1 files changed, 37 insertions, 40 deletions

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 237107c1b084..1d2fc89ca56d 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -845,38 +845,6 @@ int set_page_dirty_lock(struct page *page)
 EXPORT_SYMBOL(set_page_dirty_lock);
 
 /*
- * Clear a page's dirty flag, while caring for dirty memory accounting. 
- * Returns true if the page was previously dirty.
- */
-int test_clear_page_dirty(struct page *page)
-{
-        struct address_space *mapping = page_mapping(page);
-        unsigned long flags;
-
-        if (!mapping)
-                return TestClearPageDirty(page);
-
-        write_lock_irqsave(&mapping->tree_lock, flags);
-        if (TestClearPageDirty(page)) {
-                radix_tree_tag_clear(&mapping->page_tree,
-                                page_index(page), PAGECACHE_TAG_DIRTY);
-                write_unlock_irqrestore(&mapping->tree_lock, flags);
-                /*
-                 * We can continue to use `mapping' here because the
-                 * page is locked, which pins the address_space
-                 */
-                if (mapping_cap_account_dirty(mapping)) {
-                        page_mkclean(page);
-                        dec_zone_page_state(page, NR_FILE_DIRTY);
-                }
-                return 1;
-        }
-        write_unlock_irqrestore(&mapping->tree_lock, flags);
-        return 0;
-}
-EXPORT_SYMBOL(test_clear_page_dirty);
-
-/*
  * Clear a page's dirty flag, while caring for dirty memory accounting.
  * Returns true if the page was previously dirty.
  *
@@ -894,17 +862,46 @@ int clear_page_dirty_for_io(struct page *page)
 {
         struct address_space *mapping = page_mapping(page);
 
-        if (!mapping)
-                return TestClearPageDirty(page);
-
-        if (TestClearPageDirty(page)) {
-                if (mapping_cap_account_dirty(mapping)) {
-                        page_mkclean(page);
+        if (mapping && mapping_cap_account_dirty(mapping)) {
+                /*
+                 * Yes, Virginia, this is indeed insane.
+                 *
+                 * We use this sequence to make sure that
+                 *  (a) we account for dirty stats properly
+                 *  (b) we tell the low-level filesystem to
+                 *      mark the whole page dirty if it was
+                 *      dirty in a pagetable. Only to then
+                 *  (c) clean the page again and return 1 to
+                 *      cause the writeback.
+                 *
+                 * This way we avoid all nasty races with the
+                 * dirty bit in multiple places and clearing
+                 * them concurrently from different threads.
+                 *
+                 * Note! Normally the "set_page_dirty(page)"
+                 * has no effect on the actual dirty bit - since
+                 * that will already usually be set. But we
+                 * need the side effects, and it can help us
+                 * avoid races.
+                 *
+                 * We basically use the page "master dirty bit"
+                 * as a serialization point for all the different
+                 * threads doing their things.
+                 *
+                 * FIXME! We still have a race here: if somebody
+                 * adds the page back to the page tables in
+                 * between the "page_mkclean()" and the "TestClearPageDirty()",
+                 * we might have it mapped without the dirty bit set.
+                 */
+                if (page_mkclean(page))
+                        set_page_dirty(page);
+                if (TestClearPageDirty(page)) {
                         dec_zone_page_state(page, NR_FILE_DIRTY);
+                        return 1;
                 }
-                return 1;
+                return 0;
         }
-        return 0;
+        return TestClearPageDirty(page);
 }
 EXPORT_SYMBOL(clear_page_dirty_for_io);