From ff0545e0c263727b200f60af47d0364e4d041bde Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Sat, 17 Oct 2026 17:22:26 +0200 Subject: sched_ext: Don't leave balance callbacks queued across a pick retry The dispatch path can request deferred work to be run from a balance callback and pick_task_scx() queues rq->scx.deferred_bal_cb right after dispatching. However, a balance callback must be consumed before the rq lock is released and pick_task_scx() is not necessarily the end of the pick: - it returns RETRY_TASK when a higher priority class task has been enqueued while the dispatch had the rq lock released; - the dl_server pick can return NULL, in which case the lower classes are picked next. In both cases the callback stays queued while the core keeps picking, and the rq lock can be released again, either by prev_balance() or by another dispatch. For example, with an RT task as prev: __schedule() __pick_next_task() pick_task_scx() dispatch_pick() maybe_queue_balance_callback() <- deferred_bal_cb queued return RETRY_TASK prev_balance() balance_rt() pull_rt_task() double_lock_balance() <- rq lock released Any CPU acquiring the rq lock in that window finds a pending balance callback and triggers the following warning in rq_pin_lock(): WARNING: kernel/sched/sched.h:1919 at rq_lock+0x7f/0xe0, CPU#10: stress-ng-sleep/533 CPU: 10 UID: 0 PID: 533 Comm: stress-ng-sleep Not tainted 7.2.0-rc6-virtme #61 PREEMPT(full) Sched_ext: qmap (enabled+all) Call Trace: try_to_wake_up+0x2c1/0x5c0 hrtimer_wakeup+0x22/0x30 __hrtimer_run_queues+0x1d5/0x350 hrtimer_interrupt+0x106/0x1e0 __sysvec_apic_timer_interrupt+0x6f/0x210 sysvec_apic_timer_interrupt+0x71/0x90 This can be reproduced running scx_qmap -I together with a SCHED_FIFO workload that frequently sleeps, e.g.: $ vng -v --cpus 16 --memory 4G -- \ 'tools/sched_ext/build/bin/scx_qmap -I >/dev/null & \ stress-ng --sleep 4 --sched fifo --sched-prio 1 -t 30 -q' Fix this by queueing the balance callbacks only when the pick is final. Otherwise, defer the pending work to the irq_work path, which doesn't depend on the current rq lock section, and leave the kick sync wait pending for the next pick. Fixes: 4c95380701f5 ("sched/ext: Fold balance_scx() into pick_task_scx()") Cc: stable@vger.kernel.org # v6.19+ Signed-off-by: Andrea Righi Signed-off-by: Tejun Heo --- kernel/sched/ext/ext.c | 73 +++++++++++++++++++++++++++++++------------------- 1 file changed, 45 insertions(+), 28 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c index 6b472506944e..2cd24a50f06c 100644 --- a/kernel/sched/ext/ext.c +++ b/kernel/sched/ext/ext.c @@ -3330,7 +3330,8 @@ static struct task_struct *first_local_task(struct rq *rq) } /* - * Run dispatch and queue the follow-up work for a pick. + * Run dispatch for a pick. The follow-up work is queued by do_pick_task_scx() + * once the pick is final. */ static enum scx_dsp_verdict dispatch_pick(struct rq *rq, struct rq_flags *rf, struct task_struct *prev) @@ -3340,18 +3341,6 @@ static enum scx_dsp_verdict dispatch_pick(struct rq *rq, struct rq_flags *rf, rq_unpin_lock(rq, rf); verdict = dispatch_one(rq, prev); rq_repin_lock(rq, rf); - maybe_queue_balance_callback(rq); - - /* - * Defer to a balance callback which can drop rq lock and enable IRQs. - * Waiting directly in the pick path would deadlock against CPUs sending - * us IPIs (e.g. TLB flushes) while we wait for them. - */ - if (unlikely(rq->scx.kick_sync_pending)) { - rq->scx.kick_sync_pending = false; - queue_balance_callback(rq, &rq->scx.kick_sync_bal_cb, - kick_sync_wait_bal_cb); - } return verdict; } @@ -3378,16 +3367,8 @@ static