sched_ext: sync disable_irq_work in bpf_scx_unreg()
Subsystems (2)
PATCH v2 1/1 sched_ext: sync disable_irq_work in bpf_scx_unreg()
When unregistered my self-written scx scheduler, the following panic occurs.
[ 229.923133] Kernel text patching generated an invalid instruction at 0xffff80009bc2c1f8! [ 229.923146] Internal error: Oops - BRK: 00000000f2000100 [#1] SMP [ 230.077871] CPU: 48 UID: 0 PID: 1760 Comm: kworker/u583:7 Not tainted 7.0.0+ #3 PREEMPT(full) [ 230.086677] Hardware name: NVIDIA GB200 NVL/P3809-BMC, BIOS 02.05.12 20251107 [ 230.093972] Workqueue: events_unbound bpf_map_free_deferred [ 230.099675] Sched_ext: invariant_0.1.0_aarch64_unknown_linux_gnu_debug (disabling), task: runnable_at=-174ms [ 230.116843] pc : 0xffff80009bc2c1f8 [ 230.120406] lr : dequeue_task_scx+0x270/0x2d0 [ 230.217749] Call trace: [ 230.228515] 0xffff80009bc2c1f8 (P) [ 230.232077] dequeue_task+0x84/0x188 [ 230.235728] sched_change_begin+0x1dc/0x250 [ 230.240000] __set_cpus_allowed_ptr_locked+0x17c/0x240 [ 230.245250] __set_cpus_allowed_ptr+0x74/0xf0 [ 230.249701] ___migrate_enable+0x4c/0xa0 [ 230.253707] bpf_map_free_deferred+0x1a4/0x1b0 [ 230.258246] process_one_work+0x184/0x540 [ 230.262342] worker_thread+0x19c/0x348 [ 230.266170] kthread+0x13c/0x150 [ 230.269465] ret_from_fork+0x10/0x20 [ 230.281393] Code: d4202000 d4202000 d4202000 d4202000 (d4202000) [ 230.287621] ---[ end trace 0000000000000000 ]--- [ 231.160046] Kernel panic - not syncing: Oops - BRK: Fatal exception in interrupt
The root cause is that the JIT page backing ops->quiescent() is freed before all callers of that function have stopped.
The expected ordering during teardown is:
bitmap_zero(sch->has_op) + synchronize_rcu()
-> guarantees no CPU will ever call sch->ops.* again
-> only THEN free the BPF struct_ops JIT pagebpf_scx_unreg() is supposed to enforce the order, but after commit f4a6c506d118 ("sched_ext: Always bounce scx_disable() through irq_work"), disable_work is no longer queued directly, causing kthread_flush_work() to be a noop. Thus, the caller drops the struct_ops map too early and poisoned with AARCH64_BREAK_FAULT before disable_workfn ever execute.
So the subsequent dequeue_task() still sees SCX_HAS_OP(sch, quiescent) as true and calls ops.quiescent, which hit on the poisoned page and BRK panic.
Add a helper scx_flush_disable_work() so the future use cases that want to flush disable_work can use it.
Also amend the call for scx_root_enable_workfn() and scx_sub_enable_workfn() which have similar pattern in the error path.
---
Changelog:
v1 -> v2:
- Add scx_flush_disable_work() helper
- Amend error path in scx_root_enable_workfn() and scx_sub_enable_workfn()
Best regards,
Richard Cheng.
