Re: [PATCH sched_ext/for-7.4-fixes] sched_ext: Don't route tasks to SCX before __scx_enabled is fully patched

From: Tao Cui

Date: Wed Nov 18 2026 - 08:26:07 EST


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@xxxxxxxxxxxxxxx # v6.12+
> Signed-off-by: Kuba Piecuch <jpiecuch@xxxxxxxxxx>

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@xxxxxxxxxx>
Reviewed-by: Tao Cui <cuitao@xxxxxxxxxx>