From e6ac89b8b1c12e9104df45a14a26e2dfa96ded06 Mon Sep 17 00:00:00 2001 From: Kuba Piecuch Date: Sat, 3 Oct 2026 11:53:17 +0000 Subject: [PATCH] sched_ext: Generate qseq from a per-task counter finish_dispatch() uses the qseq embedded in p->scx.ops_state to tell whether the QUEUED instance of a task it's about to claim is the one scx_bpf_dsq_insert() saw. qseq is generated from rq->scx.ops_qseq, but the counters of different rqs are independent, so if a task is dequeued and re-enqueued on a different rq between scx_bpf_dsq_insert() and finish_dispatch(), the new QUEUED instance can end up with the same qseq as the old one: CPU X CPU Z ----- ----- enqueue p on rq A, qseq = N ops.dispatch() scx_bpf_dsq_insert(p) records qseq N sched_setaffinity(p) dequeue p from rq A enqueue p on rq B, qseq = N finish_dispatch(p, N) qseq matches, p is claimed The claim itself is still atomic so the core stays consistent, but an insert issued for a previous QUEUED instance gets applied to a new one which the BPF scheduler has just received through ops.enqueue(). This breaks the guarantee that dispatches targeting a stale instance are ignored. Generate qseq from a per-task counter, p->scx.ops_qseq, instead so that consecutive QUEUED instances of a task never share a qseq regardless of which rq they're on. The counter is only updated in scx_do_enqueue_task() with the task's rq locked, so no additional synchronization is needed, and it fits in an existing hole in struct sched_ext_entity on 64bit. Remove the now unused rq->scx.ops_qseq. Never generate qseq 0. NONE and DISPATCHING don't carry a qseq, so scx_bpf_dsq_insert() on a task in either state records 0. With a per-task counter, every task's first QUEUED instance would otherwise get qseq 0 and could be claimed by such an insert. Wrap the counter where the QSEQ field wraps so that it can't reach a value that shifts to 0 on 32bit either. Fixes: f0e1a0643a59 ("sched_ext: Implement BPF extensible scheduler class") Cc: stable@vger.kernel.org # v6.12+ Assisted-by: Claude:claude-opus-5.5 Signed-off-by: Kuba Piecuch Signed-off-by: Tejun Heo --- include/linux/sched/ext.h | 1 + kernel/sched/ext/ext.c | 14 ++++++++++---- kernel/sched/ext/internal.h | 5 +++++ kernel/sched/sched.h | 1 - 4 files changed, 16 insertions(+), 5 deletions(-) diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 582d7cd4a983..36c04797436c 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -207,6 +207,7 @@ struct sched_ext_entity { s32 holding_cpu; s32 selected_cpu; s32 runnable_cpu; /* cpu @p is runnable on, -1 if not */ + u32 ops_qseq; /* protected by rq lock */ struct task_struct *kf_tasks[2]; /* see SCX_CALL_OP_TASK() */ struct list_head runnable_node; /* rq->scx.runnable_list */ diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c index 5209510d6a5e..ac8fe70a9fb6 100644 --- a/kernel/sched/ext/ext.c +++ b/kernel/sched/ext/ext.c @@ -2057,8 +2057,14 @@ void scx_do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags, if (unlikely(!SCX_HAS_OP(sch, enqueue))) goto global; - /* DSQ bypass didn't trigger, enqueue on the BPF scheduler */ - qseq = rq->scx.ops_qseq++ << SCX_OPSS_QSEQ_SHIFT; + /* + * DSQ bypass didn't trigger, enqueue on the BPF scheduler. Wrap the + * per-task qseq counter where the QSEQ field wraps and skip 0, which is + * what scx_bpf_dsq_insert() records for a task in NONE or DISPATCHING. + */ + p->scx.ops_qseq = ((p->scx.ops_qseq + 1) & + (SCX_OPSS_QSEQ_MASK >> SCX_OPSS_QSEQ_SHIFT)) ?: 1; + qseq = (unsigned long)p->scx.ops_qseq << SCX_OPSS_QSEQ_SHIFT; WARN_ON_ONCE(atomic_long_read(&p->scx.ops_state) != SCX_OPSS_NONE); atomic_long_set(&p->scx.ops_state, SCX_OPSS_QUEUEING | qseq); @@ -6969,9 +6975,9 @@ static void scx_dump_cpu(struct scx_sched *sch, struct seq_buf *s, seq_buf_init(&ns, buf, avail); dump_newline(&ns); - scx_dump_line(&ns, "CPU %-4d: nr_run=%u flags=0x%x cpu_rel=%d ops_qseq=%lu ksync=%lu", + scx_dump_line(&ns, "CPU %-4d: nr_run=%u flags=0x%x cpu_rel=%d ksync=%lu", cpu, rq->scx.nr_running, rq->scx.flags, rq->scx.cpu_released, - rq->scx.ops_qseq, rq->scx.kick_sync); + rq->scx.kick_sync); scx_rescue_dump(&ns, rq); scx_dump_line(&ns, " curr=%s[%d] class=%ps", rq->curr->comm, rq->curr->pid, rq->curr->sched_class); diff --git a/kernel/sched/ext/internal.h b/kernel/sched/ext/internal.h index 1df8f583b0ec..5b37faa532d6 100644 --- a/kernel/sched/ext/internal.h +++ b/kernel/sched/ext/internal.h @@ -1998,6 +1998,11 @@ enum scx_ops_state { * dequeue/requeue, the dispatcher can tell whether it still has a claim * on the task being dispatched. * + * QSEQ is generated from the per-task p->scx.ops_qseq counter so that + * it doesn't repeat across QUEUED instances of the same task even if + * the task moves between rqs. 0 is never used as a valid QSEQ since + * NONE and DISPATCHING map to this value. + * * As some 32bit archs can't do 64bit store_release/load_acquire, * p->scx.ops_state is atomic_long_t which leaves 30 bits for QSEQ on * 32bit machines. The dispatch race window QSEQ protects is very narrow diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 742cce9da4e9..9ed0cb605c33 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -813,7 +813,6 @@ struct scx_rq { #endif struct list_head runnable_list; /* runnable tasks on this rq */ struct list_head ddsp_deferred_locals; /* deferred ddsps from enq */ - unsigned long ops_qseq; /* both stashed across the activate_task() in move_remote_task_to_local_dsq() */ u64 remote_activate_enq_flags; struct scx_sched *remote_activate_sch;