diff options
| author | Tejun Heo <tj@kernel.org> | 2015-11-03 17:29:03 -0500 |
|---|---|---|
| committer | Tejun Heo <tj@kernel.org> | 2015-11-03 17:29:03 -0500 |
| commit | 159b5bb46492e4dcef2070b12861030bc360402b (patch) | |
| tree | 93de7d6e94a059aade50ee5437de6a50ccd1cf7b /Documentation | |
| parent | 56e74338a535cbcc2f2da08b1ea1a92920194364 (diff) | |
| parent | 469eabb3aec03d9defed3462df743a223a5c8f54 (diff) | |
| download | linux-159b5bb46492e4dcef2070b12861030bc360402b.tar.bz2 | |
Merge branch 'for-4.3-fixes' into for-4.4
Diffstat (limited to 'Documentation')
58 files changed, 965 insertions, 100 deletions
diff --git a/Documentation/ABI/testing/sysfs-hypervisor-pmu b/Documentation/ABI/testing/sysfs-hypervisor-pmu new file mode 100644 index 000000000000..224faa105e18 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-hypervisor-pmu @@ -0,0 +1,23 @@ +What: /sys/hypervisor/pmu/pmu_mode +Date: August 2015 +KernelVersion: 4.3 +Contact: Boris Ostrovsky <boris.ostrovsky@oracle.com> +Description: + Describes mode that Xen's performance-monitoring unit (PMU) + uses. Accepted values are + "off" -- PMU is disabled + "self" -- The guest can profile itself + "hv" -- The guest can profile itself and, if it is + privileged (e.g. dom0), the hypervisor + "all" -- The guest can profile itself, the hypervisor + and all other guests. Only available to + privileged guests. + +What: /sys/hypervisor/pmu/pmu_features +Date: August 2015 +KernelVersion: 4.3 +Contact: Boris Ostrovsky <boris.ostrovsky@oracle.com> +Description: + Describes Xen PMU features (as an integer). A set bit indicates + that the corresponding feature is enabled. See + include/xen/interface/xenpmu.h for available features diff --git a/Documentation/Changes b/Documentation/Changes index 646cdaa6e9d1..6d8863004858 100644 --- a/Documentation/Changes +++ b/Documentation/Changes @@ -43,6 +43,7 @@ o udev 081 # udevd --version o grub 0.93 # grub --version || grub-install --version o mcelog 0.6 # mcelog --version o iptables 1.4.2 # iptables -V +o openssl & libcrypto 1.0.1k # openssl version Kernel compilation @@ -79,6 +80,17 @@ BC You will need bc to build kernels 3.10 and higher +OpenSSL +------- + +Module signing and external certificate handling use the OpenSSL program and +crypto library to do key creation and signature generation. + +You will need openssl to build kernels 3.7 and higher if module signing is +enabled. You will also need openssl development packages to build kernels 4.3 +and higher. + + System utilities ================ @@ -295,6 +307,10 @@ Binutils -------- o <ftp://ftp.kernel.org/pub/linux/devel/binutils/> +OpenSSL +------- +o <https://www.openssl.org/> + System utilities **************** @@ -392,4 +408,3 @@ o <http://oprofile.sf.net/download/> NFS-Utils --------- o <http://nfs.sourceforge.net/> - diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt index 7eba542eff7c..edccacd4f048 100644 --- a/Documentation/DMA-API.txt +++ b/Documentation/DMA-API.txt @@ -104,6 +104,13 @@ crossing restrictions, pass 0 for alloc; passing 4096 says memory allocated from this pool must not cross 4KByte boundaries. + void *dma_pool_zalloc(struct dma_pool *pool, gfp_t mem_flags, + dma_addr_t *handle) + +Wraps dma_pool_alloc() and also zeroes the returned memory if the +allocation attempt succeeded. + + void *dma_pool_alloc(struct dma_pool *pool, gfp_t gfp_flags, dma_addr_t *dma_handle); diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl index abba93f9d64a..1d6008d51b55 100644 --- a/Documentation/DocBook/device-drivers.tmpl +++ b/Documentation/DocBook/device-drivers.tmpl @@ -490,4 +490,31 @@ X!Ilib/fonts/fonts.c !Edrivers/hsi/hsi.c </chapter> + <chapter id="pwm"> + <title>Pulse-Width Modulation (PWM)</title> + <para> + Pulse-width modulation is a modulation technique primarily used to + control power supplied to electrical devices. + </para> + <para> + The PWM framework provides an abstraction for providers and consumers + of PWM signals. A controller that provides one or more PWM signals is + registered as <structname>struct pwm_chip</structname>. Providers are + expected to embed this structure in a driver-specific structure. This + structure contains fields that describe a particular chip. + </para> + <para> + A chip exposes one or more PWM signal sources, each of which exposed + as a <structname>struct pwm_device</structname>. Operations can be + performed on PWM devices to control the period, duty cycle, polarity + and active state of the signal. + </para> + <para> + Note that PWM devices are exclusive resources: they can always only be + used by one consumer at a time. + </para> +!Iinclude/linux/pwm.h +!Edrivers/pwm/core.c + </chapter> + </book> diff --git a/Documentation/blockdev/zram.txt b/Documentation/blockdev/zram.txt index c4de576093af..62435bb25266 100644 --- a/Documentation/blockdev/zram.txt +++ b/Documentation/blockdev/zram.txt @@ -144,7 +144,8 @@ mem_used_max RW the maximum amount memory zram have consumed to store compressed data mem_limit RW the maximum amount of memory ZRAM can use to store the compressed data -num_migrated RO the number of objects migrated migrated by compaction +pages_compacted RO the number of pages freed during compaction + (available only via zram<id>/mm_stat node) compact WO trigger memory compaction WARNING diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt index 68b6a6a470b0..12686bec37b9 100644 --- a/Documentation/cgroups/blkio-controller.txt +++ b/Documentation/cgroups/blkio-controller.txt @@ -201,7 +201,7 @@ Proportional weight policy files specifies the number of bytes. - blkio.io_serviced - - Number of IOs completed to/from the disk by the group. These + - Number of IOs (bio) issued to the disk by the group. These are further divided by the type of operation - read or write, sync or async. First two fields specify the major and minor number of the device, third field specifies the operation type and the fourth field @@ -327,18 +327,11 @@ Note: If both BW and IOPS rules are specified for a device, then IO is subjected to both the constraints. - blkio.throttle.io_serviced - - Number of IOs (bio) completed to/from the disk by the group (as - seen by throttling policy). These are further divided by the type - of operation - read or write, sync or async. First two fields specify - the major and minor number of the device, third field specifies the - operation type and the fourth field specifies the number of IOs. - - blkio.io_serviced does accounting as seen by CFQ and counts are in - number of requests (struct request). On the other hand, - blkio.throttle.io_serviced counts number of IO in terms of number - of bios as seen by throttling policy. These bios can later be - merged by elevator and total number of requests completed can be - lesser. + - Number of IOs (bio) issued to the disk by the group. These + are further divided by the type of operation - read or write, sync + or async. First two fields specify the major and minor number of the + device, third field specifies the operation type and the fourth field + specifies the number of IOs. - blkio.throttle.io_service_bytes - Number of bytes transferred to/from the disk by the group. These @@ -347,11 +340,6 @@ Note: If both BW and IOPS rules are specified for a device, then IO is device, third field specifies the operation type and the fourth field specifies the number of bytes. - These numbers should roughly be same as blkio.io_service_bytes as - updated by CFQ. The difference between two is that - blkio.io_service_bytes will not be updated if CFQ is not operating - on request queue. - Common files among various policies ----------------------------------- - blkio.reset_stats diff --git a/Documentation/cgroups/unified-hierarchy.txt b/Documentation/cgroups/unified-hierarchy.txt index 1ee9caf29e57..e0975c2cf03d 100644 --- a/Documentation/cgroups/unified-hierarchy.txt +++ b/Documentation/cgroups/unified-hierarchy.txt @@ -27,7 +27,7 @@ CONTENTS 5-3-1. Format 5-3-2. Control Knobs 5-4. Per-Controller Changes - 5-4-1. blkio + 5-4-1. io 5-4-2. cpuset 5-4-3. memory 6. Planned Changes @@ -203,7 +203,7 @@ other issues. The mapping from nice level to weight isn't obvious or universal, and there are various other knobs which simply aren't available for tasks. -The blkio controller implicitly creates a hidden leaf node for each +The io controller implicitly creates a hidden leaf node for each cgroup to host the tasks. The hidden leaf has its own copies of all the knobs with "leaf_" prefixed. While this allows equivalent control over internal tasks, it's with serious drawbacks. It always adds an @@ -438,9 +438,62 @@ may be specified in any order and not all pairs have to be specified. 