Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1586065 > unrolled thread

Re: [PATCH -v4 00/10] FUTEX_UNLOCK_PI wobbles

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.

Contents

  Re: [PATCH -v4 00/10] FUTEX_UNLOCK_PI wobbles Peter Zijlstra <peterz@infradead.org> - 2017-02-22 12:10 +0100
    Re: [PATCH -v4 00/10] FUTEX_UNLOCK_PI wobbles Peter Zijlstra <peterz@infradead.org> - 2017-02-22 16:40 +0100

#1586065 — Re: [PATCH -v4 00/10] FUTEX_UNLOCK_PI wobbles

On Tue, Dec 13, 2016 at 05:07:14PM +0100, Peter Zijlstra wrote:
> On Tue, Dec 13, 2016 at 09:36:38AM +0100, Peter Zijlstra wrote:
> 
> > The basic idea is to, like requeue PI, break the rt_mutex_lock() function into
> > pieces, such that we can enqueue the waiter while holding hb->lock, wait for
> > acquisition without hb->lock and can remove the waiter, on failure, while
> > holding hb->lock again.
> > 
> > That way, when we drop hb->lock to wait, futex and rt_mutex wait state is
> > consistent.
> 
> And of course, there's a hole in...
> 
> There is a point in futex_unlock_pi() where we hold neither hb->lock nor
> wait_lock, at that point a futex_lock_pi() that had failed its
> rt_mutex_wait_proxy_lock() can sneak in and remove itself, even though
> we saw its waiter, recreating a vraiant of the initial problem.
> 
> The below plugs the hole, but its rather fragile in that it relies on
> overlapping critical sections and the specific detail that we call
> rt_mutex_cleanup_proxy_lock() immediately after (re)acquiring hb->lock.
> 
> There is another solution, but that's more involved and uglier still.
> 
> I'll give it a bit more thought.
> 

OK, so after having not thought about this, and then spend the last two
days trying to cram all this nonsense back into my head, I think I have
a slightly simpler option.

In any case, I'll go respin the patch-set and repost.


--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1395,7 +1395,18 @@ static int wake_futex_pi(u32 __user *uad
 
 	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 	new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
-	BUG_ON(!new_owner);
+	if (!new_owner) {
+		/*
+		 * Since we held neither hb->lock nor wait_lock when coming
+		 * into this function, we could have raced with futex_lock_pi()
+		 * such that it will have removed the waiter that brought us
+		 * here.
+		 *
+		 * In this case, retry the entire operation.
+		 */
+		ret = -EAGAIN;
+		goto out_unlock;
+	}
 
 	/*
 	 * We pass it to the next owner. The WAITERS bit is always kept
@@ -2657,8 +2668,8 @@ static int futex_lock_pi(u32 __user *uad
 	 * rt_mutex waitqueue, such that we can keep the hb and rt_mutex
 	 * wait lists consistent.
 	 */
-	if (ret)
-		rt_mutex_cleanup_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter);
+	if (ret && !rt_mutex_cleanup_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter))
+		ret = 0;
 
 did_trylock:
 	/*
@@ -3043,8 +3054,9 @@ static int futex_wait_requeue_pi(u32 __u
 		debug_rt_mutex_free_waiter(&rt_waiter);
 
 		spin_lock(q.lock_ptr);
-		if (ret)
-			rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter);
+		if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter))
+			ret = 0;
+
 		/*
 		 * Fixup the pi_state owner and possibly acquire the lock if we
 		 * haven't already.
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1781,16 +1781,29 @@ int rt_mutex_wait_proxy_lock(struct rt_m
  *
  * Clean up the failed lock acquisition as per rt_mutex_wait_proxy_lock().
  *
+ * Returns:
+ *  true  - did the cleanup, we done.
+ *  false - we acquired the lock after rt_mutex_wait_proxy_lock() returned,
+ *          caller should disregards its return value.
+ *
  * Special API call for PI-futex support
  */
-void rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
+bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
 				 struct rt_mutex_waiter *waiter)
 {
-	raw_spin_lock_irq(&lock->wait_lock);
-
-	remove_waiter(lock, waiter);
-	fixup_rt_mutex_waiters(lock);
+	bool cleanup = false;
 
+	raw_spin_lock_irq(&lock->wait_lock);
+	/*
+	 * If we acquired the lock, no cleanup required.
+	 */
+	if (rt_mutex_owner(lock) != current) {
+		remove_waiter(lock, waiter);
+		fixup_rt_mutex_waiters(lock);
+		cleanup = true;
+	}
 	raw_spin_unlock_irq(&lock->wait_lock);
+
+	return cleanup;
 }
 
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -106,11 +106,10 @@ extern void rt_mutex_proxy_unlock(struct
 extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 				     struct rt_mutex_waiter *waiter,
 				     struct task_struct *task);
-
 extern int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
 			       struct hrtimer_sleeper *to,
 			       struct rt_mutex_waiter *waiter);
-extern void rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
+extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
 				 struct rt_mutex_waiter *waiter);
 
 extern int rt_mutex_futex_trylock(struct rt_mutex *l);

[toc] | [next] | [standalone]

#1586268

On Wed, Feb 22, 2017 at 12:02:44PM +0100, Peter Zijlstra wrote:
> OK, so after having not thought about this, and then spend the last two
> days trying to cram all this nonsense back into my head, I think I have
> a slightly simpler option.
> 
> In any case, I'll go respin the patch-set and repost.

That is; what is wrong with the below patch against mainline?

---

 kernel/futex.c | 48 +++++++++++++-----------------------------------
 1 file changed, 13 insertions(+), 35 deletions(-)

diff --git a/kernel/futex.c b/kernel/futex.c
index c591a2a..fafa25a 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1318,12 +1318,18 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
 	new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
 
 	/*
-	 * It is possible that the next waiter (the one that brought
-	 * this 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 = this->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
@@ -2245,43 +2251,15 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 	}
 
 	/*
-	 * 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_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;

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web