[tip: sched/core] workqueue: Manually break affinity on hotplug

[tip-bot2 for Peter Zijlstra]

The following commit has been merged into the sched/core branch of tip:

Commit-ID:     06249738a41a70f2201a148866899f84cbebc45e
Gitweb:        https://git.kernel.org/tip/06249738a41a70f2201a148866899f84cbebc45e
Author:        Peter Zijlstra <peterz@xxxxxxxxxxxxx>
AuthorDate:    Fri, 25 Sep 2020 15:45:11 +02:00
Committer:     Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Tue, 10 Nov 2020 18:38:58 +01:00

workqueue: Manually break affinity on hotplug

Don't rely on the scheduler to force break affinity for us -- it will
stop doing that for per-cpu-kthreads.

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Reviewed-by: Valentin Schneider <valentin.schneider@xxxxxxx>
Acked-by: Tejun Heo <tj@xxxxxxxxxx>
Reviewed-by: Daniel Bristot de Oliveira <bristot@xxxxxxxxxx>
Link: https://lkml.kernel.org/r/20201023102346.464718669@xxxxxxxxxxxxx
---
 kernel/workqueue.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 437935e..c71da2a 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -4908,6 +4908,10 @@ static void unbind_workers(int cpu)
 		pool->flags |= POOL_DISASSOCIATED;
 
 		raw_spin_unlock_irq(&pool->lock);
+
+		for_each_pool_worker(worker, pool)
+			WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_active_mask) < 0);
+
 		mutex_unlock(&wq_pool_attach_mutex);
 
 		/*