summaryrefslogtreecommitdiff
path: root/fs/ext3
diff options
context:
space:
mode:
authorChris Mason <chris.mason@oracle.com>2009-09-08 00:22:14 +0200
committerJan Kara <jack@suse.cz>2009-09-16 17:44:11 +0200
commit4f003fd32bc54ec438b8691795279844df27ce38 (patch)
tree2fe0a97307f9b3fe481f07713a271630951eb51b /fs/ext3
parent00171d3c7e3b738ba582c7a9b37408e796f49046 (diff)
ext3: Add locking to ext3_do_update_inode
I've been struggling with this off and on while I've been testing the data=guarded work. The symptom is corrupted orphan lists and inodes with the wrong i_size stored on disk. I was convinced the data=guarded code was just missing a call to ext3_mark_inode_dirty, but tracing showed the i_disksize I was sending to ext3_mark_inode_dirty wasn't actually making it to the drive. ext3_mark_inode_dirty can be called without locks held (atime updates and a few others), so the data=guarded code uses locks while updating the in-memory inode, and then calls ext3_mark_inode_dirty without any locks held. But, ext3_mark_inode_dirty has no internal locking to make sure that only one CPU is updating the buffer head at a time. Generally this works out ok because everyone that changes the inode then calls ext3_mark_inode_dirty themselves. Even though it races, eventually someone updates the buffer heads and things move on. But there is still a risk of the wrong values getting in, and the data=guarded code seems to hit the race very often. Since everyone that changes the inode also logs it, it should be possible to fix this with some memory barriers. I'll leave that as an exercise to the reader and lock the buffer head instead. It it probably a good idea to have a different patch series for lockless bit flipping on the ext3 i_state field. ext3_do_update_inode &= clears EXT3_STATE_NEW without any locks held. Signed-off-by: Chris Mason <chris.mason@oracle.com> Signed-off-by: Jan Kara <jack@suse.cz>
Diffstat (limited to 'fs/ext3')
-rw-r--r--fs/ext3/inode.c9
1 files changed, 9 insertions, 0 deletions
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index eb0b4e0d517..cd098a7b77f 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -2903,6 +2903,10 @@ static int ext3_do_update_inode(handle_t *handle,
struct buffer_head *bh = iloc->bh;
int err = 0, rc, block;
+again:
+ /* we can't allow multiple procs in here at once, its a bit racey */
+ lock_buffer(bh);
+
/* For fields not not tracking in the in-memory inode,
* initialise them to zero for new inodes. */
if (ei->i_state & EXT3_STATE_NEW)
@@ -2962,16 +2966,20 @@ static int ext3_do_update_inode(handle_t *handle,
/* If this is the first large file
* created, add a flag to the superblock.
*/
+ unlock_buffer(bh);
err = ext3_journal_get_write_access(handle,
EXT3_SB(sb)->s_sbh);
if (err)
goto out_brelse;
+
ext3_update_dynamic_rev(sb);
EXT3_SET_RO_COMPAT_FEATURE(sb,
EXT3_FEATURE_RO_COMPAT_LARGE_FILE);
handle->h_sync = 1;
err = ext3_journal_dirty_metadata(handle,
EXT3_SB(sb)->s_sbh);
+ /* get our lock and start over */
+ goto again;
}
}
}
@@ -2994,6 +3002,7 @@ static int ext3_do_update_inode(handle_t *handle,
raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize);
BUFFER_TRACE(bh, "call ext3_journal_dirty_metadata");
+ unlock_buffer(bh);
rc = ext3_journal_dirty_metadata(handle, bh);
if (!err)
err = rc;