diff options
| -rw-r--r-- | Documentation/devicetree/bindings/arm/cpus.txt | 8 | ||||
| -rw-r--r-- | Documentation/devicetree/bindings/arm/idle-states.txt | 679 | ||||
| -rw-r--r-- | Documentation/devicetree/bindings/arm/psci.txt | 14 | ||||
| -rw-r--r-- | arch/arm64/include/asm/cpu_ops.h | 3 | ||||
| -rw-r--r-- | arch/arm64/include/asm/cpuidle.h | 13 | ||||
| -rw-r--r-- | arch/arm64/include/asm/suspend.h | 1 | ||||
| -rw-r--r-- | arch/arm64/kernel/Makefile | 1 | ||||
| -rw-r--r-- | arch/arm64/kernel/cpuidle.c | 31 | ||||
| -rw-r--r-- | arch/arm64/kernel/psci.c | 104 | ||||
| -rw-r--r-- | arch/arm64/kernel/sleep.S | 47 | ||||
| -rw-r--r-- | arch/arm64/kernel/suspend.c | 48 |
11 files changed, 916 insertions, 33 deletions
diff --git a/Documentation/devicetree/bindings/arm/cpus.txt b/Documentation/devicetree/bindings/arm/cpus.txt index 298e2f6b33c6..6fd0f15e899a 100644 --- a/Documentation/devicetree/bindings/arm/cpus.txt +++ b/Documentation/devicetree/bindings/arm/cpus.txt @@ -219,6 +219,12 @@ nodes to be present and contain the properties described below. Value type: <phandle> Definition: Specifies the ACC[2] node associated with this CPU. + - cpu-idle-states + Usage: Optional + Value type: <prop-encoded-array> + Definition: + # List of phandles to idle state nodes supported + by this cpu [3]. Example 1 (dual-cluster big.LITTLE system 32-bit): @@ -415,3 +421,5 @@ cpus { -- [1] arm/msm/qcom,saw2.txt [2] arm/msm/qcom,kpss-acc.txt +[3] ARM Linux kernel documentation - idle states bindings + Documentation/devicetree/bindings/arm/idle-states.txt diff --git a/Documentation/devicetree/bindings/arm/idle-states.txt b/Documentation/devicetree/bindings/arm/idle-states.txt new file mode 100644 index 000000000000..37375c7f3ccc --- /dev/null +++ b/Documentation/devicetree/bindings/arm/idle-states.txt @@ -0,0 +1,679 @@ +========================================== +ARM idle states binding description +========================================== + +========================================== +1 - Introduction +========================================== + +ARM systems contain HW capable of managing power consumption dynamically, +where cores can be put in different low-power states (ranging from simple +wfi to power gating) according to OS PM policies. The CPU states representing +the range of dynamic idle states that a processor can enter at run-time, can be +specified through device tree bindings representing the parameters required +to enter/exit specific idle states on a given processor. + +According to the Server Base System Architecture document (SBSA, [3]), the +power states an ARM CPU can be put into are identified by the following list: + +- Running +- Idle_standby +- Idle_retention +- Sleep +- Off + +The power states described in the SBSA document define the basic CPU states on +top of which ARM platforms implement power management schemes that allow an OS +PM implementation to put the processor in different idle states (which include +states listed above; "off" state is not an idle state since it does not have +wake-up capabilities, hence it is not considered in this document). + +Idle state parameters (eg entry latency) are platform specific and need to be +characterized with bindings that provide the required information to OS PM +code so that it can build the required tables and use them at runtime. + +The device tree binding definition for ARM idle states is the subject of this +document. + +=========================================== +2 - idle-states definitions +=========================================== + +Idle states are characterized for a specific system through a set of +timing and energy related properties, that underline the HW behaviour +triggered upon idle states entry and exit. + +The following diagram depicts the CPU execution phases and related timing +properties required to enter and exit an idle state: + +..