diff options
Diffstat (limited to 'Documentation')
37 files changed, 737 insertions, 121 deletions
diff --git a/Documentation/ABI/removed/net_dma b/Documentation/ABI/removed/net_dma new file mode 100644 index 000000000000..a173aecc2f18 --- /dev/null +++ b/Documentation/ABI/removed/net_dma @@ -0,0 +1,8 @@ +What: tcp_dma_copybreak sysctl +Date: Removed in kernel v3.13 +Contact: Dan Williams <dan.j.williams@intel.com> +Description: + Formerly the lower limit, in bytes, of the size of socket reads + that will be offloaded to a DMA copy engine. Removed due to + coherency issues of the cpu potentially touching the buffers + while dma is in flight. diff --git a/Documentation/DocBook/media/v4l/compat.xml b/Documentation/DocBook/media/v4l/compat.xml index eee6f0f4aa43..3a626d1b8f2e 100644 --- a/Documentation/DocBook/media/v4l/compat.xml +++ b/Documentation/DocBook/media/v4l/compat.xml @@ -2545,6 +2545,30 @@ fields changed from _s32 to _u32. </orderedlist> </section> + <section> + <title>V4L2 in Linux 3.16</title> + <orderedlist> + <listitem> + <para>Added event V4L2_EVENT_SOURCE_CHANGE. + </para> + </listitem> + </orderedlist> + </section> + + <section> + <title>V4L2 in Linux 3.17</title> + <orderedlist> + <listitem> + <para>Extended &v4l2-pix-format;. Added format flags. + </para> + </listitem> + <listitem> + <para>Added compound control types and &VIDIOC-QUERY-EXT-CTRL;. + </para> + </listitem> + </orderedlist> + </section> + <section id="other"> <title>Relation of V4L2 to other Linux multimedia APIs</title> diff --git a/Documentation/DocBook/media/v4l/func-poll.xml b/Documentation/DocBook/media/v4l/func-poll.xml index 85cad8bff5ba..4c73f115219b 100644 --- a/Documentation/DocBook/media/v4l/func-poll.xml +++ b/Documentation/DocBook/media/v4l/func-poll.xml @@ -29,9 +29,12 @@ can suspend execution until the driver has captured data or is ready to accept data for output.</para> <para>When streaming I/O has been negotiated this function waits -until a buffer has been filled or displayed and can be dequeued with -the &VIDIOC-DQBUF; ioctl. When buffers are already in the outgoing -queue of the driver the function returns immediately.</para> +until a buffer has been filled by the capture device and can be dequeued +with the &VIDIOC-DQBUF; ioctl. For output devices this function waits +until the device is ready to accept a new buffer to be queued up with +the &VIDIOC-QBUF; ioctl for display. When buffers are already in the outgoing +queue of the driver (capture) or the incoming queue isn't full (display) +the function returns immediately.</para> <para>On success <function>poll()</function> returns the number of file descriptors that have been selected (that is, file descriptors @@ -44,10 +47,22 @@ Capture devices set the <constant>POLLIN</constant> and flags. When the function timed out it returns a value of zero, on failure it returns <returnvalue>-1</returnvalue> and the <varname>errno</varname> variable is set appropriately. When the -application did not call &VIDIOC-QBUF; or &VIDIOC-STREAMON; yet the +application did not call &VIDIOC-STREAMON; the <function>poll()</function> function succeeds, but sets the <constant>POLLERR</constant> flag in the -<structfield>revents</structfield> field.</para> +<structfield>revents</structfield> field. When the +application has called &VIDIOC-STREAMON; for a capture device but hasn't +yet called &VIDIOC-QBUF;, the <function>poll()</function> function +succeeds and sets the <constant>POLLERR</constant> flag in the +<structfield>revents</structfield> field. For output devices this +same situation will cause <function>poll()</function> to succeed +as well, but it sets the <constant>POLLOUT</constant> and +<constant>POLLWRNORM</constant> flags in the <structfield>revents</structfield> +field.</para> + + <para>If an event occurred (see &VIDIOC-DQEVENT;) then +<constant>POLLPRI</constant> will be set in the <structfield>revents</structfield> +field and <function>poll()</function> will return.</para> <para>When use of the <function>read()</function> function has been negotiated and the driver does not capture yet, the @@ -58,10 +73,18 @@ continuously (as opposed to, for example, still images) the function may return immediately.</para> <para>When use of the <function>write()</function> function has -been negotiated the <function>poll</function> function just waits +been negotiated and the driver does not stream yet, the +<function>poll</function> function starts streaming. When that fails +it returns a <constant>POLLERR</constant> as above. Otherwise it waits until the driver is ready for a non-blocking <function>write()</function> call.</para> + <para>If the caller is only interested in events (just +<constant>POLLPRI</constant> is set in the <structfield>events</structfield> +field), then <function>poll()</function> will <emphasis>not</emphasis> +start streaming if the driver does not stream yet. This makes it +possible to just poll for events and not for buffers.</para> + <para>All drivers implementing the <function>read()</function> or <function>write()</function> function or streaming I/O must also support the <function>poll()</function> function.</para> diff --git a/Documentation/DocBook/media/v4l/v4l2.xml b/Documentation/DocBook/media/v4l/v4l2.xml index f2f81f06a17b..7cfe618f754d 100644 --- a/Documentation/DocBook/media/v4l/v4l2.xml +++ b/Documentation/DocBook/media/v4l/v4l2.xml @@ -152,10 +152,11 @@ structs, ioctls) must be noted in more detail in the history chapter applications. --> <revision> - <revnumber>3.16</revnumber> - <date>2014-05-27</date> - <authorinitials>lp</authorinitials> - <revremark>Extended &v4l2-pix-format;. Added format flags. + <revnumber>3.17</revnumber> + <date>2014-08-04</date> + <authorinitials>lp, hv</authorinitials> + <revremark>Extended &v4l2-pix-format;. Added format flags. Added compound control types +and VIDIOC_QUERY_EXT_CTRL. </revremark> </revision> @@ -538,7 +539,7 @@ and discussions on the V4L mailing list.</revremark> </partinfo> <title>Video for Linux Two API Specification</title> - <subtitle>Revision 3.14</subtitle> + <subtitle>Revision 3.17</subtitle> <chapter id="common"> &sub-common; diff --git a/Documentation/DocBook/media/v4l/vidioc-subdev-g-selection.xml b/Documentation/DocBook/media/v4l/vidioc-subdev-g-selection.xml index 1ba9e999af3f..c62a7360719b 100644 --- a/Documentation/DocBook/media/v4l/vidioc-subdev-g-selection.xml +++ b/Documentation/DocBook/media/v4l/vidioc-subdev-g-selection.xml @@ -119,7 +119,7 @@ </row> <row> <entry>&v4l2-rect;</entry> - <entry><structfield>rect</structfield></entry> + <entry><structfield>r</structfield></entry> <entry>Selection rectangle, in pixels.