* [PATCH sched_ext/for-7.4-fixes] sched_ext: Don't route tasks to SCX before __scx_enabled is fully patched
@ 2026-11-18 10:24 Kuba Piecuch
2026-11-18 13:25 ` Tao Cui
0 siblings, 1 reply; 2+ messages in thread
From: Kuba Piecuch @ 2026-11-18 10:24 UTC (permalink / raw)
To: Tejun Heo, David Vernet, Andrea Righi, Changwoo Min
Cc: Kuba Piecuch, sched-ext, linux-kernel
scx_root_enable_workfn() sets scx_switching_all and calls
static_branch_enable(&__scx_enabled) before switching tasks, and
task_should_scx() gates only on scx_enabled(). static_branch_enable()
patches jump-label sites in address order rather than atomically:
task_should_scx() may be patched before __schedule().
If a concurrent fork or sched_setscheduler() runs in that window,
task_should_scx() observes scx_enabled() and moves the running task
from fair_sched_class to ext_sched_class, setting need_resched on the
class degradation. The following __schedule() can still observe
!scx_enabled() in next_active_class(), skip ext_sched_class, and pick
rq->idle while the runnable SCX task is still rq->donor:
WARNING: kernel/sched/ext/ext.c:3840 at put_prev_task_scx+0x405/0x7a0
Sched_ext: enq_select_cpu (enabling+all), task: runnable_at=+0ms
Call Trace:
__schedule+0x5cc/0x1100
preempt_schedule_common+0x12/0x40
preempt_schedule_thunk+0x16/0x40
__sched_setscheduler+0x8d8/0x920
Gate task_should_scx() on a scx_task_switch_enabled flag that is set with
release semantics only after static_branch_enable(&__scx_enabled) has
finished patching all call sites and scx_switching_all is updated, and
cleared on disable alongside scx_switching_all.
This bug was found and the patch was written with the help of an AI
coding assistant.
Fixes: f0e1a0643a59 ("sched_ext: Implement BPF extensible scheduler class")
Cc: stable@vger.kernel.org # v6.12+
Signed-off-by: Kuba Piecuch <jpiecuch@google.com>
---
kernel/sched/ext/ext.c | 20 +++++++++++++++++---
1 file changed, 17 insertions(+), 3 deletions(-)
diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 10de6bd865e8..e8c30a21e03e 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -134,6 +134,7 @@ DEFINE_PERCPU_RWSEM(scx_fork_rwsem);
static atomic_t scx_enable_state_var = ATOMIC_INIT(SCX_DISABLED);
static DEFINE_RAW_SPINLOCK(scx_bypass_lock);
static bool scx_init_task_enabled;
+static bool scx_task_switch_enabled;
static bool scx_switching_all;
DEFINE_STATIC_KEY_FALSE(__scx_switched_all);
static DEFINE_STATIC_KEY_FALSE(__scx_tid_to_task_enabled);
@@ -6493,6 +6494,15 @@ bool task_should_scx(int policy)
if (!scx_enabled())
return false;
+ /*
+ * static_branch_enable(&__scx_enabled) patches call sites one by one.
+ * Wait until all sites are patched before routing tasks to SCX, so
+ * __schedule() never sees !scx_enabled() when a task is on SCX. Pairs
+ * with smp_store_release() in scx_root_enable_workfn().
+ */
+ if (unlikely(!smp_load_acquire(&scx_task_switch_enabled)))
+ return false;
+
/* scx is taking over all SCHED_OTHER and SCHED_EXT tasks */
if (READ_ONCE(scx_switching_all))
return true;
@@ -7568,6 +7578,7 @@ static void scx_root_disable(struct scx_sched *sch)
static_branch_disable(&__scx_switched_all);
WRITE_ONCE(scx_switching_all, false);
+ WRITE_ONCE(scx_task_switch_enabled, false);
/*
* Shut down cgroup support before tasks so that the cgroup attach and
@@ -8965,11 +8976,14 @@ static void scx_root_enable_workfn(struct kthread_work *work)
percpu_up_write(&scx_fork_rwsem);
/*
- * All tasks are READY. It's safe to turn on scx_enabled() and switch
- * all eligible tasks.
+ * All tasks are READY. Finish patching all scx_enabled() sites before
+ * opening task_should_scx() and switching eligible tasks.
