From d9c0ffcabd6aae7ff1e34e8078354c13bb9f1183 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 28 Jun 2018 18:29:41 +0200 Subject: sched/nohz: Skip remote tick on idle task entirely Some people have reported that the warning in sched_tick_remote() occasionally triggers, especially in favour of some RCU-Torture pressure: WARNING: CPU: 11 PID: 906 at kernel/sched/core.c:3138 sched_tick_remote+0xb6/0xc0 Modules linked in: CPU: 11 PID: 906 Comm: kworker/u32:3 Not tainted 4.18.0-rc2+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 Workqueue: events_unbound sched_tick_remote RIP: 0010:sched_tick_remote+0xb6/0xc0 Code: e8 0f 06 b8 00 c6 03 00 fb eb 9d 8b 43 04 85 c0 75 8d 48 8b 83 e0 0a 00 00 48 85 c0 75 81 eb 88 48 89 df e8 bc fe ff ff eb aa <0f> 0b eb +c5 66 0f 1f 44 00 00 bf 17 00 00 00 e8 b6 2e fe ff 0f b6 Call Trace: process_one_work+0x1df/0x3b0 worker_thread+0x44/0x3d0 kthread+0xf3/0x130 ? set_worker_desc+0xb0/0xb0 ? kthread_create_worker_on_cpu+0x70/0x70 ret_from_fork+0x35/0x40 This happens when the remote tick applies on an idle task. Usually the idle_cpu() check avoids that, but it is performed before we lock the runqueue and it is therefore racy. It was intended to be that way in order to prevent from useless runqueue locks since idle task tick callback is a no-op. Now if the racy check slips out of our hands and we end up remotely ticking an idle task, the empty task_tick_idle() is harmless. Still it won't pass the WARN_ON_ONCE() test that ensures rq_clock_task() is not too far from curr->se.exec_start because update_curr_idle() doesn't update the exec_start value like other scheduler policies. Hence the reported false positive. So let's have another check, while the rq is locked, to make sure we don't remote tick on an idle task. The lockless idle_cpu() still applies to avoid unecessary rq lock contention. Reported-by: Jacek Tomaka Reported-by: Paul E. McKenney Reported-by: Anna-Maria Gleixner Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1530203381-31234-1-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 36 +++++++++++++++++++++--------------- 1 file changed, 21 insertions(+), 15 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 78d8fac..22fce36 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3113,7 +3113,9 @@ static void sched_tick_remote(struct work_struct *work) struct tick_work *twork = container_of(dwork, struct tick_work, work); int cpu = twork->cpu; struct rq *rq = cpu_rq(cpu); + struct task_struct *curr; struct rq_flags rf; + u64 delta; /* * Handle the tick only if it appears the remote CPU is running in full @@ -3122,24 +3124,28 @@ static void sched_tick_remote(struct work_struct *work) * statistics and checks timeslices in a time-independent way, regardless * of when exactly it is running. */ - if (!idle_cpu(cpu) && tick_nohz_tick_stopped_cpu(cpu)) { - struct task_struct *curr; - u64 delta; + if (idle_cpu(cpu) || !tick_nohz_tick_stopped_cpu(cpu)) + goto out_requeue; - rq_lock_irq(rq, &rf); - update_rq_clock(rq); - curr = rq->curr; - delta = rq_clock_task(rq) - curr->se.exec_start; + rq_lock_irq(rq, &rf); + curr = rq->curr; + if (is_idle_task(curr)) + goto out_unlock; - /* - * Make sure the next tick runs within a reasonable - * amount of time. - */ - WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3); - curr->sched_class->task_tick(rq, curr, 0); - rq_unlock_irq(rq, &rf); - } + update_rq_clock(rq); + delta = rq_clock_task(rq) - curr->se.exec_start; + + /* + * Make sure the next tick runs within a reasonable + * amount of time. + */ + WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3); + curr->sched_class->task_tick(rq, curr, 0); + +out_unlock: + rq_unlock_irq(rq, &rf); +out_requeue: /* * Run the remote tick once per second (1Hz). This arbitrary * frequency is large enough to avoid overload but short enough -- cgit v1.1 From 296b2ffe7fa9ed756c41415c6b1512bc4ad687b1 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Tue, 26 Jun 2018 15:53:22 +0200 Subject: sched/rt: Fix call to cpufreq_update_util() With commit: 8f111bc357aa ("cpufreq/schedutil: Rewrite CPUFREQ_RT support") the schedutil governor uses rq->rt.rt_nr_running to detect whether an RT task is currently running on the CPU and to set frequency to max if necessary. cpufreq_update_util() is called in enqueue/dequeue_top_rt_rq() but rq->rt.rt_nr_running has not been updated yet when dequeue_top_rt_rq() is called so schedutil still considers that an RT task is running when the last task is dequeued. The update of rq->rt.rt_nr_running happens later in dequeue_rt_stack(). In fact, we can take advantage of the sequence that the dequeue then re-enqueue rt entities when a rt task is enqueued or dequeued; As a result enqueue_top_rt_rq() is always called when a task is enqueued or dequeued and also when groups are throttled or unthrottled. The only place that not use enqueue_top_rt_rq() is when root rt_rq is throttled. Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: efault@gmx.de Cc: juri.lelli@redhat.com Cc: patrick.bellasi@arm.com Cc: viresh.kumar@linaro.org Fixes: 8f111bc357aa ('cpufreq/schedutil: Rewrite CPUFREQ_RT support') Link: http://lkml.kernel.org/r/1530021202-21695-1-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar --- kernel/sched/cpufreq_schedutil.c | 2 +- kernel/sched/rt.c | 16 ++++++++++------ kernel/sched/sched.h | 5 +++++ 3 files changed, 16 insertions(+), 7 deletions(-) diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 3cde464..c907fde 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -192,7 +192,7 @@ static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu) { struct rq *rq = cpu_rq(sg_cpu->cpu); - if (rq->rt.rt_nr_running) + if (rt_rq_is_runnable(&rq->rt)) return sg_cpu->max; /* diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 47556b0..5725670 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -508,8 +508,11 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq) rt_se = rt_rq->tg->rt_se[cpu]; - if (!rt_se) + if (!rt_se) { dequeue_top_rt_rq(rt_rq); + /* Kick cpufreq (see the comment in kernel/sched/sched.h). */ + cpufreq_update_util(rq_of_rt_rq(rt_rq), 0); + } else if (on_rt_rq(rt_se)) dequeue_rt_entity(rt_se, 0); } @@ -1001,8 +1004,6 @@ dequeue_top_rt_rq(struct rt_rq *rt_rq) sub_nr_running(rq, rt_rq->rt_nr_running); rt_rq->rt_queued = 0; - /* Kick cpufreq (see the comment in kernel/sched/sched.h). */ - cpufreq_update_util(rq, 0); } static void @@ -1014,11 +1015,14 @@ enqueue_top_rt_rq(struct rt_rq *rt_rq) if (rt_rq->rt_queued) return; - if (rt_rq_throttled(rt_rq) || !rt_rq->rt_nr_running) + + if (rt_rq_throttled(rt_rq)) return; - add_nr_running(rq, rt_rq->rt_nr_running); - rt_rq->rt_queued = 1; + if (rt_rq->rt_nr_running) { + add_nr_running(rq, rt_rq->rt_nr_running); + rt_rq->rt_queued = 1; + } /* Kick cpufreq (see the comment in kernel/sched/sched.h). */ cpufreq_update_util(rq, 0); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 6601baf..27ddec3 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -609,6 +609,11 @@ struct rt_rq { #endif }; +static inline bool rt_rq_is_runnable(struct rt_rq *rt_rq) +{ + return rt_rq->rt_queued && rt_rq->rt_nr_running; +} + /* Deadline class' related fields in a runqueue */ struct dl_rq { /* runqueue is an rbtree, ordered by deadline */ -- cgit v1.1 From 512ac999d2755d2b7109e996a76b6fb8b888631d Mon Sep 17 00:00:00 2001 From: Xunlei Pang Date: Wed, 20 Jun 2018 18:18:33 +0800 Subject: sched/fair: Fix bandwidth timer clock drift condition I noticed that cgroup task groups constantly get throttled even if they have low CPU usage, this causes some jitters on the response time to some of our business containers when enabling CPU quotas. It's very simple to reproduce: mkdir /sys/fs/cgroup/cpu/test cd /sys/fs/cgroup/cpu/test echo 100000 > cpu.cfs_quota_us echo $$ > tasks then repeat: cat cpu.stat | grep nr_throttled # nr_throttled will increase steadily After some analysis, we found that cfs_rq::runtime_remaining will be cleared by expire_cfs_rq_runtime() due to two equal but stale "cfs_{b|q}->runtime_expires" after period timer is re-armed. The current condition to judge clock drift in expire_cfs_rq_runtime() is wrong, the two runtime_expires are actually the same when clock drift happens, so this condtion can never hit. The orginal design was correctly done by this commit: a9cf55b28610 ("sched: Expire invalid runtime") ... but was changed to be the current implementation due to its locking bug. This patch introduces another way, it adds a new field in both structures cfs_rq and cfs_bandwidth to record the expiration update sequence, and uses them to figure out if clock drift happens (true if they are equal). Signed-off-by: Xunlei Pang Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Ben Segall Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: 51f2176d74ac ("sched/fair: Fix unlocked reads of some cfs_b->quota/period") Link: http://lkml.kernel.org/r/20180620101834.24455-1-xlpang@linux.alibaba.