</entry> </row> <row> diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches index 0a523c9a5ff4..482c74947de0 100644 --- a/Documentation/SubmittingPatches +++ b/Documentation/SubmittingPatches @@ -794,6 +794,7 @@ Greg Kroah-Hartman, "How to piss off a kernel subsystem maintainer". <http://www.kroah.com/log/linux/maintainer-03.html> <http://www.kroah.com/log/linux/maintainer-04.html> <http://www.kroah.com/log/linux/maintainer-05.html> + <http://www.kroah.com/log/linux/maintainer-06.html> NO!!!! No more huge patch bombs to linux-kernel@vger.kernel.org people! <https://lkml.org/lkml/2005/7/11/336> diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt index 7740038d82bc..3c94ff3f9693 100644 --- a/Documentation/cgroups/cpusets.txt +++ b/Documentation/cgroups/cpusets.txt @@ -345,14 +345,14 @@ the named feature on. The implementation is simple. Setting the flag 'cpuset.memory_spread_page' turns on a per-process flag -PF_SPREAD_PAGE for each task that is in that cpuset or subsequently +PFA_SPREAD_PAGE for each task that is in that cpuset or subsequently joins that cpuset. The page allocation calls for the page cache -is modified to perform an inline check for this PF_SPREAD_PAGE task +is modified to perform an inline check for this PFA_SPREAD_PAGE task flag, and if set, a call to a new routine cpuset_mem_spread_node() returns the node to prefer for the allocation. Similarly, setting 'cpuset.memory_spread_slab' turns on the flag -PF_SPREAD_SLAB, and appropriately marked slab caches will allocate +PFA_SPREAD_SLAB, and appropriately marked slab caches will allocate pages from the node returned by cpuset_mem_spread_node(). The cpuset_mem_spread_node() routine is also simple. It uses the diff --git a/Documentation/devicetree/bindings/dma/rcar-audmapp.txt b/Documentation/devicetree/bindings/dma/rcar-audmapp.txt index 9f1d750d76de..61bca509d7b9 100644 --- a/Documentation/devicetree/bindings/dma/rcar-audmapp.txt +++ b/Documentation/devicetree/bindings/dma/rcar-audmapp.txt @@ -16,9 +16,9 @@ Example: * DMA client Required properties: -- dmas: a list of <[DMA multiplexer phandle] [SRS/DRS value]> pairs, - where SRS/DRS values are fixed handles, specified in the SoC - manual as the value that would be written into the PDMACHCR. +- dmas: a list of <[DMA multiplexer phandle] [SRS << 8 | DRS]> pairs. + where SRS/DRS are specified in the SoC manual. + It will be written into PDMACHCR as high 16-bit parts. - dma-names: a list of DMA channel names, one per "dmas" entry Example: diff --git a/Documentation/devicetree/bindings/input/atmel,maxtouch.txt b/Documentation/devicetree/bindings/input/atmel,maxtouch.txt index baef432e8369..1852906517ab 100644 --- a/Documentation/devicetree/bindings/input/atmel,maxtouch.txt +++ b/Documentation/devicetree/bindings/input/atmel,maxtouch.txt @@ -11,10 +11,17 @@ Required properties: Optional properties for main touchpad device: -- linux,gpio-keymap: An array of up to 4 entries indicating the Linux - keycode generated by each GPIO. Linux keycodes are defined in +- linux,gpio-keymap: When enabled, the SPT_GPIOPWN_T19 object sends messages + on GPIO bit changes. An array of up to 8 entries can be provided + indicating the Linux keycode mapped to each bit of the status byte, + starting at the LSB. Linux keycodes are defined in <dt-bindings/input/input.h>. + Note: the numbering of the GPIOs and the bit they start at varies between + maXTouch devices. You must either refer to the documentation, or + experiment to determine which bit corresponds to which input. Use + KEY_RESERVED for unused padding values. + Example: touch@4b { diff --git a/Documentation/devicetree/bindings/mfd/tc3589x.txt b/Documentation/devicetree/bindings/mfd/tc3589x.txt new file mode 100644 index 000000000000..6fcedba46ae9 --- /dev/null +++ b/Documentation/devicetree/bindings/mfd/tc3589x.txt @@ -0,0 +1,107 @@ +* Toshiba TC3589x multi-purpose expander + +The Toshiba TC3589x series are I2C-based MFD devices which may expose the +following built-in devices: gpio, keypad, rotator (vibrator), PWM (for +e.g. LEDs or vibrators) The included models are: + +- TC35890 +- TC35892 +- TC35893 +- TC35894 +- TC35895 +- TC35896 + +Required properties: + - compatible : must be "toshiba,tc35890", "toshiba,tc35892", "toshiba,tc35893", + "toshiba,tc35894", "toshiba,tc35895" or "toshiba,tc35896" + - reg : I2C address of the device + - interrupt-parent : specifies which IRQ controller we're connected to + - interrupts : the interrupt on the parent the controller is connected to + - interrupt-controller : marks the device node as an interrupt controller + - #interrupt-cells : should be <1>, the first cell is the IRQ offset on this + TC3589x interrupt controller. + +Optional nodes: + +- GPIO + This GPIO module inside the TC3589x has 24 (TC35890, TC35892) or 20 + (other models) GPIO lines. + - compatible : must be "toshiba,tc3589x-gpio" + - interrupts : interrupt on the parent, which must be the tc3589x MFD device + - interrupt-controller : marks the device node as an interrupt controller + - #interrupt-cells : should be <2>, the first cell is the IRQ offset on this + TC3589x GPIO interrupt controller, the second cell is the interrupt flags + in accordance with <dt-bindings/interrupt-controller/irq.h>. The following + flags are valid: + - IRQ_TYPE_LEVEL_LOW + - IRQ_TYPE_LEVEL_HIGH + - IRQ_TYPE_EDGE_RISING + - IRQ_TYPE_EDGE_FALLING + - IRQ_TYPE_EDGE_BOTH + - gpio-controller : marks the device node as a GPIO controller + - #gpio-cells : should be <2>, the first cell is the GPIO offset on this + GPIO controller, the second cell is the flags. + +- Keypad + This keypad is the same on all variants, supporting up to 96 different + keys. The linux-specific properties are modeled on those already existing + in other input drivers. + - compatible : must be "toshiba,tc3589x-keypad" + - debounce-delay-ms : debounce interval in milliseconds + - keypad,num-rows : number of rows in the matrix, see + bindings/input/matrix-keymap.txt + - keypad,num-columns : number of columns in the matrix, see + bindings/input/matrix-keymap.txt + - linux,keymap: the definition can be found in + bindings/input/matrix-keymap.txt + - linux,no-autorepeat: do no enable autorepeat feature. + - linux,wakeup: use any event on keypad as wakeup event. + +Example: + +tc35893@44 { + compatible = "toshiba,tc35893"; + reg = <0x44>; + interrupt-parent = <&gpio6>; + interrupts = <26 IRQ_TYPE_EDGE_RISING>; + + interrupt-controller; + #interrupt-cells = <1>; + + tc3589x_gpio { + compatible = "toshiba,tc3589x-gpio"; + interrupts = <0>; + + interrupt-controller; + #interrupt-cells = <2>; + gpio-controller; + #gpio-cells = <2>; + }; + tc3589x_keypad { + compatible = "toshiba,tc3589x-keypad"; + interrupts = <6>; + debounce-delay-ms = <4>; + keypad,num-columns = <8>; + keypad,num-rows = <8>; + linux,no-autorepeat; + linux,wakeup; + linux,keymap = <0x0301006b + 0x04010066 + 0x06040072 + 0x040200d7 + 0x0303006a + 0x0205000e + 0x0607008b + 0x0500001c + 0x0403000b + 0x03040034 + 0x05020067 + 0x0305006c + 0x040500e7 + 0x0005009e + 0x06020073 + 0x01030039 + 0x07060069 + 0x050500d9>; + }; +}; diff --git a/Documentation/devicetree/bindings/mtd/gpmc-nand.txt b/Documentation/devicetree/bindings/mtd/gpmc-nand.txt index 65f4f7c43136..ee654e95d8ad 100644 --- a/Documentation/devicetree/bindings/mtd/gpmc-nand.txt +++ b/Documentation/devicetree/bindings/mtd/gpmc-nand.txt @@ -22,7 +22,7 @@ Optional properties: width of 8 is assumed. - ti,nand-ecc-opt: A string setting the ECC layout to use. One of: - "sw" <deprecated> use "ham1" instead + "sw" 1-bit Hamming ecc code via software "hw" <deprecated> use "ham1" instead "hw-romcode" <deprecated> use "ham1" instead "ham1" 1-bit Hamming ecc code diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt index 9b03c57563a4..e45ac3f926b1 100644 --- a/Documentation/devicetree/bindings/net/stmmac.txt +++ b/Documentation/devicetree/bindings/net/stmmac.txt @@ -39,6 +39,10 @@ Optional properties: further clocks may be specified in derived bindings. - clock-names: One name for each entry in the clocks property, the first one should be "stmmaceth". +- clk_ptp_ref: this is the PTP reference clock; in case of the PTP is + available this clock is used for programming the Timestamp Addend Register. + If not passed then the system clock will be used and this is fine on some + platforms. Examples: diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,apq8064-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,apq8064-pinctrl.txt index ca5bfa5a8921..2fb90b37aa09 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,apq8064-pinctrl.txt +++ b/Documentation/devicetree/bindings/pinctrl/qcom,apq8064-pinctrl.txt @@ -62,7 +62,7 @@ Example: #gpio-cells = <2>; interrupt-controller; #interrupt-cells = <2>; - interrupts = <0 32 0x4>; + interrupts = <0 16 0x4>; pinctrl-names = "default"; pinctrl-0 = <&gsbi5_uart_default>; diff --git a/Documentation/devicetree/bindings/regulator/tps65090.txt b/Documentation/devicetree/bindings/regulator/tps65090.txt index 340980239ea9..ca69f5e3040c 100644 --- a/Documentation/devicetree/bindings/regulator/tps65090.txt +++ b/Documentation/devicetree/bindings/regulator/tps65090.txt @@ -45,8 +45,8 @@ Example: infet5-supply = <&some_reg>; infet6-supply = <&some_reg>; infet7-supply = <&some_reg>; - vsys_l1-supply = <&some_reg>; - vsys_l2-supply = <&some_reg>; + vsys-l1-supply = <&some_reg>; + vsys-l2-supply = <&some_reg>; regulators { dcdc1 { diff --git a/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt b/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt index 46f344965313..4eb7997674a0 100644 --- a/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt +++ b/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt @@ -1,7 +1,7 @@ ADI AXI-SPDIF controller Required properties: - - compatible : Must be "adi,axi-spdif-1.00.a" + - compatible : Must be "adi,axi-spdif-tx-1.00.a" - reg : Must contain SPDIF core's registers location and length - clocks : Pairs of phandle and specifier referencing the controller's clocks. The controller expects two clocks, the clock used for the AXI interface and diff --git a/Documentation/devicetree/bindings/sound/rockchip-i2s.txt b/Documentation/devicetree/bindings/sound/rockchip-i2s.txt index 6c55fcfe5e1d..9b82c20b306b 100644 --- a/Documentation/devicetree/bindings/sound/rockchip-i2s.txt +++ b/Documentation/devicetree/bindings/sound/rockchip-i2s.txt @@ -31,7 +31,7 @@ i2s@ff890000 { #address-cells = <1>; #size-cells = <0>; dmas = <&pdma1 0>, <&pdma1 1>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; clock-names = "i2s_hclk", "i2s_clk"; clocks = <&cru HCLK_I2S0>, <&cru SCLK_I2S0>; }; diff --git a/Documentation/devicetree/bindings/spi/spi-rockchip.txt b/Documentation/devicetree/bindings/spi/spi-rockchip.txt index 7bab35575817..467dec441c62 100644 --- a/Documentation/devicetree/bindings/spi/spi-rockchip.txt +++ b/Documentation/devicetree/bindings/spi/spi-rockchip.txt @@ -16,11 +16,15 @@ Required Properties: - clocks: Must contain an entry for each entry in clock-names. - clock-names: Shall be "spiclk" for the transfer-clock, and "apb_pclk" for the peripheral clock. +- #address-cells: should be 1. +- #size-cells: should be 0. + +Optional Properties: + - dmas: DMA specifiers for tx and rx dma. See the DMA client binding, Documentation/devicetree/bindings/dma/dma.txt - dma-names: DMA request names should include "tx" and "rx" if present. -- #address-cells: should be 1. -- #size-cells: should be 0. + Example: diff --git a/Documentation/devicetree/bindings/staging/imx-drm/ldb.txt b/Documentation/devicetree/bindings/staging/imx-drm/ldb.txt index 578a1fca366e..443bcb6134d5 100644 --- a/Documentation/devicetree/bindings/staging/imx-drm/ldb.txt +++ b/Documentation/devicetree/bindings/staging/imx-drm/ldb.txt @@ -56,6 +56,9 @@ Required properties: - fsl,data-width : should be <18> or <24> - port: A port node with endpoint definitions as defined in Documentation/devicetree/bindings/media/video-interfaces.txt. + On i.MX5, the internal two-input-multiplexer is used. + Due to hardware limitations, only one port (port@[0,1]) + can be used for each channel (lvds-channel@[0,1], respectively) On i.MX6, there should be four ports (port@[0-3]) that correspond to the four LVDS multiplexer inputs. @@ -78,6 +81,8 @@ ldb: ldb@53fa8008 { "di0", "di1"; lvds-channel@0 { + #address-cells = <1>; + #size-cells = <0>; reg = <0>; fsl,data-mapping = "spwg"; fsl,data-width = <24>; @@ -86,7 +91,9 @@ ldb: ldb@53fa8008 { /* ... */ }; - port { + port@0 { + reg = <0>; + lvds0_in: endpoint { remote-endpoint = <&ipu_di0_lvds0>; }; @@ -94,6 +101,8 @@ ldb: ldb@53fa8008 { }; lvds-channel@1 { + #address-cells = <1>; + #size-cells = <0>; reg = <1>; fsl,data-mapping = "spwg"; fsl,data-width = <24>; @@ -102,7 +111,9 @@ ldb: ldb@53fa8008 { /* ... */ }; - port { + port@1 { + reg = <1>; + lvds1_in: endpoint { remote-endpoint = <&ipu_di1_lvds1>; }; diff --git a/Documentation/devicetree/bindings/usb/mxs-phy.txt b/Documentation/devicetree/bindings/usb/mxs-phy.txt index cef181a9d8bd..96681c93b86d 100644 --- a/Documentation/devicetree/bindings/usb/mxs-phy.txt +++ b/Documentation/devicetree/bindings/usb/mxs-phy.txt @@ -5,6 +5,7 @@ Required properties: * "fsl,imx23-usbphy" for imx23 and imx28 * "fsl,imx6q-usbphy" for imx6dq and imx6dl * "fsl,imx6sl-usbphy" for imx6sl + * "fsl,imx6sx-usbphy" for imx6sx "fsl,imx23-usbphy" is still a fallback for other strings - reg: Should contain registers location and length - interrupts: Should contain phy interrupt diff --git a/Documentation/devicetree/bindings/video/analog-tv-connector.txt b/Documentation/devicetree/bindings/video/analog-tv-connector.txt index 0218fcdc1299..0c0970c210ab 100644 --- a/Documentation/devicetree/bindings/video/analog-tv-connector.txt +++ b/Documentation/devicetree/bindings/video/analog-tv-connector.txt @@ -2,7 +2,7 @@ Analog TV Connector =================== Required properties: -- compatible: "composite-connector" or "svideo-connector" +- compatible: "composite-video-connector" or "svideo-connector" Optional properties: - label: a symbolic name for the connector @@ -14,7 +14,7 @@ Example ------- tv: connector { - compatible = "composite-connector"; + compatible = "composite-video-connector"; label = "tv"; port { diff --git a/Documentation/devicetree/of_selftest.txt b/Documentation/devicetree/of_selftest.txt new file mode 100644 index 000000000000..3a2f54d07fc5 --- /dev/null +++ b/Documentation/devicetree/of_selftest.txt @@ -0,0 +1,211 @@ +Open Firmware Device Tree Selftest +---------------------------------- + +Author: Gaurav Minocha <gaurav.minocha.os@gmail.com> + +1. Introduction + +This document explains how the test data required for executing OF selftest +is attached to the live tree dynamically, independent of the machine's +architecture. + +It is recommended to read the following documents before moving ahead. + +[1] Documentation/devicetree/usage-model.txt +[2] http://www.devicetree.org/Device_Tree_Usage + +OF Selftest has been designed to test the interface (include/linux/of.h) +provided to device driver developers to fetch the device information..etc. +from the unflattened device tree data structure. This interface is used by +most of the device drivers in various use cases. + + +2. Test-data + +The Device Tree Source file (drivers/of/testcase-data/testcases.dts) contains +the test data required for executing the unit tests automated in +drivers/of/selftests.c. Currently, following Device Tree Source Include files +(.dtsi) are included in testcase.dts: + +drivers/of/testcase-data/tests-interrupts.dtsi +drivers/of/testcase-data/tests-platform.dtsi +drivers/of/testcase-data/tests-phandle.dtsi +drivers/of/testcase-data/tests-match.dtsi + +When the kernel is build with OF_SELFTEST enabled, then the following make rule + +$(obj)/%.dtb: $(src)/%.dts FORCE + $(call if_changed_dep, dtc) + +is used to compile the DT source file (testcase.dts) into a binary blob +(testcase.dtb), also referred as flattened DT. + +After that, using the following rule the binary blob above is wrapped as an +assembly file (testcase.dtb.S). + +$(obj)/%.dtb.S: $(obj)/%.dtb + $(call cmd, dt_S_dtb) + +The assembly file is compiled into an object file (testcase.dtb.o), and is +linked into the kernel image. + + +2.1. Adding the test data + +Un-flattened device tree structure: + +Un-flattened device tree consists of connected device_node(s) in form of a tree +structure described below. + +// following struct members are used to construct the tree +struct device_node { + ... + struct device_node *parent; + struct device_node *child; + struct device_node *sibling; + struct device_node *allnext; /* next in list of all nodes */ + ... + }; + +Figure 1, describes a generic structure of machine’s un-flattened device tree +considering only child and sibling pointers. There exists another pointer, +*parent, that is used to traverse the tree in the reverse direction. So, at +a particular level the child node and all the sibling nodes will have a parent +pointer pointing to a common node (e.g. child1, sibling2, sibling3, sibling4’s +parent points to root node) + +root (‘/’) + | +child1 -> sibling2 -> sibling3 -> sibling4 -> null + | | | | + | | | null + | | | + | | child31 -> sibling32 -> null + | | | | + | | null null + | | + | child21 -> sibling22 -> sibling23 -> null + | | | | + | null null null + | +child11 -> sibling12 -> sibling13 -> sibling14 -> null + | | | | + | | | null + | | | + null null child131 -> null + | + null + +Figure 1: Generic structure of un-flattened device tree + + +*allnext: it is used to link all the nodes of DT into a list. So, for the + above tree the list would be as follows: + +root->child1->child11->sibling12->sibling13->child131->sibling14->sibling2-> +child21->sibling22->sibling23->sibling3->child31->sibling32->sibling4->null + +Before executing OF selftest, it is required to attach the test data to +machine's device tree (if present). So, when selftest_data_add() is called, +at first it reads the flattened device tree data linked into the kernel image +via the following kernel symbols: + +__dtb_testcases_begin - address marking the start of test data blob +__dtb_testcases_end - address marking the end of test data blob + +Secondly, it calls of_fdt_unflatten_device_tree() to unflatten the flattened +blob. And finally, if the machine’s device tree (i.e live tree) is present, +then it attaches the unflattened test data tree to the live tree, else it +attaches itself as a live device tree. + +attach_node_and_children() uses of_attach_node() to attach the nodes into the +live tree as explained below. To explain the same, the test data tree described + in Figure 2 is attached to the live tree described in Figure 1. + +root (‘/’) + | + testcase-data + | + test-child0 -> test-sibling1 -> test-sibling2 -> test-sibling3 -> null + | | | | + test-child01 null null null + + +allnext list: + +root->testcase-data->test-child0->test-child01->test-sibling1->test-sibling2 +->test-sibling3->null + +Figure 2: Example test data tree to be attached to live tree. + +According to the scenario above, the live tree is already present so it isn’t +required to attach the root(‘/’) node. All other nodes are attached by calling +of_attach_node() on each node. + +In the function of_attach_node(), the new node is attached as the child of the +given parent in live tree. But, if parent already has a child then the new node +replaces the current child and turns it into its sibling. So, when the testcase +data node is attached to the live tree above (Figure 1), the final structure is + as shown in Figure 3. + +root (‘/’) + | +testcase-data -> child1 -> sibling2 -> sibling3 -> sibling4 -> null + | | | | | + (...) | | | null + | | child31 -> sibling32 -> null + | | | | + | | null null + | | + | child21 -> sibling22 -> sibling23 -> null + | | | | + | null null null + | + child11 -> sibling12 -> sibling13 -> sibling14 -> null + | | | | + null null | null + | + child131 -> null + | + null +----------------------------------------------------------------------- + +root (‘/’) + | +testcase-data -> child1 -> sibling2 -> sibling3 -> sibling4 -> null + | | | | | + | (...) (...) (...) null + | +test-sibling3 -> test-sibling2 -> test-sibling1 -> test-child0 -> null + | | | | + null null null test-child01 + + +Figure 3: Live device tree structure after attaching the testcase-data. + + +Astute readers would have noticed that test-child0 node becomes the last +sibling compared to the earlier structure (Figure 2). After attaching first +test-child0 the test-sibling1 is attached that pushes the child node +(i.e. test-child0) to become a sibling and makes itself a child node, + as mentioned above. + +If a duplicate node is found (i.e. if a node with same full_name property is +already present in the live tree), then the node isn’t attached rather its +properties are updated to the live tree’s node by calling the function +update_node_properties(). + + +2.2. Removing the test data + +Once the test case execution is complete, selftest_data_remove is called in +order to remove the device nodes attached initially (first the leaf nodes are +detached and then moving up the parent nodes are removed, and eventually the +whole tree). selftest_data_remove() calls detach_node_and_children() that uses +of_detach_node() to detach the nodes from the live device tree. + +To detach a node, of_detach_node() first updates all_next linked list, by +attaching the previous node’s allnext to current node’s allnext pointer. And +then, it either updates the child pointer of given node’s parent to its +sibling or attaches the previous sibling to the given node’s sibling, as +appropriate. That is it :) diff --git a/Documentation/dma-buf-sharing.txt b/Documentation/dma-buf-sharing.txt index 67a4087d53f9..bb9753b635a3 100644 --- a/Documentation/dma-buf-sharing.txt +++ b/Documentation/dma-buf-sharing.txt @@ -56,10 +56,10 @@ The dma_buf buffer sharing API usage contains the following steps: size_t size, int flags, const char *exp_name) - If this succeeds, dma_buf_export allocates a dma_buf structure, and returns a - pointer to the same. It also associates an anonymous file with this buffer, - so it can be exported. On failure to allocate the dma_buf object, it returns - NULL. + If this succeeds, dma_buf_export_named allocates a dma_buf structure, and + returns a pointer to the same. It also associates an anonymous file with this + buffer, so it can be exported. On failure to allocate the dma_buf object, + it returns NULL. 'exp_name' is the name of exporter - to facilitate information while debugging. @@ -76,7 +76,7 @@ The dma_buf buffer sharing API usage contains the following steps: drivers and/or processes. Interface: - int dma_buf_fd(struct dma_buf *dmabuf) + int dma_buf_fd(struct dma_buf *dmabuf, int flags) This API installs an fd for the anonymous file associated with this buffer; returns either 'fd', or error. @@ -157,7 +157,9 @@ to request use of buffer for allocation. "dma_buf->ops->" indirection from the users of this interface. In struct dma_buf_ops, unmap_dma_buf is defined as - void (*unmap_dma_buf)(struct dma_buf_attachment *, struct sg_table *); + void (*unmap_dma_buf)(struct dma_buf_attachment *, + struct sg_table *, + enum dma_data_direction); unmap_dma_buf signifies the end-of-DMA for the attachment provided. Like map_dma_buf, this API also must be implemented by the exporter. diff --git a/Documentation/filesystems/nfs/nfs-rdma.txt b/Documentation/filesystems/nfs/nfs-rdma.txt index e386f7e4bcee..724043858b08 100644 --- a/Documentation/filesystems/nfs/nfs-rdma.txt +++ b/Documentation/filesystems/nfs/nfs-rdma.txt @@ -138,9 +138,9 @@ Installation - Build, install, reboot The NFS/RDMA code will be enabled automatically if NFS and RDMA - are turned on. The NFS/RDMA client and