diff options
Diffstat (limited to 'Documentation')
19 files changed, 624 insertions, 46 deletions
diff --git a/Documentation/ABI/testing/sysfs-bus-fcoe b/Documentation/ABI/testing/sysfs-bus-fcoe index 50e2a80ea28..21640eaad37 100644 --- a/Documentation/ABI/testing/sysfs-bus-fcoe +++ b/Documentation/ABI/testing/sysfs-bus-fcoe @@ -1,14 +1,53 @@ -What: /sys/bus/fcoe/ctlr_X +What: /sys/bus/fcoe/ +Date: August 2012 +KernelVersion: TBD +Contact: Robert Love <robert.w.love@intel.com>, devel@open-fcoe.org +Description: The FCoE bus. Attributes in this directory are control interfaces. +Attributes: + + ctlr_create: 'FCoE Controller' instance creation interface. Writing an + <ifname> to this file will allocate and populate sysfs with a + fcoe_ctlr_device (ctlr_X). The user can then configure any + per-port settings and finally write to the fcoe_ctlr_device's + 'start' attribute to begin the kernel's discovery and login + process. + + ctlr_destroy: 'FCoE Controller' instance removal interface. Writing a + fcoe_ctlr_device's sysfs name to this file will log the + fcoe_ctlr_device out of the fabric or otherwise connected + FCoE devices. It will also free all kernel memory allocated + for this fcoe_ctlr_device and any structures associated + with it, this includes the scsi_host. + +What: /sys/bus/fcoe/devices/ctlr_X Date: March 2012 KernelVersion: TBD Contact: Robert Love <robert.w.love@intel.com>, devel@open-fcoe.org -Description: 'FCoE Controller' instances on the fcoe bus +Description: 'FCoE Controller' instances on the fcoe bus. + The FCoE Controller now has a three stage creation process. + 1) Write interface name to ctlr_create 2) Configure the FCoE + Controller (ctlr_X) 3) Enable the FCoE Controller to begin + discovery and login. The FCoE Controller is destroyed by + writing it's name, i.e. ctlr_X to the ctlr_delete file. + Attributes: fcf_dev_loss_tmo: Device loss timeout peroid (see below). Changing this value will change the dev_loss_tmo for all FCFs discovered by this controller. + mode: Display or change the FCoE Controller's mode. Possible + modes are 'Fabric' and 'VN2VN'. If a FCoE Controller + is started in 'Fabric' mode then FIP FCF discovery is + initiated and ultimately a fabric login is attempted. + If a FCoE Controller is started in 'VN2VN' mode then + FIP VN2VN discovery and login is performed. A FCoE + Controller only supports one mode at a time. + + enabled: Whether an FCoE controller is enabled or disabled. + 0 if disabled, 1 if enabled. Writing either 0 or 1 + to this file will enable or disable the FCoE controller. + lesb/link_fail: Link Error Status Block (LESB) link failure count. lesb/vlink_fail: Link Error Status Block (LESB) virtual link @@ -26,7 +65,7 @@ Attributes: Notes: ctlr_X (global increment starting at 0) -What: /sys/bus/fcoe/fcf_X +What: /sys/bus/fcoe/devices/fcf_X Date: March 2012 KernelVersion: TBD Contact: Robert Love <robert.w.love@intel.com>, devel@open-fcoe.org diff --git a/Documentation/devicetree/bindings/arc/interrupts.txt b/Documentation/devicetree/bindings/arc/interrupts.txt new file mode 100644 index 00000000000..9a5d562435e --- /dev/null +++ b/Documentation/devicetree/bindings/arc/interrupts.txt @@ -0,0 +1,24 @@ +* ARC700 incore Interrupt Controller + + The core interrupt controller provides 32 prioritised interrupts (2 levels) + to ARC700 core. + +Properties: + +- compatible: "snps,arc700-intc" +- interrupt-controller: This is an interrupt controller. +- #interrupt-cells: Must be <1>. + + Single Cell "interrupts" property of a device specifies the IRQ number + between 0 to 31 + + intc accessed via the special ARC AUX register interface, hence "reg" property + is not specified. + +Example: + + intc: interrupt-controller { + compatible = "snps,arc700-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; diff --git a/Documentation/devicetree/bindings/arm/armadeus.txt b/Documentation/devicetree/bindings/arm/armadeus.txt new file mode 100644 index 00000000000..9821283ff51 --- /dev/null +++ b/Documentation/devicetree/bindings/arm/armadeus.txt @@ -0,0 +1,6 @@ +Armadeus i.MX Platforms Device Tree Bindings +----------------------------------------------- + +APF51: i.MX51 based module. +Required root node properties: + - compatible = "armadeus,imx51-apf51", "fsl,imx51"; diff --git a/Documentation/devicetree/bindings/arm/fsl.txt b/Documentation/devicetree/bindings/arm/fsl.txt index f79818711e8..e935d7d4ac4 100644 --- a/Documentation/devicetree/bindings/arm/fsl.txt +++ b/Documentation/devicetree/bindings/arm/fsl.txt @@ -5,6 +5,14 @@ i.MX23 Evaluation Kit Required root node properties: - compatible = "fsl,imx23-evk", "fsl,imx23"; +i.MX25 Product Development Kit +Required root node properties: + - compatible = "fsl,imx25-pdk", "fsl,imx25"; + +i.MX27 Product Development Kit +Required root node properties: + - compatible = "fsl,imx27-pdk", "fsl,imx27"; + i.MX28 Evaluation Kit Required root node properties: - compatible = "fsl,imx28-evk", "fsl,imx28"; diff --git a/Documentation/devicetree/bindings/clock/imx5-clock.txt b/Documentation/devicetree/bindings/clock/imx5-clock.txt index 04ad47876be..2a0c904c46a 100644 --- a/Documentation/devicetree/bindings/clock/imx5-clock.txt +++ b/Documentation/devicetree/bindings/clock/imx5-clock.txt @@ -171,6 +171,7 @@ clocks and IDs. can_sel 156 can1_serial_gate 157 can1_ipg_gate 158 + owire_gate 159 Examples (for mx53): diff --git a/Documentation/devicetree/bindings/clock/imx6q-clock.txt b/Documentation/devicetree/bindings/clock/imx6q-clock.txt index f73fdf59556..969b38e06ad 100644 --- a/Documentation/devicetree/bindings/clock/imx6q-clock.txt +++ b/Documentation/devicetree/bindings/clock/imx6q-clock.txt @@ -203,6 +203,8 @@ clocks and IDs. pcie_ref 188 pcie_ref_125m 189 enet_ref 190 + usbphy1_gate 191 + usbphy2_gate 192 Examples: diff --git a/Documentation/devicetree/bindings/mips/cpu_irq.txt b/Documentation/devicetree/bindings/mips/cpu_irq.txt new file mode 100644 index 00000000000..13aa4b62c62 --- /dev/null +++ b/Documentation/devicetree/bindings/mips/cpu_irq.txt @@ -0,0 +1,47 @@ +MIPS CPU interrupt controller + +On MIPS the mips_cpu_intc_init() helper can be used to initialize the 8 CPU +IRQs from a devicetree file and create a irq_domain for IRQ controller. + +With the irq_domain in place we can describe how the 8 IRQs are wired to the +platforms internal interrupt controller cascade. + +Below is an example of a platform describing the cascade inside the devicetree +and the code used to load it inside arch_init_irq(). + +Required properties: +- compatible : Should be "mti,cpu-interrupt-controller" + +Example devicetree: + cpu-irq: cpu-irq@0 { + #address-cells = <0>; + + interrupt-controller; + #interrupt-cells = <1>; + + compatible = "mti,cpu-interrupt-controller"; + }; + + intc: intc@200 { + compatible = "ralink,rt2880-intc"; + reg = <0x200 0x100>; + + interrupt-controller; + #interrupt-cells = <1>; + + interrupt-parent = <&cpu-irq>; + interrupts = <2>; + }; + + +Example platform irq.c: +static struct of_device_id __initdata of_irq_ids[] = { + { .compatible = "mti,cpu-interrupt-controller", .data = mips_cpu_intc_init }, + { .compatible = "ralink,rt2880-intc", .data = intc_of_init }, + {}, +}; + +void __init arch_init_irq(void) +{ + of_irq_init(of_irq_ids); +} diff --git a/Documentation/devicetree/bindings/serial/lantiq_asc.txt b/Documentation/devicetree/bindings/serial/lantiq_asc.txt new file mode 100644 index 00000000000..5b78591aaa4 --- /dev/null +++ b/Documentation/devicetree/bindings/serial/lantiq_asc.txt @@ -0,0 +1,16 @@ +Lantiq SoC ASC serial controller + +Required properties: +- compatible : Should be "lantiq,asc" +- reg : Address and length of the register set for the device +- interrupts: the 3 (tx rx err) interrupt numbers. The interrupt specifier + depends on the interrupt-parent interrupt controller. + +Example: + +asc1: serial@E100C00 { + compatible = "lantiq,asc"; + reg = <0xE100C00 0x400>; + interrupt-parent = <&icu0>; + interrupts = <112 113 114>; +}; diff --git a/Documentation/devicetree/bindings/thermal/dove-thermal.txt