5-4. Per-Controller Changes -5-4-1. blkio +5-4-1. io -- blk-throttle becomes properly hierarchical. +- blkio is renamed to io. The interface is overhauled anyway. The + new name is more in line with the other two major controllers, cpu + and memory, and better suited given that it may be used for cgroup + writeback without involving block layer. + +- Everything including stat is always hierarchical making separate + recursive stat files pointless and, as no internal node can have + tasks, leaf weights are meaningless. The operation model is + simplified and the interface is overhauled accordingly. + + io.stat + + The stat file. The reported stats are from the point where + bio's are issued to request_queue. The stats are counted + independent of which policies are enabled. Each line in the + file follows the following format. More fields may later be + added at the end. + + $MAJ:$MIN rbytes=$RBYTES wbytes=$WBYTES rios=$RIOS wrios=$WIOS + + io.weight + + The weight setting, currently only available and effective if + cfq-iosched is in use for the target device. The weight is + between 1 and 10000 and defaults to 100. The first line + always contains the default weight in the following format to + use when per-device setting is missing. + + default $WEIGHT + + Subsequent lines list per-device weights of the following + format. + + $MAJ:$MIN $WEIGHT + + Writing "$WEIGHT" or "default $WEIGHT" changes the default + setting. Writing "$MAJ:$MIN $WEIGHT" sets per-device weight + while "$MAJ:$MIN default" clears it. + + This file is available only on non-root cgroups. + + io.max + + The maximum bandwidth and/or iops setting, only available if + blk-throttle is enabled. The file is of the following format. + + $MAJ:$MIN rbps=$RBPS wbps=$WBPS riops=$RIOPS wiops=$WIOPS + + ${R|W}BPS are read/write bytes per second and ${R|W}IOPS are + read/write IOs per second. "max" indicates no limit. Writing + to the file follows the same format but the individual + settings may be ommitted or specified in any order. + + This file is available only on non-root cgroups. 5-4-2. cpuset diff --git a/Documentation/devicetree/bindings/i2c/ina209.txt b/Documentation/devicetree/bindings/hwmon/ina209.txt index 9dd2bee80840..9dd2bee80840 100644 --- a/Documentation/devicetree/bindings/i2c/ina209.txt +++ b/Documentation/devicetree/bindings/hwmon/ina209.txt diff --git a/Documentation/devicetree/bindings/i2c/ina2xx.txt b/Documentation/devicetree/bindings/hwmon/ina2xx.txt index a2ad85d7e747..a2ad85d7e747 100644 --- a/Documentation/devicetree/bindings/i2c/ina2xx.txt +++ b/Documentation/devicetree/bindings/hwmon/ina2xx.txt diff --git a/Documentation/devicetree/bindings/i2c/max6697.txt b/Documentation/devicetree/bindings/hwmon/max6697.txt index 5f793998e4a4..5f793998e4a4 100644 --- a/Documentation/devicetree/bindings/i2c/max6697.txt +++ b/Documentation/devicetree/bindings/hwmon/max6697.txt diff --git a/Documentation/devicetree/bindings/i2c/i2c-cadence.txt b/Documentation/devicetree/bindings/i2c/i2c-cadence.txt index 7cb0b5608f49..ebaa90c58c8e 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-cadence.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-cadence.txt @@ -2,7 +2,11 @@ Binding for the Cadence I2C controller Required properties: - reg: Physical base address and size of the controller's register area. - - compatible: Compatibility string. Must be 'cdns,i2c-r1p10'. + - compatible: Should contain one of: + * "cdns,i2c-r1p10" + Note: Use this when cadence i2c controller version 1.0 is used. + * "cdns,i2c-r1p14" + Note: Use this when cadence i2c controller version 1.4 is used. - clocks: Input clock specifier. Refer to common clock bindings. - interrupts: Interrupt specifier. Refer to interrupt bindings. - #address-cells: Should be 1. diff --git a/Documentation/devicetree/bindings/i2c/i2c-emev2.txt b/Documentation/devicetree/bindings/i2c/i2c-emev2.txt new file mode 100644 index 000000000000..5ed1ea1c7e14 --- /dev/null +++ b/Documentation/devicetree/bindings/i2c/i2c-emev2.txt @@ -0,0 +1,22 @@ +Device tree configuration for Renesas EMEV2 IIC controller + +Required properties: +- compatible : "renesas,iic-emev2" +- reg : address start and address range size of device +- interrupts : specifier for the IIC controller interrupt +- clocks : phandle to the IP core SCLK +- clock-names : must be "sclk" +- #address-cells : should be <1> +- #size-cells : should be <0> + +Example: + + iic0: i2c@e0070000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "renesas,iic-emev2"; + reg = <0xe0070000 0x28>; + interrupts = <0 32 IRQ_TYPE_EDGE_RISING>; + clocks = <&iic0_sclk>; + clock-names = "sclk"; + }; diff --git a/Documentation/devicetree/bindings/i2c/i2c-lpc2k.txt b/Documentation/devicetree/bindings/i2c/i2c-lpc2k.txt new file mode 100644 index 000000000000..4101aa621ad4 --- /dev/null +++ b/Documentation/devicetree/bindings/i2c/i2c-lpc2k.txt @@ -0,0 +1,33 @@ +NXP I2C controller for LPC2xxx/178x/18xx/43xx + +Required properties: + - compatible: must be "nxp,lpc1788-i2c" + - reg: physical address and length of the device registers + - interrupts: a single interrupt specifier + - clocks: clock for the device + - #address-cells: should be <1> + - #size-cells: should be <0> + +Optional properties: +- clock-frequency: the desired I2C bus clock frequency in Hz; in + absence of this property the default value is used (100 kHz). + +Example: +i2c0: i2c@400a1000 { + compatible = "nxp,lpc1788-i2c"; + reg = <0x400a1000 0x1000>; + interrupts = <18>; + clocks = <&ccu1 CLK_APB1_I2C0>; + #address-cells = <1>; + #size-cells = <0>; +}; + +&i2c0 { + clock-frequency = <400000>; + + lm75@48 { + compatible = "nxp,lm75"; + reg = <0x48>; + }; +}; + diff --git a/Documentation/devicetree/bindings/i2c/i2c-mux-reg.txt b/Documentation/devicetree/bindings/i2c/i2c-mux-reg.txt new file mode 100644 index 000000000000..688783fbe696 --- /dev/null +++ b/Documentation/devicetree/bindings/i2c/i2c-mux-reg.txt @@ -0,0 +1,74 @@ +Register-based I2C Bus Mux + +This binding describes an I2C bus multiplexer that uses a single register +to route the I2C signals. + +Required properties: +- compatible: i2c-mux-reg +- i2c-parent: The phandle of the I2C bus that this multiplexer's master-side + port is connected to. +* Standard I2C mux properties. See mux.txt in this directory. +* I2C child bus nodes. See mux.txt in this directory. + +Optional properties: +- reg: this pair of <offset size> specifies the register to control the mux. + The <offset size> depends on its parent node. It can be any memory-mapped + address. The size must be either 1, 2, or 4 bytes. If reg is omitted, the + resource of this device will be used. +- little-endian: The existence indicates the register is in little endian. +- big-endian: The existence indicates the register is in big endian. + If both little-endian and big-endian are omitted, the endianness of the + CPU will be used. +- write-only: The existence indicates the register is write-only. +- idle-state: value to set the muxer to when idle. When no value is + given, it defaults to the last value used. + +Whenever an access is made to a device on a child bus, the value set +in the revelant node's reg property will be output to the register. + +If an idle state is defined, using the idle-state (optional) property, +whenever an access is not being made to a device on a child bus, the +register will be set according to the idle value. + +If an idle state is not defined, the most recently used value will be +left programmed into the register. + +Example of a mux on PCIe card, the host is a powerpc SoC (big endian): + + i2c-mux { + /* the <offset size> depends on the address translation + * of the parent device. If omitted, device resource + * will be used instead. The size is to determine + * whether iowrite32, iowrite16, or iowrite8 will be used. + */ + reg = <0x6028 0x4>; + little-endian; /* little endian register on PCIe */ + compatible = "i2c-mux-reg"; + #address-cells = <1>; + #size-cells = <0>; + i2c-parent = <&i2c1>; + i2c@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + + si5338: clock-generator@70 { + compatible = "silabs,si5338"; + reg = <0x70>; + /* other stuff */ + }; + }; + + i2c@1 { + /* data is written using iowrite32 */ + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + + si5338: clock-generator@70 { + compatible = "silabs,si5338"; + reg = <0x70>; + /* other stuff */ + }; + }; + }; diff --git a/Documentation/devicetree/bindings/i2c/i2c.txt b/Documentation/devicetree/bindings/i2c/i2c.txt new file mode 100644 index 000000000000..8a99150ac3a7 --- /dev/null +++ b/Documentation/devicetree/bindings/i2c/i2c.txt @@ -0,0 +1,45 @@ +Generic device tree bindings for I2C busses +=========================================== + +This document describes generic bindings which can be used to describe I2C +busses in a device tree. + +Required properties +------------------- + +- #address-cells - should be <1>. Read more about addresses below. +- #size-cells - should be <0>. +- compatible - name of I2C bus controller following generic names + recommended practice. + +For other required properties e.g. to describe register sets, +clocks, etc. check the binding documentation of the specific driver. + +The cells properties above define that an address of children of an I2C bus +are described by a single value. This is usually a 7 bit address. However, +flags can be attached to the address. I2C_TEN_BIT_ADDRESS is used to mark a 10 +bit address. It is needed to avoid the ambiguity between e.g. a 7 bit address +of 0x50 and a 10 bit address of 0x050 which, in theory, can be on the same bus. +Another flag is I2C_OWN_SLAVE_ADDRESS to mark addresses on which we listen to +be devices ourselves. + +Optional properties +------------------- + +These properties may not be supported by all drivers. However, if a driver +wants to support one of the below features, it should adapt the bindings below. + +- clock-frequency - frequency of bus clock in Hz. +- wakeup-source - device can be used as a wakeup source. + +- interrupts - interrupts used by the device. +- interrupt-names - "irq" and "wakeup" names are recognized by I2C core, + other names are left to individual drivers. + +Binding may contain optional "interrupts" property, describing interrupts +used by the device. I2C core will assign "irq" interrupt (or the very first +interrupt if not using interrupt names) as