server are configured via the hidden - SUNRPC_XPRT_RDMA config option that depends on SUNRPC and INFINIBAND. The - value of SUNRPC_XPRT_RDMA will be: + are turned on. The NFS/RDMA client and server are configured via the + SUNRPC_XPRT_RDMA_CLIENT and SUNRPC_XPRT_RDMA_SERVER config options that both + depend on SUNRPC and INFINIBAND. The default value of both options will be: - N if either SUNRPC or INFINIBAND are N, in this case the NFS/RDMA client and server will not be built @@ -235,8 +235,9 @@ NFS/RDMA Setup - Start the NFS server - If the NFS/RDMA server was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in - kernel config), load the RDMA transport module: + If the NFS/RDMA server was built as a module + (CONFIG_SUNRPC_XPRT_RDMA_SERVER=m in kernel config), load the RDMA + transport module: $ modprobe svcrdma @@ -255,8 +256,9 @@ NFS/RDMA Setup - On the client system - If the NFS/RDMA client was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in - kernel config), load the RDMA client module: + If the NFS/RDMA client was built as a module + (CONFIG_SUNRPC_XPRT_RDMA_CLIENT=m in kernel config), load the RDMA client + module: $ modprobe xprtrdma.ko diff --git a/Documentation/filesystems/seq_file.txt b/Documentation/filesystems/seq_file.txt index 1fe0ccb1af55..8ea3e90ace07 100644 --- a/Documentation/filesystems/seq_file.txt +++ b/Documentation/filesystems/seq_file.txt @@ -235,6 +235,39 @@ be used for more than one file, you can store an arbitrary pointer in the private field of the seq_file structure; that value can then be retrieved by the iterator functions. +There is also a wrapper function to seq_open() called seq_open_private(). It +kmallocs a zero filled block of memory and stores a pointer to it in the +private field of the seq_file structure, returning 0 on success. The +block size is specified in a third parameter to the function, e.g.: + + static int ct_open(struct inode *inode, struct file *file) + { + return seq_open_private(file, &ct_seq_ops, + sizeof(struct mystruct)); + } + +There is also a variant function, __seq_open_private(), which is functionally +identical except that, if successful, it returns the pointer to the allocated +memory block, allowing further initialisation e.g.: + + static int ct_open(struct inode *inode, struct file *file) + { + struct mystruct *p = + __seq_open_private(file, &ct_seq_ops, sizeof(*p)); + + if (!p) + return -ENOMEM; + + p->foo = bar; /* initialize my stuff */ + ... + p->baz = true; + + return 0; + } + +A corresponding close function, seq_release_private() is available which +frees the memory allocated in the corresponding open. + The other operations of interest - read(), llseek(), and release() - are all implemented by the seq_file code itself. So a virtual file's file_operations structure will look like: diff --git a/Documentation/gpio/consumer.txt b/Documentation/gpio/consumer.txt index 76546324e968..6ce544191ca6 100644 --- a/Documentation/gpio/consumer.txt +++ b/Documentation/gpio/consumer.txt @@ -53,7 +53,20 @@ with IS_ERR() (they will never return a NULL pointer). -ENOENT will be returned if and only if no GPIO has been assigned to the device/function/index triplet, other error codes are used for cases where a GPIO has been assigned but an error occurred while trying to acquire it. This is useful to discriminate between mere -errors and an absence of GPIO for optional GPIO parameters. +errors and an absence of GPIO for optional GPIO parameters. For the common +pattern where a GPIO is optional, the gpiod_get_optional() and +gpiod_get_index_optional() functions can be used. These functions return NULL +instead of -ENOENT if no GPIO has been assigned to the requested function: + + + struct gpio_desc *gpiod_get_optional(struct device *dev, + const char *con_id, + enum gpiod_flags flags) + + struct gpio_desc *gpiod_get_index_optional(struct device *dev, + const char *con_id, + unsigned int index, + enum gpiod_flags flags) Device-managed variants of these functions are also defined: @@ -65,6 +78,15 @@ Device-managed variants of these functions are also defined: unsigned int idx, enum gpiod_flags flags) + struct gpio_desc *devm_gpiod_get_optional(struct device *dev, + const char *con_id, + enum gpiod_flags flags) + + struct gpio_desc * devm_gpiod_get_index_optional(struct device *dev, + const char *con_id, + unsigned int index, + enum gpiod_flags flags) + A GPIO descriptor can be disposed of using the gpiod_put() function: void gpiod_put(struct gpio_desc *desc) diff --git a/Documentation/i2c/dev-interface b/Documentation/i2c/dev-interface index 3e742ba25536..2ac78ae1039d 100644 --- a/Documentation/i2c/dev-interface +++ b/Documentation/i2c/dev-interface @@ -57,12 +57,12 @@ Well, you are all set up now. You can now use SMBus commands or plain I2C to communicate with your device. SMBus commands are preferred if the device supports them. Both are illustrated below. - __u8 register = 0x10; /* Device register to access */ + __u8 reg = 0x10; /* Device register to access */ __s32 res; char buf[10]; /* Using SMBus commands */ - res = i2c_smbus_read_word_data(file, register); + res = i2c_smbus_read_word_data(file, reg); if (res < 0) { /* ERROR HANDLING: i2c transaction failed */ } else { @@ -70,11 +70,11 @@ the device supports them. Both are illustrated below. } /* Using I2C Write, equivalent of - i2c_smbus_write_word_data(file, register, 0x6543) */ - buf[0] = register; + i2c_smbus_write_word_data(file, reg, 0x6543) */ + buf[0] = reg; buf[1] = 0x43; buf[2] = 0x65; - if (write(file, buf, 3) ! =3) { + if (write(file, buf, 3) != 3) { /* ERROR HANDLING: i2c transaction failed */ } diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt index 88d5a863712a..6c0b9f27e465 100644 --- a/Documentation/kdump/kdump.txt +++ b/Documentation/kdump/kdump.txt @@ -18,7 +18,7 @@ memory image to a dump file on the local disk, or across the network to a remote system. Kdump and kexec are currently supported on the x86, x86_64, ppc64, ia64, -and s390x architectures. +s390x and arm architectures. When the system kernel boots, it reserves a small section of memory for the dump-capture kernel. This ensures that ongoing Direct Memory Access @@ -112,7 +112,7 @@ There are two possible methods of using Kdump. 2) Or use the system kernel binary itself as dump-capture kernel and there is no need to build a separate dump-capture kernel. This is possible only with the architectures which support a relocatable kernel. As - of today, i386, x86_64, ppc64 and ia64 architectures support relocatable + of today, i386, x86_64, ppc64, ia64 and arm architectures support relocatable kernel. Building a relocatable kernel is advantageous from the point of view that @@ -241,6 +241,13 @@ Dump-capture kernel config options (Arch Dependent, ia64) kernel will be aligned to 64Mb, so if the start address is not then any space below the alignment point will be wasted. +Dump-capture kernel config options (Arch Dependent, arm) +---------------------------------------------------------- + +- To use a relocatable kernel, + Enable "AUTO_ZRELADDR" support under "Boot" options: + + AUTO_ZRELADDR=y Extended crashkernel syntax =========================== @@ -256,6 +263,10 @@ The syntax is: crashkernel=<range1>:<size1>[,<range2>:<size2>,...][@offset] range=start-[end] +Please note, on arm, the offset is required. + crashkernel=<range1>:<size1>[,<range2>:<size2>,...]