From da7e6f45c34d39186b72328bacc4dd86bff60e0a Mon Sep 17 00:00:00 2001 From: Preeti U Murthy Date: Fri, 7 Feb 2014 13:36:06 +0530 Subject: time: Change the return type of clockevents_notify() to integer The broadcast framework can potentially be made use of by archs which do not have an external clock device as well. Then, it is required that one of the CPUs need to handle the broadcasting of wakeup IPIs to the CPUs in deep idle. As a result its local timers should remain functional all the time. For such a CPU, the BROADCAST_ENTER notification has to fail indicating that its clock device cannot be shutdown. To make way for this support, change the return type of tick_broadcast_oneshot_control() and hence clockevents_notify() to indicate such scenarios. Signed-off-by: Preeti U Murthy Cc: deepthi@linux.vnet.ibm.com Cc: paulmck@linux.vnet.ibm.com Cc: fweisbec@gmail.com Cc: paulus@samba.org Cc: srivatsa.bhat@linux.vnet.ibm.com Cc: svaidy@linux.vnet.ibm.com Cc: peterz@infradead.org Cc: benh@kernel.crashing.org Cc: rafael.j.wysocki@intel.com Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/20140207080606.17187.78306.stgit@preeti.in.ibm.com Signed-off-by: Thomas Gleixner --- include/linux/clockchips.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 493aa021c7a9..e0c5a6c418de 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -186,9 +186,9 @@ static inline int tick_check_broadcast_expired(void) { return 0; } #endif #ifdef CONFIG_GENERIC_CLOCKEVENTS -extern void clockevents_notify(unsigned long reason, void *arg); +extern int clockevents_notify(unsigned long reason, void *arg); #else -static inline void clockevents_notify(unsigned long reason, void *arg) {} +static inline int clockevents_notify(unsigned long reason, void *arg) { return 0; } #endif #else /* CONFIG_GENERIC_CLOCKEVENTS_BUILD */ @@ -196,7 +196,7 @@ static inline void clockevents_notify(unsigned long reason, void *arg) {} static inline void clockevents_suspend(void) {} static inline void clockevents_resume(void) {} -static inline void clockevents_notify(unsigned long reason, void *arg) {} +static inline int clockevents_notify(unsigned long reason, void *arg) { return 0; } static inline int tick_check_broadcast_expired(void) { return 0; } #endif -- cgit v1.2.3-59-g8ed1b From 5d1638acb9f62fa7eb0c07cb85318bbe1f13b227 Mon Sep 17 00:00:00 2001 From: Preeti U Murthy Date: Fri, 7 Feb 2014 13:36:32 +0530 Subject: tick: Introduce hrtimer based broadcast On some architectures, in certain CPU deep idle states the local timers stop. An external clock device is used to wakeup these CPUs. The kernel support for the wakeup of these CPUs is provided by the tick broadcast framework by using the external clock device as the wakeup source. However not all implementations of architectures provide such an external clock device. This patch includes support in the broadcast framework to handle the wakeup of the CPUs in deep idle states on such systems by queuing a hrtimer on one of the CPUs, which is meant to handle the wakeup of CPUs in deep idle states. This patchset introduces a pseudo clock device which can be registered by the archs as tick_broadcast_device in the absence of a real external clock device. Once registered, the broadcast framework will work as is for these architectures as long as the archs take care of the BROADCAST_ENTER notification failing for one of the CPUs. This CPU is made the stand by CPU to handle wakeup of the CPUs in deep idle and it *must not enter deep idle states*. The CPU with the earliest wakeup is chosen to be this CPU. Hence this way the stand by CPU dynamically moves around and so does the hrtimer which is queued to trigger at the next earliest wakeup time. This is consistent with the case where an external clock device is present. The smp affinity of this clock device is set to the CPU with the earliest wakeup. This patchset handles the hotplug of the stand by CPU as well by moving the hrtimer on to the CPU handling the CPU_DEAD