This patch corrects the way memory barriers are used in the MCS lock
with smp_load_acquire and smp_store_release fucnctions. The previous
barriers could leak critical sections if mcs lock is used by itself.
It is not a problem when mcs lock is embedded in mutex but will be an
issue when the mcs_lock is used elsewhere.
The patch removes the incorrect barriers and put in correct
barriers with the pair of functions smp_load_acquire and smp_store_release.
Suggested-by: Michel Lespinasse <walken@google.com>
Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Signed-off-by: Jason Low <jason.low2@hp.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1390347353.3138.62.camel@schen9-DESK
Signed-off-by: Ingo Molnar <mingo@kernel.org>
return;
}
ACCESS_ONCE(prev->next) = node;
- smp_wmb();
- /* Wait until the lock holder passes the lock down */
- while (!ACCESS_ONCE(node->locked))
+ /*
+ * Wait until the lock holder passes the lock down.
+ * Using smp_load_acquire() provides a memory barrier that
+ * ensures subsequent operations happen after the lock is acquired.
+ */
+ while (!(smp_load_acquire(&node->locked)))
arch_mutex_cpu_relax();
}
while (!(next = ACCESS_ONCE(node->next)))
arch_mutex_cpu_relax();
}
- ACCESS_ONCE(next->locked) = 1;
- smp_wmb();
+ /*
+ * Pass lock to next waiter.
+ * smp_store_release() provides a memory barrier to ensure
+ * all operations in the critical section has been completed
+ * before unlocking.
+ */
+ smp_store_release(&next->locked, 1);
}
/*