@offset + range=start-[end] + 'start' is inclusive and 'end' is exclusive. For example: @@ -296,6 +307,12 @@ Boot into System Kernel on the memory consumption of the kdump system. In general this is not dependent on the memory size of the production system. + On arm, use "crashkernel=Y@X". Note that the start address of the kernel + will be aligned to 128MiB (0x08000000), so if the start address is not then + any space below the alignment point may be overwritten by the dump-capture kernel, + which means it is possible that the vmcore is not that precise as expected. + + Load the Dump-capture Kernel ============================ @@ -315,7 +332,8 @@ For ia64: - Use vmlinux or vmlinuz.gz For s390x: - Use image or bzImage - +For arm: + - Use zImage If you are using a uncompressed vmlinux image then use following command to load dump-capture kernel. @@ -331,6 +349,15 @@ to load dump-capture kernel. --initrd=<initrd-for-dump-capture-kernel> \ --append="root=<root-dev> <arch-specific-options>" +If you are using a compressed zImage, then use following command +to load dump-capture kernel. + + kexec --type zImage -p <dump-capture-kernel-bzImage> \ + --initrd=<initrd-for-dump-capture-kernel> \ + --dtb=<dtb-for-dump-capture-kernel> \ + --append="root=<root-dev> <arch-specific-options>" + + Please note, that --args-linux does not need to be specified for ia64. It is planned to make this a no-op on that architecture, but for now it should be omitted @@ -347,6 +374,9 @@ For ppc64: For s390x: "1 maxcpus=1 cgroup_disable=memory" +For arm: + "1 maxcpus=1 reset_devices" + Notes on loading the dump-capture kernel: * By default, the ELF headers are stored in ELF64 format to support diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 5ae8608ca9f5..10d51c2f10d7 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3541,6 +3541,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. bogus residue values); s = SINGLE_LUN (the device has only one Logical Unit); + u = IGNORE_UAS (don't bind to the uas driver); w = NO_WP_DETECT (don't test whether the medium is write-protected). Example: quirks=0419:aaf5:rl,0421:0433:rc diff --git a/Documentation/misc-devices/lis3lv02d b/Documentation/misc-devices/lis3lv02d index af815b9ba413..f89960a0ff95 100644 --- a/Documentation/misc-devices/lis3lv02d +++ b/Documentation/misc-devices/lis3lv02d @@ -59,7 +59,7 @@ acts similar to /dev/rtc and reacts on free-fall interrupts received from the device. It supports blocking operations, poll/select and fasync operation modes. You must read 1 bytes from the device. The result is number of free-fall interrupts since the last successful -read (or 255 if number of interrupts would not fit). See the hpfall.c +read (or 255 if number of interrupts would not fit). See the freefall.c file for an example on using the device. diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt index c48a9704bda8..d16f424c5e8d 100644 --- a/Documentation/networking/filter.txt +++ b/Documentation/networking/filter.txt @@ -462,9 +462,9 @@ JIT compiler ------------ The Linux kernel has a built-in BPF JIT compiler for x86_64, SPARC, PowerPC, -ARM and s390 and can be enabled through CONFIG_BPF_JIT. The JIT compiler is -transparently invoked for each attached filter from user space or for internal -kernel users if it has been previously enabled by root: +ARM, MIPS and s390 and can be enabled through CONFIG_BPF_JIT. The JIT compiler +is transparently invoked for each attached filter from user space or for +internal kernel users if it has been previously enabled by root: echo 1 > /proc/sys/net/core/bpf_jit_enable diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 29a93518bf18..caedb18d4564 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -580,12 +580,6 @@ tcp_workaround_signed_windows - BOOLEAN not receive a window scaling option from them. Default: 0 -tcp_dma_copybreak - INTEGER - Lower limit, in bytes, of the size of socket reads that will be - offloaded to a DMA copy engine, if one is present in the system - and CONFIG_NET_DMA is enabled. - Default: 4096 - tcp_thin_linear_timeouts - BOOLEAN Enable dynamic triggering of linear timeouts for thin streams. If set, a check is performed upon retransmission by timeout to diff --git a/Documentation/power/regulator/consumer.txt b/Documentation/power/regulator/consumer.txt index 81c0e2b49cd8..8afb236ca765 100644 --- a/Documentation/power/regulator/consumer.txt +++ b/Documentation/power/regulator/consumer.txt @@ -143,8 +143,9 @@ This will cause the core to recalculate the total load on the regulator (based on all its consumers) and change operating mode (if necessary and permitted) to best match the current operating load. -The load_uA value can be determined from the consumers datasheet. e.g.most -datasheets have tables showing the max current consumed in certain situations. +The load_uA value can be determined from the consumer's datasheet. e.g. most +datasheets have tables showing the maximum current consumed in certain +situations. Most consumers will use indirect operating mode control since they have no knowledge of the regulator or whether the regulator is shared with other @@ -173,7 +174,7 @@ Consumers can register interest in regulator events by calling :- int regulator_register_notifier(struct regulator *regulator, struct notifier_block *nb); -Consumers can uregister interest by calling :- +Consumers can unregister interest by calling :- int regulator_unregister_notifier(struct regulator *regulator, struct notifier_block *nb); diff --git a/Documentation/power/regulator/design.txt b/Documentation/power/regulator/design.txt index f9b56b72b782..fdd919b96830 100644 --- a/Documentation/power/regulator/design.txt +++ b/Documentation/power/regulator/design.txt @@ -9,14 +9,14 @@ Safety - Errors in regulator configuration can have very serious consequences for the system, potentially including lasting hardware damage. - - It is not possible to automatically determine the power confugration + - It is not possible to automatically determine the power configuration of the system - software-equivalent variants of the same chip may - have different power requirments, and not all components with power + have different power requirements, and not all components with power requirements are visible to software. => The API should make no changes to the hardware state unless it has - specific knowledge that these changes are safe to do perform on - this particular system. + specific knowledge that these changes are safe to perform on this + particular system. Consumer use cases ------------------ diff --git a/Documentation/power/regulator/machine.txt b/Documentation/power/regulator/machine.txt index ce63af0a8e35..757e3b53dc11 100644 --- a/Documentation/power/regulator/machine.txt +++ b/Documentation/power/regulator/machine.txt @@ -11,7 +11,7 @@ Consider the following machine :- +-> [Consumer B @ 3.3V] The drivers for consumers A & B must be mapped to the correct regulator in -order to control their power supply. This mapping can be achieved in machine +order to control their power supplies. This mapping can be achieved in machine initialisation code by creating a struct regulator_consumer_supply for each regulator. @@ -39,7 +39,7 @@ to the 'Vcc' supply for Consumer A. Constraints can now be registered by defining a struct regulator_init_data for each regulator power domain. This structure also maps the consumers -to their supply regulator :- +to their supply regulators :- static struct regulator_init_data regulator1_data = { .constraints = { diff --git a/Documentation/power/regulator/overview.txt b/Documentation/power/regulator/overview.txt index 8ed17587a74b..40ca2d6e2742 100644 --- a/Documentation/power/regulator/overview.txt +++ b/Documentation/power/regulator/overview.txt @@ -36,11 +36,11 @@ Some terms used in this document:- Consumers can be classified