Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

[mirror_ubuntu-zesty-kernel.git] / mm / filemap.c

diff --git a/mm/filemap.c b/mm/filemap.c
index 82f26cde830c4b70df30cfa47c7e21dbe6d05a7f..b772a33ef640ab0d6770bb3d249a6fe6f16eeebc 100644 (file)
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -138,7 +138,7 @@ static int page_cache_tree_insert(struct address_space *mapping,
                                dax_radix_locked_entry(0, RADIX_DAX_EMPTY));
                        /* Wakeup waiters for exceptional entry lock */
                        dax_wake_mapping_entry_waiter(mapping, page->index, p,
-                                                     false);
+                                                     true);
                }
        }
        __radix_tree_replace(&mapping->page_tree, node, slot, page,
@@ -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, mem);
+}
+
+#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);