVE_IP(x) ((size_t)(ip_end - ip) >= (size_t)(x)) +#define HAVE_OP(x) ((size_t)(op_end - op) >= (size_t)(x)) +#define NEED_IP(x) if (!HAVE_IP(x)) goto input_overrun +#define NEED_OP(x) if (!HAVE_OP(x)) goto output_overrun +#define TEST_LB(m_pos) if ((m_pos) < out) goto lookbehind_overrun -#define HAVE_OP(t, x) \ - (((size_t)(op_end - op) >= (size_t)(t + x)) && \ - (((t + x) >= t) && ((t + x) >= x))) - -#define NEED_IP(t, x) \ - do { \ - if (!HAVE_IP(t, x)) \ - goto input_overrun; \ - } while (0) - -#define NEED_OP(t, x) \ - do { \ - if (!HAVE_OP(t, x)) \ - goto output_overrun; \ - } while (0) - -#define TEST_LB(m_pos) \ - do { \ - if ((m_pos) < out) \ - goto lookbehind_overrun; \ - } while (0) +/* This MAX_255_COUNT is the maximum number of times we can add 255 to a base + * count without overflowing an integer. The multiply will overflow when + * multiplying 255 by more than MAXINT/255. The sum will overflow earlier + * depending on the base count. Since the base count is taken from a u8 + * and a few bits, it is safe to assume that it will always be lower than + * or equal to 2*255, thus we can always prevent any overflow by accepting + * two less 255 steps. See Documentation/lzo.txt for more information. + */ +#define MAX_255_COUNT ((((size_t)~0) / 255) - 2) int lzo1x_decompress_safe(const unsigned char *in, size_t in_len, unsigned char *out, size_t *out_len) @@ -75,17 +65,24 @@ int lzo1x_decompress_safe(const unsigned char *in, size_t in_len, if (t < 16) { if (likely(state == 0)) { if (unlikely(t == 0)) { + size_t offset; + const unsigned char *ip_last = ip; + while (unlikely(*ip == 0)) { - t += 255; ip++; - NEED_IP(1, 0); + NEED_IP(1); } - t += 15 + *ip++; + offset = ip - ip_last; + if (unlikely(offset > MAX_255_COUNT)) + return LZO_E_ERROR; + + offset = (offset << 8) - offset; + t += offset + 15 + *ip++; } t += 3; copy_literal_run: #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) - if (likely(HAVE_IP(t, 15) && HAVE_OP(t, 15))) { + if (likely(HAVE_IP(t + 15) && HAVE_OP(t + 15))) { const unsigned char *ie = ip + t; unsigned char *oe = op + t; do { @@ -101,8 +98,8 @@ copy_literal_run: } else #endif { - NEED_OP(t, 0); - NEED_IP(t, 3); + NEED_OP(t); + NEED_IP(t + 3); do { *op++ = *ip++; } while (--t > 0); @@ -115,7 +112,7 @@ copy_literal_run: m_pos -= t >> 2; m_pos -= *ip++ << 2; TEST_LB(m_pos); - NEED_OP(2, 0); + NEED_OP(2); op[0] = m_pos[0]; op[1] = m_pos[1]; op += 2; @@ -136,13 +133,20 @@ copy_literal_run: } else if (t >= 32) { t = (t & 31) + (3 - 1); if (unlikely(t == 2)) { + size_t offset; + const unsigned char *ip_last = ip; + while (unlikely(*ip == 0)) { - t += 255; ip++; - NEED_IP(1, 0); + NEED_IP(1); } - t += 31 + *ip++; - NEED_IP(2, 0); + offset = ip - ip_last; + if (unlikely(offset > MAX_255_COUNT)) + return LZO_E_ERROR; + + offset = (offset << 8) - offset; + t += offset + 31 + *ip++; + NEED_IP(2); } m_pos = op - 1; next = get_unaligned_le16(ip); @@ -154,13 +158,20 @@ copy_literal_run: m_pos -= (t & 8) << 11; t = (t & 7) + (3 - 1); if (unlikely(t == 2)) { + size_t offset; + const unsigned char *ip_last = ip; + while (unlikely(*ip == 0)) { - t += 255; ip++; - NEED_IP(1, 0); + NEED_IP(1); } - t += 7 + *ip++; - NEED_IP(2, 0); + offset = ip - ip_last; + if (unlikely(offset > MAX_255_COUNT)) + return LZO_E_ERROR; + + offset = (offset << 8) - offset; + t += offset + 7 + *ip++; + NEED_IP(2); } next = get_unaligned_le16(ip); ip += 2; @@ -174,7 +185,7 @@ copy_literal_run: #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) if (op - m_pos >= 8) { unsigned char *oe = op + t; - if (likely(HAVE_OP(t, 15))) { + if (likely(HAVE_OP(t + 15))) { do { COPY8(op, m_pos); op += 8; @@ -184,7 +195,7 @@ copy_literal_run: m_pos += 8; } while (op < oe); op = oe; - if (HAVE_IP(6, 0)) { + if (HAVE_IP(6)) { state = next; COPY4(op, ip); op += next; @@ -192,7 +203,7 @@ copy_literal_run: continue; } } else { - NEED_OP(t, 0); + NEED_OP(t); do { *op++ = *m_pos++; } while (op < oe); @@ -201,7 +212,7 @@ copy_literal_run: #endif { unsigned char *oe = op + t; - NEED_OP(t, 0); + NEED_OP(t); op[0] = m_pos[0]; op[1] = m_pos[1]; op += 2; @@ -214,15 +225,15 @@ match_next: state = next; t = next; #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) - if (likely(HAVE_IP(6, 0) && HAVE_OP(4, 0))) { + if (likely(HAVE_IP(6) && HAVE_OP(4))) { COPY4(op, ip); op += t; ip += t; } else #endif { - NEED_IP(t, 3); - NEED_OP(t, 0); + NEED_IP(t + 3); + NEED_OP(t); while (t > 0) { *op++ = *ip++; t--; diff --git a/lib/plist.c b/lib/plist.c index 1ebc95f7a46f..0f2084d30798 100644 --- a/lib/plist.c +++ b/lib/plist.c @@ -134,6 +134,46 @@ void plist_del(struct plist_node *node, struct plist_head *head) plist_check_head(head); } +/** + * plist_requeue - Requeue @node at end of same-prio entries. + * + * This is essentially an optimized plist_del() followed by + * plist_add(). It moves an entry already in the plist to + * after any other same-priority entries. + * + * @node: &struct plist_node pointer - entry to be moved + * @head: &struct plist_head pointer - list head + */ +void plist_requeue(struct plist_node *node, struct plist_head *head) +{ + struct plist_node *iter; + struct list_head *node_next = &head->node_list; + + plist_check_head(head); + BUG_ON(plist_head_empty(head)); + BUG_ON(plist_node_empty(node)); + + if (node == plist_last(head)) + return; + + iter = plist_next(node); + + if (node->prio != iter->prio) + return; + + plist_del(node, head); + + plist_for_each_continue(iter, head) { + if (node->prio != iter->prio) { + node_next = &iter->node_list; + break; + } + } + list_add_tail(&node->node_list, node_next); + + plist_check_head(head); +} + #ifdef CONFIG_DEBUG_PI_LIST #include <linux/sched.h> #include <linux/module.h> @@ -170,6 +210,14 @@ static void __init plist_test_check(int nr_expect) BUG_ON(prio_pos->prio_list.next != &first->prio_list); } +static void __init plist_test_requeue(struct plist_node *node) +{ + plist_requeue(node, &test_head); + + if (node != plist_last(&test_head)) + BUG_ON(node->prio == plist_next(node)->prio); +} + static int __init plist_test(void) { int nr_expect = 0, i, loop; @@ -193,6 +241,10 @@ static int __init plist_test(void) nr_expect--; } plist_test_check(nr_expect); + if (!plist_node_empty(test_node + i)) { + plist_test_requeue(test_node + i); + plist_test_check(nr_expect); + } } for (i = 0; i < ARRAY_SIZE(test_node); i++) { diff --git a/lib/radix-tree.c b/lib/radix-tree.c index bd4a8dfdf0b8..7e30d2a7f346 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -946,81 +946,6 @@ next: } EXPORT_SYMBOL(radix_tree_range_tag_if_tagged); - -/** - * radix_tree_next_hole - find the next hole (not-present entry) - * @root: tree root - * @index: index key - * @max_scan: maximum range to search - * - * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the lowest - * indexed hole. - * - * Returns: the index of the hole if found, otherwise returns an index - * outside of the set specified (in which case 'return - index >= max_scan' - * will be true). In rare cases of index wrap-around, 0 will be returned. - * - * radix_tree_next_hole may be called under rcu_read_lock. However, like - * radix_tree_gang_lookup, this will not atomically search a snapshot of - * the tree at a single point in time. For example, if a hole is created - * at index 5, then subsequently a hole is created at index 10, - * radix_tree_next_hole covering both indexes may return 10 if called - * under rcu_read_lock. - */ -unsigned long radix_tree_next_hole(struct radix_tree_root *root, - unsigned long index, unsigned long max_scan) -{ - unsigned long i; - - for (i = 0; i < max_scan; i++) { - if (!radix_tree_lookup(root, index)) - break; - index++; - if (index == 0) - break; - } - - return index; -} -EXPORT_SYMBOL(radix_tree_next_hole); - -/** - * radix_tree_prev_hole - find the prev hole (not-present entry) - * @root: tree root - * @index: index key - * @max_scan: maximum range to search - * - * Search backwards in the range [max(index-max_scan+1, 0), index] - * for the first hole. - * - * Returns: the index of the hole if found, otherwise returns an index - * outside of the set specified (in which case 'index - return >= max_scan' - * will be true). In rare cases of wrap-around, ULONG_MAX will be returned. - * - * radix_tree_next_hole may be called under rcu_read_lock. However, like - * radix_tree_gang_lookup, this will not atomically search a snapshot of - * the tree at a single point in time. For example, if a hole is created - * at index 10, then subsequently a hole is created at index 5, - * radix_tree_prev_hole covering both indexes may return 5 if called under - * rcu_read_lock. - */ -unsigned long radix_tree_prev_hole(struct radix_tree_root *root, - unsigned long index, unsigned long max_scan) -{ - unsigned long i; - - for (i = 0; i < max_scan; i++) { - if (!radix_tree_lookup(root, index)) - break; - index--; - if (index == ULONG_MAX) - break; - } - - return index; -} -EXPORT_SYMBOL(radix_tree_prev_hole); - /** * radix_tree_gang_lookup - perform multiple lookup on a radix tree * @root: radix tree root @@ -1337,15 +1262,18 @@ static inline void radix_tree_shrink(struct radix_tree_root *root) } /** - * radix_tree_delete - delete an item from a radix tree + * radix_tree_delete_item - delete an item from a radix tree * @root: radix tree root * @index: index key + * @item: expected item * - * Remove the item at @index from the radix tree rooted at @root. + * Remove @item at @index from the radix tree rooted at @root. * - * Returns the address of the deleted item, or NULL if it was not present. + * Returns the address of the deleted item, or NULL if it was not present + * or the entry at the given @index was not @item. */ -void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) +void *radix_tree_delete_item(struct radix_tree_root *root, + unsigned long index, void *item) { struct radix_tree_node *node = NULL; struct radix_tree_node *slot = NULL; @@ -1380,6 +1308,11 @@ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) if (slot == NULL) goto out; + if (item && slot != item) { + slot = NULL; + goto out; + } + /* * Clear all tags associated with the item to be deleted. * This way of doing it would be inefficient, but seldom is any set. @@ -1424,6 +1357,21 @@ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) out: return slot; } +EXPORT_SYMBOL(radix_tree_delete_item); + +/** + * radix_tree_delete - delete an item from a radix tree + * @root: radix tree root + * @index: index key + * + * Remove the item at @index from the radix tree rooted at @root. + * + * Returns the address of the deleted item, or NULL if it was not present. + */ +void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) +{ + return radix_tree_delete_item(root, index, NULL); +} EXPORT_SYMBOL(radix_tree_delete); /** diff --git a/lib/string.c b/lib/string.c index e5878de4f101..43d0781daf47 100644 --- a/lib/string.c +++ b/lib/string.c @@ -586,6 +586,22 @@ void *memset(void *s, int c, size_t count) EXPORT_SYMBOL(memset); #endif +/** + * memzero_explicit - Fill a region of memory (e.g. sensitive + * keying data) with 0s. + * @s: Pointer to the start of the area. + * @count: The size of the area. + * + * memzero_explicit() doesn't need an arch-specific version as + * it just invokes the one of memset() implicitly. + */ +void memzero_explicit(void *s, size_t count) +{ + memset(s, 0, count); + OPTIMIZER_HIDE_VAR(s); +} +EXPORT_SYMBOL(memzero_explicit); + #ifndef __HAVE_ARCH_MEMCPY /** * memcpy - Copy one area of memory to another diff --git a/linaro/configs/booting-test.conf b/linaro/configs/booting-test.conf new file mode 100644 index 000000000000..7592b2185963 --- /dev/null +++ b/linaro/configs/booting-test.conf @@ -0,0 +1,66 @@ +CONFIG_UNUSED_SYMBOLS=y +CONFIG_HEADERS_CHECK=y +CONFIG_DEBUG_SECTION_MISMATCH=y +CONFIG_DEBUG_SHIRQ=y +CONFIG_LOCKUP_DETECTOR=y +CONFIG_DEBUG_OBJECTS=y +CONFIG_DEBUG_OBJECTS_SELFTEST=y +CONFIG_DEBUG_OBJECTS_TIMERS=y +CONFIG_DEBUG_OBJECTS_WORK=y +CONFIG_DEBUG_OBJECTS_RCU_HEAD=y +CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y +CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT=1 +CONFIG_DEBUG_KMEMLEAK=y +CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE=400 +CONFIG_DEBUG_KMEMLEAK_TEST=m +CONFIG_DEBUG_RT_MUTEXES=y +CONFIG_DEBUG_PI_LIST=y +CONFIG_RT_MUTEX_TESTER=y +CONFIG_DEBUG_LOCKDEP=y +CONFIG_DEBUG_ATOMIC_SLEEP=y +CONFIG_DEBUG_LOCKING_API_SELFTESTS=y +CONFIG_DEBUG_STACK_USAGE=y +CONFIG_DEBUG_KOBJECT=y +CONFIG_DEBUG_HIGHMEM=y +CONFIG_DEBUG_BUGVERBOSE=y +CONFIG_DEBUG_VM=y +CONFIG_DEBUG_VM_RB=y +CONFIG_DEBUG_WRITECOUNT=y +CONFIG_DEBUG_MEMORY_INIT=y +CONFIG_DEBUG_LIST=y +CONFIG_TEST_LIST_SORT=y +CONFIG_DEBUG_SG=y +CONFIG_DEBUG_NOTIFIERS=y +CONFIG_DEBUG_CREDENTIALS=y +CONFIG_DEBUG_BLOCK_EXT_DEVT=y +CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y +CONFIG_DEBUG_PER_CPU_MAPS=y +CONFIG_FAULT_INJECTION=y +CONFIG_TRACER_MAX_TRACE=y +CONFIG_GENERIC_TRACER=y +CONFIG_FUNCTION_TRACER=y +CONFIG_FUNCTION_GRAPH_TRACER=y +CONFIG_IRQSOFF_TRACER=y +CONFIG_SCHED_TRACER=y +CONFIG_FTRACE_SYSCALLS=y +CONFIG_TRACER_SNAPSHOT=y +CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y +CONFIG_STACK_TRACER=y +CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_DYNAMIC_FTRACE=y +CONFIG_FUNCTION_PROFILER=y +CONFIG_FTRACE_MCOUNT_RECORD=y +CONFIG_FTRACE_SELFTEST=y +CONFIG_FTRACE_STARTUP_TEST=y +CONFIG_EVENT_TRACE_TEST_SYSCALLS=y +CONFIG_RING_BUFFER_BENCHMARK=y +CONFIG_RING_BUFFER_STARTUP_TEST=y +CONFIG_DYNAMIC_DEBUG=y +CONFIG_DMA_API_DEBUG=y +CONFIG_ATOMIC64_SELFTEST=y +CONFIG_TEST_STRING_HELPERS=y +CONFIG_TEST_KSTRTOX=y +CONFIG_STRICT_DEVMEM=y +CONFIG_OLD_MCOUNT=y +CONFIG_DEBUG_USER=y + diff --git a/linaro/configs/linaro-base.conf b/linaro/configs/linaro-base.conf index bbd0f160398f..15f6ea784f63 100644 --- a/linaro/configs/linaro-base.conf +++ b/linaro/configs/linaro-base.conf @@ -116,3 +116,5 @@ CONFIG_EXT4_FS_SECURITY=y CONFIG_BLK_DEV_LOOP=y CONFIG_DEBUG_INFO=y CONFIG_FANOTIFY=y +CONFIG_RCU_TORTURE_TEST=m +CONFIG_RCU_TORTURE_TEST_RUNNABLE=n diff --git a/mm/Makefile b/mm/Makefile index 9d9c587620a3..3c21f087037d 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -16,7 +16,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ util.o mmzone.o vmstat.o backing-dev.o \ mm_init.o mmu_context.o percpu.o slab_common.o \ - compaction.o balloon_compaction.o \ + compaction.o balloon_compaction.o vmacache.o \ interval_tree.o list_lru.o $(mmu-y) obj-y += init-mm.o diff --git a/mm/compaction.c b/mm/compaction.c index 5f702ef0a65f..a522208bb8ea 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -89,7 +89,8 @@ static void __reset_isolation_suitable(struct zone *zone) unsigned long end_pfn = zone_end_pfn(zone); unsigned long pfn; - zone->compact_cached_migrate_pfn = start_pfn; + zone->compact_cached_migrate_pfn[0] = start_pfn; + zone->compact_cached_migrate_pfn[1] = start_pfn; zone->compact_cached_free_pfn = end_pfn; zone->compact_blockskip_flush = false; @@ -131,9 +132,10 @@ void reset_isolation_suitable(pg_data_t *pgdat) */ static void update_pageblock_skip(struct compact_control *cc, struct page *page, unsigned long nr_isolated, - bool migrate_scanner) + bool set_unsuitable, bool migrate_scanner) { struct zone *zone = cc->zone; + unsigned long pfn; if (cc->ignore_skip_hint) return; @@ -141,20 +143,32 @@ static void update_pageblock_skip(struct compact_control *cc, if (!page) return; - if (!nr_isolated) { - unsigned long pfn = page_to_pfn(page); + if (nr_isolated) + return; + + /* + * Only skip pageblocks when all forms of compaction will be known to + * fail in the near future. + */ + if (set_unsuitable) set_pageblock_skip(page); - /* Update where compaction should restart */ - if (migrate_scanner) { - if (!cc->finished_update_migrate && - pfn > zone->compact_cached_migrate_pfn) - zone->compact_cached_migrate_pfn = pfn; - } else { - if (!cc->finished_update_free && - pfn < zone->compact_cached_free_pfn) - zone->compact_cached_free_pfn = pfn; - } + pfn = page_to_pfn(page); + + /* Update where async and sync compaction should restart */ + if (migrate_scanner) { + if (cc->finished_update_migrate) + return; + if (pfn > zone->compact_cached_migrate_pfn[0]) + zone->compact_cached_migrate_pfn[0] = pfn; + if (cc->mode != MIGRATE_ASYNC && + pfn > zone->compact_cached_migrate_pfn[1]) + zone->compact_cached_migrate_pfn[1] = pfn; + } else { + if (cc->finished_update_free) + return; + if (pfn < zone->compact_cached_free_pfn) + zone->compact_cached_free_pfn = pfn; } } #else @@ -166,7 +180,7 @@ static inline bool isolation_suitable(struct compact_control *cc, static void update_pageblock_skip(struct compact_control *cc, struct page *page, unsigned long nr_isolated, - bool migrate_scanner) + bool set_unsuitable, bool migrate_scanner) { } #endif /* CONFIG_COMPACTION */ @@ -195,7 +209,7 @@ static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags, } /* async aborts if taking too long or contended */ - if (!cc->sync) { + if (cc->mode == MIGRATE_ASYNC) { cc->contended = true; return false; } @@ -208,30 +222,39 @@ static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags, return true; } -static inline bool compact_trylock_irqsave(spinlock_t *lock, - unsigned long *flags, struct compact_control *cc) +/* + * Aside from avoiding lock contention, compaction also periodically checks + * need_resched() and either schedules in sync compaction or aborts async + * compaction. This is similar to what compact_checklock_irqsave() does, but + * is used where no lock is concerned. + * + * Returns false when no scheduling was needed, or sync compaction scheduled. + * Returns true when async compaction should abort. + */ +static inline bool compact_should_abort(struct compact_control *cc) { - return compact_checklock_irqsave(lock, flags, false, cc); + /* async compaction aborts if contended */ + if (need_resched()) { + if (cc->mode == MIGRATE_ASYNC) { + cc->contended = true; + return true; + } + + cond_resched(); + } + + return false; } /* Returns true if the page is within a block suitable for migration to */ static bool suitable_migration_target(struct page *page) { - int migratetype = get_pageblock_migratetype(page); - - /* Don't interfere with memory hot-remove or the min_free_kbytes blocks */ - if (migratetype == MIGRATE_RESERVE) - return false; - - if (is_migrate_isolate(migratetype)) - return false; - - /* If the page is a large free page, then allow migration */ + /* If the page is a large free page, then disallow migration */ if (PageBuddy(page) && page_order(page) >= pageblock_order) - return true; + return false; /* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */ - if (migrate_async_suitable(migratetype)) + if (migrate_async_suitable(get_pageblock_migratetype(page))) return true; /* Otherwise skip the block */ @@ -253,6 +276,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, struct page *cursor, *valid_page = NULL; unsigned long flags; bool locked = false; + bool checked_pageblock = false; cursor = pfn_to_page(blockpfn); @@ -284,8 +308,16 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, break; /* Recheck this is a suitable migration target under lock */ - if (!strict && !suitable_migration_target(page)) - break; + if (!strict && !checked_pageblock) { + /* + * We need to check suitability of pageblock only once + * and this isolate_freepages_block() is called with + * pageblock range, so just check once is sufficient. + */ + checked_pageblock = true; + if (!suitable_migration_target(page)) + break; + } /* Recheck this is a buddy page under lock */ if (!PageBuddy(page)) @@ -329,7 +361,8 @@ isolate_fail: /* Update the pageblock-skip if the whole pageblock was scanned */ if (blockpfn == end_pfn) - update_pageblock_skip(cc, valid_page, total_isolated, false); + update_pageblock_skip(cc, valid_page, total_isolated, true, + false); count_compact_events(COMPACTFREE_SCANNED, nr_scanned); if (total_isolated) @@ -460,12 +493,14 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, unsigned long last_pageblock_nr = 0, pageblock_nr; unsigned long nr_scanned = 0, nr_isolated = 0; struct list_head *migratelist = &cc->migratepages; - isolate_mode_t mode = 0; struct lruvec *lruvec; unsigned long flags; bool locked = false; struct page *page = NULL, *valid_page = NULL; - bool skipped_async_unsuitable = false; + bool set_unsuitable = true; + const isolate_mode_t mode = (cc->mode == MIGRATE_ASYNC ? + ISOLATE_ASYNC_MIGRATE : 0) | + (unevictable ? ISOLATE_UNEVICTABLE : 0); /* * Ensure that there are not too many pages isolated from the LRU @@ -474,7 +509,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, */ while (unlikely(too_many_isolated(zone))) { /* async migration should just abort */ - if (!cc->sync) + if (cc->mode == MIGRATE_ASYNC) return 0; congestion_wait(BLK_RW_ASYNC, HZ/10); @@ -483,11 +518,13 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, return 0; } + if (compact_should_abort(cc)) + return 0; + /* Time to isolate some pages for migration */ - cond_resched(); for (; low_pfn < end_pfn; low_pfn++) { /* give a chance to irqs before checking need_resched() */ - if (locked && !((low_pfn+1) % SWAP_CLUSTER_MAX)) { + if (locked && !(low_pfn % SWAP_CLUSTER_MAX)) { if (should_release_lock(&zone->lru_lock)) { spin_unlock_irqrestore(&zone->lru_lock, flags); locked = false; @@ -526,8 +563,25 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, /* If isolation recently failed, do not retry */ pageblock_nr = low_pfn >> pageblock_order; - if (!isolation_suitable(cc, page)) - goto next_pageblock; + if (last_pageblock_nr != pageblock_nr) { + int mt; + + last_pageblock_nr = pageblock_nr; + if (!isolation_suitable(cc, page)) + goto next_pageblock; + + /* + * For async migration, also only scan in MOVABLE + * blocks. Async migration is optimistic to see if + * the minimum amount of work satisfies the allocation + */ + mt = get_pageblock_migratetype(page); + if (cc->mode == MIGRATE_ASYNC && + !migrate_async_suitable(mt)) { + set_unsuitable = false; + goto next_pageblock; + } + } /* * Skip if free. page_order cannot be used without zone->lock @@ -537,18 +591,6 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, continue; /* - * For async migration, also only scan in MOVABLE blocks. Async - * migration is optimistic to see if the minimum amount of work - * satisfies the allocation - */ - if (!cc->sync && last_pageblock_nr != pageblock_nr && - !migrate_async_suitable(get_pageblock_migratetype(page))) { - cc->finished_update_migrate = true; - skipped_async_unsuitable = true; - goto next_pageblock; - } - - /* * Check may be lockless but that's ok as we recheck later. * It's possible to migrate LRU pages and balloon pages * Skip any other type of page @@ -557,11 +599,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, if (unlikely(balloon_page_movable(page))) { if (locked && balloon_page_isolate(page)) { /* Successfully isolated */ - cc->finished_update_migrate = true; - list_add(&page->lru, migratelist); - cc->nr_migratepages++; - nr_isolated++; - goto check_compact_cluster; + goto isolate_success; } } continue; @@ -584,6 +622,15 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, continue; } + /* + * Migration will fail if an anonymous page is pinned in memory, + * so avoid taking lru_lock and isolating it unnecessarily in an + * admittedly racy check. + */ + if (!page_mapping(page) && + page_count(page) > page_mapcount(page)) + continue; + /* Check if it is ok to still hold the lock */ locked = compact_checklock_irqsave(&zone->lru_lock, &flags, locked, cc); @@ -598,12 +645,6 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, continue; } - if (!cc->sync) - mode |= ISOLATE_ASYNC_MIGRATE; - - if (unevictable) - mode |= ISOLATE_UNEVICTABLE; - lruvec = mem_cgroup_page_lruvec(page, zone); /* Try isolate the page */ @@ -613,13 +654,14 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, VM_BUG_ON_PAGE(PageTransCompound(page), page); /* Successfully isolated */ - cc->finished_update_migrate = true; del_page_from_lru_list(page, lruvec, page_lru(page)); + +isolate_success: + cc->finished_update_migrate = true; list_add(&page->lru, migratelist); cc->nr_migratepages++; nr_isolated++; -check_compact_cluster: /* Avoid isolating too much */ if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) { ++low_pfn; @@ -630,7 +672,6 @@ check_compact_cluster: next_pageblock: low_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages) - 1; - last_pageblock_nr = pageblock_nr; } acct_isolated(zone, locked, cc); @@ -641,11 +682,10 @@ next_pageblock: /* * Update the pageblock-skip information and cached scanner pfn, * if the whole pageblock was scanned without isolating any page. - * This is not done when pageblock was skipped due to being unsuitable - * for async compaction, so that eventual sync compaction can try. */ - if (low_pfn == end_pfn && !skipped_async_unsuitable) - update_pageblock_skip(cc, valid_page, nr_isolated, true); + if (low_pfn == end_pfn) + update_pageblock_skip(cc, valid_page, nr_isolated, + set_unsuitable, true); trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated); @@ -666,7 +706,9 @@ static void isolate_freepages(struct zone *zone, struct compact_control *cc) { struct page *page; - unsigned long high_pfn, low_pfn, pfn, z_end_pfn; + unsigned long block_start_pfn; /* start of current pageblock */ + unsigned long block_end_pfn; /* end of current pageblock */ + unsigned long low_pfn; /* lowest pfn scanner is able to scan */ int nr_freepages = cc->nr_freepages; struct list_head *freelist = &cc->freepages; @@ -674,41 +716,38 @@ static void isolate_freepages(struct zone *zone, * Initialise the free scanner. The starting point is where we last * successfully isolated from, zone-cached value, or the end of the * zone when isolating for the first time. We need this aligned to - * the pageblock boundary, because we do pfn -= pageblock_nr_pages - * in the for loop. + * the pageblock boundary, because we do + * block_start_pfn -= pageblock_nr_pages in the for loop. + * For ending point, take care when isolating in last pageblock of a + * a zone which ends in the middle of a pageblock. * The low boundary is the end of the pageblock the migration scanner * is using. */ - pfn = cc->free_pfn & ~(pageblock_nr_pages-1); + block_start_pfn = cc->free_pfn & ~(pageblock_nr_pages-1); + block_end_pfn = min(block_start_pfn + pageblock_nr_pages, + zone_end_pfn(zone)); low_pfn = ALIGN(cc->migrate_pfn + 1, pageblock_nr_pages); /* - * Take care that if the migration scanner is at the end of the zone - * that the free scanner does not accidentally move to the next zone - * in the next isolation cycle. - */ - high_pfn = min(low_pfn, pfn); - - z_end_pfn = zone_end_pfn(zone); - - /* * Isolate free pages until enough are available to migrate the * pages on cc->migratepages. We stop searching if the migrate * and free page scanners meet or enough free pages are isolated. */ - for (; pfn >= low_pfn && cc->nr_migratepages > nr_freepages; - pfn -= pageblock_nr_pages) { + for (; block_start_pfn >= low_pfn && cc->nr_migratepages > nr_freepages; + block_end_pfn = block_start_pfn, + block_start_pfn -= pageblock_nr_pages) { unsigned long isolated; - unsigned long end_pfn; /* * This can iterate a massively long zone without finding any * suitable migration targets, so periodically check if we need - * to schedule. + * to schedule, or even abort async compaction. */ - cond_resched(); + if (!(block_start_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages)) + && compact_should_abort(cc)) + break; - if (!pfn_valid(pfn)) + if (!pfn_valid(block_start_pfn)) continue; /* @@ -718,7 +757,7 @@ static void isolate_freepages(struct zone *zone, * i.e. it's possible that all pages within a zones range of * pages do not belong to a single zone. */ - page = pfn_to_page(pfn); + page = pfn_to_page(block_start_pfn); if (page_zone(page) != zone) continue; @@ -731,26 +770,26 @@ static void isolate_freepages(struct zone *zone, continue; /* Found a block suitable for isolating free pages from */ - isolated = 0; + cc->free_pfn = block_start_pfn; + isolated = isolate_freepages_block(cc, block_start_pfn, + block_end_pfn, freelist, false); + nr_freepages += isolated; /* - * Take care when isolating in last pageblock of a zone which - * ends in the middle of a pageblock. + * Set a flag that we successfully isolated in this pageblock. + * In the next loop iteration, zone->compact_cached_free_pfn + * will not be updated and thus it will effectively contain the + * highest pageblock we isolated pages from. */ - end_pfn = min(pfn + pageblock_nr_pages, z_end_pfn); - isolated = isolate_freepages_block(cc, pfn, end_pfn, - freelist, false); - nr_freepages += isolated; + if (isolated) + cc->finished_update_free = true; /* - * Record the highest PFN we isolated pages from. When next - * looking for free pages, the search will restart here as - * page migration may have returned some pages to the allocator + * isolate_freepages_block() might have aborted due to async + * compaction being contended */ - if (isolated) { - cc->finished_update_free = true; - high_pfn = max(high_pfn, pfn); - } + if (cc->contended) + break; } /* split_free_page does not map the pages */ @@ -760,10 +799,9 @@ static void isolate_freepages(struct zone *zone, * If we crossed the migrate scanner, we want to keep it that way * so that compact_finished() may detect this */ - if (pfn < low_pfn) - cc->free_pfn = max(pfn, zone->zone_start_pfn); - else - cc->free_pfn = high_pfn; + if (block_start_pfn < low_pfn) + cc->free_pfn = cc->migrate_pfn; + cc->nr_freepages = nr_freepages; } @@ -778,9 +816,13 @@ static struct page *compaction_alloc(struct page *migratepage, struct compact_control *cc = (struct compact_control *)data; struct page *freepage; - /* Isolate free pages if necessary */ + /* + * Isolate free pages if necessary, and if we are not aborting due to + * contention. + */ if (list_empty(&cc->freepages)) { - isolate_freepages(cc->zone, cc); + if (!cc->contended) + isolate_freepages(cc->zone, cc); if (list_empty(&cc->freepages)) return NULL; @@ -794,23 +836,16 @@ static struct page *compaction_alloc(struct page *migratepage, } /* - * We cannot control nr_migratepages and nr_freepages fully when migration is - * running as migrate_pages() has no knowledge of compact_control. When - * migration is complete, we count the number of pages on the lists by hand. + * This is a migrate-callback that "frees" freepages back to the isolated + * freelist. All pages on the freelist are from the same zone, so there is no + * special handling needed for NUMA. */ -static void update_nr_listpages(struct compact_control *cc) +static void compaction_free(struct page *page, unsigned long data) { - int nr_migratepages = 0; - int nr_freepages = 0; - struct page *page; - - list_for_each_entry(page, &cc->migratepages, lru) - nr_migratepages++; - list_for_each_entry(page, &cc->freepages, lru) - nr_freepages++; + struct compact_control *cc = (struct compact_control *)data; - cc->nr_migratepages = nr_migratepages; - cc->nr_freepages = nr_freepages; + list_add(&page->lru, &cc->freepages); + cc->nr_freepages++; } /* possible outcome of isolate_migratepages */ @@ -857,13 +892,14 @@ static int compact_finished(struct zone *zone, unsigned int order; unsigned long watermark; - if (fatal_signal_pending(current)) + if (cc->contended || fatal_signal_pending(current)) return COMPACT_PARTIAL; /* Compaction run completes if the migrate and free scanner meet */ if (cc->free_pfn <= cc->migrate_pfn) { /* Let the next compaction start anew. */ - zone->compact_cached_migrate_pfn = zone->zone_start_pfn; + zone->compact_cached_migrate_pfn[0] = zone->zone_start_pfn; + zone->compact_cached_migrate_pfn[1] = zone->zone_start_pfn; zone->compact_cached_free_pfn = zone_end_pfn(zone); /* @@ -901,7 +937,7 @@ static int compact_finished(struct zone *zone, return COMPACT_PARTIAL; /* Job done if allocation would set block type */ - if (cc->order >= pageblock_order && area->nr_free) + if (order >= pageblock_order && area->nr_free) return COMPACT_PARTIAL; } @@ -963,6 +999,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) int ret; unsigned long start_pfn = zone->zone_start_pfn; unsigned long end_pfn = zone_end_pfn(zone); + const bool sync = cc->mode != MIGRATE_ASYNC; ret = compaction_suitable(zone, cc->order); switch (ret) { @@ -988,7 +1025,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) * information on where the scanners should start but check that it * is initialised by ensuring the values are within zone boundaries. */ - cc->migrate_pfn = zone->compact_cached_migrate_pfn; + cc->migrate_pfn = zone->compact_cached_migrate_pfn[sync]; cc->free_pfn = zone->compact_cached_free_pfn; if (cc->free_pfn < start_pfn || cc->free_pfn > end_pfn) { cc->free_pfn = end_pfn & ~(pageblock_nr_pages-1); @@ -996,7 +1033,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) } if (cc->migrate_pfn < start_pfn || cc->migrate_pfn > end_pfn) { cc->migrate_pfn = start_pfn; - zone->compact_cached_migrate_pfn = cc->migrate_pfn; + zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn; + zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn; } trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, cc->free_pfn, end_pfn); @@ -1004,7 +1042,6 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) migrate_prep_local(); while ((ret = compact_finished(zone, cc)) == COMPACT_CONTINUE) { - unsigned long nr_migrate, nr_remaining; int err; switch (isolate_migratepages(zone, cc)) { @@ -1019,21 +1056,20 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) ; } - nr_migrate = cc->nr_migratepages; + if (!cc->nr_migratepages) + continue; + err = migrate_pages(&cc->migratepages, compaction_alloc, - (unsigned long)cc, - cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC, + compaction_free, (unsigned long)cc, cc->mode, MR_COMPACTION); - update_nr_listpages(cc); - nr_remaining = cc->nr_migratepages; - trace_mm_compaction_migratepages(nr_migrate - nr_remaining, - nr_remaining); + trace_mm_compaction_migratepages(cc->nr_migratepages, err, + &cc->migratepages); - /* Release isolated pages not migrated */ + /* All pages were either migrated or will be released */ + cc->nr_migratepages = 0; if (err) { putback_movable_pages(&cc->migratepages); - cc->nr_migratepages = 0; /* * migrate_pages() may return -ENOMEM when scanners meet * and we want compact_finished() to detect it @@ -1055,9 +1091,8 @@ out: return ret; } -static unsigned long compact_zone_order(struct zone *zone, - int order, gfp_t gfp_mask, - bool sync, bool *contended) +static unsigned long compact_zone_order(struct zone *zone, int order, + gfp_t gfp_mask, enum migrate_mode mode, bool *contended) { unsigned long ret; struct compact_control cc = { @@ -1066,7 +1101,7 @@ static unsigned long compact_zone_order(struct zone *zone, .order = order, .migratetype = allocflags_to_migratetype(gfp_mask), .zone = zone, - .sync = sync, + .mode = mode, }; INIT_LIST_HEAD(&cc.freepages); INIT_LIST_HEAD(&cc.migratepages); @@ -1088,7 +1123,7 @@ int sysctl_extfrag_threshold = 500; * @order: The order of the current allocation * @gfp_mask: The GFP mask of the current allocation * @nodemask: The allowed nodes to allocate from - * @sync: Whether migration is synchronous or not + * @mode: The migration mode for async, sync light, or sync migration * @contended: Return value that is true if compaction was aborted due to lock contention * @page: Optionally capture a free page of the requested order during compaction * @@ -1096,7 +1131,7 @@ int sysctl_extfrag_threshold = 500; */ unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask, - bool sync, bool *contended) + enum migrate_mode mode, bool *contended) { enum zone_type high_zoneidx = gfp_zone(gfp_mask); int may_enter_fs = gfp_mask & __GFP_FS; @@ -1121,7 +1156,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, nodemask) { int status; - status = compact_zone_order(zone, order, gfp_mask, sync, + status = compact_zone_order(zone, order, gfp_mask, mode, contended); rc = max(status, rc); @@ -1160,9 +1195,6 @@ static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc) if (zone_watermark_ok(zone, cc->order, low_wmark_pages(zone), 0, 0)) compaction_defer_reset(zone, cc->order, false); - /* Currently async compaction is never deferred. */ - else if (cc->sync) - defer_compaction(zone, cc->order); } VM_BUG_ON(!list_empty(&cc->freepages)); @@ -1174,7 +1206,7 @@ void compact_pgdat(pg_data_t *pgdat, int order) { struct compact_control cc = { .order = order, - .sync = false, + .mode = MIGRATE_ASYNC, }; if (!order) @@ -1187,7 +1219,8 @@ static void compact_node(int nid) { struct compact_control cc = { .order = -1, - .sync = true, + .mode = MIGRATE_SYNC, + .ignore_skip_hint = true, }; __compact_pgdat(NODE_DATA(nid), &cc); diff --git a/mm/filemap.c b/mm/filemap.c index 7a13f6ac5421..217cfd3b3264 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -192,9 +192,11 @@ static int filemap_check_errors(struct address_space *mapping) { int ret = 0; /* Check for outstanding write errors */ - if (test_and_clear_bit(AS_ENOSPC, &mapping->flags)) + if (test_bit(AS_ENOSPC, &mapping->flags) && + test_and_clear_bit(AS_ENOSPC, &mapping->flags)) ret = -ENOSPC; - if (test_and_clear_bit(AS_EIO, &mapping->flags)) + if (test_bit(AS_EIO, &mapping->flags) && + test_and_clear_bit(AS_EIO, &mapping->flags)) ret = -EIO; return ret; } @@ -446,6 +448,29 @@ 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 **slot; + int error; + + slot = radix_tree_lookup_slot(&mapping->page_tree, page->index); + if (slot) { + void *p; + + p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock); + if (!radix_tree_exceptional_entry(p)) + return -EEXIST; + radix_tree_replace_slot(slot, page); + mapping->nrpages++; + return 0; + } + error = radix_tree_insert(&mapping->page_tree, page->index, page); + if (!error) + mapping->nrpages++; + return error; +} + /** * add_to_page_cache_locked - add a locked page to the pagecache * @page: page to add @@ -480,11 +505,10 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, page->index = offset; spin_lock_irq(&mapping->tree_lock); - error = radix_tree_insert(&mapping->page_tree, offset, page); + error = page_cache_tree_insert(mapping, page); radix_tree_preload_end(); if (unlikely(error)) goto err_insert; - mapping->nrpages++; __inc_zone_page_state(page, NR_FILE_PAGES); spin_unlock_irq(&mapping->tree_lock); trace_mm_filemap_add_to_page_cache(page); @@ -520,10 +544,10 @@ struct page *__page_cache_alloc(gfp_t gfp) if (cpuset_do_page_mem_spread()) { unsigned int cpuset_mems_cookie; do { - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); page = alloc_pages_exact_node(n, gfp, 0); - } while (!put_mems_allowed(cpuset_mems_cookie) && !page); + } while (!page && read_mems_allowed_retry(cpuset_mems_cookie)); return page; } @@ -620,8 +644,17 @@ EXPORT_SYMBOL(unlock_page); */ void end_page_writeback(struct page *page) { - if (TestClearPageReclaim(page)) + /* + * TestClearPageReclaim could be used here but it is an atomic + * operation and overkill in this particular case. Failing to + * shuffle a page marked for immediate reclaim is too mild to + * justify taking an atomic operation penalty at the end of + * ever page writeback. + */ + if (PageReclaim(page)) { + ClearPageReclaim(page); rotate_reclaimable_page(page); + } if (!test_clear_page_writeback(page)) BUG(); @@ -686,14 +719,101 @@ int __lock_page_or_retry(struct page *page, struct mm_struct *mm, } /** - * find_get_page - find and get a page reference + * page_cache_next_hole - find the next hole (not-present entry) + * @mapping: mapping + * @index: index + * @max_scan: maximum range to search + * + * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the + * lowest indexed hole. + * + * Returns: the index of the hole if found, otherwise returns an index + * outside of the set specified (in which case 'return - index >= + * max_scan' will be true). In rare cases of index wrap-around, 0 will + * be returned. + * + * page_cache_next_hole may be called under rcu_read_lock. However, + * like radix_tree_gang_lookup, this will not atomically search a + * snapshot of the tree at a single point in time. For example, if a + * hole is created at index 5, then subsequently a hole is created at + * index 10, page_cache_next_hole covering both indexes may return 10 + * if called under rcu_read_lock. + */ +pgoff_t page_cache_next_hole(struct address_space *mapping, + pgoff_t index, unsigned long max_scan) +{ + unsigned long i; + + for (i = 0; i < max_scan; i++) { + struct page *page; + + page = radix_tree_lookup(&mapping->page_tree, index); + if (!page || radix_tree_exceptional_entry(page)) + break; + index++; + if (index == 0) + break; + } + + return index; +} +EXPORT_SYMBOL(page_cache_next_hole); + +/** + * page_cache_prev_hole - find the prev hole (not-present entry) + * @mapping: mapping + * @index: index + * @max_scan: maximum range to search + * + * Search backwards in the range [max(index-max_scan+1, 0), index] for + * the first hole. + * + * Returns: the index of the hole if found, otherwise returns an index + * outside of the set specified (in which case 'index - return >= + * max_scan' will be true). In rare cases of wrap-around, ULONG_MAX + * will be returned. + * + * page_cache_prev_hole may be called under rcu_read_lock. However, + * like radix_tree_gang_lookup, this will not atomically search a + * snapshot of the tree at a single point in time. For example, if a + * hole is created at index 10, then subsequently a hole is created at + * index 5, page_cache_prev_hole covering both indexes may return 5 if + * called under rcu_read_lock. + */ +pgoff_t page_cache_prev_hole(struct address_space *mapping, + pgoff_t index, unsigned long max_scan) +{ + unsigned long i; + + for (i = 0; i < max_scan; i++) { + struct page *page; + + page = radix_tree_lookup(&mapping->page_tree, index); + if (!page || radix_tree_exceptional_entry(page)) + break; + index--; + if (index == ULONG_MAX) + break; + } + + return index; +} +EXPORT_SYMBOL(page_cache_prev_hole); + +/** + * find_get_entry - find and get a page cache entry * @mapping: the address_space to search - * @offset: the page index + * @offset: the page cache index * - * Is there a pagecache struct page at the given (mapping, offset) tuple? - * If yes, increment its refcount and return it; if no, return NULL. + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned with an increased refcount. + * + * If the slot holds a shadow entry of a previously evicted page, it + * is returned. + * + * Otherwise, %NULL is returned. */ -struct page *find_get_page(struct address_space *mapping, pgoff_t offset) +struct page *find_get_entry(struct address_space *mapping, pgoff_t offset) { void **pagep; struct page *page; @@ -734,24 +854,30 @@ out: return page; } -EXPORT_SYMBOL(find_get_page); +EXPORT_SYMBOL(find_get_entry); /** - * find_lock_page - locate, pin and lock a pagecache page + * find_lock_entry - locate, pin and lock a page cache entry * @mapping: the address_space to search - * @offset: the page index + * @offset: the page cache index * - * Locates the desired pagecache page, locks it, increments its reference - * count and returns its address. + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. * - * Returns zero if the page was not present. find_lock_page() may sleep. + * If the slot holds a shadow entry of a previously evicted page, it + * is returned. + * + * Otherwise, %NULL is returned. + * + * find_lock_entry() may sleep. */ -struct page *find_lock_page(struct address_space *mapping, pgoff_t offset) +struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset) { struct page *page; repeat: - page = find_get_page(mapping, offset); + page = find_get_entry(mapping, offset); if (page && !radix_tree_exception(page)) { lock_page(page); /* Has the page been truncated? */ @@ -764,44 +890,86 @@ repeat: } return page; } -EXPORT_SYMBOL(find_lock_page); +EXPORT_SYMBOL(find_lock_entry); /** - * find_or_create_page - locate or add a pagecache page - * @mapping: the page's address_space - * @index: the page's index into the mapping - * @gfp_mask: page allocation mode + * pagecache_get_page - find and get a page reference + * @mapping: the address_space to search + * @offset: the page index + * @fgp_flags: PCG flags + * @gfp_mask: gfp mask to use for the page cache data page allocation + * + * Looks up the page cache slot at @mapping & @offset. * - * Locates a page in the pagecache. If the page is not present, a new page - * is allocated using @gfp_mask and is added to the pagecache and to the VM's - * LRU list. The returned page is locked and has its reference count - * incremented. + * PCG flags modify how the page is returned * - * find_or_create_page() may sleep, even if @gfp_flags specifies an atomic - * allocation! + * FGP_ACCESSED: the page will be marked accessed + * FGP_LOCK: Page is return locked + * FGP_CREAT: If page is not present then a new page is allocated using + * @gfp_mask and added to the page cache and the VM's LRU + * list. The page is returned locked and with an increased + * refcount. Otherwise, %NULL is returned. * - * find_or_create_page() returns the desired page's address, or zero on - * memory exhaustion. + * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even + * if the GFP flags specified for FGP_CREAT are atomic. + * + * If there is a page cache page, it is returned with an increased refcount. */ -struct page *find_or_create_page(struct address_space *mapping, - pgoff_t index, gfp_t gfp_mask) +struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, + int fgp_flags, gfp_t gfp_mask) { struct page *page; - int err; + repeat: - page = find_lock_page(mapping, index); - if (!page) { + page = find_get_entry(mapping, offset); + if (radix_tree_exceptional_entry(page)) + page = NULL; + if (!page) + goto no_page; + + if (fgp_flags & FGP_LOCK) { + if (fgp_flags & FGP_NOWAIT) { + if (!trylock_page(page)) { + page_cache_release(page); + return NULL; + } + } else { + lock_page(page); + } + + /* Has the page been truncated? */ + if (unlikely(page->mapping != mapping)) { + unlock_page(page); + page_cache_release(page); + goto repeat; + } + VM_BUG_ON(page->index != offset); + } + + if (page && (fgp_flags & FGP_ACCESSED)) + mark_page_accessed(page); + +no_page: + if (!page && (fgp_flags & FGP_CREAT)) { + int err; + if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping)) + gfp_mask |= __GFP_WRITE; + if (fgp_flags & FGP_NOFS) + gfp_mask &= ~__GFP_FS; + page = __page_cache_alloc(gfp_mask); if (!page) return NULL; - /* - * We want a regular kernel memory (not highmem or DMA etc) - * allocation for the radix tree nodes, but we need to honour - * the context-specific requirements the caller has asked for. - * GFP_RECLAIM_MASK collects those requirements. - */ - err = add_to_page_cache_lru(page, mapping, index, - (gfp_mask & GFP_RECLAIM_MASK)); + + if (WARN_ON_ONCE(!(fgp_flags & FGP_LOCK))) + fgp_flags |= FGP_LOCK; + + /* Init accessed so avoit atomic mark_page_accessed later */ + if (fgp_flags & FGP_ACCESSED) + init_page_accessed(page); + + err = add_to_page_cache_lru(page, mapping, offset, + gfp_mask & GFP_RECLAIM_MASK); if (unlikely(err)) { page_cache_release(page); page = NULL; @@ -809,9 +977,80 @@ repeat: goto repeat; } } + return page; } -EXPORT_SYMBOL(find_or_create_page); +EXPORT_SYMBOL(pagecache_get_page); + +/** + * find_get_entries - gang pagecache lookup + * @mapping: The address_space to search + * @start: The starting page cache index + * @nr_entries: The maximum number of entries + * @entries: Where the resulting entries are placed + * @indices: The cache indices corresponding to the entries in @entries + * + * find_get_entries() will search for and return a group of up to + * @nr_entries entries in the mapping. The entries are placed at + * @entries. find_get_entries() takes a reference against any actual + * pages it returns. + * + * The search returns a group of mapping-contiguous page cache entries + * with ascending indexes. There may be holes in the indices due to + * not-present pages. + * + * Any shadow entries of evicted pages are included in the returned + * array. + * + * find_get_entries() returns the number of pages and shadow entries + * which were found. + */ +unsigned find_get_entries(struct address_space *mapping, + pgoff_t start, unsigned int nr_entries, + struct page **entries, pgoff_t *indices) +{ + void **slot; + unsigned int ret = 0; + struct radix_tree_iter iter; + + if (!nr_entries) + return 0; + + rcu_read_lock(); +restart: + radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { + struct page *page; +repeat: + page = radix_tree_deref_slot(slot); + if (unlikely(!page)) + continue; + if (radix_tree_exception(page)) { + if (radix_tree_deref_retry(page)) + goto restart; + /* + * Otherwise, we must be storing a swap entry + * here as an exceptional entry: so return it + * without attempting to raise page count. + */ + goto export; + } + if (!page_cache_get_speculative(page)) + goto repeat; + + /* Has the page moved? */ + if (unlikely(page != *slot)) { + page_cache_release(page); + goto repeat; + } +export: + indices[ret] = iter.index; + entries[ret] = page; + if (++ret == nr_entries) + break; + } + rcu_read_unlock(); + return ret; +} /** * find_get_pages - gang pagecache lookup @@ -1031,39 +1270,6 @@ repeat: } EXPORT_SYMBOL(find_get_pages_tag); -/** - * grab_cache_page_nowait - returns locked page at given index in given cache - * @mapping: target address_space - * @index: the page index - * - * Same as grab_cache_page(), but do not wait if the page is unavailable. - * This is intended for speculative data generators, where the data can - * be regenerated if the page couldn't be grabbed. This routine should - * be safe to call while holding the lock for another page. - * - * Clear __GFP_FS when allocating the page to avoid recursion into the fs - * and deadlock against the caller's locked page. - */ -struct page * -grab_cache_page_nowait(struct address_space *mapping, pgoff_t index) -{ - struct page *page = find_get_page(mapping, index); - - if (page) { - if (trylock_page(page)) - return page; - page_cache_release(page); - return NULL; - } - page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS); - if (page && add_to_page_cache_lru(page, mapping, index, GFP_NOFS)) { - page_cache_release(page); - page = NULL; - } - return page; -} -EXPORT_SYMBOL(grab_cache_page_nowait); - /* * CD/DVDs are error prone. When a medium error occurs, the driver may fail * a _large_ part of the i/o request. Imagine the worst scenario: @@ -1795,6 +2001,18 @@ int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma) EXPORT_SYMBOL(generic_file_mmap); EXPORT_SYMBOL(generic_file_readonly_mmap); +static struct page *wait_on_page_read(struct page *page) +{ + if (!IS_ERR(page)) { + wait_on_page_locked(page); + if (!PageUptodate(page)) { + page_cache_release(page); + page = ERR_PTR(-EIO); + } + } + return page; +} + static struct page *__read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), @@ -1821,6 +2039,8 @@ repeat: if (err < 0) { page_cache_release(page); page = ERR_PTR(err); + } else { + page = wait_on_page_read(page); } } return page; @@ -1857,6 +2077,10 @@ retry: if (err < 0) { page_cache_release(page); return ERR_PTR(err); + } else { + page = wait_on_page_read(page); + if (IS_ERR(page)) + return page; } out: mark_page_accessed(page); @@ -1864,40 +2088,25 @@ out: } /** - * read_cache_page_async - read into page cache, fill it if needed + * read_cache_page - read into page cache, fill it if needed * @mapping: the page's address_space * @index: the page index * @filler: function to perform the read * @data: first arg to filler(data, page) function, often left as NULL * - * Same as read_cache_page, but don't wait for page to become unlocked - * after submitting it to the filler. - * * Read into the page cache. If a page already exists, and PageUptodate() is - * not set, try to fill the page but don't wait for it to become unlocked. + * not set, try to fill the page and wait for it to become unlocked. * * If the page does not get brought uptodate, return -EIO. */ -struct page *read_cache_page_async(struct address_space *mapping, +struct page *read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), void *data) { return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping)); } -EXPORT_SYMBOL(read_cache_page_async); - -static struct page *wait_on_page_read(struct page *page) -{ - if (!IS_ERR(page)) { - wait_on_page_locked(page); - if (!PageUptodate(page)) { - page_cache_release(page); - page = ERR_PTR(-EIO); - } - } - return page; -} +EXPORT_SYMBOL(read_cache_page); /** * read_cache_page_gfp - read into page cache, using specified page allocation flags. @@ -1916,31 +2125,10 @@ struct page *read_cache_page_gfp(struct address_space *mapping, { filler_t *filler = (filler_t *)mapping->a_ops->readpage; - return wait_on_page_read(do_read_cache_page(mapping, index, filler, NULL, gfp)); + return do_read_cache_page(mapping, index, filler, NULL, gfp); } EXPORT_SYMBOL(read_cache_page_gfp); -/** - * read_cache_page - read into page cache, fill it if needed - * @mapping: the page's address_space - * @index: the page index - * @filler: function to perform the read - * @data: first arg to filler(data, page) function, often left as NULL - * - * Read into the page cache. If a page already exists, and PageUptodate() is - * not set, try to fill the page then wait for it to become unlocked. - * - * If the page does not get brought uptodate, return -EIO. - */ -struct page *read_cache_page(struct address_space *mapping, - pgoff_t index, - int (*filler)(void *, struct page *), - void *data) -{ - return wait_on_page_read(read_cache_page_async(mapping, index, filler, data)); -} -EXPORT_SYMBOL(read_cache_page); - static size_t __iovec_copy_from_user_inatomic(char *vaddr, const struct iovec *iov, size_t base, size_t bytes) { @@ -1974,7 +2162,6 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, char *kaddr; size_t copied; - BUG_ON(!in_atomic()); kaddr = kmap_atomic(page); if (likely(i->nr_segs == 1)) { int left; @@ -2184,7 +2371,6 @@ int pagecache_write_end(struct file *file, struct address_space *mapping, { const struct address_space_operations *aops = mapping->a_ops; - mark_page_accessed(page); return aops->write_end(file, mapping, pos, len, copied, page, fsdata); } EXPORT_SYMBOL(pagecache_write_end); @@ -2266,34 +2452,17 @@ EXPORT_SYMBOL(generic_file_direct_write); struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index, unsigned flags) { - int status; - gfp_t gfp_mask; struct page *page; - gfp_t gfp_notmask = 0; + int fgp_flags = FGP_LOCK|FGP_ACCESSED|FGP_WRITE|FGP_CREAT; - gfp_mask = mapping_gfp_mask(mapping); - if (mapping_cap_account_dirty(mapping)) - gfp_mask |= __GFP_WRITE; if (flags & AOP_FLAG_NOFS) - gfp_notmask = __GFP_FS; -repeat: - page = find_lock_page(mapping, index); + fgp_flags |= FGP_NOFS; + + page = pagecache_get_page(mapping, index, fgp_flags, + mapping_gfp_mask(mapping)); if (page) - goto found; + wait_for_stable_page(page); - page = __page_cache_alloc(gfp_mask & ~gfp_notmask); - if (!page) - return NULL; - status = add_to_page_cache_lru(page, mapping, index, - GFP_KERNEL & ~gfp_notmask); - if (unlikely(status)) { - page_cache_release(page); - if (status == -EEXIST) - goto repeat; - return NULL; - } -found: - wait_for_stable_page(page); return page; } EXPORT_SYMBOL(grab_cache_page_write_begin); @@ -2342,18 +2511,15 @@ again: status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); - if (unlikely(status)) + if (unlikely(status < 0)) break; if (mapping_writably_mapped(mapping)) flush_dcache_page(page); - pagefault_disable(); copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); - pagefault_enable(); flush_dcache_page(page); - mark_page_accessed(page); status = a_ops->write_end(file, mapping, pos, bytes, copied, page, fsdata); if (unlikely(status < 0)) diff --git a/mm/frontswap.c b/mm/frontswap.c index 1b24bdcb3197..f2a3571c6e22 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -244,8 +244,10 @@ int __frontswap_store(struct page *page) the (older) page from frontswap */ inc_frontswap_failed_stores(); - if (dup) + if (dup) { __frontswap_clear(sis, offset); + frontswap_ops->invalidate_page(type, offset); + } } if (frontswap_writethrough_enabled) /* report failure so swap also writes to swap device */ @@ -327,15 +329,12 @@ EXPORT_SYMBOL(__frontswap_invalidate_area); static unsigned long __frontswap_curr_pages(void) { - int type; unsigned long totalpages = 0; struct swap_info_struct *si = NULL; assert_spin_locked(&swap_lock); - for (type = swap_list.head; type >= 0; type = si->next) { - si = swap_info[type]; + plist_for_each_entry(si, &swap_active_head, list) totalpages += atomic_read(&si->frontswap_pages); - } return totalpages; } @@ -347,11 +346,9 @@ static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused, int si_frontswap_pages; unsigned long total_pages_to_unuse = total; unsigned long pages = 0, pages_to_unuse = 0; - int type; assert_spin_locked(&swap_lock); - for (type = swap_list.head; type >= 0; type = si->next) { - si = swap_info[type]; + plist_for_each_entry(si, &swap_active_head, list) { si_frontswap_pages = atomic_read(&si->frontswap_pages); if (total_pages_to_unuse < si_frontswap_pages) { pages = pages_to_unuse = total_pages_to_unuse; @@ -366,7 +363,7 @@ static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused, } vm_unacct_memory(pages); *unused = pages_to_unuse; - *swapid = type; + *swapid = si->type; ret = 0; break; } @@ -413,7 +410,7 @@ void frontswap_shrink(unsigned long target_pages) /* * we don't want to hold swap_lock while doing a very * lengthy try_to_unuse, but swap_list may change - * so restart scan from swap_list.head each time + * so restart scan from swap_active_head each time */ spin_lock(&swap_lock); ret = __frontswap_shrink(target_pages, &pages_to_unuse, &type); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1c42d0c36d0b..adce656d2e9c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -199,7 +199,7 @@ retry: preempt_disable(); if (cmpxchg(&huge_zero_page, NULL, zero_page)) { preempt_enable(); - __free_page(zero_page); + __free_pages(zero_page, compound_order(zero_page)); goto retry; } @@ -231,7 +231,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { struct page *zero_page = xchg(&huge_zero_page, NULL); BUG_ON(zero_page == NULL); - __free_page(zero_page); + __free_pages(zero_page, compound_order(zero_page)); return HPAGE_PMD_NR; } @@ -1819,21 +1819,24 @@ static int __split_huge_page_map(struct page *page, if (pmd) { pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); + if (pmd_write(*pmd)) + BUG_ON(page_mapcount(page) != 1); haddr = address; for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { pte_t *pte, entry; BUG_ON(PageCompound(page+i)); + /* + * Note that pmd_numa is not transferred deliberately + * to avoid any possibility that pte_numa leaks to + * a PROT_NONE VMA by accident. + */ entry = mk_pte(page + i, vma->vm_page_prot); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (!pmd_write(*pmd)) entry = pte_wrprotect(entry); - else - BUG_ON(page_mapcount(page) != 1); if (!pmd_young(*pmd)) entry = pte_mkold(entry); - if (pmd_numa(*pmd)) - entry = pte_mknuma(entry); pte = pte_offset_map(&_pmd, haddr); BUG_ON(!pte_none(*pte)); set_pte_at(mm, haddr, pte, entry); @@ -2270,6 +2273,30 @@ static void khugepaged_alloc_sleep(void) static int khugepaged_node_load[MAX_NUMNODES]; +static bool khugepaged_scan_abort(int nid) +{ + int i; + + /* + * If zone_reclaim_mode is disabled, then no extra effort is made to + * allocate memory locally. + */ + if (!zone_reclaim_mode) + return false; + + /* If there is a count for this node already, it must be acceptable */ + if (khugepaged_node_load[nid]) + return false; + + for (i = 0; i < MAX_NUMNODES; i++) { + if (!khugepaged_node_load[i]) + continue; + if (node_distance(nid, i) > RECLAIM_DISTANCE) + return true; + } + return false; +} + #ifdef CONFIG_NUMA static int khugepaged_find_target_node(void) { @@ -2586,6 +2613,8 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, * hit record. */ node = page_to_nid(page); + if (khugepaged_scan_abort(node)) + goto out_unmap; khugepaged_node_load[node]++; VM_BUG_ON_PAGE(PageCompound(page), page); if (!PageLRU(page) || PageLocked(page) || !PageAnon(page)) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 923f38e62bcf..c3e8660cb616 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -540,7 +540,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, goto err; retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); zonelist = huge_zonelist(vma, address, htlb_alloc_mask(h), &mpol, &nodemask); @@ -562,7 +562,7 @@ retry_cpuset: } mpol_cond_put(mpol); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; @@ -2071,6 +2071,9 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy, unsigned long tmp; int ret; + if (!hugepages_supported()) + return -ENOTSUPP; + tmp = h->max_huge_pages; if (write && h->order >= MAX_ORDER) @@ -2124,6 +2127,9 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, unsigned long tmp; int ret; + if (!hugepages_supported()) + return -ENOTSUPP; + tmp = h->nr_overcommit_huge_pages; if (write && h->order >= MAX_ORDER) @@ -2149,6 +2155,8 @@ out: void hugetlb_report_meminfo(struct seq_file *m) { struct hstate *h = &default_hstate; + if (!hugepages_supported()) + return; seq_printf(m, "HugePages_Total: %5lu\n" "HugePages_Free: %5lu\n" @@ -2165,6 +2173,8 @@ void hugetlb_report_meminfo(struct seq_file *m) int hugetlb_report_node_meminfo(int nid, char *buf) { struct hstate *h = &default_hstate; + if (!hugepages_supported()) + return 0; return sprintf(buf, "Node %d HugePages_Total: %5u\n" "Node %d HugePages_Free: %5u\n" @@ -2179,6 +2189,9 @@ void hugetlb_show_meminfo(void) struct hstate *h; int nid; + if (!hugepages_supported()) + return; + for_each_node_state(nid, N_MEMORY) for_each_hstate(h) pr_info("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n", @@ -2475,9 +2488,10 @@ again: goto unlock; /* - * HWPoisoned hugepage is already unmapped and dropped reference + * Migrating hugepage or HWPoisoned hugepage is already + * unmapped and its refcount is dropped, so just clear pte here. */ - if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) { + if (unlikely(!pte_present(pte))) { huge_pte_clear(mm, address, ptep); goto unlock; } @@ -3150,7 +3164,26 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, spin_unlock(ptl); continue; } - if (!huge_pte_none(huge_ptep_get(ptep))) { + pte = huge_ptep_get(ptep); + if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) { + spin_unlock(ptl); + continue; + } + if (unlikely(is_hugetlb_entry_migration(pte))) { + swp_entry_t entry = pte_to_swp_entry(pte); + + if (is_write_migration_entry(entry)) { + pte_t newpte; + + make_migration_entry_read(&entry); + newpte = swp_entry_to_pte(entry); + set_huge_pte_at(mm, address, ptep, newpte); + pages++; + } + spin_unlock(ptl); + continue; + } + if (!huge_pte_none(pte)) { pte = huge_ptep_get_and_clear(mm, address, ptep); pte = pte_mkhuge(huge_pte_modify(pte, newprot)); pte = arch_make_huge_pte(pte, vma, NULL, 0); @@ -3443,6 +3476,8 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, { struct page *page; + if (!pmd_present(*pmd)) + return NULL; page = pte_page(*(pte_t *)pmd); if (page) page += ((address & ~PMD_MASK) >> PAGE_SHIFT); diff --git a/mm/internal.h b/mm/internal.h index 3e910000fda4..1a8a0d4b687a 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -11,6 +11,7 @@ #ifndef __MM_INTERNAL_H #define __MM_INTERNAL_H +#include <linux/fs.h> #include <linux/mm.h> void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, @@ -21,6 +22,20 @@ static inline void set_page_count(struct page *page, int v) atomic_set(&page->_count, v); } +extern int __do_page_cache_readahead(struct address_space *mapping, + struct file *filp, pgoff_t offset, unsigned long nr_to_read, + unsigned long lookahead_size); + +/* + * Submit IO for the read-ahead request in file_ra_state. + */ +static inline unsigned long ra_submit(struct file_ra_state *ra, + struct address_space *mapping, struct file *filp) +{ + return __do_page_cache_readahead(mapping, filp, + ra->start, ra->size, ra->async_size); +} + /* * Turn a non-refcounted page (->_count == 0) into refcounted with * a count of one. @@ -119,7 +134,7 @@ struct compact_control { unsigned long nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ unsigned long migrate_pfn; /* isolate_migratepages search base */ - bool sync; /* Synchronous migration */ + enum migrate_mode mode; /* Async or sync migration mode */ bool ignore_skip_hint; /* Scan blocks even if marked skip */ bool finished_update_free; /* True when the zone cached pfns are * no longer being updated @@ -129,7 +144,10 @@ struct compact_control { int order; /* order a direct compactor needs */ int migratetype; /* MOVABLE, RECLAIMABLE etc */ struct zone *zone; - bool contended; /* True if a lock was contended */ + bool contended; /* True if a lock was contended, or + * need_resched() true during async + * compaction + */ }; unsigned long diff --git a/mm/madvise.c b/mm/madvise.c index 539eeb96b323..a402f8fdc68e 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -195,7 +195,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma, for (; start < end; start += PAGE_SIZE) { index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; - page = find_get_page(mapping, index); + page = find_get_entry(mapping, index); if (!radix_tree_exceptional_entry(page)) { if (page) page_cache_release(page); diff --git a/mm/memblock.c b/mm/memblock.c index 39a31e7f0045..0739dc1b4095 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -183,8 +183,7 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, int nid) { - int ret; - phys_addr_t kernel_end; + phys_addr_t kernel_end, ret; /* pump up @end */ if (end == MEMBLOCK_ALLOC_ACCESSIBLE) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9b35da28b587..b58d4fbe6c48 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -292,6 +292,9 @@ struct mem_cgroup { /* vmpressure notifications */ struct vmpressure vmpressure; + /* css_online() has been completed */ + int initialized; + /* * the counter to account for mem+swap usage. */ @@ -1127,9 +1130,21 @@ skip_node: * skipping css reference should be safe. */ if (next_css) { - if ((next_css == &root->css) || - ((next_css->flags & CSS_ONLINE) && css_tryget(next_css))) - return mem_cgroup_from_css(next_css); + struct mem_cgroup *memcg = mem_cgroup_from_css(next_css); + + if (next_css == &root->css) + return memcg; + + if (css_tryget(next_css)) { + /* + * Make sure the memcg is initialized: + * mem_cgroup_css_online() orders the the + * initialization against setting the flag. + */ + if (smp_load_acquire(&memcg->initialized)) + return memcg; + css_put(next_css); + } prev_css = next_css; goto skip_node; @@ -6538,6 +6553,7 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(css)); + int ret; if (css->cgroup->id > MEM_CGROUP_ID_MAX) return -ENOSPC; @@ -6574,7 +6590,18 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) } mutex_unlock(&memcg_create_mutex); - return memcg_init_kmem(memcg, &mem_cgroup_subsys); + ret = memcg_init_kmem(memcg, &mem_cgroup_subsys); + if (ret) + return ret; + + /* + * Make sure the memcg is initialized: mem_cgroup_iter() + * orders reading memcg->initialized against its callers + * reading the memcg members. + */ + smp_store_release(&memcg->initialized, 1); + + return 0; } /* diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 33365e9ce6a7..a98c7fce470a 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1540,7 +1540,7 @@ static int soft_offline_huge_page(struct page *page, int flags) /* Keep page count to indicate a given hugepage is isolated. */ list_move(&hpage->lru, &pagelist); - ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, + ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { pr_info("soft offline: %#lx: migration failed %d, type %lx\n", @@ -1621,7 +1621,7 @@ static int __soft_offline_page(struct page *page, int flags) inc_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); list_add(&page->lru, &pagelist); - ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, + ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { if (!list_empty(&pagelist)) { diff --git a/mm/memory.c b/mm/memory.c index 30976b120eae..8348bccd9323 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -810,20 +810,20 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (!pte_file(pte)) { swp_entry_t entry = pte_to_swp_entry(pte); - if (swap_duplicate(entry) < 0) - return entry.val; - - /* make sure dst_mm is on swapoff's mmlist. */ - if (unlikely(list_empty(&dst_mm->mmlist))) { - spin_lock(&mmlist_lock); - if (list_empty(&dst_mm->mmlist)) - list_add(&dst_mm->mmlist, - &src_mm->mmlist); - spin_unlock(&mmlist_lock); - } - if (likely(!non_swap_entry(entry))) + if (likely(!non_swap_entry(entry))) { + if (swap_duplicate(entry) < 0) + return entry.val; + + /* make sure dst_mm is on swapoff's mmlist. */ + if (unlikely(list_empty(&dst_mm->mmlist))) { + spin_lock(&mmlist_lock); + if (list_empty(&dst_mm->mmlist)) + list_add(&dst_mm->mmlist, + &src_mm->mmlist); + spin_unlock(&mmlist_lock); + } rss[MM_SWAPENTS]++; - else if (is_migration_entry(entry)) { + } else if (is_migration_entry(entry)) { page = migration_entry_to_page(entry); if (PageAnon(page)) @@ -880,7 +880,7 @@ out_set_pte: return 0; } -int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, +static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma, unsigned long addr, unsigned long end) { @@ -1122,7 +1122,7 @@ again: addr) != page->index) { pte_t ptfile = pgoff_to_pte(page->index); if (pte_soft_dirty(ptent)) - pte_file_mksoft_dirty(ptfile); + ptfile = pte_file_mksoft_dirty(ptfile); set_pte_at(mm, addr, pte, ptfile); } if (PageAnon(page)) @@ -3206,7 +3206,7 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo if (prev && prev->vm_end == address) return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM; - expand_downwards(vma, address - PAGE_SIZE); + return expand_downwards(vma, address - PAGE_SIZE); } if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) { struct vm_area_struct *next = vma->vm_next; @@ -3215,7 +3215,7 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo if (next && next->vm_start == address + PAGE_SIZE) return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM; - expand_upwards(vma, address + PAGE_SIZE); + return expand_upwards(vma, address + PAGE_SIZE); } return 0; } @@ -3648,7 +3648,7 @@ static int handle_pte_fault(struct mm_struct *mm, pte_t entry; spinlock_t *ptl; - entry = *pte; + entry = ACCESS_ONCE(*pte); if (!pte_present(entry)) { if (pte_none(entry)) { if (vma->vm_ops) { @@ -4026,7 +4026,7 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, if (follow_phys(vma, addr, write, &prot, &phys_addr)) return -EINVAL; - maddr = ioremap_prot(phys_addr, PAGE_SIZE, prot); + maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot); if (write) memcpy_toio(maddr + offset, buf, len); else diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index a650db29606f..c8e450132813 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1016,6 +1016,10 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) return NULL; arch_refresh_nodedata(nid, pgdat); + } else { + /* Reset the nr_zones and classzone_idx to 0 before reuse */ + pgdat->nr_zones = 0; + pgdat->classzone_idx = 0; } /* we can use NODE_DATA(nid) from here */ @@ -1332,7 +1336,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) * alloc_migrate_target should be improooooved!! * migrate_pages returns # of failed pages. */ - ret = migrate_pages(&source, alloc_migrate_target, 0, + ret = migrate_pages(&source, alloc_migrate_target, NULL, 0, MIGRATE_SYNC, MR_MEMORY_HOTPLUG); if (ret) putback_movable_pages(&source); @@ -1863,15 +1867,6 @@ void try_offline_node(int nid) if (is_vmalloc_addr(zone->wait_table)) vfree(zone->wait_table); } - - /* - * Since there is no way to guarentee the address of pgdat/zone is not - * on stack of any kernel threads or used by other kernel objects - * without reference counting or other symchronizing method, do not - * reset node_data and free pgdat here. Just reset it to 0 and reuse - * the memory when the node is online again. - */ - memset(pgdat, 0, sizeof(*pgdat)); } EXPORT_SYMBOL(try_offline_node); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 15a8ea031526..e8fff0fa1202 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1060,7 +1060,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, flags | MPOL_MF_DISCONTIG_OK, &pagelist); if (!list_empty(&pagelist)) { - err = migrate_pages(&pagelist, new_node_page, dest, + err = migrate_pages(&pagelist, new_node_page, NULL, dest, MIGRATE_SYNC, MR_SYSCALL); if (err) putback_movable_pages(&pagelist); @@ -1306,7 +1306,7 @@ static long do_mbind(unsigned long start, unsigned long len, if (!list_empty(&pagelist)) { WARN_ON_ONCE(flags & MPOL_MF_LAZY); - nr_failed = migrate_pages(&pagelist, new_page, + nr_failed = migrate_pages(&pagelist, new_page, NULL, start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND); if (nr_failed) putback_movable_pages(&pagelist); @@ -1897,7 +1897,7 @@ int node_random(const nodemask_t *maskp) * If the effective policy is 'BIND, returns a pointer to the mempolicy's * @nodemask for filtering the zonelist. * - * Must be protected by get_mems_allowed() + * Must be protected by read_mems_allowed_begin() */ struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, @@ -2061,7 +2061,7 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, retry_cpuset: pol = get_vma_policy(current, vma, addr); - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); if (unlikely(pol->mode == MPOL_INTERLEAVE)) { unsigned nid; @@ -2069,7 +2069,7 @@ retry_cpuset: nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); mpol_cond_put(pol); page = alloc_page_interleave(gfp, order, nid); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; @@ -2079,7 +2079,7 @@ retry_cpuset: policy_nodemask(gfp, pol)); if (unlikely(mpol_needs_cond_ref(pol))) __mpol_put(pol); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; } @@ -2113,7 +2113,7 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order) pol = &default_policy; retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); /* * No reference counting needed for current->mempolicy @@ -2126,7 +2126,7 @@ retry_cpuset: policy_zonelist(gfp, pol, numa_node_id()), policy_nodemask(gfp, pol)); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; diff --git a/mm/migrate.c b/mm/migrate.c index bed48809e5d0..3acac4a62c4b 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -148,8 +148,11 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, pte = pte_mkold(mk_pte(new, vma->vm_page_prot)); if (pte_swp_soft_dirty(*ptep)) pte = pte_mksoft_dirty(pte); + + /* Recheck VMA as permissions can change since migration started */ if (is_write_migration_entry(entry)) - pte = pte_mkwrite(pte); + pte = maybe_mkwrite(pte, vma); + #ifdef CONFIG_HUGETLB_PAGE if (PageHuge(new)) { pte = pte_mkhuge(pte); @@ -938,8 +941,9 @@ out: * Obtain the lock on page, remove all ptes and migrate the page * to the newly allocated page in newpage. */ -static int unmap_and_move(new_page_t get_new_page, unsigned long private, - struct page *page, int force, enum migrate_mode mode) +static int unmap_and_move(new_page_t get_new_page, free_page_t put_new_page, + unsigned long private, struct page *page, int force, + enum migrate_mode mode) { int rc = 0; int *result = NULL; @@ -983,11 +987,18 @@ out: page_is_file_cache(page)); putback_lru_page(page); } + /* - * Move the new page to the LRU. If migration was not successful - * then this will free the page. + * If migration was not successful and there's a freeing callback, use + * it. Otherwise, putback_lru_page() will drop the reference grabbed + * during isolation. */ - putback_lru_page(newpage); + if (rc != MIGRATEPAGE_SUCCESS && put_new_page) { + ClearPageSwapBacked(newpage); + put_new_page(newpage, private); + } else + putback_lru_page(newpage); + if (result) { if (rc) *result = rc; @@ -1016,8 +1027,9 @@ out: * will wait in the page fault for migration to complete. */ static int unmap_and_move_huge_page(new_page_t get_new_page, - unsigned long private, struct page *hpage, - int force, enum migrate_mode mode) + free_page_t put_new_page, unsigned long private, + struct page *hpage, int force, + enum migrate_mode mode) { int rc = 0; int *result = NULL; @@ -1056,20 +1068,30 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, if (!page_mapped(hpage)) rc = move_to_new_page(new_hpage, hpage, 1, mode); - if (rc) + if (rc != MIGRATEPAGE_SUCCESS) remove_migration_ptes(hpage, hpage); if (anon_vma) put_anon_vma(anon_vma); - if (!rc) + if (rc == MIGRATEPAGE_SUCCESS) hugetlb_cgroup_migrate(hpage, new_hpage); unlock_page(hpage); out: if (rc != -EAGAIN) putback_active_hugepage(hpage); - put_page(new_hpage); + + /* + * If migration was not successful and there's a freeing callback, use + * it. Otherwise, put_page() will drop the reference grabbed during + * isolation. + */ + if (rc != MIGRATEPAGE_SUCCESS && put_new_page) + put_new_page(new_hpage, private); + else + put_page(new_hpage); + if (result) { if (rc) *result = rc; @@ -1086,6 +1108,8 @@ out: * @from: The list of pages to be migrated. * @get_new_page: The function used to allocate free pages to be used * as the target of the page migration. + * @put_new_page: The function used to free target pages if migration + * fails, or NULL if no special handling is necessary. * @private: Private data to be passed on to get_new_page() * @mode: The migration mode that specifies the constraints for * page migration, if any. @@ -1099,7 +1123,8 @@ out: * Returns the number of pages that were not migrated, or an error code. */ int migrate_pages(struct list_head *from, new_page_t get_new_page, - unsigned long private, enum migrate_mode mode, int reason) + free_page_t put_new_page, unsigned long private, + enum migrate_mode mode, int reason) { int retry = 1; int nr_failed = 0; @@ -1121,10 +1146,11 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page, if (PageHuge(page)) rc = unmap_and_move_huge_page(get_new_page, - private, page, pass > 2, mode); + put_new_page, private, page, + pass > 2, mode); else - rc = unmap_and_move(get_new_page, private, - page, pass > 2, mode); + rc = unmap_and_move(get_new_page, put_new_page, + private, page, pass > 2, mode); switch(rc) { case -ENOMEM: @@ -1273,7 +1299,7 @@ set_status: err = 0; if (!list_empty(&pagelist)) { - err = migrate_pages(&pagelist, new_page_node, + err = migrate_pages(&pagelist, new_page_node, NULL, (unsigned long)pm, MIGRATE_SYNC, MR_SYSCALL); if (err) putback_movable_pages(&pagelist); @@ -1729,7 +1755,8 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, list_add(&page->lru, &migratepages); nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page, - node, MIGRATE_ASYNC, MR_NUMA_MISPLACED); + NULL, node, MIGRATE_ASYNC, + MR_NUMA_MISPLACED); if (nr_remaining) { if (!list_empty(&migratepages)) { list_del(&page->lru); diff --git a/mm/mincore.c b/mm/mincore.c index 101623378fbf..725c80961048 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -70,13 +70,21 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff) * any other file mapping (ie. marked !present and faulted in with * tmpfs's .fault). So swapped out tmpfs mappings are tested here. */ - page = find_get_page(mapping, pgoff); #ifdef CONFIG_SWAP - /* shmem/tmpfs may return swap: account for swapcache page too. */ - if (radix_tree_exceptional_entry(page)) { - swp_entry_t swap = radix_to_swp_entry(page); - page = find_get_page(swap_address_space(swap), swap.val); - } + if (shmem_mapping(mapping)) { + page = find_get_entry(mapping, pgoff); + /* + * shmem/tmpfs may return swap: account for swapcache + * page too. + */ + if (radix_tree_exceptional_entry(page)) { + swp_entry_t swp = radix_to_swp_entry(page); + page = find_get_page(swap_address_space(swp), swp.val); + } + } else + page = find_get_page(mapping, pgoff); +#else + page = find_get_page(mapping, pgoff); #endif if (page) { present = PageUptodate(page); diff --git a/mm/mmap.c b/mm/mmap.c index 20ff0c33274c..d4c97ba6843b 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -10,6 +10,7 @@ #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/shm.h> #include <linux/mman.h> #include <linux/pagemap.h> @@ -128,7 +129,7 @@ EXPORT_SYMBOL_GPL(vm_memory_committed); */ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) { - unsigned long free, allowed, reserve; + long free, allowed, reserve; vm_acct_memory(pages); @@ -192,7 +193,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) */ if (mm) { reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10); - allowed -= min(mm->total_vm / 32, reserve); + allowed -= min_t(long, mm->total_vm / 32, reserve); } if (percpu_counter_read_positive(&vm_committed_as) < allowed) @@ -681,8 +682,9 @@ __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma, prev->vm_next = next = vma->vm_next; if (next) next->vm_prev = prev; - if (mm->mmap_cache == vma) - mm->mmap_cache = prev; + + /* Kill the cache */ + vmacache_invalidate(mm); } /* @@ -743,8 +745,11 @@ again: remove_next = 1 + (end > next->vm_end); * shrinking vma had, to cover any anon pages imported. */ if (exporter && exporter->anon_vma && !importer->anon_vma) { - if (anon_vma_clone(importer, exporter)) - return -ENOMEM; + int error; + + error = anon_vma_clone(importer, exporter); + if (error) + return error; importer->anon_vma = exporter->anon_vma; } } @@ -1989,34 +1994,33 @@ EXPORT_SYMBOL(get_unmapped_area); /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) { - struct vm_area_struct *vma = NULL; + struct rb_node *rb_node; + struct vm_area_struct *vma; /* Check the cache first. */ - /* (Cache hit rate is typically around 35%.) */ - vma = ACCESS_ONCE(mm->mmap_cache); - if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) { - struct rb_node *rb_node; + vma = vmacache_find(mm, addr); + if (likely(vma)) + return vma; - rb_node = mm->mm_rb.rb_node; - vma = NULL; + rb_node = mm->mm_rb.rb_node; + vma = NULL; - while (rb_node) { - struct vm_area_struct *vma_tmp; - - vma_tmp = rb_entry(rb_node, - struct vm_area_struct, vm_rb); - - if (vma_tmp->vm_end > addr) { - vma = vma_tmp; - if (vma_tmp->vm_start <= addr) - break; - rb_node = rb_node->rb_left; - } else - rb_node = rb_node->rb_right; - } - if (vma) - mm->mmap_cache = vma; + while (rb_node) { + struct vm_area_struct *tmp; + + tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb); + + if (tmp->vm_end > addr) { + vma = tmp; + if (tmp->vm_start <= addr) + break; + rb_node = rb_node->rb_left; + } else + rb_node = rb_node->rb_right; } + + if (vma) + vmacache_update(addr, vma); return vma; } @@ -2054,14 +2058,17 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns { struct mm_struct *mm = vma->vm_mm; struct rlimit *rlim = current->signal->rlim; - unsigned long new_start; + unsigned long new_start, actual_size; /* address space limit tests */ if (!may_expand_vm(mm, grow)) return -ENOMEM; /* Stack limit test */ - if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur)) + actual_size = size; + if (size && (vma->vm_flags & (VM_GROWSUP | VM_GROWSDOWN))) + actual_size -= PAGE_SIZE; + if (actual_size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur)) return -ENOMEM; /* mlock limit tests */ @@ -2388,7 +2395,9 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, } else mm->highest_vm_end = prev ? prev->vm_end : 0; tail_vma->vm_next = NULL; - mm->mmap_cache = NULL; /* Kill the cache. */ + + /* Kill the cache */ + vmacache_invalidate(mm); } /* @@ -2425,7 +2434,8 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, if (err) goto out_free_vma; - if (anon_vma_clone(new, vma)) + err = anon_vma_clone(new, vma); + if (err) goto out_free_mpol; if (new->vm_file) diff --git a/mm/nommu.c b/mm/nommu.c index 8740213b1647..76b3f90ada7b 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -15,6 +15,7 @@ #include <linux/export.h> #include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/mman.h> #include <linux/swap.h> #include <linux/file.h> @@ -768,16 +769,23 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma) */ static void delete_vma_from_mm(struct vm_area_struct *vma) { + int i; struct address_space *mapping; struct mm_struct *mm = vma->vm_mm; + struct task_struct *curr = current; kenter("%p", vma); protect_vma(vma, 0); mm->map_count--; - if (mm->mmap_cache == vma) - mm->mmap_cache = NULL; + for (i = 0; i < VMACACHE_SIZE; i++) { + /* if the vma is cached, invalidate the entire cache */ + if (curr->vmacache[i] == vma) { + vmacache_invalidate(curr->mm); + break; + } + } /* remove the VMA from the mapping */ if (vma->vm_file) { @@ -825,8 +833,8 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) struct vm_area_struct *vma; /* check the cache first */ - vma = ACCESS_ONCE(mm->mmap_cache); - if (vma && vma->vm_start <= addr && vma->vm_end > addr) + vma = vmacache_find(mm, addr); + if (likely(vma)) return vma; /* trawl the list (there may be multiple mappings in which addr @@ -835,7 +843,7 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) if (vma->vm_start > addr) return NULL; if (vma->vm_end > addr) { - mm->mmap_cache = vma; + vmacache_update(addr, vma); return vma; } } @@ -874,8 +882,8 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm, unsigned long end = addr + len; /* check the cache first */ - vma = mm->mmap_cache; - if (vma && vma->vm_start == addr && vma->vm_end == end) + vma = vmacache_find_exact(mm, addr, end); + if (vma) return vma; /* trawl the list (there may be multiple mappings in which addr @@ -886,7 +894,7 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm, if (vma->vm_start > addr) return NULL; if (vma->vm_end == end) { - mm->mmap_cache = vma; + vmacache_update(addr, vma); return vma; } } @@ -1897,7 +1905,7 @@ EXPORT_SYMBOL(unmap_mapping_range); */ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) { - unsigned long free, allowed, reserve; + long free, allowed, reserve; vm_acct_memory(pages); @@ -1961,7 +1969,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) */ if (mm) { reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10); - allowed -= min(mm->total_vm / 32, reserve); + allowed -= min_t(long, mm->total_vm / 32, reserve); } if (percpu_counter_read_positive(&vm_committed_as) < allowed) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 3291e82d4352..171c00f2e495 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -406,6 +406,23 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, dump_tasks(memcg, nodemask); } +/* + * Number of OOM killer invocations (including memcg OOM killer). + * Primarily used by PM freezer to check for potential races with + * OOM killed frozen task. + */ +static atomic_t oom_kills = ATOMIC_INIT(0); + +int oom_kills_count(void) +{ + return atomic_read(&oom_kills); +} + +void note_oom_kill(void) +{ + atomic_inc(&oom_kills); +} + #define K(x) ((x) << (PAGE_SHIFT-10)) /* * Must be called while holding a reference to p, which will be released upon diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 9f45f87a5859..51d8d15f48d7 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -878,8 +878,11 @@ static void bdi_update_write_bandwidth(struct backing_dev_info *bdi, * bw * elapsed + write_bandwidth * (period - elapsed) * write_bandwidth = --------------------------------------------------- * period + * + * @written may have decreased due to account_page_redirty(). + * Avoid underflowing @bw calculation. */ - bw = written - bdi->written_stamp; + bw = written - min(written, bdi->written_stamp); bw *= HZ; if (unlikely(elapsed > period)) { do_div(bw, elapsed); @@ -943,7 +946,7 @@ static void global_update_bandwidth(unsigned long thresh, unsigned long now) { static DEFINE_SPINLOCK(dirty_lock); - static unsigned long update_time; + static unsigned long update_time = INITIAL_JIFFIES; /* * check locklessly first to optimize away locking for the most time diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 62e400d00e3f..0479732f6b02 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -408,7 +408,8 @@ static int destroy_compound_page(struct page *page, unsigned long order) return bad; } -static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags) +static inline void prep_zero_page(struct page *page, unsigned int order, + gfp_t gfp_flags) { int i; @@ -452,7 +453,7 @@ static inline void set_page_guard_flag(struct page *page) { } static inline void clear_page_guard_flag(struct page *page) { } #endif -static inline void set_page_order(struct page *page, int order) +static inline void set_page_order(struct page *page, unsigned int order) { set_page_private(page, order); __SetPageBuddy(page); @@ -503,21 +504,31 @@ __find_buddy_index(unsigned long page_idx, unsigned int order) * For recording page's order, we use page_private(page). */ static inline int page_is_buddy(struct page *page, struct page *buddy, - int order) + unsigned int order) { if (!pfn_valid_within(page_to_pfn(buddy))) return 0; - if (page_zone_id(page) != page_zone_id(buddy)) - return 0; - if (page_is_guard(buddy) && page_order(buddy) == order) { VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); + + if (page_zone_id(page) != page_zone_id(buddy)) + return 0; + return 1; } if (PageBuddy(buddy) && page_order(buddy) == order) { VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); + + /* + * zone check is done late to avoid uselessly + * calculating zone/node ids for pages that could + * never merge. + */ + if (page_zone_id(page) != page_zone_id(buddy)) + return 0; + return 1; } return 0; @@ -549,6 +560,7 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, */ static inline void __free_one_page(struct page *page, + unsigned long pfn, struct zone *zone, unsigned int order, int migratetype) { @@ -565,7 +577,7 @@ static inline void __free_one_page(struct page *page, VM_BUG_ON(migratetype == -1); - page_idx = page_to_pfn(page) & ((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); @@ -666,9 +678,12 @@ static void free_pcppages_bulk(struct zone *zone, int count, int migratetype = 0; int batch_free = 0; int to_free = count; + unsigned long nr_scanned; spin_lock(&zone->lock); - zone->pages_scanned = 0; + nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED); + if (nr_scanned) + __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned); while (to_free) { struct page *page; @@ -700,7 +715,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, list_del(&page->lru); mt = get_freepage_migratetype(page); /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ - __free_one_page(page, zone, 0, mt); + __free_one_page(page, page_to_pfn(page), zone, 0, mt); trace_mm_page_pcpu_drain(page, 0, mt); if (likely(!is_migrate_isolate_page(page))) { __mod_zone_page_state(zone, NR_FREE_PAGES, 1); @@ -712,13 +727,18 @@ static void free_pcppages_bulk(struct zone *zone, int count, spin_unlock(&zone->lock); } -static void free_one_page(struct zone *zone, struct page *page, int order, +static void free_one_page(struct zone *zone, + struct page *page, unsigned long pfn, + unsigned int order, int migratetype) { + unsigned long nr_scanned; spin_lock(&zone->lock); - zone->pages_scanned = 0; + nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED); + if (nr_scanned) + __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned); - __free_one_page(page, zone, order, migratetype); + __free_one_page(page, pfn, zone, order, migratetype); if (unlikely(!is_migrate_isolate(migratetype))) __mod_zone_freepage_state(zone, 1 << order, migratetype); spin_unlock(&zone->lock); @@ -755,15 +775,16 @@ static void __free_pages_ok(struct page *page, unsigned int order) { unsigned long flags; int migratetype; + unsigned long pfn = page_to_pfn(page); if (!free_pages_prepare(page, order)) return; + migratetype = get_pfnblock_migratetype(page, pfn); local_irq_save(flags); __count_vm_events(PGFREE, 1 << order); - migratetype = get_pageblock_migratetype(page); set_freepage_migratetype(page, migratetype); - free_one_page(page_zone(page), page, order, migratetype); + free_one_page(page_zone(page), page, pfn, order, migratetype); local_irq_restore(flags); } @@ -894,7 +915,7 @@ static inline int check_new_page(struct page *page) return 0; } -static int prep_new_page(struct page *page, int order, gfp_t gfp_flags) +static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags) { int i; @@ -943,6 +964,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, rmv_page_order(page); area->nr_free--; expand(zone, page, order, current_order, area, migratetype); + set_freepage_migratetype(page, migratetype); return page; } @@ -1059,8 +1081,8 @@ static void change_pageblock_range(struct page *pageblock_page, * nor move CMA pages to different free lists. We don't want unmovable pages * to be allocated from MIGRATE_CMA areas. * - * Returns the new migratetype of the pageblock (or the same old migratetype - * if it was unchanged). + * Returns the allocation migratetype if free pages were stolen, or the + * fallback migratetype if it was decided not to steal. */ static int try_to_steal_freepages(struct zone *zone, struct page *page, int start_type, int fallback_type) @@ -1069,7 +1091,9 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page, /* * When borrowing from MIGRATE_CMA, we need to release the excess - * buddy pages to CMA itself. + * buddy pages to CMA itself. We also ensure the freepage_migratetype + * is set to CMA so it is returned to the correct freelist in case + * the page ends up being not actually allocated from the pcp lists. */ if (is_migrate_cma(fallback_type)) return fallback_type; @@ -1089,12 +1113,10 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page, /* Claim the whole block if over half of it is free */ if (pages >= (1 << (pageblock_order-1)) || - page_group_by_mobility_disabled) { - + page_group_by_mobility_disabled) set_pageblock_migratetype(page, start_type); - return start_type; - } + return start_type; } return fallback_type; @@ -1102,16 +1124,17 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page, /* Remove an element from the buddy allocator from the fallback list */ static inline struct page * -__rmqueue_fallback(struct zone *zone, int order, int start_migratetype) +__rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype) { struct free_area *area; - int current_order; + unsigned int current_order; struct page *page; int migratetype, new_type, i; /* Find the largest possible block of pages in the other list */ - for (current_order = MAX_ORDER-1; current_order >= order; - --current_order) { + for (current_order = MAX_ORDER-1; + current_order >= order && current_order <= MAX_ORDER-1; + --current_order) { for (i = 0;; i++) { migratetype = fallbacks[start_migratetype][i]; @@ -1137,9 +1160,15 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype) expand(zone, page, order, current_order, area, new_type); + /* The freepage_migratetype may differ from pageblock's + * migratetype depending on the decisions in + * try_to_steal_freepages. This is OK as long as it does + * not differ for MIGRATE_CMA type. + */ + set_freepage_migratetype(page, new_type); trace_mm_page_alloc_extfrag(page, order, current_order, - start_migratetype, migratetype, new_type); + start_migratetype, migratetype); return page; } @@ -1185,9 +1214,9 @@ retry_reserve: */ static int rmqueue_bulk(struct zone *zone, unsigned int order, unsigned long count, struct list_head *list, - int migratetype, int cold) + int migratetype, bool cold) { - int mt = migratetype, i; + int i; spin_lock(&zone->lock); for (i = 0; i < count; ++i) { @@ -1204,18 +1233,12 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, * merge IO requests if the physical pages are ordered * properly. */ - if (likely(cold == 0)) + if (likely(!cold)) list_add(&page->lru, list); else list_add_tail(&page->lru, list); - if (IS_ENABLED(CONFIG_CMA)) { - mt = get_pageblock_migratetype(page); - if (!is_migrate_cma(mt) && !is_migrate_isolate(mt)) - mt = migratetype; - } - set_freepage_migratetype(page, mt); list = &page->lru; - if (is_migrate_cma(mt)) + if (is_migrate_cma(get_freepage_migratetype(page))) __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, -(1 << order)); } @@ -1339,7 +1362,7 @@ void mark_free_pages(struct zone *zone) { unsigned long pfn, max_zone_pfn; unsigned long flags; - int order, t; + unsigned int order, t; struct list_head *curr; if (zone_is_empty(zone)) @@ -1371,19 +1394,20 @@ void mark_free_pages(struct zone *zone) /* * Free a 0-order page - * cold == 1 ? free a cold page : free a hot page + * cold == true ? free a cold page : free a hot page */ -void free_hot_cold_page(struct page *page, int cold) +void free_hot_cold_page(struct page *page, bool cold) { struct zone *zone = page_zone(page); struct per_cpu_pages *pcp; unsigned long flags; + unsigned long pfn = page_to_pfn(page); int migratetype; if (!free_pages_prepare(page, 0)) return; - migratetype = get_pageblock_migratetype(page); + migratetype = get_pfnblock_migratetype(page, pfn); set_freepage_migratetype(page, migratetype); local_irq_save(flags); __count_vm_event(PGFREE); @@ -1397,17 +1421,17 @@ void free_hot_cold_page(struct page *page, int cold) */ if (migratetype >= MIGRATE_PCPTYPES) { if (unlikely(is_migrate_isolate(migratetype))) { - free_one_page(zone, page, 0, migratetype); + free_one_page(zone, page, pfn, 0, migratetype); goto out; } migratetype = MIGRATE_MOVABLE; } pcp = &this_cpu_ptr(zone->pageset)->pcp; - if (cold) - list_add_tail(&page->lru, &pcp->lists[migratetype]); - else + if (!cold) list_add(&page->lru, &pcp->lists[migratetype]); + else + list_add_tail(&page->lru, &pcp->lists[migratetype]); pcp->count++; if (pcp->count >= pcp->high) { unsigned long batch = ACCESS_ONCE(pcp->batch); @@ -1422,7 +1446,7 @@ out: /* * Free a list of 0-order pages */ -void free_hot_cold_page_list(struct list_head *list, int cold) +void free_hot_cold_page_list(struct list_head *list, bool cold) { struct page *page, *next; @@ -1534,12 +1558,12 @@ int split_free_page(struct page *page) */ static inline struct page *buffered_rmqueue(struct zone *preferred_zone, - struct zone *zone, int order, gfp_t gfp_flags, - int migratetype) + struct zone *zone, unsigned int order, + gfp_t gfp_flags, int migratetype) { unsigned long flags; struct page *page; - int cold = !!