notification. Originally-from: Thomas Gleixner Signed-off-by: Preeti U Murthy Cc: deepthi@linux.vnet.ibm.com Cc: paulmck@linux.vnet.ibm.com Cc: fweisbec@gmail.com Cc: paulus@samba.org Cc: srivatsa.bhat@linux.vnet.ibm.com Cc: svaidy@linux.vnet.ibm.com Cc: peterz@infradead.org Cc: benh@kernel.crashing.org Cc: rafael.j.wysocki@intel.com Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/20140207080632.17187.80532.stgit@preeti.in.ibm.com Signed-off-by: Thomas Gleixner --- include/linux/clockchips.h | 9 +++ kernel/time/Makefile | 2 +- kernel/time/tick-broadcast-hrtimer.c | 106 +++++++++++++++++++++++++++++++++++ kernel/time/tick-broadcast.c | 54 +++++++++++++++++- 4 files changed, 167 insertions(+), 4 deletions(-) create mode 100644 kernel/time/tick-broadcast-hrtimer.c (limited to 'include/linux') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index e0c5a6c418de..dbe9e1457168 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -62,6 +62,11 @@ enum clock_event_mode { #define CLOCK_EVT_FEAT_DYNIRQ 0x000020 #define CLOCK_EVT_FEAT_PERCPU 0x000040 +/* + * Clockevent device is based on a hrtimer for broadcast + */ +#define CLOCK_EVT_FEAT_HRTIMER 0x000080 + /** * struct clock_event_device - clock event device descriptor * @event_handler: Assigned by the framework to be called by the low @@ -83,6 +88,7 @@ enum clock_event_mode { * @name: ptr to clock event name * @rating: variable to rate clock event devices * @irq: IRQ number (only for non CPU local devices) + * @bound_on: Bound on CPU * @cpumask: cpumask to indicate for which CPUs this device works * @list: list head for the management code * @owner: module reference @@ -113,6 +119,7 @@ struct clock_event_device { const char *name; int rating; int irq; + int bound_on; const struct cpumask *cpumask; struct list_head list; struct module *owner; @@ -180,9 +187,11 @@ extern int tick_receive_broadcast(void); #endif #if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) +extern void tick_setup_hrtimer_broadcast(void); extern int tick_check_broadcast_expired(void); #else static inline int tick_check_broadcast_expired(void) { return 0; } +static void tick_setup_hrtimer_broadcast(void) {}; #endif #ifdef CONFIG_GENERIC_CLOCKEVENTS diff --git a/kernel/time/Makefile b/kernel/time/Makefile index 9250130646f5..06151ef4a744 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -3,7 +3,7 @@ obj-y += timeconv.o posix-clock.o alarmtimer.o obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD) += clockevents.o obj-$(CONFIG_GENERIC_CLOCKEVENTS) += tick-common.o -obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) += tick-broadcast.o +obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) += tick-broadcast.o tick-broadcast-hrtimer.o obj-$(CONFIG_GENERIC_SCHED_CLOCK) += sched_clock.o obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o obj-$(CONFIG_TICK_ONESHOT) += tick-sched.o diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c new file mode 100644 index 000000000000..92425279312b --- /dev/null +++ b/kernel/time/tick-broadcast-hrtimer.c @@ -0,0 +1,106 @@ +/* + * linux/kernel/time/tick-broadcast-hrtimer.c + * This file emulates a local clock event device + * via a pseudo clock device. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "tick-internal.h" + +static struct hrtimer bctimer; + +static void bc_set_mode(enum clock_event_mode mode, + struct clock_event_device *bc) +{ + switch (mode) { + case CLOCK_EVT_MODE_SHUTDOWN: + /* + * Note, we cannot cancel the timer here as we might + * run into the following live lock scenario: + * + * cpu 0 cpu1 + * lock(broadcast_lock); + * hrtimer_interrupt() + * bc_handler() + * tick_handle_oneshot_broadcast(); + * lock(broadcast_lock); + * hrtimer_cancel() + * wait_for_callback() + */ + hrtimer_try_to_cancel(&bctimer); + break; + default: + break; + } +} + +/* + * This is called from the guts of the broadcast code when the cpu + * which is about to enter idle has the earliest broadcast timer event. + */ +static int bc_set_next(ktime_t expires, struct