sched: Optimize migration_cpu_stop()

When the purpose of migration_cpu_stop() is to migrate the task to
'any' valid CPU, don't migrate the task when it's already running on a
valid CPU.

Fixes: 6d337eab041d ("sched: Fix migrate_disable() vs set_cpus_allowed_ptr()")
Cc: stable@kernel.org
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Link: https://lkml.kernel.org/r/20210224131355.569238629@infradead.org

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 84b657f056258fd2dfae749466edc775468a125b..ac05afbd982eec9f176293d458b907a39ffb446b 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1936,14 +1936,25 @@ static int migration_cpu_stop(void *data)
                        complete = true;
                }
 
-               if (dest_cpu < 0)
+               if (dest_cpu < 0) {
+                       if (cpumask_test_cpu(task_cpu(p), &p->cpus_mask))
+                               goto out;
+
                        dest_cpu = cpumask_any_distribute(&p->cpus_mask);
+               }
 
                if (task_on_rq_queued(p))
                        rq = __migrate_task(rq, &rf, p, dest_cpu);
                else
                        p->wake_cpu = dest_cpu;
 
+               /*
+                * XXX __migrate_task() can fail, at which point we might end
+                * up running on a dodgy CPU, AFAICT this can only happen
+                * during CPU hotplug, at which point we'll get pushed out
+                * anyway, so it's probably not a big deal.
+                */
+
        } else if (pending) {
                /*
                 * This happens when we get migrated between migrate_enable()'s