*/
- WRITE_ONCE(scx_switching_all, !(ops->flags & SCX_OPS_SWITCH_PARTIAL));
+ WARN_ON_ONCE(scx_task_switch_enabled);
static_branch_enable(&__scx_enabled);
+ WRITE_ONCE(scx_switching_all, !(ops->flags & SCX_OPS_SWITCH_PARTIAL));
+ /* pairs with smp_load_acquire() in task_should_scx() */
+ smp_store_release(&scx_task_switch_enabled, true);
/*
* We're fully committed and can't fail. The task READY -> ENABLED
base-commit: 700a332c3fe33014bbd5ae852d71ba679fc29e0a
--
2.56.0.679.gc527c65306-goog
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: [PATCH sched_ext/for-7.4-fixes] sched_ext: Don't route tasks to SCX before __scx_enabled is fully patched
2026-11-18 10:24 [PATCH sched_ext/for-7.4-fixes] sched_ext: Don't route tasks to SCX before __scx_enabled is fully patched Kuba Piecuch
@ 2026-11-18 13:25 ` Tao Cui
0 siblings, 0 replies; 2+ messages in thread
From: Tao Cui @ 2026-11-18 13:25 UTC (permalink / raw)
To: Kuba Piecuch, Tejun Heo, David Vernet, Andrea Righi, Changwoo Min
Cc: cui.tao, sched-ext, linux-kernel
Hello, Kuba,
在 2026/11/18 18:24, Kuba Piecuch 写道:
> scx_root_enable_workfn() sets scx_switching_all and calls
> static_branch_enable(&__scx_enabled) before switching tasks, and
> task_should_scx() gates only on scx_enabled(). static_branch_enable()
> patches jump-label sites in address order rather than atomically:
> task_should_scx() may be patched before __schedule().
>
> If a concurrent fork or sched_setscheduler() runs in that window,
> task_should_scx() observes scx_enabled() and moves the running task
> from fair_sched_class to ext_sched_class, setting need_resched on the
> class degradation. The following __schedule() can still observe
> !scx_enabled() in next_active_class(), skip ext_sched_class, and pick
> rq->idle while the runnable SCX task is still rq->donor:
>
> WARNING: kernel/sched/ext/ext.c:3840 at put_prev_task_scx+0x405/0x7a0
> Sched_ext: enq_select_cpu (enabling+all), task: runnable_at=+0ms
> Call Trace:
> __schedule+0x5cc/0x1100
> preempt_schedule_common+0x12/0x40
> preempt_schedule_thunk+0x16/0x40
> __sched_setscheduler+0x8d8/0x920
>
> Gate task_should_scx() on a scx_task_switch_enabled flag that is set with
> release semantics only after static_branch_enable(&__scx_enabled) has
> finished patching all call sites and scx_switching_all is updated, and
> cleared on disable alongside scx_switching_all.
>
> This bug was found and the patch was written with the help of an AI
> coding assistant.
>
> Fixes: f0e1a0643a59 ("sched_ext: Implement BPF extensible scheduler class")
> Cc: stable@vger.kernel.org # v6.12+
> Signed-off-by: Kuba Piecuch <jpiecuch@google.com>
The release/acquire gate looks right on both the
enable and disable paths.
Applied on top of 700a332c3fe3 (for-7.4-fixes HEAD) and ran 25
scx_simple load/unload cycles in qemu under a fork and
sched_setscheduler() storm. The baseline hit the reported warning on
its own 14s into the run, log below. The patched kernel went through
the identical run with zero warnings.
[ 14.225125] CYCLE-7-start
[ 14.352153] ------------[ cut here ]------------
[ 14.352157] WARNING: kernel/sched/ext/ext.c:3840 at put_prev_task_scx+0x4e4/0x750, CPU#2: storm/91
[ 14.354627] Sched_ext: simple (enabling+all), task: runnable_at=+0ms
[ 14.372849] Call Trace:
[ 14.373019] <TASK>
[ 14.373164] __schedule+0x52d/0xe60
[ 14.373395] ? bpf__sched_ext_ops_running+0x62/0xac
[ 14.373709] preempt_schedule_common+0x12/0x40
[ 14.380061] preempt_schedule_thunk+0x16/0x40
[ 14.380628] __sched_setscheduler+0x815/0x8a0
[ 14.380918] do_sched_setscheduler+0x154/0x1f0
[ 14.381220] __x64_sys_sched_setscheduler+0x1c/0x40
Tested-by: Tao Cui <cuitao@kylinos.cn>
Reviewed-by: Tao Cui <cuitao@kylinos.cn>
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2026-11-18 13:26 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2026-11-18 10:24 [PATCH sched_ext/for-7.4-fixes] sched_ext: Don't route tasks to SCX before __scx_enabled is fully patched Kuba Piecuch
2026-11-18 13:25 ` Tao Cui
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®