From 60f21a2649308bbd84919ba6656d5ccd660953cf Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 27 Apr 2026 14:16:34 -1000 Subject: [PATCH 1/3] cgroup, sched_ext: Include exiting tasks in cgroup iter a72f73c4dd9b ("cgroup: Don't expose dead tasks in cgroup") made css_task_iter_advance() skip exiting tasks so cgroup.procs stays consistent with waitpid() visibility. Unfortunately, this broke scx_task_iter. scx_task_iter walks either scx_tasks (global) or a cgroup subtree via css_task_iter() and the two modes are expected to cover the same set of tasks. After the above change the cgroup-scoped mode silently skips tasks past exit_signals() that are still on scx_tasks. scx_sub_enable_workfn()'s abort path is one of the symptoms: an exiting SCX_TASK_SUB_INIT task can race past the cgroup iter leaking __scx_init_task() state. Other iterations share the same gap. Add CSS_TASK_ITER_WITH_DEAD to opt out of the skip and use it from scx_task_iter(). Fixes: b0e4c2f8a0f0 ("sched_ext: Implement cgroup subtree iteration for scx_task_iter") Reported-by: Cheng-Yang Chou Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 1 + kernel/cgroup/cgroup.c | 8 +++++--- kernel/sched/ext.c | 6 ++++-- 3 files changed, 10 insertions(+), 5 deletions(-) diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index e52160e85af4..f6d037a30fd8 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -53,6 +53,7 @@ struct kernel_clone_args; enum css_task_iter_flags { CSS_TASK_ITER_PROCS = (1U << 0), /* walk only threadgroup leaders */ CSS_TASK_ITER_THREADED = (1U << 1), /* walk all threaded css_sets in the domain */ + CSS_TASK_ITER_WITH_DEAD = (1U << 2), /* include exiting tasks */ CSS_TASK_ITER_SKIPPED = (1U << 16), /* internal flags */ }; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 1f084ee71443..e51ce4cd3739 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5059,10 +5059,12 @@ repeat: task = list_entry(it->task_pos, struct task_struct, cg_list); /* - * Hide tasks that are exiting but not yet removed. Keep zombie - * leaders with live threads visible. + * Hide tasks that are exiting but not yet removed by default. Keep + * zombie leaders with live threads visible. Usages that need to walk + * every existing task can opt out via CSS_TASK_ITER_WITH_DEAD. */ - if ((task->flags & PF_EXITING) && !atomic_read(&task->signal->live)) + if (!(it->flags & CSS_TASK_ITER_WITH_DEAD) && + (task->flags & PF_EXITING) && !atomic_read(&task->signal->live)) goto repeat; if (it->flags & CSS_TASK_ITER_PROCS) { diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 9483be03a4ca..dc5d4787296b 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -766,7 +766,8 @@ static void scx_task_iter_start(struct scx_task_iter *iter, struct cgroup *cgrp) lockdep_assert_held(&cgroup_mutex); iter->cgrp = cgrp; iter->css_pos = css_next_descendant_pre(NULL, &iter->cgrp->self); - css_task_iter_start(iter->css_pos, 0, &iter->css_iter); + css_task_iter_start(iter->css_pos, CSS_TASK_ITER_WITH_DEAD, + &iter->css_iter); return; } #endif @@ -866,7 +867,8 @@ static struct task_struct *scx_task_iter_next(struct scx_task_iter *iter) iter->css_pos = css_next_descendant_pre(iter->css_pos, &iter->cgrp->self); if (iter->css_pos) - css_task_iter_start(iter->css_pos, 0, &iter->css_iter); + css_task_iter_start(iter->css_pos, CSS_TASK_ITER_WITH_DEAD, + &iter->css_iter); } return NULL; } From ff9eda4ea906b1f02fc260ddc42d2d9bd736a49c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 27 Apr 2026 14:16:35 -1000 Subject: [PATCH 2/3] sched_ext: Skip past-sched_ext_dead() tasks in scx_task_iter_next_locked() scx_task_iter's cgroup-scoped mode can return tasks whose sched_ext_dead() has already completed: cgroup_task_dead() removes from cset->tasks after sched_ext_dead() in finish_task_switch() and is irq-work deferred on PREEMPT_RT. The global mode is fine - sched_ext_dead() removes from scx_tasks via list_del_init() first. Callers (sub-sched enable prep/abort/apply, scx_sub_disable(), scx_fail_parent()) assume returned tasks are still on @sch and trip WARN_ON_ONCE() or operate on torn-down state otherwise. Set %SCX_TASK_OFF_TASKS in sched_ext_dead() under @p's rq lock and have scx_task_iter_next_locked() skip flagged tasks under the same lock. Setter and reader serialize on the per-task rq lock - no race. Signed-off-by: Tejun Heo --- include/linux/sched/ext.h | 1 + kernel/sched/ext.c | 35 ++++++++++++++++++++++++++--------- 2 files changed, 27 insertions(+), 9 deletions(-) diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 1a3af2ea2a79..adb9a4de068a 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -101,6 +101,7 @@ enum scx_ent_flags { SCX_TASK_DEQD_FOR_SLEEP = 1 << 3, /* last dequeue was for SLEEP */ SCX_TASK_SUB_INIT = 1 << 4, /* task being initialized for a sub sched */ SCX_TASK_IMMED = 1 << 5, /* task is on local DSQ with %SCX_ENQ_IMMED */ + SCX_TASK_OFF_TASKS = 1 << 6, /* removed from scx_tasks by sched_ext_dead() */ /* * Bits 8 and 9 are used to carry task state: diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index dc5d4787296b..3f0d8aeaed81 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -928,16 +928,27 @@ static struct task_struct *scx_task_iter_next_locked(struct scx_task_iter *iter) * * Test for idle_sched_class as only init_tasks are on it. */ - if (p->sched_class != &idle_sched_class) - break; + if (p->sched_class == &idle_sched_class) + continue; + + iter->rq = task_rq_lock(p, &iter->rf); + iter->locked_task = p; + + /* + * cgroup_task_dead() removes the dead tasks from cset->tasks + * after sched_ext_dead() and cgroup iteration may see tasks + * which already finished sched_ext_dead(). %SCX_TASK_OFF_TASKS + * is set by sched_ext_dead() under @p's rq lock. Test it to + * avoid visiting tasks which are already dead from SCX POV. + */ + if (p->scx.flags & SCX_TASK_OFF_TASKS) { + __scx_task_iter_rq_unlock(iter); + continue; + } + + return p; } - if (!p) - return NULL; - - iter->rq = task_rq_lock(p, &iter->rf); - iter->locked_task = p; - - return p; + return NULL; } /** @@ -3850,6 +3861,11 @@ void sched_ext_dead(struct task_struct *p) /* * @p is off scx_tasks and wholly ours. scx_root_enable()'s READY -> * ENABLED transitions can't race us. Disable ops for @p. + * + * %SCX_TASK_OFF_TASKS synchronizes against cgroup task iteration - see + * scx_task_iter_next_locked(). NONE tasks need no marking: cgroup + * iteration is only used from sub-sched paths, which require root + * enabled. Root enable transitions every live task to at least READY. */ if (scx_get_task_state(p) != SCX_TASK_NONE) { struct rq_flags rf; @@ -3857,6 +3873,7 @@ void sched_ext_dead(struct task_struct *p) rq = task_rq_lock(p, &rf); scx_disable_and_exit_task(scx_task_sched(p), p); + p->scx.flags |= SCX_TASK_OFF_TASKS; task_rq_unlock(rq, p, &rf); } } From b34c82777a2c0648ee053595f4b290fd5249b093 Mon Sep 17 00:00:00 2001 From: David Carlier Date: Thu, 30 Apr 2026 10:27:47 +0100 Subject: [PATCH 3/3] sched_ext: idle: Recheck prev_cpu after narrowing allowed mask scx_select_cpu_dfl() narrows @allowed to @cpus_allowed & @p->cpus_ptr when the BPF caller supplies a @cpus_allowed that differs from @p->cpus_ptr and @p doesn't have full affinity. However, @is_prev_allowed was computed against the original (wider) @cpus_allowed, so the prev_cpu fast paths could pick a @prev_cpu that is in @cpus_allowed but not in @p->cpus_ptr, violating the intended invariant that the returned CPU is always usable by @p. The kernel masks this via the SCX_EV_SELECT_CPU_FALLBACK fallback, but the behavior contradicts the documented contract. Move the @is_prev_allowed evaluation past the narrowing block so it tests against the final @allowed mask. Fixes: ee9a4e92799d ("sched_ext: idle: Properly handle invalid prev_cpu during idle selection") Cc: stable@vger.kernel.org # v6.16+ Assisted-by: Claude Signed-off-by: David Carlier Reviewed-by: Andrea Righi Signed-off-by: Tejun Heo --- kernel/sched/ext_idle.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c index 7468560a6d80..6e1980763270 100644 --- a/kernel/sched/ext_idle.c +++ b/kernel/sched/ext_idle.c @@ -465,12 +465,6 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, preempt_disable(); - /* - * Check whether @prev_cpu is still within the allowed set. If not, - * we can still try selecting a nearby CPU. - */ - is_prev_allowed = cpumask_test_cpu(prev_cpu, allowed); - /* * Determine the subset of CPUs usable by @p within @cpus_allowed. */ @@ -487,6 +481,12 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, } } + /* + * Check whether @prev_cpu is still within the allowed set. If not, + * we can still try selecting a nearby CPU. + */ + is_prev_allowed = cpumask_test_cpu(prev_cpu, allowed); + /* * This is necessary to protect llc_cpus. */