primary interrupt for the slave. + +Also, if device is marked as a wakeup source, I2C core will set up "wakeup" +interrupt for the device. If "wakeup" interrupt name is not present in the +binding, then primary interrupt will be used as wakeup interrupt. diff --git a/Documentation/devicetree/bindings/i2c/trivial-devices.txt b/Documentation/devicetree/bindings/i2c/trivial-devices.txt index 00f8652e193a..d77d412cbc68 100644 --- a/Documentation/devicetree/bindings/i2c/trivial-devices.txt +++ b/Documentation/devicetree/bindings/i2c/trivial-devices.txt @@ -95,6 +95,8 @@ stm,m41t00 Serial Access TIMEKEEPER stm,m41t62 Serial real-time clock (RTC) with alarm stm,m41t80 M41T80 - SERIAL ACCESS RTC WITH ALARMS taos,tsl2550 Ambient Light Sensor with SMBUS/Two Wire Serial Interface +ti,ads7828 8-Channels, 12-bit ADC +ti,ads7830 8-Channels, 8-bit ADC ti,tsc2003 I2C Touch-Screen Controller ti,tmp102 Low Power Digital Temperature Sensor with SMBUS/Two Wire Serial Interface ti,tmp103 Low Power Digital Temperature Sensor with SMBUS/Two Wire Serial Interface diff --git a/Documentation/devicetree/bindings/input/touchscreen/colibri-vf50-ts.txt b/Documentation/devicetree/bindings/input/touchscreen/colibri-vf50-ts.txt new file mode 100644 index 000000000000..9d9e930f3251 --- /dev/null +++ b/Documentation/devicetree/bindings/input/touchscreen/colibri-vf50-ts.txt @@ -0,0 +1,36 @@ +* Toradex Colibri VF50 Touchscreen driver + +Required Properties: +- compatible must be toradex,vf50-touchscreen +- io-channels: adc channels being used by the Colibri VF50 module +- xp-gpios: FET gate driver for input of X+ +- xm-gpios: FET gate driver for input of X- +- yp-gpios: FET gate driver for input of Y+ +- ym-gpios: FET gate driver for input of Y- +- interrupt-parent: phandle for the interrupt controller +- interrupts: pen irq interrupt for touch detection +- pinctrl-names: "idle", "default", "gpios" +- pinctrl-0: pinctrl node for pen/touch detection state pinmux +- pinctrl-1: pinctrl node for X/Y and pressure measurement (ADC) state pinmux +- pinctrl-2: pinctrl node for gpios functioning as FET gate drivers +- vf50-ts-min-pressure: pressure level at which to stop measuring X/Y values + +Example: + + touchctrl: vf50_touchctrl { + compatible = "toradex,vf50-touchscreen"; + io-channels = <&adc1 0>,<&adc0 0>, + <&adc0 1>,<&adc1 2>; + xp-gpios = <&gpio0 13 GPIO_ACTIVE_LOW>; + xm-gpios = <&gpio2 29 GPIO_ACTIVE_HIGH>; + yp-gpios = <&gpio0 12 GPIO_ACTIVE_LOW>; + ym-gpios = <&gpio0 4 GPIO_ACTIVE_HIGH>; + interrupt-parent = <&gpio0>; + interrupts = <8 IRQ_TYPE_LEVEL_LOW>; + pinctrl-names = "idle","default","gpios"; + pinctrl-0 = <&pinctrl_touchctrl_idle>; + pinctrl-1 = <&pinctrl_touchctrl_default>; + pinctrl-2 = <&pinctrl_touchctrl_gpios>; + vf50-ts-min-pressure = <200>; + status = "disabled"; + }; diff --git a/Documentation/devicetree/bindings/input/touchscreen/imx6ul_tsc.txt b/Documentation/devicetree/bindings/input/touchscreen/imx6ul_tsc.txt new file mode 100644 index 000000000000..853dff96dd9f --- /dev/null +++ b/Documentation/devicetree/bindings/input/touchscreen/imx6ul_tsc.txt @@ -0,0 +1,36 @@ +* Freescale i.MX6UL Touch Controller + +Required properties: +- compatible: must be "fsl,imx6ul-tsc". +- reg: this touch controller address and the ADC2 address. +- interrupts: the interrupt of this touch controller and ADC2. +- clocks: the root clock of touch controller and ADC2. +- clock-names; must be "tsc" and "adc". +- xnur-gpio: the X- gpio this controller connect to. + This xnur-gpio returns to low once the finger leave the touch screen (The + last touch event the touch controller capture). + +Optional properties: +- measure-delay-time: the value of measure delay time. + Before X-axis or Y-axis measurement, the screen need some time before + even potential distribution ready. + This value depends on the touch screen. +- pre-charge-time: the touch screen need some time to precharge. + This value depends on the touch screen. + +Example: + tsc: tsc@02040000 { + compatible = "fsl,imx6ul-tsc"; + reg = <0x02040000 0x4000>, <0x0219c000 0x4000>; + interrupts = <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clks IMX6UL_CLK_IPG>, + <&clks IMX6UL_CLK_ADC2>; + clock-names = "tsc", "adc"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_tsc>; + xnur-gpio = <&gpio1 3 GPIO_ACTIVE_LOW>; + measure-delay-time = <0xfff>; + pre-charge-time = <0xffff>; + status = "okay"; + }; diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.txt b/Documentation/devicetree/bindings/iommu/arm,smmu.txt index 06760503a819..718074501fcb 100644 --- a/Documentation/devicetree/bindings/iommu/arm,smmu.txt +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.txt @@ -43,6 +43,12 @@ conditions. ** System MMU optional properties: +- dma-coherent : Present if page table walks made by the SMMU are + cache coherent with the CPU. + + NOTE: this only applies to the SMMU itself, not + masters connected upstream of the SMMU. + - calxeda,smmu-secure-config-access : Enable proper handling of buggy implementations that always use secure access to SMMU configuration registers. In this case non-secure diff --git a/Documentation/devicetree/bindings/iommu/ti,omap-iommu.txt b/Documentation/devicetree/bindings/iommu/ti,omap-iommu.txt index 42531dc387aa..869699925fd5 100644 --- a/Documentation/devicetree/bindings/iommu/ti,omap-iommu.txt +++ b/Documentation/devicetree/bindings/iommu/ti,omap-iommu.txt @@ -8,6 +8,11 @@ Required properties: - ti,hwmods : Name of the hwmod associated with the IOMMU instance - reg : Address space for the configuration registers - interrupts : Interrupt specifier for the IOMMU instance +- #iommu-cells : Should be 0. OMAP IOMMUs are all "single-master" devices, + and needs no additional data in the pargs specifier. Please + also refer to the generic bindings document for more info + on this property, + Documentation/devicetree/bindings/iommu/iommu.txt Optional properties: - ti,#tlb-entries : Number of entries in the translation look-aside buffer. @@ -18,6 +23,7 @@ Optional properties: Example: /* OMAP3 ISP MMU */ mmu_isp: mmu@480bd400 { + #iommu-cells = <0>; compatible = "ti,omap2-iommu"; reg = <0x480bd400 0x80>; interrupts = <24>; diff --git a/Documentation/devicetree/bindings/ipmi.txt b/Documentation/devicetree/bindings/ipmi.txt new file mode 100644 index 000000000000..d5f1a877ed3e --- /dev/null +++ b/Documentation/devicetree/bindings/ipmi.txt @@ -0,0 +1,25 @@ +IPMI device + +Required properties: +- compatible: should be one of ipmi-kcs, ipmi-smic, or ipmi-bt +- device_type: should be ipmi +- reg: Address and length of the register set for the device + +Optional properties: +- interrupts: The interrupt for the device. Without this the interface + is polled. +- reg-size - The size of the register. Defaults to 1 +- reg-spacing - The number of bytes between register starts. Defaults to 1 +- reg-shift - The amount to shift the registers to the right to get the data + into bit zero. + +Example: + +smic@fff3a000 { + compatible = "ipmi-smic"; + device_type = "ipmi"; + reg = <0xfff3a000 0x1000>; + interrupts = <0 24 4>; + reg-size = <4>; + reg-spacing = <4>; +}; diff --git a/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt b/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt index 7e9490313d5a..da541c3631f8 100644 --- a/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt +++ b/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt @@ -9,7 +9,7 @@ Device Tree Bindings for the Arasan SDHCI Controller Required Properties: - compatible: Compatibility string. Must be 'arasan,sdhci-8.9a' or - 'arasan,sdhci-4.9a' + 'arasan,sdhci-4.9a' or 'arasan,sdhci-5.1' - reg: From mmc bindings: Register location and length. - clocks: From clock bindings: Handles to clock inputs. - clock-names: From clock bindings: Tuple including "clk_xin" and "clk_ahb" diff --git a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt index 211e7785f4d2..dca56d6248f5 100644 --- a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt +++ b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt @@ -15,6 +15,7 @@ Required properties: "fsl,imx6q-usdhc" "fsl,imx6sl-usdhc" "fsl,imx6sx-usdhc" + "fsl,imx7d-usdhc" Optional properties: - fsl,wp-controller : Indicate to use controller internal write protection @@ -27,6 +28,11 @@ Optional properties: transparent level shifters on the outputs of the controller. Two cells are required, first cell specifies minimum slot voltage (mV), second cell specifies maximum slot voltage (mV). Several ranges could be specified. +- fsl,tuning-step: Specify the increasing delay cell steps in tuning procedure. + The uSDHC use one delay cell as default increasing step to do tuning process. + This property allows user to change the tuning step to more than one delay + cells which is useful for some special boards or cards when the default + tuning step can't find the proper delay window within limited tuning retries. Examples: diff --git a/Documentation/devicetree/bindings/mmc/sdhci-atmel.txt b/Documentation/devicetree/bindings/mmc/sdhci-atmel.txt new file mode 100644 index 000000000000..1b662d7171a0 --- /dev/null +++ b/Documentation/devicetree/bindings/mmc/sdhci-atmel.txt @@ -0,0 +1,21 @@ +* Atmel SDHCI controller + +This file documents the differences between the core properties in +Documentation/devicetree/bindings/mmc/mmc.txt and the properties used by the +sdhci-of-at91 driver. + +Required properties: +- compatible: Must be "atmel,sama5d2-sdhci". +- clocks: Phandlers to the clocks. +- clock-names: Must be "hclock", "multclk", "baseclk"; + + +Example: + +sdmmc0: sdio-host@a0000000 { + compatible = "atmel,sama5d2-sdhci"; + reg = <0xa0000000 0x300>; + interrupts = <31 IRQ_TYPE_LEVEL_HIGH 0>; + clocks = <&sdmmc0_hclk>, <&sdmmc0_gclk>, <&main>; + clock-names = "hclock", "multclk", "baseclk"; +}; diff --git a/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt b/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt index 76bf087bc889..74166a0d460d 100644 --- a/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt +++ b/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt @@ -102,7 +102,7 @@ not every application needs SDIO irq, e.g. MMC cards. pinctrl-1 = <&mmc1_idle>; pinctrl-2 = <&mmc1_sleep>; ... - interrupts-extended = <&intc 64 &gpio2 28 0>; + interrupts-extended = <&intc 64 &gpio2 28 GPIO_ACTIVE_LOW>; }; mmc1_idle : pinmux_cirq_pin { diff --git a/Documentation/devicetree/bindings/pwm/lpc1850-sct-pwm.txt b/Documentation/devicetree/bindings/pwm/lpc1850-sct-pwm.txt new file mode 100644 index 000000000000..36e49d4325cd --- /dev/null +++ b/Documentation/devicetree/bindings/pwm/lpc1850-sct-pwm.txt @@ -0,0 +1,20 @@ +* NXP LPC18xx State Configurable Timer - Pulse Width Modulator driver + +Required properties: + - compatible: Should be "nxp,lpc1850-sct-pwm" + - reg: Should contain physical base address and length of pwm registers. + - clocks: Must contain an entry for each entry in clock-names. + See ../clock/clock-bindings.txt for details. + - clock-names: Must include the following entries. + - pwm: PWM operating clock. + - #pwm-cells: Should be 3. See pwm.txt in this directory for the description + of the cells format. + +Example: + pwm: pwm@40000000 { + compatible = "nxp,lpc1850-sct-pwm"; + reg = <0x40000000 0x1000>; + clocks =<&ccu1 CLK_CPU_SCT>; + clock-names = "pwm"; + #pwm-cells = <3>; + }; diff --git a/Documentation/devicetree/bindings/rtc/nxp,lpc1788-rtc.txt b/Documentation/devicetree/bindings/rtc/nxp,lpc1788-rtc.txt new file mode 100644 index 000000000000..3c97bd180592 --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/nxp,lpc1788-rtc.txt @@ -0,0 +1,21 @@ +NXP LPC1788 real-time clock + +The LPC1788 RTC provides calendar and clock functionality +together with periodic tick and alarm interrupt support. + +Required properties: +- compatible : must contain "nxp,lpc1788-rtc" +- reg : Specifies base physical address and size of the registers. +- interrupts : A single interrupt specifier. +- clocks : Must contain clock specifiers for rtc and register clock +- clock-names : Must contain "rtc" and "reg" + See ../clocks/clock-bindings.txt for details. + +Example: +rtc: rtc@40046000 { + compatible = "nxp,lpc1788-rtc"; + reg = <0x40046000 0x1000>; + interrupts = <47>; + clocks = <&creg_clk 0>, <&ccu1 CLK_CPU_BUS>; + clock-names = "rtc", "reg"; +}; diff --git a/Documentation/devicetree/bindings/rtc/rtc-omap.txt b/Documentation/devicetree/bindings/rtc/rtc-omap.txt index 43a83668673a..bf7d11ae9bea 100644 --- a/Documentation/devicetree/bindings/rtc/rtc-omap.txt +++ b/Documentation/devicetree/bindings/rtc/rtc-omap.txt @@ -16,6 +16,8 @@ Required properties: Optional properties: - system-power-controller: whether the rtc is controlling the system power through pmic_power_en +- clocks: Any internal or external clocks feeding in to rtc +- clock-names: Corresponding names of the clocks Example: @@ -26,4 +28,6 @@ rtc@1c23000 { 19>; interrupt-parent = <&intc>; system-power-controller; + clocks = <&clk_32k_rtc>, <&clk_32768_ck>; + clock-names = "ext-clk", "int-clk"; }; diff --git a/Documentation/devicetree/bindings/i2c/ti,bq32k.txt b/Documentation/devicetree/bindings/rtc/ti,bq32k.txt index e204906b9ad3..e204906b9ad3 100644 --- a/Documentation/devicetree/bindings/i2c/ti,bq32k.txt +++ b/Documentation/devicetree/bindings/rtc/ti,bq32k.txt diff --git a/Documentation/devicetree/bindings/rtc/xlnx-rtc.txt b/Documentation/devicetree/bindings/rtc/xlnx-rtc.txt new file mode 100644 index 000000000000..0df6f016b1b7 --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/xlnx-rtc.txt @@ -0,0 +1,25 @@ +* Xilinx Zynq Ultrascale+ MPSoC Real Time Clock + +RTC controller for the Xilinx Zynq MPSoC Real Time Clock +Separate IRQ lines for seconds and alarm + +Required properties: +- compatible: Should be "xlnx,zynqmp-rtc" +- reg: Physical base address of the controller and length + of memory mapped region. +- interrupts: IRQ lines for the RTC. +- interrupt-names: interrupt line names eg. "sec" "alarm" + +Optional: +- calibration: calibration value for 1 sec period which will + be programmed directly to calibration register + +Example: +rtc: rtc@ffa60000 { + compatible = "xlnx,zynqmp-rtc"; + reg = <0x0 0xffa60000 0x100>; + interrupt-parent = <&gic>; + interrupts = <0 26 4>, <0 27 4>; + interrupt-names = "alarm", "sec"; + calibration = <0x198233>; +}; diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,smd.txt b/Documentation/devicetree/bindings/soc/qcom/qcom,smd.txt index f65c76db9859..97d9b3e1bf39 100644 --- a/Documentation/devicetree/bindings/soc/qcom/qcom,smd.txt +++ b/Documentation/devicetree/bindings/soc/qcom/qcom,smd.txt @@ -37,6 +37,12 @@ The edge is described by the following properties: Definition: the identifier of the remote processor in the smd channel allocation table +- qcom,remote-pid: + Usage: optional + Value type: <u32> + Definition: the identifier for the remote processor as known by the rest + of the system. + = SMD DEVICES In turn, subnodes of the "edges" represent devices tied to SMD channels on that diff --git a/Documentation/devicetree/bindings/watchdog/atmel-sama5d4-wdt.txt b/Documentation/devicetree/bindings/watchdog/atmel-sama5d4-wdt.txt new file mode 100644 index 000000000000..f7cc7c060910 --- /dev/null +++ b/Documentation/devicetree/bindings/watchdog/atmel-sama5d4-wdt.txt @@ -0,0 +1,35 @@ +* Atmel SAMA5D4 Watchdog Timer (WDT) Controller + +Required properties: +- compatible: "atmel,sama5d4-wdt" +- reg: base physical address and length of memory mapped region. + +Optional properties: +- timeout-sec: watchdog timeout value (in seconds). +- interrupts: interrupt number to the CPU. +- atmel,watchdog-type: should be "hardware" or "software". + "hardware": enable watchdog fault reset. A watchdog fault triggers + watchdog reset. + "software": enable watchdog fault interrupt. A watchdog fault asserts + watchdog interrupt. +- atmel,idle-halt: present if you want to stop the watchdog when the CPU is + in idle state. + CAUTION: This property should be used with care, it actually makes the + watchdog not counting when the CPU is in idle state, therefore the + watchdog reset time depends on mean CPU usage and will not reset at all + if the CPU stop working while it is in idle state, which is probably + not what you want. +- atmel,dbg-halt: present if you want to stop the watchdog when the CPU is + in debug state. + +Example: + watchdog@fc068640 { + compatible = "atmel,sama5d4-wdt"; + reg = <0xfc068640 0x10>; + interrupts = <4 IRQ_TYPE_LEVEL_HIGH 5>; + timeout-sec = <10>; + atmel,watchdog-type = "hardware"; + atmel,dbg-halt; + atmel,idle-halt; + status = "okay"; + }; diff --git a/Documentation/devicetree/bindings/watchdog/lpc18xx-wdt.txt b/Documentation/devicetree/bindings/watchdog/lpc18xx-wdt.txt new file mode 100644 index 000000000000..09f6b24969e0 --- /dev/null +++ b/Documentation/devicetree/bindings/watchdog/lpc18xx-wdt.txt @@ -0,0 +1,19 @@ +* NXP LPC18xx Watchdog Timer (WDT) + +Required properties: +- compatible: Should be "nxp,lpc1850-wwdt" +- reg: Should contain WDT registers location and length +- clocks: Must contain an entry for each entry in clock-names. +- clock-names: Should contain "wdtclk" and "reg"; the watchdog counter + clock and register interface clock respectively. +- interrupts: Should contain WDT interrupt + +Examples: + +watchdog@40080000 { + compatible = "nxp,lpc1850-wwdt"; + reg = <0x40080000 0x24>; + clocks = <&cgu BASE_SAFE_CLK>, <&ccu1 CLK_CPU_WWDT>; + clock-names = "wdtclk", "reg"; + interrupts = <49>; +}; diff --git a/Documentation/features/vm/THP/arch-support.txt b/Documentation/features/vm/THP/arch-support.txt index 972d02c2a74c..df384e3e845f 100644 --- a/Documentation/features/vm/THP/arch-support.txt +++ b/Documentation/features/vm/THP/arch-support.txt @@ -20,7 +20,7 @@ | ia64: | TODO | | m32r: | .. | | m68k: | .. | - | metag: | .. | + | metag: | TODO | | microblaze: | .. | | mips: | ok | | mn10300: | .. | diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 6a34a0f4d37c..06d443450f21 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -397,7 +397,8 @@ prototypes: int (*release) (struct gendisk *, fmode_t); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); - int (*direct_access) (struct block_device *, sector_t, void **, unsigned long *); + int (*direct_access) (struct block_device *, sector_t, void __pmem **, + unsigned long *); int (*media_changed) (struct gendisk *); void (*unlock_native_capacity) (struct gendisk *); int (*revalidate_disk) (struct gendisk *); diff --git a/Documentation/filesystems/dax.txt b/Documentation/filesystems/dax.txt index 7af2851d667c..7bde64014a89 100644 --- a/Documentation/filesystems/dax.txt +++ b/Documentation/filesystems/dax.txt @@ -60,9 +60,10 @@ Filesystem support consists of - implementing the direct_IO address space operation, and calling dax_do_io() instead of blockdev_direct_IO() if S_DAX is set - implementing an mmap file operation for DAX files which sets the - VM_MIXEDMAP flag on the VMA, and setting the vm_ops to include handlers - for fault and page_mkwrite (which should probably call dax_fault() and - dax_mkwrite(), passing the appropriate get_block() callback) + VM_MIXEDMAP and VM_HUGEPAGE flags on the VMA, and setting the vm_ops to + include handlers for fault, pmd_fault and page_mkwrite (which should + probably call dax_fault(), dax_pmd_fault() and dax_mkwrite(), passing the + appropriate get_block() callback) - calling dax_truncate_page() instead of block_truncate_page() for DAX files - calling dax_zero_page_range() instead of zero_user() for DAX files - ensuring that there is sufficient locking between reads, writes, diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 6f7fafde0884..d411ca63c8b6 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -424,6 +424,7 @@ Private_Dirty: 0 kB Referenced: 892 kB Anonymous: 0 kB Swap: 0 kB +SwapPss: 0 kB KernelPageSize: 4 kB MMUPageSize: 4 kB Locked: 374 kB @@ -433,16 +434,23 @@ the first of these lines shows the same information as is displayed for the mapping in /proc/PID/maps. The remaining lines show the size of the mapping (size), the amount of the mapping that is currently resident in RAM (RSS), the process' proportional share of this mapping (PSS), the number of clean and -dirty private pages in the mapping. Note that even a page which is part of a -MAP_SHARED mapping, but has only a single pte mapped, i.e. is currently used -by only one process, is accounted as private and not as shared. "Referenced" -indicates the amount of memory currently marked as referenced or accessed. +dirty private pages in the mapping. + +The "proportional set size" (PSS) of a process is the count of pages it has +in memory, where each page is divided by the number of processes sharing it. +So if a process has 1000 pages all to itself, and 1000 shared with one other +process, its PSS will be 1500. +Note that even a page which is part of a MAP_SHARED mapping, but has only +a single pte mapped, i.e. is currently used by only one process, is accounted +as private and not as shared. +"Referenced" indicates the amount of memory currently marked as referenced or +accessed. "Anonymous" shows the amount of memory that does not belong to any file. Even a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE and a page is modified, the file page is replaced by a private anonymous copy. "Swap" shows how much would-be-anonymous memory is also used, but out on swap. - +"SwapPss" shows proportional swap share of this mapping. "VmFlags" field deserves a separate description. This member represents the kernel flags associated with the particular virtual memory area in two letter encoded manner. The codes are the following: diff --git a/Documentation/i2c/busses/i2c-parport b/Documentation/i2c/busses/i2c-parport index 0e2d17b460fd..c3dbb3bfd814 100644 --- a/Documentation/i2c/busses/i2c-parport +++ b/Documentation/i2c/busses/i2c-parport @@ -20,6 +20,7 @@ It currently supports the following devices: * (type=5) Analog Devices evaluation boards: ADM1025, ADM1030, ADM1031 * (type=6) Barco LPT->DVI (K5800236) adapter * (type=7) One For All JP1 parallel port adapter + * (type=8) VCT-jig These devices use different pinout configurations, so you have to tell the driver what you have, using the type module parameter. There is no diff --git a/Documentation/i2c/slave-interface b/Documentation/i2c/slave-interface index 2dee4e2d62df..61ed05cd9531 100644 --- a/Documentation/i2c/slave-interface +++ b/Documentation/i2c/slave-interface @@ -31,10 +31,13 @@ User manual =========== I2C slave backends behave like standard I2C clients. So, you can instantiate -them as described in the document 'instantiating-devices'. A quick example for -instantiating the slave-eeprom driver from userspace at address 0x64 on bus 1: +them as described in the document 'instantiating-devices'. The only difference +is that i2c slave backends have their own address space. So, you have to add +0x1000 to the address you would originally request. An example for +instantiating the slave-eeprom driver from userspace at the 7 bit address 0x64 +on bus 1: - # echo slave-24c02 0x64 > /sys/bus/i2c/devices/i2c-1/new_device + # echo slave-24c02 0x1064 > /sys/bus/i2c/devices/i2c-1/new_device Each backend should come with separate documentation to describe its specific behaviour and setup. diff --git a/Documentation/i2c/ten-bit-addresses b/Documentation/i2c/ten-bit-addresses index cdfe13901b99..7b2d11e53a49 100644 --- a/Documentation/i2c/ten-bit-addresses +++ b/Documentation/i2c/ten-bit-addresses @@ -2,6 +2,10 @@ The I2C protocol knows about two kinds of device addresses: normal 7 bit addresses, and an extended set of 10 bit addresses. The sets of addresses do not intersect: the 7 bit address 0x10 is not the same as the 10 bit address 0x10 (though a single device could respond to both of them). +To avoid ambiguity, the user sees 10 bit addresses mapped to a different +address space, namely 0xa000-0xa3ff. The leading 0xa (= 10) represents the +10 bit mode. This is used for creating device names in sysfs. It is also +needed when instantiating 10 bit devices via the new_device file in sysfs. I2C messages to and from 10-bit address devices have a different format. See the I2C specification for the details. diff --git a/Documentation/infiniband/sysfs.txt b/Documentation/infiniband/sysfs.txt index ddd519b72ee1..9028b025501a 100644 --- a/Documentation/infiniband/sysfs.txt +++ b/Documentation/infiniband/sysfs.txt @@ -64,3 +64,23 @@ MTHCA fw_ver - Firmware version hca_type - HCA type: "MT23108", "MT25208 (MT23108 compat mode)", or "MT25208" + +HFI1 + + The hfi1 driver also creates these additional files: + + hw_rev - hardware revision + board_id - manufacturing board id + tempsense - thermal sense information + serial - board serial number + nfreectxts - number of free user contexts + nctxts - number of allowed contexts (PSM2) + chip_reset - diagnostic (root only) + boardversion - board version + ports/1/ + CMgtA/ + cc_settings_bin - CCA tables used by PSM2 + cc_table_bin + sc2v/ - 32 files (0 - 31) used to translate sl->vl + sl2sc/ - 32 files (0 - 31) used to translate sl->sc + vl2mtu/ - 16 (0 - 15) files used to determine MTU for vl diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt index 39ac6546d4a4..df1b25eb8382 100644 --- a/Documentation/ioctl/ioctl-number.txt +++ b/Documentation/ioctl/ioctl-number.txt @@ -265,7 +265,7 @@ Code Seq#(hex) Include File Comments 's' all linux/cdk.h 't' 00-7F linux/ppp-ioctl.h 't' 80-8F linux/isdn_ppp.h -'t' 90 linux/toshiba.h +'t' 90-91 linux/toshiba.h toshiba and toshiba_acpi SMM 'u' 00-1F linux/smb_fs.h gone 'u' 20-3F linux/uvcvideo.h USB video class host driver 'v' 00-1F linux/ext2_fs.h conflict! diff --git a/Documentation/kbuild/kbuild.txt b/Documentation/kbuild/kbuild.txt index 6466704d47b5..0ff6a466a05b 100644 --- a/Documentation/kbuild/kbuild.txt +++ b/Documentation/kbuild/kbuild.txt @@ -174,6 +174,11 @@ The output directory is often set using "O=..." on the commandline. The value can be overridden in which case the default value is ignored. +KBUILD_SIGN_PIN +-------------------------------------------------- +This variable allows a passphrase or PIN to be passed to the sign-file +utility when signing kernel modules, if the private key requires such. + KBUILD_MODPOST_WARN -------------------------------------------------- KBUILD_MODPOST_WARN can be set to avoid errors in case of undefined diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index f0c950598582..22a4b687ea5b 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -4106,6 +4106,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted. plus one apbt timer for broadcast timer. x86_intel_mid_timer=apbt_only | lapic_and_apbt + xen_512gb_limit [KNL,X86-64,XEN] + Restricts the kernel running paravirtualized under Xen + to use only up to 512 GB of RAM. The reason to do so is + crash analysis tools and Xen tools for doing domain + save/restore/migration must be enabled to handle larger + domains. + xen_emul_unplug= [HW,X86,XEN] Unplug Xen emulated devices Format: [unplug0,][unplug1] diff --git a/Documentation/module-signing.txt b/Documentation/module-signing.txt index c72702ec1ded..a78bf1ffa68c 100644 --- a/Documentation/module-signing.txt +++ b/Documentation/module-signing.txt @@ -89,6 +89,32 @@ This has a number of options available: their signatures checked without causing a dependency loop. + (4) "File name or PKCS#11 URI of module signing key" (CONFIG_MODULE_SIG_KEY) + + Setting this option to something other than its default of + "certs/signing_key.pem" will disable the autogeneration of signing keys + and allow the kernel modules to be signed with a key of your choosing. + The string provided should identify a file containing both a private key + and its corresponding X.509 certificate in PEM form, or — on systems where + the OpenSSL ENGINE_pkcs11 is functional — a PKCS#11 URI as defined by + RFC7512. In the latter case, the PKCS#11 URI should reference both a + certificate and a private key. + + If the PEM file containing the private key is encrypted, or if the + PKCS#11 token requries a PIN, this can be provided at build time by + means of the KBUILD_SIGN_PIN variable. + + + (5) "Additional X.509 keys for default system keyring" (CONFIG_SYSTEM_TRUSTED_KEYS) + + This option can be set to the filename of a PEM-encoded file containing + additional certificates which will be included in the system keyring by + default. + +Note that enabling module signing adds a dependency on the OpenSSL devel +packages to the kernel build processes for the tool that does the signing. + + ======================= GENERATING