summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorQu Wenruo <wqu@suse.com>2021-03-03 18:41:52 +0800
committerDavid Sterba <dsterba@suse.com>2021-03-15 16:57:15 +0100
commita3ee79bd8fe17812d2305ccc4bf81bfeab395576 (patch)
tree51af6072e995014ef553aaa187008af9e22927e1
parentfbf48bb0b197e6894a04c714728c952af7153bf3 (diff)
downloadlinux-a3ee79bd8fe17812d2305ccc4bf81bfeab395576.tar.bz2
btrfs: fix qgroup data rsv leak caused by falloc failure
[BUG] When running fsstress with only falloc workload, and a very low qgroup limit set, we can get qgroup data rsv leak at unmount time. BTRFS warning (device dm-0): qgroup 0/5 has unreleased space, type 0 rsv 20480 BTRFS error (device dm-0): qgroup reserved space leaked The minimal reproducer looks like: #!/bin/bash dev=/dev/test/test mnt="/mnt/btrfs" fsstress=~/xfstests-dev/ltp/fsstress runtime=8 workload() { umount $dev &> /dev/null umount $mnt &> /dev/null mkfs.btrfs -f $dev > /dev/null mount $dev $mnt btrfs quota en $mnt btrfs quota rescan -w $mnt btrfs qgroup limit 16m 0/5 $mnt $fsstress -w -z -f creat=10 -f fallocate=10 -p 2 -n 100 \ -d $mnt -v > /tmp/fsstress umount $mnt if dmesg | grep leak ; then echo "!!! FAILED !!!" exit 1 fi } for (( i=0; i < $runtime; i++)); do echo "=== $i/$runtime===" workload done Normally it would fail before round 4. [CAUSE] In function insert_prealloc_file_extent(), we first call btrfs_qgroup_release_data() to know how many bytes are reserved for qgroup data rsv. Then use that @qgroup_released number to continue our work. But after we call btrfs_qgroup_release_data(), we should either queue @qgroup_released to delayed ref or free them manually in error path. Unfortunately, we lack the error handling to free the released bytes, leaking qgroup data rsv. All the error handling function outside won't help at all, as we have released the range, meaning in inode io tree, the EXTENT_QGROUP_RESERVED bit is already cleared, thus all btrfs_qgroup_free_data() call won't free any data rsv. [FIX] Add free_qgroup tag to manually free the released qgroup data rsv. Reported-by: Nikolay Borisov <nborisov@suse.com> Reported-by: David Sterba <dsterba@suse.cz> Fixes: 9729f10a608f ("btrfs: inode: move qgroup reserved space release to the callers of insert_reserved_file_extent()") CC: stable@vger.kernel.org # 5.10+ Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
-rw-r--r--fs/btrfs/inode.c24
1 files changed, 19 insertions, 5 deletions
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 77182be403c5..ea5ede619220 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -9895,7 +9895,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
file_offset, &stack_fi,
true, qgroup_released);
if (ret)
- return ERR_PTR(ret);
+ goto free_qgroup;
return trans;
}
@@ -9910,17 +9910,31 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
extent_info.insertions = 0;
path = btrfs_alloc_path();
- if (!path)
- return ERR_PTR(-ENOMEM);
+ if (!path) {
+ ret = -ENOMEM;
+ goto free_qgroup;
+ }
ret = btrfs_replace_file_extents(&inode->vfs_inode, path, file_offset,
file_offset + len - 1, &extent_info,
&trans);
btrfs_free_path(path);
if (ret)
- return ERR_PTR(ret);
-
+ goto free_qgroup;
return trans;
+
+free_qgroup:
+ /*
+ * We have released qgroup data range at the beginning of the function,
+ * and normally qgroup_released bytes will be freed when committing
+ * transaction.
+ * But if we error out early, we have to free what we have released
+ * or we leak qgroup data reservation.
+ */
+ btrfs_qgroup_free_refroot(inode->root->fs_info,
+ inode->root->root_key.objectid, qgroup_released,
+ BTRFS_QGROUP_RSV_DATA);
+ return ERR_PTR(ret);
}
static int __btrfs_prealloc_file_range(struct inode *inode, int mode,