b/Documentation/devicetree/bindings/thermal/dove-thermal.txt new file mode 100644 index 00000000000..6f474677d47 --- /dev/null +++ b/Documentation/devicetree/bindings/thermal/dove-thermal.txt @@ -0,0 +1,18 @@ +* Dove Thermal + +This driver is for Dove SoCs which contain a thermal sensor. + +Required properties: +- compatible : "marvell,dove-thermal" +- reg : Address range of the thermal registers + +The reg properties should contain two ranges. The first is for the +three Thermal Manager registers, while the second range contains the +Thermal Diode Control Registers. + +Example: + + thermal@10078 { + compatible = "marvell,dove-thermal"; + reg = <0xd001c 0x0c>, <0xd005c 0x08>; + }; diff --git a/Documentation/devicetree/bindings/thermal/kirkwood-thermal.txt b/Documentation/devicetree/bindings/thermal/kirkwood-thermal.txt new file mode 100644 index 00000000000..8c0f5eb86da --- /dev/null +++ b/Documentation/devicetree/bindings/thermal/kirkwood-thermal.txt @@ -0,0 +1,15 @@ +* Kirkwood Thermal + +This version is for Kirkwood 88F8262 & 88F6283 SoCs. Other kirkwoods +don't contain a thermal sensor. + +Required properties: +- compatible : "marvell,kirkwood-thermal" +- reg : Address range of the thermal registers + +Example: + + thermal@10078 { + compatible = "marvell,kirkwood-thermal"; + reg = <0x10078 0x4>; + }; diff --git a/Documentation/devicetree/bindings/thermal/rcar-thermal.txt b/Documentation/devicetree/bindings/thermal/rcar-thermal.txt new file mode 100644 index 00000000000..28ef498a66e --- /dev/null +++ b/Documentation/devicetree/bindings/thermal/rcar-thermal.txt @@ -0,0 +1,29 @@ +* Renesas R-Car Thermal + +Required properties: +- compatible : "renesas,rcar-thermal" +- reg : Address range of the thermal registers. + The 1st reg will be recognized as common register + if it has "interrupts". + +Option properties: + +- interrupts : use interrupt + +Example (non interrupt support): + +thermal@e61f0100 { + compatible = "renesas,rcar-thermal"; + reg = <0xe61f0100 0x38>; +}; + +Example (interrupt support): + +thermal@e61f0000 { + compatible = "renesas,rcar-thermal"; + reg = <0xe61f0000 0x14 + 0xe61f0100 0x38 + 0xe61f0200 0x38 + 0xe61f0300 0x38>; + interrupts = <0 69 4>; +}; diff --git a/Documentation/devicetree/bindings/arm/armada-370-xp-timer.txt b/Documentation/devicetree/bindings/timer/marvell,armada-370-xp-timer.txt index 64830118b01..36381129d14 100644 --- a/Documentation/devicetree/bindings/arm/armada-370-xp-timer.txt +++ b/Documentation/devicetree/bindings/timer/marvell,armada-370-xp-timer.txt @@ -1,10 +1,13 @@ -Marvell Armada 370 and Armada XP Global Timers ----------------------------------------------- +Marvell Armada 370 and Armada XP Timers +--------------------------------------- Required properties: - compatible: Should be "marvell,armada-370-xp-timer" -- interrupts: Should contain the list of Global Timer interrupts -- reg: Should contain the base address of the Global Timer registers +- interrupts: Should contain the list of Global Timer interrupts and + then local timer interrupts +- reg: Should contain location and length for timers register. First + pair for the Global Timer registers, second pair for the + local/private timers. - clocks: clock driving the timer hardware Optional properties: diff --git a/Documentation/devicetree/bindings/w1/fsl-imx-owire.txt b/Documentation/devicetree/bindings/w1/fsl-imx-owire.txt new file mode 100644 index 00000000000..ecf42c07684 --- /dev/null +++ b/Documentation/devicetree/bindings/w1/fsl-imx-owire.txt @@ -0,0 +1,19 @@ +* Freescale i.MX One wire bus master controller + +Required properties: +- compatible : should be "fsl,imx21-owire" +- reg : Address and length of the register set for the device + +Optional properties: +- clocks : phandle of clock that supplies the module (required if platform + clock bindings use device tree) + +Example: + +- From imx53.dtsi: +owire: owire@63fa4000 { + compatible = "fsl,imx53-owire", "fsl,imx21-owire"; + reg = <0x63fa4000 0x4000>; + clocks = <&clks 159>; + status = "disabled"; +}; diff --git a/Documentation/dma-buf-sharing.txt b/Documentation/dma-buf-sharing.txt index 0188903bc9e..4966b1be42a 100644 --- a/Documentation/dma-buf-sharing.txt +++ b/Documentation/dma-buf-sharing.txt @@ -302,7 +302,11 @@ Access to a dma_buf from the kernel context involves three steps: void dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr) The vmap call can fail if there is no vmap support in the exporter, or if it - runs out of vmalloc space. Fallback to kmap should be implemented. + runs out of vmalloc space. Fallback to kmap should be implemented. Note that + the dma-buf layer keeps a reference count for all vmap access and calls down + into the exporter's vmap function only when no vmapping exists, and only + unmaps it once. Protection against concurrent vmap/vunmap calls is provided + by taking the dma_buf->lock mutex. 3. Finish access diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index e567af39ee3..3a54fca730c 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1645,42 +1645,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted. that the amount of memory usable for all allocations is not too small. - movablemem_map=acpi - [KNL,X86,IA-64,PPC] This parameter is similar to - memmap except it specifies the memory map of - ZONE_MOVABLE. - This option inform the kernel to use Hot Pluggable bit - in flags from SRAT from ACPI BIOS to determine which - memory devices could be hotplugged. The corresponding - memory ranges will be set as ZONE_MOVABLE. - NOTE: Whatever node the kernel resides in will always - be un-hotpluggable. - - movablemem_map=nn[KMG]@ss[KMG] - [KNL,X86,IA-64,PPC] This parameter is similar to - memmap except it specifies the memory map of - ZONE_MOVABLE. - If user specifies memory ranges, the info in SRAT will - be ingored. And it works like the following: - - If more ranges are all within one node, then from - lowest ss to the end of the node will be ZONE_MOVABLE. - - If a range is within a node, then from ss to the end - of the node will be ZONE_MOVABLE. - - If a range covers two or more nodes, then from ss to - the end of the 1st node will be ZONE_MOVABLE, and all - the rest nodes will only have ZONE_MOVABLE. - If memmap is specified at the same time, the - movablemem_map will be limited within the memmap - areas. If kernelcore or movablecore is also specified, - movablemem_map will have higher priority to be - satisfied. So the administrator should be careful that - the amount of movablemem_map areas are not too large. - Otherwise kernel won't have enough memory to start. - NOTE: We don't stop users specifying the node the - kernel resides in as hotpluggable so that this - option can be used as a workaround of firmware - bugs. - MTD_Partition= [MTD] Format: <name>,<region-number>,<size>,<offset> diff --git a/Documentation/scsi/ChangeLog.megaraid_sas b/Documentation/scsi/ChangeLog.megaraid_sas index da03146c182..09673c7fc8e 100644 --- a/Documentation/scsi/ChangeLog.megaraid_sas +++ b/Documentation/scsi/ChangeLog.megaraid_sas @@ -1,3 +1,12 @@ +Release Date : Sat. Feb 9, 2013 17:00:00 PST 2013 - + (emaild-id:megaraidlinux@lsi.com) + Adam Radford +Current Version : 06.506.00.00-rc1 +Old Version : 06.504.01.00-rc1 + 1. Add 4k FastPath DIF support. + 2. Dont load DevHandle unless FastPath enabled. + 3. Version and Changelog update. +------------------------------------------------------------------------------- Release Date : Mon. Oct 1, 2012 17:00:00 PST 2012 - (emaild-id:megaraidlinux@lsi.com) Adam Radford diff --git a/Documentation/thermal/exynos_thermal_emulation b/Documentation/thermal/exynos_thermal_emulation new file mode 100644 index 00000000000..b73bbfb697b --- /dev/null +++ b/Documentation/thermal/exynos_thermal_emulation @@ -0,0 +1,53 @@ +EXYNOS EMULATION MODE +======================== + +Copyright (C) 2012 Samsung Electronics + +Written by Jonghwa Lee <jonghwa3.lee@samsung.com> + +Description +----------- + +Exynos 4x12 (4212, 4412) and 5 series provide emulation mode for thermal management