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

Pull overlayfs updates from Miklos Szeredi:
 "This update contains:

   - try to clone on copy-up

   - allow renaming a directory

   - split source into managable chunks

   - misc cleanups and fixes

  It does not contain the read-only fd data inconsistency fix, which Al
  didn't like. I'll leave that to the next year..."

* 'overlayfs-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs: (36 commits)
  ovl: fix reStructuredText syntax errors in documentation
  ovl: fix return value of ovl_fill_super
  ovl: clean up kstat usage
  ovl: fold ovl_copy_up_truncate() into ovl_copy_up()
  ovl: create directories inside merged parent opaque
  ovl: opaque cleanup
  ovl: show redirect_dir mount option
  ovl: allow setting max size of redirect
  ovl: allow redirect_dir to default to "on"
  ovl: check for emptiness of redirect dir
  ovl: redirect on rename-dir
  ovl: lookup redirects
  ovl: consolidate lookup for underlying layers
  ovl: fix nested overlayfs mount
  ovl: check namelen
  ovl: split super.c
  ovl: use d_is_dir()
  ovl: simplify lookup
  ovl: check lower existence of rename target
  ovl: rename: simplify handling of lower/merged directory
  ...

Documentation/filesystems/overlayfs.txt

@@ -66,7 +66,7 @@ At mount time, the two directories given as mount options "lowerdir" and
 "upperdir" are combined into a merged directory:
 
   mount -t overlay overlay -olowerdir=/lower,upperdir=/upper,\
-workdir=/work /merged
+  workdir=/work /merged
 
 The "workdir" needs to be an empty directory on the same filesystem
 as upperdir.
@@ -118,6 +118,7 @@ programs.
 
 seek offsets are assigned sequentially when the directories are read.
 Thus if
+
   - read part of a directory
   - remember an offset, and close the directory
   - re-open the directory some time later
@@ -130,6 +131,23 @@ directory.
 Readdir on directories that are not merged is simply handled by the
 underlying directory (upper or lower).
 
+renaming directories
+--------------------
+
+When renaming a directory that is on the lower layer or merged (i.e. the
+directory was not created on the upper layer to start with) overlayfs can
+handle it in two different ways:
+
+1. return EXDEV error: this error is returned by rename(2) when trying to
+   move a file or directory across filesystem boundaries.  Hence
+   applications are usually prepared to hande this error (mv(1) for example
+   recursively copies the directory tree).  This is the default behavior.
+
+2. If the "redirect_dir" feature is enabled, then the directory will be
+   copied up (but not the contents).  Then the "trusted.overlay.redirect"
+   extended attribute is set to the path of the original location from the
+   root of the overlay.  Finally the directory is moved to the new
+   location.
 
 Non-directories
 ---------------
@@ -185,13 +203,13 @@ filesystem, so both st_dev and st_ino of the file may change.
 
 Any open files referring to this inode will access the old data.
 
-Any file locks (and leases) obtained before copy_up will not apply
-to the copied up file.
-
 If a file with multiple hard links is copied up, then this will
 "break" the link.  Changes will not be 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/ioctl.c

@@ -223,7 +223,11 @@ static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd,
 
 	if (!src_file.file)
 		return -EBADF;
-	ret = vfs_clone_file_range(src_file.file, off, dst_file, destoff, olen);
+	ret = -EXDEV;
+	if (src_file.file->f_path.mnt != dst_file->f_path.mnt)
+		goto fdput;
+	ret = do_clone_file_range(src_file.file, off, dst_file, destoff, olen);
+fdput:
 	fdput(src_file);
 	return ret;
 }

fs/namei.c

@@ -4306,11 +4306,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	bool new_is_dir = false;
 	unsigned max_links = new_dir->i_sb->s_max_links;
 
-	/*
-	 * Check source == target.
-	 * On overlayfs need to look at underlying inodes.
-	 */
-	if (d_real_inode(old_dentry) == d_real_inode(new_dentry))
+	if (source == target)
 		return 0;
 
 	error = may_delete(old_dir, old_dentry, is_dir);

fs/nfsd/vfs.c

@@ -509,8 +509,7 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp,
 __be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst,
 		u64 dst_pos, u64 count)
 {
-	return nfserrno(vfs_clone_file_range(src, src_pos, dst, dst_pos,
-			count));
+	return nfserrno(do_clone_file_range(src, src_pos, dst, dst_pos, count));
 }
 
 ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst,

fs/overlayfs/Kconfig

@@ -8,3 +8,17 @@ config OVERLAY_FS
 	  merged with the 'upper' object.
 
 	  For more information see Documentation/filesystems/overlayfs.txt
+
+config OVERLAY_FS_REDIRECT_DIR
+	bool "Overlayfs: turn on redirect dir feature by default"
+	depends on OVERLAY_FS
+	help
+	  If this config option is enabled then overlay filesystems will use
+	  redirects when renaming directories by default.  In this case it is
+	  still possible to turn off redirects globally with the
+	  "redirect_dir=off" module option or on a filesystem instance basis
+	  with the "redirect_dir=off" mount option.
+
+	  Note, that redirects are not backward compatible.  That is, mounting
+	  an overlay which has redirects on a kernel that doesn't support this
+	  feature will have unexpected results.

fs/overlayfs/Makefile

@@ -4,4 +4,4 @@
 
 obj-$(CONFIG_OVERLAY_FS) += overlay.o
 
-overlay-objs := super.o inode.o dir.o readdir.o copy_up.o
+overlay-objs := super.o namei.o util.o inode.o dir.o readdir.o copy_up.o

fs/overlayfs/copy_up.c

@@ -153,6 +153,13 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len)
 		goto out_fput;
 	}
 
+	/* Try to use clone_file_range to clone up within the same fs */
+	error = vfs_clone_file_range(old_file, 0, new_file, 0, len);
+	if (!error)
+		goto out;
+	/* Couldn't clone, so now we try to copy the data */
+	error = 0;
+
 	/* FIXME: copy up sparse files efficiently */
 	while (len) {
 		size_t this_len = OVL_COPY_UP_CHUNK_SIZE;
@@ -177,7 +184,7 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len)
 
 		len -= bytes;
 	}
-
+out:
 	if (!error)
 		error = vfs_fsync(new_file, 0);
 	fput(new_file);
@@ -231,10 +238,15 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 	struct inode *udir = upperdir->d_inode;
 	struct dentry *newdentry = NULL;
 	struct dentry *upper = NULL;
-	umode_t mode = stat->mode;
 	int err;
 	const struct cred *old_creds = NULL;
 	struct cred *new_creds = NULL;
+	struct cattr cattr = {
+		/* Can't properly set mode on creation because of the umask */
+		.mode = stat->mode & S_IFMT,
+		.rdev = stat->rdev,
+		.link = link
+	};
 
 	newdentry = ovl_lookup_temp(workdir, dentry);
 	err = PTR_ERR(newdentry);
@@ -254,10 +266,7 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 	if (new_creds)
 		old_creds = override_creds(new_creds);
 
-	/* Can't properly set mode on creation because of the umask */
-	stat->mode &= S_IFMT;
-	err = ovl_create_real(wdir, newdentry, stat, link, NULL, true);
-	stat->mode = mode;
+	err = ovl_create_real(wdir, newdentry, &cattr, NULL, true);
 
 	if (new_creds) {
 		revert_creds(old_creds);
@@ -296,12 +305,6 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 	ovl_dentry_update(dentry, newdentry);
 	ovl_inode_update(d_inode(dentry), d_inode(newdentry));
 	newdentry = NULL;
-
-	/*
-	 * Non-directores become opaque when copied up.
-	 */
-	if (!S_ISDIR(stat->mode))
-		ovl_dentry_set_opaque(dentry, true);
 out2:
 	dput(upper);
 out1:
@@ -317,20 +320,14 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 /*
  * Copy up a single dentry
  *
- * Directory renames only allowed on "pure upper" (already created on
- * upper filesystem, never copied up).  Directories which are on lower or
- * are merged may not be renamed.  For these -EXDEV is returned and
- * userspace has to deal with it.  This means, when copying up a
- * directory we can rely on it and ancestors being stable.
- *
- * Non-directory renames start with copy up of source if necessary.  The
- * actual rename will only proceed once the copy up was successful.  Copy
- * up uses upper parent i_mutex for exclusion.  Since rename can change
- * d_parent it is possible that the copy up will lock the old parent.  At
- * that point the file will have already been copied up anyway.
+ * All renames start with copy up of source if necessary.  The actual
+ * rename will only proceed once the copy up was successful.  Copy up uses
+ * upper parent i_mutex for exclusion.  Since rename can change d_parent it
+ * is possible that the copy up will lock the old parent.  At that point
+ * the file will have already been copied up anyway.
  */
-int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
-		    struct path *lowerpath, struct kstat *stat)
+static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
+			   struct path *lowerpath, struct kstat *stat)
 {
 	DEFINE_DELAYED_CALL(done);
 	struct dentry *workdir = ovl_workdir(dentry);
@@ -339,7 +336,6 @@ int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 	struct path parentpath;
 	struct dentry *lowerdentry = lowerpath->dentry;
 	struct dentry *upperdir;
-	struct dentry *upperdentry;
 	const char *link = NULL;
 
 	if (WARN_ON(!workdir))
@@ -365,8 +361,7 @@ int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 		pr_err("overlayfs: failed to lock workdir+upperdir\n");
 		goto out_unlock;
 	}
-	upperdentry = ovl_dentry_upper(dentry);
-	if (upperdentry) {
+	if (ovl_dentry_upper(dentry)) {
 		/* Raced with another copy-up?  Nothing to do, then... */
 		err = 0;
 		goto out_unlock;
@@ -385,7 +380,7 @@ int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 	return err;
 }
 
-int ovl_copy_up(struct dentry *dentry)
+int ovl_copy_up_flags(struct dentry *dentry, int flags)
 {
 	int err = 0;
 	const struct cred *old_cred = ovl_override_creds(dentry->d_sb);
@@ -415,6 +410,9 @@ int ovl_copy_up(struct dentry *dentry)
 
 		ovl_path_lower(next, &lowerpath);
 		err = vfs_getattr(&lowerpath, &stat);
+		/* maybe truncate regular file. this has no effect on dirs */
+		if (flags & O_TRUNC)
+			stat.size = 0;
 		if (!err)
 			err = ovl_copy_up_one(parent, next, &lowerpath, &stat);
 
@@ -425,3 +423,8 @@ int ovl_copy_up(struct dentry *dentry)
 
 	return err;
 }
+
+int ovl_copy_up(struct dentry *dentry)
+{
+	return ovl_copy_up_flags(dentry, 0);
+}

fs/overlayfs/dir.c

@@ -12,11 +12,18 @@
 #include <linux/xattr.h>
 #include <linux/security.h>
 #include <linux/cred.h>
+#include <linux/module.h>
 #include <linux/posix_acl.h>
 #include <linux/posix_acl_xattr.h>
 #include <linux/atomic.h>
+#include <linux/ratelimit.h>
 #include "overlayfs.h"
 
+static unsigned short ovl_redirect_max = 256;
+module_param_named(redirect_max, ovl_redirect_max, ushort, 0644);
+MODULE_PARM_DESC(ovl_redirect_max,
+		 "Maximum length of absolute redirect xattr value");
+
 void ovl_cleanup(struct inode *wdir, struct dentry *wdentry)
 {
 	int err;
@@ -75,8 +82,7 @@ static struct dentry *ovl_whiteout(struct dentry *workdir,
 }
 
 int ovl_create_real(struct inode *dir, struct dentry *newdentry,
-		    struct kstat *stat, const char *link,
-		    struct dentry *hardlink, bool debug)
+		    struct cattr *attr, struct dentry *hardlink, bool debug)
 {
 	int err;
 