clock_event_device *bc) +{ + /* + * We try to cancel the timer first. If the callback is on + * flight on some other cpu then we let it handle it. If we + * were able to cancel the timer nothing can rearm it as we + * own broadcast_lock. + * + * However we can also be called from the event handler of + * ce_broadcast_hrtimer itself when it expires. We cannot + * restart the timer because we are in the callback, but we + * can set the expiry time and let the callback return + * HRTIMER_RESTART. + */ + if (hrtimer_try_to_cancel(&bctimer) >= 0) { + hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED); + /* Bind the "device" to the cpu */ + bc->bound_on = smp_processor_id(); + } else if (bc->bound_on == smp_processor_id()) { + hrtimer_set_expires(&bctimer, expires); + } + return 0; +} + +static struct clock_event_device ce_broadcast_hrtimer = { + .set_mode = bc_set_mode, + .set_next_ktime = bc_set_next, + .features = CLOCK_EVT_FEAT_ONESHOT | + CLOCK_EVT_FEAT_KTIME | + CLOCK_EVT_FEAT_HRTIMER, + .rating = 0, + .bound_on = -1, + .min_delta_ns = 1, + .max_delta_ns = KTIME_MAX, + .min_delta_ticks = 1, + .max_delta_ticks = KTIME_MAX, + .mult = 1, + .shift = 0, + .cpumask = cpu_all_mask, +}; + +static enum hrtimer_restart bc_handler(struct hrtimer *t) +{ + ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer); + + if (ce_broadcast_hrtimer.next_event.tv64 == KTIME_MAX) + return HRTIMER_NORESTART; + + return HRTIMER_RESTART; +} + +void tick_setup_hrtimer_broadcast(void) +{ + hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + bctimer.function = bc_handler; + clockevents_register_device(&ce_broadcast_hrtimer); +} diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 84c8fd91d744..63c7b2d9ed8e 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -643,6 +643,42 @@ again: raw_spin_unlock(&tick_broadcast_lock); } +static int broadcast_needs_cpu(struct clock_event_device *bc, int cpu) +{ + if (!(bc->features & CLOCK_EVT_FEAT_HRTIMER)) + return 0; + if (bc->next_event.tv64 == KTIME_MAX) + return 0; + return bc->bound_on == cpu ? -EBUSY : 0; +} + +static void broadcast_shutdown_local(struct clock_event_device *bc, + struct clock_event_device *dev) +{ + /* + * For hrtimer based broadcasting we cannot shutdown the cpu + * local device if our own event is the first one to expire or + * if we own the broadcast timer. + */ + if (bc->features & CLOCK_EVT_FEAT_HRTIMER) { + if (broadcast_needs_cpu(bc, smp_processor_id())) + return; + if (dev->next_event.tv64 < bc->next_event.tv64) + return; + } + clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN); +} + +static void broadcast_move_bc(int deadcpu) +{ + struct clock_event_device *bc = tick_broadcast_device.evtdev; + + if (!bc || !broadcast_needs_cpu(bc, deadcpu)) + return; + /* This moves the broadcast assignment to this cpu */ + clockevents_program_event(bc, bc->next_event, 1); +} + /* * Powerstate information: The system enters/leaves a state, where * affected devices might stop @@ -661,7 +697,7 @@ int tick_broadcast_oneshot_control(unsigned long reason) * states */ if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) - return; + return 0; /* * We are called with preemtion disabled from the depth of the @@ -672,7 +708,7 @@ int tick_broadcast_oneshot_control(unsigned long reason) dev = td->evtdev; if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) - return; + return 0; bc = tick_broadcast_device.evtdev; @@ -680,7 +716,7 @@ int tick_broadcast_oneshot_control(unsigned long reason) if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) { if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) { WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask)); - clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN); + broadcast_shutdown_local(bc, dev); /* * We only reprogram the broadcast timer if we * did not mark ourself in the force mask and @@ -693,6 +729,16 @@ int tick_broadcast_oneshot_control(unsigned long reason) dev->next_event.tv64 < bc->next_event.tv64) tick_broadcast_set_event(bc, cpu, dev->next_event, 1); } + /* + * If the current CPU owns the hrtimer broadcast + * mechanism, it cannot go deep idle and we remove the + * CPU from the broadcast mask. We don't have to go + * through the EXIT path as the local timer is not + * shutdown. + */ + ret = broadcast_needs_cpu(bc, cpu); + if (ret) + cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); } else { if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) { clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT); @@ -866,6 +912,8 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup) cpumask_clear_cpu(cpu, tick_broadcast_pending_mask); cpumask_clear_cpu(cpu, tick_broadcast_force_mask); + broadcast_move_bc(cpu); + raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } -- cgit v1.2.3-59-g8ed1b From f1689bb7abec8e2e670d8ad11eaa86d54bad8cfd Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 7 Feb 2014 16:00:46 +0100 Subject: time: Fixup fallout from recent clockevent/tick changes Make the stub function static inline instead of static and move the clockevents related function into the proper ifdeffed section. Reported-by: Fengguang Wu Signed-off-by: Thomas Gleixner Cc: Soren Brinkmann Cc: Preeti U Murthy --- include/linux/clockchips.h | 2 +- kernel/time/tick-internal.h | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index dbe9e1457168..20a7183f2831 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -191,7 +191,7 @@ extern void tick_setup_hrtimer_broadcast(void); extern int tick_check_broadcast_expired(void); #else static inline int tick_check_broadcast_expired(void) { return 0; } -static void tick_setup_hrtimer_broadcast(void) {}; +static inline void tick_setup_hrtimer_broadcast(void) {}; #endif #ifdef CONFIG_GENERIC_CLOCKEVENTS diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 0756c62c219a..7ab92b19965a 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -155,8 +155,9 @@ static inline int tick_device_is_functional(struct clock_event_device *dev) return !(dev->features & CLOCK_EVT_FEAT_DUMMY); } +int __clockevents_update_freq(struct clock_event_device *dev, u32 freq); + #endif -int __clockevents_update_freq(struct clock_event_device *dev, u32 freq); extern void do_timer(unsigned long ticks); extern void update_wall_time(void); -- cgit v1.2.3-59-g8ed1b From 849401b66d305f3feb75b6db7459b95ad190552a Mon Sep 17 00:00:00 2001 From: Preeti U Murthy Date: Sun, 9 Feb 2014 11:32:22 +0530 Subject: tick: Fixup more fallout from hrtimer broadcast mode The hrtimer mode of broadcast is supported only when GENERIC_CLOCKEVENTS_BROADCAST and TICK_ONESHOT config options are enabled. Hence compile in the functions for hrtimer mode of broadcast only when these options are selected. Also fix max_delta_ticks value for the pseudo clock device. Reported-by: Fengguang Wu Reported-by: Ingo Molnar Signed-off-by: Preeti U Murthy Link: http://lkml.kernel.org/r/52F719EE.9010304@linux.vnet.ibm.com Signed-off-by: Thomas Gleixner --- include/linux/clockchips.h | 1 + kernel/time/Makefile | 5 ++++- kernel/time/tick-broadcast-hrtimer.c | 2 +- 3 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 20a7183f2831..2e4cb67f6e56 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -207,6 +207,7 @@ static inline void clockevents_resume(void) {} static inline int clockevents_notify(unsigned long reason, void *arg) { return 0; } static inline int tick_check_broadcast_expired(void) { return 0; } +static inline void tick_setup_hrtimer_broadcast(void) {}; #endif diff --git a/kernel/time/Makefile b/kernel/time/Makefile index 06151ef4a744..57a413fd0ebf 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -3,7 +3,10 @@ obj-y += timeconv.o posix-clock.o alarmtimer.o obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD) += clockevents.o obj-$(CONFIG_GENERIC_CLOCKEVENTS) += tick-common.o -obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) += tick-broadcast.o tick-broadcast-hrtimer.o +ifeq ($(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST),y) + obj-y += tick-broadcast.o + obj-$(CONFIG_TICK_ONESHOT) += tick-broadcast-hrtimer.o +endif obj-$(CONFIG_GENERIC_SCHED_CLOCK) += sched_clock.o obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o obj-$(CONFIG_TICK_ONESHOT) += tick-sched.o diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c index 92425279312b..eb682d5c697c 100644 --- a/kernel/time/tick-broadcast-hrtimer.c +++ b/kernel/time/tick-broadcast-hrtimer.c @@ -82,7 +82,7 @@ static struct clock_event_device ce_broadcast_hrtimer = { .min_delta_ns = 1, .max_delta_ns = KTIME_MAX, .min_delta_ticks = 1, - .max_delta_ticks = KTIME_MAX, + .max_delta_ticks = ULONG_MAX, .mult = 1, .shift = 0, .cpumask = cpu_all_mask, -- cgit v1.2.3-59-g8ed1b From e2e680fb7566880f7210cadf628c092c0433971c Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 19 Mar 2014 16:21:33 +0530 Subject: hrtimer: Rearrange comments in the order struct members are declared Rearrange kernel doc comments in the order members of struct hrtimer are declared. Signed-off-by: Viresh Kumar Cc: linaro-kernel@lists.linaro.org Cc: fweisbec@gmail.com Cc: trivial@kernel.org Link: http://lkml.kernel.org/r/1db1a3cfbe8a9ea49396af75c6ac04a2e67e3ab0.1395226248.git.viresh.kumar@linaro.org Signed-off-by: Thomas Gleixner --- include/linux/hrtimer.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index d19a5c2d2270..e7a8d3fa91d5 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -96,12 +96,12 @@ enum hrtimer_restart { * @function: timer expiry callback function * @base: pointer to the timer base (per cpu and per clock) * @state: state information (See bit values above) + * @start_pid: timer statistics field to store the pid of the task which + * started the timer * @start_site: timer statistics field to store the site where the timer * was started * @start_comm: timer statistics field to store the name of the process which * started the timer - * @start_pid: timer statistics field to store the pid of the task which - * started the timer * * The hrtimer structure must be initialized by hrtimer_init() */ -- cgit v1.2.3-59-g8ed1b From 6201b4d61fbf194df6371fb3376c5026cb8f5eec Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 18 Mar 2014 16:26:07 +0530 Subject: timer: Remove code redundancy while calling get_nohz_timer_target() There are only two users of get_nohz_timer_target(): timer and hrtimer. Both call it under same circumstances, i.e. #ifdef CONFIG_NO_HZ_COMMON if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu)) return get_nohz_timer_target(); #endif So, it makes more sense to get all this as part of get_nohz_timer_target() instead of duplicating code at two places. For this another parameter is required to be passed to this routine, pinned. Signed-off-by: Viresh Kumar Cc: linaro-kernel@lists.linaro.org Cc: fweisbec@gmail.com Cc: peterz@infradead.org Link: http://lkml.kernel.org/r/1e1b53537217d58d48c2d7a222a9c3ac47d5b64c.1395140107.git.viresh.kumar@linaro.org Signed-off-by: Thomas Gleixner --- include/linux/sched.h | 6 +++++- kernel/hrtimer.c | 15 +-------------- kernel/sched/core.c | 5 ++++- kernel/timer.c | 7 +------ 4 files changed, 11 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 68a0e84463a0..6f6c56f63c68 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -291,10 +291,14 @@ extern int runqueue_is_locked(int cpu); #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) extern void nohz_balance_enter_idle(int cpu); extern void set_cpu_sd_state_idle(void); -extern int get_nohz_timer_target(void); +extern int get_nohz_timer_target(int pinned); #else static inline void nohz_balance_enter_idle(int cpu) { } static inline void set_cpu_sd_state_idle(void) { } +static inline int get_nohz_timer_target(int pinned) +{ + return smp_processor_id(); +} #endif /* diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 09094361dce5..d55092ceee29 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -168,19 +168,6 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer, } } - -/* - * Get the preferred