(gfp_flags & __GFP_COLD); + bool cold = ((gfp_flags & __GFP_COLD) != 0); again: if (likely(order == 0)) { @@ -1584,10 +1608,13 @@ again: if (!page) goto failed; __mod_zone_freepage_state(zone, -(1 << order), - get_pageblock_migratetype(page)); + get_freepage_migratetype(page)); } __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); + if (zone_page_state(zone, NR_ALLOC_BATCH) == 0 && + !zone_is_fair_depleted(zone)) + zone_set_flag(zone, ZONE_FAIR_DEPLETED); __count_zone_vm_events(PGALLOC, zone, 1 << order); zone_statistics(preferred_zone, zone, gfp_flags); @@ -1684,12 +1711,12 @@ static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) * Return true if free pages are above 'mark'. This takes into account the order * of the allocation. */ -static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags, long free_pages) +static bool __zone_watermark_ok(struct zone *z, unsigned int order, + unsigned long mark, int classzone_idx, int alloc_flags, + long free_pages) { /* free_pages my go negative - that's OK */ long min = mark; - long lowmem_reserve = z->lowmem_reserve[classzone_idx]; int o; long free_cma = 0; @@ -1704,7 +1731,7 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, free_cma = zone_page_state(z, NR_FREE_CMA_PAGES); #endif - if (free_pages - free_cma <= min + lowmem_reserve) + if (free_pages - free_cma <= min + z->lowmem_reserve[classzone_idx]) return false; for (o = 0; o < order; o++) { /* At the next order, this order's pages become unavailable */ @@ -1719,15 +1746,15 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, return true; } -bool zone_watermark_ok(struct zone *z, int order, unsigned long mark, +bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int classzone_idx, int alloc_flags) { return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, zone_page_state(z, NR_FREE_PAGES)); } -bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags) +bool zone_watermark_ok_safe(struct zone *z, unsigned int order, + unsigned long mark, int classzone_idx, int alloc_flags) { long free_pages = zone_page_state(z, NR_FREE_PAGES); @@ -1869,7 +1896,7 @@ static void __paginginit init_zone_allows_reclaim(int nid) { int i; - for_each_online_node(i) + for_each_node_state(i, N_MEMORY) if (node_distance(nid, i) <= RECLAIM_DISTANCE) node_set(i, NODE_DATA(nid)->reclaim_nodes); else @@ -1912,6 +1939,18 @@ static inline void init_zone_allows_reclaim(int nid) } #endif /* CONFIG_NUMA */ +static void reset_alloc_batches(struct zone *preferred_zone) +{ + struct zone *zone = preferred_zone->zone_pgdat->node_zones; + + do { + mod_zone_page_state(zone, NR_ALLOC_BATCH, + high_wmark_pages(zone) - low_wmark_pages(zone) - + atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH])); + zone_clear_flag(zone, ZONE_FAIR_DEPLETED); + } while (zone++ != preferred_zone); +} + /* * get_page_from_freelist goes through the zonelist trying to allocate * a page. @@ -1919,18 +1958,22 @@ static inline void init_zone_allows_reclaim(int nid) static struct page * get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order, struct zonelist *zonelist, int high_zoneidx, int alloc_flags, - struct zone *preferred_zone, int migratetype) + struct zone *preferred_zone, int classzone_idx, int migratetype) { struct zoneref *z; struct page *page = NULL; - int classzone_idx; struct zone *zone; nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */ int zlc_active = 0; /* set if using zonelist_cache */ int did_zlc_setup = 0; /* just call zlc_setup() one time */ + bool consider_zone_dirty = (alloc_flags & ALLOC_WMARK_LOW) && + (gfp_mask & __GFP_WRITE); + int nr_fair_skipped = 0; + bool zonelist_rescan; - classzone_idx = zone_idx(preferred_zone); zonelist_scan: + zonelist_rescan = false; + /* * Scan zonelist, looking for a zone with enough free. * See also __cpuset_node_allowed_softwall() comment in kernel/cpuset.c. @@ -1942,12 +1985,10 @@ zonelist_scan: if (IS_ENABLED(CONFIG_NUMA) && zlc_active && !zlc_zone_worth_trying(zonelist, z, allowednodes)) continue; - if ((alloc_flags & ALLOC_CPUSET) && + if (cpusets_enabled() && + (alloc_flags & ALLOC_CPUSET) && !cpuset_zone_allowed_softwall(zone, gfp_mask)) continue; - BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK); - if (unlikely(alloc_flags & ALLOC_NO_WATERMARKS)) - goto try_this_zone; /* * Distribute pages in proportion to the individual * zone size to ensure fair page aging. The zone a @@ -1956,9 +1997,11 @@ zonelist_scan: */ if (alloc_flags & ALLOC_FAIR) { if (!zone_local(preferred_zone, zone)) + break; + if (zone_is_fair_depleted(zone)) { + nr_fair_skipped++; continue; - if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0) - continue; + } } /* * When allocating a page cache page for writing, we @@ -1986,15 +2029,19 @@ zonelist_scan: * will require awareness of zones in the * dirty-throttling and the flusher threads. */ - if ((alloc_flags & ALLOC_WMARK_LOW) && - (gfp_mask & __GFP_WRITE) && !zone_dirty_ok(zone)) - goto this_zone_full; + if (consider_zone_dirty && !zone_dirty_ok(zone)) + continue; mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK]; if (!zone_watermark_ok(zone, order, mark, classzone_idx, alloc_flags)) { int ret; + /* Checked here to keep the fast path fast */ + BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK); + if (alloc_flags & ALLOC_NO_WATERMARKS) + goto try_this_zone; + if (IS_ENABLED(CONFIG_NUMA) && !did_zlc_setup && nr_online_nodes > 1) { /* @@ -2056,17 +2103,11 @@ try_this_zone: if (page) break; this_zone_full: - if (IS_ENABLED(CONFIG_NUMA)) + if (IS_ENABLED(CONFIG_NUMA) && zlc_active) zlc_mark_zone_full(zonelist, z); } - if (unlikely(IS_ENABLED(CONFIG_NUMA) && page == NULL && zlc_active)) { - /* Disable zlc cache for second zonelist scan */ - zlc_active = 0; - goto zonelist_scan; - } - - if (page) + if (page) { /* * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was * necessary to allocate the page. The expectation is @@ -2075,8 +2116,37 @@ this_zone_full: * for !PFMEMALLOC purposes. */ page->pfmemalloc = !!(alloc_flags & ALLOC_NO_WATERMARKS); + return page; + } - return page; + /* + * The first pass makes sure allocations are spread fairly within the + * local node. However, the local node might have free pages left + * after the fairness batches are exhausted, and remote zones haven't + * even been considered yet. Try once more without fairness, and + * include remote zones now, before entering the slowpath and waking + * kswapd: prefer spilling to a remote zone over swapping locally. + */ + if (alloc_flags & ALLOC_FAIR) { + alloc_flags &= ~ALLOC_FAIR; + if (nr_fair_skipped) { + zonelist_rescan = true; + reset_alloc_batches(preferred_zone); + } + if (nr_online_nodes > 1) + zonelist_rescan = true; + } + + if (unlikely(IS_ENABLED(CONFIG_NUMA) && zlc_active)) { + /* Disable zlc cache for second zonelist scan */ + zlc_active = 0; + zonelist_rescan = true; + } + + if (zonelist_rescan) + goto zonelist_scan; + + return NULL; } /* @@ -2185,7 +2255,7 @@ static inline struct page * __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, struct zone *preferred_zone, - int migratetype) + int classzone_idx, int migratetype) { struct page *page; @@ -2196,6 +2266,14 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, } /* + * PM-freezer should be notified that there might be an OOM killer on + * its way to kill and wake somebody up. This is too early and we might + * end up not killing anything but false positives are acceptable. + * See freeze_processes. + */ + note_oom_kill(); + + /* * Go through the zonelist yet one more time, keep very high watermark * here, this is only to catch a parallel oom killing, we must fail if * we're still under heavy pressure. @@ -2203,7 +2281,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order, zonelist, high_zoneidx, ALLOC_WMARK_HIGH|ALLOC_CPUSET, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (page) goto out; @@ -2238,7 +2316,7 @@ static struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, bool sync_migration, + int classzone_idx, int migratetype, enum migrate_mode mode, bool *contended_compaction, bool *deferred_compaction, unsigned long *did_some_progress) { @@ -2252,7 +2330,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, current->flags |= PF_MEMALLOC; *did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask, - nodemask, sync_migration, + nodemask, mode, contended_compaction); current->flags &= ~PF_MEMALLOC; @@ -2266,7 +2344,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (page) { preferred_zone->compact_blockskip_flush = false; compaction_defer_reset(preferred_zone, order, true); @@ -2285,7 +2363,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, * As async compaction considers a subset of pageblocks, only * defer if the failure was a sync compaction failure. */ - if (sync_migration) + if (mode != MIGRATE_ASYNC) defer_compaction(preferred_zone, order); cond_resched(); @@ -2298,9 +2376,9 @@ static inline struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, bool sync_migration, - bool *contended_compaction, bool *deferred_compaction, - unsigned long *did_some_progress) + int classzone_idx, int migratetype, + enum migrate_mode mode, bool *contended_compaction, + bool *deferred_compaction, unsigned long *did_some_progress) { return NULL; } @@ -2339,7 +2417,7 @@ static inline struct page * __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, unsigned long *did_some_progress) + int classzone_idx, int migratetype, unsigned long *did_some_progress) { struct page *page = NULL; bool drained = false; @@ -2357,7 +2435,8 @@ retry: page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS, - preferred_zone, migratetype); + preferred_zone, classzone_idx, + migratetype); /* * If an allocation failed after direct reclaim, it could be because @@ -2380,14 +2459,14 @@ static inline struct page * __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, struct zone *preferred_zone, - int migratetype) + int classzone_idx, int migratetype) { struct page *page; do { page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, ALLOC_NO_WATERMARKS, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (!page && gfp_mask & __GFP_NOFAIL) wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50); @@ -2396,28 +2475,6 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, return page; } -static void reset_alloc_batches(struct zonelist *zonelist, - enum zone_type high_zoneidx, - struct zone *preferred_zone) -{ - struct zoneref *z; - struct zone *zone; - - for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { - /* - * Only reset the batches of zones that were actually - * considered in the fairness pass, we don't want to - * trash fairness information for zones that are not - * actually part of this zonelist's round-robin cycle. - */ - if (!zone_local(preferred_zone, zone)) - continue; - mod_zone_page_state(zone, NR_ALLOC_BATCH, - high_wmark_pages(zone) - low_wmark_pages(zone) - - atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH])); - } -} - static void wake_all_kswapds(unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, @@ -2488,14 +2545,14 @@ static inline struct page * __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, struct zone *preferred_zone, - int migratetype) + int classzone_idx, int migratetype) { const gfp_t wait = gfp_mask & __GFP_WAIT; struct page *page = NULL; int alloc_flags; unsigned long pages_reclaimed = 0; unsigned long did_some_progress; - bool sync_migration = false; + enum migrate_mode migration_mode = MIGRATE_ASYNC; bool deferred_compaction = false; bool contended_compaction = false; @@ -2537,15 +2594,19 @@ restart: * Find the true preferred zone if the allocation is unconstrained by * cpusets. */ - if (!(alloc_flags & ALLOC_CPUSET) && !nodemask) - first_zones_zonelist(zonelist, high_zoneidx, NULL, - &preferred_zone); + if (!(alloc_flags & ALLOC_CPUSET) && !nodemask) { + struct zoneref *preferred_zoneref; + preferred_zoneref = first_zones_zonelist(zonelist, high_zoneidx, + NULL, + &preferred_zone); + classzone_idx = zonelist_zone_idx(preferred_zoneref); + } rebalance: /* This is the last chance, in general, before the goto nopage. */ page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (page) goto got_pg; @@ -2560,7 +2621,7 @@ rebalance: page = __alloc_pages_high_priority(gfp_mask, order, zonelist, high_zoneidx, nodemask, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (page) { goto got_pg; } @@ -2589,17 +2650,16 @@ rebalance: * Try direct compaction. The first pass is asynchronous. Subsequent * attempts after direct reclaim are synchronous */ - page = __alloc_pages_direct_compact(gfp_mask, order, - zonelist, high_zoneidx, - nodemask, - alloc_flags, preferred_zone, - migratetype, sync_migration, - &contended_compaction, + page = __alloc_pages_direct_compact(gfp_mask, order, zonelist, + high_zoneidx, nodemask, alloc_flags, + preferred_zone, + classzone_idx, migratetype, + migration_mode, &contended_compaction, &deferred_compaction, &did_some_progress); if (page) goto got_pg; - sync_migration = true; + migration_mode = MIGRATE_SYNC_LIGHT; /* * If compaction is deferred for high-order allocations, it is because @@ -2616,7 +2676,8 @@ rebalance: zonelist, high_zoneidx, nodemask, alloc_flags, preferred_zone, - migratetype, &did_some_progress); + classzone_idx, migratetype, + &did_some_progress); if (page) goto got_pg; @@ -2635,7 +2696,7 @@ rebalance: page = __alloc_pages_may_oom(gfp_mask, order, zonelist, high_zoneidx, nodemask, preferred_zone, - migratetype); + classzone_idx, migratetype); if (page) goto got_pg; @@ -2674,12 +2735,11 @@ rebalance: * direct reclaim and reclaim/compaction depends on compaction * being called after reclaim so call directly if necessary */ - page = __alloc_pages_direct_compact(gfp_mask, order, - zonelist, high_zoneidx, - nodemask, - alloc_flags, preferred_zone, - migratetype, sync_migration, - &contended_compaction, + page = __alloc_pages_direct_compact(gfp_mask, order, zonelist, + high_zoneidx, nodemask, alloc_flags, + preferred_zone, + classzone_idx, migratetype, + migration_mode, &contended_compaction, &deferred_compaction, &did_some_progress); if (page) @@ -2705,11 +2765,13 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, { enum zone_type high_zoneidx = gfp_zone(gfp_mask); struct zone *preferred_zone; + struct zoneref *preferred_zoneref; struct page *page = NULL; int migratetype = allocflags_to_migratetype(gfp_mask); unsigned int cpuset_mems_cookie; int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_FAIR; struct mem_cgroup *memcg = NULL; + int classzone_idx; gfp_mask &= gfp_allowed_mask; @@ -2736,42 +2798,26 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, return NULL; retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); /* The preferred zone is used for statistics later */ - first_zones_zonelist(zonelist, high_zoneidx, + preferred_zoneref = first_zones_zonelist(zonelist, high_zoneidx, nodemask ? : &cpuset_current_mems_allowed, &preferred_zone); if (!preferred_zone) goto out; + classzone_idx = zonelist_zone_idx(preferred_zoneref); #ifdef CONFIG_CMA if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE) alloc_flags |= ALLOC_CMA; #endif -retry: /* First allocation attempt */ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order, zonelist, high_zoneidx, alloc_flags, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (unlikely(!page)) { /* - * The first pass makes sure allocations are spread - * fairly within the local node. However, the local - * node might have free pages left after the fairness - * batches are exhausted, and remote zones haven't - * even been considered yet. Try once more without - * fairness, and include remote zones now, before - * entering the slowpath and waking kswapd: prefer - * spilling to a remote zone over swapping locally. - */ - if (alloc_flags & ALLOC_FAIR) { - reset_alloc_batches(zonelist, high_zoneidx, - preferred_zone); - alloc_flags &= ~ALLOC_FAIR; - goto retry; - } - /* * Runtime PM, block IO and its error handling path * can deadlock because I/O on the device might not * complete. @@ -2779,7 +2825,7 @@ retry: gfp_mask = memalloc_noio_flags(gfp_mask); page = __alloc_pages_slowpath(gfp_mask, order, zonelist, high_zoneidx, nodemask, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); } trace_mm_page_alloc(page, order, gfp_mask, migratetype); @@ -2791,7 +2837,7 @@ out: * the mask is being updated. If a page allocation is about to fail, * check if the cpuset changed during allocation and if so, retry. */ - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; memcg_kmem_commit_charge(page, memcg, order); @@ -2830,7 +2876,7 @@ void __free_pages(struct page *page, unsigned int order) { if (put_page_testzero(page)) { if (order == 0) - free_hot_cold_page(page, 0); + free_hot_cold_page(page, false); else __free_pages_ok(page, order); } @@ -3059,9 +3105,9 @@ bool skip_free_areas_node(unsigned int flags, int nid) goto out; do { - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); ret = !node_isset(nid, cpuset_current_mems_allowed); - } while (!put_mems_allowed(cpuset_mems_cookie)); + } while (read_mems_allowed_retry(cpuset_mems_cookie)); out: return ret; } @@ -3214,12 +3260,12 @@ void show_free_areas(unsigned int filter) K(zone_page_state(zone, NR_BOUNCE)), K(zone_page_state(zone, NR_FREE_CMA_PAGES)), K(zone_page_state(zone, NR_WRITEBACK_TEMP)), - zone->pages_scanned, + K(zone_page_state(zone, NR_PAGES_SCANNED)), (!zone_reclaimable(zone) ? "yes" : "no") ); printk("lowmem_reserve[]:"); for (i = 0; i < MAX_NR_ZONES; i++) - printk(" %lu", zone->lowmem_reserve[i]); + printk(" %ld", zone->lowmem_reserve[i]); printk("\n"); } @@ -4107,7 +4153,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, static void __meminit zone_init_free_lists(struct zone *zone) { - int order, t; + unsigned int order, t; for_each_migratetype_order(order, t) { INIT_LIST_HEAD(&zone->free_area[order].free_list[t]); zone->free_area[order].nr_free = 0; @@ -4933,7 +4979,8 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, pgdat->node_id = nid; pgdat->node_start_pfn = node_start_pfn; - init_zone_allows_reclaim(nid); + if (node_state(nid, N_MEMORY)) + init_zone_allows_reclaim(nid); #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); #endif @@ -5546,7 +5593,7 @@ static void calculate_totalreserve_pages(void) for_each_online_pgdat(pgdat) { for (i = 0; i < MAX_NR_ZONES; i++) { struct zone *zone = pgdat->node_zones + i; - unsigned long max = 0; + long max = 0; /* Find valid and maximum lowmem_reserve in the zone */ for (j = i; j < MAX_NR_ZONES; j++) { @@ -5661,9 +5708,8 @@ static void __setup_per_zone_wmarks(void) zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1); __mod_zone_page_state(zone, NR_ALLOC_BATCH, - high_wmark_pages(zone) - - low_wmark_pages(zone) - - zone_page_state(zone, NR_ALLOC_BATCH)); + high_wmark_pages(zone) - low_wmark_pages(zone) - + atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH])); setup_zone_migrate_reserve(zone); spin_unlock_irqrestore(&zone->lock, flags); @@ -6035,17 +6081,16 @@ static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn) * @end_bitidx: The last bit of interest * returns pageblock_bits flags */ -unsigned long get_pageblock_flags_mask(struct page *page, +unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn, unsigned long end_bitidx, unsigned long mask) { struct zone *zone; unsigned long *bitmap; - unsigned long pfn, bitidx, word_bitidx; + unsigned long bitidx, word_bitidx; unsigned long word; zone = page_zone(page); - pfn = page_to_pfn(page); bitmap = get_pageblock_bitmap(zone, pfn); bitidx = pfn_to_bitidx(zone, pfn); word_bitidx = bitidx / BITS_PER_LONG; @@ -6057,25 +6102,25 @@ unsigned long get_pageblock_flags_mask(struct page *page, } /** - * set_pageblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages + * set_pfnblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages * @page: The page within the block of interest * @start_bitidx: The first bit of interest * @end_bitidx: The last bit of interest * @flags: The flags to set */ -void set_pageblock_flags_mask(struct page *page, unsigned long flags, +void set_pfnblock_flags_mask(struct page *page, unsigned long flags, + unsigned long pfn, unsigned long end_bitidx, unsigned long mask) { struct zone *zone; unsigned long *bitmap; - unsigned long pfn, bitidx, word_bitidx; + unsigned long bitidx, word_bitidx; unsigned long old_word, word; BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4); zone = page_zone(page); - pfn = page_to_pfn(page); bitmap = get_pageblock_bitmap(zone, pfn); bitidx = pfn_to_bitidx(zone, pfn); word_bitidx = bitidx / BITS_PER_LONG; @@ -6253,7 +6298,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, cc->nr_migratepages -= nr_reclaimed; ret = migrate_pages(&cc->migratepages, alloc_migrate_target, - 0, MIGRATE_SYNC, MR_CMA); + NULL, 0, cc->mode, MR_CMA); } if (ret < 0) { putback_movable_pages(&cc->migratepages); @@ -6292,7 +6337,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, .nr_migratepages = 0, .order = -1, .zone = page_zone(pfn_to_page(start)), - .sync = true, + .mode = MIGRATE_SYNC, .ignore_skip_hint = true, }; INIT_LIST_HEAD(&cc.migratepages); @@ -6447,7 +6492,7 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) { struct page *page; struct zone *zone; - int order, i; + unsigned int order, i; unsigned long pfn; unsigned long flags; /* find the first valid pfn */ @@ -6499,7 +6544,7 @@ bool is_free_buddy_page(struct page *page) struct zone *zone = page_zone(page); unsigned long pfn = page_to_pfn(page); unsigned long flags; - int order; + unsigned int order; spin_lock_irqsave(&zone->lock, flags); for (order = 0; order < MAX_ORDER; order++) { diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index cfd162882c00..0e9a319d5f8d 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -171,6 +171,7 @@ static void free_page_cgroup(void *addr) sizeof(struct page_cgroup) * PAGES_PER_SECTION; BUG_ON(PageReserved(page)); + kmemleak_free(addr); free_pages_exact(addr, table_size); } } diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 2beeabf502c5..9056d22d2880 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -199,7 +199,10 @@ int walk_page_range(unsigned long addr, unsigned long end, */ if ((vma->vm_start <= addr) && (vma->vm_flags & VM_PFNMAP)) { - next = vma->vm_end; + if (walk->pte_hole) + err = walk->pte_hole(addr, next, walk); + if (err) + break; pgd = pgd_offset(walk->mm, next); continue; } diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c index 3707c71ae4cd..51108165f829 100644 --- a/mm/percpu-vm.c +++ b/mm/percpu-vm.c @@ -108,7 +108,7 @@ static int pcpu_alloc_pages(struct pcpu_chunk *chunk, int page_start, int page_end) { const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD; - unsigned int cpu; + unsigned int cpu, tcpu; int i; for_each_possible_cpu(cpu) { @@ -116,14 +116,23 @@ static int pcpu_alloc_pages(struct pcpu_chunk *chunk, struct page **pagep = &pages[pcpu_page_idx(cpu, i)]; *pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0); - if (!*pagep) { - pcpu_free_pages(chunk, pages, populated, - page_start, page_end); - return -ENOMEM; - } + if (!*pagep) + goto err; } } return 0; + +err: + while (--i >= page_start) + __free_page(pages[pcpu_page_idx(cpu, i)]); + + for_each_possible_cpu(tcpu) { + if (tcpu == cpu) + break; + for (i = page_start; i < page_end; i++) + __free_page(pages[pcpu_page_idx(tcpu, i)]); + } + return -ENOMEM; } /** @@ -263,6 +272,7 @@ err: __pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start), page_end - page_start); } + pcpu_post_unmap_tlb_flush(chunk, page_start, page_end); return err; } diff --git a/mm/readahead.c b/mm/readahead.c index 0de2360d65f3..0ca36a7770b1 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -8,9 +8,7 @@ */ #include <linux/kernel.h> -#include <linux/fs.h> #include <linux/gfp.h> -#include <linux/mm.h> #include <linux/export.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> @@ -20,6 +18,8 @@ #include <linux/syscalls.h> #include <linux/file.h> +#include "internal.h" + /* * Initialise a struct file's readahead state. Assumes that the caller has * memset *ra to zero. @@ -149,8 +149,7 @@ out: * * Returns the number of pages requested, or the maximum amount of I/O allowed. */ -static int -__do_page_cache_readahead(struct address_space *mapping, struct file *filp, +int __do_page_cache_readahead(struct address_space *mapping, struct file *filp, pgoff_t offset, unsigned long nr_to_read, unsigned long lookahead_size) { @@ -179,7 +178,7 @@ __do_page_cache_readahead(struct address_space *mapping, struct file *filp, rcu_read_lock(); page = radix_tree_lookup(&mapping->page_tree, page_offset); rcu_read_unlock(); - if (page) + if (page && !radix_tree_exceptional_entry(page)) continue; page = page_cache_alloc_readahead(mapping); @@ -233,28 +232,14 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp, return 0; } +#define MAX_READAHEAD ((512*4096)/PAGE_CACHE_SIZE) /* * Given a desired number of PAGE_CACHE_SIZE readahead pages, return a * sensible upper limit. */ unsigned long max_sane_readahead(unsigned long nr) { - return min(nr, (node_page_state(numa_node_id(), NR_INACTIVE_FILE) - + node_page_state(numa_node_id(), NR_FREE_PAGES)) / 2); -} - -/* - * Submit IO for the read-ahead request in file_ra_state. - */ -unsigned long ra_submit(struct file_ra_state *ra, - struct address_space *mapping, struct file *filp) -{ - int actual; - - actual = __do_page_cache_readahead(mapping, filp, - ra->start, ra->size, ra->async_size); - - return actual; + return min(nr, MAX_READAHEAD); } /* @@ -347,7 +332,7 @@ static pgoff_t count_history_pages(struct address_space *mapping, pgoff_t head; rcu_read_lock(); - head = radix_tree_prev_hole(&mapping->page_tree, offset - 1, max); + head = page_cache_prev_hole(mapping, offset - 1, max); rcu_read_unlock(); return offset - 1 - head; @@ -427,7 +412,7 @@ ondemand_readahead(struct address_space *mapping, pgoff_t start; rcu_read_lock(); - start = radix_tree_next_hole(&mapping->page_tree, offset+1,max); + start = page_cache_next_hole(mapping, offset + 1, max); rcu_read_unlock(); if (!start || start - offset > max) diff --git a/mm/rmap.c b/mm/rmap.c index cdbd31285cf6..cab982084e2b 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -274,6 +274,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) { struct anon_vma_chain *avc; struct anon_vma *anon_vma; + int error; /* Don't bother if the parent process has no anon_vma here. */ if (!pvma->anon_vma) @@ -283,8 +284,9 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) * First, attach the new VMA to the parent VMA's anon_vmas, * so rmap can find non-COWed pages in child processes. */ - if (anon_vma_clone(vma, pvma)) - return -ENOMEM; + error = anon_vma_clone(vma, pvma); + if (error) + return error; /* Then add our own anon_vma. */ anon_vma = anon_vma_alloc(); diff --git a/mm/shmem.c b/mm/shmem.c index ff85863587ee..85d8a1a3626c 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -243,19 +243,17 @@ static int shmem_radix_tree_replace(struct address_space *mapping, pgoff_t index, void *expected, void *replacement) { void **pslot; - void *item = NULL; + void *item; VM_BUG_ON(!expected); + VM_BUG_ON(!replacement); pslot = radix_tree_lookup_slot(&mapping->page_tree, index); - if (pslot) - item = radix_tree_deref_slot_protected(pslot, - &mapping->tree_lock); + if (!pslot) + return -ENOENT; + item = radix_tree_deref_slot_protected(pslot, &mapping->tree_lock); if (item != expected) return -ENOENT; - if (replacement) - radix_tree_replace_slot(pslot, replacement); - else - radix_tree_delete(&mapping->page_tree, index); + radix_tree_replace_slot(pslot, replacement); return 0; } @@ -332,84 +330,20 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap) } /* - * Like find_get_pages, but collecting swap entries as well as pages. - */ -static unsigned shmem_find_get_pages_and_swap(struct address_space *mapping, - pgoff_t start, unsigned int nr_pages, - struct page **pages, pgoff_t *indices) -{ - void **slot; - unsigned int ret = 0; - struct radix_tree_iter iter; - - if (!nr_pages) - return 0; - - rcu_read_lock(); -restart: - radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { - struct page *page; -repeat: - page = radix_tree_deref_slot(slot); - if (unlikely(!page)) - continue; - if (radix_tree_exception(page)) { - if (radix_tree_deref_retry(page)) - goto restart; - /* - * Otherwise, we must be storing a swap entry - * here as an exceptional entry: so return it - * without attempting to raise page count. - */ - goto export; - } - if (!page_cache_get_speculative(page)) - goto repeat; - - /* Has the page moved? */ - if (unlikely(page != *slot)) { - page_cache_release(page); - goto repeat; - } -export: - indices[ret] = iter.index; - pages[ret] = page; - if (++ret == nr_pages) - break; - } - rcu_read_unlock(); - return ret; -} - -/* * Remove swap entry from radix tree, free the swap and its page cache. */ static int shmem_free_swap(struct address_space *mapping, pgoff_t index, void *radswap) { - int error; + void *old; spin_lock_irq(&mapping->tree_lock); - error = shmem_radix_tree_replace(mapping, index, radswap, NULL); + old = radix_tree_delete_item(&mapping->page_tree, index, radswap); spin_unlock_irq(&mapping->tree_lock); - if (!error) - free_swap_and_cache(radix_to_swp_entry(radswap)); - return error; -} - -/* - * Pagevec may contain swap entries, so shuffle up pages before releasing. - */ -static void shmem_deswap_pagevec(struct pagevec *pvec) -{ - int i, j; - - for (i = 0, j = 0; i < pagevec_count(pvec); i++) { - struct page *page = pvec->pages[i]; - if (!radix_tree_exceptional_entry(page)) - pvec->pages[j++] = page; - } - pvec->nr = j; + if (old != radswap) + return -ENOENT; + free_swap_and_cache(radix_to_swp_entry(radswap)); + return 0; } /* @@ -430,12 +364,12 @@ void shmem_unlock_mapping(struct address_space *mapping) * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it * has finished, if it hits a row of PAGEVEC_SIZE swap entries. */ - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, - PAGEVEC_SIZE, pvec.pages, indices); + pvec.nr = find_get_entries(mapping, index, + PAGEVEC_SIZE, pvec.pages, indices); if (!pvec.nr) break; index = indices[pvec.nr - 1] + 1; - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); check_move_unevictable_pages(pvec.pages, pvec.nr); pagevec_release(&pvec); cond_resched(); @@ -467,9 +401,9 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, pagevec_init(&pvec, 0); index = start; while (index < end) { - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE), - pvec.pages, indices); + pvec.nr = find_get_entries(mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + pvec.pages, indices); if (!pvec.nr) break; mem_cgroup_uncharge_start(); @@ -498,7 +432,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, } unlock_page(page); } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); @@ -536,9 +470,10 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, index = start; while (index < end) { cond_resched(); - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, + + pvec.nr = find_get_entries(mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), - pvec.pages, indices); + pvec.pages, indices); if (!pvec.nr) { /* If all gone or hole-punch or unfalloc, we're done */ if (index == start || end != -1) @@ -581,7 +516,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, } unlock_page(page); } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); index++; @@ -1088,7 +1023,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, return -EFBIG; repeat: swap.val = 0; - page = find_lock_page(mapping, index); + page = find_lock_entry(mapping, index); if (radix_tree_exceptional_entry(page)) { swap = radix_to_swp_entry(page); page = NULL; @@ -1100,6 +1035,9 @@ repeat: goto failed; } + if (page && sgp == SGP_WRITE) + mark_page_accessed(page); + /* fallocated page? */ if (page && !PageUptodate(page)) { if (sgp != SGP_READ) @@ -1181,6 +1119,9 @@ repeat: shmem_recalc_inode(inode); spin_unlock(&info->lock); + if (sgp == SGP_WRITE) + mark_page_accessed(page); + delete_from_swap_cache(page); set_page_dirty(page); swap_free(swap); @@ -1205,8 +1146,11 @@ repeat: goto decused; } - SetPageSwapBacked(page); + __SetPageSwapBacked(page); __set_page_locked(page); + if (sgp == SGP_WRITE) + init_page_accessed(page); + error = mem_cgroup_cache_charge(page, current->mm, gfp & GFP_RECLAIM_MASK); if (error) @@ -1483,6 +1427,11 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode return inode; } +bool shmem_mapping(struct address_space *mapping) +{ + return mapping->backing_dev_info == &shmem_backing_dev_info; +} + #ifdef CONFIG_TMPFS static const struct inode_operations shmem_symlink_inode_operations; static const struct inode_operations shmem_short_symlink_operations; @@ -1795,7 +1744,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping, pagevec_init(&pvec, 0); pvec.nr = 1; /* start small: we may be there already */ while (!done) { - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, + pvec.nr = find_get_entries(mapping, index, pvec.nr, pvec.pages, indices); if (!pvec.nr) { if (whence == SEEK_DATA) @@ -1822,7 +1771,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping, break; } } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); pvec.nr = PAGEVEC_SIZE; cond_resched(); @@ -2143,8 +2092,10 @@ static int shmem_rename(struct inode *old_dir, struct dentry *old_dentry, struct if (new_dentry->d_inode) { (void) shmem_unlink(new_dir, new_dentry); - if (they_are_dirs) + if (they_are_dirs) { + drop_nlink(new_dentry->d_inode); drop_nlink(old_dir); + } } else if (they_are_dirs) { drop_nlink(old_dir); inc_nlink(new_dir); diff --git a/mm/slab.c b/mm/slab.c index 6dd8d5f3a3ac..0b1c2a58559d 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2189,7 +2189,8 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) int __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) { - size_t left_over, freelist_size, ralign; + size_t left_over, freelist_size; + size_t ralign = BYTES_PER_WORD; gfp_t gfp; int err; size_t size = cachep->size; @@ -2222,14 +2223,6 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) size &= ~(BYTES_PER_WORD - 1); } - /* - * Redzoning and user store require word alignment or possibly larger. - * Note this will be overridden by architecture or caller mandated - * alignment if either is greater than BYTES_PER_WORD. - */ - if (flags & SLAB_STORE_USER) - ralign = BYTES_PER_WORD; - if (flags & SLAB_RED_ZONE) { ralign = REDZONE_ALIGN; /* If redzoning, ensure that the second redzone is suitably @@ -3129,7 +3122,7 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags) local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK); retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); zonelist = node_zonelist(slab_node(), flags); retry: @@ -3187,7 +3180,7 @@ retry: } } - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !obj)) + if (unlikely(!obj && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return obj; } diff --git a/mm/slub.c b/mm/slub.c index 25f14ad8f817..7611f148ee81 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1684,7 +1684,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, return NULL; do { - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); zonelist = node_zonelist(slab_node(), flags); for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { struct kmem_cache_node *n; @@ -1696,19 +1696,17 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, object = get_partial_node(s, n, c, flags); if (object) { /* - * Return the object even if - * put_mems_allowed indicated that - * the cpuset mems_allowed was - * updated in parallel. It's a - * harmless race between the alloc - * and the cpuset update. + * Don't check read_mems_allowed_retry() + * here - if mems_allowed was updated in + * parallel, that was a harmless race + * between allocation and the cpuset + * update */ - put_mems_allowed(cpuset_mems_cookie); return object; } } } - } while (!put_mems_allowed(cpuset_mems_cookie)); + } while (read_mems_allowed_retry(cpuset_mems_cookie)); #endif return NULL; } diff --git a/mm/swap.c b/mm/swap.c index 0092097b3f4c..d2ceddf70d42 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -67,7 +67,7 @@ static void __page_cache_release(struct page *page) static void __put_single_page(struct page *page) { __page_cache_release(page); - free_hot_cold_page(page, 0); + free_hot_cold_page(page, false); } static void __put_compound_page(struct page *page) @@ -469,7 +469,7 @@ static void __activate_page(struct page *page, struct lruvec *lruvec, SetPageActive(page); lru += LRU_ACTIVE; add_page_to_lru_list(page, lruvec, lru); - trace_mm_lru_activate(page, page_to_pfn(page)); + trace_mm_lru_activate(page); __count_vm_event(PGACTIVATE); update_page_reclaim_stat(lruvec, file, 1); @@ -581,12 +581,17 @@ void mark_page_accessed(struct page *page) EXPORT_SYMBOL(mark_page_accessed); /* - * Queue the page for addition to the LRU via pagevec. The decision on whether - * to add the page to the [in]active [file|anon] list is deferred until the - * pagevec is drained. This gives a chance for the caller of __lru_cache_add() - * have the page added to the active list using mark_page_accessed(). + * Used to mark_page_accessed(page) that is not visible yet and when it is + * still safe to use non-atomic ops */ -void __lru_cache_add(struct page *page) +void init_page_accessed(struct page *page) +{ + if (!PageReferenced(page)) + __SetPageReferenced(page); +} +EXPORT_SYMBOL(init_page_accessed); + +static void __lru_cache_add(struct page *page) { struct pagevec *pvec = &get_cpu_var(lru_add_pvec); @@ -596,11 +601,34 @@ void __lru_cache_add(struct page *page) pagevec_add(pvec, page); put_cpu_var(lru_add_pvec); } -EXPORT_SYMBOL(__lru_cache_add); + +/** + * lru_cache_add: add a page to the page lists + * @page: the page to add + */ +void lru_cache_add_anon(struct page *page) +{ + if (PageActive(page)) + ClearPageActive(page); + __lru_cache_add(page); +} + +void lru_cache_add_file(struct page *page) +{ + if (PageActive(page)) + ClearPageActive(page); + __lru_cache_add(page); +} +EXPORT_SYMBOL(lru_cache_add_file); /** * lru_cache_add - add a page to a page list * @page: the page to be added to the LRU. + * + * Queue the page for addition to the LRU via pagevec. The decision on whether + * to add the page to the [in]active [file|anon] list is deferred until the + * pagevec is drained. This gives a chance for the caller of lru_cache_add() + * have the page added to the active list using mark_page_accessed(). */ void lru_cache_add(struct page *page) { @@ -811,7 +839,7 @@ void lru_add_drain_all(void) * grabbed the page via the LRU. If it did, give up: shrink_inactive_list() * will free it. */ -void release_pages(struct page **pages, int nr, int cold) +void release_pages(struct page **pages, int nr, bool cold) { int i; LIST_HEAD(pages_to_free); @@ -852,7 +880,7 @@ void release_pages(struct page **pages, int nr, int cold) } /* Clear Active bit in case of parallel mark_page_accessed */ - ClearPageActive(page); + __ClearPageActive(page); list_add(&page->lru, &pages_to_free); } @@ -934,7 +962,7 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec, SetPageLRU(page); add_page_to_lru_list(page, lruvec, lru); update_page_reclaim_stat(lruvec, file, active); - trace_mm_lru_insertion(page, page_to_pfn(page), lru, trace_pagemap_flags(page)); + trace_mm_lru_insertion(page, lru); } /* @@ -948,6 +976,57 @@ void __pagevec_lru_add(struct pagevec *pvec) EXPORT_SYMBOL(__pagevec_lru_add); /** + * pagevec_lookup_entries - gang pagecache lookup + * @pvec: Where the resulting entries are placed + * @mapping: The address_space to search + * @start: The starting entry index + * @nr_entries: The maximum number of entries + * @indices: The cache indices corresponding to the entries in @pvec + * + * pagevec_lookup_entries() will search for and return a group of up + * to @nr_entries pages and shadow entries in the mapping. All + * entries are placed in @pvec. pagevec_lookup_entries() takes a + * reference against actual pages in @pvec. + * + * The search returns a group of mapping-contiguous entries with + * ascending indexes. There may be holes in the indices due to + * not-present entries. + * + * pagevec_lookup_entries() returns the number of entries which were + * found. + */ +unsigned pagevec_lookup_entries(struct pagevec *pvec, + struct address_space *mapping, + pgoff_t start, unsigned nr_pages, + pgoff_t *indices) +{ + pvec->nr = find_get_entries(mapping, start, nr_pages, + pvec->pages, indices); + return pagevec_count(pvec); +} + +/** + * pagevec_remove_exceptionals - pagevec exceptionals pruning + * @pvec: The pagevec to prune + * + * pagevec_lookup_entries() fills both pages and exceptional radix + * tree entries into the pagevec. This function prunes all + * exceptionals from @pvec without leaving holes, so that it can be + * passed on to page-only pagevec operations. + */ +void pagevec_remove_exceptionals(struct pagevec *pvec) +{ + int i, j; + + for (i = 0, j = 0; i < pagevec_count(pvec); i++) { + struct page *page = pvec->pages[i]; + if (!radix_tree_exceptional_entry(page)) + pvec->pages[j++] = page; + } + pvec->nr = j; +} + +/** * pagevec_lookup - gang pagecache lookup * @pvec: Where the resulting pages are placed * @mapping: The address_space to search diff --git a/mm/swap_state.c b/mm/swap_state.c index e76ace30d436..2972eee184a4 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -270,7 +270,7 @@ void free_pages_and_swap_cache(struct page **pages, int nr) for (i = 0; i < todo; i++) free_swap_cache(pagep[i]); - release_pages(pagep, todo, 0); + release_pages(pagep, todo, false); pagep += todo; nr -= todo; } diff --git a/mm/swapfile.c b/mm/swapfile.c index 4a7f7e6992b6..beeeef8a1b2d 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -51,14 +51,32 @@ atomic_long_t nr_swap_pages; /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority; -static atomic_t highest_priority_index = ATOMIC_INIT(-1); static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; static const char Unused_offset[] = "Unused swap offset entry "; -struct swap_list_t swap_list = {-1, -1}; +/* + * all active swap_info_structs + * protected with swap_lock, and ordered by priority. + */ +PLIST_HEAD(swap_active_head); + +/* + * all available (active, not full) swap_info_structs + * protected with swap_avail_lock, ordered by priority. + * This is used by get_swap_page() instead of swap_active_head + * because swap_active_head includes all swap_info_structs, + * but get_swap_page() doesn't need to look at full ones. + * This uses its own lock instead of swap_lock because when a + * swap_info_struct changes between not-full/full, it needs to + * add/remove itself to/from this list, but the swap_info_struct->lock + * is held and the locking order requires swap_lock to be taken + * before any swap_info_struct->lock. + */ +static PLIST_HEAD(swap_avail_head); +static DEFINE_SPINLOCK(swap_avail_lock); struct swap_info_struct *swap_info[MAX_SWAPFILES]; @@ -591,6 +609,9 @@ checks: if (si->inuse_pages == si->pages) { si->lowest_bit = si->max; si->highest_bit = 0; + spin_lock(&swap_avail_lock); + plist_del(&si->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); } si->swap_map[offset] = usage; inc_cluster_info_page(si, si->cluster_info, offset); @@ -640,71 +661,65 @@ no_page: swp_entry_t get_swap_page(void) { - struct swap_info_struct *si; + struct swap_info_struct *si, *next; pgoff_t offset; - int type, next; - int wrapped = 0; - int hp_index; - spin_lock(&swap_lock); if (atomic_long_read(&nr_swap_pages) <= 0) goto noswap; atomic_long_dec(&nr_swap_pages); - for (type = swap_list.next; type >= 0 && wrapped < 2; type = next) { - hp_index = atomic_xchg(&highest_priority_index, -1); - /* - * highest_priority_index records current highest priority swap - * type which just frees swap entries. If its priority is - * higher than that of swap_list.next swap type, we use it. It - * isn't protected by swap_lock, so it can be an invalid value - * if the corresponding swap type is swapoff. We double check - * the flags here. It's even possible the swap type is swapoff - * and swapon again and its priority is changed. In such rare - * case, low prority swap type might be used, but eventually - * high priority swap will be used after several rounds of - * swap. - */ - if (hp_index != -1 && hp_index != type && - swap_info[type]->prio < swap_info[hp_index]->prio && - (swap_info[hp_index]->flags & SWP_WRITEOK)) { - type = hp_index; - swap_list.next = type; - } - - si = swap_info[type]; - next = si->next; - if (next < 0 || - (!wrapped && si->prio != swap_info[next]->prio)) { - next = swap_list.head; - wrapped++; - } + spin_lock(&swap_avail_lock); +start_over: + plist_for_each_entry_safe(si, next, &swap_avail_head, avail_list) { + /* requeue si to after same-priority siblings */ + plist_requeue(&si->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); spin_lock(&si->lock); - if (!si->highest_bit) { + if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) { + spin_lock(&swap_avail_lock); + if (plist_node_empty(&si->avail_list)) { + spin_unlock(&si->lock); + goto nextsi; + } + WARN(!si->highest_bit, + "swap_info %d in list but !highest_bit\n", + si->type); + WARN(!(si->flags & SWP_WRITEOK), + "swap_info %d in list but !SWP_WRITEOK\n", + si->type); + plist_del(&si->avail_list, &swap_avail_head); spin_unlock(&si->lock); - continue; + goto nextsi; } - if (!(si->flags & SWP_WRITEOK)) { - spin_unlock(&si->lock); - continue; - } - - swap_list.next = next; - spin_unlock(&swap_lock); /* This is called for allocating swap entry for cache */ offset = scan_swap_map(si, SWAP_HAS_CACHE); spin_unlock(&si->lock); if (offset) - return swp_entry(type, offset); - spin_lock(&swap_lock); - next = swap_list.next; + return swp_entry(si->type, offset); + pr_debug("scan_swap_map of si %d failed to find offset\n", + si->type); + spin_lock(&swap_avail_lock); +nextsi: + /* + * if we got here, it's likely that si was almost full before, + * and since scan_swap_map() can drop the si->lock, multiple + * callers probably all tried to get a page from the same si + * and it filled up before we could get one; or, the si filled + * up between us dropping swap_avail_lock and taking si->lock. + * Since we dropped the swap_avail_lock, the swap_avail_head + * list may have been modified; so if next is still in the + * swap_avail_head list then try it, otherwise start over. + */ + if (plist_node_empty(&next->avail_list)) + goto start_over; } + spin_unlock(&swap_avail_lock); + atomic_long_inc(&nr_swap_pages); noswap: - spin_unlock(&swap_lock); return (swp_entry_t) {0}; } @@ -766,27 +781,6 @@ out: return NULL; } -/* - * This swap type frees swap entry, check if it is the highest priority swap - * type which just frees swap entry. get_swap_page() uses - * highest_priority_index to search highest priority swap type. The - * swap_info_struct.lock can't protect us if there are multiple swap types - * active, so we use atomic_cmpxchg. - */ -static void set_highest_priority_index(int type) -{ - int old_hp_index, new_hp_index; - - do { - old_hp_index = atomic_read(&highest_priority_index); - if (old_hp_index != -1 && - swap_info[old_hp_index]->prio >= swap_info[type]->prio) - break; - new_hp_index = type; - } while (atomic_cmpxchg(&highest_priority_index, - old_hp_index, new_hp_index) != old_hp_index); -} - static unsigned char swap_entry_free(struct swap_info_struct *p, swp_entry_t entry, unsigned char usage) { @@ -828,9 +822,18 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, dec_cluster_info_page(p, p->cluster_info, offset); if (offset < p->lowest_bit) p->lowest_bit = offset; - if (offset > p->highest_bit) + if (offset > p->highest_bit) { + bool was_full = !p->highest_bit; p->highest_bit = offset; - set_highest_priority_index(p->type); + if (was_full && (p->flags & SWP_WRITEOK)) { + spin_lock(&swap_avail_lock); + WARN_ON(!plist_node_empty(&p->avail_list)); + if (plist_node_empty(&p->avail_list)) + plist_add(&p->avail_list, + &swap_avail_head); + spin_unlock(&swap_avail_lock); + } + } atomic_long_inc(&nr_swap_pages); p->inuse_pages--; frontswap_invalidate_page(p->type, offset); @@ -1765,30 +1768,37 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info) { - int i, prev; - if (prio >= 0) p->prio = prio; else p->prio = --least_priority; + /* + * the plist prio is negated because plist ordering is + * low-to-high, while swap ordering is high-to-low + */ + p->list.prio = -p->prio; + p->avail_list.prio = -p->prio; p->swap_map = swap_map; p->cluster_info = cluster_info; p->flags |= SWP_WRITEOK; atomic_long_add(p->pages, &nr_swap_pages); total_swap_pages += p->pages; - /* insert swap space into swap_list: */ - prev = -1; - for (i = swap_list.head; i >= 0; i = swap_info[i]->next) { - if (p->prio >= swap_info[i]->prio) - break; - prev = i; - } - p->next = i; - if (prev < 0) - swap_list.head = swap_list.next = p->type; - else - swap_info[prev]->next = p->type; + assert_spin_locked(&swap_lock); + /* + * both lists are plists, and thus priority ordered. + * swap_active_head needs to be priority ordered for swapoff(), + * which on removal of any swap_info_struct with an auto-assigned + * (i.e. negative) priority increments the auto-assigned priority + * of any lower-priority swap_info_structs. + * swap_avail_head needs to be priority ordered for get_swap_page(), + * which allocates swap pages from the highest available priority + * swap_info_struct. + */ + plist_add(&p->list, &swap_active_head); + spin_lock(&swap_avail_lock); + plist_add(&p->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); } static void enable_swap_info(struct swap_info_struct *p, int prio, @@ -1823,8 +1833,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) struct address_space *mapping; struct inode *inode; struct filename *pathname; - int i, type, prev; - int err; + int err, found = 0; unsigned int old_block_size; if (!capable(CAP_SYS_ADMIN)) @@ -1842,17 +1851,16 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) goto out; mapping = victim->f_mapping; - prev = -1; spin_lock(&swap_lock); - for (type = swap_list.head; type >= 0; type = swap_info[type]->next) { - p = swap_info[type]; + plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { - if (p->swap_file->f_mapping == mapping) + if (p->swap_file->f_mapping == mapping) { + found = 1; break; + } } - prev = type; } - if (type < 0) { + if (!found) { err = -EINVAL; spin_unlock(&swap_lock); goto out_dput; @@ -1864,20 +1872,21 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&swap_lock); goto out_dput; } - if (prev < 0) - swap_list.head = p->next; - else - swap_info[prev]->next = p->next; - if (type == swap_list.next) { - /* just pick something that's safe... */ - swap_list.next = swap_list.head; - } + spin_lock(&swap_avail_lock); + plist_del(&p->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); spin_lock(&p->lock); if (p->prio < 0) { - for (i = p->next; i >= 0; i = swap_info[i]->next) - swap_info[i]->prio = p->prio--; + struct swap_info_struct *si = p; + + plist_for_each_entry_continue(si, &swap_active_head, list) { + si->prio++; + si->list.prio--; + si->avail_list.prio--; + } least_priority++; } + plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; p->flags &= ~SWP_WRITEOK; @@ -1885,7 +1894,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&swap_lock); set_current_oom_origin(); - err = try_to_unuse(type, false, 0); /* force all pages to be unused */ + err = try_to_unuse(p->type, false, 0); /* force unuse all pages */ clear_current_oom_origin(); if (err) { @@ -1926,7 +1935,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) frontswap_map = frontswap_map_get(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); - frontswap_invalidate_area(type); + frontswap_invalidate_area(p->type); frontswap_map_set(p, NULL); mutex_unlock(&swapon_mutex); free_percpu(p->percpu_cluster); @@ -1935,7 +1944,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) vfree(cluster_info); vfree(frontswap_map); /* Destroy swap account information */ - swap_cgroup_swapoff(type); + swap_cgroup_swapoff(p->type); inode = mapping->host; if (S_ISBLK(inode->i_mode)) { @@ -2142,8 +2151,9 @@ static struct swap_info_struct *alloc_swap_info(void) */ } INIT_LIST_HEAD(&p->first_swap_extent.list); + plist_node_init(&p->list, 0); + plist_node_init(&p->avail_list, 0); p->flags = SWP_USED; - p->next = -1; spin_unlock(&swap_lock); spin_lock_init(&p->lock); diff --git a/mm/truncate.c b/mm/truncate.c index 353b683afd6e..827ad8d2b5cd 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -20,8 +20,25 @@ #include <linux/buffer_head.h> /* grr. try_to_release_page, do_invalidatepage */ #include <linux/cleancache.h> +#include <linux/rmap.h> #include "internal.h" +static void clear_exceptional_entry(struct address_space *mapping, + pgoff_t index, void *entry) +{ + /* Handled by shmem itself */ + if (shmem_mapping(mapping)) + return; + + spin_lock_irq(&mapping->tree_lock); + /* + * Regular page slots are stabilized by the page lock even + * without the tree itself locked. These unlocked entries + * need verification under the tree lock. + */ + radix_tree_delete_item(&mapping->page_tree, index, entry); + spin_unlock_irq(&mapping->tree_lock); +} /** * do_invalidatepage - invalidate part or all of a page @@ -208,6 +225,7 @@ void truncate_inode_pages_range(struct address_space *mapping, unsigned int partial_start; /* inclusive */ unsigned int partial_end; /* exclusive */ struct pagevec pvec; + pgoff_t indices[PAGEVEC_SIZE]; pgoff_t index; int i; @@ -238,17 +256,23 @@ void truncate_inode_pages_range(struct address_space *mapping, pagevec_init(&pvec, 0); index = start; - while (index < end && pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE))) { + while (index < end && pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + indices)) { mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; + index = indices[i]; if (index >= end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + if (!trylock_page(page)) continue; WARN_ON(page->index != index); @@ -259,6 +283,7 @@ void truncate_inode_pages_range(struct address_space *mapping, truncate_inode_page(mapping, page); unlock_page(page); } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); @@ -307,14 +332,16 @@ void truncate_inode_pages_range(struct address_space *mapping, index = start; for ( ; ; ) { cond_resched(); - if (!pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE))) { + if (!pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + indices)) { if (index == start) break; index = start; continue; } - if (index == start && pvec.pages[0]->index >= end) { + if (index == start && indices[0] >= end) { + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); break; } @@ -323,16 +350,22 @@ void truncate_inode_pages_range(struct address_space *mapping, struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; + index = indices[i]; if (index >= end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + lock_page(page); WARN_ON(page->index != index); wait_on_page_writeback(page); truncate_inode_page(mapping, page); unlock_page(page); } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); index++; @@ -375,6 +408,7 @@ EXPORT_SYMBOL(truncate_inode_pages); unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end) { + pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; pgoff_t index = start; unsigned long ret; @@ -390,17 +424,23 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, */ pagevec_init(&pvec, 0); - while (index <= end && pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { + while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, + indices)) { mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; + index = indices[i]; if (index > end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + if (!trylock_page(page)) continue; WARN_ON(page->index != index); @@ -414,6 +454,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, deactivate_page(page); count += ret; } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); @@ -481,6 +522,7 @@ static int do_launder_page(struct address_space *mapping, struct page *page) int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end) { + pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; pgoff_t index; int i; @@ -491,17 +533,23 @@ int invalidate_inode_pages2_range(struct address_space *mapping, cleancache_invalidate_inode(mapping); pagevec_init(&pvec, 0); index = start; - while (index <= end && pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { + while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, + indices)) { mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; + index = indices[i]; if (index > end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + lock_page(page); WARN_ON(page->index != index); if (page->mapping != mapping) { @@ -539,6 +587,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, ret = ret2; unlock_page(page); } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); @@ -613,12 +662,67 @@ EXPORT_SYMBOL(truncate_pagecache); */ void truncate_setsize(struct inode *inode, loff_t newsize) { + loff_t oldsize = inode->i_size; + i_size_write(inode, newsize); + if (newsize > oldsize) + pagecache_isize_extended(inode, oldsize, newsize); truncate_pagecache(inode, newsize); } EXPORT_SYMBOL(truncate_setsize); /** + * pagecache_isize_extended - update pagecache after extension of i_size + * @inode: inode for which i_size was extended + * @from: original inode size + * @to: new inode size + * + * Handle extension of inode size either caused by extending truncate or by + * write starting after current i_size. We mark the page straddling current + * i_size RO so that page_mkwrite() is called on the nearest write access to + * the page. This way filesystem can be sure that page_mkwrite() is called on + * the page before user writes to the page via mmap after the i_size has been + * changed. + * + * The function must be called after i_size is updated so that page fault + * coming after we unlock the page will already see the new i_size. + * The function must be called while we still hold i_mutex - this not only + * makes sure i_size is stable but also that userspace cannot observe new + * i_size value before we are prepared to store mmap writes at new inode size. + */ +void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to) +{ + int bsize = 1 << inode->i_blkbits; + loff_t rounded_from; + struct page *page; + pgoff_t index; + + WARN_ON(to > inode->i_size); + + if (from >= to || bsize == PAGE_CACHE_SIZE) + return; + /* Page straddling @from will not have any hole block created? */ + rounded_from = round_up(from, bsize); + if (to <= rounded_from || !(rounded_from & (PAGE_CACHE_SIZE - 1))) + return; + + index = from >> PAGE_CACHE_SHIFT; + page = find_lock_page(inode->i_mapping, index); + /* Page not cached? Nothing to do */ + if (!page) + return; + /* + * See clear_page_dirty_for_io() for details why set_page_dirty() + * is needed. + */ + if (page_mkclean(page)) + set_page_dirty(page); + unlock_page(page); + page_cache_release(page); +} +EXPORT_SYMBOL(pagecache_isize_extended); + +/** * truncate_pagecache_range - unmap and remove pagecache that is hole-punched * @inode: inode * @lstart: offset of beginning of hole diff --git a/mm/vmacache.c b/mm/vmacache.c new file mode 100644 index 000000000000..1037a3bab505 --- /dev/null +++ b/mm/vmacache.c @@ -0,0 +1,114 @@ +/* + * Copyright (C) 2014 Davidlohr Bueso. + */ +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/vmacache.h> + +/* + * Flush vma caches for threads that share a given mm. + * + * The operation is safe because the caller holds the mmap_sem + * exclusively and other threads accessing the vma cache will + * have mmap_sem held at least for read, so no extra locking + * is required to maintain the vma cache. + */ +void vmacache_flush_all(struct mm_struct *mm) +{ + struct task_struct *g, *p; + + rcu_read_lock(); + for_each_process_thread(g, p) { + /* + * Only flush the vmacache pointers as the + * mm seqnum is already set and curr's will + * be set upon invalidation when the next + * lookup is done. + */ + if (mm == p->mm) + vmacache_flush(p); + } + rcu_read_unlock(); +} + +/* + * This task may be accessing a foreign mm via (for example) + * get_user_pages()->find_vma(). The vmacache is task-local and this + * task's vmacache pertains to a different mm (ie, its own). There is + * nothing we can do here. + * + * Also handle the case where a kernel thread has adopted this mm via use_mm(). + * That kernel thread's vmacache is not applicable to this mm. + */ +static bool vmacache_valid_mm(struct mm_struct *mm) +{ + return current->mm == mm && !(current->flags & PF_KTHREAD); +} + +void vmacache_update(unsigned long addr, struct vm_area_struct *newvma) +{ + if (vmacache_valid_mm(newvma->vm_mm)) + current->vmacache[VMACACHE_HASH(addr)] = newvma; +} + +static bool vmacache_valid(struct mm_struct *mm) +{ + struct task_struct *curr; + + if (!vmacache_valid_mm(mm)) + return false; + + curr = current; + if (mm->vmacache_seqnum != curr->vmacache_seqnum) { + /* + * First attempt will always be invalid, initialize + * the new cache for this task here. + */ + curr->vmacache_seqnum = mm->vmacache_seqnum; + vmacache_flush(curr); + return false; + } + return true; +} + +struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr) +{ + int i; + + if (!vmacache_valid(mm)) + return NULL; + + for (i = 0; i < VMACACHE_SIZE; i++) { + struct vm_area_struct *vma = current->vmacache[i]; + + if (!vma) + continue; + if (WARN_ON_ONCE(vma->vm_mm != mm)) + break; + if (vma->vm_start <= addr && vma->vm_end > addr) + return vma; + } + + return NULL; +} + +#ifndef CONFIG_MMU +struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, + unsigned long start, + unsigned long end) +{ + int i; + + if (!vmacache_valid(mm)) + return NULL; + + for (i = 0; i < VMACACHE_SIZE; i++) { + struct vm_area_struct *vma = current->vmacache[i]; + + if (vma && vma->vm_start == start && vma->vm_end == end) + return vma; + } + + return NULL; +} +#endif diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 0fdf96803c5b..aa3891e8e388 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2681,14 +2681,14 @@ void get_vmalloc_info(struct vmalloc_info *vmi) prev_end = VMALLOC_START; - spin_lock(&vmap_area_lock); + rcu_read_lock(); if (list_empty(&vmap_area_list)) { vmi->largest_chunk = VMALLOC_TOTAL; goto out; } - list_for_each_entry(va, &vmap_area_list, list) { + list_for_each_entry_rcu(va, &vmap_area_list, list) { unsigned long addr = va->va_start; /* @@ -2715,7 +2715,7 @@ void get_vmalloc_info(struct vmalloc_info *vmi) vmi->largest_chunk = VMALLOC_END - prev_end; out: - spin_unlock(&vmap_area_lock); + rcu_read_unlock(); } #endif diff --git a/mm/vmpressure.c b/mm/vmpressure.c index d4042e75f7c7..c5afd573d7da 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -165,6 +165,7 @@ static void vmpressure_work_fn(struct work_struct *work) unsigned long scanned; unsigned long reclaimed; + spin_lock(&vmpr->sr_lock); /* * Several contexts might be calling vmpressure(), so it is * possible that the work was rescheduled again before the old @@ -173,11 +174,12 @@ static void vmpressure_work_fn(struct work_struct *work) * here. No need for any locks here since we don't care if * vmpr->reclaimed is in sync. */ - if (!vmpr->scanned) + scanned = vmpr->scanned; + if (!scanned) { + spin_unlock(&vmpr->sr_lock); return; + } - spin_lock(&vmpr->sr_lock); - scanned = vmpr->scanned; reclaimed = vmpr->reclaimed; vmpr->scanned = 0; vmpr->reclaimed = 0; diff --git a/mm/vmscan.c b/mm/vmscan.c index 6ef484f0777f..b850ced69ed6 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -163,7 +163,8 @@ static unsigned long zone_reclaimable_pages(struct zone *zone) bool zone_reclaimable(struct zone *zone) { - return zone->pages_scanned < zone_reclaimable_pages(zone) * 6; + return zone_page_state(zone, NR_PAGES_SCANNED) < + zone_reclaimable_pages(zone) * 6; } static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru) @@ -224,15 +225,15 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, unsigned long freed = 0; unsigned long long delta; long total_scan; - long max_pass; + long freeable; long nr; long new_nr; int nid = shrinkctl->nid; long batch_size = shrinker->batch ? shrinker->batch : SHRINK_BATCH; - max_pass = shrinker->count_objects(shrinker, shrinkctl); - if (max_pass == 0) + freeable = shrinker->count_objects(shrinker, shrinkctl); + if (freeable == 0) return 0; /* @@ -244,14 +245,14 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, total_scan = nr; delta = (4 * nr_pages_scanned) / shrinker->seeks; - delta *= max_pass; + delta *= freeable; do_div(delta, lru_pages + 1); total_scan += delta; if (total_scan < 0) { printk(KERN_ERR "shrink_slab: %pF negative objects to delete nr=%ld\n", shrinker->scan_objects, total_scan); - total_scan = max_pass; + total_scan = freeable; } /* @@ -260,26 +261,26 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, * shrinkers to return -1 all the time. This results in a large * nr being built up so when a shrink that can do some work * comes along it empties the entire cache due to nr >>> - * max_pass. This is bad for sustaining a working set in + * freeable. This is bad for sustaining a working set in * memory. * * Hence only allow the shrinker to scan the entire cache when * a large delta change is calculated directly. */ - if (delta < max_pass / 4) - total_scan = min(total_scan, max_pass / 2); + if (delta < freeable / 4) + total_scan = min(total_scan, freeable / 2); /* * Avoid risking looping forever due to too large nr value: * never try to free more than twice the estimate number of * freeable entries. */ - if (total_scan > max_pass * 2) - total_scan = max_pass * 2; + if (total_scan > freeable * 2) + total_scan = freeable * 2; trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, nr_pages_scanned, lru_pages, - max_pass, delta, total_scan); + freeable, delta, total_scan); /* * Normally, we should not scan less than batch_size objects in one @@ -292,12 +293,12 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, * * We detect the "tight on memory" situations by looking at the total * number of objects we want to scan (total_scan). If it is greater - * than the total number of objects on slab (max_pass), we must be + * than the total number of objects on slab (freeable), we must be * scanning at high prio and therefore should try to reclaim as much as * possible. */ while (total_scan >= batch_size || - total_scan >= max_pass) { + total_scan >= freeable) { unsigned long ret; unsigned long nr_to_scan = min(batch_size, total_scan); @@ -1107,7 +1108,7 @@ keep: VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page); } - free_hot_cold_page_list(&free_pages, 1); + free_hot_cold_page_list(&free_pages, true); list_splice(&ret_pages, page_list); count_vm_events(PGACTIVATE, pgactivate); @@ -1144,7 +1145,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, TTU_UNMAP|TTU_IGNORE_ACCESS, &dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true); list_splice(&clean_pages, page_list); - __mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret); + mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret); return ret; } @@ -1470,7 +1471,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken); if (global_reclaim(sc)) { - zone->pages_scanned += nr_scanned; + __mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned); if (current_is_kswapd()) __count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scanned); else @@ -1505,7 +1506,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, spin_unlock_irq(&zone->lru_lock); - free_hot_cold_page_list(&page_list, 1); + free_hot_cold_page_list(&page_list, true); /* * If reclaim is isolating dirty pages under writeback, it implies @@ -1659,7 +1660,7 @@ static void shrink_active_list(unsigned long nr_to_scan, nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold, &nr_scanned, sc, isolate_mode, lru); if (global_reclaim(sc)) - zone->pages_scanned += nr_scanned; + __mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned); reclaim_stat->recent_scanned[file] += nr_taken; @@ -1725,7 +1726,7 @@ static void shrink_active_list(unsigned long nr_to_scan, __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken); spin_unlock_irq(&zone->lru_lock); - free_hot_cold_page_list(&l_hold, 1); + free_hot_cold_page_list(&l_hold, true); } #ifdef CONFIG_SWAP @@ -1847,7 +1848,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, struct zone *zone = lruvec_zone(lruvec); unsigned long anon_prio, file_prio; enum scan_balance scan_balance; - unsigned long anon, file, free; + unsigned long anon, file; bool force_scan = false; unsigned long ap, fp; enum lru_list lru; @@ -1895,11 +1896,6 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, goto out; } - anon = get_lru_size(lruvec, LRU_ACTIVE_ANON) + - get_lru_size(lruvec, LRU_INACTIVE_ANON); - file = get_lru_size(lruvec, LRU_ACTIVE_FILE) + - get_lru_size(lruvec, LRU_INACTIVE_FILE); - /* * If it's foreseeable that reclaiming the file cache won't be * enough to get the zone back into a desirable shape, we have @@ -1907,8 +1903,14 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * thrashing - remaining file pages alone. */ if (global_reclaim(sc)) { - free = zone_page_state(zone, NR_FREE_PAGES); - if (unlikely(file + free <= high_wmark_pages(zone))) { + unsigned long zonefile; + unsigned long zonefree; + + zonefree = zone_page_state(zone, NR_FREE_PAGES); + zonefile = zone_page_state(zone, NR_ACTIVE_FILE) + + zone_page_state(zone, NR_INACTIVE_FILE); + + if (unlikely(zonefile + zonefree <= high_wmark_pages(zone))) { scan_balance = SCAN_ANON; goto out; } @@ -1943,6 +1945,12 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * * anon in [0], file in [1] */ + + anon = get_lru_size(lruvec, LRU_ACTIVE_ANON) + + get_lru_size(lruvec, LRU_INACTIVE_ANON); + file = get_lru_size(lruvec, LRU_ACTIVE_FILE) + + get_lru_size(lruvec, LRU_INACTIVE_FILE); + spin_lock_irq(&zone->lru_lock); if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) { reclaim_stat->recent_scanned[0] /= 2; @@ -2018,13 +2026,27 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) unsigned long nr_reclaimed = 0; unsigned long nr_to_reclaim = sc->nr_to_reclaim; struct blk_plug plug; - bool scan_adjusted = false; + bool scan_adjusted; get_scan_count(lruvec, sc, nr); /* Record the original scan target for proportional adjustments later */ memcpy(targets, nr, sizeof(nr)); + /* + * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal + * event that can occur when there is little memory pressure e.g. + * multiple streaming readers/writers. Hence, we do not abort scanning + * when the requested number of pages are reclaimed when scanning at + * DEF_PRIORITY on the assumption that the fact we are direct + * reclaiming implies that kswapd is not keeping up and it is best to + * do a batch of work at once. For memcg reclaim one check is made to + * abort proportional reclaim if either the file or anon lru has already + * dropped to zero at the first pass. + */ + scan_adjusted = (global_reclaim(sc) && !current_is_kswapd() && + sc->priority == DEF_PRIORITY); + blk_start_plug(&plug); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || nr[LRU_INACTIVE_FILE]) { @@ -2045,17 +2067,8 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) continue; /* - * For global direct reclaim, reclaim only the number of pages - * requested. Less care is taken to scan proportionally as it - * is more important to minimise direct reclaim stall latency - * than it is to properly age the LRU lists. - */ - if (global_reclaim(sc) && !current_is_kswapd()) - break; - - /* * For kswapd and memcg, reclaim at least the number of pages - * requested. Ensure that the anon and file LRUs shrink + * requested. Ensure that the anon and file LRUs are scanned * proportionally what was requested by get_scan_count(). We * stop reclaiming one LRU and reduce the amount scanning * proportional to the original scan target. @@ -2063,6 +2076,15 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE]; nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON]; + /* + * It's just vindictive to attack the larger once the smaller + * has gone to zero. And given the way we stop scanning the + * smaller below, this makes sure that we only make one nudge + * towards proportionality once we've got nr_to_reclaim. + */ + if (!nr_file || !nr_anon) + break; + if (nr_file > nr_anon) { unsigned long scan_target = targets[LRU_INACTIVE_ANON] + targets[LRU_ACTIVE_ANON] + 1; @@ -2424,8 +2446,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, unsigned long lru_pages = 0; nodes_clear(shrink->nodes_to_scan); - for_each_zone_zonelist(zone, z, zonelist, - gfp_zone(sc->gfp_mask)) { + for_each_zone_zonelist_nodemask(zone, z, zonelist, + gfp_zone(sc->gfp_mask), sc->nodemask) { if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) continue; @@ -2846,18 +2868,20 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining, return false; /* - * There is a potential race between when kswapd checks its watermarks - * and a process gets throttled. There is also a potential race if - * processes get throttled, kswapd wakes, a large process exits therby - * balancing the zones that causes kswapd to miss a wakeup. If kswapd - * is going to sleep, no process should be sleeping on pfmemalloc_wait - * so wake them now if necessary. If necessary, processes will wake - * kswapd and get throttled again + * The throttled processes are normally woken up in balance_pgdat() as + * soon as pfmemalloc_watermark_ok() is true. But there is a potential + * race between when kswapd checks the watermarks and a process gets + * throttled. There is also a potential race if processes get + * throttled, kswapd wakes, a large process exits thereby balancing the + * zones, which causes kswapd to exit balance_pgdat() before reaching + * the wake up checks. If kswapd is going to sleep, no process should + * be sleeping on pfmemalloc_wait, so wake them now if necessary. If + * the wake up is premature, processes will wake kswapd and get + * throttled again. The difference from wake ups in balance_pgdat() is + * that here we are under prepare_to_wait(). */ - if (waitqueue_active(&pgdat->pfmemalloc_wait)) { - wake_up(&pgdat->pfmemalloc_wait); - return false; - } + if (waitqueue_active(&pgdat->pfmemalloc_wait)) + wake_up_all(&pgdat->pfmemalloc_wait); return pgdat_balanced(pgdat, order, classzone_idx); } diff --git a/mm/vmstat.c b/mm/vmstat.c index def5dd2fbe61..eded1909a690 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -200,7 +200,7 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat, continue; threshold = (*calculate_pressure)(zone); - for_each_possible_cpu(cpu) + for_each_online_cpu(cpu) per_cpu_ptr(zone->pageset, cpu)->stat_threshold = threshold; } @@ -761,6 +761,7 @@ const char * const vmstat_text[] = { "nr_shmem", "nr_dirtied", "nr_written", + "nr_pages_scanned", #ifdef CONFIG_NUMA "numa_hit", @@ -1055,7 +1056,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, min_wmark_pages(zone), low_wmark_pages(zone), high_wmark_pages(zone), - zone->pages_scanned, + zone_page_state(zone, NR_PAGES_SCANNED), zone->spanned_pages, zone->present_pages, zone->managed_pages); @@ -1065,10 +1066,10 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, zone_page_state(zone, i)); seq_printf(m, - "\n protection: (%lu", + "\n protection: (%ld", zone->lowmem_reserve[0]); for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++) - seq_printf(m, ", %lu", zone->lowmem_reserve[i]); + seq_printf(m, ", %ld", zone->lowmem_reserve[i]); seq_printf(m, ")" "\n pagesets"); diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 7e57135c7cc4..5d56e05d83dd 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -106,59 +106,6 @@ u16 vlan_dev_vlan_id(const struct net_device *dev) } EXPORT_SYMBOL(vlan_dev_vlan_id); -static struct sk_buff *vlan_reorder_header(struct sk_buff *skb) -{ - if (skb_cow(skb, skb_headroom(skb)) < 0) { - kfree_skb(skb); - return NULL; - } - - memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN); - skb->mac_header += VLAN_HLEN; - return skb; -} - -struct sk_buff *vlan_untag(struct sk_buff *skb) -{ - struct vlan_hdr *vhdr; - u16 vlan_tci; - - if (unlikely(vlan_tx_tag_present(skb))) { - /* vlan_tci is already set-up so leave this for another time */ - return skb; - } - - skb = skb_share_check(skb, GFP_ATOMIC); - if (unlikely(!skb)) - goto err_free; - - if (unlikely(!pskb_may_pull(skb, VLAN_HLEN))) - goto err_free; - - vhdr = (struct vlan_hdr *) skb->data; - vlan_tci = ntohs(vhdr->h_vlan_TCI); - __vlan_hwaccel_put_tag(skb, skb->protocol, vlan_tci); - - skb_pull_rcsum(skb, VLAN_HLEN); - vlan_set_encap_proto(skb, vhdr); - - skb = vlan_reorder_header(skb); - if (unlikely(!skb)) - goto err_free; - - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - skb_reset_mac_len(skb); - - return skb; - -err_free: - kfree_skb(skb); - return NULL; -} -EXPORT_SYMBOL(vlan_untag); - - /* * vlan info and vid list */ diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index c46387a46535..e5c5f573c0d4 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -251,7 +251,7 @@ batadv_frag_merge_packets(struct hlist_head *chain, struct sk_buff *skb) kfree(entry); /* Make room for the rest of the fragments. */ - if (pskb_expand_head(skb_out, 0, size - skb->len, GFP_ATOMIC) < 0) { + if (pskb_expand_head(skb_out, 0, size - skb_out->len, GFP_ATOMIC) < 0) { kfree_skb(skb_out); skb_out = NULL; goto free; @@ -434,7 +434,7 @@ bool batadv_frag_send_packet(struct sk_buff *skb, * fragments larger than BATADV_FRAG_MAX_FRAG_SIZE */ mtu = min_t(unsigned, mtu, BATADV_FRAG_MAX_FRAG_SIZE); - max_fragment_size = (mtu - header_size - ETH_HLEN); + max_fragment_size = mtu - header_size; max_packet_size = max_fragment_size * BATADV_FRAG_MAX_FRAGMENTS; /* Don't even try to fragment, if we need more than 16 fragments */ diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 36b9ae61f5e8..2393ea72d65f 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -812,7 +812,7 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, goto out; gw_node = batadv_gw_node_get(bat_priv, orig_dst_node); - if (!gw_node->bandwidth_down == 0) + if (!gw_node) goto out; switch (atomic_read(&bat_priv->gw_mode)) { diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index b851cc580853..fbda6b54baff 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -83,7 +83,7 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev) return true; /* no more parents..stop recursion */ - if (net_dev->iflink == net_dev->ifindex) + if (net_dev->iflink == 0 || net_dev->iflink == net_dev->ifindex) return false; /* recurse over the parent device */ diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 6afa3b45f25a..0007c9e9853a 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -2608,12 +2608,8 @@ static int l2cap_segment_le_sdu(struct l2cap_chan *chan, BT_DBG("chan %p, msg %p, len %zu", chan, msg, len); - pdu_len = chan->conn->mtu - L2CAP_HDR_SIZE; - - pdu_len = min_t(size_t, pdu_len, chan->remote_mps); - sdu_len = len; - pdu_len -= L2CAP_SDULEN_SIZE; + pdu_len = chan->remote_mps - L2CAP_SDULEN_SIZE; while (len > 0) { if (len <= pdu_len) diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index f2d254b69353..4acfc3eef56a 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -302,6 +302,9 @@ struct br_input_skb_cb { int igmp; int mrouters_only; #endif +#ifdef CONFIG_BRIDGE_VLAN_FILTERING + bool vlan_filtered; +#endif }; #define BR_INPUT_SKB_CB(__skb) ((struct br_input_skb_cb *)(__skb)->cb) diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index b1c637208497..e1bd2539f9dc 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -125,7 +125,8 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br, { u16 vid; - if (!br->vlan_enabled) + /* If this packet was not filtered at input, let it pass */ + if (!BR_INPUT_SKB_CB(skb)->vlan_filtered) goto out; /* Vlan filter table must be configured at this point. The @@ -163,8 +164,10 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, /* If VLAN filtering is disabled on the bridge, all packets are * permitted. */ - if (!br->vlan_enabled) + if (!br->vlan_enabled) { + BR_INPUT_SKB_CB(skb)->vlan_filtered = false; return true; + } /* If there are no vlan in the permitted list, all packets are * rejected. @@ -172,6 +175,8 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, if (!v) goto drop; + BR_INPUT_SKB_CB(skb)->vlan_filtered = true; + /* If vlan tx offload is disabled on bridge device and frame was * sent from vlan device on the bridge device, it does not have * HW accelerated vlan tag. @@ -179,7 +184,7 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, if (unlikely(!vlan_tx_tag_present(skb) && (skb->protocol == htons(ETH_P_8021Q) || skb->protocol == htons(ETH_P_8021AD)))) { - skb = vlan_untag(skb); + skb = skb_vlan_untag(skb); if (unlikely(!skb)) return false; } @@ -228,7 +233,8 @@ bool br_allowed_egress(struct net_bridge *br, { u16 vid; - if (!br->vlan_enabled) + /* If this packet was not filtered at input, let it pass */ + if (!BR_INPUT_SKB_CB(skb)->vlan_filtered) return true; if (!v) @@ -247,6 +253,7 @@ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid) struct net_bridge *br = p->br; struct net_port_vlans *v; + /* If filtering was disabled at input, let it pass. */ if (!br->vlan_enabled) return true; diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index d6be3edb7a43..526bf56f4d31 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -283,7 +283,7 @@ static int caif_seqpkt_recvmsg(struct kiocb *iocb, struct socket *sock, int copylen; ret = -EOPNOTSUPP; - if (m->msg_flags&MSG_OOB) + if (flags & MSG_OOB) goto read_error; skb = skb_recv_datagram(sk, flags, 0 , &ret); diff --git a/net/can/af_can.c b/net/can/af_can.c index a27f8aad9e99..5e9a2272b7a7 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -262,6 +262,9 @@ int can_send(struct sk_buff *skb, int loop) goto inval_skb; } + skb->ip_summed = CHECKSUM_UNNECESSARY; + + skb_reset_mac_header(skb); skb_reset_network_header(skb); skb_reset_transport_header(skb); diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c index 6e7a236525b6..06f19b9e159a 100644 --- a/net/ceph/crypto.c +++ b/net/ceph/crypto.c @@ -89,11 +89,82 @@ static struct crypto_blkcipher *ceph_crypto_alloc_cipher(void) static const u8 *aes_iv = (u8 *)CEPH_AES_IV; +/* + * Should be used for buffers allocated with ceph_kvmalloc(). + * Currently these are encrypt out-buffer (ceph_buffer) and decrypt + * in-buffer (msg front). + * + * Dispose of @sgt with teardown_sgtable(). + * + * @prealloc_sg is to avoid memory allocation inside sg_alloc_table() + * in cases where a single sg is sufficient. No attempt to reduce the + * number of sgs by squeezing physically contiguous pages together is + * made though, for simplicity. + */ +static int setup_sgtable(struct sg_table *sgt, struct scatterlist *prealloc_sg, + const void *buf, unsigned int buf_len) +{ + struct scatterlist *sg; + const bool is_vmalloc = is_vmalloc_addr(buf); + unsigned int off = offset_in_page(buf); + unsigned int chunk_cnt = 1; + unsigned int chunk_len = PAGE_ALIGN(off + buf_len); + int i; + int ret; + + if (buf_len == 0) { + memset(sgt, 0, sizeof(*sgt)); + return -EINVAL; + } + + if (is_vmalloc) { + chunk_cnt = chunk_len >> PAGE_SHIFT; + chunk_len = PAGE_SIZE; + } + + if (chunk_cnt > 1) { + ret = sg_alloc_table(sgt, chunk_cnt, GFP_NOFS); + if (ret) + return ret; + } else { + WARN_ON(chunk_cnt != 1); + sg_init_table(prealloc_sg, 1); + sgt->sgl = prealloc_sg; + sgt->nents = sgt->orig_nents = 1; + } + + for_each_sg(sgt->sgl, sg, sgt->orig_nents, i) { + struct page *page; + unsigned int len = min(chunk_len - off, buf_len); + + if (is_vmalloc) + page = vmalloc_to_page(buf); + else + page = virt_to_page(buf); + + sg_set_page(sg, page, len, off); + + off = 0; + buf += len; + buf_len -= len; + } + WARN_ON(buf_len != 0); + + return 0; +} + +static void teardown_sgtable(struct sg_table *sgt) +{ + if (sgt->orig_nents > 1) + sg_free_table(sgt); +} + static int ceph_aes_encrypt(const void *key, int key_len, void *dst, size_t *dst_len, const void *src, size_t src_len) { - struct scatterlist sg_in[2], sg_out[1]; + struct scatterlist sg_in[2], prealloc_sg; + struct sg_table sg_out; struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 }; int ret; @@ -109,16 +180,18 @@ static int ceph_aes_encrypt(const void *key, int key_len, *dst_len = src_len + zero_padding; - crypto_blkcipher_setkey((void *)tfm, key, key_len); sg_init_table(sg_in, 2); sg_set_buf(&sg_in[0], src, src_len); sg_set_buf(&sg_in[1], pad, zero_padding); - sg_init_table(sg_out, 1); - sg_set_buf(sg_out, dst, *dst_len); + ret = setup_sgtable(&sg_out, &prealloc_sg, dst, *dst_len); + if (ret) + goto out_tfm; + + crypto_blkcipher_setkey((void *)tfm, key, key_len); iv = crypto_blkcipher_crt(tfm)->iv; ivsize = crypto_blkcipher_ivsize(tfm); - memcpy(iv, aes_iv, ivsize); + /* print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1, key, key_len, 1); @@ -127,16 +200,22 @@ static int ceph_aes_encrypt(const void *key, int key_len, print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1, pad, zero_padding, 1); */ - ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in, + ret = crypto_blkcipher_encrypt(&desc, sg_out.sgl, sg_in, src_len + zero_padding); - crypto_free_blkcipher(tfm); - if (ret < 0) + if (ret < 0) { pr_err("ceph_aes_crypt failed %d\n", ret); + goto out_sg; + } /* print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1, dst, *dst_len, 1); */ - return 0; + +out_sg: + teardown_sgtable(&sg_out); +out_tfm: + crypto_free_blkcipher(tfm); + return ret; } static int ceph_aes_encrypt2(const void *key, int key_len, void *dst, @@ -144,7 +223,8 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst, const void *src1, size_t src1_len, const void *src2, size_t src2_len) { - struct scatterlist sg_in[3], sg_out[1]; + struct scatterlist sg_in[3], prealloc_sg; + struct sg_table sg_out; struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 }; int ret; @@ -160,17 +240,19 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst, *dst_len = src1_len + src2_len + zero_padding; - crypto_blkcipher_setkey((void *)tfm, key, key_len); sg_init_table(sg_in, 3); sg_set_buf(&sg_in[0], src1, src1_len); sg_set_buf(&sg_in[1], src2, src2_len); sg_set_buf(&sg_in[2], pad, zero_padding); - sg_init_table(sg_out, 1); - sg_set_buf(sg_out, dst, *dst_len); + ret = setup_sgtable(&sg_out, &prealloc_sg, dst, *dst_len); + if (ret) + goto out_tfm; + + crypto_blkcipher_setkey((void *)tfm, key, key_len); iv = crypto_blkcipher_crt(tfm)->iv; ivsize = crypto_blkcipher_ivsize(tfm); - memcpy(iv, aes_iv, ivsize); + /* print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1, key, key_len, 1); @@ -181,23 +263,30 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst, print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1, pad, zero_padding, 1); */ - ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in, + ret = crypto_blkcipher_encrypt(&desc, sg_out.sgl, sg_in, src1_len + src2_len + zero_padding); - crypto_free_blkcipher(tfm); - if (ret < 0) + if (ret < 0) { pr_err("ceph_aes_crypt2 failed %d\n", ret); + goto out_sg; + } /* print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1, dst, *dst_len, 1); */ - return 0; + +out_sg: + teardown_sgtable(&sg_out); +out_tfm: + crypto_free_blkcipher(tfm); + return ret; } static int ceph_aes_decrypt(const void *key, int key_len, void *dst, size_t *dst_len, const void *src, size_t src_len) { - struct scatterlist sg_in[1], sg_out[2]; + struct sg_table sg_in; + struct scatterlist sg_out[2], prealloc_sg; struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); struct blkcipher_desc desc = { .tfm = tfm }; char pad[16]; @@ -209,16 +298,16 @@ static int ceph_aes_decrypt(const void *key, int key_len, if (IS_ERR(tfm)) return PTR_ERR(tfm); - crypto_blkcipher_setkey((void *)tfm, key, key_len); - sg_init_table(sg_in, 1); sg_init_table(sg_out, 2); - sg_set_buf(sg_in, src, src_len); sg_set_buf(&sg_out[0], dst, *dst_len); sg_set_buf(&sg_out[1], pad, sizeof(pad)); + ret = setup_sgtable(&sg_in, &prealloc_sg, src, src_len); + if (ret) + goto out_tfm; + crypto_blkcipher_setkey((void *)tfm, key, key_len); iv = crypto_blkcipher_crt(tfm)->iv; ivsize = crypto_blkcipher_ivsize(tfm); - memcpy(iv, aes_iv, ivsize); /* @@ -227,12 +316,10 @@ static int ceph_aes_decrypt(const void *key, int key_len, print_hex_dump(KERN_ERR, "dec in: ", DUMP_PREFIX_NONE, 16, 1, src, src_len, 1); */ - - ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len); - crypto_free_blkcipher(tfm); + ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in.sgl, src_len); if (ret < 0) { pr_err("ceph_aes_decrypt failed %d\n", ret); - return ret; + goto out_sg; } if (src_len <= *dst_len) @@ -250,7 +337,12 @@ static int ceph_aes_decrypt(const void *key, int key_len, print_hex_dump(KERN_ERR, "dec out: ", DUMP_PREFIX_NONE, 16, 1, dst, *dst_len, 1); */ - return 0; + +out_sg: + teardown_sgtable(&sg_in); +out_tfm: + crypto_free_blkcipher(tfm); + return ret; } static int ceph_aes_decrypt2(const void *key, int key_len, @@ -258,7 +350,8 @@ static int ceph_aes_decrypt2(const void *key, int key_len, void *dst2, size_t *dst2_len, const void *src, size_t src_len) { - struct scatterlist sg_in[1], sg_out[3]; + struct sg_table sg_in; + struct scatterlist sg_out[3], prealloc_sg; struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); struct blkcipher_desc desc = { .tfm = tfm }; char pad[16]; @@ -270,17 +363,17 @@ static int ceph_aes_decrypt2(const void *key, int key_len, if (IS_ERR(tfm)) return PTR_ERR(tfm); - sg_init_table(sg_in, 1); - sg_set_buf(sg_in, src, src_len); sg_init_table(sg_out, 3); sg_set_buf(&sg_out[0], dst1, *dst1_len); sg_set_buf(&sg_out[1], dst2, *dst2_len); sg_set_buf(&sg_out[2], pad, sizeof(pad)); + ret = setup_sgtable(&sg_in, &prealloc_sg, src, src_len); + if (ret) + goto out_tfm; crypto_blkcipher_setkey((void *)tfm, key, key_len); iv = crypto_blkcipher_crt(tfm)->iv; ivsize = crypto_blkcipher_ivsize(tfm); - memcpy(iv, aes_iv, ivsize); /* @@ -289,12 +382,10 @@ static int ceph_aes_decrypt2(const void *key, int key_len, print_hex_dump(KERN_ERR, "dec in: ", DUMP_PREFIX_NONE, 16, 1, src, src_len, 1); */ - - ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len); - crypto_free_blkcipher(tfm); + ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in.sgl, src_len); if (ret < 0) { pr_err("ceph_aes_decrypt failed %d\n", ret); - return ret; + goto out_sg; } if (src_len <= *dst1_len) @@ -324,7 +415,11 @@ static int ceph_aes_decrypt2(const void *key, int key_len, dst2, *dst2_len, 1); */ - return 0; +out_sg: + teardown_sgtable(&sg_in); +out_tfm: + crypto_free_blkcipher(tfm); + return ret; } diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 0a31298737ac..2e87eecec8f6 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -291,7 +291,11 @@ int ceph_msgr_init(void) if (ceph_msgr_slab_init()) return -ENOMEM; - ceph_msgr_wq = alloc_workqueue("ceph-msgr", 0, 0); + /* + * The number of active work items is limited by the number of + * connections, so leave @max_active at default. + */ + ceph_msgr_wq = alloc_workqueue("ceph-msgr", WQ_MEM_RECLAIM, 0); if (ceph_msgr_wq) return 0; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 0676f2b199d6..45f077c60348 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -977,12 +977,24 @@ static void put_osd(struct ceph_osd *osd) */ static void __remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) { - dout("__remove_osd %p\n", osd); - BUG_ON(!list_empty(&osd->o_requests)); - rb_erase(&osd->o_node, &osdc->osds); + dout("%s %p osd%d\n", __func__, osd, osd->o_osd); + WARN_ON(!list_empty(&osd->o_requests)); + WARN_ON(!list_empty(&osd->o_linger_requests)); + list_del_init(&osd->o_osd_lru); - ceph_con_close(&osd->o_con); - put_osd(osd); + rb_erase(&osd->o_node, &osdc->osds); + RB_CLEAR_NODE(&osd->o_node); +} + +static void remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) +{ + dout("%s %p osd%d\n", __func__, osd, osd->o_osd); + + if (!RB_EMPTY_NODE(&osd->o_node)) { + ceph_con_close(&osd->o_con); + __remove_osd(osdc, osd); + put_osd(osd); + } } static void remove_all_osds(struct ceph_osd_client *osdc) @@ -992,7 +1004,7 @@ static void remove_all_osds(struct ceph_osd_client *osdc) while (!RB_EMPTY_ROOT(&osdc->osds)) { struct ceph_osd *osd = rb_entry(rb_first(&osdc->osds), struct ceph_osd, o_node); - __remove_osd(osdc, osd); + remove_osd(osdc, osd); } mutex_unlock(&osdc->request_mutex); } @@ -1022,7 +1034,7 @@ static void remove_old_osds(struct ceph_osd_client *osdc) list_for_each_entry_safe(osd, nosd, &osdc->osd_lru, o_osd_lru) { if (time_before(jiffies, osd->lru_ttl)) break; - __remove_osd(osdc, osd); + remove_osd(osdc, osd); } mutex_unlock(&osdc->request_mutex); } @@ -1037,8 +1049,7 @@ static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) dout("__reset_osd %p osd%d\n", osd, osd->o_osd); if (list_empty(&osd->o_requests) && list_empty(&osd->o_linger_requests)) { - __remove_osd(osdc, osd); - + remove_osd(osdc, osd); return -ENODEV; } @@ -1840,6 +1851,7 @@ static void reset_changed_osds(struct ceph_osd_client *osdc) { struct rb_node *p, *n; + dout("%s %p\n", __func__, osdc); for (p = rb_first(&osdc->osds); p; p = n) { struct ceph_osd *osd = rb_entry(p, struct ceph_osd, o_node); diff --git a/net/compat.c b/net/compat.c index cbc1a2a26587..d12529050b29 100644 --- a/net/compat.c +++ b/net/compat.c @@ -71,6 +71,13 @@ int get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg) __get_user(kmsg->msg_controllen, &umsg->msg_controllen) || __get_user(kmsg->msg_flags, &umsg->msg_flags)) return -EFAULT; + + if (!tmp1) + kmsg->msg_namelen = 0; + + if (kmsg->msg_namelen < 0) + return -EINVAL; + if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) kmsg->msg_namelen = sizeof(struct sockaddr_storage); kmsg->msg_name = compat_ptr(tmp1); @@ -738,24 +745,18 @@ static unsigned char nas[21] = { asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags) { - if (flags & MSG_CMSG_COMPAT) - return -EINVAL; return __sys_sendmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); } asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags) { - if (flags & MSG_CMSG_COMPAT) - return -EINVAL; return __sys_sendmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, flags | MSG_CMSG_COMPAT); } asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags) { - if (flags & MSG_CMSG_COMPAT) - return -EINVAL; return __sys_recvmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); } @@ -778,9 +779,6 @@ asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, int datagrams; struct timespec ktspec; - if (flags & MSG_CMSG_COMPAT) - return -EINVAL; - if (timeout == NULL) return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, flags | MSG_CMSG_COMPAT, NULL); diff --git a/net/core/dev.c b/net/core/dev.c index 37bddf729e77..f6d8d7fe29ab 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -940,7 +940,7 @@ bool dev_valid_name(const char *name) return false; while (*name) { - if (*name == '/' || isspace(*name)) + if (*name == '/' || *name == ':' || isspace(*name)) return false; name++; } @@ -1709,6 +1709,7 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) skb_scrub_packet(skb, true); skb->protocol = eth_type_trans(skb, dev); + skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); return netif_rx_internal(skb); } @@ -2529,11 +2530,14 @@ netdev_features_t netif_skb_dev_features(struct sk_buff *skb, if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs) features &= ~NETIF_F_GSO_MASK; - if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) { - struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; - protocol = veh->h_vlan_encapsulated_proto; - } else if (!vlan_tx_tag_present(skb)) { - return harmonize_features(skb, dev, features); + if (!vlan_tx_tag_present(skb)) { + if (unlikely(protocol == htons(ETH_P_8021Q) || + protocol == htons(ETH_P_8021AD))) { + struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; + protocol = veh->h_vlan_encapsulated_proto; + } else { + return harmonize_features(skb, dev, features); + } } features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | @@ -3554,7 +3558,7 @@ another_round: if (skb->protocol == cpu_to_be16(ETH_P_8021Q) || skb->protocol == cpu_to_be16(ETH_P_8021AD)) { - skb = vlan_untag(skb); + skb = skb_vlan_untag(skb); if (unlikely(!skb)) goto unlock; } @@ -4701,9 +4705,14 @@ static void netdev_adjacent_sysfs_del(struct net_device *dev, sysfs_remove_link(&(dev->dev.kobj), linkname); } -#define netdev_adjacent_is_neigh_list(dev, dev_list) \ - (dev_list == &dev->adj_list.upper || \ - dev_list == &dev->adj_list.lower) +static inline bool netdev_adjacent_is_neigh_list(struct net_device *dev, + struct net_device *adj_dev, + struct list_head *dev_list) +{ + return (dev_list == &dev->adj_list.upper || + dev_list == &dev->adj_list.lower) && + net_eq(dev_net(dev), dev_net(adj_dev)); +} static int __netdev_adjacent_dev_insert(struct net_device *dev, struct net_device *adj_dev, @@ -4733,7 +4742,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, pr_debug("dev_hold for %s, because of link added from %s to %s\n", adj_dev->name, dev->name, adj_dev->name); - if (netdev_adjacent_is_neigh_list(dev, dev_list)) { + if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) { ret = netdev_adjacent_sysfs_add(dev, adj_dev, dev_list); if (ret) goto free_adj; @@ -4754,7 +4763,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, return 0; remove_symlinks: - if (netdev_adjacent_is_neigh_list(dev, dev_list)) + if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); free_adj: kfree(adj); @@ -4787,7 +4796,7 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev, if (adj->master) sysfs_remove_link(&(dev->dev.kobj), "master"); - if (netdev_adjacent_is_neigh_list(dev, dev_list)) + if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); list_del_rcu(&adj->list); @@ -5057,11 +5066,65 @@ void netdev_upper_dev_unlink(struct net_device *dev, } EXPORT_SYMBOL(netdev_upper_dev_unlink); +void netdev_adjacent_add_links(struct net_device *dev) +{ + struct netdev_adjacent *iter; + + struct net *net = dev_net(dev); + + list_for_each_entry(iter, &dev->adj_list.upper, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; + netdev_adjacent_sysfs_add(iter->dev, dev, + &iter->dev->adj_list.lower); + netdev_adjacent_sysfs_add(dev, iter->dev, + &dev->adj_list.upper); + } + + list_for_each_entry(iter, &dev->adj_list.lower, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; + netdev_adjacent_sysfs_add(iter->dev, dev, + &iter->dev->adj_list.upper); + netdev_adjacent_sysfs_add(dev, iter->dev, + &dev->adj_list.lower); + } +} + +void netdev_adjacent_del_links(struct net_device *dev) +{ + struct netdev_adjacent *iter; + + struct net *net = dev_net(dev); + + list_for_each_entry(iter, &dev->adj_list.upper, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; + netdev_adjacent_sysfs_del(iter->dev, dev->name, + &iter->dev->adj_list.lower); + netdev_adjacent_sysfs_del(dev, iter->dev->name, + &dev->adj_list.upper); + } + + list_for_each_entry(iter, &dev->adj_list.lower, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; + netdev_adjacent_sysfs_del(iter->dev, dev->name, + &iter->dev->adj_list.upper); + netdev_adjacent_sysfs_del(dev, iter->dev->name, + &dev->adj_list.lower); + } +} + void netdev_adjacent_rename_links(struct net_device *dev, char *oldname) { struct netdev_adjacent *iter; + struct net *net = dev_net(dev); + list_for_each_entry(iter, &dev->adj_list.upper, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; netdev_adjacent_sysfs_del(iter->dev, oldname, &iter->dev->adj_list.lower); netdev_adjacent_sysfs_add(iter->dev, dev, @@ -5069,6 +5132,8 @@ void netdev_adjacent_rename_links(struct net_device *dev, char *oldname) } list_for_each_entry(iter, &dev->adj_list.lower, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; netdev_adjacent_sysfs_del(iter->dev, oldname, &iter->dev->adj_list.upper); netdev_adjacent_sysfs_add(iter->dev, dev, @@ -6675,6 +6740,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* Send a netdev-removed uevent to the old namespace */ kobject_uevent(&dev->dev.kobj, KOBJ_REMOVE); + netdev_adjacent_del_links(dev); /* Actually switch the network namespace */ dev_net_set(dev, net); @@ -6689,6 +6755,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* Send a netdev-add uevent to the new namespace */ kobject_uevent(&dev->dev.kobj, KOBJ_ADD); + netdev_adjacent_add_links(dev); /* Fixup kobjects */ err = device_rename(&dev->dev, dev->name); @@ -6745,10 +6812,20 @@ static int dev_cpu_callback(struct notifier_block *nfb, oldsd->output_queue = NULL; oldsd->output_queue_tailp = &oldsd->output_queue; } - /* Append NAPI poll list from offline CPU. */ - if (!list_empty(&oldsd->poll_list)) { - list_splice_init(&oldsd->poll_list, &sd->poll_list); - raise_softirq_irqoff(NET_RX_SOFTIRQ); + /* Append NAPI poll list from offline CPU, with one exception : + * process_backlog() must be called by cpu owning percpu backlog. + * We properly handle process_queue & input_pkt_queue later. + */ + while (!list_empty(&oldsd->poll_list)) { + struct napi_struct *napi = list_first_entry(&oldsd->poll_list, + struct napi_struct, + poll_list); + + list_del_init(&napi->poll_list); + if (napi->poll == process_backlog) + napi->state = 0; + else + ____napi_schedule(sd, napi); } raise_softirq_irqoff(NET_TX_SOFTIRQ); @@ -6759,7 +6836,7 @@ static int dev_cpu_callback(struct notifier_block *nfb, netif_rx_internal(skb); input_queue_head_incr(oldsd); } - while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { + while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) { netif_rx_internal(skb); input_queue_head_incr(oldsd); } diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index 9d3d9e78397b..372ac662adf9 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -32,6 +32,9 @@ gnet_stats_copy(struct gnet_dump *d, int type, void *buf, int size) return 0; nla_put_failure: + kfree(d->xstats); + d->xstats = NULL; + d->xstats_len = 0; spin_unlock_bh(d->lock); return -1; } @@ -217,7 +220,9 @@ int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len) { if (d->compat_xstats) { - d->xstats = st; + d->xstats = kmemdup(st, len, GFP_ATOMIC); + if (!d->xstats) + goto err_out; d->xstats_len = len; } @@ -225,6 +230,11 @@ gnet_stats_copy_app(struct gnet_dump *d, void *st, int len) return gnet_stats_copy(d, TCA_STATS_APP, st, len); return 0; + +err_out: + d->xstats_len = 0; + spin_unlock_bh(d->lock); + return -1; } EXPORT_SYMBOL(gnet_stats_copy_app); @@ -257,6 +267,9 @@ gnet_stats_finish_copy(struct gnet_dump *d) return -1; } + kfree(d->xstats); + d->xstats = NULL; + d->xstats_len = 0; spin_unlock_bh(d->lock); return 0; } diff --git a/net/core/netpoll.c b/net/core/netpoll.c index df9e6b1a9759..723fa7da8025 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -788,7 +788,7 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) } if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) { - skb = vlan_untag(skb); + skb = skb_vlan_untag(skb); if (unlikely(!skb)) goto out; } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index fdac61cac1bd..ca68d32b49ba 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2812,25 +2812,25 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, skb->dev = odev; skb->pkt_type = PACKET_HOST; + pktgen_finalize_skb(pkt_dev, skb, datalen); + if (!(pkt_dev->flags & F_UDPCSUM)) { skb->ip_summed = CHECKSUM_NONE; } else if (odev->features & NETIF_F_V4_CSUM) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; - udp4_hwcsum(skb, udph->source, udph->dest); + udp4_hwcsum(skb, iph->saddr, iph->daddr); } else { - __wsum csum = udp_csum(skb); + __wsum csum = skb_checksum(skb, skb_transport_offset(skb), datalen + 8, 0); /* add protocol-dependent pseudo-header */ - udph->check = csum_tcpudp_magic(udph->source, udph->dest, + udph->check = csum_tcpudp_magic(iph->saddr, iph->daddr, datalen + 8, IPPROTO_UDP, csum); if (udph->check == 0) udph->check = CSUM_MANGLED_0; } - pktgen_finalize_skb(pkt_dev, skb, datalen); - #ifdef CONFIG_XFRM if (!process_ipsec(pkt_dev, skb, protocol)) return NULL; @@ -2946,6 +2946,8 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, skb->dev = odev; skb->pkt_type = PACKET_HOST; + pktgen_finalize_skb(pkt_dev, skb, datalen); + if (!(pkt_dev->flags & F_UDPCSUM)) { skb->ip_summed = CHECKSUM_NONE; } else if (odev->features & NETIF_F_V6_CSUM) { @@ -2954,7 +2956,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, skb->csum_offset = offsetof(struct udphdr, check); udph->check = ~csum_ipv6_magic(&iph->saddr, &iph->daddr, udplen, IPPROTO_UDP, 0); } else { - __wsum csum = udp_csum(skb); + __wsum csum = skb_checksum(skb, skb_transport_offset(skb), udplen, 0); /* add protocol-dependent pseudo-header */ udph->check = csum_ipv6_magic(&iph->saddr, &iph->daddr, udplen, IPPROTO_UDP, csum); @@ -2963,8 +2965,6 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, udph->check = CSUM_MANGLED_0; } - pktgen_finalize_skb(pkt_dev, skb, datalen); - return skb; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index aef1500ebc05..8aadd6a072a4 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -799,7 +799,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, (nla_total_size(sizeof(struct ifla_vf_mac)) + nla_total_size(sizeof(struct ifla_vf_vlan)) + nla_total_size(sizeof(struct ifla_vf_tx_rate)) + - nla_total_size(sizeof(struct ifla_vf_spoofchk))); + nla_total_size(sizeof(struct ifla_vf_spoofchk)) + + nla_total_size(sizeof(struct ifla_vf_link_state))); return size; } else return 0; @@ -1263,14 +1264,10 @@ static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = { }; static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { - [IFLA_VF_MAC] = { .type = NLA_BINARY, - .len = sizeof(struct ifla_vf_mac) }, - [IFLA_VF_VLAN] = { .type = NLA_BINARY, - .len = sizeof(struct ifla_vf_vlan) }, - [IFLA_VF_TX_RATE] = { .type = NLA_BINARY, - .len = sizeof(struct ifla_vf_tx_rate) }, - [IFLA_VF_SPOOFCHK] = { .type = NLA_BINARY, - .len = sizeof(struct ifla_vf_spoofchk) }, + [IFLA_VF_MAC] = { .len = sizeof(struct ifla_vf_mac) }, + [IFLA_VF_VLAN] = { .len = sizeof(struct ifla_vf_vlan) }, + [IFLA_VF_TX_RATE] = { .len = sizeof(struct ifla_vf_tx_rate) }, + [IFLA_VF_SPOOFCHK] = { .len = sizeof(struct ifla_vf_spoofchk) }, }; static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { @@ -1452,6 +1449,7 @@ static int do_setlink(const struct sk_buff *skb, goto errout; } if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { + put_net(net); err = -EPERM; goto errout; } @@ -2032,8 +2030,16 @@ replay: } } err = rtnl_configure_link(dev, ifm); - if (err < 0) - unregister_netdevice(dev); + if (err < 0) { + if (ops->newlink) { + LIST_HEAD(list_kill); + + ops->dellink(dev, &list_kill); + unregister_netdevice_many(&list_kill); + } else { + unregister_netdevice(dev); + } + } out: put_net(dest_net); return err; @@ -2647,12 +2653,16 @@ static int rtnl_bridge_notify(struct net_device *dev, u16 flags) goto errout; } + if (!skb->len) + goto errout; + rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); return 0; errout: WARN_ON(err == -EMSGSIZE); kfree_skb(skb); - rtnl_set_sk_err(net, RTNLGRP_LINK, err); + if (err) + rtnl_set_sk_err(net, RTNLGRP_LINK, err); return err; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 8f6391bbf509..e2b1bba69882 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -62,6 +62,7 @@ #include <linux/scatterlist.h> #include <linux/errqueue.h> #include <linux/prefetch.h> +#include <linux/if_vlan.h> #include <net/protocol.h> #include <net/dst.h> @@ -3139,6 +3140,9 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD; goto done; } + /* switch back to head shinfo */ + pinfo = skb_shinfo(p); + if (pinfo->frag_list) goto merge; if (skb_gro_len(p) != pinfo->gso_size) @@ -3933,6 +3937,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) skb->local_df = 0; skb_dst_drop(skb); skb->mark = 0; + skb_init_secmark(skb); secpath_reset(skb); nf_reset(skb); nf_reset_trace(skb); @@ -3963,3 +3968,55 @@ unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) return shinfo->gso_size; } EXPORT_SYMBOL_GPL(skb_gso_transport_seglen); + +static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) +{ + if (skb_cow(skb, skb_headroom(skb)) < 0) { + kfree_skb(skb); + return NULL; + } + + memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN); + skb->mac_header += VLAN_HLEN; + return skb; +} + +struct sk_buff *skb_vlan_untag(struct sk_buff *skb) +{ + struct vlan_hdr *vhdr; + u16 vlan_tci; + + if (unlikely(vlan_tx_tag_present(skb))) { + /* vlan_tci is already set-up so leave this for another time */ + return skb; + } + + skb = skb_share_check(skb, GFP_ATOMIC); + if (unlikely(!skb)) + goto err_free; + + if (unlikely(!pskb_may_pull(skb, VLAN_HLEN))) + goto err_free; + + vhdr = (struct vlan_hdr *)skb->data; + vlan_tci = ntohs(vhdr->h_vlan_TCI); + __vlan_hwaccel_put_tag(skb, skb->protocol, vlan_tci); + + skb_pull_rcsum(skb, VLAN_HLEN); + vlan_set_encap_proto(skb, vhdr); + + skb = skb_reorder_vlan_header(skb); + if (unlikely(!skb)) + goto err_free; + + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + skb_reset_mac_len(skb); + + return skb; + +err_free: + kfree_skb(skb); + return NULL; +} +EXPORT_SYMBOL(skb_vlan_untag); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index cf9cd13509a7..e731c96eac4b 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -25,6 +25,8 @@ static int zero = 0; static int one = 1; static int ushort_max = USHRT_MAX; +static int min_sndbuf = SOCK_MIN_SNDBUF; +static int min_rcvbuf = SOCK_MIN_RCVBUF; #ifdef CONFIG_RPS static int rps_sock_flow_sysctl(struct ctl_table *table, int write, @@ -223,7 +225,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_sndbuf, }, { .procname = "rmem_max", @@ -231,7 +233,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_rcvbuf, }, { .procname = "wmem_default", @@ -239,7 +241,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_sndbuf, }, { .procname = "rmem_default", @@ -247,7 +249,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_rcvbuf, }, { .procname = "dev_weight", diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index f2e15738534d..8f7bd56955b0 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -62,6 +62,10 @@ int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res) else res->tclassid = 0; #endif + + if (err == -ESRCH) + err = -ENETUNREACH; + return err; } EXPORT_SYMBOL_GPL(__fib_lookup); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 9d43468722ed..017fa5e17594 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -535,7 +535,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) return 1; attrlen = rtnh_attrlen(rtnh); - if (attrlen < 0) { + if (attrlen > 0) { struct nlattr *nla, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 2d24f293f977..278836f1a5ad 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -50,7 +50,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, greh = (struct gre_base_hdr *)skb_transport_header(skb); - ghl = skb_inner_network_header(skb) - skb_transport_header(skb); + ghl = skb_inner_mac_header(skb) - skb_transport_header(skb); if (unlikely(ghl < sizeof(*greh))) goto out; @@ -271,6 +271,9 @@ static int gre_gro_complete(struct sk_buff *skb, int nhoff) err = ptype->callbacks.gro_complete(skb, nhoff + grehlen); rcu_read_unlock(); + + skb_set_inner_mac_header(skb, nhoff + grehlen); + return err; } diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index e34dccbc4d70..4eeba4e497a0 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -71,6 +71,20 @@ static inline void inet_diag_unlock_handler( mutex_unlock(&inet_diag_table_mutex); } +static size_t inet_sk_attr_size(void) +{ + return nla_total_size(sizeof(struct tcp_info)) + + nla_total_size(1) /* INET_DIAG_SHUTDOWN */ + + nla_total_size(1) /* INET_DIAG_TOS */ + + nla_total_size(1) /* INET_DIAG_TCLASS */ + + nla_total_size(sizeof(struct inet_diag_meminfo)) + + nla_total_size(sizeof(struct inet_diag_msg)) + + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) + + nla_total_size(TCP_CA_NAME_MAX) + + nla_total_size(sizeof(struct tcpvegas_info)) + + 64; +} + int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct sk_buff *skb, struct inet_diag_req_v2 *req, struct user_namespace *user_ns, @@ -324,9 +338,7 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_s if (err) goto out; - rep = nlmsg_new(sizeof(struct inet_diag_msg) + - sizeof(struct inet_diag_meminfo) + - sizeof(struct tcp_info) + 64, GFP_KERNEL); + rep = nlmsg_new(inet_sk_attr_size(), GFP_KERNEL); if (!rep) { err = -ENOMEM; goto out; diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 1c6bd4359cbd..ecb34b5ea42f 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -178,7 +178,8 @@ int ip_forward(struct sk_buff *skb) * We now generate an ICMP HOST REDIRECT giving the route * we calculated. */ - if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb)) + if (IPCB(skb)->flags & IPSKB_DOREDIRECT && !opt->srr && + !skb_sec_path(skb)) ip_rt_send_redirect(skb); skb->priority = rt_tos2priority(iph->tos); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index c10a3ce5cbff..9ff497d17545 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -679,27 +679,30 @@ EXPORT_SYMBOL(ip_defrag); struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user) { struct iphdr iph; + int netoff; u32 len; if (skb->protocol != htons(ETH_P_IP)) return skb; - if (!skb_copy_bits(skb, 0, &iph, sizeof(iph))) + netoff = skb_network_offset(skb); + + if (skb_copy_bits(skb, netoff, &iph, sizeof(iph)) < 0) return skb; if (iph.ihl < 5 || iph.version != 4) return skb; len = ntohs(iph.tot_len); - if (skb->len < len || len < (iph.ihl * 4)) + if (skb->len < netoff + len || len < (iph.ihl * 4)) return skb; if (ip_is_fragment(&iph)) { skb = skb_share_check(skb, GFP_ATOMIC); if (skb) { - if (!pskb_may_pull(skb, iph.ihl*4)) + if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) return skb; - if (pskb_trim_rcsum(skb, len)) + if (pskb_trim_rcsum(skb, netoff + len)) return skb; memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); if (ip_defrag(skb, user)) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 94213c891565..b40b90d3bd2b 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -250,10 +250,6 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tnl_params; - skb = gre_handle_offloads(skb, !!(tunnel->parms.o_flags&TUNNEL_CSUM)); - if (IS_ERR(skb)) - goto out; - if (dev->header_ops) { /* Need space for new headers */ if (skb_cow_head(skb, dev->needed_headroom - @@ -266,6 +262,7 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, * to gre header. */ skb_pull(skb, tunnel->hlen + sizeof(struct iphdr)); + skb_reset_mac_header(skb); } else { if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; @@ -273,6 +270,10 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, tnl_params = &tunnel->parms.iph; } + skb = gre_handle_offloads(skb, !!(tunnel->parms.o_flags&TUNNEL_CSUM)); + if (IS_ERR(skb)) + goto out; + __gre_xmit(skb, dev, tnl_params, skb->protocol); return NETDEV_TX_OK; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index ed88d781248f..05686c47a289 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -843,7 +843,8 @@ static int __ip_append_data(struct sock *sk, cork->length += length; if (((length > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && - (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len) { + (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len && + (sk->sk_type == SOCK_DGRAM)) { err = ip_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, maxfraglen, flags); @@ -1460,23 +1461,8 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset, /* * Generic function to send a packet as reply to another packet. * Used to send some TCP resets/acks so far. - * - * Use a fake percpu inet socket to avoid false sharing and contention. */ -static DEFINE_PER_CPU(struct inet_sock, unicast_sock) = { - .sk = { - .__sk_common = { - .skc_refcnt = ATOMIC_INIT(1), - }, - .sk_wmem_alloc = ATOMIC_INIT(1), - .sk_allocation = GFP_ATOMIC, - .sk_flags = (1UL << SOCK_USE_WRITE_QUEUE), - }, - .pmtudisc = IP_PMTUDISC_WANT, - .uc_ttl = -1, -}; - -void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, +void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, unsigned int len) { @@ -1484,9 +1470,9 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, struct ipcm_cookie ipc; struct flowi4 fl4; struct rtable *rt = skb_rtable(skb); + struct net *net = sock_net(sk); struct sk_buff *nskb; - struct sock *sk; - struct inet_sock *inet; + int err; if (ip_options_echo(&replyopts.opt.opt, skb)) return; @@ -1515,18 +1501,19 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, if (IS_ERR(rt)) return; - inet = &get_cpu_var(unicast_sock); + inet_sk(sk)->tos = arg->tos; - inet->tos = arg->tos; - sk = &inet->sk; sk->sk_priority = skb->priority; sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; - sock_net_set(sk, net); - __skb_queue_head_init(&sk->sk_write_queue); sk->sk_sndbuf = sysctl_wmem_default; - ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, - &ipc, &rt, MSG_DONTWAIT); + err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, + len, 0, &ipc, &rt, MSG_DONTWAIT); + if (unlikely(err)) { + ip_flush_pending_frames(sk); + goto out; + } + nskb = skb_peek(&sk->sk_write_queue); if (nskb) { if (arg->csumoffset >= 0) @@ -1534,13 +1521,10 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, arg->csumoffset) = csum_fold(csum_add(nskb->csum, arg->csum)); nskb->ip_summed = CHECKSUM_NONE; - skb_orphan(nskb); skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb)); ip_push_pending_frames(sk, &fl4); } - - put_cpu_var(unicast_sock); - +out: ip_rt_put(rt); } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 580dd96666e0..135045e0e125 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -426,15 +426,11 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); sin = &errhdr.offender; - sin->sin_family = AF_UNSPEC; + memset(sin, 0, sizeof(*sin)); if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP) { - struct inet_sock *inet = inet_sk(sk); - sin->sin_family = AF_INET; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; - sin->sin_port = 0; - memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); - if (inet->cmsg_flags) + if (inet_sk(sk)->cmsg_flags) ip_cmsg_recv(msg, skb); } diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 65b664d30fa1..791a419f0699 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -91,11 +91,12 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto) skb_pull_rcsum(skb, hdr_len); if (inner_proto == htons(ETH_P_TEB)) { - struct ethhdr *eh = (struct ethhdr *)skb->data; + struct ethhdr *eh; if (unlikely(!pskb_may_pull(skb, ETH_HLEN))) return -ENOMEM; + eh = (struct ethhdr *)skb->data; if (likely(ntohs(eh->h_proto) >= ETH_P_802_3_MIN)) skb->protocol = eh->h_proto; else diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index e4a8f76c8995..b0a9cb4bbfdb 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -369,6 +369,7 @@ static struct rtnl_link_ops vti_link_ops __read_mostly = { .validate = vti_tunnel_validate, .newlink = vti_newlink, .changelink = vti_changelink, + .dellink = ip_tunnel_dellink, .get_size = vti_get_size, .fill_info = vti_fill_info, }; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index e21934b06d4c..b94002ab8052 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -217,6 +217,8 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident) &ipv6_hdr(skb)->daddr)) continue; #endif + } else { + continue; } if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) @@ -257,6 +259,10 @@ int ping_init_sock(struct sock *sk) kgid_t low, high; int ret = 0; +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) + inet6_sk(sk)->ipv6only = 1; +#endif inet_get_ping_group_range_net(net, &low, &high); if (gid_lte(low, group) && gid_lte(group, high)) return 0; @@ -303,6 +309,11 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, if (addr_len < sizeof(*addr)) return -EINVAL; + if (addr->sin_family != AF_INET && + !(addr->sin_family == AF_UNSPEC && + addr->sin_addr.s_addr == htonl(INADDR_ANY))) + return -EAFNOSUPPORT; + pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n", sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port)); @@ -328,7 +339,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, return -EINVAL; if (addr->sin6_family != AF_INET6) - return -EINVAL; + return -EAFNOSUPPORT; pr_debug("ping_check_bind_addr(sk=%p,addr=%pI6c,port=%d)\n", sk, addr->sin6_addr.s6_addr, ntohs(addr->sin6_port)); @@ -714,7 +725,7 @@ static int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m if (msg->msg_namelen < sizeof(*usin)) return -EINVAL; if (usin->sin_family != AF_INET) - return -EINVAL; + return -EAFNOSUPPORT; daddr = usin->sin_addr.s_addr; /* no remote port */ } else { @@ -971,8 +982,11 @@ void ping_rcv(struct sk_buff *skb) sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id)); if (sk != NULL) { + struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); + pr_debug("rcv on socket %p\n", sk); - ping_queue_rcv_skb(sk, skb_get(skb)); + if (skb2) + ping_queue_rcv_skb(sk, skb2); sock_put(sk); return; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ca5a01ed8ed6..b64330f25fbe 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1554,11 +1554,10 @@ static int __mkroute_input(struct sk_buff *skb, do_cache = res->fi && !itag; if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) && + skb->protocol == htons(ETH_P_IP) && (IN_DEV_SHARED_MEDIA(out_dev) || - inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) { - flags |= RTCF_DOREDIRECT; - do_cache = false; - } + inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) + IPCB(skb)->flags |= IPSKB_DOREDIRECT; if (skb->protocol != htons(ETH_P_IP)) { /* Not IP (i.e. ARP). Do not create route, if it is @@ -2268,9 +2267,9 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, return rt; if (flp4->flowi4_proto) - rt = (struct rtable *) xfrm_lookup(net, &rt->dst, - flowi4_to_flowi(flp4), - sk, 0); + rt = (struct rtable *)xfrm_lookup_route(net, &rt->dst, + flowi4_to_flowi(flp4), + sk, 0); return rt; } @@ -2305,6 +2304,8 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED; if (rt->rt_flags & RTCF_NOTIFY) r->rtm_flags |= RTM_F_NOTIFY; + if (IPCB(skb)->flags & IPSKB_DOREDIRECT) + r->rtm_flags |= RTCF_DOREDIRECT; if (nla_put_be32(skb, RTA_DST, dst)) goto nla_put_failure; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b48fba0aaa92..29d240b87af1 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1175,13 +1175,6 @@ new_segment: goto wait_for_memory; /* - * All packets are restored as if they have - * already been sent. - */ - if (tp->repair) - TCP_SKB_CB(skb)->when = tcp_time_stamp; - - /* * Check whether we can use HW checksum. */ if (sk->sk_route_caps & NETIF_F_ALL_CSUM) @@ -1190,6 +1183,13 @@ new_segment: skb_entail(sk, skb); copy = size_goal; max = size_goal; + + /* All packets are restored as if they have + * already been sent. skb_mstamp isn't set to + * avoid wrong rtt estimation. + */ + if (tp->repair) + TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED; } /* Try to append data to the end of skb. */ @@ -2954,61 +2954,42 @@ EXPORT_SYMBOL(compat_tcp_getsockopt); #endif #ifdef CONFIG_TCP_MD5SIG -static struct tcp_md5sig_pool __percpu *tcp_md5sig_pool __read_mostly; +static DEFINE_PER_CPU(struct tcp_md5sig_pool, tcp_md5sig_pool); static DEFINE_MUTEX(tcp_md5sig_mutex); - -static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool __percpu *pool) -{ - int cpu; - - for_each_possible_cpu(cpu) { - struct tcp_md5sig_pool *p = per_cpu_ptr(pool, cpu); - - if (p->md5_desc.tfm) - crypto_free_hash(p->md5_desc.tfm); - } - free_percpu(pool); -} +static bool tcp_md5sig_pool_populated = false; static void __tcp_alloc_md5sig_pool(void) { int cpu; - struct tcp_md5sig_pool __percpu *pool; - - pool = alloc_percpu(struct tcp_md5sig_pool); - if (!pool) - return; for_each_possible_cpu(cpu) { - struct crypto_hash *hash; - - hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC); - if (IS_ERR_OR_NULL(hash)) - goto out_free; + if (!per_cpu(tcp_md5sig_pool, cpu).md5_desc.tfm) { + struct crypto_hash *hash; - per_cpu_ptr(pool, cpu)->md5_desc.tfm = hash; + hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR_OR_NULL(hash)) + return; + per_cpu(tcp_md5sig_pool, cpu).md5_desc.tfm = hash; + } } - /* before setting tcp_md5sig_pool, we must commit all writes - * to memory. See ACCESS_ONCE() in tcp_get_md5sig_pool() + /* before setting tcp_md5sig_pool_populated, we must commit all writes + * to memory. See smp_rmb() in tcp_get_md5sig_pool() */ smp_wmb(); - tcp_md5sig_pool = pool; - return; -out_free: - __tcp_free_md5sig_pool(pool); + tcp_md5sig_pool_populated = true; } bool tcp_alloc_md5sig_pool(void) { - if (unlikely(!tcp_md5sig_pool)) { + if (unlikely(!tcp_md5sig_pool_populated)) { mutex_lock(&tcp_md5sig_mutex); - if (!tcp_md5sig_pool) + if (!tcp_md5sig_pool_populated) __tcp_alloc_md5sig_pool(); mutex_unlock(&tcp_md5sig_mutex); } - return tcp_md5sig_pool != NULL; + return tcp_md5sig_pool_populated; } EXPORT_SYMBOL(tcp_alloc_md5sig_pool); @@ -3022,13 +3003,13 @@ EXPORT_SYMBOL(tcp_alloc_md5sig_pool); */ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void) { - struct tcp_md5sig_pool __percpu *p; - local_bh_disable(); - p = ACCESS_ONCE(tcp_md5sig_pool); - if (p) - return __this_cpu_ptr(p); + if (tcp_md5sig_pool_populated) { + /* coupled with smp_wmb() in __tcp_alloc_md5sig_pool() */ + smp_rmb(); + return this_cpu_ptr(&tcp_md5sig_pool); + } local_bh_enable(); return NULL; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3898694d0300..22917918fa80 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2678,7 +2678,6 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack) */ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) { - struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); bool recovered = !before(tp->snd_una, tp->high_seq); @@ -2704,12 +2703,9 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) if (recovered) { /* F-RTO RFC5682 sec 3.1 step 2.a and 1st part of step 3.a */ - icsk->icsk_retransmits = 0; tcp_try_undo_recovery(sk); return; } - if (flag & FLAG_DATA_ACKED) - icsk->icsk_retransmits = 0; if (tcp_is_reno(tp)) { /* A Reno DUPACK means new data in F-RTO step 2.b above are * delivered. Lower inflight to clock out (re)tranmissions. @@ -3398,8 +3394,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk); - if (after(ack, prior_snd_una)) + if (after(ack, prior_snd_una)) { flag |= FLAG_SND_UNA_ADVANCED; + icsk->icsk_retransmits = 0; + } prior_fackets = tp->fackets_out; prior_in_flight = tcp_packets_in_flight(tp); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 1e4eac779f51..b7effad5a58c 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -269,7 +269,7 @@ EXPORT_SYMBOL(tcp_v4_connect); * It can be called through tcp_release_cb() if socket was owned by user * at the time tcp_v4_err() was called to handle ICMP message. */ -static void tcp_v4_mtu_reduced(struct sock *sk) +void tcp_v4_mtu_reduced(struct sock *sk) { struct dst_entry *dst; struct inet_sock *inet = inet_sk(sk); @@ -300,6 +300,7 @@ static void tcp_v4_mtu_reduced(struct sock *sk) tcp_simple_retransmit(sk); } /* else let the usual retransmit timer handle it */ } +EXPORT_SYMBOL(tcp_v4_mtu_reduced); static void do_redirect(struct sk_buff *skb, struct sock *sk) { @@ -690,7 +691,8 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) net = dev_net(skb_dst(skb)->dev); arg.tos = ip_hdr(skb)->tos; - ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr, + ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), + skb, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); @@ -773,7 +775,8 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, if (oif) arg.bound_dev_if = oif; arg.tos = tos; - ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr, + ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), + skb, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); @@ -2117,6 +2120,7 @@ const struct inet_connection_sock_af_ops ipv4_specific = { .compat_setsockopt = compat_ip_setsockopt, .compat_getsockopt = compat_ip_getsockopt, #endif + .mtu_reduced = tcp_v4_mtu_reduced, }; EXPORT_SYMBOL(ipv4_specific); @@ -2736,7 +2740,6 @@ struct proto tcp_prot = { .sendpage = tcp_sendpage, .backlog_rcv = tcp_v4_do_rcv, .release_cb = tcp_release_cb, - .mtu_reduced = tcp_v4_mtu_reduced, .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, @@ -2768,14 +2771,39 @@ struct proto tcp_prot = { }; EXPORT_SYMBOL(tcp_prot); +static void __net_exit tcp_sk_exit(struct net *net) +{ + int cpu; + + for_each_possible_cpu(cpu) + inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu)); + free_percpu(net->ipv4.tcp_sk); +} + static int __net_init tcp_sk_init(struct net *net) { + int res, cpu; + + net->ipv4.tcp_sk = alloc_percpu(struct sock *); + if (!net->ipv4.tcp_sk) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + struct sock *sk; + + res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW, + IPPROTO_TCP, net); + if (res) + goto fail; + *per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk; + } net->ipv4.sysctl_tcp_ecn = 2; return 0; -} -static void __net_exit tcp_sk_exit(struct net *net) -{ +fail: + tcp_sk_exit(net); + + return res; } static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b3d1addd816b..96f64e59d70c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -787,7 +787,7 @@ void tcp_release_cb(struct sock *sk) __sock_put(sk); } if (flags & (1UL << TCP_MTU_REDUCED_DEFERRED)) { - sk->sk_prot->mtu_reduced(sk); + inet_csk(sk)->icsk_af_ops->mtu_reduced(sk); __sock_put(sk); } } @@ -1876,8 +1876,11 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, tso_segs = tcp_init_tso_segs(sk, skb, mss_now); BUG_ON(!tso_segs); - if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) + if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) { + /* "when" is used as a start point for the retransmit timer */ + TCP_SKB_CB(skb)->when = tcp_time_stamp; goto repair; /* Skip network transmission */ + } cwnd_quota = tcp_cwnd_test(tp, skb); if (!cwnd_quota) { @@ -1891,7 +1894,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now))) break; - if (tso_segs == 1) { + if (tso_segs == 1 || !sk->sk_gso_max_segs) { if (unlikely(!tcp_nagle_test(tp, skb, mss_now, (tcp_skb_is_last(sk, skb) ? nonagle : TCP_NAGLE_PUSH)))) @@ -1928,7 +1931,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, } limit = mss_now; - if (tso_segs > 1 && !tcp_urg_mode(tp)) + if (tso_segs > 1 && sk->sk_gso_max_segs && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, min_t(unsigned int, cwnd_quota, @@ -2066,9 +2069,7 @@ void tcp_send_loss_probe(struct sock *sk) if (WARN_ON(!skb || !tcp_skb_pcount(skb))) goto rearm_timer; - /* Probe with zero data doesn't trigger fast recovery. */ - if (skb->len > 0) - err = __tcp_retransmit_skb(sk, skb); + err = __tcp_retransmit_skb(sk, skb); /* Record snd_nxt for loss detection. */ if (likely(!err)) @@ -2616,15 +2617,11 @@ void tcp_send_fin(struct sock *sk) } else { /* Socket is locked, keep trying until memory is available. */ for (;;) { - skb = alloc_skb_fclone(MAX_TCP_HEADER, - sk->sk_allocation); + skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation); if (skb) break; yield(); } - - /* Reserve space for headers and prepare control bits. */ - skb_reserve(skb, MAX_TCP_HEADER); /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ tcp_init_nondata_skb(skb, tp->write_seq, TCPHDR_ACK | TCPHDR_FIN); @@ -2898,9 +2895,9 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_fastopen_request *fo = tp->fastopen_req; - int syn_loss = 0, space, i, err = 0, iovlen = fo->data->msg_iovlen; - struct sk_buff *syn_data = NULL, *data; + int syn_loss = 0, space, err = 0; unsigned long last_syn_loss = 0; + struct sk_buff *syn_data; tp->rx_opt.mss_clamp = tp->advmss; /* If MSS is not cached */ tcp_fastopen_cache_get(sk, &tp->rx_opt.mss_clamp, &fo->cookie, @@ -2931,42 +2928,39 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) /* limit to order-0 allocations */ space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER)); - syn_data = skb_copy_expand(syn, MAX_TCP_HEADER, space, - sk->sk_allocation); - if (syn_data == NULL) + syn_data = sk_stream_alloc_skb(sk, space, sk->sk_allocation); + if (!syn_data) goto fallback; + syn_data->ip_summed = CHECKSUM_PARTIAL; + memcpy(syn_data->cb, syn->cb, sizeof(syn->cb)); + skb_shinfo(syn_data)->gso_segs = 1; + if (unlikely(memcpy_fromiovecend(skb_put(syn_data, space), + fo->data->msg_iov, 0, space))) { + kfree_skb(syn_data); + goto fallback; + } - for (i = 0; i < iovlen && syn_data->len < space; ++i) { - struct iovec *iov = &fo->data->msg_iov[i]; - unsigned char __user *from = iov->iov_base; - int len = iov->iov_len; - - if (syn_data->len + len > space) - len = space - syn_data->len; - else if (i + 1 == iovlen) - /* No more data pending in inet_wait_for_connect() */ - fo->data = NULL; + /* No more data pending in inet_wait_for_connect() */ + if (space == fo->size) + fo->data = NULL; + fo->copied = space; - if (skb_add_data(syn_data, from, len)) - goto fallback; - } + tcp_connect_queue_skb(sk, syn_data); - /* Queue a data-only packet after the regular SYN for retransmission */ - data = pskb_copy(syn_data, sk->sk_allocation); - if (data == NULL) - goto fallback; - TCP_SKB_CB(data)->seq++; - TCP_SKB_CB(data)->tcp_flags &= ~TCPHDR_SYN; - TCP_SKB_CB(data)->tcp_flags = (TCPHDR_ACK|TCPHDR_PSH); - tcp_connect_queue_skb(sk, data); - fo->copied = data->len; + err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation); - if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) { + /* Now full SYN+DATA was cloned and sent (or not), + * remove the SYN from the original skb (syn_data) + * we keep in write queue in case of a retransmit, as we + * also have the SYN packet (with no data) in the same queue. + */ + TCP_SKB_CB(syn_data)->seq++; + TCP_SKB_CB(syn_data)->tcp_flags = TCPHDR_ACK | TCPHDR_PSH; + if (!err) { tp->syn_data = (fo->copied > 0); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE); goto done; } - syn_data = NULL; fallback: /* Send a regular SYN with Fast Open cookie request option */ @@ -2975,7 +2969,6 @@ fallback: err = tcp_transmit_skb(sk, syn, 1, sk->sk_allocation); if (err) tp->syn_fastopen = 0; - kfree_skb(syn_data); done: fo->cookie.len = -1; /* Exclude Fast Open option for SYN retries */ return err; @@ -2995,13 +2988,10 @@ int tcp_connect(struct sock *sk) return 0; } - buff = alloc_skb_fclone(MAX_TCP_HEADER + 15, sk->sk_allocation); - if (unlikely(buff == NULL)) + buff = sk_stream_alloc_skb(sk, 0, sk->sk_allocation); + if (unlikely(!buff)) return -ENOBUFS; - /* Reserve space for headers. */ - skb_reserve(buff, MAX_TCP_HEADER); - tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN); tp->retrans_stamp = TCP_SKB_CB(buff)->when = tcp_time_stamp; tcp_connect_queue_skb(sk, buff); diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 7927db0a9279..4a000f1dd757 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -99,11 +99,13 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlin s_slot = cb->args[0]; num = s_num = cb->args[1]; - for (slot = s_slot; slot <= table->mask; num = s_num = 0, slot++) { + for (slot = s_slot; slot <= table->mask; s_num = 0, slot++) { struct sock *sk; struct hlist_nulls_node *node; struct udp_hslot *hslot = &table->hash[slot]; + num = 0; + if (hlist_nulls_empty(&hslot->head)) continue; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 6c7fa0853fc7..3f0ec063d7f8 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1684,14 +1684,12 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) addrconf_mod_dad_work(ifp, 0); } -/* Join to solicited addr multicast group. */ - +/* Join to solicited addr multicast group. + * caller must hold RTNL */ void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr) { struct in6_addr maddr; - ASSERT_RTNL(); - if (dev->flags&(IFF_LOOPBACK|IFF_NOARP)) return; @@ -1699,12 +1697,11 @@ void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr) ipv6_dev_mc_inc(dev, &maddr); } +/* caller must hold RTNL */ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr) { struct in6_addr maddr; - ASSERT_RTNL(); - if (idev->dev->flags&(IFF_LOOPBACK|IFF_NOARP)) return; @@ -1712,12 +1709,11 @@ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr) __ipv6_dev_mc_dec(idev, &maddr); } +/* caller must hold RTNL */ static void addrconf_join_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; - ASSERT_RTNL(); - if (ifp->prefix_len >= 127) /* RFC 6164 */ return; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); @@ -1726,12 +1722,11 @@ static void addrconf_join_anycast(struct inet6_ifaddr *ifp) ipv6_dev_ac_inc(ifp->idev->dev, &addr); } +/* caller must hold RTNL */ static void addrconf_leave_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; - ASSERT_RTNL(); - if (ifp->prefix_len >= 127) /* RFC 6164 */ return; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 210183244689..ff2de7d9d8e6 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -77,6 +77,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) pac->acl_next = NULL; pac->acl_addr = *addr; + rtnl_lock(); rcu_read_lock(); if (ifindex == 0) { struct rt6_info *rt; @@ -137,6 +138,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) error: rcu_read_unlock(); + rtnl_unlock(); if (pac) sock_kfree_s(sk, pac, sizeof(*pac)); return err; @@ -171,11 +173,13 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) spin_unlock_bh(&ipv6_sk_ac_lock); + rtnl_lock(); rcu_read_lock(); dev = dev_get_by_index_rcu(net, pac->acl_ifindex); if (dev) ipv6_dev_ac_dec(dev, &pac->acl_addr); rcu_read_unlock(); + rtnl_unlock(); sock_kfree_s(sk, pac, sizeof(*pac)); return 0; @@ -198,6 +202,7 @@ void ipv6_sock_ac_close(struct sock *sk) spin_unlock_bh(&ipv6_sk_ac_lock); prev_index = 0; + rtnl_lock(); rcu_read_lock(); while (pac) { struct ipv6_ac_socklist *next = pac->acl_next; @@ -212,6 +217,7 @@ void ipv6_sock_ac_close(struct sock *sk) pac = next; } rcu_read_unlock(); + rtnl_unlock(); } static void aca_put(struct ifacaddr6 *ac) @@ -233,6 +239,8 @@ int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr) struct rt6_info *rt; int err; + ASSERT_RTNL(); + idev = in6_dev_get(dev); if (idev == NULL) @@ -302,6 +310,8 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifacaddr6 *aca, *prev_aca; + ASSERT_RTNL(); + write_lock_bh(&idev->lock); prev_aca = NULL; for (aca = idev->ac_list; aca; aca = aca->aca_next) { diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index c3bf2d2e519e..841cfa2c4600 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -382,11 +382,10 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); sin = &errhdr.offender; - sin->sin6_family = AF_UNSPEC; + memset(sin, 0, sizeof(*sin)); + if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) { sin->sin6_family = AF_INET6; - sin->sin6_flowinfo = 0; - sin->sin6_port = 0; if (np->rxopt.all) ip6_datagram_recv_common_ctl(sk, msg, skb); if (skb->protocol == htons(ETH_P_IPV6)) { @@ -397,12 +396,9 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) ipv6_iface_scope_id(&sin->sin6_addr, IP6CB(skb)->iif); } else { - struct inet_sock *inet = inet_sk(sk); - ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &sin->sin6_addr); - sin->sin6_scope_id = 0; - if (inet->cmsg_flags) + if (inet_sk(sk)->cmsg_flags) ip_cmsg_recv(msg, skb); } } diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index b4d5e1d97c1b..27ca79682efb 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -104,6 +104,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, goto again; flp6->saddr = saddr; } + err = rt->dst.error; goto out; } again: diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 1e55f5eba185..7daaeaf1bc1a 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -638,6 +638,29 @@ static inline bool rt6_qualify_for_ecmp(struct rt6_info *rt) RTF_GATEWAY; } +static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, + struct net *net) +{ + if (atomic_read(&rt->rt6i_ref) != 1) { + /* This route is used as dummy address holder in some split + * nodes. It is not leaked, but it still holds other resources, + * which must be released in time. So, scan ascendant nodes + * and replace dummy references to this route with references + * to still alive ones. + */ + while (fn) { + if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) { + fn->leaf = fib6_find_prefix(net, fn); + atomic_inc(&fn->leaf->rt6i_ref); + rt6_release(rt); + } + fn = fn->parent; + } + /* No more references are possible at this point. */ + BUG_ON(atomic_read(&rt->rt6i_ref) != 1); + } +} + /* * Insert routing information in a node. */ @@ -775,11 +798,12 @@ add: rt->dst.rt6_next = iter->dst.rt6_next; atomic_inc(&rt->rt6i_ref); inet6_rt_notify(RTM_NEWROUTE, rt, info); - rt6_release(iter); if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } + fib6_purge_rt(iter, fn, info->nl_net); + rt6_release(iter); } return 0; @@ -1284,24 +1308,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, fn = fib6_repair_tree(net, fn); } - if (atomic_read(&rt->rt6i_ref) != 1) { - /* This route is used as dummy address holder in some split - * nodes. It is not leaked, but it still holds other resources, - * which must be released in time. So, scan ascendant nodes - * and replace dummy references to this route with references - * to still alive ones. - */ - while (fn) { - if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) { - fn->leaf = fib6_find_prefix(net, fn); - atomic_inc(&fn->leaf->rt6i_ref); - rt6_release(rt); - } - fn = fn->parent; - } - /* No more references are possible at this point. */ - BUG_ON(atomic_read(&rt->rt6i_ref) != 1); - } + fib6_purge_rt(rt, fn, net); inet6_rt_notify(RTM_DELROUTE, rt, info); rt6_release(rt); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 2465d18e8a26..4a230b18dfe3 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -508,11 +508,11 @@ static int ip6gre_rcv(struct sk_buff *skb) skb->protocol = gre_proto; /* WCCP version 1 and 2 protocol decoding. - * - Change protocol to IP + * - Change protocol to IPv6 * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header */ if (flags == 0 && gre_proto == htons(ETH_P_WCCP)) { - skb->protocol = htons(ETH_P_IP); + skb->protocol = htons(ETH_P_IPV6); if ((*(h + offset) & 0xF0) != 0x40) offset += 4; } @@ -787,7 +787,7 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev) encap_limit = t->parms.encap_limit; memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); - fl6.flowi6_proto = IPPROTO_IPIP; + fl6.flowi6_proto = IPPROTO_GRE; dsfield = ipv4_get_dsfield(iph); @@ -837,7 +837,7 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev) encap_limit = t->parms.encap_limit; memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); - fl6.flowi6_proto = IPPROTO_IPV6; + fl6.flowi6_proto = IPPROTO_GRE; dsfield = ipv6_get_dsfield(ipv6h); if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) @@ -962,8 +962,6 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) else dev->flags &= ~IFF_POINTOPOINT; - dev->iflink = p->link; - /* Precalculate GRE options length */ if (t->parms.o_flags&(GRE_CSUM|GRE_KEY|GRE_SEQ)) { if (t->parms.o_flags&GRE_CSUM) @@ -1273,6 +1271,7 @@ static int ip6gre_tunnel_init(struct net_device *dev) u64_stats_init(&ip6gre_tunnel_stats->syncp); } + dev->iflink = tunnel->parms.link; return 0; } @@ -1474,6 +1473,8 @@ static int ip6gre_tap_init(struct net_device *dev) u64_stats_init(&ip6gre_tap_stats->syncp); } + dev->iflink = tunnel->parms.link; + return 0; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 073e5a6fc631..d7907ecf0b75 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1008,7 +1008,7 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, if (final_dst) fl6->daddr = *final_dst; - return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); + return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); } EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow); @@ -1040,7 +1040,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, if (final_dst) fl6->daddr = *final_dst; - return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); + return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); } EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow); @@ -1294,7 +1294,8 @@ emsgsize: if (((length > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && - (rt->dst.dev->features & NETIF_F_UFO)) { + (rt->dst.dev->features & NETIF_F_UFO) && + (sk->sk_type == SOCK_DGRAM)) { err = ip6_ufo_append_data(sk, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, mtu, flags, rt); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 912033957ad3..657639d39f70 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -272,9 +272,6 @@ static int ip6_tnl_create2(struct net_device *dev) int err; t = netdev_priv(dev); - err = ip6_tnl_dev_init(dev); - if (err < 0) - goto out; err = register_netdevice(dev); if (err < 0) @@ -1456,6 +1453,7 @@ ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) static const struct net_device_ops ip6_tnl_netdev_ops = { + .ndo_init = ip6_tnl_dev_init, .ndo_uninit = ip6_tnl_dev_uninit, .ndo_start_xmit = ip6_tnl_xmit, .ndo_do_ioctl = ip6_tnl_ioctl, @@ -1547,16 +1545,10 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - int err = ip6_tnl_dev_init_gen(dev); - - if (err) - return err; t->parms.proto = IPPROTO_IPV6; dev_hold(dev); - ip6_tnl_link_config(t); - rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; } diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 2d19272b8cee..28456c9a1847 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -172,10 +172,6 @@ static int vti6_tnl_create2(struct net_device *dev) struct vti6_net *ip6n = net_generic(net, vti6_net_id); int err; - err = vti6_dev_init(dev); - if (err < 0) - goto out; - err = register_netdevice(dev); if (err < 0) goto out; @@ -693,6 +689,7 @@ static int vti6_change_mtu(struct net_device *dev, int new_mtu) } static const struct net_device_ops vti6_netdev_ops = { + .ndo_init = vti6_dev_init, .ndo_uninit = vti6_dev_uninit, .ndo_start_xmit = vti6_tnl_xmit, .ndo_do_ioctl = vti6_ioctl, @@ -772,16 +769,10 @@ static int __net_init vti6_fb_tnl_dev_init(struct net_device *dev) struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); - int err = vti6_dev_init_gen(dev); - - if (err) - return err; t->parms.proto = IPPROTO_IPV6; dev_hold(dev); - vti6_link_config(t); - rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; } @@ -834,6 +825,15 @@ static int vti6_newlink(struct net *src_net, struct net_device *dev, return vti6_tnl_create2(dev); } +static void vti6_dellink(struct net_device *dev, struct list_head *head) +{ + struct net *net = dev_net(dev); + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + + if (dev != ip6n->fb_tnl_dev) + unregister_netdevice_queue(dev, head); +} + static int vti6_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { @@ -909,6 +909,7 @@ static struct rtnl_link_ops vti6_link_ops __read_mostly = { .setup = vti6_dev_setup, .validate = vti6_validate, .newlink = vti6_newlink, + .dellink = vti6_dellink, .changelink = vti6_changelink, .get_size = vti6_get_size, .fill_info = vti6_fill_info, @@ -954,6 +955,7 @@ static int __net_init vti6_init_net(struct net *net) if (!ip6n->fb_tnl_dev) goto err_alloc_dev; dev_net_set(ip6n->fb_tnl_dev, net); + ip6n->fb_tnl_dev->rtnl_link_ops = &vti6_link_ops; err = vti6_fb_tnl_dev_init(ip6n->fb_tnl_dev); if (err < 0) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 08b367c6b9cf..761e4586ab5f 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -172,6 +172,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) mc_lst->next = NULL; mc_lst->addr = *addr; + rtnl_lock(); rcu_read_lock(); if (ifindex == 0) { struct rt6_info *rt; @@ -185,6 +186,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) if (dev == NULL) { rcu_read_unlock(); + rtnl_unlock(); sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return -ENODEV; } @@ -202,6 +204,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) if (err) { rcu_read_unlock(); + rtnl_unlock(); sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return err; } @@ -212,6 +215,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) spin_unlock(&ipv6_sk_mc_lock); rcu_read_unlock(); + rtnl_unlock(); return 0; } @@ -229,6 +233,7 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) if (!ipv6_addr_is_multicast(addr)) return -EINVAL; + rtnl_lock(); spin_lock(&ipv6_sk_mc_lock); for (lnk = &np->ipv6_mc_list; (mc_lst = rcu_dereference_protected(*lnk, @@ -252,12 +257,15 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) } else (void) ip6_mc_leave_src(sk, mc_lst, NULL); rcu_read_unlock(); + rtnl_unlock(); + atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); kfree_rcu(mc_lst, rcu); return 0; } } spin_unlock(&ipv6_sk_mc_lock); + rtnl_unlock(); return -EADDRNOTAVAIL; } @@ -302,6 +310,7 @@ void ipv6_sock_mc_close(struct sock *sk) if (!rcu_access_pointer(np->ipv6_mc_list)) return; + rtnl_lock(); spin_lock(&ipv6_sk_mc_lock); while ((mc_lst = rcu_dereference_protected(np->ipv6_mc_list, lockdep_is_held(&ipv6_sk_mc_lock))) != NULL) { @@ -328,6 +337,7 @@ void ipv6_sock_mc_close(struct sock *sk) spin_lock(&ipv6_sk_mc_lock); } spin_unlock(&ipv6_sk_mc_lock); + rtnl_unlock(); } int ip6_mc_source(int add, int omode, struct sock *sk, @@ -845,6 +855,8 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) struct ifmcaddr6 *mc; struct inet6_dev *idev; + ASSERT_RTNL(); + /* we need to take a reference on idev */ idev = in6_dev_get(dev); @@ -916,6 +928,8 @@ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifmcaddr6 *ma, **map; + ASSERT_RTNL(); + write_lock_bh(&idev->lock); for (map = &idev->mc_list; (ma=*map) != NULL; map = &ma->next) { if (ipv6_addr_equal(&ma->mca_addr, addr)) { diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 798eb0f79078..ae4a06be14df 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -3,10 +3,43 @@ * not configured or static. These functions are needed by GSO/GRO implementation. */ #include <linux/export.h> +#include <net/ip.h> #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/addrconf.h> +/* This function exists only for tap drivers that must support broken + * clients requesting UFO without specifying an IPv6 fragment ID. + * + * This is similar to ipv6_select_ident() but we use an independent hash + * seed to limit information leakage. + * + * The network header must be set before calling this. + */ +void ipv6_proxy_select_ident(struct sk_buff *skb) +{ + static u32 ip6_proxy_idents_hashrnd __read_mostly; + struct in6_addr buf[2]; + struct in6_addr *addrs; + u32 hash, id; + + addrs = skb_header_pointer(skb, + skb_network_offset(skb) + + offsetof(struct ipv6hdr, saddr), + sizeof(buf), buf); + if (!addrs) + return; + + net_get_random_once(&ip6_proxy_idents_hashrnd, + sizeof(ip6_proxy_idents_hashrnd)); + + hash = __ipv6_addr_jhash(&addrs[1], ip6_proxy_idents_hashrnd); + hash = __ipv6_addr_jhash(&addrs[0], hash); + + id = ip_idents_reserve(hash, 1); + skb_shinfo(skb)->ip6_frag_id = htonl(id); +} +EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) { diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index bda74291c3e0..461199533fe4 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -103,9 +103,10 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_in6 *, u, msg->msg_name); - if (msg->msg_namelen < sizeof(struct sockaddr_in6) || - u->sin6_family != AF_INET6) { + if (msg->msg_namelen < sizeof(*u)) return -EINVAL; + if (u->sin6_family != AF_INET6) { + return -EAFNOSUPPORT; } if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != u->sin6_scope_id) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7cc1102e298c..3809ca234c69 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -141,7 +141,7 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) u32 *p = NULL; if (!(rt->dst.flags & DST_HOST)) - return NULL; + return dst_cow_metrics_generic(dst, old); peer = rt6_get_peer_create(rt); if (peer) { @@ -1160,12 +1160,9 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct net *net = dev_net(dst->dev); rt6->rt6i_flags |= RTF_MODIFIED; - if (mtu < IPV6_MIN_MTU) { - u32 features = dst_metric(dst, RTAX_FEATURES); + if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - features |= RTAX_FEATURE_ALLFRAG; - dst_metric_set(dst, RTAX_FEATURES, features); - } + dst_metric_set(dst, RTAX_MTU, mtu); rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires); } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index fe548ba72687..317b6dbf3190 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -101,19 +101,19 @@ static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net, for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && - (!dev || !t->parms.link || dev->iflink == t->parms.link) && + (!dev || !t->parms.link || dev->ifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) { if (remote == t->parms.iph.daddr && - (!dev || !t->parms.link || dev->iflink == t->parms.link) && + (!dev || !t->parms.link || dev->ifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) { if (local == t->parms.iph.saddr && - (!dev || !t->parms.link || dev->iflink == t->parms.link) && + (!dev || !t->parms.link || dev->ifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } @@ -195,10 +195,8 @@ static int ipip6_tunnel_create(struct net_device *dev) struct sit_net *sitn = net_generic(net, sit_net_id); int err; - err = ipip6_tunnel_init(dev); - if (err < 0) - goto out; - ipip6_tunnel_clone_6rd(dev, sitn); + memcpy(dev->dev_addr, &t->parms.iph.saddr, 4); + memcpy(dev->broadcast, &t->parms.iph.daddr, 4); if ((__force u16)t->parms.i_flags & SIT_ISATAP) dev->priv_flags |= IFF_ISATAP; @@ -207,7 +205,8 @@ static int ipip6_tunnel_create(struct net_device *dev) if (err < 0) goto out; - strcpy(t->parms.name, dev->name); + ipip6_tunnel_clone_6rd(dev, sitn); + dev->rtnl_link_ops = &sit_link_ops; dev_hold(dev); @@ -1321,6 +1320,7 @@ static int ipip6_tunnel_change_mtu(struct net_device *dev, int new_mtu) } static const struct net_device_ops ipip6_netdev_ops = { + .ndo_init = ipip6_tunnel_init, .ndo_uninit = ipip6_tunnel_uninit, .ndo_start_xmit = sit_tunnel_xmit, .ndo_do_ioctl = ipip6_tunnel_ioctl, @@ -1367,9 +1367,7 @@ static int ipip6_tunnel_init(struct net_device *dev) tunnel->dev = dev; tunnel->net = dev_net(dev); - - memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4); - memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); + strcpy(tunnel->parms.name, dev->name); ipip6_tunnel_bind_dev(dev); dev->tstats = alloc_percpu(struct pcpu_sw_netstats); @@ -1401,7 +1399,6 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) tunnel->dev = dev; tunnel->net = dev_net(dev); - strcpy(tunnel->parms.name, dev->name); iph->version = 4; iph->protocol = IPPROTO_IPV6; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 889079b2ea85..a4f890dd223a 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1668,6 +1668,7 @@ static const struct inet_connection_sock_af_ops ipv6_specific = { .compat_setsockopt = compat_ipv6_setsockopt, .compat_getsockopt = compat_ipv6_getsockopt, #endif + .mtu_reduced = tcp_v6_mtu_reduced, }; #ifdef CONFIG_TCP_MD5SIG @@ -1699,6 +1700,7 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = { .compat_setsockopt = compat_ipv6_setsockopt, .compat_getsockopt = compat_ipv6_getsockopt, #endif + .mtu_reduced = tcp_v4_mtu_reduced, }; #ifdef CONFIG_TCP_MD5SIG @@ -1935,7 +1937,6 @@ struct proto tcpv6_prot = { .sendpage = tcp_sendpage, .backlog_rcv = tcp_v6_do_rcv, .release_cb = tcp_release_cb, - .mtu_reduced = tcp_v6_mtu_reduced, .hash = tcp_v6_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index 00b2a6d1c009..d65aea21ce81 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -1763,6 +1763,7 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock, struct ipxhdr *ipx = NULL; struct sk_buff *skb; int copied, rc; + bool locked = true; lock_sock(sk); /* put the autobinding in */ @@ -1789,6 +1790,8 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock, if (sock_flag(sk, SOCK_ZAPPED)) goto out; + release_sock(sk); + locked = false; skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &rc); if (!skb) @@ -1822,7 +1825,8 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock, out_free: skb_free_datagram(sk, skb); out: - release_sock(sk); + if (locked) + release_sock(sk); return rc; } diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c index 2ba8b9705bb7..fdcb9688b5d3 100644 --- a/net/irda/ircomm/ircomm_tty.c +++ b/net/irda/ircomm/ircomm_tty.c @@ -818,7 +818,9 @@ static void ircomm_tty_wait_until_sent(struct tty_struct *tty, int timeout) orig_jiffies = jiffies; /* Set poll time to 200 ms */ - poll_time = IRDA_MIN(timeout, msecs_to_jiffies(200)); + poll_time = msecs_to_jiffies(200); + if (timeout) + poll_time = min_t(unsigned long, timeout, poll_time); spin_lock_irqsave(&self->spinlock, flags); while (self->tx_skb && self->tx_skb->len) { diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 1e05bbde47ba..da8d067d6107 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -758,7 +758,8 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, /* If PMTU discovery was enabled, use the MTU that was discovered */ dst = sk_dst_get(tunnel->sock); if (dst != NULL) { - u32 pmtu = dst_mtu(__sk_dst_get(tunnel->sock)); + u32 pmtu = dst_mtu(dst); + if (pmtu != 0) session->mtu = session->mru = pmtu - PPPOL2TP_HEADER_OVERHEAD; diff --git a/net/llc/sysctl_net_llc.c b/net/llc/sysctl_net_llc.c index 612a5ddaf93b..799bafc2af39 100644 --- a/net/llc/sysctl_net_llc.c +++ b/net/llc/sysctl_net_llc.c @@ -18,28 +18,28 @@ static struct ctl_table llc2_timeout_table[] = { { .procname = "ack", .data = &sysctl_llc2_ack_timeout, - .maxlen = sizeof(long), + .maxlen = sizeof(sysctl_llc2_ack_timeout), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "busy", .data = &sysctl_llc2_busy_timeout, - .maxlen = sizeof(long), + .maxlen = sizeof(sysctl_llc2_busy_timeout), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "p", .data = &sysctl_llc2_p_timeout, - .maxlen = sizeof(long), + .maxlen = sizeof(sysctl_llc2_p_timeout), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "rej", .data = &sysctl_llc2_rej_timeout, - .maxlen = sizeof(long), + .maxlen = sizeof(sysctl_llc2_rej_timeout), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, diff --git a/net/mac80211/aes_ccm.c b/net/mac80211/aes_ccm.c index 7c7df475a401..f056f9ed97fb 100644 --- a/net/mac80211/aes_ccm.c +++ b/net/mac80211/aes_ccm.c @@ -54,6 +54,9 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, memset(&aead_req, 0, sizeof(aead_req)); + if (data_len == 0) + return -EINVAL; + sg_init_one(&pt, data, data_len); sg_init_one(&assoc, &aad[2], be16_to_cpup((__be16 *)aad)); sg_init_table(ct, 2); diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index ea7013cb7e52..3f076b9c9308 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -815,7 +815,7 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata, memset(¶ms, 0, sizeof(params)); memset(&csa_ie, 0, sizeof(csa_ie)); - err = ieee80211_parse_ch_switch_ie(sdata, elems, beacon, + err = ieee80211_parse_ch_switch_ie(sdata, elems, ifibss->chandef.chan->band, sta_flags, ifibss->bssid, &csa_ie); /* can't switch to destination channel, fail */ diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index b127902361f4..e278c64572de 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -57,13 +57,24 @@ struct ieee80211_local; #define IEEE80211_UNSET_POWER_LEVEL INT_MIN /* - * Some APs experience problems when working with U-APSD. Decrease the - * probability of that happening by using legacy mode for all ACs but VO. - * The AP that caused us trouble was a Cisco 4410N. It ignores our - * setting, and always treats non-VO ACs as legacy. + * Some APs experience problems when working with U-APSD. Decreasing the + * probability of that happening by using legacy mode for all ACs but VO isn't + * enough. + * + * Cisco 4410N originally forced us to enable VO by default only because it + * treated non-VO ACs as legacy. + * + * However some APs (notably Netgear R7000) silently reclassify packets to + * different ACs. Since u-APSD ACs require trigger frames for frame retrieval + * clients would never see some frames (e.g. ARP responses) or would fetch them + * accidentally after a long time. + * + * It makes little sense to enable u-APSD queues by default because it needs + * userspace applications to be aware of it to actually take advantage of the + * possible additional powersavings. Implicitly depending on driver autotrigger + * frame support doesn't make much sense. */ -#define IEEE80211_DEFAULT_UAPSD_QUEUES \ - IEEE80211_WMM_IE_STA_QOSINFO_AC_VO +#define IEEE80211_DEFAULT_UAPSD_QUEUES 0 #define IEEE80211_DEFAULT_MAX_SP_LEN \ IEEE80211_WMM_IE_STA_QOSINFO_SP_ALL @@ -1569,7 +1580,6 @@ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, * ieee80211_parse_ch_switch_ie - parses channel switch IEs * @sdata: the sdata of the interface which has received the frame * @elems: parsed 802.11 elements received with the frame - * @beacon: indicates if the frame was a beacon or probe response * @current_band: indicates the current band * @sta_flags: contains information about own capabilities and restrictions * to decide which channel switch announcements can be accepted. Only the @@ -1583,7 +1593,7 @@ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, * Return: 0 on success, <0 on error and >0 if there is nothing to parse. */ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, - struct ieee802_11_elems *elems, bool beacon, + struct ieee802_11_elems *elems, enum ieee80211_band current_band, u32 sta_flags, u8 *bssid, struct ieee80211_csa_ie *csa_ie); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 8f7fabc46c97..06f5de4e4fbb 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -760,10 +760,12 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, int i, flushed; struct ps_data *ps; struct cfg80211_chan_def chandef; + bool cancel_scan; clear_bit(SDATA_STATE_RUNNING, &sdata->state); - if (rcu_access_pointer(local->scan_sdata) == sdata) + cancel_scan = rcu_access_pointer(local->scan_sdata) == sdata; + if (cancel_scan) ieee80211_scan_cancel(local); /* @@ -973,6 +975,9 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, ieee80211_recalc_ps(local, -1); + if (cancel_scan) + flush_delayed_work(&local->scan_work); + if (local->open_count == 0) { ieee80211_stop_device(local); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 6ff65a1ebaa9..d78b37a5d951 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -652,7 +652,7 @@ void ieee80211_free_sta_keys(struct ieee80211_local *local, int i; mutex_lock(&local->key_mtx); - for (i = 0; i < NUM_DEFAULT_KEYS; i++) { + for (i = 0; i < ARRAY_SIZE(sta->gtk); i++) { key = key_mtx_dereference(local, sta->gtk[i]); if (!key) continue; diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 5b919cab1de0..3d52d1d68431 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -885,7 +885,7 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata, memset(¶ms, 0, sizeof(params)); memset(&csa_ie, 0, sizeof(csa_ie)); - err = ieee80211_parse_ch_switch_ie(sdata, elems, beacon, band, + err = ieee80211_parse_ch_switch_ie(sdata, elems, band, sta_flags, sdata->vif.addr, &csa_ie); if (err < 0) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index e6a84cb1a5e4..c9535a976b56 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1001,7 +1001,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, current_band = cbss->channel->band; memset(&csa_ie, 0, sizeof(csa_ie)); - res = ieee80211_parse_ch_switch_ie(sdata, elems, beacon, current_band, + res = ieee80211_parse_ch_switch_ie(sdata, elems, current_band, ifmgd->flags, ifmgd->associated->bssid, &csa_ie); if (res < 0) @@ -1086,7 +1086,8 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, ieee80211_queue_work(&local->hw, &ifmgd->chswitch_work); else mod_timer(&ifmgd->chswitch_timer, - TU_TO_EXP_TIME(csa_ie.count * cbss->beacon_interval)); + TU_TO_EXP_TIME((csa_ie.count - 1) * + cbss->beacon_interval)); } static u32 ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata, @@ -4240,8 +4241,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, rcu_read_unlock(); if (bss->wmm_used && bss->uapsd_supported && - (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD) && - sdata->wmm_acm != 0xff) { + (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD)) { assoc_data->uapsd = true; ifmgd->flags |= IEEE80211_STA_UAPSD_ENABLED; } else { diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index 22b223f13c9f..74350c3863b8 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -462,7 +462,7 @@ static void rate_fixup_ratelist(struct ieee80211_vif *vif, */ if (!(rates[0].flags & IEEE80211_TX_RC_MCS)) { u32 basic_rates = vif->bss_conf.basic_rates; - s8 baserate = basic_rates ? ffs(basic_rates - 1) : 0; + s8 baserate = basic_rates ? ffs(basic_rates) - 1 : 0; rate = &sband->bitrates[rates[0].idx]; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 3e57f96c9666..9abb445ea261 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -261,7 +261,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, else if (rate && rate->flags & IEEE80211_RATE_ERP_G) channel_flags |= IEEE80211_CHAN_OFDM | IEEE80211_CHAN_2GHZ; else if (rate) - channel_flags |= IEEE80211_CHAN_OFDM | IEEE80211_CHAN_2GHZ; + channel_flags |= IEEE80211_CHAN_CCK | IEEE80211_CHAN_2GHZ; else channel_flags |= IEEE80211_CHAN_2GHZ; put_unaligned_le16(channel_flags, pos); @@ -1679,11 +1679,14 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) sc = le16_to_cpu(hdr->seq_ctrl); frag = sc & IEEE80211_SCTL_FRAG; - if (likely((!ieee80211_has_morefrags(fc) && frag == 0) || - is_multicast_ether_addr(hdr->addr1))) { - /* not fragmented */ - goto out; + if (is_multicast_ether_addr(hdr->addr1)) { + rx->local->dot11MulticastReceivedFrameCount++; + goto out_no_led; } + + if (likely(!ieee80211_has_morefrags(fc) && frag == 0)) + goto out; + I802_DEBUG_INC(rx->local->rx_handlers_fragments); if (skb_linearize(rx->skb)) @@ -1774,12 +1777,10 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) status->rx_flags |= IEEE80211_RX_FRAGMENTED; out: + ieee80211_led_rx(rx->local); + out_no_led: if (rx->sta) rx->sta->rx_packets++; - if (is_multicast_ether_addr(hdr->addr1)) - rx->local->dot11MulticastReceivedFrameCount++; - else - ieee80211_led_rx(rx->local); return RX_CONTINUE; } @@ -2106,6 +2107,9 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) hdr = (struct ieee80211_hdr *) skb->data; mesh_hdr = (struct ieee80211s_hdr *) (skb->data + hdrlen); + if (ieee80211_drop_unencrypted(rx, hdr->frame_control)) + return RX_DROP_MONITOR; + /* frame is in RMC, don't forward */ if (ieee80211_is_data(hdr->frame_control) && is_multicast_ether_addr(hdr->addr1) && diff --git a/net/mac80211/spectmgmt.c b/net/mac80211/spectmgmt.c index 6ab009070084..efeba56c913b 100644 --- a/net/mac80211/spectmgmt.c +++ b/net/mac80211/spectmgmt.c @@ -22,7 +22,7 @@ #include "wme.h" int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, - struct ieee802_11_elems *elems, bool beacon, + struct ieee802_11_elems *elems, enum ieee80211_band current_band, u32 sta_flags, u8 *bssid, struct ieee80211_csa_ie *csa_ie) @@ -91,19 +91,13 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, return -EINVAL; } - if (!beacon && sec_chan_offs) { + if (sec_chan_offs) { secondary_channel_offset = sec_chan_offs->sec_chan_offs; - } else if (beacon && ht_oper) { - secondary_channel_offset = - ht_oper->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET; } else if (!(sta_flags & IEEE80211_STA_DISABLE_HT)) { - /* If it's not a beacon, HT is enabled and the IE not present, - * it's 20 MHz, 802.11-2012 8.5.2.6: - * This element [the Secondary Channel Offset Element] is - * present when switching to a 40 MHz channel. It may be - * present when switching to a 20 MHz channel (in which - * case the secondary channel offset is set to SCN). - */ + /* If the secondary channel offset IE is not present, + * we can't know what's the post-CSA offset, so the + * best we can do is use 20MHz. + */ secondary_channel_offset = IEEE80211_HT_PARAM_CHA_SEC_NONE; } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index e5a7ac2f3687..dca076f6252c 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -562,6 +562,7 @@ ieee80211_tx_h_check_control_port_protocol(struct ieee80211_tx_data *tx) if (tx->sdata->control_port_no_encrypt) info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; info->control.flags |= IEEE80211_TX_CTRL_PORT_CTRL_PROTO; + info->flags |= IEEE80211_TX_CTL_USE_MINRATE; } return TX_CONTINUE; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index de770ec39e51..53ea1644a297 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -636,7 +636,7 @@ ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index) struct ip_set *set; struct ip_set_net *inst = ip_set_pernet(net); - if (index > inst->ip_set_max) + if (index >= inst->ip_set_max) return IPSET_INVALID_ID; nfnl_lock(NFNL_SUBSYS_IPSET); @@ -1839,6 +1839,12 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) if (*op < IP_SET_OP_VERSION) { /* Check the version at the beginning of operations */ struct ip_set_req_version *req_version = data; + + if (*len < sizeof(struct ip_set_req_version)) { + ret = -EINVAL; + goto done; + } + if (req_version->version != IPSET_PROTOCOL) { ret = -EPROTO; goto done; diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index a8eb0a89326a..610e19c0e13f 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -797,7 +797,6 @@ static void ip_vs_conn_expire(unsigned long data) ip_vs_control_del(cp); if (cp->flags & IP_VS_CONN_F_NFCT) { - ip_vs_conn_drop_conntrack(cp); /* Do not access conntracks during subsys cleanup * because nf_conntrack_find_get can not be used after * conntrack cleanup for the net. diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 3d2d2c8108ca..847d2a2c5d05 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -658,16 +658,24 @@ static inline int ip_vs_gather_frags(struct sk_buff *skb, u_int32_t user) return err; } -static int ip_vs_route_me_harder(int af, struct sk_buff *skb) +static int ip_vs_route_me_harder(int af, struct sk_buff *skb, + unsigned int hooknum) { + if (!sysctl_snat_reroute(skb)) + return 0; + /* Reroute replies only to remote clients (FORWARD and LOCAL_OUT) */ + if (NF_INET_LOCAL_IN == hooknum) + return 0; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { - if (sysctl_snat_reroute(skb) && ip6_route_me_harder(skb) != 0) + struct dst_entry *dst = skb_dst(skb); + + if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) && + ip6_route_me_harder(skb) != 0) return 1; } else #endif - if ((sysctl_snat_reroute(skb) || - skb_rtable(skb)->rt_flags & RTCF_LOCAL) && + if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) && ip_route_me_harder(skb, RTN_LOCAL) != 0) return 1; @@ -790,7 +798,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb, union nf_inet_addr *snet, __u8 protocol, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, - unsigned int offset, unsigned int ihl) + unsigned int offset, unsigned int ihl, + unsigned int hooknum) { unsigned int verdict = NF_DROP; @@ -820,7 +829,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb, #endif ip_vs_nat_icmp(skb, pp, cp, 1); - if (ip_vs_route_me_harder(af, skb)) + if (ip_vs_route_me_harder(af, skb, hooknum)) goto out; /* do the statistics and put it back */ @@ -915,7 +924,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related, snet.ip = iph->saddr; return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp, - pp, ciph.len, ihl); + pp, ciph.len, ihl, hooknum); } #ifdef CONFIG_IP_VS_IPV6 @@ -980,7 +989,8 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related, snet.in6 = ciph.saddr.in6; writable = ciph.len; return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp, - pp, writable, sizeof(struct ipv6hdr)); + pp, writable, sizeof(struct ipv6hdr), + hooknum); } #endif @@ -1039,7 +1049,8 @@ static inline bool is_new_conn(const struct sk_buff *skb, */ static unsigned int handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, - struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) + struct ip_vs_conn *cp, struct ip_vs_iphdr *iph, + unsigned int hooknum) { struct ip_vs_protocol *pp = pd->pp; @@ -1077,7 +1088,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, * if it came from this machine itself. So re-compute * the routing information. */ - if (ip_vs_route_me_harder(af, skb)) + if (ip_vs_route_me_harder(af, skb, hooknum)) goto drop; IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT"); @@ -1180,7 +1191,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) cp = pp->conn_out_get(af, skb, &iph, 0); if (likely(cp)) - return handle_response(af, skb, pd, cp, &iph); + return handle_response(af, skb, pd, cp, &iph, hooknum); if (sysctl_nat_icmp_send(net) && (pp->protocol == IPPROTO_TCP || pp->protocol == IPPROTO_UDP || @@ -1906,7 +1917,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { { .hook = ip_vs_local_reply6, .owner = THIS_MODULE, - .pf = NFPROTO_IPV4, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 1, }, diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 77c173282f38..4a662f15eaee 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -183,6 +183,8 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, struct nf_conn *ct; struct net *net; + *diff = 0; + #ifdef CONFIG_IP_VS_IPV6 /* This application helper doesn't work with IPv6 yet, * so turn this into a no-op for IPv6 packets @@ -191,8 +193,6 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, return 1; #endif - *diff = 0; - /* Only useful for established sessions */ if (cp->state != IP_VS_TCP_S_ESTABLISHED) return 1; @@ -321,6 +321,9 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, struct ip_vs_conn *n_cp; struct net *net; + /* no diff required for incoming packets */ + *diff = 0; + #ifdef CONFIG_IP_VS_IPV6 /* This application helper doesn't work with IPv6 yet, * so turn this into a no-op for IPv6 packets @@ -329,9 +332,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, return 1; #endif - /* no diff required for incoming packets */ - *diff = 0; - /* Only useful for established sessions */ if (cp->state != IP_VS_TCP_S_ESTABLISHED) return 1; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index db801263ee9f..a8027e73b6a2 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -891,6 +891,8 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param, IP_VS_DBG(2, "BACKUP, add new conn. failed\n"); return; } + if (!