__[EXEC]__|__[PREP]__|__[ENTRY]__|__[IDLE]__|__[EXIT]__|__[EXEC]__.. + | | | | | + + |<------ entry ------->| + | latency | + |<- exit ->| + | latency | + |<-------- min-residency -------->| + |<------- wakeup-latency ------->| + + Diagram 1: CPU idle state execution phases + +EXEC: Normal CPU execution. + +PREP: Preparation phase before committing the hardware to idle mode + like cache flushing. This is abortable on pending wake-up + event conditions. The abort latency is assumed to be negligible + (i.e. less than the ENTRY + EXIT duration). If aborted, CPU + goes back to EXEC. This phase is optional. If not abortable, + this should be included in the ENTRY phase instead. + +ENTRY: The hardware is committed to idle mode. This period must run + to completion up to IDLE before anything else can happen. + +IDLE: This is the actual energy-saving idle period. This may last + between 0 and infinite time, until a wake-up event occurs. + +EXIT: Period during which the CPU is brought back to operational + mode (EXEC). + +entry-latency: Worst case latency required to enter the idle state. The +exit-latency may be guaranteed only after entry-latency has passed. + +min-residency: Minimum period, including preparation and entry, for a given +idle state to be worthwhile energywise. + +wakeup-latency: Maximum delay between the signaling of a wake-up event and the +CPU being able to execute normal code again. If not specified, this is assumed +to be entry-latency + exit-latency. + +These timing parameters can be used by an OS in different circumstances. + +An idle CPU requires the expected min-residency time to select the most +appropriate idle state based on the expected expiry time of the next IRQ +(ie wake-up) that causes the CPU to return to the EXEC phase. + +An operating system scheduler may need to compute the shortest wake-up delay +for CPUs in the system by detecting how long will it take to get a CPU out +of an idle state, eg: + +wakeup-delay = exit-latency + max(entry-latency - (now - entry-timestamp), 0) + +In other words, the scheduler can make its scheduling decision by selecting +(eg waking-up) the CPU with the shortest wake-up latency. +The wake-up latency must take into account the entry latency if that period +has not expired. The abortable nature of the PREP period can be ignored +if it cannot be relied upon (e.g. the PREP deadline may occur much sooner than +the worst case since it depends on the CPU operating conditions, ie caches +state). + +An OS has to reliably probe the wakeup-latency since some devices can enforce +latency constraints guarantees to work properly, so the OS has to detect the +worst case wake-up latency it can incur if a CPU is allowed to enter an +idle state, and possibly to prevent that to guarantee reliable device +functioning. + +The min-residency time parameter deserves further explanation since it is +expressed in time units but must factor in energy consumption coefficients. + +The energy consumption of a cpu when it enters a power state can be roughly +characterised by the following graph: + + | + | + | + e | + n | /--- + e | /------ + r | /------ + g | /----- + y | /------ + | ---- + | /| + | / | + | / | + | / | + | / | + | / | + |/ | + -----|-------+---------------------------------- + 0| 1 time(ms) + + Graph 1: Energy vs time example + +The graph is split in two parts delimited by time 1ms on the X-axis. +The graph curve with X-axis values = { x | 0 < x < 1ms } has a steep slope +and denotes the energy costs incurred whilst entering and leaving the idle +state. +The graph curve in the area delimited by X-axis values = {x | x > 1ms } has +shallower slope and essentially represents the energy consumption of the idle +state. + +min-residency is defined for a given idle state as the minimum expected +residency time for a state (inclusive of preparation and entry) after +which choosing that state become the most energy efficient option. A good +way to visualise this, is by taking the same graph above and comparing some +states energy consumptions plots. + +For sake of simplicity, let's consider a system with two idle states IDLE1, +and IDLE2: + + | + | + | + | /-- IDLE1 + e | /--- + n | /---- + e | /--- + r | /-----/--------- IDLE2 + g | /-------/--------- + y | ------------ /---| + | / /---- | + | / /--- | + | / /---- | + | / /--- | + | --- | + | / | + | / | + |/ | time + ---/----------------------------+------------------------ + |IDLE1-energy < IDLE2-energy | IDLE2-energy < IDLE1-energy + | + IDLE2-min-residency + + Graph 2: idle states min-residency example + +In graph 2 above, that takes into account idle states entry/exit energy +costs, it is clear that if the idle state residency time (ie time till next +wake-up IRQ) is less than IDLE2-min-residency, IDLE1 is the better idle state +choice energywise. + +This is mainly down to the fact that IDLE1 entry/exit energy costs are lower +than IDLE2. + +However, the lower power consumption (ie shallower energy curve slope) of idle +state IDLE2 implies that after a suitable time, IDLE2 becomes more energy +efficient. + +The