Btrfs: extent_map and data=ordered fixes for space balancing
* Add an EXTENT_BOUNDARY state bit to keep the writepage code
from merging data extents that are in the process of being
relocated. This allows us to do accounting for them properly.
* The balancing code relocates data extents indepdent of the underlying
inode. The extent_map code was modified to properly account for
things moving around (invalidating extent_map caches in the inode).
* Don't take the drop_mutex in the create_subvol ioctl. It isn't
required.
* Fix walking of the ordered extent list to avoid races with sys_unlink
* Change the lock ordering rules. Transaction start goes outside
the drop_mutex. This allows btrfs_commit_transaction to directly
drop the relocation trees.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index da6d43e..951eacf 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -309,7 +309,6 @@
{
struct list_head splice;
struct list_head *cur;
- struct list_head *tmp;
struct btrfs_ordered_extent *ordered;
struct inode *inode;
@@ -317,37 +316,38 @@
spin_lock(&root->fs_info->ordered_extent_lock);
list_splice_init(&root->fs_info->ordered_extents, &splice);
- list_for_each_safe(cur, tmp, &splice) {
+ while (!list_empty(&splice)) {
cur = splice.next;
ordered = list_entry(cur, struct btrfs_ordered_extent,
root_extent_list);
if (nocow_only &&
!test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags)) {
+ list_move(&ordered->root_extent_list,
+ &root->fs_info->ordered_extents);
cond_resched_lock(&root->fs_info->ordered_extent_lock);
continue;
}
list_del_init(&ordered->root_extent_list);
atomic_inc(&ordered->refs);
- inode = ordered->inode;
/*
- * the inode can't go away until all the pages are gone
- * and the pages won't go away while there is still
- * an ordered extent and the ordered extent won't go
- * away until it is off this list. So, we can safely
- * increment i_count here and call iput later
+ * the inode may be getting freed (in sys_unlink path).
*/
- atomic_inc(&inode->i_count);
+ inode = igrab(ordered->inode);
+
spin_unlock(&root->fs_info->ordered_extent_lock);
- btrfs_start_ordered_extent(inode, ordered, 1);
- btrfs_put_ordered_extent(ordered);
- iput(inode);
+ if (inode) {
+ btrfs_start_ordered_extent(inode, ordered, 1);
+ btrfs_put_ordered_extent(ordered);
+ iput(inode);
+ } else {
+ btrfs_put_ordered_extent(ordered);
+ }
spin_lock(&root->fs_info->ordered_extent_lock);
}
- list_splice_init(&splice, &root->fs_info->ordered_extents);
spin_unlock(&root->fs_info->ordered_extent_lock);
return 0;
}