[PATCH 4.4 117/137] Btrfs: fix file/data loss caused by fsync after rename and new inode

[Greg Kroah-Hartman <gregkh@linuxfoundation.org>]

4.4-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Filipe Manana <fdmanana@suse.com>

commit 56f23fdbb600e6087db7b009775b95ce07cc3195 upstream.

If we rename an inode A (be it a file or a directory), create a new
inode B with the old name of inode A and under the same parent directory,
fsync inode B and then power fail, at log tree replay time we end up
removing inode A completely. If inode A is a directory then all its files
are gone too.

Example scenarios where this happens:
This is reproducible with the following steps, taken from a couple of
test cases written for fstests which are going to be submitted upstream
soon:

   # Scenario 1

   mkfs.btrfs -f /dev/sdc
   mount /dev/sdc /mnt
   mkdir -p /mnt/a/x
   echo "hello" > /mnt/a/x/foo
   echo "world" > /mnt/a/x/bar
   sync
   mv /mnt/a/x /mnt/a/y
   mkdir /mnt/a/x
   xfs_io -c fsync /mnt/a/x
   <power failure happens>

   The next time the fs is mounted, log tree replay happens and
   the directory "y" does not exist nor do the files "foo" and
   "bar" exist anywhere (neither in "y" nor in "x", nor the root
   nor anywhere).

   # Scenario 2

   mkfs.btrfs -f /dev/sdc
   mount /dev/sdc /mnt
   mkdir /mnt/a
   echo "hello" > /mnt/a/foo
   sync
   mv /mnt/a/foo /mnt/a/bar
   echo "world" > /mnt/a/foo
   xfs_io -c fsync /mnt/a/foo
   <power failure happens>

   The next time the fs is mounted, log tree replay happens and the
   file "bar" does not exists anymore. A file with the name "foo"
   exists and it matches the second file we created.

Another related problem that does not involve file/data loss is when a
new inode is created with the name of a deleted snapshot and we fsync it:

   mkfs.btrfs -f /dev/sdc
   mount /dev/sdc /mnt
   mkdir /mnt/testdir
   btrfs subvolume snapshot /mnt /mnt/testdir/snap
   btrfs subvolume delete /mnt/testdir/snap
   rmdir /mnt/testdir
   mkdir /mnt/testdir
   xfs_io -c fsync /mnt/testdir # or fsync some file inside /mnt/testdir
   <power failure>

   The next time the fs is mounted the log replay procedure fails because
   it attempts to delete the snapshot entry (which has dir item key type
   of BTRFS_ROOT_ITEM_KEY) as if it were a regular (non-root) entry,
   resulting in the following error that causes mount to fail:

