summaryrefslogtreecommitdiffstats
path: root/fs/btrfs/ordered-data.c
diff options
context:
space:
mode:
authorJosef Bacik <jbacik@fb.com>2014-11-21 20:52:38 +0100
committerChris Mason <clm@fb.com>2014-11-21 20:58:32 +0100
commit50d9aa99bd35c77200e0e3dd7a72274f8304701f (patch)
tree346a80fdf2343a5c5e010b57b0213c989eed4ac8 /fs/btrfs/ordered-data.c
parentBtrfs: make sure we wait on logged extents when fsycning two subvols (diff)
downloadlinux-50d9aa99bd35c77200e0e3dd7a72274f8304701f.tar.xz
linux-50d9aa99bd35c77200e0e3dd7a72274f8304701f.zip
Btrfs: make sure logged extents complete in the current transaction V3
Liu Bo pointed out that my previous fix would lose the generation update in the scenario I described. It is actually much worse than that, we could lose the entire extent if we lose power right after the transaction commits. Consider the following write extent 0-4k log extent in log tree commit transaction < power fail happens here ordered extent completes We would lose the 0-4k extent because it hasn't updated the actual fs tree, and the transaction commit will reset the log so it isn't replayed. If we lose power before the transaction commit we are save, otherwise we are not. Fix this by keeping track of all extents we logged in this transaction. Then when we go to commit the transaction make sure we wait for all of those ordered extents to complete before proceeding. This will make sure that if we lose power after the transaction commit we still have our data. This also fixes the problem of the improperly updated extent generation. Thanks, cc: stable@vger.kernel.org Signed-off-by: Josef Bacik <jbacik@fb.com> Signed-off-by: Chris Mason <clm@fb.com>
Diffstat (limited to 'fs/btrfs/ordered-data.c')
-rw-r--r--fs/btrfs/ordered-data.c9
1 files changed, 7 insertions, 2 deletions
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 1401b1af4f06..9c28eb4da4dd 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -220,6 +220,7 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
INIT_LIST_HEAD(&entry->work_list);
init_completion(&entry->completion);
INIT_LIST_HEAD(&entry->log_list);
+ INIT_LIST_HEAD(&entry->trans_list);
trace_btrfs_ordered_extent_add(inode, entry);
@@ -443,6 +444,8 @@ void btrfs_get_logged_extents(struct inode *inode,
ordered = rb_entry(n, struct btrfs_ordered_extent, rb_node);
if (!list_empty(&ordered->log_list))
continue;
+ if (test_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
+ continue;
list_add_tail(&ordered->log_list, logged_list);
atomic_inc(&ordered->refs);
}
@@ -472,7 +475,8 @@ void btrfs_submit_logged_extents(struct list_head *logged_list,
spin_unlock_irq(&log->log_extents_lock[index]);
}
-void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid)
+void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans,
+ struct btrfs_root *log, u64 transid)
{
struct btrfs_ordered_extent *ordered;
int index = transid % 2;
@@ -497,7 +501,8 @@ void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid)
wait_event(ordered->wait, test_bit(BTRFS_ORDERED_IO_DONE,
&ordered->flags));
- btrfs_put_ordered_extent(ordered);
+ if (!test_and_set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
+ list_add_tail(&ordered->trans_list, &trans->ordered);
spin_lock_irq(&log->log_extents_lock[index]);
}
spin_unlock_irq(&log->log_extents_lock[index]);