diff options
Diffstat (limited to 'drivers/cpuidle')
25 files changed, 3856 insertions, 457 deletions
diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig index 7dbc4a83c45..1b96fb91d32 100644 --- a/drivers/cpuidle/Kconfig +++ b/drivers/cpuidle/Kconfig @@ -1,7 +1,10 @@ +menu "CPU Idle" config CPU_IDLE bool "CPU idle PM support" - default ACPI + default y if ACPI || PPC_PSERIES + select CPU_IDLE_GOV_LADDER if (!NO_HZ && !NO_HZ_IDLE) + select CPU_IDLE_GOV_MENU if (NO_HZ || NO_HZ_IDLE) help CPU idle is a generic framework for supporting software-controlled idle processor power management. It includes modular cross-platform @@ -9,12 +12,41 @@ config CPU_IDLE If you're using an ACPI-enabled platform, you should say Y here. +if CPU_IDLE + +config CPU_IDLE_MULTIPLE_DRIVERS + bool "Support multiple cpuidle drivers" + default n + help + Allows the cpuidle framework to use different drivers for each CPU. + This is useful if you have a system with different CPU latencies and + states. If unsure say N. + config CPU_IDLE_GOV_LADDER - bool - depends on CPU_IDLE + bool "Ladder governor (for periodic timer tick)" default y config CPU_IDLE_GOV_MENU - bool - depends on CPU_IDLE && NO_HZ + bool "Menu governor (for tickless system)" default y + +menu "ARM CPU Idle Drivers" +depends on ARM +source "drivers/cpuidle/Kconfig.arm" +endmenu + +menu "MIPS CPU Idle Drivers" +depends on MIPS +source "drivers/cpuidle/Kconfig.mips" +endmenu + +menu "POWERPC CPU Idle Drivers" +depends on PPC +source "drivers/cpuidle/Kconfig.powerpc" +endmenu + +endif + +config ARCH_NEEDS_CPU_IDLE_COUPLED + def_bool n +endmenu diff --git a/drivers/cpuidle/Kconfig.arm b/drivers/cpuidle/Kconfig.arm new file mode 100644 index 00000000000..b6d69e899f5 --- /dev/null +++ b/drivers/cpuidle/Kconfig.arm @@ -0,0 +1,63 @@ +# +# ARM CPU Idle drivers +# +config ARM_ARMADA_370_XP_CPUIDLE + bool "CPU Idle Driver for Armada 370/XP family processors" + depends on ARCH_MVEBU + help + Select this to enable cpuidle on Armada 370/XP processors. + +config ARM_BIG_LITTLE_CPUIDLE + bool "Support for ARM big.LITTLE processors" + depends on ARCH_VEXPRESS_TC2_PM + select ARM_CPU_SUSPEND + select CPU_IDLE_MULTIPLE_DRIVERS + help + Select this option to enable CPU idle driver for big.LITTLE based + ARM systems. Driver manages CPUs coordination through MCPM and + define different C-states for little and big cores through the + multiple CPU idle drivers infrastructure. + +config ARM_CLPS711X_CPUIDLE + bool "CPU Idle Driver for CLPS711X processors" + depends on ARCH_CLPS711X || COMPILE_TEST + help + Select this to enable cpuidle on Cirrus Logic CLPS711X SOCs. + +config ARM_HIGHBANK_CPUIDLE + bool "CPU Idle Driver for Calxeda processors" + depends on ARM_PSCI + select ARM_CPU_SUSPEND + help + Select this to enable cpuidle on Calxeda processors. + +config ARM_KIRKWOOD_CPUIDLE + bool "CPU Idle Driver for Marvell Kirkwood SoCs" + depends on ARCH_KIRKWOOD || MACH_KIRKWOOD + help + This adds the CPU Idle driver for Marvell Kirkwood SoCs. + +config ARM_ZYNQ_CPUIDLE + bool "CPU Idle Driver for Xilinx Zynq processors" + depends on ARCH_ZYNQ + help + Select this to enable cpuidle on Xilinx Zynq processors. + +config ARM_U8500_CPUIDLE + bool "Cpu Idle Driver for the ST-E u8500 processors" + depends on ARCH_U8500 + help + Select this to enable cpuidle for ST-E u8500 processors + +config ARM_AT91_CPUIDLE + bool "Cpu Idle Driver for the AT91 processors" + default y + depends on ARCH_AT91 + help + Select this to enable cpuidle for AT91 processors + +config ARM_EXYNOS_CPUIDLE + bool "Cpu Idle Driver for the Exynos processors" + depends on ARCH_EXYNOS + help + Select this to enable cpuidle for Exynos processors diff --git a/drivers/cpuidle/Kconfig.mips b/drivers/cpuidle/Kconfig.mips new file mode 100644 index 00000000000..0e70ee28a5c --- /dev/null +++ b/drivers/cpuidle/Kconfig.mips @@ -0,0 +1,17 @@ +# +# MIPS CPU Idle Drivers +# +config MIPS_CPS_CPUIDLE + bool "CPU Idle driver for MIPS CPS platforms" + depends on CPU_IDLE + depends on SYS_SUPPORTS_MIPS_CPS + select ARCH_NEEDS_CPU_IDLE_COUPLED if MIPS_MT + select GENERIC_CLOCKEVENTS_BROADCAST if SMP + select MIPS_CPS_PM + default y + help + Select this option to enable processor idle state management + through cpuidle for systems built around the MIPS Coherent + Processing System (CPS) architecture. In order to make use of + the deepest idle states you will need to ensure that you are + also using the CONFIG_MIPS_CPS SMP implementation. diff --git a/drivers/cpuidle/Kconfig.powerpc b/drivers/cpuidle/Kconfig.powerpc new file mode 100644 index 00000000000..66c3a09574e --- /dev/null +++ b/drivers/cpuidle/Kconfig.powerpc @@ -0,0 +1,20 @@ +# +# POWERPC CPU Idle Drivers +# +config PSERIES_CPUIDLE + bool "Cpuidle driver for pSeries platforms" + depends on CPU_IDLE + depends on PPC_PSERIES + default y + help + Select this option to enable processor idle state management + through cpuidle subsystem. + +config POWERNV_CPUIDLE + bool "Cpuidle driver for powernv platforms" + depends on CPU_IDLE + depends on PPC_POWERNV + default y + help + Select this option to enable processor idle state management + through cpuidle subsystem. diff --git a/drivers/cpuidle/Makefile b/drivers/cpuidle/Makefile index 5634f88379d..d8bb1ff7256 100644 --- a/drivers/cpuidle/Makefile +++ b/drivers/cpuidle/Makefile @@ -3,3 +3,25 @@ # obj-y += cpuidle.o driver.o governor.o sysfs.o governors/ +obj-$(CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED) += coupled.o + +################################################################################## +# ARM SoC drivers +obj-$(CONFIG_ARM_ARMADA_370_XP_CPUIDLE) += cpuidle-armada-370-xp.o +obj-$(CONFIG_ARM_BIG_LITTLE_CPUIDLE) += cpuidle-big_little.o +obj-$(CONFIG_ARM_CLPS711X_CPUIDLE) += cpuidle-clps711x.o +obj-$(CONFIG_ARM_HIGHBANK_CPUIDLE) += cpuidle-calxeda.o +obj-$(CONFIG_ARM_KIRKWOOD_CPUIDLE) += cpuidle-kirkwood.o +obj-$(CONFIG_ARM_ZYNQ_CPUIDLE) += cpuidle-zynq.o +obj-$(CONFIG_ARM_U8500_CPUIDLE) += cpuidle-ux500.o +obj-$(CONFIG_ARM_AT91_CPUIDLE) += cpuidle-at91.o +obj-$(CONFIG_ARM_EXYNOS_CPUIDLE) += cpuidle-exynos.o + +############################################################################### +# MIPS drivers +obj-$(CONFIG_MIPS_CPS_CPUIDLE) += cpuidle-cps.o + +############################################################################### +# POWERPC drivers +obj-$(CONFIG_PSERIES_CPUIDLE) += cpuidle-pseries.o +obj-$(CONFIG_POWERNV_CPUIDLE) += cpuidle-powernv.o diff --git a/drivers/cpuidle/coupled.c b/drivers/cpuidle/coupled.c new file mode 100644 index 00000000000..73fe2f8d7f9 --- /dev/null +++ b/drivers/cpuidle/coupled.c @@ -0,0 +1,794 @@ +/* + * coupled.c - helper functions to enter the same idle state on multiple cpus + * + * Copyright (c) 2011 Google, Inc. + * + * Author: Colin Cross <ccross@android.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include <linux/kernel.h> +#include <linux/cpu.h> +#include <linux/cpuidle.h> +#include <linux/mutex.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/spinlock.h> + +#include "cpuidle.h" + +/** + * DOC: Coupled cpuidle states + * + * On some ARM SMP SoCs (OMAP4460, Tegra 2, and probably more), the + * cpus cannot be independently powered down, either due to + * sequencing restrictions (on Tegra 2, cpu 0 must be the last to + * power down), or due to HW bugs (on OMAP4460, a cpu powering up + * will corrupt the gic state unless the other cpu runs a work + * around). Each cpu has a power state that it can enter without + * coordinating with the other cpu (usually Wait For Interrupt, or + * WFI), and one or more "coupled" power states that affect blocks + * shared between the cpus (L2 cache, interrupt controller, and + * sometimes the whole SoC). Entering a coupled power state must + * be tightly controlled on both cpus. + * + * This file implements a solution, where each cpu will wait in the + * WFI state until all cpus are ready to enter a coupled state, at + * which point the coupled state function will be called on all + * cpus at approximately the same time. + * + * Once all cpus are ready to enter idle, they are woken by an smp + * cross call. At this point, there is a chance that one of the + * cpus will find work to do, and choose not to enter idle. A + * final pass is needed to guarantee that all cpus will call the + * power state enter function at the same time. During this pass, + * each cpu will increment the ready counter, and continue once the + * ready counter matches the number of online coupled cpus. If any + * cpu exits idle, the other cpus will decrement their counter and + * retry. + * + * requested_state stores the deepest coupled idle state each cpu + * is ready for. It is assumed that the states are indexed from + * shallowest (highest power, lowest exit latency) to deepest + * (lowest power, highest exit latency). The requested_state + * variable is not locked. It is only written from the cpu that + * it stores (or by the on/offlining cpu if that cpu is offline), + * and only read after all the cpus are ready for the coupled idle + * state are are no longer updating it. + * + * Three atomic counters are used. alive_count tracks the number + * of cpus in the coupled set that are currently or soon will be + * online. waiting_count tracks the number of cpus that are in + * the waiting loop, in the ready loop, or in the coupled idle state. + * ready_count tracks the number of cpus that are in the ready loop + * or in the coupled idle state. + * + * To use coupled cpuidle states, a cpuidle driver must: + * + * Set struct cpuidle_device.coupled_cpus to the mask of all + * coupled cpus, usually the same as cpu_possible_mask if all cpus + * are part of the same cluster. The coupled_cpus mask must be + * set in the struct cpuidle_device for each cpu. + * + * Set struct cpuidle_device.safe_state to a state that is not a + * coupled state. This is usually WFI. + * + * Set CPUIDLE_FLAG_COUPLED in struct cpuidle_state.flags for each + * state that affects multiple cpus. + * + * Provide a struct cpuidle_state.enter function for each state + * that affects multiple cpus. This function is guaranteed to be + * called on all cpus at approximately the same time. The driver + * should ensure that the cpus all abort together if any cpu tries + * to abort once the function is called. The function should return + * with interrupts still disabled. + */ + +/** + * struct cpuidle_coupled - data for set of cpus that share a coupled idle state + * @coupled_cpus: mask of cpus that are part of the coupled set + * @requested_state: array of requested states for cpus in the coupled set + * @ready_waiting_counts: combined count of cpus in ready or waiting loops + * @online_count: count of cpus that are online + * @refcnt: reference count of cpuidle devices that are using this struct + * @prevent: flag to prevent coupled idle while a cpu is hotplugging + */ +struct cpuidle_coupled { + cpumask_t coupled_cpus; + int requested_state[NR_CPUS]; + atomic_t ready_waiting_counts; + atomic_t abort_barrier; + int online_count; + int refcnt; + int prevent; +}; + +#define WAITING_BITS 16 +#define MAX_WAITING_CPUS (1 << WAITING_BITS) +#define WAITING_MASK (MAX_WAITING_CPUS - 1) +#define READY_MASK (~WAITING_MASK) + +#define CPUIDLE_COUPLED_NOT_IDLE (-1) + +static DEFINE_MUTEX(cpuidle_coupled_lock); +static DEFINE_PER_CPU(struct call_single_data, cpuidle_coupled_poke_cb); + +/* + * The cpuidle_coupled_poke_pending mask is used to avoid calling + * __smp_call_function_single with the per cpu call_single_data struct already + * in use. This prevents a deadlock where two cpus are waiting for each others + * call_single_data struct to be available + */ +static cpumask_t cpuidle_coupled_poke_pending; + +/* + * The cpuidle_coupled_poked mask is used to ensure that each cpu has been poked + * once to minimize entering the ready loop with a poke pending, which would + * require aborting and retrying. + */ +static cpumask_t cpuidle_coupled_poked; + +/** + * cpuidle_coupled_parallel_barrier - synchronize all online coupled cpus + * @dev: cpuidle_device of the calling cpu + * @a: atomic variable to hold the barrier + * + * No caller to this function will return from this function until all online + * cpus in the same coupled group have called this function. Once any caller + * has returned from this function, the barrier is immediately available for + * reuse. + * + * The atomic variable must be initialized to 0 before any cpu calls + * this function, will be reset to 0 before any cpu returns from this function. + * + * Must only be called from within a coupled idle state handler + * (state.enter when state.flags has CPUIDLE_FLAG_COUPLED set). + * + * Provides full smp barrier semantics before and after calling. + */ +void cpuidle_coupled_parallel_barrier(struct cpuidle_device *dev, atomic_t *a) +{ + int n = dev->coupled->online_count; + + smp_mb__before_atomic(); + atomic_inc(a); + + while (atomic_read(a) < n) + cpu_relax(); + + if (atomic_inc_return(a) == n * 2) { + atomic_set(a, 0); + return; + } + + while (atomic_read(a) > n) + cpu_relax(); +} + +/** + * cpuidle_state_is_coupled - check if a state is part of a coupled set + * @dev: struct cpuidle_device for the current cpu + * @drv: struct cpuidle_driver for the platform + * @state: index of the target state in drv->states + * + * Returns true if the target state is coupled with cpus besides this one + */ +bool cpuidle_state_is_coupled(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int state) +{ + return drv->states[state].flags & CPUIDLE_FLAG_COUPLED; +} + +/** + * cpuidle_coupled_set_ready - mark a cpu as ready + * @coupled: the struct coupled that contains the current cpu + */ +static inline void cpuidle_coupled_set_ready(struct cpuidle_coupled *coupled) +{ + atomic_add(MAX_WAITING_CPUS, &coupled->ready_waiting_counts); +} + +/** + * cpuidle_coupled_set_not_ready - mark a cpu as not ready + * @coupled: the struct coupled that contains the current cpu + * + * Decrements the ready counter, unless the ready (and thus the waiting) counter + * is equal to the number of online cpus. Prevents a race where one cpu + * decrements the waiting counter and then re-increments it just before another + * cpu has decremented its ready counter, leading to the ready counter going + * down from the number of online cpus without going through the coupled idle + * state. + * + * Returns 0 if the counter was decremented successfully, -EINVAL if the ready + * counter was equal to the number of online cpus. + */ +static +inline int cpuidle_coupled_set_not_ready(struct cpuidle_coupled *coupled) +{ + int all; + int ret; + + all = coupled->online_count | (coupled->online_count << WAITING_BITS); + ret = atomic_add_unless(&coupled->ready_waiting_counts, + -MAX_WAITING_CPUS, all); + + return ret ? 0 : -EINVAL; +} + +/** + * cpuidle_coupled_no_cpus_ready - check if no cpus in a coupled set are ready + * @coupled: the struct coupled that contains the current cpu + * + * Returns true if all of the cpus in a coupled set are out of the ready loop. + */ +static inline int cpuidle_coupled_no_cpus_ready(struct cpuidle_coupled *coupled) +{ + int r = atomic_read(&coupled->ready_waiting_counts) >> WAITING_BITS; + return r == 0; +} + +/** + * cpuidle_coupled_cpus_ready - check if all cpus in a coupled set are ready + * @coupled: the struct coupled that contains the current cpu + * + * Returns true if all cpus coupled to this target state are in the ready loop + */ +static inline bool cpuidle_coupled_cpus_ready(struct cpuidle_coupled *coupled) +{ + int r = atomic_read(&coupled->ready_waiting_counts) >> WAITING_BITS; + return r == coupled->online_count; +} + +/** + * cpuidle_coupled_cpus_waiting - check if all cpus in a coupled set are waiting + * @coupled: the struct coupled that contains the current cpu + * + * Returns true if all cpus coupled to this target state are in the wait loop + */ +static inline bool cpuidle_coupled_cpus_waiting(struct cpuidle_coupled *coupled) +{ + int w = atomic_read(&coupled->ready_waiting_counts) & WAITING_MASK; + return w == coupled->online_count; +} + +/** + * cpuidle_coupled_no_cpus_waiting - check if no cpus in coupled set are waiting + * @coupled: the struct coupled that contains the current cpu + * + * Returns true if all of the cpus in a coupled set are out of the waiting loop. + */ +static inline int cpuidle_coupled_no_cpus_waiting(struct cpuidle_coupled *coupled) +{ + int w = atomic_read(&coupled->ready_waiting_counts) & WAITING_MASK; + return w == 0; +} + +/** + * cpuidle_coupled_get_state - determine the deepest idle state + * @dev: struct cpuidle_device for this cpu + * @coupled: the struct coupled that contains the current cpu + * + * Returns the deepest idle state that all coupled cpus can enter + */ +static inline int cpuidle_coupled_get_state(struct cpuidle_device *dev, + struct cpuidle_coupled *coupled) +{ + int i; + int state = INT_MAX; + + /* + * Read barrier ensures that read of requested_state is ordered after + * reads of ready_count. Matches the write barriers + * cpuidle_set_state_waiting. + */ + smp_rmb(); + + for_each_cpu_mask(i, coupled->coupled_cpus) + if (cpu_online(i) && coupled->requested_state[i] < state) + state = coupled->requested_state[i]; + + return state; +} + +static void cpuidle_coupled_handle_poke(void *info) +{ + int cpu = (unsigned long)info; + cpumask_set_cpu(cpu, &cpuidle_coupled_poked); + cpumask_clear_cpu(cpu, &cpuidle_coupled_poke_pending); +} + +/** + * cpuidle_coupled_poke - wake up a cpu that may be waiting + * @cpu: target cpu + * + * Ensures that the target cpu exits it's waiting idle state (if it is in it) + * and will see updates to waiting_count before it re-enters it's waiting idle + * state. + * + * If cpuidle_coupled_poked_mask is already set for the target cpu, that cpu + * either has or will soon have