(flags & IP_VS_CONN_F_TEMPLATE)) + kfree(param->pe_data); } if (opt) @@ -1164,6 +1166,7 @@ static inline int ip_vs_proc_sync_conn(struct net *net, __u8 *p, __u8 *msg_end) (opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL) ); #endif + ip_vs_pe_put(param.pe); return 0; /* Error exit */ out: diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 7f0e1cf2d7e8..1692e7534759 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -967,8 +967,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, iph->nexthdr = IPPROTO_IPV6; iph->payload_len = old_iph->payload_len; be16_add_cpu(&iph->payload_len, sizeof(*old_iph)); - iph->priority = old_iph->priority; memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl)); + ipv6_change_dsfield(iph, 0, ipv6_get_dsfield(old_iph)); iph->daddr = cp->daddr.in6; iph->saddr = saddr; iph->hop_limit = old_iph->hop_limit; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index bf8a108b46e2..6cf2f077e09c 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -265,7 +265,8 @@ replay: nlh = nlmsg_hdr(skb); err = 0; - if (nlh->nlmsg_len < NLMSG_HDRLEN) { + if (nlmsg_len(nlh) < sizeof(struct nfgenmsg) || + skb->len < nlh->nlmsg_len) { err = -EINVAL; goto ack; } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index a155d19a225e..6ff12a191400 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -45,7 +45,8 @@ #define NFULNL_NLBUFSIZ_DEFAULT NLMSG_GOODSIZE #define NFULNL_TIMEOUT_DEFAULT 100 /* every second */ #define NFULNL_QTHRESH_DEFAULT 100 /* 100 packets */ -#define NFULNL_COPY_RANGE_MAX 0xFFFF /* max packet size is limited by 16-bit struct nfattr nfa_len field */ +/* max packet size is limited by 16-bit struct nfattr nfa_len field */ +#define NFULNL_COPY_RANGE_MAX (0xFFFF - NLA_HDRLEN) #define PRINTR(x, args...) do { if (net_ratelimit()) \ printk(x, ## args); } while (0); @@ -255,6 +256,8 @@ nfulnl_set_mode(struct nfulnl_instance *inst, u_int8_t mode, case NFULNL_COPY_PACKET: inst->copy_mode = mode; + if (range == 0) + range = NFULNL_COPY_RANGE_MAX; inst->copy_range = min_t(unsigned int, range, NFULNL_COPY_RANGE_MAX); break; @@ -346,26 +349,25 @@ nfulnl_alloc_skb(struct net *net, u32 peer_portid, unsigned int inst_size, return skb; } -static int +static void __nfulnl_send(struct nfulnl_instance *inst) { - int status = -1; - if (inst->qlen > 1) { struct nlmsghdr *nlh = nlmsg_put(inst->skb, 0, 0, NLMSG_DONE, sizeof(struct nfgenmsg), 0); - if (!nlh) + if (WARN_ONCE(!nlh, "bad nlskb size: %u, tailroom %d\n", + inst->skb->len, skb_tailroom(inst->skb))) { + kfree_skb(inst->skb); goto out; + } } - status = nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid, - MSG_DONTWAIT); - + nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid, + MSG_DONTWAIT); +out: inst->qlen = 0; inst->skb = NULL; -out: - return status; } static void @@ -652,7 +654,8 @@ nfulnl_log_packet(struct net *net, + nla_total_size(sizeof(u_int32_t)) /* gid */ + nla_total_size(plen) /* prefix */ + nla_total_size(sizeof(struct nfulnl_msg_packet_hw)) - + nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp)); + + nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp)) + + nla_total_size(sizeof(struct nfgenmsg)); /* NLMSG_DONE */ if (in && skb_mac_header_was_set(skb)) { size += nla_total_size(skb->dev->hard_header_len) @@ -681,8 +684,7 @@ nfulnl_log_packet(struct net *net, break; case NFULNL_COPY_PACKET: - if (inst->copy_range == 0 - || inst->copy_range > skb->len) + if (inst->copy_range > skb->len) data_len = skb->len; else data_len = inst->copy_range; @@ -695,8 +697,7 @@ nfulnl_log_packet(struct net *net, goto unlock_and_release; } - if (inst->skb && - size > skb_tailroom(inst->skb) - sizeof(struct nfgenmsg)) { + if (inst->skb && size > skb_tailroom(inst->skb)) { /* either the queue len is too high or we don't have * enough room in the skb left. flush to userspace. */ __nfulnl_flush(inst); diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 82cb8236f8a1..7350723aeb15 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -611,8 +611,12 @@ nft_match_select_ops(const struct nft_ctx *ctx, struct xt_match *match = nft_match->ops.data; if (strcmp(match->name, mt_name) == 0 && - match->revision == rev && match->family == family) + match->revision == rev && match->family == family) { + if (!try_module_get(match->me)) + return ERR_PTR(-ENOENT); + return &nft_match->ops; + } } match = xt_request_find_match(family, mt_name, rev); @@ -678,12 +682,16 @@ nft_target_select_ops(const struct nft_ctx *ctx, family = ctx->afi->family; /* Re-use the existing target if it's already loaded. */ - list_for_each_entry(nft_target, &nft_match_list, head) { + list_for_each_entry(nft_target, &nft_target_list, head) { struct xt_target *target = nft_target->ops.data; if (strcmp(target->name, tg_name) == 0 && - target->revision == rev && target->family == family) + target->revision == rev && target->family == family) { + if (!try_module_get(target->me)) + return ERR_PTR(-ENOENT); + return &nft_target->ops; + } } target = xt_request_find_target(family, tg_name, rev); diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c index 9a8e77e7f8d4..ef5c75a5b200 100644 --- a/net/netfilter/xt_cgroup.c +++ b/net/netfilter/xt_cgroup.c @@ -31,7 +31,7 @@ static int cgroup_mt_check(const struct xt_mtchk_param *par) if (info->invert & ~1) return -EINVAL; - return info->id ? 0 : -EINVAL; + return 0; } static bool diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index a3910fc2122b..47dc6836830a 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -104,7 +104,7 @@ struct xt_hashlimit_htable { spinlock_t lock; /* lock for list_head */ u_int32_t rnd; /* random seed for hash */ unsigned int count; /* number entries in table */ - struct timer_list timer; /* timer for gc */ + struct delayed_work gc_work; /* seq_file stuff */ struct proc_dir_entry *pde; @@ -213,7 +213,7 @@ dsthash_free(struct xt_hashlimit_htable *ht, struct dsthash_ent *ent) call_rcu_bh(&ent->rcu, dsthash_free_rcu); ht->count--; } -static void htable_gc(unsigned long htlong); +static void htable_gc(struct work_struct *work); static int htable_create(struct net *net, struct xt_hashlimit_mtinfo1 *minfo, u_int8_t family) @@ -273,9 +273,9 @@ static int htable_create(struct net *net, struct xt_hashlimit_mtinfo1 *minfo, } hinfo->net = net; - setup_timer(&hinfo->timer, htable_gc, (unsigned long)hinfo); - hinfo->timer.expires = jiffies + msecs_to_jiffies(hinfo->cfg.gc_interval); - add_timer(&hinfo->timer); + INIT_DEFERRABLE_WORK(&hinfo->gc_work, htable_gc); + queue_delayed_work(system_power_efficient_wq, &hinfo->gc_work, + msecs_to_jiffies(hinfo->cfg.gc_interval)); hlist_add_head(&hinfo->node, &hashlimit_net->htables); @@ -300,29 +300,30 @@ static void htable_selective_cleanup(struct xt_hashlimit_htable *ht, { unsigned int i; - /* lock hash table and iterate over it */ - spin_lock_bh(&ht->lock); for (i = 0; i < ht->cfg.size; i++) { struct dsthash_ent *dh; struct hlist_node *n; + + spin_lock_bh(&ht->lock); hlist_for_each_entry_safe(dh, n, &ht->hash[i], node) { if ((*select)(ht, dh)) dsthash_free(ht, dh); } + spin_unlock_bh(&ht->lock); + cond_resched(); } - spin_unlock_bh(&ht->lock); } -/* hash table garbage collector, run by timer */ -static void htable_gc(unsigned long htlong) +static void htable_gc(struct work_struct *work) { - struct xt_hashlimit_htable *ht = (struct xt_hashlimit_htable *)htlong; + struct xt_hashlimit_htable *ht; + + ht = container_of(work, struct xt_hashlimit_htable, gc_work.work); htable_selective_cleanup(ht, select_gc); - /* re-add the timer accordingly */ - ht->timer.expires = jiffies + msecs_to_jiffies(ht->cfg.gc_interval); - add_timer(&ht->timer); + queue_delayed_work(system_power_efficient_wq, + &ht->gc_work, msecs_to_jiffies(ht->cfg.gc_interval)); } static void htable_remove_proc_entry(struct xt_hashlimit_htable *hinfo) @@ -341,7 +342,7 @@ static void htable_remove_proc_entry(struct xt_hashlimit_htable *hinfo) static void htable_destroy(struct xt_hashlimit_htable *hinfo) { - del_timer_sync(&hinfo->timer); + cancel_delayed_work_sync(&hinfo->gc_work); htable_remove_proc_entry(hinfo); htable_selective_cleanup(hinfo, select_all); kfree(hinfo->name); diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 1ba67931eb1b..13332dbf291d 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -243,12 +243,13 @@ static int extract_icmp6_fields(const struct sk_buff *skb, unsigned int outside_hdrlen, int *protocol, - struct in6_addr **raddr, - struct in6_addr **laddr, + const struct in6_addr **raddr, + const struct in6_addr **laddr, __be16 *rport, - __be16 *lport) + __be16 *lport, + struct ipv6hdr *ipv6_var) { - struct ipv6hdr *inside_iph, _inside_iph; + const struct ipv6hdr *inside_iph; struct icmp6hdr *icmph, _icmph; __be16 *ports, _ports[2]; u8 inside_nexthdr; @@ -263,12 +264,14 @@ extract_icmp6_fields(const struct sk_buff *skb, if (icmph->icmp6_type & ICMPV6_INFOMSG_MASK) return 1; - inside_iph = skb_header_pointer(skb, outside_hdrlen + sizeof(_icmph), sizeof(_inside_iph), &_inside_iph); + inside_iph = skb_header_pointer(skb, outside_hdrlen + sizeof(_icmph), + sizeof(*ipv6_var), ipv6_var); if (inside_iph == NULL) return 1; inside_nexthdr = inside_iph->nexthdr; - inside_hdrlen = ipv6_skip_exthdr(skb, outside_hdrlen + sizeof(_icmph) + sizeof(_inside_iph), + inside_hdrlen = ipv6_skip_exthdr(skb, outside_hdrlen + sizeof(_icmph) + + sizeof(*ipv6_var), &inside_nexthdr, &inside_fragoff); if (inside_hdrlen < 0) return 1; /* hjm: Packet has no/incomplete transport layer headers. */ @@ -315,10 +318,10 @@ xt_socket_get_sock_v6(struct net *net, const u8 protocol, static bool socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) { - struct ipv6hdr *iph = ipv6_hdr(skb); + struct ipv6hdr ipv6_var, *iph = ipv6_hdr(skb); struct udphdr _hdr, *hp = NULL; struct sock *sk = skb->sk; - struct in6_addr *daddr = NULL, *saddr = NULL; + const struct in6_addr *daddr = NULL, *saddr = NULL; __be16 uninitialized_var(dport), uninitialized_var(sport); int thoff = 0, uninitialized_var(tproto); const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo; @@ -342,7 +345,7 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) } else if (tproto == IPPROTO_ICMPV6) { if (extract_icmp6_fields(skb, thoff, &tproto, &saddr, &daddr, - &sport, &dport)) + &sport, &dport, &ipv6_var)) return false; } else { return false; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 0dfe894afd48..1d52506bda14 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -205,7 +205,7 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb, nskb->protocol = htons((u16) sk->sk_protocol); nskb->pkt_type = netlink_is_kernel(sk) ? PACKET_KERNEL : PACKET_USER; - + skb_reset_network_header(nskb); ret = dev_queue_xmit(nskb); if (unlikely(ret > 0)) ret = net_xmit_errno(ret); @@ -510,14 +510,14 @@ out: return err; } -static void netlink_frame_flush_dcache(const struct nl_mmap_hdr *hdr) +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 + hdr->nm_len - 1); + 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++; @@ -535,9 +535,9 @@ static enum nl_mmap_status netlink_get_status(const struct nl_mmap_hdr *hdr) 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)); - smp_wmb(); } static struct nl_mmap_hdr * @@ -699,24 +699,16 @@ static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg, struct nl_mmap_hdr *hdr; struct sk_buff *skb; unsigned int maxlen; - bool excl = true; int err = 0, len = 0; - /* Netlink messages are validated by the receiver before processing. - * In order to avoid userspace changing the contents of the message - * after validation, the socket and the ring may only be used by a - * single process, otherwise we fall back to copying. - */ - if (atomic_long_read(&sk->sk_socket->file->f_count) > 2 || - atomic_read(&nlk->mapped) > 1) - excl = false; - 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) && @@ -724,35 +716,23 @@ static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg, schedule(); continue; } - if (hdr->nm_len > maxlen) { + + nm_len = ACCESS_ONCE(hdr->nm_len); + if (nm_len > maxlen) { err = -EINVAL; goto out; } - netlink_frame_flush_dcache(hdr); + netlink_frame_flush_dcache(hdr, nm_len); - if (likely(dst_portid == 0 && dst_group == 0 && excl)) { - skb = alloc_skb_head(GFP_KERNEL); - if (skb == NULL) { - err = -ENOBUFS; - goto out; - } - sock_hold(sk); - netlink_ring_setup_skb(skb, sk, ring, hdr); - NETLINK_CB(skb).flags |= NETLINK_SKB_TX; - __skb_put(skb, hdr->nm_len); - netlink_set_status(hdr, NL_MMAP_STATUS_RESERVED); - atomic_inc(&ring->pending); - } else { - skb = alloc_skb(hdr->nm_len, GFP_KERNEL); - if (skb == NULL) { - err = -ENOBUFS; - goto out; - } - __skb_put(skb, hdr->nm_len); - memcpy(skb->data, (void *)hdr + NL_MMAP_HDRLEN, hdr->nm_len); - netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED); + 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); @@ -798,7 +778,7 @@ static void netlink_queue_mmaped_skb(struct sock *sk, struct sk_buff *skb) 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); + netlink_frame_flush_dcache(hdr, hdr->nm_len); netlink_set_status(hdr, NL_MMAP_STATUS_VALID); NETLINK_CB(skb).flags |= NETLINK_SKB_DELIVERED; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 2c77e7b1a913..600c7646b3d3 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -42,6 +42,9 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, static int make_writable(struct sk_buff *skb, int write_len) { + if (!pskb_may_pull(skb, write_len)) + return -ENOMEM; + if (!skb_cloned(skb) || skb_clone_writable(skb, write_len)) return 0; @@ -70,6 +73,8 @@ static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci) vlan_set_encap_proto(skb, vhdr); skb->mac_header += VLAN_HLEN; + if (skb_network_offset(skb) < ETH_HLEN) + skb_set_network_header(skb, ETH_HLEN); skb_reset_mac_len(skb); return 0; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 48a6a93db296..48b181797d7b 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -635,6 +635,7 @@ static void init_prb_bdqc(struct packet_sock *po, p1->tov_in_jiffies = msecs_to_jiffies(p1->retire_blk_tov); p1->blk_sizeof_priv = req_u->req3.tp_sizeof_priv; + p1->max_frame_len = p1->kblk_size - BLK_PLUS_PRIV(p1->blk_sizeof_priv); prb_init_ft_ops(p1, req_u); prb_setup_retire_blk_timer(po, tx_ring); prb_open_block(p1, pbd); @@ -1946,6 +1947,18 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if ((int)snaplen < 0) snaplen = 0; } + } else if (unlikely(macoff + snaplen > + GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len)) { + u32 nval; + + nval = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len - macoff; + pr_err_once("tpacket_rcv: packet too big, clamped from %u to %u. macoff=%u\n", + snaplen, nval, macoff); + snaplen = nval; + if (unlikely((int)snaplen < 0)) { + snaplen = 0; + macoff = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len; + } } spin_lock(&sk->sk_receive_queue.lock); h.raw = packet_current_rx_frame(po, skb, @@ -3779,6 +3792,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, goto out; if (unlikely(req->tp_block_size & (PAGE_SIZE - 1))) goto out; + if (po->tp_version >= TPACKET_V3 && + (int)(req->tp_block_size - + BLK_PLUS_PRIV(req_u->req3.tp_sizeof_priv)) <= 0) + goto out; if (unlikely(req->tp_frame_size < po->tp_hdrlen + po->tp_reserve)) goto out; diff --git a/net/packet/internal.h b/net/packet/internal.h index eb9580a6b25f..cdddf6a30399 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -29,6 +29,7 @@ struct tpacket_kbdq_core { char *pkblk_start; char *pkblk_end; int kblk_size; + unsigned int max_frame_len; unsigned int knum_blocks; uint64_t knxt_seq_num; char *prev; diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c index a817705ce2d0..dba8d0864f18 100644 --- a/net/rds/iw_rdma.c +++ b/net/rds/iw_rdma.c @@ -88,7 +88,9 @@ static unsigned int rds_iw_unmap_fastreg_list(struct rds_iw_mr_pool *pool, int *unpinned); static void rds_iw_destroy_fastreg(struct rds_iw_mr_pool *pool, struct rds_iw_mr *ibmr); -static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwdev, struct rdma_cm_id **cm_id) +static int rds_iw_get_device(struct sockaddr_in *src, struct sockaddr_in *dst, + struct rds_iw_device **rds_iwdev, + struct rdma_cm_id **cm_id) { struct rds_iw_device *iwdev; struct rds_iw_cm_id *i_cm_id; @@ -112,15 +114,15 @@ static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwd src_addr->sin_port, dst_addr->sin_addr.s_addr, dst_addr->sin_port, - rs->rs_bound_addr, - rs->rs_bound_port, - rs->rs_conn_addr, - rs->rs_conn_port); + src->sin_addr.s_addr, + src->sin_port, + dst->sin_addr.s_addr, + dst->sin_port); #ifdef WORKING_TUPLE_DETECTION - if (src_addr->sin_addr.s_addr == rs->rs_bound_addr && - src_addr->sin_port == rs->rs_bound_port && - dst_addr->sin_addr.s_addr == rs->rs_conn_addr && - dst_addr->sin_port == rs->rs_conn_port) { + if (src_addr->sin_addr.s_addr == src->sin_addr.s_addr && + src_addr->sin_port == src->sin_port && + dst_addr->sin_addr.s_addr == dst->sin_addr.s_addr && + dst_addr->sin_port == dst->sin_port) { #else /* FIXME - needs to compare the local and remote * ipaddr/port tuple, but the ipaddr is the only @@ -128,7 +130,7 @@ static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwd * zero'ed. It doesn't appear to be properly populated * during connection setup... */ - if (src_addr->sin_addr.s_addr == rs->rs_bound_addr) { + if (src_addr->sin_addr.s_addr == src->sin_addr.s_addr) { #endif spin_unlock_irq(&iwdev->spinlock); *rds_iwdev = iwdev; @@ -180,19 +182,13 @@ int rds_iw_update_cm_id(struct rds_iw_device *rds_iwdev, struct rdma_cm_id *cm_i { struct sockaddr_in *src_addr, *dst_addr; struct rds_iw_device *rds_iwdev_old; - struct rds_sock rs; struct rdma_cm_id *pcm_id; int rc; src_addr = (struct sockaddr_in *)&cm_id->route.addr.src_addr; dst_addr = (struct sockaddr_in *)&cm_id->route.addr.dst_addr; - rs.rs_bound_addr = src_addr->sin_addr.s_addr; - rs.rs_bound_port = src_addr->sin_port; - rs.rs_conn_addr = dst_addr->sin_addr.s_addr; - rs.rs_conn_port = dst_addr->sin_port; - - rc = rds_iw_get_device(&rs, &rds_iwdev_old, &pcm_id); + rc = rds_iw_get_device(src_addr, dst_addr, &rds_iwdev_old, &pcm_id); if (rc) rds_iw_remove_cm_id(rds_iwdev, cm_id); @@ -598,9 +594,17 @@ void *rds_iw_get_mr(struct scatterlist *sg, unsigned long nents, struct rds_iw_device *rds_iwdev; struct rds_iw_mr *ibmr = NULL; struct rdma_cm_id *cm_id; + struct sockaddr_in src = { + .sin_addr.s_addr = rs->rs_bound_addr, + .sin_port = rs->rs_bound_port, + }; + struct sockaddr_in dst = { + .sin_addr.s_addr = rs->rs_conn_addr, + .sin_port = rs->rs_conn_port, + }; int ret; - ret = rds_iw_get_device(rs, &rds_iwdev, &cm_id); + ret = rds_iw_get_device(&src, &dst, &rds_iwdev, &cm_id); if (ret || !cm_id) { ret = -ENODEV; goto out; diff --git a/net/rds/sysctl.c b/net/rds/sysctl.c index b5cb2aa08f33..35773ad6d23d 100644 --- a/net/rds/sysctl.c +++ b/net/rds/sysctl.c @@ -71,14 +71,14 @@ static struct ctl_table rds_sysctl_rds_table[] = { { .procname = "max_unacked_packets", .data = &rds_sysctl_max_unacked_packets, - .maxlen = sizeof(unsigned long), + .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "max_unacked_bytes", .data = &rds_sysctl_max_unacked_bytes, - .maxlen = sizeof(unsigned long), + .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c index 34b5490dde65..4949f753686c 100644 --- a/net/rxrpc/ar-recvmsg.c +++ b/net/rxrpc/ar-recvmsg.c @@ -87,7 +87,7 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock, if (!skb) { /* nothing remains on the queue */ if (copied && - (msg->msg_flags & MSG_PEEK || timeo == 0)) + (flags & MSG_PEEK || timeo == 0)) goto out; /* wait for a message to turn up */ diff --git a/net/sched/ematch.c b/net/sched/ematch.c index 3a633debb6df..a2abc449ce8f 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -227,6 +227,7 @@ static int tcf_em_validate(struct tcf_proto *tp, * to replay the request. */ module_put(em->ops->owner); + em->ops = NULL; err = -EAGAIN; } #endif diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 5d97d8fe4be7..abc0922d0e31 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1235,7 +1235,6 @@ void sctp_assoc_update(struct sctp_association *asoc, asoc->peer.peer_hmacs = new->peer.peer_hmacs; new->peer.peer_hmacs = NULL; - sctp_auth_key_put(asoc->asoc_shared_key); sctp_auth_asoc_init_active_key(asoc, GFP_ATOMIC); } @@ -1627,6 +1626,8 @@ struct sctp_chunk *sctp_assoc_lookup_asconf_ack( * ack chunk whose serial number matches that of the request. */ list_for_each_entry(ack, &asoc->asconf_ack_list, transmitted_list) { + if (sctp_chunk_pending(ack)) + continue; if (ack->subh.addip_hdr->serial == serial) { sctp_chunk_hold(ack); return ack; diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 0e8529113dc5..fb7976aee61c 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -862,8 +862,6 @@ int sctp_auth_set_key(struct sctp_endpoint *ep, list_add(&cur_key->key_list, sh_keys); cur_key->key = key; - sctp_auth_key_hold(key); - return 0; nomem: if (!replace) diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 4de12afa13d4..7e8a16c77039 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -140,18 +140,9 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) } else { /* Nothing to do. Next chunk in the packet, please. */ ch = (sctp_chunkhdr_t *) chunk->chunk_end; - /* Force chunk->skb->data to chunk->chunk_end. */ - skb_pull(chunk->skb, - chunk->chunk_end - chunk->skb->data); - - /* Verify that we have at least chunk headers - * worth of buffer left. - */ - if (skb_headlen(chunk->skb) < sizeof(sctp_chunkhdr_t)) { - sctp_chunk_free(chunk); - chunk = queue->in_progress = NULL; - } + skb_pull(chunk->skb, chunk->chunk_end - chunk->skb->data); + /* We are guaranteed to pull a SCTP header. */ } } @@ -187,24 +178,14 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) skb_pull(chunk->skb, sizeof(sctp_chunkhdr_t)); chunk->subh.v = NULL; /* Subheader is no longer valid. */ - if (chunk->chunk_end < skb_tail_pointer(chunk->skb)) { + if (chunk->chunk_end + sizeof(sctp_chunkhdr_t) < + skb_tail_pointer(chunk->skb)) { /* This is not a singleton */ chunk->singleton = 0; } else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) { - /* RFC 2960, Section 6.10 Bundling - * - * Partial chunks MUST NOT be placed in an SCTP packet. - * If the receiver detects a partial chunk, it MUST drop - * the chunk. - * - * Since the end of the chunk is past the end of our buffer - * (which contains the whole packet, we can freely discard - * the whole packet. - */ - sctp_chunk_free(chunk); - chunk = queue->in_progress = NULL; - - return NULL; + /* Discard inside state machine. */ + chunk->pdiscard = 1; + chunk->chunk_end = skb_tail_pointer(chunk->skb); } else { /* We are at the end of the packet, so mark the chunk * in case we need to send a SACK. diff --git a/net/sctp/output.c b/net/sctp/output.c index 8267b06c3646..740ca5f7add0 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -401,12 +401,12 @@ int sctp_packet_transmit(struct sctp_packet *packet) sk = chunk->skb->sk; /* Allocate the new skb. */ - nskb = alloc_skb(packet->size + LL_MAX_HEADER, GFP_ATOMIC); + nskb = alloc_skb(packet->size + MAX_HEADER, GFP_ATOMIC); if (!nskb) goto nomem; /* Make sure the outbound skb has enough header room reserved. */ - skb_reserve(nskb, packet->overhead + LL_MAX_HEADER); + skb_reserve(nskb, packet->overhead + MAX_HEADER); /* Set the owning socket so that we know where to get the * destination IP address. diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index fee5552ddf92..df06b13a50f6 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2608,7 +2608,10 @@ do_addr_param: addr_param = param.v + sizeof(sctp_addip_param_t); - af = sctp_get_af_specific(param_type2af(param.p->type)); + af = sctp_get_af_specific(param_type2af(addr_param->p.type)); + if (af == NULL) + break; + af->from_addr_param(&addr, addr_param, htons(asoc->peer.port), 0); @@ -3110,50 +3113,63 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, return SCTP_ERROR_NO_ERROR; } -/* Verify the ASCONF packet before we process it. */ -int sctp_verify_asconf(const struct sctp_association *asoc, - struct sctp_paramhdr *param_hdr, void *chunk_end, - struct sctp_paramhdr **errp) { - sctp_addip_param_t *asconf_param; +/* Verify the ASCONF packet before we process it. */ +bool sctp_verify_asconf(const struct sctp_association *asoc, + struct sctp_chunk *chunk, bool addr_param_needed, + struct sctp_paramhdr **errp) +{ + sctp_addip_chunk_t *addip = (sctp_addip_chunk_t *) chunk->chunk_hdr; union sctp_params param; - int length, plen; + bool addr_param_seen = false; - param.v = (sctp_paramhdr_t *) param_hdr; - while (param.v <= chunk_end - sizeof(sctp_paramhdr_t)) { - length = ntohs(param.p->length); - *errp = param.p; - - if (param.v > chunk_end - length || - length < sizeof(sctp_paramhdr_t)) - return 0; + sctp_walk_params(param, addip, addip_hdr.params) { + size_t length = ntohs(param.p->length); + *errp = param.p; switch (param.p->type) { + case SCTP_PARAM_ERR_CAUSE: + break; + case SCTP_PARAM_IPV4_ADDRESS: + if (length != sizeof(sctp_ipv4addr_param_t)) + return false; + addr_param_seen = true; + break; + case SCTP_PARAM_IPV6_ADDRESS: + if (length != sizeof(sctp_ipv6addr_param_t)) + return false; + addr_param_seen = true; + break; case SCTP_PARAM_ADD_IP: case SCTP_PARAM_DEL_IP: case SCTP_PARAM_SET_PRIMARY: - asconf_param = (sctp_addip_param_t *)param.v; - plen = ntohs(asconf_param->param_hdr.length); - if (plen < sizeof(sctp_addip_param_t) + - sizeof(sctp_paramhdr_t)) - return 0; + /* In ASCONF chunks, these need to be first. */ + if (addr_param_needed && !addr_param_seen) + return false; + length = ntohs(param.addip->param_hdr.length); + if (length < sizeof(sctp_addip_param_t) + + sizeof(sctp_paramhdr_t)) + return false; break; case SCTP_PARAM_SUCCESS_REPORT: case SCTP_PARAM_ADAPTATION_LAYER_IND: if (length != sizeof(sctp_addip_param_t)) - return 0; - + return false; break; default: - break; + /* This is unkown to us, reject! */ + return false; } - - param.v += WORD_ROUND(length); } - if (param.v != chunk_end) - return 0; + /* Remaining sanity checks. */ + if (addr_param_needed && !addr_param_seen) + return false; + if (!addr_param_needed && addr_param_seen) + return false; + if (param.v != chunk->chunk_end) + return false; - return 1; + return true; } /* Process an incoming ASCONF chunk with the next expected serial no. and @@ -3162,16 +3178,17 @@ int sctp_verify_asconf(const struct sctp_association *asoc, struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, struct sctp_chunk *asconf) { + sctp_addip_chunk_t *addip = (sctp_addip_chunk_t *) asconf->chunk_hdr; + bool all_param_pass = true; + union sctp_params param; sctp_addiphdr_t *hdr; union sctp_addr_param *addr_param; sctp_addip_param_t *asconf_param; struct sctp_chunk *asconf_ack; - __be16 err_code; int length = 0; int chunk_len; __u32 serial; - int all_param_pass = 1; chunk_len = ntohs(asconf->chunk_hdr->length) - sizeof(sctp_chunkhdr_t); hdr = (sctp_addiphdr_t *)asconf->skb->data; @@ -3199,9 +3216,14 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, goto done; /* Process the TLVs contained within the ASCONF chunk. */ - while (chunk_len > 0) { + sctp_walk_params(param, addip, addip_hdr.params) { + /* Skip preceeding address parameters. */ + if (param.p->type == SCTP_PARAM_IPV4_ADDRESS || + param.p->type == SCTP_PARAM_IPV6_ADDRESS) + continue; + err_code = sctp_process_asconf_param(asoc, asconf, - asconf_param); + param.addip); /* ADDIP 4.1 A7) * If an error response is received for a TLV parameter, * all TLVs with no response before the failed TLV are @@ -3209,28 +3231,20 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, * the failed response are considered unsuccessful unless * a specific success indication is present for the parameter. */ - if (SCTP_ERROR_NO_ERROR != err_code) - all_param_pass = 0; - + if (err_code != SCTP_ERROR_NO_ERROR) + all_param_pass = false; if (!all_param_pass) - sctp_add_asconf_response(asconf_ack, - asconf_param->crr_id, err_code, - asconf_param); + sctp_add_asconf_response(asconf_ack, param.addip->crr_id, + err_code, param.addip); /* ADDIP 4.3 D11) When an endpoint receiving an ASCONF to add * an IP address sends an 'Out of Resource' in its response, it * MUST also fail any subsequent add or delete requests bundled * in the ASCONF. */ - if (SCTP_ERROR_RSRC_LOW == err_code) + if (err_code == SCTP_ERROR_RSRC_LOW) goto done; - - /* Move to the next ASCONF param. */ - length = ntohs(asconf_param->param_hdr.length); - asconf_param = (void *)asconf_param + length; - chunk_len -= length; } - done: asoc->peer.addip_serial++; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 5170a1ff95a1..3e287a3fa03b 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -170,6 +170,9 @@ sctp_chunk_length_valid(struct sctp_chunk *chunk, { __u16 chunk_length = ntohs(chunk->chunk_hdr->length); + /* Previously already marked? */ + if (unlikely(chunk->pdiscard)) + return 0; if (unlikely(chunk_length < required_length)) return 0; @@ -1775,9 +1778,22 @@ static sctp_disposition_t sctp_sf_do_dupcook_a(struct net *net, /* Update the content of current association. */ sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc)); sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); - sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, - SCTP_STATE(SCTP_STATE_ESTABLISHED)); - sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); + if (sctp_state(asoc, SHUTDOWN_PENDING) && + (sctp_sstate(asoc->base.sk, CLOSING) || + sock_flag(asoc->base.sk, SOCK_DEAD))) { + /* if were currently in SHUTDOWN_PENDING, but the socket + * has been closed by user, don't transition to ESTABLISHED. + * Instead trigger SHUTDOWN bundled with COOKIE_ACK. + */ + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); + return sctp_sf_do_9_2_start_shutdown(net, ep, asoc, + SCTP_ST_CHUNK(0), NULL, + commands); + } else { + sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, + SCTP_STATE(SCTP_STATE_ESTABLISHED)); + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); + } return SCTP_DISPOSITION_CONSUME; nomem_ev: @@ -3578,9 +3594,7 @@ sctp_disposition_t sctp_sf_do_asconf(struct net *net, struct sctp_chunk *asconf_ack = NULL; struct sctp_paramhdr *err_param = NULL; sctp_addiphdr_t *hdr; - union sctp_addr_param *addr_param; __u32 serial; - int length; if (!sctp_vtag_verify(chunk, asoc)) { sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_BAD_TAG, @@ -3605,17 +3619,8 @@ sctp_disposition_t sctp_sf_do_asconf(struct net *net, hdr = (sctp_addiphdr_t *)chunk->skb->data; serial = ntohl(hdr->serial); - addr_param = (union sctp_addr_param *)hdr->params; - length = ntohs(addr_param->p.length); - if (length < sizeof(sctp_paramhdr_t)) - return sctp_sf_violation_paramlen(net, ep, asoc, type, arg, - (void *)addr_param, commands); - /* Verify the ASCONF chunk before processing it. */ - if (!sctp_verify_asconf(asoc, - (sctp_paramhdr_t *)((void *)addr_param + length), - (void *)chunk->chunk_end, - &err_param)) + if (!sctp_verify_asconf(asoc, chunk, true, &err_param)) return sctp_sf_violation_paramlen(net, ep, asoc, type, arg, (void *)err_param, commands); @@ -3732,10 +3737,7 @@ sctp_disposition_t sctp_sf_do_asconf_ack(struct net *net, rcvd_serial = ntohl(addip_hdr->serial); /* Verify the ASCONF-ACK chunk before processing it. */ - if (!sctp_verify_asconf(asoc, - (sctp_paramhdr_t *)addip_hdr->params, - (void *)asconf_ack->chunk_end, - &err_param)) + if (!sctp_verify_asconf(asoc, asconf_ack, false, &err_param)) return sctp_sf_violation_paramlen(net, ep, asoc, type, arg, (void *)err_param, commands); diff --git a/net/socket.c b/net/socket.c index a19ae1968d37..1b2c2d62ff20 100644 --- a/net/socket.c +++ b/net/socket.c @@ -886,9 +886,6 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos, static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb, struct sock_iocb *siocb) { - if (!is_sync_kiocb(iocb)) - BUG(); - siocb->kiocb = iocb; iocb->private = siocb; return siocb; diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index ae333c1845bb..0adc66caae2f 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -920,7 +920,7 @@ static unsigned int cache_poll(struct file *filp, poll_table *wait, poll_wait(filp, &queue_wait, wait); /* alway allow write */ - mask = POLL_OUT | POLLWRNORM; + mask = POLLOUT | POLLWRNORM; if (!rp) return mask; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 3ea5cda787c7..5ff8b87c3d04 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -533,6 +533,8 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) if (args->flags & RPC_CLNT_CREATE_AUTOBIND) clnt->cl_autobind = 1; + if (args->flags & RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT) + clnt->cl_noretranstimeo = 1; if (args->flags & RPC_CLNT_CREATE_DISCRTRY) clnt->cl_discrtry = 1; if (!(args->flags & RPC_CLNT_CREATE_QUIET)) @@ -571,6 +573,7 @@ static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args, /* Turn off autobind on clones */ new->cl_autobind = 0; new->cl_softrtry = clnt->cl_softrtry; + new->cl_noretranstimeo = clnt->cl_noretranstimeo; new->cl_discrtry = clnt->cl_discrtry; new->cl_chatty = clnt->cl_chatty; return new; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 0addefca8e77..41c2f9d7a148 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -842,6 +842,8 @@ static void xs_error_report(struct sock *sk) dprintk("RPC: xs_error_report client %p, error=%d...\n", xprt, -err); trace_rpc_socket_error(xprt, sk->sk_socket, err); + if (test_bit(XPRT_CONNECTION_REUSE, &xprt->state)) + goto out; xprt_wake_pending_tasks(xprt, err); out: read_unlock_bh(&sk->sk_callback_lock); @@ -2251,7 +2253,9 @@ static void xs_tcp_setup_socket(struct work_struct *work) abort_and_exit = test_and_clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); /* "close" the socket, preserving the local port */ + set_bit(XPRT_CONNECTION_REUSE, &xprt->state); xs_tcp_reuse_connection(transport); + clear_bit(XPRT_CONNECTION_REUSE, &xprt->state); if (abort_and_exit) goto out_eagain; diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 78559b5bbd1f..27157a7801e8 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -516,7 +516,7 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, { struct ieee80211_sta_ht_cap *ht_cap; struct ieee80211_sta_vht_cap *vht_cap; - u32 width, control_freq; + u32 width, control_freq, cap; if (WARN_ON(!cfg80211_chandef_valid(chandef))) return false; @@ -554,7 +554,8 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, return false; break; case NL80211_CHAN_WIDTH_80P80: - if (!(vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ)) + cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; + if (cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) return false; case NL80211_CHAN_WIDTH_80: if (!vht_cap->vht_supported) @@ -565,7 +566,9 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, case NL80211_CHAN_WIDTH_160: if (!vht_cap->vht_supported) return false; - if (!(vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ)) + cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; + if (cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ && + cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) return false; prohibited_flags |= IEEE80211_CHAN_NO_160MHZ; width = 160; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index e6283464a8e6..c260243dbe07 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2697,6 +2697,9 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->get_key) return -EOPNOTSUPP; + if (!pairwise && mac_addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) + return -ENOENT; + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; @@ -2716,10 +2719,6 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, mac_addr)) goto nla_put_failure; - if (pairwise && mac_addr && - !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) - return -ENOENT; - err = rdev_get_key(rdev, dev, key_idx, pairwise, mac_addr, &cookie, get_key_callback); @@ -2890,7 +2889,7 @@ static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info) wdev_lock(dev->ieee80211_ptr); err = nl80211_key_allowed(dev->ieee80211_ptr); - if (key.type == NL80211_KEYTYPE_PAIRWISE && mac_addr && + if (key.type == NL80211_KEYTYPE_GROUP && mac_addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) err = -ENOENT; @@ -4191,6 +4190,16 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) if (parse_station_flags(info, dev->ieee80211_ptr->iftype, ¶ms)) return -EINVAL; + /* HT/VHT requires QoS, but if we don't have that just ignore HT/VHT + * as userspace might just pass through the capabilities from the IEs + * directly, rather than enforcing this restriction and returning an + * error in this case. + */ + if (!(params.sta_flags_set & BIT(NL80211_STA_FLAG_WME))) { + params.ht_capa = NULL; + params.vht_capa = NULL; + } + /* When you run into this, adjust the code below for the new flag */ BUILD_BUG_ON(NL80211_STA_FLAG_MAX != 7); @@ -6796,6 +6805,9 @@ void __cfg80211_send_event_skb(struct sk_buff *skb, gfp_t gfp) struct nlattr *data = ((void **)skb->cb)[2]; enum nl80211_multicast_groups mcgrp = NL80211_MCGRP_TESTMODE; + /* clear CB data for netlink core to own from now on */ + memset(skb->cb, 0, sizeof(skb->cb)); + nla_nest_end(skb, data); genlmsg_end(skb, hdr); @@ -9075,6 +9087,9 @@ int cfg80211_vendor_cmd_reply(struct sk_buff *skb) void *hdr = ((void **)skb->cb)[1]; struct nlattr *data = ((void **)skb->cb)[2]; + /* clear CB data for netlink core to own from now on */ + memset(skb->cb, 0, sizeof(skb->cb)); + if (WARN_ON(!rdev->cur_cmd_info)) { kfree_skb(skb); return -EINVAL; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 338794ea44d1..04d530560ec8 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1547,7 +1547,7 @@ static enum reg_request_treatment reg_process_hint_driver(struct wiphy *wiphy, struct regulatory_request *driver_request) { - const struct ieee80211_regdomain *regd; + const struct ieee80211_regdomain *regd, *tmp; enum reg_request_treatment treatment; treatment = __reg_process_hint_driver(driver_request); @@ -1566,7 +1566,10 @@ reg_process_hint_driver(struct wiphy *wiphy, kfree(driver_request); return REG_REQ_IGNORE; } + + tmp = get_wiphy_regdom(wiphy); rcu_assign_pointer(wiphy->regd, regd); + rcu_free_regdom(tmp); } @@ -1625,11 +1628,8 @@ __reg_process_hint_country_ie(struct wiphy *wiphy, return REG_REQ_IGNORE; return REG_REQ_ALREADY_SET; } - /* - * Two consecutive Country IE hints on the same wiphy. - * This should be picked up early by the driver/stack - */ - if (WARN_ON(regdom_changes(country_ie_request->alpha2))) + + if (regdom_changes(country_ie_request->alpha2)) return REG_REQ_OK; return REG_REQ_ALREADY_SET; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 1d5c7bf29938..59cf325f2772 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -41,6 +41,11 @@ static struct dst_entry *xfrm_policy_sk_bundles; +struct xfrm_flo { + struct dst_entry *dst_orig; + u8 flags; +}; + static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock); static struct xfrm_policy_afinfo __rcu *xfrm_policy_afinfo[NPROTO] __read_mostly; @@ -1889,13 +1894,14 @@ static int xdst_queue_output(struct sk_buff *skb) } static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net, - struct dst_entry *dst, + struct xfrm_flo *xflo, const struct flowi *fl, int num_xfrms, u16 family) { int err; struct net_device *dev; + struct dst_entry *dst; struct dst_entry *dst1; struct xfrm_dst *xdst; @@ -1903,9 +1909,12 @@ static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net, if (IS_ERR(xdst)) return xdst; - if (net->xfrm.sysctl_larval_drop || num_xfrms <= 0) + if (!(xflo->flags & XFRM_LOOKUP_QUEUE) || + net->xfrm.sysctl_larval_drop || + num_xfrms <= 0) return xdst; + dst = xflo->dst_orig; dst1 = &xdst->u.dst; dst_hold(dst); xdst->route = dst; @@ -1947,7 +1956,7 @@ static struct flow_cache_object * xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, struct flow_cache_object *oldflo, void *ctx) { - struct dst_entry *dst_orig = (struct dst_entry *)ctx; + struct xfrm_flo *xflo = (struct xfrm_flo *)ctx; struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; struct xfrm_dst *xdst, *new_xdst; int num_pols = 0, num_xfrms = 0, i, err, pol_dead; @@ -1988,7 +1997,8 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, goto make_dummy_bundle; } - new_xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family, dst_orig); + new_xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family, + xflo->dst_orig); if (IS_ERR(new_xdst)) { err = PTR_ERR(new_xdst); if (err != -EAGAIN) @@ -2022,7 +2032,7 @@ make_dummy_bundle: /* We found policies, but there's no bundles to instantiate: * either because the policy blocks, has no transformations or * we could not build template (no xfrm_states).*/ - xdst = xfrm_create_dummy_bundle(net, dst_orig, fl, num_xfrms, family); + xdst = xfrm_create_dummy_bundle(net, xflo, fl, num_xfrms, family); if (IS_ERR(xdst)) { xfrm_pols_put(pols, num_pols); return ERR_CAST(xdst); @@ -2121,13 +2131,18 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, } if (xdst == NULL) { + struct xfrm_flo xflo; + + xflo.dst_orig = dst_orig; + xflo.flags = flags; + /* To accelerate a bit... */ if ((dst_orig->flags & DST_NOXFRM) || !net->xfrm.policy_count[XFRM_POLICY_OUT]) goto nopol; flo = flow_cache_lookup(net, fl, family, dir, - xfrm_bundle_lookup, dst_orig); + xfrm_bundle_lookup, &xflo); if (flo == NULL) goto nopol; if (IS_ERR(flo)) { @@ -2155,7 +2170,7 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, xfrm_pols_put(pols, drop_pols); XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); - return make_blackhole(net, family, dst_orig); + return ERR_PTR(-EREMOTE); } err = -EAGAIN; @@ -2212,6 +2227,23 @@ dropdst: } EXPORT_SYMBOL(xfrm_lookup); +/* Callers of xfrm_lookup_route() must ensure a call to dst_output(). + * Otherwise we may send out blackholed packets. + */ +struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, + const struct flowi *fl, + struct sock *sk, int flags) +{ + struct dst_entry *dst = xfrm_lookup(net, dst_orig, fl, sk, + flags | XFRM_LOOKUP_QUEUE); + + if (IS_ERR(dst) && PTR_ERR(dst) == -EREMOTE) + return make_blackhole(net, dst_orig->ops->family, dst_orig); + + return dst; +} +EXPORT_SYMBOL(xfrm_lookup_route); + static inline int xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl) { @@ -2477,7 +2509,7 @@ int __xfrm_route_forward(struct sk_buff *skb, unsigned short family) skb_dst_force(skb); - dst = xfrm_lookup(net, skb_dst(skb), &fl, NULL, 0); + dst = xfrm_lookup(net, skb_dst(skb), &fl, NULL, XFRM_LOOKUP_QUEUE); if (IS_ERR(dst)) { res = 0; dst = NULL; diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c index db1512ae30cc..f53542b55de6 100644 --- a/scripts/kconfig/menu.c +++ b/scripts/kconfig/menu.c @@ -545,7 +545,7 @@ static void get_prompt_str(struct gstr *r, struct property *prop, { int i, j; struct menu *submenu[8], *menu, *location = NULL; - struct jump_key *jump; + struct jump_key *jump = NULL; str_printf(r, _("Prompt: %s\n"), _(prop->text)); menu = prop->menu->parent; @@ -583,7 +583,7 @@ static void get_prompt_str(struct gstr *r, struct property *prop, str_printf(r, _(" Location:\n")); for (j = 4; --i >= 0; j += 2) { menu = submenu[i]; - if (head && location && menu == location) + if (jump && menu == location) jump->offset = strlen(r->s); str_printf(r, "%*c-> %s", j, ' ', _(menu_get_prompt(menu))); diff --git a/scripts/kernel-doc b/scripts/kernel-doc index da058da413e7..2438cc351952 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1753,7 +1753,7 @@ sub dump_struct($$) { # strip kmemcheck_bitfield_{begin,end}.*; $members =~ s/kmemcheck_bitfield_.*?;//gos; # strip attributes - $members =~ s/__aligned\s*\(.+\)//gos; + $members =~ s/__aligned\s*\([^;]*\)//gos; create_parameterlist($members, ';', $file); check_sections($file, $declaration_name, "struct", $sectcheck, $struct_actual, $nested); diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index 397b6b84e8c5..e28f38eff70e 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -262,7 +262,6 @@ if ($arch eq "x86_64") { # force flags for this arch $ld .= " -m shlelf_linux"; $objcopy .= " -O elf32-sh-linux"; - $cc .= " -m32"; } elsif ($arch eq "powerpc") { $local_regex = "^[0-9a-fA-F]+\\s+t\\s+(\\.?\\S+)"; diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c index 3bab89eb21d6..e90ab0e20db8 100644 --- a/security/integrity/evm/evm_crypto.c +++ b/security/integrity/evm/evm_crypto.c @@ -137,7 +137,7 @@ static int evm_calc_hmac_or_hash(struct dentry *dentry, int error; int size; - if (!inode->i_op || !inode->i_op->getxattr) + if (!inode->i_op->getxattr) return -EOPNOTSUPP; desc = init_desc(type); if (IS_ERR(desc)) diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c index 3c5cbb977254..690cd632bd5b 100644 --- a/security/integrity/evm/evm_main.c +++ b/security/integrity/evm/evm_main.c @@ -62,7 +62,7 @@ static int evm_find_protected_xattrs(struct dentry *dentry) int error; int count = 0; - if (!inode->i_op || !inode->i_op->getxattr) + if (!inode->i_op->getxattr) return -EOPNOTSUPP; for (xattr = evm_config_xattrnames; *xattr != NULL; xattr++) { @@ -269,6 +269,13 @@ static int evm_protect_xattr(struct dentry *dentry, const char *xattr_name, goto out; } evm_status = evm_verify_current_integrity(dentry); + if (evm_status == INTEGRITY_NOXATTRS) { + struct integrity_iint_cache *iint; + + iint = integrity_iint_find(dentry->d_inode); + if (iint && (iint->flags & IMA_NEW_FILE)) + return 0; + } out: if (evm_status != INTEGRITY_PASS) integrity_audit_msg(AUDIT_INTEGRITY_METADATA, dentry->d_inode, @@ -296,9 +303,12 @@ int evm_inode_setxattr(struct dentry *dentry, const char *xattr_name, { const struct evm_ima_xattr_data *xattr_data = xattr_value; - if ((strcmp(xattr_name, XATTR_NAME_EVM) == 0) - && (xattr_data->type == EVM_XATTR_HMAC)) - return -EPERM; + if (strcmp(xattr_name, XATTR_NAME_EVM) == 0) { + if (!xattr_value_len) + return -EINVAL; + if (xattr_data->type != EVM_IMA_XATTR_DIGSIG) + return -EPERM; + } return evm_protect_xattr(dentry, xattr_name, xattr_value, xattr_value_len); } diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index 734e9468aca0..6df1b2527d02 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -194,8 +194,11 @@ int ima_appraise_measurement(int func, struct integrity_iint_cache *iint, goto out; cause = "missing-hash"; - status = - (inode->i_size == 0) ? INTEGRITY_PASS : INTEGRITY_NOLABEL; + status = INTEGRITY_NOLABEL; + if (inode->i_size == 0) { + iint->flags |= IMA_NEW_FILE; + status = INTEGRITY_PASS; + } goto out; } diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 76d8aad146a8..9f70efd08058 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -131,11 +131,13 @@ static void ima_check_last_writer(struct integrity_iint_cache *iint, return; mutex_lock(&inode->i_mutex); - if (atomic_read(&inode->i_writecount) == 1 && - iint->version != inode->i_version) { - iint->flags &= ~IMA_DONE_MASK; - if (iint->flags & IMA_APPRAISE) - ima_update_xattr(iint, file); + if (atomic_read(&inode->i_writecount) == 1) { + if ((iint->version != inode->i_version) || + (iint->flags & IMA_NEW_FILE)) { + iint->flags &= ~(IMA_DONE_MASK | IMA_NEW_FILE); + if (iint->flags & IMA_APPRAISE) + ima_update_xattr(iint, file); + } } mutex_unlock(&inode->i_mutex); } diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h index 33c0a70f6b15..2f8715d77a5a 100644 --- a/security/integrity/integrity.h +++ b/security/integrity/integrity.h @@ -31,6 +31,7 @@ #define IMA_DIGSIG 0x01000000 #define IMA_DIGSIG_REQUIRED 0x02000000 #define IMA_PERMIT_DIRECTIO 0x04000000 +#define IMA_NEW_FILE 0x08000000 #define IMA_DO_MASK (IMA_MEASURE | IMA_APPRAISE | IMA_AUDIT | \ IMA_APPRAISE_SUBMASK) diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c index 9e1e005c7596..c4c8df4b214d 100644 --- a/security/keys/encrypted-keys/encrypted.c +++ b/security/keys/encrypted-keys/encrypted.c @@ -1018,10 +1018,13 @@ static int __init init_encrypted(void) ret = encrypted_shash_alloc(); if (ret < 0) return ret; + ret = aes_get_sizes(); + if (ret < 0) + goto out; ret = register_key_type(&key_type_encrypted); if (ret < 0) goto out; - return aes_get_sizes(); + return 0; out: encrypted_shash_release(); return ret; diff --git a/security/keys/gc.c b/security/keys/gc.c index d3222b6d7d59..009d9370c8fd 100644 --- a/security/keys/gc.c +++ b/security/keys/gc.c @@ -157,12 +157,12 @@ static noinline void key_gc_unused_keys(struct list_head *keys) if (test_bit(KEY_FLAG_INSTANTIATED, &key->flags)) atomic_dec(&key->user->nikeys); - key_user_put(key->user); - /* now throw away the key memory */ if (key->type->destroy) key->type->destroy(key); + key_user_put(key->user); + kfree(key->description); #ifdef KEY_DEBUGGING diff --git a/security/security.c b/security/security.c index 919cad93ac82..8b774f362a3d 100644 --- a/security/security.c +++ b/security/security.c @@ -433,11 +433,20 @@ int security_path_link(struct dentry *old_dentry, struct path *new_dir, } int security_path_rename(struct path *old_dir, struct dentry *old_dentry, - struct path *new_dir, struct dentry *new_dentry) + struct path *new_dir, struct dentry *new_dentry, + unsigned int flags) { if (unlikely(IS_PRIVATE(old_dentry->d_inode) || (new_dentry->d_inode && IS_PRIVATE(new_dentry->d_inode)))) return 0; + + if (flags & RENAME_EXCHANGE) { + int err = security_ops->path_rename(new_dir, new_dentry, + old_dir, old_dentry); + if (err) + return err; + } + return security_ops->path_rename(old_dir, old_dentry, new_dir, new_dentry); } @@ -524,11 +533,20 @@ int security_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, } int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry) + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags) { if (unlikely(IS_PRIVATE(old_dentry->d_inode) || (new_dentry->d_inode && IS_PRIVATE(new_dentry->d_inode)))) return 0; + + if (flags & RENAME_EXCHANGE) { + int err = security_ops->inode_rename(new_dir, new_dentry, + old_dir, old_dentry); + if (err) + return err; + } + return security_ops->inode_rename(old_dir, old_dentry, new_dir, new_dentry); } diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index e294b86c8d88..47b5c69e4605 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -470,6 +470,7 @@ next_inode: list_entry(sbsec->isec_head.next, struct inode_security_struct, list); struct inode *inode = isec->inode; + list_del_init(&isec->list); spin_unlock(&sbsec->isec_lock); inode = igrab(inode); if (inode) { @@ -478,7 +479,6 @@ next_inode: iput(inode); } spin_lock(&sbsec->isec_lock); - list_del_init(&isec->list); goto next_inode; } spin_unlock(&sbsec->isec_lock); diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index d60c0ee66387..6c4cbd97a673 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -152,7 +152,7 @@ static ssize_t sel_write_enforce(struct file *file, const char __user *buf, goto out; /* No partial writes. */ - length = EINVAL; + length = -EINVAL; if (*ppos != 0) goto out; diff --git a/security/tomoyo/realpath.c b/security/tomoyo/realpath.c index 80a09c37cac8..bed745c8b1a3 100644 --- a/security/tomoyo/realpath.c +++ b/security/tomoyo/realpath.c @@ -173,7 +173,7 @@ static char *tomoyo_get_local_path(struct dentry *dentry, char * const buffer, * Use filesystem name if filesystem does not support rename() * operation. */ - if (inode->i_op && !inode->i_op->rename) + if (!inode->i_op->rename && !inode->i_op->rename2) goto prepend_filesystem_name; } /* Prepend device name. */ @@ -282,7 +282,8 @@ char *tomoyo_realpath_from_path(struct path *path) * Get local name for filesystems without rename() operation * or dentry without vfsmount. */ - if (!path->mnt || (inode->i_op && !inode->i_op->rename)) + if (!path->mnt || + (!inode->i_op->rename && !inode->i_op->rename2)) pos = tomoyo_get_local_path(path->dentry, buf, buf_len - 1); /* Get absolute name for the rest. */ diff --git a/sound/core/control.c b/sound/core/control.c index 98a29b26c5f4..f2082a35b890 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -1168,6 +1168,10 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file, if (info->count < 1) return -EINVAL; + if (!*info->id.name) + return -EINVAL; + if (strnlen(info->id.name, sizeof(info->id.name)) >= sizeof(info->id.name)) + return -EINVAL; access = info->access == 0 ? SNDRV_CTL_ELEM_ACCESS_READWRITE : (info->access & (SNDRV_CTL_ELEM_ACCESS_READWRITE| SNDRV_CTL_ELEM_ACCESS_INACTIVE| diff --git a/sound/core/info.c b/sound/core/info.c index e79baa11b60e..08070e1eefeb 100644 --- a/sound/core/info.c +++ b/sound/core/info.c @@ -679,7 +679,7 @@ int snd_info_card_free(struct snd_card *card) * snd_info_get_line - read one line from the procfs buffer * @buffer: the procfs buffer * @line: the buffer to store - * @len: the max. buffer size - 1 + * @len: the max. buffer size * * Reads one line from the buffer and stores the string. * @@ -699,7 +699,7 @@ int snd_info_get_line(struct snd_info_buffer *buffer, char *line, int len) buffer->stop = 1; if (c == '\n') break; - if (len) { + if (len > 1) { len--; *line++ = c; } diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c index af49721ba0e3..c4ac3c1e19af 100644 --- a/sound/core/pcm_compat.c +++ b/sound/core/pcm_compat.c @@ -206,6 +206,8 @@ static int snd_pcm_status_user_compat(struct snd_pcm_substream *substream, if (err < 0) return err; + if (clear_user(src, sizeof(*src))) + return -EFAULT; if (put_user(status.state, &src->state) || compat_put_timespec(&status.trigger_tstamp, &src->trigger_tstamp) || compat_put_timespec(&status.tstamp, &src->tstamp) || diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index a2104671f51d..e1ef106c8a6f 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -1783,14 +1783,16 @@ static int snd_pcm_lib_ioctl_fifo_size(struct snd_pcm_substream *substream, { struct snd_pcm_hw_params *params = arg; snd_pcm_format_t format; - int channels, width; + int channels; + ssize_t frame_size; params->fifo_size = substream->runtime->hw.fifo_size; if (!(substream->runtime->hw.info & SNDRV_PCM_INFO_FIFO_IN_FRAMES)) { format = params_format(params); channels = params_channels(params); - width = snd_pcm_format_physical_width(format); - params->fifo_size /= width * channels; + frame_size = snd_pcm_format_size(format, channels); + if (frame_size > 0) + params->fifo_size /= (unsigned)frame_size; } return 0; } diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 01a5e05ede95..ee2405723188 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -1404,6 +1404,8 @@ static int snd_pcm_do_drain_init(struct snd_pcm_substream *substream, int state) if (! snd_pcm_playback_empty(substream)) { snd_pcm_do_start(substream, SNDRV_PCM_STATE_DRAINING); snd_pcm_post_start(substream, SNDRV_PCM_STATE_DRAINING); + } else { + runtime->status->state = SNDRV_PCM_STATE_SETUP; } break; case SNDRV_PCM_STATE_RUNNING: @@ -3189,7 +3191,7 @@ static const struct vm_operations_struct snd_pcm_vm_ops_data_fault = { #ifndef ARCH_HAS_DMA_MMAP_COHERENT /* This should be defined / handled globally! */ -#ifdef CONFIG_ARM +#if defined(CONFIG_ARM) || defined(CONFIG_ARM64) #define ARCH_HAS_DMA_MMAP_COHERENT #endif #endif diff --git a/sound/core/seq/seq_dummy.c b/sound/core/seq/seq_dummy.c index dbc550716790..f60d81497f28 100644 --- a/sound/core/seq/seq_dummy.c +++ b/sound/core/seq/seq_dummy.c @@ -82,36 +82,6 @@ struct snd_seq_dummy_port { static int my_client = -1; /* - * unuse callback - send ALL_SOUNDS_OFF and RESET_CONTROLLERS events - * to subscribers. - * Note: this callback is called only after all subscribers are removed. - */ -static int -dummy_unuse(void *private_data, struct snd_seq_port_subscribe *info) -{ - struct snd_seq_dummy_port *p; - int i; - struct snd_seq_event ev; - - p = private_data; - memset(&ev, 0, sizeof(ev)); - if (p->duplex) - ev.source.port = p->connect; - else - ev.source.port = p->port; - ev.dest.client = SNDRV_SEQ_ADDRESS_SUBSCRIBERS; - ev.type = SNDRV_SEQ_EVENT_CONTROLLER; - for (i = 0; i < 16; i++) { - ev.data.control.channel = i; - ev.data.control.param = MIDI_CTL_ALL_SOUNDS_OFF; - snd_seq_kernel_client_dispatch(p->client, &ev, 0, 0); - ev.data.control.param = MIDI_CTL_RESET_CONTROLLERS; - snd_seq_kernel_client_dispatch(p->client, &ev, 0, 0); - } - return 0; -} - -/* * event input callback - just redirect events to subscribers */ static int @@ -175,7 +145,6 @@ create_port(int idx, int type) | SNDRV_SEQ_PORT_TYPE_PORT; memset(&pcb, 0, sizeof(pcb)); pcb.owner = THIS_MODULE; - pcb.unuse = dummy_unuse; pcb.event_input = dummy_input; pcb.private_free = dummy_free; pcb.private_data = rec; diff --git a/sound/i2c/other/ak4113.c b/sound/i2c/other/ak4113.c index e04e750a77ed..7a9149bb2a38 100644 --- a/sound/i2c/other/ak4113.c +++ b/sound/i2c/other/ak4113.c @@ -56,8 +56,7 @@ static inline unsigned char reg_read(struct ak4113 *ak4113, unsigned char reg) static void snd_ak4113_free(struct ak4113 *chip) { - chip->init = 1; /* don't schedule new work */ - mb(); + atomic_inc(&chip->wq_processing); /* don't schedule new work */ cancel_delayed_work_sync(&chip->work); kfree(chip); } @@ -89,6 +88,7 @@ int snd_ak4113_create(struct snd_card *card, ak4113_read_t *read, chip->write = write; chip->private_data = private_data; INIT_DELAYED_WORK(&chip->work, ak4113_stats); + atomic_set(&chip->wq_processing, 0); for (reg = 0; reg < AK4113_WRITABLE_REGS ; reg++) chip->regmap[reg] = pgm[reg]; @@ -139,13 +139,11 @@ static void ak4113_init_regs(struct ak4113 *chip) void snd_ak4113_reinit(struct ak4113 *chip) { - chip->init = 1; - mb(); - flush_delayed_work(&chip->work); + if (atomic_inc_return(&chip->wq_processing) == 1) + cancel_delayed_work_sync(&chip->work); ak4113_init_regs(chip); /* bring up statistics / event queing */ - chip->init = 0; - if (chip->kctls[0]) + if (atomic_dec_and_test(&chip->wq_processing)) schedule_delayed_work(&chip->work, HZ / 10); } EXPORT_SYMBOL_GPL(snd_ak4113_reinit); @@ -632,8 +630,9 @@ static void ak4113_stats(struct work_struct *work) { struct ak4113 *chip = container_of(work, struct ak4113, work.work); - if (!chip->init) + if (atomic_inc_return(&chip->wq_processing) == 1) snd_ak4113_check_rate_and_errors(chip, chip->check_flags); - schedule_delayed_work(&chip->work, HZ / 10); + if (atomic_dec_and_test(&chip->wq_processing)) + schedule_delayed_work(&chip->work, HZ / 10); } diff --git a/sound/i2c/other/ak4114.c b/sound/i2c/other/ak4114.c index 15ae0250eace..bf515db7c2e1 100644 --- a/sound/i2c/other/ak4114.c +++ b/sound/i2c/other/ak4114.c @@ -66,8 +66,7 @@ static void reg_dump(struct ak4114 *ak4114) static void snd_ak4114_free(struct ak4114 *chip) { - chip->init = 1; /* don't schedule new work */ - mb(); + atomic_inc(&chip->wq_processing); /* don't schedule new work */ cancel_delayed_work_sync(&chip->work); kfree(chip); } @@ -100,6 +99,7 @@ int snd_ak4114_create(struct snd_card *card, chip->write = write; chip->private_data = private_data; INIT_DELAYED_WORK(&chip->work, ak4114_stats); + atomic_set(&chip->wq_processing, 0); for (reg = 0; reg < 6; reg++) chip->regmap[reg] = pgm[reg]; @@ -152,13 +152,11 @@ static void ak4114_init_regs(struct ak4114 *chip) void snd_ak4114_reinit(struct ak4114 *chip) { - chip->init = 1; - mb(); - flush_delayed_work(&chip->work); + if (atomic_inc_return(&chip->wq_processing) == 1) + cancel_delayed_work_sync(&chip->work); ak4114_init_regs(chip); /* bring up statistics / event queing */ - chip->init = 0; - if (chip->kctls[0]) + if (atomic_dec_and_test(&chip->wq_processing)) schedule_delayed_work(&chip->work, HZ / 10); } @@ -612,10 +610,10 @@ static void ak4114_stats(struct work_struct *work) { struct ak4114 *chip = container_of(work, struct ak4114, work.work); - if (!chip->init) + if (atomic_inc_return(&chip->wq_processing) == 1) snd_ak4114_check_rate_and_errors(chip, chip->check_flags); - - schedule_delayed_work(&chip->work, HZ / 10); + if (atomic_dec_and_test(&chip->wq_processing)) + schedule_delayed_work(&chip->work, HZ / 10); } EXPORT_SYMBOL(snd_ak4114_create); diff --git a/sound/pci/emu10k1/emu10k1_callback.c b/sound/pci/emu10k1/emu10k1_callback.c index cae36597aa71..0a34b5f1c475 100644 --- a/sound/pci/emu10k1/emu10k1_callback.c +++ b/sound/pci/emu10k1/emu10k1_callback.c @@ -85,6 +85,8 @@ snd_emu10k1_ops_setup(struct snd_emux *emux) * get more voice for pcm * * terminate most inactive voice and give it as a pcm voice. + * + * voice_lock is already held. */ int snd_emu10k1_synth_get_voice(struct snd_emu10k1 *hw) @@ -92,12 +94,10 @@ snd_emu10k1_synth_get_voice(struct snd_emu10k1 *hw) struct snd_emux *emu; struct snd_emux_voice *vp; struct best_voice best[V_END]; - unsigned long flags; int i; emu = hw->synth; - spin_lock_irqsave(&emu->voice_lock, flags); lookup_voices(emu, hw, best, 1); /* no OFF voices */ for (i = 0; i < V_END; i++) { if (best[i].voice >= 0) { @@ -113,11 +113,9 @@ snd_emu10k1_synth_get_voice(struct snd_emu10k1 *hw) vp->emu->num_voices--; vp->ch = -1; vp->state = SNDRV_EMUX_ST_OFF; - spin_unlock_irqrestore(&emu->voice_lock, flags); return ch; } } - spin_unlock_irqrestore(&emu->voice_lock, flags); /* not found */ return -ENOMEM; diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index dafcf82139e2..f6e5c4ed03ed 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -338,8 +338,10 @@ int snd_hda_get_sub_nodes(struct hda_codec *codec, hda_nid_t nid, unsigned int parm; parm = snd_hda_param_read(codec, nid, AC_PAR_NODE_COUNT); - if (parm == -1) + if (parm == -1) { + *start_id = 0; return 0; + } *start_id = (parm >> 16) & 0x7fff; return (int)(parm & 0x7fff); } diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index d9a09bdd09db..9a23bdea97d8 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -653,12 +653,45 @@ static int get_amp_val_to_activate(struct hda_codec *codec, hda_nid_t nid, return val; } +/* is this a stereo widget or a stereo-to-mono mix? */ +static bool is_stereo_amps(struct hda_codec *codec, hda_nid_t nid, int dir) +{ + unsigned int wcaps = get_wcaps(codec, nid); + hda_nid_t conn; + + if (wcaps & AC_WCAP_STEREO) + return true; + if (dir != HDA_INPUT || get_wcaps_type(wcaps) != AC_WID_AUD_MIX) + return false; + if (snd_hda_get_num_conns(codec, nid) != 1) + return false; + if (snd_hda_get_connections(codec, nid, &conn, 1) < 0) + return false; + return !!(get_wcaps(codec, conn) & AC_WCAP_STEREO); +} + /* initialize the amp value (only at the first time) */ static void init_amp(struct hda_codec *codec, hda_nid_t nid, int dir, int idx) { unsigned int caps = query_amp_caps(codec, nid, dir); int val = get_amp_val_to_activate(codec, nid, dir, caps, false); - snd_hda_codec_amp_init_stereo(codec, nid, dir, idx, 0xff, val); + + if (is_stereo_amps(codec, nid, dir)) + snd_hda_codec_amp_init_stereo(codec, nid, dir, idx, 0xff, val); + else + snd_hda_codec_amp_init(codec, nid, 0, dir, idx, 0xff, val); +} + +/* update the amp, doing in stereo or mono depending on NID */ +static int update_amp(struct hda_codec *codec, hda_nid_t nid, int dir, int idx, + unsigned int mask, unsigned int val) +{ + if (is_stereo_amps(codec, nid, dir)) + return snd_hda_codec_amp_stereo(codec, nid, dir, idx, + mask, val); + else + return snd_hda_codec_amp_update(codec, nid, 0, dir, idx, + mask, val); } /* calculate amp value mask we can modify; @@ -698,7 +731,7 @@ static void activate_amp(struct hda_codec *codec, hda_nid_t nid, int dir, return; val &= mask; - snd_hda_codec_amp_stereo(codec, nid, dir, idx, mask, val); + update_amp(codec, nid, dir, idx, mask, val); } static void activate_amp_out(struct hda_codec *codec, struct nid_path *path, @@ -4337,13 +4370,11 @@ static void mute_all_mixer_nid(struct hda_codec *codec, hda_nid_t mix) has_amp = nid_has_mute(codec, mix, HDA_INPUT); for (i = 0; i < nums; i++) { if (has_amp) - snd_hda_codec_amp_stereo(codec, mix, - HDA_INPUT, i, - 0xff, HDA_AMP_MUTE); + update_amp(codec, mix, HDA_INPUT, i, + 0xff, HDA_AMP_MUTE); else if (nid_has_volume(codec, conn[i], HDA_OUTPUT)) - snd_hda_codec_amp_stereo(codec, conn[i], - HDA_OUTPUT, 0, - 0xff, HDA_AMP_MUTE); + update_amp(codec, conn[i], HDA_OUTPUT, 0, + 0xff, HDA_AMP_MUTE); } } diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 7ec91424ba22..84e8879cc372 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -959,7 +959,7 @@ static unsigned int azx_rirb_get_response(struct hda_bus *bus, } } - if (!bus->no_response_fallback) + if (bus->no_response_fallback) return -1; if (!chip->polling_mode && chip->poll_count < 2) { @@ -3984,7 +3984,7 @@ static DEFINE_PCI_DEVICE_TABLE(azx_ids) = { .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH_NOPM }, /* Panther Point */ { PCI_DEVICE(0x8086, 0x1e20), - .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH }, + .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH_NOPM }, /* Lynx Point */ { PCI_DEVICE(0x8086, 0x8c20), .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH }, @@ -4027,6 +4027,9 @@ static DEFINE_PCI_DEVICE_TABLE(azx_ids) = { /* BayTrail */ { PCI_DEVICE(0x8086, 0x0f04), .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH_NOPM }, + /* Braswell */ + { PCI_DEVICE(0x8086, 0x2284), + .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH }, /* ICH */ { PCI_DEVICE(0x8086, 0x2668), .driver_data = AZX_DRIVER_ICH | AZX_DCAPS_OLD_SSYNC | diff --git a/sound/pci/hda/hda_proc.c b/sound/pci/hda/hda_proc.c index ce5a6da83419..05e19f78b4cb 100644 --- a/sound/pci/hda/hda_proc.c +++ b/sound/pci/hda/hda_proc.c @@ -134,13 +134,38 @@ static void print_amp_caps(struct snd_info_buffer *buffer, (caps & AC_AMPCAP_MUTE) >> AC_AMPCAP_MUTE_SHIFT); } +/* is this a stereo widget or a stereo-to-mono mix? */ +static bool is_stereo_amps(struct hda_codec *codec, hda_nid_t nid, + int dir, unsigned int wcaps, int indices) +{ + hda_nid_t conn; + + if (wcaps & AC_WCAP_STEREO) + return true; + /* check for a stereo-to-mono mix; it must be: + * only a single connection, only for input, and only a mixer widget + */ + if (indices != 1 || dir != HDA_INPUT || + get_wcaps_type(wcaps) != AC_WID_AUD_MIX) + return false; + + if (snd_hda_get_raw_connections(codec, nid, &conn, 1) < 0) + return false; + /* the connection source is a stereo? */ + wcaps = snd_hda_param_read(codec, conn, AC_PAR_AUDIO_WIDGET_CAP); + return !!(wcaps & AC_WCAP_STEREO); +} + static void print_amp_vals(struct snd_info_buffer *buffer, struct hda_codec *codec, hda_nid_t nid, - int dir, int stereo, int indices) + int dir, unsigned int wcaps, int indices) { unsigned int val; + bool stereo; int i; + stereo = is_stereo_amps(codec, nid, dir, wcaps, indices); + dir = dir == HDA_OUTPUT ? AC_AMP_GET_OUTPUT : AC_AMP_GET_INPUT; for (i = 0; i < indices; i++) { snd_iprintf(buffer, " ["); @@ -757,12 +782,10 @@ static void print_codec_info(struct snd_info_entry *entry, (codec->single_adc_amp && wid_type == AC_WID_AUD_IN)) print_amp_vals(buffer, codec, nid, HDA_INPUT, - wid_caps & AC_WCAP_STEREO, - 1); + wid_caps, 1); else print_amp_vals(buffer, codec, nid, HDA_INPUT, - wid_caps & AC_WCAP_STEREO, - conn_len); + wid_caps, conn_len); } if (wid_caps & AC_WCAP_OUT_AMP) { snd_iprintf(buffer, " Amp-Out caps: "); @@ -771,11 +794,10 @@ static void print_codec_info(struct snd_info_entry *entry, if (wid_type == AC_WID_PIN && codec->pin_amp_workaround) print_amp_vals(buffer, codec, nid, HDA_OUTPUT, - wid_caps & AC_WCAP_STEREO, - conn_len); + wid_caps, conn_len); else print_amp_vals(buffer, codec, nid, HDA_OUTPUT, - wid_caps & AC_WCAP_STEREO, 1); + wid_caps, 1); } switch (wid_type) { diff --git a/sound/pci/hda/patch_analog.c b/sound/pci/hda/patch_analog.c index eaf64ea2e1c1..1a05efa08d96 100644 --- a/sound/pci/hda/patch_analog.c +++ b/sound/pci/hda/patch_analog.c @@ -333,6 +333,7 @@ static const struct hda_fixup ad1986a_fixups[] = { static const struct snd_pci_quirk ad1986a_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x30af, "HP B2800", AD1986A_FIXUP_LAPTOP_IMIC), + SND_PCI_QUIRK(0x1043, 0x1443, "ASUS Z99He", AD1986A_FIXUP_EAPD), SND_PCI_QUIRK(0x1043, 0x1447, "ASUS A8JN", AD1986A_FIXUP_EAPD), SND_PCI_QUIRK_MASK(0x1043, 0xff00, 0x8100, "ASUS P5", AD1986A_FIXUP_3STACK), SND_PCI_QUIRK_MASK(0x1043, 0xff00, 0x8200, "ASUS M2", AD1986A_FIXUP_3STACK), diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c index fc492ac24caa..51e208022cc8 100644 --- a/sound/pci/hda/patch_cirrus.c +++ b/sound/pci/hda/patch_cirrus.c @@ -396,6 +396,7 @@ static const struct snd_pci_quirk cs420x_fixup_tbl[] = { SND_PCI_QUIRK(0x106b, 0x1c00, "MacBookPro 8,1", CS420X_MBP81), SND_PCI_QUIRK(0x106b, 0x2000, "iMac 12,2", CS420X_IMAC27_122), SND_PCI_QUIRK(0x106b, 0x2800, "MacBookPro 10,1", CS420X_MBP101), + SND_PCI_QUIRK(0x106b, 0x5600, "MacBookAir 5,2", CS420X_MBP81), SND_PCI_QUIRK(0x106b, 0x5b00, "MacBookAir 4,2", CS420X_MBA42), SND_PCI_QUIRK_VENDOR(0x106b, "Apple", CS420X_APPLE), {} /* terminator */ @@ -587,6 +588,7 @@ static int patch_cs420x(struct hda_codec *codec) return -ENOMEM; spec->gen.automute_hook = cs_automute; + codec->single_adc_amp = 1; snd_hda_pick_fixup(codec, cs420x_models, cs420x_fixup_tbl, cs420x_fixups); diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index bcf91bea3317..976493c4a695 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -3232,11 +3232,13 @@ enum { CXT_PINCFG_LENOVO_TP410, CXT_PINCFG_LEMOTE_A1004, CXT_PINCFG_LEMOTE_A1205, + CXT_PINCFG_COMPAQ_CQ60, CXT_FIXUP_STEREO_DMIC, CXT_FIXUP_INC_MIC_BOOST, CXT_FIXUP_HEADPHONE_MIC_PIN, CXT_FIXUP_HEADPHONE_MIC, CXT_FIXUP_GPIO1, + CXT_FIXUP_ASPIRE_DMIC, CXT_FIXUP_THINKPAD_ACPI, }; @@ -3367,6 +3369,15 @@ static const struct hda_fixup cxt_fixups[] = { .type = HDA_FIXUP_PINS, .v.pins = cxt_pincfg_lemote, }, + [CXT_PINCFG_COMPAQ_CQ60] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + /* 0x17 was falsely set up as a mic, it should 0x1d */ + { 0x17, 0x400001f0 }, + { 0x1d, 0x97a70120 }, + { } + } + }, [CXT_FIXUP_STEREO_DMIC] = { .type = HDA_FIXUP_FUNC, .v.func = cxt_fixup_stereo_dmic, @@ -3397,6 +3408,12 @@ static const struct hda_fixup cxt_fixups[] = { { } }, }, + [CXT_FIXUP_ASPIRE_DMIC] = { + .type = HDA_FIXUP_FUNC, + .v.func = cxt_fixup_stereo_dmic, + .chained = true, + .chain_id = CXT_FIXUP_GPIO1, + }, [CXT_FIXUP_THINKPAD_ACPI] = { .type = HDA_FIXUP_FUNC, .v.func = hda_fixup_thinkpad_acpi, @@ -3404,13 +3421,14 @@ static const struct hda_fixup cxt_fixups[] = { }; static const struct snd_pci_quirk cxt5051_fixups[] = { + SND_PCI_QUIRK(0x103c, 0x360b, "Compaq CQ60", CXT_PINCFG_COMPAQ_CQ60), SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo X200", CXT_PINCFG_LENOVO_X200), {} }; static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x1025, 0x0543, "Acer Aspire One 522", CXT_FIXUP_STEREO_DMIC), - SND_PCI_QUIRK(0x1025, 0x054c, "Acer Aspire 3830TG", CXT_FIXUP_GPIO1), + SND_PCI_QUIRK(0x1025, 0x054c, "Acer Aspire 3830TG", CXT_FIXUP_ASPIRE_DMIC), SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400", CXT_PINCFG_LENOVO_TP410), SND_PCI_QUIRK(0x17aa, 0x215e, "Lenovo T410", CXT_PINCFG_LENOVO_TP410), diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index d135c906caff..611110a3f1a4 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1557,19 +1557,22 @@ static bool hdmi_present_sense(struct hdmi_spec_per_pin *per_pin, int repoll) } } - if (pin_eld->eld_valid && !eld->eld_valid) { - update_eld = true; + if (pin_eld->eld_valid != eld->eld_valid) eld_changed = true; - } + + if (pin_eld->eld_valid && !eld->eld_valid) + update_eld = true; + if (update_eld) { bool old_eld_valid = pin_eld->eld_valid; pin_eld->eld_valid = eld->eld_valid; - eld_changed = pin_eld->eld_size != eld->eld_size || + if (pin_eld->eld_size != eld->eld_size || memcmp(pin_eld->eld_buffer, eld->eld_buffer, - eld->eld_size) != 0; - if (eld_changed) + eld->eld_size) != 0) { memcpy(pin_eld->eld_buffer, eld->eld_buffer, eld->eld_size); + eld_changed = true; + } pin_eld->eld_size = eld->eld_size; pin_eld->info = eld->info; @@ -3314,6 +3317,7 @@ static const struct hda_codec_preset snd_hda_preset_hdmi[] = { { .id = 0x80862808, .name = "Broadwell HDMI", .patch = patch_generic_hdmi }, { .id = 0x80862880, .name = "CedarTrail HDMI", .patch = patch_generic_hdmi }, { .id = 0x80862882, .name = "Valleyview2 HDMI", .patch = patch_generic_hdmi }, +{ .id = 0x80862883, .name = "Braswell HDMI", .patch = patch_generic_hdmi }, { .id = 0x808629fb, .name = "Crestline HDMI", .patch = patch_generic_hdmi }, {} /* terminator */ }; @@ -3370,6 +3374,7 @@ MODULE_ALIAS("snd-hda-codec-id:80862807"); MODULE_ALIAS("snd-hda-codec-id:80862808"); MODULE_ALIAS("snd-hda-codec-id:80862880"); MODULE_ALIAS("snd-hda-codec-id:80862882"); +MODULE_ALIAS("snd-hda-codec-id:80862883"); MODULE_ALIAS("snd-hda-codec-id:808629fb"); MODULE_LICENSE("GPL"); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index b35dbe25a6e3..ca26373ebe70 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -271,7 +271,7 @@ static void alc_auto_setup_eapd(struct hda_codec *codec, bool on) { /* We currently only handle front, HP */ static hda_nid_t pins[] = { - 0x0f, 0x10, 0x14, 0x15, 0 + 0x0f, 0x10, 0x14, 0x15, 0x17, 0 }; hda_nid_t *p; for (p = pins; *p; p++) @@ -327,6 +327,7 @@ static void alc_auto_init_amp(struct hda_codec *codec, int type) case 0x10ec0885: case 0x10ec0887: /*case 0x10ec0889:*/ /* this causes an SPDIF problem */ + case 0x10ec0900: alc889_coef_init(codec); break; case 0x10ec0888: @@ -2330,6 +2331,7 @@ static int patch_alc882(struct hda_codec *codec) switch (codec->vendor_id) { case 0x10ec0882: case 0x10ec0885: + case 0x10ec0900: break; default: /* ALC883 and variants */ @@ -2883,6 +2885,8 @@ static void alc283_init(struct hda_codec *codec) if (!hp_pin) return; + + msleep(30); hp_pin_sense = snd_hda_jack_detect(codec, hp_pin); /* Index 0x43 Direct Drive HP AMP LPM Control 1 */ @@ -2924,6 +2928,9 @@ static void alc283_shutup(struct hda_codec *codec) alc_write_coef_idx(codec, 0x43, 0x9004); + /*depop hp during suspend*/ + alc_write_coef_idx(codec, 0x06, 0x2100); + snd_hda_codec_write(codec, hp_pin, 0, AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE); @@ -3946,6 +3953,7 @@ enum { ALC269_FIXUP_QUANTA_MUTE, ALC269_FIXUP_LIFEBOOK, ALC269_FIXUP_LIFEBOOK_EXTMIC, + ALC269_FIXUP_LIFEBOOK_HP_PIN, ALC269_FIXUP_AMIC, ALC269_FIXUP_DMIC, ALC269VB_FIXUP_AMIC, @@ -4080,6 +4088,13 @@ static const struct hda_fixup alc269_fixups[] = { { } }, }, + [ALC269_FIXUP_LIFEBOOK_HP_PIN] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x21, 0x0221102f }, /* HP out */ + { } + }, + }, [ALC269_FIXUP_AMIC] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -4533,6 +4548,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x104d, 0x9084, "Sony VAIO", ALC275_FIXUP_SONY_HWEQ), SND_PCI_QUIRK_VENDOR(0x104d, "Sony VAIO", ALC269_FIXUP_SONY_VAIO), SND_PCI_QUIRK(0x10cf, 0x1475, "Lifebook", ALC269_FIXUP_LIFEBOOK), + SND_PCI_QUIRK(0x10cf, 0x15dc, "Lifebook T731", ALC269_FIXUP_LIFEBOOK_HP_PIN), SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC), SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE), @@ -4549,6 +4565,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x2212, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x2214, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x2215, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x17aa, 0x5013, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x501a, "Thinkpad", ALC283_FIXUP_INT_MIC), diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c index 978df990f27c..231b26471a63 100644 --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -85,6 +85,7 @@ enum { STAC_ALIENWARE_M17X, STAC_92HD89XX_HP_FRONT_JACK, STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK, + STAC_92HD73XX_ASUS_MOBO, STAC_92HD73XX_MODELS }; @@ -559,8 +560,8 @@ static void stac_init_power_map(struct hda_codec *codec) if (snd_hda_jack_tbl_get(codec, nid)) continue; if (def_conf == AC_JACK_PORT_COMPLEX && - !(spec->vref_mute_led_nid == nid || - is_jack_detectable(codec, nid))) { + spec->vref_mute_led_nid != nid && + is_jack_detectable(codec, nid)) { snd_hda_jack_detect_enable_callback(codec, nid, STAC_PWR_EVENT, jack_update_power); @@ -593,9 +594,9 @@ static void stac_store_hints(struct hda_codec *codec) spec->gpio_mask; } if (get_int_hint(codec, "gpio_dir", &spec->gpio_dir)) - spec->gpio_mask &= spec->gpio_mask; - if (get_int_hint(codec, "gpio_data", &spec->gpio_data)) spec->gpio_dir &= spec->gpio_mask; + if (get_int_hint(codec, "gpio_data", &spec->gpio_data)) + spec->gpio_data &= spec->gpio_mask; if (get_int_hint(codec, "eapd_mask", &spec->eapd_mask)) spec->eapd_mask &= spec->gpio_mask; if (get_int_hint(codec, "gpio_mute", &spec->gpio_mute)) @@ -1935,7 +1936,18 @@ static const struct hda_fixup stac92hd73xx_fixups[] = { [STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK] = { .type = HDA_FIXUP_PINS, .v.pins = stac92hd89xx_hp_z1_g2_right_mic_jack_pin_configs, - } + }, + [STAC_92HD73XX_ASUS_MOBO] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + /* enable 5.1 and SPDIF out */ + { 0x0c, 0x01014411 }, + { 0x0d, 0x01014410 }, + { 0x0e, 0x01014412 }, + { 0x22, 0x014b1180 }, + { } + } + }, }; static const struct hda_model_fixup stac92hd73xx_models[] = { @@ -1947,6 +1959,7 @@ static const struct hda_model_fixup stac92hd73xx_models[] = { { .id = STAC_DELL_M6_BOTH, .name = "dell-m6" }, { .id = STAC_DELL_EQ, .name = "dell-eq" }, { .id = STAC_ALIENWARE_M17X, .name = "alienware" }, + { .id = STAC_92HD73XX_ASUS_MOBO, .name = "asus-mobo" }, {} }; @@ -1999,6 +2012,8 @@ static const struct snd_pci_quirk stac92hd73xx_fixup_tbl[] = { "HP Z1 G2", STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK), SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x2b17, "unknown HP", STAC_92HD89XX_HP_FRONT_JACK), + SND_PCI_QUIRK(PCI_VENDOR_ID_ASUSTEK, 0x83f8, "ASUS AT4NM10", + STAC_92HD73XX_ASUS_MOBO), {} /* terminator */ }; @@ -4212,11 +4227,18 @@ static int stac_parse_auto_config(struct hda_codec *codec) return err; } - stac_init_power_map(codec); - return 0; } +static int stac_build_controls(struct hda_codec *codec) +{ + int err = snd_hda_gen_build_controls(codec); + + if (err < 0) + return err; + stac_init_power_map(codec); + return 0; +} static int stac_init(struct hda_codec *codec) { @@ -4328,7 +4350,7 @@ static int stac_suspend(struct hda_codec *codec) #endif /* CONFIG_PM */ static const struct hda_codec_ops stac_patch_ops = { - .build_controls = snd_hda_gen_build_controls, + .build_controls = stac_build_controls, .build_pcms = snd_hda_gen_build_pcms, .init = stac_init, .free = stac_free, diff --git a/sound/pci/riptide/riptide.c b/sound/pci/riptide/riptide.c index 56cc891e395e..d99c8d341e50 100644 --- a/sound/pci/riptide/riptide.c +++ b/sound/pci/riptide/riptide.c @@ -2032,32 +2032,43 @@ snd_riptide_joystick_probe(struct pci_dev *pci, const struct pci_device_id *id) { static int dev; struct gameport *gameport; + int ret; if (dev >= SNDRV_CARDS) return -ENODEV; + if (!enable[dev]) { - dev++; - return -ENOENT; + ret = -ENOENT; + goto inc_dev; } - if (!joystick_port[dev++]) - return 0; + if (!joystick_port[dev]) { + ret = 0; + goto inc_dev; + } gameport = gameport_allocate_port(); - if (!gameport) - return -ENOMEM; + if (!gameport) { + ret = -ENOMEM; + goto inc_dev; + } if (!request_region(joystick_port[dev], 8, "Riptide gameport")) { snd_printk(KERN_WARNING "Riptide: cannot grab gameport 0x%x\n", joystick_port[dev]); gameport_free_port(gameport); - return -EBUSY; + ret = -EBUSY; + goto inc_dev; } gameport->io = joystick_port[dev]; gameport_register_port(gameport); pci_set_drvdata(pci, gameport); - return 0; + + ret = 0; +inc_dev: + dev++; + return ret; } static void snd_riptide_joystick_remove(struct pci_dev *pci) diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c index e98dc008de0b..21167503a3f9 100644 --- a/sound/pci/rme9652/hdspm.c +++ b/sound/pci/rme9652/hdspm.c @@ -6102,6 +6102,9 @@ static int snd_hdspm_playback_open(struct snd_pcm_substream *substream) snd_pcm_hw_constraint_minmax(runtime, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, 64, 8192); + snd_pcm_hw_constraint_minmax(runtime, + SNDRV_PCM_HW_PARAM_PERIODS, + 2, 2); break; } @@ -6176,6 +6179,9 @@ static int snd_hdspm_capture_open(struct snd_pcm_substream *substream) snd_pcm_hw_constraint_minmax(runtime, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, 64, 8192); + snd_pcm_hw_constraint_minmax(runtime, + SNDRV_PCM_HW_PARAM_PERIODS, + 2, 2); break; } diff --git a/sound/soc/atmel/atmel_ssc_dai.c b/sound/soc/atmel/atmel_ssc_dai.c index 1ead3c977a51..f20e703b2a35 100644 --- a/sound/soc/atmel/atmel_ssc_dai.c +++ b/sound/soc/atmel/atmel_ssc_dai.c @@ -344,7 +344,6 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream, struct atmel_pcm_dma_params *dma_params; int dir, channels, bits; u32 tfmr, rfmr, tcmr, rcmr; - int start_event; int ret; /* @@ -451,19 +450,10 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream, * The SSC transmit clock is obtained from the BCLK signal on * on the TK line, and the SSC receive clock is * generated from the transmit clock. - * - * For single channel data, one sample is transferred - * on the falling edge of the LRC clock. - * For two channel data, one sample is - * transferred on both edges of the LRC clock. */ - start_event = ((channels == 1) - ? SSC_START_FALLING_RF - : SSC_START_EDGE_RF); - rcmr = SSC_BF(RCMR_PERIOD, 0) | SSC_BF(RCMR_STTDLY, START_DELAY) - | SSC_BF(RCMR_START, start_event) + | SSC_BF(RCMR_START, SSC_START_FALLING_RF) | SSC_BF(RCMR_CKI, SSC_CKI_RISING) | SSC_BF(RCMR_CKO, SSC_CKO_NONE) | SSC_BF(RCMR_CKS, SSC_CKS_CLOCK); @@ -471,14 +461,14 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream, rfmr = SSC_BF(RFMR_FSEDGE, SSC_FSEDGE_POSITIVE) | SSC_BF(RFMR_FSOS, SSC_FSOS_NONE) | SSC_BF(RFMR_FSLEN, 0) - | SSC_BF(RFMR_DATNB, 0) + | SSC_BF(RFMR_DATNB, (channels - 1)) | SSC_BIT(RFMR_MSBF) | SSC_BF(RFMR_LOOP, 0) | SSC_BF(RFMR_DATLEN, (bits - 1)); tcmr = SSC_BF(TCMR_PERIOD, 0) | SSC_BF(TCMR_STTDLY, START_DELAY) - | SSC_BF(TCMR_START, start_event) + | SSC_BF(TCMR_START, SSC_START_FALLING_RF) | SSC_BF(TCMR_CKI, SSC_CKI_FALLING) | SSC_BF(TCMR_CKO, SSC_CKO_NONE) | SSC_BF(TCMR_CKS, SSC_CKS_PIN); @@ -487,7 +477,7 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream, | SSC_BF(TFMR_FSDEN, 0) | SSC_BF(TFMR_FSOS, SSC_FSOS_NONE) | SSC_BF(TFMR_FSLEN, 0) - | SSC_BF(TFMR_DATNB, 0) + | SSC_BF(TFMR_DATNB, (channels - 1)) | SSC_BIT(TFMR_MSBF) | SSC_BF(TFMR_DATDEF, 0) | SSC_BF(TFMR_DATLEN, (bits - 1)); diff --git a/sound/soc/codecs/adav80x.c b/sound/soc/codecs/adav80x.c index f78b27a7c461..23454e9a5d3a 100644 --- a/sound/soc/codecs/adav80x.c +++ b/sound/soc/codecs/adav80x.c @@ -319,7 +319,7 @@ static int adav80x_put_deemph(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct adav80x *adav80x = snd_soc_codec_get_drvdata(codec); - unsigned int deemph = ucontrol->value.enumerated.item[0]; + unsigned int deemph = ucontrol->value.integer.value[0]; if (deemph > 1) return -EINVAL; @@ -335,7 +335,7 @@ static int adav80x_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct adav80x *adav80x = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = adav80x->deemph; + ucontrol->value.integer.value[0] = adav80x->deemph; return 0; }; diff --git a/sound/soc/codecs/ak4641.c b/sound/soc/codecs/ak4641.c index 94cbe508dd37..d7184726f8a0 100644 --- a/sound/soc/codecs/ak4641.c +++ b/sound/soc/codecs/ak4641.c @@ -76,7 +76,7 @@ static int ak4641_put_deemph(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct ak4641_priv *ak4641 = snd_soc_codec_get_drvdata(codec); - int deemph = ucontrol->value.enumerated.item[0]; + int deemph = ucontrol->value.integer.value[0]; if (deemph > 1) return -EINVAL; @@ -92,7 +92,7 @@ static int ak4641_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct ak4641_priv *ak4641 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = ak4641->deemph; + ucontrol->value.integer.value[0] = ak4641->deemph; return 0; }; diff --git a/sound/soc/codecs/cs4271.c b/sound/soc/codecs/cs4271.c index ce05fd93dc74..a0ad41ac5574 100644 --- a/sound/soc/codecs/cs4271.c +++ b/sound/soc/codecs/cs4271.c @@ -288,7 +288,7 @@ static int cs4271_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct cs4271_private *cs4271 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = cs4271->deemph; + ucontrol->value.integer.value[0] = cs4271->deemph; return 0; } @@ -298,7 +298,7 @@ static int cs4271_put_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct cs4271_private *cs4271 = snd_soc_codec_get_drvdata(codec); - cs4271->deemph = ucontrol->value.enumerated.item[0]; + cs4271->deemph = ucontrol->value.integer.value[0]; return cs4271_set_deemph(codec); } diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c index ddfb0fddd030..9dd260f9dd06 100644 --- a/sound/soc/codecs/max98090.c +++ b/sound/soc/codecs/max98090.c @@ -1378,8 +1378,8 @@ static const struct snd_soc_dapm_route max98090_dapm_routes[] = { {"STENL Mux", "Sidetone Left", "DMICL"}, {"STENR Mux", "Sidetone Right", "ADCR"}, {"STENR Mux", "Sidetone Right", "DMICR"}, - {"DACL", "NULL", "STENL Mux"}, - {"DACR", "NULL", "STENL Mux"}, + {"DACL", NULL, "STENL Mux"}, + {"DACR", NULL, "STENL Mux"}, {"AIFINL", NULL, "SHDN"}, {"AIFINR", NULL, "SHDN"}, diff --git a/sound/soc/codecs/pcm1681.c b/sound/soc/codecs/pcm1681.c index 73f9c3630e2c..651e2fe2c31f 100644 --- a/sound/soc/codecs/pcm1681.c +++ b/sound/soc/codecs/pcm1681.c @@ -118,7 +118,7 @@ static int pcm1681_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct pcm1681_private *priv = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = priv->deemph; + ucontrol->value.integer.value[0] = priv->deemph; return 0; } @@ -129,7 +129,7 @@ static int pcm1681_put_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct pcm1681_private *priv = snd_soc_codec_get_drvdata(codec); - priv->deemph = ucontrol->value.enumerated.item[0]; + priv->deemph = ucontrol->value.integer.value[0]; return pcm1681_set_deemph(codec); } diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c index 0fcbe90f3ef2..e93c36fd3073 100644 --- a/sound/soc/codecs/sgtl5000.c +++ b/sound/soc/codecs/sgtl5000.c @@ -1198,13 +1198,7 @@ static int sgtl5000_set_power_regs(struct snd_soc_codec *codec) /* Enable VDDC charge pump */ ana_pwr |= SGTL5000_VDDC_CHRGPMP_POWERUP; } else if (vddio >= 3100 && vdda >= 3100) { - /* - * if vddio and vddd > 3.1v, - * charge pump should be clean before set ana_pwr - */ - snd_soc_update_bits(codec, SGTL5000_CHIP_ANA_POWER, - SGTL5000_VDDC_CHRGPMP_POWERUP, 0); - + ana_pwr &= ~SGTL5000_VDDC_CHRGPMP_POWERUP; /* VDDC use VDDIO rail */ lreg_ctrl |= SGTL5000_VDDC_ASSN_OVRD; lreg_ctrl |= SGTL5000_VDDC_MAN_ASSN_VDDIO << @@ -1369,8 +1363,7 @@ static int sgtl5000_probe(struct snd_soc_codec *codec) /* enable small pop, introduce 400ms delay in turning off */ snd_soc_update_bits(codec, SGTL5000_CHIP_REF_CTRL, - SGTL5000_SMALL_POP, - SGTL5000_SMALL_POP); + SGTL5000_SMALL_POP, 1); /* disable short cut detector */ snd_soc_write(codec, SGTL5000_CHIP_SHORT_CTRL, 0); @@ -1522,6 +1515,9 @@ static int sgtl5000_i2c_probe(struct i2c_client *client, if (ret) return ret; + /* Need 8 clocks before I2C accesses */ + udelay(1); + /* read chip information */ ret = regmap_read(sgtl5000->regmap, SGTL5000_CHIP_ID, ®); if (ret) diff --git a/sound/soc/codecs/sgtl5000.h b/sound/soc/codecs/sgtl5000.h index 2f8c88931f69..bd7a344bf8c5 100644 --- a/sound/soc/codecs/sgtl5000.h +++ b/sound/soc/codecs/sgtl5000.h @@ -275,7 +275,7 @@ #define SGTL5000_BIAS_CTRL_MASK 0x000e #define SGTL5000_BIAS_CTRL_SHIFT 1 #define SGTL5000_BIAS_CTRL_WIDTH 3 -#define SGTL5000_SMALL_POP 0x0001 +#define SGTL5000_SMALL_POP 0 /* * SGTL5000_CHIP_MIC_CTRL diff --git a/sound/soc/codecs/sigmadsp.c b/sound/soc/codecs/sigmadsp.c index 4068f2491232..bb3878c9625f 100644 --- a/sound/soc/codecs/sigmadsp.c +++ b/sound/soc/codecs/sigmadsp.c @@ -176,6 +176,13 @@ static int _process_sigma_firmware(struct device *dev, goto done; } + if (ssfw_head->version != 1) { + dev_err(dev, + "Failed to load firmware: Invalid version %d. Supported firmware versions: 1\n", + ssfw_head->version); + goto done; + } + crc = crc32(0, fw->data + sizeof(*ssfw_head), fw->size - sizeof(*ssfw_head)); pr_debug("%s: crc=%x\n", __func__, crc); diff --git a/sound/soc/codecs/tas5086.c b/sound/soc/codecs/tas5086.c index a895a5e4bdf2..c6c65001457d 100644 --- a/sound/soc/codecs/tas5086.c +++ b/sound/soc/codecs/tas5086.c @@ -275,7 +275,7 @@ static int tas5086_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct tas5086_private *priv = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = priv->deemph; + ucontrol->value.integer.value[0] = priv->deemph; return 0; } @@ -286,7 +286,7 @@ static int tas5086_put_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct tas5086_private *priv = snd_soc_codec_get_drvdata(codec); - priv->deemph = ucontrol->value.enumerated.item[0]; + priv->deemph = ucontrol->value.integer.value[0]; return tas5086_set_deemph(codec); } diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c index eb241c6571a9..fd53d37e1181 100644 --- a/sound/soc/codecs/tlv320aic3x.c +++ b/sound/soc/codecs/tlv320aic3x.c @@ -1121,6 +1121,7 @@ static int aic3x_regulator_event(struct notifier_block *nb, static int aic3x_set_power(struct snd_soc_codec *codec, int power) { struct aic3x_priv *aic3x = snd_soc_codec_get_drvdata(codec); + unsigned int pll_c, pll_d; int ret; if (power) { @@ -1138,6 +1139,18 @@ static int aic3x_set_power(struct snd_soc_codec *codec, int power) /* Sync reg_cache with the hardware */ regcache_cache_only(aic3x->regmap, false); regcache_sync(aic3x->regmap); + + /* Rewrite paired PLL D registers in case cached sync skipped + * writing one of them and thus caused other one also not + * being written + */ + pll_c = snd_soc_read(codec, AIC3X_PLL_PROGC_REG); + pll_d = snd_soc_read(codec, AIC3X_PLL_PROGD_REG); + if (pll_c == aic3x_reg[AIC3X_PLL_PROGC_REG].def || + pll_d == aic3x_reg[AIC3X_PLL_PROGD_REG].def) { + snd_soc_write(codec, AIC3X_PLL_PROGC_REG, pll_c); + snd_soc_write(codec, AIC3X_PLL_PROGD_REG, pll_d); + } } else { /* * Do soft reset to this codec instance in order to clear diff --git a/sound/soc/codecs/wm2000.c b/sound/soc/codecs/wm2000.c index 8ae50274ea8f..1a9f4574b65b 100644 --- a/sound/soc/codecs/wm2000.c +++ b/sound/soc/codecs/wm2000.c @@ -610,7 +610,7 @@ static int wm2000_anc_mode_get(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev); - ucontrol->value.enumerated.item[0] = wm2000->anc_active; + ucontrol->value.integer.value[0] = wm2000->anc_active; return 0; } @@ -620,7 +620,7 @@ static int wm2000_anc_mode_put(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev); - int anc_active = ucontrol->value.enumerated.item[0]; + int anc_active = ucontrol->value.integer.value[0]; int ret; if (anc_active > 1) @@ -643,7 +643,7 @@ static int wm2000_speaker_get(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev); - ucontrol->value.enumerated.item[0] = wm2000->spk_ena; + ucontrol->value.integer.value[0] = wm2000->spk_ena; return 0; } @@ -653,7 +653,7 @@ static int wm2000_speaker_put(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev); - int