diff options
Diffstat (limited to 'kernel/sched')
| -rw-r--r-- | kernel/sched/core.c | 47 | ||||
| -rw-r--r-- | kernel/sched/fair.c | 25 | ||||
| -rw-r--r-- | kernel/sched/sched.h | 5 | ||||
| -rw-r--r-- | kernel/sched/work-simple.c | 1 |
4 files changed, 50 insertions, 28 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 392aad4ec3d6..d21091f2fd1f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1558,9 +1558,9 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) { check_preempt_curr(rq, p, wake_flags); - trace_sched_wakeup(p, true); - p->state = TASK_RUNNING; + trace_sched_wakeup(p); + #ifdef CONFIG_SMP if (p->sched_class->task_woken) p->sched_class->task_woken(rq, p); @@ -1784,6 +1784,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) if (!(wake_flags & WF_LOCK_SLEEPER)) p->saved_state = TASK_RUNNING; + trace_sched_waking(p); + success = 1; /* we're going to change ->state */ cpu = task_cpu(p); @@ -2188,7 +2190,7 @@ void wake_up_new_task(struct task_struct *p) rq = __task_rq_lock(p); activate_task(rq, p, 0); p->on_rq = TASK_ON_RQ_QUEUED; - trace_sched_wakeup_new(p, true); + trace_sched_wakeup_new(p); check_preempt_curr(rq, p, WF_FORK); #ifdef CONFIG_SMP if (p->sched_class->task_woken) @@ -2311,11 +2313,11 @@ static struct rq *finish_task_switch(struct task_struct *prev) * If a task dies, then it sets TASK_DEAD in tsk->state and calls * schedule one last time. The schedule call will never return, and * the scheduled task must drop that reference. - * The test for TASK_DEAD must occur while the runqueue locks are - * still held, otherwise prev could be scheduled on another cpu, die - * there before we look at prev->state, and then the reference would - * be dropped twice. - * Manfred Spraul <manfred@colorfullife.com> + * + * We must observe prev->state before clearing prev->on_cpu (in + * finish_lock_switch), otherwise a concurrent wakeup can get prev + * running on another CPU and we could rave with its RUNNING -> DEAD + * transition, resulting in a double drop. */ prev_state = prev->state; vtime_task_switch(prev); @@ -2456,13 +2458,20 @@ unsigned long nr_running(void) /* * Check if only the current task is running on the cpu. + * + * Caution: this function does not check that the caller has disabled + * preemption, thus the result might have a time-of-check-to-time-of-use + * race. The caller is responsible to use it correctly, for example: + * + * - from a non-preemptable section (of course) + * + * - from a thread that is bound to a single CPU + * + * - in a loop with very short iterations (e.g. a polling loop) */ bool single_task_running(void) { - if (cpu_rq(smp_processor_id())->nr_running == 1) - return true; - else - return false; + return raw_rq()->nr_running == 1; } EXPORT_SYMBOL(single_task_running); @@ -4475,7 +4484,7 @@ SYSCALL_DEFINE0(sched_yield) int __sched _cond_resched(void) { - if (should_resched()) { + if (should_resched(0)) { preempt_schedule_common(); return 1; } @@ -4493,7 +4502,7 @@ EXPORT_SYMBOL(_cond_resched); */ int __cond_resched_lock(spinlock_t *lock) { - int resched = should_resched(); + int resched = should_resched(PREEMPT_LOCK_OFFSET); int ret = 0; lockdep_assert_held(lock); @@ -4516,7 +4525,7 @@ int __sched __cond_resched_softirq(void) { BUG_ON(!in_softirq()); - if (should_resched()) { + if (should_resched(SOFTIRQ_DISABLE_OFFSET)) { local_bh_enable(); preempt_schedule_common(); local_bh_disable(); @@ -5672,6 +5681,14 @@ static int sched_cpu_active(struct notifier_block *nfb, case CPU_STARTING: set_cpu_rq_start_time(); return NOTIFY_OK; + case CPU_ONLINE: + /* + * At this point a starting CPU has marked itself as online via + * set_cpu_online(). But it might not yet have marked itself + * as active, which is essential from here on. + * + * Thus, fall-through and help the starting CPU along. + */ case CPU_DOWN_FAILED: set_cpu_active((long)hcpu, true); return NOTIFY_OK; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 92c53d074f41..7aae8d27611e 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5126,18 +5126,21 @@ again: * entity, update_curr() will update its vruntime, otherwise * forget we've ever seen it. */ - if (curr && curr->on_rq) - update_curr(cfs_rq); - else - curr = NULL; + if (curr) { + if (curr->on_rq) + update_curr(cfs_rq); + else + curr = NULL; - /* - * This call to check_cfs_rq_runtime() will do the throttle and - * dequeue its entity in the parent(s). Therefore the 'simple' - * nr_running test will indeed be correct. - */ - if (unlikely(check_cfs_rq_runtime(cfs_rq))) - goto simple; + /* + * This call to check_cfs_rq_runtime() will do the + * throttle and dequeue its entity in the parent(s). + * Therefore the 'simple' nr_running test will indeed + * be correct. + */ + if (unlikely(check_cfs_rq_runtime(cfs_rq))) + goto simple; + } se = pick_next_entity(cfs_rq, curr); cfs_rq = group_cfs_rq(se); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 308f664541a5..1bdd1e5f056d 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1068,9 +1068,10 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) * After ->on_cpu is cleared, the task can be moved to a different CPU. * We must ensure this doesn't happen until the switch is completely * finished. + * + * Pairs with the control dependency and rmb in try_to_wake_up(). */ - smp_wmb(); - prev->on_cpu = 0; + smp_store_release(&prev->on_cpu, 0); #endif #ifdef CONFIG_DEBUG_SPINLOCK /* this is a valid case when another task releases the spinlock */ diff --git a/kernel/sched/work-simple.c b/kernel/sched/work-simple.c index c996f755dba6..e57a0522573f 100644 --- a/kernel/sched/work-simple.c +++ b/kernel/sched/work-simple.c @@ -10,6 +10,7 @@ #include <linux/kthread.h> #include <linux/slab.h> #include <linux/spinlock.h> +#include <linux/export.h> #define SWORK_EVENT_PENDING (1 << 0) |