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);
+}