val = ucontrol->value.enumerated.item[0]; + int val = ucontrol->value.integer.value[0]; int ret; if (val > 1) diff --git a/sound/soc/codecs/wm8731.c b/sound/soc/codecs/wm8731.c index 029720366ff8..e593722574de 100644 --- a/sound/soc/codecs/wm8731.c +++ b/sound/soc/codecs/wm8731.c @@ -122,7 +122,7 @@ static int wm8731_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm8731_priv *wm8731 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = wm8731->deemph; + ucontrol->value.integer.value[0] = wm8731->deemph; return 0; } @@ -132,7 +132,7 @@ static int wm8731_put_deemph(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm8731_priv *wm8731 = snd_soc_codec_get_drvdata(codec); - int deemph = ucontrol->value.enumerated.item[0]; + int deemph = ucontrol->value.integer.value[0]; int ret = 0; if (deemph > 1) diff --git a/sound/soc/codecs/wm8903.c b/sound/soc/codecs/wm8903.c index eebcb1da3b7b..ae7d76efe063 100644 --- a/sound/soc/codecs/wm8903.c +++ b/sound/soc/codecs/wm8903.c @@ -442,7 +442,7 @@ static int wm8903_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm8903_priv *wm8903 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = wm8903->deemph; + ucontrol->value.integer.value[0] = wm8903->deemph; return 0; } @@ -452,7 +452,7 @@ static int wm8903_put_deemph(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm8903_priv *wm8903 = snd_soc_codec_get_drvdata(codec); - int deemph = ucontrol->value.enumerated.item[0]; + int deemph = ucontrol->value.integer.value[0]; int ret = 0; if (deemph > 1) diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c index 53bbfac6a83a..66cb9e95b5eb 100644 --- a/sound/soc/codecs/wm8904.c +++ b/sound/soc/codecs/wm8904.c @@ -523,7 +523,7 @@ static int wm8904_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm8904_priv *wm8904 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = wm8904->deemph; + ucontrol->value.integer.value[0] = wm8904->deemph; return 0; } @@ -532,7 +532,7 @@ static int wm8904_put_deemph(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm8904_priv *wm8904 = snd_soc_codec_get_drvdata(codec); - int deemph = ucontrol->value.enumerated.item[0]; + int deemph = ucontrol->value.integer.value[0]; if (deemph > 1) return -EINVAL; diff --git a/sound/soc/codecs/wm8955.c b/sound/soc/codecs/wm8955.c index 82c8ba975720..1c1fc6119758 100644 --- a/sound/soc/codecs/wm8955.c +++ b/sound/soc/codecs/wm8955.c @@ -393,7 +393,7 @@ static int wm8955_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm8955_priv *wm8955 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = wm8955->deemph; + ucontrol->value.integer.value[0] = wm8955->deemph; return 0; } @@ -402,7 +402,7 @@ static int wm8955_put_deemph(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm8955_priv *wm8955 = snd_soc_codec_get_drvdata(codec); - int deemph = ucontrol->value.enumerated.item[0]; + int deemph = ucontrol->value.integer.value[0]; if (deemph > 1) return -EINVAL; diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c index f156010e52bc..2a0bfb848512 100644 --- a/sound/soc/codecs/wm8960.c +++ b/sound/soc/codecs/wm8960.c @@ -181,7 +181,7 @@ static int wm8960_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm8960_priv *wm8960 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = wm8960->deemph; + ucontrol->value.integer.value[0] = wm8960->deemph; return 0; } @@ -190,7 +190,7 @@ static int wm8960_put_deemph(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol); struct wm8960_priv *wm8960 = snd_soc_codec_get_drvdata(codec); - int deemph = ucontrol->value.enumerated.item[0]; + int deemph = ucontrol->value.integer.value[0]; if (deemph > 1) return -EINVAL; @@ -555,7 +555,7 @@ static struct { { 22050, 2 }, { 24000, 2 }, { 16000, 3 }, - { 11250, 4 }, + { 11025, 4 }, { 12000, 4 }, { 8000, 5 }, }; diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 53c03aff762e..0502e3f17412 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -1341,6 +1341,7 @@ static int wm_adsp_load_coeff(struct wm_adsp *dsp) file, blocks, pos - firmware->size); out_fw: + regmap_async_complete(regmap); release_firmware(firmware); wm_adsp_buf_free(&buf_list); out: diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c index 670afa29e30d..7350ebbae642 100644 --- a/sound/soc/davinci/davinci-mcasp.c +++ b/sound/soc/davinci/davinci-mcasp.c @@ -418,8 +418,17 @@ static int davinci_config_channel_size(struct davinci_mcasp *mcasp, { u32 fmt; u32 tx_rotate = (word_length / 4) & 0x7; - u32 rx_rotate = (32 - word_length) / 4; u32 mask = (1ULL << word_length) - 1; + /* + * For captured data we should not rotate, inversion and masking is + * enoguh to get the data to the right position: + * Format data from bus after reverse (XRBUF) + * S16_LE: |LSB|MSB|xxx|xxx| |xxx|xxx|MSB|LSB| + * S24_3LE: |LSB|DAT|MSB|xxx| |xxx|MSB|DAT|LSB| + * S24_LE: |LSB|DAT|MSB|xxx| |xxx|MSB|DAT|LSB| + * S32_LE: |LSB|DAT|DAT|MSB| |MSB|DAT|DAT|LSB| + */ + u32 rx_rotate = 0; /* * if s BCLK-to-LRCLK ratio has been configured via the set_clkdiv() diff --git a/sound/soc/dwc/designware_i2s.c b/sound/soc/dwc/designware_i2s.c index 25c31f1655f6..2f6357578616 100644 --- a/sound/soc/dwc/designware_i2s.c +++ b/sound/soc/dwc/designware_i2s.c @@ -263,6 +263,19 @@ static void dw_i2s_shutdown(struct snd_pcm_substream *substream, snd_soc_dai_set_dma_data(dai, substream, NULL); } +static int dw_i2s_prepare(struct snd_pcm_substream *substream, + struct snd_soc_dai *dai) +{ + struct dw_i2s_dev *dev = snd_soc_dai_get_drvdata(dai); + + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) + i2s_write_reg(dev->i2s_base, TXFFR, 1); + else + i2s_write_reg(dev->i2s_base, RXFFR, 1); + + return 0; +} + static int dw_i2s_trigger(struct snd_pcm_substream *substream, int cmd, struct snd_soc_dai *dai) { @@ -294,6 +307,7 @@ static struct snd_soc_dai_ops dw_i2s_dai_ops = { .startup = dw_i2s_startup, .shutdown = dw_i2s_shutdown, .hw_params = dw_i2s_hw_params, + .prepare = dw_i2s_prepare, .trigger = dw_i2s_trigger, }; diff --git a/sound/soc/fsl/fsl_esai.h b/sound/soc/fsl/fsl_esai.h index 75e14033e8d8..dfdbaa014561 100644 --- a/sound/soc/fsl/fsl_esai.h +++ b/sound/soc/fsl/fsl_esai.h @@ -302,7 +302,7 @@ #define ESAI_xCCR_xFP_MASK (((1 << ESAI_xCCR_xFP_WIDTH) - 1) << ESAI_xCCR_xFP_SHIFT) #define ESAI_xCCR_xFP(v) ((((v) - 1) << ESAI_xCCR_xFP_SHIFT) & ESAI_xCCR_xFP_MASK) #define ESAI_xCCR_xDC_SHIFT 9 -#define ESAI_xCCR_xDC_WIDTH 4 +#define ESAI_xCCR_xDC_WIDTH 5 #define ESAI_xCCR_xDC_MASK (((1 << ESAI_xCCR_xDC_WIDTH) - 1) << ESAI_xCCR_xDC_SHIFT) #define ESAI_xCCR_xDC(v) ((((v) - 1) << ESAI_xCCR_xDC_SHIFT) & ESAI_xCCR_xDC_MASK) #define ESAI_xCCR_xPSR_SHIFT 8 diff --git a/sound/soc/jz4740/Makefile b/sound/soc/jz4740/Makefile index be873c1b0c20..d32c540555c4 100644 --- a/sound/soc/jz4740/Makefile +++ b/sound/soc/jz4740/Makefile @@ -1,10 +1,8 @@ # # Jz4740 Platform Support # -snd-soc-jz4740-objs := jz4740-pcm.o snd-soc-jz4740-i2s-objs := jz4740-i2s.o -obj-$(CONFIG_SND_JZ4740_SOC) += snd-soc-jz4740.o obj-$(CONFIG_SND_JZ4740_SOC_I2S) += snd-soc-jz4740-i2s.o # Jz4740 Machine Support diff --git a/sound/soc/omap/omap-mcbsp.c b/sound/soc/omap/omap-mcbsp.c index 6c19bba23570..6a339fb55479 100644 --- a/sound/soc/omap/omap-mcbsp.c +++ b/sound/soc/omap/omap-mcbsp.c @@ -436,7 +436,7 @@ static int omap_mcbsp_dai_set_dai_fmt(struct snd_soc_dai *cpu_dai, case SND_SOC_DAIFMT_CBM_CFS: /* McBSP slave. FS clock as output */ regs->srgr2 |= FSGM; - regs->pcr0 |= FSXM; + regs->pcr0 |= FSXM | FSRM; break; case SND_SOC_DAIFMT_CBM_CFM: /* McBSP slave */ diff --git a/sound/soc/omap/omap-pcm.c b/sound/soc/omap/omap-pcm.c index 07b8b7bc9d20..81f6a7545ef5 100644 --- a/sound/soc/omap/omap-pcm.c +++ b/sound/soc/omap/omap-pcm.c @@ -200,7 +200,7 @@ static int omap_pcm_new(struct snd_soc_pcm_runtime *rtd) struct snd_pcm *pcm = rtd->pcm; int ret; - ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(64)); + ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32)); if (ret) return ret; diff --git a/sound/soc/sh/fsi.c b/sound/soc/sh/fsi.c index 1967f44e7cd4..9d0c59ce6de8 100644 --- a/sound/soc/sh/fsi.c +++ b/sound/soc/sh/fsi.c @@ -1785,8 +1785,7 @@ static const struct snd_soc_dai_ops fsi_dai_ops = { static struct snd_pcm_hardware fsi_pcm_hardware = { .info = SNDRV_PCM_INFO_INTERLEAVED | SNDRV_PCM_INFO_MMAP | - SNDRV_PCM_INFO_MMAP_VALID | - SNDRV_PCM_INFO_PAUSE, + SNDRV_PCM_INFO_MMAP_VALID, .buffer_bytes_max = 64 * 1024, .period_bytes_min = 32, .period_bytes_max = 8192, diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c index 743de5e3b1e1..37fcd93ed1fd 100644 --- a/sound/soc/sh/rcar/core.c +++ b/sound/soc/sh/rcar/core.c @@ -626,8 +626,7 @@ static void rsnd_dai_remove(struct platform_device *pdev, static struct snd_pcm_hardware rsnd_pcm_hardware = { .info = SNDRV_PCM_INFO_INTERLEAVED | SNDRV_PCM_INFO_MMAP | - SNDRV_PCM_INFO_MMAP_VALID | - SNDRV_PCM_INFO_PAUSE, + SNDRV_PCM_INFO_MMAP_VALID, .buffer_bytes_max = 64 * 1024, .period_bytes_min = 32, .period_bytes_max = 8192, diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c index 5e9690c85d8f..4f98ff14cf12 100644 --- a/sound/soc/soc-compress.c +++ b/sound/soc/soc-compress.c @@ -696,7 +696,8 @@ int soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num) rtd->dai_link->stream_name); ret = snd_pcm_new_internal(rtd->card->snd_card, new_name, num, - 1, 0, &be_pcm); + rtd->dai_link->dpcm_playback, + rtd->dai_link->dpcm_capture, &be_pcm); if (ret < 0) { dev_err(rtd->card->dev, "ASoC: can't create compressed for %s\n", rtd->dai_link->name); @@ -705,8 +706,10 @@ int soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num) rtd->pcm = be_pcm; rtd->fe_compr = 1; - be_pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream->private_data = rtd; - be_pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream->private_data = rtd; + if (rtd->dai_link->dpcm_playback) + be_pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream->private_data = rtd; + else if (rtd->dai_link->dpcm_capture) + be_pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream->private_data = rtd; memcpy(compr->ops, &soc_compr_dyn_ops, sizeof(soc_compr_dyn_ops)); } else memcpy(compr->ops, &soc_compr_ops, sizeof(soc_compr_ops)); diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 731d47b64daa..e4da224d7253 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -689,9 +689,9 @@ static int dapm_create_or_share_mixmux_kcontrol(struct snd_soc_dapm_widget *w, int shared; struct snd_kcontrol *kcontrol; bool wname_in_long_name, kcname_in_long_name; - char *long_name; + char *long_name = NULL; const char *name; - int ret; + int ret = 0; if (dapm->codec) prefix = dapm->codec->name_prefix; @@ -756,15 +756,17 @@ static int dapm_create_or_share_mixmux_kcontrol(struct snd_soc_dapm_widget *w, kcontrol = snd_soc_cnew(&w->kcontrol_news[kci], NULL, name, prefix); - kfree(long_name); - if (!kcontrol) - return -ENOMEM; + if (!kcontrol) { + ret = -ENOMEM; + goto exit_free; + } + kcontrol->private_free = dapm_kcontrol_free; ret = dapm_kcontrol_data_alloc(w, kcontrol); if (ret) { snd_ctl_free_one(kcontrol); - return ret; + goto exit_free; } ret = snd_ctl_add(card, kcontrol); @@ -772,17 +774,18 @@ static int dapm_create_or_share_mixmux_kcontrol(struct snd_soc_dapm_widget *w, dev_err(dapm->dev, "ASoC: failed to add widget %s dapm kcontrol %s: %d\n", w->name, name, ret); - return ret; + goto exit_free; } } ret = dapm_kcontrol_add_widget(kcontrol, w); - if (ret) - return ret; + if (ret == 0) + w->kcontrols[kci] = kcontrol; - w->kcontrols[kci] = kcontrol; +exit_free: + kfree(long_name); - return 0; + return ret; } /* create new dapm mixer control */ diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 02733ded2cb1..e28704e1274a 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -1258,13 +1258,36 @@ static void dpcm_set_fe_runtime(struct snd_pcm_substream *substream) dpcm_init_runtime_hw(runtime, &cpu_dai_drv->capture); } +static int dpcm_fe_dai_do_trigger(struct snd_pcm_substream *substream, int cmd); + +/* Set FE's runtime_update state; the state is protected via PCM stream lock + * for avoiding the race with trigger callback. + * If the state is unset and a trigger is pending while the previous operation, + * process the pending trigger action here. + */ +static void dpcm_set_fe_update_state(struct snd_soc_pcm_runtime *fe, + int stream, enum snd_soc_dpcm_update state) +{ + struct snd_pcm_substream *substream = + snd_soc_dpcm_get_substream(fe, stream); + + snd_pcm_stream_lock_irq(substream); + if (state == SND_SOC_DPCM_UPDATE_NO && fe->dpcm[stream].trigger_pending) { + dpcm_fe_dai_do_trigger(substream, + fe->dpcm[stream].trigger_pending - 1); + fe->dpcm[stream].trigger_pending = 0; + } + fe->dpcm[stream].runtime_update = state; + snd_pcm_stream_unlock_irq(substream); +} + static int dpcm_fe_dai_startup(struct snd_pcm_substream *fe_substream) { struct snd_soc_pcm_runtime *fe = fe_substream->private_data; struct snd_pcm_runtime *runtime = fe_substream->runtime; int stream = fe_substream->stream, ret = 0; - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_FE); ret = dpcm_be_dai_startup(fe, fe_substream->stream); if (ret < 0) { @@ -1286,13 +1309,13 @@ static int dpcm_fe_dai_startup(struct snd_pcm_substream *fe_substream) dpcm_set_fe_runtime(fe_substream); snd_pcm_limit_hw_rates(runtime); - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO); return 0; unwind: dpcm_be_dai_startup_unwind(fe, fe_substream->stream); be_err: - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO); return ret; } @@ -1339,7 +1362,7 @@ static int dpcm_fe_dai_shutdown(struct snd_pcm_substream *substream) struct snd_soc_pcm_runtime *fe = substream->private_data; int stream = substream->stream; - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_FE); /* shutdown the BEs */ dpcm_be_dai_shutdown(fe, substream->stream); @@ -1353,7 +1376,7 @@ static int dpcm_fe_dai_shutdown(struct snd_pcm_substream *substream) dpcm_dapm_stream_event(fe, stream, SND_SOC_DAPM_STREAM_STOP); fe->dpcm[stream].state = SND_SOC_DPCM_STATE_CLOSE; - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO); return 0; } @@ -1401,7 +1424,7 @@ static int dpcm_fe_dai_hw_free(struct snd_pcm_substream *substream) int err, stream = substream->stream; mutex_lock_nested(&fe->card->mutex, SND_SOC_CARD_CLASS_RUNTIME); - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_FE); dev_dbg(fe->dev, "ASoC: hw_free FE %s\n", fe->dai_link->name); @@ -1416,7 +1439,7 @@ static int dpcm_fe_dai_hw_free(struct snd_pcm_substream *substream) err = dpcm_be_dai_hw_free(fe, stream); fe->dpcm[stream].state = SND_SOC_DPCM_STATE_HW_FREE; - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO); mutex_unlock(&fe->card->mutex); return 0; @@ -1509,7 +1532,7 @@ static int dpcm_fe_dai_hw_params(struct snd_pcm_substream *substream, int ret, stream = substream->stream; mutex_lock_nested(&fe->card->mutex, SND_SOC_CARD_CLASS_RUNTIME); - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_FE); memcpy(&fe->dpcm[substream->stream].hw_params, params, sizeof(struct snd_pcm_hw_params)); @@ -1532,7 +1555,7 @@ static int dpcm_fe_dai_hw_params(struct snd_pcm_substream *substream, fe->dpcm[stream].state = SND_SOC_DPCM_STATE_HW_PARAMS; out: - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO); mutex_unlock(&fe->card->mutex); return ret; } @@ -1646,7 +1669,7 @@ int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream, } EXPORT_SYMBOL_GPL(dpcm_be_dai_trigger); -static int dpcm_fe_dai_trigger(struct snd_pcm_substream *substream, int cmd) +static int dpcm_fe_dai_do_trigger(struct snd_pcm_substream *substream, int cmd) { struct snd_soc_pcm_runtime *fe = substream->private_data; int stream = substream->stream, ret; @@ -1720,6 +1743,23 @@ out: return ret; } +static int dpcm_fe_dai_trigger(struct snd_pcm_substream *substream, int cmd) +{ + struct snd_soc_pcm_runtime *fe = substream->private_data; + int stream = substream->stream; + + /* if FE's runtime_update is already set, we're in race; + * process this trigger later at exit + */ + if (fe->dpcm[stream].runtime_update != SND_SOC_DPCM_UPDATE_NO) { + fe->dpcm[stream].trigger_pending = cmd + 1; + return 0; /* delayed, assuming it's successful */ + } + + /* we're alone, let's trigger */ + return dpcm_fe_dai_do_trigger(substream, cmd); +} + int dpcm_be_dai_prepare(struct snd_soc_pcm_runtime *fe, int stream) { struct snd_soc_dpcm *dpcm; @@ -1763,7 +1803,7 @@ static int dpcm_fe_dai_prepare(struct snd_pcm_substream *substream) dev_dbg(fe->dev, "ASoC: prepare FE %s\n", fe->dai_link->name); - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_FE); /* there is no point preparing this FE if there are no BEs */ if (list_empty(&fe->dpcm[stream].be_clients)) { @@ -1790,7 +1830,7 @@ static int dpcm_fe_dai_prepare(struct snd_pcm_substream *substream) fe->dpcm[stream].state = SND_SOC_DPCM_STATE_PREPARE; out: - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO); mutex_unlock(&fe->card->mutex); return ret; @@ -1937,11 +1977,11 @@ static int dpcm_run_new_update(struct snd_soc_pcm_runtime *fe, int stream) { int ret; - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_BE; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_BE); ret = dpcm_run_update_startup(fe, stream); if (ret < 0) dev_err(fe->dev, "ASoC: failed to startup some BEs\n"); - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO); return ret; } @@ -1950,11 +1990,11 @@ static int dpcm_run_old_update(struct snd_soc_pcm_runtime *fe, int stream) { int ret; - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_BE; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_BE); ret = dpcm_run_update_shutdown(fe, stream); if (ret < 0) dev_err(fe->dev, "ASoC: failed to shutdown some BEs\n"); - fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO; + dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO); return ret; } diff --git a/sound/usb/card.c b/sound/usb/card.c index af1956042c9e..ab433a02dbf1 100644 --- a/sound/usb/card.c +++ b/sound/usb/card.c @@ -586,18 +586,19 @@ static void snd_usb_audio_disconnect(struct usb_device *dev, { struct snd_card *card; struct list_head *p; + bool was_shutdown; if (chip == (void *)-1L) return; card = chip->card; down_write(&chip->shutdown_rwsem); + was_shutdown = chip->shutdown; chip->shutdown = 1; up_write(&chip->shutdown_rwsem); mutex_lock(®ister_mutex); - chip->num_interfaces--; - if (chip->num_interfaces <= 0) { + if (!was_shutdown) { struct snd_usb_endpoint *ep; snd_card_disconnect(card); @@ -617,6 +618,10 @@ static void snd_usb_audio_disconnect(struct usb_device *dev, list_for_each(p, &chip->mixer_list) { snd_usb_mixer_disconnect(p); } + } + + chip->num_interfaces--; + if (chip->num_interfaces <= 0) { usb_chip[chip->index] = NULL; mutex_unlock(®ister_mutex); snd_card_free_when_closed(card); diff --git a/sound/usb/midi.c b/sound/usb/midi.c index b901f468b67a..c7aa71ee775b 100644 --- a/sound/usb/midi.c +++ b/sound/usb/midi.c @@ -364,6 +364,8 @@ static void snd_usbmidi_error_timer(unsigned long data) if (in && in->error_resubmit) { in->error_resubmit = 0; for (j = 0; j < INPUT_URBS; ++j) { + if (atomic_read(&in->urbs[j]->use_count)) + continue; in->urbs[j]->dev = umidi->dev; snd_usbmidi_submit_urb(in->urbs[j], GFP_ATOMIC); } diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 1bed780e21d9..2d37b3fc3a21 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -886,6 +886,7 @@ static void volume_control_quirks(struct usb_mixer_elem_info *cval, case USB_ID(0x046d, 0x0807): /* Logitech Webcam C500 */ case USB_ID(0x046d, 0x0808): case USB_ID(0x046d, 0x0809): + case USB_ID(0x046d, 0x0819): /* Logitech Webcam C210 */ case USB_ID(0x046d, 0x081b): /* HD Webcam c310 */ case USB_ID(0x046d, 0x081d): /* HD Webcam c510 */ case USB_ID(0x046d, 0x0825): /* HD Webcam c270 */ diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index d1d72ff50347..621bc9ebb55e 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -328,8 +328,11 @@ static struct usbmix_name_map gamecom780_map[] = { {} }; -static const struct usbmix_name_map kef_x300a_map[] = { - { 10, NULL }, /* firmware locks up (?) when we try to access this FU */ +/* some (all?) SCMS USB3318 devices are affected by a firmware lock up + * when anything attempts to access FU 10 (control) + */ +static const struct usbmix_name_map scms_usb3318_map[] = { + { 10, NULL }, { 0 } }; @@ -425,8 +428,14 @@ static struct usbmix_ctl_map usbmix_ctl_maps[] = { .map = ebox44_map, }, { + /* KEF X300A */ .id = USB_ID(0x27ac, 0x1000), - .map = kef_x300a_map, + .map = scms_usb3318_map, + }, + { + /* Arcam rPAC */ + .id = USB_ID(0x25c4, 0x0003), + .map = scms_usb3318_map, }, { 0 } /* terminator */ }; diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index f4b12c216f1c..a82ec53b8fb3 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -178,6 +178,7 @@ static const struct rc_config { { USB_ID(0x041e, 0x3040), 2, 2, 6, 6, 2, 0x6e91 }, /* Live! 24-bit */ { USB_ID(0x041e, 0x3042), 0, 1, 1, 1, 1, 0x000d }, /* Usb X-Fi S51 */ { USB_ID(0x041e, 0x30df), 0, 1, 1, 1, 1, 0x000d }, /* Usb X-Fi S51 Pro */ + { USB_ID(0x041e, 0x3237), 0, 1, 1, 1, 1, 0x000d }, /* Usb X-Fi S51 Pro */ { USB_ID(0x041e, 0x3048), 2, 2, 6, 6, 2, 0x6e91 }, /* Toshiba SB0500 */ }; @@ -885,6 +886,11 @@ static int snd_ftu_eff_switch_put(struct snd_kcontrol *kctl, return changed; } +static void kctl_private_value_free(struct snd_kcontrol *kctl) +{ + kfree((void *)kctl->private_value); +} + static int snd_ftu_create_effect_switch(struct usb_mixer_interface *mixer, int validx, int bUnitID) { @@ -919,6 +925,7 @@ static int snd_ftu_create_effect_switch(struct usb_mixer_interface *mixer, return -ENOMEM; } + kctl->private_free = kctl_private_value_free; err = snd_ctl_add(mixer->chip->card, kctl); if (err < 0) return err; diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index 223c47b33ba3..5293b5ac8b9d 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -385,6 +385,36 @@ YAMAHA_DEVICE(0x105d, NULL), } }, { + USB_DEVICE(0x0499, 0x1509), + .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { + /* .vendor_name = "Yamaha", */ + /* .product_name = "Steinberg UR22", */ + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = (const struct snd_usb_audio_quirk[]) { + { + .ifnum = 1, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 2, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 3, + .type = QUIRK_MIDI_YAMAHA + }, + { + .ifnum = 4, + .type = QUIRK_IGNORE_INTERFACE + }, + { + .ifnum = -1 + } + } + } +}, +{ USB_DEVICE(0x0499, 0x150a), .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { /* .vendor_name = "Yamaha", */ @@ -1743,6 +1773,36 @@ YAMAHA_DEVICE(0x7010, "UB99"), } } }, +{ + USB_DEVICE(0x0582, 0x0159), + .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { + /* .vendor_name = "Roland", */ + /* .product_name = "UA-22", */ + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = (const struct snd_usb_audio_quirk[]) { + { + .ifnum = 0, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 1, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 2, + .type = QUIRK_MIDI_FIXED_ENDPOINT, + .data = & (const struct snd_usb_midi_endpoint_info) { + .out_cables = 0x0001, + .in_cables = 0x0001 + } + }, + { + .ifnum = -1 + } + } + } +}, /* this catches most recent vendor-specific Roland devices */ { .match_flags = USB_DEVICE_ID_MATCH_VENDOR | @@ -2774,133 +2834,45 @@ YAMAHA_DEVICE(0x7010, "UB99"), } }, -/* Hauppauge HVR-950Q and HVR-850 */ -{ - USB_DEVICE_VENDOR_SPEC(0x2040, 0x7200), - .match_flags = USB_DEVICE_ID_MATCH_DEVICE | - USB_DEVICE_ID_MATCH_INT_CLASS | - USB_DEVICE_ID_MATCH_INT_SUBCLASS, - .bInterfaceClass = USB_CLASS_AUDIO, - .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, - .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { - .vendor_name = "Hauppauge", - .product_name = "HVR-950Q", - .ifnum = QUIRK_ANY_INTERFACE, - .type = QUIRK_AUDIO_ALIGN_TRANSFER, - } -}, -{ - USB_DEVICE_VENDOR_SPEC(0x2040, 0x7210), - .match_flags = USB_DEVICE_ID_MATCH_DEVICE | - USB_DEVICE_ID_MATCH_INT_CLASS | - USB_DEVICE_ID_MATCH_INT_SUBCLASS, - .bInterfaceClass = USB_CLASS_AUDIO, - .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, - .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { - .vendor_name = "Hauppauge", - .product_name = "HVR-950Q", - .ifnum = QUIRK_ANY_INTERFACE, - .type = QUIRK_AUDIO_ALIGN_TRANSFER, - } -}, -{ - USB_DEVICE_VENDOR_SPEC(0x2040, 0x7217), - .match_flags = USB_DEVICE_ID_MATCH_DEVICE | - USB_DEVICE_ID_MATCH_INT_CLASS | - USB_DEVICE_ID_MATCH_INT_SUBCLASS, - .bInterfaceClass = USB_CLASS_AUDIO, - .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, - .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { - .vendor_name = "Hauppauge", - .product_name = "HVR-950Q", - .ifnum = QUIRK_ANY_INTERFACE, - .type = QUIRK_AUDIO_ALIGN_TRANSFER, - } -}, -{ - USB_DEVICE_VENDOR_SPEC(0x2040, 0x721b), - .match_flags = USB_DEVICE_ID_MATCH_DEVICE | - USB_DEVICE_ID_MATCH_INT_CLASS | - USB_DEVICE_ID_MATCH_INT_SUBCLASS, - .bInterfaceClass = USB_CLASS_AUDIO, - .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, - .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { - .vendor_name = "Hauppauge", - .product_name = "HVR-950Q", - .ifnum = QUIRK_ANY_INTERFACE, - .type = QUIRK_AUDIO_ALIGN_TRANSFER, - } -}, -{ - USB_DEVICE_VENDOR_SPEC(0x2040, 0x721e), - .match_flags = USB_DEVICE_ID_MATCH_DEVICE | - USB_DEVICE_ID_MATCH_INT_CLASS | - USB_DEVICE_ID_MATCH_INT_SUBCLASS, - .bInterfaceClass = USB_CLASS_AUDIO, - .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, - .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { - .vendor_name = "Hauppauge", - .product_name = "HVR-950Q", - .ifnum = QUIRK_ANY_INTERFACE, - .type = QUIRK_AUDIO_ALIGN_TRANSFER, - } -}, -{ - USB_DEVICE_VENDOR_SPEC(0x2040, 0x721f), - .match_flags = USB_DEVICE_ID_MATCH_DEVICE | - USB_DEVICE_ID_MATCH_INT_CLASS | - USB_DEVICE_ID_MATCH_INT_SUBCLASS, - .bInterfaceClass = USB_CLASS_AUDIO, - .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, - .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { - .vendor_name = "Hauppauge", - .product_name = "HVR-950Q", - .ifnum = QUIRK_ANY_INTERFACE, - .type = QUIRK_AUDIO_ALIGN_TRANSFER, - } -}, -{ - USB_DEVICE_VENDOR_SPEC(0x2040, 0x7240), - .match_flags = USB_DEVICE_ID_MATCH_DEVICE | - USB_DEVICE_ID_MATCH_INT_CLASS | - USB_DEVICE_ID_MATCH_INT_SUBCLASS, - .bInterfaceClass = USB_CLASS_AUDIO, - .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, - .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { - .vendor_name = "Hauppauge", - .product_name = "HVR-850", - .ifnum = QUIRK_ANY_INTERFACE, - .type = QUIRK_AUDIO_ALIGN_TRANSFER, - } -}, -{ - USB_DEVICE_VENDOR_SPEC(0x2040, 0x7280), - .match_flags = USB_DEVICE_ID_MATCH_DEVICE | - USB_DEVICE_ID_MATCH_INT_CLASS | - USB_DEVICE_ID_MATCH_INT_SUBCLASS, - .bInterfaceClass = USB_CLASS_AUDIO, - .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, - .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { - .vendor_name = "Hauppauge", - .product_name = "HVR-950Q", - .ifnum = QUIRK_ANY_INTERFACE, - .type = QUIRK_AUDIO_ALIGN_TRANSFER, - } -}, -{ - USB_DEVICE_VENDOR_SPEC(0x0fd9, 0x0008), - .match_flags = USB_DEVICE_ID_MATCH_DEVICE | - USB_DEVICE_ID_MATCH_INT_CLASS | - USB_DEVICE_ID_MATCH_INT_SUBCLASS, - .bInterfaceClass = USB_CLASS_AUDIO, - .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, - .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { - .vendor_name = "Hauppauge", - .product_name = "HVR-950Q", - .ifnum = QUIRK_ANY_INTERFACE, - .type = QUIRK_AUDIO_ALIGN_TRANSFER, - } -}, +/* + * Auvitek au0828 devices with audio interface. + * This should be kept in sync with drivers/media/usb/au0828/au0828-cards.c + * Please notice that some drivers are DVB only, and don't need to be + * here. That's the case, for example, of DVICO_FUSIONHDTV7. + */ + +#define AU0828_DEVICE(vid, pid, vname, pname) { \ + USB_DEVICE_VENDOR_SPEC(vid, pid), \ + .match_flags = USB_DEVICE_ID_MATCH_DEVICE | \ + USB_DEVICE_ID_MATCH_INT_CLASS | \ + USB_DEVICE_ID_MATCH_INT_SUBCLASS, \ + .bInterfaceClass = USB_CLASS_AUDIO, \ + .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, \ + .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { \ + .vendor_name = vname, \ + .product_name = pname, \ + .ifnum = QUIRK_ANY_INTERFACE, \ + .type = QUIRK_AUDIO_ALIGN_TRANSFER, \ + } \ +} + +AU0828_DEVICE(0x2040, 0x7200, "Hauppauge", "HVR-950Q"), +AU0828_DEVICE(0x2040, 0x7240, "Hauppauge", "HVR-850"), +AU0828_DEVICE(0x2040, 0x7210, "Hauppauge", "HVR-950Q"), +AU0828_DEVICE(0x2040, 0x7217, "Hauppauge", "HVR-950Q"), +AU0828_DEVICE(0x2040, 0x721b, "Hauppauge", "HVR-950Q"), +AU0828_DEVICE(0x2040, 0x721e, "Hauppauge", "HVR-950Q"), +AU0828_DEVICE(0x2040, 0x721f, "Hauppauge", "HVR-950Q"), +AU0828_DEVICE(0x2040, 0x7280, "Hauppauge", "HVR-950Q"), +AU0828_DEVICE(0x0fd9, 0x0008, "Hauppauge", "HVR-950Q"), +AU0828_DEVICE(0x2040, 0x7201, "Hauppauge", "HVR-950Q-MXL"), +AU0828_DEVICE(0x2040, 0x7211, "Hauppauge", "HVR-950Q-MXL"), +AU0828_DEVICE(0x2040, 0x7281, "Hauppauge", "HVR-950Q-MXL"), +AU0828_DEVICE(0x05e1, 0x0480, "Hauppauge", "Woodbury"), +AU0828_DEVICE(0x2040, 0x8200, "Hauppauge", "Woodbury"), +AU0828_DEVICE(0x2040, 0x7260, "Hauppauge", "HVR-950Q"), +AU0828_DEVICE(0x2040, 0x7213, "Hauppauge", "HVR-950Q"), +AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"), /* Digidesign Mbox */ { diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index c64a3d96db22..827d40441ec7 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1142,6 +1142,20 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe, if ((le16_to_cpu(dev->descriptor.idVendor) == 0x23ba) && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) mdelay(20); + + /* Marantz/Denon devices with USB DAC functionality need a delay + * after each class compliant request + */ + if ((le16_to_cpu(dev->descriptor.idVendor) == 0x154e) && + (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) { + + switch (le16_to_cpu(dev->descriptor.idProduct)) { + case 0x3005: /* Marantz HD-DAC1 */ + case 0x3006: /* Marantz SA-14S1 */ + mdelay(20); + break; + } + } } /* diff --git a/tools/gator/daemon/Android.mk b/tools/gator/daemon/Android.mk index 44c069cc7e24..970ac6946150 100644 --- a/tools/gator/daemon/Android.mk +++ b/tools/gator/daemon/Android.mk @@ -3,13 +3,16 @@ include $(CLEAR_VARS) XML_H := $(shell cd $(LOCAL_PATH) && make events_xml.h defaults_xml.h) -LOCAL_CFLAGS += -Wall -O3 -mthumb-interwork -fno-exceptions -pthread -DETCDIR=\"/etc\" -Ilibsensors - LOCAL_SRC_FILES := \ + AnnotateListener.cpp \ Buffer.cpp \ + CCNDriver.cpp \ + CPUFreqDriver.cpp \ CapturedXML.cpp \ Child.cpp \ + Command.cpp \ ConfigurationXML.cpp \ + DiskIODriver.cpp \ Driver.cpp \ DriverSource.cpp \ DynBuf.cpp \ @@ -17,13 +20,17 @@ LOCAL_SRC_FILES := \ ExternalSource.cpp \ FSDriver.cpp \ Fifo.cpp \ - Hwmon.cpp \ + FtraceDriver.cpp \ + FtraceSource.cpp \ + HwmonDriver.cpp \ KMod.cpp \ LocalCapture.cpp \ Logging.cpp \ main.cpp \ MaliVideoDriver.cpp \ + MemInfoDriver.cpp\ Monitor.cpp \ + NetDriver.cpp \ OlySocket.cpp \ OlyUtility.cpp \ PerfBuffer.cpp \ @@ -34,6 +41,7 @@ LOCAL_SRC_FILES := \ Sender.cpp \ SessionData.cpp \ SessionXML.cpp \ + Setup.cpp \ Source.cpp \ StreamlineSetup.cpp \ UEvent.cpp \ @@ -57,6 +65,9 @@ LOCAL_SRC_FILES := \ mxml/mxml-set.c \ mxml/mxml-string.c +LOCAL_CFLAGS += -Wall -O3 -fno-exceptions -pthread -DETCDIR=\"/etc\" -Ilibsensors -fPIE +LOCAL_LDFLAGS += -fPIE -pie + LOCAL_C_INCLUDES := $(LOCAL_PATH) LOCAL_MODULE := gatord diff --git a/tools/gator/daemon/AnnotateListener.cpp b/tools/gator/daemon/AnnotateListener.cpp new file mode 100644 index 000000000000..50110b4dc84c --- /dev/null +++ b/tools/gator/daemon/AnnotateListener.cpp @@ -0,0 +1,69 @@ +/** + * Copyright (C) ARM Limited 2014. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "AnnotateListener.h" + +#include <unistd.h> + +#include "OlySocket.h" + +struct AnnotateClient { + AnnotateClient *next; + int fd; +}; + +AnnotateListener::AnnotateListener() : mClients(NULL), mSock(NULL) { +} + +AnnotateListener::~AnnotateListener() { + close(); + delete mSock; +} + +void AnnotateListener::setup() { + mSock = new OlyServerSocket(8082); +} + +int AnnotateListener::getFd() { + return mSock->getFd(); +} + +void AnnotateListener::handle() { + AnnotateClient *const client = new AnnotateClient(); + client->fd = mSock->acceptConnection(); + client->next = mClients; + mClients = client; +} + +void AnnotateListener::close() { + mSock->closeServerSocket(); + while (mClients != NULL) { + ::close(mClients->fd); + AnnotateClient *next = mClients->next; + delete mClients; + mClients = next; + } +} + +void AnnotateListener::signal() { + const char ch = 0; + AnnotateClient **ptr = &mClients; + AnnotateClient *client = mClients; + while (client != NULL) { + if (write(client->fd, &ch, sizeof(ch)) != 1) { + ::close(client->fd); + AnnotateClient *next = client->next; + delete client; + *ptr = next; + client = next; + continue; + } + ptr = &client->next; + client = client->next; + } +} diff --git a/tools/gator/daemon/AnnotateListener.h b/tools/gator/daemon/AnnotateListener.h new file mode 100644 index 000000000000..cdefef12db22 --- /dev/null +++ b/tools/gator/daemon/AnnotateListener.h @@ -0,0 +1,31 @@ +/** + * Copyright (C) ARM Limited 2014. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +class AnnotateClient; +class OlyServerSocket; + +class AnnotateListener { +public: + AnnotateListener(); + ~AnnotateListener(); + + void setup(); + int getFd(); + + void handle(); + void close(); + void signal(); + +private: + AnnotateClient *mClients; + OlyServerSocket *mSock; + + // Intentionally unimplemented + AnnotateListener(const AnnotateListener &); + AnnotateListener &operator=(const AnnotateListener &); +}; diff --git a/tools/gator/daemon/Application.mk b/tools/gator/daemon/Application.mk index 631ba54148d1..3ada471cac19 100644 --- a/tools/gator/daemon/Application.mk +++ b/tools/gator/daemon/Application.mk @@ -1 +1,3 @@ APP_PLATFORM := android-8 +# Replace armeabi-v7a with arm64-v8a to build an arm64 gatord or with armeabi to build an ARM11 gatord +APP_ABI := armeabi-v7a diff --git a/tools/gator/daemon/Buffer.cpp b/tools/gator/daemon/Buffer.cpp index dd19f7f8be76..8fa628015069 100644 --- a/tools/gator/daemon/Buffer.cpp +++ b/tools/gator/daemon/Buffer.cpp @@ -15,12 +15,15 @@ #define mask (mSize - 1) enum { - CODE_PEA = 1, - CODE_KEYS = 2, - CODE_FORMAT = 3, - CODE_MAPS = 4, - CODE_COMM = 5, - CODE_KEYS_OLD = 6, + CODE_PEA = 1, + CODE_KEYS = 2, + CODE_FORMAT = 3, + CODE_MAPS = 4, + CODE_COMM = 5, + CODE_KEYS_OLD = 6, + CODE_ONLINE_CPU = 7, + CODE_OFFLINE_CPU = 8, + CODE_KALLSYMS = 9, }; // Summary Frame Messages @@ -42,16 +45,18 @@ enum { /* Add another character so the length isn't 0x0a bytes */ \ "5" -Buffer::Buffer(const int32_t core, const int32_t buftype, const int size, sem_t *const readerSem) : mCore(core), mBufType(buftype), mSize(size), mReadPos(0), mWritePos(0), mCommitPos(0), mAvailable(true), mIsDone(false), mBuf(new char[mSize]), mCommitTime(gSessionData->mLiveRate), mReaderSem(readerSem) { +Buffer::Buffer(const int32_t core, const int32_t buftype, const int size, sem_t *const readerSem) : mBuf(new char[size]), mReaderSem(readerSem), mCommitTime(gSessionData->mLiveRate), mSize(size), mReadPos(0), mWritePos(0), mCommitPos(0), mAvailable(true), mIsDone(false), mCore(core), mBufType(buftype) { if ((mSize & mask) != 0) { logg->logError(__FILE__, __LINE__, "Buffer size is not a power of 2"); handleException(); } + sem_init(&mWriterSem, 0, 0); frame(); } Buffer::~Buffer() { delete [] mBuf; + sem_destroy(&mWriterSem); } void Buffer::write(Sender *const sender) { @@ -59,14 +64,18 @@ void Buffer::write(Sender *const sender) { return; } + // commit and read are updated by the writer, only read them once + int commitPos = mCommitPos; + int readPos = mReadPos; + // determine the size of two halves - int length1 = mCommitPos - mReadPos; - char *buffer1 = mBuf + mReadPos; + int length1 = commitPos - readPos; + char *buffer1 = mBuf + readPos; int length2 = 0; char *buffer2 = mBuf; if (length1 < 0) { - length1 = mSize - mReadPos; - length2 = mCommitPos; + length1 = mSize - readPos; + length2 = commitPos; } logg->logMessage("Sending data length1: %i length2: %i", length1, length2); @@ -81,7 +90,10 @@ void Buffer::write(Sender *const sender) { sender->writeData(buffer2, length2, RESPONSE_APC_DATA); } - mReadPos = mCommitPos; + mReadPos = commitPos; + + // send a notification that space is available + sem_post(&mWriterSem); } bool Buffer::commitReady() const { @@ -193,7 +205,7 @@ void Buffer::packInt(int32_t x) { packInt(mBuf, mSize, mWritePos, x); } -void Buffer::packInt64(int64_t x) { +void Buffer::packInt64(char *const buf, const int size, int &writePos, int64_t x) { int packedBytes = 0; int more = true; while (more) { @@ -207,11 +219,15 @@ void Buffer::packInt64(int64_t x) { b |= 0x80; } - mBuf[(mWritePos + packedBytes) & mask] = b; + buf[(writePos + packedBytes) & /*mask*/(size - 1)] = b; packedBytes++; } - mWritePos = (mWritePos + packedBytes) & mask; + writePos = (writePos + packedBytes) & /*mask*/(size - 1); +} + +void Buffer::packInt64(int64_t x) { + packInt64(mBuf, mSize, mWritePos, x); } void Buffer::writeBytes(const void *const data, size_t count) { @@ -236,10 +252,12 @@ void Buffer::frame() { // Reserve space for the length mWritePos += sizeof(int32_t); packInt(mBufType); - packInt(mCore); + if ((mBufType == FRAME_BLOCK_COUNTER) || (mBufType == FRAME_PERF_ATTRS) || (mBufType == FRAME_PERF)) { + packInt(mCore); + } } -void Buffer::summary(const int64_t timestamp, const int64_t uptime, const int64_t monotonicDelta, const char *const uname) { +void Buffer::summary(const uint64_t currTime, const int64_t timestamp, const int64_t uptime, const int64_t monotonicDelta, const char *const uname) { packInt(MESSAGE_SUMMARY); writeString(NEWLINE_CANARY); packInt64(timestamp); @@ -248,23 +266,24 @@ void Buffer::summary(const int64_t timestamp, const int64_t uptime, const int64_ writeString("uname"); writeString(uname); writeString(""); - check(1); + check(currTime); } -void Buffer::coreName(const int core, const int cpuid, const char *const name) { +void Buffer::coreName(const uint64_t currTime, const int core, const int cpuid, const char *const name) { if (checkSpace(3 * MAXSIZE_PACK32 + 0x100)) { packInt(MESSAGE_CORE_NAME); packInt(core); packInt(cpuid); writeString(name); } - check(1); + check(currTime); } bool Buffer::eventHeader(const uint64_t curr_time) { bool retval = false; if (checkSpace(MAXSIZE_PACK32 + MAXSIZE_PACK64)) { - packInt(0); // key of zero indicates a timestamp + // key of zero indicates a timestamp + packInt(0); packInt64(curr_time); retval = true; } @@ -275,7 +294,8 @@ bool Buffer::eventHeader(const uint64_t curr_time) { bool Buffer::eventTid(const int tid) { bool retval = false; if (checkSpace(2 * MAXSIZE_PACK32)) { - packInt(1); // key of 1 indicates a tid + // key of 1 indicates a tid + packInt(1); packInt(tid); retval = true; } @@ -283,102 +303,119 @@ bool Buffer::eventTid(const int tid) { return retval; } -void Buffer::event(const int32_t key, const int32_t value) { +void Buffer::event(const int key, const int32_t value) { if (checkSpace(2 * MAXSIZE_PACK32)) { packInt(key); packInt(value); } } -void Buffer::event64(const int64_t key, const int64_t value) { - if (checkSpace(2 * MAXSIZE_PACK64)) { - packInt64(key); +void Buffer::event64(const int key, const int64_t value) { + if (checkSpace(MAXSIZE_PACK64 + MAXSIZE_PACK32)) { + packInt(key); packInt64(value); } } -void Buffer::pea(const struct perf_event_attr *const pea, int key) { - if (checkSpace(2 * MAXSIZE_PACK32 + pea->size)) { - packInt(CODE_PEA); - writeBytes(pea, pea->size); - packInt(key); - } else { - logg->logError(__FILE__, __LINE__, "Ran out of buffer space for perf attrs"); - handleException(); +void Buffer::pea(const uint64_t currTime, const struct perf_event_attr *const pea, int key) { + while (!checkSpace(2 * MAXSIZE_PACK32 + pea->size)) { + sem_wait(&mWriterSem); } - // Don't know the real perf time so use 1 as it will work for now - check(1); + packInt(CODE_PEA); + writeBytes(pea, pea->size); + packInt(key); + check(currTime); } -void Buffer::keys(const int count, const __u64 *const ids, const int *const keys) { - if (checkSpace(2 * MAXSIZE_PACK32 + count * (MAXSIZE_PACK32 + MAXSIZE_PACK64))) { - packInt(CODE_KEYS); - packInt(count); - for (int i = 0; i < count; ++i) { - packInt64(ids[i]); - packInt(keys[i]); - } - } else { - logg->logError(__FILE__, __LINE__, "Ran out of buffer space for perf attrs"); - handleException(); +void Buffer::keys(const uint64_t currTime, const int count, const __u64 *const ids, const int *const keys) { + while (!checkSpace(2 * MAXSIZE_PACK32 + count * (MAXSIZE_PACK32 + MAXSIZE_PACK64))) { + sem_wait(&mWriterSem); + } + packInt(CODE_KEYS); + packInt(count); + for (int i = 0; i < count; ++i) { + packInt64(ids[i]); + packInt(keys[i]); } - check(1); + check(currTime); } -void Buffer::keysOld(const int keyCount, const int *const keys, const int bytes, const char *const buf) { - if (checkSpace((2 + keyCount) * MAXSIZE_PACK32 + bytes)) { - packInt(CODE_KEYS_OLD); - packInt(keyCount); - for (int i = 0; i < keyCount; ++i) { - packInt(keys[i]); - } - writeBytes(buf, bytes); - } else { - logg->logError(__FILE__, __LINE__, "Ran out of buffer space for perf attrs"); - handleException(); +void Buffer::keysOld(const uint64_t currTime, const int keyCount, const int *const keys, const int bytes, const char *const buf) { + while (!checkSpace((2 + keyCount) * MAXSIZE_PACK32 + bytes)) { + sem_wait(&mWriterSem); + } + packInt(CODE_KEYS_OLD); + packInt(keyCount); + for (int i = 0; i < keyCount; ++i) { + packInt(keys[i]); } - check(1); + writeBytes(buf, bytes); + check(currTime); } -void Buffer::format(const int length, const char *const format) { - if (checkSpace(MAXSIZE_PACK32 + length + 1)) { - packInt(CODE_FORMAT); - writeBytes(format, length + 1); - } else { - logg->logError(__FILE__, __LINE__, "Ran out of buffer space for perf attrs"); - handleException(); +void Buffer::format(const uint64_t currTime, const int length, const char *const format) { + while (!checkSpace(MAXSIZE_PACK32 + length + 1)) { + sem_wait(&mWriterSem); } - check(1); + packInt(CODE_FORMAT); + writeBytes(format, length + 1); + check(currTime); } -void Buffer::maps(const int pid, const int tid, const char *const maps) { +void Buffer::maps(const uint64_t currTime, const int pid, const int tid, const char *const maps) { const int mapsLen = strlen(maps) + 1; - if (checkSpace(3 * MAXSIZE_PACK32 + mapsLen)) { - packInt(CODE_MAPS); - packInt(pid); - packInt(tid); - writeBytes(maps, mapsLen); - } else { - logg->logError(__FILE__, __LINE__, "Ran out of buffer space for perf attrs"); - handleException(); + while (!checkSpace(3 * MAXSIZE_PACK32 + mapsLen)) { + sem_wait(&mWriterSem); } - check(1); + packInt(CODE_MAPS); + packInt(pid); + packInt(tid); + writeBytes(maps, mapsLen); + check(currTime); } -void Buffer::comm(const int pid, const int tid, const char *const image, const char *const comm) { +void Buffer::comm(const uint64_t currTime, const int pid, const int tid, const char *const image, const char *const comm) { const int imageLen = strlen(image) + 1; const int commLen = strlen(comm) + 1; - if (checkSpace(3 * MAXSIZE_PACK32 + imageLen + commLen)) { - packInt(CODE_COMM); - packInt(pid); - packInt(tid); - writeBytes(image, imageLen); - writeBytes(comm, commLen); - } else { - logg->logError(__FILE__, __LINE__, "Ran out of buffer space for perf attrs"); - handleException(); + while (!checkSpace(3 * MAXSIZE_PACK32 + imageLen + commLen)) { + sem_wait(&mWriterSem); + } + packInt(CODE_COMM); + packInt(pid); + packInt(tid); + writeBytes(image, imageLen); + writeBytes(comm, commLen); + check(currTime); +} + +void Buffer::onlineCPU(const uint64_t currTime, const uint64_t time, const int cpu) { + while (!checkSpace(MAXSIZE_PACK32 + MAXSIZE_PACK64)) { + sem_wait(&mWriterSem); + } + packInt(CODE_ONLINE_CPU); + packInt64(time); + packInt(cpu); + check(currTime); +} + +void Buffer::offlineCPU(const uint64_t currTime, const uint64_t time, const int cpu) { + while (!checkSpace(MAXSIZE_PACK32 + MAXSIZE_PACK64)) { + sem_wait(&mWriterSem); + } + packInt(CODE_OFFLINE_CPU); + packInt64(time); + packInt(cpu); + check(currTime); +} + +void Buffer::kallsyms(const uint64_t currTime, const char *const kallsyms) { + const int kallsymsLen = strlen(kallsyms) + 1; + while (!checkSpace(3 * MAXSIZE_PACK32 + kallsymsLen)) { + sem_wait(&mWriterSem); } - check(1); + packInt(CODE_KALLSYMS); + writeBytes(kallsyms, kallsymsLen); + check(currTime); } void Buffer::setDone() { diff --git a/tools/gator/daemon/Buffer.h b/tools/gator/daemon/Buffer.h index 2de1b97ac091..6cffd8e39a36 100644 --- a/tools/gator/daemon/Buffer.h +++ b/tools/gator/daemon/Buffer.h @@ -39,25 +39,26 @@ public: void commit(const uint64_t time); void check(const uint64_t time); - void frame(); - // Summary messages - void summary(const int64_t timestamp, const int64_t uptime, const int64_t monotonicDelta, const char *const uname); - void coreName(const int core, const int cpuid, const char *const name); + void summary(const uint64_t currTime, const int64_t timestamp, const int64_t uptime, const int64_t monotonicDelta, const char *const uname); + void coreName(const uint64_t currTime, const int core, const int cpuid, const char *const name); // Block Counter messages bool eventHeader(uint64_t curr_time); bool eventTid(int tid); - void event(int32_t key, int32_t value); - void event64(int64_t key, int64_t value); + void event(int key, int32_t value); + void event64(int key, int64_t value); // Perf Attrs messages - void pea(const struct perf_event_attr *const pea, int key); - void keys(const int count, const __u64 *const ids, const int *const keys); - void keysOld(const int keyCount, const int *const keys, const int bytes, const char *const buf); - void format(const int length, const char *const format); - void maps(const int pid, const int tid, const char *const maps); - void comm(const int pid, const int tid, const char *const image, const char *const comm); + void pea(const uint64_t currTime, const struct perf_event_attr *const pea, int key); + void keys(const uint64_t currTime, const int count, const __u64 *const ids, const int *const keys); + void keysOld(const uint64_t currTime, const int keyCount, const int *const keys, const int bytes, const char *const buf); + void format(const uint64_t currTime, const int length, const char *const format); + void maps(const uint64_t currTime, const int pid, const int tid, const char *const maps); + void comm(const uint64_t currTime, const int pid, const int tid, const char *const image, const char *const comm); + void onlineCPU(const uint64_t currTime, const uint64_t time, const int cpu); + void offlineCPU(const uint64_t currTime, const uint64_t time, const int cpu); + void kallsyms(const uint64_t currTime, const char *const kallsyms); void setDone(); bool isDone() const; @@ -67,6 +68,7 @@ public: void advanceWrite(int bytes) { mWritePos = (mWritePos + bytes) & /*mask*/(mSize - 1); } static void packInt(char *const buf, const int size, int &writePos, int32_t x); void packInt(int32_t x); + static void packInt64(char *const buf, const int size, int &writePos, int64_t x); void packInt64(int64_t x); void writeBytes(const void *const data, size_t count); void writeString(const char *const str); @@ -79,20 +81,22 @@ public: } private: + void frame(); bool commitReady() const; bool checkSpace(int bytes); - const int32_t mCore; - const int32_t mBufType; + char *const mBuf; + sem_t *const mReaderSem; + uint64_t mCommitTime; + sem_t mWriterSem; const int mSize; int mReadPos; int mWritePos; int mCommitPos; bool mAvailable; bool mIsDone; - char *const mBuf; - uint64_t mCommitTime; - sem_t *const mReaderSem; + const int32_t mCore; + const int32_t mBufType; // Intentionally unimplemented Buffer(const Buffer &); diff --git a/tools/gator/daemon/CCNDriver.cpp b/tools/gator/daemon/CCNDriver.cpp new file mode 100644 index 000000000000..dd1a2b133842 --- /dev/null +++ b/tools/gator/daemon/CCNDriver.cpp @@ -0,0 +1,295 @@ +/** + * Copyright (C) ARM Limited 2014. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "CCNDriver.h" + +#include <unistd.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> + +#include "k/perf_event.h" + +#include "Config.h" +#include "DriverSource.h" +#include "Logging.h" + +static const char TAG_CATEGORY[] = "category"; +static const char TAG_COUNTER_SET[] = "counter_set"; +static const char TAG_EVENT[] = "event"; +static const char TAG_OPTION[] = "option"; +static const char TAG_OPTION_SET[] = "option_set"; + +static const char ATTR_AVERAGE_SELECTION[] = "average_selection"; +static const char ATTR_COUNTER[] = "counter"; +static const char ATTR_COUNTER_SET[] = "counter_set"; +static const char ATTR_COUNT[] = "count"; +static const char ATTR_DESCRIPTION[] = "description"; +static const char ATTR_DISPLAY[] = "display"; +static const char ATTR_EVENT[] = "event"; +static const char ATTR_EVENT_DELTA[] = "event_delta"; +static const char ATTR_NAME[] = "name"; +static const char ATTR_OPTION_SET[] = "option_set"; +static const char ATTR_TITLE[] = "title"; +static const char ATTR_UNITS[] = "units"; + +static const char XP_REGION[] = "XP_Region"; +static const char HNF_REGION[] = "HN-F_Region"; +static const char RNI_REGION[] = "RN-I_Region"; +static const char SBAS_REGION[] = "SBAS_Region"; +static const char CCN_5XX[] = "CCN-5xx"; +#define ARM_CCN_5XX "ARM_CCN_5XX_" + +static const char *const VC_TYPES[] = { "REQ", "RSP", "SNP", "DAT" }; +static const char *const XP_EVENT_NAMES[] = { NULL, "H-bit", "S-bit", "P-Cnt", "TknV" }; +static const char *const XP_EVENT_DESCRIPTIONS[] = { NULL, "Set H-bit, signaled when this XP sets the H-bit.", "Set S-bit, signaled when this XP sets the S-bit.", "Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC.", "No TknV, signaled when this XP transmits a valid packet." }; +static const char *const HNF_EVENT_NAMES[] = { NULL, "Cache Miss", "L3 SF Cache Access", "Cache Fill", "POCQ Retry", "POCQ Reqs Recvd", "SF Hit", "SF Evictions", "Snoops Sent", "Snoops Broadcast", "L3 Eviction", "L3 Fill Invalid Way", "MC Retries", "MC Reqs", "QOS HH Retry" }; +static const char *const HNF_EVENT_DESCRIPTIONS[] = { NULL, "Counts the total cache misses. This is the first time lookup result, and is high priority.", "Counts the number of cache accesses. This is the first time access, and is high priority.", "Counts the total allocations in the HN L3 cache, and all cache line allocations to the L3 cache.", "Counts the number of requests that have been retried.", "Counts the number of requests received by HN.", "Counts the number of snoop filter hits.", "Counts the number of snoop filter evictions. Cache invalidations are initiated.", "Counts the number of snoops sent. Does not differentiate between broadcast or directed snoops.", "Counts the number of snoop broadcasts sent.", "Counts the number of L3 evictions.", "Counts the number of L3 fills to an invalid way.", "Counts the number of transactions retried by the memory controller.", "Counts the number of requests to the memory controller.", "Counts the number of times a highest-priority QoS class was retried at the HN-F." }; +static const char *const RNI_EVENT_NAMES[] = { NULL, "S0 RDataBeats", "S1 RDataBeats", "S2 RDataBeats", "RXDAT Flits received", "TXDAT Flits sent", "Total TXREQ Flits sent", "Retried TXREQ Flits sent", "RRT full", "WRT full", "Replayed TXREQ Flits" }; +static const char *const RNI_EVENT_DESCRIPTIONS[] = { NULL, "S0 RDataBeats.", "S1 RDataBeats.", "S2 RDataBeats.", "RXDAT Flits received.", "TXDAT Flits sent.", "Total TXREQ Flits sent.", "Retried TXREQ Flits sent.", "RRT full.", "WRT full.", "Replayed TXREQ Flits." }; +static const char *const SBAS_EVENT_NAMES[] = { NULL, "S0 RDataBeats", NULL, NULL, "RXDAT Flits received", "TXDAT Flits sent", "Total TXREQ Flits sent", "Retried TXREQ Flits sent", "RRT full", "WRT full", "Replayed TXREQ Flits" }; +static const char *const SBAS_EVENT_DESCRIPTIONS[] = { NULL, "S0 RDataBeats.", NULL, NULL, "RXDAT Flits received.", "TXDAT Flits sent.", "Total TXREQ Flits sent.", "Retried TXREQ Flits sent.", "RRT full.", "WRT full.", "Replayed TXREQ Flits." }; + +// This class is used only to poll for CCN-5xx configuration and emit events XML for it. All other operations are handled by PerfDriver + +static int sys_perf_event_open(struct perf_event_attr *const attr, const pid_t pid, const int cpu, const int group_fd, const unsigned long flags) { + return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags); +} + +static unsigned int getConfig(unsigned int node, unsigned int type, unsigned int event, unsigned int port, unsigned int vc) { + return + ((node & 0xff) << 0) | + ((type & 0xff) << 8) | + ((event & 0xff) << 16) | + ((port & 0x03) << 24) | + ((vc & 0x07) << 26) | + 0; +} + +static bool perfPoll(struct perf_event_attr *const pea) { + int fd = sys_perf_event_open(pea, -1, 0, -1, 0); + if (fd < 0) { + return false; + } + close(fd); + return true; +} + +CCNDriver::CCNDriver() : mNodeTypes(NULL), mXpCount(0) { +} + +CCNDriver::~CCNDriver() { + delete mNodeTypes; +} + +bool CCNDriver::claimCounter(const Counter &) const { + // Handled by PerfDriver + return false; +} + +void CCNDriver::resetCounters() { + // Handled by PerfDriver +} + +void CCNDriver::setupCounter(Counter &) { + // Handled by PerfDriver +} + +void CCNDriver::readEvents(mxml_node_t *const) { + struct stat st; + if (stat("/sys/bus/event_source/devices/ccn", &st) != 0) { + // Not found + return; + } + + int type; + if (DriverSource::readIntDriver("/sys/bus/event_source/devices/ccn/type", &type) != 0) { + logg->logError(__FILE__, __LINE__, "Unable to read CCN-5xx type"); + handleException(); + } + + // Detect number of xps + struct perf_event_attr pea; + memset(&pea, 0, sizeof(pea)); + pea.type = type; + pea.size = sizeof(pea); + + mXpCount = 1; + while (true) { + pea.config = getConfig(0, 0x08, 1, 0, 1) | mXpCount; + if (!perfPoll(&pea)) { + break; + } + mXpCount *= 2; + }; + { + int lower = mXpCount/2 + 1; + while (lower < mXpCount) { + int mid = (lower + mXpCount)/2; + pea.config = getConfig(0, 0x08, 1, 0, 1) | mid; + if (perfPoll(&pea)) { + lower = mid + 1; + } else { + mXpCount = mid; + } + } + } + + mNodeTypes = new NodeType[2*mXpCount]; + + // Detect node types + for (int i = 0; i < 2*mXpCount; ++i) { + pea.config = getConfig(0, 0x04, 1, 0, 0) | i; + if (perfPoll(&pea)) { + mNodeTypes[i] = NT_HNF; + continue; + } + + pea.config = getConfig(0, 0x16, 1, 0, 0) | i; + if (perfPoll(&pea)) { + mNodeTypes[i] = NT_RNI; + continue; + } + + pea.config = getConfig(0, 0x10, 1, 0, 0) | i; + if (perfPoll(&pea)) { + mNodeTypes[i] = NT_SBAS; + continue; + } + + mNodeTypes[i] = NT_UNKNOWN; + } +} + +int CCNDriver::writeCounters(mxml_node_t *const) const { + // Handled by PerfDriver + return 0; +} + +void CCNDriver::writeEvents(mxml_node_t *const root) const { + mxml_node_t *const counter_set = mxmlNewElement(root, TAG_COUNTER_SET); + mxmlElementSetAttr(counter_set, ATTR_NAME, ARM_CCN_5XX "cnt"); + mxmlElementSetAttr(counter_set, ATTR_COUNT, "8"); + + mxml_node_t *const category = mxmlNewElement(root, TAG_CATEGORY); + mxmlElementSetAttr(category, ATTR_NAME, CCN_5XX); + mxmlElementSetAttr(category, TAG_COUNTER_SET, ARM_CCN_5XX "cnt"); + + mxml_node_t *const clock_event = mxmlNewElement(category, TAG_EVENT); + mxmlElementSetAttr(clock_event, ATTR_COUNTER, ARM_CCN_5XX "ccnt"); + mxmlElementSetAttr(clock_event, ATTR_EVENT, "0xff00"); + mxmlElementSetAttr(clock_event, ATTR_TITLE, "CCN-5xx Clock"); + mxmlElementSetAttr(clock_event, ATTR_NAME, "Cycles"); + mxmlElementSetAttr(clock_event, ATTR_DISPLAY, "hertz"); + mxmlElementSetAttr(clock_event, ATTR_UNITS, "Hz"); + mxmlElementSetAttr(clock_event, ATTR_AVERAGE_SELECTION, "yes"); + mxmlElementSetAttr(clock_event, ATTR_DESCRIPTION, "The number of core clock cycles"); + + mxml_node_t *const xp_option_set = mxmlNewElement(category, TAG_OPTION_SET); + mxmlElementSetAttr(xp_option_set, ATTR_NAME, XP_REGION); + + for (int i = 0; i < mXpCount; ++i) { + mxml_node_t *const option = mxmlNewElement(xp_option_set, TAG_OPTION); + mxmlElementSetAttrf(option, ATTR_EVENT_DELTA, "0x%x", getConfig(i, 0, 0, 0, 0)); + mxmlElementSetAttrf(option, ATTR_NAME, "XP %i", i); + mxmlElementSetAttrf(option, ATTR_DESCRIPTION, "Crosspoint %i", i); + } + + for (int vc = 0; vc < ARRAY_LENGTH(VC_TYPES); ++vc) { + if (VC_TYPES[vc] == NULL) { + continue; + } + for (int bus = 0; bus < 2; ++bus) { + for (int eventId = 0; eventId < ARRAY_LENGTH(XP_EVENT_NAMES); ++eventId) { + if (XP_EVENT_NAMES[eventId] == NULL) { + continue; + } + mxml_node_t *const event = mxmlNewElement(category, TAG_EVENT); + mxmlElementSetAttrf(event, ATTR_EVENT, "0x%x", getConfig(0, 0x08, eventId, bus, vc)); + mxmlElementSetAttr(event, ATTR_OPTION_SET, XP_REGION); + mxmlElementSetAttr(event, ATTR_TITLE, CCN_5XX); + mxmlElementSetAttrf(event, ATTR_NAME, "Bus %i: %s: %s", bus, VC_TYPES[vc], XP_EVENT_NAMES[eventId]); + mxmlElementSetAttrf(event, ATTR_DESCRIPTION, "Bus %i: %s: %s", bus, VC_TYPES[vc], XP_EVENT_DESCRIPTIONS[eventId]); + } + } + } + + mxml_node_t *const hnf_option_set = mxmlNewElement(category, TAG_OPTION_SET); + mxmlElementSetAttr(hnf_option_set, ATTR_NAME, HNF_REGION); + + for (int eventId = 0; eventId < ARRAY_LENGTH(HNF_EVENT_NAMES); ++eventId) { + if (HNF_EVENT_NAMES[eventId] == NULL) { + continue; + } + mxml_node_t *const event = mxmlNewElement(category, TAG_EVENT); + mxmlElementSetAttrf(event, ATTR_EVENT, "0x%x", getConfig(0, 0x04, eventId, 0, 0)); + mxmlElementSetAttr(event, ATTR_OPTION_SET, HNF_REGION); + mxmlElementSetAttr(event, ATTR_TITLE, CCN_5XX); + mxmlElementSetAttr(event, ATTR_NAME, HNF_EVENT_NAMES[eventId]); + mxmlElementSetAttr(event, ATTR_DESCRIPTION, HNF_EVENT_DESCRIPTIONS[eventId]); + } + + mxml_node_t *const rni_option_set = mxmlNewElement(category, TAG_OPTION_SET); + mxmlElementSetAttr(rni_option_set, ATTR_NAME, RNI_REGION); + + for (int eventId = 0; eventId < ARRAY_LENGTH(RNI_EVENT_NAMES); ++eventId) { + if (RNI_EVENT_NAMES[eventId] == NULL) { + continue; + } + mxml_node_t *const event = mxmlNewElement(category, TAG_EVENT); + mxmlElementSetAttrf(event, ATTR_EVENT, "0x%x", getConfig(0, 0x16, eventId, 0, 0)); + mxmlElementSetAttr(event, ATTR_OPTION_SET, RNI_REGION); + mxmlElementSetAttr(event, ATTR_TITLE, CCN_5XX); + mxmlElementSetAttr(event, ATTR_NAME, RNI_EVENT_NAMES[eventId]); + mxmlElementSetAttr(event, ATTR_DESCRIPTION, RNI_EVENT_DESCRIPTIONS[eventId]); + } + + mxml_node_t *const sbas_option_set = mxmlNewElement(category, TAG_OPTION_SET); + mxmlElementSetAttr(sbas_option_set, ATTR_NAME, SBAS_REGION); + + for (int eventId = 0; eventId < ARRAY_LENGTH(SBAS_EVENT_NAMES); ++eventId) { + if (SBAS_EVENT_NAMES[eventId] == NULL) { + continue; + } + mxml_node_t *const event = mxmlNewElement(category, TAG_EVENT); + mxmlElementSetAttrf(event, ATTR_EVENT, "0x%x", getConfig(0, 0x10, eventId, 0, 0)); + mxmlElementSetAttr(event, ATTR_OPTION_SET, SBAS_REGION); + mxmlElementSetAttr(event, ATTR_TITLE, CCN_5XX); + mxmlElementSetAttr(event, ATTR_NAME, SBAS_EVENT_NAMES[eventId]); + mxmlElementSetAttr(event, ATTR_DESCRIPTION, SBAS_EVENT_DESCRIPTIONS[eventId]); + } + + for (int i = 0; i < 2*mXpCount; ++i) { + switch (mNodeTypes[i]) { + case NT_HNF: { + mxml_node_t *const option = mxmlNewElement(hnf_option_set, TAG_OPTION); + mxmlElementSetAttrf(option, ATTR_EVENT_DELTA, "0x%x", getConfig(i, 0, 0, 0, 0)); + mxmlElementSetAttrf(option, ATTR_NAME, "HN-F %i", i); + mxmlElementSetAttrf(option, ATTR_DESCRIPTION, "Fully-coherent Home Node %i", i); + break; + } + case NT_RNI: { + mxml_node_t *const option = mxmlNewElement(rni_option_set, TAG_OPTION); + mxmlElementSetAttrf(option, ATTR_EVENT_DELTA, "0x%x", getConfig(i, 0, 0, 0, 0)); + mxmlElementSetAttrf(option, ATTR_NAME, "RN-I %i", i); + mxmlElementSetAttrf(option, ATTR_DESCRIPTION, "I/O-coherent Requesting Node %i", i); + break; + } + case NT_SBAS: { + mxml_node_t *const option = mxmlNewElement(sbas_option_set, TAG_OPTION); + mxmlElementSetAttrf(option, ATTR_EVENT_DELTA, "0x%x", getConfig(i, 0, 0, 0, 0)); + mxmlElementSetAttrf(option, ATTR_NAME, "SBAS %i", i); + mxmlElementSetAttrf(option, ATTR_DESCRIPTION, "ACE master to CHI protocol bridge %i", i); + break; + } + default: + continue; + } + } +} diff --git a/tools/gator/daemon/CCNDriver.h b/tools/gator/daemon/CCNDriver.h new file mode 100644 index 000000000000..fb4c717e969a --- /dev/null +++ b/tools/gator/daemon/CCNDriver.h @@ -0,0 +1,43 @@ +/** + * Copyright (C) ARM Limited 2014. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef CCNDRIVER_H +#define CCNDRIVER_H + +#include "Driver.h" + +class CCNDriver : public Driver { +public: + CCNDriver(); + ~CCNDriver(); + + bool claimCounter(const Counter &counter) const; + void resetCounters(); + void setupCounter(Counter &counter); + + void readEvents(mxml_node_t *const); + int writeCounters(mxml_node_t *const root) const; + void writeEvents(mxml_node_t *const) const; + +private: + enum NodeType { + NT_UNKNOWN, + NT_HNF, + NT_RNI, + NT_SBAS, + }; + + NodeType *mNodeTypes; + int mXpCount; + + // Intentionally unimplemented + CCNDriver(const CCNDriver &); + CCNDriver &operator=(const CCNDriver &); +}; + +#endif // CCNDRIVER_H diff --git a/tools/gator/daemon/CPUFreqDriver.cpp b/tools/gator/daemon/CPUFreqDriver.cpp new file mode 100644 index 000000000000..41f9d6f2b3f4 --- /dev/null +++ b/tools/gator/daemon/CPUFreqDriver.cpp @@ -0,0 +1,58 @@ +/** + * Copyright (C) ARM Limited 2013-2014. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "CPUFreqDriver.h" + +#include "Buffer.h" +#include "DriverSource.h" +#include "Logging.h" +#include "SessionData.h" + +CPUFreqDriver::CPUFreqDriver() : mPrev() { +} + +CPUFreqDriver::~CPUFreqDriver() { +} + +void CPUFreqDriver::readEvents(mxml_node_t *const) { + // Only for use with perf + if (!gSessionData->perf.isSetup()) { + return; + } + + setCounters(new DriverCounter(getCounters(), strdup("Linux_power_cpu_freq"))); +} + +void CPUFreqDriver::read(Buffer *const buffer) { + char buf[64]; + const DriverCounter *const counter = getCounters(); + if ((counter == NULL) || !counter->isEnabled()) { + return; + } + + const int key = getCounters()->getKey(); + bool resetCores = false; + for (int i = 0; i < gSessionData->mCores; ++i) { + snprintf(buf, sizeof(buf), "/sys/devices/system/cpu/cpu%i/cpufreq/cpuinfo_cur_freq", i); + int64_t freq; + if (DriverSource::readInt64Driver(buf, &freq) != 0) { + freq = 0; + } + if (mPrev[i] != freq) { + mPrev[i] = freq; + // Change cores + buffer->event64(2, i); + resetCores = true; + buffer->event64(key, 1000*freq); + } + } + if (resetCores) { + // Revert cores, UserSpaceSource is all on core 0 + buffer->event64(2, 0); + } +} diff --git a/tools/gator/daemon/CPUFreqDriver.h b/tools/gator/daemon/CPUFreqDriver.h new file mode 100644 index 000000000000..ad8c9aaa9e7d --- /dev/null +++ b/tools/gator/daemon/CPUFreqDriver.h @@ -0,0 +1,34 @@ +/** + * Copyright (C) ARM Limited 2013-2014. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef CPUFREQDRIVER_H +#define CPUFREQDRIVER_H + +#include "Config.h" +#include "Driver.h" + +class CPUFreqDriver : public PolledDriver { +private: + typedef PolledDriver super; + +public: + CPUFreqDriver(); + ~CPUFreqDriver(); + + void readEvents(mxml_node_t *const root); + void read(Buffer *const buffer); + +private: + int64_t mPrev[NR_CPUS]; + + // Intentionally unimplemented + CPUFreqDriver(const CPUFreqDriver &); + CPUFreqDriver &operator=(const CPUFreqDriver &); +}; + +#endif // CPUFREQDRIVER_H diff --git a/tools/gator/daemon/CapturedXML.cpp b/tools/gator/daemon/CapturedXML.cpp index 4a11415a00c9..0b5802c893bb 100644 --- a/tools/gator/daemon/CapturedXML.cpp +++ b/tools/gator/daemon/CapturedXML.cpp @@ -34,6 +34,7 @@ mxml_node_t* CapturedXML::getTree(bool includeTime) { mxmlElementSetAttr(captured, "version", "1"); if (gSessionData->perf.isSetup()) { mxmlElementSetAttr(captured, "type", "Perf"); + mxmlElementSetAttr(captured, "perf_beta", "yes"); } mxmlElementSetAttrf(captured, "protocol", "%d", PROTOCOL_VERSION); if (includeTime) { // Send the following only after the capture is complete @@ -113,32 +114,32 @@ const char * mxmlWhitespaceCB(mxml_node_t *node, int loc) { if (loc == MXML_WS_BEFORE_OPEN) { // Single indentation if (!strcmp(name, "target") || !strcmp(name, "counters")) - return("\n "); + return "\n "; // Double indentation if (!strcmp(name, "counter")) - return("\n "); + return "\n "; // Avoid a carriage return on the first line of the xml file if (!strncmp(name, "?xml", 4)) - return(NULL); + return NULL; // Default - no indentation - return("\n"); + return "\n"; } if (loc == MXML_WS_BEFORE_CLOSE) { // No indentation if (!strcmp(name, "captured")) - return("\n"); + return "\n"; // Single indentation if (!strcmp(name, "counters")) - return("\n "); + return "\n "; // Default - no carriage return - return(NULL); + return NULL; } - return(NULL); + return NULL; } diff --git a/tools/gator/daemon/CapturedXML.h b/tools/gator/daemon/CapturedXML.h index ed08c44bc3ff..b704f6e53bb5 100644 --- a/tools/gator/daemon/CapturedXML.h +++ b/tools/gator/daemon/CapturedXML.h @@ -6,8 +6,8 @@ * published by the Free Software Foundation. */ -#ifndef __CAPTURED_XML_H__ -#define __CAPTURED_XML_H__ +#ifndef __CAPTURED_XML_H__ +#define __CAPTURED_XML_H__ #include "mxml/mxml.h" diff --git a/tools/gator/daemon/Child.cpp b/tools/gator/daemon/Child.cpp index 1901ecc6a724..6b5bbb3bf6af 100644 --- a/tools/gator/daemon/Child.cpp +++ b/tools/gator/daemon/Child.cpp @@ -14,25 +14,28 @@ #include <unistd.h> #include <sys/prctl.h> -#include "Logging.h" #include "CapturedXML.h" -#include "SessionData.h" -#include "LocalCapture.h" -#include "Sender.h" -#include "OlyUtility.h" -#include "OlySocket.h" -#include "StreamlineSetup.h" +#include "Command.h" #include "ConfigurationXML.h" #include "Driver.h" -#include "PerfSource.h" #include "DriverSource.h" #include "ExternalSource.h" +#include "FtraceSource.h" +#include "LocalCapture.h" +#include "Logging.h" +#include "OlySocket.h" +#include "OlyUtility.h" +#include "PerfSource.h" +#include "Sender.h" +#include "SessionData.h" +#include "StreamlineSetup.h" #include "UserSpaceSource.h" static sem_t haltPipeline, senderThreadStarted, startProfile, senderSem; // Shared by Child and spawned threads static Source *primarySource = NULL; static Source *externalSource = NULL; static Source *userSpaceSource = NULL; +static Source *ftraceSource = NULL; static Sender* sender = NULL; // Shared by Child.cpp and spawned threads Child* child = NULL; // shared by Child.cpp and main.cpp @@ -149,7 +152,8 @@ static void *senderThread(void *) { while (!primarySource->isDone() || !externalSource->isDone() || - (userSpaceSource != NULL && !userSpaceSource->isDone())) { + (userSpaceSource != NULL && !userSpaceSource->isDone()) || + (ftraceSource != NULL && !ftraceSource->isDone())) { sem_wait(&senderSem); primarySource->write(sender); @@ -157,6 +161,9 @@ static void *senderThread(void *) { if (userSpaceSource != NULL) { userSpaceSource->write(sender); } + if (ftraceSource != NULL) { + ftraceSource->write(sender); + } } // write end-of-capture sequence @@ -206,6 +213,9 @@ void Child::endSession() { if (userSpaceSource != NULL) { userSpaceSource->interrupt(); } + if (ftraceSource != NULL) { + ftraceSource->interrupt(); + } sem_post(&haltPipeline); } @@ -269,15 +279,32 @@ void Child::run() { free(xmlString); } + if (gSessionData->kmod.isMaliCapture() && (gSessionData->mSampleRate == 0)) { + logg->logError(__FILE__, __LINE__, "Mali counters are not supported with Sample Rate: None."); + handleException(); + } + // Must be after session XML is parsed if (!primarySource->prepare()) { - logg->logError(__FILE__, __LINE__, "Unable to prepare for capture"); + if (gSessionData->perf.isSetup()) { + logg->logError(__FILE__, __LINE__, "Unable to prepare gator driver for capture"); + } else { + logg->logError(__FILE__, __LINE__, "Unable to communicate with the perf API, please ensure that CONFIG_TRACING and CONFIG_CONTEXT_SWITCH_TRACER are enabled. Please refer to README_Streamline.txt for more information."); + } handleException(); } // Sender thread shall be halted until it is signaled for one shot mode sem_init(&haltPipeline, 0, gSessionData->mOneShot ? 0 : 2); + // Must be initialized before senderThread is started as senderThread checks externalSource + externalSource = new ExternalSource(&senderSem); + if (!externalSource->prepare()) { + logg->logError(__FILE__, __LINE__, "Unable to prepare external source for capture"); + handleException(); + } + externalSource->start(); + // Create the duration, stop, and sender threads bool thread_creation_success = true; if (gSessionData->mDuration > 0 && pthread_create(&durationThreadID, NULL, durationThread, NULL)) { @@ -288,22 +315,37 @@ void Child::run() { thread_creation_success = false; } - externalSource = new ExternalSource(&senderSem); - if (!externalSource->prepare()) { - logg->logError(__FILE__, __LINE__, "Unable to prepare for capture"); - handleException(); + bool startUSSource = false; + for (int i = 0; i < ARRAY_LENGTH(gSessionData->usDrivers); ++i) { + if (gSessionData->usDrivers[i]->countersEnabled()) { + startUSSource = true; + } } - externalSource->start(); - - if (gSessionData->hwmon.countersEnabled() || gSessionData->fsDriver.countersEnabled()) { + if (startUSSource) { userSpaceSource = new UserSpaceSource(&senderSem); if (!userSpaceSource->prepare()) { - logg->logError(__FILE__, __LINE__, "Unable to prepare for capture"); + logg->logError(__FILE__, __LINE__, "Unable to prepare userspace source for capture"); handleException(); } userSpaceSource->start(); } + if (gSessionData->ftraceDriver.countersEnabled()) { + ftraceSource = new FtraceSource(&senderSem); + if (!ftraceSource->prepare()) { + logg->logError(__FILE__, __LINE__, "Unable to prepare userspace source for capture"); + handleException(); + } + ftraceSource->start(); + } + + if (gSessionData->mAllowCommands && (gSessionData->mCaptureCommand != NULL)) { + pthread_t thread; + if (pthread_create(&thread, NULL, commandThread, NULL)) { + thread_creation_success = false; + } + } + if (!thread_creation_success) { logg->logError(__FILE__, __LINE__, "Failed to create gator threads"); handleException(); @@ -315,6 +357,9 @@ void Child::run() { // Start profiling primarySource->run(); + if (ftraceSource != NULL) { + ftraceSource->join(); + } if (userSpaceSource != NULL) { userSpaceSource->join(); } @@ -338,6 +383,7 @@ void Child::run() { logg->logMessage("Profiling ended."); + delete ftraceSource; delete userSpaceSource; delete externalSource; delete primarySource; diff --git a/tools/gator/daemon/Child.h b/tools/gator/daemon/Child.h index a306a7760819..cc78202ceb5c 100644 --- a/tools/gator/daemon/Child.h +++ b/tools/gator/daemon/Child.h @@ -6,8 +6,8 @@ * published by the Free Software Foundation. */ -#ifndef __CHILD_H__ -#define __CHILD_H__ +#ifndef __CHILD_H__ +#define __CHILD_H__ class OlySocket; diff --git a/tools/gator/daemon/Command.cpp b/tools/gator/daemon/Command.cpp new file mode 100644 index 000000000000..28d73cf5a905 --- /dev/null +++ b/tools/gator/daemon/Command.cpp @@ -0,0 +1,172 @@ +/** + * Copyright (C) ARM Limited 2014. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "Command.h" + +#include <fcntl.h> +#include <pwd.h> +#include <stdio.h> +#include <sys/prctl.h> +#include <sys/resource.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <sys/time.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "Logging.h" +#include "SessionData.h" + +static int getUid(const char *const name, char *const shPath, const char *const tmpDir) { + // Lookups may fail when using a different libc or a statically compiled executable + char gatorTemp[32]; + snprintf(gatorTemp, sizeof(gatorTemp), "%s/gator_temp", tmpDir); + + const int fd = open(gatorTemp, 600, O_CREAT | O_CLOEXEC); + if (fd < 0) { + return -1; + } + close(fd); + + char cmd[128]; + snprintf(cmd, sizeof(cmd), "chown %s %s || rm %s", name, gatorTemp, gatorTemp); + + const int pid = fork(); + if (pid < 0) { + logg->logError(__FILE__, __LINE__, "fork failed"); + handleException(); + } + if (pid == 0) { + char cargv1[] = "-c"; + char *cargv[] = { + shPath, + cargv1, + cmd, + NULL, + }; + + execv(cargv[0], cargv); + exit(-1); + } + while ((waitpid(pid, NULL, 0) < 0) && (errno == EINTR)); + + struct stat st; + int result = -1; + if (stat(gatorTemp, &st) == 0) { + result = st.st_uid; + } + unlink(gatorTemp); + return result; +} + +static int getUid(const char *const name) { + // Look up the username + struct passwd *const user = getpwnam(name); + if (user != NULL) { + return user->pw_uid; + } + + + // Are we on Linux + char cargv0l[] = "/bin/sh"; + if ((access(cargv0l, X_OK) == 0) && (access("/tmp", W_OK) == 0)) { + return getUid(name, cargv0l, "/tmp"); + } + + // Are we on android + char cargv0a[] = "/system/bin/sh"; + if ((access(cargv0a, X_OK) == 0) && (access("/data", W_OK) == 0)) { + return getUid(name, cargv0a, "/data"); + } + + return -1; +} + +void *commandThread(void *) { + prctl(PR_SET_NAME, (unsigned long)&"gatord-command", 0, 0, 0); + + const char *const name = gSessionData->mCaptureUser == NULL ? "nobody" : gSessionData->mCaptureUser; + const int uid = getUid(name); + if (uid < 0) { + logg->logError(__FILE__, __LINE__, "Unable to lookup the user %s, please double check that the user exists", name); + handleException(); + } + + sleep(3); + + char buf[128]; + int pipefd[2]; + if (pipe_cloexec(pipefd) != 0) { + logg->logError(__FILE__, __LINE__, "pipe failed"); + handleException(); + } + + const int pid = fork(); + if (pid < 0) { + logg->logError(__FILE__, __LINE__, "fork failed"); + handleException(); + } + if (pid == 0) { + char cargv0l[] = "/bin/sh"; + char cargv0a[] = "/system/bin/sh"; + char cargv1[] = "-c"; + char *cargv[] = { + cargv0l, + cargv1, + gSessionData->mCaptureCommand, + NULL, + }; + + buf[0] = '\0'; + close(pipefd[0]); + + // Gator runs at a high priority, reset the priority to the default + if (setpriority(PRIO_PROCESS, syscall(__NR_gettid), 0) == -1) { + snprintf(buf, sizeof(buf), "setpriority failed"); + goto fail_exit; + } + + if (setuid(uid) != 0) { + snprintf(buf, sizeof(buf), "setuid failed"); + goto fail_exit; + } + + { + const char *const path = gSessionData->mCaptureWorkingDir == NULL ? "/" : gSessionData->mCaptureWorkingDir; + if (chdir(path) != 0) { + snprintf(buf, sizeof(buf), "Unable to cd to %s, please verify the directory exists and is accessable to %s", path, name); + goto fail_exit; + } + } + + execv(cargv[0], cargv); + cargv[0] = cargv0a; + execv(cargv[0], cargv); + snprintf(buf, sizeof(buf), "execv failed"); + + fail_exit: + if (buf[0] != '\0') { + const ssize_t bytes = write(pipefd[1], buf, sizeof(buf)); + // Can't do anything if this fails + (void)bytes; + } + + exit(-1); + } + + close(pipefd[1]); + const ssize_t bytes = read(pipefd[0], buf, sizeof(buf)); + if (bytes > 0) { + logg->logError(__FILE__, __LINE__, buf); + handleException(); + } + close(pipefd[0]); + + return NULL; +} diff --git a/tools/gator/daemon/Command.h b/tools/gator/daemon/Command.h new file mode 100644 index 000000000000..17244b7aaebc --- /dev/null +++ b/tools/gator/daemon/Command.h @@ -0,0 +1,14 @@ +/** + * Copyright (C) ARM Limited 2014. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef COMMAND_H +#define COMMAND_H + +void *commandThread(void *); + +#endif // COMMAND_H diff --git a/tools/gator/daemon/Config.h b/tools/gator/daemon/Config.h index 6f5e2aae50e1..bee383a1c797 100644 --- a/tools/gator/daemon/Config.h +++ b/tools/gator/daemon/Config.h @@ -10,8 +10,19 @@ #define CONFIG_H #define ARRAY_LENGTH(A) static_cast<int>(sizeof(A)/sizeof((A)[0])) +#define ACCESS_ONCE(x) (*(volatile typeof(x)*)&(x)) #define MAX_PERFORMANCE_COUNTERS 50 -#define NR_CPUS 16 +#define NR_CPUS 32 + +template<typename T> +static inline T min(const T a, const T b) { + return (a < b ? a : b); +} + +template<typename T> +static inline T max(const T a, const T b) { + return (a > b ? a : b); +} #endif // CONFIG_H diff --git a/tools/gator/daemon/DiskIODriver.cpp b/tools/gator/daemon/DiskIODriver.cpp new file mode 100644 index 000000000000..5deb0f375f3a --- /dev/null +++ b/tools/gator/daemon/DiskIODriver.cpp @@ -0,0 +1,125 @@ +/** + * Copyright (C) ARM Limited 2013-2014. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +// Define to get format macros from inttypes.h +#define __STDC_FORMAT_MACROS + +#include "DiskIODriver.h" + +#include <inttypes.h> + +#include "Logging.h" +#include "SessionData.h" + +class DiskIOCounter : public DriverCounter { +public: + DiskIOCounter(DriverCounter *next, char *const name, int64_t *const value); + ~DiskIOCounter(); + + int64_t read(); + +private: + int64_t *const mValue; + int64_t mPrev; + + // Intentionally unimplemented + DiskIOCounter(const DiskIOCounter &); + DiskIOCounter &operator=(const DiskIOCounter &); +}; + +DiskIOCounter::DiskIOCounter(DriverCounter *next, char *const name, int64_t *const value) : DriverCounter(next, name), mValue(value), mPrev(0) { +} + +DiskIOCounter::~DiskIOCounter() { +} + +int64_t DiskIOCounter::read() { + int64_t result = *mValue - mPrev; + mPrev = *mValue; + // Kernel assumes a sector is 512 bytes + return result << 9; +} + +DiskIODriver::DiskIODriver() : mBuf(), mReadBytes(0), mWriteBytes(0) { +} + +DiskIODriver::~DiskIODriver() { +} + +void DiskIODriver::readEvents(mxml_node_t *const) { + // Only for use with perf + if (!gSessionData->perf.isSetup()) { + return; + } + + setCounters(new DiskIOCounter(getCounters(), strdup("Linux_block_rq_rd"), &mReadBytes)); + setCounters(new DiskIOCounter(getCounters(), strdup("Linux_block_rq_wr"), &mWriteBytes)); +} + +void DiskIODriver::doRead() { + if (!countersEnabled()) { + return; + } + + if (!mBuf.read("/proc/diskstats")) { + logg->logError(__FILE__, __LINE__, "Unable to read /proc/diskstats"); + handleException(); + } + + mReadBytes = 0; + mWriteBytes = 0; + + char *lastName = NULL; + int lastNameLen = -1; + char *start = mBuf.getBuf(); + while (*start != '\0') { + char *end = strchr(start, '\n'); + if (end != NULL) { + *end = '\0'; + } + + int nameStart = -1; + int nameEnd = -1; + int64_t readBytes = -1; + int64_t writeBytes = -1; + const int count = sscanf(start, "%*d %*d %n%*s%n %*u %*u %" SCNu64 " %*u %*u %*u %" SCNu64, &nameStart, &nameEnd, &readBytes, &writeBytes); + if (count != 2) { + logg->logError(__FILE__, __LINE__, "Unable to parse /proc/diskstats"); + handleException(); + } + + // Skip partitions which are identified if the name is a substring of the last non-partition + if ((lastName == NULL) || (strncmp(lastName, start + nameStart, lastNameLen) != 0)) { + lastName = start + nameStart; + lastNameLen = nameEnd - nameStart; + mReadBytes += readBytes; + mWriteBytes += writeBytes; + } + + if (end == NULL) { + break; + } + start = end + 1; + } +} + +void DiskIODriver::start() { + doRead(); + // Initialize previous values + for (DriverCounter *counter = getCounters(); counter != NULL; counter = counter->getNext()) { + if (!counter->isEnabled()) { + continue; + } + counter->read(); + } +} + +void DiskIODriver::read(Buffer *const buffer) { + doRead(); + super::read(buffer); +} diff --git a/tools/gator/daemon/DiskIODriver.h b/tools/gator/daemon/DiskIODriver.h new file mode 100644 index 000000000000..d0db18c77d04 --- /dev/null +++ b/tools/gator/daemon/DiskIODriver.h @@ -0,0 +1,39 @@ +/** + * Copyright (C) ARM Limited 2013-2014. