From ff77e468535987b3d21b7bd4da15608ea3ce7d0b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 18 Jan 2016 15:27:07 +0100 Subject: sched/rt: Fix PI handling vs. sched_setscheduler() Andrea Parri reported: > I found that the following scenario (with CONFIG_RT_GROUP_SCHED=y) is not > handled correctly: > > T1 (prio = 20) > lock(rtmutex); > > T2 (prio = 20) > blocks on rtmutex (rt_nr_boosted = 0 on T1's rq) > > T1 (prio = 20) > sys_set_scheduler(prio = 0) > [new_effective_prio == oldprio] > T1 prio = 20 (rt_nr_boosted = 0 on T1's rq) > > The last step is incorrect as T1 is now boosted (c.f., rt_se_boosted()); > in particular, if we continue with > > T1 (prio = 20) > unlock(rtmutex) > wakeup(T2) > adjust_prio(T1) > [prio != rt_mutex_getprio(T1)] > dequeue(T1) > rt_nr_boosted = (unsigned long)(-1) > ... > T1 prio = 0 > > then we end up leaving rt_nr_boosted in an "inconsistent" state. > > The simple program attached could reproduce the previous scenario; note > that, as a consequence of the presence of this state, the "assertion" > > WARN_ON(!rt_nr_running && rt_nr_boosted) > > from dec_rt_group() may trigger. So normally we dequeue/enqueue tasks in sched_setscheduler(), which would ensure the accounting stays correct. However in the early PI path we fail to do so. So this was introduced at around v3.14, by: c365c292d059 ("sched: Consider pi boosting in setscheduler()") which fixed another problem exactly because that dequeue/enqueue, joy. Fix this by teaching rt about DEQUEUE_SAVE/ENQUEUE_RESTORE and have it preserve runqueue location with that option. This requires decoupling the on_rt_rq() state from being on the list. In order to allow for explicit movement during the SAVE/RESTORE, introduce {DE,EN}QUEUE_MOVE. We still must use SAVE/RESTORE in these cases to preserve other invariants. Respecting the SAVE/RESTORE flags also has the (nice) side-effect that things like sys_nice()/sys_sched_setaffinity() also do not reorder FIFO tasks (whereas they used to before this patch). Reported-by: Andrea Parri Tested-by: Andrea Parri Signed-off-by: Peter Zijlstra (Intel) Cc: Juri Lelli Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- kernel/sched/rt.c | 86 ++++++++++++++++++++++++++++++++++++++----------------- 1 file changed, 60 insertions(+), 26 deletions(-) (limited to 'kernel/sched/rt.c') diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 8ec86abe0ea1..406a9c20b210 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -436,7 +436,7 @@ static void dequeue_top_rt_rq(struct rt_rq *rt_rq); static inline int on_rt_rq(struct sched_rt_entity *rt_se) { - return !list_empty(&rt_se->run_list); + return rt_se->on_rq; } #ifdef CONFIG_RT_GROUP_SCHED @@ -482,8 +482,8 @@ static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se) return rt_se->my_q; } -static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head); -static void dequeue_rt_entity(struct sched_rt_entity *rt_se); +static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags); +static void dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags); static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) { @@ -499,7 +499,7 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) if (!rt_se) enqueue_top_rt_rq(rt_rq); else if (!on_rt_rq(rt_se)) - enqueue_rt_entity(rt_se, false); + enqueue_rt_entity(rt_se, 0); if (rt_rq->highest_prio.curr < curr->prio) resched_curr(rq); @@ -516,7 +516,7 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq) if (!rt_se) dequeue_top_rt_rq(rt_rq); else if (on_rt_rq(rt_se)) - dequeue_rt_entity(rt_se); + dequeue_rt_entity(rt_se, 0); } static inline int rt_rq_throttled(struct rt_rq *rt_rq) @@ -1166,7 +1166,30 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) dec_rt_group(rt_se, rt_rq); } -static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head) +/* + * Change rt_se->run_list location unless SAVE && !MOVE + * + * assumes ENQUEUE/DEQUEUE flags match + */ +static inline bool move_entity(unsigned int flags) +{ + if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) == DEQUEUE_SAVE) + return false; + + return true; +} + +static void __delist_rt_entity(struct sched_rt_entity *rt_se, struct rt_prio_array *array) +{ + list_del_init(&rt_se->run_list); + + if (list_empty(array->queue + rt_se_prio(rt_se))) + __clear_bit(rt_se_prio(rt_se), array->bitmap); + + rt_se->on_list = 0; +} + +static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags) { struct rt_rq *rt_rq = rt_rq_of_se(rt_se); struct rt_prio_array *array = &rt_rq->active; @@ -1179,26 +1202,37 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head) * get throttled and the current group doesn't have any other * active members. */ - if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running)) + if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running)) { + if (rt_se->on_list) + __delist_rt_entity(rt_se, array); return; + } - if (head) - list_add(&rt_se->run_list, queue); - else - list_add_tail(&rt_se->run_list, queue); - __set_bit(rt_se_prio(rt_se), array->bitmap); + if (move_entity(flags)) { + WARN_ON_ONCE(rt_se->on_list); + if (flags & ENQUEUE_HEAD) + list_add(&rt_se->run_list, queue); + else + list_add_tail(&rt_se->run_list, queue); + + __set_bit(rt_se_prio(rt_se), array->bitmap); + rt_se->on_list = 1; + } + rt_se->on_rq = 1; inc_rt_tasks(rt_se, rt_rq); } -static void __dequeue_rt_entity(struct sched_rt_entity *rt_se) +static void __dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags) { struct rt_rq *rt_rq = rt_rq_of_se(rt_se); struct rt_prio_array *array = &rt_rq->active; - list_del_init(&rt_se->run_list); - if (list_empty(array->queue + rt_se_prio(rt_se))) - __clear_bit(rt_se_prio(rt_se), array->bitmap); + if (move_entity(flags)) { + WARN_ON_ONCE(!rt_se->on_list); + __delist_rt_entity(rt_se, array); + } + rt_se->on_rq = 0; dec_rt_tasks(rt_se, rt_rq); } @@ -1207,7 +1241,7 @@ static void __dequeue_rt_entity(struct sched_rt_entity *rt_se) * Because the prio of an upper entry depends on the lower * entries, we must remove entries top - down. */ -static void dequeue_rt_stack(struct sched_rt_entity *rt_se) +static void dequeue_rt_stack(struct sched_rt_entity *rt_se, unsigned int flags) { struct sched_rt_entity *back = NULL; @@ -1220,31 +1254,31 @@ static void dequeue_rt_stack(struct sched_rt_entity *rt_se) for (rt_se = back; rt_se; rt_se = rt_se->back) { if (on_rt_rq(rt_se)) - __dequeue_rt_entity(rt_se); + __dequeue_rt_entity(rt_se, flags); } } -static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head) +static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags) { struct rq *rq = rq_of_rt_se(rt_se); - dequeue_rt_stack(rt_se); + dequeue_rt_stack(rt_se, flags); for_each_sched_rt_entity(rt_se) - __enqueue_rt_entity(rt_se, head); + __enqueue_rt_entity(rt_se, flags); enqueue_top_rt_rq(&rq->rt); } -static void dequeue_rt_entity(struct sched_rt_entity *rt_se) +static void dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags) { struct rq *rq = rq_of_rt_se(rt_se); - dequeue_rt_stack(rt_se); + dequeue_rt_stack(rt_se, flags); for_each_sched_rt_entity(rt_se) { struct rt_rq *rt_rq = group_rt_rq(rt_se); if (rt_rq && rt_rq->rt_nr_running) - __enqueue_rt_entity(rt_se, false); + __enqueue_rt_entity(rt_se, flags); } enqueue_top_rt_rq(&rq->rt); } @@ -1260,7 +1294,7 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags) if (flags & ENQUEUE_WAKEUP) rt_se->timeout = 0; - enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD); + enqueue_rt_entity(rt_se, flags); if (!task_current(rq, p) && p->nr_cpus_allowed > 1) enqueue_pushable_task(rq, p); @@ -1271,7 +1305,7 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags) struct sched_rt_entity *rt_se = &p->rt; update_curr_rt(rq); - dequeue_rt_entity(rt_se); + dequeue_rt_entity(rt_se, flags); dequeue_pushable_task(rq, p); } -- cgit v1.2.3 From c3a990dc9fab590fb88608410f1cc2bc866bdf30 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 16 Feb 2016 18:37:46 -0500 Subject: sched/rt: Kick RT bandwidth timer immediately on start up I've been debugging why deadline tasks can cause the RT scheduler to throttle, even when the deadline tasks are only taking up 50% of the CPU and RT tasks are not even using 1% of the CPU. Here's what I found. In order to keep a CPU from being hogged by RT tasks, the deadline scheduler adds its run time (delta_exec) to the rt_time of the RT bandwidth. That way, if the two use more than 95% of the CPU within one second (default settings), the RT tasks are throttled to allow non RT tasks to run. Although the deadline tasks add their run time to the RT bandwidth, it lets the RT tasks do the accounting. This is where the problem lies. If a deadline task runs for a bit, and no RT tasks are running, then it will continually add to the RT rt_time that is used to calculate how much CPU the RT tasks use. But no RT period is in play, and this accumulation of the runtime never gets reset. When an RT task finally gets to run, and the watchdog goes off, it can see that the RT task has used more than it should of, because the deadline task added all this runtime to its rt_time. Then the RT task that just woke up gets throttled for no good reason. I also noticed that when an RT task is queued, it starts the timer to account for overload and such. But that timer goes off one period later, which may be too late and the extra rt_time will trigger a throttle. This is a quick work around to the problem. When a new RT task is queued, the bandwidth timer is set to go off immediately. Then the timer can clear out the extra time added to the rt_time while there was no RT task running. This stops my tests from triggering the throttle, and it will still throttle if an RT task runs too much, even while a deadline task is running. A better solution may be to subtract the bandwidth that the deadline task uses from the rt_runtime, and add it back when its finished. Then there wont be a need for runtime tracking of the time used by deadline tasks. I may play with that solution tomorrow. Signed-off-by: Steven Rostedt Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Cc: Clark Williams Cc: Daniel Bristot de Oliveira Cc: John Kacur Cc: Juri Lelli Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20160216183746.349ec98b@gandalf.local.home Signed-off-by: Ingo Molnar --- kernel/sched/rt.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'kernel/sched/rt.c') diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 406a9c20b210..a774b4dbf291 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -58,7 +58,15 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) raw_spin_lock(&rt_b->rt_runtime_lock); if (!rt_b->rt_period_active) { rt_b->rt_period_active = 1; - hrtimer_forward_now(&rt_b->rt_period_timer, rt_b->rt_period); + /* + * SCHED_DEADLINE updates the bandwidth, as a run away + * RT task with a DL task could hog a CPU. But DL does + * not reset the period. If a deadline task was running + * without an RT task running, it can cause RT tasks to + * throttle when they start up. Kick the timer right away + * to update the period. + */ + hrtimer_forward_now(&rt_b->rt_period_timer, ns_to_ktime(0)); hrtimer_start_expires(&rt_b->rt_period_timer, HRTIMER_MODE_ABS_PINNED); } raw_spin_unlock(&rt_b->rt_runtime_lock); -- cgit v1.2.3