@@ -86,13 +92,13 @@ int ovl_create_real(struct inode *dir, struct dentry *newdentry,
 	if (hardlink) {
 		err = ovl_do_link(hardlink, dir, newdentry, debug);
 	} else {
-		switch (stat->mode & S_IFMT) {
+		switch (attr->mode & S_IFMT) {
 		case S_IFREG:
-			err = ovl_do_create(dir, newdentry, stat->mode, debug);
+			err = ovl_do_create(dir, newdentry, attr->mode, debug);
 			break;
 
 		case S_IFDIR:
-			err = ovl_do_mkdir(dir, newdentry, stat->mode, debug);
+			err = ovl_do_mkdir(dir, newdentry, attr->mode, debug);
 			break;
 
 		case S_IFCHR:
@@ -100,11 +106,11 @@ int ovl_create_real(struct inode *dir, struct dentry *newdentry,
 		case S_IFIFO:
 		case S_IFSOCK:
 			err = ovl_do_mknod(dir, newdentry,
-					   stat->mode, stat->rdev, debug);
+					   attr->mode, attr->rdev, debug);
 			break;
 
 		case S_IFLNK:
-			err = ovl_do_symlink(dir, newdentry, link, debug);
+			err = ovl_do_symlink(dir, newdentry, attr->link, debug);
 			break;
 
 		default:
@@ -121,20 +127,15 @@ int ovl_create_real(struct inode *dir, struct dentry *newdentry,
 	return err;
 }
 
-static int ovl_set_opaque(struct dentry *upperdentry)
-{
-	return ovl_do_setxattr(upperdentry, OVL_XATTR_OPAQUE, "y", 1, 0);
-}
-
-static void ovl_remove_opaque(struct dentry *upperdentry)
+static int ovl_set_opaque(struct dentry *dentry, struct dentry *upperdentry)
 {
 	int err;
 
-	err = ovl_do_removexattr(upperdentry, OVL_XATTR_OPAQUE);
-	if (err) {
-		pr_warn("overlayfs: failed to remove opaque from '%s' (%i)\n",
-			upperdentry->d_name.name, err);
-	}
+	err = ovl_do_setxattr(upperdentry, OVL_XATTR_OPAQUE, "y", 1, 0);
+	if (!err)
+		ovl_dentry_set_opaque(dentry);
+
+	return err;
 }
 
 static int ovl_dir_getattr(struct vfsmount *mnt, struct dentry *dentry,
@@ -182,9 +183,13 @@ static void ovl_instantiate(struct dentry *dentry, struct inode *inode,
 	d_instantiate(dentry, inode);
 }
 
+static bool ovl_type_merge(struct dentry *dentry)
+{
+	return OVL_TYPE_MERGE(ovl_path_type(dentry));
+}
+
 static int ovl_create_upper(struct dentry *dentry, struct inode *inode,
-			    struct kstat *stat, const char *link,
-			    struct dentry *hardlink)
+			    struct cattr *attr, struct dentry *hardlink)
 {
 	struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
 	struct inode *udir = upperdir->d_inode;
@@ -192,7 +197,7 @@ static int ovl_create_upper(struct dentry *dentry, struct inode *inode,
 	int err;
 
 	if (!hardlink && !IS_POSIXACL(udir))
-		stat->mode &= ~current_umask();
+		attr->mode &= ~current_umask();
 
 	inode_lock_nested(udir, I_MUTEX_PARENT);
 	newdentry = lookup_one_len(dentry->d_name.name, upperdir,
@@ -200,10 +205,15 @@ static int ovl_create_upper(struct dentry *dentry, struct inode *inode,
 	err = PTR_ERR(newdentry);
 	if (IS_ERR(newdentry))
 		goto out_unlock;
-	err = ovl_create_real(udir, newdentry, stat, link, hardlink, false);
+	err = ovl_create_real(udir, newdentry, attr, hardlink, false);
 	if (err)
 		goto out_dput;
 
+	if (ovl_type_merge(dentry->d_parent)) {
+		/* Setting opaque here is just an optimization, allow to fail */
+		ovl_set_opaque(dentry, newdentry);
+	}
+
 	ovl_instantiate(dentry, inode, newdentry, !!hardlink);
 	newdentry = NULL;
 out_dput:
@@ -270,7 +280,8 @@ static struct dentry *ovl_clear_empty(struct dentry *dentry,
 	if (IS_ERR(opaquedir))
 		goto out_unlock;
 
-	err = ovl_create_real(wdir, opaquedir, &stat, NULL, NULL, true);
+	err = ovl_create_real(wdir, opaquedir,
+			      &(struct cattr){.mode = stat.mode}, NULL, true);
 	if (err)
 		goto out_dput;
 
@@ -278,7 +289,7 @@ static struct dentry *ovl_clear_empty(struct dentry *dentry,
 	if (err)
 		goto out_cleanup;
 
-	err = ovl_set_opaque(opaquedir);
+	err = ovl_set_opaque(dentry, opaquedir);
 	if (err)
 		goto out_cleanup;
 
@@ -370,7 +381,7 @@ static int ovl_set_upper_acl(struct dentry *upperdentry, const char *name,
 }
 
 static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
-				    struct kstat *stat, const char *link,
+				    struct cattr *cattr,
 				    struct dentry *hardlink)
 {
 	struct dentry *workdir = ovl_workdir(dentry);
@@ -387,7 +398,7 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
 
 	if (!hardlink) {
 		err = posix_acl_create(dentry->d_parent->d_inode,
-				       &stat->mode, &default_acl, &acl);
+				       &cattr->mode, &default_acl, &acl);
 		if (err)
 			return err;
 	}
@@ -407,7 +418,7 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
 	if (IS_ERR(upper))
 		goto out_dput;
 
-	err = ovl_create_real(wdir, newdentry, stat, link, hardlink, true);
+	err = ovl_create_real(wdir, newdentry, cattr, hardlink, true);
 	if (err)
 		goto out_dput2;
 
@@ -415,10 +426,11 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
 	 * mode could have been mutilated due to umask (e.g. sgid directory)
 	 */
 	if (!hardlink &&
-	    !S_ISLNK(stat->mode) && newdentry->d_inode->i_mode != stat->mode) {
+	    !S_ISLNK(cattr->mode) &&
+	    newdentry->d_inode->i_mode != cattr->mode) {
 		struct iattr attr = {
 			.ia_valid = ATTR_MODE,
-			.ia_mode = stat->mode,
+			.ia_mode = cattr->mode,
 		};
 		inode_lock(newdentry->d_inode);
 		err = notify_change(newdentry, &attr, NULL);
@@ -438,8 +450,8 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
 			goto out_cleanup;
 	}
 
-	if (!hardlink && S_ISDIR(stat->mode)) {
-		err = ovl_set_opaque(newdentry);
+	if (!hardlink && S_ISDIR(cattr->mode)) {
+		err = ovl_set_opaque(dentry, newdentry);
 		if (err)
 			goto out_cleanup;
 
@@ -475,8 +487,7 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
 }
 
 static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
-			      struct kstat *stat, const char *link,
-			      struct dentry *hardlink)
+			      struct cattr *attr, struct dentry *hardlink)
 {
 	int err;
 	const struct cred *old_cred;
@@ -494,7 +505,7 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
 		override_cred->fsgid = inode->i_gid;
 		if (!hardlink) {
 			err = security_dentry_create_files_as(dentry,
-					stat->mode, &dentry->d_name, old_cred,
+					attr->mode, &dentry->d_name, old_cred,
 					override_cred);
 			if (err) {
 				put_cred(override_cred);
@@ -504,12 +515,12 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
 		put_cred(override_creds(override_cred));
 		put_cred(override_cred);
 
-		if (!ovl_dentry_is_opaque(dentry))
-			err = ovl_create_upper(dentry, inode, stat, link,
+		if (!ovl_dentry_is_whiteout(dentry))
+			err = ovl_create_upper(dentry, inode, attr,
 						hardlink);
 		else
-			err = ovl_create_over_whiteout(dentry, inode, stat,
-							link, hardlink);
+			err = ovl_create_over_whiteout(dentry, inode, attr,
+							hardlink);
 	}
 out_revert_creds:
 	revert_creds(old_cred);
@@ -528,8 +539,9 @@ static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev,
 {
 	int err;
 	struct inode *inode;
-	struct kstat stat = {
+	struct cattr attr = {
 		.rdev = rdev,
+		.link = link,
 	};
 
 	err = ovl_want_write(dentry);
@@ -537,14 +549,14 @@ static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev,
 		goto out;
 
 	err = -ENOMEM;
-	inode = ovl_new_inode(dentry->d_sb, mode);
+	inode = ovl_new_inode(dentry->d_sb, mode, rdev);
 	if (!inode)
 		goto out_drop_write;
 
 	inode_init_owner(inode, dentry->d_parent->d_inode, mode);
-	stat.mode = inode->i_mode;
+	attr.mode = inode->i_mode;
 
-	err = ovl_create_or_link(dentry, inode, &stat, link, NULL);
+	err = ovl_create_or_link(dentry, inode, &attr, NULL);
 	if (err)
 		iput(inode);
 
@@ -598,7 +610,7 @@ static int ovl_link(struct dentry *old, struct inode *newdir,
 	inode = d_inode(old);
 	ihold(inode);
 
-	err = ovl_create_or_link(new, inode, NULL, NULL, ovl_dentry_upper(old));
+	err = ovl_create_or_link(new, inode, NULL, ovl_dentry_upper(old));
 	if (err)
 		iput(inode);
 
@@ -684,8 +696,17 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
 	struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
 	struct inode *dir = upperdir->d_inode;
 	struct dentry *upper;
+	struct dentry *opaquedir = NULL;
 	int err;
 
+	/* Redirect dir can be !ovl_lower_positive && OVL_TYPE_MERGE */
+	if (is_dir && ovl_dentry_get_redirect(dentry)) {
+		opaquedir = ovl_check_empty_and_clear(dentry);
+		err = PTR_ERR(opaquedir);
+		if (IS_ERR(opaquedir))
+			goto out;
+	}
+
 	inode_lock_nested(dir, I_MUTEX_PARENT);
 	upper = lookup_one_len(dentry->d_name.name, upperdir,
 			       dentry->d_name.len);
@@ -694,14 +715,15 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
 		goto out_unlock;
 
 	err = -ESTALE;
-	if (upper == ovl_dentry_upper(dentry)) {
-		if (is_dir)
-			err = vfs_rmdir(dir, upper);
-		else
-			err = vfs_unlink(dir, upper, NULL);
-		ovl_dentry_version_inc(dentry->d_parent);
-	}
-	dput(upper);
+	if ((opaquedir && upper != opaquedir) ||
+	    (!opaquedir && upper != ovl_dentry_upper(dentry)))
+		goto out_dput_upper;
+
+	if (is_dir)
+		err = vfs_rmdir(dir, upper);
+	else
+		err = vfs_unlink(dir, upper, NULL);
+	ovl_dentry_version_inc(dentry->d_parent);
 
 	/*
 	 * Keeping this dentry hashed would mean having to release
@@ -711,34 +733,21 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
 	 */
 	if (!err)
 		d_drop(dentry);
+out_dput_upper:
+	dput(upper);
 out_unlock:
 	inode_unlock(dir);
-
+	dput(opaquedir);
+out:
 	return err;
 }
 
-static inline int ovl_check_sticky(struct dentry *dentry)
-{
-	struct inode *dir = ovl_dentry_real(dentry->d_parent)->d_inode;
-	struct inode *inode = ovl_dentry_real(dentry)->d_inode;
-
-	if (check_sticky(dir, inode))
-		return -EPERM;
-
-	return 0;
-}
-
 static int ovl_do_remove(struct dentry *dentry, bool is_dir)
 {
 	enum ovl_path_type type;
 	int err;
 	const struct cred *old_cred;
 