target CPU for NOHZ - */ -static int hrtimer_get_target(int this_cpu, int pinned) -{ -#ifdef CONFIG_NO_HZ_COMMON - if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu)) - return get_nohz_timer_target(); -#endif - return this_cpu; -} - /* * With HIGHRES=y we do not migrate the timer when it is expiring * before the next event on the target cpu because we cannot reprogram @@ -214,7 +201,7 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base, struct hrtimer_clock_base *new_base; struct hrtimer_cpu_base *new_cpu_base; int this_cpu = smp_processor_id(); - int cpu = hrtimer_get_target(this_cpu, pinned); + int cpu = get_nohz_timer_target(pinned); int basenum = base->index; again: diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b46131ef6aab..c0339e206cc2 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -555,12 +555,15 @@ void resched_cpu(int cpu) * selecting an idle cpu will add more delays to the timers than intended * (as that cpu's timer base may not be uptodate wrt jiffies etc). */ -int get_nohz_timer_target(void) +int get_nohz_timer_target(int pinned) { int cpu = smp_processor_id(); int i; struct sched_domain *sd; + if (pinned || !get_sysctl_timer_migration() || !idle_cpu(cpu)) + return cpu; + rcu_read_lock(); for_each_domain(cpu, sd) { for_each_cpu(i, sched_domain_span(sd)) { diff --git a/kernel/timer.c b/kernel/timer.c index 8e503fec1fba..1d35ddadc045 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -760,12 +760,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, debug_activate(timer, expires); - cpu = smp_processor_id(); - -#if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP) - if (!pinned && get_sysctl_timer_migration() && idle_cpu(cpu)) - cpu = get_nohz_timer_target(); -#endif + cpu = get_nohz_timer_target(pinned); new_base = per_cpu(tvec_bases, cpu); if (base != new_base) { -- cgit v1.2.3-59-g8ed1b From ea2e64f280d2a34a8ed9ae3d783cd770d14b70ec Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 23 Mar 2014 14:20:44 +0000 Subject: workqueue: Provide destroy_delayed_work_on_stack() If a delayed or deferrable work is on stack we need to tell debug objects that we are destroying the timer and the work. Otherwise we leak the tracking object. Signed-off-by: Thomas Gleixner Cc: Vince Weaver Acked-by: Tejun Heo Link: http://lkml.kernel.org/r/20140323141939.911487677@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/workqueue.h | 2 ++ kernel/workqueue.c | 7 +++++++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 594521ba0d43..abdbe5af119d 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -191,6 +191,7 @@ struct execute_work { #ifdef CONFIG_DEBUG_OBJECTS_WORK extern void __init_work(struct work_struct *work, int onstack); extern void destroy_work_on_stack(struct work_struct *work); +extern void destroy_delayed_work_on_stack(struct delayed_work *work); static inline unsigned int work_static(struct work_struct *work) { return *work_data_bits(work) & WORK_STRUCT_STATIC; @@ -198,6 +199,7 @@ static inline unsigned int work_static(struct work_struct *work) #else static inline void __init_work(struct work_struct *work, int onstack) { } static inline void destroy_work_on_stack(struct work_struct *work) { } +static inline void destroy_delayed_work_on_stack(struct delayed_work *work) { } static inline unsigned int work_static(struct work_struct *work) { return 0; } #endif diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 82ef9f3b7473..5b690b5a9e74 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -516,6 +516,13 @@ void destroy_work_on_stack(struct work_struct *work) } EXPORT_SYMBOL_GPL(destroy_work_on_stack); +void destroy_delayed_work_on_stack(struct delayed_work *work) +{ + destroy_timer_on_stack(&work->timer); + debug_object_free(&work->work, &work_debug_descr); +} +EXPORT_SYMBOL_GPL(destroy_delayed_work_on_stack); + #else static inline void debug_work_activate(struct work_struct *work) { } static inline void debug_work_deactivate(struct work_struct *work) { } -- cgit v1.2.3-59-g8ed1b