From 0aeb9cac6f8a6fc68acfb07d30b62ad6106a6384 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Fri, 4 May 2012 14:06:02 -0700 Subject: cpuidle: remove unused hrtimer_peek_ahead_timers() call commit 9a6558371bcd01c2973b7638181db4ccc34eab4f Author: Arjan van de Ven Date: Sun Nov 9 12:45:10 2008 -0800 regression: disable timer peek-ahead for 2.6.28 It's showing up as regressions; disabling it very likely just papers over an underlying issue, but time is running out for 2.6.28, lets get back to this for 2.6.29 Many years has passed since 2008, so it seems ok to remove whole `#if 0' block. Signed-off-by: Sergey Senozhatsky Cc: Kevin Hilman Cc: Trinabh Gupta Cc: Deepthi Dharwar Cc: Arjan van de Ven Signed-off-by: Andrew Morton Signed-off-by: Len Brown --- drivers/cpuidle/cpuidle.c | 9 --------- 1 file changed, 9 deletions(-) (limited to 'drivers/cpuidle') diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 2f0083a51a9a..588b44aa1de4 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -124,15 +124,6 @@ int cpuidle_idle_call(void) if (!dev || !dev->enabled) return -EBUSY; -#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 - /* ask the governor for the next state */ next_state = cpuidle_curr_governor->select(drv, dev); if (need_resched()) { -- cgit v1.2.3 From 1b0a0e9a15b976d91f3b5ae619c6a8964c2818eb Mon Sep 17 00:00:00 2001 From: "Srivatsa S. Bhat" Date: Fri, 4 May 2012 14:06:02 -0700 Subject: cpuidle: add checks to avoid NULL pointer dereference The existing check for dev == NULL in __cpuidle_register_device() is rendered useless because dev is dereferenced before the check itself. Moreover, correctly speaking, it is the job of the callers of this function, i.e., cpuidle_register_device() & cpuidle_enable_device() (which also happen to be exported functions) to ensure that __cpuidle_register_device() is called with a non-NULL dev. So add the necessary dev == NULL checks in the two callers and remove the (useless) check from __cpuidle_register_device(). Signed-off-by: Srivatsa S. Bhat Acked-by: Daniel Lezcano Signed-off-by: Andrew Morton Signed-off-by: Len Brown --- drivers/cpuidle/cpuidle.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'drivers/cpuidle') diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 588b44aa1de4..8ffef26ffdcf 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -285,6 +285,9 @@ int cpuidle_enable_device(struct cpuidle_device *dev) int ret, i; struct cpuidle_driver *drv = cpuidle_get_driver(); + if (!dev) + return -EINVAL; + if (dev->enabled) return 0; if (!drv || !cpuidle_curr_governor) @@ -369,8 +372,6 @@ static int __cpuidle_register_device(struct cpuidle_device *dev) struct device *cpu_dev = get_cpu_device((unsigned long)dev->cpu); struct cpuidle_driver *cpuidle_driver = cpuidle_get_driver(); - if (!dev) - return -EINVAL; if (!try_module_get(cpuidle_driver->owner)) return -EINVAL; @@ -395,6 +396,9 @@ int cpuidle_register_device(struct cpuidle_device *dev) { int ret; + if (!dev) + return -EINVAL; + mutex_lock(&cpuidle_lock); if ((ret = __cpuidle_register_device(dev))) { -- cgit v1.2.3 From 56cfbf74a17c40f3a741398103c9f5d5a6806715 Mon Sep 17 00:00:00 2001 From: Colin Cross Date: Mon, 7 May 2012 17:57:39 -0700 Subject: cpuidle: refactor out cpuidle_enter_state Split the code to enter a state and update the stats into a helper function, cpuidle_enter_state, and export it. This function will be called by the coupled state code to handle entering the safe state and the final coupled state. Reviewed-by: Santosh Shilimkar Tested-by: Santosh Shilimkar Reviewed-by: Kevin Hilman Tested-by: Kevin Hilman Signed-off-by: Colin Cross Reviewed-by: Rafael J. Wysocki Signed-off-by: Len Brown --- drivers/cpuidle/cpuidle.c | 42 +++++++++++++++++++++++++++++------------- drivers/cpuidle/cpuidle.h | 2 ++ 2 files changed, 31 insertions(+), 13 deletions(-) (limited to 'drivers/cpuidle') diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 2f0083a51a9a..3e3e3e4d9581 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -102,6 +102,34 @@ int cpuidle_play_dead(void) return -ENODEV; } +/** + * 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 next_state) +{ + int entered_state; + + entered_state = cpuidle_enter_ops(dev, drv, next_state); + + 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 += + (unsigned long long)dev->last_residency; + dev->states_usage[entered_state].usage++; + } else { + dev->last_residency = 0; + } + + return entered_state; +} + /** * cpuidle_idle_call - the main idle loop * @@ -143,23 +171,11 @@ int cpuidle_idle_call(void) trace_power_start_rcuidle(POWER_CSTATE, next_state, dev->cpu); trace_cpu_idle_rcuidle(next_state, dev->cpu); - entered_state = cpuidle_enter_ops(dev, drv, next_state); + entered_state = cpuidle_enter_state(dev, drv, next_state); trace_power_end_rcuidle(dev->cpu); trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu); - 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 += - (unsigned long long)dev->last_residency; - dev->states_usage[entered_state].usage++; - } else { - dev->last_residency = 0; - } - /* give the governor an opportunity to reflect on the outcome */ if (cpuidle_curr_governor->reflect) cpuidle_curr_governor->reflect(dev, entered_state); diff --git a/drivers/cpuidle/cpuidle.h b/drivers/cpuidle/cpuidle.h index 7db186685c27..d8a3ccce8281 100644 --- a/drivers/cpuidle/cpuidle.h +++ b/drivers/cpuidle/cpuidle.h @@ -14,6 +14,8 @@ 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); -- cgit v1.2.3 From 3af272ab75c7a0c7fa5ae5507724d961f7e7718b Mon Sep 17 00:00:00 2001 From: Colin Cross Date: Mon, 7 May 2012 17:57:40 -0700 Subject: cpuidle: fix error handling in __cpuidle_register_device Fix the error handling in __cpuidle_register_device to include the missing list_del. Move it to a label, which will simplify the error handling when coupled states are added. Reviewed-by: Santosh Shilimkar Tested-by: Santosh Shilimkar Reviewed-by: Kevin Hilman Tested-by: Kevin Hilman Signed-off-by: Colin Cross Reviewed-by: Rafael J. Wysocki Signed-off-by: Len Brown --- drivers/cpuidle/cpuidle.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'drivers/cpuidle') diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 3e3e3e4d9581..4540672a2e1c 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -403,13 +403,18 @@ static int __cpuidle_register_device(struct cpuidle_device *dev) per_cpu(cpuidle_devices, dev->cpu) = dev; list_add(&dev->device_list, &cpuidle_detected_devices); - if ((ret = cpuidle_add_sysfs(cpu_dev))) { - module_put(cpuidle_driver->owner); - return ret; - } + ret = cpuidle_add_sysfs(cpu_dev); + if (ret) + goto err_sysfs; dev->registered = 1; return 0; + +err_sysfs: + list_del(&dev->device_list); + per_cpu(cpuidle_devices, dev->cpu) = NULL; + module_put(cpuidle_driver->owner); + return ret; } /** -- cgit v1.2.3 From 4126c0197bc8c58a0bb7fcda07b01b596b6fb4c5 Mon Sep 17 00:00:00 2001 From: Colin Cross Date: Mon, 7 May 2012 17:57:41 -0700 Subject: cpuidle: add support for states that affect multiple cpus 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. The easiest solution to implementing coupled cpu power states is to hotplug all but one cpu whenever possible, usually using a cpufreq governor that looks at cpu load to determine when to enable the secondary cpus. This causes problems, as hotplug is an expensive operation, so the number of hotplug transitions must be minimized, leading to very slow response to loads, often on the order of seconds. This file implements an alternative 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. 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. update1: cpuidle: coupled: fix count of online cpus online_count was never incremented on boot, and was also counting cpus that were not part of the coupled set. Fix both issues by introducting a new function that counts online coupled cpus, and call it from register as well as the hotplug notifier. update2: cpuidle: coupled: fix decrementing ready count cpuidle_coupled_set_not_ready sometimes refuses to decrement the ready count in order to prevent a race condition. This makes it unsuitable for use when finished with idle. Add a new function cpuidle_coupled_set_done that decrements both the ready count and waiting count, and call it after idle is complete. Cc: Amit Kucheria Cc: Arjan van de Ven Cc: Trinabh Gupta Cc: Deepthi Dharwar Reviewed-by: Santosh Shilimkar Tested-by: Santosh Shilimkar Reviewed-by: Kevin Hilman Tested-by: Kevin Hilman Signed-off-by: Colin Cross Acked-by: Rafael J. Wysocki Signed-off-by: Len Brown --- drivers/cpuidle/Kconfig | 3 + drivers/cpuidle/Makefile | 1 + drivers/cpuidle/coupled.c | 678 ++++++++++++++++++++++++++++++++++++++++++++++ drivers/cpuidle/cpuidle.c | 15 +- drivers/cpuidle/cpuidle.h | 30 ++ include/linux/cpuidle.h | 7 + 6 files changed, 733 insertions(+), 1 deletion(-) create mode 100644 drivers/cpuidle/coupled.c (limited to 'drivers/cpuidle') diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig index 78a666d1e5f5..a76b689e553b 100644 --- a/drivers/cpuidle/Kconfig +++ b/drivers/cpuidle/Kconfig @@ -18,3 +18,6 @@ config CPU_IDLE_GOV_MENU bool depends on CPU_IDLE && NO_HZ default y + +config ARCH_NEEDS_CPU_IDLE_COUPLED + def_bool n diff --git a/drivers/cpuidle/Makefile b/drivers/cpuidle/Makefile index 5634f88379df..38c8f69f30cf 100644 --- a/drivers/cpuidle/Makefile +++ b/drivers/cpuidle/Makefile @@ -3,3 +3,4 @@ # obj-y += cpuidle.o driver.o governor.o sysfs.o governors/ +obj-$(CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED) += coupled.o diff --git a/drivers/cpuidle/coupled.c b/drivers/cpuidle/coupled.c new file mode 100644 index 000000000000..aab6bba8daec --- /dev/null +++ b/drivers/cpuidle/coupled.c @@ -0,0 +1,678 @@ +/* + * coupled.c - helper functions to enter the same idle state on multiple cpus + * + * Copyright (c) 2011 Google, Inc. + * + * Author: Colin Cross + * + * 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 +#include +#include +#include +#include +#include +#include + +#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; + 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_poked_mask 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_poked_mask; + +/** + * 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_poked(void *info) +{ + int cpu = (unsigned long)info; + cpumask_clear_cpu(cpu, &cpuidle_coupled_poked_mask); +} + +/** + * 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_poked_mask)) + __smp_call_function_single(cpu, csd, 0); +} + +/** + * 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, + * poking all coupled cpus out of idle if necessary to let them see the new + * state. + */ +static void cpuidle_coupled_set_waiting(int cpu, + struct cpuidle_coupled *coupled, int next_state) +{ + int w; + + coupled->requested_state[cpu] = 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. + * + * The atomic_inc_return provides a write barrier to order the write + * to requested_state with the later write that increments ready_count. + */ + w = atomic_inc_return(&coupled->ready_waiting_counts) & WAITING_MASK; + if (w == coupled->online_count) + cpuidle_coupled_poke_others(cpu, coupled); +} + +/** + * 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 turning interrupts off again to make sure + * the interrupt didn't schedule work that should take the cpu out of idle. + * + * Returns 0 if need_resched was false, -EINTR if need_resched was true. + */ +static int cpuidle_coupled_clear_pokes(int cpu) +{ + local_irq_enable(); + while (cpumask_test_cpu(cpu, &cpuidle_coupled_poked_mask)) + cpu_relax(); + local_irq_disable(); + + return need_resched() ? -EINTR : 0; +} + +/** + * 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; + + if (!coupled) + return -EINVAL; + + while (coupled->prevent) { + if (cpuidle_coupled_clear_pokes(dev->cpu)) { + local_irq_enable(); + return entered_state; + } + entered_state = cpuidle_enter_state(dev, drv, + dev->safe_state_index); + } + + /* Read barrier ensures online_count is read after prevent is cleared */ + smp_rmb(); + + cpuidle_coupled_set_waiting(dev->cpu, coupled, next_state); + +retry: + /* + * Wait for all coupled cpus to be idle, using the deepest state + * allowed for a single cpu. + */ + while (!cpuidle_coupled_cpus_waiting(coupled)) { + if (cpuidle_coupled_clear_pokes(dev->cpu)) { + 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); + } + + if (cpuidle_coupled_clear_pokes(dev->cpu)) { + cpuidle_coupled_set_not_waiting(dev->cpu, coupled); + goto out; + } + + /* + * 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(); + } + + /* 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_poked; + 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; + + mutex_lock(&cpuidle_lock); + + dev = per_cpu(cpuidle_devices, cpu); + if (!