   [52174.510532] BTRFS info (device dm-0): failed to delete reference to snap, inode 257 parent 257
   [52174.512570] ------------[ cut here ]------------
   [52174.513278] WARNING: CPU: 12 PID: 28024 at fs/btrfs/inode.c:3986 __btrfs_unlink_inode+0x178/0x351 [btrfs]()
   [52174.514681] BTRFS: Transaction aborted (error -2)
   [52174.515630] Modules linked in: btrfs dm_flakey dm_mod overlay crc32c_generic ppdev xor raid6_pq acpi_cpufreq parport_pc tpm_tis sg parport tpm evdev i2c_piix4 proc
   [52174.521568] CPU: 12 PID: 28024 Comm: mount Tainted: G        W       4.5.0-rc6-btrfs-next-27+ #1
   [52174.522805] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS by qemu-project.org 04/01/2014
   [52174.524053]  0000000000000000 ffff8801df2a7710 ffffffff81264e93 ffff8801df2a7758
   [52174.524053]  0000000000000009 ffff8801df2a7748 ffffffff81051618 ffffffffa03591cd
   [52174.524053]  00000000fffffffe ffff88015e6e5000 ffff88016dbc3c88 ffff88016dbc3c88
   [52174.524053] Call Trace:
   [52174.524053]  [<ffffffff81264e93>] dump_stack+0x67/0x90
   [52174.524053]  [<ffffffff81051618>] warn_slowpath_common+0x99/0xb2
   [52174.524053]  [<ffffffffa03591cd>] ? __btrfs_unlink_inode+0x178/0x351 [btrfs]
   [52174.524053]  [<ffffffff81051679>] warn_slowpath_fmt+0x48/0x50
   [52174.524053]  [<ffffffffa03591cd>] __btrfs_unlink_inode+0x178/0x351 [btrfs]
   [52174.524053]  [<ffffffff8118f5e9>] ? iput+0xb0/0x284
   [52174.524053]  [<ffffffffa0359fe8>] btrfs_unlink_inode+0x1c/0x3d [btrfs]
   [52174.524053]  [<ffffffffa038631e>] check_item_in_log+0x1fe/0x29b [btrfs]
   [52174.524053]  [<ffffffffa0386522>] replay_dir_deletes+0x167/0x1cf [btrfs]
   [52174.524053]  [<ffffffffa038739e>] fixup_inode_link_count+0x289/0x2aa [btrfs]
   [52174.524053]  [<ffffffffa038748a>] fixup_inode_link_counts+0xcb/0x105 [btrfs]
   [52174.524053]  [<ffffffffa038a5ec>] btrfs_recover_log_trees+0x258/0x32c [btrfs]
   [52174.524053]  [<ffffffffa03885b2>] ? replay_one_extent+0x511/0x511 [btrfs]
   [52174.524053]  [<ffffffffa034f288>] open_ctree+0x1dd4/0x21b9 [btrfs]
   [52174.524053]  [<ffffffffa032b753>] btrfs_mount+0x97e/0xaed [btrfs]
   [52174.524053]  [<ffffffff8108e1b7>] ? trace_hardirqs_on+0xd/0xf
   [52174.524053]  [<ffffffff8117bafa>] mount_fs+0x67/0x131
   [52174.524053]  [<ffffffff81193003>] vfs_kern_mount+0x6c/0xde
   [52174.524053]  [<ffffffffa032af81>] btrfs_mount+0x1ac/0xaed [btrfs]
   [52174.524053]  [<ffffffff8108e1b7>] ? trace_hardirqs_on+0xd/0xf
   [52174.524053]  [<ffffffff8108c262>] ? lockdep_init_map+0xb9/0x1b3
   [52174.524053]  [<ffffffff8117bafa>] mount_fs+0x67/0x131
   [52174.524053]  [<ffffffff81193003>] vfs_kern_mount+0x6c/0xde
   [52174.524053]  [<ffffffff8119590f>] do_mount+0x8a6/0x9e8
   [52174.524053]  [<ffffffff811358dd>] ? strndup_user+0x3f/0x59
   [52174.524053]  [<ffffffff81195c65>] SyS_mount+0x77/0x9f
   [52174.524053]  [<ffffffff814935d7>] entry_SYSCALL_64_fastpath+0x12/0x6b
   [52174.561288] ---[ end trace 6b53049efb1a3ea6 ]---

Fix this by forcing a transaction commit when such cases happen.
This means we check in the commit root of the subvolume tree if there
was any other inode with the same reference when the inode we are
fsync'ing is a new inode (created in the current transaction).

Test cases for fstests, covering all the scenarios given above, were
submitted upstream for fstests:

  * fstests: generic test for fsync after renaming directory
    https://patchwork.kernel.org/patch/8694281/

  * fstests: generic test for fsync after renaming file
    https://patchwork.kernel.org/patch/8694301/

  * fstests: add btrfs test for fsync after snapshot deletion
    https://patchwork.kernel.org/patch/8670671/

Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 fs/btrfs/tree-log.c |  137 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 137 insertions(+)

--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4406,6 +4406,127 @@ static int btrfs_log_trailing_hole(struc
 	return ret;
 }
 