into two types:- Static: consumer does not change its supply voltage or - current limit. It only needs to enable or disable it's + current limit. It only needs to enable or disable its power supply. Its supply voltage is set by the hardware, bootloader, firmware or kernel board initialisation code. - Dynamic: consumer needs to change it's supply voltage or + Dynamic: consumer needs to change its supply voltage or current limit to meet operation demands. @@ -156,7 +156,7 @@ relevant to non SoC devices and is split into the following four interfaces:- This interface is for machine specific code and allows the creation of voltage/current domains (with constraints) for each regulator. It can provide regulator constraints that will prevent device damage through - overvoltage or over current caused by buggy client drivers. It also + overvoltage or overcurrent caused by buggy client drivers. It also allows the creation of a regulator tree whereby some regulators are supplied by others (similar to a clock tree). diff --git a/Documentation/power/regulator/regulator.txt b/Documentation/power/regulator/regulator.txt index 13902778ae44..b17e5833ce21 100644 --- a/Documentation/power/regulator/regulator.txt +++ b/Documentation/power/regulator/regulator.txt @@ -13,7 +13,7 @@ Drivers can register a regulator by calling :- struct regulator_dev *regulator_register(struct regulator_desc *regulator_desc, const struct regulator_config *config); -This will register the regulators capabilities and operations to the regulator +This will register the regulator's capabilities and operations to the regulator core. Regulators can be unregistered by calling :- @@ -23,8 +23,8 @@ void regulator_unregister(struct regulator_dev *rdev); Regulator Events ================ -Regulators can send events (e.g. over temp, under voltage, etc) to consumer -drivers by calling :- +Regulators can send events (e.g. overtemperature, undervoltage, etc) to +consumer drivers by calling :- int regulator_notifier_call_chain(struct regulator_dev *rdev, unsigned long event, void *data); diff --git a/Documentation/this_cpu_ops.txt b/Documentation/this_cpu_ops.txt index 1a4ce7e3e05f..0ec995712176 100644 --- a/Documentation/this_cpu_ops.txt +++ b/Documentation/this_cpu_ops.txt @@ -2,26 +2,26 @@ this_cpu operations ------------------- this_cpu operations are a way of optimizing access to per cpu -variables associated with the *currently* executing processor through -the use of segment registers (or a dedicated register where the cpu -permanently stored the beginning of the per cpu area for a specific -processor). +variables associated with the *currently* executing processor. This is +done through the use of segment registers (or a dedicated register where +the cpu permanently stored the beginning of the per cpu area for a +specific processor). -The this_cpu operations add a per cpu variable offset to the processor -specific percpu base and encode that operation in the instruction +this_cpu operations add a per cpu variable offset to the processor +specific per cpu base and encode that operation in the instruction operating on the per cpu variable. -This means there are no atomicity issues between the calculation of +This means that there are no atomicity issues between the calculation of the offset and the operation on the data. Therefore it is not -necessary to disable preempt or interrupts to ensure that the +necessary to disable preemption or interrupts to ensure that the processor is not changed between the calculation of the address and the operation on the data. Read-modify-write operations are of particular interest. Frequently processors have special lower latency instructions that can operate -without the typical synchronization overhead but still provide some -sort of relaxed atomicity guarantee. The x86 for example can execute -RMV (Read Modify Write) instructions like inc/dec/cmpxchg without the +without the typical synchronization overhead, but still provide some +sort of relaxed atomicity guarantees. The x86, for example, can execute +RMW (Read Modify Write) instructions like inc/dec/cmpxchg without the lock prefix and the associated latency penalty. Access to the variable without the lock prefix is not synchronized but @@ -30,6 +30,38 @@ data specific to the currently executing processor. Only the current processor should be accessing that variable and therefore there are no concurrency issues with other processors in the system. +Please note that accesses by remote processors to a per cpu area are +exceptional situations and may impact performance and/or correctness +(remote write operations) of local RMW operations via this_cpu_*. + +The main use of the this_cpu operations has been to optimize counter +operations. + +The following this_cpu() operations with implied preemption protection +are defined. These operations can be used without worrying about +preemption and interrupts. + + this_cpu_add() + this_cpu_read(pcp) + this_cpu_write(pcp, val) + this_cpu_add(pcp, val) + this_cpu_and(pcp, val) + this_cpu_or(pcp, val) + this_cpu_add_return(pcp, val) + this_cpu_xchg(pcp, nval) + this_cpu_cmpxchg(pcp, oval, nval) + this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) + this_cpu_sub(pcp, val) + this_cpu_inc(pcp) + this_cpu_dec(pcp) + this_cpu_sub_return(pcp, val) + this_cpu_inc_return(pcp) + this_cpu_dec_return(pcp) + + +Inner working of this_cpu operations +------------------------------------ + On x86 the fs: or the gs: segment registers contain the base of the per cpu area. It is then possible to simply use the segment override to relocate a per cpu relative address to the proper per cpu area for @@ -48,22 +80,21 @@ results in a single instruction mov ax, gs:[x] instead of a sequence of calculation of the address and then a fetch -from that address which occurs with the percpu operations. Before +from that address which occurs with the per cpu operations. Before this_cpu_ops such sequence also required preempt disable/enable to prevent the kernel from moving the thread to a different processor while the calculation is performed. -The main use of the this_cpu operations has been to optimize counter -operations. +Consider the following this_cpu operation: this_cpu_inc(x) -results in the following single instruction (no lock prefix!) +The above results in the following single instruction (no lock prefix!) inc gs:[x] instead of the following operations required if there is no segment -register. +register: int *y; int cpu; @@ -73,10 +104,10 @@ register. (*y)++; put_cpu(); -Note that these operations can only be used on percpu data that is +Note that these operations can only be used on per cpu data that is reserved for a specific processor. Without disabling preemption in the surrounding code this_cpu_inc() will only guarantee that one of the -percpu counters is correctly incremented. However, there is no +per cpu counters is correctly incremented. However, there is no guarantee that the OS will not move the process directly before or after the this_cpu instruction is executed. In general this means that the value of the individual counters for each processor are @@ -86,9 +117,9 @@ that is of interest. Per cpu variables are used for performance reasons. Bouncing cache lines can be avoided if multiple processors concurrently go through the same code paths. Since each processor has its own per cpu -variables no concurrent cacheline updates take place. The price that +variables no concurrent cache line updates take place. The price that has to be paid for this optimization is the need to add up the per cpu -counters when the value