From 4ae8d9aa9f9dc7137ea5e564d79c5aa5af1bc45c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 16 Sep 2025 23:02:41 +0200 Subject: [PATCH 1/2] sched/deadline: Fix dl_server getting stuck John found it was easy to hit lockup warnings when running locktorture on a 2 CPU VM, which he bisected down to: commit cccb45d7c429 ("sched/deadline: Less agressive dl_server handling"). While debugging it seems there is a chance where we end up with the dl_server dequeued, with dl_se->dl_server_active. This causes dl_server_start() to return without enqueueing the dl_server, thus it fails to run when RT tasks starve the cpu. When this happens, dl_server_timer() catches the '!dl_se->server_has_tasks(dl_se)' case, which then calls replenish_dl_entity() and dl_server_stopped() and finally return HRTIMER_NO_RESTART. This ends in no new timer and also no enqueue, leaving the dl_server 'dead', allowing starvation. What should have happened is for the bandwidth timer to start the zero-laxity timer, which in turn would enqueue the dl_server and cause dl_se->server_pick_task() to be called -- which will stop the dl_server if no fair tasks are observed for a whole period. IOW, it is totally irrelevant if there are fair tasks at the moment of bandwidth refresh. This removes all dl_se->server_has_tasks() users, so remove the whole thing. Fixes: cccb45d7c4295 ("sched/deadline: Less agressive dl_server handling") Reported-by: John Stultz Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Peter Zijlstra (Intel) Tested-by: John Stultz --- include/linux/sched.h | 1 - kernel/sched/deadline.c | 12 +----------- kernel/sched/fair.c | 7 +------ kernel/sched/sched.h | 4 ---- 4 files changed, 2 insertions(+), 22 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index f8188b833350..f89313b150e6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -733,7 +733,6 @@ struct sched_dl_entity { * runnable task. */ struct rq *rq; - dl_server_has_tasks_f server_has_tasks; dl_server_pick_f server_pick_task; #ifdef CONFIG_RT_MUTEXES diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index f25301267e47..5a5080b3a670 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -875,7 +875,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se) */ if (dl_se->dl_defer && !dl_se->dl_defer_running && dl_time_before(rq_clock(dl_se->rq), dl_se->deadline - dl_se->runtime)) { - if (!is_dl_boosted(dl_se) && dl_se->server_has_tasks(dl_se)) { + if (!is_dl_boosted(dl_se)) { /* * Set dl_se->dl_defer_armed and dl_throttled variables to @@ -1152,8 +1152,6 @@ static void __push_dl_task(struct rq *rq, struct rq_flags *rf) /* a defer timer will not be reset if the runtime consumed was < dl_server_min_res */ static const u64 dl_server_min_res = 1 * NSEC_PER_MSEC; -static bool dl_server_stopped(struct sched_dl_entity *dl_se); - static enum hrtimer_restart dl_server_timer(struct hrtimer *timer, struct sched_dl_entity *dl_se) { struct rq *rq = rq_of_dl_se(dl_se); @@ -1171,12 +1169,6 @@ static enum hrtimer_restart dl_server_timer(struct hrtimer *timer, struct sched_ if (!dl_se->dl_runtime) return HRTIMER_NORESTART; - if (!dl_se->server_has_tasks(dl_se)) { - replenish_dl_entity(dl_se); - dl_server_stopped(dl_se); - return HRTIMER_NORESTART; - } - if (dl_se->dl_defer_armed) { /* * First check if the server could consume runtime in background. @@ -1625,11 +1617,9 @@ static bool dl_server_stopped(struct sched_dl_entity *dl_se) } void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq, - dl_server_has_tasks_f has_tasks, dl_server_pick_f pick_task) { dl_se->rq = rq; - dl_se->server_has_tasks = has_tasks; dl_se->server_pick_task = pick_task; } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index b173a059315c..8ce56a8d507f 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8859,11 +8859,6 @@ static struct task_struct *__pick_next_task_fair(struct rq *rq, struct task_stru return pick_next_task_fair(rq, prev, NULL); } -static bool fair_server_has_tasks(struct sched_dl_entity *dl_se) -{ - return !!dl_se->rq->cfs.nr_queued; -} - static struct task_struct *fair_server_pick_task(struct sched_dl_entity *dl_se) { return pick_task_fair(dl_se->rq); @@ -8875,7 +8870,7 @@ void fair_server_init(struct rq *rq) init_dl_entity(dl_se); - dl_server_init(dl_se, rq, fair_server_has_tasks, fair_server_pick_task); + dl_server_init(dl_se, rq, fair_server_pick_task); } /* diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index be9745d104f7..f10d6277dca1 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -365,9 +365,6 @@ extern s64 dl_scaled_delta_exec(struct rq *rq, struct sched_dl_entity *dl_se, s6 * * dl_se::rq -- runqueue we belong to. * - * dl_se::server_has_tasks() -- used on bandwidth enforcement; we 'stop' the - * server when it runs out of tasks to run. - * * dl_se::server_pick() -- nested pick_next_task(); we yield the period if this * returns NULL. * @@ -383,7 +380,6 @@ extern void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec); extern void dl_server_start(struct sched_dl_entity *dl_se); extern void dl_server_stop(struct sched_dl_entity *dl_se); extern void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq, - dl_server_has_tasks_f has_tasks, dl_server_pick_f pick_task); extern void sched_init_dl_servers(void); From a3a70caf7906708bf9bbc80018752a6b36543808 