-
-	err = ovl_check_sticky(dentry);
-	if (err)
-		goto out;
-
 	err = ovl_want_write(dentry);
 	if (err)
 		goto out;
@@ -750,7 +759,7 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir)
 	type = ovl_path_type(dentry);
 
 	old_cred = ovl_override_creds(dentry->d_sb);
-	if (OVL_TYPE_PURE_UPPER(type))
+	if (!ovl_lower_positive(dentry))
 		err = ovl_remove_upper(dentry, is_dir);
 	else
 		err = ovl_remove_and_whiteout(dentry, is_dir);
@@ -777,13 +786,114 @@ static int ovl_rmdir(struct inode *dir, struct dentry *dentry)
 	return ovl_do_remove(dentry, true);
 }
 
-static int ovl_rename2(struct inode *olddir, struct dentry *old,
-		       struct inode *newdir, struct dentry *new,
-		       unsigned int flags)
+static bool ovl_type_merge_or_lower(struct dentry *dentry)
+{
+	enum ovl_path_type type = ovl_path_type(dentry);
+
+	return OVL_TYPE_MERGE(type) || !OVL_TYPE_UPPER(type);
+}
+
+static bool ovl_can_move(struct dentry *dentry)
+{
+	return ovl_redirect_dir(dentry->d_sb) ||
+		!d_is_dir(dentry) || !ovl_type_merge_or_lower(dentry);
+}
+
+static char *ovl_get_redirect(struct dentry *dentry, bool samedir)
+{
+	char *buf, *ret;
+	struct dentry *d, *tmp;
+	int buflen = ovl_redirect_max + 1;
+
+	if (samedir) {
+		ret = kstrndup(dentry->d_name.name, dentry->d_name.len,
+			       GFP_KERNEL);
+		goto out;
+	}
+
+	buf = ret = kmalloc(buflen, GFP_TEMPORARY);
+	if (!buf)
+		goto out;
+
+	buflen--;
+	buf[buflen] = '\0';
+	for (d = dget(dentry); !IS_ROOT(d);) {
+		const char *name;
+		int thislen;
+
+		spin_lock(&d->d_lock);
+		name = ovl_dentry_get_redirect(d);
+		if (name) {
+			thislen = strlen(name);
+		} else {
+			name = d->d_name.name;
+			thislen = d->d_name.len;
+		}
+
+		/* If path is too long, fall back to userspace move */
+		if (thislen + (name[0] != '/') > buflen) {
+			ret = ERR_PTR(-EXDEV);
+			spin_unlock(&d->d_lock);
+			goto out_put;
+		}
+
+		buflen -= thislen;
+		memcpy(&buf[buflen], name, thislen);
+		tmp = dget_dlock(d->d_parent);
+		spin_unlock(&d->d_lock);
+
+		dput(d);
+		d = tmp;
+
+		/* Absolute redirect: finished */
+		if (buf[buflen] == '/')
+			break;
+		buflen--;
+		buf[buflen] = '/';
+	}
+	ret = kstrdup(&buf[buflen], GFP_KERNEL);
+out_put:
+	dput(d);
+	kfree(buf);
+out:
+	return ret ? ret : ERR_PTR(-ENOMEM);
+}
+
+static int ovl_set_redirect(struct dentry *dentry, bool samedir)
+{
+	int err;
+	const char *redirect = ovl_dentry_get_redirect(dentry);
+
+	if (redirect && (samedir || redirect[0] == '/'))
+		return 0;
+
+	redirect = ovl_get_redirect(dentry, samedir);
+	if (IS_ERR(redirect))
+		return PTR_ERR(redirect);
+
+	err = ovl_do_setxattr(ovl_dentry_upper(dentry), OVL_XATTR_REDIRECT,
+			      redirect, strlen(redirect), 0);
+	if (!err) {
+		spin_lock(&dentry->d_lock);
+		ovl_dentry_set_redirect(dentry, redirect);
+		spin_unlock(&dentry->d_lock);
+	} else {
+		kfree(redirect);
+		if (err == -EOPNOTSUPP)
+			ovl_clear_redirect_dir(dentry->d_sb);
+		else
+			pr_warn_ratelimited("overlay: failed to set redirect (%i)\n", err);
+		/* Fall back to userspace copy-up */
+		err = -EXDEV;
+	}
+	return err;
+}
+
+static int ovl_rename(struct inode *olddir, struct dentry *old,
+		      struct inode *newdir, struct dentry *new,
+		      unsigned int flags)
 {
 	int err;
-	enum ovl_path_type old_type;
-	enum ovl_path_type new_type;
 	struct dentry *old_upperdir;
 	struct dentry *new_upperdir;
 	struct dentry *olddentry;
@@ -794,7 +904,8 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 	bool cleanup_whiteout = false;
 	bool overwrite = !(flags & RENAME_EXCHANGE);
 	bool is_dir = d_is_dir(old);
-	bool new_is_dir = false;
+	bool new_is_dir = d_is_dir(new);
+	bool samedir = olddir == newdir;
 	struct dentry *opaquedir = NULL;
 	const struct cred *old_cred = NULL;
 
@@ -804,46 +915,12 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 
 	flags &= ~RENAME_NOREPLACE;
 
-	err = ovl_check_sticky(old);
-	if (err)
-		goto out;
-
 	/* Don't copy up directory trees */
-	old_type = ovl_path_type(old);
 	err = -EXDEV;
-	if (OVL_TYPE_MERGE_OR_LOWER(old_type) && is_dir)
+	if (!ovl_can_move(old))
+		goto out;
+	if (!overwrite && !ovl_can_move(new))
 		goto out;
-
-	if (new->d_inode) {
-		err = ovl_check_sticky(new);
-		if (err)
-			goto out;
-
-		if (d_is_dir(new))
-			new_is_dir = true;
-
-		new_type = ovl_path_type(new);
-		err = -EXDEV;
-		if (!overwrite && OVL_TYPE_MERGE_OR_LOWER(new_type) && new_is_dir)
-			goto out;
-
-		err = 0;
-		if (!OVL_TYPE_UPPER(new_type) && !OVL_TYPE_UPPER(old_type)) {
-			if (ovl_dentry_lower(old)->d_inode ==
-			    ovl_dentry_lower(new)->d_inode)
-				goto out;
-		}
-		if (OVL_TYPE_UPPER(new_type) && OVL_TYPE_UPPER(old_type)) {
-			if (ovl_dentry_upper(old)->d_inode ==
-			    ovl_dentry_upper(new)->d_inode)
-				goto out;
-		}
-	} else {
-		if (ovl_dentry_is_opaque(new))
-			new_type = __OVL_PATH_UPPER;
-		else
-			new_type = __OVL_PATH_UPPER | __OVL_PATH_PURE;
-	}
 
 	err = ovl_want_write(old);
 	if (err)
@@ -862,12 +939,9 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 			goto out_drop_write;
 	}
 
-	old_opaque = !OVL_TYPE_PURE_UPPER(old_type);
-	new_opaque = !OVL_TYPE_PURE_UPPER(new_type);
-
 	old_cred = ovl_override_creds(old->d_sb);
 
-	if (overwrite && OVL_TYPE_MERGE_OR_LOWER(new_type) && new_is_dir) {
+	if (overwrite && new_is_dir && ovl_type_merge_or_lower(new)) {
 		opaquedir = ovl_check_empty_and_clear(new);
 		err = PTR_ERR(opaquedir);
 		if (IS_ERR(opaquedir)) {
@@ -877,15 +951,15 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 	}
 
 	if (overwrite) {
-		if (old_opaque) {
-			if (new->d_inode || !new_opaque) {
+		if (ovl_lower_positive(old)) {
+			if (!ovl_dentry_is_whiteout(new)) {
 				/* Whiteout source */
 				flags |= RENAME_WHITEOUT;
 			} else {
 				/* Switch whiteouts */
 				flags |= RENAME_EXCHANGE;
 			}
-		} else if (is_dir && !new->d_inode && new_opaque) {
+		} else if (is_dir && ovl_dentry_is_whiteout(new)) {
 			flags |= RENAME_EXCHANGE;
 			cleanup_whiteout = true;
 		}
@@ -896,7 +970,6 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 
 	trap = lock_rename(new_upperdir, old_upperdir);
 
-
 	olddentry = lookup_one_len(old->d_name.name, old_upperdir,
 				   old->d_name.len);
 	err = PTR_ERR(olddentry);
@@ -913,6 +986,9 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 	if (IS_ERR(newdentry))
 		goto out_dput_old;
 
+	old_opaque = ovl_dentry_is_opaque(old);
+	new_opaque = ovl_dentry_is_opaque(new);
+
 	err = -ESTALE;
 	if (ovl_dentry_upper(new)) {
 		if (opaquedir) {
@@ -933,54 +1009,31 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 	if (newdentry == trap)
 		goto out_dput;
 
-	if (is_dir && !old_opaque && new_opaque) {
-		err = ovl_set_opaque(olddentry);
+	if (WARN_ON(olddentry->d_inode == newdentry->d_inode))
+		goto out_dput;
+
+	err = 0;
+	if (is_dir) {
+		if (ovl_type_merge_or_lower(old))
+			err = ovl_set_redirect(old, samedir);
+		else if (!old_opaque && ovl_type_merge(new->d_parent))
+			err = ovl_set_opaque(old, olddentry);
 		if (err)
 			goto out_dput;
 	}
-	if (!overwrite && new_is_dir && old_opaque && !new_opaque) {
-		err = ovl_set_opaque(newdentry);
+	if (!overwrite && new_is_dir) {
+		if (ovl_type_merge_or_lower(new))
+			err = ovl_set_redirect(new, samedir);
+		else if (!new_opaque && ovl_type_merge(old->d_parent))
+			err = ovl_set_opaque(new, newdentry);
 		if (err)
 			goto out_dput;
 	}
 
-	if (old_opaque || new_opaque) {
-		err = ovl_do_rename(old_upperdir->d_inode, olddentry,
-				    new_upperdir->d_inode, newdentry,
-				    flags);
-	} else {
-		/* No debug for the plain case */
-		BUG_ON(flags & ~RENAME_EXCHANGE);
-		err = vfs_rename(old_upperdir->d_inode, olddentry,
-				 new_upperdir->d_inode, newdentry,
-				 NULL, flags);
-	}
-
-	if (err) {
-		if (is_dir && !old_opaque && new_opaque)
-			ovl_remove_opaque(olddentry);
-		if (!overwrite && new_is_dir && old_opaque && !new_opaque)
-			ovl_remove_opaque(newdentry);
+	err = ovl_do_rename(old_upperdir->d_inode, olddentry,
+			    new_upperdir->d_inode, newdentry, flags);
+	if (err)
 		goto out_dput;
-	}
-
-	if (is_dir && old_opaque && !new_opaque)
-		ovl_remove_opaque(olddentry);
-	if (!overwrite && new_is_dir && !old_opaque && new_opaque)
-		ovl_remove_opaque(newdentry);
-
-	/*
-	 * Old dentry now lives in different location. Dentries in
-	 * lowerstack are stale. We cannot drop them here because
-	 * access to them is lockless. This could be only pure upper
-	 * or opaque directory - numlower is zero. Or upper non-dir
-	 * entry - its pureness is tracked by flag opaque.
-	 */
-	if (old_opaque != new_opaque) {
-		ovl_dentry_set_opaque(old, new_opaque);
-		if (!overwrite)
-			ovl_dentry_set_opaque(new, old_opaque);
-	}
 
 	if (cleanup_whiteout)
 		ovl_cleanup(old_upperdir->d_inode, newdentry);
@@ -1009,7 +1062,7 @@ const struct inode_operations ovl_dir_inode_operations = {
 	.symlink	= ovl_symlink,
 	.unlink		= ovl_unlink,
 	.rmdir		= ovl_rmdir,
-	.rename		= ovl_rename2,
+	.rename		= ovl_rename,
 	.link		= ovl_link,
 	.setattr	= ovl_setattr,
 	.create		= ovl_create,

fs/overlayfs/inode.c

@@ -13,34 +13,6 @@
 #include <linux/posix_acl.h>
 #include "overlayfs.h"
 