a pending IPI that will wake it out of idle, + * or it is currently processing the IPI and is not in idle. + */ +static void cpuidle_coupled_poke(int cpu) +{ + struct call_single_data *csd = &per_cpu(cpuidle_coupled_poke_cb, cpu); + + if (!cpumask_test_and_set_cpu(cpu, &cpuidle_coupled_poke_pending)) + smp_call_function_single_async(cpu, csd); +} + +/** + * cpuidle_coupled_poke_others - wake up all other cpus that may be waiting + * @dev: struct cpuidle_device for this cpu + * @coupled: the struct coupled that contains the current cpu + * + * Calls cpuidle_coupled_poke on all other online cpus. + */ +static void cpuidle_coupled_poke_others(int this_cpu, + struct cpuidle_coupled *coupled) +{ + int cpu; + + for_each_cpu_mask(cpu, coupled->coupled_cpus) + if (cpu != this_cpu && cpu_online(cpu)) + cpuidle_coupled_poke(cpu); +} + +/** + * cpuidle_coupled_set_waiting - mark this cpu as in the wait loop + * @dev: struct cpuidle_device for this cpu + * @coupled: the struct coupled that contains the current cpu + * @next_state: the index in drv->states of the requested state for this cpu + * + * Updates the requested idle state for the specified cpuidle device. + * Returns the number of waiting cpus. + */ +static int cpuidle_coupled_set_waiting(int cpu, + struct cpuidle_coupled *coupled, int next_state) +{ + coupled->requested_state[cpu] = next_state; + + /* + * The atomic_inc_return provides a write barrier to order the write + * to requested_state with the later write that increments ready_count. + */ + return atomic_inc_return(&coupled->ready_waiting_counts) & WAITING_MASK; +} + +/** + * cpuidle_coupled_set_not_waiting - mark this cpu as leaving the wait loop + * @dev: struct cpuidle_device for this cpu + * @coupled: the struct coupled that contains the current cpu + * + * Removes the requested idle state for the specified cpuidle device. + */ +static void cpuidle_coupled_set_not_waiting(int cpu, + struct cpuidle_coupled *coupled) +{ + /* + * Decrementing waiting count can race with incrementing it in + * cpuidle_coupled_set_waiting, but that's OK. Worst case, some + * cpus will increment ready_count and then spin until they + * notice that this cpu has cleared it's requested_state. + */ + atomic_dec(&coupled->ready_waiting_counts); + + coupled->requested_state[cpu] = CPUIDLE_COUPLED_NOT_IDLE; +} + +/** + * cpuidle_coupled_set_done - mark this cpu as leaving the ready loop + * @cpu: the current cpu + * @coupled: the struct coupled that contains the current cpu + * + * Marks this cpu as no longer in the ready and waiting loops. Decrements + * the waiting count first to prevent another cpu looping back in and seeing + * this cpu as waiting just before it exits idle. + */ +static void cpuidle_coupled_set_done(int cpu, struct cpuidle_coupled *coupled) +{ + cpuidle_coupled_set_not_waiting(cpu, coupled); + atomic_sub(MAX_WAITING_CPUS, &coupled->ready_waiting_counts); +} + +/** + * cpuidle_coupled_clear_pokes - spin until the poke interrupt is processed + * @cpu - this cpu + * + * Turns on interrupts and spins until any outstanding poke interrupts have + * been processed and the poke bit has been cleared. + * + * Other interrupts may also be processed while interrupts are enabled, so + * need_resched() must be tested after this function returns to make sure + * the interrupt didn't schedule work that should take the cpu out of idle. + * + * Returns 0 if no poke was pending, 1 if a poke was cleared. + */ +static int cpuidle_coupled_clear_pokes(int cpu) +{ + if (!cpumask_test_cpu(cpu, &cpuidle_coupled_poke_pending)) + return 0; + + local_irq_enable(); + while (cpumask_test_cpu(cpu, &cpuidle_coupled_poke_pending)) + cpu_relax(); + local_irq_disable(); + + return 1; +} + +static bool cpuidle_coupled_any_pokes_pending(struct cpuidle_coupled *coupled) +{ + cpumask_t cpus; + int ret; + + cpumask_and(&cpus, cpu_online_mask, &coupled->coupled_cpus); + ret = cpumask_and(&cpus, &cpuidle_coupled_poke_pending, &cpus); + + return ret; +} + +/** + * cpuidle_enter_state_coupled - attempt to enter a state with coupled cpus + * @dev: struct cpuidle_device for the current cpu + * @drv: struct cpuidle_driver for the platform + * @next_state: index of the requested state in drv->states + * + * Coordinate with coupled cpus to enter the target state. This is a two + * stage process. In the first stage, the cpus are operating independently, + * and may call into cpuidle_enter_state_coupled at completely different times. + * To save as much power as possible, the first cpus to call this function will + * go to an intermediate state (the cpuidle_device's safe state), and wait for + * all the other cpus to call this function. Once all coupled cpus are idle, + * the second stage will start. Each coupled cpu will spin until all cpus have + * guaranteed that they will call the target_state. + * + * This function must be called with interrupts disabled. It may enable + * interrupts while preparing for idle, and it will always return with + * interrupts enabled. + */ +int cpuidle_enter_state_coupled(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int next_state) +{ + int entered_state = -1; + struct cpuidle_coupled *coupled = dev->coupled; + int w; + + if (!coupled) + return -EINVAL; + + while (coupled->prevent) { + cpuidle_coupled_clear_pokes(dev->cpu); + if (need_resched()) { + local_irq_enable(); + return entered_state; + } + entered_state = cpuidle_enter_state(dev, drv, + dev->safe_state_index); + local_irq_disable(); + } + + /* Read barrier ensures online_count is read after prevent is cleared */ + smp_rmb(); + +reset: + cpumask_clear_cpu(dev->cpu, &cpuidle_coupled_poked); + + w = cpuidle_coupled_set_waiting(dev->cpu, coupled, next_state); + /* + * If this is the last cpu to enter the waiting state, poke + * all the other cpus out of their waiting state so they can + * enter a deeper state. This can race with one of the cpus + * exiting the waiting state due to an interrupt and + * decrementing waiting_count, see comment below. + */ + if (w == coupled->online_count) { + cpumask_set_cpu(dev->cpu, &cpuidle_coupled_poked); + cpuidle_coupled_poke_others(dev->cpu, coupled); + } + +retry: + /* + * Wait for all coupled cpus to be idle, using the deepest state + * allowed for a single cpu. If this was not the poking cpu, wait + * for at least one poke before leaving to avoid a race where + * two cpus could arrive at the waiting loop at the same time, + * but the first of the two to arrive could skip the loop without + * processing the pokes from the last to arrive. + */ + while (!cpuidle_coupled_cpus_waiting(coupled) || + !cpumask_test_cpu(dev->cpu, &cpuidle_coupled_poked)) { + if (cpuidle_coupled_clear_pokes(dev->cpu)) + continue; + + if (need_resched()) { + cpuidle_coupled_set_not_waiting(dev->cpu, coupled); + goto out; + } + + if (coupled->prevent) { + cpuidle_coupled_set_not_waiting(dev->cpu, coupled); + goto out; + } + + entered_state = cpuidle_enter_state(dev, drv, + dev->safe_state_index); + local_irq_disable(); + } + + cpuidle_coupled_clear_pokes(dev->cpu); + if (need_resched()) { + cpuidle_coupled_set_not_waiting(dev->cpu, coupled); + goto out; + } + + /* + * Make sure final poke status for this cpu is visible before setting + * cpu as ready. + */ + smp_wmb(); + + /* + * All coupled cpus are probably idle. There is a small chance that + * one of the other cpus just became active. Increment the ready count, + * and spin until all coupled cpus have incremented the counter. Once a + * cpu has incremented the ready counter, it cannot abort idle and must + * spin until either all cpus have incremented the ready counter, or + * another cpu leaves idle and decrements the waiting counter. + */ + + cpuidle_coupled_set_ready(coupled); + while (!cpuidle_coupled_cpus_ready(coupled)) { + /* Check if any other cpus bailed out of idle. */ + if (!cpuidle_coupled_cpus_waiting(coupled)) + if (!cpuidle_coupled_set_not_ready(coupled)) + goto retry; + + cpu_relax(); + } + + /* + * Make sure read of all cpus ready is done before reading pending pokes + */ + smp_rmb(); + + /* + * There is a small chance that a cpu left and reentered idle after this + * cpu saw that all cpus were waiting. The cpu that reentered idle will + * have sent this cpu a poke, which will still be pending after the + * ready loop. The pending interrupt may be lost by the interrupt + * controller when entering the deep idle state. It's not possible to + * clear a pending interrupt without turning interrupts on and handling + * it, and it's too late to turn on interrupts here, so reset the + * coupled idle state of all cpus and retry. + */ + if (cpuidle_coupled_any_pokes_pending(coupled)) { + cpuidle_coupled_set_done(dev->cpu, coupled); + /* Wait for all cpus to see the pending pokes */ + cpuidle_coupled_parallel_barrier(dev, &coupled->abort_barrier); + goto reset; + } + + /* all cpus have acked the coupled state */ + next_state = cpuidle_coupled_get_state(dev, coupled); + + entered_state = cpuidle_enter_state(dev, drv, next_state); + + cpuidle_coupled_set_done(dev->cpu, coupled); + +out: + /* + * Normal cpuidle states are expected to return with irqs enabled. + * That leads to an inefficiency where a cpu receiving an interrupt + * that brings it out of idle will process that interrupt before + * exiting the idle enter function and decrementing ready_count. All + * other cpus will need to spin waiting for the cpu that is processing + * the interrupt. If the driver returns with interrupts disabled, + * all other cpus will loop back into the safe idle state instead of + * spinning, saving power. + * + * Calling local_irq_enable here allows coupled states to return with + * interrupts disabled, but won't cause problems for drivers that + * exit with interrupts enabled. + */ + local_irq_enable(); + + /* + * Wait until all coupled cpus have exited idle. There is no risk that + * a cpu exits and re-enters the ready state because this cpu has + * already decremented its waiting_count. + */ + while (!cpuidle_coupled_no_cpus_ready(coupled)) + cpu_relax(); + + return entered_state; +} + +static void cpuidle_coupled_update_online_cpus(struct cpuidle_coupled *coupled) +{ + cpumask_t cpus; + cpumask_and(&cpus, cpu_online_mask, &coupled->coupled_cpus); + coupled->online_count = cpumask_weight(&cpus); +} + +/** + * cpuidle_coupled_register_device - register a coupled cpuidle device + * @dev: struct cpuidle_device for the current cpu + * + * Called from cpuidle_register_device to handle coupled idle init. Finds the + * cpuidle_coupled struct for this set of coupled cpus, or creates one if none + * exists yet. + */ +int cpuidle_coupled_register_device(struct cpuidle_device *dev) +{ + int cpu; + struct cpuidle_device *other_dev; + struct call_single_data *csd; + struct cpuidle_coupled *coupled; + + if (cpumask_empty(&dev->coupled_cpus)) + return 0; + + for_each_cpu_mask(cpu, dev->coupled_cpus) { + other_dev = per_cpu(cpuidle_devices, cpu); + if (other_dev && other_dev->coupled) { + coupled = other_dev->coupled; + goto have_coupled; + } + } + + /* No existing coupled info found, create a new one */ + coupled = kzalloc(sizeof(struct cpuidle_coupled), GFP_KERNEL); + if (!coupled) + return -ENOMEM; + + coupled->coupled_cpus = dev->coupled_cpus; + +have_coupled: + dev->coupled = coupled; + if (WARN_ON(!cpumask_equal(&dev->coupled_cpus, &coupled->coupled_cpus))) + coupled->prevent++; + + cpuidle_coupled_update_online_cpus(coupled); + + coupled->refcnt++; + + csd = &per_cpu(cpuidle_coupled_poke_cb, dev->cpu); + csd->func = cpuidle_coupled_handle_poke; + csd->info = (void *)(unsigned long)dev->cpu; + + return 0; +} + +/** + * cpuidle_coupled_unregister_device - unregister a coupled cpuidle device + * @dev: struct cpuidle_device for the current cpu + * + * Called from cpuidle_unregister_device to tear down coupled idle. Removes the + * cpu from the coupled idle set, and frees the cpuidle_coupled_info struct if + * this was the last cpu in the set. + */ +void cpuidle_coupled_unregister_device(struct cpuidle_device *dev) +{ + struct cpuidle_coupled *coupled = dev->coupled; + + if (cpumask_empty(&dev->coupled_cpus)) + return; + + if (--coupled->refcnt) + kfree(coupled); + dev->coupled = NULL; +} + +/** + * cpuidle_coupled_prevent_idle - prevent cpus from entering a coupled state + * @coupled: the struct coupled that contains the cpu that is changing state + * + * Disables coupled cpuidle on a coupled set of cpus. Used to ensure that + * cpu_online_mask doesn't change while cpus are coordinating coupled idle. + */ +static void cpuidle_coupled_prevent_idle(struct cpuidle_coupled *coupled) +{ + int cpu = get_cpu(); + + /* Force all cpus out of the waiting loop. */ + coupled->prevent++; + cpuidle_coupled_poke_others(cpu, coupled); + put_cpu(); + while (!cpuidle_coupled_no_cpus_waiting(coupled)) + cpu_relax(); +} + +/** + * cpuidle_coupled_allow_idle - allows cpus to enter a coupled state + * @coupled: the struct coupled that contains the cpu that is changing state + * + * Enables coupled cpuidle on a coupled set of cpus. Used to ensure that + * cpu_online_mask doesn't change while cpus are coordinating coupled idle. + */ +static void cpuidle_coupled_allow_idle(struct cpuidle_coupled *coupled) +{ + int cpu = get_cpu(); + + /* + * Write barrier ensures readers see the new online_count when they + * see prevent == 0. + */ + smp_wmb(); + coupled->prevent--; + /* Force cpus out of the prevent loop. */ + cpuidle_coupled_poke_others(cpu, coupled); + put_cpu(); +} + +/** + * cpuidle_coupled_cpu_notify - notifier called during hotplug transitions + * @nb: notifier block + * @action: hotplug transition + * @hcpu: target cpu number + * + * Called when a cpu is brought on or offline using hotplug. Updates the + * coupled cpu set appropriately + */ +static int cpuidle_coupled_cpu_notify(struct notifier_block *nb, + unsigned long action, void *hcpu) +{ + int cpu = (unsigned long)hcpu; + struct cpuidle_device *dev; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: + case CPU_DOWN_PREPARE: + case CPU_ONLINE: + case CPU_DEAD: + case CPU_UP_CANCELED: + case CPU_DOWN_FAILED: + break; + default: + return NOTIFY_OK; + } + + mutex_lock(&cpuidle_lock); + + dev = per_cpu(cpuidle_devices, cpu); + if (!dev || !dev->coupled) + goto out; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: + case CPU_DOWN_PREPARE: + cpuidle_coupled_prevent_idle(dev->coupled); + break; + case CPU_ONLINE: + case CPU_DEAD: + cpuidle_coupled_update_online_cpus(dev->coupled); + /* Fall through */ + case CPU_UP_CANCELED: + case CPU_DOWN_FAILED: + cpuidle_coupled_allow_idle(dev->coupled); + break; + } + +out: + mutex_unlock(&cpuidle_lock); + return NOTIFY_OK; +} + +static struct notifier_block cpuidle_coupled_cpu_notifier = { + .notifier_call = cpuidle_coupled_cpu_notify, +}; + +static int __init cpuidle_coupled_init(void) +{ + return register_cpu_notifier(&cpuidle_coupled_cpu_notifier); +} +core_initcall(cpuidle_coupled_init); diff --git a/drivers/cpuidle/cpuidle-armada-370-xp.c b/drivers/cpuidle/cpuidle-armada-370-xp.c new file mode 100644 index 00000000000..a5fba0287bf --- /dev/null +++ b/drivers/cpuidle/cpuidle-armada-370-xp.c @@ -0,0 +1,93 @@ +/* + * Marvell Armada 370 and Armada XP SoC cpuidle driver + * + * Copyright (C) 2014 Marvell + * + * Nadav Haklai <nadavh@marvell.com> + * Gregory CLEMENT <gregory.clement@free-electrons.com> + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + * + * Maintainer: Gregory CLEMENT <gregory.clement@free-electrons.com> + */ + +#include <linux/cpu_pm.h> +#include <linux/cpuidle.