Btrfs: fix find_free_dev_extent() malfunction in case device tree has hole

If device tree has hole, find_free_dev_extent() cannot find available
address properly.

The problem can be reproduce by following script.

    mntpath=/btrfs
    loopdev=/dev/loop0
    filepath=/home/forrest/image

    umount $mntpath
    losetup -d $loopdev
    truncate --size 100g $filepath
    losetup $loopdev $filepath
    mkfs.btrfs -f $loopdev
    mount $loopdev $mntpath

    # make device tree with one big hole
    for i in `seq 1 1 100`; do
        fallocate -l 1g $mntpath/$i
    done
    sync
    for i in `seq 1 1 95`; do
        rm $mntpath/$i
    done
    sync

    # wait cleaner thread remove unused block group
    sleep 300

    fallocate -l 1g $mntpath/aaa

    # failed to allocate new chunk
    fallocate -l 1g $mntpath/bbb

Above script will make device tree with one big hole, and can only allocate
just one chunk in a transaction, so failed to allocate new chunk for $mntpath/bbb

    item 8 key (1 DEV_EXTENT 2185232384) itemoff 15859 itemsize 48
        dev extent chunk_tree 3
        chunk objectid 256 chunk offset 106292051968 length 1073741824
    item 9 key (1 DEV_EXTENT 104190705664) itemoff 15811 itemsize 48
        dev extent chunk_tree 3
        chunk objectid 256 chunk offset 103108575232 length 1073741824

Signed-off-by: Forrest Liu <forrestl@synology.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Chris Mason <clm@fb.com>

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 8bcd2a00751785e0a6d41df74a3475e1acd8c455..96aebf3bcd5b37d35604c76ec584d29686ad34e2 100644 (file)
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1058,6 +1058,7 @@ static int contains_pending_extent(struct btrfs_trans_handle *trans,
        struct extent_map *em;
        struct list_head *search_list = &trans->transaction->pending_chunks;
        int ret = 0;
+       u64 physical_start = *start;
 
 again:
        list_for_each_entry(em, search_list, list) {
@@ -1068,9 +1069,9 @@ again:
                for (i = 0; i < map->num_stripes; i++) {
                        if (map->stripes[i].dev != device)
                                continue;
-                       if (map->stripes[i].physical >= *start + len ||
+                       if (map->stripes[i].physical >= physical_start + len ||
                            map->stripes[i].physical + em->orig_block_len <=
-                           *start)
+                           physical_start)
                                continue;
                        *start = map->stripes[i].physical +
                                em->orig_block_len;
@@ -1193,8 +1194,14 @@ again:
                         */
                        if (contains_pending_extent(trans, device,
                                                    &search_start,
-                                                   hole_size))
-                               hole_size = 0;
+                                                   hole_size)) {
+                               if (key.offset >= search_start) {
+                                       hole_size = key.offset - search_start;
+                               } else {
+                                       WARN_ON_ONCE(1);
+                                       hole_size = 0;
+                               }
+                       }
 
                        if (hole_size > max_hole_size) {
                                max_hole_start = search_start;