[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Sat, 2 Feb 2019 12:20:06 +0100
From: Heiko Carstens <heiko.carstens@...ibm.com>
To: Thomas Gleixner <tglx@...utronix.de>
Cc: Sebastian Sewior <bigeasy@...utronix.de>,
"Paul E. McKenney" <paulmck@...ux.ibm.com>,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...nel.org>,
Martin Schwidefsky <schwidefsky@...ibm.com>,
LKML <linux-kernel@...r.kernel.org>, linux-s390@...r.kernel.org,
Stefan Liebler <stli@...ux.ibm.com>
Subject: Re: WARN_ON_ONCE(!new_owner) within wake_futex_pi() triggerede
On Sat, Feb 02, 2019 at 11:14:27AM +0100, Thomas Gleixner wrote:
> On Sat, 2 Feb 2019, Heiko Carstens wrote:
> So after the unlock @timestamp 337.215675 the kernel does not deal with
> that futex at all until the failed lock attempt where it rightfully rejects
> the attempt due to the alleged owner being gone.
>
> So this looks more like user space doing something stupid...
>
> As we talked about the missing barriers before, I just looked at
> pthread_mutex_trylock() and that does still:
>
> if (robust)
> {
> ENQUEUE_MUTEX_PI (mutex);
> THREAD_SETMEM (THREAD_SELF, robust_head.list_op_pending, NULL);
> }
>
> So it's missing the barriers which pthread_mutex_lock() has. Grasping for
> straws obviously....
Excellent! Taking a look into the disassembly of nptl/pthread_mutex_trylock.o
reveals this part:
140: a5 1b 00 01 oill %r1,1
144: e5 48 a0 f0 00 00 mvghi 240(%r10),0 <--- THREAD_SETMEM (THREAD_SELF, robust_head.list_op_pending, NULL);
14a: e3 10 a0 e0 00 24 stg %r1,224(%r10) <--- last THREAD_SETMEM of ENQUEUE_MUTEX_PI
I added a barrier between those two and now the code looks like this:
140: a5 1b 00 01 oill %r1,1
144: e3 10 a0 e0 00 24 stg %r1,224(%r10)
14a: e5 48 a0 f0 00 00 mvghi 240(%r10),0
Looks like this was a one instruction race...
I'll try to reproduce with the patch below (sprinkling compiler
barriers just like the other files have).
diff --git a/nptl/pthread_mutex_trylock.c b/nptl/pthread_mutex_trylock.c
index 7de61f4f68..3b093cb09c 100644
--- a/nptl/pthread_mutex_trylock.c
+++ b/nptl/pthread_mutex_trylock.c
@@ -116,8 +116,12 @@ __pthread_mutex_trylock (pthread_mutex_t *mutex)
mutex->__data.__count = 1;
/* But it is inconsistent unless marked otherwise. */
mutex->__data.__owner = PTHREAD_MUTEX_INCONSISTENT;
-
+ /* We must not enqueue the mutex before we have acquired it.
+ Also see comments at ENQUEUE_MUTEX. */
+ __asm ("" ::: "memory");
ENQUEUE_MUTEX (mutex);
+ /* We need to clear op_pending after we enqueue the mutex. */
+ __asm ("" ::: "memory");
THREAD_SETMEM (THREAD_SELF, robust_head.list_op_pending, NULL);
/* Note that we deliberately exist here. If we fall
@@ -177,7 +181,12 @@ __pthread_mutex_trylock (pthread_mutex_t *mutex)
}
while ((oldval & FUTEX_OWNER_DIED) != 0);
+ /* We must not enqueue the mutex before we have acquired it.
+ Also see comments at ENQUEUE_MUTEX. */
+ __asm ("" ::: "memory");
ENQUEUE_MUTEX (mutex);
+ /* We need to clear op_pending after we enqueue the mutex. */
+ __asm ("" ::: "memory");
THREAD_SETMEM (THREAD_SELF, robust_head.list_op_pending, NULL);
mutex->__data.__owner = id;
@@ -279,7 +288,11 @@ __pthread_mutex_trylock (pthread_mutex_t *mutex)
/* But it is inconsistent unless marked otherwise. */
mutex->__data.__owner = PTHREAD_MUTEX_INCONSISTENT;
+ /* We must not enqueue the mutex before we have acquired it.
+ Also see comments at ENQUEUE_MUTEX. */
+ __asm ("" ::: "memory");
ENQUEUE_MUTEX (mutex);
+ __asm ("" ::: "memory");
THREAD_SETMEM (THREAD_SELF, robust_head.list_op_pending, NULL);
/* Note that we deliberately exit here. If we fall
@@ -308,7 +321,12 @@ __pthread_mutex_trylock (pthread_mutex_t *mutex)
if (robust)
{
+ /* We must not enqueue the mutex before we have acquired it.
+ Also see comments at ENQUEUE_MUTEX. */
+ __asm ("" ::: "memory");
ENQUEUE_MUTEX_PI (mutex);
+ /* We need to clear op_pending after we enqueue the mutex. */
+ __asm ("" ::: "memory");
THREAD_SETMEM (THREAD_SELF, robust_head.list_op_pending, NULL);
}
Powered by blists - more mailing lists