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/suspend.h> +#include <linux/platform_device.h> +#include <asm/cpuidle.h> + +#define ARMADA_370_XP_MAX_STATES 3 +#define ARMADA_370_XP_FLAG_DEEP_IDLE 0x10000 + +static int (*armada_370_xp_cpu_suspend)(int); + +static int armada_370_xp_enter_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + int ret; + bool deepidle = false; + cpu_pm_enter(); + + if (drv->states[index].flags & ARMADA_370_XP_FLAG_DEEP_IDLE) + deepidle = true; + + ret = armada_370_xp_cpu_suspend(deepidle); + if (ret) + return ret; + + cpu_pm_exit(); + + return index; +} + +static struct cpuidle_driver armada_370_xp_idle_driver = { + .name = "armada_370_xp_idle", + .states[0] = ARM_CPUIDLE_WFI_STATE, + .states[1] = { + .enter = armada_370_xp_enter_idle, + .exit_latency = 10, + .power_usage = 50, + .target_residency = 100, + .flags = CPUIDLE_FLAG_TIME_VALID, + .name = "Idle", + .desc = "CPU power down", + }, + .states[2] = { + .enter = armada_370_xp_enter_idle, + .exit_latency = 100, + .power_usage = 5, + .target_residency = 1000, + .flags = CPUIDLE_FLAG_TIME_VALID | + ARMADA_370_XP_FLAG_DEEP_IDLE, + .name = "Deep idle", + .desc = "CPU and L2 Fabric power down", + }, + .state_count = ARMADA_370_XP_MAX_STATES, +}; + +static int armada_370_xp_cpuidle_probe(struct platform_device *pdev) +{ + + armada_370_xp_cpu_suspend = (void *)(pdev->dev.platform_data); + return cpuidle_register(&armada_370_xp_idle_driver, NULL); +} + +static struct platform_driver armada_370_xp_cpuidle_plat_driver = { + .driver = { + .name = "cpuidle-armada-370-xp", + .owner = THIS_MODULE, + }, + .probe = armada_370_xp_cpuidle_probe, +}; + +module_platform_driver(armada_370_xp_cpuidle_plat_driver); + +MODULE_AUTHOR("Gregory CLEMENT <gregory.clement@free-electrons.com>"); +MODULE_DESCRIPTION("Armada 370/XP cpu idle driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/cpuidle/cpuidle-at91.c b/drivers/cpuidle/cpuidle-at91.c new file mode 100644 index 00000000000..a0774370c6b --- /dev/null +++ b/drivers/cpuidle/cpuidle-at91.c @@ -0,0 +1,69 @@ +/* + * based on arch/arm/mach-kirkwood/cpuidle.c + * + * CPU idle support for AT91 SoC + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + * + * The cpu idle uses wait-for-interrupt and RAM self refresh in order + * to implement two idle states - + * #1 wait-for-interrupt + * #2 wait-for-interrupt and RAM self refresh + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/platform_device.h> +#include <linux/cpuidle.h> +#include <linux/io.h> +#include <linux/export.h> +#include <asm/proc-fns.h> +#include <asm/cpuidle.h> + +#define AT91_MAX_STATES 2 + +static void (*at91_standby)(void); + +/* Actual code that puts the SoC in different idle states */ +static int at91_enter_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + at91_standby(); + return index; +} + +static struct cpuidle_driver at91_idle_driver = { + .name = "at91_idle", + .owner = THIS_MODULE, + .states[0] = ARM_CPUIDLE_WFI_STATE, + .states[1] = { + .enter = at91_enter_idle, + .exit_latency = 10, + .target_residency = 10000, + .flags = CPUIDLE_FLAG_TIME_VALID, + .name = "RAM_SR", + .desc = "WFI and DDR Self Refresh", + }, + .state_count = AT91_MAX_STATES, +}; + +/* Initialize CPU idle by registering the idle states */ +static int at91_cpuidle_probe(struct platform_device *dev) +{ + at91_standby = (void *)(dev->dev.platform_data); + + return cpuidle_register(&at91_idle_driver, NULL); +} + +static struct platform_driver at91_cpuidle_driver = { + .driver = { + .name = "cpuidle-at91", + .owner = THIS_MODULE, + }, + .probe = at91_cpuidle_probe, +}; + +module_platform_driver(at91_cpuidle_driver); diff --git a/drivers/cpuidle/cpuidle-big_little.c b/drivers/cpuidle/cpuidle-big_little.c new file mode 100644 index 00000000000..b45fc624904 --- /dev/null +++ b/drivers/cpuidle/cpuidle-big_little.c @@ -0,0 +1,209 @@ +/* + * Copyright (c) 2013 ARM/Linaro + * + * Authors: Daniel Lezcano <daniel.lezcano@linaro.org> + * Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> + * Nicolas Pitre <nicolas.pitre@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Maintainer: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> + * Maintainer: Daniel Lezcano <daniel.lezcano@linaro.org> + */ +#include <linux/cpuidle.h> +#include <linux/cpu_pm.h> +#include <linux/slab.h> +#include <linux/of.h> + +#include <asm/cpu.h> +#include <asm/cputype.h> +#include <asm/cpuidle.h> +#include <asm/mcpm.h> +#include <asm/smp_plat.h> +#include <asm/suspend.h> + +static int bl_enter_powerdown(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int idx); + +/* + * NB: Owing to current menu governor behaviour big and LITTLE + * index 1 states have to define exit_latency and target_residency for + * cluster state since, when all CPUs in a cluster hit it, the cluster + * can be shutdown. This means that when a single CPU enters this state + * the exit_latency and target_residency values are somewhat overkill. + * There is no notion of cluster states in the menu governor, so CPUs + * have to define CPU states where possibly the cluster will be shutdown + * depending on the state of other CPUs. idle states entry and exit happen + * at random times; however the cluster state provides target_residency + * values as if all CPUs in a cluster enter the state at once; this is + * somewhat optimistic and behaviour should be fixed either in the governor + * or in the MCPM back-ends. + * To make this driver 100% generic the number of states and the exit_latency + * target_residency values must be obtained from device tree bindings. + * + * exit_latency: refers to the TC2 vexpress test chip and depends on the + * current cluster operating point. It is the time it takes to get the CPU + * up and running when the CPU is powered up on cluster wake-up from shutdown. + * Current values for big and LITTLE clusters are provided for clusters + * running at default operating points. + * + * target_residency: it is the minimum amount of time the cluster has + * to be down to break even in terms of power consumption. cluster + * shutdown has inherent dynamic power costs (L2 writebacks to DRAM + * being the main factor) that depend on the current operating points. + * The current values for both clusters are provided for a CPU whose half + * of L2 lines are dirty and require cleaning to DRAM, and takes into + * account leakage static power values related to the vexpress TC2 testchip. + */ +static struct cpuidle_driver bl_idle_little_driver = { + .name = "little_idle", + .owner = THIS_MODULE, + .states[0] = ARM_CPUIDLE_WFI_STATE, + .states[1] = { + .enter = bl_enter_powerdown, + .exit_latency = 700, + .target_residency = 2500, + .flags = CPUIDLE_FLAG_TIME_VALID | + CPUIDLE_FLAG_TIMER_STOP, + .name = "C1", + .desc = "ARM little-cluster power down", + }, + .state_count = 2, +}; + +static struct cpuidle_driver bl_idle_big_driver = { + .name = "big_idle", + .owner = THIS_MODULE, + .states[0] = ARM_CPUIDLE_WFI_STATE, + .states[1] = { + .enter = bl_enter_powerdown, + .exit_latency = 500, + .target_residency = 2000, + .flags = CPUIDLE_FLAG_TIME_VALID | + CPUIDLE_FLAG_TIMER_STOP, + .name = "C1", + .desc = "ARM big-cluster power down", + }, + .state_count = 2, +}; + +/* + * notrace prevents trace shims from getting inserted where they + * should not. Global jumps and ldrex/strex must not be inserted + * in power down sequences where caches and MMU may be turned off. + */ +static int notrace bl_powerdown_finisher(unsigned long arg) +{ + /* MCPM works with HW CPU identifiers */ + unsigned int mpidr = read_cpuid_mpidr(); + unsigned int cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + unsigned int cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + + mcpm_set_entry_vector(cpu, cluster, cpu_resume); + + /* + * Residency value passed to mcpm_cpu_suspend back-end + * has to be given clear semantics. Set to 0 as a + * temporary value. + */ + mcpm_cpu_suspend(0); + + /* return value != 0 means failure */ + return 1; +} + +/** + * bl_enter_powerdown - Programs CPU to enter the specified state + * @dev: cpuidle device + * @drv: The target state to be programmed + * @idx: state index + * + * Called from the CPUidle framework to program the device to the + * specified target state selected by the governor. + */ +static int bl_enter_powerdown(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int idx) +{ + cpu_pm_enter(); + + cpu_suspend(0, bl_powerdown_finisher); + + /* signals the MCPM core that CPU is out of low power state */ + mcpm_cpu_powered_up(); + + cpu_pm_exit(); + + return idx; +} + +static int __init bl_idle_driver_init(struct cpuidle_driver *drv, int cpu_id) +{ + struct cpuinfo_arm *cpu_info; + struct cpumask *cpumask; + unsigned long cpuid; + int cpu; + + cpumask = kzalloc(cpumask_size(), GFP_KERNEL); + if (!cpumask) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + cpu_info = &per_cpu(cpu_data, cpu); + cpuid = is_smp() ? cpu_info->cpuid : read_cpuid_id(); + + /* read cpu id part number */ + if ((cpuid & 0xFFF0) == cpu_id) + cpumask_set_cpu(cpu, cpumask); + } + + drv->cpumask = cpumask; + + return 0; +} + +static int __init bl_idle_init(void) +{ + int ret; + + /* + * Initialize the driver just for a compliant set of machines + */ + if (!of_machine_is_compatible("arm,vexpress,v2p-ca15_a7")) + return -ENODEV; + /* + * For now the differentiation between little and big cores + * is based on the part number. A7 cores are considered little + * cores, A15 are considered big cores. This distinction may + * evolve in the future with a more generic matching approach. + */ + ret = bl_idle_driver_init(&bl_idle_little_driver, + ARM_CPU_PART_CORTEX_A7); + if (ret) + return ret; + + ret = bl_idle_driver_init(&bl_idle_big_driver, ARM_CPU_PART_CORTEX_A15); + if (ret) + goto out_uninit_little; + + ret = cpuidle_register(&bl_idle_little_driver, NULL); + if (ret) + goto out_uninit_big; + + ret = cpuidle_register(&bl_idle_big_driver, NULL); + if (ret) + goto out_unregister_little; + + return 0; + +out_unregister_little: + cpuidle_unregister(&bl_idle_little_driver); +out_uninit_big: + kfree(bl_idle_big_driver.cpumask); +out_uninit_little: + kfree(bl_idle_little_driver.cpumask); + + return ret; +} +device_initcall(bl_idle_init); diff --git a/drivers/cpuidle/cpuidle-calxeda.c b/drivers/cpuidle/cpuidle-calxeda.c new file mode 100644 index 00000000000..6e51114057d --- /dev/null +++ b/drivers/cpuidle/cpuidle-calxeda.c @@ -0,0 +1,81 @@ +/* + * Copyright 2012 Calxeda, Inc. + * + * Based on arch/arm/plat-mxc/cpuidle.c: #v3.7 + * Copyright 2012 Freescale Semiconductor, Inc. + * Copyright 2012 Linaro Ltd. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + * + * Maintainer: Rob Herring <rob.herring@calxeda.com> + */ + +#include <linux/cpuidle.h> +#include <linux/cpu_pm.h> +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/platform_device.h> +#include <asm/cpuidle.h> +#include <asm/suspend.h> +#include <asm/psci.h> + +static int calxeda_idle_finish(unsigned long val) +{ + const struct psci_power_state ps = { + .type = PSCI_POWER_STATE_TYPE_POWER_DOWN, + }; + return psci_ops.cpu_suspend(ps, __pa(cpu_resume)); +} + +static int calxeda_pwrdown_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + cpu_pm_enter(); + cpu_suspend(0, calxeda_idle_finish); + cpu_pm_exit(); + + return index; +} + +static struct cpuidle_driver calxeda_idle_driver = { + .name = "calxeda_idle", + .states = { + ARM_CPUIDLE_WFI_STATE, + { + .name = "PG", + .desc = "Power Gate", + .flags = CPUIDLE_FLAG_TIME_VALID, + .exit_latency = 30, + .power_usage = 50, + .target_residency = 200, + .enter = calxeda_pwrdown_idle, + }, + }, + .state_count = 2, +}; + +static int calxeda_cpuidle_probe(struct platform_device *pdev) +{ + return cpuidle_register(&calxeda_idle_driver, NULL); +} + +static struct platform_driver calxeda_cpuidle_plat_driver = { + .driver = { + .name = "cpuidle-calxeda", + .owner = THIS_MODULE, + }, + .probe = calxeda_cpuidle_probe, +}; + +module_platform_driver(calxeda_cpuidle_plat_driver); diff --git a/drivers/cpuidle/cpuidle-clps711x.c b/drivers/cpuidle/cpuidle-clps711x.c new file mode 100644 index 00000000000..5243811daa6 --- /dev/null +++ b/drivers/cpuidle/cpuidle-clps711x.c @@ -0,0 +1,64 @@ +/* + * CLPS711X CPU idle driver + * + * Copyright (C) 2014 Alexander Shiyan <shc_work@mail.ru> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/cpuidle.h> +#include <linux/err.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/platform_device.h> + +#define CLPS711X_CPUIDLE_NAME "clps711x-cpuidle" + +static void __iomem *clps711x_halt; + +static int clps711x_cpuidle_halt(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + writel(0xaa, clps711x_halt); + + return index; +} + +static struct cpuidle_driver clps711x_idle_driver = { + .name = CLPS711X_CPUIDLE_NAME, + .owner = THIS_MODULE, + .states[0] = { + .name = "HALT", + .desc = "CLPS711X HALT", + .enter = clps711x_cpuidle_halt, + .exit_latency = 1, + }, + .state_count = 1, +}; + +static int __init clps711x_cpuidle_probe(struct platform_device *pdev) +{ + struct resource *res; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + clps711x_halt = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(clps711x_halt)) + return PTR_ERR(clps711x_halt); + + return cpuidle_register(&clps711x_idle_driver, NULL); +} + +static struct platform_driver clps711x_cpuidle_driver = { + .driver = { + .name = CLPS711X_CPUIDLE_NAME, + .owner = THIS_MODULE, + }, +}; +module_platform_driver_probe(clps711x_cpuidle_driver, clps711x_cpuidle_probe); + +MODULE_AUTHOR("Alexander Shiyan <shc_work@mail.ru>"); +MODULE_DESCRIPTION("CLPS711X CPU idle driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/cpuidle/cpuidle-cps.c b/drivers/cpuidle/cpuidle-cps.c new file mode 100644 index 00000000000..fc7b62720de --- /dev/null +++ b/drivers/cpuidle/cpuidle-cps.c @@ -0,0 +1,186 @@ +/* + * Copyright (C) 2014 Imagination Technologies + * Author: Paul Burton <paul.burton@imgtec.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/cpu_pm.h> +#include <linux/cpuidle.h> +#include <linux/init.h> + +#include <asm/idle.h> +#include <asm/pm-cps.h> + +/* Enumeration of the various idle states this driver may enter */ +enum cps_idle_state { + STATE_WAIT = 0, /* MIPS wait instruction, coherent */ + STATE_NC_WAIT, /* MIPS wait instruction, non-coherent */ + STATE_CLOCK_GATED, /* Core clock gated */ + STATE_POWER_GATED, /* Core power gated */ + STATE_COUNT +}; + +static int cps_nc_enter(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + enum cps_pm_state pm_state; + int err; + + /* + * At least one core must remain powered up & clocked in order for the + * system to have any hope of functioning. + * + * TODO: don't treat core 0 specially, just prevent the final core + * TODO: remap interrupt affinity temporarily + */ + if (!cpu_data[dev->cpu].core && (index > STATE_NC_WAIT)) + index = STATE_NC_WAIT; + + /* Select the appropriate cps_pm_state */ + switch (index) { + case STATE_NC_WAIT: + pm_state = CPS_PM_NC_WAIT; + break; + case STATE_CLOCK_GATED: + pm_state = CPS_PM_CLOCK_GATED; + break; + case STATE_POWER_GATED: + pm_state = CPS_PM_POWER_GATED; + break; + default: + BUG(); + return -EINVAL; + } + + /* Notify listeners the CPU is about to power down */ + if ((pm_state == CPS_PM_POWER_GATED) && cpu_pm_enter()) + return -EINTR; + + /* Enter that state */ + err = cps_pm_enter_state(pm_state); + + /* Notify listeners the CPU is back up */ + if (pm_state == CPS_PM_POWER_GATED) + cpu_pm_exit(); + + return err ?: index; +} + +static struct cpuidle_driver cps_driver = { + .name = "cpc_cpuidle", + .owner = THIS_MODULE, + .states = { + [STATE_WAIT] = MIPS_CPUIDLE_WAIT_STATE, + [STATE_NC_WAIT] = { + .enter = cps_nc_enter, + .exit_latency = 200, + .target_residency = 450, + .flags = CPUIDLE_FLAG_TIME_VALID, + .name = "nc-wait", + .desc = "non-coherent MIPS wait", + }, + [STATE_CLOCK_GATED] = { + .enter = cps_nc_enter, + .exit_latency = 300, + .target_residency = 700, + .flags = CPUIDLE_FLAG_TIME_VALID | + CPUIDLE_FLAG_TIMER_STOP, + .name = "clock-gated", + .desc = "core clock gated", + }, + [STATE_POWER_GATED] = { + .enter = cps_nc_enter, + .exit_latency = 600, + .target_residency = 1000, + .flags = CPUIDLE_FLAG_TIME_VALID | + CPUIDLE_FLAG_TIMER_STOP, + .name = "power-gated", + .desc = "core power gated", + }, + }, + .state_count = STATE_COUNT, + .safe_state_index = 0, +}; + +static void __init cps_cpuidle_unregister(void) +{ + int cpu; + struct cpuidle_device *device; + + for_each_possible_cpu(cpu) { + device = &per_cpu(cpuidle_dev, cpu); + cpuidle_unregister_device(device); + } + + cpuidle_unregister_driver(&cps_driver); +} + +static int __init cps_cpuidle_init(void) +{ + int err, cpu, core, i; + struct cpuidle_device *device; + + /* Detect supported states */ + if (!cps_pm_support_state(CPS_PM_POWER_GATED)) + cps_driver.state_count = STATE_CLOCK_GATED + 1; + if (!cps_pm_support_state(CPS_PM_CLOCK_GATED)) + cps_driver.state_count = STATE_NC_WAIT + 1; + if (!cps_pm_support_state(CPS_PM_NC_WAIT)) + cps_driver.state_count = STATE_WAIT + 1; + + /* Inform the user if some states are unavailable */ + if (cps_driver.state_count < STATE_COUNT) { + pr_info("cpuidle-cps: limited to "); + switch (cps_driver.state_count - 1) { + case STATE_WAIT: + pr_cont("coherent wait\n"); + break; + case STATE_NC_WAIT: + pr_cont("non-coherent wait\n"); + break; + case STATE_CLOCK_GATED: + pr_cont("clock gating\n"); + break; + } + } + + /* + * Set the coupled flag on the appropriate states if this system + * requires it. + */ + if (coupled_coherence) + for (i = STATE_NC_WAIT; i < cps_driver.state_count; i++) + cps_driver.states[i].flags |= CPUIDLE_FLAG_COUPLED; + + err = cpuidle_register_driver(&cps_driver); + if (err) { + pr_err("Failed to register CPS cpuidle driver\n"); + return err; + } + + for_each_possible_cpu(cpu) { + core = cpu_data[cpu].core; + device = &per_cpu(cpuidle_dev, cpu); + device->cpu = cpu; +#ifdef CONFIG_MIPS_MT + cpumask_copy(&device->coupled_cpus, &cpu_sibling_map[cpu]); +#endif + + err = cpuidle_register_device(device); + if (err) { + pr_err("Failed to register CPU%d cpuidle device\n", + cpu); + goto err_out; + } + } + + return 0; +err_out: + cps_cpuidle_unregister(); + return err; +} +device_initcall(cps_cpuidle_init); diff --git a/drivers/cpuidle/cpuidle-exynos.c b/drivers/cpuidle/cpuidle-exynos.c new file mode 100644 index 00000000000..7c015126382 --- /dev/null +++ b/drivers/cpuidle/cpuidle-exynos.c @@ -0,0 +1,99 @@ +/* linux/arch/arm/mach-exynos/cpuidle.c + * + * Copyright (c) 2011 Samsung Electronics Co., Ltd. + * http://www.samsung.