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 14 ++++++++------ kernel/sched/sched.h | 6 ++++-- 2 files changed, 12 insertions(+), 8 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 1866e64..791707c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4590,6 +4590,7 @@ void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b) now = sched_clock_cpu(smp_processor_id()); cfs_b->runtime = cfs_b->quota; cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period); + cfs_b->expires_seq++; } static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) @@ -4612,6 +4613,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) struct task_group *tg = cfs_rq->tg; struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg); u64 amount = 0, min_amount, expires; + int expires_seq; /* note: this is a positive sum as runtime_remaining <= 0 */ min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining; @@ -4628,6 +4630,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) cfs_b->idle = 0; } } + expires_seq = cfs_b->expires_seq; expires = cfs_b->runtime_expires; raw_spin_unlock(&cfs_b->lock); @@ -4637,8 +4640,10 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) * spread between our sched_clock and the one on which runtime was * issued. */ - if ((s64)(expires - cfs_rq->runtime_expires) > 0) + if (cfs_rq->expires_seq != expires_seq) { + cfs_rq->expires_seq = expires_seq; cfs_rq->runtime_expires = expires; + } return cfs_rq->runtime_remaining > 0; } @@ -4664,12 +4669,9 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq) * has not truly expired. * * Fortunately we can check determine whether this the case by checking - * whether the global deadline has advanced. It is valid to compare - * cfs_b->runtime_expires without any locks since we only care about - * exact equality, so a partial write will still work. + * whether the global deadline(cfs_b->expires_seq) has advanced. */ - - if (cfs_rq->runtime_expires != cfs_b->runtime_expires) { + if (cfs_rq->expires_seq == cfs_b->expires_seq) { /* extend local deadline, drift is bounded above by 2 ticks */ cfs_rq->runtime_expires += TICK_NSEC; } else { diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 27ddec3..c7742dc 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -334,9 +334,10 @@ struct cfs_bandwidth { u64 runtime; s64 hierarchical_quota; u64 runtime_expires; + int expires_seq; - int idle; - int period_active; + short idle; + short period_active; struct hrtimer period_timer; struct hrtimer slack_timer; struct list_head throttled_cfs_rq; @@ -551,6 +552,7 @@ struct cfs_rq { #ifdef CONFIG_CFS_BANDWIDTH int runtime_enabled; + int expires_seq; u64 runtime_expires; s64 runtime_remaining; -- cgit v1.1 From f1d1be8aee6c461652aea8f58bedebaa73d7f4d3 Mon Sep 17 00:00:00 2001 From: Xunlei Pang Date: Wed, 20 Jun 2018 18:18:34 +0800 Subject: sched/fair: Advance global expiration when period timer is restarted When period gets restarted after some idle time, start_cfs_bandwidth() doesn't update the expiration information, expire_cfs_rq_runtime() will see cfs_rq->runtime_expires smaller than rq clock and go to the clock drift logic, wasting needless CPU cycles on the scheduler hot path. Update the global expiration in start_cfs_bandwidth() to avoid frequent expire_cfs_rq_runtime() calls once a new period begins. Signed-off-by: Xunlei Pang Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Ben Segall Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180620101834.24455-2-xlpang@linux.alibaba.