sched: Fix race in migrate_swap_stop()

There is a subtle race in migrate_swap, when task P, on CPU A, decides to swap
places with task T, on CPU B.

Task P:
  - call migrate_swap
Task T:
  - go to sleep, removing itself from the runqueue
Task P:
  - double lock the runqueues on CPU A & B
Task T:
  - get woken up, place itself on the runqueue of CPU C
Task P:
  - see that task T is on a runqueue, and pretend to remove it
    from the runqueue on CPU B

Now CPUs B & C both have corrupted scheduler data structures.

This patch fixes it, by holding the pi_lock for both of the tasks
involved in the migrate swap. This prevents task T from waking up,
and placing itself onto another runqueue, until after migrate_swap
has released all locks.

This means that, when migrate_swap checks, task T will be either
on the runqueue where it was originally seen, or not on any
runqueue at all. Migrate_swap deals correctly with of those cases.

Tested-by: Joe Mario <[email protected]>
Acked-by: Mel Gorman <[email protected]>
Reviewed-by: Rik van Riel <[email protected]>
Signed-off-by: Peter Zijlstra <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

Author: Peter Zijlstra

kernel/sched/core.c

@@ -1049,6 +1049,8 @@ static int migrate_swap_stop(void *data)
 	src_rq = cpu_rq(arg->src_cpu);
 	dst_rq = cpu_rq(arg->dst_cpu);
 
+	double_raw_lock(&arg->src_task->pi_lock,
+			&arg->dst_task->pi_lock);
 	double_rq_lock(src_rq, dst_rq);
 	if (task_cpu(arg->dst_task) != arg->dst_cpu)
 		goto unlock;
@@ -1069,6 +1071,8 @@ static int migrate_swap_stop(void *data)
 
 unlock:
 	double_rq_unlock(src_rq, dst_rq);
+	raw_spin_unlock(&arg->dst_task->pi_lock);
+	raw_spin_unlock(&arg->src_task->pi_lock);
 
 	return ret;
 }

kernel/sched/fair.c

@@ -1448,15 +1448,6 @@ static inline void put_numa_group(struct numa_group *grp)
 		kfree_rcu(grp, rcu);
 }
 
-static void double_lock(spinlock_t *l1, spinlock_t *l2)
-{
-	if (l1 > l2)
-		swap(l1, l2);
-
-	spin_lock(l1);
-	spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
-}
-
 static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 			int *priv)
 {

kernel/sched/sched.h

@@ -1249,6 +1249,24 @@ static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
 	lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
 }
 
+static inline void double_lock(spinlock_t *l1, spinlock_t *l2)
+{
+	if (l1 > l2)
+		swap(l1, l2);
+
+	spin_lock(l1);
+	spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
+}
+
+static inline void double_raw_lock(raw_spinlock_t *l1, raw_spinlock_t *l2)
+{
+	if (l1 > l2)
+		swap(l1, l2);
+
+	raw_spin_lock(l1);
+	raw_spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
+}
+
 /*
  * double_rq_lock - safely lock two runqueues
  *