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.c b/drivers/cpuidle/cpuidle.c index 4540672a2e1c..e81cfda295a5 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -171,7 +171,11 @@ int cpuidle_idle_call(void) trace_power_start_rcuidle(POWER_CSTATE, next_state, dev->cpu); trace_cpu_idle_rcuidle(next_state, dev->cpu); - entered_state = cpuidle_enter_state(dev, drv, next_state); + if (cpuidle_state_is_coupled(dev, drv, next_state)) + entered_state = cpuidle_enter_state_coupled(dev, drv, + next_state); + else + entered_state = cpuidle_enter_state(dev, drv, next_state); trace_power_end_rcuidle(dev->cpu); trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu); @@ -407,9 +411,16 @@ static int __cpuidle_register_device(struct cpuidle_device *dev) if (ret) goto err_sysfs; + ret = cpuidle_coupled_register_device(dev); + if (ret) + goto err_coupled; + dev->registered = 1; return 0; +err_coupled: + cpuidle_remove_sysfs(cpu_dev); + wait_for_completion(&dev->kobj_unregister); err_sysfs: list_del(&dev->device_list); per_cpu(cpuidle_devices, dev->cpu) = NULL; @@ -464,6 +475,8 @@ void cpuidle_unregister_device(struct cpuidle_device *dev) wait_for_completion(&dev->kobj_unregister); per_cpu(cpuidle_devices, dev->cpu) = NULL; + cpuidle_coupled_unregister_device(dev); + cpuidle_resume_and_unlock(); module_put(cpuidle_driver->owner); diff --git a/drivers/cpuidle/cpuidle.h b/drivers/cpuidle/cpuidle.h index d8a3ccce8281..76e7f696ad8c 100644 --- a/drivers/cpuidle/cpuidle.h +++ b/drivers/cpuidle/cpuidle.h @@ -32,4 +32,34 @@ extern void cpuidle_remove_state_sysfs(struct cpuidle_device *device); extern int cpuidle_add_sysfs(struct device *dev); extern void cpuidle_remove_sysfs(struct 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/include/linux/cpuidle.h b/include/linux/cpuidle.h index 6c26a3da0e03..603844835bc7 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -57,6 +57,7 @@ struct cpuidle_state { /* Idle State Flags */ #define CPUIDLE_FLAG_TIME_VALID (0x01) /* is residency time measurable? */ +#define CPUIDLE_FLAG_COUPLED (0x02) /* state applies to multiple cpus */ #define CPUIDLE_DRIVER_FLAGS_MASK (0xFFFF0000) @@ -100,6 +101,12 @@ struct cpuidle_device { struct list_head device_list; struct kobject kobj; struct completion kobj_unregister; + +#ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED + int safe_state_index; + cpumask_t coupled_cpus; + struct cpuidle_coupled *coupled; +#endif }; DECLARE_PER_CPU(struct cpuidle_device *, cpuidle_devices); -- cgit v1.2.3 From 20ff51a36b2cd25ee7eb3216b6d02b68935435ba Mon Sep 17 00:00:00 2001 From: Colin Cross Date: Mon, 7 May 2012 17:57:42 -0700 Subject: cpuidle: coupled: add parallel barrier function Adds cpuidle_coupled_parallel_barrier, which can be used by coupled cpuidle state enter functions to handle resynchronization after determining if any cpu needs to abort. The normal use case will be: static bool abort_flag; static atomic_t abort_barrier; int arch_cpuidle_enter(struct cpuidle_device *dev, ...) { if (arch_turn_off_irq_controller()) { /* returns an error if an irq is pending and would be lost if idle continued and turned off power */ abort_flag = true; } cpuidle_coupled_parallel_barrier(dev, &abort_barrier); if (abort_flag) { /* One of the cpus didn't turn off it's irq controller */ arch_turn_on_irq_controller(); return -EINTR; } /* continue with idle */ ... } This will cause all cpus to abort idle together if one of them needs to abort. Reviewed-by: Santosh Shilimkar Tested-by: Santosh Shilimkar Reviewed-by: Kevin Hilman Tested-by: Kevin Hilman Signed-off-by: Colin Cross Signed-off-by: Len Brown --- drivers/cpuidle/coupled.c | 37 +++++++++++++++++++++++++++++++++++++ include/linux/cpuidle.h | 4 ++++ 2 files changed, 41 insertions(+) (limited to 'drivers/cpuidle') diff --git a/drivers/cpuidle/coupled.c b/drivers/cpuidle/coupled.c index aab6bba8daec..2c9bf2692232 100644 --- a/drivers/cpuidle/coupled.c +++ b/drivers/cpuidle/coupled.c @@ -129,6 +129,43 @@ static DEFINE_PER_CPU(struct call_single_data, cpuidle_coupled_poke_cb); */ static cpumask_t cpuidle_coupled_poked_mask; +/** + * 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 a 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_inc(); + 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 diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 603844835bc7..5ab7183313ce 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -183,6 +183,10 @@ static inline int cpuidle_play_dead(void) {return -ENODEV; } #endif +#ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED +void cpuidle_coupled_parallel_barrier(struct cpuidle_device *dev, atomic_t *a); +#endif + /****************************** * CPUIDLE GOVERNOR INTERFACE * ******************************/ -- cgit v1.2.3