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 791707c..840b92e 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5204,13 +5204,18 @@ static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b) { + u64 overrun; + lockdep_assert_held(&cfs_b->lock); - if (!cfs_b->period_active) { - cfs_b->period_active = 1; - hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period); - hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED); - } + if (cfs_b->period_active) + return; + + cfs_b->period_active = 1; + overrun = hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period); + cfs_b->runtime_expires += (overrun + 1) * ktime_to_ns(cfs_b->period); + cfs_b->expires_seq++; + hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED); } static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) -- cgit v1.1 From 3482d98bbc730758b63a5d1cf41d05ea17481412 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Thu, 14 Jun 2018 12:33:00 +0200 Subject: sched/util_est: Fix util_est_dequeue() for throttled cfs_rq When a cfs_rq is throttled, parent cfs_rq->nr_running is decreased and everything happens at cfs_rq level. Currently util_est stays unchanged in such case and it keeps accounting the utilization of throttled tasks. This can somewhat make sense as we don't dequeue tasks but only throttled cfs_rq. If a task of another group is enqueued/dequeued and root cfs_rq becomes idle during the dequeue, util_est will be cleared whereas it was accounting util_est of throttled tasks before. So the behavior of util_est is not always the same regarding throttled tasks and depends of side activity. Furthermore, util_est will not be updated when the cfs_rq is unthrottled as everything happens at cfs_rq level. Main results is that util_est will stay null whereas we now have running tasks. We have to wait for the next dequeue/enqueue of the previously throttled tasks to get an up to date util_est. Remove the assumption that cfs_rq's estimated utilization of a CPU is 0 if there is no running task so the util_est of a task remains until the latter is dequeued even if its cfs_rq has been throttled. Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Patrick Bellasi Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: 7f65ea42eb00 ("sched/fair: Add util_est on top of PELT") Link: http://lkml.kernel.org/r/1528972380-16268-1-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 840b92e..2f0a0be 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3982,18 +3982,10 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) if (!sched_feat(UTIL_EST)) return; - /* - * Update root cfs_rq's estimated utilization - * - * If *p is the last task then the root cfs_rq's estimated utilization - * of a CPU is 0 by definition. - */ - ue.enqueued = 0; - if (cfs_rq->nr_running) { - ue.enqueued = cfs_rq->avg.util_est.enqueued; - ue.enqueued -= min_t(unsigned int, ue.enqueued, - (_task_util_est(p) | UTIL_AVG_UNCHANGED)); - } + /* Update root cfs_rq's estimated utilization */ + ue.enqueued = cfs_rq->avg.util_est.enqueued; + ue.enqueued -= min_t(unsigned int, ue.enqueued, + (_task_util_est(p) | UTIL_AVG_UNCHANGED)); WRITE_ONCE(cfs_rq->avg.util_est.enqueued, ue.enqueued); /* -- cgit v1.1 From 1cef1150ef40ec52f507436a14230cbc2623299c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Jun 2018 11:45:49 +0200 Subject: kthread, sched/core: Fix kthread_parkme() (again...) Gaurav reports that commit: 85f1abe0019f ("kthread, sched/wait: Fix kthread_parkme() completion issue") isn't working for him. Because of the following race: > controller Thread CPUHP Thread > takedown_cpu > kthread_park > kthread_parkme > Set KTHREAD_SHOULD_PARK > smpboot_thread_fn > set Task interruptible > > > wake_up_process > if (!(p->state & state)) > goto out; > > Kthread_parkme > SET TASK_PARKED > schedule > raw_spin_lock(&rq->lock) > ttwu_remote > waiting for __task_rq_lock > context_switch > > finish_lock_switch > > > > Case TASK_PARKED > kthread_park_complete > > > SET Running Furthermore, Oleg noticed that the whole scheduler TASK_PARKED handling is buggered because the TASK_DEAD thing is done with preemption disabled, the current code can still complete early on preemption :/ So basically revert that earlier fix and go with a variant of the alternative mentioned in the commit. Promote TASK_PARKED to special state to avoid the store-store issue on task->state leading to the WARN in kthread_unpark() -> __kthread_bind(). But in addition, add wait_task_inactive() to kthread_park() to ensure the task really is PARKED when we return from kthread_park(). This avoids the whole kthread still gets migrated nonsense -- although it would be really good to get this done differently. Reported-by: Gaurav Kohli Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: 85f1abe0019f ("kthread, sched/wait: Fix kthread_parkme() completion issue") Signed-off-by: Ingo Molnar --- include/linux/kthread.h | 1 - include/linux/sched.h | 2 +- kernel/kthread.c | 30 ++++++++++++++++++++++++------ kernel/sched/core.c | 31 +++++++++++-------------------- 4 files changed, 36 insertions(+), 28 deletions(-) diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 2803264..c196176 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -62,7 +62,6 @@ void *kthread_probe_data(struct task_struct *k); int kthread_park(struct task_struct *k); void kthread_unpark(struct task_struct *k); void kthread_parkme(void); -void kthread_park_complete(struct task_struct *k); int kthreadd(void *unused); extern struct task_struct *kthreadd_task; diff --git a/include/linux/sched.h b/include/linux/sched.h index 9256118..43731fe 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -118,7 +118,7 @@ struct task_group; * the comment with set_special_state(). */ #define is_special_task_state(state) \ - ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_DEAD)) + ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | TASK_DEAD)) #define __set_current_state(state_value) \ do { \ diff --git a/kernel/kthread.c b/kernel/kthread.c index 481951b..750cb80 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -177,9 +177,20 @@ void *kthread_probe_data(struct task_struct *task) static void __kthread_parkme(struct kthread *self) { for (;;) { - set_current_state(TASK_PARKED); + /* + * TASK_PARKED is a special state; we must serialize against + * possible pending wakeups to avoid store-store collisions on + * task->state. + * + * Such a collision might possibly result in the task state + * changin from TASK_PARKED and us failing the + * wait_task_inactive() in kthread_park(). + */ + set_special_state(TASK_PARKED); if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags)) break; + + complete_all(&self->parked); schedule(); } __set_current_state(TASK_RUNNING); @@ -191,11 +202,6 @@ void kthread_parkme(void) } EXPORT_SYMBOL_GPL(kthread_parkme); -void kthread_park_complete(struct task_struct *k) -{ - complete_all(&to_kthread(k)->parked); -} - static int kthread(void *_create) { /* Copy data: it's on kthread's stack */ @@ -461,6 +467,9 @@ void kthread_unpark(struct task_struct *k) reinit_completion(&kthread->parked); clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags); + /* + * __kthread_parkme() will either see !SHOULD_PARK or get the wakeup. + */ wake_up_state(k, TASK_PARKED); } EXPORT_SYMBOL_GPL(kthread_unpark); @@ -487,7 +496,16 @@ int kthread_park(struct task_struct *k) set_bit(KTHREAD_SHOULD_PARK, &kthread->flags); if (k != current) { wake_up_process(k); + /* + * Wait for __kthread_parkme() to complete(), this means we + * _will_ have TASK_PARKED and are about to call schedule(). + */ wait_for_completion(&kthread->parked); + /* + * Now wait for that schedule() to complete and the task to + * get scheduled out. + */ + WARN_ON_ONCE(!wait_task_inactive(k, TASK_PARKED)); } return 0; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 22fce36..fe365c9 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7,7 +7,6 @@ */ #include "sched.h" -#include #include #include @@ -2724,28 +2723,20 @@ static struct rq *finish_task_switch(struct task_struct *prev) membarrier_mm_sync_core_before_usermode(mm); mmdrop(mm); } - if (unlikely(prev_state & (TASK_DEAD|TASK_PARKED))) { - switch (prev_state) { - case TASK_DEAD: - if (prev->sched_class->task_dead) - prev->sched_class->task_dead(prev); + if (unlikely(prev_state == TASK_DEAD)) { + if (prev->sched_class->task_dead) + prev->sched_class->task_dead(prev); - /* - * Remove function-return probe instances associated with this - * task and put them back on the free list. - */ - kprobe_flush_task(prev); - - /* Task is done with its stack. */ - put_task_stack(prev); + /* + * Remove function-return probe instances associated with this + * task and put them back on the free list. + */ + kprobe_flush_task(prev); - put_task_struct(prev); - break; + /* Task is done with its stack. */ + put_task_stack(prev); - case TASK_PARKED: - kthread_park_complete(prev); - break; - } + put_task_struct(prev); } tick_nohz_task_switch(); -- cgit v1.1