of the counter is needed. +counters when the value of a counter is needed. Special operations: @@ -100,33 +131,39 @@ Takes the offset of a per cpu variable (&x !) and returns the address of the per cpu variable that belongs to the currently executing processor. this_cpu_ptr avoids multiple steps that the common get_cpu/put_cpu sequence requires. No processor number is -available. Instead the offset of the local per cpu area is simply -added to the percpu offset. +available. Instead, the offset of the local per cpu area is simply +added to the per cpu offset. +Note that this operation is usually used in a code segment when +preemption has been disabled. The pointer is then used to +access local per cpu data in a critical section. When preemption +is re-enabled this pointer is usually no longer useful since it may +no longer point to per cpu data of the current processor. Per cpu variables and offsets ----------------------------- -Per cpu variables have *offsets* to the beginning of the percpu +Per cpu variables have *offsets* to the beginning of the per cpu area. They do not have addresses although they look like that in the code. Offsets cannot be directly dereferenced. The offset must be -added to a base pointer of a percpu area of a processor in order to +added to a base pointer of a per cpu area of a processor in order to form a valid address. Therefore the use of x or &x outside of the context of per cpu operations is invalid and will generally be treated like a NULL pointer dereference. -In the context of per cpu operations + DEFINE_PER_CPU(int, x); - x is a per cpu variable. Most this_cpu operations take a cpu - variable. +In the context of per cpu operations the above implies that x is a per +cpu variable. Most this_cpu operations take a cpu variable. - &x is the *offset* a per cpu variable. this_cpu_ptr() takes - the offset of a per cpu variable which makes this look a bit - strange. + int __percpu *p = &x; +&x and hence p is the *offset* of a per cpu variable. this_cpu_ptr() +takes the offset of a per cpu variable which makes this look a bit +strange. Operations on a field of a per cpu structure @@ -152,7 +189,7 @@ If we have an offset to struct s: struct s __percpu *ps = &p; - z = this_cpu_dec(ps->m); + this_cpu_dec(ps->m); z = this_cpu_inc_return(ps->n); @@ -172,29 +209,52 @@ if we do not make use of this_cpu ops later to manipulate fields: Variants of this_cpu ops ------------------------- -this_cpu ops are interrupt safe. Some architecture do not support +this_cpu ops are interrupt safe. Some architectures do not support these per cpu local operations. In that case the operation must be replaced by code that disables interrupts, then does the operations -that are guaranteed to be atomic and then reenable interrupts. Doing +that are guaranteed to be atomic and then re-enable interrupts. Doing so is expensive. If there are other reasons why the scheduler cannot change the processor we are executing on then there is no reason to -disable interrupts. For that purpose the __this_cpu operations are -provided. For example. - - __this_cpu_inc(x); - -Will increment x and will not fallback to code that disables +disable interrupts. For that purpose the following __this_cpu operations +are provided. + +These operations have no guarantee against concurrent interrupts or +preemption. If a per cpu variable is not used in an interrupt context +and the scheduler cannot preempt, then they are safe. If any interrupts +still occur while an operation is in progress and if the interrupt too +modifies the variable, then RMW actions can not be guaranteed to be +safe. + + __this_cpu_add() + __this_cpu_read(pcp) + __this_cpu_write(pcp, val) + __this_cpu_add(pcp, val) + __this_cpu_and(pcp, val) + __this_cpu_or(pcp, val) + __this_cpu_add_return(pcp, val) + __this_cpu_xchg(pcp, nval) + __this_cpu_cmpxchg(pcp, oval, nval) + __this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) + __this_cpu_sub(pcp, val) + __this_cpu_inc(pcp) + __this_cpu_dec(pcp) + __this_cpu_sub_return(pcp, val) + __this_cpu_inc_return(pcp) + __this_cpu_dec_return(pcp) + + +Will increment x and will not fall-back to code that disables interrupts on platforms that cannot accomplish atomicity through address relocation and a Read-Modify-Write operation in the same instruction. - &this_cpu_ptr(pp)->n vs this_cpu_ptr(&pp->n) -------------------------------------------- The first operation takes the offset and forms an address and then -adds the offset of the n field. +adds the offset of the n field. This may result in two add +instructions emitted by the compiler. The second one first adds the two offsets and then does the relocation. IMHO the second form looks cleaner and has an easier time @@ -202,4 +262,73 @@ with (). The second form also is consistent with the way this_cpu_read() and friends are used. -Christoph Lameter, April 3rd, 2013 +Remote access to per cpu data +------------------------------ + +Per cpu data structures are designed to be used by one cpu exclusively. +If you use the variables as intended, this_cpu_ops() are guaranteed to +be "atomic" as no other CPU has access to these data structures. + +There are special cases where you might need to access per cpu data +structures remotely. It is usually safe to do a remote read access +and that is frequently done to summarize counters. Remote write access +something which could be problematic because this_cpu ops do not +have lock semantics. A remote write may interfere with a this_cpu +RMW operation. + +Remote write accesses to percpu data structures are highly discouraged +unless absolutely necessary. Please consider using an IPI to wake up +the remote CPU and perform the update to its per cpu area. + +To access per-cpu data structure remotely, typically the per_cpu_ptr() +function is used: + + + DEFINE_PER_CPU(struct data, datap); + + struct data *p = per_cpu_ptr(&datap, cpu); + +This makes it explicit that we are getting ready to access a percpu +area remotely. + +You can also do the following to convert the datap offset to an address + + struct data *p = this_cpu_ptr(&datap); + +but, passing of pointers calculated via this_cpu_ptr to other cpus is +unusual and should be avoided. + +Remote access are typically only for reading the status of another cpus +per cpu data. Write accesses can cause unique problems due to the +relaxed synchronization requirements for this_cpu operations. + +One example that illustrates some concerns with write operations is +the following scenario that occurs because two per cpu variables +share a cache-line but the relaxed synchronization is applied to +only one process updating the cache-line. + +Consider the following example + + + struct test { + atomic_t a; + int b; + }; + + DEFINE_PER_CPU(struct test, onecacheline); + +There is some concern about what would happen if the field 'a' is updated +remotely from one processor and the local processor would use this_cpu ops +to update field b. Care should be taken that such simultaneous accesses to +data within the same cache line are avoided. Also costly synchronization +may be necessary. IPIs are generally recommended in such scenarios instead +of a remote write to the per cpu area of another processor. + +Even in cases where the remote writes are rare, please bear in +mind that a remote write will evict the cache line from the processor +that most likely will access it. If the processor wakes up and finds a +missing local cache line of a per cpu area, its performance and hence +the wake up times will be affected. + +Christoph Lameter, August 4th, 2014 +Pranith Kumar, Aug 2nd, 2014 |