Merge branch 'overlayfs-linus' of git://git.kernel.org/pub/scm/linux/…

…kernel/git/mszeredi/vfs

Pull overlayfs updates from Miklos Szeredi:
 "In addition to bug fixes and cleanups there are two new features from
  Amir:

   - Consistent inode number support for the case when layers are not
     all on the same filesystem (feature is dubbed "xino").

   - Optimize overlayfs file handle decoding. This one touches the
     exportfs interface to allow detecting the disconnected directory
     case"

* 'overlayfs-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs:
  ovl: update documentation w.r.t "xino" feature
  ovl: add support for "xino" mount and config options
  ovl: consistent d_ino for non-samefs with xino
  ovl: consistent i_ino for non-samefs with xino
  ovl: constant st_ino for non-samefs with xino
  ovl: allocate anon bdev per unique lower fs
  ovl: factor out ovl_map_dev_ino() helper
  ovl: cleanup ovl_update_time()
  ovl: add WARN_ON() for non-dir redirect cases
  ovl: cleanup setting OVL_INDEX
  ovl: set d->is_dir and d->opaque for last path element
  ovl: Do not check for redirect if this is last layer
  ovl: lookup in inode cache first when decoding lower file handle
  ovl: do not try to reconnect a disconnected origin dentry
  ovl: disambiguate ovl_encode_fh()
  ovl: set lower layer st_dev only if setting lower st_ino
  ovl: fix lookup with middle layer opaque dir and absolute path redirects
  ovl: Set d->last properly during lookup
  ovl: set i_ino to the value of st_ino for NFS export

Documentation/filesystems/overlayfs.txt

@@ -14,9 +14,13 @@ The result will inevitably fail to look exactly like a normal
 filesystem for various technical reasons.  The expectation is that
 many use cases will be able to ignore these differences.
 
-This approach is 'hybrid' because the objects that appear in the
-filesystem do not all appear to belong to that filesystem.  In many
-cases an object accessed in the union will be indistinguishable
+
+Overlay objects
+---------------
+
+The overlay filesystem approach is 'hybrid', because the objects that
+appear in the filesystem do not always appear to belong to that filesystem.
+In many cases, an object accessed in the union will be indistinguishable
 from accessing the corresponding object from the original filesystem.
 This is most obvious from the 'st_dev' field returned by stat(2).
 
@@ -34,6 +38,19 @@ make the overlay mount more compliant with filesystem scanners and
 overlay objects will be distinguishable from the corresponding
 objects in the original filesystem.
 
+On 64bit systems, even if all overlay layers are not on the same
+underlying filesystem, the same compliant behavior could be achieved
+with the "xino" feature.  The "xino" feature composes a unique object
+identifier from the real object st_ino and an underlying fsid index.
+If all underlying filesystems support NFS file handles and export file
+handles with 32bit inode number encoding (e.g. ext4), overlay filesystem
+will use the high inode number bits for fsid.  Even when the underlying
+filesystem uses 64bit inode numbers, users can still enable the "xino"
+feature with the "-o xino=on" overlay mount option.  That is useful for the
+case of underlying filesystems like xfs and tmpfs, which use 64bit inode
+numbers, but are very unlikely to use the high inode number bit.
+
+
 Upper and Lower
 ---------------
 
@@ -290,10 +307,19 @@ Non-standard behavior
 ---------------------
 
 The copy_up operation essentially creates a new, identical file and
-moves it over to the old name.  The new file may be on a different
-filesystem, so both st_dev and st_ino of the file may change.
+moves it over to the old name.  Any open files referring to this inode
+will access the old data.
+
+The new file may be on a different filesystem, so both st_dev and st_ino
+of the real file may change.  The values of st_dev and st_ino returned by
+stat(2) on an overlay object are often not the same as the real file
+stat(2) values to prevent the values from changing on copy_up.
 
-Any open files referring to this inode will access the old data.
+Unless "xino" feature is enabled, when overlay layers are not all on the
+same underlying filesystem, the value of st_dev may be different for two
+non-directory objects in the same overlay filesystem and the value of
+st_ino for directory objects may be non persistent and could change even
+while the overlay filesystem is still mounted.
 
 Unless "inode index" feature is enabled, if a file with multiple hard
 links is copied up, then this will "break" the link.  Changes will not be
@@ -302,6 +328,7 @@ propagated to other names referring to the same inode.
 Unless "redirect_dir" feature is enabled, rename(2) on a lower or merged
 directory will fail with EXDEV.
 
