The following commit has been merged into the sched/core branch of tip: Commit-ID: dfa0a574cbc47bfd5f8985f74c8ea003a37fa078 Gitweb: https://git.kernel.org/tip/dfa0a574cbc47bfd5f8985f74c8ea003a37fa078 Author: Peter Zijlstra <peterz@xxxxxxxxxxxxx> AuthorDate: Wed, 05 Jun 2024 12:09:11 +02:00 Committer: Peter Zijlstra <peterz@xxxxxxxxxxxxx> CommitterDate: Sat, 17 Aug 2024 11:06:42 +02:00 sched/uclamg: Handle delayed dequeue Delayed dequeue has tasks sit around on the runqueue that are not actually runnable -- specifically, they will be dequeued the moment they get picked. One side-effect is that such a task can get migrated, which leads to a 'nested' dequeue_task() scenario that messes up uclamp if we don't take care. Notably, dequeue_task(DEQUEUE_SLEEP) can 'fail' and keep the task on the runqueue. This however will have removed the task from uclamp -- per uclamp_rq_dec() in dequeue_task(). So far so good. However, if at that point the task gets migrated -- or nice adjusted or any of a myriad of operations that does a dequeue-enqueue cycle -- we'll pass through dequeue_task()/enqueue_task() again. Without modification this will lead to a double decrement for uclamp, which is wrong. Reported-by: Luis Machado <luis.machado@xxxxxxx> Reported-by: Hongyan Xia <hongyan.xia2@xxxxxxx> Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx> Reviewed-by: Valentin Schneider <vschneid@xxxxxxxxxx> Tested-by: Valentin Schneider <vschneid@xxxxxxxxxx> Link: https://lkml.kernel.org/r/20240727105029.315205425@xxxxxxxxxxxxx --- kernel/sched/core.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7356464..80e639e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1691,6 +1691,9 @@ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p) if (unlikely(!p->sched_class->uclamp_enabled)) return; + if (p->se.sched_delayed) + return; + for_each_clamp_id(clamp_id) uclamp_rq_inc_id(rq, p, clamp_id); @@ -1715,6 +1718,9 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) if (unlikely(!p->sched_class->uclamp_enabled)) return; + if (p->se.sched_delayed) + return; + for_each_clamp_id(clamp_id) uclamp_rq_dec_id(rq, p, clamp_id); } @@ -1994,8 +2000,12 @@ void enqueue_task(struct rq *rq, struct task_struct *p, int flags) psi_enqueue(p, (flags & ENQUEUE_WAKEUP) && !(flags & ENQUEUE_MIGRATED)); } - uclamp_rq_inc(rq, p); p->sched_class->enqueue_task(rq, p, flags); + /* + * Must be after ->enqueue_task() because ENQUEUE_DELAYED can clear + * ->sched_delayed. + */ + uclamp_rq_inc(rq, p); if (sched_core_enabled(rq)) sched_core_enqueue(rq, p); @@ -2017,6 +2027,10 @@ inline bool dequeue_task(struct rq *rq, struct task_struct *p, int flags) psi_dequeue(p, flags & DEQUEUE_SLEEP); } + /* + * Must be before ->dequeue_task() because ->dequeue_task() can 'fail' + * and mark the task ->sched_delayed. + */ uclamp_rq_dec(rq, p); return p->sched_class->dequeue_task(rq, p, flags); }
|