From df8d116ffa379f3ef09d7ff28da0f0c921cc9fa1 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 14 Jan 2015 01:52:25 +0000 Subject: Btrfs: fix fsync log replay for inodes with a mix of regular refs and extrefs If we have an inode with a large number of hard links, some of which may be extrefs, turn a regular ref into an extref, fsync the inode and then replay the fsync log (after a crash/reboot), we can endup with an fsync log that makes the replay code always fail with -EOVERFLOW when processing the inode's references. This is easy to reproduce with the test case I made for xfstests. Its steps are the following: _scratch_mkfs "-O extref" >> $seqres.full 2>&1 _init_flakey _mount_flakey # Create a test file with 3001 hard links. This number is large enough to # make btrfs start using extrefs at some point even if the fs has the maximum # possible leaf/node size (64Kb). echo "hello world" > $SCRATCH_MNT/foo for i in `seq 1 3000`; do ln $SCRATCH_MNT/foo $SCRATCH_MNT/foo_link_`printf "%04d" $i` done # Make sure all metadata and data are durably persisted. sync # Now remove one link, add a new one with a new name, add another new one with # the same name as the one we just removed and fsync the inode. rm -f $SCRATCH_MNT/foo_link_0001 ln $SCRATCH_MNT/foo $SCRATCH_MNT/foo_link_3001 ln $SCRATCH_MNT/foo $SCRATCH_MNT/foo_link_0001 rm -f $SCRATCH_MNT/foo_link_0002 ln $SCRATCH_MNT/foo $SCRATCH_MNT/foo_link_3002 ln $SCRATCH_MNT/foo $SCRATCH_MNT/foo_link_3003 $XFS_IO_PROG -c "fsync" $SCRATCH_MNT/foo # Simulate a crash/power loss. This makes sure the next mount # will see an fsync log and will replay that log. _load_flakey_table $FLAKEY_DROP_WRITES _unmount_flakey _load_flakey_table $FLAKEY_ALLOW_WRITES _mount_flakey # Check that the number of hard links is correct, we are able to remove all # the hard links and read the file's data. This is just to verify we don't # get stale file handle errors (due to dangling directory index entries that # point to inodes that no longer exist). echo "Link count: $(stat --format=%h $SCRATCH_MNT/foo)" [ -f $SCRATCH_MNT/foo ] || echo "Link foo is missing" for ((i = 1; i <= 3003; i++)); do name=foo_link_`printf "%04d" $i` if [ $i -eq 2 ]; then [ -f $SCRATCH_MNT/$name ] && echo "Link $name found" else [ -f $SCRATCH_MNT/$name ] || echo "Link $name is missing" fi done rm -f $SCRATCH_MNT/foo_link_* cat $SCRATCH_MNT/foo rm -f $SCRATCH_MNT/foo status=0 exit The fix is simply to correct the overflow condition when overwriting a reference item because it was wrong, trying to increase the item in the fs/subvol tree by an impossible amount. Also ensure that we don't insert one normal ref and one ext ref for the same dentry - this happened because processing a dir index entry from the parent in the log happened when the normal ref item was full, which made the logic insert an extref and later when the normal ref had enough room, it would be inserted again when processing the ref item from the child inode in the log. This issue has been present since the introduction of the extrefs feature (2012). A test case for xfstests follows soon. This test only passes if the previous patch titled "Btrfs: fix fsync when extend references are added to an inode" is applied too. Signed-off-by: Filipe Manana Signed-off-by: Chris Mason diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c index 8ffa478..265e03c 100644 --- a/fs/btrfs/inode-item.c +++ b/fs/btrfs/inode-item.c @@ -344,6 +344,7 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans, return -ENOMEM; path->leave_spinning = 1; + path->skip_release_on_error = 1; ret = btrfs_insert_empty_item(trans, root, path, &key, ins_len); if (ret == -EEXIST) { @@ -362,8 +363,12 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans, ptr = (unsigned long)(ref + 1); ret = 0; } else if (ret < 0) { - if (ret == -EOVERFLOW) - ret = -EMLINK; + if (ret == -EOVERFLOW) { + if (find_name_in_backref(path, name, name_len, &ref)) + ret = -EEXIST; + else + ret = -EMLINK; + } goto out; } else { ref = btrfs_item_ptr(path->nodes[0], path->slots[0], diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 533cdb0..a266587 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -453,11 +453,13 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans, insert: btrfs_release_path(path); /* try to insert the key into the destination tree */ + path->skip_release_on_error = 1; ret = btrfs_insert_empty_item(trans, root, path, key, item_size); + path->skip_release_on_error = 0; /* make sure any existing item is the correct size */ - if (ret == -EEXIST) { + if (ret == -EEXIST || ret == -EOVERFLOW) { u32 found_size; found_size = btrfs_item_size_nr(path->nodes[0], path->slots[0]); @@ -844,7 +846,7 @@ out: static noinline int backref_in_log(struct btrfs_root *log, struct btrfs_key *key, u64 ref_objectid, - char *name, int namelen) + const char *name, int namelen) { struct btrfs_path *path; struct btrfs_inode_ref *ref; @@ -1556,6 +1558,30 @@ static noinline int insert_one_name(struct btrfs_trans_handle *trans, } /* + * Return true if an inode reference exists in the log for the given name, + * inode and parent inode. + */ +static bool name_in_log_ref(struct btrfs_root *log_root, + const char *name, const int name_len, + const u64 dirid, const u64 ino) +{ + struct btrfs_key search_key; + + search_key.objectid = ino; + search_key.type = BTRFS_INODE_REF_KEY; + search_key.offset = dirid; + if (backref_in_log(log_root, &search_key, dirid, name, name_len)) + return true; + + search_key.type = BTRFS_INODE_EXTREF_KEY; + search_key.offset = btrfs_extref_hash(dirid, name, name_len); + if (backref_in_log(log_root, &search_key, dirid, name, name_len)) + return true; + + return false; +} + +/* * take a single entry in a log directory item and replay it into * the subvolume. * @@ -1665,10 +1691,17 @@ out: return ret; insert: + if (name_in_log_ref(root->log_root, name, name_len, + key->objectid, log_key.objectid)) { + /* The dentry will be added later. */ + ret = 0; + update_size = false; + goto out; + } btrfs_release_path(path); ret = insert_one_name(trans, root, path, key->objectid, key->offset, name, name_len, log_type, &log_key); - if (ret && ret != -ENOENT) + if (ret && ret != -ENOENT && ret != -EEXIST) goto out; update_size = false; ret = 0; -- cgit v0.10.2