[PATCH] resierfs: fix reiserfs_invalidatepage race against data=ordered

After a transaction has closed but before it has finished commit, there is
a window where data=ordered mode requires invalidatepage to pin pages
instead of freeing them.  This patch fixes a race between the
invalidatepage checks and data=ordered writeback, and it also adds a check
to the reiserfs write_ordered_buffers routines to write any anonymous
buffers that were dirtied after its first writeback loop.

That bug works like this:

proc1: transaction closes and a new one starts
proc1: write_ordered_buffers starts processing data=ordered list
proc1: buffer A is cleaned and written
proc2: buffer A is dirtied by another process
proc2: File is truncated to zero, page A goes through invalidatepage
proc2: reiserfs_invalidatepage sees dirty buffer A with reiserfs
       journal head, pins it
proc1: write_ordered_buffers frees the journal head on buffer A

At this point, buffer A stays dirty forever

Signed-off-by: Chris Mason <mason@suse.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 16 insertions, 1 deletions

diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index ffa34b861bd..60e2f234470 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -2743,6 +2743,7 @@ static int invalidatepage_can_drop(struct inode *inode, struct buffer_head *bh)
         int ret = 1;
         struct reiserfs_journal *j = SB_JOURNAL(inode->i_sb);
 
+        lock_buffer(bh);
         spin_lock(&j->j_dirty_buffers_lock);
         if (!buffer_mapped(bh)) {
                 goto free_jh;
@@ -2758,7 +2759,7 @@ static int invalidatepage_can_drop(struct inode *inode, struct buffer_head *bh)
                 if (buffer_journaled(bh) || buffer_journal_dirty(bh)) {
                         ret = 0;
                 }
-        } else if (buffer_dirty(bh) || buffer_locked(bh)) {
+        } else  if (buffer_dirty(bh)) {
                 struct reiserfs_journal_list *jl;
                 struct reiserfs_jh *jh = bh->b_private;
 
@@ -2784,6 +2785,7 @@ static int invalidatepage_can_drop(struct inode *inode, struct buffer_head *bh)
                 reiserfs_free_jh(bh);
         }
         spin_unlock(&j->j_dirty_buffers_lock);
+        unlock_buffer(bh);
         return ret;
 }
 
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 2d04efb22ee..bc8fe963b3c 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -877,6 +877,19 @@ static int write_ordered_buffers(spinlock_t * lock,
                 if (!buffer_uptodate(bh)) {
                         ret = -EIO;
                 }
+                /* ugly interaction with invalidatepage here.
+                 * reiserfs_invalidate_page will pin any buffer that has a valid
+                 * journal head from an older transaction.  If someone else sets
+                 * our buffer dirty after we write it in the first loop, and
+                 * then someone truncates the page away, nobody will ever write
+                 * the buffer. We're safe if we write the page one last time
+                 * after freeing the journal header.
+                 */
+                if (buffer_dirty(bh) && unlikely(bh->b_page->mapping == NULL)) {
+                        spin_unlock(lock);
+                        ll_rw_block(WRITE, 1, &bh);
+                        spin_lock(lock);
+                }
                 put_bh(bh);
                 cond_resched_lock(lock);
         }