unit. +Thermal emulation mode supports software debug for TMU's operation. User can set temperature +manually with software code and TMU will read current temperature from user value not from +sensor's value. + +Enabling CONFIG_EXYNOS_THERMAL_EMUL option will make this support in available. +When it's enabled, sysfs node will be created under +/sys/bus/platform/devices/'exynos device name'/ with name of 'emulation'. + +The sysfs node, 'emulation', will contain value 0 for the initial state. When you input any +temperature you want to update to sysfs node, it automatically enable emulation mode and +current temperature will be changed into it. +(Exynos also supports user changable delay time which would be used to delay of + changing temperature. However, this node only uses same delay of real sensing time, 938us.) + +Exynos emulation mode requires synchronous of value changing and enabling. It means when you +want to update the any value of delay or next temperature, then you have to enable emulation +mode at the same time. (Or you have to keep the mode enabling.) If you don't, it fails to +change the value to updated one and just use last succeessful value repeatedly. That's why +this node gives users the right to change termerpature only. Just one interface makes it more +simply to use. + +Disabling emulation mode only requires writing value 0 to sysfs node. + + +TEMP 120 | + | + 100 | + | + 80 | + | +----------- + 60 | | | + | +-------------| | + 40 | | | | + | | | | + 20 | | | +---------- + | | | | | + 0 |______________|_____________|__________|__________|_________ + A A A A TIME + |<----->| |<----->| |<----->| | + | 938us | | | | | | +emulation : 0 50 | 70 | 20 | 0 +current temp : sensor 50 70 20 sensor diff --git a/Documentation/thermal/intel_powerclamp.txt b/Documentation/thermal/intel_powerclamp.txt new file mode 100644 index 00000000000..332de4a39b5 --- /dev/null +++ b/Documentation/thermal/intel_powerclamp.txt @@ -0,0 +1,307 @@ + ======================= + INTEL POWERCLAMP DRIVER + ======================= +By: Arjan van de Ven <arjan@linux.intel.com> + Jacob Pan <jacob.jun.pan@linux.intel.com> + +Contents: + (*) Introduction + - Goals and Objectives + + (*) Theory of Operation + - Idle Injection + - Calibration + + (*) Performance Analysis + - Effectiveness and Limitations + - Power vs Performance + - Scalability + - Calibration + - Comparison with Alternative Techniques + + (*) Usage and Interfaces + - Generic Thermal Layer (sysfs) + - Kernel APIs (TBD) + +============ +INTRODUCTION +============ + +Consider the situation where a system’s power consumption must be +reduced at runtime, due to power budget, thermal constraint, or noise +level, and where active cooling is not preferred. Software managed +passive power reduction must be performed to prevent the hardware +actions that are designed for catastrophic scenarios. + +Currently, P-states, T-states (clock modulation), and CPU offlining +are used for CPU throttling. + +On Intel CPUs, C-states provide effective power reduction, but so far +they’re only used opportunistically, based on workload. With the +development of intel_powerclamp driver, the method of synchronizing +idle injection across all online CPU threads was introduced. The goal +is to achieve forced and controllable C-state residency. + +Test/Analysis has been made in the areas of power, performance, +scalability, and user experience. In many cases, clear advantage is +shown over taking the CPU offline or modulating the CPU clock. + + +=================== +THEORY OF OPERATION +=================== + +Idle Injection +-------------- + +On modern Intel processors (Nehalem or later), package level C-state +residency is available in MSRs, thus also available to the kernel. + +These MSRs are: + #define MSR_PKG_C2_RESIDENCY 0x60D + #define MSR_PKG_C3_RESIDENCY 0x3F8 + #define MSR_PKG_C6_RESIDENCY 0x3F9 + #define MSR_PKG_C7_RESIDENCY 0x3FA + +If the kernel can also inject idle time to the system, then a +closed-loop control system