time at which IDLE2 becomes more energy efficient than IDLE1 (and other +shallower states in a system with multiple idle states) is defined +IDLE2-min-residency and corresponds to the time when energy consumption of +IDLE1 and IDLE2 states breaks even. + +The definitions provided in this section underpin the idle states +properties specification that is the subject of the following sections. + +=========================================== +3 - idle-states node +=========================================== + +ARM processor idle states are defined within the idle-states node, which is +a direct child of the cpus node [1] and provides a container where the +processor idle states, defined as device tree nodes, are listed. + +- idle-states node + + Usage: Optional - On ARM systems, it is a container of processor idle + states nodes. If the system does not provide CPU + power management capabilities or the processor just + supports idle_standby an idle-states node is not + required. + + Description: idle-states node is a container node, where its + subnodes describe the CPU idle states. + + Node name must be "idle-states". + + The idle-states node's parent node must be the cpus node. + + The idle-states node's child nodes can be: + + - one or more state nodes + + Any other configuration is considered invalid. + + An idle-states node defines the following properties: + + - entry-method + Value type: <stringlist> + Usage and definition depend on ARM architecture version. + # On ARM v8 64-bit this property is required and must + be one of: + - "psci" (see bindings in [2]) + # On ARM 32-bit systems this property is optional + +The nodes describing the idle states (state) can only be defined within the +idle-states node, any other configuration is considered invalid and therefore +must be ignored. + +=========================================== +4 - state node +=========================================== + +A state node represents an idle state description and must be defined as +follows: + +- state node + + Description: must be child of the idle-states node + + The state node name shall follow standard device tree naming + rules ([5], 2.2.1 "Node names"), in particular state nodes which + are siblings within a single common parent must be given a unique name. + + The idle state entered by executing the wfi instruction (idle_standby + SBSA,[3][4]) is considered standard on all ARM platforms and therefore + must not be listed. + + With the definitions provided above, the following list represents + the valid properties for a state node: + + - compatible + Usage: Required + Value type: <stringlist> + Definition: Must be "arm,idle-state". + + - local-timer-stop + Usage: See definition + Value type: <none> + Definition: if present the CPU local timer control logic is + lost on state entry, otherwise it is retained. + + - entry-latency-us + Usage: Required + Value type: <prop-encoded-array> + Definition: u32 value representing worst case latency in + microseconds required to enter the idle state. + The exit-latency-us duration may be guaranteed + only after entry-latency-us has passed. + + - exit-latency-us + Usage: Required + Value type: <prop-encoded-array> + Definition: u32 value representing worst case latency + in microseconds required to exit the idle state. + + - min-residency-us + Usage: Required + Value type: <prop-encoded-array> + Definition: u32 value representing minimum residency duration + in microseconds, inclusive of preparation and + entry, for this idle state to be considered + worthwhile energy wise (refer to section 2 of + this document for a complete description). + + - wakeup-latency-us: + Usage: Optional + Value type: <prop-encoded-array> + Definition: u32 value representing maximum delay between the + signaling of a wake-up event and the CPU being + able to execute normal code again. If omitted, + this is assumed to be equal to: + + entry-latency-us + exit-latency-us + + It is important to supply this value on systems + where the duration of PREP phase (see diagram 1, + section 2) is non-neglibigle. + In such systems entry-latency-us + exit-latency-us + will exceed wakeup-latency-us by this duration. + + In addition to the properties listed above, a state node may require + additional properties specifics to the entry-method defined in the + idle-states node, please refer to the entry-method bindings + documentation for properties definitions. + +=========================================== +4 - Examples +=========================================== + +Example 1 (ARM 64-bit, 16-cpu system, PSCI enable-method): + +cpus { + #size-cells = <0>; + #address-cells = <2>; + + CPU0: cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x0 0x0>; + enable-method = "psci"; + cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0 + &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>; + }; + + CPU1: cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x0 0x1>; + enable-method = "psci"; + cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0 + &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>; + }; + + CPU2: cpu@100 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x0 0x100>; + enable-method = "psci"; + cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0 + &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>; + }; + + CPU3: cpu@101 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x0 0x101>; + enable-method = "psci"; + cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0 + &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>; + }; + + CPU4: cpu@10000 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x0 0x10000>; + enable-method = "psci"; + cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0 + &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>; + }; + + CPU5: cpu@10001 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x0 0x10001>; + enable-method = "psci"; + cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0 + &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>; + }; + + CPU6: cpu@10100 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x0 0x10100>; + enable-method = "psci"; + cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0 + &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>; + }; + + CPU7: cpu@10101 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x0 0x10101>; + enable-method = "psci"; + cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0 + &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>; + }; + + CPU8: cpu@100000000 { + device_type = "cpu"; + compatible = "arm,cortex-a53"; + reg = <0x1 0x0>; + enable-method = "psci"; + cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0 + &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>; + }; + + CPU9: cpu@100000001 { + device_type = "cpu"; + compatible = "arm,cortex-a53"; + reg = <0x1 0x1>; + enable-method = "psci"; + cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0 + &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>; + }; + + CPU10: cpu@100000100 { + device_type = "cpu"; + compatible = "arm,cortex-a53"; + reg = <0x1 0x100>; + enable-method = "psci"; + cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0 + &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>; + }; + + CPU11: cpu@100000101 { + device_type = "cpu"; + compatible = "arm,cortex-a53"; + reg = <0x1 0x101>; + enable-method = "psci"; + cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0 + &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>; + }; + + CPU12: cpu@100010000 { + device_type = "cpu"; + compatible = "arm,cortex-a53"; + reg = <0x1 0x10000>; + enable-method = "psci"; + cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0 + &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>; + }; + + CPU13: cpu@100010001 { + device_type = "cpu"; + compatible = "arm,cortex-a53"; + reg = <0x1 0x10001>; + enable-method = "psci"; + cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0 + &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>; + }; + + CPU14: cpu@100010100 { + device_type = "cpu"; + compatible = "arm,cortex-a53"; + reg = <0x1 0x10100>; + enable-method = "psci"; + cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0 + &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>; + }; + + CPU15: cpu@100010101 { + device_type = "cpu"; + compatible = "arm,cortex-a53"; + reg = <0x1 0x10101>; + enable-method = "psci"; + cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0 + &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>; + }; + + idle-states { + entry-method = "arm,psci"; + + CPU_RETENTION_0_0: cpu-retention-0-0 { + compatible = "arm,idle-state"; + arm,psci-suspend-param = <0x0010000>; + entry-latency-us = <20>; + exit-latency-us = <40>; + min-residency-us = <80>; + }; + + CLUSTER_RETENTION_0: cluster-retention-0 { + compatible = "arm,idle-state"; + local-timer-stop; + arm,psci-suspend-param = <0x1010000>; + entry-latency-us = <50>; + exit-latency-us = <100>; + min-residency-us = <250>; + wakeup-latency-us = <130>; + }; + + CPU_SLEEP_0_0: cpu-sleep-0-0 { + compatible = "arm,idle-state"; + local-timer-stop; + arm,psci-suspend-param = <0x0010000>; + entry-latency-us = <250>; + exit-latency-us = <500>; + min-residency-us = <950>; + }; + + CLUSTER_SLEEP_0: cluster-sleep-0 { + compatible = "arm,idle-state"; + local-timer-stop; + arm,psci-suspend-param = <0x1010000>; + entry-latency-us = <600>; + exit-latency-us = <1100>; + min-residency-us = <2700>; + wakeup-latency-us = <1500>; + }; + + CPU_RETENTION_1_0: cpu-retention-1-0 { + compatible = "arm,idle-state"; + arm,psci-suspend-param = <0x0010000>; + entry-latency-us = <20>; + exit-latency-us = <40>; + min-residency-us = <90>; + }; + + CLUSTER_RETENTION_1: cluster-retention-1 { + compatible = "arm,idle-state"; + local-timer-stop; + arm,psci-suspend-param = <0x1010000>; + entry-latency-us = <50>; + exit-latency-us = <100>; + min-residency-us = <270>; + wakeup-latency-us = <100>; + }; + + CPU_SLEEP_1_0: cpu-sleep-1-0 { + compatible = "arm,idle-state"; + local-timer-stop; + arm,psci-suspend-param = <0x0010000>; + entry-latency-us = <70>; + exit-latency-us = <100>; + min-residency-us = <300>; + wakeup-latency-us = <150>; + }; + + CLUSTER_SLEEP_1: cluster-sleep-1 { + compatible = "arm,idle-state"; + local-timer-stop; + arm,psci-suspend-param = <0x1010000>; + entry-latency-us = <500>; + exit-latency-us = <1200>; + min-residency-us = <3500>; + wakeup-latency-us = <1300>; + }; + }; + +}; + +Example 2 (ARM 32-bit, 8-cpu system, two clusters): + +cpus { + #size-cells = <0>; + #address-cells = <1>; + + CPU0: cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0x0>; + cpu-idle-states = <&CPU_SLEEP_0_0 &CLUSTER_SLEEP_0>; + }; + + CPU1: cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0x1>; + cpu-idle-states = <&CPU_SLEEP_0_0 &CLUSTER_SLEEP_0>; + }; + + CPU2: cpu@2 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0x2>; + cpu-idle-states = <&CPU_SLEEP_0_0 &CLUSTER_SLEEP_0>; + }; + + CPU3: cpu@3 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0x3>; + cpu-idle-states = <&CPU_SLEEP_0_0 &CLUSTER_SLEEP_0>; + }; + + CPU4: cpu@100 { + device_type = "cpu"; + compatible = "arm,cortex-a7"; + reg = <0x100>; + cpu-idle-states = <&CPU_SLEEP_1_0 &CLUSTER_SLEEP_1>; + }; + + CPU5: cpu@101 { + device_type = "cpu"; + compatible = "arm,cortex-a7"; + reg = <0x101>; + cpu-idle-states = <&CPU_SLEEP_1_0 &CLUSTER_SLEEP_1>; + }; + + CPU6: cpu@102 { + device_type = "cpu"; + compatible = "arm,cortex-a7"; + reg = <0x102>; + cpu-idle-states = <&CPU_SLEEP_1_0 &CLUSTER_SLEEP_1>; + }; + + CPU7: cpu@103 { + device_type = "cpu"; + compatible = "arm,cortex-a7"; + reg = <0x103>; + cpu-idle-states = <&CPU_SLEEP_1_0 &CLUSTER_SLEEP_1>; + }; + + idle-states { + CPU_SLEEP_0_0: cpu-sleep-0-0 { + compatible = "arm,idle-state"; + local-timer-stop; + entry-latency-us = <200>; + exit-latency-us = <100>; + min-residency-us = <400>; + wakeup-latency-us = <250>; + }; + + CLUSTER_SLEEP_0: cluster-sleep-0 { + compatible = "arm,idle-state"; + local-timer-stop; + entry-latency-us = <500>; + exit-latency-us = <1500>; + min-residency-us = <2500>; + wakeup-latency-us = <1700>; + }; + + CPU_SLEEP_1_0: cpu-sleep-1-0 { + compatible = "arm,idle-state"; + local-timer-stop; + entry-latency-us = <300>; + exit-latency-us = <500>; + min-residency-us = <900>; + wakeup-latency-us = <600>; + }; + + CLUSTER_SLEEP_1: cluster-sleep-1 { + compatible = "arm,idle-state"; + local-timer-stop; + entry-latency-us = <800>; + exit-latency-us = <2000>; + min-residency-us = <6500>; + wakeup-latency-us = <2300>; + }; + }; + +}; + +=========================================== +5 - References +=========================================== + +[1] ARM Linux Kernel documentation - CPUs bindings + Documentation/devicetree/bindings/arm/cpus.txt + +[2] ARM Linux Kernel documentation - PSCI bindings + Documentation/devicetree/bindings/arm/psci.txt + +[3] ARM Server Base System Architecture (SBSA) + http://infocenter.arm.com/help/index.jsp + +[4] ARM Architecture Reference Manuals + http://infocenter.arm.com/help/index.jsp + +[5] ePAPR standard + https://www.power.org/documentation/epapr-version-1-1/ diff --git a/Documentation/devicetree/bindings/arm/psci.txt b/Documentation/devicetree/bindings/arm/psci.txt index b4a58f39223c..5aa40ede0e99 100644 --- a/Documentation/devicetree/bindings/arm/psci.txt +++ b/Documentation/devicetree/bindings/arm/psci.txt @@ -50,6 +50,16 @@ Main node optional properties: - migrate : Function ID for MIGRATE operation +Device tree nodes that require usage of PSCI CPU_SUSPEND function (ie idle +state nodes, as per bindings in [1]) must specify the following properties: + +- arm,psci-suspend-param + Usage: Required for state nodes[1] if the corresponding + idle-states node entry-method property is set + to "psci". + Value type: <u32> + Definition: power_state parameter to pass to the PSCI + suspend call. Example: @@ -64,7 +74,6 @@ Case 1: PSCI v0.1 only. migrate = <0x95c10003>; }; - Case 2: PSCI v0.2 only psci { @@ -88,3 +97,6 @@ Case 3: PSCI v0.2 and PSCI v0.1. ... }; + +[1] Kernel documentation - ARM idle states bindings + Documentation/devicetree/bindings/arm/idle-states.txt diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h index d7b4b38a8e86..47dfa31ad71a 100644 --- a/arch/arm64/include/asm/cpu_ops.h +++ b/arch/arm64/include/asm/cpu_ops.h @@ -28,6 +28,8 @@ struct device_node; * enable-method property. * @cpu_init: Reads any data necessary for a specific enable-method from the * devicetree, for a given cpu node and proposed logical id. + * @cpu_init_idle: Reads any data necessary to initialize CPU idle states from + * devicetree, for a given cpu node and proposed logical id. * @cpu_prepare: Early one-time preparation step for a cpu. If there is a * mechanism for doing so, tests whether it is possible to boot * the given CPU. @@ -47,6 +49,7 @@ struct device_node; struct cpu_operations { const char *name; int (*cpu_init)(struct device_node *, unsigned int); + int (*cpu_init_idle)(struct device_node *, unsigned int); int (*cpu_prepare)(unsigned int); int (*cpu_boot)(unsigned int); void (*cpu_postboot)(void); diff --git a/arch/arm64/include/asm/cpuidle.h b/arch/arm64/include/asm/cpuidle.h new file mode 100644 index 000000000000..b52a9932e2b1 --- /dev/null +++ b/arch/arm64/include/asm/cpuidle.h @@ -0,0 +1,13 @@ +#ifndef __ASM_CPUIDLE_H +#define __ASM_CPUIDLE_H + +#ifdef CONFIG_CPU_IDLE +extern int cpu_init_idle(unsigned int cpu); +#else +static inline int cpu_init_idle(unsigned int cpu) +{ + return -EOPNOTSUPP; +} +#endif + +#endif diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h index e9c149c042e0..456d67c1f0fa 100644 --- a/arch/arm64/include/asm/suspend.h +++ b/arch/arm64/include/asm/suspend.h @@ -21,6 +21,7 @@ struct sleep_save_sp { phys_addr_t save_ptr_stash_phys; }; +extern int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long)); extern void cpu_resume(void); extern int cpu_suspend(unsigned long); diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index df7ef8768fc2..6e9538c2d28a 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -26,6 +26,7 @@ arm64-obj-$(CONFIG_PERF_EVENTS) += perf_regs.o arm64-obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o arm64-obj-$(CONFIG_ARM64_CPU_SUSPEND) += sleep.o suspend.o +arm64-obj-$(CONFIG_CPU_IDLE) += cpuidle.o arm64-obj-$(CONFIG_JUMP_LABEL) += jump_label.o arm64-obj-$(CONFIG_KGDB) += kgdb.o arm64-obj-$(CONFIG_EFI) += efi.o efi-stub.o efi-entry.o diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c new file mode 100644 index 000000000000..19d17f51db37 --- /dev/null +++ b/arch/arm64/kernel/cpuidle.c @@ -0,0 +1,31 @@ +/* + * ARM64 CPU idle arch support + * + * Copyright (C) 2014 ARM Ltd. + * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/of.h> +#include <linux/of_device.h> + +#include <asm/cpuidle.h> +#include <asm/cpu_ops.h> + +int cpu_init_idle(unsigned int cpu) +{ + int ret = -EOPNOTSUPP; + struct device_node *cpu_node = of_cpu_device_node_get(cpu); + + if (!cpu_node) + return -ENODEV; + + if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_init_idle) + ret = cpu_ops[cpu]->cpu_init_idle(cpu_node, cpu); + + of_node_put(cpu_node); + return ret; +} diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c index 553954771a67..866c1c821860 100644 --- a/arch/arm64/kernel/psci.c +++ b/arch/arm64/kernel/psci.c @@ -21,6 +21,7 @@ #include <linux/reboot.h> #include <linux/pm.h> #include <linux/delay.h> +#include <linux/slab.h> #include <uapi/linux/psci.h> #include <asm/compiler.h> @@ -28,6 +29,7 @@ #include <asm/errno.h> #include <asm/psci.h> #include <asm/smp_plat.h> +#include <asm/suspend.h> #include <asm/system_misc.h> #define PSCI_POWER_STATE_TYPE_STANDBY 0 @@ -65,6 +67,8 @@ enum psci_function { PSCI_FN_MAX, }; +static DEFINE_PER_CPU_READ_MOSTLY(struct psci_power_state *, psci_power_state); + static u32 psci_function_id[PSCI_FN_MAX]; static int psci_to_linux_errno(int errno) @@ -93,6 +97,18 @@ static u32 psci_power_state_pack(struct psci_power_state