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef DISKIODRIVER_H +#define DISKIODRIVER_H + +#include "Driver.h" +#include "DynBuf.h" + +class DiskIODriver : public PolledDriver { +private: + typedef PolledDriver super; + +public: + DiskIODriver(); + ~DiskIODriver(); + + void readEvents(mxml_node_t *const root); + void start(); + void read(Buffer *const buffer); + +private: + void doRead(); + + DynBuf mBuf; + int64_t mReadBytes; + int64_t mWriteBytes; + + // Intentionally unimplemented + DiskIODriver(const DiskIODriver &); + DiskIODriver &operator=(const DiskIODriver &); +}; + +#endif // DISKIODRIVER_H diff --git a/tools/gator/daemon/Driver.cpp b/tools/gator/daemon/Driver.cpp index 09e040162912..275da31c7a0d 100644 --- a/tools/gator/daemon/Driver.cpp +++ b/tools/gator/daemon/Driver.cpp @@ -8,8 +8,89 @@ #include "Driver.h" +#include "Buffer.h" +#include "SessionData.h" + +DriverCounter::DriverCounter(DriverCounter *const next, const char *const name) : mNext(next), mName(name), mKey(getEventKey()), mEnabled(false) { +} + +DriverCounter::~DriverCounter() { + delete mName; +} + Driver *Driver::head = NULL; Driver::Driver() : next(head) { head = this; } + +SimpleDriver::~SimpleDriver() { + DriverCounter *counters = mCounters; + while (counters != NULL) { + DriverCounter *counter = counters; + counters = counter->getNext(); + delete counter; + } +} + +DriverCounter *SimpleDriver::findCounter(const Counter &counter) const { + for (DriverCounter *driverCounter = mCounters; driverCounter != NULL; driverCounter = driverCounter->getNext()) { + if (strcmp(driverCounter->getName(), counter.getType()) == 0) { + return driverCounter; + } + } + + return NULL; +} + +bool SimpleDriver::claimCounter(const Counter &counter) const { + return findCounter(counter) != NULL; +} + +bool SimpleDriver::countersEnabled() const { + for (DriverCounter *counter = mCounters; counter != NULL; counter = counter->getNext()) { + if (counter->isEnabled()) { + return true; + } + } + return false; +} + +void SimpleDriver::resetCounters() { + for (DriverCounter *counter = mCounters; counter != NULL; counter = counter->getNext()) { + counter->setEnabled(false); + } +} + +void SimpleDriver::setupCounter(Counter &counter) { + DriverCounter *const driverCounter = findCounter(counter); + if (driverCounter == NULL) { + counter.setEnabled(false); + return; + } + driverCounter->setEnabled(true); + counter.setKey(driverCounter->getKey()); +} + +int SimpleDriver::writeCounters(mxml_node_t *root) const { + int count = 0; + for (DriverCounter *counter = mCounters; counter != NULL; counter = counter->getNext()) { + mxml_node_t *node = mxmlNewElement(root, "counter"); + mxmlElementSetAttr(node, "name", counter->getName()); + ++count; + } + + return count; +} + +PolledDriver::~PolledDriver() { +} + +void PolledDriver::read(Buffer *const buffer) { + for (DriverCounter *counter = getCounters(); counter != NULL; counter = counter->getNext()) { + if (!counter->isEnabled()) { + continue; + } + buffer->event64(counter->getKey(), counter->read()); + } +} diff --git a/tools/gator/daemon/Driver.h b/tools/gator/daemon/Driver.h index e5ed7b6c1295..72870e3dbca1 100644 --- a/tools/gator/daemon/Driver.h +++ b/tools/gator/daemon/Driver.h @@ -9,10 +9,36 @@ #ifndef DRIVER_H #define DRIVER_H +#include <stdint.h> + #include "mxml/mxml.h" +class Buffer; class Counter; +class DriverCounter { +public: + DriverCounter(DriverCounter *const next, const char *const name); + virtual ~DriverCounter(); + + DriverCounter *getNext() const { return mNext; } + const char *getName() const { return mName; } + int getKey() const { return mKey; } + bool isEnabled() const { return mEnabled; } + void setEnabled(const bool enabled) { mEnabled = enabled; } + virtual int64_t read() { return -1; } + +private: + DriverCounter *const mNext; + const char *const mName; + const int mKey; + bool mEnabled; + + // Intentionally unimplemented + DriverCounter(const DriverCounter &); + DriverCounter &operator=(const DriverCounter &); +}; + class Driver { public: static Driver *getHead() { return head; } @@ -26,15 +52,17 @@ public: // Enables and prepares the counter for capture virtual void setupCounter(Counter &counter) = 0; + // Performs any actions needed for setup or based on eventsXML + virtual void readEvents(mxml_node_t *const) {} // Emits available counters - virtual int writeCounters(mxml_node_t *root) const = 0; + virtual int writeCounters(mxml_node_t *const root) const = 0; // Emits possible dynamically generated events/counters - virtual void writeEvents(mxml_node_t *) const {} + virtual void writeEvents(mxml_node_t *const) const {} Driver *getNext() const { return next; } protected: - Driver (); + Driver(); private: static Driver *head; @@ -45,4 +73,46 @@ private: Driver &operator=(const Driver &); }; +class SimpleDriver : public Driver { +public: + virtual ~SimpleDriver(); + + bool claimCounter(const Counter &counter) const; + bool countersEnabled() const; + void resetCounters(); + void setupCounter(Counter &counter); + int writeCounters(mxml_node_t *root) const; + +protected: + SimpleDriver() : mCounters(NULL) {} + + DriverCounter *getCounters() const { return mCounters; } + void setCounters(DriverCounter *const counter) { mCounters = counter; } + + DriverCounter *findCounter(const Counter &counter) const; + +private: + DriverCounter *mCounters; + + // Intentionally unimplemented + SimpleDriver(const SimpleDriver &); + SimpleDriver &operator=(const SimpleDriver &); +}; + +class PolledDriver : public SimpleDriver { +public: + virtual ~PolledDriver(); + + virtual void start() {} + virtual void read(Buffer *const buffer); + +protected: + PolledDriver() {} + +private: + // Intentionally unimplemented + PolledDriver(const PolledDriver &); + PolledDriver &operator=(const PolledDriver &); +}; + #endif // DRIVER_H diff --git a/tools/gator/daemon/DriverSource.cpp b/tools/gator/daemon/DriverSource.cpp index 11d3095ef6d2..7f299b646952 100644 --- a/tools/gator/daemon/DriverSource.cpp +++ b/tools/gator/daemon/DriverSource.cpp @@ -6,6 +6,7 @@ * published by the Free Software Foundation. */ +// Define to get format macros from inttypes.h #define __STDC_FORMAT_MACROS #include "DriverSource.h" @@ -93,19 +94,19 @@ bool DriverSource::prepare() { } void DriverSource::bootstrapThread() { - prctl(PR_SET_NAME, (unsigned long)&"gatord-bootstrap", 0, 0, 0); + prctl(PR_SET_NAME, (unsigned long)&"gatord-proc", 0, 0, 0); DynBuf printb; DynBuf b1; DynBuf b2; - DynBuf b3; + const uint64_t currTime = getTime(); - if (!readProc(mBuffer, false, &printb, &b1, &b2, &b3)) { - logg->logMessage("%s(%s:%i): readProc failed", __FUNCTION__, __FILE__, __LINE__); + if (!readProcComms(currTime, mBuffer, &printb, &b1, &b2)) { + logg->logError(__FILE__, __LINE__, "readProcComms failed"); handleException(); } - mBuffer->commit(1); + mBuffer->commit(currTime); mBuffer->setDone(); } @@ -128,7 +129,7 @@ void DriverSource::run() { } // open the buffer which calls userspace_buffer_open() in the driver - mBufferFD = open("/dev/gator/buffer", O_RDONLY); + mBufferFD = open("/dev/gator/buffer", O_RDONLY | O_CLOEXEC); if (mBufferFD < 0) { logg->logError(__FILE__, __LINE__, "The gator driver did not set up properly. Please view the linux console or dmesg log for more information on the failure."); handleException(); @@ -232,7 +233,7 @@ void DriverSource::write(Sender *sender) { int DriverSource::readIntDriver(const char *fullpath, int *value) { char data[40]; // Sufficiently large to hold any integer - const int fd = open(fullpath, O_RDONLY); + const int fd = open(fullpath, O_RDONLY | O_CLOEXEC); if (fd < 0) { return -1; } @@ -257,7 +258,7 @@ int DriverSource::readIntDriver(const char *fullpath, int *value) { int DriverSource::readInt64Driver(const char *fullpath, int64_t *value) { char data[40]; // Sufficiently large to hold any integer - const int fd = open(fullpath, O_RDONLY); + const int fd = open(fullpath, O_RDONLY | O_CLOEXEC); if (fd < 0) { return -1; } @@ -281,7 +282,7 @@ int DriverSource::readInt64Driver(const char *fullpath, int64_t *value) { } int DriverSource::writeDriver(const char *fullpath, const char *data) { - int fd = open(fullpath, O_WRONLY); + int fd = open(fullpath, O_WRONLY | O_CLOEXEC); if (fd < 0) { return -1; } diff --git a/tools/gator/daemon/DynBuf.cpp b/tools/gator/daemon/DynBuf.cpp index 6f92b336ae19..df20713ad63c 100644 --- a/tools/gator/daemon/DynBuf.cpp +++ b/tools/gator/daemon/DynBuf.cpp @@ -40,7 +40,7 @@ int DynBuf::resize(const size_t minCapacity) { bool DynBuf::read(const char *const path) { int result = false; - const int fd = open(path, O_RDONLY); + const int fd = open(path, O_RDONLY | O_CLOEXEC); if (fd < 0) { logg->logMessage("%s(%s:%i): open failed", __FUNCTION__, __FILE__, __LINE__); return false; diff --git a/tools/gator/daemon/EventsXML.cpp b/tools/gator/daemon/EventsXML.cpp index cf0192ef671f..d905bbabe988 100644 --- a/tools/gator/daemon/EventsXML.cpp +++ b/tools/gator/daemon/EventsXML.cpp @@ -47,7 +47,7 @@ char *EventsXML::getXML() { // Add dynamic events from the drivers mxml_node_t *events = mxmlFindElement(xml, xml, "events", NULL, NULL, MXML_DESCEND); if (!events) { - logg->logMessage("Unable to find <events> node in the events.xml"); + logg->logError(__FILE__, __LINE__, "Unable to find <events> node in the events.xml"); handleException(); } for (Driver *driver = Driver::getHead(); driver != NULL; driver = driver->getNext()) { diff --git a/tools/gator/daemon/ExternalSource.cpp b/tools/gator/daemon/ExternalSource.cpp index b6ec301d0c08..8f5e6b684c53 100644 --- a/tools/gator/daemon/ExternalSource.cpp +++ b/tools/gator/daemon/ExternalSource.cpp @@ -19,6 +19,9 @@ static const char MALI_VIDEO[] = "\0mali-video"; static const char MALI_VIDEO_STARTUP[] = "\0mali-video-startup"; static const char MALI_VIDEO_V1[] = "MALI_VIDEO 1\n"; +static const char MALI_GRAPHICS[] = "\0mali_thirdparty_server"; +static const char MALI_GRAPHICS_STARTUP[] = "\0mali_thirdparty_client"; +static const char MALI_GRAPHICS_V1[] = "MALI_GRAPHICS 1\n"; static bool setNonblock(const int fd) { int flags; @@ -37,16 +40,15 @@ static bool setNonblock(const int fd) { return true; } -ExternalSource::ExternalSource(sem_t *senderSem) : mBuffer(0, FRAME_EXTERNAL, 128*1024, senderSem), mMonitor(), mMveStartupUds(MALI_VIDEO_STARTUP, sizeof(MALI_VIDEO_STARTUP)), mInterruptFd(-1), mMveUds(-1) { +ExternalSource::ExternalSource(sem_t *senderSem) : mBuffer(0, FRAME_EXTERNAL, 128*1024, senderSem), mMonitor(), mMveStartupUds(MALI_VIDEO_STARTUP, sizeof(MALI_VIDEO_STARTUP)), mMaliStartupUds(MALI_GRAPHICS_STARTUP, sizeof(MALI_GRAPHICS_STARTUP)), mAnnotate(8083), mInterruptFd(-1), mMaliUds(-1), mMveUds(-1) { sem_init(&mBufferSem, 0, 0); } ExternalSource::~ExternalSource() { } -void ExternalSource::waitFor(const uint64_t currTime, const int bytes) { +void ExternalSource::waitFor(const int bytes) { while (mBuffer.bytesAvailable() <= bytes) { - mBuffer.check(currTime); sem_wait(&mBufferSem); } } @@ -63,11 +65,21 @@ void ExternalSource::configureConnection(const int fd, const char *const handsha } // Write the handshake to the circular buffer - waitFor(1, Buffer::MAXSIZE_PACK32 + 4 + size - 1); + waitFor(Buffer::MAXSIZE_PACK32 + size - 1); mBuffer.packInt(fd); - mBuffer.writeLEInt((unsigned char *)mBuffer.getWritePos(), size - 1); - mBuffer.advanceWrite(4); mBuffer.writeBytes(handshake, size - 1); + mBuffer.commit(1); +} + +bool ExternalSource::connectMali() { + mMaliUds = OlySocket::connect(MALI_GRAPHICS, sizeof(MALI_GRAPHICS)); + if (mMaliUds < 0) { + return false; + } + + configureConnection(mMaliUds, MALI_GRAPHICS_V1, sizeof(MALI_GRAPHICS_V1)); + + return true; } bool ExternalSource::connectMve() { @@ -90,10 +102,15 @@ bool ExternalSource::connectMve() { } bool ExternalSource::prepare() { - if (!mMonitor.init() || !setNonblock(mMveStartupUds.getFd()) || !mMonitor.add(mMveStartupUds.getFd())) { + if (!mMonitor.init() || + !setNonblock(mMveStartupUds.getFd()) || !mMonitor.add(mMveStartupUds.getFd()) || + !setNonblock(mMaliStartupUds.getFd()) || !mMonitor.add(mMaliStartupUds.getFd()) || + !setNonblock(mAnnotate.getFd()) || !mMonitor.add(mAnnotate.getFd()) || + false) { return false; } + connectMali(); connectMve(); return true; @@ -104,7 +121,7 @@ void ExternalSource::run() { prctl(PR_SET_NAME, (unsigned long)&"gatord-external", 0, 0, 0); - if (pipe(pipefd) != 0) { + if (pipe_cloexec(pipefd) != 0) { logg->logError(__FILE__, __LINE__, "pipe failed"); handleException(); } @@ -115,6 +132,9 @@ void ExternalSource::run() { handleException(); } + // Notify annotate clients to retry connecting to gatord + gSessionData->annotateListener.signal(); + while (gSessionData->mSessionIsActive) { struct epoll_event events[16]; // Clear any pending sem posts @@ -138,36 +158,60 @@ void ExternalSource::run() { logg->logError(__FILE__, __LINE__, "Unable to configure incoming Mali video connection"); handleException(); } + } else if (fd == mMaliStartupUds.getFd()) { + // Mali Graphics says it's alive + int client = mMaliStartupUds.acceptConnection(); + // Don't read from this connection, establish a new connection to Mali Graphics + close(client); + if (!connectMali()) { + logg->logError(__FILE__, __LINE__, "Unable to configure incoming Mali graphics connection"); + handleException(); + } + } else if (fd == mAnnotate.getFd()) { + int client = mAnnotate.acceptConnection(); + if (!setNonblock(client) || !mMonitor.add(client)) { + logg->logError(__FILE__, __LINE__, "Unable to set socket options on incoming annotation connection"); + handleException(); + } } else if (fd == pipefd[0]) { // Means interrupt has been called and mSessionIsActive should be reread } else { - while (true) { - waitFor(currTime, Buffer::MAXSIZE_PACK32 + 4); - + /* This can result in some starvation if there are multiple + * threads which are annotating heavily, but it is not + * recommended that threads annotate that much as it can also + * starve out the gator data. + */ + while (gSessionData->mSessionIsActive) { + // Wait until there is enough room for the fd, two headers and two ints + waitFor(7*Buffer::MAXSIZE_PACK32 + 2*sizeof(uint32_t)); mBuffer.packInt(fd); - char *const bytesPos = mBuffer.getWritePos(); - mBuffer.advanceWrite(4); const int contiguous = mBuffer.contiguousSpaceAvailable(); const int bytes = read(fd, mBuffer.getWritePos(), contiguous); if (bytes < 0) { if (errno == EAGAIN) { - // Nothing left to read, and Buffer convention dictates that writePos can't go backwards - mBuffer.writeLEInt((unsigned char *)bytesPos, 0); + // Nothing left to read + mBuffer.commit(currTime); break; } // Something else failed, close the socket - mBuffer.writeLEInt((unsigned char *)bytesPos, -1); + mBuffer.commit(currTime); + mBuffer.packInt(-1); + mBuffer.packInt(fd); + mBuffer.commit(currTime); close(fd); break; } else if (bytes == 0) { // The other side is closed - mBuffer.writeLEInt((unsigned char *)bytesPos, -1); + mBuffer.commit(currTime); + mBuffer.packInt(-1); + mBuffer.packInt(fd); + mBuffer.commit(currTime); close(fd); break; } - mBuffer.writeLEInt((unsigned char *)bytesPos, bytes); mBuffer.advanceWrite(bytes); + mBuffer.commit(currTime); // Short reads also mean nothing is left to read if (bytes < contiguous) { @@ -176,13 +220,14 @@ void ExternalSource::run() { } } } - - // Only call mBufferCheck once per iteration - mBuffer.check(currTime); } mBuffer.setDone(); + if (mMveUds >= 0) { + gSessionData->maliVideo.stop(mMveUds); + } + mInterruptFd = -1; close(pipefd[0]); close(pipefd[1]); diff --git a/tools/gator/daemon/ExternalSource.h b/tools/gator/daemon/ExternalSource.h index 2e7ed27df255..919e75e8a41a 100644 --- a/tools/gator/daemon/ExternalSource.h +++ b/tools/gator/daemon/ExternalSource.h @@ -16,7 +16,7 @@ #include "OlySocket.h" #include "Source.h" -// Unix domain socket counters from external sources like graphics drivers +// Counters from external sources like graphics drivers and annotations class ExternalSource : public Source { public: ExternalSource(sem_t *senderSem); @@ -30,15 +30,19 @@ public: void write(Sender *sender); private: - void waitFor(const uint64_t currTime, const int bytes); + void waitFor(const int bytes); void configureConnection(const int fd, const char *const handshake, size_t size); + bool connectMali(); bool connectMve(); sem_t mBufferSem; Buffer mBuffer; Monitor mMonitor; OlyServerSocket mMveStartupUds; + OlyServerSocket mMaliStartupUds; + OlyServerSocket mAnnotate; int mInterruptFd; + int mMaliUds; int mMveUds; // Intentionally unimplemented diff --git a/tools/gator/daemon/FSDriver.cpp b/tools/gator/daemon/FSDriver.cpp index 40c8df1af222..dd8eb804dc99 100644 --- a/tools/gator/daemon/FSDriver.cpp +++ b/tools/gator/daemon/FSDriver.cpp @@ -14,43 +14,34 @@ #include <sys/types.h> #include <unistd.h> -#include "Buffer.h" -#include "Counter.h" #include "DriverSource.h" #include "Logging.h" -#include "SessionData.h" -class FSCounter { +class FSCounter : public DriverCounter { public: - FSCounter(FSCounter *next, char *name, const char *regex); + FSCounter(DriverCounter *next, char *name, char *path, const char *regex); ~FSCounter(); - FSCounter *getNext() const { return next; } - int getKey() const { return key; } - bool isEnabled() const { return enabled; } - void setEnabled(const bool enabled) { this->enabled = enabled; } - const char *getName() const { return name; } + const char *getPath() const { return mPath; } + int64_t read(); private: - FSCounter *const next; - regex_t reg; - char *name; - const int key; - int enabled : 1, - useRegex : 1; + char *const mPath; + regex_t mReg; + bool mUseRegex; // Intentionally unimplemented FSCounter(const FSCounter &); FSCounter &operator=(const FSCounter &); }; -FSCounter::FSCounter(FSCounter *next, char *name, const char *regex) : next(next), name(name), key(getEventKey()), enabled(false), useRegex(regex != NULL) { - if (useRegex) { - int result = regcomp(®, regex, REG_EXTENDED); +FSCounter::FSCounter(DriverCounter *next, char *name, char *path, const char *regex) : DriverCounter(next, name), mPath(path), mUseRegex(regex != NULL) { + if (mUseRegex) { + int result = regcomp(&mReg, regex, REG_EXTENDED); if (result != 0) { char buf[128]; - regerror(result, ®, buf, sizeof(buf)); + regerror(result, &mReg, buf, sizeof(buf)); logg->logError(__FILE__, __LINE__, "Invalid regex '%s': %s", regex, buf); handleException(); } @@ -58,18 +49,18 @@ FSCounter::FSCounter(FSCounter *next, char *name, const char *regex) : next(next } FSCounter::~FSCounter() { - free(name); - if (useRegex) { - regfree(®); + free(mPath); + if (mUseRegex) { + regfree(&mReg); } } int64_t FSCounter::read() { int64_t value; - if (useRegex) { + if (mUseRegex) { char buf[4096]; size_t pos = 0; - const int fd = open(name, O_RDONLY); + const int fd = open(mPath, O_RDONLY | O_CLOEXEC); if (fd < 0) { goto fail; } @@ -86,53 +77,43 @@ int64_t FSCounter::read() { buf[pos] = '\0'; regmatch_t match[2]; - int result = regexec(®, buf, 2, match, 0); + int result = regexec(&mReg, buf, 2, match, 0); if (result != 0) { - regerror(result, ®, buf, sizeof(buf)); - logg->logError(__FILE__, __LINE__, "Parsing %s failed: %s", name, buf); + regerror(result, &mReg, buf, sizeof(buf)); + logg->logError(__FILE__, __LINE__, "Parsing %s failed: %s", mPath, buf); handleException(); } if (match[1].rm_so < 0) { - logg->logError(__FILE__, __LINE__, "Parsing %s failed", name); + logg->logError(__FILE__, __LINE__, "Parsing %s failed", mPath); handleException(); } - char *endptr; + errno = 0; - value = strtoll(buf + match[1].rm_so, &endptr, 0); + value = strtoll(buf + match[1].rm_so, NULL, 0); if (errno != 0) { - logg->logError(__FILE__, __LINE__, "Parsing %s failed: %s", name, strerror(errno)); + logg->logError(__FILE__, __LINE__, "Parsing %s failed: %s", mPath, strerror(errno)); handleException(); } } else { - if (DriverSource::readInt64Driver(name, &value) != 0) { + if (DriverSource::readInt64Driver(mPath, &value) != 0) { goto fail; } } return value; fail: - logg->logError(__FILE__, __LINE__, "Unable to read %s", name); + logg->logError(__FILE__, __LINE__, "Unable to read %s", mPath); handleException(); } -FSDriver::FSDriver() : counters(NULL) { +FSDriver::FSDriver() { } FSDriver::~FSDriver() { - while (counters != NULL) { - FSCounter * counter = counters; - counters = counter->getNext(); - delete counter; - } } -void FSDriver::setup(mxml_node_t *const xml) { - // fs driver does not currently work with perf - if (gSessionData->perf.isSetup()) { - return; - } - +void FSDriver::readEvents(mxml_node_t *const xml) { mxml_node_t *node = xml; while (true) { node = mxmlFindElement(node, xml, "event", NULL, NULL, MXML_DESCEND); @@ -140,56 +121,33 @@ void FSDriver::setup(mxml_node_t *const xml) { break; } const char *counter = mxmlElementGetAttr(node, "counter"); - if ((counter != NULL) && (counter[0] == '/')) { - const char *regex = mxmlElementGetAttr(node, "regex"); - counters = new FSCounter(counters, strdup(counter), regex); + if (counter == NULL) { + continue; } - } -} -FSCounter *FSDriver::findCounter(const Counter &counter) const { - for (FSCounter * fsCounter = counters; fsCounter != NULL; fsCounter = fsCounter->getNext()) { - if (strcmp(fsCounter->getName(), counter.getType()) == 0) { - return fsCounter; + if (counter[0] == '/') { + logg->logError(__FILE__, __LINE__, "Old style filesystem counter (%s) detected, please create a new unique counter value and move the filename into the path attribute, see events-Filesystem.xml for examples", counter); + handleException(); } - } - - return NULL; -} -bool FSDriver::claimCounter(const Counter &counter) const { - return findCounter(counter) != NULL; -} - -bool FSDriver::countersEnabled() const { - for (FSCounter *counter = counters; counter != NULL; counter = counter->getNext()) { - if (counter->isEnabled()) { - return true; + if (strncmp(counter, "filesystem_", 11) != 0) { + continue; } - } - return false; -} -void FSDriver::resetCounters() { - for (FSCounter * counter = counters; counter != NULL; counter = counter->getNext()) { - counter->setEnabled(false); - } -} - -void FSDriver::setupCounter(Counter &counter) { - FSCounter *const fsCounter = findCounter(counter); - if (fsCounter == NULL) { - counter.setEnabled(false); - return; + const char *path = mxmlElementGetAttr(node, "path"); + if (path == NULL) { + logg->logError(__FILE__, __LINE__, "The filesystem counter %s is missing the required path attribute", counter); + handleException(); + } + const char *regex = mxmlElementGetAttr(node, "regex"); + setCounters(new FSCounter(getCounters(), strdup(counter), strdup(path), regex)); } - fsCounter->setEnabled(true); - counter.setKey(fsCounter->getKey()); } int FSDriver::writeCounters(mxml_node_t *root) const { int count = 0; - for (FSCounter * counter = counters; counter != NULL; counter = counter->getNext()) { - if (access(counter->getName(), R_OK) == 0) { + for (FSCounter *counter = static_cast<FSCounter *>(getCounters()); counter != NULL; counter = static_cast<FSCounter *>(counter->getNext())) { + if (access(counter->getPath(), R_OK) == 0) { mxml_node_t *node = mxmlNewElement(root, "counter"); mxmlElementSetAttr(node, "name", counter->getName()); ++count; @@ -198,15 +156,3 @@ int FSDriver::writeCounters(mxml_node_t *root) const { return count; } - -void FSDriver::start() { -} - -void FSDriver::read(Buffer * const buffer) { - for (FSCounter * counter = counters; counter != NULL; counter = counter->getNext()) { - if (!counter->isEnabled()) { - continue; - } - buffer->event(counter->getKey(), counter->read()); - } -} diff --git a/tools/gator/daemon/FSDriver.h b/tools/gator/daemon/FSDriver.h index ef3955362331..a7dc8b4df9dd 100644 --- a/tools/gator/daemon/FSDriver.h +++ b/tools/gator/daemon/FSDriver.h @@ -11,31 +11,16 @@ #include "Driver.h" -class Buffer; -class FSCounter; - -class FSDriver : public Driver { +class FSDriver : public PolledDriver { public: FSDriver(); ~FSDriver(); - void setup(mxml_node_t *const xml); - - bool claimCounter(const Counter &counter) const; - bool countersEnabled() const; - void resetCounters(); - void setupCounter(Counter &counter); + void readEvents(mxml_node_t *const xml); int writeCounters(mxml_node_t *root) const; - void start(); - void read(Buffer * buffer); - private: - FSCounter *findCounter(const Counter &counter) const; - - FSCounter *counters; - // Intentionally unimplemented FSDriver(const FSDriver &); FSDriver &operator=(const FSDriver &); diff --git a/tools/gator/daemon/Fifo.cpp b/tools/gator/daemon/Fifo.cpp index f672e92a6807..41275fd287b8 100644 --- a/tools/gator/daemon/Fifo.cpp +++ b/tools/gator/daemon/Fifo.cpp @@ -9,9 +9,6 @@ #include "Fifo.h" #include <stdlib.h> -#ifdef WIN32 -#define valloc malloc -#endif #include "Logging.h" @@ -23,7 +20,7 @@ Fifo::Fifo(int singleBufferSize, int bufferSize, sem_t* readerSem) { mWrapThreshold = bufferSize; mSingleBufferSize = singleBufferSize; mReaderSem = readerSem; - mBuffer = (char*)valloc(bufferSize + singleBufferSize); + mBuffer = (char*)malloc(bufferSize + singleBufferSize); mEnd = false; if (mBuffer == NULL) { diff --git a/tools/gator/daemon/Fifo.h b/tools/gator/daemon/Fifo.h index bdda3f549b50..21c8d8580391 100644 --- a/tools/gator/daemon/Fifo.h +++ b/tools/gator/daemon/Fifo.h @@ -6,8 +6,8 @@ * published by the Free Software Foundation. */ -#ifndef __FIFO_H__ -#define __FIFO_H__ +#ifndef __FIFO_H__ +#define __FIFO_H__ #ifdef WIN32 #include <windows.h> @@ -35,10 +35,10 @@ public: private: int mSingleBufferSize, mWrite, mRead, mReadCommit, mRaggedEnd, mWrapThreshold; - sem_t mWaitForSpaceSem; + sem_t mWaitForSpaceSem; sem_t* mReaderSem; - char* mBuffer; - bool mEnd; + char* mBuffer; + bool mEnd; // Intentionally unimplemented Fifo(const Fifo &); diff --git a/tools/gator/daemon/FtraceDriver.cpp b/tools/gator/daemon/FtraceDriver.cpp new file mode 100644 index 000000000000..b156f1c0b8b4 --- /dev/null +++ b/tools/gator/daemon/FtraceDriver.cpp @@ -0,0 +1,118 @@ +/** + * Copyright (C) ARM Limited 2014. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "FtraceDriver.h" + +#include <regex.h> + +#include "Logging.h" + +class FtraceCounter : public DriverCounter { +public: + FtraceCounter(DriverCounter *next, char *name, const char *regex); + ~FtraceCounter(); + + int read(const char *const line, int64_t *values); + +private: + regex_t reg; + + // Intentionally unimplemented + FtraceCounter(const FtraceCounter &); + FtraceCounter &operator=(const FtraceCounter &); +}; + +FtraceCounter::FtraceCounter(DriverCounter *next, char *name, const char *regex) : DriverCounter(next, name) { + int result = regcomp(®, regex, REG_EXTENDED); + if (result != 0) { + char buf[128]; + regerror(result, ®, buf, sizeof(buf)); + logg->logError(__FILE__, __LINE__, "Invalid regex '%s': %s", regex, buf); + handleException(); + } +} + +FtraceCounter::~FtraceCounter() { + regfree(®); +} + +int FtraceCounter::read(const char *const line, int64_t *values) { + regmatch_t match[2]; + int result = regexec(®, line, 2, match, 0); + if (result != 0) { + // No match + return 0; + } + + if (match[1].rm_so < 0) { + logg->logError(__FILE__, __LINE__, "Parsing %s failed", getName()); + handleException(); + } + + errno = 0; + int64_t value = strtoll(line + match[1].rm_so, NULL, 0); + if (errno != 0) { + logg->logError(__FILE__, __LINE__, "Parsing %s failed: %s", getName(), strerror(errno)); + handleException(); + } + + values[0] = getKey(); + values[1] = value; + + return 1; +} + +FtraceDriver::FtraceDriver() : mValues(NULL) { +} + +FtraceDriver::~FtraceDriver() { + delete [] mValues; +} + +void FtraceDriver::readEvents(mxml_node_t *const xml) { + mxml_node_t *node = xml; + int count = 0; + while (true) { + node = mxmlFindElement(node, xml, "event", NULL, NULL, MXML_DESCEND); + if (node == NULL) { + break; + } + const char *counter = mxmlElementGetAttr(node, "counter"); + if (counter == NULL) { + continue; + } + + if (strncmp(counter, "ftrace_", 7) != 0) { + continue; + } + + const char *regex = mxmlElementGetAttr(node, "regex"); + if (regex == NULL) { + logg->logError(__FILE__, __LINE__, "The regex counter %s is missing the required regex attribute", counter); + handleException(); + } + setCounters(new FtraceCounter(getCounters(), strdup(counter), regex)); + ++count; + } + + mValues = new int64_t[2*count]; +} + +int FtraceDriver::read(const char *line, int64_t **buf) { + int count = 0; + + for (FtraceCounter *counter = static_cast<FtraceCounter *>(getCounters()); counter != NULL; counter = static_cast<FtraceCounter *>(counter->getNext())) { + if (!counter->isEnabled()) { + continue; + } + count += counter->read(line, mValues + 2*count); + } + + *buf = mValues; + return count; +} diff --git a/tools/gator/daemon/FtraceDriver.h b/tools/gator/daemon/FtraceDriver.h new file mode 100644 index 000000000000..5f958bec672c --- /dev/null +++ b/tools/gator/daemon/FtraceDriver.h @@ -0,0 +1,31 @@ +/** + * Copyright (C) ARM Limited 2014. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef FTRACEDRIVER_H +#define FTRACEDRIVER_H + +#include "Driver.h" + +class FtraceDriver : public SimpleDriver { +public: + FtraceDriver(); + ~FtraceDriver(); + + void readEvents(mxml_node_t *const xml); + + int read(const char *line, int64_t **buf); + +private: + int64_t *mValues; + + // Intentionally unimplemented + FtraceDriver(const FtraceDriver &); + FtraceDriver &operator=(const FtraceDriver &); +}; + +#endif // FTRACEDRIVER_H diff --git a/tools/gator/daemon/FtraceSource.cpp b/tools/gator/daemon/FtraceSource.cpp new file mode 100644 index 000000000000..521633357417 --- /dev/null +++ b/tools/gator/daemon/FtraceSource.cpp @@ -0,0 +1,158 @@ +/** + * Copyright (C) ARM Limited 2010-2014. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "FtraceSource.h" + +#include <fcntl.h> +#include <signal.h> +#include <sys/prctl.h> +#include <sys/syscall.h> +#include <unistd.h> + +#include "DriverSource.h" +#include "Logging.h" +#include "SessionData.h" + +static void handler(int signum) +{ + (void)signum; +}; + +FtraceSource::FtraceSource(sem_t *senderSem) : mFtraceFh(NULL), mBuffer(0, FRAME_BLOCK_COUNTER, 128*1024, senderSem), mTid(-1), mTracingOn(0) { +} + +FtraceSource::~FtraceSource() { +} + +bool FtraceSource::prepare() { + { + struct sigaction act; + act.sa_handler = handler; + act.sa_flags = (int)SA_RESETHAND; + if (sigaction(SIGUSR1, &act, NULL) != 0) { + logg->logError(__FILE__, __LINE__, "sigaction failed: %s\n", strerror(errno)); + handleException(); + } + } + + if (DriverSource::readIntDriver("/sys/kernel/debug/tracing/tracing_on", &mTracingOn)) { + logg->logError(__FILE__, __LINE__, "Unable to read if ftrace is enabled"); + handleException(); + } + + if (DriverSource::writeDriver("/sys/kernel/debug/tracing/tracing_on", "0") != 0) { + logg->logError(__FILE__, __LINE__, "Unable to turn ftrace off before truncating the buffer"); + handleException(); + } + + { + int fd; + fd = open("/sys/kernel/debug/tracing/trace", O_WRONLY | O_TRUNC | O_CLOEXEC, 0666); + if (fd < 0) { + logg->logError(__FILE__, __LINE__, "Unable truncate ftrace buffer: %s", strerror(errno)); + handleException(); + } + close(fd); + } + + if (DriverSource::writeDriver("/sys/kernel/debug/tracing/trace_clock", "perf") != 0) { + logg->logError(__FILE__, __LINE__, "Unable to switch ftrace to the perf clock, please ensure you are running Linux 3.10 or later"); + handleException(); + } + + mFtraceFh = fopen_cloexec("/sys/kernel/debug/tracing/trace_pipe", "rb"); + if (mFtraceFh == NULL) { + logg->logError(__FILE__, __LINE__, "Unable to open trace_pipe"); + handleException(); + } + + return true; +} + +void FtraceSource::run() { + prctl(PR_SET_NAME, (unsigned long)&"gatord-ftrace", 0, 0, 0); + mTid = syscall(__NR_gettid); + + if (DriverSource::writeDriver("/sys/kernel/debug/tracing/tracing_on", "1") != 0) { + logg->logError(__FILE__, __LINE__, "Unable to turn ftrace on"); + handleException(); + } + + while (gSessionData->mSessionIsActive) { + char buf[1<<12]; + + if (fgets(buf, sizeof(buf), mFtraceFh) == NULL) { + if (errno == EINTR) { + // Interrupted by interrupt - likely user request to terminate + break; + } + logg->logError(__FILE__, __LINE__, "Unable read trace data: %s", strerror(errno)); + handleException(); + } + + const uint64_t currTime = getTime(); + + char *const colon = strstr(buf, ": "); + if (colon == NULL) { + logg->logError(__FILE__, __LINE__, "Unable find colon: %s", buf); + handleException(); + } + *colon = '\0'; + + char *const space = strrchr(buf, ' '); + if (space == NULL) { + logg->logError(__FILE__, __LINE__, "Unable find space: %s", buf); + handleException(); + } + *colon = ':'; + + int64_t *data = NULL; + int count = gSessionData->ftraceDriver.read(colon + 2, &data); + if (count > 0) { + errno = 0; + const long long time = strtod(space, NULL) * 1000000000; + if (errno != 0) { + logg->logError(__FILE__, __LINE__, "Unable to parse time: %s", strerror(errno)); + handleException(); + } + mBuffer.event64(-1, time); + + for (int i = 0; i < count; ++i) { + mBuffer.event64(data[2*i + 0], data[2*i + 1]); + } + + mBuffer.check(currTime); + } + + } + + mBuffer.setDone(); + + DriverSource::writeDriver("/sys/kernel/debug/tracing/tracing_on", mTracingOn); + fclose(mFtraceFh); + DriverSource::writeDriver("/sys/kernel/debug/tracing/trace_clock", "local"); +} + +void FtraceSource::interrupt() { + // Closing the underlying file handle does not result in the read on the ftrace file handle to return, so send a signal to the thread + syscall(__NR_tgkill, getpid(), mTid, SIGUSR1); +} + +bool FtraceSource::isDone() { + return mBuffer.isDone(); +} + +void FtraceSource::write(Sender *sender) { + // Don't send ftrace data until the summary packet is sent so that monotonic delta is available + if (!gSessionData->mSentSummary) { + return; + } + if (!mBuffer.isDone()) { + mBuffer.write(sender); + } +} diff --git a/tools/gator/daemon/FtraceSource.h b/tools/gator/daemon/FtraceSource.h new file mode 100644 index 000000000000..2391b881494e --- /dev/null +++ b/tools/gator/daemon/FtraceSource.h @@ -0,0 +1,43 @@ +/** + * Copyright (C) ARM Limited 2010-2014. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef FTRACESOURCE_H +#define FTRACESOURCE_H + +#include <semaphore.h> +#include <stdio.h> + +#include "Buffer.h" +#include "Source.h" + +class FtraceSource : public Source { +public: + FtraceSource(sem_t *senderSem); + ~FtraceSource(); + + bool prepare(); + void run(); + void interrupt(); + + bool isDone(); + void write(Sender *sender); + +private: + void waitFor(const int bytes); + + FILE *mFtraceFh; + Buffer mBuffer; + int mTid; + int mTracingOn; + + // Intentionally unimplemented + FtraceSource(const FtraceSource &); + FtraceSource &operator=(const FtraceSource &); +}; + +#endif // FTRACESOURCE_H diff --git a/tools/gator/daemon/Hwmon.h b/tools/gator/daemon/Hwmon.h deleted file mode 100644 index a22a3609f99f..000000000000 --- a/tools/gator/daemon/Hwmon.h +++ /dev/null @@ -1,45 +0,0 @@ -/** - * Copyright (C) ARM Limited 2013-2014. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#ifndef HWMON_H -#define HWMON_H - -#include "Driver.h" - -class Buffer; -class HwmonCounter; - -class Hwmon : public Driver { -public: - Hwmon(); - ~Hwmon(); - - void setup(); - - bool claimCounter(const Counter &counter) const; - bool countersEnabled() const; - void resetCounters(); - void setupCounter(Counter &counter); - - int writeCounters(mxml_node_t *root) const; - void writeEvents(mxml_node_t *root) const; - - void start(); - void read(Buffer * buffer); - -private: - HwmonCounter *findCounter(const Counter &counter) const; - - HwmonCounter *counters; - - // Intentionally unimplemented - Hwmon(const Hwmon &); - Hwmon &operator=(const Hwmon &); -}; - -#endif // HWMON_H diff --git a/tools/gator/daemon/Hwmon.cpp b/tools/gator/daemon/HwmonDriver.cpp index e44424743ef0..9d161ae5ac56 100644 --- a/tools/gator/daemon/Hwmon.cpp +++ b/tools/gator/daemon/HwmonDriver.cpp @@ -6,24 +6,33 @@ * published by the Free Software Foundation. */ -#include "Hwmon.h" +#include "HwmonDriver.h" #include "libsensors/sensors.h" -#include "Buffer.h" -#include "Counter.h" #include "Logging.h" -#include "SessionData.h" -class HwmonCounter { +// feature->type to input map +static sensors_subfeature_type getInput(const sensors_feature_type type) { + switch (type) { + case SENSORS_FEATURE_IN: return SENSORS_SUBFEATURE_IN_INPUT; + case SENSORS_FEATURE_FAN: return SENSORS_SUBFEATURE_FAN_INPUT; + case SENSORS_FEATURE_TEMP: return SENSORS_SUBFEATURE_TEMP_INPUT; + case SENSORS_FEATURE_POWER: return SENSORS_SUBFEATURE_POWER_INPUT; + case SENSORS_FEATURE_ENERGY: return SENSORS_SUBFEATURE_ENERGY_INPUT; + case SENSORS_FEATURE_CURR: return SENSORS_SUBFEATURE_CURR_INPUT; + case SENSORS_FEATURE_HUMIDITY: return SENSORS_SUBFEATURE_HUMIDITY_INPUT; + default: + logg->logError(__FILE__, __LINE__, "Unsupported hwmon feature %i", type); + handleException(); + } +}; + +class HwmonCounter : public DriverCounter { public: - HwmonCounter(HwmonCounter *next, const sensors_chip_name *chip, const sensors_feature *feature); + HwmonCounter(DriverCounter *next, char *const name, const sensors_chip_name *chip, const sensors_feature *feature); ~HwmonCounter(); - HwmonCounter *getNext() const { return next; } - int getKey() const { return key; } - bool isEnabled() const { return enabled; } - const char *getName() const { return name; } const char *getLabel() const { return label; } const char *getTitle() const { return title; } bool isDuplicate() const { return duplicate; } @@ -32,63 +41,34 @@ public: const char *getUnit() const { return unit; } int getModifier() const { return modifier; } - void setEnabled(const bool enabled) { - this->enabled = enabled; - // canRead will clear enabled if the counter is not readable - canRead(); - } - - double read(); - bool canRead(); + int64_t read(); private: void init(const sensors_chip_name *chip, const sensors_feature *feature); - HwmonCounter *const next; - const int key; - int polled : 1, - readable : 1, - enabled : 1, - monotonic: 1, - duplicate : 1; - const sensors_chip_name *chip; const sensors_feature *feature; - - char *name; char *label; const char *title; const char *display; const char *counter_class; const char *unit; - int modifier; double previous_value; - - sensors_subfeature_type input; + int modifier; + int monotonic: 1, + duplicate : 1; // Intentionally unimplemented HwmonCounter(const HwmonCounter &); HwmonCounter &operator=(const HwmonCounter &); }; -HwmonCounter::HwmonCounter(HwmonCounter *next, const sensors_chip_name *chip, const sensors_feature *feature) : next(next), key(getEventKey()), polled(false), readable(false), enabled(false), duplicate(false), chip(chip), feature(feature) { - - int len = sensors_snprintf_chip_name(NULL, 0, chip) + 1; - char *chip_name = new char[len]; - sensors_snprintf_chip_name(chip_name, len, chip); - - len = snprintf(NULL, 0, "hwmon_%s_%d", chip_name, feature->number) + 1; - name = new char[len]; - snprintf(name, len, "hwmon_%s_%d", chip_name, feature->number); - - delete [] chip_name; - +HwmonCounter::HwmonCounter(DriverCounter *next, char *const name, const sensors_chip_name *chip, const sensors_feature *feature) : DriverCounter(next, name), chip(chip), feature(feature), duplicate(false) { label = sensors_get_label(chip, feature); switch (feature->type) { case SENSORS_FEATURE_IN: title = "Voltage"; - input = SENSORS_SUBFEATURE_IN_INPUT; display = "maximum"; counter_class = "absolute"; unit = "V"; @@ -97,7 +77,6 @@ HwmonCounter::HwmonCounter(HwmonCounter *next, const sensors_chip_name *chip, co break; case SENSORS_FEATURE_FAN: title = "Fan"; - input = SENSORS_SUBFEATURE_FAN_INPUT; display = "average"; counter_class = "absolute"; unit = "RPM"; @@ -106,7 +85,6 @@ HwmonCounter::HwmonCounter(HwmonCounter *next, const sensors_chip_name *chip, co break; case SENSORS_FEATURE_TEMP: title = "Temperature"; - input = SENSORS_SUBFEATURE_TEMP_INPUT; display = "maximum"; counter_class = "absolute"; unit = "°C"; @@ -115,7 +93,6 @@ HwmonCounter::HwmonCounter(HwmonCounter *next, const sensors_chip_name *chip, co break; case SENSORS_FEATURE_POWER: title = "Power"; - input = SENSORS_SUBFEATURE_POWER_INPUT; display = "maximum"; counter_class = "absolute"; unit = "W"; @@ -124,7 +101,6 @@ HwmonCounter::HwmonCounter(HwmonCounter *next, const sensors_chip_name *chip, co break; case SENSORS_FEATURE_ENERGY: title = "Energy"; - input = SENSORS_SUBFEATURE_ENERGY_INPUT; display = "accumulate"; counter_class = "delta"; unit = "J"; @@ -133,7 +109,6 @@ HwmonCounter::HwmonCounter(HwmonCounter *next, const sensors_chip_name *chip, co break; case SENSORS_FEATURE_CURR: title = "Current"; - input = SENSORS_SUBFEATURE_CURR_INPUT; display = "maximum"; counter_class = "absolute"; unit = "A"; @@ -142,7 +117,6 @@ HwmonCounter::HwmonCounter(HwmonCounter *next, const sensors_chip_name *chip, co break; case SENSORS_FEATURE_HUMIDITY: title = "Humidity"; - input = SENSORS_SUBFEATURE_HUMIDITY_INPUT; display = "average"; counter_class = "absolute"; unit = "%"; @@ -154,7 +128,7 @@ HwmonCounter::HwmonCounter(HwmonCounter *next, const sensors_chip_name *chip, co handleException(); } - for (HwmonCounter * counter = next; counter != NULL; counter = counter->getNext()) { + for (HwmonCounter * counter = static_cast<HwmonCounter *>(next); counter != NULL; counter = static_cast<HwmonCounter *>(counter->getNext())) { if (strcmp(label, counter->getLabel()) == 0 && strcmp(title, counter->getTitle()) == 0) { duplicate = true; counter->duplicate = true; @@ -165,16 +139,15 @@ HwmonCounter::HwmonCounter(HwmonCounter *next, const sensors_chip_name *chip, co HwmonCounter::~HwmonCounter() { free((void *)label); - delete [] name; } -double HwmonCounter::read() { +int64_t HwmonCounter::read() { double value; double result; const sensors_subfeature *subfeature; - // Keep in sync with canRead - subfeature = sensors_get_subfeature(chip, feature, input); + // Keep in sync with the read check in HwmonDriver::readEvents + subfeature = sensors_get_subfeature(chip, feature, getInput(feature->type)); if (!subfeature) { logg->logError(__FILE__, __LINE__, "No input value for hwmon sensor %s", label); handleException(); @@ -191,46 +164,14 @@ double HwmonCounter::read() { return result; } -bool HwmonCounter::canRead() { - if (!polled) { - double value; - const sensors_subfeature *subfeature; - bool result = true; - - subfeature = sensors_get_subfeature(chip, feature, input); - if (!subfeature) { - result = false; - } else { - result = sensors_get_value(chip, subfeature->number, &value) == 0; - } - - polled = true; - readable = result; - } - - enabled &= readable; - - return readable; -} - -Hwmon::Hwmon() : counters(NULL) { +HwmonDriver::HwmonDriver() { } -Hwmon::~Hwmon() { - while (counters != NULL) { - HwmonCounter * counter = counters; - counters = counter->getNext(); - delete counter; - } +HwmonDriver::~HwmonDriver() { sensors_cleanup(); } -void Hwmon::setup() { - // hwmon does not currently work with perf - if (gSessionData->perf.isSetup()) { - return; - } - +void HwmonDriver::readEvents(mxml_node_t *const) { int err = sensors_init(NULL); if (err) { logg->logMessage("Failed to initialize libsensors! (%d)", err); @@ -244,73 +185,34 @@ void Hwmon::setup() { int feature_nr = 0; const sensors_feature *feature; while ((feature = sensors_get_features(chip, &feature_nr))) { - counters = new HwmonCounter(counters, chip, feature); + // Keep in sync with HwmonCounter::read + // Can this counter be read? + double value; + const sensors_subfeature *const subfeature = sensors_get_subfeature(chip, feature, getInput(feature->type)); + if ((subfeature == NULL) || (sensors_get_value(chip, subfeature->number, &value) != 0)) { + continue; + } + + // Get the name of the counter + int len = sensors_snprintf_chip_name(NULL, 0, chip) + 1; + char *chip_name = new char[len]; + sensors_snprintf_chip_name(chip_name, len, chip); + len = snprintf(NULL, 0, "hwmon_%s_%d_%d", chip_name, chip_nr, feature->number) + 1; + char *const name = new char[len]; + snprintf(name, len, "hwmon_%s_%d_%d", chip_name, chip_nr, feature->number); + delete [] chip_name; + + setCounters(new HwmonCounter(getCounters(), name, chip, feature)); } } } -HwmonCounter *Hwmon::findCounter(const Counter &counter) const { - for (HwmonCounter * hwmonCounter = counters; hwmonCounter != NULL; hwmonCounter = hwmonCounter->getNext()) { - if (hwmonCounter->canRead() && strcmp(hwmonCounter->getName(), counter.getType()) == 0) { - return hwmonCounter; - } - } - - return NULL; -} - -bool Hwmon::claimCounter(const Counter &counter) const { - return findCounter(counter) != NULL; -} - -bool Hwmon::countersEnabled() const { - for (HwmonCounter * counter = counters; counter != NULL; counter = counter->getNext()) { - if (counter->isEnabled()) { - return true; - } - } - return false; -} - -void Hwmon::resetCounters() { - for (HwmonCounter * counter = counters; counter != NULL; counter = counter->getNext()) { - counter->setEnabled(false); - } -} - -void Hwmon::setupCounter(Counter &counter) { - HwmonCounter *const hwmonCounter = findCounter(counter); - if (hwmonCounter == NULL) { - counter.setEnabled(false); - return; - } - hwmonCounter->setEnabled(true); - counter.setKey(hwmonCounter->getKey()); -} - -int Hwmon::writeCounters(mxml_node_t *root) const { - int count = 0; - for (HwmonCounter * counter = counters; counter != NULL; counter = counter->getNext()) { - if (!counter->canRead()) { - continue; - } - mxml_node_t *node = mxmlNewElement(root, "counter"); - mxmlElementSetAttr(node, "name", counter->getName()); - ++count; - } - - return count; -} - -void Hwmon::writeEvents(mxml_node_t *root) const { +void HwmonDriver::writeEvents(mxml_node_t *root) const { root = mxmlNewElement(root, "category"); mxmlElementSetAttr(root, "name", "hwmon"); char buf[1024]; - for (HwmonCounter * counter = counters; counter != NULL; counter = counter->getNext()) { - if (!counter->canRead()) { - continue; - } + for (HwmonCounter *counter = static_cast<HwmonCounter *>(getCounters()); counter != NULL; counter = static_cast<HwmonCounter *>(counter->getNext())) { mxml_node_t *node = mxmlNewElement(root, "event"); mxmlElementSetAttr(node, "counter", counter->getName()); mxmlElementSetAttr(node, "title", counter->getTitle()); @@ -333,20 +235,11 @@ void Hwmon::writeEvents(mxml_node_t *root) const { } } -void Hwmon::start() { - for (HwmonCounter * counter = counters; counter != NULL; counter = counter->getNext()) { +void HwmonDriver::start() { + for (DriverCounter *counter = getCounters(); counter != NULL; counter = counter->getNext()) { if (!counter->isEnabled()) { continue; } counter->read(); } } - -void Hwmon::read(Buffer * const buffer) { - for (HwmonCounter * counter = counters; counter != NULL; counter = counter->getNext()) { - if (!counter->isEnabled()) { - continue; - } - buffer->event(counter->getKey(), counter->read()); - } -} diff --git a/tools/gator/daemon/HwmonDriver.h b/tools/gator/daemon/HwmonDriver.h new file mode 100644 index 000000000000..f28d825e3b7b --- /dev/null +++ b/tools/gator/daemon/HwmonDriver.h @@ -0,0 +1,31 @@ +/** + * Copyright (C) ARM Limited 2013-2014. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef HWMONDRIVER_H +#define HWMONDRIVER_H + +#include "Driver.h" + +class HwmonDriver : public PolledDriver { +public: + HwmonDriver(); + ~HwmonDriver(); + + void readEvents(mxml_node_t *const root); + + void writeEvents(mxml_node_t *root) const; + + void start(); + +private: + // Intentionally unimplemented + HwmonDriver(const HwmonDriver &); + HwmonDriver &operator=(const HwmonDriver &); +}; + +#endif // HWMONDRIVER_H diff --git a/tools/gator/daemon/KMod.cpp b/tools/gator/daemon/KMod.cpp index 73e123d2f14e..fe9dc6a7e4f7 100644 --- a/tools/gator/daemon/KMod.cpp +++ b/tools/gator/daemon/KMod.cpp @@ -16,6 +16,7 @@ #include "Counter.h" #include "DriverSource.h" #include "Logging.h" +#include "SessionData.h" // Claim all the counters in /dev/gator/events bool KMod::claimCounter(const Counter &counter) const { @@ -46,11 +47,19 @@ void KMod::resetCounters() { } } +static const char ARM_MALI_MIDGARD[] = "ARM_Mali-Midgard_"; +static const char ARM_MALI_T[] = "ARM_Mali-T"; + void KMod::setupCounter(Counter &counter) { char base[128]; char text[128]; snprintf(base, sizeof(base), "/dev/gator/events/%s", counter.getType()); + if ((strncmp(counter.getType(), ARM_MALI_MIDGARD, sizeof(ARM_MALI_MIDGARD) - 1) == 0 || + strncmp(counter.getType(), ARM_MALI_T, sizeof(ARM_MALI_T) - 1) == 0)) { + mIsMaliCapture = true; + } + snprintf(text, sizeof(text), "%s/enabled", base); int enabled = true; if (DriverSource::writeReadDriver(text, &enabled) || !enabled) { diff --git a/tools/gator/daemon/KMod.h b/tools/gator/daemon/KMod.h index fb7fc8a8f9c6..900a60e87d24 100644 --- a/tools/gator/daemon/KMod.h +++ b/tools/gator/daemon/KMod.h @@ -14,7 +14,7 @@ // Driver for the gator kernel module class KMod : public Driver { public: - KMod() {} + KMod() : mIsMaliCapture(false) {} ~KMod() {} bool claimCounter(const Counter &counter) const; @@ -22,6 +22,11 @@ public: void setupCounter(Counter &counter); int writeCounters(mxml_node_t *root) const; + + bool isMaliCapture() const { return mIsMaliCapture; } + +private: + bool mIsMaliCapture; }; #endif // KMOD_H diff --git a/tools/gator/daemon/LocalCapture.h b/tools/gator/daemon/LocalCapture.h index b1e7219795cf..25d281f8328b 100644 --- a/tools/gator/daemon/LocalCapture.h +++ b/tools/gator/daemon/LocalCapture.h @@ -6,8 +6,8 @@ * published by the Free Software Foundation. */ -#ifndef __LOCAL_CAPTURE_H__ -#define __LOCAL_CAPTURE_H__ +#ifndef __LOCAL_CAPTURE_H__ +#define __LOCAL_CAPTURE_H__ struct ImageLinkList; diff --git a/tools/gator/daemon/Logging.cpp b/tools/gator/daemon/Logging.cpp index b8d3178950d6..41ffa1a45151 100644 --- a/tools/gator/daemon/Logging.cpp +++ b/tools/gator/daemon/Logging.cpp @@ -14,15 +14,15 @@ #include <string.h> #ifdef WIN32 -#define MUTEX_INIT() mLoggingMutex = CreateMutex(NULL, false, NULL); -#define MUTEX_LOCK() WaitForSingleObject(mLoggingMutex, 0xFFFFFFFF); -#define MUTEX_UNLOCK() ReleaseMutex(mLoggingMutex); -#define snprintf _snprintf +#define MUTEX_INIT() mLoggingMutex = CreateMutex(NULL, false, NULL); +#define MUTEX_LOCK() WaitForSingleObject(mLoggingMutex, 0xFFFFFFFF); +#define MUTEX_UNLOCK() ReleaseMutex(mLoggingMutex); +#define snprintf _snprintf #else #include <pthread.h> -#define MUTEX_INIT() pthread_mutex_init(&mLoggingMutex, NULL) -#define MUTEX_LOCK() pthread_mutex_lock(&mLoggingMutex) -#define MUTEX_UNLOCK() pthread_mutex_unlock(&mLoggingMutex) +#define MUTEX_INIT() pthread_mutex_init(&mLoggingMutex, NULL) +#define MUTEX_LOCK() pthread_mutex_lock(&mLoggingMutex) +#define MUTEX_UNLOCK() pthread_mutex_unlock(&mLoggingMutex) #endif // Global thread-safe logging @@ -40,7 +40,7 @@ Logging::~Logging() { } void Logging::logError(const char* file, int line, const char* fmt, ...) { - va_list args; + va_list args; MUTEX_LOCK(); if (mDebug) { @@ -61,7 +61,7 @@ void Logging::logError(const char* file, int line, const char* fmt, ...) { void Logging::logMessage(const char* fmt, ...) { if (mDebug) { - va_list args; + va_list args; MUTEX_LOCK(); strcpy(mLogBuf, "INFO: "); diff --git a/tools/gator/daemon/Logging.h b/tools/gator/daemon/Logging.h index 4934bb079754..09e93ff13f7a 100644 --- a/tools/gator/daemon/Logging.h +++ b/tools/gator/daemon/Logging.h @@ -6,8 +6,8 @@ * published by the Free Software Foundation. */ -#ifndef __LOGGING_H__ -#define __LOGGING_H__ +#ifndef __LOGGING_H__ +#define __LOGGING_H__ #include <pthread.h> @@ -23,10 +23,10 @@ public: char* getLastMessage() {return mLogBuf;} private: - char mErrBuf[4096]; // Arbitrarily large buffer to hold a string - char mLogBuf[4096]; // Arbitrarily large buffer to hold a string - bool mDebug; - pthread_mutex_t mLoggingMutex; + char mErrBuf[4096]; // Arbitrarily large buffer to hold a string + char mLogBuf[4096]; // Arbitrarily large buffer to hold a string + bool mDebug; + pthread_mutex_t mLoggingMutex; }; extern Logging* logg; diff --git a/tools/gator/daemon/Makefile b/tools/gator/daemon/Makefile index 2ed49fdb688b..27531b438b63 100644 --- a/tools/gator/daemon/Makefile +++ b/tools/gator/daemon/Makefile @@ -11,11 +11,8 @@ CC = $(CROSS_COMPILE)gcc CXX = $(CROSS_COMPILE)g++ -# -mthumb-interwork is required for interworking to ARM or Thumb stdlibc -CPPFLAGS += -mthumb-interwork - ifeq ($(SOFTFLOAT),1) - CPPFLAGS += -marm -march=armv4t -mfloat-abi=soft + CPPFLAGS += -marm -mthumb-interwork -march=armv4t -mfloat-abi=soft LDFLAGS += -marm -march=armv4t -mfloat-abi=soft endif ifneq ($(SYSROOT),) diff --git a/tools/gator/daemon/MaliVideoDriver.cpp b/tools/gator/daemon/MaliVideoDriver.cpp index 18b413b01a37..5eef2643ab15 100644 --- a/tools/gator/daemon/MaliVideoDriver.cpp +++ b/tools/gator/daemon/MaliVideoDriver.cpp @@ -34,51 +34,30 @@ static const char COUNTER[] = "ARM_Mali-V500_cnt"; static const char EVENT[] = "ARM_Mali-V500_evn"; static const char ACTIVITY[] = "ARM_Mali-V500_act"; -class MaliVideoCounter { +class MaliVideoCounter : public DriverCounter { public: - MaliVideoCounter(MaliVideoCounter *next, const char *name, const MaliVideoCounterType type, const int id) : mNext(next), mName(name), mType(type), mId(id), mKey(getEventKey()), mEnabled(false) { + MaliVideoCounter(DriverCounter *next, const char *name, const MaliVideoCounterType type, const int id) : DriverCounter(next, name), mType(type), mId(id) { } ~MaliVideoCounter() { - delete mName; } - MaliVideoCounter *getNext() const { return mNext; } - const char *getName() const { return mName; } MaliVideoCounterType getType() const { return mType; } int getId() const { return mId; } - int getKey() const { return mKey; } - bool isEnabled() const { return mEnabled; } - void setEnabled(const bool enabled) { mEnabled = enabled; } private: - MaliVideoCounter *const mNext; - const char *const mName; const MaliVideoCounterType mType; // Mali Video id const int mId; - // Streamline key - const int mKey; - bool mEnabled; }; -MaliVideoDriver::MaliVideoDriver() : mCounters(NULL), mActivityCount(0) { +MaliVideoDriver::MaliVideoDriver() { } MaliVideoDriver::~MaliVideoDriver() { - while (mCounters != NULL) { - MaliVideoCounter *counter = mCounters; - mCounters = counter->getNext(); - delete counter; - } } -void MaliVideoDriver::setup(mxml_node_t *const xml) { - // hwmon does not currently work with perf - if (gSessionData->perf.isSetup()) { - return; - } - +void MaliVideoDriver::readEvents(mxml_node_t *const xml) { mxml_node_t *node = xml; while (true) { node = mxmlFindElement(node, xml, "event", NULL, NULL, MXML_DESCEND); @@ -90,62 +69,15 @@ void MaliVideoDriver::setup(mxml_node_t *const xml) { // Ignore } else if (strncmp(counter, COUNTER, sizeof(COUNTER) - 1) == 0) { const int i = strtol(counter + sizeof(COUNTER) - 1, NULL, 10); - mCounters = new MaliVideoCounter(mCounters, strdup(counter), MVCT_COUNTER, i); + setCounters(new MaliVideoCounter(getCounters(), strdup(counter), MVCT_COUNTER, i)); } else if (strncmp(counter, EVENT, sizeof(EVENT) - 1) == 0) { const int i = strtol(counter + sizeof(EVENT) - 1, NULL, 10); - mCounters = new MaliVideoCounter(mCounters, strdup(counter), MVCT_EVENT, i); - } else if (strcmp(counter, ACTIVITY) == 0) { - mCounters = new MaliVideoCounter(mCounters, strdup(ACTIVITY), MVCT_ACTIVITY, 0); - mActivityCount = 0; - while (true) { - char buf[32]; - snprintf(buf, sizeof(buf), "activity%i", mActivityCount + 1); - if (mxmlElementGetAttr(node, buf) == NULL) { - break; - } - ++mActivityCount; - } - } - } -} - -MaliVideoCounter *MaliVideoDriver::findCounter(const Counter &counter) const { - for (MaliVideoCounter *maliVideoCounter = mCounters; maliVideoCounter != NULL; maliVideoCounter = maliVideoCounter->getNext()) { - if (strcmp(maliVideoCounter->getName(), counter.getType()) == 0) { - return maliVideoCounter; - } - } - - return NULL; -} - -bool MaliVideoDriver::claimCounter(const Counter &counter) const { - return findCounter(counter) != NULL; -} - -bool MaliVideoDriver::countersEnabled() const { - for (MaliVideoCounter * counter = mCounters; counter != NULL; counter = counter->getNext()) { - if (counter->isEnabled()) { - return true; + setCounters(new MaliVideoCounter(getCounters(), strdup(counter), MVCT_EVENT, i)); + } else if (strncmp(counter, ACTIVITY, sizeof(ACTIVITY) - 1) == 0) { + const int i = strtol(counter + sizeof(ACTIVITY) - 1, NULL, 10); + setCounters(new MaliVideoCounter(getCounters(), strdup(counter), MVCT_ACTIVITY, i)); } } - return false; -} - -void MaliVideoDriver::resetCounters() { - for (MaliVideoCounter * counter = mCounters; counter != NULL; counter = counter->getNext()) { - counter->setEnabled(false); - } -} - -void MaliVideoDriver::setupCounter(Counter &counter) { - MaliVideoCounter *const maliVideoCounter = findCounter(counter); - if (maliVideoCounter == NULL) { - counter.setEnabled(false); - return; - } - maliVideoCounter->setEnabled(true); - counter.setKey(maliVideoCounter->getKey()); } int MaliVideoDriver::writeCounters(mxml_node_t *root) const { @@ -153,32 +85,39 @@ int MaliVideoDriver::writeCounters(mxml_node_t *root) const { return 0; } - int count = 0; - for (MaliVideoCounter * counter = mCounters; counter != NULL; counter = counter->getNext()) { - mxml_node_t *node = mxmlNewElement(root, "counter"); - mxmlElementSetAttr(node, "name", counter->getName()); - ++count; - } - - return count; + return super::writeCounters(root); } void MaliVideoDriver::marshalEnable(const MaliVideoCounterType type, char *const buf, const size_t bufsize, int &pos) { // size int numEnabled = 0; - for (MaliVideoCounter * counter = mCounters; counter != NULL; counter = counter->getNext()) { + for (MaliVideoCounter *counter = static_cast<MaliVideoCounter *>(getCounters()); counter != NULL; counter = static_cast<MaliVideoCounter *>(counter->getNext())) { if (counter->isEnabled() && (counter->getType() == type)) { ++numEnabled; } } Buffer::packInt(buf, bufsize, pos, numEnabled*sizeof(uint32_t)); - for (MaliVideoCounter * counter = mCounters; counter != NULL; counter = counter->getNext()) { + for (MaliVideoCounter *counter = static_cast<MaliVideoCounter *>(getCounters()); counter != NULL; counter = static_cast<MaliVideoCounter *>(counter->getNext())) { if (counter->isEnabled() && (counter->getType() == type)) { Buffer::packInt(buf, bufsize, pos, counter->getId()); } } } +static bool writeAll(const int mveUds, const char *const buf, const int pos) { + int written = 0; + while (written < pos) { + size_t bytes = ::write(mveUds, buf + written, pos - written); + if (bytes <= 0) { + logg->logMessage("%s(%s:%i): write failed", __FUNCTION__, __FILE__, __LINE__); + return false; + } + written += bytes; + } + + return true; +} + bool MaliVideoDriver::start(const int mveUds) { char buf[256]; int pos = 0; @@ -225,29 +164,28 @@ bool MaliVideoDriver::start(const int mveUds) { buf[pos++] = 'e'; marshalEnable(MVCT_EVENT, buf, sizeof(buf), pos); - /* // code - MVE_INSTR_ENABLE_ACTIVITIES buf[pos++] = 'C'; buf[pos++] = 'F'; buf[pos++] = 'G'; buf[pos++] = 'a'; - // size - Buffer::packInt(buf, sizeof(buf), pos, mActivityCount*sizeof(uint32_t)); - for (int i = 0; i < mActivityCount; ++i) { - // activity_id - Buffer::packInt(buf, sizeof(buf), pos, i); - } - */ + marshalEnable(MVCT_ACTIVITY, buf, sizeof(buf), pos); - int written = 0; - while (written < pos) { - size_t bytes = ::write(mveUds, buf + written, pos - written); - if (bytes <= 0) { - logg->logMessage("%s(%s:%i): write failed", __FUNCTION__, __FILE__, __LINE__); - return false; - } - written += bytes; - } + return writeAll(mveUds, buf, pos); +} - return true; +void MaliVideoDriver::stop(const int mveUds) { + char buf[8]; + int pos = 0; + + // code - MVE_INSTR_STOP + buf[pos++] = 'S'; + buf[pos++] = 'T'; + buf[pos++] = 'O'; + buf[pos++] = 'P'; + marshalEnable(MVCT_COUNTER, buf, sizeof(buf), pos); + + writeAll(mveUds, buf, pos); + + close(mveUds); } diff --git a/tools/gator/daemon/MaliVideoDriver.h b/tools/gator/daemon/MaliVideoDriver.h index 00cb80889a74..204a57a447ac 100644 --- a/tools/gator/daemon/MaliVideoDriver.h +++ b/tools/gator/daemon/MaliVideoDriver.h @@ -19,29 +19,24 @@ enum MaliVideoCounterType { MVCT_ACTIVITY, }; -class MaliVideoDriver : public Driver { +class MaliVideoDriver : public SimpleDriver { +private: + typedef SimpleDriver super; + public: MaliVideoDriver(); ~MaliVideoDriver(); - void setup(mxml_node_t *const xml); - - bool claimCounter(const Counter &counter) const; - bool countersEnabled() const; - void resetCounters(); - void setupCounter(Counter &counter); + void readEvents(mxml_node_t *const root); int writeCounters(mxml_node_t *root) const; bool start(const int mveUds); + void stop(const int mveUds); private: - MaliVideoCounter *findCounter(const Counter &counter) const; void marshalEnable(const MaliVideoCounterType type, char *const buf, const size_t bufsize, int &pos); - MaliVideoCounter *mCounters; - int mActivityCount; - // Intentionally unimplemented MaliVideoDriver(const MaliVideoDriver &); MaliVideoDriver &operator=(const MaliVideoDriver &); diff --git a/tools/gator/daemon/MemInfoDriver.cpp b/tools/gator/daemon/MemInfoDriver.cpp new file mode 100644 index 000000000000..cce15c16fcdc --- /dev/null +++ b/tools/gator/daemon/MemInfoDriver.cpp @@ -0,0 +1,93 @@ +/** + * Copyright (C) ARM Limited 2013-2014. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "MemInfoDriver.h" + +#include "Logging.h" +#include "SessionData.h" + +class MemInfoCounter : public DriverCounter { +public: + MemInfoCounter(DriverCounter *next, char *const name, int64_t *const value); + ~MemInfoCounter(); + + int64_t read(); + +private: + int64_t *const mValue; + + // Intentionally unimplemented + MemInfoCounter(const MemInfoCounter &); + MemInfoCounter &operator=(const MemInfoCounter &); +}; + +MemInfoCounter::MemInfoCounter(DriverCounter *next, char *const name, int64_t *const value) : DriverCounter(next, name), mValue(value) { +} + +MemInfoCounter::~MemInfoCounter() { +} + +int64_t MemInfoCounter::read() { + return *mValue; +} + +MemInfoDriver::MemInfoDriver() : mBuf(), mMemUsed(0), mMemFree(0), mBuffers(0) { +} + +MemInfoDriver::~MemInfoDriver() { +} + +void MemInfoDriver::readEvents(mxml_node_t *const) { + // Only for use with perf + if (!gSessionData->perf.isSetup()) { + return; + } + + setCounters(new MemInfoCounter(getCounters(), strdup("Linux_meminfo_memused2"), &mMemUsed)); + setCounters(new MemInfoCounter(getCounters(), strdup("Linux_meminfo_memfree"), &mMemFree)); + setCounters(new MemInfoCounter(getCounters(), strdup("Linux_meminfo_bufferram"), &mBuffers)); +} + +void MemInfoDriver::read(Buffer *const buffer) { + if (!countersEnabled()) { + return; + } + + if (!mBuf.read("/proc/meminfo")) { + logg->logError(__FILE__, __LINE__, "Failed to read /proc/meminfo"); + handleException(); + } + + char *key = mBuf.getBuf(); + char *colon; + int64_t memTotal = 0; + while ((colon = strchr(key, ':')) != NULL) { + char *end = strchr(colon + 1, '\n'); + if (end != NULL) { + *end = '\0'; + } + *colon = '\0'; + + if (strcmp(key, "MemTotal") == 0) { + memTotal = strtoll(colon + 1, NULL, 10) << 10; + } else if (strcmp(key, "MemFree") == 0) { + mMemFree = strtoll(colon + 1, NULL, 10) << 10; + } else if (strcmp(key, "Buffers") == 0) { + mBuffers = strtoll(colon + 1, NULL, 10) << 10; + } + + if (end == NULL) { + break; + } + key = end + 1; + } + + mMemUsed = memTotal - mMemFree; + + super::read(buffer); +} diff --git a/tools/gator/daemon/MemInfoDriver.h b/tools/gator/daemon/MemInfoDriver.h new file mode 100644 index 000000000000..eb1b0417f309 --- /dev/null +++ b/tools/gator/daemon/MemInfoDriver.h @@ -0,0 +1,37 @@ +/** + * Copyright (C) ARM Limited 2013-2014. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef MEMINFODRIVER_H +#define MEMINFODRIVER_H + +#include "Driver.h" +#include "DynBuf.h" + +class MemInfoDriver : public PolledDriver { +private: + typedef PolledDriver super; + +public: + MemInfoDriver(); + ~MemInfoDriver(); + + void readEvents(mxml_node_t *const root); + void read(Buffer *const buffer); + +private: + DynBuf mBuf; + int64_t mMemUsed; + int64_t mMemFree; + int64_t mBuffers; + + // Intentionally unimplemented + MemInfoDriver(const MemInfoDriver &); + MemInfoDriver &operator=(const MemInfoDriver &); +}; + +#endif // MEMINFODRIVER_H diff --git a/tools/gator/daemon/Monitor.cpp b/tools/gator/daemon/Monitor.cpp index b34a15f0eb0c..74f22ee29fec 100644 --- a/tools/gator/daemon/Monitor.cpp +++ b/tools/gator/daemon/Monitor.cpp @@ -9,6 +9,7 @@ #include "Monitor.h" #include <errno.h> +#include <fcntl.h> #include <string.h> #include <unistd.h> @@ -31,12 +32,25 @@ void Monitor::close() { } bool Monitor::init() { +#ifdef EPOLL_CLOEXEC + mFd = epoll_create1(EPOLL_CLOEXEC); +#else mFd = epoll_create(16); +#endif if (mFd < 0) { logg->logMessage("%s(%s:%i): epoll_create1 failed", __FUNCTION__, __FILE__, __LINE__); return false; } +#ifndef EPOLL_CLOEXEC + int fdf = fcntl(mFd, F_GETFD); + if ((fdf == -1) || (fcntl(mFd, F_SETFD, fdf | FD_CLOEXEC) != 0)) { + logg->logMessage("%s(%s:%i): fcntl failed", __FUNCTION__, __FILE__, __LINE__); + ::close(mFd); + return -1; + } +#endif + return true; } diff --git a/tools/gator/daemon/NetDriver.cpp b/tools/gator/daemon/NetDriver.cpp new file mode 100644 index 000000000000..e75c0695779a --- /dev/null +++ b/tools/gator/daemon/NetDriver.cpp @@ -0,0 +1,129 @@ +/** + * Copyright (C) ARM Limited 2013-2014. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +// Define to get format macros from inttypes.h +#define __STDC_FORMAT_MACROS + +#include "NetDriver.h" + +#include <inttypes.h> + +#include "Logging.h" +#include "SessionData.h" + +class NetCounter : public DriverCounter { +public: + NetCounter(DriverCounter *next, char *const name, int64_t *const value); + ~NetCounter(); + + int64_t read(); + +private: + int64_t *const mValue; + int64_t mPrev; + + // Intentionally unimplemented + NetCounter(const NetCounter &); + NetCounter &operator=(const NetCounter &); +}; + +NetCounter::NetCounter(DriverCounter *next, char *const name, int64_t *const value) : DriverCounter(next, name), mValue(value), mPrev(0) { +} + +NetCounter::~NetCounter() { +} + +int64_t NetCounter::read() { + int64_t result = *mValue - mPrev; + mPrev = *mValue; + return result; +} + +NetDriver::NetDriver() : mBuf(), mReceiveBytes(0), mTransmitBytes(0) { +} + +NetDriver::~NetDriver() { +} + +void NetDriver::readEvents(mxml_node_t *const) { + // Only for use with perf + if (!gSessionData->perf.isSetup()) { + return; + } + + setCounters(new NetCounter(getCounters(), strdup("Linux_net_rx"), &mReceiveBytes)); + setCounters(new NetCounter(getCounters(), strdup("Linux_net_tx"), &mTransmitBytes)); +} + +bool NetDriver::doRead() { + if (!countersEnabled()) { + return true; + } + + if (!mBuf.read("/proc/net/dev")) { + return false; + } + + // Skip the header + char *key; + if (((key = strchr(mBuf.getBuf(), '\n')) == NULL) || + ((key = strchr(key + 1, '\n')) == NULL)) { + return false; + } + key = key + 1; + + mReceiveBytes = 0; + mTransmitBytes = 0; + + char *colon; + while ((colon = strchr(key, ':')) != NULL) { + char *end = strchr(colon + 1, '\n'); + if (end != NULL) { + *end = '\0'; + } + *colon = '\0'; + + int64_t receiveBytes; + int64_t transmitBytes; + const int count = sscanf(colon + 1, " %" SCNu64 " %*u %*u %*u %*u %*u %*u %*u %" SCNu64, &receiveBytes, &transmitBytes); + if (count != 2) { + return false; + } + mReceiveBytes += receiveBytes; + mTransmitBytes += transmitBytes; + + if (end == NULL) { + break; + } + key = end + 1; + } + + return true; +} + +void NetDriver::start() { + if (!doRead()) { + logg->logError(__FILE__, __LINE__, "Unable to read network stats"); + handleException(); + } + // Initialize previous values + for (DriverCounter *counter = getCounters(); counter != NULL; counter = counter->getNext()) { + if (!counter->isEnabled()) { + continue; + } + counter->read(); + } +} + +void NetDriver::read(Buffer *const buffer) { + if (!doRead()) { + logg->logError(__FILE__, __LINE__, "Unable to read network stats"); + handleException(); + } + super::read(buffer); +} diff --git a/tools/gator/daemon/NetDriver.h b/tools/gator/daemon/NetDriver.h new file mode 100644 index 000000000000..50ff850bfc6d --- /dev/null +++ b/tools/gator/daemon/NetDriver.h @@ -0,0 +1,39 @@ +/** + * Copyright (C) ARM Limited 2013-2014. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef NETDRIVER_H +#define NETDRIVER_H + +#include "Driver.h" +#include "DynBuf.h" + +class NetDriver : public PolledDriver { +private: + typedef PolledDriver super; + +public: + NetDriver(); + ~NetDriver(); + + void readEvents(mxml_node_t *const root); + void start(); + void read(Buffer *const buffer); + +private: + bool doRead(); + + DynBuf mBuf; + int64_t mReceiveBytes; + int64_t mTransmitBytes; + + // Intentionally unimplemented + NetDriver(const NetDriver &); + NetDriver &operator=(const NetDriver &); +}; + +#endif // NETDRIVER_H diff --git a/tools/gator/daemon/OlySocket.cpp b/tools/gator/daemon/OlySocket.cpp index 28774e36e510..aa0ce4929916 100644 --- a/tools/gator/daemon/OlySocket.cpp +++ b/tools/gator/daemon/OlySocket.cpp @@ -15,10 +15,10 @@ #include <ws2tcpip.h> #else #include <netinet/in.h> -#include <sys/socket.h> #include <sys/un.h> #include <unistd.h> #include <netdb.h> +#include <fcntl.h> #endif #include "Logging.h" @@ -32,6 +32,48 @@ #define SHUTDOWN_RX_TX SHUT_RDWR #endif +int socket_cloexec(int domain, int type, int protocol) { +#ifdef SOCK_CLOEXEC + return socket(domain, type | SOCK_CLOEXEC, protocol); +#else + int sock = socket(domain, type, protocol); +#ifdef FD_CLOEXEC + if (sock < 0) { + return -1; + } + int fdf = fcntl(sock, F_GETFD); + if ((fdf == -1) || (fcntl(sock, F_SETFD, fdf | FD_CLOEXEC) != 0)) { + close(sock); + return -1; + } +#endif + return sock; +#endif +} + +int accept_cloexec(int sockfd, struct sockaddr *addr, socklen_t *addrlen) { + int sock; +#ifdef SOCK_CLOEXEC + sock = accept4(sockfd, addr, addrlen, SOCK_CLOEXEC); + if (sock >= 0) { + return sock; + } + // accept4 with SOCK_CLOEXEC may not work on all kernels, so fallback +#endif + sock = accept(sockfd, addr, addrlen); +#ifdef FD_CLOEXEC + if (sock < 0) { + return -1; + } + int fdf = fcntl(sock, F_GETFD); + if ((fdf == -1) || (fcntl(sock, F_SETFD, fdf | FD_CLOEXEC) != 0)) { + close(sock); + return -1; + } +#endif + return sock; +} + OlyServerSocket::OlyServerSocket(int port) { #ifdef WIN32 WSADATA wsaData; @@ -57,7 +99,7 @@ OlySocket::OlySocket(int socketID) : mSocketID(socketID) { OlyServerSocket::OlyServerSocket(const char* path, const size_t pathSize) { // Create socket - mFDServer = socket(PF_UNIX, SOCK_STREAM, 0); + mFDServer = socket_cloexec(PF_UNIX, SOCK_STREAM, 0); if (mFDServer < 0) { logg->logError(__FILE__, __LINE__, "Error creating server socket"); handleException(); @@ -84,7 +126,7 @@ OlyServerSocket::OlyServerSocket(const char* path, const size_t pathSize) { } int OlySocket::connect(const char* path, const size_t pathSize) { - int fd = socket(PF_UNIX, SOCK_STREAM, 0); + int fd = socket_cloexec(PF_UNIX, SOCK_STREAM, 0); if (fd < 0) { return -1; } @@ -143,10 +185,10 @@ void OlyServerSocket::createServerSocket(int port) { int family = AF_INET6; // Create socket - mFDServer = socket(PF_INET6, SOCK_STREAM, IPPROTO_TCP); + mFDServer = socket_cloexec(PF_INET6, SOCK_STREAM, IPPROTO_TCP); if (mFDServer < 0) { family = AF_INET; - mFDServer = socket(PF_INET, SOCK_STREAM, IPPROTO_TCP); + mFDServer = socket_cloexec(PF_INET, SOCK_STREAM, IPPROTO_TCP); if (mFDServer < 0) { logg->logError(__FILE__, __LINE__, "Error creating server socket"); handleException(); @@ -190,7 +232,7 @@ int OlyServerSocket::acceptConnection() { } // Accept a connection, note that this call blocks until a client connects - socketID = accept(mFDServer, NULL, NULL); + socketID = accept_cloexec(mFDServer, NULL, NULL); if (socketID < 0) { logg->logError(__FILE__, __LINE__, "Socket acceptance failed"); handleException(); diff --git a/tools/gator/daemon/OlySocket.h b/tools/gator/daemon/OlySocket.h index 20c67cc695e1..6b53b01fc3ee 100644 --- a/tools/gator/daemon/OlySocket.h +++ b/tools/gator/daemon/OlySocket.h @@ -11,6 +11,12 @@ #include <stddef.h> +#ifdef WIN32 +typedef socklen_t int; +#else +#include <sys/socket.h> +#endif + class OlySocket { public: #ifndef WIN32 @@ -52,4 +58,7 @@ private: void createServerSocket(int port); }; +int socket_cloexec(int domain, int type, int protocol); +int accept_cloexec(int sockfd, struct sockaddr *addr, socklen_t *addrlen); + #endif //__OLY_SOCKET_H__ diff --git a/tools/gator/daemon/PerfBuffer.cpp b/tools/gator/daemon/PerfBuffer.cpp index 5fad583f7bd0..f127c996d43b 100644 --- a/tools/gator/daemon/PerfBuffer.cpp +++ b/tools/gator/daemon/PerfBuffer.cpp @@ -20,6 +20,7 @@ PerfBuffer::PerfBuffer() { for (int cpu = 0; cpu < ARRAY_LENGTH(mBuf); ++cpu) { mBuf[cpu] = MAP_FAILED; mDiscard[cpu] = false; + mFds[cpu] = -1; } } @@ -31,8 +32,8 @@ PerfBuffer::~PerfBuffer() { } } -bool PerfBuffer::useFd(const int cpu, const int fd, const int groupFd) { - if (fd == groupFd) { +bool PerfBuffer::useFd(const int cpu, const int fd) { + if (mFds[cpu] < 0) { if (mBuf[cpu] != MAP_FAILED) { logg->logMessage("%s(%s:%i): cpu %i already online or not correctly cleaned up", __FUNCTION__, __FILE__, __LINE__, cpu); return false; @@ -44,6 +45,7 @@ bool PerfBuffer::useFd(const int cpu, const int fd, const int groupFd) { logg->logMessage("%s(%s:%i): mmap failed", __FUNCTION__, __FILE__, __LINE__); return false; } + mFds[cpu] = fd; // Check the version struct perf_event_mmap_page *pemp = static_cast<struct perf_event_mmap_page *>(mBuf[cpu]); @@ -57,7 +59,7 @@ bool PerfBuffer::useFd(const int cpu, const int fd, const int groupFd) { return false; } - if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, groupFd) < 0) { + if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, mFds[cpu]) < 0) { logg->logMessage("%s(%s:%i): ioctl failed", __FUNCTION__, __FILE__, __LINE__); return false; } @@ -89,6 +91,41 @@ bool PerfBuffer::isEmpty() { return true; } +static void compressAndSend(const int cpu, const __u64 head, __u64 tail, const uint8_t *const b, Sender *const sender) { + // Pick a big size but something smaller than the chunkSize in Sender::writeData which is 100k + char buf[1<<16]; + int writePos = 0; + const int typeLength = gSessionData->mLocalCapture ? 0 : 1; + + while (head > tail) { + writePos = 0; + if (!gSessionData->mLocalCapture) { + buf[writePos++] = RESPONSE_APC_DATA; + } + // Reserve space for size + writePos += sizeof(uint32_t); + Buffer::packInt(buf, sizeof(buf), writePos, FRAME_PERF); + Buffer::packInt(buf, sizeof(buf), writePos, cpu); + + while (head > tail) { + const int count = reinterpret_cast<const struct perf_event_header *>(b + (tail & BUF_MASK))->size/sizeof(uint64_t); + // Can this whole message be written as Streamline assumes events are not split between frames + if (sizeof(buf) <= writePos + count*Buffer::MAXSIZE_PACK64) { + break; + } + for (int i = 0; i < count; ++i) { + // Must account for message size + Buffer::packInt64(buf, sizeof(buf), writePos, *reinterpret_cast<const uint64_t *>(b + (tail & BUF_MASK))); + tail += sizeof(uint64_t); + } + } + + // Write size + Buffer::writeLEInt(reinterpret_cast<unsigned char *>(buf + typeLength), writePos - typeLength - sizeof(uint32_t)); + sender->writeData(buf, writePos, RESPONSE_APC_DATA); + } +} + bool PerfBuffer::send(Sender *const sender) { for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) { if (mBuf[cpu] == MAP_FAILED) { @@ -102,26 +139,7 @@ bool PerfBuffer::send(Sender *const sender) { if (head > tail) { const uint8_t *const b = static_cast<uint8_t *>(mBuf[cpu]) + gSessionData->mPageSize; - const int offset = gSessionData->mLocalCapture ? 1 : 0; - unsigned char header[7]; - header[0] = RESPONSE_APC_DATA; - Buffer::writeLEInt(header + 1, head - tail + sizeof(header) - 5); - // Should use real packing functions - header[5] = FRAME_PERF; - header[6] = cpu; - - // Write header - sender->writeData(reinterpret_cast<const char *>(&header) + offset, sizeof(header) - offset, RESPONSE_APC_DATA); - - // Write data - if ((head & ~BUF_MASK) == (tail & ~BUF_MASK)) { - // Not wrapped - sender->writeData(reinterpret_cast<const char *>(b + (tail & BUF_MASK)), head - tail, RESPONSE_APC_DATA); - } else { - // Wrapped - sender->writeData(reinterpret_cast<const char *>(b + (tail & BUF_MASK)), BUF_SIZE - (tail & BUF_MASK), RESPONSE_APC_DATA); - sender->writeData(reinterpret_cast<const char *>(b), head & BUF_MASK, RESPONSE_APC_DATA); - } + compressAndSend(cpu, head, tail, b, sender); // Update tail with the data read pemp->data_tail = head; @@ -131,6 +149,7 @@ bool PerfBuffer::send(Sender *const sender) { munmap(mBuf[cpu], gSessionData->mPageSize + BUF_SIZE); mBuf[cpu] = MAP_FAILED; mDiscard[cpu] = false; + mFds[cpu] = -1; logg->logMessage("%s(%s:%i): Unmaped cpu %i", __FUNCTION__, __FILE__, __LINE__, cpu); } } diff --git a/tools/gator/daemon/PerfBuffer.h b/tools/gator/daemon/PerfBuffer.h index 278a3b9d6db7..25a10625a9e8 100644 --- a/tools/gator/daemon/PerfBuffer.h +++ b/tools/gator/daemon/PerfBuffer.h @@ -21,7 +21,7 @@ public: PerfBuffer(); ~PerfBuffer(); - bool useFd(const int cpu, const int fd, const int groupFd); + bool useFd(const int cpu, const int fd); void discard(const int cpu); bool isEmpty(); bool send(Sender *const sender); @@ -30,6 +30,8 @@ private: void *mBuf[NR_CPUS]; // After the buffer is flushed it should be unmaped bool mDiscard[NR_CPUS]; + // fd that corresponds to the mBuf + int mFds[NR_CPUS]; // Intentionally undefined PerfBuffer(const PerfBuffer &); diff --git a/tools/gator/daemon/PerfDriver.cpp b/tools/gator/daemon/PerfDriver.cpp index ac97a077d266..ee90284cee41 100644 --- a/tools/gator/daemon/PerfDriver.cpp +++ b/tools/gator/daemon/PerfDriver.cpp @@ -22,6 +22,7 @@ #include "Logging.h" #include "PerfGroup.h" #include "SessionData.h" +#include "Setup.h" #define PERF_DEVICES "/sys/bus/event_source/devices" @@ -47,7 +48,6 @@ static const struct gator_cpu gator_cpus[] = { { 0xc07, "Cortex-A7", "ARMv7_Cortex_A7", 4 }, { 0xc08, "Cortex-A8", "ARMv7_Cortex_A8", 4 }, { 0xc09, "Cortex-A9", "ARMv7_Cortex_A9", 6 }, - { 0xc0d, "Cortex-A12", "ARMv7_Cortex_A12", 6 }, { 0xc0f, "Cortex-A15", "ARMv7_Cortex_A15", 6 }, { 0xc0e, "Cortex-A17", "ARMv7_Cortex_A17", 6 }, { 0x00f, "Scorpion", "Scorpion", 4 }, @@ -64,68 +64,57 @@ static const char OLD_PMU_PREFIX[] = "ARMv7 Cortex-"; static const char NEW_PMU_PREFIX[] = "ARMv7_Cortex_"; struct uncore_counter { - // gatorfs event and Perf PMU name - const char *const name; + // Perf PMU name + const char *const perfName; + // gatorfs event name + const char *const gatorName; const int count; }; static const struct uncore_counter uncore_counters[] = { - { "CCI_400", 4 }, - { "CCI_400-r1", 4 }, + { "CCI_400", "CCI_400", 4 }, + { "CCI_400-r1", "CCI_400-r1", 4 }, + { "ccn", "ARM_CCN_5XX", 8 }, }; -class PerfCounter { +class PerfCounter : public DriverCounter { public: - PerfCounter(PerfCounter *next, const char *name, uint32_t type, uint64_t config, bool perCpu) : mNext(next), mName(name), mType(type), mCount(0), mKey(getEventKey()), mConfig(config), mEnabled(false), mPerCpu(perCpu) {} + PerfCounter(DriverCounter *next, const char *name, uint32_t type, uint64_t config, bool perCpu) : DriverCounter(next, name), mType(type), mCount(0), mConfig(config), mPerCpu(perCpu) {} + ~PerfCounter() { - delete [] mName; } - PerfCounter *getNext() const { return mNext; } - const char *getName() const { return mName; } uint32_t getType() const { return mType; } int getCount() const { return mCount; } void setCount(const int count) { mCount = count; } - int getKey() const { return mKey; } uint64_t getConfig() const { return mConfig; } void setConfig(const uint64_t config) { mConfig = config; } - bool isEnabled() const { return mEnabled; } - void setEnabled(const bool enabled) { mEnabled = enabled; } bool isPerCpu() const { return mPerCpu; } private: - PerfCounter *const mNext; - const char *const mName; const uint32_t mType; int mCount; - const int mKey; uint64_t mConfig; - int mEnabled : 1, - mPerCpu : 1; + bool mPerCpu; }; -PerfDriver::PerfDriver() : mCounters(NULL), mIsSetup(false), mLegacySupport(false) { +PerfDriver::PerfDriver() : mIsSetup(false), mLegacySupport(false) { } PerfDriver::~PerfDriver() { - while (mCounters != NULL) { - PerfCounter *counter = mCounters; - mCounters = counter->getNext(); - delete counter; - } } void PerfDriver::addCpuCounters(const char *const counterName, const int type, const int numCounters) { int len = snprintf(NULL, 0, "%s_ccnt", counterName) + 1; char *name = new char[len]; snprintf(name, len, "%s_ccnt", counterName); - mCounters = new PerfCounter(mCounters, name, type, -1, true); + setCounters(new PerfCounter(getCounters(), name, type, -1, true)); for (int j = 0; j < numCounters; ++j) { len = snprintf(NULL, 0, "%s_cnt%d", counterName, j) + 1; name = new char[len]; snprintf(name, len, "%s_cnt%d", counterName, j); - mCounters = new PerfCounter(mCounters, name, type, -1, true); + setCounters(new PerfCounter(getCounters(), name, type, -1, true)); } } @@ -133,40 +122,24 @@ void PerfDriver::addUncoreCounters(const char *const counterName, const int type int len = snprintf(NULL, 0, "%s_ccnt", counterName) + 1; char *name = new char[len]; snprintf(name, len, "%s_ccnt", counterName); - mCounters = new PerfCounter(mCounters, name, type, -1, false); + setCounters(new PerfCounter(getCounters(), name, type, -1, false)); for (int j = 0; j < numCounters; ++j) { len = snprintf(NULL, 0, "%s_cnt%d", counterName, j) + 1; name = new char[len]; snprintf(name, len, "%s_cnt%d", counterName, j); - mCounters = new PerfCounter(mCounters, name, type, -1, false); + setCounters(new PerfCounter(getCounters(), name, type, -1, false)); } } -// From include/generated/uapi/linux/version.h -#define KERNEL_VERSION(a,b,c) (((a) << 16) + ((b) << 8) + (c)) - bool PerfDriver::setup() { // Check the kernel version - struct utsname utsname; - if (uname(&utsname) != 0) { - logg->logMessage("%s(%s:%i): uname failed", __FUNCTION__, __FILE__, __LINE__); + int release[3]; + if (!getLinuxVersion(release)) { + logg->logMessage("%s(%s:%i): getLinuxVersion failed", __FUNCTION__, __FILE__, __LINE__); return false; } - int release[3] = { 0, 0, 0 }; - int part = 0; - char *ch = utsname.release; - while (*ch >= '0' && *ch <= '9' && part < ARRAY_LENGTH(release)) { - release[part] = 10*release[part] + *ch - '0'; - - ++ch; - if (*ch == '.') { - ++part; - ++ch; - } - } - if (KERNEL_VERSION(release[0], release[1], release[2]) < KERNEL_VERSION(3, 4, 0)) { logg->logMessage("%s(%s:%i): Unsupported kernel version", __FUNCTION__, __FILE__, __LINE__); return false; @@ -174,7 +147,7 @@ bool PerfDriver::setup() { mLegacySupport = KERNEL_VERSION(release[0], release[1], release[2]) < KERNEL_VERSION(3, 12, 0); if (access(EVENTS_PATH, R_OK) != 0) { - logg->logMessage("%s(%s:%i): " EVENTS_PATH " does not exist, is CONFIG_TRACING enabled?", __FUNCTION__, __FILE__, __LINE__); + logg->logMessage("%s(%s:%i): " EVENTS_PATH " does not exist, is CONFIG_TRACING and CONFIG_CONTEXT_SWITCH_TRACER enabled?", __FUNCTION__, __FILE__, __LINE__); return false; } @@ -189,12 +162,14 @@ bool PerfDriver::setup() { struct dirent *dirent; while ((dirent = readdir(dir)) != NULL) { for (int i = 0; i < ARRAY_LENGTH(gator_cpus); ++i) { + const struct gator_cpu *const gator_cpu = &gator_cpus[i]; + // Do the names match exactly? - if (strcmp(dirent->d_name, gator_cpus[i].pmnc_name) != 0 && - // Do these names match but have the old vs new prefix? - (strncmp(dirent->d_name, OLD_PMU_PREFIX, sizeof(OLD_PMU_PREFIX) - 1) != 0 || - strncmp(gator_cpus[i].pmnc_name, NEW_PMU_PREFIX, sizeof(NEW_PMU_PREFIX) - 1) != 0 || - strcmp(dirent->d_name + sizeof(OLD_PMU_PREFIX) - 1, gator_cpus[i].pmnc_name + sizeof(NEW_PMU_PREFIX) - 1) != 0)) { + if (strcasecmp(gator_cpu->pmnc_name, dirent->d_name) != 0 && + // Do these names match but have the old vs new prefix? + ((strncasecmp(dirent->d_name, OLD_PMU_PREFIX, sizeof(OLD_PMU_PREFIX) - 1) != 0 || + strncasecmp(gator_cpu->pmnc_name, NEW_PMU_PREFIX, sizeof(NEW_PMU_PREFIX) - 1) != 0 || + strcasecmp(dirent->d_name + sizeof(OLD_PMU_PREFIX) - 1, gator_cpu->pmnc_name + sizeof(NEW_PMU_PREFIX) - 1) != 0))) { continue; } @@ -206,11 +181,12 @@ bool PerfDriver::setup() { } foundCpu = true; - addCpuCounters(gator_cpus[i].pmnc_name, type, gator_cpus[i].pmnc_counters); + logg->logMessage("Adding cpu counters for %s", gator_cpu->pmnc_name); + addCpuCounters(gator_cpu->pmnc_name, type, gator_cpu->pmnc_counters); } for (int i = 0; i < ARRAY_LENGTH(uncore_counters); ++i) { - if (strcmp(dirent->d_name, uncore_counters[i].name) != 0) { + if (strcmp(dirent->d_name, uncore_counters[i].perfName) != 0) { continue; } @@ -221,7 +197,8 @@ bool PerfDriver::setup() { continue; } - addUncoreCounters(uncore_counters[i].name, type, uncore_counters[i].count); + logg->logMessage("Adding uncore counters for %s", uncore_counters[i].gatorName); + addUncoreCounters(uncore_counters[i].gatorName, type, uncore_counters[i].count); } } closedir(dir); @@ -234,6 +211,7 @@ bool PerfDriver::setup() { } foundCpu = true; + logg->logMessage("Adding cpu counters (based on cpuid) for %s", gator_cpus[i].pmnc_name); addCpuCounters(gator_cpus[i].pmnc_name, PERF_TYPE_RAW, gator_cpus[i].pmnc_counters); } } @@ -252,31 +230,20 @@ bool PerfDriver::setup() { id = getTracepointId("irq/softirq_exit", &printb); if (id >= 0) { - mCounters = new PerfCounter(mCounters, "Linux_irq_softirq", PERF_TYPE_TRACEPOINT, id, true); + setCounters(new PerfCounter(getCounters(), "Linux_irq_softirq", PERF_TYPE_TRACEPOINT, id, true)); } id = getTracepointId("irq/irq_handler_exit", &printb); if (id >= 0) { - mCounters = new PerfCounter(mCounters, "Linux_irq_irq", PERF_TYPE_TRACEPOINT, id, true); + setCounters(new PerfCounter(getCounters(), "Linux_irq_irq", PERF_TYPE_TRACEPOINT, id, true)); } - //Linux_block_rq_wr - //Linux_block_rq_rd - //Linux_net_rx - //Linux_net_tx - id = getTracepointId(SCHED_SWITCH, &printb); if (id >= 0) { - mCounters = new PerfCounter(mCounters, "Linux_sched_switch", PERF_TYPE_TRACEPOINT, id, true); + setCounters(new PerfCounter(getCounters(), "Linux_sched_switch", PERF_TYPE_TRACEPOINT, id, true)); } - //Linux_meminfo_memused - //Linux_meminfo_memfree - //Linux_meminfo_bufferram - //Linux_power_cpu_freq - //Linux_power_cpu_idle - - mCounters = new PerfCounter(mCounters, "Linux_cpu_wait_contention", TYPE_DERIVED, -1, false); + setCounters(new PerfCounter(getCounters(), "Linux_cpu_wait_contention", TYPE_DERIVED, -1, false)); //Linux_cpu_wait_io @@ -299,62 +266,48 @@ bool PerfDriver::summary(Buffer *const buffer) { logg->logMessage("%s(%s:%i): clock_gettime failed", __FUNCTION__, __FILE__, __LINE__); return false; } - const int64_t timestamp = (int64_t)ts.tv_sec * 1000000000L + ts.tv_nsec; + const int64_t timestamp = (int64_t)ts.tv_sec * NS_PER_S + ts.tv_nsec; - const int64_t uptime = getTime(); + const uint64_t monotonicStarted = getTime(); + gSessionData->mMonotonicStarted = monotonicStarted; - buffer->summary(timestamp, uptime, 0, buf); + buffer->summary(monotonicStarted, timestamp, monotonicStarted, monotonicStarted, buf); for (int i = 0; i < gSessionData->mCores; ++i) { - // Don't send information on a cpu we know nothing about - if (gSessionData->mCpuIds[i] == -1) { - continue; - } - - int j; - for (j = 0; j < ARRAY_LENGTH(gator_cpus); ++j) { - if (gator_cpus[j].cpuid == gSessionData->mCpuIds[i]) { - break; - } - } - if (gator_cpus[j].cpuid == gSessionData->mCpuIds[i]) { - buffer->coreName(i, gSessionData->mCpuIds[i], gator_cpus[j].core_name); - } else { - if (gSessionData->mCpuIds[i] == -1) { - snprintf(buf, sizeof(buf), "Unknown"); - } else { - snprintf(buf, sizeof(buf), "Unknown (0x%.3x)", gSessionData->mCpuIds[i]); - } - buffer->coreName(i, gSessionData->mCpuIds[i], buf); - } + coreName(monotonicStarted, buffer, i); } - buffer->commit(1); + buffer->commit(monotonicStarted); return true; } -PerfCounter *PerfDriver::findCounter(const Counter &counter) const { - for (PerfCounter * perfCounter = mCounters; perfCounter != NULL; perfCounter = perfCounter->getNext()) { - if (strcmp(perfCounter->getName(), counter.getType()) == 0) { - return perfCounter; - } +void PerfDriver::coreName(const uint32_t startTime, Buffer *const buffer, const int cpu) { + // Don't send information on a cpu we know nothing about + if (gSessionData->mCpuIds[cpu] == -1) { + return; } - return NULL; -} - -bool PerfDriver::claimCounter(const Counter &counter) const { - return findCounter(counter) != NULL; -} - -void PerfDriver::resetCounters() { - for (PerfCounter * counter = mCounters; counter != NULL; counter = counter->getNext()) { - counter->setEnabled(false); + int j; + for (j = 0; j < ARRAY_LENGTH(gator_cpus); ++j) { + if (gator_cpus[j].cpuid == gSessionData->mCpuIds[cpu]) { + break; + } + } + if (gator_cpus[j].cpuid == gSessionData->mCpuIds[cpu]) { + buffer->coreName(startTime, cpu, gSessionData->mCpuIds[cpu], gator_cpus[j].core_name); + } else { + char buf[32]; + if (gSessionData->mCpuIds[cpu] == -1) { + snprintf(buf, sizeof(buf), "Unknown"); + } else { + snprintf(buf, sizeof(buf), "Unknown (0x%.3x)", gSessionData->mCpuIds[cpu]); + } + buffer->coreName(startTime, cpu, gSessionData->mCpuIds[cpu], buf); } } void PerfDriver::setupCounter(Counter &counter) { - PerfCounter *const perfCounter = findCounter(counter); + PerfCounter *const perfCounter = static_cast<PerfCounter *>(findCounter(counter)); if (perfCounter == NULL) { counter.setEnabled(false); return; @@ -369,21 +322,10 @@ void PerfDriver::setupCounter(Counter &counter) { counter.setKey(perfCounter->getKey()); } -int PerfDriver::writeCounters(mxml_node_t *root) const { - int count = 0; - for (PerfCounter * counter = mCounters; counter != NULL; counter = counter->getNext()) { - mxml_node_t *node = mxmlNewElement(root, "counter"); - mxmlElementSetAttr(node, "name", counter->getName()); - ++count; - } - - return count; -} - -bool PerfDriver::enable(PerfGroup *const group, Buffer *const buffer) const { - for (PerfCounter * counter = mCounters; counter != NULL; counter = counter->getNext()) { +bool PerfDriver::enable(const uint64_t currTime, PerfGroup *const group, Buffer *const buffer) const { + for (PerfCounter *counter = static_cast<PerfCounter *>(getCounters()); counter != NULL; counter = static_cast<PerfCounter *>(counter->getNext())) { if (counter->isEnabled() && (counter->getType() != TYPE_DERIVED)) { - if (!group->add(buffer, counter->getKey(), counter->getType(), counter->getConfig(), counter->getCount(), counter->getCount() > 0 ? PERF_SAMPLE_TID | PERF_SAMPLE_IP : 0, counter->isPerCpu() ? PERF_GROUP_PER_CPU : 0)) { + if (!group->add(currTime, buffer, counter->getKey(), counter->getType(), counter->getConfig(), counter->getCount(), counter->getCount() > 0 ? PERF_SAMPLE_TID | PERF_SAMPLE_IP : 0, counter->isPerCpu() ? PERF_GROUP_PER_CPU : 0)) { logg->logMessage("%s(%s:%i): PerfGroup::add failed", __FUNCTION__, __FILE__, __LINE__); return false; } diff --git a/tools/gator/daemon/PerfDriver.h b/tools/gator/daemon/PerfDriver.h index 2cae575a7059..846203a9e18b 100644 --- a/tools/gator/daemon/PerfDriver.h +++ b/tools/gator/daemon/PerfDriver.h @@ -9,6 +9,8 @@ #ifndef PERFDRIVER_H #define PERFDRIVER_H +#include <stdint.h> + #include "Driver.h" // If debugfs is not mounted at /sys/kernel/debug, update DEBUGFS_PATH @@ -16,13 +18,13 @@ #define EVENTS_PATH DEBUGFS_PATH "/tracing/events" #define SCHED_SWITCH "sched/sched_switch" +#define CPU_IDLE "power/cpu_idle" class Buffer; class DynBuf; -class PerfCounter; class PerfGroup; -class PerfDriver : public Driver { +class PerfDriver : public SimpleDriver { public: PerfDriver(); ~PerfDriver(); @@ -31,24 +33,19 @@ public: bool setup(); bool summary(Buffer *const buffer); + void coreName(const uint32_t startTime, Buffer *const buffer, const int cpu); bool isSetup() const { return mIsSetup; } - bool claimCounter(const Counter &counter) const; - void resetCounters(); void setupCounter(Counter &counter); - int writeCounters(mxml_node_t *root) const; - - bool enable(PerfGroup *const group, Buffer *const buffer) const; + bool enable(const uint64_t currTime, PerfGroup *const group, Buffer *const buffer) const; static long long getTracepointId(const char *const name, DynBuf *const printb); private: - PerfCounter *findCounter(const Counter &counter) const; void addCpuCounters(const char *const counterName, const int type, const int numCounters); void addUncoreCounters(const char *const counterName, const int type, const int numCounters); - PerfCounter *mCounters; bool mIsSetup; bool mLegacySupport; diff --git a/tools/gator/daemon/PerfGroup.cpp b/tools/gator/daemon/PerfGroup.cpp index 2a0239f7c348..4fd960a9058c 100644 --- a/tools/gator/daemon/PerfGroup.cpp +++ b/tools/gator/daemon/PerfGroup.cpp @@ -9,6 +9,7 @@ #include "PerfGroup.h" #include <errno.h> +#include <fcntl.h> #include <string.h> #include <sys/ioctl.h> #include <sys/syscall.h> @@ -33,10 +34,19 @@ /* have a sampling interrupt happen when we cross the wakeup_watermark boundary */ \ pea.watermark = 1; \ /* Be conservative in flush size as only one buffer set is monitored */ \ - pea.wakeup_watermark = 3 * BUF_SIZE / 4 + pea.wakeup_watermark = BUF_SIZE / 2 static int sys_perf_event_open(struct perf_event_attr *const attr, const pid_t pid, const int cpu, const int group_fd, const unsigned long flags) { - return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags); + int fd = syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags); + if (fd < 0) { + return -1; + } + int fdf = fcntl(fd, F_GETFD); + if ((fdf == -1) || (fcntl(fd, F_SETFD, fdf | FD_CLOEXEC) != 0)) { + close(fd); + return -1; + } + return fd; } PerfGroup::PerfGroup(PerfBuffer *const pb) : mPb(pb) { @@ -54,7 +64,7 @@ PerfGroup::~PerfGroup() { } } -bool PerfGroup::add(Buffer *const buffer, const int key, const __u32 type, const __u64 config, const __u64 sample, const __u64 sampleType, const int flags) { +bool PerfGroup::add(const uint64_t currTime, Buffer *const buffer, const int key, const __u32 type, const __u64 config, const __u64 sample, const __u64 sampleType, const int flags) { int i; for (i = 0; i < ARRAY_LENGTH(mKeys); ++i) { if (mKeys[i] < 0) { @@ -82,12 +92,12 @@ bool PerfGroup::add(Buffer *const buffer, const int key, const __u32 type, const mKeys[i] = key; - buffer->pea(&mAttrs[i], key); + buffer->pea(currTime, &mAttrs[i], key); return true; } -bool PerfGroup::prepareCPU(const int cpu) { +int PerfGroup::prepareCPU(const int cpu, Monitor *const monitor) { logg->logMessage("%s(%s:%i): Onlining cpu %i", __FUNCTION__, __FILE__, __LINE__, cpu); for (int i = 0; i < ARRAY_LENGTH(mKeys); ++i) { @@ -102,26 +112,35 @@ bool PerfGroup::prepareCPU(const int cpu) { const int offset = i * gSessionData->mCores; if (mFds[cpu + offset] >= 0) { logg->logMessage("%s(%s:%i): cpu already online or not correctly cleaned up", __FUNCTION__, __FILE__, __LINE__); - return false; + return PG_FAILURE; } logg->logMessage("%s(%s:%i): perf_event_open cpu: %i type: %lli config: %lli sample: %lli sample_type: 0x%llx pinned: %i mmap: %i comm: %i freq: %i task: %i sample_id_all: %i", __FUNCTION__, __FILE__, __LINE__, cpu, (long long)mAttrs[i].type, (long long)mAttrs[i].config, (long long)mAttrs[i].sample_period, (long long)mAttrs[i].sample_type, mAttrs[i].pinned, mAttrs[i].mmap, mAttrs[i].comm, mAttrs[i].freq, mAttrs[i].task, mAttrs[i].sample_id_all); mFds[cpu + offset] = sys_perf_event_open(&mAttrs[i], -1, cpu, i == 0 ? -1 : mFds[cpu], i == 0 ? 