1 files changed, 189 insertions, 50 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index c89e9be5c6bd..7ec4fcd8a34d 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1044,8 +1044,43 @@ struct wait_page_queue {
 	wait_queue_entry_t wait;
 };
 
+/*
+ * The page wait code treats the "wait->flags" somewhat unusually, because
+ * we have multiple different kinds of waits, not just he usual "exclusive"
+ * one.
+ *
+ * We have:
+ *
+ *  (a) no special bits set:
+ *
+ *	We're just waiting for the bit to be released, and when a waker
+ *	calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up,
+ *	and remove it from the wait queue.
+ *
+ *	Simple and straightforward.
+ *
+ *  (b) WQ_FLAG_EXCLUSIVE:
+ *
+ *	The waiter is waiting to get the lock, and only one waiter should
+ *	be woken up to avoid any thundering herd behavior. We'll set the
+ *	WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue.
+ *
+ *	This is the traditional exclusive wait.
+ *
+ *  (b) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM:
+ *
+ *	The waiter is waiting to get the bit, and additionally wants the
+ *	lock to be transferred to it for fair lock behavior. If the lock
+ *	cannot be taken, we stop walking the wait queue without waking
+ *	the waiter.
+ *
+ *	This is the "fair lock handoff" case, and in addition to setting
+ *	WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see
+ *	that it now has the lock.
+ */
 static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg)
 {
+	unsigned int flags;
 	struct wait_page_key *key = arg;
 	struct wait_page_queue *wait_page
 		= container_of(wait, struct wait_page_queue, wait);
@@ -1058,17 +1093,44 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync,
 		return 0;
 
 	/*
-	 * Stop walking if it's locked.
-	 * Is this safe if put_and_wait_on_page_locked() is in use?
-	 * Yes: the waker must hold a reference to this page, and if PG_locked
-	 * has now already been set by another task, that task must also hold
-	 * a reference to the *same usage* of this page; so there is no need
-	 * to walk on to wake even the put_and_wait_on_page_locked() callers.
+	 * If it's a lock handoff wait, we get the bit for it, and
+	 * stop walking (and do not wake it up) if we can't.
 	 */
-	if (test_bit(key->bit_nr, &key->page->flags))
-		return -1;
+	flags = wait->flags;
+	if (flags & WQ_FLAG_EXCLUSIVE) {
+		if (test_bit(key->bit_nr, &key->page->flags))
+			return -1;
+		if (flags & WQ_FLAG_CUSTOM) {
+			if (test_and_set_bit(key->bit_nr, &key->page->flags))
+				return -1;
+			flags |= WQ_FLAG_DONE;
+		}
+	}
 
-	return autoremove_wake_function(wait, mode, sync, key);
+	/*
+	 * We are holding the wait-queue lock, but the waiter that
+	 * is waiting for this will be checking the flags without
+	 * any locking.
+	 *
+	 * So update the flags atomically, and wake up the waiter
+	 * afterwards to avoid any races. This store-release pairs
+	 * with the load-acquire in wait_on_page_bit_common().
+	 */
+	smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN);
+	wake_up_state(wait->private, mode);
+
+	/*
+	 * Ok, we have successfully done what we're waiting for,
+	 * and we can unconditionally remove the wait entry.
+	 *
+	 * Note that this pairs with the "finish_wait()" in the
+	 * waiter, and has to be the absolute last thing we do.
+	 * After this list_del_init(&wait->entry) the wait entry
+	 * might be de-allocated and the process might even have
+	 * exited.
+	 */
+	list_del_init_careful(&wait->entry);
+	return (flags & WQ_FLAG_EXCLUSIVE) != 0;
 }
 
 static void wake_up_page_bit(struct page *page, int bit_nr)
@@ -1147,16 +1209,35 @@ enum behavior {
 			 */
 };
 
+/*
+ * Attempt to check (or get) the page bit, and mark us done
+ * if successful.
+ */
+static inline bool trylock_page_bit_common(struct page *page, int bit_nr,
+					struct wait_queue_entry *wait)
+{
+	if (wait->flags & WQ_FLAG_EXCLUSIVE) {
+		if (test_and_set_bit(bit_nr, &page->flags))
+			return false;
+	} else if (test_bit(bit_nr, &page->flags))
+		return false;
+
+	wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE;
+	return true;
+}
+
+/* How many times do we accept lock stealing from under a waiter? */
+int sysctl_page_lock_unfairness = 5;
+
 static inline int wait_on_page_bit_common(wait_queue_head_t *q,
 	struct page *page, int bit_nr, int state, enum behavior behavior)
 {
+	int unfairness = sysctl_page_lock_unfairness;
 	struct wait_page_queue wait_page;
 	wait_queue_entry_t *wait = &wait_page.wait;
-	bool bit_is_set;
 	bool thrashing = false;
 	bool delayacct = false;
 	unsigned long pflags;
-	int ret = 0;
 
 	if (bit_nr == PG_locked &&
 	    !PageUptodate(page) && PageWorkingset(page)) {
@@ -1169,55 +1250,97 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
 	}
 
 	init_wait(wait);
-	wait->flags = behavior == EXCLUSIVE ? WQ_FLAG_EXCLUSIVE : 0;
 	wait->func = wake_page_function;
 	wait_page.page = page;
 	wait_page.bit_nr = bit_nr;
 
-	for (;;) {
-		spin_lock_irq(&q->lock);
-
-		if (likely(list_empty(&wait->entry))) {
-			__add_wait_queue_entry_tail(q, wait);
-			SetPageWaiters(page);
-		}
+repeat:
+	wait->flags = 0;
+	if (behavior == EXCLUSIVE) {
+		wait->flags = WQ_FLAG_EXCLUSIVE;
+		if (--unfairness < 0)
+			wait->flags |= WQ_FLAG_CUSTOM;
+	}
 