-static int ovl_copy_up_truncate(struct dentry *dentry)
-{
-	int err;
-	struct dentry *parent;
-	struct kstat stat;
-	struct path lowerpath;
-	const struct cred *old_cred;
-
-	parent = dget_parent(dentry);
-	err = ovl_copy_up(parent);
-	if (err)
-		goto out_dput_parent;
-
-	ovl_path_lower(dentry, &lowerpath);
-
-	old_cred = ovl_override_creds(dentry->d_sb);
-	err = vfs_getattr(&lowerpath, &stat);
-	if (!err) {
-		stat.size = 0;
-		err = ovl_copy_up_one(parent, dentry, &lowerpath, &stat);
-	}
-	revert_creds(old_cred);
-
-out_dput_parent:
-	dput(parent);
-	return err;
-}
-
 int ovl_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	int err;
@@ -64,27 +36,10 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr)
 	if (err)
 		goto out;
 
-	if (attr->ia_valid & ATTR_SIZE) {
-		struct inode *realinode = d_inode(ovl_dentry_real(dentry));
-
-		err = -ETXTBSY;
-		if (atomic_read(&realinode->i_writecount) < 0)
-			goto out_drop_write;
-	}
-
 	err = ovl_copy_up(dentry);
 	if (!err) {
-		struct inode *winode = NULL;
-
 		upperdentry = ovl_dentry_upper(dentry);
 
-		if (attr->ia_valid & ATTR_SIZE) {
-			winode = d_inode(upperdentry);
-			err = get_write_access(winode);
-			if (err)
-				goto out_drop_write;
-		}
-
 		if (attr->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID))
 			attr->ia_valid &= ~ATTR_MODE;
 
@@ -95,11 +50,7 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr)
 		if (!err)
 			ovl_copyattr(upperdentry->d_inode, dentry->d_inode);
 		inode_unlock(upperdentry->d_inode);
-
-		if (winode)
-			put_write_access(winode);
 	}
-out_drop_write:
 	ovl_drop_write(dentry);
 out:
 	return err;
@@ -302,10 +253,7 @@ int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags)
 	if (ovl_open_need_copy_up(file_flags, type, realpath.dentry)) {
 		err = ovl_want_write(dentry);
 		if (!err) {
-			if (file_flags & O_TRUNC)
-				err = ovl_copy_up_truncate(dentry);
-			else
-				err = ovl_copy_up(dentry);
+			err = ovl_copy_up_flags(dentry, file_flags);
 			ovl_drop_write(dentry);
 		}
 	}
@@ -354,7 +302,7 @@ static const struct inode_operations ovl_symlink_inode_operations = {
 	.update_time	= ovl_update_time,
 };
 
-static void ovl_fill_inode(struct inode *inode, umode_t mode)
+static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev)
 {
 	inode->i_ino = get_next_ino();
 	inode->i_mode = mode;
@@ -363,8 +311,11 @@ static void ovl_fill_inode(struct inode *inode, umode_t mode)
 	inode->i_acl = inode->i_default_acl = ACL_DONT_CACHE;
 #endif
 
-	mode &= S_IFMT;
-	switch (mode) {
+	switch (mode & S_IFMT) {
+	case S_IFREG:
+		inode->i_op = &ovl_file_inode_operations;
+		break;
+
 	case S_IFDIR:
 		inode->i_op = &ovl_dir_inode_operations;
 		inode->i_fop = &ovl_dir_operations;
@@ -375,26 +326,19 @@ static void ovl_fill_inode(struct inode *inode, umode_t mode)
 		break;
 
 	default:
-		WARN(1, "illegal file type: %i\n", mode);
-		/* Fall through */
-
-	case S_IFREG:
-	case S_IFSOCK:
-	case S_IFBLK:
-	case S_IFCHR:
-	case S_IFIFO:
 		inode->i_op = &ovl_file_inode_operations;
+		init_special_inode(inode, mode, rdev);
 		break;
 	}
 }
 
-struct inode *ovl_new_inode(struct super_block *sb, umode_t mode)
+struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev)
 {
 	struct inode *inode;
 
 	inode = new_inode(sb);
 	if (inode)
-		ovl_fill_inode(inode, mode);
+		ovl_fill_inode(inode, mode, rdev);
 
 	return inode;
 }
@@ -418,7 +362,7 @@ struct inode *ovl_get_inode(struct super_block *sb, struct inode *realinode)
 	inode = iget5_locked(sb, (unsigned long) realinode,
 			     ovl_inode_test, ovl_inode_set, realinode);
 	if (inode && inode->i_state & I_NEW) {
-		ovl_fill_inode(inode, realinode->i_mode);
+		ovl_fill_inode(inode, realinode->i_mode, realinode->i_rdev);
 		set_nlink(inode, realinode->i_nlink);
 		unlock_new_inode(inode);
 	}

fs/overlayfs/namei.c

+/*
+ * Copyright (C) 2011 Novell Inc.
+ * Copyright (C) 2016 Red Hat, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ */
+
+#include <linux/fs.h>
+#include <linux/namei.h>
+#include <linux/xattr.h>
+#include <linux/ratelimit.h>
+#include "overlayfs.h"
+#include "ovl_entry.h"
+
+struct ovl_lookup_data {
+	struct qstr name;
+	bool is_dir;
+	bool opaque;
+	bool stop;
+	bool last;
+	char *redirect;
+};
+
+static int ovl_check_redirect(struct dentry *dentry, struct ovl_lookup_data *d,
+			      size_t prelen, const char *post)
+{
+	int res;
+	char *s, *next, *buf = NULL;
+
+	res = vfs_getxattr(dentry, OVL_XATTR_REDIRECT, NULL, 0);
+	if (res < 0) {
+		if (res == -ENODATA || res == -EOPNOTSUPP)
+			return 0;
+		goto fail;
+	}
+	buf = kzalloc(prelen + res + strlen(post) + 1, GFP_TEMPORARY);
+	if (!buf)
+		return -ENOMEM;
+
+	if (res == 0)
+		goto invalid;
+
+	res = vfs_getxattr(dentry, OVL_XATTR_REDIRECT, buf, res);
+	if (res < 0)
+		goto fail;
+	if (res == 0)
+		goto invalid;
+	if (buf[0] == '/') {
+		for (s = buf; *s++ == '/'; s = next) {
+			next = strchrnul(s, '/');
+			if (s == next)
+				goto invalid;
+		}
+	} else {
+		if (strchr(buf, '/') != NULL)
+			goto invalid;
+
+		memmove(buf + prelen, buf, res);
+		memcpy(buf, d->name.name, prelen);
+	}
+
+	strcat(buf, post);
+	kfree(d->redirect);
+	d->redirect = buf;
+	d->name.name = d->redirect;
+	d->name.len = strlen(d->redirect);
+
+	return 0;
+
+err_free:
+	kfree(buf);
+	return 0;
+fail:
+	pr_warn_ratelimited("overlayfs: failed to get redirect (%i)\n", res);
+	goto err_free;
+invalid:
+	pr_warn_ratelimited("overlayfs: invalid redirect (%s)\n", buf);
+	goto err_free;
+}
+
+static bool ovl_is_opaquedir(struct dentry *dentry)
+{
+	int res;
+	char val;
+
+	if (!d_is_dir(dentry))
+		return false;
+
+	res = vfs_getxattr(dentry, OVL_XATTR_OPAQUE, &val, 1);
+	if (res == 1 && val == 'y')
+		return true;
+
+	return false;
+}
+
+static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d,
+			     const char *name, unsigned int namelen,
+			     size_t prelen, const char *post,
+			     struct dentry **ret)
+{
+	struct dentry *this;
+	int err;
+
+	this = lookup_one_len_unlocked(name, base, namelen);
+	if (IS_ERR(this)) {
+		err = PTR_ERR(this);
+		this = NULL;
+		if (err == -ENOENT || err == -ENAMETOOLONG)
+			goto out;
+		goto out_err;
+	}
+	if (!this->d_inode)
+		goto put_and_out;
+
+	if (ovl_dentry_weird(this)) {
+		/* Don't support traversing automounts and other weirdness */
+		err = -EREMOTE;
+		goto out_err;
+	}
+	if (ovl_is_whiteout(this)) {
+		d->stop = d->opaque = true;
+		goto put_and_out;
+	}
+	if (!d_can_lookup(this)) {
+		d->stop = true;
+		if (d->is_dir)
+			goto put_and_out;
+		goto out;
+	}
+	d->is_dir = true;
+	if (!d->last && ovl_is_opaquedir(this)) {
+		d->stop = d->opaque = true;
+		goto out;
+	}
+	err = ovl_check_redirect(this, d, prelen, post);
+	if (err)
+		goto out_err;
+out:
+	*ret = this;
+	return 0;
+
+put_and_out:
+	dput(this);
+	this = NULL;
+	goto out;
+
+out_err:
+	dput(this);
+	return err;
+}
+
+static int ovl_lookup_layer(struct dentry *base, struct ovl_lookup_data *d,
+			    struct dentry **ret)
+{
+	const char *s = d->name.name;
+	struct dentry *dentry = NULL;
+	int err;
+
+	if (*s != '/')
+		return ovl_lookup_single(base, d, d->name.name, d->name.len,
+					 0, "", ret);
+
+	while (*s++ == '/' && !IS_ERR_OR_NULL(base) && d_can_lookup(base)) {
+		const char *next = strchrnul(s, '/');
+		size_t slen = strlen(s);
+
+		if (WARN_ON(slen > d->name.len) ||
+		    WARN_ON(strcmp(d->name.name + d->name.len - slen, s)))
+			return -EIO;
+
+		err = ovl_lookup_single(base, d, s, next - s,
+					d->name.len - slen, next, &base);
+		dput(dentry);
+		if (err)
+			return err;
+		dentry = base;
+		s = next;
+	}
+	*ret = dentry;
+	return 0;
+}
+
+/*
+ * 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)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	BUG_ON(idx < 0);
+	if (idx == 0) {
+		ovl_path_upper(dentry, path);
+		if (path->dentry)
+			return oe->numlower ? 1 : -1;
+		idx++;
+	}
+	BUG_ON(idx > oe->numlower);
+	*path = oe->lowerstack[idx - 1];
+
+	return (idx < oe->numlower) ? idx + 1 : -1;
+}
+
+struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
+			  unsigned int flags)
+{
+	struct ovl_entry *oe;
+	const struct cred *old_cred;
+	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+	struct ovl_entry *poe = dentry->d_parent->d_fsdata;
+	struct path *stack = NULL;
+	struct dentry *upperdir, *upperdentry = NULL;
+	unsigned int ctr = 0;
+	struct inode *inode = NULL;
+	bool upperopaque = false;
+	char *upperredirect = NULL;
+	struct dentry *this;
+	unsigned int i;
+	int err;
+	struct ovl_lookup_data d = {
+		.name = dentry->d_name,
+		.is_dir = false,
+		.opaque = false,
+		.stop = false,
+		.last = !poe->numlower,
+		.redirect = NULL,
+	};
+
+	if (dentry->d_name.len > ofs->namelen)
+		return ERR_PTR(-ENAMETOOLONG);
+
+	old_cred = ovl_override_creds(dentry->d_sb);
+	upperdir = ovl_upperdentry_dereference(poe);
+	if (upperdir) {
+		err = ovl_lookup_layer(upperdir, &d, &upperdentry);
+		if (err)
+			goto out;
+
+		if (upperdentry && unlikely(ovl_dentry_remote(upperdentry))) {
+			dput(upperdentry);
+			err = -EREMOTE;
+			goto out;
+		}
+
+		if (d.redirect) {
+			upperredirect = kstrdup(d.redirect, GFP_KERNEL);
+			if (!upperredirect)
+				goto out_put_upper;
+			if (d.redirect[0] == '/')
+				poe = dentry->d_sb->s_root->d_fsdata;
+		}
+		upperopaque = d.opaque;
+	}
+
+	if (!d.stop && poe->numlower) {
+		err = -ENOMEM;
+		stack = kcalloc(ofs->numlower, sizeof(struct path),
+				GFP_TEMPORARY);
+		if (!stack)
+			goto out_put_upper;
+	}
+
+	for (i = 0; !d.stop && i < poe->numlower; i++) {
+		struct path lowerpath = poe->lowerstack[i];
+
+		d.last = i == poe->numlower - 1;
+		err = ovl_lookup_layer(lowerpath.dentry, &d, &this);
+		if (err)
+			goto out_put;
+
+		if (!this)
+			continue;
+
+		stack[ctr].dentry = this;
+		stack[ctr].mnt = lowerpath.mnt;
+		ctr++;
+
+		if (d.stop)
+			break;
+
+		if (d.redirect &&
+		    d.redirect[0] == '/' &&
+		    poe != dentry->d_sb->s_root->d_fsdata) {
+			poe = dentry->d_sb->s_root->d_fsdata;
+
+			/* Find the current layer on the root dentry */
+			for (i = 0; i < poe->numlower; i++)
+				if (poe->lowerstack[i].mnt == lowerpath.mnt)
+					break;
+			if (WARN_ON(i == poe->numlower))
+				break;
+		}
+	}
+
+	oe = ovl_alloc_entry(ctr);
+	err = -ENOMEM;
+	if (!oe)
+		goto out_put;
+
+	if (upperdentry || ctr) {
+		struct dentry *realdentry;
+		struct inode *realinode;
+
+		realdentry = upperdentry ? upperdentry : stack[0].dentry;
+		realinode = d_inode(realdentry);
+
+		err = -ENOMEM;
+		if (upperdentry && !d_is_dir(upperdentry)) {
+			inode = ovl_get_inode(dentry->d_sb, realinode);
+		} else {
+			inode = ovl_new_inode(dentry->d_sb, realinode->i_mode,
+					      realinode->i_rdev);
+			if (inode)
+				ovl_inode_init(inode, realinode, !!upperdentry);
+		}
+		if (!inode)
+			goto out_free_oe;
+		ovl_copyattr(realdentry->d_inode, inode);
+	}
+
+	revert_creds(old_cred);
+	oe->opaque = upperopaque;
+	oe->redirect = upperredirect;
+	oe->__upperdentry = upperdentry;
+	memcpy(oe->lowerstack, stack, sizeof(struct path) * ctr);
+	kfree(stack);
+	kfree(d.redirect);
+	dentry->d_fsdata = oe;
+	d_add(dentry, inode);
+
+	return NULL;
+
+out_free_oe:
+	kfree(oe);
+out_put:
+	for (i = 0; i < ctr; i++)
+		dput(stack[i].dentry);
+	kfree(stack);
+out_put_upper:
+	dput(upperdentry);
+	kfree(upperredirect);
+out:
+	kfree(d.redirect);
+	revert_creds(old_cred);
+	return ERR_PTR(err);
+}
+
+bool ovl_lower_positive(struct dentry *dentry)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+	struct ovl_entry *poe = dentry->d_parent->d_fsdata;
+	const struct qstr *name = &dentry->d_name;
+	unsigned int i;
+	bool positive = false;
+	bool done = false;
+
+	/*
+	 * If dentry is negative, then lower is positive iff this is a
+	 * whiteout.
+	 */
+	if (!dentry->d_inode)
+		return oe->opaque;
+
+	/* Negative upper -> positive lower */
+	if (!oe->__upperdentry)
+		return true;
+
+	/* Positive upper -> have to look up lower to see whether it exists */
+	for (i = 0; !done && !positive && i < poe->numlower; i++) {
+		struct dentry *this;
+		struct dentry *lowerdir = poe->lowerstack[i].dentry;
+
+		this = lookup_one_len_unlocked(name->name, lowerdir,
+					       name->len);
+		if (IS_ERR(this)) {
+			switch (PTR_ERR(this)) {
+			case -ENOENT:
+			case -ENAMETOOLONG:
+				break;
+
+			default:
+				/*
+				 * Assume something is there, we just couldn't
+				 * access it.
+				 */
+				positive = true;
+				break;
+			}
+		} else {
+			if (this->d_inode) {
+				positive = !ovl_is_whiteout(this);
+				done = true;
+			}
+			dput(this);
+		}
+	}
+
+	return positive;
+}