SIGNING KEYS ======================= @@ -100,16 +126,16 @@ it can be deleted or stored securely. The public key gets built into the kernel so that it can be used to check the signatures as the modules are loaded. -Under normal conditions, the kernel build will automatically generate a new -keypair using openssl if one does not exist in the files: +Under normal conditions, when CONFIG_MODULE_SIG_KEY is unchanged from its +default, the kernel build will automatically generate a new keypair using +openssl if one does not exist in the file: - signing_key.priv - signing_key.x509 + certs/signing_key.pem during the building of vmlinux (the public part of the key needs to be built into vmlinux) using parameters in the: - x509.genkey + certs/x509.genkey file (which is also generated if it does not already exist). @@ -135,8 +161,12 @@ kernel sources tree and the openssl command. The following is an example to generate the public/private key files: openssl req -new -nodes -utf8 -sha256 -days 36500 -batch -x509 \ - -config x509.genkey -outform DER -out signing_key.x509 \ - -keyout signing_key.priv + -config x509.genkey -outform PEM -out kernel_key.pem \ + -keyout kernel_key.pem + +The full pathname for the resulting kernel_key.pem file can then be specified +in the CONFIG_MODULE_SIG_KEY option, and the certificate and key therein will +be used instead of an autogenerated keypair. ========================= @@ -152,10 +182,9 @@ in a keyring called ".system_keyring" that can be seen by: 302d2d52 I------ 1 perm 1f010000 0 0 asymmetri Fedora kernel signing key: d69a84e6bce3d216b979e9505b3e3ef9a7118079: X509.RSA a7118079 [] ... -Beyond the public key generated specifically for module signing, any file -placed in the kernel source root directory or the kernel build root directory -whose name is suffixed with ".x509" will be assumed to be an X.509 public key -and will be added to the keyring. +Beyond the public key generated specifically for module signing, additional +trusted certificates can be provided in a PEM-encoded file referenced by the +CONFIG_SYSTEM_TRUSTED_KEYS configuration option. Further, the architecture code may take public keys from a hardware store and add those in also (e.g. from the UEFI key database). @@ -181,7 +210,7 @@ To manually sign a module, use the scripts/sign-file tool available in the Linux kernel source tree. The script requires 4 arguments: 1. The hash algorithm (e.g., sha256) - 2. The private key filename + 2. The private key filename or PKCS#11 URI 3. The public key filename 4. The kernel module to be signed @@ -194,6 +223,9 @@ The hash algorithm used does not have to match the one configured, but if it doesn't, you should make sure that hash algorithm is either built into the kernel or can be loaded without requiring itself. +If the private key requires a passphrase or PIN, it can be provided in the +$KBUILD_SIGN_PIN environment variable. + ============================ SIGNED MODULES AND STRIPPING diff --git a/Documentation/security/Smack.txt b/Documentation/security/Smack.txt index de5e1aeca7fb..5e6d07fbed07 100644 --- a/Documentation/security/Smack.txt +++ b/Documentation/security/Smack.txt @@ -28,6 +28,10 @@ Smack kernels use the CIPSO IP option. Some network configurations are intolerant of IP options and can impede access to systems that use them as Smack does. +Smack is used in the Tizen operating system. Please +go to http://wiki.tizen.org for information about how +Smack is used in Tizen. + The current git repository for Smack user space is: git://github.com/smack-team/smack.git @@ -108,6 +112,8 @@ in the smackfs filesystem. This pseudo-filesystem is mounted on /sys/fs/smackfs. access + Provided for backward compatibility. The access2 interface + is preferred and should be used instead. This interface reports whether a subject with the specified Smack label has a particular access to an object with a specified Smack label. Write a fixed format access rule to @@ -136,6 +142,8 @@ change-rule those in the fourth string. If there is no such rule it will be created using the access specified in the third and the fourth strings. cipso + Provided for backward compatibility. The cipso2 interface + is preferred and should be used instead. This interface allows a specific CIPSO header to be assigned to a Smack label. The format accepted on write is: "%24s%4d%4d"["%4d"]... @@ -157,7 +165,19 @@ direct doi This contains the CIPSO domain of interpretation used in network packets. +ipv6host + This interface allows specific IPv6 internet addresses to be + treated as single label hosts. Packets are sent to single + label hosts only from processes that have Smack write access + to the host label. All packets received from single label hosts + are given the specified label. The format accepted on write is: + "%h:%h:%h:%h:%h:%h:%h:%h label" or + "%h:%h:%h:%h:%h:%h:%h:%h/%d label". + The "::" address shortcut is not supported. + If label is "-DELETE" a matched entry will be deleted. load + Provided for backward compatibility. The load2 interface + is preferred and should be used instead. This interface allows access control rules in addition to the system defined rules to be specified. The format accepted on write is: @@ -181,6 +201,8 @@ load2 permissions that are not allowed. The string "r-x--" would specify read and execute access. load-self + Provided for backward compatibility. The load-self2 interface + is preferred and should be used instead. This interface allows process specific access rules to be defined. These rules are only consulted if access would otherwise be permitted, and are intended to provide additional @@ -205,6 +227,8 @@ netlabel received from single label hosts are given the specified label. The format accepted on write is: "%d.%d.%d.%d label" or "%d.%d.%d.%d/%d label". + If the label specified is "-CIPSO" the address is treated + as a host that supports CIPSO headers. onlycap This contains labels processes must have for CAP_MAC_ADMIN and CAP_MAC_OVERRIDE to be effective. If this file is empty @@ -232,7 +256,8 @@ unconfined is dangerous and can ruin the proper labeling of your system. It should never be used in production. -You can add access rules in /etc/smack/accesses. They take the form: +If you are using the smackload utility +you can add access rules in /etc/smack/accesses. They take the form: subjectlabel objectlabel access diff --git a/Documentation/security/Yama.txt b/Documentation/security/Yama.txt index 227a63f018a2..d9ee7d7a6c7f 100644 --- a/Documentation/security/Yama.txt +++ b/Documentation/security/Yama.txt @@ -1,9 +1,7 @@ -Yama is a Linux Security Module that collects a number of system-wide DAC -security protections that are not handled by the core kernel itself. To -select it at boot time, specify "security=yama" (though this will disable -any other LSM). - -Yama is controlled through sysctl in /proc/sys/kernel/yama: +Yama is a Linux Security Module that collects system-wide DAC security +protections that are not handled by the core kernel itself. This is +selectable at build-time with CONFIG_SECURITY_YAMA, and can be controlled +at run-time through sysctls in /proc/sys/kernel/yama: - ptrace_scope diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 9c3f2f8054b5..a4482fceacec 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -349,7 +349,7 @@ zone[i]'s protection[j] is calculated by following expression. (i < j): zone[i]->protection[j] - = (total sums of present_pages from zone[i+1] to zone[j] on the node) + = (total sums of managed_pages from zone[i+1] to zone[j] on the node) / lowmem_reserve_ratio[i]; (i = j): (should not be protected. = 0; @@ -360,7 +360,7 @@ The default values of lowmem_reserve_ratio[i] are 256 (if zone[i] means DMA or DMA32 zone) 32 (others). As above expression, they are reciprocal number of ratio. -256 means 1/256. # of protection pages becomes about "0.39%" of total present +256 means 1/256. # of protection pages becomes about "0.39%" of total managed pages of higher zones on the node. If you would like to protect more pages, smaller values are effective. diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt index 267f39386f99..13f5619b2203 100644 --- a/Documentation/sysrq.txt +++ b/Documentation/sysrq.txt @@ -75,7 +75,8 @@ On all - write a character to /proc/sysrq-trigger. e.g.: 'e' - Send a SIGTERM to all processes, except for init. -'f' - Will call oom_kill to kill a memory hog process. +'f' - Will call the oom killer to kill a memory hog process, but do not + panic if nothing can be killed. 