From 94dcf29a11b3d20a28790598d701f98484a969da Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 22 Mar 2011 16:30:45 -0700 Subject: kthread: use kthread_create_on_node() ksoftirqd, kworker, migration, and pktgend kthreads can be created with kthread_create_on_node(), to get proper NUMA affinities for their stack and task_struct. Signed-off-by: Eric Dumazet Acked-by: David S. Miller Reviewed-by: Andi Kleen Acked-by: Rusty Russell Acked-by: Tejun Heo Cc: Tony Luck Cc: Fenghua Yu Cc: David Howells Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/workqueue.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel/workqueue.c') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 5ca7ce9ce754..04ef830690ec 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1366,8 +1366,10 @@ static struct worker *create_worker(struct global_cwq *gcwq, bool bind) worker->id = id; if (!on_unbound_cpu) - worker->task = kthread_create(worker_thread, worker, - "kworker/%u:%d", gcwq->cpu, id); + worker->task = kthread_create_on_node(worker_thread, + worker, + cpu_to_node(gcwq->cpu), + "kworker/%u:%d", gcwq->cpu, id); else worker->task = kthread_create(worker_thread, worker, "kworker/u:%d", id); -- cgit v1.2.2 From 5035b20fa5cd146b66f5f89619c20a4177fb736d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 29 Apr 2011 18:08:37 +0200 Subject: workqueue: fix deadlock in worker_maybe_bind_and_lock() If a rescuer and stop_machine() bringing down a CPU race with each other, they may deadlock on non-preemptive kernel. The CPU won't accept a new task, so the rescuer can't migrate to the target CPU, while stop_machine() can't proceed because the rescuer is holding one of the CPU retrying migration. GCWQ_DISASSOCIATED is never cleared and worker_maybe_bind_and_lock() retries indefinitely. This problem can be reproduced semi reliably while the system is entering suspend. http://thread.gmane.org/gmane.linux.kernel/1122051 A lot of kudos to Thilo-Alexander for reporting this tricky issue and painstaking testing. stable: This affects all kernels with cmwq, so all kernels since and including v2.6.36 need this fix. Signed-off-by: Tejun Heo Reported-by: Thilo-Alexander Ginkel Tested-by: Thilo-Alexander Ginkel Cc: stable@kernel.org --- kernel/workqueue.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel/workqueue.c') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 04ef830690ec..e3378e8d3a5c 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1291,8 +1291,14 @@ __acquires(&gcwq->lock) return true; spin_unlock_irq(&gcwq->lock); - /* CPU has come up inbetween, retry migration */ + /* + * We've raced with CPU hot[un]plug. Give it a breather + * and retry migration. cond_resched() is required here; + * otherwise, we might deadlock against cpu_stop trying to + * bring down the CPU on non-preemptive kernel. + */ cpu_relax(); + cond_resched(); } } -- cgit v1.2.2