enum scx_dsp_verdict dispatch_core_pick(struct rq *rq, struct rq_flags *r verdict = dispatch_one(rq, prev); - if (cpu_of(rq) == smp_processor_id()) { - maybe_queue_balance_callback(rq); - - /* see dispatch_pick() */ - if (unlikely(rq->scx.kick_sync_pending)) { - rq->scx.kick_sync_pending = false; - queue_balance_callback(rq, &rq->scx.kick_sync_bal_cb, - kick_sync_wait_bal_cb); - } - } else if (unlikely(rq->scx.flags & SCX_RQ_BAL_CB_PENDING)) { + if (cpu_of(rq) != smp_processor_id() && + unlikely(rq->scx.flags & SCX_RQ_BAL_CB_PENDING)) { /* * Balance callbacks must run in the context that queued them, * so they can't be queued on another CPU's rq. Run the deferred @@ -3430,8 +3411,10 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx) else verdict = dispatch_pick(rq, rf, prev); - if (verdict == SCX_DSP_RETRY) - return RETRY_TASK; + if (verdict == SCX_DSP_RETRY) { + p = RETRY_TASK; + goto out; + } /* * If any higher-priority sched class enqueued a runnable task on this @@ -3441,8 +3424,10 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx) * If @force_scx is true, always try to pick a SCHED_EXT task, * regardless of any higher-priority sched classes activity. */ - if (!force_scx && rq_modified_above(rq, &ext_sched_class)) - return RETRY_TASK; + if (!force_scx && rq_modified_above(rq, &ext_sched_class)) { + p = RETRY_TASK; + goto out; + } /* * If we're keeping @prev, replenish slice if necessary and keep running @@ -3458,7 +3443,7 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx) } else { p = first_local_task(rq); if (!p) - return NULL; + goto out; if (unlikely(!p->scx.slice) && scx_task_can_stay_on_cpu(rq, p)) { struct scx_sched *sch = scx_task_sched(p); @@ -3473,6 +3458,38 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx) } } +out: + if (cpu_of(rq) != smp_processor_id()) + return p; + + /* + * Balance callbacks must be consumed before the rq lock is released, so + * queue them only when the pick is final. On RETRY_TASK, or after a + * NULL pick from the dl_server, the core continues picking and can + * release the rq lock (e.g., prev_balance() or another dispatch). In + * that case, run the deferred work from irq_work, which doesn't depend + * on the current rq lock section, and leave the kick sync wait pending + * for the next pick. + */ + if (p != RETRY_TASK && (p || !force_scx)) { + maybe_queue_balance_callback(rq); + + /* + * Defer to a balance callback which can drop rq lock and enable + * IRQs. Waiting directly in the pick path would deadlock against + * CPUs sending us IPIs (e.g., TLB flushes) while we wait for + * them. + */ + if (unlikely(rq->scx.kick_sync_pending)) { + rq->scx.kick_sync_pending = false; + queue_balance_callback(rq, &rq->scx.kick_sync_bal_cb, + kick_sync_wait_bal_cb); + } + } else if (rq->scx.flags & SCX_RQ_BAL_CB_PENDING) { + rq->scx.flags &= ~SCX_RQ_BAL_CB_PENDING; + schedule_deferred(rq); + } + return p; } -- cgit v1.2.3 From 680edc7f23ad71e0ecce8a2364af3ae7f30dd11a Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Sat, 17 Oct 2026 22:05:14 +0200 Subject: sched_ext: Don't queue balance callbacks from a core-sched pick Commit ff0545e0c263 ("sched_ext: Don't leave balance callbacks queued across a pick retry") queues the deferred work as a balance callback only when do_pick_task_scx() returns a final pick. However, under core scheduling, a pick that returns a task isn't final either: pick_next_task() goes on to pick the SMT siblings, and their dispatch can release the shared rq lock with the callback still queued, triggering the rq_pin_lock() warning. Moreover, dispatch_core_pick() returns