Merge tag 'ovl-fixes-6.8-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/overlayfs/vfs

Pull overlayfs fix from Amir Goldstein:
"Change the on-disk format for the new "xwhiteouts" feature introduced
in v6.7

The change reduces unneeded overhead of an extra getxattr per readdir.
The only user of the "xwhiteout" feature is the external composefs
tool, which has been updated to support the new on-disk format.

This change is also designated for 6.7.y"

* tag 'ovl-fixes-6.8-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/overlayfs/vfs:
ovl: mark xwhiteouts directory with overlay.opaque='x'

Documentation/filesystems/overlayfs.rst

···
 that files have been removed.  This is done using whiteouts and opaque
 directories (non-directories are always opaque).
 
-A whiteout is created as a character device with 0/0 device number.
+A whiteout is created as a character device with 0/0 device number or
+as a zero-size regular file with the xattr "trusted.overlay.whiteout".
+
 When a whiteout is found in the upper level of a merged directory, any
 matching name in the lower level is ignored, and the whiteout itself
 is also hidden.
···
 A directory is made opaque by setting the xattr "trusted.overlay.opaque"
 to "y".  Where the upper filesystem contains an opaque directory, any
 directory in the lower filesystem with the same name is ignored.
+
+An opaque directory should not conntain any whiteouts, because they do not
+serve any purpose.  A merge directory containing regular files with the xattr
+"trusted.overlay.whiteout", should be additionally marked by setting the xattr
+"trusted.overlay.opaque" to "x" on the merge directory itself.
+This is needed to avoid the overhead of checking the "trusted.overlay.whiteout"
+on all entries during readdir in the common case.
 
 readdir
 -------
···
 mount, so to support storing an effective whiteout file in an overlayfs mount an
 alternative form of whiteout is supported. This form is a regular, zero-size
 file with the "overlay.whiteout" xattr set, inside a directory with the
-"overlay.whiteouts" xattr set. Such whiteouts are never created by overlayfs,
-but can be used by userspace tools (like containers) that generate lower layers.
+"overlay.opaque" xattr set to "x" (see `whiteouts and opaque directories`_).
+These alternative whiteouts are never created by overlayfs, but can be used by
+userspace tools (like containers) that generate lower layers.
 These alternative whiteouts can be escaped using the standard xattr escape
 mechanism in order to properly nest to any depth.
 

fs/overlayfs/namei.c

···
 
 struct ovl_lookup_data {
 	struct super_block *sb;
-	struct vfsmount *mnt;
+	const struct ovl_layer *layer;
 	struct qstr name;
 	bool is_dir;
 	bool opaque;
+	bool xwhiteouts;
 	bool stop;
 	bool last;
 	char *redirect;
···
 	return real;
 }
 
-static bool ovl_is_opaquedir(struct ovl_fs *ofs, const struct path *path)
-{
-	return ovl_path_check_dir_xattr(ofs, path, OVL_XATTR_OPAQUE);
-}
-
 static struct dentry *ovl_lookup_positive_unlocked(struct ovl_lookup_data *d,
 						   const char *name,
 						   struct dentry *base, int len,
 						   bool drop_negative)
 {
-	struct dentry *ret = lookup_one_unlocked(mnt_idmap(d->mnt), name, base, len);
+	struct dentry *ret = lookup_one_unlocked(mnt_idmap(d->layer->mnt), name,
+						 base, len);
 
 	if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) {
 		if (drop_negative && ret->d_lockref.count == 1) {
···
 			     size_t prelen, const char *post,
 			     struct dentry **ret, bool drop_negative)
 {
+	struct ovl_fs *ofs = OVL_FS(d->sb);
 	struct dentry *this;
 	struct path path;
 	int err;
 	bool last_element = !post[0];
+	bool is_upper = d->layer->idx == 0;
+	char val;
 
 	this = ovl_lookup_positive_unlocked(d, name, base, namelen, drop_negative);
 	if (IS_ERR(this)) {
···
 	}
 
 	path.dentry = this;
-	path.mnt = d->mnt;
-	if (ovl_path_is_whiteout(OVL_FS(d->sb), &path)) {
+	path.mnt = d->layer->mnt;
+	if (ovl_path_is_whiteout(ofs, &path)) {
 		d->stop = d->opaque = true;
 		goto put_and_out;
 	}
···
 			d->stop = true;
 			goto put_and_out;
 		}
-		err = ovl_check_metacopy_xattr(OVL_FS(d->sb), &path, NULL);
+		err = ovl_check_metacopy_xattr(ofs, &path, NULL);
 		if (err < 0)
 			goto out_err;
 