fs/overlayfs/overlayfs.h

@@ -9,23 +9,17 @@
 
 #include <linux/kernel.h>
 
-struct ovl_entry;
-
 enum ovl_path_type {
-	__OVL_PATH_PURE		= (1 << 0),
-	__OVL_PATH_UPPER	= (1 << 1),
-	__OVL_PATH_MERGE	= (1 << 2),
+	__OVL_PATH_UPPER	= (1 << 0),
+	__OVL_PATH_MERGE	= (1 << 1),
 };
 
 #define OVL_TYPE_UPPER(type)	((type) & __OVL_PATH_UPPER)
 #define OVL_TYPE_MERGE(type)	((type) & __OVL_PATH_MERGE)
-#define OVL_TYPE_PURE_UPPER(type) ((type) & __OVL_PATH_PURE)
-#define OVL_TYPE_MERGE_OR_LOWER(type) \
-	(OVL_TYPE_MERGE(type) || !OVL_TYPE_UPPER(type))
-
 
 #define OVL_XATTR_PREFIX XATTR_TRUSTED_PREFIX "overlay."
 #define OVL_XATTR_OPAQUE OVL_XATTR_PREFIX "opaque"
+#define OVL_XATTR_REDIRECT OVL_XATTR_PREFIX "redirect"
 
 #define OVL_ISUPPER_MASK 1UL
 
@@ -143,35 +137,43 @@ static inline struct inode *ovl_inode_real(struct inode *inode, bool *is_upper)
 	return (struct inode *) (x & ~OVL_ISUPPER_MASK);
 }
 
+/* util.c */
+int ovl_want_write(struct dentry *dentry);
+void ovl_drop_write(struct dentry *dentry);
+struct dentry *ovl_workdir(struct dentry *dentry);
+const struct cred *ovl_override_creds(struct super_block *sb);
+struct ovl_entry *ovl_alloc_entry(unsigned int numlower);
+bool ovl_dentry_remote(struct dentry *dentry);
+bool ovl_dentry_weird(struct dentry *dentry);
 enum ovl_path_type ovl_path_type(struct dentry *dentry);
-u64 ovl_dentry_version_get(struct dentry *dentry);
-void ovl_dentry_version_inc(struct dentry *dentry);
 void ovl_path_upper(struct dentry *dentry, struct path *path);
 void ovl_path_lower(struct dentry *dentry, struct path *path);
 enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path);
-int ovl_path_next(int idx, struct dentry *dentry, struct path *path);
 struct dentry *ovl_dentry_upper(struct dentry *dentry);
 struct dentry *ovl_dentry_lower(struct dentry *dentry);
 struct dentry *ovl_dentry_real(struct dentry *dentry);
-struct vfsmount *ovl_entry_mnt_real(struct ovl_entry *oe, struct inode *inode,
-				    bool is_upper);
 struct ovl_dir_cache *ovl_dir_cache(struct dentry *dentry);
 void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache);
-struct dentry *ovl_workdir(struct dentry *dentry);
-int ovl_want_write(struct dentry *dentry);
-void ovl_drop_write(struct dentry *dentry);
 bool ovl_dentry_is_opaque(struct dentry *dentry);
-void ovl_dentry_set_opaque(struct dentry *dentry, bool opaque);
-bool ovl_is_whiteout(struct dentry *dentry);
-const struct cred *ovl_override_creds(struct super_block *sb);
+bool ovl_dentry_is_whiteout(struct dentry *dentry);
+void ovl_dentry_set_opaque(struct dentry *dentry);
+bool ovl_redirect_dir(struct super_block *sb);
+void ovl_clear_redirect_dir(struct super_block *sb);
+const char *ovl_dentry_get_redirect(struct dentry *dentry);
+void ovl_dentry_set_redirect(struct dentry *dentry, const char *redirect);
 void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry);
+void ovl_inode_init(struct inode *inode, struct inode *realinode,
+		    bool is_upper);
 void ovl_inode_update(struct inode *inode, struct inode *upperinode);
-struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
-			  unsigned int flags);
+void ovl_dentry_version_inc(struct dentry *dentry);
+u64 ovl_dentry_version_get(struct dentry *dentry);
+bool ovl_is_whiteout(struct dentry *dentry);
 struct file *ovl_path_open(struct path *path, int flags);
 
-struct dentry *ovl_upper_create(struct dentry *upperdir, struct dentry *dentry,
-				struct kstat *stat, const char *link);
+/* namei.c */
+int ovl_path_next(int idx, struct dentry *dentry, struct path *path);
+struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags);
+bool ovl_lower_positive(struct dentry *dentry);
 
 /* readdir.c */
 extern const struct file_operations ovl_dir_operations;
@@ -195,7 +197,7 @@ int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags);
 int ovl_update_time(struct inode *inode, struct timespec *ts, int flags);
 bool ovl_is_private_xattr(const char *name);
 
-struct inode *ovl_new_inode(struct super_block *sb, umode_t mode);
+struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev);
 struct inode *ovl_get_inode(struct super_block *sb, struct inode *realinode);
 static inline void ovl_copyattr(struct inode *from, struct inode *to)
 {
@@ -210,14 +212,18 @@ static inline void ovl_copyattr(struct inode *from, struct inode *to)
 /* dir.c */
 extern const struct inode_operations ovl_dir_inode_operations;
 struct dentry *ovl_lookup_temp(struct dentry *workdir, struct dentry *dentry);
+struct cattr {
+	dev_t rdev;
+	umode_t mode;
+	const char *link;
+};
 int ovl_create_real(struct inode *dir, struct dentry *newdentry,
-		    struct kstat *stat, const char *link,
+		    struct cattr *attr,
 		    struct dentry *hardlink, bool debug);
 void ovl_cleanup(struct inode *dir, struct dentry *dentry);
 