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/cpuidle.h> +#include <linux/cpu_pm.h> +#include <linux/export.h> +#include <linux/module.h> +#include <linux/platform_device.h> + +#include <asm/proc-fns.h> +#include <asm/suspend.h> +#include <asm/cpuidle.h> + +static void (*exynos_enter_aftr)(void); + +static int idle_finisher(unsigned long flags) +{ + exynos_enter_aftr(); + cpu_do_idle(); + + return 1; +} + +static int exynos_enter_core0_aftr(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + cpu_pm_enter(); + cpu_suspend(0, idle_finisher); + cpu_pm_exit(); + + return index; +} + +static int exynos_enter_lowpower(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + int new_index = index; + + /* AFTR can only be entered when cores other than CPU0 are offline */ + if (num_online_cpus() > 1 || dev->cpu != 0) + new_index = drv->safe_state_index; + + if (new_index == 0) + return arm_cpuidle_simple_enter(dev, drv, new_index); + else + return exynos_enter_core0_aftr(dev, drv, new_index); +} + +static struct cpuidle_driver exynos_idle_driver = { + .name = "exynos_idle", + .owner = THIS_MODULE, + .states = { + [0] = ARM_CPUIDLE_WFI_STATE, + [1] = { + .enter = exynos_enter_lowpower, + .exit_latency = 300, + .target_residency = 100000, + .flags = CPUIDLE_FLAG_TIME_VALID, + .name = "C1", + .desc = "ARM power down", + }, + }, + .state_count = 2, + .safe_state_index = 0, +}; + +static int exynos_cpuidle_probe(struct platform_device *pdev) +{ + int ret; + + exynos_enter_aftr = (void *)(pdev->dev.platform_data); + + ret = cpuidle_register(&exynos_idle_driver, NULL); + if (ret) { + dev_err(&pdev->dev, "failed to register cpuidle driver\n"); + return ret; + } + + return 0; +} + +static struct platform_driver exynos_cpuidle_driver = { + .probe = exynos_cpuidle_probe, + .driver = { + .name = "exynos_cpuidle", + .owner = THIS_MODULE, + }, +}; + +module_platform_driver(exynos_cpuidle_driver); diff --git a/drivers/cpuidle/cpuidle-kirkwood.c b/drivers/cpuidle/cpuidle-kirkwood.c new file mode 100644 index 00000000000..41ba843251b --- /dev/null +++ b/drivers/cpuidle/cpuidle-kirkwood.c @@ -0,0 +1,90 @@ +/* + * CPU idle Marvell Kirkwood SoCs + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + * + * The cpu idle uses wait-for-interrupt and DDR self refresh in order + * to implement two idle states - + * #1 wait-for-interrupt + * #2 wait-for-interrupt and DDR self refresh + * + * Maintainer: Jason Cooper <jason@lakedaemon.net> + * Maintainer: Andrew Lunn <andrew@lunn.ch> + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/platform_device.h> +#include <linux/cpuidle.h> +#include <linux/io.h> +#include <linux/export.h> +#include <asm/proc-fns.h> +#include <asm/cpuidle.h> + +#define KIRKWOOD_MAX_STATES 2 + +static void __iomem *ddr_operation_base; + +/* Actual code that puts the SoC in different idle states */ +static int kirkwood_enter_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + writel(0x7, ddr_operation_base); + cpu_do_idle(); + + return index; +} + +static struct cpuidle_driver kirkwood_idle_driver = { + .name = "kirkwood_idle", + .owner = THIS_MODULE, + .states[0] = ARM_CPUIDLE_WFI_STATE, + .states[1] = { + .enter = kirkwood_enter_idle, + .exit_latency = 10, + .target_residency = 100000, + .flags = CPUIDLE_FLAG_TIME_VALID, + .name = "DDR SR", + .desc = "WFI and DDR Self Refresh", + }, + .state_count = KIRKWOOD_MAX_STATES, +}; + +/* Initialize CPU idle by registering the idle states */ +static int kirkwood_cpuidle_probe(struct platform_device *pdev) +{ + struct resource *res; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + ddr_operation_base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(ddr_operation_base)) + return PTR_ERR(ddr_operation_base); + + return cpuidle_register(&kirkwood_idle_driver, NULL); +} + +static int kirkwood_cpuidle_remove(struct platform_device *pdev) +{ + cpuidle_unregister(&kirkwood_idle_driver); + return 0; +} + +static struct platform_driver kirkwood_cpuidle_driver = { + .probe = kirkwood_cpuidle_probe, + .remove = kirkwood_cpuidle_remove, + .driver = { + .name = "kirkwood_cpuidle", + .owner = THIS_MODULE, + }, +}; + +module_platform_driver(kirkwood_cpuidle_driver); + +MODULE_AUTHOR("Andrew Lunn <andrew@lunn.ch>"); +MODULE_DESCRIPTION("Kirkwood cpu idle driver"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("platform:kirkwood-cpuidle"); diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c new file mode 100644 index 00000000000..74f5788d50b --- /dev/null +++ b/drivers/cpuidle/cpuidle-powernv.c @@ -0,0 +1,254 @@ +/* + * cpuidle-powernv - idle state cpuidle driver. + * Adapted from drivers/cpuidle/cpuidle-pseries + * + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/moduleparam.h> +#include <linux/cpuidle.h> +#include <linux/cpu.h> +#include <linux/notifier.h> +#include <linux/clockchips.h> +#include <linux/of.h> + +#include <asm/machdep.h> +#include <asm/firmware.h> +#include <asm/runlatch.h> + +/* Flags and constants used in PowerNV platform */ + +#define MAX_POWERNV_IDLE_STATES 8 +#define IDLE_USE_INST_NAP 0x00010000 /* Use nap instruction */ +#define IDLE_USE_INST_SLEEP 0x00020000 /* Use sleep instruction */ + +struct cpuidle_driver powernv_idle_driver = { + .name = "powernv_idle", + .owner = THIS_MODULE, +}; + +static int max_idle_state; +static struct cpuidle_state *cpuidle_state_table; + +static int snooze_loop(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + local_irq_enable(); + set_thread_flag(TIF_POLLING_NRFLAG); + + ppc64_runlatch_off(); + while (!need_resched()) { + HMT_low(); + HMT_very_low(); + } + + HMT_medium(); + ppc64_runlatch_on(); + clear_thread_flag(TIF_POLLING_NRFLAG); + smp_mb(); + return index; +} + +static int nap_loop(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + ppc64_runlatch_off(); + power7_idle(); + ppc64_runlatch_on(); + return index; +} + +static int fastsleep_loop(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + unsigned long old_lpcr = mfspr(SPRN_LPCR); + unsigned long new_lpcr; + + if (unlikely(system_state < SYSTEM_RUNNING)) + return index; + + new_lpcr = old_lpcr; + /* Do not exit powersave upon decrementer as we've setup the timer + * offload. + */ + new_lpcr &= ~LPCR_PECE1; + + mtspr(SPRN_LPCR, new_lpcr); + power7_sleep(); + + mtspr(SPRN_LPCR, old_lpcr); + + return index; +} + +/* + * States for dedicated partition case. + */ +static struct cpuidle_state powernv_states[MAX_POWERNV_IDLE_STATES] = { + { /* Snooze */ + .name = "snooze", + .desc = "snooze", + .flags = CPUIDLE_FLAG_TIME_VALID, + .exit_latency = 0, + .target_residency = 0, + .enter = &snooze_loop }, +}; + +static int powernv_cpuidle_add_cpu_notifier(struct notifier_block *n, + unsigned long action, void *hcpu) +{ + int hotcpu = (unsigned long)hcpu; + struct cpuidle_device *dev = + per_cpu(cpuidle_devices, hotcpu); + + if (dev && cpuidle_get_driver()) { + switch (action) { + case CPU_ONLINE: + case CPU_ONLINE_FROZEN: + cpuidle_pause_and_lock(); + cpuidle_enable_device(dev); + cpuidle_resume_and_unlock(); + break; + + case CPU_DEAD: + case CPU_DEAD_FROZEN: + cpuidle_pause_and_lock(); + cpuidle_disable_device(dev); + cpuidle_resume_and_unlock(); + break; + + default: + return NOTIFY_DONE; + } + } + return NOTIFY_OK; +} + +static struct notifier_block setup_hotplug_notifier = { + .notifier_call = powernv_cpuidle_add_cpu_notifier, +}; + +/* + * powernv_cpuidle_driver_init() + */ +static int powernv_cpuidle_driver_init(void) +{ + int idle_state; + struct cpuidle_driver *drv = &powernv_idle_driver; + + drv->state_count = 0; + + for (idle_state = 0; idle_state < max_idle_state; ++idle_state) { + /* Is the state not enabled? */ + if (cpuidle_state_table[idle_state].enter == NULL) + continue; + + drv->states[drv->state_count] = /* structure copy */ + cpuidle_state_table[idle_state]; + + drv->state_count += 1; + } + + return 0; +} + +static int powernv_add_idle_states(void) +{ + struct device_node *power_mgt; + struct property *prop; + int nr_idle_states = 1; /* Snooze */ + int dt_idle_states; + u32 *flags; + int i; + + /* Currently we have snooze statically defined */ + + power_mgt = of_find_node_by_path("/ibm,opal/power-mgt"); + if (!power_mgt) { + pr_warn("opal: PowerMgmt Node not found\n"); + return nr_idle_states; + } + + prop = of_find_property(power_mgt, "ibm,cpu-idle-state-flags", NULL); + if (!prop) { + pr_warn("DT-PowerMgmt: missing ibm,cpu-idle-state-flags\n"); + return nr_idle_states; + } + + dt_idle_states = prop->length / sizeof(u32); + flags = (u32 *) prop->value; + + for (i = 0; i < dt_idle_states; i++) { + + if (flags[i] & IDLE_USE_INST_NAP) { + /* Add NAP state */ + strcpy(powernv_states[nr_idle_states].name, "Nap"); + strcpy(powernv_states[nr_idle_states].desc, "Nap"); + powernv_states[nr_idle_states].flags = CPUIDLE_FLAG_TIME_VALID; + powernv_states[nr_idle_states].exit_latency = 10; + powernv_states[nr_idle_states].target_residency = 100; + powernv_states[nr_idle_states].enter = &nap_loop; + nr_idle_states++; + } + + if (flags[i] & IDLE_USE_INST_SLEEP) { + /* Add FASTSLEEP state */ + strcpy(powernv_states[nr_idle_states].name, "FastSleep"); + strcpy(powernv_states[nr_idle_states].desc, "FastSleep"); + powernv_states[nr_idle_states].flags = + CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TIMER_STOP; + powernv_states[nr_idle_states].exit_latency = 300; + powernv_states[nr_idle_states].target_residency = 1000000; + powernv_states[nr_idle_states].enter = &fastsleep_loop; + nr_idle_states++; + } + } + + return nr_idle_states; +} + +/* + * powernv_idle_probe() + * Choose state table for shared versus dedicated partition + */ +static int powernv_idle_probe(void) +{ + if (cpuidle_disable != IDLE_NO_OVERRIDE) + return -ENODEV; + + if (firmware_has_feature(FW_FEATURE_OPALv3)) { + cpuidle_state_table = powernv_states; + /* Device tree can indicate more idle states */ + max_idle_state = powernv_add_idle_states(); + } else + return -ENODEV; + + return 0; +} + +static int __init powernv_processor_idle_init(void) +{ + int retval; + + retval = powernv_idle_probe(); + if (retval) + return retval; + + powernv_cpuidle_driver_init(); + retval = cpuidle_register(&powernv_idle_driver, NULL); + if (retval) { + printk(KERN_DEBUG "Registration of powernv driver failed.\n"); + return retval; + } + + register_cpu_notifier(&setup_hotplug_notifier); + printk(KERN_DEBUG "powernv_idle_driver registered\n"); + return 0; +} + +device_initcall(powernv_processor_idle_init); diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c new file mode 100644 index 00000000000..6f7b0195688 --- /dev/null +++ b/drivers/cpuidle/cpuidle-pseries.c @@ -0,0 +1,273 @@ +/* + * cpuidle-pseries - idle state cpuidle driver. + * Adapted from drivers/idle/intel_idle.c and + * drivers/acpi/processor_idle.c + * + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/moduleparam.h> +#include <linux/cpuidle.h> +#include <linux/cpu.h> +#include <linux/notifier.h> + +#include <asm/paca.h> +#include <asm/reg.h> +#include <asm/machdep.h> +#include <asm/firmware.h> +#include <asm/runlatch.h> +#include <asm/plpar_wrappers.h> + +struct cpuidle_driver pseries_idle_driver = { + .name = "pseries_idle", + .owner = THIS_MODULE, +}; + +static int max_idle_state; +static struct cpuidle_state *cpuidle_state_table; + +static inline void idle_loop_prolog(unsigned long *in_purr) +{ + ppc64_runlatch_off(); + *in_purr = mfspr(SPRN_PURR); + /* + * Indicate to the HV that we are idle. Now would be + * a good time to find other work to dispatch. + */ + get_lppaca()->idle = 1; +} + +static inline void idle_loop_epilog(unsigned long in_purr) +{ + u64 wait_cycles; + + wait_cycles = be64_to_cpu(get_lppaca()->wait_state_cycles); + wait_cycles += mfspr(SPRN_PURR) - in_purr; + get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles); + get_lppaca()->idle = 0; + + if (irqs_disabled()) + local_irq_enable(); + ppc64_runlatch_on(); +} + +static int snooze_loop(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + unsigned long in_purr; + + idle_loop_prolog(&in_purr); + local_irq_enable(); + set_thread_flag(TIF_POLLING_NRFLAG); + + while (!need_resched()) { + HMT_low(); + HMT_very_low(); + } + + HMT_medium(); + clear_thread_flag(TIF_POLLING_NRFLAG); + smp_mb(); + + idle_loop_epilog(in_purr); + + return index; +} + +static void check_and_cede_processor(void) +{ + /* + * Ensure our interrupt state is properly tracked, + * also checks if no interrupt has occurred while we + * were soft-disabled + */ + if (prep_irq_for_idle()) { + cede_processor(); +#ifdef CONFIG_TRACE_IRQFLAGS + /* Ensure that H_CEDE returns with IRQs on */ + if (WARN_ON(!(mfmsr() & MSR_EE))) + __hard_irq_enable(); +#endif + } +} + +static int dedicated_cede_loop(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + unsigned long in_purr; + + idle_loop_prolog(&in_purr); + get_lppaca()->donate_dedicated_cpu = 1; + + HMT_medium(); + check_and_cede_processor(); + + get_lppaca()->donate_dedicated_cpu = 0; + + idle_loop_epilog(in_purr); + + return index; +} + +static int shared_cede_loop(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + unsigned long in_purr; + + idle_loop_prolog(&in_purr); + + /* + * Yield the processor to the hypervisor. We return if + * an external interrupt occurs (which are driven prior + * to returning here) or if a prod occurs from another + * processor. When returning here, external interrupts + * are enabled. + */ + check_and_cede_processor(); + + idle_loop_epilog(in_purr); + + return index; +} + +/* + * States for dedicated partition case. + */ +static struct cpuidle_state dedicated_states[] = { + { /* Snooze */ + .name = "snooze", + .desc = "snooze", + .flags = CPUIDLE_FLAG_TIME_VALID, + .exit_latency = 0, + .target_residency = 0, + .enter = &snooze_loop }, + { /* CEDE */ + .name = "CEDE", + .desc = "CEDE", + .flags = CPUIDLE_FLAG_TIME_VALID, + .exit_latency = 10, + .target_residency = 100, + .enter = &dedicated_cede_loop }, +}; + +/* + * States for shared partition case. + */ +static struct cpuidle_state shared_states[] = { + { /* Shared Cede */ + .name = "Shared Cede", + .desc = "Shared Cede", + .flags = CPUIDLE_FLAG_TIME_VALID, + .exit_latency = 0, + .target_residency = 0, + .enter = &shared_cede_loop }, +}; + +static int pseries_cpuidle_add_cpu_notifier(struct notifier_block *n, + unsigned long action, void *hcpu) +{ + int hotcpu = (unsigned long)hcpu; + struct cpuidle_device *dev = + per_cpu(cpuidle_devices, hotcpu); + + if (dev && cpuidle_get_driver()) { + switch (action) { + case CPU_ONLINE: + case CPU_ONLINE_FROZEN: + cpuidle_pause_and_lock(); + cpuidle_enable_device(dev); + cpuidle_resume_and_unlock(); + break; + + case CPU_DEAD: + case CPU_DEAD_FROZEN: + cpuidle_pause_and_lock(); + cpuidle_disable_device(dev); + cpuidle_resume_and_unlock(); + break; + + default: + return NOTIFY_DONE; + } + } + return NOTIFY_OK; +} + +static struct notifier_block setup_hotplug_notifier = { + .notifier_call = pseries_cpuidle_add_cpu_notifier, +}; + +/* + * pseries_cpuidle_driver_init() + */ +static int pseries_cpuidle_driver_init(void) +{ + int idle_state; + struct cpuidle_driver *drv = &pseries_idle_driver; + + drv->state_count = 0; + + for (idle_state = 0; idle_state < max_idle_state; ++idle_state) { + /* Is the state not enabled? */ + if (cpuidle_state_table[idle_state].enter == NULL) + continue; + + drv->states[drv->state_count] = /* structure copy */ + cpuidle_state_table[idle_state]; + + drv->state_count += 1; + } + + return 0; +} + +/* + * pseries_idle_probe() + * Choose state table for shared versus dedicated partition + */ +static int pseries_idle_probe(void) +{ + + if (cpuidle_disable != IDLE_NO_OVERRIDE) + return -ENODEV; + + if (firmware_has_feature(FW_FEATURE_SPLPAR)) { + if (lppaca_shared_proc(get_lppaca())) { + cpuidle_state_table = shared_states; + max_idle_state = ARRAY_SIZE(shared_states); + } else { + cpuidle_state_table = dedicated_states; + max_idle_state = ARRAY_SIZE(dedicated_states); + } + } else + return -ENODEV; + + return 0; +} + +static int __init pseries_processor_idle_init(void) +{ + int retval; + + retval = pseries_idle_probe(); + if (retval) + return retval; + + pseries_cpuidle_driver_init(); + retval = cpuidle_register(&pseries_idle_driver, NULL); + if (retval) { + printk(KERN_DEBUG "Registration of pseries driver failed.\n"); + return retval; + } + + register_cpu_notifier(&setup_hotplug_notifier); + printk(KERN_DEBUG "pseries_idle_driver registered\n"); + return 0; +} + +device_initcall(pseries_processor_idle_init); diff --git a/drivers/cpuidle/cpuidle-ux500.c b/drivers/cpuidle/cpuidle-ux500.c new file mode 100644 index 00000000000..5e35804b1a9 --- /dev/null +++ b/drivers/cpuidle/cpuidle-ux500.c @@ -0,0 +1,131 @@ +/* + * Copyright (c) 2012 Linaro : Daniel Lezcano <daniel.lezcano@linaro.org> (IBM) + * + * Based on the work of Rickard Andersson <rickard.andersson@stericsson.com> + * and Jonas Aaberg <jonas.aberg@stericsson.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/module.h> +#include <linux/cpuidle.h> +#include <linux/spinlock.h> +#include <linux/atomic.h> +#include <linux/smp.h> +#include <linux/mfd/dbx500-prcmu.h> +#include <linux/platform_data/arm-ux500-pm.h> +#include <linux/platform_device.h> + +#include <asm/cpuidle.h> +#include <asm/proc-fns.h> + +static atomic_t master = ATOMIC_INIT(0); +static DEFINE_SPINLOCK(master_lock); + +static inline int ux500_enter_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + int this_cpu = smp_processor_id(); + bool recouple = false; + + if (atomic_inc_return(&master) == num_online_cpus()) { + + /* With this lock, we prevent the other cpu to exit and enter + * this function again and become the master */ + if (!spin_trylock(&master_lock)) + goto wfi; + + /* decouple the gic from the A9 cores */ + if (prcmu_gic_decouple()) { + spin_unlock(&master_lock); + goto out; + } + + /* If an error occur, we will have to recouple the gic + * manually */ + recouple = true; + + /* At this state, as the gic is decoupled, if the other + * cpu is in WFI, we have the guarantee it won't be wake + * up, so we can safely go to retention */ + if (!prcmu_is_cpu_in_wfi(this_cpu ? 