···
 		if (d->last)
 			goto out;
 
-		if (ovl_is_opaquedir(OVL_FS(d->sb), &path)) {
+		/* overlay.opaque=x means xwhiteouts directory */
+		val = ovl_get_opaquedir_val(ofs, &path);
+		if (last_element && !is_upper && val == 'x') {
+			d->xwhiteouts = true;
+			ovl_layer_set_xwhiteouts(ofs, d->layer);
+		} else if (val == 'y') {
 			d->stop = true;
 			if (last_element)
 				d->opaque = true;
···
  * Returns next layer in stack starting from top.
  * Returns -1 if this is the last layer.
  */
-int ovl_path_next(int idx, struct dentry *dentry, struct path *path)
+int ovl_path_next(int idx, struct dentry *dentry, struct path *path,
+		  const struct ovl_layer **layer)
 {
 	struct ovl_entry *oe = OVL_E(dentry);
 	struct ovl_path *lowerstack = ovl_lowerstack(oe);
···
 	BUG_ON(idx < 0);
 	if (idx == 0) {
 		ovl_path_upper(dentry, path);
-		if (path->dentry)
+		if (path->dentry) {
+			*layer = &OVL_FS(dentry->d_sb)->layers[0];
 			return ovl_numlower(oe) ? 1 : -1;
+		}
 		idx++;
 	}
 	BUG_ON(idx > ovl_numlower(oe));
 	path->dentry = lowerstack[idx - 1].dentry;
-	path->mnt = lowerstack[idx - 1].layer->mnt;
+	*layer = lowerstack[idx - 1].layer;
+	path->mnt = (*layer)->mnt;
 
 	return (idx < ovl_numlower(oe)) ? idx + 1 : -1;
 }
···
 	old_cred = ovl_override_creds(dentry->d_sb);
 	upperdir = ovl_dentry_upper(dentry->d_parent);
 	if (upperdir) {
-		d.mnt = ovl_upper_mnt(ofs);
+		d.layer = &ofs->layers[0];
 		err = ovl_lookup_layer(upperdir, &d, &upperdentry, true);
 		if (err)
 			goto out;
···
 		else if (d.is_dir || !ofs->numdatalayer)
 			d.last = lower.layer->idx == ovl_numlower(roe);
 
-		d.mnt = lower.layer->mnt;
+		d.layer = lower.layer;
 		err = ovl_lookup_layer(lower.dentry, &d, &this, false);
 		if (err)
 			goto out_put;
···
 
 	if (upperopaque)
 		ovl_dentry_set_opaque(dentry);
+	if (d.xwhiteouts)
+		ovl_dentry_set_xwhiteouts(dentry);
 
 	if (upperdentry)
 		ovl_dentry_set_upper_alias(dentry);

fs/overlayfs/overlayfs.h

···
 	OVL_XATTR_METACOPY,
 	OVL_XATTR_PROTATTR,
 	OVL_XATTR_XWHITEOUT,
-	OVL_XATTR_XWHITEOUTS,
 };
 
 enum ovl_inode_flag {
···
 	OVL_E_UPPER_ALIAS,
 	OVL_E_OPAQUE,
 	OVL_E_CONNECTED,
+	/* Lower stack may contain xwhiteout entries */
+	OVL_E_XWHITEOUTS,
 };
 