can be established that manages package +level C-state. The intel_powerclamp driver is conceived as such a +control system, where the target set point is a user-selected idle +ratio (based on power reduction), and the error is the difference +between the actual package level C-state residency ratio and the target idle +ratio. + +Injection is controlled by high priority kernel threads, spawned for +each online CPU. + +These kernel threads, with SCHED_FIFO class, are created to perform +clamping actions of controlled duty ratio and duration. Each per-CPU +thread synchronizes its idle time and duration, based on the rounding +of jiffies, so accumulated errors can be prevented to avoid a jittery +effect. Threads are also bound to the CPU such that they cannot be +migrated, unless the CPU is taken offline. In this case, threads +belong to the offlined CPUs will be terminated immediately. + +Running as SCHED_FIFO and relatively high priority, also allows such +scheme to work for both preemptable and non-preemptable kernels. +Alignment of idle time around jiffies ensures scalability for HZ +values. This effect can be better visualized using a Perf timechart. +The following diagram shows the behavior of kernel thread +kidle_inject/cpu. During idle injection, it runs monitor/mwait idle +for a given "duration", then relinquishes the CPU to other tasks, +until the next time interval. + +The NOHZ schedule tick is disabled during idle time, but interrupts +are not masked. Tests show that the extra wakeups from scheduler tick +have a dramatic impact on the effectiveness of the powerclamp driver +on large scale systems (Westmere system with 80 processors). + +CPU0 + ____________ ____________ +kidle_inject/0 | sleep | mwait | sleep | + _________| |________| |_______ + duration +CPU1 + ____________ ____________ +kidle_inject/1 | sleep | mwait | sleep | + _________| |________| |_______ + ^ + | + | + roundup(jiffies, interval) + +Only one CPU is allowed to collect statistics and update global +control parameters. This CPU is referred to as the controlling CPU in +this document. The controlling CPU is elected at runtime, with a +policy that favors BSP, taking into account the possibility of a CPU +hot-plug. + +In terms of dynamics of the idle control system, package level idle +time is considered largely as a non-causal system where its behavior +cannot be based on the past or current input. Therefore, the +intel_powerclamp driver attempts to enforce the desired idle time +instantly as given input (target idle ratio). After injection, +powerclamp moniors the actual idle for a given time window and adjust +the next injection accordingly to avoid over/under correction. + +When used in a causal control system, such as a temperature control, +it is up to the user of this driver to implement algorithms where +past samples and outputs are included in the feedback. For example, a +PID-based thermal controller can use the powerclamp driver to +maintain a desired target temperature, based on integral and +derivative gains of the past samples. + + + +Calibration +----------- +During scalability testing, it is observed that synchronized actions +among CPUs become challenging as the number of cores grows. This is +also true for the ability of a system to enter package level C-states. + +To make sure the intel_powerclamp driver scales well, online +calibration is implemented. The goals for doing such a calibration +are: + +a) determine the effective range of idle injection ratio +b) determine the amount of compensation needed at each target ratio + +Compensation to each target ratio consists of two parts: + + a) steady state error compensation + This is to offset the error occurring when the system can + enter idle without extra wakeups (such as external interrupts). + + b) dynamic error compensation + When an excessive amount of wakeups occurs during idle, an + additional idle ratio can be added to quiet interrupts, by + slowing down CPU activities. + +A debugfs file is provided for