+/*
+ * When we are logging a new inode X, check if it doesn't have a reference that
+ * matches the reference from some other inode Y created in a past transaction
+ * and that was renamed in the current transaction. If we don't do this, then at
+ * log replay time we can lose inode Y (and all its files if it's a directory):
+ *
+ * mkdir /mnt/x
+ * echo "hello world" > /mnt/x/foobar
+ * sync
+ * mv /mnt/x /mnt/y
+ * mkdir /mnt/x                 # or touch /mnt/x
+ * xfs_io -c fsync /mnt/x
+ * <power fail>
+ * mount fs, trigger log replay
+ *
+ * After the log replay procedure, we would lose the first directory and all its
+ * files (file foobar).
+ * For the case where inode Y is not a directory we simply end up losing it:
+ *
+ * echo "123" > /mnt/foo
+ * sync
+ * mv /mnt/foo /mnt/bar
+ * echo "abc" > /mnt/foo
+ * xfs_io -c fsync /mnt/foo
+ * <power fail>
+ *
+ * We also need this for cases where a snapshot entry is replaced by some other
+ * entry (file or directory) otherwise we end up with an unreplayable log due to
+ * attempts to delete the snapshot entry (entry of type BTRFS_ROOT_ITEM_KEY) as
+ * if it were a regular entry:
+ *
+ * mkdir /mnt/x
+ * btrfs subvolume snapshot /mnt /mnt/x/snap
+ * btrfs subvolume delete /mnt/x/snap
+ * rmdir /mnt/x
+ * mkdir /mnt/x
+ * fsync /mnt/x or fsync some new file inside it
+ * <power fail>
+ *
+ * The snapshot delete, rmdir of x, mkdir of a new x and the fsync all happen in
+ * the same transaction.
+ */
+static int btrfs_check_ref_name_override(struct extent_buffer *eb,
+					 const int slot,
+					 const struct btrfs_key *key,
+					 struct inode *inode)
+{
+	int ret;
+	struct btrfs_path *search_path;
+	char *name = NULL;
+	u32 name_len = 0;
+	u32 item_size = btrfs_item_size_nr(eb, slot);
+	u32 cur_offset = 0;
+	unsigned long ptr = btrfs_item_ptr_offset(eb, slot);
+
+	search_path = btrfs_alloc_path();
+	if (!search_path)
+		return -ENOMEM;
+	search_path->search_commit_root = 1;
+	search_path->skip_locking = 1;
+
+	while (cur_offset < item_size) {
+		u64 parent;
+		u32 this_name_len;
+		u32 this_len;
+		unsigned long name_ptr;
+		struct btrfs_dir_item *di;
+
+		if (key->type == BTRFS_INODE_REF_KEY) {
+			struct btrfs_inode_ref *iref;
+
+			iref = (struct btrfs_inode_ref *)(ptr + cur_offset);
+			parent = key->offset;
+			this_name_len = btrfs_inode_ref_name_len(eb, iref);
+			name_ptr = (unsigned long)(iref + 1);
+			this_len = sizeof(*iref) + this_name_len;
+		} else {
+			struct btrfs_inode_extref *extref;
+
+			extref = (struct btrfs_inode_extref *)(ptr +
+							       cur_offset);
+			parent = btrfs_inode_extref_parent(eb, extref);
+			this_name_len = btrfs_inode_extref_name_len(eb, extref);
+			name_ptr = (unsigned long)&extref->name;
+			this_len = sizeof(*extref) + this_name_len;
+		}
+
+		if (this_name_len > name_len) {
+			char *new_name;
+
+			new_name = krealloc(name, this_name_len, GFP_NOFS);
+			if (!new_name) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			name_len = this_name_len;
+			name = new_name;
+		}
+
+		read_extent_buffer(eb, name, name_ptr, this_name_len);
+		di = btrfs_lookup_dir_item(NULL, BTRFS_I(inode)->root,
+					   search_path, parent,
+					   name, this_name_len, 0);
+		if (di && !IS_ERR(di)) {
+			ret = 1;
+			goto out;
+		} else if (IS_ERR(di)) {
+			ret = PTR_ERR(di);
+			goto out;
+		}
+		btrfs_release_path(search_path);
+
+		cur_offset += this_len;
+	}
+	ret = 0;
+out:
+	btrfs_free_path(search_path);
+	kfree(name);
+	return ret;
+}
+
 /* log a single inode in the tree log.
  * At least one parent directory for this inode must exist in the tree
  * or be logged already.
@@ -4578,6 +4699,22 @@ again:
 		if (min_key.type == BTRFS_INODE_ITEM_KEY)
 			need_log_inode_item = false;
 
+		if ((min_key.type == BTRFS_INODE_REF_KEY ||
+		     min_key.type == BTRFS_INODE_EXTREF_KEY) &&
+		    BTRFS_I(inode)->generation == trans->transid) {
+			ret = btrfs_check_ref_name_override(path->nodes[0],
+							    path->slots[0],
+							    &min_key, inode);
+			if (ret < 0) {
+				err = ret;
+				goto out_unlock;
+			} else if (ret > 0) {
+				err = 1;
+				btrfs_set_log_full_commit(root->fs_info, trans);
+				goto out_unlock;
+			}
+		}
+
 		/* Skip xattrs, we log them later with btrfs_log_all_xattrs() */
 		if (min_key.type == BTRFS_XATTR_ITEM_KEY) {
 			if (ins_nr == 0)