 enum {
···
 bool ovl_dentry_is_opaque(struct dentry *dentry);
 bool ovl_dentry_is_whiteout(struct dentry *dentry);
 void ovl_dentry_set_opaque(struct dentry *dentry);
+bool ovl_dentry_has_xwhiteouts(struct dentry *dentry);
+void ovl_dentry_set_xwhiteouts(struct dentry *dentry);
+void ovl_layer_set_xwhiteouts(struct ovl_fs *ofs,
+			      const struct ovl_layer *layer);
 bool ovl_dentry_has_upper_alias(struct dentry *dentry);
 void ovl_dentry_set_upper_alias(struct dentry *dentry);
 bool ovl_dentry_needs_data_copy_up(struct dentry *dentry, int flags);
···
 int ovl_copy_up_start(struct dentry *dentry, int flags);
 void ovl_copy_up_end(struct dentry *dentry);
 bool ovl_already_copied_up(struct dentry *dentry, int flags);
-bool ovl_path_check_dir_xattr(struct ovl_fs *ofs, const struct path *path,
-			      enum ovl_xattr ox);
+char ovl_get_dir_xattr_val(struct ovl_fs *ofs, const struct path *path,
+			   enum ovl_xattr ox);
 bool ovl_path_check_origin_xattr(struct ovl_fs *ofs, const struct path *path);
 bool ovl_path_check_xwhiteout_xattr(struct ovl_fs *ofs, const struct path *path);
-bool ovl_path_check_xwhiteouts_xattr(struct ovl_fs *ofs, const struct path *path);
 bool ovl_init_uuid_xattr(struct super_block *sb, struct ovl_fs *ofs,
 			 const struct path *upperpath);
 
···
 		.mnt = ovl_upper_mnt(ofs),
 	};
 
-	return ovl_path_check_dir_xattr(ofs, &upperpath, OVL_XATTR_IMPURE);
+	return ovl_get_dir_xattr_val(ofs, &upperpath, OVL_XATTR_IMPURE) == 'y';
+}
+
+static inline char ovl_get_opaquedir_val(struct ovl_fs *ofs,
+					 const struct path *path)
+{
+	return ovl_get_dir_xattr_val(ofs, path, OVL_XATTR_OPAQUE);
 }
 
 static inline bool ovl_redirect_follow(struct ovl_fs *ofs)
···
 struct dentry *ovl_get_index_fh(struct ovl_fs *ofs, struct ovl_fh *fh);
 struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper,
 				struct dentry *origin, bool verify);
-int ovl_path_next(int idx, struct dentry *dentry, struct path *path);
+int ovl_path_next(int idx, struct dentry *dentry, struct path *path,
+		  const struct ovl_layer **layer);
 int ovl_verify_lowerdata(struct dentry *dentry);
 struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 			  unsigned int flags);

fs/overlayfs/ovl_entry.h

···
 	int idx;
 	/* One fsid per unique underlying sb (upper fsid == 0) */
 	int fsid;
+	/* xwhiteouts were found on this layer */
+	bool has_xwhiteouts;
 };
 
 struct ovl_path {
···
 	unsigned int numfs;
 	/* Number of data-only lower layers */
 	unsigned int numdatalayer;
-	const struct ovl_layer *layers;
+	struct ovl_layer *layers;
 	struct ovl_sb *fs;
 	/* workbasedir is the path at workdir= mount option */
 	struct dentry *workbasedir;

fs/overlayfs/readdir.c

···
 	if (IS_ERR(realfile))
 		return PTR_ERR(realfile);
 
-	rdd->in_xwhiteouts_dir = rdd->dentry &&
-		ovl_path_check_xwhiteouts_xattr(OVL_FS(rdd->dentry->d_sb), realpath);
 	rdd->first_maybe_whiteout = NULL;
 	rdd->ctx.pos = 0;
 	do {
···
 		.is_lowest = false,
 	};
 	int idx, next;
+	const struct ovl_layer *layer;
 
 	for (idx = 0; idx != -1; idx = next) {
-		next = ovl_path_next(idx, dentry, &realpath);
+		next = ovl_path_next(idx, dentry, &realpath, &layer);
 		rdd.is_upper = ovl_dentry_upper(dentry) == realpath.dentry;
+		rdd.in_xwhiteouts_dir = layer->has_xwhiteouts &&
+					ovl_dentry_has_xwhiteouts(dentry);
 
 		if (next != -1) {
 			err = ovl_dir_read(&realpath, &rdd);

fs/overlayfs/super.c

···
 				   struct ovl_entry *oe)
 {
 	struct dentry *root;
+	struct ovl_fs *ofs = OVL_FS(sb);
 	struct ovl_path *lowerpath = ovl_lowerstack(oe);
 	unsigned long ino = d_inode(lowerpath->dentry)->i_ino;
 	int fsid = lowerpath->layer->fsid;
···
 		ovl_dentry_set_upper_alias(root);
 		if (ovl_is_impuredir(sb, upperdentry))
 			ovl_set_flag(OVL_IMPURE, d_inode(root));
+	}
+
+	/* Look for xwhiteouts marker except in the lowermost layer */
+	for (int i = 0; i < ovl_numlower(oe) - 1; i++, lowerpath++) {
+		struct path path = {
+			.mnt = lowerpath->layer->mnt,
+			.dentry = lowerpath->dentry,
+		};
+
+		/* overlay.opaque=x means xwhiteouts directory */
+		if (ovl_get_opaquedir_val(ofs, &path) == 'x') {
+			ovl_layer_set_xwhiteouts(ofs, lowerpath->layer);
+			ovl_dentry_set_xwhiteouts(root);
+		}
 	}
 
