From 1e0e63ad6243f378e8476b42412f83c1be6ebbed Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Thu, 27 Jan 2022 15:40:59 +0000 Subject: sched/rt: Plug rt_mutex_setprio() vs push_rt_task() race [ Upstream commit 49bef33e4b87b743495627a529029156c6e09530 ] John reported that push_rt_task() can end up invoking find_lowest_rq(rq->curr) when curr is not an RT task (in this case a CFS one), which causes mayhem down convert_prio(). This can happen when current gets demoted to e.g. CFS when releasing an rt_mutex, and the local CPU gets hit with an rto_push_work irqwork before getting the chance to reschedule. Exactly who triggers this work isn't entirely clear to me - switched_from_rt() only invokes rt_queue_pull_task() if there are no RT tasks on the local RQ, which means the local CPU can't be in the rto_mask. My current suspected sequence is something along the lines of the below, with the demoted task being current. mark_wakeup_next_waiter() rt_mutex_adjust_prio() rt_mutex_setprio() // deboost originally-CFS task check_class_changed() switched_from_rt() // Only rt_queue_pull_task() if !rq->rt.rt_nr_running switched_to_fair() // Sets need_resched __balance_callbacks() // if pull_rt_task(), tell_cpu_to_push() can't select local CPU per the above raw_spin_rq_unlock(rq) // need_resched is set, so task_woken_rt() can't // invoke push_rt_tasks(). Best I can come up with is // local CPU has rt_nr_migratory >= 2 after the demotion, so stays // in the rto_mask, and then: push_rt_task() // breakage follows here as rq->curr is CFS Move an existing check to check rq->curr vs the next pushable task's priority before getting anywhere near find_lowest_rq(). While at it, add an explicit sched_class of rq->curr check prior to invoking find_lowest_rq(rq->curr). Align the DL logic to also reschedule regardless of next_task's migratability. Fixes: a7c81556ec4d ("sched: Fix migrate_disable() vs rt/dl balancing") Reported-by: John Keeping Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Dietmar Eggemann Tested-by: John Keeping Link: https://lore.kernel.org/r/20220127154059.974729-1-valentin.schneider@arm.com Signed-off-by: Sasha Levin --- kernel/sched/deadline.c | 12 ++++++------ kernel/sched/rt.c | 32 ++++++++++++++++++++++---------- 2 files changed, 28 insertions(+), 16 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index e94314633b39..1f811b375bf0 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -2145,12 +2145,6 @@ static int push_dl_task(struct rq *rq) return 0; retry: - if (is_migration_disabled(next_task)) - return 0; - - if (WARN_ON(next_task == rq->curr)) - return 0; - /* * If next_task preempts rq->curr, and rq->curr * can move away, it makes sense to just reschedule @@ -2163,6 +2157,12 @@ retry: return 0; } + if (is_migration_disabled(next_task)) + return 0; + + if (WARN_ON(next_task == rq->curr)) + return 0; + /* We might release rq lock */ get_task_struct(next_task); diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 54f9bb3f1560..2758cf5f7987 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1900,6 +1900,16 @@ static int push_rt_task(struct rq *rq, bool pull) return 0; retry: + /* + * It's possible that the next_task slipped in of + * higher priority than current. If that's the case + * just reschedule current. + */ + if (unlikely(next_task->prio < rq->curr->prio)) { + resched_curr(rq); + return 0; + } + if (is_migration_disabled(next_task)) { struct task_struct *push_task = NULL; int cpu; @@ -1907,6 +1917,18 @@ retry: if (!pull || rq->push_busy) return 0; + /* + * Invoking find_lowest_rq() on anything but an RT task doesn't + * make sense. Per the above priority check, curr has to + * be of higher priority than next_task, so no need to + * reschedule when bailing out. + * + * Note that the stoppers are masqueraded as SCHED_FIFO + * (cf. sched_set_stop_task()), so we can't rely on rt_task(). + */ + if (rq->curr->sched_class != &rt_sched_class) + return 0; + cpu = find_lowest_rq(rq->curr); if (cpu == -1 || cpu == rq->cpu) return 0; @@ -1931,16 +1953,6 @@ retry: if (WARN_ON(next_task == rq->curr)) return 0; - /* - * It's possible that the next_task slipped in of - * higher priority than current. If that's the case - * just reschedule current. - */ - if (unlikely(next_task->prio < rq->curr->prio)) { - resched_curr(rq); - return 0; - } - /* We might release rq lock */ get_task_struct(next_task); -- cgit v1.2.3