the user to examine compensation +progress and results, such as on a Westmere system. +[jacob@nex01 ~]$ cat +/sys/kernel/debug/intel_powerclamp/powerclamp_calib +controlling cpu: 0 +pct confidence steady dynamic (compensation) +0 0 0 0 +1 1 0 0 +2 1 1 0 +3 3 1 0 +4 3 1 0 +5 3 1 0 +6 3 1 0 +7 3 1 0 +8 3 1 0 +... +30 3 2 0 +31 3 2 0 +32 3 1 0 +33 3 2 0 +34 3 1 0 +35 3 2 0 +36 3 1 0 +37 3 2 0 +38 3 1 0 +39 3 2 0 +40 3 3 0 +41 3 1 0 +42 3 2 0 +43 3 1 0 +44 3 1 0 +45 3 2 0 +46 3 3 0 +47 3 0 0 +48 3 2 0 +49 3 3 0 + +Calibration occurs during runtime. No offline method is available. +Steady state compensation is used only when confidence levels of all +adjacent ratios have reached satisfactory level. A confidence level +is accumulated based on clean data collected at runtime. Data +collected during a period without extra interrupts is considered +clean. + +To compensate for excessive amounts of wakeup during idle, additional +idle time is injected when such a condition is detected. Currently, +we have a simple algorithm to double the injection ratio. A possible +enhancement might be to throttle the offending IRQ, such as delaying +EOI for level triggered interrupts. But it is a challenge to be +non-intrusive to the scheduler or the IRQ core code. + + +CPU Online/Offline +------------------ +Per-CPU kernel threads are started/stopped upon receiving +notifications of CPU hotplug activities. The intel_powerclamp driver +keeps track of clamping kernel threads, even after they are migrated +to other CPUs, after a CPU offline event. + + +===================== +Performance Analysis +===================== +This section describes the general performance data collected on +multiple systems, including Westmere (80P) and Ivy Bridge (4P, 8P). + +Effectiveness and Limitations +----------------------------- +The maximum range that idle injection is allowed is capped at 50 +percent. As mentioned earlier, since interrupts are allowed during +forced idle time, excessive interrupts could result in less +effectiveness. The extreme case would be doing a ping -f to generated +flooded network interrupts without much CPU acknowledgement. In this +case, little can be done from the idle injection threads. In most +normal cases, such as scp a large file, applications can be throttled +by the powerclamp driver, since slowing down the CPU also slows down +network protocol processing, which in turn reduces interrupts. + +When control parameters change at runtime by the controlling CPU, it +may take an additional period for the rest of the CPUs to catch up +with the changes. During this time, idle injection is out of sync, +thus not able to enter package C- states at the expected ratio. But +this effect is minor, in that in most cases change to the target +ratio is updated much less frequently than the idle injection +frequency. + +Scalability +----------- +Tests also show a minor, but measurable, difference between the 4P/8P +Ivy Bridge system and the 80P Westmere server under 50% idle ratio. +More compensation is needed on Westmere for the same amount of +target idle ratio. The compensation also increases as the idle ratio +gets larger. The above reason constitutes the need for the +calibration code. + +On the IVB 8P system, compared to an offline CPU, powerclamp can +achieve up to 40% better performance per watt. (measured by a spin +counter summed over per CPU counting threads spawned for all running +CPUs). + +==================== +Usage and Interfaces +==================== +The powerclamp driver is registered to the generic thermal layer as a +cooling device. Currently, it’s not bound to any thermal zones. + +jacob@chromoly:/sys/class/thermal/cooling_device14$ grep . * +cur_state:0 +max_state:50 +type:intel_powerclamp + +Example usage: +- To inject 25% idle time +$ sudo sh -c "echo 25 > /sys/class/thermal/cooling_device80/cur_state +" + +If the system is not busy and has more than 25% idle time already, +then the powerclamp driver will not start idle injection. Using Top +will not