sched: Make migration_call() safe for stop_machine()-free hotplug
The CPU_DYING branch of migration_call() relies on the fact that
CPU-hotplug offline operations use stop_machine(). This commit therefore
attempts to remedy this situation by acquiring the relevant runqueue
locks. Note that sched_ttwu_pending() remains outside of the scope of
these new runqueue-lock critical sections because (1) sched_ttwu_pending()
does its own runqueue-lock acquisition and (2) sched_ttwu_pending() handles
pending wakeups, and no further wakeups can select this CPU because it
is already marked as offline.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index eaead2d..2e7797a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5175,10 +5175,8 @@
* their home CPUs. So we just add the counter to another CPU's counter,
* to keep the global sum constant after CPU-down:
*/
-static void migrate_nr_uninterruptible(struct rq *rq_src)
+static void migrate_nr_uninterruptible(struct rq *rq_src, struct rq *rq_dest)
{
- struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask));
-
rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible;
rq_src->nr_uninterruptible = 0;
}
@@ -5200,7 +5198,7 @@
* there's no concurrency possible, we hold the required locks anyway
* because of lock validation efforts.
*/
-static void migrate_tasks(unsigned int dead_cpu)
+static void migrate_tasks(unsigned int dead_cpu, struct rq *rq_dest)
{
struct rq *rq = cpu_rq(dead_cpu);
struct task_struct *next, *stop = rq->stop;
@@ -5234,11 +5232,11 @@
/* Find suitable destination for @next, with force if needed. */
dest_cpu = select_fallback_rq(dead_cpu, next);
- raw_spin_unlock(&rq->lock);
+ double_rq_unlock(rq, rq_dest);
__migrate_task(next, dead_cpu, dest_cpu);
- raw_spin_lock(&rq->lock);
+ double_rq_lock(rq, rq_dest);
}
rq->stop = stop;
@@ -5452,6 +5450,7 @@
int cpu = (long)hcpu;
unsigned long flags;
struct rq *rq = cpu_rq(cpu);
+ struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask));
switch (action & ~CPU_TASKS_FROZEN) {
@@ -5474,17 +5473,19 @@
case CPU_DYING:
sched_ttwu_pending();
/* Update our root-domain */
- raw_spin_lock_irqsave(&rq->lock, flags);
+ local_irq_save(flags);
+ double_rq_lock(rq, rq_dest);
if (rq->rd) {
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
set_rq_offline(rq);
}
- migrate_tasks(cpu);
+ migrate_tasks(cpu, rq_dest);
BUG_ON(rq->nr_running != 1); /* the migration thread */
- raw_spin_unlock_irqrestore(&rq->lock, flags);
- migrate_nr_uninterruptible(rq);
+ migrate_nr_uninterruptible(rq, rq_dest);
calc_global_load_remove(rq);
+ double_rq_unlock(rq, rq_dest);
+ local_irq_restore(flags);
break;
#endif
}
