writeback: fix a subtle race condition in I_DIRTY clearing

[pandora-kernel.git] / fs / fs-writeback.c

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e494c7b..7286eb4 100644 (file)
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -418,12 +418,28 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
         * write_inode()
         */
        spin_lock(&inode->i_lock);
-       /* Clear I_DIRTY_PAGES if we've written out all dirty pages */
-       if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
-               inode->i_state &= ~I_DIRTY_PAGES;
+
        dirty = inode->i_state & I_DIRTY;
-       inode->i_state &= ~(I_DIRTY_SYNC | I_DIRTY_DATASYNC);
+       inode->i_state &= ~I_DIRTY;
+
+       /*
+        * Paired with smp_mb() in __mark_inode_dirty().  This allows
+        * __mark_inode_dirty() to test i_state without grabbing i_lock -
+        * either they see the I_DIRTY bits cleared or we see the dirtied
+        * inode.
+        *
+        * I_DIRTY_PAGES is always cleared together above even if @mapping
+        * still has dirty pages.  The flag is reinstated after smp_mb() if
+        * necessary.  This guarantees that either __mark_inode_dirty()
+        * sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY.
+        */
+       smp_mb();
+
+       if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
+               inode->i_state |= I_DIRTY_PAGES;
+
        spin_unlock(&inode->i_lock);
+
        /* Don't write the inode if only I_DIRTY_PAGES was set */
        if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
                int err = write_inode(inode, wbc);
@@ -1065,12 +1081,11 @@ void __mark_inode_dirty(struct inode *inode, int flags)
        }
 
        /*
-        * make sure that changes are seen by all cpus before we test i_state
-        * -- mikulas
+        * Paired with smp_mb() in __writeback_single_inode() for the
+        * following lockless i_state test.  See there for details.
         */
        smp_mb();
 
-       /* avoid the locking if we can */
        if ((inode->i_state & flags) == flags)
                return;