 /* copy_up.c */
 int ovl_copy_up(struct dentry *dentry);
-int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
-		    struct path *lowerpath, struct kstat *stat);
+int ovl_copy_up_flags(struct dentry *dentry, int flags);
 int ovl_copy_xattr(struct dentry *old, struct dentry *new);
 int ovl_set_attr(struct dentry *upper, struct kstat *stat);

fs/overlayfs/ovl_entry.h

+/*
+ *
+ * Copyright (C) 2011 Novell Inc.
+ * Copyright (C) 2016 Red Hat, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ */
+
+struct ovl_config {
+	char *lowerdir;
+	char *upperdir;
+	char *workdir;
+	bool default_permissions;
+	bool redirect_dir;
+};
+
+/* private information held for overlayfs's superblock */
+struct ovl_fs {
+	struct vfsmount *upper_mnt;
+	unsigned numlower;
+	struct vfsmount **lower_mnt;
+	struct dentry *workdir;
+	long namelen;
+	/* pathnames of lower and upper dirs, for show_options */
+	struct ovl_config config;
+	/* creds of process who forced instantiation of super block */
+	const struct cred *creator_cred;
+};
+
+/* private information held for every overlayfs dentry */
+struct ovl_entry {
+	struct dentry *__upperdentry;
+	struct ovl_dir_cache *cache;
+	union {
+		struct {
+			u64 version;
+			const char *redirect;
+			bool opaque;
+		};
+		struct rcu_head rcu;
+	};
+	unsigned numlower;
+	struct path lowerstack[];
+};
+
+struct ovl_entry *ovl_alloc_entry(unsigned int numlower);
+
+static inline struct dentry *ovl_upperdentry_dereference(struct ovl_entry *oe)
+{
+	return lockless_dereference(oe->__upperdentry);
+}

fs/overlayfs/super.c

@@ -9,280 +9,29 @@
 
 #include <linux/fs.h>
 #include <linux/namei.h>
-#include <linux/pagemap.h>
 #include <linux/xattr.h>
-#include <linux/security.h>
 #include <linux/mount.h>
-#include <linux/slab.h>
 #include <linux/parser.h>
 #include <linux/module.h>
-#include <linux/sched.h>
 #include <linux/statfs.h>
 #include <linux/seq_file.h>
 #include <linux/posix_acl_xattr.h>
 #include "overlayfs.h"
+#include "ovl_entry.h"
 
 MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
 MODULE_DESCRIPTION("Overlay filesystem");
 MODULE_LICENSE("GPL");
 
-struct ovl_config {
-	char *lowerdir;
-	char *upperdir;
-	char *workdir;
-	bool default_permissions;
-};
-
-/* private information held for overlayfs's superblock */
-struct ovl_fs {
-	struct vfsmount *upper_mnt;
-	unsigned numlower;
-	struct vfsmount **lower_mnt;
-	struct dentry *workdir;
-	long lower_namelen;
-	/* pathnames of lower and upper dirs, for show_options */
-	struct ovl_config config;
-	/* creds of process who forced instantiation of super block */
-	const struct cred *creator_cred;
-};
 
 struct ovl_dir_cache;
 
-/* private information held for every overlayfs dentry */
-struct ovl_entry {
-	struct dentry *__upperdentry;
-	struct ovl_dir_cache *cache;
-	union {
-		struct {
-			u64 version;
-			bool opaque;
-		};
-		struct rcu_head rcu;
-	};
-	unsigned numlower;
-	struct path lowerstack[];
-};
-
 #define OVL_MAX_STACK 500
 
-static struct dentry *__ovl_dentry_lower(struct ovl_entry *oe)
-{
-	return oe->numlower ? oe->lowerstack[0].dentry : NULL;
-}
-
-enum ovl_path_type ovl_path_type(struct dentry *dentry)
-{
-	struct ovl_entry *oe = dentry->d_fsdata;
-	enum ovl_path_type type = 0;
-
-	if (oe->__upperdentry) {
-		type = __OVL_PATH_UPPER;
-
-		/*
-		 * Non-dir dentry can hold lower dentry from previous
-		 * location. Its purity depends only on opaque flag.
-		 */
-		if (oe->numlower && S_ISDIR(dentry->d_inode->i_mode))
-			type |= __OVL_PATH_MERGE;
-		else if (!oe->opaque)
-			type |= __OVL_PATH_PURE;
-	} else {
-		if (oe->numlower > 1)
-			type |= __OVL_PATH_MERGE;
-	}
-	return type;
-}
-
-static struct dentry *ovl_upperdentry_dereference(struct ovl_entry *oe)
-{
-	return lockless_dereference(oe->__upperdentry);
-}
-
-void ovl_path_upper(struct dentry *dentry, struct path *path)
-{
-	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
-	struct ovl_entry *oe = dentry->d_fsdata;
-
-	path->mnt = ofs->upper_mnt;
-	path->dentry = ovl_upperdentry_dereference(oe);
-}
-
-enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path)
-{
-	enum ovl_path_type type = ovl_path_type(dentry);
-
-	if (!OVL_TYPE_UPPER(type))
-		ovl_path_lower(dentry, path);
-	else
-		ovl_path_upper(dentry, path);
-
-	return type;
-}
-
-struct dentry *ovl_dentry_upper(struct dentry *dentry)
-{
-	struct ovl_entry *oe = dentry->d_fsdata;
-
-	return ovl_upperdentry_dereference(oe);
-}
-
-struct dentry *ovl_dentry_lower(struct dentry *dentry)
-{
-	struct ovl_entry *oe = dentry->d_fsdata;
-
-	return __ovl_dentry_lower(oe);
-}
-
-struct dentry *ovl_dentry_real(struct dentry *dentry)
-{
-	struct ovl_entry *oe = dentry->d_fsdata;
-	struct dentry *realdentry;
-
-	realdentry = ovl_upperdentry_dereference(oe);
-	if (!realdentry)
-		realdentry = __ovl_dentry_lower(oe);
-
-	return realdentry;
-}
-
-static void ovl_inode_init(struct inode *inode, struct inode *realinode,
-			   bool is_upper)
-{
-	WRITE_ONCE(inode->i_private, (unsigned long) realinode |
-		   (is_upper ? OVL_ISUPPER_MASK : 0));
-}
-
-struct vfsmount *ovl_entry_mnt_real(struct ovl_entry *oe, struct inode *inode,
-				    bool is_upper)
-{
-	if (is_upper) {
-		struct ovl_fs *ofs = inode->i_sb->s_fs_info;
-
-		return ofs->upper_mnt;
-	} else {
-		return oe->numlower ? oe->lowerstack[0].mnt : NULL;
-	}
-}
-
-struct ovl_dir_cache *ovl_dir_cache(struct dentry *dentry)
-{
-	struct ovl_entry *oe = dentry->d_fsdata;
-
-	return oe->cache;
-}
-
-void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache)
-{
-	struct ovl_entry *oe = dentry->d_fsdata;
-
-	oe->cache = cache;
-}
-
-void ovl_path_lower(struct dentry *dentry, struct path *path)
-{
-	struct ovl_entry *oe = dentry->d_fsdata;
-
-	*path = oe->numlower ? oe->lowerstack[0] : (struct path) { NULL, NULL };
-}
-
-int ovl_want_write(struct dentry *dentry)
-{
-	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
-	return mnt_want_write(ofs->upper_mnt);
-}
-
-void ovl_drop_write(struct dentry *dentry)
-{
-	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
-	mnt_drop_write(ofs->upper_mnt);
-}
-
-struct dentry *ovl_workdir(struct dentry *dentry)
-{
-	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
-	return ofs->workdir;
-}
-
-bool ovl_dentry_is_opaque(struct dentry *dentry)
-{
-	struct ovl_entry *oe = dentry->d_fsdata;
-	return oe->opaque;
-}
-
-void ovl_dentry_set_opaque(struct dentry *dentry, bool opaque)
-{
-	struct ovl_entry *oe = dentry->d_fsdata;
-	oe->opaque = opaque;
-}
-
-void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry)
-{
-	struct ovl_entry *oe = dentry->d_fsdata;
-
-	WARN_ON(!inode_is_locked(upperdentry->d_parent->d_inode));
-	WARN_ON(oe->__upperdentry);
-	/*
-	 * Make sure upperdentry is consistent before making it visible to
-	 * ovl_upperdentry_dereference().
-	 */
-	smp_wmb();
-	oe->__upperdentry = upperdentry;
-}
-
-void ovl_inode_update(struct inode *inode, struct inode *upperinode)
-{
-	WARN_ON(!upperinode);
-	WARN_ON(!inode_unhashed(inode));
-	WRITE_ONCE(inode->i_private,
-		   (unsigned long) upperinode | OVL_ISUPPER_MASK);
-	if (!S_ISDIR(upperinode->i_mode))
-		__insert_inode_hash(inode, (unsigned long) upperinode);
-}
-
-void ovl_dentry_version_inc(struct dentry *dentry)
-{
-	struct ovl_entry *oe = dentry->d_fsdata;
-
-	WARN_ON(!inode_is_locked(dentry->d_inode));
-	oe->version++;
-}
-
-u64 ovl_dentry_version_get(struct dentry *dentry)
-{
-	struct ovl_entry *oe = dentry->d_fsdata;
-
-	WARN_ON(!inode_is_locked(dentry->d_inode));
-	return oe->version;
-}
-
-bool ovl_is_whiteout(struct dentry *dentry)
-{
-	struct inode *inode = dentry->d_inode;
-
-	return inode && IS_WHITEOUT(inode);
-}
-
-const struct cred *ovl_override_creds(struct super_block *sb)
-{
-	struct ovl_fs *ofs = sb->s_fs_info;
-
-	return override_creds(ofs->creator_cred);
-}
-
-static bool ovl_is_opaquedir(struct dentry *dentry)
-{
-	int res;
-	char val;
-
-	if (!d_is_dir(dentry))
-		return false;
-
-	res = vfs_getxattr(dentry, OVL_XATTR_OPAQUE, &val, 1);
-	if (res == 1 && val == 'y')
-		return true;
-
-	return false;
-}
+static bool ovl_redirect_dir_def = IS_ENABLED(CONFIG_OVERLAY_FS_REDIRECT_DIR);
+module_param_named(redirect_dir, ovl_redirect_dir_def, bool, 0644);
+MODULE_PARM_DESC(ovl_redirect_dir_def,
+		 "Default to on or off for the redirect_dir feature");
 
 static void ovl_dentry_release(struct dentry *dentry)
 {
@@ -292,6 +41,7 @@ static void ovl_dentry_release(struct dentry *dentry)
 		unsigned int i;
 
 		dput(oe->__upperdentry);
+		kfree(oe->redirect);
 		for (i = 0; i < oe->numlower; i++)
 			dput(oe->lowerstack[i].dentry);
 		kfree_rcu(oe, rcu);
@@ -304,7 +54,7 @@ static struct dentry *ovl_d_real(struct dentry *dentry,
 {
 	struct dentry *real;
 
-	if (d_is_dir(dentry)) {
+	if (!d_is_reg(dentry)) {
 		if (!inode || inode == d_inode(dentry))
 			return dentry;
 		goto bug;
@@ -392,226 +142,6 @@ static const struct dentry_operations ovl_reval_dentry_operations = {
 	.d_weak_revalidate = ovl_dentry_weak_revalidate,
 };
 
