[PATCH -v5 09/14] futex: Rework inconsistent rt_mutex/futex_q state

[Peter Zijlstra]

There is a weird state in the futex_unlock_pi() path when it
interleaves with a concurrent futex_lock_pi() at the point where it
drops hb->lock.

In this case, it can happen that the rt_mutex wait_list and the
futex_q disagree on pending waiters, in particular rt_mutex will find
no pending waiters where futex_q thinks there are.

In this case the rt_mutex unlock code cannot assign an owner.

What the current code does in this case is use the futex_q waiter that
got us here; however when the rt_mutex_timed_futex_lock() has already
failed; this leaves things in a weird state, resulting in much
head-aches in fixup_owner().

Simplify all this by changing wake_futex_pi() to return -EAGAIN when
this situation occurs. This then gives the futex_lock_pi() code the
opportunity to continue and the retried futex_unlock_pi() will now
observe a coherent state.

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
 kernel/futex.c |   49 +++++++++++++------------------------------------
 1 file changed, 13 insertions(+), 36 deletions(-)

--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1402,12 +1402,18 @@ static int wake_futex_pi(u32 __user *uad
 	new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
 
 	/*
-	 * It is possible that the next waiter (the one that brought
-	 * top_waiter owner to the kernel) timed out and is no longer
-	 * waiting on the lock.
+	 * When we interleave with futex_lock_pi() where it does
+	 * rt_mutex_timed_futex_lock(), we might observe @this futex_q waiter,
+	 * but the rt_mutex's wait_list can be empty (either still, or again,
+	 * depending on which side we land).
+	 *
+	 * When this happens, give up our locks and try again, giving the
+	 * futex_lock_pi() instance time to complete and unqueue_me().
 	 */
-	if (!new_owner)
-		new_owner = top_waiter->task;
+	if (!new_owner) {
+		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+		return -EAGAIN;
+	}
 
 	/*
 	 * We pass it to the next owner. The WAITERS bit is always
@@ -2324,7 +2330,6 @@ static long futex_wait_restart(struct re
  */
 static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 {
-	struct task_struct *owner;
 	int ret = 0;
 
 	if (locked) {
@@ -2338,43 +2343,15 @@ static int fixup_owner(u32 __user *uaddr
 	}
 
 	/*
-	 * Catch the rare case, where the lock was released when we were on the
-	 * way back before we locked the hash bucket.
-	 */
-	if (q->pi_state->owner == current) {
-		/*
-		 * Try to get the rt_mutex now. This might fail as some other
-		 * task acquired the rt_mutex after we removed ourself from the
-		 * rt_mutex waiters list.
-		 */
-		if (rt_mutex_futex_trylock(&q->pi_state->pi_mutex)) {
-			locked = 1;
-			goto out;
-		}
-
-		/*
-		 * pi_state is incorrect, some other task did a lock steal and
-		 * we returned due to timeout or signal without taking the
-		 * rt_mutex. Too late.
-		 */
-		raw_spin_lock_irq(&q->pi_state->pi_mutex.wait_lock);
-		owner = rt_mutex_owner(&q->pi_state->pi_mutex);
-		if (!owner)
-			owner = rt_mutex_next_owner(&q->pi_state->pi_mutex);
-		raw_spin_unlock_irq(&q->pi_state->pi_mutex.wait_lock);
-		ret = fixup_pi_state_owner(uaddr, q, owner);
-		goto out;
-	}
-
-	/*
 	 * Paranoia check. If we did not take the lock, then we should not be
 	 * the owner of the rt_mutex.
 	 */
-	if (rt_mutex_owner(&q->pi_state->pi_mutex) == current)
+	if (rt_mutex_owner(&q->pi_state->pi_mutex) == current) {
 		printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p "
 				"pi-state %p\n", ret,
 				q->pi_state->pi_mutex.owner,
 				q->pi_state->owner);
+	}
 
 out:
 	return ret ? ret : locked;