-		set_current_state(state);
+	/*
+	 * Do one last check whether we can get the
+	 * page bit synchronously.
+	 *
+	 * Do the SetPageWaiters() marking before that
+	 * to let any waker we _just_ missed know they
+	 * need to wake us up (otherwise they'll never
+	 * even go to the slow case that looks at the
+	 * page queue), and add ourselves to the wait
+	 * queue if we need to sleep.
+	 *
+	 * This part needs to be done under the queue
+	 * lock to avoid races.
+	 */
+	spin_lock_irq(&q->lock);
+	SetPageWaiters(page);
+	if (!trylock_page_bit_common(page, bit_nr, wait))
+		__add_wait_queue_entry_tail(q, wait);
+	spin_unlock_irq(&q->lock);
 
-		spin_unlock_irq(&q->lock);
+	/*
+	 * From now on, all the logic will be based on
+	 * the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to
+	 * see whether the page bit testing has already
+	 * been done by the wake function.
+	 *
+	 * We can drop our reference to the page.
+	 */
+	if (behavior == DROP)
+		put_page(page);
 
-		bit_is_set = test_bit(bit_nr, &page->flags);
-		if (behavior == DROP)
-			put_page(page);
+	/*
+	 * Note that until the "finish_wait()", or until
+	 * we see the WQ_FLAG_WOKEN flag, we need to
+	 * be very careful with the 'wait->flags', because
+	 * we may race with a waker that sets them.
+	 */
+	for (;;) {
+		unsigned int flags;
 
-		if (likely(bit_is_set))
-			io_schedule();
+		set_current_state(state);
 
-		if (behavior == EXCLUSIVE) {
-			if (!test_and_set_bit_lock(bit_nr, &page->flags))
-				break;
-		} else if (behavior == SHARED) {
-			if (!test_bit(bit_nr, &page->flags))
+		/* Loop until we've been woken or interrupted */
+		flags = smp_load_acquire(&wait->flags);
+		if (!(flags & WQ_FLAG_WOKEN)) {
+			if (signal_pending_state(state, current))
 				break;
+
+			io_schedule();
+			continue;
 		}
 
-		if (signal_pending_state(state, current)) {
-			ret = -EINTR;
+		/* If we were non-exclusive, we're done */
+		if (behavior != EXCLUSIVE)
 			break;
-		}
 
-		if (behavior == DROP) {
-			/*
-			 * We can no longer safely access page->flags:
-			 * even if CONFIG_MEMORY_HOTREMOVE is not enabled,
-			 * there is a risk of waiting forever on a page reused
-			 * for something that keeps it locked indefinitely.
-			 * But best check for -EINTR above before breaking.
-			 */
+		/* If the waker got the lock for us, we're done */
+		if (flags & WQ_FLAG_DONE)
 			break;
-		}
+
+		/*
+		 * Otherwise, if we're getting the lock, we need to
+		 * try to get it ourselves.
+		 *
+		 * And if that fails, we'll have to retry this all.
+		 */
+		if (unlikely(test_and_set_bit(bit_nr, &page->flags)))
+			goto repeat;
+
+		wait->flags |= WQ_FLAG_DONE;
+		break;
 	}
 
+	/*
+	 * If a signal happened, this 'finish_wait()' may remove the last
+	 * waiter from the wait-queues, but the PageWaiters bit will remain
+	 * set. That's ok. The next wakeup will take care of it, and trying
+	 * to do it here would be difficult and prone to races.
+	 */
 	finish_wait(q, wait);
 
 	if (thrashing) {
@@ -1227,14 +1350,22 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
 	}
 
 	/*
-	 * A signal could leave PageWaiters set. Clearing it here if
-	 * !waitqueue_active would be possible (by open-coding finish_wait),
-	 * but still fail to catch it in the case of wait hash collision. We
-	 * already can fail to clear wait hash collision cases, so don't
-	 * bother with signals either.
+	 * NOTE! The wait->flags weren't stable until we've done the
+	 * 'finish_wait()', and we could have exited the loop above due
+	 * to a signal, and had a wakeup event happen after the signal
+	 * test but before the 'finish_wait()'.
+	 *
+	 * So only after the finish_wait() can we reliably determine
+	 * if we got woken up or not, so we can now figure out the final
+	 * return value based on that state without races.
+	 *
+	 * Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive
+	 * waiter, but an exclusive one requires WQ_FLAG_DONE.
 	 */
+	if (behavior == EXCLUSIVE)
+		return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR;
 
-	return ret;
+	return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR;
 }
 
 void wait_on_page_bit(struct page *page, int bit_nr)
@@ -1355,11 +1486,19 @@ void end_page_writeback(struct page *page)
 		rotate_reclaimable_page(page);
 	}
 
+	/*
+	 * Writeback does not hold a page reference of its own, relying
+	 * on truncation to wait for the clearing of PG_writeback.
+	 * But here we must make sure that the page is not freed and
+	 * reused before the wake_up_page().
+	 */
+	get_page(page);
 	if (!test_clear_page_writeback(page))
 		BUG();
 
 	smp_mb__after_atomic();
 	wake_up_page(page, PG_writeback);
+	put_page(page);
 }
 EXPORT_SYMBOL(end_page_writeback);
 
@@ -3281,7 +3420,7 @@ ssize_t generic_perform_write(struct file *file,
 		unsigned long offset;	/* Offset into pagecache page */
 		unsigned long bytes;	/* Bytes to write to page */
 		size_t copied;		/* Bytes copied from user */
-		void *fsdata;
+		void *fsdata = NULL;
 
 		offset = (pos & (PAGE_SIZE - 1));
 		bytes = min_t(unsigned long, PAGE_SIZE - offset,