early when another dispatch is in flight on the rq, and do_pick_task_scx() then consumes %SCX_RQ_BAL_CB_PENDING set by that dispatch while it's still running. This can be reproduced running scx_qmap -I on SMT siblings with coresched-tagged workloads that frequently sleep, mixed with untagged CPU-bound tasks. Fix this by always deferring the pending work to the irq_work path from dispatch_core_pick() under core scheduling, for both the local and the sibling picks, and by leaving %SCX_RQ_BAL_CB_PENDING alone in do_pick_task_scx(), so that it's handled by the dispatch that set it. Sample the core scheduling state once at the start of the pick, since core scheduling can get enabled while a non-core dispatch has the rq lock released, and the follow-up work must match the dispatch path that ran. Fixes: 4c95380701f5 ("sched/ext: Fold balance_scx() into pick_task_scx()") Cc: stable@vger.kernel.org # v6.19+ Signed-off-by: Andrea Righi Signed-off-by: Tejun Heo --- kernel/sched/ext/ext.c | 35 ++++++++++++++++++++++++----------- 1 file changed, 24 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c index 2cd24a50f06c..e59e937534e9 100644 --- a/kernel/sched/ext/ext.c +++ b/kernel/sched/ext/ext.c @@ -3367,15 +3367,20 @@ static enum scx_dsp_verdict dispatch_core_pick(struct rq *rq, struct rq_flags *r verdict = dispatch_one(rq, prev); - if (cpu_of(rq) != smp_processor_id() && - unlikely(rq->scx.flags & SCX_RQ_BAL_CB_PENDING)) { - /* - * Balance callbacks must run in the context that queued them, - * so they can't be queued on another CPU's rq. Run the deferred - * work directly instead. - */ + /* + * A pick that returns a task isn't final under core scheduling: the + * selection goes on to pick the siblings, and their dispatch can + * release the rq lock, which can't happen with balance callbacks + * queued. Don't queue the deferred work as a balance callback, for this + * CPU or a sibling, and run it from irq_work instead. + * + * do_pick_task_scx() leaves %SCX_RQ_BAL_CB_PENDING alone under core + * scheduling, so that the early return above leaves it to the dispatch + * in flight, which handles it here. + */ + if (unlikely(rq->scx.flags & SCX_RQ_BAL_CB_PENDING)) { rq->scx.flags &= ~SCX_RQ_BAL_CB_PENDING; - run_deferred(rq); + schedule_deferred(rq); } rq_repin_lock(rq, rf); @@ -3398,6 +3403,7 @@ static struct task_struct * do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx) { struct task_struct *prev = rq->curr; + bool core_sched = sched_core_enabled(rq); enum scx_dsp_verdict verdict; struct task_struct *p; @@ -3406,7 +3412,12 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx) rq_modified_begin(rq, &ext_sched_class); - if (sched_core_enabled(rq)) + /* + * Core scheduling can get enabled while dispatch_pick() has the rq lock + * released. Stick to @core_sched, so that the follow-up work below + * matches the dispatch that ran. + */ + if (core_sched) verdict = dispatch_core_pick(rq, rf, prev); else verdict = dispatch_pick(rq, rf, prev); @@ -3472,7 +3483,9 @@ out: * for the next pick. */ if (p != RETRY_TASK && (p || !force_scx)) { - maybe_queue_balance_callback(rq); + /* under core scheduling, see dispatch_core_pick() */ + if (!core_sched) + maybe_queue_balance_callback(rq); /* * Defer to a balance callback which can drop rq lock and enable @@ -3485,7 +3498,7 @@ out: queue_balance_callback(rq, &rq->scx.kick_sync_bal_cb, kick_sync_wait_bal_cb); } - } else if (rq->scx.flags & SCX_RQ_BAL_CB_PENDING) { + } else if (!core_sched && (rq->scx.flags & SCX_RQ_BAL_CB_PENDING)) { rq->scx.flags &= ~SCX_RQ_BAL_CB_PENDING; schedule_deferred(rq); } -- cgit v1.2.3