+
 Changes to underlying filesystems
 ---------------------------------
 

fs/exportfs/expfs.c

@@ -435,6 +435,15 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
 	if (IS_ERR_OR_NULL(result))
 		return ERR_PTR(-ESTALE);
 
+	/*
+	 * If no acceptance criteria was specified by caller, a disconnected
+	 * dentry is also accepatable. Callers may use this mode to query if
+	 * file handle is stale or to get a reference to an inode without
+	 * risking the high overhead caused by directory reconnect.
+	 */
+	if (!acceptable)
+		return result;
+
 	if (d_is_dir(result)) {
 		/*
 		 * This request is for a directory.

fs/overlayfs/Kconfig

@@ -86,3 +86,20 @@ config OVERLAY_FS_NFS_EXPORT
 	  case basis with the "nfs_export=on" mount option.
 
 	  Say N unless you fully understand the consequences.
+
+config OVERLAY_FS_XINO_AUTO
+	bool "Overlayfs: auto enable inode number mapping"
+	default n
+	depends on OVERLAY_FS
+	help
+	  If this config option is enabled then overlay filesystems will use
+	  unused high bits in undelying filesystem inode numbers to map all
+	  inodes to a unified address space.  The mapped 64bit inode numbers
+	  might not be compatible with applications that expect 32bit inodes.
+
+	  If compatibility with applications that expect 32bit inodes is not an
+	  issue, then it is safe and recommended to say Y here.
+
+	  For more information, see Documentation/filesystems/overlayfs.txt
+
+	  If unsure, say N.

fs/overlayfs/copy_up.c

@@ -232,7 +232,7 @@ int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat)
 	return err;
 }
 
-struct ovl_fh *ovl_encode_fh(struct dentry *real, bool is_upper)
+struct ovl_fh *ovl_encode_real_fh(struct dentry *real, bool is_upper)
 {
 	struct ovl_fh *fh;
 	int fh_type, fh_len, dwords;
@@ -300,7 +300,7 @@ int ovl_set_origin(struct dentry *dentry, struct dentry *lower,
 	 * up and a pure upper inode.
 	 */
 	if (ovl_can_decode_fh(lower->d_sb)) {
-		fh = ovl_encode_fh(lower, false);
+		fh = ovl_encode_real_fh(lower, false);
 		if (IS_ERR(fh))
 			return PTR_ERR(fh);
 	}
@@ -321,7 +321,7 @@ static int ovl_set_upper_fh(struct dentry *upper, struct dentry *index)
 	const struct ovl_fh *fh;
 	int err;
 
-	fh = ovl_encode_fh(upper, true);
+	fh = ovl_encode_real_fh(upper, true);
 	if (IS_ERR(fh))
 		return PTR_ERR(fh);
 

fs/overlayfs/export.c

@@ -228,8 +228,8 @@ static int ovl_d_to_fh(struct dentry *dentry, char *buf, int buflen)
 		goto fail;
 
 	/* Encode an upper or lower file handle */
-	fh = ovl_encode_fh(enc_lower ? ovl_dentry_lower(dentry) :
-				       ovl_dentry_upper(dentry), !enc_lower);
+	fh = ovl_encode_real_fh(enc_lower ? ovl_dentry_lower(dentry) :
+				ovl_dentry_upper(dentry), !enc_lower);
 	err = PTR_ERR(fh);
 	if (IS_ERR(fh))
 		goto fail;
@@ -267,8 +267,8 @@ static int ovl_dentry_to_fh(struct dentry *dentry, u32 *fid, int *max_len)
 	return OVL_FILEID;
 }
 
-static int ovl_encode_inode_fh(struct inode *inode, u32 *fid, int *max_len,
-			       struct inode *parent)
+static int ovl_encode_fh(struct inode *inode, u32 *fid, int *max_len,
+			 struct inode *parent)
 {
 	struct dentry *dentry;
 	int type;
@@ -305,15 +305,12 @@ static struct dentry *ovl_obtain_alias(struct super_block *sb,
 	if (d_is_dir(upper ?: lower))
 		return ERR_PTR(-EIO);
 
-	inode = ovl_get_inode(sb, dget(upper), lower, index, !!lower);
+	inode = ovl_get_inode(sb, dget(upper), lowerpath, index, !!lower);
 	if (IS_ERR(inode)) {
 		dput(upper);
 		return ERR_CAST(inode);
 	}
 
