summaryrefslogtreecommitdiff
path: root/kernel/sched/core.c
diff options
context:
space:
mode:
authorPeter Zijlstra <peterz@infradead.org>2025-10-27 12:01:33 +0100
committerPeter Zijlstra <peterz@infradead.org>2025-10-28 15:00:48 +0100
commitaf13e5e437dc2eb8a3291aad70fc80d9cc78bc73 (patch)
tree1d744aa5b71354b60cc3bb5cb79f6f5142fb78bf /kernel/sched/core.c
parent73cbcfe255f7edca915d978a7d1b0a11f2d62812 (diff)
sched: Fix the do_set_cpus_allowed() locking fix
Commit abfc01077df6 ("sched: Fix do_set_cpus_allowed() locking") overlooked that __balance_push_cpu_stop() calls select_fallback_rq() with rq->lock held. This makes that set_cpus_allowed_force() will recursively take rq->lock and the machine locks up. Run select_fallback_rq() earlier, without holding rq->lock. This opens up a race window where a task could get migrated out from under us, but that is harmless, we want the task migrated. select_fallback_rq() itself will not be subject to concurrency as it will be fully serialized by p->pi_lock, so there is no chance of set_cpus_allowed_force() getting called with different arguments and selecting different fallback CPUs for one task. Fixes: abfc01077df6 ("sched: Fix do_set_cpus_allowed() locking") Reported-by: Jan Polensky <japo@linux.ibm.com> Reported-by: kernel test robot <oliver.sang@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Jan Polensky <japo@linux.ibm.com> Closes: https://lore.kernel.org/oe-lkp/202510271206.24495a68-lkp@intel.com Link: https://patch.msgid.link/20251027110133.GI3245006@noisy.programming.kicks-ass.net
Diffstat (limited to 'kernel/sched/core.c')
-rw-r--r--kernel/sched/core.c17
1 files changed, 7 insertions, 10 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 096e8d03d85e..fd9ff697fd90 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8044,18 +8044,15 @@ static int __balance_push_cpu_stop(void *arg)
struct rq_flags rf;
int cpu;
- raw_spin_lock_irq(&p->pi_lock);
- rq_lock(rq, &rf);
-
- update_rq_clock(rq);
-
- if (task_rq(p) == rq && task_on_rq_queued(p)) {
+ scoped_guard (raw_spinlock_irq, &p->pi_lock) {
cpu = select_fallback_rq(rq->cpu, p);
- rq = __migrate_task(rq, &rf, p, cpu);
- }
- rq_unlock(rq, &rf);
- raw_spin_unlock_irq(&p->pi_lock);
+ rq_lock(rq, &rf);
+ update_rq_clock(rq);
+ if (task_rq(p) == rq && task_on_rq_queued(p))
+ rq = __migrate_task(rq, &rf, p, cpu);
+ rq_unlock(rq, &rf);
+ }
put_task_struct(p);