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 <jmario@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: hannes@cmpxchg.org
Cc: aarcange@redhat.com
Cc: srikar@linux.vnet.ibm.com
Cc: tglx@linutronix.de
Cc: hpa@zytor.com
Link: http://lkml.kernel.org/r/20131010181722.GO13848@laptop.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

3 files changed, 22 insertions, 9 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0c3feebcf112..a972acd468b0 100644
--- a/kernel/sched/core.c
+++ b/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;
 }
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 4aa0b10889d0..813dd61a9b43 100644
--- a/kernel/sched/fair.c
+++ b/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)
 {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index d69cb325c27e..ffc708717b70 100644
--- a/kernel/sched/sched.h
+++ b/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
  *