-	if (index)
-		ovl_set_flag(OVL_INDEX, inode);
-
 	dentry = d_find_any_alias(inode);
 	if (!dentry) {
 		dentry = d_alloc_anon(inode->i_sb);
@@ -685,7 +682,7 @@ static struct dentry *ovl_upper_fh_to_d(struct super_block *sb,
 	if (!ofs->upper_mnt)
 		return ERR_PTR(-EACCES);
 
-	upper = ovl_decode_fh(fh, ofs->upper_mnt);
+	upper = ovl_decode_real_fh(fh, ofs->upper_mnt, true);
 	if (IS_ERR_OR_NULL(upper))
 		return upper;
 
@@ -703,25 +700,39 @@ static struct dentry *ovl_lower_fh_to_d(struct super_block *sb,
 	struct ovl_path *stack = &origin;
 	struct dentry *dentry = NULL;
 	struct dentry *index = NULL;
-	struct inode *inode = NULL;
-	bool is_deleted = false;
+	struct inode *inode;
 	int err;
 
-	/* First lookup indexed upper by fh */
+	/* First lookup overlay inode in inode cache by origin fh */
+	err = ovl_check_origin_fh(ofs, fh, false, NULL, &stack);
+	if (err)
+		return ERR_PTR(err);
+
+	if (!d_is_dir(origin.dentry) ||
+	    !(origin.dentry->d_flags & DCACHE_DISCONNECTED)) {
+		inode = ovl_lookup_inode(sb, origin.dentry, false);
+		err = PTR_ERR(inode);
+		if (IS_ERR(inode))
+			goto out_err;
+		if (inode) {
+			dentry = d_find_any_alias(inode);
+			iput(inode);
+			if (dentry)
+				goto out;
+		}
+	}
+
+	/* Then lookup indexed upper/whiteout by origin fh */
 	if (ofs->indexdir) {
 		index = ovl_get_index_fh(ofs, fh);
 		err = PTR_ERR(index);
 		if (IS_ERR(index)) {
-			if (err != -ESTALE)
-				return ERR_PTR(err);
-
-			/* Found a whiteout index - treat as deleted inode */
-			is_deleted = true;
 			index = NULL;
+			goto out_err;
 		}
 	}
 
-	/* Then try to get upper dir by index */
+	/* Then try to get a connected upper dir by index */
 	if (index && d_is_dir(index)) {
 		struct dentry *upper = ovl_index_upper(ofs, index);
 
@@ -734,32 +745,26 @@ static struct dentry *ovl_lower_fh_to_d(struct super_block *sb,
 		goto out;
 	}
 
-	/* Then lookup origin by fh */
-	err = ovl_check_origin_fh(ofs, fh, NULL, &stack);
-	if (err) {
-		goto out_err;
-	} else if (index) {
-		err = ovl_verify_origin(index, origin.dentry, false);
+	/* Otherwise, get a connected non-upper dir or disconnected non-dir */
+	if (d_is_dir(origin.dentry) &&
+	    (origin.dentry->d_flags & DCACHE_DISCONNECTED)) {
+		dput(origin.dentry);
+		origin.dentry = NULL;
+		err = ovl_check_origin_fh(ofs, fh, true, NULL, &stack);
 		if (err)
 			goto out_err;
-	} else if (is_deleted) {
-		/* Lookup deleted non-dir by origin inode */
-		if (!d_is_dir(origin.dentry))
-			inode = ovl_lookup_inode(sb, origin.dentry, false);
-		err = -ESTALE;
-		if (!inode || atomic_read(&inode->i_count) == 1)
+	}
+	if (index) {
+		err = ovl_verify_origin(index, origin.dentry, false);
+		if (err)
 			goto out_err;
-
-		/* Deleted but still open? */
-		index = dget(ovl_i_dentry_upper(inode));
 	}
 
 	dentry = ovl_get_dentry(sb, NULL, &origin, index);
 
 out:
 	dput(origin.dentry);
 	dput(index);
-	iput(inode);
 	return dentry;
 
 out_err:
@@ -829,7 +834,7 @@ static struct dentry *ovl_get_parent(struct dentry *dentry)
 }
 
 const struct export_operations ovl_export_operations = {
-	.encode_fh	= ovl_encode_inode_fh,
+	.encode_fh	= ovl_encode_fh,
 	.fh_to_dentry	= ovl_fh_to_dentry,
 	.fh_to_parent	= ovl_fh_to_parent,
 	.get_name	= ovl_get_name,