-static struct ovl_entry *ovl_alloc_entry(unsigned int numlower)
-{
-	size_t size = offsetof(struct ovl_entry, lowerstack[numlower]);
-	struct ovl_entry *oe = kzalloc(size, GFP_KERNEL);
-
-	if (oe)
-		oe->numlower = numlower;
-
-	return oe;
-}
-
-static bool ovl_dentry_remote(struct dentry *dentry)
-{
-	return dentry->d_flags &
-		(DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE |
-		 DCACHE_OP_REAL);
-}
-
-static bool ovl_dentry_weird(struct dentry *dentry)
-{
-	return dentry->d_flags & (DCACHE_NEED_AUTOMOUNT |
-				  DCACHE_MANAGE_TRANSIT |
-				  DCACHE_OP_HASH |
-				  DCACHE_OP_COMPARE);
-}
-
-static inline struct dentry *ovl_lookup_real(struct dentry *dir,
-					     const struct qstr *name)
-{
-	struct dentry *dentry;
-
-	dentry = lookup_one_len_unlocked(name->name, dir, name->len);
-
-	if (IS_ERR(dentry)) {
-		if (PTR_ERR(dentry) == -ENOENT)
-			dentry = NULL;
-	} else if (!dentry->d_inode) {
-		dput(dentry);
-		dentry = NULL;
-	} else if (ovl_dentry_weird(dentry)) {
-		dput(dentry);
-		/* Don't support traversing automounts and other weirdness */
-		dentry = ERR_PTR(-EREMOTE);
-	}
-	return dentry;
-}
-
-/*
- * 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)
-{
-	struct ovl_entry *oe = dentry->d_fsdata;
-
-	BUG_ON(idx < 0);
-	if (idx == 0) {
-		ovl_path_upper(dentry, path);
-		if (path->dentry)
-			return oe->numlower ? 1 : -1;
-		idx++;
-	}
-	BUG_ON(idx > oe->numlower);
-	*path = oe->lowerstack[idx - 1];
-
-	return (idx < oe->numlower) ? idx + 1 : -1;
-}
-
-struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
-			  unsigned int flags)
-{
-	struct ovl_entry *oe;
-	const struct cred *old_cred;
-	struct ovl_entry *poe = dentry->d_parent->d_fsdata;
-	struct path *stack = NULL;
-	struct dentry *upperdir, *upperdentry = NULL;
-	unsigned int ctr = 0;
-	struct inode *inode = NULL;
-	bool upperopaque = false;
-	struct dentry *this, *prev = NULL;
-	unsigned int i;
-	int err;
-
-	old_cred = ovl_override_creds(dentry->d_sb);
-	upperdir = ovl_upperdentry_dereference(poe);
-	if (upperdir) {
-		this = ovl_lookup_real(upperdir, &dentry->d_name);
-		err = PTR_ERR(this);
-		if (IS_ERR(this))
-			goto out;
-
-		if (this) {
-			if (unlikely(ovl_dentry_remote(this))) {
-				dput(this);
-				err = -EREMOTE;
-				goto out;
-			}
-			if (ovl_is_whiteout(this)) {
-				dput(this);
-				this = NULL;
-				upperopaque = true;
-			} else if (poe->numlower && ovl_is_opaquedir(this)) {
-				upperopaque = true;
-			}
-		}
-		upperdentry = prev = this;
-	}
-
-	if (!upperopaque && poe->numlower) {
-		err = -ENOMEM;
-		stack = kcalloc(poe->numlower, sizeof(struct path), GFP_KERNEL);
-		if (!stack)
-			goto out_put_upper;
-	}
-
-	for (i = 0; !upperopaque && i < poe->numlower; i++) {
-		bool opaque = false;
-		struct path lowerpath = poe->lowerstack[i];
-
-		this = ovl_lookup_real(lowerpath.dentry, &dentry->d_name);
-		err = PTR_ERR(this);
-		if (IS_ERR(this)) {
-			/*
-			 * If it's positive, then treat ENAMETOOLONG as ENOENT.
-			 */
-			if (err == -ENAMETOOLONG && (upperdentry || ctr))
-				continue;
-			goto out_put;
-		}
-		if (!this)
-			continue;
-		if (ovl_is_whiteout(this)) {
-			dput(this);
-			break;
-		}
-		/*
-		 * Only makes sense to check opaque dir if this is not the
-		 * lowermost layer.
-		 */
-		if (i < poe->numlower - 1 && ovl_is_opaquedir(this))
-			opaque = true;
-
-		if (prev && (!S_ISDIR(prev->d_inode->i_mode) ||
-			     !S_ISDIR(this->d_inode->i_mode))) {
-			/*
-			 * FIXME: check for upper-opaqueness maybe better done
-			 * in remove code.
-			 */
-			if (prev == upperdentry)
-				upperopaque = true;
-			dput(this);
-			break;
-		}
-		/*
-		 * If this is a non-directory then stop here.
-		 */
-		if (!S_ISDIR(this->d_inode->i_mode))
-			opaque = true;
-
-		stack[ctr].dentry = this;
-		stack[ctr].mnt = lowerpath.mnt;
-		ctr++;
-		prev = this;
-		if (opaque)
-			break;
-	}
-
-	oe = ovl_alloc_entry(ctr);
-	err = -ENOMEM;
-	if (!oe)
-		goto out_put;
-
-	if (upperdentry || ctr) {
-		struct dentry *realdentry;
-		struct inode *realinode;
-
-		realdentry = upperdentry ? upperdentry : stack[0].dentry;
-		realinode = d_inode(realdentry);
-
-		err = -ENOMEM;
-		if (upperdentry && !d_is_dir(upperdentry)) {
-			inode = ovl_get_inode(dentry->d_sb, realinode);
-		} else {
-			inode = ovl_new_inode(dentry->d_sb, realinode->i_mode);
-			if (inode)
-				ovl_inode_init(inode, realinode, !!upperdentry);
-		}
-		if (!inode)
-			goto out_free_oe;
-		ovl_copyattr(realdentry->d_inode, inode);
-	}
-
-	revert_creds(old_cred);
-	oe->opaque = upperopaque;
-	oe->__upperdentry = upperdentry;
-	memcpy(oe->lowerstack, stack, sizeof(struct path) * ctr);
-	kfree(stack);
-	dentry->d_fsdata = oe;
-	d_add(dentry, inode);
-
-	return NULL;
-
-out_free_oe:
-	kfree(oe);
-out_put:
-	for (i = 0; i < ctr; i++)
-		dput(stack[i].dentry);
-	kfree(stack);
-out_put_upper:
-	dput(upperdentry);
-out:
-	revert_creds(old_cred);
-	return ERR_PTR(err);
-}
-
-struct file *ovl_path_open(struct path *path, int flags)
-{
-	return dentry_open(path, flags | O_NOATIME, current_cred());
-}
-
 static void ovl_put_super(struct super_block *sb)
 {
 	struct ovl_fs *ufs = sb->s_fs_info;
@@ -649,7 +179,7 @@ static int ovl_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 	err = vfs_statfs(&path, buf);
 	if (!err) {
-		buf->f_namelen = max(buf->f_namelen, ofs->lower_namelen);
+		buf->f_namelen = ofs->namelen;
 		buf->f_type = OVERLAYFS_SUPER_MAGIC;
 	}
 
@@ -674,6 +204,9 @@ static int ovl_show_options(struct seq_file *m, struct dentry *dentry)
 	}
 	if (ufs->config.default_permissions)
 		seq_puts(m, ",default_permissions");
+	if (ufs->config.redirect_dir != ovl_redirect_dir_def)
+		seq_printf(m, ",redirect_dir=%s",
+			   ufs->config.redirect_dir ? "on" : "off");
 	return 0;
 }
 
@@ -700,6 +233,8 @@ enum {
 	OPT_UPPERDIR,
 	OPT_WORKDIR,
 	OPT_DEFAULT_PERMISSIONS,
+	OPT_REDIRECT_DIR_ON,
+	OPT_REDIRECT_DIR_OFF,
 	OPT_ERR,
 };
 
@@ -708,6 +243,8 @@ static const match_table_t ovl_tokens = {
 	{OPT_UPPERDIR,			"upperdir=%s"},
 	{OPT_WORKDIR,			"workdir=%s"},
 	{OPT_DEFAULT_PERMISSIONS,	"default_permissions"},
+	{OPT_REDIRECT_DIR_ON,		"redirect_dir=on"},
+	{OPT_REDIRECT_DIR_OFF,		"redirect_dir=off"},
 	{OPT_ERR,			NULL}
 };
 
@@ -772,6 +309,14 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
 			config->default_permissions = true;
 			break;
 
+		case OPT_REDIRECT_DIR_ON:
+			config->redirect_dir = true;
+			break;
+
+		case OPT_REDIRECT_DIR_OFF:
+			config->redirect_dir = false;
+			break;
+
 		default:
 			pr_err("overlayfs: unrecognized mount option \"%s\" or missing value\n", p);
 			return -EINVAL;
@@ -809,12 +354,9 @@ static struct dentry *ovl_workdir_create(struct vfsmount *mnt,
 			      strlen(OVL_WORKDIR_NAME));
 
 	if (!IS_ERR(work)) {
-		struct kstat stat = {
-			.mode = S_IFDIR | 0,
-		};
 		struct iattr attr = {
 			.ia_valid = ATTR_MODE,
-			.ia_mode = stat.mode,
+			.ia_mode = S_IFDIR | 0,
 		};
 
 		if (work->d_inode) {
@@ -828,7 +370,9 @@ static struct dentry *ovl_workdir_create(struct vfsmount *mnt,
 			goto retry;
 		}
 
-		err = ovl_create_real(dir, work, &stat, NULL, NULL, true);
+		err = ovl_create_real(dir, work,
+				      &(struct cattr){.mode = S_IFDIR | 0},
+				      NULL, true);
 		if (err)
 			goto out_dput;
 
@@ -903,7 +447,7 @@ static int ovl_mount_dir_noesc(const char *name, struct path *path)
 		pr_err("overlayfs: filesystem on '%s' not supported\n", name);
 		goto out_put;
 	}
-	if (!S_ISDIR(path->dentry->d_inode->i_mode)) {
+	if (!d_is_dir(path->dentry)) {
 		pr_err("overlayfs: '%s' not a directory\n", name);
 		goto out_put;
 	}
@@ -936,22 +480,33 @@ static int ovl_mount_dir(const char *name, struct path *path)
 	return err;
 }
 
-static int ovl_lower_dir(const char *name, struct path *path, long *namelen,
-			 int *stack_depth, bool *remote)
+static int ovl_check_namelen(struct path *path, struct ovl_fs *ofs,
+			     const char *name)
 {
-	int err;
 	struct kstatfs statfs;
+	int err = vfs_statfs(path, &statfs);
+
+	if (err)
+		pr_err("overlayfs: statfs failed on '%s'\n", name);
+	else
+		ofs->namelen = max(ofs->namelen, statfs.f_namelen);
+
+	return err;
+}
+
+static int ovl_lower_dir(const char *name, struct path *path,
+			 struct ovl_fs *ofs, int *stack_depth, bool *remote)
+{
+	int err;
 
 	err = ovl_mount_dir_noesc(name, path);
 	if (err)
 		goto out;
 
-	err = vfs_statfs(path, &statfs);
-	if (err) {
-		pr_err("overlayfs: statfs failed on '%s'\n", name);
+	err = ovl_check_namelen(path, ofs, name);
+	if (err)
 		goto out_put;
-	}
-	*namelen = max(*namelen, statfs.f_namelen);
+
 	*stack_depth = max(*stack_depth, path->mnt->mnt_sb->s_stack_depth);
 
 	if (ovl_dentry_remote(path->dentry))
@@ -1067,7 +622,7 @@ static int ovl_own_xattr_get(const struct xattr_handler *handler,
 			     struct dentry *dentry, struct inode *inode,
 			     const char *name, void *buffer, size_t size)
 {
-	return -EPERM;
+	return -EOPNOTSUPP;
 }
 
 static int ovl_own_xattr_set(const struct xattr_handler *handler,
@@ -1075,7 +630,7 @@ static int ovl_own_xattr_set(const struct xattr_handler *handler,
 			     const char *name, const void *value,
 			     size_t size, int flags)
 {
-	return -EPERM;
+	return -EOPNOTSUPP;
 }
 
 static int ovl_other_xattr_get(const struct xattr_handler *handler,
@@ -1153,6 +708,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	if (!ufs)
 		goto out;
 
+	ufs->config.redirect_dir = ovl_redirect_dir_def;
 	err = ovl_parse_opt((char *) data, &ufs->config);
 	if (err)
 		goto out_free_config;
@@ -1183,6 +739,10 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 			goto out_put_upperpath;
 		}
 
+		err = ovl_check_namelen(&upperpath, ufs, ufs->config.upperdir);
+		if (err)
+			goto out_put_upperpath;
+
 		err = ovl_mount_dir(ufs->config.workdir, &workpath);
 		if (err)
 			goto out_put_upperpath;
@@ -1214,15 +774,16 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 		goto out_free_lowertmp;
 	}
 
