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(-) (limited to 'kernel/sched/core.c') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 78d8facba456..22fce36426c0 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 v1.2.3 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(-) (limited to 'kernel/sched/core.c') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 2803264c512f..c1961761311d 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 9256118bd40c..43731fe51c97 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 481951bf091d..750cb8082694 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 22fce36426c0..fe365c9a08e9 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 v1.2.3