0 : PERF_FLAG_FD_OUTPUT); if (mFds[cpu + offset] < 0) { logg->logMessage("%s(%s:%i): failed %s", __FUNCTION__, __FILE__, __LINE__, strerror(errno)); + if (errno == ENODEV) { + return PG_CPU_OFFLINE; + } continue; } - if (!mPb->useFd(cpu, mFds[cpu + offset], mFds[cpu])) { + if (!mPb->useFd(cpu, mFds[cpu + offset])) { logg->logMessage("%s(%s:%i): PerfBuffer::useFd failed", __FUNCTION__, __FILE__, __LINE__); - return false; + return PG_FAILURE; + } + + + if (!monitor->add(mFds[cpu + offset])) { + logg->logMessage("%s(%s:%i): Monitor::add failed", __FUNCTION__, __FILE__, __LINE__); + return PG_FAILURE; } } - return true; + return PG_SUCCESS; } -int PerfGroup::onlineCPU(const int cpu, const bool start, Buffer *const buffer, Monitor *const monitor) { +int PerfGroup::onlineCPU(const uint64_t currTime, const int cpu, const bool start, Buffer *const buffer) { __u64 ids[ARRAY_LENGTH(mKeys)]; int coreKeys[ARRAY_LENGTH(mKeys)]; int idCount = 0; @@ -137,38 +156,37 @@ int PerfGroup::onlineCPU(const int cpu, const bool start, Buffer *const buffer, // Workaround for running 32-bit gatord on 64-bit systems, kernel patch in the works ioctl(fd, (PERF_EVENT_IOC_ID & ~IOCSIZE_MASK) | (8 << _IOC_SIZESHIFT), &ids[idCount]) != 0) { logg->logMessage("%s(%s:%i): ioctl failed", __FUNCTION__, __FILE__, __LINE__); - return false; + return 0; } ++idCount; } - if (!monitor->add(mFds[cpu])) { - logg->logMessage("%s(%s:%i): Monitor::add failed", __FUNCTION__, __FILE__, __LINE__); - return false; - } - if (!gSessionData->perf.getLegacySupport()) { - buffer->keys(idCount, ids, coreKeys); + buffer->keys(currTime, idCount, ids, coreKeys); } else { char buf[1024]; ssize_t bytes = read(mFds[cpu], buf, sizeof(buf)); if (bytes < 0) { logg->logMessage("read failed"); - return false; + return 0; } - buffer->keysOld(idCount, coreKeys, bytes, buf); + buffer->keysOld(currTime, idCount, coreKeys, bytes, buf); } if (start) { for (int i = 0; i < ARRAY_LENGTH(mKeys); ++i) { int offset = i * gSessionData->mCores + cpu; - if (mFds[offset] >= 0 && ioctl(mFds[offset], PERF_EVENT_IOC_ENABLE) < 0) { + if (mFds[offset] >= 0 && ioctl(mFds[offset], PERF_EVENT_IOC_ENABLE, 0) < 0) { logg->logMessage("%s(%s:%i): ioctl failed", __FUNCTION__, __FILE__, __LINE__); - return false; + return 0; } } } + if (idCount == 0) { + logg->logMessage("%s(%s:%i): no events came online", __FUNCTION__, __FILE__, __LINE__); + } + return idCount; } @@ -177,7 +195,7 @@ bool PerfGroup::offlineCPU(const int cpu) { for (int i = 0; i < ARRAY_LENGTH(mKeys); ++i) { int offset = i * gSessionData->mCores + cpu; - if (mFds[offset] >= 0 && ioctl(mFds[offset], PERF_EVENT_IOC_DISABLE) < 0) { + if (mFds[offset] >= 0 && ioctl(mFds[offset], PERF_EVENT_IOC_DISABLE, 0) < 0) { logg->logMessage("%s(%s:%i): ioctl failed", __FUNCTION__, __FILE__, __LINE__); return false; } @@ -203,7 +221,7 @@ bool PerfGroup::offlineCPU(const int cpu) { bool PerfGroup::start() { for (int pos = 0; pos < ARRAY_LENGTH(mFds); ++pos) { - if (mFds[pos] >= 0 && ioctl(mFds[pos], PERF_EVENT_IOC_ENABLE) < 0) { + if (mFds[pos] >= 0 && ioctl(mFds[pos], PERF_EVENT_IOC_ENABLE, 0) < 0) { logg->logMessage("%s(%s:%i): ioctl failed", __FUNCTION__, __FILE__, __LINE__); goto fail; } @@ -220,7 +238,7 @@ bool PerfGroup::start() { void PerfGroup::stop() { for (int pos = ARRAY_LENGTH(mFds) - 1; pos >= 0; --pos) { if (mFds[pos] >= 0) { - ioctl(mFds[pos], PERF_EVENT_IOC_DISABLE); + ioctl(mFds[pos], PERF_EVENT_IOC_DISABLE, 0); } } } diff --git a/tools/gator/daemon/PerfGroup.h b/tools/gator/daemon/PerfGroup.h index 3f1e2bb4d1c8..f7b3d725bac7 100644 --- a/tools/gator/daemon/PerfGroup.h +++ b/tools/gator/daemon/PerfGroup.h @@ -9,6 +9,8 @@ #ifndef PERF_GROUP #define PERF_GROUP +#include <stdint.h> + // Use a snapshot of perf_event.h as it may be more recent than what is on the target and if not newer features won't be supported anyways #include "k/perf_event.h" @@ -27,16 +29,22 @@ enum PerfGroupFlags { PERF_GROUP_PER_CPU = 1 << 5, }; +enum { + PG_SUCCESS = 0, + PG_FAILURE, + PG_CPU_OFFLINE, +}; + class PerfGroup { public: PerfGroup(PerfBuffer *const pb); ~PerfGroup(); - bool add(Buffer *const buffer, const int key, const __u32 type, const __u64 config, const __u64 sample, const __u64 sampleType, const int flags); + bool add(const uint64_t currTime, Buffer *const buffer, const int key, const __u32 type, const __u64 config, const __u64 sample, const __u64 sampleType, const int flags); // Safe to call concurrently - bool prepareCPU(const int cpu); + int prepareCPU(const int cpu, Monitor *const monitor); // Not safe to call concurrently. Returns the number of events enabled - int onlineCPU(const int cpu, const bool start, Buffer *const buffer, Monitor *const monitor); + int onlineCPU(const uint64_t currTime, const int cpu, const bool start, Buffer *const buffer); bool offlineCPU(int cpu); bool start(); void stop(); diff --git a/tools/gator/daemon/PerfSource.cpp b/tools/gator/daemon/PerfSource.cpp index ecfaa66832bd..193b7789a290 100644 --- a/tools/gator/daemon/PerfSource.cpp +++ b/tools/gator/daemon/PerfSource.cpp @@ -8,8 +8,14 @@ #include "PerfSource.h" +#include <dirent.h> #include <errno.h> +#include <signal.h> #include <string.h> +#include <sys/prctl.h> +#include <sys/resource.h> +#include <sys/syscall.h> +#include <sys/types.h> #include <unistd.h> #include "Child.h" @@ -19,11 +25,13 @@ #include "Proc.h" #include "SessionData.h" -#define MS_PER_US 1000000 +#ifndef SCHED_RESET_ON_FORK +#define SCHED_RESET_ON_FORK 0x40000000 +#endif extern Child *child; -static bool sendTracepointFormat(Buffer *const buffer, const char *const name, DynBuf *const printb, DynBuf *const b) { +static bool sendTracepointFormat(const uint64_t currTime, Buffer *const buffer, const char *const name, DynBuf *const printb, DynBuf *const b) { if (!printb->printf(EVENTS_PATH "/%s/format", name)) { logg->logMessage("%s(%s:%i): DynBuf::printf failed", __FUNCTION__, __FILE__, __LINE__); return false; @@ -32,47 +40,112 @@ static bool sendTracepointFormat(Buffer *const buffer, const char *const name, D logg->logMessage("%s(%s:%i): DynBuf::read failed", __FUNCTION__, __FILE__, __LINE__); return false; } - buffer->format(b->getLength(), b->getBuf()); + buffer->format(currTime, b->getLength(), b->getBuf()); return true; } -PerfSource::PerfSource(sem_t *senderSem, sem_t *startProfile) : mSummary(0, FRAME_SUMMARY, 1024, senderSem), mBuffer(0, FRAME_PERF_ATTRS, 4*1024*1024, senderSem), mCountersBuf(), mCountersGroup(&mCountersBuf), mMonitor(), mUEvent(), mSenderSem(senderSem), mStartProfile(startProfile), mInterruptFd(-1), mIsDone(false) { - long l = sysconf(_SC_PAGE_SIZE); - if (l < 0) { - logg->logError(__FILE__, __LINE__, "Unable to obtain the page size"); +static void *syncFunc(void *arg) +{ + struct timespec ts; + int64_t nextTime = gSessionData->mMonotonicStarted; + int err; + (void)arg; + + prctl(PR_SET_NAME, (unsigned long)&"gatord-sync", 0, 0, 0); + + // Mask all signals so that this thread will not be woken up + { + sigset_t set; + if (sigfillset(&set) != 0) { + logg->logError(__FILE__, __LINE__, "sigfillset failed"); + handleException(); + } + if ((err = pthread_sigmask(SIG_SETMASK, &set, NULL)) != 0) { + logg->logError(__FILE__, __LINE__, "pthread_sigmask failed"); + handleException(); + } + } + + for (;;) { + if (clock_gettime(CLOCK_MONOTONIC_RAW, &ts) != 0) { + logg->logError(__FILE__, __LINE__, "clock_gettime failed"); + handleException(); + } + const int64_t currTime = ts.tv_sec * NS_PER_S + ts.tv_nsec; + + // Wake up once a second + nextTime += NS_PER_S; + + // Always sleep more than 1 ms, hopefully things will line up better next time + const int64_t sleepTime = max(nextTime - currTime, (int64_t)(NS_PER_MS + 1)); + ts.tv_sec = sleepTime/NS_PER_S; + ts.tv_nsec = sleepTime % NS_PER_S; + + err = nanosleep(&ts, NULL); + if (err != 0) { + fprintf(stderr, "clock_nanosleep failed: %s\n", strerror(err)); + return NULL; + } + } + + return NULL; +} + +static long getMaxCoreNum() { + DIR *dir = opendir("/sys/devices/system/cpu"); + if (dir == NULL) { + logg->logError(__FILE__, __LINE__, "Unable to determine the number of cores on the target, opendir failed"); handleException(); } - gSessionData->mPageSize = static_cast<int>(l); - l = sysconf(_SC_NPROCESSORS_CONF); - if (l < 0) { - logg->logError(__FILE__, __LINE__, "Unable to obtain the number of cores"); + long maxCoreNum = -1; + struct dirent *dirent; + while ((dirent = readdir(dir)) != NULL) { + if (strncmp(dirent->d_name, "cpu", 3) == 0) { + char *endptr; + errno = 0; + long coreNum = strtol(dirent->d_name + 3, &endptr, 10); + if ((errno == 0) && (*endptr == '\0') && (coreNum >= maxCoreNum)) { + maxCoreNum = coreNum + 1; + } + } + } + closedir(dir); + + if (maxCoreNum < 1) { + logg->logError(__FILE__, __LINE__, "Unable to determine the number of cores on the target, no cpu# directories found"); handleException(); } - gSessionData->mCores = static_cast<int>(l); -} -PerfSource::~PerfSource() { + if (maxCoreNum >= NR_CPUS) { + logg->logError(__FILE__, __LINE__, "Too many cores on the target, please increase NR_CPUS in Config.h"); + handleException(); + } + + return maxCoreNum; } -struct PrepareParallelArgs { - PerfGroup *pg; - int cpu; -}; +PerfSource::PerfSource(sem_t *senderSem, sem_t *startProfile) : mSummary(0, FRAME_SUMMARY, 1024, senderSem), mBuffer(0, FRAME_PERF_ATTRS, 1024*1024, senderSem), mCountersBuf(), mCountersGroup(&mCountersBuf), mIdleGroup(&mCountersBuf), mMonitor(), mUEvent(), mSenderSem(senderSem), mStartProfile(startProfile), mInterruptFd(-1), mIsDone(false) { + long l = sysconf(_SC_PAGE_SIZE); + if (l < 0) { + logg->logError(__FILE__, __LINE__, "Unable to obtain the page size"); + handleException(); + } + gSessionData->mPageSize = static_cast<int>(l); + gSessionData->mCores = static_cast<int>(getMaxCoreNum()); +} -void *prepareParallel(void *arg) { - const PrepareParallelArgs *const args = (PrepareParallelArgs *)arg; - args->pg->prepareCPU(args->cpu); - return NULL; +PerfSource::~PerfSource() { } bool PerfSource::prepare() { DynBuf printb; DynBuf b1; - DynBuf b2; - DynBuf b3; long long schedSwitchId; + long long cpuIdleId; + + const uint64_t currTime = getTime(); // Reread cpuinfo since cores may have changed since startup gSessionData->readCpuInfo(); @@ -83,76 +156,146 @@ bool PerfSource::prepare() { || !mMonitor.add(mUEvent.getFd()) || (schedSwitchId = PerfDriver::getTracepointId(SCHED_SWITCH, &printb)) < 0 - || !sendTracepointFormat(&mBuffer, SCHED_SWITCH, &printb, &b1) + || !sendTracepointFormat(currTime, &mBuffer, SCHED_SWITCH, &printb, &b1) + + || (cpuIdleId = PerfDriver::getTracepointId(CPU_IDLE, &printb)) < 0 + || !sendTracepointFormat(currTime, &mBuffer, CPU_IDLE, &printb, &b1) // Only want RAW but not IP on sched_switch and don't want TID on SAMPLE_ID - || !mCountersGroup.add(&mBuffer, 100/**/, PERF_TYPE_TRACEPOINT, schedSwitchId, 1, PERF_SAMPLE_RAW, PERF_GROUP_MMAP | PERF_GROUP_COMM | PERF_GROUP_TASK | PERF_GROUP_SAMPLE_ID_ALL | PERF_GROUP_PER_CPU) + || !mCountersGroup.add(currTime, &mBuffer, 100/**/, PERF_TYPE_TRACEPOINT, schedSwitchId, 1, PERF_SAMPLE_RAW, PERF_GROUP_MMAP | PERF_GROUP_COMM | PERF_GROUP_TASK | PERF_GROUP_SAMPLE_ID_ALL | PERF_GROUP_PER_CPU) + || !mIdleGroup.add(currTime, &mBuffer, 101/**/, PERF_TYPE_TRACEPOINT, cpuIdleId, 1, PERF_SAMPLE_RAW, PERF_GROUP_PER_CPU) // Only want TID and IP but not RAW on timer - || (gSessionData->mSampleRate > 0 && !gSessionData->mIsEBS && !mCountersGroup.add(&mBuffer, 99/**/, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK, 1000000000UL / gSessionData->mSampleRate, PERF_SAMPLE_TID | PERF_SAMPLE_IP, PERF_GROUP_PER_CPU)) + || (gSessionData->mSampleRate > 0 && !gSessionData->mIsEBS && !mCountersGroup.add(currTime, &mBuffer, 102/**/, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK, 1000000000UL / gSessionData->mSampleRate, PERF_SAMPLE_TID | PERF_SAMPLE_IP, PERF_GROUP_PER_CPU)) - || !gSessionData->perf.enable(&mCountersGroup, &mBuffer) + || !gSessionData->perf.enable(currTime, &mCountersGroup, &mBuffer) || 0) { logg->logMessage("%s(%s:%i): perf setup failed, are you running Linux 3.4 or later?", __FUNCTION__, __FILE__, __LINE__); return false; } - if (!gSessionData->perf.summary(&mSummary)) { - logg->logMessage("%s(%s:%i): PerfDriver::summary failed", __FUNCTION__, __FILE__, __LINE__); - return false; - } - - { - // Run prepareCPU in parallel as perf_event_open can take more than 1 sec in some cases - pthread_t threads[NR_CPUS]; - PrepareParallelArgs args[NR_CPUS]; - for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) { - args[cpu].pg = &mCountersGroup; - args[cpu].cpu = cpu; - if (pthread_create(&threads[cpu], NULL, prepareParallel, &args[cpu]) != 0) { - logg->logMessage("%s(%s:%i): pthread_create failed", __FUNCTION__, __FILE__, __LINE__); - return false; - } + for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) { + const int result = mCountersGroup.prepareCPU(cpu, &mMonitor); + if ((result != PG_SUCCESS) && (result != PG_CPU_OFFLINE)) { + logg->logError(__FILE__, __LINE__, "PerfGroup::prepareCPU on mCountersGroup failed"); + handleException(); } - for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) { - if (pthread_join(threads[cpu], NULL) != 0) { - logg->logMessage("%s(%s:%i): pthread_join failed", __FUNCTION__, __FILE__, __LINE__); - return false; - } + } + for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) { + const int result = mIdleGroup.prepareCPU(cpu, &mMonitor); + if ((result != PG_SUCCESS) && (result != PG_CPU_OFFLINE)) { + logg->logError(__FILE__, __LINE__, "PerfGroup::prepareCPU on mIdleGroup failed"); + handleException(); } } int numEvents = 0; for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) { - numEvents += mCountersGroup.onlineCPU(cpu, false, &mBuffer, &mMonitor); + numEvents += mCountersGroup.onlineCPU(currTime, cpu, false, &mBuffer); + } + for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) { + numEvents += mIdleGroup.onlineCPU(currTime, cpu, false, &mBuffer); } if (numEvents <= 0) { logg->logMessage("%s(%s:%i): PerfGroup::onlineCPU failed on all cores", __FUNCTION__, __FILE__, __LINE__); return false; } - // Start events before reading proc to avoid race conditions - if (!mCountersGroup.start()) { - logg->logMessage("%s(%s:%i): PerfGroup::start failed", __FUNCTION__, __FILE__, __LINE__); - return false; + // Send the summary right before the start so that the monotonic delta is close to the start time + if (!gSessionData->perf.summary(&mSummary)) { + logg->logError(__FILE__, __LINE__, "PerfDriver::summary failed", __FUNCTION__, __FILE__, __LINE__); + handleException(); } - if (!readProc(&mBuffer, true, &printb, &b1, &b2, &b3)) { - logg->logMessage("%s(%s:%i): readProc failed", __FUNCTION__, __FILE__, __LINE__); - return false; + // Start the timer thread to used to sync perf and monotonic raw times + pthread_t syncThread; + if (pthread_create(&syncThread, NULL, syncFunc, NULL)) { + logg->logError(__FILE__, __LINE__, "pthread_create failed", __FUNCTION__, __FILE__, __LINE__); + handleException(); + } + struct sched_param param; + param.sched_priority = sched_get_priority_max(SCHED_FIFO); + if (pthread_setschedparam(syncThread, SCHED_FIFO | SCHED_RESET_ON_FORK, ¶m) != 0) { + logg->logError(__FILE__, __LINE__, "pthread_setschedparam failed"); + handleException(); } - mBuffer.commit(1); + mBuffer.commit(currTime); return true; } +struct ProcThreadArgs { + Buffer *mBuffer; + uint64_t mCurrTime; + bool mIsDone; +}; + +void *procFunc(void *arg) { + DynBuf printb; + DynBuf b; + const ProcThreadArgs *const args = (ProcThreadArgs *)arg; + + prctl(PR_SET_NAME, (unsigned long)&"gatord-proc", 0, 0, 0); + + // Gator runs at a high priority, reset the priority to the default + if (setpriority(PRIO_PROCESS, syscall(__NR_gettid), 0) == -1) { + logg->logError(__FILE__, __LINE__, "setpriority failed"); + handleException(); + } + + if (!readProcMaps(args->mCurrTime, args->mBuffer, &printb, &b)) { + logg->logError(__FILE__, __LINE__, "readProcMaps failed"); + handleException(); + } + args->mBuffer->commit(args->mCurrTime); + + if (!readKallsyms(args->mCurrTime, args->mBuffer, &args->mIsDone)) { + logg->logError(__FILE__, __LINE__, "readKallsyms failed"); + handleException(); + } + args->mBuffer->commit(args->mCurrTime); + + return NULL; +} + static const char CPU_DEVPATH[] = "/devices/system/cpu/cpu"; void PerfSource::run() { int pipefd[2]; + pthread_t procThread; + ProcThreadArgs procThreadArgs; + + { + DynBuf printb; + DynBuf b1; + DynBuf b2; - if (pipe(pipefd) != 0) { + const uint64_t currTime = getTime(); + + // Start events before reading proc to avoid race conditions + if (!mCountersGroup.start() || !mIdleGroup.start()) { + logg->logError(__FILE__, __LINE__, "PerfGroup::start failed", __FUNCTION__, __FILE__, __LINE__); + handleException(); + } + + if (!readProcComms(currTime, &mBuffer, &printb, &b1, &b2)) { + logg->logError(__FILE__, __LINE__, "readProcComms failed"); + handleException(); + } + mBuffer.commit(currTime); + + // Postpone reading kallsyms as on android adb gets too backed up and data is lost + procThreadArgs.mBuffer = &mBuffer; + procThreadArgs.mCurrTime = currTime; + procThreadArgs.mIsDone = false; + if (pthread_create(&procThread, NULL, procFunc, &procThreadArgs)) { + logg->logError(__FILE__, __LINE__, "pthread_create failed", __FUNCTION__, __FILE__, __LINE__); + handleException(); + } + } + + if (pipe_cloexec(pipefd) != 0) { logg->logError(__FILE__, __LINE__, "pipe failed"); handleException(); } @@ -165,7 +308,7 @@ void PerfSource::run() { int timeout = -1; if (gSessionData->mLiveRate > 0) { - timeout = gSessionData->mLiveRate/MS_PER_US; + timeout = gSessionData->mLiveRate/NS_PER_MS; } sem_post(mStartProfile); @@ -178,10 +321,11 @@ void PerfSource::run() { logg->logError(__FILE__, __LINE__, "Monitor::wait failed"); handleException(); } + const uint64_t currTime = getTime(); for (int i = 0; i < ready; ++i) { if (events[i].data.fd == mUEvent.getFd()) { - if (!handleUEvent()) { + if (!handleUEvent(currTime)) { logg->logError(__FILE__, __LINE__, "PerfSource::handleUEvent failed"); handleException(); } @@ -200,6 +344,9 @@ void PerfSource::run() { } } + procThreadArgs.mIsDone = true; + pthread_join(procThread, NULL); + mIdleGroup.stop(); mCountersGroup.stop(); mBuffer.setDone(); mIsDone = true; @@ -212,7 +359,7 @@ void PerfSource::run() { close(pipefd[1]); } -bool PerfSource::handleUEvent() { +bool PerfSource::handleUEvent(const uint64_t currTime) { UEventResult result; if (!mUEvent.read(&result)) { logg->logMessage("%s(%s:%i): UEvent::Read failed", __FUNCTION__, __FILE__, __LINE__); @@ -231,14 +378,41 @@ bool PerfSource::handleUEvent() { logg->logMessage("%s(%s:%i): strtol failed", __FUNCTION__, __FILE__, __LINE__); return false; } + + if (cpu >= gSessionData->mCores) { + logg->logError(__FILE__, __LINE__, "Only %i cores are expected but core %i reports %s", gSessionData->mCores, cpu, result.mAction); + handleException(); + } + if (strcmp(result.mAction, "online") == 0) { + mBuffer.onlineCPU(currTime, currTime - gSessionData->mMonotonicStarted, cpu); // Only call onlineCPU if prepareCPU succeeded - const bool result = mCountersGroup.prepareCPU(cpu) && - mCountersGroup.onlineCPU(cpu, true, &mBuffer, &mMonitor); - mBuffer.commit(1); + bool result = false; + int err = mCountersGroup.prepareCPU(cpu, &mMonitor); + if (err == PG_CPU_OFFLINE) { + result = true; + } else if (err == PG_SUCCESS) { + if (mCountersGroup.onlineCPU(currTime, cpu, true, &mBuffer)) { + err = mIdleGroup.prepareCPU(cpu, &mMonitor); + if (err == PG_CPU_OFFLINE) { + result = true; + } else if (err == PG_SUCCESS) { + if (mIdleGroup.onlineCPU(currTime, cpu, true, &mBuffer)) { + result = true; + } + } + } + } + mBuffer.commit(currTime); + + gSessionData->readCpuInfo(); + gSessionData->perf.coreName(currTime, &mSummary, cpu); + mSummary.commit(currTime); return result; } else if (strcmp(result.mAction, "offline") == 0) { - return mCountersGroup.offlineCPU(cpu); + const bool result = mCountersGroup.offlineCPU(cpu) && mIdleGroup.offlineCPU(cpu); + mBuffer.offlineCPU(currTime, currTime - gSessionData->mMonotonicStarted, cpu); + return result; } } diff --git a/tools/gator/daemon/PerfSource.h b/tools/gator/daemon/PerfSource.h index 3f471c8de414..ce1eafe8e953 100644 --- a/tools/gator/daemon/PerfSource.h +++ b/tools/gator/daemon/PerfSource.h @@ -33,12 +33,13 @@ public: void write(Sender *sender); private: - bool handleUEvent(); + bool handleUEvent(const uint64_t currTime); Buffer mSummary; Buffer mBuffer; PerfBuffer mCountersBuf; PerfGroup mCountersGroup; + PerfGroup mIdleGroup; Monitor mMonitor; UEvent mUEvent; sem_t *const mSenderSem; diff --git a/tools/gator/daemon/Proc.cpp b/tools/gator/daemon/Proc.cpp index 9f01770d6609..e6b26b1199fa 100644 --- a/tools/gator/daemon/Proc.cpp +++ b/tools/gator/daemon/Proc.cpp @@ -10,13 +10,16 @@ #include <dirent.h> #include <errno.h> +#include <fcntl.h> #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <unistd.h> #include "Buffer.h" #include "DynBuf.h" #include "Logging.h" +#include "SessionData.h" struct ProcStat { // From linux-dev/include/linux/sched.h @@ -57,6 +60,8 @@ static bool readProcStat(ProcStat *const ps, const char *const pathname, DynBuf return true; } +static const char APP_PROCESS[] = "app_process"; + static const char *readProcExe(DynBuf *const printb, const int pid, const int tid, DynBuf *const b) { if (tid == -1 ? !printb->printf("/proc/%i/exe", pid) : !printb->printf("/proc/%i/task/%i/exe", pid, tid)) { @@ -82,7 +87,8 @@ static const char *readProcExe(DynBuf *const printb, const int pid, const int ti } // Android apps are run by app_process but the cmdline is changed to reference the actual app name - if (strcmp(image, "app_process") != 0) { + // On 64-bit android app_process can be app_process32 or app_process64 + if (strncmp(image, APP_PROCESS, sizeof(APP_PROCESS) - 1) != 0) { return image; } @@ -100,7 +106,7 @@ static const char *readProcExe(DynBuf *const printb, const int pid, const int ti return b->getBuf(); } -static bool readProcTask(Buffer *const buffer, const int pid, DynBuf *const printb, DynBuf *const b1, DynBuf *const b2) { +static bool readProcTask(const uint64_t currTime, Buffer *const buffer, const int pid, DynBuf *const printb, DynBuf *const b1, DynBuf *const b2) { bool result = false; if (!b1->printf("/proc/%i/task", pid)) { @@ -110,7 +116,8 @@ static bool readProcTask(Buffer *const buffer, const int pid, DynBuf *const prin DIR *task = opendir(b1->getBuf()); if (task == NULL) { logg->logMessage("%s(%s:%i): opendir failed", __FUNCTION__, __FILE__, __LINE__); - return result; + // This is not a fatal error - the thread just doesn't exist any more + return true; } struct dirent *dirent; @@ -138,7 +145,7 @@ static bool readProcTask(Buffer *const buffer, const int pid, DynBuf *const prin goto fail; } - buffer->comm(pid, tid, image, ps.comm); + buffer->comm(currTime, pid, tid, image, ps.comm); } result = true; @@ -149,7 +156,7 @@ static bool readProcTask(Buffer *const buffer, const int pid, DynBuf *const prin return result; } -bool readProc(Buffer *const buffer, bool sendMaps, DynBuf *const printb, DynBuf *const b1, DynBuf *const b2, DynBuf *const b3) { +bool readProcComms(const uint64_t currTime, Buffer *const buffer, DynBuf *const printb, DynBuf *const b1, DynBuf *const b2) { bool result = false; DIR *proc = opendir("/proc"); @@ -177,19 +184,6 @@ bool readProc(Buffer *const buffer, bool sendMaps, DynBuf *const printb, DynBuf goto fail; } - if (sendMaps) { - if (!printb->printf("/proc/%i/maps", pid)) { - logg->logMessage("%s(%s:%i): DynBuf::printf failed", __FUNCTION__, __FILE__, __LINE__); - goto fail; - } - if (!b2->read(printb->getBuf())) { - logg->logMessage("%s(%s:%i): DynBuf::read failed, likely because the process exited", __FUNCTION__, __FILE__, __LINE__); - // This is not a fatal error - the process just doesn't exist any more - continue; - } - - buffer->maps(pid, pid, b2->getBuf()); - } if (ps.numThreads <= 1) { const char *const image = readProcExe(printb, pid, -1, b1); if (image == NULL) { @@ -197,9 +191,9 @@ bool readProc(Buffer *const buffer, bool sendMaps, DynBuf *const printb, DynBuf goto fail; } - buffer->comm(pid, pid, image, ps.comm); + buffer->comm(currTime, pid, pid, image, ps.comm); } else { - if (!readProcTask(buffer, pid, printb, b1, b3)) { + if (!readProcTask(currTime, buffer, pid, printb, b1, b2)) { logg->logMessage("%s(%s:%i): readProcTask failed", __FUNCTION__, __FILE__, __LINE__); goto fail; } @@ -213,3 +207,106 @@ bool readProc(Buffer *const buffer, bool sendMaps, DynBuf *const printb, DynBuf return result; } + +bool readProcMaps(const uint64_t currTime, Buffer *const buffer, DynBuf *const printb, DynBuf *const b) { + bool result = false; + + DIR *proc = opendir("/proc"); + if (proc == NULL) { + logg->logMessage("%s(%s:%i): opendir failed", __FUNCTION__, __FILE__, __LINE__); + return result; + } + + struct dirent *dirent; + while ((dirent = readdir(proc)) != NULL) { + char *endptr; + const int pid = strtol(dirent->d_name, &endptr, 10); + if (*endptr != '\0') { + // Ignore proc items that are not integers like ., cpuinfo, etc... + continue; + } + + if (!printb->printf("/proc/%i/maps", pid)) { + logg->logMessage("%s(%s:%i): DynBuf::printf failed", __FUNCTION__, __FILE__, __LINE__); + goto fail; + } + if (!b->read(printb->getBuf())) { + logg->logMessage("%s(%s:%i): DynBuf::read failed, likely because the process exited", __FUNCTION__, __FILE__, __LINE__); + // This is not a fatal error - the process just doesn't exist any more + continue; + } + + buffer->maps(currTime, pid, pid, b->getBuf()); + } + + result = true; + + fail: + closedir(proc); + + return result; +} + +bool readKallsyms(const uint64_t currTime, Buffer *const buffer, const bool *const isDone) { + int fd = ::open("/proc/kallsyms", O_RDONLY | O_CLOEXEC); + + if (fd < 0) { + logg->logMessage("%s(%s:%i): open failed", __FUNCTION__, __FILE__, __LINE__); + return true; + }; + + char buf[1<<12]; + ssize_t pos = 0; + while (gSessionData->mSessionIsActive && !ACCESS_ONCE(*isDone)) { + // Assert there is still space in the buffer + if (sizeof(buf) - pos - 1 == 0) { + logg->logError(__FILE__, __LINE__, "no space left in buffer"); + handleException(); + } + + { + // -1 to reserve space for \0 + const ssize_t bytes = ::read(fd, buf + pos, sizeof(buf) - pos - 1); + if (bytes < 0) { + logg->logError(__FILE__, __LINE__, "read failed", __FUNCTION__, __FILE__, __LINE__); + handleException(); + } + if (bytes == 0) { + // Assert the buffer is empty + if (pos != 0) { + logg->logError(__FILE__, __LINE__, "buffer not empty on eof"); + handleException(); + } + break; + } + pos += bytes; + } + + ssize_t newline; + // Find the last '\n' + for (newline = pos - 1; newline >= 0; --newline) { + if (buf[newline] == '\n') { + const char was = buf[newline + 1]; + buf[newline + 1] = '\0'; + buffer->kallsyms(currTime, buf); + // Sleep 3 ms to avoid sending out too much data too quickly + usleep(3000); + buf[0] = was; + // Assert the memory regions do not overlap + if (pos - newline >= newline + 1) { + logg->logError(__FILE__, __LINE__, "memcpy src and dst overlap"); + handleException(); + } + if (pos - newline - 2 > 0) { + memcpy(buf + 1, buf + newline + 2, pos - newline - 2); + } + pos -= newline + 1; + break; + } + } + } + + close(fd); + + return true; +} diff --git a/tools/gator/daemon/Proc.h b/tools/gator/daemon/Proc.h index 31c2eecb7aeb..2a1a7cbc1e99 100644 --- a/tools/gator/daemon/Proc.h +++ b/tools/gator/daemon/Proc.h @@ -9,9 +9,13 @@ #ifndef PROC_H #define PROC_H +#include <stdint.h> + class Buffer; class DynBuf; -bool readProc(Buffer *const buffer, bool sendMaps, DynBuf *const printb, DynBuf *const b1, DynBuf *const b2, DynBuf *const b3); +bool readProcComms(const uint64_t currTime, Buffer *const buffer, DynBuf *const printb, DynBuf *const b1, DynBuf *const b2); +bool readProcMaps(const uint64_t currTime, Buffer *const buffer, DynBuf *const printb, DynBuf *const b); +bool readKallsyms(const uint64_t currTime, Buffer *const buffer, const bool *const isDone); #endif // PROC_H diff --git a/tools/gator/daemon/Sender.cpp b/tools/gator/daemon/Sender.cpp index 3a981a6427be..8a54a6678974 100644 --- a/tools/gator/daemon/Sender.cpp +++ b/tools/gator/daemon/Sender.cpp @@ -65,18 +65,13 @@ void Sender::createDataFile(char* apcDir) { mDataFileName = (char*)malloc(strlen(apcDir) + 12); sprintf(mDataFileName, "%s/0000000000", apcDir); - mDataFile = fopen(mDataFileName, "wb"); + mDataFile = fopen_cloexec(mDataFileName, "wb"); if (!mDataFile) { logg->logError(__FILE__, __LINE__, "Failed to open binary file: %s", mDataFileName); handleException(); } } -template<typename T> -inline T min(const T a, const T b) { - return (a < b ? a : b); -} - void Sender::writeData(const char* data, int length, int type) { if (length < 0 || (data == NULL && length > 0)) { return; diff --git a/tools/gator/daemon/Sender.h b/tools/gator/daemon/Sender.h index 33b6cc3c5d8d..5aa911713820 100644 --- a/tools/gator/daemon/Sender.h +++ b/tools/gator/daemon/Sender.h @@ -6,8 +6,8 @@ * published by the Free Software Foundation. */ -#ifndef __SENDER_H__ -#define __SENDER_H__ +#ifndef __SENDER_H__ +#define __SENDER_H__ #include <stdio.h> #include <pthread.h> diff --git a/tools/gator/daemon/SessionData.cpp b/tools/gator/daemon/SessionData.cpp index 14d995fc39fa..0e65d7842647 100644 --- a/tools/gator/daemon/SessionData.cpp +++ b/tools/gator/daemon/SessionData.cpp @@ -8,15 +8,31 @@ #include "SessionData.h" +#include <fcntl.h> #include <string.h> #include <sys/mman.h> +#include <unistd.h> -#include "SessionXML.h" +#include "CPUFreqDriver.h" +#include "DiskIODriver.h" +#include "FSDriver.h" +#include "HwmonDriver.h" #include "Logging.h" +#include "MemInfoDriver.h" +#include "NetDriver.h" +#include "SessionXML.h" + +#define CORE_NAME_UNKNOWN "unknown" SessionData* gSessionData = NULL; SessionData::SessionData() { + usDrivers[0] = new HwmonDriver(); + usDrivers[1] = new FSDriver(); + usDrivers[2] = new MemInfoDriver(); + usDrivers[3] = new NetDriver(); + usDrivers[4] = new CPUFreqDriver(); + usDrivers[5] = new DiskIODriver(); initialize(); } @@ -29,6 +45,7 @@ void SessionData::initialize() { mLocalCapture = false; mOneShot = false; mSentSummary = false; + mAllowCommands = false; const size_t cpuIdSize = sizeof(int)*NR_CPUS; // Share mCpuIds across all instances of gatord mCpuIds = (int *)mmap(NULL, cpuIdSize, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0); @@ -37,15 +54,22 @@ void SessionData::initialize() { handleException(); } memset(mCpuIds, -1, cpuIdSize); + strcpy(mCoreName, CORE_NAME_UNKNOWN); + readModel(); readCpuInfo(); + mImages = NULL; mConfigurationXMLPath = NULL; mSessionXMLPath = NULL; mEventsXMLPath = NULL; mTargetPath = NULL; mAPCDir = NULL; + mCaptureWorkingDir = NULL; + mCaptureCommand = NULL; + mCaptureUser = NULL; mSampleRate = 0; mLiveRate = 0; mDuration = 0; + mMonotonicStarted = -1; mBacktraceDepth = 0; mTotalBufferSize = 0; // sysconf(_SC_NPROCESSORS_CONF) is unreliable on 2.6 Android, get the value from the kernel module @@ -71,7 +95,6 @@ void SessionData::parseSessionXML(char* xmlString) { handleException(); } mBacktraceDepth = session.parameters.call_stack_unwinding == true ? 128 : 0; - mDuration = session.parameters.duration; // Determine buffer size (in MB) based on buffer mode mOneShot = true; @@ -89,21 +112,38 @@ void SessionData::parseSessionXML(char* xmlString) { handleException(); } - mImages = session.parameters.images; // Convert milli- to nanoseconds mLiveRate = session.parameters.live_rate * (int64_t)1000000; if (mLiveRate > 0 && mLocalCapture) { logg->logMessage("Local capture is not compatable with live, disabling live"); mLiveRate = 0; } + + if (!mAllowCommands && (mCaptureCommand != NULL)) { + logg->logError(__FILE__, __LINE__, "Running a command during a capture is not currently allowed. Please restart gatord with the -a flag."); + handleException(); + } +} + +void SessionData::readModel() { + FILE *fh = fopen("/proc/device-tree/model", "rb"); + if (fh == NULL) { + return; + } + + char buf[256]; + if (fgets(buf, sizeof(buf), fh) != NULL) { + strcpy(mCoreName, buf); + } + + fclose(fh); } void SessionData::readCpuInfo() { char temp[256]; // arbitrarily large amount - strcpy(mCoreName, "unknown"); mMaxCpuId = -1; - FILE* f = fopen("/proc/cpuinfo", "r"); + FILE *f = fopen("/proc/cpuinfo", "r"); if (f == NULL) { logg->logMessage("Error opening /proc/cpuinfo\n" "The core name in the captured xml file will be 'unknown'."); @@ -122,7 +162,8 @@ void SessionData::readCpuInfo() { } if (len > 0) { - temp[len - 1] = '\0'; // Replace the line feed with a null + // Replace the line feed with a null + temp[len - 1] = '\0'; } const bool foundHardware = strstr(temp, "Hardware") != 0; @@ -137,7 +178,7 @@ void SessionData::readCpuInfo() { } position += 2; - if (foundHardware) { + if (foundHardware && (strcmp(mCoreName, CORE_NAME_UNKNOWN) == 0)) { strncpy(mCoreName, position, sizeof(mCoreName)); mCoreName[sizeof(mCoreName) - 1] = 0; // strncpy does not guarantee a null-terminated string foundCoreName = true; @@ -171,10 +212,6 @@ void SessionData::readCpuInfo() { uint64_t getTime() { struct timespec ts; -#ifndef CLOCK_MONOTONIC_RAW - // Android doesn't have this defined but it was added in Linux 2.6.28 -#define CLOCK_MONOTONIC_RAW 4 -#endif if (clock_gettime(CLOCK_MONOTONIC_RAW, &ts) != 0) { logg->logError(__FILE__, __LINE__, "Failed to get uptime"); handleException(); @@ -185,10 +222,40 @@ uint64_t getTime() { int getEventKey() { // key 0 is reserved as a timestamp // key 1 is reserved as the marker for thread specific counters + // key 2 is reserved as the marker for core // Odd keys are assigned by the driver, even keys by the daemon - static int key = 2; + static int key = 4; const int ret = key; key += 2; return ret; } + +int pipe_cloexec(int pipefd[2]) { + if (pipe(pipefd) != 0) { + return -1; + } + + int fdf; + if (((fdf = fcntl(pipefd[0], F_GETFD)) == -1) || (fcntl(pipefd[0], F_SETFD, fdf | FD_CLOEXEC) != 0) || + ((fdf = fcntl(pipefd[1], F_GETFD)) == -1) || (fcntl(pipefd[1], F_SETFD, fdf | FD_CLOEXEC) != 0)) { + close(pipefd[0]); + close(pipefd[1]); + return -1; + } + return 0; +} + +FILE *fopen_cloexec(const char *path, const char *mode) { + FILE *fh = fopen(path, mode); + if (fh == NULL) { + return NULL; + } + int fd = fileno(fh); + int fdf = fcntl(fd, F_GETFD); + if ((fdf == -1) || (fcntl(fd, F_SETFD, fdf | FD_CLOEXEC) != 0)) { + fclose(fh); + return NULL; + } + return fh; +} diff --git a/tools/gator/daemon/SessionData.h b/tools/gator/daemon/SessionData.h index 835082d86c4b..ed282af4a869 100644 --- a/tools/gator/daemon/SessionData.h +++ b/tools/gator/daemon/SessionData.h @@ -11,17 +11,21 @@ #include <stdint.h> +#include "AnnotateListener.h" #include "Config.h" #include "Counter.h" -#include "FSDriver.h" -#include "Hwmon.h" +#include "FtraceDriver.h" +#include "KMod.h" #include "MaliVideoDriver.h" #include "PerfDriver.h" -#define PROTOCOL_VERSION 19 -#define PROTOCOL_DEV 1000 // Differentiates development versions (timestamp) from release versions +#define PROTOCOL_VERSION 20 +// Differentiates development versions (timestamp) from release versions +#define PROTOCOL_DEV 1000 -#define NS_PER_S ((uint64_t)1000000000) +#define NS_PER_S 1000000000LL +#define NS_PER_MS 1000000LL +#define NS_PER_US 1000LL struct ImageLinkList { char* path; @@ -36,30 +40,40 @@ public: ~SessionData(); void initialize(); void parseSessionXML(char* xmlString); + void readModel(); void readCpuInfo(); - Hwmon hwmon; - FSDriver fsDriver; + PolledDriver *usDrivers[6]; + KMod kmod; PerfDriver perf; MaliVideoDriver maliVideo; + FtraceDriver ftraceDriver; + AnnotateListener annotateListener; char mCoreName[MAX_STRING_LEN]; struct ImageLinkList *mImages; - char* mConfigurationXMLPath; - char* mSessionXMLPath; - char* mEventsXMLPath; - char* mTargetPath; - char* mAPCDir; + char *mConfigurationXMLPath; + char *mSessionXMLPath; + char *mEventsXMLPath; + char *mTargetPath; + char *mAPCDir; + char *mCaptureWorkingDir; + char *mCaptureCommand; + char *mCaptureUser; bool mWaitingOnCommand; bool mSessionIsActive; bool mLocalCapture; - bool mOneShot; // halt processing of the driver data until profiling is complete or the buffer is filled + // halt processing of the driver data until profiling is complete or the buffer is filled + bool mOneShot; bool mIsEBS; bool mSentSummary; + bool mAllowCommands; + int64_t mMonotonicStarted; int mBacktraceDepth; - int mTotalBufferSize; // number of MB to use for the entire collection buffer + // number of MB to use for the entire collection buffer + int mTotalBufferSize; int mSampleRate; int64_t mLiveRate; int mDuration; @@ -82,5 +96,7 @@ extern SessionData* gSessionData; uint64_t getTime(); int getEventKey(); +int pipe_cloexec(int pipefd[2]); +FILE *fopen_cloexec(const char *path, const char *mode); #endif // SESSION_DATA_H diff --git a/tools/gator/daemon/SessionXML.cpp b/tools/gator/daemon/SessionXML.cpp index 8cdc9409ca21..dea4c8f299ec 100644 --- a/tools/gator/daemon/SessionXML.cpp +++ b/tools/gator/daemon/SessionXML.cpp @@ -16,33 +16,30 @@ #include "OlyUtility.h" #include "SessionData.h" -static const char* TAG_SESSION = "session"; -static const char* TAG_IMAGE = "image"; - -static const char* ATTR_VERSION = "version"; -static const char* ATTR_CALL_STACK_UNWINDING = "call_stack_unwinding"; -static const char* ATTR_BUFFER_MODE = "buffer_mode"; -static const char* ATTR_SAMPLE_RATE = "sample_rate"; -static const char* ATTR_DURATION = "duration"; -static const char* ATTR_PATH = "path"; -static const char* ATTR_LIVE_RATE = "live_rate"; +static const char *TAG_SESSION = "session"; +static const char *TAG_IMAGE = "image"; + +static const char *ATTR_VERSION = "version"; +static const char *ATTR_CALL_STACK_UNWINDING = "call_stack_unwinding"; +static const char *ATTR_BUFFER_MODE = "buffer_mode"; +static const char *ATTR_SAMPLE_RATE = "sample_rate"; +static const char *ATTR_DURATION = "duration"; +static const char *ATTR_PATH = "path"; +static const char *ATTR_LIVE_RATE = "live_rate"; +static const char *ATTR_CAPTURE_WORKING_DIR = "capture_working_dir"; +static const char *ATTR_CAPTURE_COMMAND = "capture_command"; +static const char *ATTR_CAPTURE_USER = "capture_user"; SessionXML::SessionXML(const char *str) { parameters.buffer_mode[0] = 0; parameters.sample_rate[0] = 0; - parameters.duration = 0; parameters.call_stack_unwinding = false; parameters.live_rate = 0; - parameters.images = NULL; - mPath = 0; - mSessionXML = (const char *)str; + mSessionXML = str; logg->logMessage(mSessionXML); } SessionXML::~SessionXML() { - if (mPath != 0) { - free((char *)mSessionXML); - } } void SessionXML::parse() { @@ -79,10 +76,13 @@ void SessionXML::sessionTag(mxml_node_t *tree, mxml_node_t *node) { strncpy(parameters.sample_rate, mxmlElementGetAttr(node, ATTR_SAMPLE_RATE), sizeof(parameters.sample_rate)); parameters.sample_rate[sizeof(parameters.sample_rate) - 1] = 0; // strncpy does not guarantee a null-terminated string } + if (mxmlElementGetAttr(node, ATTR_CAPTURE_WORKING_DIR)) gSessionData->mCaptureWorkingDir = strdup(mxmlElementGetAttr(node, ATTR_CAPTURE_WORKING_DIR)); + if (mxmlElementGetAttr(node, ATTR_CAPTURE_COMMAND)) gSessionData->mCaptureCommand = strdup(mxmlElementGetAttr(node, ATTR_CAPTURE_COMMAND)); + if (mxmlElementGetAttr(node, ATTR_CAPTURE_USER)) gSessionData->mCaptureUser = strdup(mxmlElementGetAttr(node, ATTR_CAPTURE_USER)); // integers/bools parameters.call_stack_unwinding = util->stringToBool(mxmlElementGetAttr(node, ATTR_CALL_STACK_UNWINDING), false); - if (mxmlElementGetAttr(node, ATTR_DURATION)) parameters.duration = strtol(mxmlElementGetAttr(node, ATTR_DURATION), NULL, 10); + if (mxmlElementGetAttr(node, ATTR_DURATION)) gSessionData->mDuration = strtol(mxmlElementGetAttr(node, ATTR_DURATION), NULL, 10); if (mxmlElementGetAttr(node, ATTR_LIVE_RATE)) parameters.live_rate = strtol(mxmlElementGetAttr(node, ATTR_LIVE_RATE), NULL, 10); // parse subtags @@ -106,6 +106,6 @@ void SessionXML::sessionImage(mxml_node_t *node) { image = (struct ImageLinkList *)malloc(sizeof(struct ImageLinkList)); image->path = (char*)malloc(length + 1); image->path = strdup(mxmlElementGetAttr(node, ATTR_PATH)); - image->next = parameters.images; - parameters.images = image; + image->next = gSessionData->mImages; + gSessionData->mImages = image; } diff --git a/tools/gator/daemon/SessionXML.h b/tools/gator/daemon/SessionXML.h index e146094a4d17..53965749c74b 100644 --- a/tools/gator/daemon/SessionXML.h +++ b/tools/gator/daemon/SessionXML.h @@ -14,12 +14,13 @@ struct ImageLinkList; struct ConfigParameters { - char buffer_mode[64]; // buffer mode, "streaming", "low", "normal", "high" defines oneshot and buffer size - char sample_rate[64]; // capture mode, "high", "normal", or "low" - int duration; // length of profile in seconds - bool call_stack_unwinding; // whether stack unwinding is performed + // buffer mode, "streaming", "low", "normal", "high" defines oneshot and buffer size + char buffer_mode[64]; + // capture mode, "high", "normal", or "low" + char sample_rate[64]; + // whether stack unwinding is performed + bool call_stack_unwinding; int live_rate; - struct ImageLinkList *images; // linked list of image strings }; class SessionXML { @@ -30,7 +31,6 @@ public: ConfigParameters parameters; private: const char *mSessionXML; - const char *mPath; void sessionTag(mxml_node_t *tree, mxml_node_t *node); void sessionImage(mxml_node_t *node); diff --git a/tools/gator/daemon/Setup.cpp b/tools/gator/daemon/Setup.cpp new file mode 100644 index 000000000000..d4ce0328c633 --- /dev/null +++ b/tools/gator/daemon/Setup.cpp @@ -0,0 +1,232 @@ +/** + * Copyright (C) ARM Limited 2014. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "Setup.h" + +#include <dirent.h> +#include <errno.h> +#include <fcntl.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <sys/utsname.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "Config.h" +#include "DynBuf.h" +#include "Logging.h" + +bool getLinuxVersion(int version[3]) { + // Check the kernel version + struct utsname utsname; + if (uname(&utsname) != 0) { + logg->logMessage("%s(%s:%i): uname failed", __FUNCTION__, __FILE__, __LINE__); + return false; + } + + version[0] = 0; + version[1] = 0; + version[2] = 0; + + int part = 0; + char *ch = utsname.release; + while (*ch >= '0' && *ch <= '9' && part < 3) { + version[part] = 10*version[part] + *ch - '0'; + + ++ch; + if (*ch == '.') { + ++part; + ++ch; + } + } + + return true; +} + +static int pgrep_gator(DynBuf *const printb) { + DynBuf b; + + DIR *proc = opendir("/proc"); + if (proc == NULL) { + logg->logError(__FILE__, __LINE__, "gator: error: opendir failed"); + handleException(); + } + + int self = getpid(); + + struct dirent *dirent; + while ((dirent = readdir(proc)) != NULL) { + char *endptr; + const int pid = strtol(dirent->d_name, &endptr, 10); + if (*endptr != '\0' || (pid == self)) { + // Ignore proc items that are not integers like ., cpuinfo, etc... + continue; + } + + if (!printb->printf("/proc/%i/stat", pid)) { + logg->logError(__FILE__, __LINE__, "gator: error: DynBuf::printf failed"); + handleException(); + } + + if (!b.read(printb->getBuf())) { + // This is not a fatal error - the thread just doesn't exist any more + continue; + } + + char *comm = strchr(b.getBuf(), '('); + if (comm == NULL) { + logg->logError(__FILE__, __LINE__, "gator: error: parsing stat begin failed"); + handleException(); + } + ++comm; + char *const str = strrchr(comm, ')'); + if (str == NULL) { + logg->logError(__FILE__, __LINE__, "gator: error: parsing stat end failed"); + handleException(); + } + *str = '\0'; + + if (strncmp(comm, "gator", 5) == 0) { + // Assume there is only one gator process + return pid; + } + } + + closedir(proc); + + return -1; +} + +int update(const char *const gatorPath) { + printf("gator: starting\n"); + + int version[3]; + if (!getLinuxVersion(version)) { + logg->logError(__FILE__, __LINE__, "gator: error: getLinuxVersion failed"); + handleException(); + } + + if (KERNEL_VERSION(version[0], version[1], version[2]) < KERNEL_VERSION(2, 6, 32)) { + logg->logError(__FILE__, __LINE__, "gator: error: Streamline can't automatically setup gator as this kernel version is not supported. Please upgrade the kernel on your device."); + handleException(); + } + + if (KERNEL_VERSION(version[0], version[1], version[2]) < KERNEL_VERSION(3, 4, 0)) { + logg->logError(__FILE__, __LINE__, "gator: error: Streamline can't automatically setup gator as gator.ko is required for this version of Linux. Please build gator.ko and gatord and install them on your device."); + handleException(); + } + + if (access("/sys/module/gator", F_OK) == 0) { + logg->logError(__FILE__, __LINE__, "gator: error: Streamline has detected that the gator kernel module is loaded on your device. Please build an updated version of gator.ko and gatord and install them on your device."); + handleException(); + } + + if (geteuid() != 0) { + printf("gator: trying sudo\n"); + execlp("sudo", "sudo", gatorPath, "-u", NULL); + // Streamline will provide the password if needed + + printf("gator: trying su\n"); + char buf[1<<10]; + snprintf(buf, sizeof(buf), "%s -u", gatorPath); + execlp("su", "su", "-", "-c", buf, NULL); + // Streamline will provide the password if needed + + logg->logError(__FILE__, __LINE__, "gator: error: Streamline was unable to sudo to root on your device. Please double check passwords, ensure sudo or su work with this user or try a different username."); + handleException(); + } + printf("gator: now root\n"); + + // setenforce 0 not needed for userspace gator + + // Kill existing gator + DynBuf gatorStatPath; + int gator_main = pgrep_gator(&gatorStatPath); + if (gator_main > 0) { + if (kill(gator_main, SIGTERM) != 0) { + logg->logError(__FILE__, __LINE__, "gator: error: kill SIGTERM failed"); + handleException(); + } + for (int i = 0; ; ++i) { + if (access(gatorStatPath.getBuf(), F_OK) != 0) { + break; + } + if (i == 5) { + if (kill(gator_main, SIGKILL) != 0) { + logg->logError(__FILE__, __LINE__, "gator: error: kill SIGKILL failed"); + handleException(); + } + } else if (i >= 10) { + logg->logError(__FILE__, __LINE__, "gator: error: unable to kill running gator"); + handleException(); + } + sleep(1); + } + } + printf("gator: no gatord running\n"); + + rename("gatord", "gatord.old"); + rename("gator.ko", "gator.ko.old"); + + // Rename gatord.YYYYMMDDHHMMSSMMMM to gatord + char *newGatorPath = strdup(gatorPath); + char *dot = strrchr(newGatorPath, '.'); + if (dot != NULL) { + *dot = '\0'; + if (rename(gatorPath, newGatorPath) != 0) { + logg->logError(__FILE__, __LINE__, "gator: error: rename failed"); + handleException(); + } + } + + // Fork and start gatord (redirect stdout and stderr) + int child = fork(); + if (child < 0) { + logg->logError(__FILE__, __LINE__, "gator: error: fork failed"); + handleException(); + } else if (child == 0) { + int inFd = open("/dev/null", O_RDONLY | O_CLOEXEC); + if (inFd < 0) { + logg->logError(__FILE__, __LINE__, "gator: error: open of /dev/null failed"); + handleException(); + } + int outFd = open("gatord.out", O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0600); + if (outFd < 0) { + logg->logError(__FILE__, __LINE__, "gator: error: open of gatord.out failed"); + handleException(); + } + int errFd = open("gatord.err", O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0600); + if (errFd < 0) { + logg->logError(__FILE__, __LINE__, "gator: error: open of gatord.err failed"); + handleException(); + } + if (dup2(inFd, STDIN_FILENO) < 0) { + logg->logError(__FILE__, __LINE__, "gator: error: dup2 for stdin failed"); + handleException(); + } + if (dup2(outFd, STDOUT_FILENO) < 0) { + logg->logError(__FILE__, __LINE__, "gator: error: dup2 for stdout failed"); + handleException(); + } + if (dup2(errFd, STDERR_FILENO) < 0) { + logg->logError(__FILE__, __LINE__, "gator: error: dup2 for stderr failed"); + handleException(); + } + execlp(newGatorPath, newGatorPath, "-a", NULL); + logg->logError(__FILE__, __LINE__, "gator: error: execlp failed"); + handleException(); + } + + printf("gator: done\n"); + + return 0; +} diff --git a/tools/gator/daemon/Setup.h b/tools/gator/daemon/Setup.h new file mode 100644 index 000000000000..280d61139784 --- /dev/null +++ b/tools/gator/daemon/Setup.h @@ -0,0 +1,18 @@ +/** + * Copyright (C) ARM Limited 2014. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef SETUP_H +#define SETUP_H + +// From include/generated/uapi/linux/version.h +#define KERNEL_VERSION(a,b,c) (((a) << 16) + ((b) << 8) + (c)) + +bool getLinuxVersion(int version[3]); +int update(const char *const gatorPath); + +#endif // SETUP_H diff --git a/tools/gator/daemon/StreamlineSetup.h b/tools/gator/daemon/StreamlineSetup.h index b380f46b98f0..623e14f2b64a 100644 --- a/tools/gator/daemon/StreamlineSetup.h +++ b/tools/gator/daemon/StreamlineSetup.h @@ -6,8 +6,8 @@ * published by the Free Software Foundation. */ -#ifndef __STREAMLINE_SETUP_H__ -#define __STREAMLINE_SETUP_H__ +#ifndef __STREAMLINE_SETUP_H__ +#define __STREAMLINE_SETUP_H__ #include <stdint.h> #include <string.h> diff --git a/tools/gator/daemon/UEvent.cpp b/tools/gator/daemon/UEvent.cpp index 54d45751e3c9..f94a995393e8 100644 --- a/tools/gator/daemon/UEvent.cpp +++ b/tools/gator/daemon/UEvent.cpp @@ -15,6 +15,7 @@ #include <linux/netlink.h> #include "Logging.h" +#include "OlySocket.h" static const char EMPTY[] = ""; static const char ACTION[] = "ACTION="; @@ -31,7 +32,7 @@ UEvent::~UEvent() { } bool UEvent::init() { - mFd = socket(PF_NETLINK, SOCK_RAW, NETLINK_KOBJECT_UEVENT); + mFd = socket_cloexec(PF_NETLINK, SOCK_RAW, NETLINK_KOBJECT_UEVENT); if (mFd < 0) { logg->logMessage("%s(%s:%i): socket failed", __FUNCTION__, __FILE__, __LINE__); return false; diff --git a/tools/gator/daemon/UserSpaceSource.cpp b/tools/gator/daemon/UserSpaceSource.cpp index 8c328e0e0fb5..4a9b22f4b555 100644 --- a/tools/gator/daemon/UserSpaceSource.cpp +++ b/tools/gator/daemon/UserSpaceSource.cpp @@ -16,8 +16,6 @@ #include "Logging.h" #include "SessionData.h" -#define NS_PER_US 1000 - extern Child *child; UserSpaceSource::UserSpaceSource(sem_t *senderSem) : mBuffer(0, FRAME_BLOCK_COUNTER, gSessionData->mTotalBufferSize*1024*1024, senderSem) { @@ -33,16 +31,22 @@ bool UserSpaceSource::prepare() { void UserSpaceSource::run() { prctl(PR_SET_NAME, (unsigned long)&"gatord-counters", 0, 0, 0); - gSessionData->hwmon.start(); - gSessionData->fsDriver.start(); + for (int i = 0; i < ARRAY_LENGTH(gSessionData->usDrivers); ++i) { + gSessionData->usDrivers[i]->start(); + } int64_t monotonic_started = 0; while (monotonic_started <= 0) { usleep(10); - if (DriverSource::readInt64Driver("/dev/gator/started", &monotonic_started) == -1) { - logg->logError(__FILE__, __LINE__, "Error reading gator driver start time"); - handleException(); + if (gSessionData->perf.isSetup()) { + monotonic_started = gSessionData->mMonotonicStarted; + } else { + if (DriverSource::readInt64Driver("/dev/gator/started", &monotonic_started) == -1) { + logg->logError(__FILE__, __LINE__, "Error reading gator driver start time"); + handleException(); + } + gSessionData->mMonotonicStarted = monotonic_started; } } @@ -57,8 +61,9 @@ void UserSpaceSource::run() { } if (mBuffer.eventHeader(curr_time)) { - gSessionData->hwmon.read(&mBuffer); - gSessionData->fsDriver.read(&mBuffer); + for (int i = 0; i < ARRAY_LENGTH(gSessionData->usDrivers); ++i) { + gSessionData->usDrivers[i]->read(&mBuffer); + } // Only check after writing all counters so that time and corresponding counters appear in the same frame mBuffer.check(curr_time); } diff --git a/tools/gator/daemon/defaults.xml b/tools/gator/daemon/defaults.xml index 39a0f656f7e6..086eca1e804e 100644 --- a/tools/gator/daemon/defaults.xml +++ b/tools/gator/daemon/defaults.xml @@ -24,16 +24,16 @@ <configuration counter="ARMv7_Cortex_A9_cnt2" event="0x07"/> <configuration counter="ARMv7_Cortex_A9_cnt3" event="0x03"/> <configuration counter="ARMv7_Cortex_A9_cnt4" event="0x04"/> - <configuration counter="ARMv7_Cortex_A12_ccnt" event="0xff"/> - <configuration counter="ARMv7_Cortex_A12_cnt0" event="0x08"/> - <configuration counter="ARMv7_Cortex_A12_cnt1" event="0x16"/> - <configuration counter="ARMv7_Cortex_A12_cnt2" event="0x10"/> - <configuration counter="ARMv7_Cortex_A12_cnt3" event="0x19"/> <configuration counter="ARMv7_Cortex_A15_ccnt" event="0xff"/> <configuration counter="ARMv7_Cortex_A15_cnt0" event="0x8"/> <configuration counter="ARMv7_Cortex_A15_cnt1" event="0x16"/> <configuration counter="ARMv7_Cortex_A15_cnt2" event="0x10"/> <configuration counter="ARMv7_Cortex_A15_cnt3" event="0x19"/> + <configuration counter="ARMv7_Cortex_A17_ccnt" event="0xff"/> + <configuration counter="ARMv7_Cortex_A17_cnt0" event="0x08"/> + <configuration counter="ARMv7_Cortex_A17_cnt1" event="0x16"/> + <configuration counter="ARMv7_Cortex_A17_cnt2" event="0x10"/> + <configuration counter="ARMv7_Cortex_A17_cnt3" event="0x19"/> <configuration counter="ARM_Cortex-A53_ccnt" event="0x11"/> <configuration counter="ARM_Cortex-A53_cnt0" event="0x8"/> <configuration counter="ARM_Cortex-A53_cnt1" event="0x16"/> @@ -56,12 +56,29 @@ <configuration counter="Linux_block_rq_wr"/> <configuration counter="Linux_block_rq_rd"/> <configuration counter="Linux_meminfo_memused"/> + <configuration counter="Linux_meminfo_memused2"/> <configuration counter="Linux_meminfo_memfree"/> <configuration counter="Linux_power_cpu_freq"/> <configuration counter="ARM_Mali-4xx_fragment"/> <configuration counter="ARM_Mali-4xx_vertex"/> - <configuration counter="ARM_Mali-T6xx_fragment" cores="1"/> - <configuration counter="ARM_Mali-T6xx_vertex" cores="1"/> - <configuration counter="ARM_Mali-T6xx_opencl" cores="1"/> + <configuration counter="ARM_Mali-Midgard_fragment" cores="1"/> + <configuration counter="ARM_Mali-Midgard_vertex" cores="1"/> + <configuration counter="ARM_Mali-Midgard_opencl" cores="1"/> + <configuration counter="ARM_Mali-T60x_GPU_ACTIVE"/> + <configuration counter="ARM_Mali-T60x_JS0_ACTIVE"/> + <configuration counter="ARM_Mali-T60x_JS1_ACTIVE"/> + <configuration counter="ARM_Mali-T60x_JS2_ACTIVE"/> + <configuration counter="ARM_Mali-T62x_GPU_ACTIVE"/> + <configuration counter="ARM_Mali-T62x_JS0_ACTIVE"/> + <configuration counter="ARM_Mali-T62x_JS1_ACTIVE"/> + <configuration counter="ARM_Mali-T62x_JS2_ACTIVE"/> + <configuration counter="ARM_Mali-T72x_GPU_ACTIVE"/> + <configuration counter="ARM_Mali-T72x_JS0_ACTIVE"/> + <configuration counter="ARM_Mali-T72x_JS1_ACTIVE"/> + <configuration counter="ARM_Mali-T72x_JS2_ACTIVE"/> + <configuration counter="ARM_Mali-T76x_GPU_ACTIVE"/> + <configuration counter="ARM_Mali-T76x_JS0_ACTIVE"/> + <configuration counter="ARM_Mali-T76x_JS1_ACTIVE"/> + <configuration counter="ARM_Mali-T76x_JS2_ACTIVE"/> <configuration counter="L2C-310_cnt0" event="0x1"/> </configurations> diff --git a/tools/gator/daemon/events-Cortex-A12.xml b/tools/gator/daemon/events-Cortex-A17.xml index 9c04354ad137..4dd08c1f203d 100644 --- a/tools/gator/daemon/events-Cortex-A12.xml +++ b/tools/gator/daemon/events-Cortex-A17.xml @@ -1,6 +1,6 @@ - <counter_set name="ARMv7_Cortex_A12_cnt" count="6"/> - <category name="Cortex-A12" counter_set="ARMv7_Cortex_A12_cnt" per_cpu="yes" supports_event_based_sampling="yes"> - <event counter="ARMv7_Cortex_A12_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/> + <counter_set name="ARMv7_Cortex_A17_cnt" count="6"/> + <category name="Cortex-A17" counter_set="ARMv7_Cortex_A17_cnt" per_cpu="yes" supports_event_based_sampling="yes"> + <event counter="ARMv7_Cortex_A17_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/> <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/> <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/> <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/> @@ -62,7 +62,7 @@ <event event="0xc2" title="Cache" name="4 Ways Read" description="Number of set of 4 ways read in the instruction cache - Tag RAM"/> <event event="0xc3" title="Cache" name="Ways Read" description="Number of ways read in the instruction cache - Data RAM"/> <event event="0xc4" title="Cache" name="BATC Read" description="Number of ways read in the instruction BTAC RAM"/> - <event event="0xca" title="Memory" name="Snoop" description="Data snooped from other processor. This event counts memory-read operations that read data from another processor within the local Cortex-A12 cluster, rather than accessing the L2 cache or issuing an external read. It increments on each transaction, rather than on each beat of data"/> + <event event="0xca" title="Memory" name="Snoop" description="Data snooped from other processor. This event counts memory-read operations that read data from another processor within the local Cortex-A17 cluster, rather than accessing the L2 cache or issuing an external read. It increments on each transaction, rather than on each beat of data"/> <event event="0xd3" title="Slots" name="Load-Store Unit" description="Duration during which all slots in the Load-Store Unit are busy"/> <event event="0xd8" title="Slots" name="Load-Store Issue Queue" description="Duration during which all slots in the Load-Store Issue queue are busy"/> <event event="0xd9" title="Slots" name="Data Processing Issue Queue" description="Duration during which all slots in the Data Processing issue queue are busy"/> diff --git a/tools/gator/daemon/events-Filesystem.xml b/tools/gator/daemon/events-Filesystem.xml index 5feeb9014a63..9ef61ddac811 100644 --- a/tools/gator/daemon/events-Filesystem.xml +++ b/tools/gator/daemon/events-Filesystem.xml @@ -1,11 +1,11 @@ <category name="Filesystem"> - <!-- counter attributes must be unique --> + <!-- counter attribute must start with filesystem_ and be unique --> <!-- regex item in () is the value shown --> - <!-- these counters are not compatible with userspace gator, i.e. gator.ko must be loaded --> <!-- - <event counter="/sys/devices/system/cpu/cpu1/online" title="online" name="cpu 1" class="absolute" description="If cpu 1 is online"/> - <event counter="/proc/self/loginuid" title="loginuid" name="loginuid" class="absolute" description="loginuid"/> - <event counter="/proc/self/stat" title="stat" name="rss" class="absolute" regex="-?[0-9]+ \(.*\) . -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ (-?[0-9]+)" units="pages" description="resident set size"/> - <event counter="/proc/stat" title="proc-stat" name="processes" class="absolute" regex="processes ([0-9]+)" description="Number of processes and threads created"/> + <event counter="filesystem_cpu1_online" path="/sys/devices/system/cpu/cpu1/online" title="online" name="cpu 1" class="absolute" description="If cpu 1 is online"/> + <event counter="filesystem_loginuid" path="/proc/self/loginuid" title="loginuid" name="loginuid" class="absolute" description="loginuid"/> + <event counter="filesystem_gatord_rss" path="/proc/self/stat" title="stat" name="rss" class="absolute" regex="-?[0-9]+ \(.*\) . -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ (-?[0-9]+)" units="pages" description="resident set size"/> + <event counter="filesystem_processes" path="/proc/stat" title="proc-stat" name="processes" class="absolute" regex="processes ([0-9]+)" description="Number of processes and threads created"/> + <event counter="filesystem_context_switches" path="/proc/stat" title="proc-stat" name="context switches" class="absolute" regex="ctxt ([0-9]+)" description="Number of processes and threads created"/> --> </category> diff --git a/tools/gator/daemon/events-Linux.xml b/tools/gator/daemon/events-Linux.xml index c306dd62208e..62a7018d038f 100644 --- a/tools/gator/daemon/events-Linux.xml +++ b/tools/gator/daemon/events-Linux.xml @@ -1,16 +1,17 @@ <category name="Linux"> <event counter="Linux_irq_softirq" title="Interrupts" name="SoftIRQ" per_cpu="yes" description="Linux SoftIRQ taken"/> <event counter="Linux_irq_irq" title="Interrupts" name="IRQ" per_cpu="yes" description="Linux IRQ taken"/> - <event counter="Linux_block_rq_wr" title="Disk IO" name="Write" units="B" description="Disk IO Bytes Written"/> - <event counter="Linux_block_rq_rd" title="Disk IO" name="Read" units="B" description="Disk IO Bytes Read"/> + <event counter="Linux_block_rq_wr" title="Disk I/O" name="Write" units="B" description="Disk I/O Bytes Written"/> + <event counter="Linux_block_rq_rd" title="Disk I/O" name="Read" units="B" description="Disk I/O Bytes Read"/> <event counter="Linux_net_rx" title="Network" name="Receive" units="B" description="Receive network traffic, including effect from Streamline"/> <event counter="Linux_net_tx" title="Network" name="Transmit" units="B" description="Transmit network traffic, including effect from Streamline"/> <event counter="Linux_sched_switch" title="Scheduler" name="Switch" per_cpu="yes" description="Context switch events"/> <event counter="Linux_meminfo_memused" title="Memory" name="Used" class="absolute" units="B" proc="yes" description="Total used memory size. Note: a process' used memory includes shared memory that may be counted more than once (equivalent to RES from top). Kernel threads are not filterable."/> + <event counter="Linux_meminfo_memused2" title="Memory" name="Used" class="absolute" units="B" description="Total used memory size"/> <event counter="Linux_meminfo_memfree" title="Memory" name="Free" class="absolute" display="minimum" units="B" description="Available memory size"/> <event counter="Linux_meminfo_bufferram" title="Memory" name="Buffer" class="absolute" units="B" description="Memory used by OS disk buffers"/> <event counter="Linux_power_cpu_freq" title="Clock" name="Frequency" per_cpu="yes" class="absolute" units="Hz" series_composition="overlay" average_cores="yes" description="Frequency setting of the CPU"/> - <event counter="Linux_power_cpu_idle" title="Idle" name="State" per_cpu="yes" class="absolute" description="CPU Idle State + 1, set the Sample Rate to None to prevent the hrtimer from interrupting the system"/> - <event counter="Linux_cpu_wait_contention" title="CPU Contention" name="Wait" per_cpu="no" class="activity" derived="yes" rendering_type="bar" average_selection="yes" percentage="yes" modifier="10000" color="0x003c96fb" description="Thread waiting on contended resource"/> - <event counter="Linux_cpu_wait_io" title="CPU I/O" name="Wait" per_cpu="no" class="activity" derived="yes" rendering_type="bar" average_selection="yes" percentage="yes" modifier="10000" color="0x00b30000" description="Thread waiting on I/O resource"/> + <event counter="Linux_cpu_wait_contention" title="CPU Contention" name="Wait" per_cpu="no" class="activity" derived="yes" rendering_type="bar" average_selection="yes" percentage="yes" modifier="10000" color="0x003c96fb" description="One or more threads are runnable but waiting due to CPU contention"/> + <event counter="Linux_cpu_wait_io" title="CPU I/O" name="Wait" per_cpu="no" class="activity" derived="yes" rendering_type="bar" average_selection="yes" percentage="yes" modifier="10000" color="0x00b30000" description="One or more threads are blocked on an I/O resource"/> + <event counter="Linux_power_cpu" title="CPU Status" name="Activity" class="activity" activity1="Off" activity_color1="0x0000ff00" activity2="WFI" activity_color2="0x000000ff" rendering_type="bar" average_selection="yes" average_cores="yes" percentage="yes" description="CPU Status"/> </category> diff --git a/tools/gator/daemon/events-Mali-Midgard.xml b/tools/gator/daemon/events-Mali-Midgard.xml new file mode 100644 index 000000000000..b6ab4b88cd2e --- /dev/null +++ b/tools/gator/daemon/events-Mali-Midgard.xml @@ -0,0 +1,46 @@ + <category name="Mali-Midgard Software Counters" per_cpu="no"> + <event counter="ARM_Mali-Midgard_TOTAL_ALLOC_PAGES" title="Mali Total Alloc Pages" name="Total number of allocated pages" description="Mali total number of allocated pages."/> + </category> + <category name="Mali-Midgard PM Shader" per_cpu="no"> + <event counter="ARM_Mali-Midgard_PM_SHADER_0" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 0" description="Mali PM Shader: PM Shader Core 0."/> + <event counter="ARM_Mali-Midgard_PM_SHADER_1" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 1" description="Mali PM Shader: PM Shader Core 1."/> + <event counter="ARM_Mali-Midgard_PM_SHADER_2" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 2" description="Mali PM Shader: PM Shader Core 2."/> + <event counter="ARM_Mali-Midgard_PM_SHADER_3" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 3" description="Mali PM Shader: PM Shader Core 3."/> + <event counter="ARM_Mali-Midgard_PM_SHADER_4" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 4" description="Mali PM Shader: PM Shader Core 4."/> + <event counter="ARM_Mali-Midgard_PM_SHADER_5" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 5" description="Mali PM Shader: PM Shader Core 5."/> + <event counter="ARM_Mali-Midgard_PM_SHADER_6" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 6" description="Mali PM Shader: PM Shader Core 6."/> + <event counter="ARM_Mali-Midgard_PM_SHADER_7" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 7" description="Mali PM Shader: PM Shader Core 7."/> + </category> + <category name="Mali-Midgard PM Tiler" per_cpu="no"> + <event counter="ARM_Mali-Midgard_PM_TILER_0" display="average" average_selection="yes" percentage="yes" title="Mali PM Tiler" name="PM Tiler Core 0" description="Mali PM Tiler: PM Tiler Core 0."/> + </category> + <category name="Mali-Midgard PM L2" per_cpu="no"> + <event counter="ARM_Mali-Midgard_PM_L2_0" display="average" average_selection="yes" percentage="yes" title="Mali PM L2" name="PM L2 Core 0" description="Mali PM L2: PM L2 Core 0."/> + <event counter="ARM_Mali-Midgard_PM_L2_1" display="average" average_selection="yes" percentage="yes" title="Mali PM L2" name="PM L2 Core 1" description="Mali PM L2: PM L2 Core 1."/> + </category> + <category name="Mali-Midgard MMU Address Space" per_cpu="no"> + <event counter="ARM_Mali-Midgard_MMU_AS_0" display="average" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 0" description="Mali MMU Address Space 0 usage."/> + <event counter="ARM_Mali-Midgard_MMU_AS_1" display="average" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 1" description="Mali MMU Address Space 1 usage."/> + <event counter="ARM_Mali-Midgard_MMU_AS_2" display="average" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 2" description="Mali MMU Address Space 2 usage."/> + <event counter="ARM_Mali-Midgard_MMU_AS_3" display="average" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 3" description="Mali MMU Address Space 3 usage."/> + </category> + <category name="Mali-Midgard MMU Page Fault" per_cpu="no"> + <event counter="ARM_Mali-Midgard_MMU_PAGE_FAULT_0" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 0" description="Reports the number of newly allocated pages after a MMU page fault in address space 0."/> + <event counter="ARM_Mali-Midgard_MMU_PAGE_FAULT_1" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 1" description="Reports the number of newly allocated pages after a MMU page fault in address space 1."/> + <event counter="ARM_Mali-Midgard_MMU_PAGE_FAULT_2" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 2" description="Reports the number of newly allocated pages after a MMU page fault in address space 2."/> + <event counter="ARM_Mali-Midgard_MMU_PAGE_FAULT_3" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 3" description="Reports the number of newly allocated pages after a MMU page fault in address space 3."/> + </category> + <counter_set name="ARM_Mali-Midgard_Filmstrip_cnt" count="1"/> + <category name="Mali-Midgard Filmstrip" counter_set="ARM_Mali-Midgard_Filmstrip_cnt" per_cpu="no"> + <option_set name="fs"> + <option event_delta="0x3c" name="1:60" description="captures every 60th frame"/> + <option event_delta="0x1e" name="1:30" description="captures every 30th frame"/> + <option event_delta="0xa" name="1:10" description="captures every 10th frame"/> + </option_set> + <event event="0x0400" option_set="fs" title="ARM Mali-Midgard" name="Filmstrip" description="Scaled framebuffer"/> + </category> + <category name="Mali-Midgard Activity" per_cpu="no"> + <event counter="ARM_Mali-Midgard_fragment" title="GPU Fragment" name="Activity" class="activity" activity1="Activity" activity_color1="0x00006fcc" rendering_type="bar" average_selection="yes" percentage="yes" cores="1" description="GPU Job Slot 0 Activity"/> + <event counter="ARM_Mali-Midgard_vertex" title="GPU Vertex-Tiling-Compute" name="Activity" class="activity" activity1="Activity" activity_color1="0x00eda000" rendering_type="bar" average_selection="yes" percentage="yes" cores="1" description="GPU Job Slot 1 Activity"/> + <event counter="ARM_Mali-Midgard_opencl" title="GPU Vertex-Compute" name="Activity" class="activity" activity1="Activity" activity_color1="0x00ef022f" rendering_type="bar" average_selection="yes" percentage="yes" cores="1" description="GPU Job Slot 2 Activity"/> + </category> diff --git a/tools/gator/daemon/events-Mali-Midgard_hw.xml b/tools/gator/daemon/events-Mali-Midgard_hw.xml new file mode 100644 index 000000000000..4f3323f197d7 --- /dev/null +++ b/tools/gator/daemon/events-Mali-Midgard_hw.xml @@ -0,0 +1,91 @@ + <category name="Mali-Midgard Job Manager" per_cpu="no"> + <event counter="ARM_Mali-Midgard_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles the GPU was active"/> + <event counter="ARM_Mali-Midgard_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles the GPU had a pending interrupt"/> + <event counter="ARM_Mali-Midgard_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) was active"/> + <event counter="ARM_Mali-Midgard_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) was active"/> + <event counter="ARM_Mali-Midgard_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) was active"/> + <event counter="ARM_Mali-Midgard_JS0_JOBS" title="Mali Job Manager Work" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/> + <event counter="ARM_Mali-Midgard_JS0_TASKS" title="Mali Job Manager Work" name="JS0 tasks" description="Number of Tasks completed in JS0"/> + <event counter="ARM_Mali-Midgard_JS1_JOBS" title="Mali Job Manager Work" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/> + <event counter="ARM_Mali-Midgard_JS1_TASKS" title="Mali Job Manager Work" name="JS1 tasks" description="Number of Tasks completed in JS1"/> + <event counter="ARM_Mali-Midgard_JS2_TASKS" title="Mali Job Manager Work" name="JS2 tasks" description="Number of Tasks completed in JS2"/> + <event counter="ARM_Mali-Midgard_JS2_JOBS" title="Mali Job Manager Work" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/> + </category> + <category name="Mali-Midgard Tiler" per_cpu="no"> + <event counter="ARM_Mali-Midgard_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/> + <event counter="ARM_Mali-Midgard_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/> + <event counter="ARM_Mali-Midgard_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/> + <event counter="ARM_Mali-Midgard_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/> + <event counter="ARM_Mali-Midgard_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/> + <event counter="ARM_Mali-Midgard_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/> + <event counter="ARM_Mali-Midgard_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/> + <event counter="ARM_Mali-Midgard_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/> + <event counter="ARM_Mali-Midgard_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/> + <event counter="ARM_Mali-Midgard_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/> + <event counter="ARM_Mali-Midgard_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/> + <event counter="ARM_Mali-Midgard_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/> + <event counter="ARM_Mali-Midgard_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/> + <event counter="ARM_Mali-Midgard_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/> + <event counter="ARM_Mali-Midgard_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/> + <event counter="ARM_Mali-Midgard_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/> + <event counter="ARM_Mali-Midgard_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/> + <event counter="ARM_Mali-Midgard_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/> + <event counter="ARM_Mali-Midgard_COMMAND_1" title="Mali Tiler Commands" name="Prims in 1 command" description="Number of primitives producing 1 command"/> + <event counter="ARM_Mali-Midgard_COMMAND_2" title="Mali Tiler Commands" name="Prims in 2 command" description="Number of primitives producing 2 commands"/> + <event counter="ARM_Mali-Midgard_COMMAND_3" title="Mali Tiler Commands" name="Prims in 3 command" description="Number of primitives producing 3 commands"/> + <event counter="ARM_Mali-Midgard_COMMAND_4" title="Mali Tiler Commands" name="Prims in 4 command" description="Number of primitives producing 4 commands"/> + <event counter="ARM_Mali-Midgard_COMMAND_4_7" title="Mali Tiler Commands" name="Prims in 4-7 commands" description="Number of primitives producing 4-7 commands"/> + <event counter="ARM_Mali-Midgard_COMMAND_5_7" title="Mali Tiler Commands" name="Prims in 5-7 commands" description="Number of primitives producing 5-7 commands"/> + <event counter="ARM_Mali-Midgard_COMMAND_8_15" title="Mali Tiler Commands" name="Prims in 8-15 commands" description="Number of primitives producing 8-15 commands"/> + <event counter="ARM_Mali-Midgard_COMMAND_16_63" title="Mali Tiler Commands" name="Prims in 16-63 commands" description="Number of primitives producing 16-63 commands"/> + <event counter="ARM_Mali-Midgard_COMMAND_64" title="Mali Tiler Commands" name="Prims in >= 64 commands" description="Number of primitives producing >= 64 commands"/> + </category> + <category name="Mali-Midgard Shader Core" per_cpu="no"> + <event counter="ARM_Mali-Midgard_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles the Tripipe was active"/> + <event counter="ARM_Mali-Midgard_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/> + <event counter="ARM_Mali-Midgard_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/> + <event counter="ARM_Mali-Midgard_FRAG_CYCLE_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/> + <event counter="ARM_Mali-Midgard_FRAG_THREADS" title="Mali Core Threads" name="Fragment threads" description="Number of fragment threads started"/> + <event counter="ARM_Mali-Midgard_FRAG_DUMMY_THREADS" title="Mali Core Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/> + <event counter="ARM_Mali-Midgard_FRAG_QUADS_LZS_TEST" title="Mali Core Threads" name="Frag threads doing late ZS" description="Number of threads doing late ZS test"/> + <event counter="ARM_Mali-Midgard_FRAG_QUADS_LZS_KILLED" title="Mali Core Threads" name="Frag threads killed late ZS" description="Number of threads killed by late ZS test"/> + <event counter="ARM_Mali-Midgard_FRAG_THREADS_LZS_TEST" title="Mali Core Threads" name="Frag threads doing late ZS" description="Number of threads doing late ZS test"/> + <event counter="ARM_Mali-Midgard_FRAG_THREADS_LZS_KILLED" title="Mali Core Threads" name="Frag threads killed late ZS" description="Number of threads killed by late ZS test"/> + <event counter="ARM_Mali-Midgard_COMPUTE_TASKS" title="Mali Compute Threads" name="Compute tasks" description="Number of compute tasks"/> + <event counter="ARM_Mali-Midgard_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads started" description="Number of compute threads started"/> + <event counter="ARM_Mali-Midgard_COMPUTE_CYCLES_DESC" title="Mali Compute Threads" name="Compute cycles awaiting descriptors" description="Number of compute cycles spent waiting for descriptors"/> + <event counter="ARM_Mali-Midgard_FRAG_PRIMATIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/> + <event counter="ARM_Mali-Midgard_FRAG_PRIMATIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/> + <event counter="ARM_Mali-Midgard_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/> + <event counter="ARM_Mali-Midgard_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/> + <event counter="ARM_Mali-Midgard_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/> + <event counter="ARM_Mali-Midgard_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/> + <event counter="ARM_Mali-Midgard_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/> + <event counter="ARM_Mali-Midgard_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/> + <event counter="ARM_Mali-Midgard_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/> + <event counter="ARM_Mali-Midgard_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/> + <event counter="ARM_Mali-Midgard_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/> + <event counter="ARM_Mali-Midgard_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/> + <event counter="ARM_Mali-Midgard_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/> + <event counter="ARM_Mali-Midgard_TEX_THREADS" title="Mali Texture Pipe" name="T instruction issues" description="Number of instructions issused to the T-pipe, including restarts"/> + <event counter="ARM_Mali-Midgard_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/> + <event counter="ARM_Mali-Midgard_LSC_READ_HITS" title="Mali Load/Store Cache" name="Read hits" description="Number of read hits in the Load/Store cache"/> + <event counter="ARM_Mali-Midgard_LSC_READ_MISSES" title="Mali Load/Store Cache" name="Read misses" description="Number of read misses in the Load/Store cache"/> + <event counter="ARM_Mali-Midgard_LSC_WRITE_HITS" title="Mali Load/Store Cache" name="Write hits" description="Number of write hits in the Load/Store cache"/> + <event counter="ARM_Mali-Midgard_LSC_WRITE_MISSES" title="Mali Load/Store Cache" name="Write misses" description="Number of write misses in the Load/Store cache"/> + <event counter="ARM_Mali-Midgard_LSC_ATOMIC_HITS" title="Mali Load/Store Cache" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/> + <event counter="ARM_Mali-Midgard_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/> + <event counter="ARM_Mali-Midgard_LSC_LINE_FETCHES" title="Mali Load/Store Cache" name="Line fetches" description="Number of line fetches in the Load/Store cache"/> + <event counter="ARM_Mali-Midgard_LSC_DIRTY_LINE" title="Mali Load/Store Cache" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/> + <event counter="ARM_Mali-Midgard_LSC_SNOOPS" title="Mali Load/Store Cache" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/> + </category> + <category name="Mali-Midgard L2 and MMU" per_cpu="no"> + <event counter="ARM_Mali-Midgard_L2_WRITE_BEATS" title="Mali L2 Cache" name="External write beats" description="Number of external bus write beats"/> + <event counter="ARM_Mali-Midgard_L2_READ_BEATS" title="Mali L2 Cache" name="External read beats" description="Number of external bus read beats"/> + <event counter="ARM_Mali-Midgard_L2_READ_SNOOP" title="Mali L2 Cache" name="Read snoops" description="Number of read transaction snoops"/> + <event counter="ARM_Mali-Midgard_L2_READ_HIT" title="Mali L2 Cache" name="L2 read hits" description="Number of reads hitting in the L2 cache"/> + <event counter="ARM_Mali-Midgard_L2_WRITE_SNOOP" title="Mali L2 Cache" name="Write snoops" description="Number of write transaction snoops"/> + <event counter="ARM_Mali-Midgard_L2_WRITE_HIT" title="Mali L2 Cache" name="L2 write hits" description="Number of writes hitting in the L2 cache"/> + <event counter="ARM_Mali-Midgard_L2_EXT_AR_STALL" title="Mali L2 Cache" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/> + <event counter="ARM_Mali-Midgard_L2_EXT_W_STALL" title="Mali L2 Cache" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/> + </category> diff --git a/tools/gator/daemon/events-Mali-T60x_hw.xml b/tools/gator/daemon/events-Mali-T60x_hw.xml new file mode 100644 index 000000000000..50797e6492ad --- /dev/null +++ b/tools/gator/daemon/events-Mali-T60x_hw.xml @@ -0,0 +1,108 @@ + + <category name="Mali Job Manager" per_cpu="no"> + + <event counter="ARM_Mali-T60x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/> + <event counter="ARM_Mali-T60x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/> + <event counter="ARM_Mali-T60x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/> + <event counter="ARM_Mali-T60x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/> + <event counter="ARM_Mali-T60x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/> + + <event counter="ARM_Mali-T60x_JS0_JOBS" title="Mali Job Manager Work" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/> + <event counter="ARM_Mali-T60x_JS0_TASKS" title="Mali Job Manager Work" name="JS0 tasks" description="Number of Tasks completed in JS0"/> + <event counter="ARM_Mali-T60x_JS1_JOBS" title="Mali Job Manager Work" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/> + <event counter="ARM_Mali-T60x_JS1_TASKS" title="Mali Job Manager Work" name="JS1 tasks" description="Number of Tasks completed in JS1"/> + <event counter="ARM_Mali-T60x_JS2_TASKS" title="Mali Job Manager Work" name="JS2 tasks" description="Number of Tasks completed in JS2"/> + <event counter="ARM_Mali-T60x_JS2_JOBS" title="Mali Job Manager Work" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/> + + </category> + + <category name="Mali Tiler" per_cpu="no"> + + <event counter="ARM_Mali-T60x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/> + + <event counter="ARM_Mali-T60x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/> + <event counter="ARM_Mali-T60x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/> + <event counter="ARM_Mali-T60x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/> + <event counter="ARM_Mali-T60x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/> + <event counter="ARM_Mali-T60x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/> + + <event counter="ARM_Mali-T60x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/> + <event counter="ARM_Mali-T60x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/> + <event counter="ARM_Mali-T60x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/> + <event counter="ARM_Mali-T60x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/> + <event counter="ARM_Mali-T60x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/> + + <event counter="ARM_Mali-T60x_TI_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/> + <event counter="ARM_Mali-T60x_TI_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/> + <event counter="ARM_Mali-T60x_TI_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/> + <event counter="ARM_Mali-T60x_TI_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/> + <event counter="ARM_Mali-T60x_TI_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/> + <event counter="ARM_Mali-T60x_TI_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/> + <event counter="ARM_Mali-T60x_TI_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/> + <event counter="ARM_Mali-T60x_TI_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/> + + </category> + + <category name="Mali Shader Core" per_cpu="no"> + + <event counter="ARM_Mali-T60x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/> + <event counter="ARM_Mali-T60x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/> + <event counter="ARM_Mali-T60x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/> + <event counter="ARM_Mali-T60x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/> + + <event counter="ARM_Mali-T60x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/> + <event counter="ARM_Mali-T60x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/> + <event counter="ARM_Mali-T60x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/> + <event counter="ARM_Mali-T60x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/> + + <event counter="ARM_Mali-T60x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/> + <event counter="ARM_Mali-T60x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/> + + <event counter="ARM_Mali-T60x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/> + <event counter="ARM_Mali-T60x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/> + + <event counter="ARM_Mali-T60x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/> + <event counter="ARM_Mali-T60x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/> + <event counter="ARM_Mali-T60x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/> + + <event counter="ARM_Mali-T60x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/> + <event counter="ARM_Mali-T60x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/> + + <event counter="ARM_Mali-T60x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/> + + <event counter="ARM_Mali-T60x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/> + <event counter="ARM_Mali-T60x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/> + + <event counter="ARM_Mali-T60x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/> + <event counter="ARM_Mali-T60x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/> + <event counter="ARM_Mali-T60x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/> + + <event counter="ARM_Mali-T60x_LSC_READ_HITS" title="Mali Load/Store Cache" name="Read hits" description="Number of read hits in the Load/Store cache"/> + <event counter="ARM_Mali-T60x_LSC_READ_MISSES" title="Mali Load/Store Cache" name="Read misses" description="Number of read misses in the Load/Store cache"/> + <event counter="ARM_Mali-T60x_LSC_WRITE_HITS" title="Mali Load/Store Cache" name="Write hits" description="Number of write hits in the Load/Store cache"/> + <event counter="ARM_Mali-T60x_LSC_WRITE_MISSES" title="Mali Load/Store Cache" name="Write misses" description="Number of write misses in the Load/Store cache"/> + <event counter="ARM_Mali-T60x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/> + <event counter="ARM_Mali-T60x_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/> + <event counter="ARM_Mali-T60x_LSC_LINE_FETCHES" title="Mali Load/Store Cache" name="Line fetches" description="Number of line fetches in the Load/Store cache"/> + <event counter="ARM_Mali-T60x_LSC_DIRTY_LINE" title="Mali Load/Store Cache" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/> + <event counter="ARM_Mali-T60x_LSC_SNOOPS" title="Mali Load/Store Cache" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/> + + </category> + + <category name="Mali L2 Cache" per_cpu="no"> + + <event counter="ARM_Mali-T60x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache" name="External write beats" description="Number of external bus write beats"/> + <event counter="ARM_Mali-T60x_L2_EXT_READ_BEATS" title="Mali L2 Cache" name="External read beats" description="Number of external bus read beats"/> + <event counter="ARM_Mali-T60x_L2_READ_SNOOP" title="Mali L2 Cache" name="Read snoops" description="Number of read transaction snoops"/> + <event counter="ARM_Mali-T60x_L2_READ_HIT" title="Mali L2 Cache" name="L2 read hits" description="Number of reads hitting in the L2 cache"/> + <event counter="ARM_Mali-T60x_L2_WRITE_SNOOP" title="Mali L2 Cache" name="Write snoops" description="Number of write transaction snoops"/> + <event counter="ARM_Mali-T60x_L2_WRITE_HIT" title="Mali L2 Cache" name="L2 write hits" description="Number of writes hitting in the L2 cache"/> + <event counter="ARM_Mali-T60x_L2_EXT_AR_STALL" title="Mali L2 Cache" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/> + <event counter="ARM_Mali-T60x_L2_EXT_W_STALL" title="Mali L2 Cache" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/> + <event counter="ARM_Mali-T60x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/> + <event counter="ARM_Mali-T60x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/> + <event counter="ARM_Mali-T60x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/> + <event counter="ARM_Mali-T60x_L2_READ_LOOKUP" title="Mali L2 Cache" name="L2 read lookups" description="Number of reads into the L2 cache"/> + <event counter="ARM_Mali-T60x_L2_WRITE_LOOKUP" title="Mali L2 Cache" name="L2 write lookups" description="Number of writes into the L2 cache"/> + + </category> diff --git a/tools/gator/daemon/events-Mali-T62x_hw.xml b/tools/gator/daemon/events-Mali-T62x_hw.xml new file mode 100644 index 000000000000..6ecc53c2ada1 --- /dev/null +++ b/tools/gator/daemon/events-Mali-T62x_hw.xml @@ -0,0 +1,109 @@ + + <category name="Mali Job Manager" per_cpu="no"> + + <event counter="ARM_Mali-T62x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/> + <event counter="ARM_Mali-T62x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/> + <event counter="ARM_Mali-T62x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/> + <event counter="ARM_Mali-T62x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/> + <event counter="ARM_Mali-T62x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/> + + <event counter="ARM_Mali-T62x_JS0_JOBS" title="Mali Job Manager Work" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/> + <event counter="ARM_Mali-T62x_JS0_TASKS" title="Mali Job Manager Work" name="JS0 tasks" description="Number of Tasks completed in JS0"/> + <event counter="ARM_Mali-T62x_JS1_JOBS" title="Mali Job Manager Work" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/> + <event counter="ARM_Mali-T62x_JS1_TASKS" title="Mali Job Manager Work" name="JS1 tasks" description="Number of Tasks completed in JS1"/> + <event counter="ARM_Mali-T62x_JS2_TASKS" title="Mali Job Manager Work" name="JS2 tasks" description="Number of Tasks completed in JS2"/> + <event counter="ARM_Mali-T62x_JS2_JOBS" title="Mali Job Manager Work" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/> + + </category> + + <category name="Mali Tiler" per_cpu="no"> + + <event counter="ARM_Mali-T62x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/> + + <event counter="ARM_Mali-T62x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/> + <event counter="ARM_Mali-T62x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/> + <event counter="ARM_Mali-T62x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/> + <event counter="ARM_Mali-T62x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/> + <event counter="ARM_Mali-T62x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/> + + <event counter="ARM_Mali-T62x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/> + <event counter="ARM_Mali-T62x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/> + <event counter="ARM_Mali-T62x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/> + <event counter="ARM_Mali-T62x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/> + <event counter="ARM_Mali-T62x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/> + + <event counter="ARM_Mali-T62x_TI_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/> + <event counter="ARM_Mali-T62x_TI_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/> + <event counter="ARM_Mali-T62x_TI_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/> + <event counter="ARM_Mali-T62x_TI_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/> + <event counter="ARM_Mali-T62x_TI_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/> + <event counter="ARM_Mali-T62x_TI_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/> + <event counter="ARM_Mali-T62x_TI_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/> + <event counter="ARM_Mali-T62x_TI_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/> + + </category> + + <category name="Mali Shader Core" per_cpu="no"> + + <event counter="ARM_Mali-T62x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/> + <event counter="ARM_Mali-T62x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/> + <event counter="ARM_Mali-T62x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/> + <event counter="ARM_Mali-T62x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/> + <event counter="ARM_Mali-T62x_FRAG_CYCLES_FPKQ_ACTIVE" title="Mali Core Cycles" name="Fragment cycles pre-pipe buffer not empty" description="Number of cycles the pre-pipe queue contains quads"/> + + <event counter="ARM_Mali-T62x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/> + <event counter="ARM_Mali-T62x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/> + <event counter="ARM_Mali-T62x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/> + <event counter="ARM_Mali-T62x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/> + + <event counter="ARM_Mali-T62x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/> + <event counter="ARM_Mali-T62x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/> + + <event counter="ARM_Mali-T62x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/> + <event counter="ARM_Mali-T62x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/> + + <event counter="ARM_Mali-T62x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/> + <event counter="ARM_Mali-T62x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/> + <event counter="ARM_Mali-T62x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/> + + <event counter="ARM_Mali-T62x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/> + <event counter="ARM_Mali-T62x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/> + + <event counter="ARM_Mali-T62x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/> + + <event counter="ARM_Mali-T62x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/> + <event counter="ARM_Mali-T62x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/> + + <event counter="ARM_Mali-T62x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/> + <event counter="ARM_Mali-T62x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/> + <event counter="ARM_Mali-T62x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/> + + <event counter="ARM_Mali-T62x_LSC_READ_HITS" title="Mali Load/Store Cache" name="Read hits" description="Number of read hits in the Load/Store cache"/> + <event counter="ARM_Mali-T62x_LSC_READ_MISSES" title="Mali Load/Store Cache" name="Read misses" description="Number of read misses in the Load/Store cache"/> + <event counter="ARM_Mali-T62x_LSC_WRITE_HITS" title="Mali Load/Store Cache" name="Write hits" description="Number of write hits in the Load/Store cache"/> + <event counter="ARM_Mali-T62x_LSC_WRITE_MISSES" title="Mali Load/Store Cache" name="Write misses" description="Number of write misses in the Load/Store cache"/> + <event counter="ARM_Mali-T62x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/> + <event counter="ARM_Mali-T62x_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/> + <event counter="ARM_Mali-T62x_LSC_LINE_FETCHES" title="Mali Load/Store Cache" name="Line fetches" description="Number of line fetches in the Load/Store cache"/> + <event counter="ARM_Mali-T62x_LSC_DIRTY_LINE" title="Mali Load/Store Cache" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/> + <event counter="ARM_Mali-T62x_LSC_SNOOPS" title="Mali Load/Store Cache" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/> + + </category> + + <category name="Mali L2 Cache" per_cpu="no"> + + <event counter="ARM_Mali-T62x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache" name="External write beats" description="Number of external bus write beats"/> + <event counter="ARM_Mali-T62x_L2_EXT_READ_BEATS" title="Mali L2 Cache" name="External read beats" description="Number of external bus read beats"/> + <event counter="ARM_Mali-T62x_L2_READ_SNOOP" title="Mali L2 Cache" name="Read snoops" description="Number of read transaction snoops"/> + <event counter="ARM_Mali-T62x_L2_READ_HIT" title="Mali L2 Cache" name="L2 read hits" description="Number of reads hitting in the L2 cache"/> + <event counter="ARM_Mali-T62x_L2_WRITE_SNOOP" title="Mali L2 Cache" name="Write snoops" description="Number of write transaction snoops"/> + <event counter="ARM_Mali-T62x_L2_WRITE_HIT" title="Mali L2 Cache" name="L2 write hits" description="Number of writes hitting in the L2 cache"/> + <event counter="ARM_Mali-T62x_L2_EXT_AR_STALL" title="Mali L2 Cache" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/> + <event counter="ARM_Mali-T62x_L2_EXT_W_STALL" title="Mali L2 Cache" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/> + <event counter="ARM_Mali-T62x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/> + <event counter="ARM_Mali-T62x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/> + <event counter="ARM_Mali-T62x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/> + <event counter="ARM_Mali-T62x_L2_READ_LOOKUP" title="Mali L2 Cache" name="L2 read lookups" description="Number of reads into the L2 cache"/> + <event counter="ARM_Mali-T62x_L2_WRITE_LOOKUP" title="Mali L2 Cache" name="L2 write lookups" description="Number of writes into the L2 cache"/> + + </category> diff --git a/tools/gator/daemon/events-Mali-T6xx.xml b/tools/gator/daemon/events-Mali-T6xx.xml deleted file mode 100644 index 5e8979704870..000000000000 --- a/tools/gator/daemon/events-Mali-T6xx.xml +++ /dev/null @@ -1,46 +0,0 @@ - <category name="Mali-T6xx Software Counters" per_cpu="no"> - <event counter="ARM_Mali-T6xx_TOTAL_ALLOC_PAGES" title="Mali Total Alloc Pages" name="Total number of allocated pages" description="Mali total number of allocated pages."/> - </category> - <category name="Mali-T6xx PM Shader" per_cpu="no"> - <event counter="ARM_Mali-T6xx_PM_SHADER_0" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 0" description="Mali PM Shader: PM Shader Core 0."/> - <event counter="ARM_Mali-T6xx_PM_SHADER_1" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 1" description="Mali PM Shader: PM Shader Core 1."/> - <event counter="ARM_Mali-T6xx_PM_SHADER_2" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 2" description="Mali PM Shader: PM Shader Core 2."