'g' - Used by kgdb (kernel debugger) diff --git a/Documentation/thermal/sysfs-api.txt b/Documentation/thermal/sysfs-api.txt index c1f6864a8c5d..10f062ea6bc2 100644 --- a/Documentation/thermal/sysfs-api.txt +++ b/Documentation/thermal/sysfs-api.txt @@ -180,6 +180,7 @@ Thermal zone device sys I/F, created once it's registered: |---temp: Current temperature |---mode: Working mode of the thermal zone |---policy: Thermal governor used for this zone + |---available_policies: Available thermal governors for this zone |---trip_point_[0-*]_temp: Trip point temperature |---trip_point_[0-*]_type: Trip point type |---trip_point_[0-*]_hyst: Hysteresis value for this trip point @@ -256,6 +257,10 @@ policy One of the various thermal governors used for a particular zone. RW, Required +available_policies + Available thermal governors which can be used for a particular zone. + RO, Required + trip_point_[0-*]_temp The temperature above which trip point will be fired. Unit: millidegree Celsius @@ -417,6 +422,7 @@ method, the sys I/F structure will be built like this: |---temp: 37000 |---mode: enabled |---policy: step_wise + |---available_policies: step_wise fair_share |---trip_point_0_temp: 100000 |---trip_point_0_type: critical |---trip_point_1_temp: 80000 diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt index 87bb4aa6a6b9..ef621d34ba5b 100644 --- a/Documentation/trace/ftrace.txt +++ b/Documentation/trace/ftrace.txt @@ -691,6 +691,8 @@ The above is mostly meaningful for kernel developers. The marks are determined by the difference between this current trace and the next trace. '$' - greater than 1 second + '@' - greater than 100 milisecond + '*' - greater than 10 milisecond '#' - greater than 1000 microsecond '!' - greater than 100 microsecond '+' - greater than 10 microsecond @@ -1944,26 +1946,49 @@ want, depending on your needs. ie: - 0) | up_write() { - 0) 0.646 us | _spin_lock_irqsave(); - 0) 0.684 us | _spin_unlock_irqrestore(); - 0) 3.123 us | } - 0) 0.548 us | fput(); - 0) + 58.628 us | } + 3) # 1837.709 us | } /* __switch_to */ + 3) | finish_task_switch() { + 3) 0.313 us | _raw_spin_unlock_irq(); + 3) 3.177 us | } + 3) # 1889.063 us | } /* __schedule */ + 3) ! 140.417 us | } /* __schedule */ + 3) # 2034.948 us | } /* schedule */ + 3) * 33998.59 us | } /* schedule_preempt_disabled */ [...] - 0) | putname() { - 0) | kmem_cache_free() { - 0) 0.518 us | __phys_addr(); - 0) 1.757 us | } - 0) 2.861 us | } - 0) ! 115.305 us | } - 0) ! 116.402 us | } + 1) 0.260 us | msecs_to_jiffies(); + 1) 0.313 us | __rcu_read_unlock(); + 1) + 61.770 us | } + 1) + 64.479 us | } + 1) 0.313 us | rcu_bh_qs(); + 1) 0.313 us | __local_bh_enable(); + 1) ! 217.240 us | } + 1) 0.365 us | idle_cpu(); + 1) | rcu_irq_exit() { + 1) 0.417 us | rcu_eqs_enter_common.isra.47(); + 1) 3.125 us | } + 1) ! 227.812 us | } + 1) ! 457.395 us | } + 1) @ 119760.2 us | } + + [...] + + 2) | handle_IPI() { + 1) 6.979 us | } + 2) 0.417 us | scheduler_ipi(); + 1) 9.791 us | } + 1) + 12.917 us | } + 2) 3.490 us | } + 1) + 15.729 us | } + 1) + 18.542 us | } + 2) $ 3594274 us | } + means that the function exceeded 10 usecs. ! means that the function exceeded 100 usecs. # means that the function exceeded 1000 usecs. + * means that the function exceeded 10 msecs. + @ means that the function exceeded 100 msecs. $ means that the function exceeded 1 sec. diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index a4ebcb712375..d9ecceea5a02 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -2671,7 +2671,7 @@ handled. 4.87 KVM_SET_GUEST_DEBUG Capability: KVM_CAP_SET_GUEST_DEBUG -Architectures: x86, s390, ppc +Architectures: x86, s390, ppc, arm64 Type: vcpu ioctl Parameters: struct kvm_guest_debug (in) Returns: 0 on success; -1 on error @@ -2693,8 +2693,8 @@ when running. Common control bits are: The top 16 bits of the control field are architecture specific control flags which can include the following: - - KVM_GUESTDBG_USE_SW_BP: using software breakpoints [x86] - - KVM_GUESTDBG_USE_HW_BP: using hardware breakpoints [x86, s390] + - KVM_GUESTDBG_USE_SW_BP: using software breakpoints [x86, arm64] + - KVM_GUESTDBG_USE_HW_BP: using hardware breakpoints [x86, s390, arm64] - KVM_GUESTDBG_INJECT_DB: inject DB type exception [x86] - KVM_GUESTDBG_INJECT_BP: inject BP type exception [x86] - KVM_GUESTDBG_EXIT_PENDING: trigger an immediate guest exit [s390] @@ -2709,6 +2709,11 @@ updated to the correct (supplied) values. The second part of the structure is architecture specific and typically contains a set of debug registers. +For arm64 the number of debug registers is implementation defined and +can be determined by querying the KVM_CAP_GUEST_DEBUG_HW_BPS and +KVM_CAP_GUEST_DEBUG_HW_WPS capabilities which return a positive number +indicating the number of supported registers. + When debug events exit the main run loop with the reason KVM_EXIT_DEBUG with the kvm_debug_exit_arch part of the kvm_run structure containing architecture specific debug information. @@ -3111,11 +3116,13 @@ data_offset describes where the data is located (KVM_EXIT_IO_OUT) or where kvm expects application code to place the data for the next KVM_RUN invocation (KVM_EXIT_IO_IN). Data format is a packed array. + /* KVM_EXIT_DEBUG */ struct { struct kvm_debug_exit_arch arch; } debug; -Unused. +If the exit_reason is KVM_EXIT_DEBUG, then a vcpu is processing a debug event +for which architecture specific information is returned. /* KVM_EXIT_MMIO */ struct { diff --git a/Documentation/vm/00-INDEX b/Documentation/vm/00-INDEX index 081c49777abb..6a5e2a102a45 100644 --- a/Documentation/vm/00-INDEX +++ b/Documentation/vm/00-INDEX @@ -14,6 +14,8 @@ hugetlbpage.txt - a brief summary of hugetlbpage support in the Linux kernel. hwpoison.txt - explains what hwpoison is +idle_page_tracking.txt + - description of the idle page tracking feature. ksm.txt - how to use the Kernel Samepage Merging feature. numa diff --git a/Documentation/vm/hugetlbpage.txt b/Documentation/vm/hugetlbpage.txt index 030977fb8d2d..54dd9b9c6c31 100644 --- a/Documentation/vm/hugetlbpage.txt +++ b/Documentation/vm/hugetlbpage.txt @@ -329,7 +329,14 @@ Examples 3) hugepage-mmap: see tools/testing/selftests/vm/hugepage-mmap.c -4) The libhugetlbfs (http://libhugetlbfs.sourceforge.net) library provides a - wide range of userspace tools to help with huge page usability, environment - setup, and control. Furthermore it provides useful test cases that should be - used when modifying code to ensure no regressions are introduced. +4) The libhugetlbfs (https://github.com/libhugetlbfs/libhugetlbfs) library + provides a wide range of userspace tools to help with huge page usability, + environment setup, and control. + +Kernel development regression testing +===================================== + +The most complete set of hugetlb tests are in the libhugetlbfs repository. +If you modify any hugetlb related code, use the libhugetlbfs test suite +to check for regressions. In addition, if you add any new hugetlb +functionality, please add appropriate tests to libhugetlbfs. diff --git a/Documentation/vm/idle_page_tracking.txt b/Documentation/vm/idle_page_tracking.txt new file mode 100644 index 000000000000..85dcc3bb85dc --- /dev/null +++ b/Documentation/vm/idle_page_tracking.txt @@ -0,0 +1,98 @@ +MOTIVATION + +The idle page tracking feature allows to track which memory pages are being +accessed by a workload and which are idle. This information can be useful for +estimating the workload's working set size, which, in turn, can be taken into +account when configuring the workload parameters, setting memory cgroup limits, +or deciding where to place the workload within a compute cluster. + +It is enabled by CONFIG_IDLE_PAGE_TRACKING=y. + +USER API + +The idle page tracking API is located at /sys/kernel/mm/page_idle. Currently, +it consists of the only read-write file, /sys/kernel/mm/page_idle/bitmap. + +The file implements a bitmap where each bit corresponds to a memory page. The +bitmap is represented by an array of 8-byte integers, and the page at PFN #i is +mapped to bit #i%64 of array element #i/64, byte order is native. When a bit is +set, the corresponding page is idle. + +A page is considered idle if it has not been accessed since it was marked idle +(for more details on what "accessed" actually means see the IMPLEMENTATION +DETAILS section). To mark a page idle one has to set the bit corresponding to +the page by writing to the file. A value written to the file is OR-ed with the +current bitmap value. + +Only accesses to user memory pages are tracked. These are pages mapped to a +process address space, page cache and buffer pages, swap cache pages. For other +page types (e.g. SLAB pages) an attempt to mark a page idle is silently ignored, +and hence such pages are never reported idle. + +For huge pages the idle flag is set only on the head page, so one has to read +/proc/kpageflags in order to correctly count idle huge pages. + +Reading from or writing to /sys/kernel/mm/page_idle/bitmap will return +-EINVAL if you are not starting the read/write on an 8-byte boundary, or +if the size of the read/write is not a multiple of 8 bytes. Writing to +this file beyond max PFN will return -ENXIO. + +That said, in order to estimate the amount of pages that are not used by a +workload one should: + + 1. Mark all the workload's pages as idle by setting corresponding bits in + /sys/kernel/mm/page_idle/bitmap. The pages can be found by reading + /proc/pid/pagemap if the workload is represented by a process, or by + filtering out alien pages using /proc/kpagecgroup in case the workload is + placed in a memory cgroup. + + 2. Wait until the workload accesses its working set. + + 3. Read /sys/kernel/mm/page_idle/bitmap and count the number of bits set. If + one wants to ignore certain types of pages, e.g. mlocked pages since they + are not reclaimable, he or she can filter them out using /proc/kpageflags. + +See Documentation/vm/pagemap.txt for more information about /proc/pid/pagemap, +/proc/kpageflags, and /proc/kpagecgroup. + +IMPLEMENTATION DETAILS + +The kernel internally keeps track of accesses to user memory pages in order to +reclaim unreferenced pages first on memory shortage conditions. A page is +considered referenced if it has been recently accessed via a process address +space, in which case one or more PTEs it is mapped to will have the Accessed bit +set, or marked accessed explicitly by the kernel (see mark_page_accessed()). The +latter happens when: + + - a userspace process reads or writes a page using