state) & PSCI_0_2_POWER_STATE_AFFL_MASK); } +static void psci_power_state_unpack(u32 power_state, + struct psci_power_state *state) +{ + state->id = (power_state & PSCI_0_2_POWER_STATE_ID_MASK) >> + PSCI_0_2_POWER_STATE_ID_SHIFT; + state->type = (power_state & PSCI_0_2_POWER_STATE_TYPE_MASK) >> + PSCI_0_2_POWER_STATE_TYPE_SHIFT; + state->affinity_level = + (power_state & PSCI_0_2_POWER_STATE_AFFL_MASK) >> + PSCI_0_2_POWER_STATE_AFFL_SHIFT; +} + /* * The following two functions are invoked via the invoke_psci_fn pointer * and will not be inlined, allowing us to piggyback on the AAPCS. @@ -199,6 +215,63 @@ static int psci_migrate_info_type(void) return err; } +static int __maybe_unused cpu_psci_cpu_init_idle(struct device_node *cpu_node, + unsigned int cpu) +{ + int i, ret, count = 0; + struct psci_power_state *psci_states; + struct device_node *state_node; + + /* + * If the PSCI cpu_suspend function hook has not been initialized + * idle states must not be enabled, so bail out + */ + if (!psci_ops.cpu_suspend) + return -EOPNOTSUPP; + + /* Count idle states */ + while ((state_node = of_parse_phandle(cpu_node, "cpu-idle-states", + count))) { + count++; + of_node_put(state_node); + } + + if (!count) + return -ENODEV; + + psci_states = kcalloc(count, sizeof(*psci_states), GFP_KERNEL); + if (!psci_states) + return -ENOMEM; + + for (i = 0; i < count; i++) { + u32 psci_power_state; + + state_node = of_parse_phandle(cpu_node, "cpu-idle-states", i); + + ret = of_property_read_u32(state_node, + "arm,psci-suspend-param", + &psci_power_state); + if (ret) { + pr_warn(" * %s missing arm,psci-suspend-param property\n", + state_node->full_name); + of_node_put(state_node); + goto free_mem; + } + + of_node_put(state_node); + pr_debug("psci-power-state %#x index %d\n", psci_power_state, + i); + psci_power_state_unpack(psci_power_state, &psci_states[i]); + } + /* Idle states parsed correctly, initialize per-cpu pointer */ + per_cpu(psci_power_state, cpu) = psci_states; + return 0; + +free_mem: + kfree(psci_states); + return ret; +} + static int get_set_conduit_method(struct device_node *np) { const char *method; @@ -436,8 +509,39 @@ static int cpu_psci_cpu_kill(unsigned int cpu) #endif #endif +static int psci_suspend_finisher(unsigned long index) +{ + struct psci_power_state *state = __get_cpu_var(psci_power_state); + + return psci_ops.cpu_suspend(state[index - 1], + virt_to_phys(cpu_resume)); +} + +static int __maybe_unused cpu_psci_cpu_suspend(unsigned long index) +{ + int ret; + struct psci_power_state *state = __get_cpu_var(psci_power_state); + /* + * idle state index 0 corresponds to wfi, should never be called + * from the cpu_suspend operations + */ + if (WARN_ON_ONCE(!index)) + return -EINVAL; + + if (state->type == PSCI_POWER_STATE_TYPE_STANDBY) + ret = psci_ops.cpu_suspend(state[index - 1], 0); + else + ret = __cpu_suspend(index, psci_suspend_finisher); + + return ret; +} + const struct cpu_operations cpu_psci_ops = { .name = "psci", +#ifdef CONFIG_CPU_IDLE + .cpu_init_idle = cpu_psci_cpu_init_idle, + .cpu_suspend = cpu_psci_cpu_suspend, +#endif #ifdef CONFIG_SMP .cpu_init = cpu_psci_cpu_init, .cpu_prepare = cpu_psci_cpu_prepare, diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index b1925729c692..a564b440416a 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -49,28 +49,39 @@ orr \dst, \dst, \mask // dst|=(aff3>>rs3) .endm /* - * Save CPU state for a suspend. This saves callee registers, and allocates - * space on the kernel stack to save the CPU specific registers + some - * other data for resume. + * Save CPU state for a suspend and execute the suspend finisher. + * On success it will return 0 through cpu_resume - ie through a CPU + * soft/hard reboot from the reset vector. + * On failure it returns the suspend finisher return value or force + * -EOPNOTSUPP if the finisher erroneously returns 0 (the suspend finisher + * is not allowed to return, if it does this must be considered failure). + * It saves callee registers, and allocates space on the kernel stack + * to save the CPU specific registers + some other data for resume. * * x0 = suspend finisher argument + * x1 = suspend finisher function pointer */ -ENTRY(__cpu_suspend) +ENTRY(__cpu_suspend_enter) stp x29, lr, [sp, #-96]! stp x19, x20, [sp,#16] stp x21, x22, [sp,#32] stp x23, x24, [sp,#48] stp x25, x26, [sp,#64] stp x27, x28, [sp,#80] + /* + * Stash suspend finisher and its argument in x20 and x19 + */ + mov x19, x0 + mov x20, x1 mov x2, sp sub