show idle injection kernel threads. + +If the system is busy (spin test below) and has less than 25% natural +idle time, powerclamp kernel threads will do idle injection, which +appear running to the scheduler. But the overall system idle is still +reflected. In this example, 24.1% idle is shown. This helps the +system admin or user determine the cause of slowdown, when a +powerclamp driver is in action. + + +Tasks: 197 total, 1 running, 196 sleeping, 0 stopped, 0 zombie +Cpu(s): 71.2%us, 4.7%sy, 0.0%ni, 24.1%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st +Mem: 3943228k total, 1689632k used, 2253596k free, 74960k buffers +Swap: 4087804k total, 0k used, 4087804k free, 945336k cached + + PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND + 3352 jacob 20 0 262m 644 428 S 286 0.0 0:17.16 spin + 3341 root -51 0 0 0 0 D 25 0.0 0:01.62 kidle_inject/0 + 3344 root -51 0 0 0 0 D 25 0.0 0:01.60 kidle_inject/3 + 3342 root -51 0 0 0 0 D 25 0.0 0:01.61 kidle_inject/1 + 3343 root -51 0 0 0 0 D 25 0.0 0:01.60 kidle_inject/2 + 2935 jacob 20 0 696m 125m 35m S 5 3.3 0:31.11 firefox + 1546 root 20 0 158m 20m 6640 S 3 0.5 0:26.97 Xorg + 2100 jacob 20 0 1223m 88m 30m S 3 2.3 0:23.68 compiz + +Tests have shown that by using the powerclamp driver as a cooling +device, a PID based userspace thermal controller can manage to +control CPU temperature effectively, when no other thermal influence +is added. For example, a UltraBook user can compile the kernel under +certain temperature (below most active trip points). diff --git a/Documentation/thermal/sysfs-api.txt b/Documentation/thermal/sysfs-api.txt index 88c02334e35..6859661c9d3 100644 --- a/Documentation/thermal/sysfs-api.txt +++ b/Documentation/thermal/sysfs-api.txt @@ -55,6 +55,8 @@ temperature) and throttle appropriate devices. .get_trip_type: get the type of certain trip point. .get_trip_temp: get the temperature above which the certain trip point will be fired. + .set_emul_temp: set the emulation temperature which helps in debugging + different threshold temperature points. 1.1.2 void thermal_zone_device_unregister(struct thermal_zone_device *tz) @@ -153,6 +155,7 @@ Thermal zone device sys I/F, created once it's registered: |---trip_point_[0-*]_temp: Trip point temperature |---trip_point_[0-*]_type: Trip point type |---trip_point_[0-*]_hyst: Hysteresis value for this trip point + |---emul_temp: Emulated temperature set node Thermal cooling device sys I/F, created once it's registered: /sys/class/thermal/cooling_device[0-*]: @@ -252,6 +255,16 @@ passive Valid values: 0 (disabled) or greater than 1000 RW, Optional +emul_temp + Interface to set the emulated temperature method in thermal zone + (sensor). After setting this temperature, the thermal zone may pass + this temperature to platform emulation function if registered or + cache it locally. This is useful in debugging different temperature + threshold and its associated cooling action. This is write only node + and writing 0 on this node should disable emulation. + Unit: millidegree Celsius + WO, Optional + ***************************** * Cooling device attributes * ***************************** @@ -329,8 +342,9 @@ The framework includes a simple notification mechanism, in the form of a netlink event. Netlink socket initialization is done during the _init_ of the framework. Drivers which intend to use the notification mechanism just need to call thermal_generate_netlink_event() with two arguments viz -(originator, event). Typically the originator will be an integer assigned -to a thermal_zone_device when it registers itself with the framework. The +(originator, event). The originator is a pointer to struct thermal_zone_device +from where the event has been originated. An integer which represents the +thermal zone device will be used in the message to identify the zone. The event will be one of:{THERMAL_AUX0, THERMAL_AUX1, THERMAL_CRITICAL, THERMAL_DEV_FAULT}. Notification can be sent when the current temperature crosses any of the configured thresholds. |