a system call (e.g. read(2) + or write(2)) + + - a page that is used for storing filesystem buffers is read or written, + because a process needs filesystem metadata stored in it (e.g. lists a + directory tree) + + - a page is accessed by a device driver using get_user_pages() + +When a dirty page is written to swap or disk as a result of memory reclaim or +exceeding the dirty memory limit, it is not marked referenced. + +The idle memory tracking feature adds a new page flag, the Idle flag. This flag +is set manually, by writing to /sys/kernel/mm/page_idle/bitmap (see the USER API +section), and cleared automatically whenever a page is referenced as defined +above. + +When a page is marked idle, the Accessed bit must be cleared in all PTEs it is +mapped to, otherwise we will not be able to detect accesses to the page coming +from a process address space. To avoid interference with the reclaimer, which, +as noted above, uses the Accessed bit to promote actively referenced pages, one +more page flag is introduced, the Young flag. When the PTE Accessed bit is +cleared as a result of setting or updating a page's Idle flag, the Young flag +is set on the page. The reclaimer treats the Young flag as an extra PTE +Accessed bit and therefore will consider such a page as referenced. + +Since the idle memory tracking feature is based on the memory reclaimer logic, +it only works with pages that are on an LRU list, other pages are silently +ignored. That means it will ignore a user memory page if it is isolated, but +since there are usually not many of them, it should not affect the overall +result noticeably. In order not to stall scanning of the idle page bitmap, +locked pages may be skipped too. diff --git a/Documentation/vm/pagemap.txt b/Documentation/vm/pagemap.txt index 6bfbc172cdb9..0e1e55588b59 100644 --- a/Documentation/vm/pagemap.txt +++ b/Documentation/vm/pagemap.txt @@ -5,7 +5,7 @@ pagemap is a new (as of 2.6.25) set of interfaces in the kernel that allow userspace programs to examine the page tables and related information by reading files in /proc. -There are three components to pagemap: +There are four components to pagemap: * /proc/pid/pagemap. This file lets a userspace process find out which physical frame each virtual page is mapped to. It contains one 64-bit @@ -16,11 +16,17 @@ There are three components to pagemap: * Bits 0-4 swap type if swapped * Bits 5-54 swap offset if swapped * Bit 55 pte is soft-dirty (see Documentation/vm/soft-dirty.txt) - * Bits 56-60 zero - * Bit 61 page is file-page or shared-anon + * Bit 56 page exclusively mapped (since 4.2) + * Bits 57-60 zero + * Bit 61 page is file-page or shared-anon (since 3.5) * Bit 62 page swapped * Bit 63 page present + Since Linux 4.0 only users with the CAP_SYS_ADMIN capability can get PFNs. + In 4.0 and 4.1 opens by unprivileged fail with -EPERM. Starting from + 4.2 the PFN field is zeroed if the user does not have CAP_SYS_ADMIN. + Reason: information about PFNs helps in exploiting Rowhammer vulnerability. + If the page is not present but in swap, then the PFN contains an encoding of the swap file number and the page's offset into the swap. Unmapped pages return a null PFN. This allows determining @@ -64,6 +70,11 @@ There are three components to pagemap: 22. THP 23. BALLOON 24. ZERO_PAGE + 25. IDLE + + * /proc/kpagecgroup. This file contains a 64-bit inode number of the + memory cgroup each page is charged to, indexed by PFN. Only available when + CONFIG_MEMCG is set. Short descriptions to the page flags: @@ -110,6 +121,12 @@ Short descriptions to the page flags: 24. ZERO_PAGE zero page for pfn_zero or huge_zero page +25. IDLE + page has not been accessed since it was marked idle (see + Documentation/vm/idle_page_tracking.txt). Note that this flag may be + stale in case the page was accessed via a PTE. To make sure the flag + is up-to-date one has to read /sys/kernel/mm/page_idle/bitmap first. + [IO related page flags] 1. ERROR IO error occurred 3. UPTODATE page has up-to-date data @@ -159,3 +176,8 @@ Other notes: Reading from any of the files will return -EINVAL if you are not starting the read on an 8-byte boundary (e.g., if you sought an odd number of bytes into the file), or if the size of the read is not a multiple of 8 bytes. + +Before Linux 3.11 pagemap bits 55-60 were used for "page-shift" (which is +always 12 at most architectures). Since Linux 3.11 their meaning changes +after first clear of soft-dirty bits. Since Linux 4.2 they are used for +flags unconditionally. diff --git a/Documentation/vm/zswap.txt b/Documentation/vm/zswap.txt index 8458c0861e4e..89fff7d611cc 100644 --- a/Documentation/vm/zswap.txt +++ b/Documentation/vm/zswap.txt @@ -32,7 +32,7 @@ can also be enabled and disabled at runtime using the sysfs interface. An example command to enable zswap at runtime, assuming sysfs is mounted at /sys, is: -echo 1 > /sys/modules/zswap/parameters/enabled +echo 1 > /sys/module/zswap/parameters/enabled When zswap is disabled at runtime it will stop storing pages that are being swapped out. However, it will _not_ immediately write out or fault @@ -49,14 +49,26 @@ Zswap receives pages for compression through the Frontswap API and is able to evict pages from its own compressed pool on an LRU basis and write them back to the backing swap device in the case that the compressed pool is full. -Zswap makes use of zbud for the managing the compressed memory pool. Each -allocation in zbud is not directly accessible by address. Rather, a handle is +Zswap makes use of zpool for the managing the compressed memory pool. Each +allocation in zpool is not directly accessible by address. Rather, a handle is returned by the allocation routine and that handle must be mapped before being accessed. The compressed memory pool grows on demand and shrinks as compressed -pages are freed. The pool is not preallocated. +pages are freed. The pool is not preallocated. By default, a zpool of type +zbud is created, but it can be selected at boot time by setting the "zpool" +attribute, e.g. zswap.zpool=zbud. It can also be changed at runtime using the +sysfs "zpool" attribute, e.g. + +echo zbud > /sys/module/zswap/parameters/zpool + +The zbud type zpool allocates exactly 1 page to store 2 compressed pages, which +means the compression ratio will always be 2:1 or worse (because of half-full +zbud pages). The zsmalloc type zpool has a more complex compressed page +storage method, and it can achieve greater storage densities. However, +zsmalloc does not implement compressed page eviction, so once zswap fills it +cannot evict the oldest page, it can only reject new pages. When a swap page is passed from frontswap to zswap, zswap maintains a mapping -of the swap entry, a combination of the swap type and swap offset, to the zbud +of the swap entry, a combination of the swap type and swap offset, to the zpool handle that references that compressed swap page. This mapping is achieved with a red-black tree per swap type. The swap offset is the search key for the tree nodes. @@ -74,9 +86,17 @@ controlled policy: * max_pool_percent - The maximum percentage of memory that the compressed pool can occupy. -Zswap allows the compressor to be selected at kernel boot time by setting the -“compressor” attribute. The default compressor is lzo. e.g. -zswap.compressor=deflate +The default compressor is lzo, but it can be selected at boot time by setting +the “compressor” attribute, e.g. zswap.compressor=lzo. It can also be changed +at runtime using the sysfs "compressor" attribute, e.g. + +echo lzo > /sys/module/zswap/parameters/compressor + +When the zpool and/or compressor parameter is changed at runtime, any existing +compressed pages are not modified; they are left in their own zpool. When a +request is made for a page in an old zpool, it is uncompressed using its +original compressor. Once all pages are removed from an old zpool, the zpool +and its compressor are freed. A debugfs interface is provided for various statistic about pool size, number of pages stored, and various counters for the reasons pages are rejected. diff --git a/Documentation/watchdog/src/watchdog-test.c b/Documentation/watchdog/src/watchdog-test.c index 3da822967ee0..fcdde8fc98be 100644 --- a/Documentation/watchdog/src/watchdog-test.c +++ b/Documentation/watchdog/src/watchdog-test.c @@ -41,6 +41,7 @@ static void term(int sig) int main(int argc, char *argv[]) { int flags; + unsigned int ping_rate = 1; fd = open("/dev/watchdog", O_WRONLY); @@ -63,22 +64,33 @@ int main(int argc, char *argv[]) fprintf(stderr, "Watchdog card enabled.\n"); fflush(stderr); goto end; + } else if (!strncasecmp(argv[1], "-t", 2) && argv[2]) { + flags = atoi(argv[2]); + ioctl(fd, WDIOC_SETTIMEOUT, &flags); + fprintf(stderr, "Watchdog timeout set to %u seconds.\n", flags); + fflush(stderr); + goto end; + } else if (!strncasecmp(argv[1], "-p", 2) && argv[2]) { + ping_rate = strtoul(argv[2], NULL, 0); + fprintf(stderr, "Watchdog ping rate set to %u seconds.\n", ping_rate); + fflush(stderr); } else { - fprintf(stderr, "-d to disable, -e to enable.\n"); + fprintf(stderr, "-d to disable, -e to enable, -t <n> to set " \ + "the timeout,\n-p <n> to set the ping rate, and \n"); fprintf(stderr, "run by itself to tick the card.\n"); fflush(stderr); goto end; } - } else { - fprintf(stderr, "Watchdog Ticking Away!\n"); - fflush(stderr); } + fprintf(stderr, "Watchdog Ticking Away!\n"); + fflush(stderr); + signal(SIGINT, term); while(1) { keep_alive(); - sleep(1); + sleep(ping_rate); } end: close(fd); |