summaryrefslogtreecommitdiff
path: root/kernel/workqueue.c
diff options
context:
space:
mode:
authorFrederic Weisbecker <frederic@kernel.org>2021-12-01 16:19:45 +0100
committerTejun Heo <tj@kernel.org>2021-12-02 13:00:59 -1000
commit45c753f5f24d2d4717acb38ce35e604ff9abcb50 (patch)
tree26a2bd00e9eccd018a879c9490e43c0ef46ebe92 /kernel/workqueue.c
parent07edfece8bcb0580a1828d939e6f8d91a8603eb2 (diff)
workqueue: Fix unbind_workers() VS wq_worker_sleeping() race
At CPU-hotplug time, unbind_workers() may preempt a worker while it is going to sleep. In that case the following scenario can happen: unbind_workers() wq_worker_sleeping() -------------- ------------------- if (worker->flags & WORKER_NOT_RUNNING) return; //PREEMPTED by unbind_workers worker->flags |= WORKER_UNBOUND; [...] atomic_set(&pool->nr_running, 0); //resume to worker atomic_dec_and_test(&pool->nr_running); After unbind_worker() resets pool->nr_running, the value is expected to remain 0 until the pool ever gets rebound in case cpu_up() is called on the target CPU in the future. But here the race leaves pool->nr_running with a value of -1, triggering the following warning when the worker goes idle: WARNING: CPU: 3 PID: 34 at kernel/workqueue.c:1823 worker_enter_idle+0x95/0xc0 Modules linked in: CPU: 3 PID: 34 Comm: kworker/3:0 Not tainted 5.16.0-rc1+ #34 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.12.0-59-gc9ba527-rebuilt.opensuse.org 04/01/2014 Workqueue: 0x0 (rcu_par_gp) RIP: 0010:worker_enter_idle+0x95/0xc0 Code: 04 85 f8 ff ff ff 39 c1 7f 09 48 8b 43 50 48 85 c0 74 1b 83 e2 04 75 99 8b 43 34 39 43 30 75 91 8b 83 00 03 00 00 85 c0 74 87 <0f> 0b 5b c3 48 8b 35 70 f1 37 01 48 8d 7b 48 48 81 c6 e0 93 0 RSP: 0000:ffff9b7680277ed0 EFLAGS: 00010086 RAX: 00000000ffffffff RBX: ffff93465eae9c00 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff9346418a0000 RDI: ffff934641057140 RBP: ffff934641057170 R08: 0000000000000001 R09: ffff9346418a0080 R10: ffff9b768027fdf0 R11: 0000000000002400 R12: ffff93465eae9c20 R13: ffff93465eae9c20 R14: ffff93465eae9c70 R15: ffff934641057140 FS: 0000000000000000(0000) GS:ffff93465eac0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000001cc0c000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> worker_thread+0x89/0x3d0 ? process_one_work+0x400/0x400 kthread+0x162/0x190 ? set_kthread_struct+0x40/0x40 ret_from_fork+0x22/0x30 </TASK> Also due to this incorrect "nr_running == -1", all sorts of hazards can happen, starting with queued works being ignored because no workers are awaken at insert_work() time. Fix this with checking again the worker flags while pool->lock is locked. Fixes: b945efcdd07d ("sched: Remove pointless preemption disable in sched_submit_work()") Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com> Tested-by: Paul E. McKenney <paulmck@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Frederic Weisbecker <frederic@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Paul E. McKenney <paulmck@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Daniel Bristot de Oliveira <bristot@redhat.com> Signed-off-by: Tejun Heo <tj@kernel.org>
Diffstat (limited to 'kernel/workqueue.c')
-rw-r--r--kernel/workqueue.c10
1 files changed, 10 insertions, 0 deletions
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 5094573e8b45..5557d19ea81c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -913,6 +913,16 @@ void wq_worker_sleeping(struct task_struct *task)
raw_spin_lock_irq(&pool->lock);
/*
+ * Recheck in case unbind_workers() preempted us. We don't
+ * want to decrement nr_running after the worker is unbound
+ * and nr_running has been reset.
+ */
+ if (worker->flags & WORKER_NOT_RUNNING) {
+ raw_spin_unlock_irq(&pool->lock);
+ return;
+ }
+
+ /*
* The counterpart of the following dec_and_test, implied mb,
* worklist not empty test sequence is in insert_work().
* Please read comment there.