0 : 1)) + goto out; + + /* The prcmu will be in charge of watching the interrupts + * and wake up the cpus */ + if (prcmu_copy_gic_settings()) + goto out; + + /* Check in the meantime an interrupt did + * not occur on the gic ... */ + if (prcmu_gic_pending_irq()) + goto out; + + /* ... and the prcmu */ + if (prcmu_pending_irq()) + goto out; + + /* Go to the retention state, the prcmu will wait for the + * cpu to go WFI and this is what happens after exiting this + * 'master' critical section */ + if (prcmu_set_power_state(PRCMU_AP_IDLE, true, true)) + goto out; + + /* When we switch to retention, the prcmu is in charge + * of recoupling the gic automatically */ + recouple = false; + + spin_unlock(&master_lock); + } +wfi: + cpu_do_idle(); +out: + atomic_dec(&master); + + if (recouple) { + prcmu_gic_recouple(); + spin_unlock(&master_lock); + } + + return index; +} + +static struct cpuidle_driver ux500_idle_driver = { + .name = "ux500_idle", + .owner = THIS_MODULE, + .states = { + ARM_CPUIDLE_WFI_STATE, + { + .enter = ux500_enter_idle, + .exit_latency = 70, + .target_residency = 260, + .flags = CPUIDLE_FLAG_TIME_VALID | + CPUIDLE_FLAG_TIMER_STOP, + .name = "ApIdle", + .desc = "ARM Retention", + }, + }, + .safe_state_index = 0, + .state_count = 2, +}; + +static int dbx500_cpuidle_probe(struct platform_device *pdev) +{ + /* Configure wake up reasons */ + prcmu_enable_wakeups(PRCMU_WAKEUP(ARM) | PRCMU_WAKEUP(RTC) | + PRCMU_WAKEUP(ABB)); + + return cpuidle_register(&ux500_idle_driver, NULL); +} + +static struct platform_driver dbx500_cpuidle_plat_driver = { + .driver = { + .name = "cpuidle-dbx500", + .owner = THIS_MODULE, + }, + .probe = dbx500_cpuidle_probe, +}; + +module_platform_driver(dbx500_cpuidle_plat_driver); diff --git a/drivers/cpuidle/cpuidle-zynq.c b/drivers/cpuidle/cpuidle-zynq.c new file mode 100644 index 00000000000..aded7592802 --- /dev/null +++ b/drivers/cpuidle/cpuidle-zynq.c @@ -0,0 +1,88 @@ +/* + * Copyright (C) 2012-2013 Xilinx + * + * CPU idle support for Xilinx Zynq + * + * based on arch/arm/mach-at91/cpuidle.c + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + * + * The cpu idle uses wait-for-interrupt and RAM self refresh in order + * to implement two idle states - + * #1 wait-for-interrupt + * #2 wait-for-interrupt and RAM self refresh + * + * Maintainer: Michal Simek <michal.simek@xilinx.com> + */ + +#include <linux/init.h> +#include <linux/cpu_pm.h> +#include <linux/cpuidle.h> +#include <linux/platform_device.h> +#include <asm/proc-fns.h> +#include <asm/cpuidle.h> + +#define ZYNQ_MAX_STATES 2 + +/* Actual code that puts the SoC in different idle states */ +static int zynq_enter_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + /* Devices must be stopped here */ + cpu_pm_enter(); + + /* Add code for DDR self refresh start */ + cpu_do_idle(); + + /* Add code for DDR self refresh stop */ + cpu_pm_exit(); + + return index; +} + +static struct cpuidle_driver zynq_idle_driver = { + .name = "zynq_idle", + .owner = THIS_MODULE, + .states = { + ARM_CPUIDLE_WFI_STATE, + { + .enter = zynq_enter_idle, + .exit_latency = 10, + .target_residency = 10000, + .flags = CPUIDLE_FLAG_TIME_VALID | + CPUIDLE_FLAG_TIMER_STOP, + .name = "RAM_SR", + .desc = "WFI and RAM Self Refresh", + }, + }, + .safe_state_index = 0, + .state_count = ZYNQ_MAX_STATES, +}; + +/* Initialize CPU idle by registering the idle states */ +static int zynq_cpuidle_probe(struct platform_device *pdev) +{ + pr_info("Xilinx Zynq CpuIdle Driver started\n"); + + return cpuidle_register(&zynq_idle_driver, NULL); +} + +static struct platform_driver zynq_cpuidle_driver = { + .driver = { + .name = "cpuidle-zynq", + .owner = THIS_MODULE, + }, + .probe = zynq_cpuidle_probe, +}; + +module_platform_driver(zynq_cpuidle_driver); diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index a5071084337..cb7019977c5 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -8,105 +8,198 @@ * This code is licenced under the GPL. */ +#include <linux/clockchips.h> #include <linux/kernel.h> #include <linux/mutex.h> #include <linux/sched.h> #include <linux/notifier.h> -#include <linux/pm_qos_params.h> +#include <linux/pm_qos.h> #include <linux/cpu.h> #include <linux/cpuidle.h> #include <linux/ktime.h> #include <linux/hrtimer.h> +#include <linux/module.h> #include <trace/events/power.h> #include "cpuidle.h" DEFINE_PER_CPU(struct cpuidle_device *, cpuidle_devices); +DEFINE_PER_CPU(struct cpuidle_device, cpuidle_dev); DEFINE_MUTEX(cpuidle_lock); LIST_HEAD(cpuidle_detected_devices); -static void (*pm_idle_old)(void); static int enabled_devices; +static int off __read_mostly; +static int initialized __read_mostly; +static bool use_deepest_state __read_mostly; -#if defined(CONFIG_ARCH_HAS_CPU_IDLE_WAIT) -static void cpuidle_kick_cpus(void) +int cpuidle_disabled(void) { - cpu_idle_wait(); + return off; } -#elif defined(CONFIG_SMP) -# error "Arch needs cpu_idle_wait() equivalent here" -#else /* !CONFIG_ARCH_HAS_CPU_IDLE_WAIT && !CONFIG_SMP */ -static void cpuidle_kick_cpus(void) {} -#endif +void disable_cpuidle(void) +{ + off = 1; +} + +/** + * cpuidle_play_dead - cpu off-lining + * + * Returns in case of an error or no driver + */ +int cpuidle_play_dead(void) +{ + struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices); + struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); + int i; + + if (!drv) + return -ENODEV; + + /* Find lowest-power state that supports long-term idle */ + for (i = drv->state_count - 1; i >= CPUIDLE_DRIVER_STATE_START; i--) + if (drv->states[i].enter_dead) + return drv->states[i].enter_dead(dev, i); -static int __cpuidle_register_device(struct cpuidle_device *dev); + return -ENODEV; +} /** - * cpuidle_idle_call - the main idle loop + * cpuidle_use_deepest_state - Enable/disable the "deepest idle" mode. + * @enable: Whether enable or disable the feature. + * + * If the "deepest idle" mode is enabled, cpuidle will ignore the governor and + * always use the state with the greatest exit latency (out of the states that + * are not disabled). * - * NOTE: no locks or semaphores should be used here + * This function can only be called after cpuidle_pause() to avoid races. */ -static void cpuidle_idle_call(void) +void cpuidle_use_deepest_state(bool enable) { - struct cpuidle_device *dev = __get_cpu_var(cpuidle_devices); - struct cpuidle_state *target_state; - int next_state; - - /* check if the device is ready */ - if (!dev || !dev->enabled) { - if (pm_idle_old) - pm_idle_old(); - else -#if defined(CONFIG_ARCH_HAS_DEFAULT_IDLE) - default_idle(); -#else - local_irq_enable(); -#endif - return; + use_deepest_state = enable; +} + +/** + * cpuidle_find_deepest_state - Find the state of the greatest exit latency. + * @drv: cpuidle driver for a given CPU. + * @dev: cpuidle device for a given CPU. + */ +static int cpuidle_find_deepest_state(struct cpuidle_driver *drv, + struct cpuidle_device *dev) +{ + unsigned int latency_req = 0; + int i, ret = CPUIDLE_DRIVER_STATE_START - 1; + + for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) { + struct cpuidle_state *s = &drv->states[i]; + struct cpuidle_state_usage *su = &dev->states_usage[i]; + + if (s->disabled || su->disable || s->exit_latency <= latency_req) + continue; + + latency_req = s->exit_latency; + ret = i; } + return ret; +} -#if 0 - /* shows regressions, re-enable for 2.6.29 */ - /* - * run any timers that can be run now, at this point - * before calculating the idle duration etc. - */ - hrtimer_peek_ahead_timers(); -#endif +/** + * cpuidle_enter_state - enter the state and update stats + * @dev: cpuidle device for this cpu + * @drv: cpuidle driver for this cpu + * @next_state: index into drv->states of the state to enter + */ +int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, + int index) +{ + int entered_state; + + struct cpuidle_state *target_state = &drv->states[index]; + ktime_t time_start, time_end; + s64 diff; - /* - * Call the device's prepare function before calling the - * governor's select function. ->prepare gives the device's - * cpuidle driver a chance to update any dynamic information - * of its cpuidle states for the current idle period, e.g. - * state availability, latencies, residencies, etc. - */ - if (dev->prepare) - dev->prepare(dev); - - /* ask the governor for the next state */ - next_state = cpuidle_curr_governor->select(dev); - if (need_resched()) { + time_start = ktime_get(); + + entered_state = target_state->enter(dev, drv, index); + + time_end = ktime_get(); + + if (!cpuidle_state_is_coupled(dev, drv, entered_state)) local_irq_enable(); - return; + + diff = ktime_to_us(ktime_sub(time_end, time_start)); + if (diff > INT_MAX) + diff = INT_MAX; + + dev->last_residency = (int) diff; + + if (entered_state >= 0) { + /* Update cpuidle counters */ + /* This can be moved to within driver enter routine + * but that results in multiple copies of same code. + */ + dev->states_usage[entered_state].time += dev->last_residency; + dev->states_usage[entered_state].usage++; + } else { + dev->last_residency = 0; } - target_state = &dev->states[next_state]; + return entered_state; +} - /* enter the state and update stats */ - dev->last_state = target_state; - dev->last_residency = target_state->enter(dev, target_state); - if (dev->last_state) - target_state = dev->last_state; +/** + * cpuidle_select - ask the cpuidle framework to choose an idle state + * + * @drv: the cpuidle driver + * @dev: the cpuidle device + * + * Returns the index of the idle state. + */ +int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) +{ + if (off || !initialized) + return -ENODEV; - target_state->time += (unsigned long long)dev->last_residency; - target_state->usage++; + if (!drv || !dev || !dev->enabled) + return -EBUSY; - /* give the governor an opportunity to reflect on the outcome */ - if (cpuidle_curr_governor->reflect) - cpuidle_curr_governor->reflect(dev); - trace_power_end(smp_processor_id()); + if (unlikely(use_deepest_state)) + return cpuidle_find_deepest_state(drv, dev); + + return cpuidle_curr_governor->select(drv, dev); +} + +/** + * cpuidle_enter - enter into the specified idle state + * + * @drv: the cpuidle driver tied with the cpu + * @dev: the cpuidle device + * @index: the index in the idle state table + * + * Returns the index in the idle state, < 0 in case of error. + * The error code depends on the backend driver + */ +int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev, + int index) +{ + if (cpuidle_state_is_coupled(dev, drv, index)) + return cpuidle_enter_state_coupled(dev, drv, index); + return cpuidle_enter_state(dev, drv, index); +} + +/** + * cpuidle_reflect - tell the underlying governor what was the state + * we were in + * + * @dev : the cpuidle device + * @index: the index in the idle state table + * + */ +void cpuidle_reflect(struct cpuidle_device *dev, int index) +{ + if (cpuidle_curr_governor->reflect && !unlikely(use_deepest_state)) + cpuidle_curr_governor->reflect(dev, index); } /** @@ -114,10 +207,10 @@ static void cpuidle_idle_call(void) */ void cpuidle_install_idle_handler(void) { - if (enabled_devices && (pm_idle != cpuidle_idle_call)) { + if (enabled_devices) { /* Make sure all changes finished before we switch to new idle */ smp_wmb(); - pm_idle = cpuidle_idle_call; + initialized = 1; } } @@ -126,9 +219,9 @@ void cpuidle_install_idle_handler(void) */ void cpuidle_uninstall_idle_handler(void) { - if (enabled_devices && pm_idle_old && (pm_idle != pm_idle_old)) { - pm_idle = pm_idle_old; - cpuidle_kick_cpus(); + if (enabled_devices) { + initialized = 0; + kick_all_cpus_sync(); } } @@ -154,6 +247,22 @@ void cpuidle_resume_and_unlock(void) EXPORT_SYMBOL_GPL(cpuidle_resume_and_unlock); +/* Currently used in suspend/resume path to suspend cpuidle */ +void cpuidle_pause(void) +{ + mutex_lock(&cpuidle_lock); + cpuidle_uninstall_idle_handler(); + mutex_unlock(&cpuidle_lock); +} + +/* Currently used in suspend/resume path to resume cpuidle */ +void cpuidle_resume(void) +{ + mutex_lock(&cpuidle_lock); + cpuidle_install_idle_handler(); + mutex_unlock(&cpuidle_lock); +} + /** * cpuidle_enable_device - enables idle PM for a CPU * @dev: the CPU @@ -163,35 +272,34 @@ EXPORT_SYMBOL_GPL(cpuidle_resume_and_unlock); */ int cpuidle_enable_device(struct cpuidle_device *dev) { - int ret, i; + int ret; + struct cpuidle_driver *drv; + + if (!dev) + return -EINVAL; if (dev->enabled) return 0; - if (!cpuidle_get_driver() || !cpuidle_curr_governor) + + drv = cpuidle_get_cpu_driver(dev); + + if (!drv || !cpuidle_curr_governor) return -EIO; - if (!dev->state_count) + + if (!dev->registered) return -EINVAL; - if (dev->registered == 0) { - ret = __cpuidle_register_device(dev); - if (ret) - return ret; - } + if (!dev->state_count) + dev->state_count = drv->state_count; - if ((ret = cpuidle_add_state_sysfs(dev))) + ret = cpuidle_add_device_sysfs(dev); + if (ret) return ret; if (cpuidle_curr_governor->enable && - (ret = cpuidle_curr_governor->enable(dev))) + (ret = cpuidle_curr_governor->enable(drv, dev))) goto fail_sysfs; - for (i = 0; i < dev->state_count; i++) { - dev->states[i].usage = 0; - dev->states[i].time = 0; - } - dev->last_residency = 0; - dev->last_state = NULL; - smp_wmb(); dev->enabled = 1; @@ -200,7 +308,7 @@ int cpuidle_enable_device(struct cpuidle_device *dev) return 0; fail_sysfs: - cpuidle_remove_state_sysfs(dev); + cpuidle_remove_device_sysfs(dev); return ret; } @@ -216,60 +324,39 @@ EXPORT_SYMBOL_GPL(cpuidle_enable_device); */ void cpuidle_disable_device(struct cpuidle_device *dev) { - if (!dev->enabled) + struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); + + if (!dev || !dev->enabled) return; - if (!cpuidle_get_driver() || !cpuidle_curr_governor) + + if (!drv || !cpuidle_curr_governor) return; dev->enabled = 0; if (cpuidle_curr_governor->disable) - cpuidle_curr_governor->disable(dev); + cpuidle_curr_governor->disable(drv, dev); - cpuidle_remove_state_sysfs(dev); + cpuidle_remove_device_sysfs(dev); enabled_devices--; } EXPORT_SYMBOL_GPL(cpuidle_disable_device); -#ifdef CONFIG_ARCH_HAS_CPU_RELAX -static int poll_idle(struct cpuidle_device *dev, struct cpuidle_state *st) +static void __cpuidle_unregister_device(struct cpuidle_device *dev) { - ktime_t t1, t2; - s64 diff; - int ret; - - t1 = ktime_get(); - local_irq_enable(); - while (!need_resched()) - cpu_relax(); - - t2 = ktime_get(); - diff = ktime_to_us(ktime_sub(t2, t1)); - if (diff > INT_MAX) - diff = INT_MAX; + struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); - ret = (int) diff; - return ret; + list_del(&dev->device_list); + per_cpu(cpuidle_devices, dev->cpu) = NULL; + module_put(drv->owner); } -static void poll_idle_init(struct cpuidle_device *dev) +static void __cpuidle_device_init(struct cpuidle_device *dev) { - struct cpuidle_state *state = &dev->states[0]; - - cpuidle_set_statedata(state, NULL); - - snprintf(state->name, CPUIDLE_NAME_LEN, "C0"); - snprintf(state->desc, CPUIDLE_DESC_LEN, "CPUIDLE CORE POLL IDLE"); - state->exit_latency = 0; - state->target_residency = 0; - state->power_usage = -1; - state->flags = CPUIDLE_FLAG_POLL; - state->enter = poll_idle; + memset(dev->states_usage, 0, sizeof(dev->states_usage)); + dev->last_residency = 0; } -#else -static void poll_idle_init(struct cpuidle_device *dev) {} -#endif /* CONFIG_ARCH_HAS_CPU_RELAX */ /** * __cpuidle_register_device - internal register function called before register @@ -281,47 +368,21 @@ static void poll_idle_init(struct cpuidle_device *dev) {} static int __cpuidle_register_device(struct cpuidle_device *dev) { int ret; - struct sys_device *sys_dev = get_cpu_sysdev((unsigned long)dev->cpu); - struct cpuidle_driver *cpuidle_driver = cpuidle_get_driver(); + struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); - if (!sys_dev) - return -EINVAL; - if (!try_module_get(cpuidle_driver->owner)) + if (!try_module_get(drv->owner)) return -EINVAL; - init_completion(&dev->kobj_unregister); - - poll_idle_init(dev); - - /* - * cpuidle driver should set the dev->power_specified bit - * before registering the device if the driver provides - * power_usage numbers. - * - * For those devices whose ->power_specified is not set, - * we fill in power_usage with decreasing values as the - * cpuidle code has an implicit assumption that state Cn - * uses less power than C(n-1). - * - * With CONFIG_ARCH_HAS_CPU_RELAX, C0 is already assigned - * an power value of -1. So we use -2, -3, etc, for other - * c-states. - */ - if (!dev->power_specified) { - int i; - for (i = CPUIDLE_DRIVER_STATE_START; i < dev->state_count; i++) - dev->states[i].power_usage = -1 - i; - } - per_cpu(cpuidle_devices, dev->cpu) = dev; list_add(&dev->device_list, &cpuidle_detected_devices); - if ((ret = cpuidle_add_sysfs(sys_dev))) { - module_put(cpuidle_driver->owner); - return ret; - } - dev->registered = 1; - return 0; + ret = cpuidle_coupled_register_device(dev); + if (ret) + __cpuidle_unregister_device(dev); + else + dev->registered = 1; + + return ret; } /** @@ -330,22 +391,42 @@ static int __cpuidle_register_device(struct cpuidle_device *dev) */ int cpuidle_register_device(struct cpuidle_device *dev) { - int ret; + int ret = -EBUSY; + + if (!dev) + return -EINVAL; mutex_lock(&cpuidle_lock); - if ((ret = __cpuidle_register_device(dev))) { - mutex_unlock(&cpuidle_lock); - return ret; - } + if (dev->registered) + goto out_unlock; + + __cpuidle_device_init(dev); + + ret = __cpuidle_register_device(dev); + if (ret) + goto out_unlock; + + ret = cpuidle_add_sysfs(dev); + if (ret) + goto out_unregister; + + ret = cpuidle_enable_device(dev); + if (ret) + goto out_sysfs; - cpuidle_enable_device(dev); cpuidle_install_idle_handler(); +out_unlock: mutex_unlock(&cpuidle_lock); - return 0; + return ret; +out_sysfs: + cpuidle_remove_sysfs(dev); +out_unregister: + __cpuidle_unregister_device(dev); + goto out_unlock; } EXPORT_SYMBOL_GPL(cpuidle_register_device); @@ -356,28 +437,95 @@ EXPORT_SYMBOL_GPL(cpuidle_register_device); */ void cpuidle_unregister_device(struct cpuidle_device *dev) { - struct sys_device *sys_dev = get_cpu_sysdev((unsigned long)dev->cpu); - struct cpuidle_driver *cpuidle_driver = cpuidle_get_driver(); - - if (dev->registered == 0) + if (!dev || dev->registered == 0) return; cpuidle_pause_and_lock(); cpuidle_disable_device(dev); - cpuidle_remove_sysfs(sys_dev); - list_del(&dev->device_list); - wait_for_completion(&dev->kobj_unregister); - per_cpu(cpuidle_devices, dev->cpu) = NULL; + cpuidle_remove_sysfs(dev); - cpuidle_resume_and_unlock(); + __cpuidle_unregister_device(dev); - module_put(cpuidle_driver->owner); + cpuidle_coupled_unregister_device(dev); + + cpuidle_resume_and_unlock(); } EXPORT_SYMBOL_GPL(cpuidle_unregister_device); +/** + * cpuidle_unregister: unregister a driver and the devices. This function + * can be used only if the driver has been previously registered through + * the cpuidle_register function. + * + * @drv: a valid pointer to a struct cpuidle_driver + */ +void cpuidle_unregister(struct cpuidle_driver *drv) +{ + int cpu; + struct cpuidle_device *device; + + for_each_cpu(cpu, drv->cpumask) { + device = &per_cpu(cpuidle_dev, cpu); + cpuidle_unregister_device(device); + } + + cpuidle_unregister_driver(drv); +} +EXPORT_SYMBOL_GPL(cpuidle_unregister); + +/** + * cpuidle_register: registers the driver and the cpu devices with the + * coupled_cpus passed as parameter. This function is used for all common + * initialization pattern there are in the arch specific drivers. The + * devices is globally defined in this file. + * + * @drv : a valid pointer to a struct cpuidle_driver + * @coupled_cpus: a cpumask for the coupled states + * + * Returns 0 on success, < 0 otherwise + */ +int cpuidle_register(struct cpuidle_driver *drv, + const struct cpumask *const coupled_cpus) +{ + int ret, cpu; + struct cpuidle_device *device; + + ret = cpuidle_register_driver(drv); + if (ret) { + pr_err("failed to register cpuidle driver\n"); + return ret; + } + + for_each_cpu(cpu, drv->cpumask) { + device = &per_cpu(cpuidle_dev, cpu); + device->cpu = cpu; + +#ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED + /* + * On multiplatform for ARM, the coupled idle states could be + * enabled in the kernel even if the cpuidle driver does not + * use it. Note, coupled_cpus is a struct copy. + */ + if (coupled_cpus) + device->coupled_cpus = *coupled_cpus; +#endif + ret = cpuidle_register_device(device); + if (!ret) + continue; + + pr_err("Failed to register cpuidle device for cpu%d\n", cpu); + + cpuidle_unregister(drv); + break; + } + + return ret; +} +EXPORT_SYMBOL_GPL(cpuidle_register); + #ifdef CONFIG_SMP static void smp_callback(void *v) @@ -420,9 +568,10 @@ static int __init cpuidle_init(void) { int ret; - pm_idle_old = pm_idle; + if (cpuidle_disabled()) + return -ENODEV; - ret = cpuidle_add_class_sysfs(&cpu_sysdev_class); + ret = cpuidle_add_interface(cpu_subsys.dev_root); if (ret) return ret; @@ -431,4 +580,5 @@ static int __init cpuidle_init(void) return 0; } +module_param(off, int, 0444); core_initcall(cpuidle_init); diff --git a/drivers/cpuidle/cpuidle.h b/drivers/cpuidle/cpuidle.h index 33e50d556f1..ee97e9672ec 100644 --- a/drivers/cpuidle/cpuidle.h +++ b/drivers/cpuidle/cpuidle.h @@ -5,14 +5,15 @@ #ifndef __DRIVER_CPUIDLE_H #define __DRIVER_CPUIDLE_H -#include <linux/sysdev.h> - /* For internal use only */ extern struct cpuidle_governor *cpuidle_curr_governor; extern struct list_head cpuidle_governors; extern struct list_head cpuidle_detected_devices; extern struct mutex cpuidle_lock; extern spinlock_t cpuidle_driver_lock; +extern int cpuidle_disabled(void); +extern int cpuidle_enter_state(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int next_state); /* idle loop */ extern void cpuidle_install_idle_handler(void); @@ -22,11 +23,44 @@ extern void cpuidle_uninstall_idle_handler(void); extern int cpuidle_switch_governor(struct cpuidle_governor *gov); /* sysfs */ -extern int cpuidle_add_class_sysfs(struct sysdev_class *cls); -extern void cpuidle_remove_class_sysfs(struct sysdev_class *cls); -extern int cpuidle_add_state_sysfs(struct cpuidle_device *device); -extern void cpuidle_remove_state_sysfs(struct cpuidle_device *device); -extern int cpuidle_add_sysfs(struct sys_device *sysdev); -extern void cpuidle_remove_sysfs(struct sys_device *sysdev); + +struct device; + +extern int cpuidle_add_interface(struct device *dev); +extern void cpuidle_remove_interface(struct device *dev); +extern int cpuidle_add_device_sysfs(struct cpuidle_device *device); +extern void cpuidle_remove_device_sysfs(struct cpuidle_device *device); +extern int cpuidle_add_sysfs(struct cpuidle_device *dev); +extern void cpuidle_remove_sysfs(struct cpuidle_device *dev); + +#ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED +bool cpuidle_state_is_coupled(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int state); +int cpuidle_enter_state_coupled(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int next_state); +int cpuidle_coupled_register_device(struct cpuidle_device *dev); +void cpuidle_coupled_unregister_device(struct cpuidle_device *dev); +#else +static inline bool cpuidle_state_is_coupled(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int state) +{ + return false; +} + +static inline int cpuidle_enter_state_coupled(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int next_state) +{ + return -1; +} + +static inline int cpuidle_coupled_register_device(struct cpuidle_device *dev) +{ + return 0; +} + +static inline void cpuidle_coupled_unregister_device(struct cpuidle_device *dev) +{ +} +#endif #endif /* __DRIVER_CPUIDLE_H */ diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c index fd1601e3d12..9634f20e392 100644 --- a/drivers/cpuidle/driver.c +++ b/drivers/cpuidle/driver.c @@ -10,59 +10,386 @@ #include <linux/mutex.h> #include <linux/module.h> +#include <linux/sched.h> #include <linux/cpuidle.h> +#include <linux/cpumask.h> +#include <linux/clockchips.h> #include "cpuidle.h" -static struct cpuidle_driver *cpuidle_curr_driver; DEFINE_SPINLOCK(cpuidle_driver_lock); +#ifdef CONFIG_CPU_IDLE_MULTIPLE_DRIVERS + +static DEFINE_PER_CPU(struct cpuidle_driver *, cpuidle_drivers); + /** - * cpuidle_register_driver - registers a driver - * @drv: the driver + * __cpuidle_get_cpu_driver - return the cpuidle driver tied to a CPU. + * @cpu: the CPU handled by the driver + * + * Returns a pointer to struct cpuidle_driver or NULL if no driver has been + * registered for @cpu. */ -int cpuidle_register_driver(struct cpuidle_driver *drv) +static struct cpuidle_driver *__cpuidle_get_cpu_driver(int cpu) { - if (!drv) - return -EINVAL; + return per_cpu(cpuidle_drivers, cpu); +} - spin_lock(&cpuidle_driver_lock); - if (cpuidle_curr_driver) { - spin_unlock(&cpuidle_driver_lock); - return -EBUSY; +/** + * __cpuidle_unset_driver - unset per CPU driver variables. + * @drv: a valid pointer to a struct cpuidle_driver + * + * For each CPU in the driver's CPU mask, unset the registered driver per CPU + * variable. If @drv is different from the registered driver, the corresponding + * variable is not cleared. + */ +static inline void __cpuidle_unset_driver(struct cpuidle_driver *drv) +{ + int cpu; + + for_each_cpu(cpu, drv->cpumask) { + + if (drv != __cpuidle_get_cpu_driver(cpu)) + continue; + + per_cpu(cpuidle_drivers, cpu) = NULL; + } +} + +/** + * __cpuidle_set_driver - set per CPU driver variables for the given driver. + * @drv: a valid pointer to a struct cpuidle_driver + * + * For each CPU in the driver's cpumask, unset the registered driver per CPU + * to @drv. + * + * Returns 0 on success, -EBUSY if the CPUs have driver(s) already. + */ +static inline int __cpuidle_set_driver(struct cpuidle_driver *drv) +{ + int cpu; + + for_each_cpu(cpu, drv->cpumask) { + + if (__cpuidle_get_cpu_driver(cpu)) { + __cpuidle_unset_driver(drv); + return -EBUSY; + } + + per_cpu(cpuidle_drivers, cpu) = drv; } - cpuidle_curr_driver = drv; - spin_unlock(&cpuidle_driver_lock); return 0; } -EXPORT_SYMBOL_GPL(cpuidle_register_driver); +#else + +static struct cpuidle_driver *cpuidle_curr_driver; /** - * cpuidle_get_driver - return the current driver + * __cpuidle_get_cpu_driver - return the global cpuidle driver pointer. + * @cpu: ignored without the multiple driver support + * + * Return a pointer to a struct cpuidle_driver object or NULL if no driver was + * previously registered. */ -struct cpuidle_driver *cpuidle_get_driver(void) +static inline struct cpuidle_driver *__cpuidle_get_cpu_driver(int cpu) { return cpuidle_curr_driver; } -EXPORT_SYMBOL_GPL(cpuidle_get_driver); /** - * cpuidle_unregister_driver - unregisters a driver - * @drv: the driver + * __cpuidle_set_driver - assign the global cpuidle driver variable. + * @drv: pointer to a struct cpuidle_driver object + * + * Returns 0 on success, -EBUSY if the driver is already registered. */ -void cpuidle_unregister_driver(struct cpuidle_driver *drv) +static inline int __cpuidle_set_driver(struct cpuidle_driver *drv) +{ + if (cpuidle_curr_driver) + return -EBUSY; + + cpuidle_curr_driver = drv; + + return 0; +} + +/** + * __cpuidle_unset_driver - unset the global cpuidle driver variable. + * @drv: a pointer to a struct cpuidle_driver + * + * Reset the global cpuidle variable to NULL. If @drv does not match the + * registered driver, do nothing. + */ +static inline void __cpuidle_unset_driver(struct cpuidle_driver *drv) +{ + if (drv == cpuidle_curr_driver) + cpuidle_curr_driver = NULL; +} + +#endif + +/** + * cpuidle_setup_broadcast_timer - enable/disable the broadcast timer + * @arg: a void pointer used to match the SMP cross call API + * + * @arg is used as a value of type 'long' with one of the two values: + * - CLOCK_EVT_NOTIFY_BROADCAST_ON + * - CLOCK_EVT_NOTIFY_BROADCAST_OFF + * + * Set the broadcast timer notification for the current CPU. This function + * is executed per CPU by an SMP cross call. It not supposed to be called + * directly. + */ +static void cpuidle_setup_broadcast_timer(void *arg) +{ + int cpu = smp_processor_id(); + clockevents_notify((long)(arg), &cpu); +} + +/** + * __cpuidle_driver_init - initialize the driver's internal data + * @drv: a valid pointer to a struct cpuidle_driver + */ +static void __cpuidle_driver_init(struct cpuidle_driver *drv) +{ + int i; + + drv->refcnt = 0; + + /* + * Use all possible CPUs as the default, because if the kernel boots + * with some CPUs offline and then we online one of them, the CPU + * notifier has to know which driver to assign. + */ + if (!drv->cpumask) + drv->cpumask = (struct cpumask *)cpu_possible_mask; + + /* + * Look for the timer stop flag in the different states, so that we know + * if the broadcast timer has to be set up. The loop is in the reverse + * order, because usually one of the deeper states have this flag set. + */ + for (i = drv->state_count - 1; i >= 0 ; i--) { + if (drv->states[i].flags & CPUIDLE_FLAG_TIMER_STOP) { + drv->bctimer = 1; + break; + } + } +} + +#ifdef CONFIG_ARCH_HAS_CPU_RELAX +static int poll_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + ktime_t t1, t2; + s64 diff; + + t1 = ktime_get(); + local_irq_enable(); + if (!current_set_polling_and_test()) { + while (!need_resched()) + cpu_relax(); + } + current_clr_polling(); + + t2 = ktime_get(); + diff = ktime_to_us(ktime_sub(t2, t1)); + if (diff > INT_MAX) + diff = INT_MAX; + + dev->last_residency = (int) diff; + + return index; +} + +static void poll_idle_init(struct cpuidle_driver *drv) +{ + struct cpuidle_state *state = &drv->states[0]; + + snprintf(state->name, CPUIDLE_NAME_LEN, "POLL"); + snprintf(state->desc, CPUIDLE_DESC_LEN, "CPUIDLE CORE POLL IDLE"); + state->exit_latency = 0; + state->target_residency = 0; + state->power_usage = -1; + state->flags = CPUIDLE_FLAG_TIME_VALID; + state->enter = poll_idle; + state->disabled = false; +} +#else +static void poll_idle_init(struct cpuidle_driver *drv) {} +#endif /* !CONFIG_ARCH_HAS_CPU_RELAX */ + +/** + * __cpuidle_register_driver: register the driver + * @drv: a valid pointer to a struct cpuidle_driver + * + * Do some sanity checks, initialize the driver, assign the driver to the + * global cpuidle driver variable(s) and set up the broadcast timer if the + * cpuidle driver has some states that shut down the local timer. + * + * Returns 0 on success, a negative error code otherwise: + * * -EINVAL if the driver pointer is NULL or no idle states are available + * * -ENODEV if the cpuidle framework is disabled + * * -EBUSY if the driver is already assigned to the global variable(s) + */ +static int __cpuidle_register_driver(struct cpuidle_driver *drv) { - if (drv != cpuidle_curr_driver) { - WARN(1, "invalid cpuidle_unregister_driver(%s)\n", - drv->name); + int ret; + + if (!drv || !drv->state_count) + return -EINVAL; + + if (cpuidle_disabled()) + return -ENODEV; + + __cpuidle_driver_init(drv); + + ret = __cpuidle_set_driver(drv); + if (ret) + return ret; + + if (drv->bctimer) + on_each_cpu_mask(drv->cpumask, cpuidle_setup_broadcast_timer, + (void *)CLOCK_EVT_NOTIFY_BROADCAST_ON, 1); + + poll_idle_init(drv); + + return 0; +} + +/** + * __cpuidle_unregister_driver - unregister the driver + * @drv: a valid pointer to a struct cpuidle_driver + * + * Check if the driver is no longer in use, reset the global cpuidle driver + * variable(s) and disable the timer broadcast notification mechanism if it was + * in use. + * + */ +static void __cpuidle_unregister_driver(struct cpuidle_driver *drv) +{ + if (WARN_ON(drv->refcnt > 0)) return; + + if (drv->bctimer) { + drv->bctimer = 0; + on_each_cpu_mask(drv->cpumask, cpuidle_setup_broadcast_timer, + (void *)CLOCK_EVT_NOTIFY_BROADCAST_OFF, 1); } + __cpuidle_unset_driver(drv); +} + +/** + * cpuidle_register_driver - registers a driver + * @drv: a pointer to a valid struct cpuidle_driver + * + * Register the driver under a lock to prevent concurrent attempts to + * [un]register the driver from occuring at the same time. + * + * Returns 0 on success, a negative error code (returned by + * __cpuidle_register_driver()) otherwise. + */ +int cpuidle_register_driver(struct cpuidle_driver *drv) +{ + int ret; + spin_lock(&cpuidle_driver_lock); - cpuidle_curr_driver = NULL; + ret = __cpuidle_register_driver(drv); spin_unlock(&cpuidle_driver_lock); + + return ret; } +EXPORT_SYMBOL_GPL(cpuidle_register_driver); +/** + * cpuidle_unregister_driver - unregisters a driver + * @drv: a pointer to a valid struct cpuidle_driver + * + * Unregisters the cpuidle driver under a lock to prevent concurrent attempts + * to [un]register the driver from occuring at the same time. @drv has to + * match the currently registered driver. + */ +void cpuidle_unregister_driver(struct cpuidle_driver *drv) +{ + spin_lock(&cpuidle_driver_lock); + __cpuidle_unregister_driver(drv); + spin_unlock(&cpuidle_driver_lock); +} EXPORT_SYMBOL_GPL(cpuidle_unregister_driver); + +/** + * cpuidle_get_driver - return the driver tied to the current CPU. + * + * Returns a struct cpuidle_driver pointer, or NULL if no driver is registered. + */ +struct cpuidle_driver *cpuidle_get_driver(void) +{ + struct cpuidle_driver *drv; + int cpu; + + cpu = get_cpu(); + drv = __cpuidle_get_cpu_driver(cpu); + put_cpu(); + + return drv; +} +EXPORT_SYMBOL_GPL(cpuidle_get_driver); + +/** + * cpuidle_get_cpu_driver - return the driver registered for a CPU. + * @dev: a valid pointer to a struct cpuidle_device + * + * Returns a struct cpuidle_driver pointer, or NULL if no driver is registered + * for the CPU associated with @dev. + */ +struct cpuidle_driver *cpuidle_get_cpu_driver(struct cpuidle_device *dev) +{ + if (!dev) + return NULL; + + return __cpuidle_get_cpu_driver(dev->cpu); +} +EXPORT_SYMBOL_GPL(cpuidle_get_cpu_driver); + +/** + * cpuidle_driver_ref - get a reference to the driver. + * + * Increment the reference counter of the cpuidle driver associated with + * the current CPU. + * + * Returns a pointer to the driver, or NULL if the current CPU has no driver. + */ +struct cpuidle_driver *cpuidle_driver_ref(void) +{ + struct cpuidle_driver *drv; + + spin_lock(&cpuidle_driver_lock); + + drv = cpuidle_get_driver(); + if (drv) + drv->refcnt++; + + spin_unlock(&cpuidle_driver_lock); + return drv; +} + +/** + * cpuidle_driver_unref - puts down the refcount for the driver + * + * Decrement the reference counter of the cpuidle driver associated with + * the current CPU. + */ +void cpuidle_driver_unref(void) +{ + struct cpuidle_driver *drv; + + spin_lock(&cpuidle_driver_lock); + + drv = cpuidle_get_driver(); + if (drv && !WARN_ON(drv->refcnt <= 0)) + drv->refcnt--; + + spin_unlock(&cpuidle_driver_lock); +} diff --git a/drivers/cpuidle/governor.c b/drivers/cpuidle/governor.c index 724c164d31c..ca89412f512 100644 --- a/drivers/cpuidle/governor.c +++ b/drivers/cpuidle/governor.c @@ -81,6 +81,9 @@ int cpuidle_register_governor(struct cpuidle_governor *gov) if (!gov || !gov->select) return -EINVAL; + if (cpuidle_disabled()) + return -ENODEV; + mutex_lock(&cpuidle_lock); if (__cpuidle_find_governor(gov->name) == NULL) { ret = 0; @@ -93,46 +96,3 @@ int cpuidle_register_governor(struct cpuidle_governor *gov) return ret; } - -/** - * cpuidle_replace_governor - find a replacement governor - * @exclude_rating: the rating that will be skipped while looking for - * new governor. - */ -static struct cpuidle_governor *cpuidle_replace_governor(int exclude_rating) -{ - struct cpuidle_governor *gov; - struct cpuidle_governor *ret_gov = NULL; - unsigned int max_rating = 0; - - list_for_each_entry(gov, &cpuidle_governors, governor_list) { - if (gov->rating == exclude_rating) - continue; - if (gov->rating > max_rating) { - max_rating = gov->rating; - ret_gov = gov; - } - } - - return ret_gov; -} - -/** - * cpuidle_unregister_governor - unregisters a governor - * @gov: the governor - */ -void cpuidle_unregister_governor(struct cpuidle_governor *gov) -{ - if (!gov) - return; - - mutex_lock(&cpuidle_lock); - if (gov == cpuidle_curr_governor) { - struct cpuidle_governor *new_gov; - new_gov = cpuidle_replace_governor(gov->rating); - cpuidle_switch_governor(new_gov); - } - list_del(&gov->governor_list); - mutex_unlock(&cpuidle_lock); -} - diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c index 12c98900dcf..9f08e8cce1a 100644 --- a/drivers/cpuidle/governors/ladder.c +++ b/drivers/cpuidle/governors/ladder.c @@ -14,8 +14,8 @@ #include <linux/kernel.h> #include <linux/cpuidle.h> -#include <linux/pm_qos_params.h> -#include <linux/moduleparam.h> +#include <linux/pm_qos.h> +#include <linux/module.h> #include <linux/jiffies.h> #include <asm/io.h> @@ -60,9 +60,11 @@ static inline void ladder_do_selection(struct ladder_device *ldev, /** * ladder_select_state - selects the next state to enter + * @drv: cpuidle driver * @dev: the CPU */ -static int ladder_select_state(struct cpuidle_device *dev) +static int ladder_select_state(struct cpuidle_driver *drv, + struct cpuidle_device *dev) { struct ladder_device *ldev = &__get_cpu_var(ladder_devices); struct ladder_device_state *last_state; @@ -77,15 +79,19 @@ static int ladder_select_state(struct cpuidle_device *dev) last_state = &ldev->states[last_idx]; - if (dev->states[last_idx].flags & CPUIDLE_FLAG_TIME_VALID) - last_residency = cpuidle_get_last_residency(dev) - dev->states[last_idx].exit_latency; + if (drv->states[last_idx].flags & CPUIDLE_FLAG_TIME_VALID) { + last_residency = cpuidle_get_last_residency(dev) - \ + drv->states[last_idx].exit_latency; + } else last_residency = last_state->threshold.promotion_time + 1; /* consider promotion */ - if (last_idx < dev->state_count - 1 && + if (last_idx < drv->state_count - 1 && + !drv->states[last_idx + 1].disabled && + !dev->states_usage[last_idx + 1].disable && last_residency > last_state->threshold.promotion_time && - dev->states[last_idx + 1].exit_latency <= latency_req) { + drv->states[last_idx + 1].exit_latency <= latency_req) { last_state->stats.promotion_count++; last_state->stats.demotion_count = 0; if (last_state->stats.promotion_count >= last_state->threshold.promotion_count) { @@ -96,11 +102,13 @@ static int ladder_select_state(struct cpuidle_device *dev) /* consider demotion */ if (last_idx > CPUIDLE_DRIVER_STATE_START && - dev->states[last_idx].exit_latency > latency_req) { + (drv->states[last_idx].disabled || + dev->states_usage[last_idx].disable || + drv->states[last_idx].exit_latency > latency_req)) { int i; for (i = last_idx - 1; i > CPUIDLE_DRIVER_STATE_START; i--) { - if (dev->states[i].exit_latency <= latency_req) + if (drv->states[i].exit_latency <= latency_req) break; } ladder_do_selection(ldev, last_idx, i); @@ -123,9 +131,11 @@ static int ladder_select_state(struct cpuidle_device *dev) /** * ladder_enable_device - setup for the governor + * @drv: cpuidle driver * @dev: the CPU */ -static int ladder_enable_device(struct cpuidle_device *dev) +static int ladder_enable_device(struct cpuidle_driver *drv, + struct cpuidle_device *dev) { int i; struct ladder_device *ldev = &per_cpu(ladder_devices, dev->cpu); @@ -134,8 +144,8 @@ static int ladder_enable_device(struct cpuidle_device *dev) ldev->last_state_idx = CPUIDLE_DRIVER_STATE_START; - for (i = 0; i < dev->state_count; i++) { - state = &dev->states[i]; + for (i = 0; i < drv->state_count; i++) { + state = &drv->states[i]; lstate = &ldev->states[i]; lstate->stats.promotion_count = 0; @@ -144,7 +154,7 @@ static int ladder_enable_device(struct cpuidle_device *dev) lstate->threshold.promotion_count = PROMOTION_COUNT; lstate->threshold.demotion_count = DEMOTION_COUNT; - if (i < dev->state_count - 1) + if (i < drv->state_count - 1) lstate->threshold.promotion_time = state->exit_latency; if (i > 0) lstate->threshold.demotion_time = state->exit_latency; @@ -153,11 +163,24 @@ static int ladder_enable_device(struct cpuidle_device *dev) return 0; } +/** + * ladder_reflect - update the correct last_state_idx + * @dev: the CPU + * @index: the index of actual state entered + */ +static void ladder_reflect(struct cpuidle_device *dev, int index) +{ + struct ladder_device *ldev = &__get_cpu_var(ladder_devices); + if (index > 0) + ldev->last_state_idx = index; +} + static struct cpuidle_governor ladder_governor = { .name = "ladder", .rating = 10, .enable = ladder_enable_device, .select = ladder_select_state, + .reflect = ladder_reflect, .owner = THIS_MODULE, }; @@ -169,14 +192,4 @@ static int __init init_ladder(void) return cpuidle_register_governor(&ladder_governor); } -/** - * exit_ladder - exits the governor - */ -static void __exit exit_ladder(void) -{ - cpuidle_unregister_governor(&ladder_governor); -} - -MODULE_LICENSE("GPL"); -module_init(init_ladder); -module_exit(exit_ladder); +postcore_initcall(init_ladder); diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index f508690eb95..c4f80c15a48 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -12,14 +12,24 @@ #include <linux/kernel.h> #include <linux/cpuidle.h> -#include <linux/pm_qos_params.h> +#include <linux/pm_qos.h> #include <linux/time.h> #include <linux/ktime.h> #include <linux/hrtimer.h> #include <linux/tick.h> #include <linux/sched.h> #include <linux/math64.h> +#include <linux/module.h> +/* + * Please note when changing the tuning values: + * If (MAX_INTERESTING-1) * RESOLUTION > UINT_MAX, the result of + * a scaling operation multiplication may overflow on 32 bit platforms. + * In that case, #define RESOLUTION as ULL to get 64 bit result: + * #define RESOLUTION 1024ULL + * + * The default values do not overflow. + */ #define BUCKETS 12 #define INTERVALS 8 #define RESOLUTION 1024 @@ -112,12 +122,11 @@ struct menu_device { int last_state_idx; int needs_update; - unsigned int expected_us; - u64 predicted_us; - unsigned int exit_us; + unsigned int next_timer_us; + unsigned int predicted_us; unsigned int bucket; - u64 correction_factor[BUCKETS]; - u32 intervals[INTERVALS]; + unsigned int correction_factor[BUCKETS]; + unsigned int intervals[INTERVALS]; int interval_ptr; }; @@ -182,7 +191,7 @@ static inline int performance_multiplier(void) static DEFINE_PER_CPU(struct menu_device, menu_devices); -static void menu_update(struct cpuidle_device *dev); +static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev); /* This implements DIV_ROUND_CLOSEST but avoids 64 bit division */ static u64 div_round64(u64 dividend, u32 divisor) @@ -196,110 +205,156 @@ static u64 div_round64(u64 dividend, u32 divisor) * of points is below a threshold. If it is... then use the * average of these 8 points as the estimated value. */ -static void detect_repeating_patterns(struct menu_device *data) +static void get_typical_interval(struct menu_device *data) { - int i; - uint64_t avg = 0; - uint64_t stddev = 0; /* contains the square of the std deviation */ - - /* first calculate average and standard deviation of the past */ - for (i = 0; i < INTERVALS; i++) - avg += data->intervals[i]; - avg = avg / INTERVALS; - - /* if the avg is beyond the known next tick, it's worthless */ - if (avg > data->expected_us) - return; - - for (i = 0; i < INTERVALS; i++) - stddev += (data->intervals[i] - avg) * - (data->intervals[i] - avg); - - stddev = stddev / INTERVALS; + int i, divisor; + unsigned int max, thresh; + uint64_t avg, stddev; + + thresh = UINT_MAX; /* Discard outliers above this value */ + +again: + + /* First calculate the average of past intervals */ + max = 0; + avg = 0; + divisor = 0; + for (i = 0; i < INTERVALS; i++) { + unsigned int value = data->intervals[i]; + if (value <= thresh) { + avg += value; + divisor++; + if (value > max) + max = value; + } + } + do_div(avg, divisor); + + /* Then try to determine standard deviation */ + stddev = 0; + for (i = 0; i < INTERVALS; i++) { + unsigned int value = data->intervals[i]; + if (value <= thresh) { + int64_t diff = value - avg; + stddev += diff * diff; + } + } + do_div(stddev, divisor); + /* + * The typical interval is obtained when standard deviation is small + * or standard deviation is small compared to the average interval. + * + * int_sqrt() formal parameter type is unsigned long. When the + * greatest difference to an outlier exceeds ~65 ms * sqrt(divisor) + * the resulting squared standard deviation exceeds the input domain + * of int_sqrt on platforms where unsigned long is 32 bits in size. + * In such case reject the candidate average. + * + * Use this result only if there is no timer to wake us up sooner. + */ + if (likely(stddev <= ULONG_MAX)) { + stddev = int_sqrt(stddev); + if (((avg > stddev * 6) && (divisor * 4 >= INTERVALS * 3)) + || stddev <= 20) { + if (data->next_timer_us > avg) + data->predicted_us = avg; + return; + } + } /* - * now.. if stddev is small.. then assume we have a - * repeating pattern and predict we keep doing this. + * If we have outliers to the upside in our distribution, discard + * those by setting the threshold to exclude these outliers, then + * calculate the average and standard deviation again. Once we get + * down to the bottom 3/4 of our samples, stop excluding samples. + * + * This can deal with workloads that have long pauses interspersed + * with sporadic activity with a bunch of short pauses. */ + if ((divisor * 4) <= INTERVALS * 3) + return; - if (avg && stddev < STDDEV_THRESH) - data->predicted_us = avg; + thresh = max - 1; + goto again; } /** * menu_select - selects the next idle state to enter + * @drv: cpuidle driver containing state data * @dev: the CPU */ -static int menu_select(struct cpuidle_device *dev) +static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) { struct menu_device *data = &__get_cpu_var(menu_devices); int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY); - unsigned int power_usage = -1; int i; - int multiplier; + unsigned int interactivity_req; + struct timespec t; if (data->needs_update) { - menu_update(dev); + menu_update(drv, dev); data->needs_update = 0; } - data->last_state_idx = 0; - data->exit_us = 0; + data->last_state_idx = CPUIDLE_DRIVER_STATE_START - 1; /* Special case when user has set very strict latency requirement */ if (unlikely(latency_req == 0)) return 0; /* determine the expected residency time, round up */ - data->expected_us = - DIV_ROUND_UP((u32)ktime_to_ns(tick_nohz_get_sleep_length()), 1000); - + t = ktime_to_timespec(tick_nohz_get_sleep_length()); + data->next_timer_us = + t.tv_sec * USEC_PER_SEC + t.tv_nsec / NSEC_PER_USEC; - data->bucket = which_bucket(data->expected_us); - multiplier = performance_multiplier(); + data->bucket = which_bucket(data->next_timer_us); /* - * if the correction factor is 0 (eg first time init or cpu hotplug - * etc), we actually want to start out with a unity factor. + * Force the result of multiplication to be 64 bits even if both + * operands are 32 bits. + * Make sure to round up for half microseconds. */ - if (data->correction_factor[data->bucket] == 0) - data->correction_factor[data->bucket] = RESOLUTION * DECAY; - - /* Make sure to round up for half microseconds */ - data->predicted_us = div_round64(data->expected_us * data->correction_factor[data->bucket], + data->predicted_us = div_round64((uint64_t)data->next_timer_us * + data->correction_factor[data->bucket], RESOLUTION * DECAY); - detect_repeating_patterns(data); + get_typical_interval(data); + + /* + * Performance multiplier defines a minimum predicted idle + * duration / latency ratio. Adjust the latency limit if + * necessary. + */ + interactivity_req = data->predicted_us / performance_multiplier(); + if (latency_req > interactivity_req) + latency_req = interactivity_req; /* * We want to default to C1 (hlt), not to busy polling * unless the timer is happening really really soon. */ - if (data->expected_us > 5) + if (data->next_timer_us > 5 && + !drv->states[CPUIDLE_DRIVER_STATE_START].disabled && + dev->states_usage[CPUIDLE_DRIVER_STATE_START].disable == 0) data->last_state_idx = CPUIDLE_DRIVER_STATE_START; /* * Find the idle state with the lowest power while satisfying * our constraints. */ - for (i = CPUIDLE_DRIVER_STATE_START; i < dev->state_count; i++) { - struct cpuidle_state *s = &dev->states[i]; + for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) { + struct cpuidle_state *s = &drv->states[i]; + struct cpuidle_state_usage *su = &dev->states_usage[i]; - if (s->flags & CPUIDLE_FLAG_IGNORE) + if (s->disabled || su->disable) continue; if (s->target_residency > data->predicted_us) continue; if (s->exit_latency > latency_req) continue; - if (s->exit_latency * multiplier > data->predicted_us) - continue; - if (s->power_usage < power_usage) { - power_usage = s->power_usage; - data->last_state_idx = i; - data->exit_us = s->exit_latency; - } + data->last_state_idx = i; } return data->last_state_idx; @@ -308,55 +363,69 @@ static int menu_select(struct cpuidle_device *dev) /** * menu_reflect - records that data structures need update * @dev: the CPU + * @index: the index of actual entered state * * NOTE: it's important to be fast here because this operation will add to * the overall exit latency. */ -static void menu_reflect(struct cpuidle_device *dev) +static void menu_reflect(struct cpuidle_device *dev, int index) { struct menu_device *data = &__get_cpu_var(menu_devices); - data->needs_update = 1; + data->last_state_idx = index; + if (index >= 0) + data->needs_update = 1; } /** * menu_update - attempts to guess what happened after entry + * @drv: cpuidle driver containing state data * @dev: the CPU */ -static void menu_update(struct cpuidle_device *dev) +static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) { struct menu_device *data = &__get_cpu_var(menu_devices); int last_idx = data->last_state_idx; - unsigned int last_idle_us = cpuidle_get_last_residency(dev); - struct cpuidle_state *target = &dev->states[last_idx]; + struct cpuidle_state *target = &drv->states[last_idx]; unsigned int measured_us; - u64 new_factor; + unsigned int new_factor; /* - * Ugh, this idle state doesn't support residency measurements, so we - * are basically lost in the dark. As a compromise, assume we slept - * for the whole expected time. + * Try to figure out how much time passed between entry to low + * power state and occurrence of the wakeup event. + * + * If the entered idle state didn't support residency measurements, + * we are basically lost in the dark how much time passed. + * As a compromise, assume we slept for the whole expected time. + * + * Any measured amount of time will include the exit latency. + * Since we are interested in when the wakeup begun, not when it + * was completed, we must substract the exit latency. However, if + * the measured amount of time is less than the exit latency, + * assume the state was never reached and the exit latency is 0. */ - if (unlikely(!(target->flags & CPUIDLE_FLAG_TIME_VALID))) - last_idle_us = data->expected_us; + if (unlikely(!(target->flags & CPUIDLE_FLAG_TIME_VALID))) { + /* Use timer value as is */ + measured_us = data->next_timer_us; + } else { + /* Use measured value */ + measured_us = cpuidle_get_last_residency(dev); - measured_us = last_idle_us; + /* Deduct exit latency */ + if (measured_us > target->exit_latency) + measured_us -= target->exit_latency; - /* - * We correct for the exit latency; we are assuming here that the - * exit latency happens after the event that we're interested in. - */ - if (measured_us > data->exit_us) - measured_us -= data->exit_us; - - - /* update our correction ratio */ + /* Make sure our coefficients do not exceed unity */ + if (measured_us > data->next_timer_us) + measured_us = data->next_timer_us; + } - new_factor = data->correction_factor[data->bucket] - * (DECAY - 1) / DECAY; + /* Update our correction ratio */ + new_factor = data->correction_factor[data->bucket]; + new_factor -= new_factor / DECAY; - if (data->expected_us > 0 && measured_us < MAX_INTERESTING) - new_factor += RESOLUTION * measured_us / data->expected_us; + if (data->next_timer_us > 0 && measured_us < MAX_INTERESTING) + new_factor += RESOLUTION * measured_us / data->next_timer_us; else /* * we were idle so long that we count it as a perfect @@ -366,29 +435,41 @@ static void menu_update(struct cpuidle_device *dev) /* * We don't want 0 as factor; we always want at least - * a tiny bit of estimated time. + * a tiny bit of estimated time. Fortunately, due to rounding, + * new_factor will stay nonzero regardless of measured_us values + * and the compiler can eliminate this test as long as DECAY > 1. */ - if (new_factor == 0) + if (DECAY == 1 && unlikely(new_factor == 0)) new_factor = 1; data->correction_factor[data->bucket] = new_factor; /* update the repeating-pattern data */ - data->intervals[data->interval_ptr++] = last_idle_us; + data->intervals[data->interval_ptr++] = measured_us; if (data->interval_ptr >= INTERVALS) data->interval_ptr = 0; } /** * menu_enable_device - scans a CPU's states and does setup + * @drv: cpuidle driver * @dev: the CPU */ -static int menu_enable_device(struct cpuidle_device *dev) +static int menu_enable_device(struct cpuidle_driver *drv, + struct cpuidle_device *dev) { struct menu_device *data = &per_cpu(menu_devices, dev->cpu); + int i; memset(data, 0, sizeof(struct menu_device)); + /* + * if the correction factor is 0 (eg first time init or cpu hotplug + * etc), we actually want to start out with a unity factor. + */ + for(i = 0; i < BUCKETS; i++) + data->correction_factor[i] = RESOLUTION * DECAY; + return 0; } @@ -409,14 +490,4 @@ static int __init init_menu(void) return cpuidle_register_governor(&menu_governor); } -/** - * exit_menu - exits the governor - */ -static void __exit exit_menu(void) -{ - cpuidle_unregister_governor(&menu_governor); -} - -MODULE_LICENSE("GPL"); -module_init(init_menu); -module_exit(exit_menu); +postcore_initcall(init_menu); diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c index 0310ffaec9d..efe2f175168 100644 --- a/drivers/cpuidle/sysfs.c +++ b/drivers/cpuidle/sysfs.c @@ -11,6 +11,10 @@ #include <linux/sysfs.h> #include <linux/slab.h> #include <linux/cpu.h> +#include <linux/completion.h> +#include <linux/capability.h> +#include <linux/device.h> +#include <linux/kobject.h> #include "cpuidle.h" @@ -22,8 +26,8 @@ static int __init cpuidle_sysfs_setup(char *unused) } __setup("cpuidle_sysfs_switch", cpuidle_sysfs_setup); -static ssize_t show_available_governors(struct sysdev_class *class, - struct sysdev_class_attribute *attr, +static ssize_t show_available_governors(struct device *dev, + struct device_attribute *attr, char *buf) { ssize_t i = 0; @@ -31,7 +35,8 @@ static ssize_t show_available_governors(struct sysdev_class *class, mutex_lock(&cpuidle_lock); list_for_each_entry(tmp, &cpuidle_governors, governor_list) { - if (i >= (ssize_t) ((PAGE_SIZE/sizeof(char)) - CPUIDLE_NAME_LEN - 2)) + if (i >= (ssize_t) ((PAGE_SIZE/sizeof(char)) - + CPUIDLE_NAME_LEN - 2)) goto out; i += scnprintf(&buf[i], CPUIDLE_NAME_LEN, "%s ", tmp->name); } @@ -42,16 +47,17 @@ out: return i; } -static ssize_t show_current_driver(struct sysdev_class *class, - struct sysdev_class_attribute *attr, +static ssize_t show_current_driver(struct device *dev, + struct device_attribute *attr, char *buf) { ssize_t ret; - struct