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 17 Sep 2025 12:03:20 +0200 Subject: [PATCH 2/2] sched/deadline: Fix dl_server behaviour John reported undesirable behaviour with the dl_server since commit: cccb45d7c4295 ("sched/deadline: Less agressive dl_server handling"). When starving fair tasks on purpose (starting spinning FIFO tasks), his fair workload, which often goes (briefly) idle, would delay fair invocations for a second, running one invocation per second was both unexpected and terribly slow. The reason this happens is that when dl_se->server_pick_task() returns NULL, indicating no runnable tasks, it would yield, pushing any later jobs out a whole period (1 second). Instead simply stop the server. This should restore behaviour in that a later wakeup (which restarts the server) will be able to continue running (subject to the CBS wakeup rules). Notably, this does not re-introduce the behaviour cccb45d7c4295 set out to solve, any start/stop cycle is naturally throttled by the timer period (no active cancel). Fixes: cccb45d7c4295 ("sched/deadline: Less agressive dl_server handling") Reported-by: John Stultz Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Peter Zijlstra (Intel) Tested-by: John Stultz --- include/linux/sched.h | 1 - kernel/sched/deadline.c | 23 ++--------------------- kernel/sched/sched.h | 33 +++++++++++++++++++++++++++++++-- 3 files changed, 33 insertions(+), 24 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index f89313b150e6..e4ce0a76831e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -706,7 +706,6 @@ struct sched_dl_entity { unsigned int dl_defer : 1; unsigned int dl_defer_armed : 1; unsigned int dl_defer_running : 1; - unsigned int dl_server_idle : 1; /* * Bandwidth enforcement timer. Each -deadline task has its diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 5a5080b3a670..72c1f72463c7 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1571,10 +1571,8 @@ void dl_server_update_idle_time(struct rq *rq, struct task_struct *p) void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec) { /* 0 runtime = fair server disabled */ - if (dl_se->dl_runtime) { - dl_se->dl_server_idle = 0; + if (dl_se->dl_runtime) update_curr_dl_se(dl_se->rq, dl_se, delta_exec); - } } void dl_server_start(struct sched_dl_entity *dl_se) @@ -1602,20 +1600,6 @@ void dl_server_stop(struct sched_dl_entity *dl_se) dl_se->dl_server_active = 0; } -static bool dl_server_stopped(struct sched_dl_entity *dl_se) -{ - if (!dl_se->dl_server_active) - return true; - - if (dl_se->dl_server_idle) { - dl_server_stop(dl_se); - return true; - } - - dl_se->dl_server_idle = 1; - return false; -} - void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq, dl_server_pick_f pick_task) { @@ -2384,10 +2368,7 @@ again: if (dl_server(dl_se)) { p = dl_se->server_pick_task(dl_se); if (!p) { - if (!dl_server_stopped(dl_se)) { - dl_se->dl_yielded = 1; - update_curr_dl_se(rq, dl_se, 0); - } + dl_server_stop(dl_se); goto again; } rq->dl_server = dl_se; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index f10d6277dca1..cf2109b67f9a 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -371,10 +371,39 @@ extern s64 dl_scaled_delta_exec(struct rq *rq, struct sched_dl_entity *dl_se, s6 * dl_server_update() -- called from update_curr_common(), propagates runtime * to the server. * - * dl_server_start() - * dl_server_stop() -- start/stop the server when it has (no) tasks. + * dl_server_start() -- start the server when it has tasks; it will stop + * automatically when there are no more tasks, per + * dl_se::server_pick() returning NULL. + * + * dl_server_stop() -- (force) stop the server; use when updating + * parameters. * * dl_server_init() -- initializes the server. + * + * When started the dl_server will (per dl_defer) schedule a timer for its + * zero-laxity point -- that is, unlike regular EDF tasks which run ASAP, a + * server will run at the very end of its period. + * + * This is done such that any runtime from the target class can be accounted + * against the server -- through dl_server_update() above -- such that when it + * becomes time to run, it might already be out of runtime and get deferred + * until the next period. In this case dl_server_timer() will alternate + * between defer and replenish but never actually enqueue the server. + * + * Only when the target class does not manage to exhaust the server's runtime + * (there's actualy starvation in the given period), will the dl_server get on + * the runqueue. Once queued it will pick tasks from the target class and run + * them until either its runtime is exhaused, at which point its back to + * dl_server_timer, or until there are no more tasks to run, at which point + * the dl_server stops itself. + * + * By stopping at this point the dl_server retains bandwidth, which, if a new + * task wakes up imminently (starting the server again), can be used -- + * subject to CBS wakeup rules -- without having to wait for the next period. + * + * Additionally, because of the dl_defer behaviour the start/stop behaviour is + * naturally thottled to once per period, avoiding high context switch + * workloads from spamming the hrtimer program/cancel paths. */ extern void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec); extern void dl_server_start(struct sched_dl_entity *dl_se);