ovl: introduce new "uuid=off" option for inodes index feature

This replaces uuid with null in overlayfs file handles and thus relaxes
uuid checks for overlay index feature. It is only possible in case there is
only one filesystem for all the work/upper/lower directories and bare file
handles from this backing filesystem are unique. In other case when we have
multiple filesystems lets just fallback to "uuid=on" which is and
equivalent of how it worked before with all uuid checks.

This is needed when overlayfs is/was mounted in a container with index
enabled (e.g.: to be able to resolve inotify watch file handles on it to
paths in CRIU), and this container is copied and started alongside with the
original one. This way the "copy" container can't have the same uuid on the
superblock and mounting the overlayfs from it later would fail.

That is an example of the problem on top of loop+ext4:

dd if=/dev/zero of=loopbackfile.img bs=100M count=10
losetup -fP loopbackfile.img
losetup -a
  #/dev/loop0: [64768]:35 (/loop-test/loopbackfile.img)
mkfs.ext4 loopbackfile.img
mkdir loop-mp
mount -o loop /dev/loop0 loop-mp
mkdir loop-mp/{lower,upper,work,merged}
mount -t overlay overlay -oindex=on,lowerdir=loop-mp/lower,\
upperdir=loop-mp/upper,workdir=loop-mp/work loop-mp/merged
umount loop-mp/merged
umount loop-mp
e2fsck -f /dev/loop0
tune2fs -U random /dev/loop0

mount -o loop /dev/loop0 loop-mp
mount -t overlay overlay -oindex=on,lowerdir=loop-mp/lower,\
upperdir=loop-mp/upper,workdir=loop-mp/work loop-mp/merged
  #mount: /loop-test/loop-mp/merged:
  #mount(2) system call failed: Stale file handle.

If you just change the uuid of the backing filesystem, overlay is not
mounting any more. In Virtuozzo we copy container disks (ploops) when
create the copy of container and we require fs uuid to be unique for a new
container.

Signed-off-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

Documentation/filesystems/overlayfs.rst

@@ -563,6 +563,11 @@ This verification may cause significant overhead in some cases.
 Note: the mount options index=off,nfs_export=on are conflicting for a
 read-write mount and will result in an error.
 
+Note: the mount option uuid=off can be used to replace UUID of the underlying
+filesystem in file handles with null, and effectively disable UUID checks. This
+can be useful in case the underlying disk is copied and the UUID of this copy
+is changed. This is only applicable if all lower/upper/work directories are on
+the same filesystem, otherwise it will fallback to normal behaviour.
 
 Volatile mount
 --------------

fs/overlayfs/copy_up.c

@@ -320,7 +320,8 @@ struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real,
 	if (is_upper)
 		fh->fb.flags |= OVL_FH_FLAG_PATH_UPPER;
 	fh->fb.len = sizeof(fh->fb) + buflen;
-	fh->fb.uuid = *uuid;
+	if (ofs->config.uuid)
+		fh->fb.uuid = *uuid;
 
 	return fh;
 

fs/overlayfs/namei.c

@@ -159,8 +159,10 @@ struct dentry *ovl_decode_real_fh(struct ovl_fs *ofs, struct ovl_fh *fh,
 	/*
 	 * Make sure that the stored uuid matches the uuid of the lower
 	 * layer where file handle will be decoded.
+	 * In case of uuid=off option just make sure that stored uuid is null.
 	 */
-	if (!uuid_equal(&fh->fb.uuid, &mnt->mnt_sb->s_uuid))
+	if (ofs->config.uuid ? !uuid_equal(&fh->fb.uuid, &mnt->mnt_sb->s_uuid) :
+			      !uuid_is_null(&fh->fb.uuid))
 		return NULL;
 
 	bytes = (fh->fb.len - offsetof(struct ovl_fb, fid));

fs/overlayfs/ovl_entry.h

@@ -14,6 +14,7 @@ struct ovl_config {
 	bool redirect_follow;
 	const char *redirect_mode;
 	bool index;
+	bool uuid;
 	bool nfs_export;
 	int xino;
 	bool metacopy;

fs/overlayfs/super.c

@@ -356,6 +356,8 @@ static int ovl_show_options(struct seq_file *m, struct dentry *dentry)
 		seq_printf(m, ",redirect_dir=%s", ofs->config.redirect_mode);
 	if (ofs->config.index != ovl_index_def)
 		seq_printf(m, ",index=%s", ofs->config.index ? "on" : "off");
+	if (!ofs->config.uuid)
+		seq_puts(m, ",uuid=off");
 	if (ofs->config.nfs_export != ovl_nfs_export_def)
 		seq_printf(m, ",nfs_export=%s", ofs->config.nfs_export ?
 						"on" : "off");
@@ -410,6 +412,8 @@ enum {
 	OPT_REDIRECT_DIR,
 	OPT_INDEX_ON,
 	OPT_INDEX_OFF,
+	OPT_UUID_ON,
+	OPT_UUID_OFF,
 	OPT_NFS_EXPORT_ON,
 	OPT_NFS_EXPORT_OFF,
 	OPT_XINO_ON,
@@ -429,6 +433,8 @@ static const match_table_t ovl_tokens = {
 	{OPT_REDIRECT_DIR,		"redirect_dir=%s"},
 	{OPT_INDEX_ON,			"index=on"},
 	{OPT_INDEX_OFF,			"index=off"},
+	{OPT_UUID_ON,			"uuid=on"},
+	{OPT_UUID_OFF,			"uuid=off"},
 	{OPT_NFS_EXPORT_ON,		"nfs_export=on"},
 	{OPT_NFS_EXPORT_OFF,		"nfs_export=off"},
 	{OPT_XINO_ON,			"xino=on"},
@@ -549,6 +555,14 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
 			index_opt = true;
 			break;
 
+		case OPT_UUID_ON:
+			config->uuid = true;
+			break;
+
+		case OPT_UUID_OFF:
+			config->uuid = false;
+			break;
+
 		case OPT_NFS_EXPORT_ON:
 			config->nfs_export = true;
 			nfs_export_opt = true;
@@ -1877,6 +1891,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	ofs->share_whiteout = true;
 
 	ofs->config.index = ovl_index_def;
+	ofs->config.uuid = true;
 	ofs->config.nfs_export = ovl_nfs_export_def;
 	ofs->config.xino = ovl_xino_def();
 	ofs->config.metacopy = ovl_metacopy_def;
@@ -1956,6 +1971,11 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	if (!ovl_upper_mnt(ofs))
 		sb->s_flags |= SB_RDONLY;
 
+	if (!ofs->config.uuid && ofs->numfs > 1) {
+		pr_warn("The uuid=off requires a single fs for lower and upper, falling back to uuid=on.\n");
+		ofs->config.uuid = true;
+	}
+
 	if (!ovl_force_readonly(ofs) && ofs->config.index) {
 		err = ovl_get_indexdir(sb, ofs, oe, &upperpath);
 		if (err)