cpuidle_driver *cpuidle_driver = cpuidle_get_driver(); + struct cpuidle_driver *drv; spin_lock(&cpuidle_driver_lock); - if (cpuidle_driver) - ret = sprintf(buf, "%s\n", cpuidle_driver->name); + drv = cpuidle_get_driver(); + if (drv) + ret = sprintf(buf, "%s\n", drv->name); else ret = sprintf(buf, "none\n"); spin_unlock(&cpuidle_driver_lock); @@ -59,8 +65,8 @@ static ssize_t show_current_driver(struct sysdev_class *class, return ret; } -static ssize_t show_current_governor(struct sysdev_class *class, - struct sysdev_class_attribute *attr, +static ssize_t show_current_governor(struct device *dev, + struct device_attribute *attr, char *buf) { ssize_t ret; @@ -75,8 +81,8 @@ static ssize_t show_current_governor(struct sysdev_class *class, return ret; } -static ssize_t store_current_governor(struct sysdev_class *class, - struct sysdev_class_attribute *attr, +static ssize_t store_current_governor(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) { char gov_name[CPUIDLE_NAME_LEN]; @@ -109,50 +115,48 @@ static ssize_t store_current_governor(struct sysdev_class *class, return count; } -static SYSDEV_CLASS_ATTR(current_driver, 0444, show_current_driver, NULL); -static SYSDEV_CLASS_ATTR(current_governor_ro, 0444, show_current_governor, - NULL); +static DEVICE_ATTR(current_driver, 0444, show_current_driver, NULL); +static DEVICE_ATTR(current_governor_ro, 0444, show_current_governor, NULL); -static struct attribute *cpuclass_default_attrs[] = { - &attr_current_driver.attr, - &attr_current_governor_ro.attr, +static struct attribute *cpuidle_default_attrs[] = { + &dev_attr_current_driver.attr, + &dev_attr_current_governor_ro.attr, NULL }; -static SYSDEV_CLASS_ATTR(available_governors, 0444, show_available_governors, - NULL); -static SYSDEV_CLASS_ATTR(current_governor, 0644, show_current_governor, - store_current_governor); +static DEVICE_ATTR(available_governors, 0444, show_available_governors, NULL); +static DEVICE_ATTR(current_governor, 0644, show_current_governor, + store_current_governor); -static struct attribute *cpuclass_switch_attrs[] = { - &attr_available_governors.attr, - &attr_current_driver.attr, - &attr_current_governor.attr, +static struct attribute *cpuidle_switch_attrs[] = { + &dev_attr_available_governors.attr, + &dev_attr_current_driver.attr, + &dev_attr_current_governor.attr, NULL }; -static struct attribute_group cpuclass_attr_group = { - .attrs = cpuclass_default_attrs, +static struct attribute_group cpuidle_attr_group = { + .attrs = cpuidle_default_attrs, .name = "cpuidle", }; /** - * cpuidle_add_class_sysfs - add CPU global sysfs attributes + * cpuidle_add_interface - add CPU global sysfs attributes */ -int cpuidle_add_class_sysfs(struct sysdev_class *cls) +int cpuidle_add_interface(struct device *dev) { if (sysfs_switch) - cpuclass_attr_group.attrs = cpuclass_switch_attrs; + cpuidle_attr_group.attrs = cpuidle_switch_attrs; - return sysfs_create_group(&cls->kset.kobj, &cpuclass_attr_group); + return sysfs_create_group(&dev->kobj, &cpuidle_attr_group); } /** - * cpuidle_remove_class_sysfs - remove CPU global sysfs attributes + * cpuidle_remove_interface - remove CPU global sysfs attributes */ -void cpuidle_remove_class_sysfs(struct sysdev_class *cls) +void cpuidle_remove_interface(struct device *dev) { - sysfs_remove_group(&cls->kset.kobj, &cpuclass_attr_group); + sysfs_remove_group(&dev->kobj, &cpuidle_attr_group); } struct cpuidle_attr { @@ -166,13 +170,28 @@ struct cpuidle_attr { #define define_one_rw(_name, show, store) \ static struct cpuidle_attr attr_##_name = __ATTR(_name, 0644, show, store) -#define kobj_to_cpuidledev(k) container_of(k, struct cpuidle_device, kobj) #define attr_to_cpuidleattr(a) container_of(a, struct cpuidle_attr, attr) -static ssize_t cpuidle_show(struct kobject * kobj, struct attribute * attr ,char * buf) + +struct cpuidle_device_kobj { + struct cpuidle_device *dev; + struct completion kobj_unregister; + struct kobject kobj; +}; + +static inline struct cpuidle_device *to_cpuidle_device(struct kobject *kobj) +{ + struct cpuidle_device_kobj *kdev = + container_of(kobj, struct cpuidle_device_kobj, kobj); + + return kdev->dev; +} + +static ssize_t cpuidle_show(struct kobject *kobj, struct attribute *attr, + char *buf) { int ret = -EIO; - struct cpuidle_device *dev = kobj_to_cpuidledev(kobj); - struct cpuidle_attr * cattr = attr_to_cpuidleattr(attr); + struct cpuidle_device *dev = to_cpuidle_device(kobj); + struct cpuidle_attr *cattr = attr_to_cpuidleattr(attr); if (cattr->show) { mutex_lock(&cpuidle_lock); @@ -182,12 +201,12 @@ static ssize_t cpuidle_show(struct kobject * kobj, struct attribute * attr ,char return ret; } -static ssize_t cpuidle_store(struct kobject * kobj, struct attribute * attr, - const char * buf, size_t count) +static ssize_t cpuidle_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) { int ret = -EIO; - struct cpuidle_device *dev = kobj_to_cpuidledev(kobj); - struct cpuidle_attr * cattr = attr_to_cpuidleattr(attr); + struct cpuidle_device *dev = to_cpuidle_device(kobj); + struct cpuidle_attr *cattr = attr_to_cpuidleattr(attr); if (cattr->store) { mutex_lock(&cpuidle_lock); @@ -204,9 +223,10 @@ static const struct sysfs_ops cpuidle_sysfs_ops = { static void cpuidle_sysfs_release(struct kobject *kobj) { - struct cpuidle_device *dev = kobj_to_cpuidledev(kobj); + struct cpuidle_device_kobj *kdev = + container_of(kobj, struct cpuidle_device_kobj, kobj); - complete(&dev->kobj_unregister); + complete(&kdev->kobj_unregister); } static struct kobj_type ktype_cpuidle = { @@ -216,27 +236,56 @@ static struct kobj_type ktype_cpuidle = { struct cpuidle_state_attr { struct attribute attr; - ssize_t (*show)(struct cpuidle_state *, char *); - ssize_t (*store)(struct cpuidle_state *, const char *, size_t); + ssize_t (*show)(struct cpuidle_state *, \ + struct cpuidle_state_usage *, char *); + ssize_t (*store)(struct cpuidle_state *, \ + struct cpuidle_state_usage *, const char *, size_t); }; #define define_one_state_ro(_name, show) \ static struct cpuidle_state_attr attr_##_name = __ATTR(_name, 0444, show, NULL) +#define define_one_state_rw(_name, show, store) \ +static struct cpuidle_state_attr attr_##_name = __ATTR(_name, 0644, show, store) + #define define_show_state_function(_name) \ -static ssize_t show_state_##_name(struct cpuidle_state *state, char *buf) \ +static ssize_t show_state_##_name(struct cpuidle_state *state, \ + struct cpuidle_state_usage *state_usage, char *buf) \ { \ return sprintf(buf, "%u\n", state->_name);\ } +#define define_store_state_ull_function(_name) \ +static ssize_t store_state_##_name(struct cpuidle_state *state, \ + struct cpuidle_state_usage *state_usage, \ + const char *buf, size_t size) \ +{ \ + unsigned long long value; \ + int err; \ + if (!capable(CAP_SYS_ADMIN)) \ + return -EPERM; \ + err = kstrtoull(buf, 0, &value); \ + if (err) \ + return err; \ + if (value) \ + state_usage->_name = 1; \ + else \ + state_usage->_name = 0; \ + return size; \ +} + #define define_show_state_ull_function(_name) \ -static ssize_t show_state_##_name(struct cpuidle_state *state, char *buf) \ +static ssize_t show_state_##_name(struct cpuidle_state *state, \ + struct cpuidle_state_usage *state_usage, \ + char *buf) \ { \ - return sprintf(buf, "%llu\n", state->_name);\ + return sprintf(buf, "%llu\n", state_usage->_name);\ } #define define_show_state_str_function(_name) \ -static ssize_t show_state_##_name(struct cpuidle_state *state, char *buf) \ +static ssize_t show_state_##_name(struct cpuidle_state *state, \ + struct cpuidle_state_usage *state_usage, \ + char *buf) \ { \ if (state->_name[0] == '\0')\ return sprintf(buf, "<null>\n");\ @@ -244,47 +293,79 @@ static ssize_t show_state_##_name(struct cpuidle_state *state, char *buf) \ } define_show_state_function(exit_latency) +define_show_state_function(target_residency) define_show_state_function(power_usage) define_show_state_ull_function(usage) define_show_state_ull_function(time) define_show_state_str_function(name) define_show_state_str_function(desc) +define_show_state_ull_function(disable) +define_store_state_ull_function(disable) define_one_state_ro(name, show_state_name); define_one_state_ro(desc, show_state_desc); define_one_state_ro(latency, show_state_exit_latency); +define_one_state_ro(residency, show_state_target_residency); define_one_state_ro(power, show_state_power_usage); define_one_state_ro(usage, show_state_usage); define_one_state_ro(time, show_state_time); +define_one_state_rw(disable, show_state_disable, store_state_disable); static struct attribute *cpuidle_state_default_attrs[] = { &attr_name.attr, &attr_desc.attr, &attr_latency.attr, + &attr_residency.attr, &attr_power.attr, &attr_usage.attr, &attr_time.attr, + &attr_disable.attr, NULL }; +struct cpuidle_state_kobj { + struct cpuidle_state *state; + struct cpuidle_state_usage *state_usage; + struct completion kobj_unregister; + struct kobject kobj; +}; + #define kobj_to_state_obj(k) container_of(k, struct cpuidle_state_kobj, kobj) #define kobj_to_state(k) (kobj_to_state_obj(k)->state) +#define kobj_to_state_usage(k) (kobj_to_state_obj(k)->state_usage) #define attr_to_stateattr(a) container_of(a, struct cpuidle_state_attr, attr) -static ssize_t cpuidle_state_show(struct kobject * kobj, - struct attribute * attr ,char * buf) + +static ssize_t cpuidle_state_show(struct kobject *kobj, struct attribute *attr, + char * buf) { int ret = -EIO; struct cpuidle_state *state = kobj_to_state(kobj); + struct cpuidle_state_usage *state_usage = kobj_to_state_usage(kobj); struct cpuidle_state_attr * cattr = attr_to_stateattr(attr); if (cattr->show) - ret = cattr->show(state, buf); + ret = cattr->show(state, state_usage, buf); + + return ret; +} + +static ssize_t cpuidle_state_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t size) +{ + int ret = -EIO; + struct cpuidle_state *state = kobj_to_state(kobj); + struct cpuidle_state_usage *state_usage = kobj_to_state_usage(kobj); + struct cpuidle_state_attr *cattr = attr_to_stateattr(attr); + + if (cattr->store) + ret = cattr->store(state, state_usage, buf, size); return ret; } static const struct sysfs_ops cpuidle_state_sysfs_ops = { .show = cpuidle_state_show, + .store = cpuidle_state_store, }; static void cpuidle_state_sysfs_release(struct kobject *kobj) @@ -300,7 +381,7 @@ static struct kobj_type ktype_state_cpuidle = { .release = cpuidle_state_sysfs_release, }; -static void inline cpuidle_free_state_kobj(struct cpuidle_device *device, int i) +static inline void cpuidle_free_state_kobj(struct cpuidle_device *device, int i) { kobject_put(&device->kobjs[i]->kobj); wait_for_completion(&device->kobjs[i]->kobj_unregister); @@ -309,24 +390,27 @@ static void inline cpuidle_free_state_kobj(struct cpuidle_device *device, int i) } /** - * cpuidle_add_driver_sysfs - adds driver-specific sysfs attributes + * cpuidle_add_state_sysfs - adds cpuidle states sysfs attributes * @device: the target device */ -int cpuidle_add_state_sysfs(struct cpuidle_device *device) +static int cpuidle_add_state_sysfs(struct cpuidle_device *device) { int i, ret = -ENOMEM; struct cpuidle_state_kobj *kobj; + struct cpuidle_device_kobj *kdev = device->kobj_dev; + struct cpuidle_driver *drv = cpuidle_get_cpu_driver(device); /* state statistics */ for (i = 0; i < device->state_count; i++) { kobj = kzalloc(sizeof(struct cpuidle_state_kobj), GFP_KERNEL); if (!kobj) goto error_state; - kobj->state = &device->states[i]; + kobj->state = &drv->states[i]; + kobj->state_usage = &device->states_usage[i]; init_completion(&kobj->kobj_unregister); - ret = kobject_init_and_add(&kobj->kobj, &ktype_state_cpuidle, &device->kobj, - "state%d", i); + ret = kobject_init_and_add(&kobj->kobj, &ktype_state_cpuidle, + &kdev->kobj, "state%d", i); if (ret) { kfree(kobj); goto error_state; @@ -344,10 +428,10 @@ error_state: } /** - * cpuidle_remove_driver_sysfs - removes driver-specific sysfs attributes + * cpuidle_remove_driver_sysfs - removes the cpuidle states sysfs attributes * @device: the target device */ -void cpuidle_remove_state_sysfs(struct cpuidle_device *device) +static void cpuidle_remove_state_sysfs(struct cpuidle_device *device) { int i; @@ -355,33 +439,208 @@ void cpuidle_remove_state_sysfs(struct cpuidle_device *device) cpuidle_free_state_kobj(device, i); } +#ifdef CONFIG_CPU_IDLE_MULTIPLE_DRIVERS +#define kobj_to_driver_kobj(k) container_of(k, struct cpuidle_driver_kobj, kobj) +#define attr_to_driver_attr(a) container_of(a, struct cpuidle_driver_attr, attr) + +#define define_one_driver_ro(_name, show) \ + static struct cpuidle_driver_attr attr_driver_##_name = \ + __ATTR(_name, 0644, show, NULL) + +struct cpuidle_driver_kobj { + struct cpuidle_driver *drv; + struct completion kobj_unregister; + struct kobject kobj; +}; + +struct cpuidle_driver_attr { + struct attribute attr; + ssize_t (*show)(struct cpuidle_driver *, char *); + ssize_t (*store)(struct cpuidle_driver *, const char *, size_t); +}; + +static ssize_t show_driver_name(struct cpuidle_driver *drv, char *buf) +{ + ssize_t ret; + + spin_lock(&cpuidle_driver_lock); + ret = sprintf(buf, "%s\n", drv ? drv->name : "none"); + spin_unlock(&cpuidle_driver_lock); + + return ret; +} + +static void cpuidle_driver_sysfs_release(struct kobject *kobj) +{ + struct cpuidle_driver_kobj *driver_kobj = kobj_to_driver_kobj(kobj); + complete(&driver_kobj->kobj_unregister); +} + +static ssize_t cpuidle_driver_show(struct kobject *kobj, struct attribute *attr, + char *buf) +{ + int ret = -EIO; + struct cpuidle_driver_kobj *driver_kobj = kobj_to_driver_kobj(kobj); + struct cpuidle_driver_attr *dattr = attr_to_driver_attr(attr); + + if (dattr->show) + ret = dattr->show(driver_kobj->drv, buf); + + return ret; +} + +static ssize_t cpuidle_driver_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t size) +{ + int ret = -EIO; + struct cpuidle_driver_kobj *driver_kobj = kobj_to_driver_kobj(kobj); + struct cpuidle_driver_attr *dattr = attr_to_driver_attr(attr); + + if (dattr->store) + ret = dattr->store(driver_kobj->drv, buf, size); + + return ret; +} + +define_one_driver_ro(name, show_driver_name); + +static const struct sysfs_ops cpuidle_driver_sysfs_ops = { + .show = cpuidle_driver_show, + .store = cpuidle_driver_store, +}; + +static struct attribute *cpuidle_driver_default_attrs[] = { + &attr_driver_name.attr, + NULL +}; + +static struct kobj_type ktype_driver_cpuidle = { + .sysfs_ops = &cpuidle_driver_sysfs_ops, + .default_attrs = cpuidle_driver_default_attrs, + .release = cpuidle_driver_sysfs_release, +}; + +/** + * cpuidle_add_driver_sysfs - adds the driver name sysfs attribute + * @device: the target device + */ +static int cpuidle_add_driver_sysfs(struct cpuidle_device *dev) +{ + struct cpuidle_driver_kobj *kdrv; + struct cpuidle_device_kobj *kdev = dev->kobj_dev; + struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); + int ret; + + kdrv = kzalloc(sizeof(*kdrv), GFP_KERNEL); + if (!kdrv) + return -ENOMEM; + + kdrv->drv = drv; + init_completion(&kdrv->kobj_unregister); + + ret = kobject_init_and_add(&kdrv->kobj, &ktype_driver_cpuidle, + &kdev->kobj, "driver"); + if (ret) { + kfree(kdrv); + return ret; + } + + kobject_uevent(&kdrv->kobj, KOBJ_ADD); + dev->kobj_driver = kdrv; + + return ret; +} + +/** + * cpuidle_remove_driver_sysfs - removes the driver name sysfs attribute + * @device: the target device + */ +static void cpuidle_remove_driver_sysfs(struct cpuidle_device *dev) +{ + struct cpuidle_driver_kobj *kdrv = dev->kobj_driver; + kobject_put(&kdrv->kobj); + wait_for_completion(&kdrv->kobj_unregister); + kfree(kdrv); +} +#else +static inline int cpuidle_add_driver_sysfs(struct cpuidle_device *dev) +{ + return 0; +} + +static inline void cpuidle_remove_driver_sysfs(struct cpuidle_device *dev) +{ + ; +} +#endif + +/** + * cpuidle_add_device_sysfs - adds device specific sysfs attributes + * @device: the target device + */ +int cpuidle_add_device_sysfs(struct cpuidle_device *device) +{ + int ret; + + ret = cpuidle_add_state_sysfs(device); + if (ret) + return ret; + + ret = cpuidle_add_driver_sysfs(device); + if (ret) + cpuidle_remove_state_sysfs(device); + return ret; +} + +/** + * cpuidle_remove_device_sysfs : removes device specific sysfs attributes + * @device : the target device + */ +void cpuidle_remove_device_sysfs(struct cpuidle_device *device) +{ + cpuidle_remove_driver_sysfs(device); + cpuidle_remove_state_sysfs(device); +} + /** * cpuidle_add_sysfs - creates a sysfs instance for the target device - * @sysdev: the target device + * @dev: the target device */ -int cpuidle_add_sysfs(struct sys_device *sysdev) +int cpuidle_add_sysfs(struct cpuidle_device *dev) { - int cpu = sysdev->id; - struct cpuidle_device *dev; + struct cpuidle_device_kobj *kdev; + struct device *cpu_dev = get_cpu_device((unsigned long)dev->cpu); int error; - dev = per_cpu(cpuidle_devices, cpu); - error = kobject_init_and_add(&dev->kobj, &ktype_cpuidle, &sysdev->kobj, - "cpuidle"); - if (!error) - kobject_uevent(&dev->kobj, KOBJ_ADD); - return error; + kdev = kzalloc(sizeof(*kdev), GFP_KERNEL); + if (!kdev) + return -ENOMEM; + kdev->dev = dev; + dev->kobj_dev = kdev; + + init_completion(&kdev->kobj_unregister); + + error = kobject_init_and_add(&kdev->kobj, &ktype_cpuidle, &cpu_dev->kobj, + "cpuidle"); + if (error) { + kfree(kdev); + return error; + } + + kobject_uevent(&kdev->kobj, KOBJ_ADD); + + return 0; } /** * cpuidle_remove_sysfs - deletes a sysfs instance on the target device - * @sysdev: the target device + * @dev: the target device */ -void cpuidle_remove_sysfs(struct sys_device *sysdev) +void cpuidle_remove_sysfs(struct cpuidle_device *dev) { - int cpu = sysdev->id; - struct cpuidle_device *dev; + struct cpuidle_device_kobj *kdev = dev->kobj_dev; - dev = per_cpu(cpuidle_devices, cpu); - kobject_put(&dev->kobj); + kobject_put(&kdev->kobj); + wait_for_completion(&kdev->kobj_unregister); + kfree(kdev); } |