sp, sp, #CPU_SUSPEND_SZ // allocate cpu_suspend_ctx - mov x1, sp + mov x0, sp /* - * x1 now points to struct cpu_suspend_ctx allocated on the stack + * x0 now points to struct cpu_suspend_ctx allocated on the stack */ - str x2, [x1, #CPU_CTX_SP] - ldr x2, =sleep_save_sp - ldr x2, [x2, #SLEEP_SAVE_SP_VIRT] + str x2, [x0, #CPU_CTX_SP] + ldr x1, =sleep_save_sp + ldr x1, [x1, #SLEEP_SAVE_SP_VIRT] #ifdef CONFIG_SMP mrs x7, mpidr_el1 ldr x9, =mpidr_hash @@ -82,11 +93,21 @@ ENTRY(__cpu_suspend) ldp w3, w4, [x9, #MPIDR_HASH_SHIFTS] ldp w5, w6, [x9, #(MPIDR_HASH_SHIFTS + 8)] compute_mpidr_hash x8, x3, x4, x5, x6, x7, x10 - add x2, x2, x8, lsl #3 + add x1, x1, x8, lsl #3 #endif - bl __cpu_suspend_finisher + bl __cpu_suspend_save + /* + * Grab suspend finisher in x20 and its argument in x19 + */ + mov x0, x19 + mov x1, x20 + /* + * We are ready for power down, fire off the suspend finisher + * in x1, with argument in x0 + */ + blr x1 /* - * Never gets here, unless suspend fails. + * Never gets here, unless suspend finisher fails. * Successful cpu_suspend should return from cpu_resume, returning * through this code path is considered an error * If the return value is set to 0 force x0 = -EOPNOTSUPP @@ -103,7 +124,7 @@ ENTRY(__cpu_suspend) ldp x27, x28, [sp, #80] ldp x29, lr, [sp], #96 ret -ENDPROC(__cpu_suspend) +ENDPROC(__cpu_suspend_enter) .ltorg /* diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 55a99b9a97e0..13ad4dbb1615 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -9,22 +9,19 @@ #include <asm/suspend.h> #include <asm/tlbflush.h> -extern int __cpu_suspend(unsigned long); +extern int __cpu_suspend_enter(unsigned long arg, int (*fn)(unsigned long)); /* - * This is called by __cpu_suspend() to save the state, and do whatever + * This is called by __cpu_suspend_enter() to save the state, and do whatever * flushing is required to ensure that when the CPU goes to sleep we have * the necessary data available when the caches are not searched. * - * @arg: Argument to pass to suspend operations - * @ptr: CPU context virtual address - * @save_ptr: address of the location where the context physical address - * must be saved + * ptr: CPU context virtual address + * save_ptr: address of the location where the context physical address + * must be saved */ -int __cpu_suspend_finisher(unsigned long arg, struct cpu_suspend_ctx *ptr, - phys_addr_t *save_ptr) +void notrace __cpu_suspend_save(struct cpu_suspend_ctx *ptr, + phys_addr_t *save_ptr) { - int cpu = smp_processor_id(); - *save_ptr = virt_to_phys(ptr); cpu_do_suspend(ptr); @@ -35,8 +32,6 @@ int __cpu_suspend_finisher(unsigned long arg, struct cpu_suspend_ctx *ptr, */ __flush_dcache_area(ptr, sizeof(*ptr)); __flush_dcache_area(save_ptr, sizeof(*save_ptr)); - - return cpu_ops[cpu]->cpu_suspend(arg); } /* @@ -56,15 +51,15 @@ void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *)) } /** - * cpu_suspend + * cpu_suspend() - function to enter a low-power state + * @arg: argument to pass to CPU suspend operations * - * @arg: argument to pass to the finisher function + * Return: 0 on success, -EOPNOTSUPP if CPU suspend hook not initialized, CPU + * operations back-end error code otherwise. */ int cpu_suspend(unsigned long arg) { - struct mm_struct *mm = current->active_mm; - int ret, cpu = smp_processor_id(); - unsigned long flags; + int cpu = smp_processor_id(); /* * If cpu_ops have not been registered or suspend @@ -72,6 +67,21 @@ int cpu_suspend(unsigned long arg) */ if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_suspend) return -EOPNOTSUPP; + return cpu_ops[cpu]->cpu_suspend(arg); +} + +/* + * __cpu_suspend + * + * arg: argument to pass to the finisher function + * fn: finisher function pointer + * + */ +int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) +{ + struct mm_struct *mm = current->active_mm; + int ret; + unsigned long flags; /* * From this point debug exceptions are disabled to prevent @@ -86,7 +96,7 @@ int cpu_suspend(unsigned long arg) * page tables, so that the thread address space is properly * set-up on function return. */ - ret = __cpu_suspend(arg); + ret = __cpu_suspend_enter(arg, fn); if (ret == 0) { cpu_switch_mm(mm->pgd, mm); flush_tlb_all(); @@ -95,7 +105,7 @@ int cpu_suspend(unsigned long arg) * Restore per-cpu offset before any kernel * subsystem relying on it has a chance to run. */ - set_my_cpu_offset(per_cpu_offset(cpu)); + set_my_cpu_offset(per_cpu_offset(smp_processor_id())); /* * Restore HW breakpoint registers to sane values |