 	/* Root is always merge -> can have whiteouts */

fs/overlayfs/util.c

···
 	ovl_dentry_set_flag(OVL_E_OPAQUE, dentry);
 }
 
+bool ovl_dentry_has_xwhiteouts(struct dentry *dentry)
+{
+	return ovl_dentry_test_flag(OVL_E_XWHITEOUTS, dentry);
+}
+
+void ovl_dentry_set_xwhiteouts(struct dentry *dentry)
+{
+	ovl_dentry_set_flag(OVL_E_XWHITEOUTS, dentry);
+}
+
+/*
+ * ovl_layer_set_xwhiteouts() is called before adding the overlay dir
+ * dentry to dcache, while readdir of that same directory happens after
+ * the overlay dir dentry is in dcache, so if some cpu observes that
+ * ovl_dentry_is_xwhiteouts(), it will also observe layer->has_xwhiteouts
+ * for the layers where xwhiteouts marker was found in that merge dir.
+ */
+void ovl_layer_set_xwhiteouts(struct ovl_fs *ofs,
+			      const struct ovl_layer *layer)
+{
+	if (layer->has_xwhiteouts)
+		return;
+
+	/* Write once to read-mostly layer properties */
+	ofs->layers[layer->idx].has_xwhiteouts = true;
+}
+
 /*
  * For hard links and decoded file handles, it's possible for ovl_dentry_upper()
  * to return positive, while there's no actual upper alias for the inode.
···
 	return res >= 0;
 }
 
-bool ovl_path_check_xwhiteouts_xattr(struct ovl_fs *ofs, const struct path *path)
-{
-	struct dentry *dentry = path->dentry;
-	int res;
-
-	/* xattr.whiteouts must be a directory */
-	if (!d_is_dir(dentry))
-		return false;
-
-	res = ovl_path_getxattr(ofs, path, OVL_XATTR_XWHITEOUTS, NULL, 0);
-	return res >= 0;
-}
-
 /*
  * Load persistent uuid from xattr into s_uuid if found, or store a new
  * random generated value in s_uuid and in xattr.
···
 	return false;
 }
 
-bool ovl_path_check_dir_xattr(struct ovl_fs *ofs, const struct path *path,
-			       enum ovl_xattr ox)
+char ovl_get_dir_xattr_val(struct ovl_fs *ofs, const struct path *path,
+			   enum ovl_xattr ox)
 {
 	int res;
 	char val;
 
 	if (!d_is_dir(path->dentry))
-		return false;
+		return 0;
 
 	res = ovl_path_getxattr(ofs, path, ox, &val, 1);
-	if (res == 1 && val == 'y')
-		return true;
-
-	return false;
+	return res == 1 ? val : 0;
 }
 
 #define OVL_XATTR_OPAQUE_POSTFIX	"opaque"
···
 #define OVL_XATTR_METACOPY_POSTFIX	"metacopy"
 #define OVL_XATTR_PROTATTR_POSTFIX	"protattr"
 #define OVL_XATTR_XWHITEOUT_POSTFIX	"whiteout"
-#define OVL_XATTR_XWHITEOUTS_POSTFIX	"whiteouts"
 
 #define OVL_XATTR_TAB_ENTRY(x) \
 	[x] = { [false] = OVL_XATTR_TRUSTED_PREFIX x ## _POSTFIX, \
···
 	OVL_XATTR_TAB_ENTRY(OVL_XATTR_METACOPY),
 	OVL_XATTR_TAB_ENTRY(OVL_XATTR_PROTATTR),
 	OVL_XATTR_TAB_ENTRY(OVL_XATTR_XWHITEOUT),
-	OVL_XATTR_TAB_ENTRY(OVL_XATTR_XWHITEOUTS),
 };
 
 int ovl_check_setxattr(struct ovl_fs *ofs, struct dentry *upperdentry,