futex: Fix a race condition between REQUEUE_PI and task death

commit 30a6b803 upstream.

free_pi_state and exit_pi_state_list both clean up futex_pi_state's.
exit_pi_state_list takes the hb lock first, and most callers of
free_pi_state do too. requeue_pi doesn't, which means free_pi_state
can free the pi_state out from under exit_pi_state_list. For example:

task A                            |  task B
exit_pi_state_list                |
  pi_state =                      |
      curr->pi_state_list->next   |
                                  |  futex_requeue(requeue_pi=1)
                                  |    // pi_state is the same as
                                  |    // the one in task A
                                  |    free_pi_state(pi_state)
                                  |      list_del_init(&pi_state->list)
                                  |      kfree(pi_state)
  list_del_init(&pi_state->list)  |

Move the free_pi_state calls in requeue_pi to before it drops the hb
locks which it's already holding.

[ tglx: Removed a pointless free_pi_state() call and the hb->lock held
  	debugging. The latter comes via a seperate patch ]
Signed-off-by: Brian Silverman <bsilver16384@gmail.com>
Cc: austin.linux@gmail.com
Cc: darren@dvhart.com
Cc: peterz@infradead.org
Cc: Mike Galbraith <mgalbraith@suse.de>
Link: http://lkml.kernel.org/r/1414282837-23092-1-git-send-email-bsilver16384@gmail.comSigned-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>

kernel/futex.c

@@ -490,8 +490,14 @@ static struct futex_pi_state * alloc_pi_state(void)
 	return pi_state;
 }
 
+/*
+ * Must be called with the hb lock held.
+ */
 static void free_pi_state(struct futex_pi_state *pi_state)
 {
+	if (!pi_state)
+		return;
+
 	if (!atomic_dec_and_test(&pi_state->refcount))
 		return;
 
@@ -1405,15 +1411,6 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 	}
 
 retry:
-	if (pi_state != NULL) {
-		/*
-		 * We will have to lookup the pi_state again, so free this one
-		 * to keep the accounting correct.
-		 */
-		free_pi_state(pi_state);
-		pi_state = NULL;
-	}
-
 	ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ);
 	if (unlikely(ret != 0))
 		goto out;
@@ -1501,6 +1498,8 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 		case 0:
 			break;
 		case -EFAULT:
+			free_pi_state(pi_state);
+			pi_state = NULL;
 			double_unlock_hb(hb1, hb2);
 			put_futex_key(&key2);
 			put_futex_key(&key1);
@@ -1510,6 +1509,8 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 			goto out;
 		case -EAGAIN:
 			/* The owner was exiting, try again. */
+			free_pi_state(pi_state);
+			pi_state = NULL;
 			double_unlock_hb(hb1, hb2);
 			put_futex_key(&key2);
 			put_futex_key(&key1);
@@ -1586,6 +1587,7 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 	}
 
 out_unlock:
+	free_pi_state(pi_state);
 	double_unlock_hb(hb1, hb2);
 
 	/*
@@ -1602,8 +1604,6 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 out_put_key1:
 	put_futex_key(&key1);
 out:
-	if (pi_state != NULL)
-		free_pi_state(pi_state);
 	return ret ? ret : task_count;
 }