arch/x86/include/asm/bitops.h | 13 +++++++++++++
 include/linux/page-flags.h    |  2 +-
 mm/filemap.c                  | 36 +++++++++++++++++++++++++++++++-----
 3 files changed, 45 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 68557f52b961..854022772c5b 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -139,6 +139,19 @@ static __always_inline void __clear_bit(long nr, volatile unsigned long *addr)
 	asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
 }
 
+static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
+{
+	bool negative;
+	asm volatile(LOCK_PREFIX "andb %2,%1\n\t"
+		CC_SET(s)
+		: CC_OUT(s) (negative), ADDR
+		: "ir" ((char) ~(1 << nr)) : "memory");
+	return negative;
+}
+
+// Let everybody know we have it
+#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte
+
 /*
  * __clear_bit_unlock - Clears a bit in memory
  * @nr: Bit to clear
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index c56b39890a41..6b5818d6de32 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -73,13 +73,13 @@
  */
 enum pageflags {
 	PG_locked,		/* Page is locked. Don't touch. */
-	PG_waiters,		/* Page has waiters, check its waitqueue */
 	PG_error,
 	PG_referenced,
 	PG_uptodate,
 	PG_dirty,
 	PG_lru,
 	PG_active,
+	PG_waiters,		/* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */
 	PG_slab,
 	PG_owner_priv_1,	/* Owner use. If pagecache, fs may use*/
 	PG_arch_1,
diff --git a/mm/filemap.c b/mm/filemap.c
index 82f26cde830c..6b1d96f86a9c 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -912,6 +912,29 @@ void add_page_wait_queue(struct page *page, wait_queue_t *waiter)
 }
 EXPORT_SYMBOL_GPL(add_page_wait_queue);
 
+#ifndef clear_bit_unlock_is_negative_byte
+
+/*
+ * PG_waiters is the high bit in the same byte as PG_lock.
+ *
+ * On x86 (and on many other architectures), we can clear PG_lock and
+ * test the sign bit at the same time. But if the architecture does
+ * not support that special operation, we just do this all by hand
+ * instead.
+ *
+ * The read of PG_waiters has to be after (or concurrently with) PG_locked
+ * being cleared, but a memory barrier should be unneccssary since it is
+ * in the same byte as PG_locked.
+ */
+static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem)
+{
+	clear_bit_unlock(nr, mem);
+	/* smp_mb__after_atomic(); */
+	return test_bit(PG_waiters);
+}
+
+#endif
+
 /**
  * unlock_page - unlock a locked page
  * @page: the page
@@ -921,16 +944,19 @@ EXPORT_SYMBOL_GPL(add_page_wait_queue);
  * mechanism between PageLocked pages and PageWriteback pages is shared.
  * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
  *
- * The mb is necessary to enforce ordering between the clear_bit and the read
- * of the waitqueue (to avoid SMP races with a parallel wait_on_page_locked()).
+ * Note that this depends on PG_waiters being the sign bit in the byte
+ * that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to
+ * clear the PG_locked bit and test PG_waiters at the same time fairly
+ * portably (architectures that do LL/SC can test any bit, while x86 can
+ * test the sign bit).
  */
 void unlock_page(struct page *page)
 {
+	BUILD_BUG_ON(PG_waiters != 7);
 	page = compound_head(page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
-	clear_bit_unlock(PG_locked, &page->flags);
-	smp_mb__after_atomic();
-	wake_up_page(page, PG_locked);
+	if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags))
+		wake_up_page_bit(page, PG_locked);
 }
 EXPORT_SYMBOL(unlock_page);