/> - <event counter="ARM_Mali-T6xx_PM_SHADER_3" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 3" description="Mali PM Shader: PM Shader Core 3."/> - <event counter="ARM_Mali-T6xx_PM_SHADER_4" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 4" description="Mali PM Shader: PM Shader Core 4."/> - <event counter="ARM_Mali-T6xx_PM_SHADER_5" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 5" description="Mali PM Shader: PM Shader Core 5."/> - <event counter="ARM_Mali-T6xx_PM_SHADER_6" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 6" description="Mali PM Shader: PM Shader Core 6."/> - <event counter="ARM_Mali-T6xx_PM_SHADER_7" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 7" description="Mali PM Shader: PM Shader Core 7."/> - </category> - <category name="Mali-T6xx PM Tiler" per_cpu="no"> - <event counter="ARM_Mali-T6xx_PM_TILER_0" display="average" average_selection="yes" percentage="yes" title="Mali PM Tiler" name="PM Tiler Core 0" description="Mali PM Tiler: PM Tiler Core 0."/> - </category> - <category name="Mali-T6xx PM L2" per_cpu="no"> - <event counter="ARM_Mali-T6xx_PM_L2_0" display="average" average_selection="yes" percentage="yes" title="Mali PM L2" name="PM L2 Core 0" description="Mali PM L2: PM L2 Core 0."/> - <event counter="ARM_Mali-T6xx_PM_L2_1" display="average" average_selection="yes" percentage="yes" title="Mali PM L2" name="PM L2 Core 1" description="Mali PM L2: PM L2 Core 1."/> - </category> - <category name="Mali-T6xx MMU Address Space" per_cpu="no"> - <event counter="ARM_Mali-T6xx_MMU_AS_0" display="average" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 0" description="Mali MMU Address Space 0 usage."/> - <event counter="ARM_Mali-T6xx_MMU_AS_1" display="average" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 1" description="Mali MMU Address Space 1 usage."/> - <event counter="ARM_Mali-T6xx_MMU_AS_2" display="average" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 2" description="Mali MMU Address Space 2 usage."/> - <event counter="ARM_Mali-T6xx_MMU_AS_3" display="average" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 3" description="Mali MMU Address Space 3 usage."/> - </category> - <category name="Mali-T6xx MMU Page Fault" per_cpu="no"> - <event counter="ARM_Mali-T6xx_MMU_PAGE_FAULT_0" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 0" description="Reports the number of newly allocated pages after a MMU page fault in address space 0."/> - <event counter="ARM_Mali-T6xx_MMU_PAGE_FAULT_1" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 1" description="Reports the number of newly allocated pages after a MMU page fault in address space 1."/> - <event counter="ARM_Mali-T6xx_MMU_PAGE_FAULT_2" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 2" description="Reports the number of newly allocated pages after a MMU page fault in address space 2."/> - <event counter="ARM_Mali-T6xx_MMU_PAGE_FAULT_3" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 3" description="Reports the number of newly allocated pages after a MMU page fault in address space 3."/> - </category> - <counter_set name="ARM_Mali-T6xx_Filmstrip_cnt" count="1"/> - <category name="Mali-T6xx Filmstrip" counter_set="ARM_Mali-T6xx_Filmstrip_cnt" per_cpu="no"> - <option_set name="fs"> - <option event_delta="0x3c" name="1:60" description="captures every 60th frame"/> - <option event_delta="0x1e" name="1:30" description="captures every 30th frame"/> - <option event_delta="0xa" name="1:10" description="captures every 10th frame"/> - </option_set> - <event event="0x0400" option_set="fs" title="ARM Mali-T6xx" name="Filmstrip" description="Scaled framebuffer"/> - </category> - <category name="Mali-T6xx Activity" per_cpu="no"> - <event counter="ARM_Mali-T6xx_fragment" title="GPU Fragment" name="Activity" class="activity" activity1="Activity" activity_color1="0x00006fcc" rendering_type="bar" average_selection="yes" percentage="yes" cores="1" description="GPU Job Slot 0 Activity"/> - <event counter="ARM_Mali-T6xx_vertex" title="GPU Vertex-Tiling-Compute" name="Activity" class="activity" activity1="Activity" activity_color1="0x00eda000" rendering_type="bar" average_selection="yes" percentage="yes" cores="1" description="GPU Job Slot 1 Activity"/> - <event counter="ARM_Mali-T6xx_opencl" title="GPU Vertex-Compute" name="Activity" class="activity" activity1="Activity" activity_color1="0x00ef022f" rendering_type="bar" average_selection="yes" percentage="yes" cores="1" description="GPU Job Slot 2 Activity"/> - </category> diff --git a/tools/gator/daemon/events-Mali-T6xx_hw.xml b/tools/gator/daemon/events-Mali-T6xx_hw.xml deleted file mode 100644 index df2796262473..000000000000 --- a/tools/gator/daemon/events-Mali-T6xx_hw.xml +++ /dev/null @@ -1,91 +0,0 @@ - <category name="Mali-T6xx Job Manager" per_cpu="no"> - <event counter="ARM_Mali-T6xx_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles the GPU was active"/> - <event counter="ARM_Mali-T6xx_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles the GPU had a pending interrupt"/> - <event counter="ARM_Mali-T6xx_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) was active"/> - <event counter="ARM_Mali-T6xx_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) was active"/> - <event counter="ARM_Mali-T6xx_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) was active"/> - <event counter="ARM_Mali-T6xx_JS0_JOBS" title="Mali Job Manager Work" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/> - <event counter="ARM_Mali-T6xx_JS0_TASKS" title="Mali Job Manager Work" name="JS0 tasks" description="Number of Tasks completed in JS0"/> - <event counter="ARM_Mali-T6xx_JS1_JOBS" title="Mali Job Manager Work" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/> - <event counter="ARM_Mali-T6xx_JS1_TASKS" title="Mali Job Manager Work" name="JS1 tasks" description="Number of Tasks completed in JS1"/> - <event counter="ARM_Mali-T6xx_JS2_TASKS" title="Mali Job Manager Work" name="JS2 tasks" description="Number of Tasks completed in JS2"/> - <event counter="ARM_Mali-T6xx_JS2_JOBS" title="Mali Job Manager Work" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/> - </category> - <category name="Mali-T6xx Tiler" per_cpu="no"> - <event counter="ARM_Mali-T6xx_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/> - <event counter="ARM_Mali-T6xx_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/> - <event counter="ARM_Mali-T6xx_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/> - <event counter="ARM_Mali-T6xx_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/> - <event counter="ARM_Mali-T6xx_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/> - <event counter="ARM_Mali-T6xx_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/> - <event counter="ARM_Mali-T6xx_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/> - <event counter="ARM_Mali-T6xx_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/> - <event counter="ARM_Mali-T6xx_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/> - <event counter="ARM_Mali-T6xx_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/> - <event counter="ARM_Mali-T6xx_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/> - <event counter="ARM_Mali-T6xx_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/> - <event counter="ARM_Mali-T6xx_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/> - <event counter="ARM_Mali-T6xx_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/> - <event counter="ARM_Mali-T6xx_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/> - <event counter="ARM_Mali-T6xx_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/> - <event counter="ARM_Mali-T6xx_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/> - <event counter="ARM_Mali-T6xx_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/> - <event counter="ARM_Mali-T6xx_COMMAND_1" title="Mali Tiler Commands" name="Prims in 1 command" description="Number of primitives producing 1 command"/> - <event counter="ARM_Mali-T6xx_COMMAND_2" title="Mali Tiler Commands" name="Prims in 2 command" description="Number of primitives producing 2 commands"/> - <event counter="ARM_Mali-T6xx_COMMAND_3" title="Mali Tiler Commands" name="Prims in 3 command" description="Number of primitives producing 3 commands"/> - <event counter="ARM_Mali-T6xx_COMMAND_4" title="Mali Tiler Commands" name="Prims in 4 command" description="Number of primitives producing 4 commands"/> - <event counter="ARM_Mali-T6xx_COMMAND_4_7" title="Mali Tiler Commands" name="Prims in 4-7 commands" description="Number of primitives producing 4-7 commands"/> - <event counter="ARM_Mali-T6xx_COMMAND_5_7" title="Mali Tiler Commands" name="Prims in 5-7 commands" description="Number of primitives producing 5-7 commands"/> - <event counter="ARM_Mali-T6xx_COMMAND_8_15" title="Mali Tiler Commands" name="Prims in 8-15 commands" description="Number of primitives producing 8-15 commands"/> - <event counter="ARM_Mali-T6xx_COMMAND_16_63" title="Mali Tiler Commands" name="Prims in 16-63 commands" description="Number of primitives producing 16-63 commands"/> - <event counter="ARM_Mali-T6xx_COMMAND_64" title="Mali Tiler Commands" name="Prims in >= 64 commands" description="Number of primitives producing >= 64 commands"/> - </category> - <category name="Mali-T6xx Shader Core" per_cpu="no"> - <event counter="ARM_Mali-T6xx_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles the Tripipe was active"/> - <event counter="ARM_Mali-T6xx_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/> - <event counter="ARM_Mali-T6xx_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/> - <event counter="ARM_Mali-T6xx_FRAG_CYCLE_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/> - <event counter="ARM_Mali-T6xx_FRAG_THREADS" title="Mali Core Threads" name="Fragment threads" description="Number of fragment threads started"/> - <event counter="ARM_Mali-T6xx_FRAG_DUMMY_THREADS" title="Mali Core Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/> - <event counter="ARM_Mali-T6xx_FRAG_QUADS_LZS_TEST" title="Mali Core Threads" name="Frag threads doing late ZS" description="Number of threads doing late ZS test"/> - <event counter="ARM_Mali-T6xx_FRAG_QUADS_LZS_KILLED" title="Mali Core Threads" name="Frag threads killed late ZS" description="Number of threads killed by late ZS test"/> - <event counter="ARM_Mali-T6xx_FRAG_THREADS_LZS_TEST" title="Mali Core Threads" name="Frag threads doing late ZS" description="Number of threads doing late ZS test"/> - <event counter="ARM_Mali-T6xx_FRAG_THREADS_LZS_KILLED" title="Mali Core Threads" name="Frag threads killed late ZS" description="Number of threads killed by late ZS test"/> - <event counter="ARM_Mali-T6xx_COMPUTE_TASKS" title="Mali Compute Threads" name="Compute tasks" description="Number of compute tasks"/> - <event counter="ARM_Mali-T6xx_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads started" description="Number of compute threads started"/> - <event counter="ARM_Mali-T6xx_COMPUTE_CYCLES_DESC" title="Mali Compute Threads" name="Compute cycles awaiting descriptors" description="Number of compute cycles spent waiting for descriptors"/> - <event counter="ARM_Mali-T6xx_FRAG_PRIMATIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/> - <event counter="ARM_Mali-T6xx_FRAG_PRIMATIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/> - <event counter="ARM_Mali-T6xx_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/> - <event counter="ARM_Mali-T6xx_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/> - <event counter="ARM_Mali-T6xx_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/> - <event counter="ARM_Mali-T6xx_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/> - <event counter="ARM_Mali-T6xx_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/> - <event counter="ARM_Mali-T6xx_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/> - <event counter="ARM_Mali-T6xx_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/> - <event counter="ARM_Mali-T6xx_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/> - <event counter="ARM_Mali-T6xx_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/> - <event counter="ARM_Mali-T6xx_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/> - <event counter="ARM_Mali-T6xx_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/> - <event counter="ARM_Mali-T6xx_TEX_THREADS" title="Mali Texture Pipe" name="T instruction issues" description="Number of instructions issused to the T-pipe, including restarts"/> - <event counter="ARM_Mali-T6xx_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/> - <event counter="ARM_Mali-T6xx_LSC_READ_HITS" title="Mali Load/Store Cache" name="Read hits" description="Number of read hits in the Load/Store cache"/> - <event counter="ARM_Mali-T6xx_LSC_READ_MISSES" title="Mali Load/Store Cache" name="Read misses" description="Number of read misses in the Load/Store cache"/> - <event counter="ARM_Mali-T6xx_LSC_WRITE_HITS" title="Mali Load/Store Cache" name="Write hits" description="Number of write hits in the Load/Store cache"/> - <event counter="ARM_Mali-T6xx_LSC_WRITE_MISSES" title="Mali Load/Store Cache" name="Write misses" description="Number of write misses in the Load/Store cache"/> - <event counter="ARM_Mali-T6xx_LSC_ATOMIC_HITS" title="Mali Load/Store Cache" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/> - <event counter="ARM_Mali-T6xx_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/> - <event counter="ARM_Mali-T6xx_LSC_LINE_FETCHES" title="Mali Load/Store Cache" name="Line fetches" description="Number of line fetches in the Load/Store cache"/> - <event counter="ARM_Mali-T6xx_LSC_DIRTY_LINE" title="Mali Load/Store Cache" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/> - <event counter="ARM_Mali-T6xx_LSC_SNOOPS" title="Mali Load/Store Cache" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/> - </category> - <category name="Mali-T6xx L2 and MMU" per_cpu="no"> - <event counter="ARM_Mali-T6xx_L2_WRITE_BEATS" title="Mali L2 Cache" name="External write beats" description="Number of external bus write beats"/> - <event counter="ARM_Mali-T6xx_L2_READ_BEATS" title="Mali L2 Cache" name="External read beats" description="Number of external bus read beats"/> - <event counter="ARM_Mali-T6xx_L2_READ_SNOOP" title="Mali L2 Cache" name="Read snoops" description="Number of read transaction snoops"/> - <event counter="ARM_Mali-T6xx_L2_READ_HIT" title="Mali L2 Cache" name="L2 read hits" description="Number of reads hitting in the L2 cache"/> - <event counter="ARM_Mali-T6xx_L2_WRITE_SNOOP" title="Mali L2 Cache" name="Write snoops" description="Number of write transaction snoops"/> - <event counter="ARM_Mali-T6xx_L2_WRITE_HIT" title="Mali L2 Cache" name="L2 write hits" description="Number of writes hitting in the L2 cache"/> - <event counter="ARM_Mali-T6xx_L2_EXT_AR_STALL" title="Mali L2 Cache" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/> - <event counter="ARM_Mali-T6xx_L2_EXT_W_STALL" title="Mali L2 Cache" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/> - </category> diff --git a/tools/gator/daemon/events-Mali-T72x_hw.xml b/tools/gator/daemon/events-Mali-T72x_hw.xml new file mode 100644 index 000000000000..5587534770c8 --- /dev/null +++ b/tools/gator/daemon/events-Mali-T72x_hw.xml @@ -0,0 +1,95 @@ + + <category name="Mali Job Manager" per_cpu="no"> + + <event counter="ARM_Mali-T72x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/> + <event counter="ARM_Mali-T72x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/> + <event counter="ARM_Mali-T72x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/> + <event counter="ARM_Mali-T72x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/> + <event counter="ARM_Mali-T72x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/> + + <event counter="ARM_Mali-T72x_JS0_JOBS" title="Mali Job Manager Work" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/> + <event counter="ARM_Mali-T72x_JS0_TASKS" title="Mali Job Manager Work" name="JS0 tasks" description="Number of Tasks completed in JS0"/> + <event counter="ARM_Mali-T72x_JS1_JOBS" title="Mali Job Manager Work" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/> + <event counter="ARM_Mali-T72x_JS1_TASKS" title="Mali Job Manager Work" name="JS1 tasks" description="Number of Tasks completed in JS1"/> + <event counter="ARM_Mali-T72x_JS2_TASKS" title="Mali Job Manager Work" name="JS2 tasks" description="Number of Tasks completed in JS2"/> + <event counter="ARM_Mali-T72x_JS2_JOBS" title="Mali Job Manager Work" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/> + + </category> + + <category name="Mali Tiler" per_cpu="no"> + + <event counter="ARM_Mali-T72x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/> + + <event counter="ARM_Mali-T72x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/> + <event counter="ARM_Mali-T72x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/> + <event counter="ARM_Mali-T72x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/> + <event counter="ARM_Mali-T72x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/> + <event counter="ARM_Mali-T72x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/> + + <event counter="ARM_Mali-T72x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/> + <event counter="ARM_Mali-T72x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/> + <event counter="ARM_Mali-T72x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/> + <event counter="ARM_Mali-T72x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/> + <event counter="ARM_Mali-T72x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/> + + </category> + + <category name="Mali Shader Core" per_cpu="no"> + + <event counter="ARM_Mali-T72x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/> + <event counter="ARM_Mali-T72x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/> + <event counter="ARM_Mali-T72x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/> + <event counter="ARM_Mali-T72x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/> + + <event counter="ARM_Mali-T72x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/> + <event counter="ARM_Mali-T72x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/> + <event counter="ARM_Mali-T72x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/> + <event counter="ARM_Mali-T72x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/> + + <event counter="ARM_Mali-T72x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/> + <event counter="ARM_Mali-T72x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/> + + <event counter="ARM_Mali-T72x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/> + <event counter="ARM_Mali-T72x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/> + + <event counter="ARM_Mali-T72x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/> + <event counter="ARM_Mali-T72x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/> + <event counter="ARM_Mali-T72x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/> + + <event counter="ARM_Mali-T72x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/> + <event counter="ARM_Mali-T72x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/> + + <event counter="ARM_Mali-T72x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of batched instructions executed by the A-pipe"/> + + <event counter="ARM_Mali-T72x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/> + <event counter="ARM_Mali-T72x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/> + + <event counter="ARM_Mali-T72x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/> + <event counter="ARM_Mali-T72x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/> + + <event counter="ARM_Mali-T72x_LSC_READ_HITS" title="Mali Load/Store Cache" name="Read hits" description="Number of read hits in the Load/Store cache"/> + <event counter="ARM_Mali-T72x_LSC_READ_MISSES" title="Mali Load/Store Cache" name="Read misses" description="Number of read misses in the Load/Store cache"/> + <event counter="ARM_Mali-T72x_LSC_WRITE_HITS" title="Mali Load/Store Cache" name="Write hits" description="Number of write hits in the Load/Store cache"/> + <event counter="ARM_Mali-T72x_LSC_WRITE_MISSES" title="Mali Load/Store Cache" name="Write misses" description="Number of write misses in the Load/Store cache"/> + <event counter="ARM_Mali-T72x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/> + <event counter="ARM_Mali-T72x_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/> + <event counter="ARM_Mali-T72x_LSC_LINE_FETCHES" title="Mali Load/Store Cache" name="Line fetches" description="Number of line fetches in the Load/Store cache"/> + <event counter="ARM_Mali-T72x_LSC_DIRTY_LINE" title="Mali Load/Store Cache" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/> + <event counter="ARM_Mali-T72x_LSC_SNOOPS" title="Mali Load/Store Cache" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/> + + </category> + + <category name="Mali L2 Cache" per_cpu="no"> + + <event counter="ARM_Mali-T72x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache" name="External write beats" description="Number of external bus write beats"/> + <event counter="ARM_Mali-T72x_L2_EXT_READ_BEATS" title="Mali L2 Cache" name="External read beats" description="Number of external bus read beats"/> + <event counter="ARM_Mali-T72x_L2_READ_SNOOP" title="Mali L2 Cache" name="Read snoops" description="Number of read transaction snoops"/> + <event counter="ARM_Mali-T72x_L2_READ_HIT" title="Mali L2 Cache" name="L2 read hits" description="Number of reads hitting in the L2 cache"/> + <event counter="ARM_Mali-T72x_L2_WRITE_SNOOP" title="Mali L2 Cache" name="Write snoops" description="Number of write transaction snoops"/> + <event counter="ARM_Mali-T72x_L2_WRITE_HIT" title="Mali L2 Cache" name="L2 write hits" description="Number of writes hitting in the L2 cache"/> + <event counter="ARM_Mali-T72x_L2_EXT_AR_STALL" title="Mali L2 Cache" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/> + <event counter="ARM_Mali-T72x_L2_EXT_W_STALL" title="Mali L2 Cache" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/> + <event counter="ARM_Mali-T72x_L2_READ_LOOKUP" title="Mali L2 Cache" name="L2 read lookups" description="Number of reads into the L2 cache"/> + <event counter="ARM_Mali-T72x_L2_WRITE_LOOKUP" title="Mali L2 Cache" name="L2 write lookups" description="Number of writes into the L2 cache"/> + + </category> diff --git a/tools/gator/daemon/events-Mali-T76x_hw.xml b/tools/gator/daemon/events-Mali-T76x_hw.xml new file mode 100644 index 000000000000..be74c5a42624 --- /dev/null +++ b/tools/gator/daemon/events-Mali-T76x_hw.xml @@ -0,0 +1,108 @@ + + <category name="Mali Job Manager" per_cpu="no"> + + <event counter="ARM_Mali-T76x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/> + <event counter="ARM_Mali-T76x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/> + <event counter="ARM_Mali-T76x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/> + <event counter="ARM_Mali-T76x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/> + <event counter="ARM_Mali-T76x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/> + + <event counter="ARM_Mali-T76x_JS0_JOBS" title="Mali Job Manager Work" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/> + <event counter="ARM_Mali-T76x_JS0_TASKS" title="Mali Job Manager Work" name="JS0 tasks" description="Number of Tasks completed in JS0"/> + <event counter="ARM_Mali-T76x_JS1_JOBS" title="Mali Job Manager Work" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/> + <event counter="ARM_Mali-T76x_JS1_TASKS" title="Mali Job Manager Work" name="JS1 tasks" description="Number of Tasks completed in JS1"/> + <event counter="ARM_Mali-T76x_JS2_TASKS" title="Mali Job Manager Work" name="JS2 tasks" description="Number of Tasks completed in JS2"/> + <event counter="ARM_Mali-T76x_JS2_JOBS" title="Mali Job Manager Work" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/> + + </category> + + <category name="Mali Tiler" per_cpu="no"> + + <event counter="ARM_Mali-T76x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/> + + <event counter="ARM_Mali-T76x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/> + <event counter="ARM_Mali-T76x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/> + <event counter="ARM_Mali-T76x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/> + <event counter="ARM_Mali-T76x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/> + <event counter="ARM_Mali-T76x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/> + + <event counter="ARM_Mali-T76x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/> + <event counter="ARM_Mali-T76x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/> + <event counter="ARM_Mali-T76x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/> + <event counter="ARM_Mali-T76x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/> + <event counter="ARM_Mali-T76x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/> + + <event counter="ARM_Mali-T76x_TI_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/> + <event counter="ARM_Mali-T76x_TI_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/> + <event counter="ARM_Mali-T76x_TI_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/> + <event counter="ARM_Mali-T76x_TI_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/> + <event counter="ARM_Mali-T76x_TI_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/> + <event counter="ARM_Mali-T76x_TI_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/> + <event counter="ARM_Mali-T76x_TI_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/> + <event counter="ARM_Mali-T76x_TI_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/> + + </category> + + <category name="Mali Shader Core" per_cpu="no"> + + <event counter="ARM_Mali-T76x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/> + <event counter="ARM_Mali-T76x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/> + <event counter="ARM_Mali-T76x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/> + <event counter="ARM_Mali-T76x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/> + <event counter="ARM_Mali-T76x_FRAG_CYCLES_FPKQ_ACTIVE" title="Mali Core Cycles" name="Fragment cycles pre-pipe buffer not empty" description="Number of cycles the pre-pipe queue contains quads"/> + + <event counter="ARM_Mali-T76x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/> + <event counter="ARM_Mali-T76x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/> + <event counter="ARM_Mali-T76x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/> + <event counter="ARM_Mali-T76x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/> + + <event counter="ARM_Mali-T76x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/> + <event counter="ARM_Mali-T76x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/> + + <event counter="ARM_Mali-T76x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/> + <event counter="ARM_Mali-T76x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/> + + <event counter="ARM_Mali-T76x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/> + <event counter="ARM_Mali-T76x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/> + <event counter="ARM_Mali-T76x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/> + + <event counter="ARM_Mali-T76x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/> + <event counter="ARM_Mali-T76x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/> + + <event counter="ARM_Mali-T76x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/> + + <event counter="ARM_Mali-T76x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/> + <event counter="ARM_Mali-T76x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/> + + <event counter="ARM_Mali-T76x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/> + <event counter="ARM_Mali-T76x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/> + <event counter="ARM_Mali-T76x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/> + + <event counter="ARM_Mali-T76x_LSC_READ_HITS" title="Mali Load/Store Cache" name="Read hits" description="Number of read hits in the Load/Store cache"/> + <event counter="ARM_Mali-T76x_LSC_READ_MISSES" title="Mali Load/Store Cache" name="Read misses" description="Number of read misses in the Load/Store cache"/> + <event counter="ARM_Mali-T76x_LSC_WRITE_HITS" title="Mali Load/Store Cache" name="Write hits" description="Number of write hits in the Load/Store cache"/> + <event counter="ARM_Mali-T76x_LSC_WRITE_MISSES" title="Mali Load/Store Cache" name="Write misses" description="Number of write misses in the Load/Store cache"/> + <event counter="ARM_Mali-T76x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/> + <event counter="ARM_Mali-T76x_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/> + <event counter="ARM_Mali-T76x_LSC_LINE_FETCHES" title="Mali Load/Store Cache" name="Line fetches" description="Number of line fetches in the Load/Store cache"/> + <event counter="ARM_Mali-T76x_LSC_DIRTY_LINE" title="Mali Load/Store Cache" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/> + <event counter="ARM_Mali-T76x_LSC_SNOOPS" title="Mali Load/Store Cache" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/> + + </category> + + <category name="Mali L2 Cache" per_cpu="no"> + + <event counter="ARM_Mali-T76x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache" name="External write beats" description="Number of external bus write beats"/> + <event counter="ARM_Mali-T76x_L2_EXT_READ_BEATS" title="Mali L2 Cache" name="External read beats" description="Number of external bus read beats"/> + <event counter="ARM_Mali-T76x_L2_READ_SNOOP" title="Mali L2 Cache" name="Read snoops" description="Number of read transaction snoops"/> + <event counter="ARM_Mali-T76x_L2_READ_HIT" title="Mali L2 Cache" name="L2 read hits" description="Number of reads hitting in the L2 cache"/> + <event counter="ARM_Mali-T76x_L2_WRITE_SNOOP" title="Mali L2 Cache" name="Write snoops" description="Number of write transaction snoops"/> + <event counter="ARM_Mali-T76x_L2_WRITE_HIT" title="Mali L2 Cache" name="L2 write hits" description="Number of writes hitting in the L2 cache"/> + <event counter="ARM_Mali-T76x_L2_EXT_AR_STALL" title="Mali L2 Cache" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/> + <event counter="ARM_Mali-T76x_L2_EXT_W_STALL" title="Mali L2 Cache" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/> + <event counter="ARM_Mali-T76x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/> + <event counter="ARM_Mali-T76x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/> + <event counter="ARM_Mali-T76x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/> + <event counter="ARM_Mali-T76x_L2_READ_LOOKUP" title="Mali L2 Cache" name="L2 read lookups" description="Number of reads into the L2 cache"/> + <event counter="ARM_Mali-T76x_L2_WRITE_LOOKUP" title="Mali L2 Cache" name="L2 write lookups" description="Number of writes into the L2 cache"/> + </category> diff --git a/tools/gator/daemon/events-Mali-V500.xml b/tools/gator/daemon/events-Mali-V500.xml index d2751e7239b5..89bc7f4734df 100644 --- a/tools/gator/daemon/events-Mali-V500.xml +++ b/tools/gator/daemon/events-Mali-V500.xml @@ -1,29 +1,30 @@ <category name="Mali-V500"> - <event counter="ARM_Mali-V500_cnt0" title="Mali Video Engine" name="Samples" class="absolute" description="The number of times we have taken a sample"/> - <event counter="ARM_Mali-V500_cnt1" title="Mali Video Engine" name="Queued input-buffers" class="absolute" description="The number of input-buffers that has been queued for consumption by the MVE"/> - <event counter="ARM_Mali-V500_cnt2" title="Mali Video Engine" name="Consumed input-buffers" class="absolute" description="The number of input-buffers that has been consumed by the MVE and returned to the application"/> - <event counter="ARM_Mali-V500_cnt3" title="Mali Video Engine" name="Queued output-buffers" class="absolute" description="The number of output-buffers that has been queued for usage by the MVE"/> - <event counter="ARM_Mali-V500_cnt4" title="Mali Video Engine" name="Consumed output-buffers" class="absolute" description="The number of output-buffers that has been consumed by the MVE and returned to the application"/> - <event counter="ARM_Mali-V500_cnt5" title="Mali Video Engine" name="Created Sessions" class="absolute" description="The number of created sessions throughout the lifetime of the process"/> - <event counter="ARM_Mali-V500_cnt6" title="Mali Video Engine" name="Active Sessions" description="The number of currently existing sessions"/> - <event counter="ARM_Mali-V500_cnt7" title="Mali Video Engine" name="Processed Frames" class="absolute" description="The number of processed frames. A processed frame is one where the encode or decode is complete for that particular frame. Frames can be processed out of order so this is not the same as the number of output-buffers returned"/> - <event counter="ARM_Mali-V500_cnt8" title="Mali Video Engine" name="Input Flushes Requested" class="absolute" description="The number of requested flushes of the input queue"/> - <event counter="ARM_Mali-V500_cnt9" title="Mali Video Engine" name="Input Flushes Complete" class="absolute" description="The number of completed flushes of the input queue"/> - <event counter="ARM_Mali-V500_cnt10" title="Mali Video Engine" name="Output Flushes Requested" class="absolute" description="The number of requested flushes of the output queue"/> - <event counter="ARM_Mali-V500_cnt11" title="Mali Video Engine" name="Output Flushes Complete" class="absolute" description="The number of completed flushes of the output queue"/> - <event counter="ARM_Mali-V500_cnt12" title="Mali Video Engine" name="Queued Output Buffers (current)" description="The number of output-buffers that are currently queued for usage by the MVE"/> - <event counter="ARM_Mali-V500_cnt13" title="Mali Video Engine" name="Queued Input Buffers (current)" description="The number of input-buffers that are currently queued for consumption by the MVE"/> - <event counter="ARM_Mali-V500_cnt14" title="Mali Video Engine" name="Output Queue Flushes" description="The number of pending flushes for the MVE output-queue"/> - <event counter="ARM_Mali-V500_cnt15" title="Mali Video Engine" name="Input Queue Flushes" description="The number of pending flushes for the MVE input-queue"/> - <event counter="ARM_Mali-V500_cnt16" title="Mali Video Engine" name="Errors encountered" class="absolute" description="The number of errors encountered"/> - <event counter="ARM_Mali-V500_cnt17" title="Mali Video Engine" name="Bits consumed" class="absolute" description="The number of bits consumed during decode"/> - <event counter="ARM_Mali-V500_cnt18" title="Mali Video Engine" name="AFBC bandwidth" class="absolute" description="The amount of AFBC-encoded bytes read or written"/> - <event counter="ARM_Mali-V500_cnt19" title="Mali Video Engine" name="Bandwidth (read)" class="absolute" description="The amount of bytes read over the AXI bus"/> - <event counter="ARM_Mali-V500_cnt20" title="Mali Video Engine" name="Bandwidth (write)" class="absolute" description="The amount of bytes written over the AXI bus"/> - <event counter="ARM_Mali-V500_evn0" title="Mali Video Engine" name="Session created" description="Generated when a session has been created"/> - <event counter="ARM_Mali-V500_evn1" title="Mali Video Engine" name="Session destroyed" description="Generated when a session has been destroyed"/> - <event counter="ARM_Mali-V500_evn2" title="Mali Video Engine" name="Frame Processed" description="Generated when the MVE has finished processing a frame"/> - <event counter="ARM_Mali-V500_evn3" title="Mali Video Engine" name="Output buffer received" description="Generated when an an output buffer is returned to us from the MVE"/> - <event counter="ARM_Mali-V500_evn4" title="Mali Video Engine" name="Input buffer received" description="Generated when we an input buffer is returned to us from the MVE"/> - <!--event counter="ARM_Mali-V500_act" title="VPU" name="Activity" class="activity" activity1="Parsed" activity_color1="0x000000ff" activity2="Piped" activity_color2="0x0000ff00" rendering_type="bar" average_selection="yes" average_cores="yes" percentage="yes" cores="8" description="Mali-V500 Activity"/--> + <event counter="ARM_Mali-V500_cnt0" title="MVE-V500 Stats" name="Samples" class="absolute" description="The number of times we have taken a sample"/> + <event counter="ARM_Mali-V500_cnt1" title="MVE-V500 Input Totals" name="Queued input-buffers" class="absolute" description="The number of input-buffers that has been queued for consumption by the MVE"/> + <event counter="ARM_Mali-V500_cnt2" title="MVE-V500 Input Totals" name="Consumed input-buffers" class="absolute" description="The number of input-buffers that has been consumed by the MVE and returned to the application"/> + <event counter="ARM_Mali-V500_cnt3" title="MVE-V500 Output Totals" name="Queued output-buffers" class="absolute" description="The number of output-buffers that has been queued for usage by the MVE"/> + <event counter="ARM_Mali-V500_cnt4" title="MVE-V500 Output Totals" name="Consumed output-buffers" class="absolute" description="The number of output-buffers that has been consumed by the MVE and returned to the application"/> + <event counter="ARM_Mali-V500_cnt5" title="MVE-V500 Stats" name="Created Sessions" class="absolute" description="The number of created sessions throughout the lifetime of the process"/> + <event counter="ARM_Mali-V500_cnt6" title="MVE-V500 Sessions" name="Active Sessions" description="The number of currently existing sessions"/> + <event counter="ARM_Mali-V500_cnt7" title="MVE-V500 Stats" name="Processed Frames" class="absolute" description="The number of processed frames. A processed frame is one where the encode or decode is complete for that particular frame. Frames can be processed out of order so this is not the same as the number of output-buffers returned"/> + <event counter="ARM_Mali-V500_cnt8" title="MVE-V500 Input Totals" name="Input Flushes Requested" class="absolute" description="The number of requested flushes of the input queue"/> + <event counter="ARM_Mali-V500_cnt9" title="MVE-V500 Input Totals" name="Input Flushes Complete" class="absolute" description="The number of completed flushes of the input queue"/> + <event counter="ARM_Mali-V500_cnt10" title="MVE-V500 Output Totals" name="Output Flushes Requested" class="absolute" description="The number of requested flushes of the output queue"/> + <event counter="ARM_Mali-V500_cnt11" title="MVE-V500 Output Totals" name="Output Flushes Complete" class="absolute" description="The number of completed flushes of the output queue"/> + <event counter="ARM_Mali-V500_cnt12" title="MVE-V500 Output" name="Queued Output Buffers (current)" description="The number of output-buffers that are currently queued for usage by the MVE"/> + <event counter="ARM_Mali-V500_cnt13" title="MVE-V500 Input" name="Queued Input Buffers (current)" description="The number of input-buffers that are currently queued for consumption by the MVE"/> + <event counter="ARM_Mali-V500_cnt14" title="MVE-V500 Output" name="Output Queue Flushes" description="The number of pending flushes for the MVE output-queue"/> + <event counter="ARM_Mali-V500_cnt15" title="MVE-V500 Input" name="Input Queue Flushes" description="The number of pending flushes for the MVE input-queue"/> + <event counter="ARM_Mali-V500_cnt16" title="MVE-V500 Stats" name="Errors encountered" class="absolute" description="The number of errors encountered"/> + <event counter="ARM_Mali-V500_cnt17" title="MVE-V500 Bandwidth" name="Bits consumed" class="absolute" description="The number of bits consumed during decode"/> + <event counter="ARM_Mali-V500_cnt18" title="MVE-V500 Bandwidth" name="AFBC bandwidth" class="absolute" description="The amount of AFBC-encoded bytes read or written"/> + <event counter="ARM_Mali-V500_cnt19" title="MVE-V500 Bandwidth" name="Bandwidth (read)" class="absolute" description="The amount of bytes read over the AXI bus"/> + <event counter="ARM_Mali-V500_cnt20" title="MVE-V500 Bandwidth" name="Bandwidth (write)" class="absolute" description="The amount of bytes written over the AXI bus"/> + <event counter="ARM_Mali-V500_evn0" title="MVE-V500 Sessions" name="Session created" description="Generated when a session has been created"/> + <event counter="ARM_Mali-V500_evn1" title="MVE-V500 Sessions" name="Session destroyed" description="Generated when a session has been destroyed"/> + <event counter="ARM_Mali-V500_evn2" title="MVE-V500 Frames" name="Frame Processed" description="Generated when the MVE has finished processing a frame"/> + <event counter="ARM_Mali-V500_evn3" title="MVE-V500 Output" name="Output buffer received" description="Generated when an an output buffer is returned to us from the MVE"/> + <event counter="ARM_Mali-V500_evn4" title="MVE-V500 Input" name="Input buffer received" description="Generated when we an input buffer is returned to us from the MVE"/> + <event counter="ARM_Mali-V500_act0" title="MVE-V500 Parsed" name="Activity" class="activity" activity1="activity" activity_color1="0x000000ff" rendering_type="bar" average_selection="yes" average_cores="yes" percentage="yes" cores="8" description="Mali-V500 Activity"/> + <event counter="ARM_Mali-V500_act1" title="MVE-V500 Piped" name="Activity" class="activity" activity1="activity" activity_color1="0x0000ff00" rendering_type="bar" average_selection="yes" average_cores="yes" percentage="yes" cores="8" description="Mali-V500 Activity"/> </category> diff --git a/tools/gator/daemon/events-ftrace.xml b/tools/gator/daemon/events-ftrace.xml new file mode 100644 index 000000000000..33ab7aab2196 --- /dev/null +++ b/tools/gator/daemon/events-ftrace.xml @@ -0,0 +1,7 @@ + <category name="Ftrace"> + <!-- counter attribute must start with ftrace_ and be unique --> + <!-- regex item in () is the value shown --> + <!-- + <event counter="ftrace_trace_marker_numbers" title="ftrace" name="trace_marker" class="absolute" regex="([0-9]+)" description="Numbers written to /sys/kernel/debug/tracing/trace_marker, ex: echo 42 > /sys/kernel/debug/tracing/trace_marker"/> + --> + </category> diff --git a/tools/gator/daemon/main.cpp b/tools/gator/daemon/main.cpp index 2998c7012221..fbce1e15d0d0 100644 --- a/tools/gator/daemon/main.cpp +++ b/tools/gator/daemon/main.cpp @@ -19,16 +19,15 @@ #include <sys/wait.h> #include <unistd.h> +#include "CCNDriver.h" #include "Child.h" #include "EventsXML.h" -#include "KMod.h" #include "Logging.h" #include "Monitor.h" #include "OlySocket.h" #include "OlyUtility.h" #include "SessionData.h" - -#define DEBUG false +#include "Setup.h" extern Child* child; static int shutdownFilesystem(); @@ -40,8 +39,9 @@ static bool driverRunningAtStart = false; static bool driverMountedAtStart = false; struct cmdline_t { + char *module; int port; - char* module; + bool update; }; #define DEFAULT_PORT 8080 @@ -105,7 +105,6 @@ static void child_exit(int) { } } -static const int UDP_ANS_PORT = 30000; static const int UDP_REQ_PORT = 30001; typedef struct { @@ -125,11 +124,10 @@ static const char DST_REQ[] = { 'D', 'S', 'T', '_', 'R', 'E', 'Q', ' ', 0, 0, 0, class UdpListener { public: - UdpListener() : mDstAns(), mReq(-1), mAns(-1) {} + UdpListener() : mDstAns(), mReq(-1) {} void setup(int port) { mReq = udpPort(UDP_REQ_PORT); - mAns = udpPort(UDP_ANS_PORT); // Format the answer buffer memset(&mDstAns, 0, sizeof(mDstAns)); @@ -161,16 +159,13 @@ public: logg->logError(__FILE__, __LINE__, "recvfrom failed"); handleException(); } else if ((read == 12) && (memcmp(buf, DST_REQ, sizeof(DST_REQ)) == 0)) { - if (sendto(mAns, &mDstAns, sizeof(mDstAns), 0, (struct sockaddr *)&sockaddr, addrlen) != sizeof(mDstAns)) { - logg->logError(__FILE__, __LINE__, "sendto failed"); - handleException(); - } + // Don't care if sendto fails - gatord shouldn't exit because of it and Streamline will retry + sendto(mReq, &mDstAns, sizeof(mDstAns), 0, (struct sockaddr *)&sockaddr, addrlen); } } void close() { ::close(mReq); - ::close(mAns); } private: @@ -180,10 +175,10 @@ private: int on; int family = AF_INET6; - s = socket(AF_INET6, SOCK_DGRAM, IPPROTO_UDP); + s = socket_cloexec(AF_INET6, SOCK_DGRAM, IPPROTO_UDP); if (s == -1) { family = AF_INET; - s = socket(AF_INET, SOCK_DGRAM, IPPROTO_UDP); + s = socket_cloexec(AF_INET, SOCK_DGRAM, IPPROTO_UDP); if (s == -1) { logg->logError(__FILE__, __LINE__, "socket failed"); handleException(); @@ -210,7 +205,6 @@ private: RVIConfigureInfo mDstAns; int mReq; - int mAns; }; static UdpListener udpListener; @@ -233,7 +227,7 @@ static int mountGatorFS() { static bool init_module (const char * const location) { bool ret(false); - const int fd = open(location, O_RDONLY); + const int fd = open(location, O_RDONLY | O_CLOEXEC); if (fd >= 0) { struct stat st; if (fstat(fd, &st) == 0) { @@ -332,10 +326,26 @@ static int shutdownFilesystem() { return 0; // success } +static const char OPTSTRING[] = "hvudap:s:c:e:m:o:"; + +static bool hasDebugFlag(int argc, char** argv) { + int c; + + optind = 1; + while ((c = getopt(argc, argv, OPTSTRING)) != -1) { + if (c == 'd') { + return true; + } + } + + return false; +} + static struct cmdline_t parseCommandLine(int argc, char** argv) { struct cmdline_t cmdline; cmdline.port = DEFAULT_PORT; cmdline.module = NULL; + cmdline.update = false; char version_string[256]; // arbitrary length to hold the version information int c; @@ -346,11 +356,15 @@ static struct cmdline_t parseCommandLine(int argc, char** argv) { snprintf(version_string, sizeof(version_string), "Streamline gatord development version %d", PROTOCOL_VERSION); } - while ((c = getopt(argc, argv, "hvp:s:c:e:m:o:")) != -1) { - switch(c) { + optind = 1; + while ((c = getopt(argc, argv, OPTSTRING)) != -1) { + switch (c) { case 'c': gSessionData->mConfigurationXMLPath = optarg; break; + case 'd': + // Already handled + break; case 'e': gSessionData->mEventsXMLPath = optarg; break; @@ -366,6 +380,12 @@ static struct cmdline_t parseCommandLine(int argc, char** argv) { case 'o': gSessionData->mTargetPath = optarg; break; + case 'u': + cmdline.update = true; + break; + case 'a': + gSessionData->mAllowCommands = true; + break; case 'h': case '?': logg->logError(__FILE__, __LINE__, @@ -375,9 +395,11 @@ static struct cmdline_t parseCommandLine(int argc, char** argv) { "-h this help page\n" "-m module path and filename of gator.ko\n" "-p port_number port upon which the server listens; default is 8080\n" - "-s session_xml path and filename of a session xml used for local capture\n" + "-s session_xml path and filename of a session.xml used for local capture\n" "-o apc_dir path and name of the output for a local capture\n" "-v version information\n" + "-d enable debug messages\n" + "-a allow the user user to provide a command to run at the start of a capture" , version_string); handleException(); break; @@ -407,7 +429,7 @@ static struct cmdline_t parseCommandLine(int argc, char** argv) { return cmdline; } -void handleClient() { +static void handleClient() { OlySocket client(sock->acceptConnection()); int pid = fork(); @@ -452,12 +474,15 @@ int main(int argc, char** argv) { // e.g. it may not be the group leader when launched as 'sudo gatord' setsid(); - logg = new Logging(DEBUG); // Set up global thread-safe logging - gSessionData = new SessionData(); // Global data class - util = new OlyUtility(); // Set up global utility class + // Set up global thread-safe logging + logg = new Logging(hasDebugFlag(argc, argv)); + // Global data class + gSessionData = new SessionData(); + // Set up global utility class + util = new OlyUtility(); // Initialize drivers - new KMod(); + new CCNDriver(); prctl(PR_SET_NAME, (unsigned long)&"gatord-main", 0, 0, 0); pthread_mutex_init(&numSessions_mutex, NULL); @@ -474,6 +499,10 @@ int main(int argc, char** argv) { // Parse the command line parameters struct cmdline_t cmdline = parseCommandLine(argc, argv); + if (cmdline.update) { + return update(argv[0]); + } + // Verify root permissions uid_t euid = geteuid(); if (euid) { @@ -490,17 +519,18 @@ int main(int argc, char** argv) { " >>> gator.ko should be co-located with gatord in the same directory\n" " >>> OR insmod gator.ko prior to launching gatord\n" " >>> OR specify the location of gator.ko on the command line\n" - " >>> OR run Linux 3.4 or later with perf (CONFIG_PERF_EVENTS and CONFIG_HW_PERF_EVENTS) and tracing (CONFIG_TRACING) support to collect data via userspace only"); + " >>> OR run Linux 3.4 or later with perf (CONFIG_PERF_EVENTS and CONFIG_HW_PERF_EVENTS) and tracing (CONFIG_TRACING and CONFIG_CONTEXT_SWITCH_TRACER) support to collect data via userspace only"); handleException(); } } - gSessionData->hwmon.setup(); { EventsXML eventsXML; mxml_node_t *xml = eventsXML.getTree(); - gSessionData->fsDriver.setup(xml); - gSessionData->maliVideo.setup(xml); + // Initialize all drivers + for (Driver *driver = Driver::getHead(); driver != NULL; driver = driver->getNext()) { + driver->readEvents(xml); + } mxmlDelete(xml); } @@ -517,9 +547,14 @@ int main(int argc, char** argv) { child->run(); delete child; } else { + gSessionData->annotateListener.setup(); sock = new OlyServerSocket(cmdline.port); udpListener.setup(cmdline.port); - if (!monitor.init() || !monitor.add(sock->getFd()) || !monitor.add(udpListener.getReq())) { + if (!monitor.init() || + !monitor.add(sock->getFd()) || + !monitor.add(udpListener.getReq()) || + !monitor.add(gSessionData->annotateListener.getFd()) || + false) { logg->logError(__FILE__, __LINE__, "Monitor setup failed"); handleException(); } @@ -537,6 +572,8 @@ int main(int argc, char** argv) { handleClient(); } else if (events[i].data.fd == udpListener.getReq()) { udpListener.handle(); + } else if (events[i].data.fd == gSessionData->annotateListener.getFd()) { + gSessionData->annotateListener.handle(); } } } diff --git a/tools/gator/daemon/mxml/config.h b/tools/gator/daemon/mxml/config.h index 1f59ba34a474..ad6df1d7debe 100644 --- a/tools/gator/daemon/mxml/config.h +++ b/tools/gator/daemon/mxml/config.h @@ -1,10 +1,10 @@ /* config.h. Generated from config.h.in by configure. */ /* - * "$Id: config.h.in 408 2010-09-19 05:26:46Z mike $" + * "$Id: config.h.in 451 2014-01-04 21:50:06Z msweet $" * * Configuration file for Mini-XML, a small XML-like file parsing library. * - * Copyright 2003-2010 by Michael R Sweet. + * Copyright 2003-2014 by Michael R Sweet. * * These coded instructions, statements, and computer programs are the * property of Michael R Sweet and are protected by Federal copyright @@ -12,7 +12,7 @@ * which should have been included with this file. If this file is * missing or damaged, see the license at: * - * http://www.minixml.org/ + * http://www.msweet.org/projects.php/Mini-XML */ /* @@ -30,7 +30,7 @@ * Version number... */ -#define MXML_VERSION "Mini-XML v2.7" +#define MXML_VERSION "Mini-XML v2.8" /* @@ -92,5 +92,5 @@ extern int _mxml_vsnprintf(char *, size_t, const char *, va_list); # endif /* !HAVE_VSNPRINTF */ /* - * End of "$Id: config.h.in 408 2010-09-19 05:26:46Z mike $". + * End of "$Id: config.h.in 451 2014-01-04 21:50:06Z msweet $". */ diff --git a/tools/gator/daemon/mxml/mxml-attr.c b/tools/gator/daemon/mxml/mxml-attr.c index c9950f5fb732..8e89cc1474f8 100644 --- a/tools/gator/daemon/mxml/mxml-attr.c +++ b/tools/gator/daemon/mxml/mxml-attr.c @@ -1,9 +1,9 @@ /* - * "$Id: mxml-attr.c 408 2010-09-19 05:26:46Z mike $" + * "$Id: mxml-attr.c 451 2014-01-04 21:50:06Z msweet $" * * Attribute support code for Mini-XML, a small XML-like file parsing library. * - * Copyright 2003-2010 by Michael R Sweet. + * Copyright 2003-2014 by Michael R Sweet. * * These coded instructions, statements, and computer programs are the * property of Michael R Sweet and are protected by Federal copyright @@ -11,15 +11,7 @@ * which should have been included with this file. If this file is * missing or damaged, see the license at: * - * http://www.minixml.org/ - * - * Contents: - * - * mxmlElementDeleteAttr() - Delete an attribute. - * mxmlElementGetAttr() - Get an attribute. - * mxmlElementSetAttr() - Set an attribute. - * mxmlElementSetAttrf() - Set an attribute with a formatted value. - * mxml_set_attr() - Set or add an attribute name/value pair. + * http://www.msweet.org/projects.php/Mini-XML */ /* @@ -90,6 +82,9 @@ mxmlElementDeleteAttr(mxml_node_t *node,/* I - Element */ memmove(attr, attr + 1, i * sizeof(mxml_attr_t)); node->value.element.num_attrs --; + + if (node->value.element.num_attrs == 0) + free(node->value.element.attrs); return; } } @@ -315,5 +310,5 @@ mxml_set_attr(mxml_node_t *node, /* I - Element node */ /* - * End of "$Id: mxml-attr.c 408 2010-09-19 05:26:46Z mike $". + * End of "$Id: mxml-attr.c 451 2014-01-04 21:50:06Z msweet $". */ diff --git a/tools/gator/daemon/mxml/mxml-entity.c b/tools/gator/daemon/mxml/mxml-entity.c index c5c9f61f73c2..0d11df6a70bc 100644 --- a/tools/gator/daemon/mxml/mxml-entity.c +++ b/tools/gator/daemon/mxml/mxml-entity.c @@ -1,10 +1,10 @@ /* - * "$Id: mxml-entity.c 408 2010-09-19 05:26:46Z mike $" + * "$Id: mxml-entity.c 451 2014-01-04 21:50:06Z msweet $" * * Character entity support code for Mini-XML, a small XML-like * file parsing library. * - * Copyright 2003-2010 by Michael R Sweet. + * Copyright 2003-2014 by Michael R Sweet. * * These coded instructions, statements, and computer programs are the * property of Michael R Sweet and are protected by Federal copyright @@ -12,18 +12,7 @@ * which should have been included with this file. If this file is * missing or damaged, see the license at: * - * http://www.minixml.org/ - * - * Contents: - * - * mxmlEntityAddCallback() - Add a callback to convert entities to - * Unicode. - * mxmlEntityGetName() - Get the name that corresponds to the - * character value. - * mxmlEntityGetValue() - Get the character corresponding to a named - * entity. - * mxmlEntityRemoveCallback() - Remove a callback. - * _mxml_entity_cb() - Lookup standard (X)HTML entities. + * http://www.msweet.org/projects.php/Mini-XML */ /* @@ -456,5 +445,5 @@ _mxml_entity_cb(const char *name) /* I - Entity name */ /* - * End of "$Id: mxml-entity.c 408 2010-09-19 05:26:46Z mike $". + * End of "$Id: mxml-entity.c 451 2014-01-04 21:50:06Z msweet $". */ diff --git a/tools/gator/daemon/mxml/mxml-file.c b/tools/gator/daemon/mxml/mxml-file.c index 7860ee5f8370..3812c253fc3e 100644 --- a/tools/gator/daemon/mxml/mxml-file.c +++ b/tools/gator/daemon/mxml/mxml-file.c @@ -1,9 +1,9 @@ /* - * "$Id: mxml-file.c 438 2011-03-24 05:47:51Z mike $" + * "$Id: mxml-file.c 455 2014-01-05 03:28:03Z msweet $" * * File loading code for Mini-XML, a small XML-like file parsing library. * - * Copyright 2003-2011 by Michael R Sweet. + * Copyright 2003-2014 by Michael R Sweet. * * These coded instructions, statements, and computer programs are the * property of Michael R Sweet and are protected by Federal copyright @@ -11,44 +11,11 @@ * which should have been included with this file. If this file is * missing or damaged, see the license at: * - * http://www.minixml.org/ - * - * Contents: - * - * mxmlLoadFd() - Load a file descriptor into an XML node tree. - * mxmlLoadFile() - Load a file into an XML node tree. - * mxmlLoadString() - Load a string into an XML node tree. - * mxmlSaveAllocString() - Save an XML tree to an allocated string. - * mxmlSaveFd() - Save an XML tree to a file descriptor. - * mxmlSaveFile() - Save an XML tree to a file. - * mxmlSaveString() - Save an XML node tree to a string. - * mxmlSAXLoadFd() - Load a file descriptor into an XML node tree - * using a SAX callback. - * mxmlSAXLoadFile() - Load a file into an XML node tree - * using a SAX callback. - * mxmlSAXLoadString() - Load a string into an XML node tree - * using a SAX callback. - * mxmlSetCustomHandlers() - Set the handling functions for custom data. - * mxmlSetErrorCallback() - Set the error message callback. - * mxmlSetWrapMargin() - Set the wrap margin when saving XML data. - * mxml_add_char() - Add a character to a buffer, expanding as needed. - * mxml_fd_getc() - Read a character from a file descriptor. - * mxml_fd_putc() - Write a character to a file descriptor. - * mxml_fd_read() - Read a buffer of data from a file descriptor. - * mxml_fd_write() - Write a buffer of data to a file descriptor. - * mxml_file_getc() - Get a character from a file. - * mxml_file_putc() - Write a character to a file. - * mxml_get_entity() - Get the character corresponding to an entity... - * mxml_load_data() - Load data into an XML node tree. - * mxml_parse_element() - Parse an element for any attributes... - * mxml_string_getc() - Get a character from a string. - * mxml_string_putc() - Write a character to a string. - * mxml_write_name() - Write a name string. - * mxml_write_node() - Save an XML node to a file. - * mxml_write_string() - Write a string, escaping & and < as needed. - * mxml_write_ws() - Do whitespace callback... + * http://www.msweet.org/projects.php/Mini-XML */ +/*** This file modified by ARM on 25 Aug 2014 to avoid pointer overflow when checking if the write position is beyond the end of the buffer in mxmlSaveString and mxml_string_putc ***/ + /* * Include necessary headers... */ @@ -128,7 +95,7 @@ static int mxml_write_node(mxml_node_t *node, void *p, _mxml_global_t *global); static int mxml_write_string(const char *s, void *p, _mxml_putc_cb_t putc_cb); -static int mxml_write_ws(mxml_node_t *node, void *p, +static int mxml_write_ws(mxml_node_t *node, void *p, mxml_save_cb_t cb, int ws, int col, _mxml_putc_cb_t putc_cb); @@ -400,7 +367,7 @@ mxmlSaveString(mxml_node_t *node, /* I - Node to write */ mxml_save_cb_t cb) /* I - Whitespace callback or MXML_NO_CALLBACK */ { int col; /* Final column */ - char *ptr[2]; /* Pointers for putc_cb */ + char *ptr[3]; /* Pointers for putc_cb */ _mxml_global_t *global = _mxml_global(); /* Global data */ @@ -411,6 +378,7 @@ mxmlSaveString(mxml_node_t *node, /* I - Node to write */ ptr[0] = buffer; ptr[1] = buffer + bufsize; + ptr[2] = 0; if ((col = mxml_write_node(node, ptr, cb, 0, mxml_string_putc, global)) < 0) return (-1); @@ -422,7 +390,7 @@ mxmlSaveString(mxml_node_t *node, /* I - Node to write */ * Nul-terminate the buffer... */ - if (ptr[0] >= ptr[1]) + if (ptr[2] != 0) buffer[bufsize - 1] = '\0'; else ptr[0][0] = '\0'; @@ -567,7 +535,7 @@ mxmlSAXLoadString( * * The save function accepts a node pointer and must return a malloc'd * string on success and NULL on error. - * + * */ void @@ -756,7 +724,7 @@ mxml_fd_getc(void *p, /* I - File descriptor buffer */ return (EOF); ch = *(buf->current)++; - + if (ch != 0xff) return (EOF); @@ -775,7 +743,7 @@ mxml_fd_getc(void *p, /* I - File descriptor buffer */ return (EOF); ch = *(buf->current)++; - + if (ch != 0xfe) return (EOF); @@ -1287,8 +1255,8 @@ mxml_file_getc(void *p, /* I - Pointer to file */ * Multi-word UTF-16 char... */ - int lch = (getc(fp) << 8); - lch |= getc(fp); + int lch = getc(fp); + lch = (lch << 8) | getc(fp); if (lch < 0xdc00 || lch >= 0xdfff) return (EOF); @@ -1317,7 +1285,7 @@ mxml_file_getc(void *p, /* I - Pointer to file */ */ int lch = getc(fp); - lch |= (getc(fp) << 8); + lch |= (getc(fp) << 8); if (lch < 0xdc00 || lch >= 0xdfff) return (EOF); @@ -1463,8 +1431,10 @@ mxml_load_data( if (cb && parent) type = (*cb)(parent); - else + else if (parent) type = MXML_TEXT; + else + type = MXML_IGNORE; while ((ch = (*getc_cb)(p, &encoding)) != EOF) { @@ -1518,7 +1488,7 @@ mxml_load_data( default : /* Ignore... */ node = NULL; break; - } + } if (*bufptr) { @@ -1661,9 +1631,9 @@ mxml_load_data( * There can only be one root element! */ - mxml_error("<%s> cannot be a second root node after <%s>", + mxml_error("<%s> cannot be a second root node after <%s>", buffer, first->value.element.name); - goto error; + goto error; } if ((node = mxmlNewElement(parent, buffer)) == NULL) @@ -1729,9 +1699,9 @@ mxml_load_data( * There can only be one root element! */ - mxml_error("<%s> cannot be a second root node after <%s>", + mxml_error("<%s> cannot be a second root node after <%s>", buffer, first->value.element.name); - goto error; + goto error; } if ((node = mxmlNewElement(parent, buffer)) == NULL) @@ -1796,9 +1766,9 @@ mxml_load_data( * There can only be one root element! */ - mxml_error("<%s> cannot be a second root node after <%s>", + mxml_error("<%s> cannot be a second root node after <%s>", buffer, first->value.element.name); - goto error; + goto error; } if ((node = mxmlNewElement(parent, buffer)) == NULL) @@ -1882,9 +1852,9 @@ mxml_load_data( * There can only be one root element! */ - mxml_error("<%s> cannot be a second root node after <%s>", + mxml_error("<%s> cannot be a second root node after <%s>", buffer, first->value.element.name); - goto error; + goto error; } if ((node = mxmlNewElement(parent, buffer)) == NULL) @@ -1974,9 +1944,9 @@ mxml_load_data( * There can only be one root element! */ - mxml_error("<%s> cannot be a second root node after <%s>", + mxml_error("<%s> cannot be a second root node after <%s>", buffer, first->value.element.name); - goto error; + goto error; } if ((node = mxmlNewElement(parent, buffer)) == NULL) @@ -2076,7 +2046,7 @@ mxml_load_data( { node = parent; - while (parent->parent != top && parent->parent) + while (parent != top && parent->parent) parent = parent->parent; if (node != parent) @@ -2286,7 +2256,7 @@ mxml_parse_element( if (ch == '&') if ((ch = mxml_get_entity(node, p, encoding, getc_cb)) == EOF) goto error; - + if (mxml_add_char(ch, &ptr, &value, &valsize)) goto error; } @@ -2310,7 +2280,7 @@ mxml_parse_element( if (ch == '&') if ((ch = mxml_get_entity(node, p, encoding, getc_cb)) == EOF) goto error; - + if (mxml_add_char(ch, &ptr, &value, &valsize)) goto error; } @@ -2643,8 +2613,12 @@ mxml_string_putc(int ch, /* I - Character to write */ pp = (char **)p; - if (pp[0] < pp[1]) - pp[0][0] = ch; + if (pp[2] == 0) { + if (pp[0] < pp[1]) + pp[0][0] = ch; + else + pp[2] = (char *)1; + } pp[0] ++; @@ -3078,5 +3052,5 @@ mxml_write_ws(mxml_node_t *node, /* I - Current node */ /* - * End of "$Id: mxml-file.c 438 2011-03-24 05:47:51Z mike $". + * End of "$Id: mxml-file.c 455 2014-01-05 03:28:03Z msweet $". */ diff --git a/tools/gator/daemon/mxml/mxml-get.c b/tools/gator/daemon/mxml/mxml-get.c index a5356d57e186..40ed3d0839b4 100644 --- a/tools/gator/daemon/mxml/mxml-get.c +++ b/tools/gator/daemon/mxml/mxml-get.c @@ -1,9 +1,9 @@ /* - * "$Id: mxml-get.c 427 2011-01-03 02:03:29Z mike $" + * "$Id: mxml-get.c 451 2014-01-04 21:50:06Z msweet $" * * Node get functions for Mini-XML, a small XML-like file parsing library. * - * Copyright 2011 by Michael R Sweet. + * Copyright 2014 by Michael R Sweet. * * These coded instructions, statements, and computer programs are the * property of Michael R Sweet and are protected by Federal copyright @@ -11,26 +11,7 @@ * which should have been included with this file. If this file is * missing or damaged, see the license at: * - * http://www.minixml.org/ - * - * Contents: - * - * mxmlGetCDATA() - Get the value for a CDATA node. - * mxmlGetCustom() - Get the value for a custom node. - * mxmlGetElement() - Get the name for an element node. - * mxmlGetFirstChild() - Get the first child of an element node. - * mxmlGetInteger() - Get the integer value from the specified node or its - * first child. - * mxmlGetLastChild() - Get the last child of an element node. - * mxmlGetNextSibling() - Get the next node for the current parent. - * mxmlGetOpaque() - Get an opaque string value for a node or its first - * child. - * mxmlGetParent() - Get the parent node. - * mxmlGetPrevSibling() - Get the previous node for the current parent. - * mxmlGetReal() - Get the real value for a node or its first child. - * mxmlGetText() - Get the text value for a node or its first child. - * mxmlGetType() - Get the node type. - * mxmlGetUserData() - Get the user data pointer for a node. + * http://www.msweet.org/projects.php/Mini-XML */ /* @@ -467,5 +448,5 @@ mxmlGetUserData(mxml_node_t *node) /* I - Node to get */ /* - * End of "$Id: mxml-get.c 427 2011-01-03 02:03:29Z mike $". + * End of "$Id: mxml-get.c 451 2014-01-04 21:50:06Z msweet $". */ diff --git a/tools/gator/daemon/mxml/mxml-index.c b/tools/gator/daemon/mxml/mxml-index.c index b6efc66f055c..10814390d3a0 100644 --- a/tools/gator/daemon/mxml/mxml-index.c +++ b/tools/gator/daemon/mxml/mxml-index.c @@ -1,9 +1,9 @@ /* - * "$Id: mxml-index.c 426 2011-01-01 23:42:17Z mike $" + * "$Id: mxml-index.c 451 2014-01-04 21:50:06Z msweet $" * * Index support code for Mini-XML, a small XML-like file parsing library. * - * Copyright 2003-2011 by Michael R Sweet. + * Copyright 2003-2014 by Michael R Sweet. * * These coded instructions, statements, and computer programs are the * property of Michael R Sweet and are protected by Federal copyright @@ -11,10 +11,7 @@ * which should have been included with this file. If this file is * missing or damaged, see the license at: * - * http://www.minixml.org/ - * - * Contents: - * + * http://www.msweet.org/projects.php/Mini-XML */ /* @@ -658,5 +655,5 @@ index_sort(mxml_index_t *ind, /* I - Index to sort */ /* - * End of "$Id: mxml-index.c 426 2011-01-01 23:42:17Z mike $". + * End of "$Id: mxml-index.c 451 2014-01-04 21:50:06Z msweet $". */ diff --git a/tools/gator/daemon/mxml/mxml-node.c b/tools/gator/daemon/mxml/mxml-node.c index 44af759f9de3..128cda1a4cf2 100644 --- a/tools/gator/daemon/mxml/mxml-node.c +++ b/tools/gator/daemon/mxml/mxml-node.c @@ -1,9 +1,9 @@ /* - * "$Id: mxml-node.c 436 2011-01-22 01:02:05Z mike $" + * "$Id: mxml-node.c 451 2014-01-04 21:50:06Z msweet $" * * Node support code for Mini-XML, a small XML-like file parsing library. * - * Copyright 2003-2011 by Michael R Sweet. + * Copyright 2003-2014 by Michael R Sweet. * * These coded instructions, statements, and computer programs are the * property of Michael R Sweet and are protected by Federal copyright @@ -11,26 +11,7 @@ * which should have been included with this file. If this file is * missing or damaged, see the license at: * - * http://www.minixml.org/ - * - * Contents: - * - * mxmlAdd() - Add a node to a tree. - * mxmlDelete() - Delete a node and all of its children. - * mxmlGetRefCount() - Get the current reference (use) count for a node. - * mxmlNewCDATA() - Create a new CDATA node. - * mxmlNewCustom() - Create a new custom data node. - * mxmlNewElement() - Create a new element node. - * mxmlNewInteger() - Create a new integer node. - * mxmlNewOpaque() - Create a new opaque string. - * mxmlNewReal() - Create a new real number node. - * mxmlNewText() - Create a new text fragment node. - * mxmlNewTextf() - Create a new formatted text fragment node. - * mxmlRemove() - Remove a node from its parent. - * mxmlNewXML() - Create a new XML document tree. - * mxmlRelease() - Release a node. - * mxmlRetain() - Retain a node. - * mxml_new() - Create a new node. + * http://www.msweet.org/projects.php/Mini-XML */ /* @@ -529,7 +510,7 @@ mxmlNewReal(mxml_node_t *parent, /* I - Parent node or MXML_NO_PARENT */ * list. The constant MXML_NO_PARENT can be used to specify that the new * text node has no parent. The whitespace parameter is used to specify * whether leading whitespace is present before the node. The text - * string must be nul-terminated and is copied into the new node. + * string must be nul-terminated and is copied into the new node. */ mxml_node_t * /* O - New node */ @@ -573,7 +554,7 @@ mxmlNewText(mxml_node_t *parent, /* I - Parent node or MXML_NO_PARENT */ * list. The constant MXML_NO_PARENT can be used to specify that the new * text node has no parent. The whitespace parameter is used to specify * whether leading whitespace is present before the node. The format - * string must be nul-terminated and is formatted into the new node. + * string must be nul-terminated and is formatted into the new node. */ mxml_node_t * /* O - New node */ @@ -803,5 +784,5 @@ mxml_new(mxml_node_t *parent, /* I - Parent node */ /* - * End of "$Id: mxml-node.c 436 2011-01-22 01:02:05Z mike $". + * End of "$Id: mxml-node.c 451 2014-01-04 21:50:06Z msweet $". */ diff --git a/tools/gator/daemon/mxml/mxml-private.c b/tools/gator/daemon/mxml/mxml-private.c index 72f3e2320c7c..bec4bbfbf378 100644 --- a/tools/gator/daemon/mxml/mxml-private.c +++ b/tools/gator/daemon/mxml/mxml-private.c @@ -1,9 +1,9 @@ /* - * "$Id: mxml-private.c 422 2010-11-07 22:55:11Z mike $" + * "$Id: mxml-private.c 451 2014-01-04 21:50:06Z msweet $" * * Private functions for Mini-XML, a small XML-like file parsing library. * - * Copyright 2003-2010 by Michael R Sweet. + * Copyright 2003-2014 by Michael R Sweet. * * These coded instructions, statements, and computer programs are the * property of Michael R Sweet and are protected by Federal copyright @@ -11,15 +11,7 @@ * which should have been included with this file. If this file is * missing or damaged, see the license at: * - * http://www.minixml.org/ - * - * Contents: - * - * mxml_error() - Display an error message. - * mxml_integer_cb() - Default callback for integer values. - * mxml_opaque_cb() - Default callback for opaque values. - * mxml_real_cb() - Default callback for real number values. - * _mxml_global() - Get global data. + * http://www.msweet.org/projects.php/Mini-XML */ /* @@ -238,7 +230,7 @@ static DWORD _mxml_tls_index; /* Index for global storage */ /* * 'DllMain()' - Main entry for library. */ - + BOOL WINAPI /* O - Success/failure */ DllMain(HINSTANCE hinst, /* I - DLL module handle */ DWORD reason, /* I - Reason */ @@ -250,28 +242,28 @@ DllMain(HINSTANCE hinst, /* I - DLL module handle */ (void)hinst; (void)reserved; - switch (reason) - { + switch (reason) + { case DLL_PROCESS_ATTACH : /* Called on library initialization */ - if ((_mxml_tls_index = TlsAlloc()) == TLS_OUT_OF_INDEXES) - return (FALSE); - break; + if ((_mxml_tls_index = TlsAlloc()) == TLS_OUT_OF_INDEXES) + return (FALSE); + break; case DLL_THREAD_DETACH : /* Called when a thread terminates */ if ((global = (_mxml_global_t *)TlsGetValue(_mxml_tls_index)) != NULL) free(global); - break; + break; case DLL_PROCESS_DETACH : /* Called when library is unloaded */ if ((global = (_mxml_global_t *)TlsGetValue(_mxml_tls_index)) != NULL) free(global); - TlsFree(_mxml_tls_index); - break; + TlsFree(_mxml_tls_index); + break; - default: - break; - } + default: + break; + } return (TRUE); } @@ -295,7 +287,7 @@ _mxml_global(void) global->entity_cbs[0] = _mxml_entity_cb; global->wrap = 72; - TlsSetValue(_mxml_tls_index, (LPVOID)global); + TlsSetValue(_mxml_tls_index, (LPVOID)global); } return (global); @@ -327,5 +319,5 @@ _mxml_global(void) /* - * End of "$Id: mxml-private.c 422 2010-11-07 22:55:11Z mike $". + * End of "$Id: mxml-private.c 451 2014-01-04 21:50:06Z msweet $". */ diff --git a/tools/gator/daemon/mxml/mxml-private.h b/tools/gator/daemon/mxml/mxml-private.h index 8789e6c52cbd..c5e4e6b6f27a 100644 --- a/tools/gator/daemon/mxml/mxml-private.h +++ b/tools/gator/daemon/mxml/mxml-private.h @@ -1,9 +1,9 @@ /* - * "$Id: mxml-private.h 408 2010-09-19 05:26:46Z mike $" + * "$Id: mxml-private.h 451 2014-01-04 21:50:06Z msweet $" * * Private definitions for Mini-XML, a small XML-like file parsing library. * - * Copyright 2003-2010 by Michael R Sweet. + * Copyright 2003-2014 by Michael R Sweet. * * These coded instructions, statements, and computer programs are the * property of Michael R Sweet and are protected by Federal copyright @@ -11,7 +11,7 @@ * which should have been included with this file. If this file is * missing or damaged, see the license at: * - * http://www.minixml.org/ + * http://www.msweet.org/projects.php/Mini-XML */ /* @@ -46,5 +46,5 @@ extern int _mxml_entity_cb(const char *name); /* - * End of "$Id: mxml-private.h 408 2010-09-19 05:26:46Z mike $". + * End of "$Id: mxml-private.h 451 2014-01-04 21:50:06Z msweet $". */ diff --git a/tools/gator/daemon/mxml/mxml-search.c b/tools/gator/daemon/mxml/mxml-search.c index f975af1543ca..313a52f0ce2f 100644 --- a/tools/gator/daemon/mxml/mxml-search.c +++ b/tools/gator/daemon/mxml/mxml-search.c @@ -1,10 +1,10 @@ /* - * "$Id: mxml-search.c 427 2011-01-03 02:03:29Z mike $" + * "$Id: mxml-search.c 451 2014-01-04 21:50:06Z msweet $" * * Search/navigation functions for Mini-XML, a small XML-like file * parsing library. * - * Copyright 2003-2010 by Michael R Sweet. + * Copyright 2003-2014 by Michael R Sweet. * * These coded instructions, statements, and computer programs are the * property of Michael R Sweet and are protected by Federal copyright @@ -12,14 +12,7 @@ * which should have been included with this file. If this file is * missing or damaged, see the license at: * - * http://www.minixml.org/ - * - * Contents: - * - * mxmlFindElement() - Find the named element. - * mxmlFindValue() - Find a value with the given path. - * mxmlWalkNext() - Walk to the next logical node in the tree. - * mxmlWalkPrev() - Walk to the previous logical node in the tree. + * http://www.msweet.org/projects.php/Mini-XML */ /* @@ -126,7 +119,7 @@ mxmlFindElement(mxml_node_t *node, /* I - Current node */ * * The first child node of the found node is returned if the given node has * children and the first child is a value node. - * + * * @since Mini-XML 2.7@ */ @@ -283,5 +276,5 @@ mxmlWalkPrev(mxml_node_t *node, /* I - Current node */ /* - * End of "$Id: mxml-search.c 427 2011-01-03 02:03:29Z mike $". + * End of "$Id: mxml-search.c 451 2014-01-04 21:50:06Z msweet $". */ diff --git a/tools/gator/daemon/mxml/mxml-set.c b/tools/gator/daemon/mxml/mxml-set.c index b0bd52790b2e..16d4bf1050dd 100644 --- a/tools/gator/daemon/mxml/mxml-set.c +++ b/tools/gator/daemon/mxml/mxml-set.c @@ -1,9 +1,9 @@ /* - * "$Id: mxml-set.c 441 2011-12-09 23:49:00Z mike $" + * "$Id: mxml-set.c 451 2014-01-04 21:50:06Z msweet $" * * Node set functions for Mini-XML, a small XML-like file parsing library. * - * Copyright 2003-2011 by Michael R Sweet. + * Copyright 2003-2014 by Michael R Sweet. * * These coded instructions, statements, and computer programs are the * property of Michael R Sweet and are protected by Federal copyright @@ -11,19 +11,7 @@ * which should have been included with this file. If this file is * missing or damaged, see the license at: * - * http://www.minixml.org/ - * - * Contents: - * - * mxmlSetCDATA() - Set the element name of a CDATA node. - * mxmlSetCustom() - Set the data and destructor of a custom data node. - * mxmlSetElement() - Set the name of an element node. - * mxmlSetInteger() - Set the value of an integer node. - * mxmlSetOpaque() - Set the value of an opaque node. - * mxmlSetReal() - Set the value of a real number node. - * mxmlSetText() - Set the value of a text node. - * mxmlSetTextf() - Set the value of a text node to a formatted string. - * mxmlSetUserData() - Set the user data pointer for a node. + * http://www.msweet.org/projects.php/Mini-XML */ /* @@ -345,5 +333,5 @@ mxmlSetUserData(mxml_node_t *node, /* I - Node to set */ /* - * End of "$Id: mxml-set.c 441 2011-12-09 23:49:00Z mike $". + * End of "$Id: mxml-set.c 451 2014-01-04 21:50:06Z msweet $". */ diff --git a/tools/gator/daemon/mxml/mxml-string.c b/tools/gator/daemon/mxml/mxml-string.c index 6be42523f95c..9d5b58e6adb7 100644 --- a/tools/gator/daemon/mxml/mxml-string.c +++ b/tools/gator/daemon/mxml/mxml-string.c @@ -1,9 +1,9 @@ /* - * "$Id: mxml-string.c 424 2010-12-25 16:21:50Z mike $" + * "$Id: mxml-string.c 454 2014-01-05 03:25:07Z msweet $" * * String functions for Mini-XML, a small XML-like file parsing library. * - * Copyright 2003-2010 by Michael R Sweet. + * Copyright 2003-2014 by Michael R Sweet. * * These coded instructions, statements, and computer programs are the * property of Michael R Sweet and are protected by Federal copyright @@ -11,15 +11,7 @@ * which should have been included with this file. If this file is * missing or damaged, see the license at: * - * http://www.minixml.org/ - * - * Contents: - * - * _mxml_snprintf() - Format a string. - * _mxml_strdup() - Duplicate a string. - * _mxml_strdupf() - Format and duplicate a string. - * _mxml_vsnprintf() - Format a string into a fixed size buffer. - * _mxml_vstrdupf() - Format and duplicate a string. + * http://www.msweet.org/projects.php/Mini-XML */ /* @@ -38,7 +30,7 @@ # ifdef __va_copy # define va_copy(dst,src) __va_copy(dst,src) # else -# define va_copy(dst,src) memcpy(&dst, &src, sizeof(va_list)) +# define va_copy(dst,src) memcpy(&dst, src, sizeof(va_list)) # endif /* __va_copy */ #endif /* va_copy */ @@ -157,7 +149,8 @@ _mxml_vsnprintf(char *buffer, /* O - Output buffer */ if (*format == '%') { - if (bufptr && bufptr < bufend) *bufptr++ = *format; + if (bufptr && bufptr < bufend) + *bufptr++ = *format; bytes ++; format ++; continue; @@ -472,5 +465,5 @@ _mxml_vstrdupf(const char *format, /* I - Printf-style format string */ /* - * End of "$Id: mxml-string.c 424 2010-12-25 16:21:50Z mike $". + * End of "$Id: mxml-string.c 454 2014-01-05 03:25:07Z msweet $". */ diff --git a/tools/gator/daemon/mxml/mxml.h b/tools/gator/daemon/mxml/mxml.h index 79c711f4c80f..bba5fd23a67b 100644 --- a/tools/gator/daemon/mxml/mxml.h +++ b/tools/gator/daemon/mxml/mxml.h @@ -1,9 +1,9 @@ /* - * "$Id: mxml.h 427 2011-01-03 02:03:29Z mike $" + * "$Id: mxml.h 451 2014-01-04 21:50:06Z msweet $" * * Header file for Mini-XML, a small XML-like file parsing library. * - * Copyright 2003-2011 by Michael R Sweet. + * Copyright 2003-2014 by Michael R Sweet. * * These coded instructions, statements, and computer programs are the * property of Michael R Sweet and are protected by Federal copyright @@ -11,7 +11,7 @@ * which should have been included with this file. If this file is * missing or damaged, see the license at: * - * http://www.minixml.org/ + * http://www.msweet.org/projects.php/Mini-XML */ /* @@ -36,6 +36,9 @@ * Constants... */ +# define MXML_MAJOR_VERSION 2 /* Major version number */ +# define MXML_MINOR_VERSION 8 /* Minor version number */ + # define MXML_TAB 8 /* Tabs every N columns */ # define MXML_NO_CALLBACK 0 /* Don't use a type callback */ @@ -93,7 +96,7 @@ typedef enum mxml_type_e /**** The XML node type. ****/ typedef void (*mxml_custom_destroy_cb_t)(void *); /**** Custom data destructor ****/ -typedef void (*mxml_error_cb_t)(const char *); +typedef void (*mxml_error_cb_t)(const char *); /**** Error callback function ****/ typedef struct mxml_attr_s /**** An XML element attribute value. @private@ ****/ @@ -161,7 +164,7 @@ typedef struct mxml_index_s mxml_index_t; typedef int (*mxml_custom_load_cb_t)(mxml_node_t *, const char *); /**** Custom data load callback function ****/ -typedef char *(*mxml_custom_save_cb_t)(mxml_node_t *); +typedef char *(*mxml_custom_save_cb_t)(mxml_node_t *); /**** Custom data save callback function ****/ typedef int (*mxml_entity_cb_t)(const char *); @@ -173,7 +176,7 @@ typedef mxml_type_t (*mxml_load_cb_t)(mxml_node_t *); typedef const char *(*mxml_save_cb_t)(mxml_node_t *, int); /**** Save callback function ****/ -typedef void (*mxml_sax_cb_t)(mxml_node_t *, mxml_sax_event_t, void *); +typedef void (*mxml_sax_cb_t)(mxml_node_t *, mxml_sax_event_t, void *); /**** SAX callback function ****/ @@ -325,5 +328,5 @@ extern mxml_type_t mxml_real_cb(mxml_node_t *node); /* - * End of "$Id: mxml.h 427 2011-01-03 02:03:29Z mike $". + * End of "$Id: mxml.h 451 2014-01-04 21:50:06Z msweet $". */ diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index a59743fa3ef7..0001c9aa8b71 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -36,6 +36,7 @@ struct events_stats { u32 nr_invalid_chains; u32 nr_unknown_id; u32 nr_unprocessable_samples; + u32 nr_unordered_events; }; enum hist_column { diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 5da6ce74c676..c1f20e91f968 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -638,8 +638,7 @@ int perf_session_queue_event(struct perf_session *s, union perf_event *event, return -ETIME; if (timestamp < s->ordered_samples.last_flush) { - printf("Warning: Timestamp below last timeslice flush\n"); - return -EINVAL; + s->stats.nr_unordered_events++; } if (!list_empty(sc)) { @@ -1135,6 +1134,8 @@ static void perf_session__warn_about_errors(const struct perf_session *session, "Do you have a KVM guest running and not using 'perf kvm'?\n", session->stats.nr_unprocessable_samples); } + if (session->stats.nr_unordered_events != 0) + ui__warning("%u out of order events recorded.\n", session->stats.nr_unordered_events); } volatile int session_done; diff --git a/tools/testing/selftests/mount/unprivileged-remount-test.c b/tools/testing/selftests/mount/unprivileged-remount-test.c index 1b3ff2fda4d0..517785052f1c 100644 --- a/tools/testing/selftests/mount/unprivileged-remount-test.c +++ b/tools/testing/selftests/mount/unprivileged-remount-test.c @@ -6,6 +6,8 @@ #include <sys/types.h> #include <sys/mount.h> #include <sys/wait.h> +#include <sys/vfs.h> +#include <sys/statvfs.h> #include <stdlib.h> #include <unistd.h> #include <fcntl.h> @@ -32,11 +34,14 @@ # define CLONE_NEWPID 0x20000000 #endif +#ifndef MS_REC +# define MS_REC 16384 +#endif #ifndef MS_RELATIME -#define MS_RELATIME (1 << 21) +# define MS_RELATIME (1 << 21) #endif #ifndef MS_STRICTATIME -#define MS_STRICTATIME (1 << 24) +# define MS_STRICTATIME (1 << 24) #endif static void die(char *fmt, ...) @@ -48,17 +53,14 @@ static void die(char *fmt, ...) exit(EXIT_FAILURE); } -static void write_file(char *filename, char *fmt, ...) +static void vmaybe_write_file(bool enoent_ok, char *filename, char *fmt, va_list ap) { char buf[4096]; int fd; ssize_t written; int buf_len; - va_list ap; - va_start(ap, fmt); buf_len = vsnprintf(buf, sizeof(buf), fmt, ap); - va_end(ap); if (buf_len < 0) { die("vsnprintf failed: %s\n", strerror(errno)); @@ -69,6 +71,8 @@ static void write_file(char *filename, char *fmt, ...) fd = open(filename, O_WRONLY); if (fd < 0) { + if ((errno == ENOENT) && enoent_ok) + return; die("open of %s failed: %s\n", filename, strerror(errno)); } @@ -87,6 +91,65 @@ static void write_file(char *filename, char *fmt, ...) } } +static void maybe_write_file(char *filename, char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + vmaybe_write_file(true, filename, fmt, ap); + va_end(ap); + +} + +static void write_file(char *filename, char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + vmaybe_write_file(false, filename, fmt, ap); + va_end(ap); + +} + +static int read_mnt_flags(const char *path) +{ + int ret; + struct statvfs stat; + int mnt_flags; + + ret = statvfs(path, &stat); + if (ret != 0) { + die("statvfs of %s failed: %s\n", + path, strerror(errno)); + } + if (stat.f_flag & ~(ST_RDONLY | ST_NOSUID | ST_NODEV | \ + ST_NOEXEC | ST_NOATIME | ST_NODIRATIME | ST_RELATIME | \ + ST_SYNCHRONOUS | ST_MANDLOCK)) { + die("Unrecognized mount flags\n"); + } + mnt_flags = 0; + if (stat.f_flag & ST_RDONLY) + mnt_flags |= MS_RDONLY; + if (stat.f_flag & ST_NOSUID) + mnt_flags |= MS_NOSUID; + if (stat.f_flag & ST_NODEV) + mnt_flags |= MS_NODEV; + if (stat.f_flag & ST_NOEXEC) + mnt_flags |= MS_NOEXEC; + if (stat.f_flag & ST_NOATIME) + mnt_flags |= MS_NOATIME; + if (stat.f_flag & ST_NODIRATIME) + mnt_flags |= MS_NODIRATIME; + if (stat.f_flag & ST_RELATIME) + mnt_flags |= MS_RELATIME; + if (stat.f_flag & ST_SYNCHRONOUS) + mnt_flags |= MS_SYNCHRONOUS; + if (stat.f_flag & ST_MANDLOCK) + mnt_flags |= ST_MANDLOCK; + + return mnt_flags; +} + static void create_and_enter_userns(void) { uid_t uid; @@ -100,13 +163,10 @@ static void create_and_enter_userns(void) strerror(errno)); } + maybe_write_file("/proc/self/setgroups", "deny"); write_file("/proc/self/uid_map", "0 %d 1", uid); write_file("/proc/self/gid_map", "0 %d 1", gid); - if (setgroups(0, NULL) != 0) { - die("setgroups failed: %s\n", - strerror(errno)); - } if (setgid(0) != 0) { die ("setgid(0) failed %s\n", strerror(errno)); @@ -118,7 +178,8 @@ static void create_and_enter_userns(void) } static -bool test_unpriv_remount(int mount_flags, int remount_flags, int invalid_flags) +bool test_unpriv_remount(const char *fstype, const char *mount_options, + int mount_flags, int remount_flags, int invalid_flags) { pid_t child; @@ -151,9 +212,11 @@ bool test_unpriv_remount(int mount_flags, int remount_flags, int invalid_flags) strerror(errno)); } - if (mount("testing", "/tmp", "ramfs", mount_flags, NULL) != 0) { - die("mount of /tmp failed: %s\n", - strerror(errno)); + if (mount("testing", "/tmp", fstype, mount_flags, mount_options) != 0) { + die("mount of %s with options '%s' on /tmp failed: %s\n", + fstype, + mount_options? mount_options : "", + strerror(errno)); } create_and_enter_userns(); @@ -181,62 +244,127 @@ bool test_unpriv_remount(int mount_flags, int remount_flags, int invalid_flags) static bool test_unpriv_remount_simple(int mount_flags) { - return test_unpriv_remount(mount_flags, mount_flags, 0); + return test_unpriv_remount("ramfs", NULL, mount_flags, mount_flags, 0); } static bool test_unpriv_remount_atime(int mount_flags, int invalid_flags) { - return test_unpriv_remount(mount_flags, mount_flags, invalid_flags); + return test_unpriv_remount("ramfs", NULL, mount_flags, mount_flags, + invalid_flags); +} + +static bool test_priv_mount_unpriv_remount(void) +{ + pid_t child; + int ret; + const char *orig_path = "/dev"; + const char *dest_path = "/tmp"; + int orig_mnt_flags, remount_mnt_flags; + + child = fork(); + if (child == -1) { + die("fork failed: %s\n", + strerror(errno)); + } + if (child != 0) { /* parent */ + pid_t pid; + int status; + pid = waitpid(child, &status, 0); + if (pid == -1) { + die("waitpid failed: %s\n", + strerror(errno)); + } + if (pid != child) { + die("waited for %d got %d\n", + child, pid); + } + if (!WIFEXITED(status)) { + die("child did not terminate cleanly\n"); + } + return WEXITSTATUS(status) == EXIT_SUCCESS ? true : false; + } + + orig_mnt_flags = read_mnt_flags(orig_path); + + create_and_enter_userns(); + ret = unshare(CLONE_NEWNS); + if (ret != 0) { + die("unshare(CLONE_NEWNS) failed: %s\n", + strerror(errno)); + } + + ret = mount(orig_path, dest_path, "bind", MS_BIND | MS_REC, NULL); + if (ret != 0) { + die("recursive bind mount of %s onto %s failed: %s\n", + orig_path, dest_path, strerror(errno)); + } + + ret = mount(dest_path, dest_path, "none", + MS_REMOUNT | MS_BIND | orig_mnt_flags , NULL); + if (ret != 0) { + /* system("cat /proc/self/mounts"); */ + die("remount of /tmp failed: %s\n", + strerror(errno)); + } + + remount_mnt_flags = read_mnt_flags(dest_path); + if (orig_mnt_flags != remount_mnt_flags) { + die("Mount flags unexpectedly changed during remount of %s originally mounted on %s\n", + dest_path, orig_path); + } + exit(EXIT_SUCCESS); } int main(int argc, char **argv) { - if (!test_unpriv_remount_simple(MS_RDONLY|MS_NODEV)) { + if (!test_unpriv_remount_simple(MS_RDONLY)) { die("MS_RDONLY malfunctions\n"); } - if (!test_unpriv_remount_simple(MS_NODEV)) { + if (!test_unpriv_remount("devpts", "newinstance", MS_NODEV, MS_NODEV, 0)) { die("MS_NODEV malfunctions\n"); } - if (!test_unpriv_remount_simple(MS_NOSUID|MS_NODEV)) { + if (!test_unpriv_remount_simple(MS_NOSUID)) { die("MS_NOSUID malfunctions\n"); } - if (!test_unpriv_remount_simple(MS_NOEXEC|MS_NODEV)) { + if (!test_unpriv_remount_simple(MS_NOEXEC)) { die("MS_NOEXEC malfunctions\n"); } - if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODEV, - MS_NOATIME|MS_NODEV)) + if (!test_unpriv_remount_atime(MS_RELATIME, + MS_NOATIME)) { die("MS_RELATIME malfunctions\n"); } - if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODEV, - MS_NOATIME|MS_NODEV)) + if (!test_unpriv_remount_atime(MS_STRICTATIME, + MS_NOATIME)) { die("MS_STRICTATIME malfunctions\n"); } - if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODEV, - MS_STRICTATIME|MS_NODEV)) + if (!test_unpriv_remount_atime(MS_NOATIME, + MS_STRICTATIME)) { - die("MS_RELATIME malfunctions\n"); + die("MS_NOATIME malfunctions\n"); } - if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODIRATIME|MS_NODEV, - MS_NOATIME|MS_NODEV)) + if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODIRATIME, + MS_NOATIME)) { - die("MS_RELATIME malfunctions\n"); + die("MS_RELATIME|MS_NODIRATIME malfunctions\n"); } - if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODIRATIME|MS_NODEV, - MS_NOATIME|MS_NODEV)) + if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODIRATIME, + MS_NOATIME)) { - die("MS_RELATIME malfunctions\n"); + die("MS_STRICTATIME|MS_NODIRATIME malfunctions\n"); } - if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODIRATIME|MS_NODEV, - MS_STRICTATIME|MS_NODEV)) + if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODIRATIME, + MS_STRICTATIME)) { - die("MS_RELATIME malfunctions\n"); + die("MS_NOATIME|MS_DIRATIME malfunctions\n"); } - if (!test_unpriv_remount(MS_STRICTATIME|MS_NODEV, MS_NODEV, - MS_NOATIME|MS_NODEV)) + if (!test_unpriv_remount("ramfs", NULL, MS_STRICTATIME, 0, MS_NOATIME)) { die("Default atime malfunctions\n"); } + if (!test_priv_mount_unpriv_remount()) { + die("Mount flags unexpectedly changed after remount\n"); + } return EXIT_SUCCESS; } diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c index 714b94932312..1f0dc1e5f1f0 100644 --- a/virt/kvm/iommu.c +++ b/virt/kvm/iommu.c @@ -43,13 +43,13 @@ static void kvm_iommu_put_pages(struct kvm *kvm, gfn_t base_gfn, unsigned long npages); static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, - unsigned long size) + unsigned long npages) { gfn_t end_gfn; pfn_t pfn; pfn = gfn_to_pfn_memslot(slot, gfn); - end_gfn = gfn + (size >> PAGE_SHIFT); + end_gfn = gfn + npages; gfn += 1; if (is_error_noslot_pfn(pfn)) @@ -119,7 +119,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) * Pin all pages we are about to map in memory. This is * important because we unmap and unpin in 4kb steps later. */ - pfn = kvm_pin_pages(slot, gfn, page_size); + pfn = kvm_pin_pages(slot, gfn, page_size >> PAGE_SHIFT); if (is_error_noslot_pfn(pfn)) { gfn += 1; continue; @@ -131,7 +131,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) if (r) { printk(KERN_ERR "kvm_iommu_map_address:" "iommu failed to map pfn=%llx\n", pfn); - kvm_unpin_pages(kvm, pfn, page_size); + kvm_unpin_pages(kvm, pfn, page_size >> PAGE_SHIFT); goto unmap_pages; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 4bdadf1a6754..a0f02bc7b264 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -52,6 +52,7 @@ #include <asm/processor.h> #include <asm/io.h> +#include <asm/ioctl.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -1997,6 +1998,9 @@ static long kvm_vcpu_ioctl(struct file *filp, if (vcpu->kvm->mm != current->mm) return -EIO; + if (unlikely(_IOC_TYPE(ioctl) != KVMIO)) + return -EINVAL; + #if defined(CONFIG_S390) || defined(CONFIG_PPC) || defined(CONFIG_MIPS) /* * Special cases: vcpu ioctls that are asynchronous to vcpu execution, |