averello/linux-stable-mirror
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git synced 2026-09-22 09:34:56 +02:00
Code Issues Packages Projects Releases Wiki Activity

sched_ext: Defer scx_hardlockup() out of NMI

Browse Source 
scx_hardlockup() runs from NMI and eventually calls scx_claim_exit(),
which takes scx_sched_lock. scx_sched_lock isn't NMI-safe and grabbing
it from NMI context can lead to deadlocks.

The hardlockup handler is best-effort recovery and the disable path it
triggers runs off of irq_work anyway. Move the handle_lockup() call into
an irq_work so it runs in IRQ context.

Fixes: ebeca1f930 ("sched_ext: Introduce cgroup sub-sched support")
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
This commit is contained in:
Tejun Heo
2026-04-24 14:13:22 -10:00
parent 510a270554
commit bd2d76455b
1 changed files with 27 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
kernel/sched/ext.c
+27 -6
View File
@@ -4940,6 +4940,25 @@ void scx_softlockup(u32 dur_s)
smp_processor_id(), dur_s); smp_processor_id(), dur_s);
} }
/*
* scx_hardlockup() runs from NMI and eventually calls scx_claim_exit(),
* which takes scx_sched_lock. scx_sched_lock isn't NMI-safe and grabbing
* it from NMI context can lead to deadlocks. Defer via irq_work; the
* disable path runs off irq_work anyway.
*/
static atomic_t scx_hardlockup_cpu = ATOMIC_INIT(-1);
static void scx_hardlockup_irq_workfn(struct irq_work *work)
{
int cpu = atomic_xchg(&scx_hardlockup_cpu, -1);
if (cpu >= 0 && handle_lockup("hard lockup - CPU %d", cpu))
printk_deferred(KERN_ERR "sched_ext: Hard lockup - CPU %d, disabling BPF scheduler\n",
cpu);
}
static DEFINE_IRQ_WORK(scx_hardlockup_irq_work, scx_hardlockup_irq_workfn);
/** /**
* scx_hardlockup - sched_ext hardlockup handler * scx_hardlockup - sched_ext hardlockup handler
* *
@@ -4948,17 +4967,19 @@ void scx_softlockup(u32 dur_s)
* Try kicking out the current scheduler in an attempt to recover the system to * Try kicking out the current scheduler in an attempt to recover the system to
* a good state before taking more drastic actions. * a good state before taking more drastic actions.
* *
* Returns %true if sched_ext is enabled and abort was initiated, which may * Queues an irq_work; the handle_lockup() call happens in IRQ context (see
* resolve the reported hardlockup. %false if sched_ext is not enabled or * scx_hardlockup_irq_workfn).
* someone else already initiated abort. *
* Returns %true if sched_ext is enabled and the work was queued, %false
* otherwise.
*/ */
bool scx_hardlockup(int cpu) bool scx_hardlockup(int cpu)
{ {
if (!handle_lockup("hard lockup - CPU %d", cpu)) if (!rcu_access_pointer(scx_root))
return false; return false;
printk_deferred(KERN_ERR "sched_ext: Hard lockup - CPU %d, disabling BPF scheduler\n", atomic_cmpxchg(&scx_hardlockup_cpu, -1, cpu);
cpu); irq_work_queue(&scx_hardlockup_irq_work);
return true; return true;
} }