+	err = -ENOMEM;
 	stack = kcalloc(stacklen, sizeof(struct path), GFP_KERNEL);
 	if (!stack)
 		goto out_free_lowertmp;
 
+	err = -EINVAL;
 	lower = lowertmp;
 	for (numlower = 0; numlower < stacklen; numlower++) {
-		err = ovl_lower_dir(lower, &stack[numlower],
-				    &ufs->lower_namelen, &sb->s_stack_depth,
-				    &remote);
+		err = ovl_lower_dir(lower, &stack[numlower], ufs,
+				    &sb->s_stack_depth, &remote);
 		if (err)
 			goto out_put_lowerpath;
 
@@ -1324,7 +885,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_fs_info = ufs;
 	sb->s_flags |= MS_POSIXACL | MS_NOREMOTELOCK;
 
-	root_dentry = d_make_root(ovl_new_inode(sb, S_IFDIR));
+	root_dentry = d_make_root(ovl_new_inode(sb, S_IFDIR, 0));
 	if (!root_dentry)
 		goto out_free_oe;
 

fs/overlayfs/util.c

+/*
+ * Copyright (C) 2011 Novell Inc.
+ * Copyright (C) 2016 Red Hat, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ */
+
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/slab.h>
+#include <linux/xattr.h>
+#include "overlayfs.h"
+#include "ovl_entry.h"
+
+int ovl_want_write(struct dentry *dentry)
+{
+	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+	return mnt_want_write(ofs->upper_mnt);
+}
+
+void ovl_drop_write(struct dentry *dentry)
+{
+	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+	mnt_drop_write(ofs->upper_mnt);
+}
+
+struct dentry *ovl_workdir(struct dentry *dentry)
+{
+	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+	return ofs->workdir;
+}
+
+const struct cred *ovl_override_creds(struct super_block *sb)
+{
+	struct ovl_fs *ofs = sb->s_fs_info;
+
+	return override_creds(ofs->creator_cred);
+}
+
+struct ovl_entry *ovl_alloc_entry(unsigned int numlower)
+{
+	size_t size = offsetof(struct ovl_entry, lowerstack[numlower]);
+	struct ovl_entry *oe = kzalloc(size, GFP_KERNEL);
+
+	if (oe)
+		oe->numlower = numlower;
+
+	return oe;
+}
+
+bool ovl_dentry_remote(struct dentry *dentry)
+{
+	return dentry->d_flags &
+		(DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE |
+		 DCACHE_OP_REAL);
+}
+
+bool ovl_dentry_weird(struct dentry *dentry)
+{
+	return dentry->d_flags & (DCACHE_NEED_AUTOMOUNT |
+				  DCACHE_MANAGE_TRANSIT |
+				  DCACHE_OP_HASH |
+				  DCACHE_OP_COMPARE);
+}
+
+enum ovl_path_type ovl_path_type(struct dentry *dentry)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+	enum ovl_path_type type = 0;
+
+	if (oe->__upperdentry) {
+		type = __OVL_PATH_UPPER;
+
+		/*
+		 * Non-dir dentry can hold lower dentry from previous
+		 * location.
+		 */
+		if (oe->numlower && d_is_dir(dentry))
+			type |= __OVL_PATH_MERGE;
+	} else {
+		if (oe->numlower > 1)
+			type |= __OVL_PATH_MERGE;
+	}
+	return type;
+}
+
+void ovl_path_upper(struct dentry *dentry, struct path *path)
+{
+	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	path->mnt = ofs->upper_mnt;
+	path->dentry = ovl_upperdentry_dereference(oe);
+}
+
+void ovl_path_lower(struct dentry *dentry, struct path *path)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	*path = oe->numlower ? oe->lowerstack[0] : (struct path) { NULL, NULL };
+}
+
+enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path)
+{
+	enum ovl_path_type type = ovl_path_type(dentry);
+
+	if (!OVL_TYPE_UPPER(type))
+		ovl_path_lower(dentry, path);
+	else
+		ovl_path_upper(dentry, path);
+
+	return type;
+}
+
+struct dentry *ovl_dentry_upper(struct dentry *dentry)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	return ovl_upperdentry_dereference(oe);
+}
+
+static struct dentry *__ovl_dentry_lower(struct ovl_entry *oe)
+{
+	return oe->numlower ? oe->lowerstack[0].dentry : NULL;
+}
+
+struct dentry *ovl_dentry_lower(struct dentry *dentry)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	return __ovl_dentry_lower(oe);
+}
+
+struct dentry *ovl_dentry_real(struct dentry *dentry)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+	struct dentry *realdentry;
+
+	realdentry = ovl_upperdentry_dereference(oe);
+	if (!realdentry)
+		realdentry = __ovl_dentry_lower(oe);
+
+	return realdentry;
+}
+
+struct ovl_dir_cache *ovl_dir_cache(struct dentry *dentry)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	return oe->cache;
+}
+
+void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	oe->cache = cache;
+}
+
+bool ovl_dentry_is_opaque(struct dentry *dentry)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+	return oe->opaque;
+}
+
+bool ovl_dentry_is_whiteout(struct dentry *dentry)
+{
+	return !dentry->d_inode && ovl_dentry_is_opaque(dentry);
+}
+
+void ovl_dentry_set_opaque(struct dentry *dentry)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	oe->opaque = true;
+}
+
+bool ovl_redirect_dir(struct super_block *sb)
+{
+	struct ovl_fs *ofs = sb->s_fs_info;
+
+	return ofs->config.redirect_dir;
+}
+
+void ovl_clear_redirect_dir(struct super_block *sb)
+{
+	struct ovl_fs *ofs = sb->s_fs_info;
+
+	ofs->config.redirect_dir = false;
+}
+
+const char *ovl_dentry_get_redirect(struct dentry *dentry)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	return oe->redirect;
+}
+
+void ovl_dentry_set_redirect(struct dentry *dentry, const char *redirect)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	kfree(oe->redirect);
+	oe->redirect = redirect;
+}
+
+void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	WARN_ON(!inode_is_locked(upperdentry->d_parent->d_inode));
+	WARN_ON(oe->__upperdentry);
+	/*
+	 * Make sure upperdentry is consistent before making it visible to
+	 * ovl_upperdentry_dereference().
+	 */
+	smp_wmb();
+	oe->__upperdentry = upperdentry;
+}
+
+void ovl_inode_init(struct inode *inode, struct inode *realinode, bool is_upper)
+{
+	WRITE_ONCE(inode->i_private, (unsigned long) realinode |
+		   (is_upper ? OVL_ISUPPER_MASK : 0));
+}
+
+void ovl_inode_update(struct inode *inode, struct inode *upperinode)
+{
+	WARN_ON(!upperinode);
+	WARN_ON(!inode_unhashed(inode));
+	WRITE_ONCE(inode->i_private,
+		   (unsigned long) upperinode | OVL_ISUPPER_MASK);
+	if (!S_ISDIR(upperinode->i_mode))
+		__insert_inode_hash(inode, (unsigned long) upperinode);
+}
+
+void ovl_dentry_version_inc(struct dentry *dentry)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	WARN_ON(!inode_is_locked(dentry->d_inode));
+	oe->version++;
+}
+
+u64 ovl_dentry_version_get(struct dentry *dentry)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	WARN_ON(!inode_is_locked(dentry->d_inode));
+	return oe->version;
+}
+
+bool ovl_is_whiteout(struct dentry *dentry)
+{
+	struct inode *inode = dentry->d_inode;
+
+	return inode && IS_WHITEOUT(inode);
+}
+
+struct file *ovl_path_open(struct path *path, int flags)
+{
+	return dentry_open(path, flags | O_NOATIME, current_cred());
+}

fs/read_write.c

@@ -1538,9 +1538,7 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 	if (len == 0)
 		return 0;
 
-	ret = mnt_want_write_file(file_out);
-	if (ret)
-		return ret;
+	sb_start_write(inode_out->i_sb);
 
 	ret = -EOPNOTSUPP;
 	if (file_out->f_op->copy_file_range)
@@ -1559,7 +1557,7 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 	inc_syscr(current);
 	inc_syscw(current);
 
-	mnt_drop_write_file(file_out);
+	sb_end_write(inode_out->i_sb);
 
 	return ret;
 }
@@ -1657,15 +1655,19 @@ int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
 	struct inode *inode_out = file_inode(file_out);
 	int ret;
 
-	if (inode_in->i_sb != inode_out->i_sb ||
-	    file_in->f_path.mnt != file_out->f_path.mnt)
-		return -EXDEV;
-
 	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
 		return -EISDIR;
 	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
 		return -EINVAL;
 
+	/*
+	 * FICLONE/FICLONERANGE ioctls enforce that src and dest files are on
+	 * the same mount. Practically, they only need to be on the same file
+	 * system.
+	 */
+	if (inode_in->i_sb != inode_out->i_sb)
+		return -EXDEV;
+
 	if (!(file_in->f_mode & FMODE_READ) ||
 	    !(file_out->f_mode & FMODE_WRITE) ||
 	    (file_out->f_flags & O_APPEND))
@@ -1685,10 +1687,6 @@ int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
 	if (pos_in + len > i_size_read(inode_in))
 		return -EINVAL;
 
-	ret = mnt_want_write_file(file_out);
-	if (ret)
-		return ret;
-
 	ret = file_in->f_op->clone_file_range(file_in, pos_in,
 			file_out, pos_out, len);
 	if (!ret) {
@@ -1696,7 +1694,6 @@ int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
 		fsnotify_modify(file_out);
 	}
 
-	mnt_drop_write_file(file_out);
 	return ret;
 }
 EXPORT_SYMBOL(vfs_clone_file_range);

include/linux/fs.h

@@ -1731,6 +1731,19 @@ extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
 extern int vfs_dedupe_file_range(struct file *file,
 				 struct file_dedupe_range *same);
 
+static inline int do_clone_file_range(struct file *file_in, loff_t pos_in,
+				      struct file *file_out, loff_t pos_out,
+				      u64 len)
+{
+	int ret;
+
+	sb_start_write(file_inode(file_out)->i_sb);
+	ret = vfs_clone_file_range(file_in, pos_in, file_out, pos_out, len);
+	sb_end_write(file_inode(file_out)->i_sb);
+
+	return ret;
+}
+
 struct super_operations {
    	struct inode *(*alloc_inode)(struct super_block *sb);
 	void (*destroy_inode)(struct inode *);

net/unix/af_unix.c

@@ -315,7 +315,7 @@ static struct sock *unix_find_socket_byinode(struct inode *i)
 		    &unix_socket_table[i->i_ino & (UNIX_HASH_SIZE - 1)]) {
 		struct dentry *dentry = unix_sk(s)->path.dentry;
 
-		if (dentry && d_real_inode(dentry) == i) {
+		if (dentry && d_backing_inode(dentry) == i) {
 			sock_hold(s);
 			goto found;
 		}
@@ -913,7 +913,7 @@ static struct sock *unix_find_other(struct net *net,
 		err = kern_path(sunname->sun_path, LOOKUP_FOLLOW, &path);
 		if (err)
 			goto fail;
-		inode = d_real_inode(path.dentry);
+		inode = d_backing_inode(path.dentry);
 		err = inode_permission(inode, MAY_WRITE);
 		if (err)
 			goto put_fail;
@@ -1040,7 +1040,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 			goto out_up;
 		}
 		addr->hash = UNIX_HASH_SIZE;
-		hash = d_real_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1);
+		hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1);
 		spin_lock(&unix_table_lock);
 		u->path = path;
 		list = &unix_socket_table[hash];