Revert "sched/core: Do not use smp_processor_id() with preempt enabled in smpboot_thread_fn()"
This reverts commit 4fa5cd5245b627db88c9ca08ae442373b02596b4.
The original change widens a preempt-off section, to avoid a seemingly unsafe
smp_processor_id() use.
During review I overlooked two facts:
- The code to calls a non-trivial function callback:
ht->park(td->cpu);
... which might (and does occasionally) sleep, triggering the warning.
- More importantly, as pointed out by Peter Zijlstra, using
smp_processor_id() in that context is safe, if it's done from
a kernel thread that is pinned to a single CPU - which is the
case here.
So revert to the original code that enables preemption sooner.
Reported-by: kernel test robot <xiaolong.ye@intel.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Con Kolivas <kernel@kolivas.org>
Cc: Alfred Chen <cchalpha@gmail.com>
Link: http://lkml.kernel.org/r/20160930015102.GB20189@yexl-desktop
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index fc0d8270..13bc43d 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -122,12 +122,12 @@
if (kthread_should_park()) {
__set_current_state(TASK_RUNNING);
+ preempt_enable();
if (ht->park && td->status == HP_THREAD_ACTIVE) {
BUG_ON(td->cpu != smp_processor_id());
ht->park(td->cpu);
td->status = HP_THREAD_PARKED;
}
- preempt_enable();
kthread_parkme();
/* We might have been woken for stop */
continue;
