wait: prevent exclusive waiter starvation

With exclusive waiters, every process woken up through the wait queue must
ensure that the next waiter down the line is woken when it has finished.

Interruptible waiters don't do that when aborting due to a signal.  And if
an aborting waiter is concurrently woken up through the waitqueue, noone
will ever wake up the next waiter.

This has been observed with __wait_on_bit_lock() used by
lock_page_killable(): the first contender on the queue was aborting when
the actual lock holder woke it up concurrently.  The aborted contender
didn't acquire the lock and therefor never did an unlock followed by
waking up the next waiter.

Add abort_exclusive_wait() which removes the process' wait descriptor from
the waitqueue, iff still queued, or wakes up the next waiter otherwise.
It does so under the waitqueue lock.  Racing with a wake up means the
aborting process is either already woken (removed from the queue) and will
wake up the next waiter, or it will remove itself from the queue and the
concurrent wake up will apply to the next waiter after it.

Use abort_exclusive_wait() in __wait_event_interruptible_exclusive() and
__wait_on_bit_lock() when they were interrupted by other means than a wake
up through the queue.

[akpm@linux-foundation.org: coding-style fixes]
Reported-by: Chris Mason <chris.mason@oracle.com>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Mentored-by: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Matthew Wilcox <matthew@wil.cx>
Cc: Chuck Lever <cel@citi.umich.edu>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: <stable@kernel.org>		["after some testing"]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 9 insertions, 2 deletions

diff --git a/include/linux/wait.h b/include/linux/wait.h
index ef609f842fa..a210ede73b5 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -132,6 +132,8 @@ static inline void __remove_wait_queue(wait_queue_head_t *head,
 	list_del(&old->task_list);
 }
 
+void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+			int nr_exclusive, int sync, void *key);
 void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
 extern void __wake_up_locked(wait_queue_head_t *q, unsigned int mode);
 extern void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr);
@@ -333,16 +335,19 @@ do {									\
 	for (;;) {							\
 		prepare_to_wait_exclusive(&wq, &__wait,			\
 					TASK_INTERRUPTIBLE);		\
-		if (condition)						\
+		if (condition) {					\
+			finish_wait(&wq, &__wait);			\
 			break;						\
+		}							\
 		if (!signal_pending(current)) {				\
 			schedule();					\
 			continue;					\
 		}							\
 		ret = -ERESTARTSYS;					\
+		abort_exclusive_wait(&wq, &__wait, 			\
+				TASK_INTERRUPTIBLE, NULL);		\
 		break;							\
 	}								\
-	finish_wait(&wq, &__wait);					\
 } while (0)
 
 #define wait_event_interruptible_exclusive(wq, condition)		\
@@ -431,6 +436,8 @@ extern long interruptible_sleep_on_timeout(wait_queue_head_t *q,
 void prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state);
 void prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state);
 void finish_wait(wait_queue_head_t *q, wait_queue_t *wait);
+void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
+			unsigned int mode, void *key);
 int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);