--- kernel/sched/ext.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-)
kernel/sched/ext.c +17 -3
@@ -5921,6 +5921,20 @@ static void scx_disable(struct scx_sched *sch, enum scx_exit_kind kind)irq_work_queue (&sch->disable_irq_work); } +/** +* scx_flush_disable_work - flush the disable work and wait for it to finish +* @sch: the scheduler +* +* sch->disable_work might still not queued, causing kthread_flush_work() +* as a noop. Syncing the irq_work first is required to guarantee the +* kthread work has been queued before waiting for it. +*/ +static void scx_flush_disable_work (struct scx_sched *sch) +{ +irq_work_sync (&sch->disable_irq_work); +kthread_flush_work (&sch->disable_work); +} +static void dump_newline (struct seq_buf *s) {trace_sched_ext_dump ("" );
@@ -6821,7 +6835,7 @@ static void scx_root_enable_workfn(struct kthread_work *work)* completion. sch's base reference will be put by bpf_scx_unreg(). */ scx_error (sch,"scx_root_enable() failed (%d)" , ret); -kthread_flush_work (&sch->disable_work); +scx_flush_disable_work (sch); cmd->ret =0 ; }
@@ -7088,7 +7102,7 @@ static void scx_sub_enable_workfn(struct kthread_work *work)percpu_up_write (&scx_fork_rwsem); err_disable:mutex_unlock (&scx_enable_mutex); -kthread_flush_work (&sch->disable_work); +scx_flush_disable_work (sch); cmd->ret =0 ; }
@@ -7349,7 +7363,7 @@ static void bpf_scx_unreg(void *kdata, struct bpf_link *link)struct scx_sched *sch =rcu_dereference_protected (ops->priv, true);scx_disable (sch,SCX_EXIT_UNREG ); -kthread_flush_work (&sch->disable_work); +scx_flush_disable_work (sch);RCU_INIT_POINTER (ops->priv,NULL );kobject_put (&sch->kobj); }
Signature · 1 line
2.43.0
Hi Richard,
On Fri, Apr 24, 2026 at 06:02:21PM +0800, Richard Cheng wrote:
[...]
Quoted 9 lines
--- kernel/sched/ext.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-)kernel/sched/ext.c +0
-0
kernel/sched/ext.c static void scx_disable(struct scx_sched *sch, enum scx_exit_kind kind) · line 5926
Quoted 6 lines
kernel/sched/ext.c +3
-0@@ -5921,6 +5921,20 @@ static void scx_disable(struct scx_sched *sch, enum scx_exit_kind kind)irq_work_queue (&sch->disable_irq_work); } +/** +* scx_flush_disable_work - flush the disable work and wait for it to finish +* @sch: the scheduler
Not to be picky here, but I think '@sch: the scheduler' is a bit vague. Since nearly every 'sch' in ext.c is a scheduler instance, maybe '@sch: sched to be flushed' would be more descriptive?
You can check more specific comments for 'sch' elsewhere in ext.c as well. WDYT, thanks!
Quoted 44 lines
kernel/sched/ext.c +14
-3+* +* sch->disable_work might still not queued, causing kthread_flush_work() +* as a noop. Syncing the irq_work first is required to guarantee the +* kthread work has been queued before waiting for it. +*/ +static void scx_flush_disable_work (struct scx_sched *sch) +{ +irq_work_sync (&sch->disable_irq_work); +kthread_flush_work (&sch->disable_work); +} +static void dump_newline (struct seq_buf *s) {trace_sched_ext_dump ("" );@@ -6821,7 +6835,7 @@ static void scx_root_enable_workfn(struct kthread_work *work)* completion. sch's base reference will be put by bpf_scx_unreg(). */ scx_error (sch,"scx_root_enable() failed (%d)" , ret); -kthread_flush_work (&sch->disable_work); +scx_flush_disable_work (sch); cmd->ret =0 ; }@@ -7088,7 +7102,7 @@ static void scx_sub_enable_workfn(struct kthread_work *work)percpu_up_write (&scx_fork_rwsem); err_disable:mutex_unlock (&scx_enable_mutex); -kthread_flush_work (&sch->disable_work); +scx_flush_disable_work (sch); cmd->ret =0 ; }@@ -7349,7 +7363,7 @@ static void bpf_scx_unreg(void *kdata, struct bpf_link *link)struct scx_sched *sch =rcu_dereference_protected (ops->priv, true);scx_disable (sch,SCX_EXIT_UNREG ); -kthread_flush_work (&sch->disable_work); +scx_flush_disable_work (sch);RCU_INIT_POINTER (ops->priv,NULL );kobject_put (&sch->kobj); }Signature · 1 line
2.43.0
Signature · 2 lines
Cheers, Cheng-Yang
Hello,
Quoted 1 line · Richard Cheng
[PATCH v2]
sched_ext: syncdisable_irq_workinbpf_scx_unreg()
Applied to sched_ext/for-7.1-fixes.
Thanks.
Signature · 1 line
tejun