Merge branch 'overlayfs.v25' of...

Merge branch 'overlayfs.v25' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs into for-linus

Documentation/filesystems/Locking

@@ -67,6 +67,7 @@ prototypes:
 				struct file *, unsigned open_flag,
 				umode_t create_mode, int *opened);
 	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
+	int (*dentry_open)(struct dentry *, struct file *, const struct cred *);
 
 locking rules:
 	all may block
@@ -96,6 +97,7 @@ fiemap:		no
 update_time:	no
 atomic_open:	yes
 tmpfile:	no
+dentry_open:	no
 
 	Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
 victim.

Documentation/filesystems/overlayfs.txt

+Written by: Neil Brown <neilb@suse.de>
+
+Overlay Filesystem
+==================
+
+This document describes a prototype for a new approach to providing
+overlay-filesystem functionality in Linux (sometimes referred to as
+union-filesystems).  An overlay-filesystem tries to present a
+filesystem which is the result over overlaying one filesystem on top
+of the other.
+
+The result will inevitably fail to look exactly like a normal
+filesystem for various technical reasons.  The expectation is that
+many use cases will be able to ignore these differences.
+
+This approach is 'hybrid' because the objects that appear in the
+filesystem do not all appear to belong to that filesystem.  In many
+cases an object accessed in the union will be indistinguishable
+from accessing the corresponding object from the original filesystem.
+This is most obvious from the 'st_dev' field returned by stat(2).
+
+While directories will report an st_dev from the overlay-filesystem,
+all non-directory objects will report an st_dev from the lower or
+upper filesystem that is providing the object.  Similarly st_ino will
+only be unique when combined with st_dev, and both of these can change
+over the lifetime of a non-directory object.  Many applications and
+tools ignore these values and will not be affected.
+
+Upper and Lower
+---------------
+
+An overlay filesystem combines two filesystems - an 'upper' filesystem
+and a 'lower' filesystem.  When a name exists in both filesystems, the
+object in the 'upper' filesystem is visible while the object in the
+'lower' filesystem is either hidden or, in the case of directories,
+merged with the 'upper' object.
+
+It would be more correct to refer to an upper and lower 'directory
+tree' rather than 'filesystem' as it is quite possible for both
+directory trees to be in the same filesystem and there is no
+requirement that the root of a filesystem be given for either upper or
+lower.
+
+The lower filesystem can be any filesystem supported by Linux and does
+not need to be writable.  The lower filesystem can even be another
+overlayfs.  The upper filesystem will normally be writable and if it
+is it must support the creation of trusted.* extended attributes, and
+must provide valid d_type in readdir responses, so NFS is not suitable.
+
+A read-only overlay of two read-only filesystems may use any
+filesystem type.
+
+Directories
+-----------
+
+Overlaying mainly involves directories.  If a given name appears in both
+upper and lower filesystems and refers to a non-directory in either,
+then the lower object is hidden - the name refers only to the upper
+object.
+
+Where both upper and lower objects are directories, a merged directory
+is formed.
+
+At mount time, the two directories given as mount options "lowerdir" and
+"upperdir" are combined into a merged directory:
+
+  mount -t overlayfs overlayfs -olowerdir=/lower,upperdir=/upper,\
+workdir=/work /merged
+
+The "workdir" needs to be an empty directory on the same filesystem
+as upperdir.
+
+Then whenever a lookup is requested in such a merged directory, the
+lookup is performed in each actual directory and the combined result
+is cached in the dentry belonging to the overlay filesystem.  If both
+actual lookups find directories, both are stored and a merged
+directory is created, otherwise only one is stored: the upper if it
+exists, else the lower.
+
+Only the lists of names from directories are merged.  Other content
+such as metadata and extended attributes are reported for the upper
+directory only.  These attributes of the lower directory are hidden.
+
+whiteouts and opaque directories
+--------------------------------
+
+In order to support rm and rmdir without changing the lower
+filesystem, an overlay filesystem needs to record in the upper filesystem
+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.
+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.
+
+readdir
+-------
+
+When a 'readdir' request is made on a merged directory, the upper and
+lower directories are each read and the name lists merged in the
+obvious way (upper is read first, then lower - entries that already
+exist are not re-added).  This merged name list is cached in the
+'struct file' and so remains as long as the file is kept open.  If the
+directory is opened and read by two processes at the same time, they
+will each have separate caches.  A seekdir to the start of the
+directory (offset 0) followed by a readdir will cause the cache to be
+discarded and rebuilt.
+
+This means that changes to the merged directory do not appear while a
+directory is being read.  This is unlikely to be noticed by many
+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
+  - seek to the remembered offset
+
+there may be little correlation between the old and new locations in
+the list of filenames, particularly if anything has changed in the
+directory.
+
+Readdir on directories that are not merged is simply handled by the
+underlying directory (upper or lower).
+
+
+Non-directories
+---------------
+
+Objects that are not directories (files, symlinks, device-special
+files etc.) are presented either from the upper or lower filesystem as
+appropriate.  When a file in the lower filesystem is accessed in a way
+the requires write-access, such as opening for write access, changing
+some metadata etc., the file is first copied from the lower filesystem
+to the upper filesystem (copy_up).  Note that creating a hard-link
+also requires copy_up, though of course creation of a symlink does
+not.
+
+The copy_up may turn out to be unnecessary, for example if the file is
+opened for read-write but the data is not modified.
+
+The copy_up process first makes sure that the containing directory
+exists in the upper filesystem - creating it and any parents as
+necessary.  It then creates the object with the same metadata (owner,
+mode, mtime, symlink-target etc.) and then if the object is a file, the
+data is copied from the lower to the upper filesystem.  Finally any
+extended attributes are copied up.
+
+Once the copy_up is complete, the overlay filesystem simply
+provides direct access to the newly created file in the upper
+filesystem - future operations on the file are barely noticed by the
+overlay filesystem (though an operation on the name of the file such as
+rename or unlink will of course be noticed and handled).
+
+
+Non-standard behavior
+---------------------
+
+The copy_up operation essentially creates a new, identical file and
+moves it over to the old name.  The new file may be on a different
+filesystem, so both st_dev and st_ino of the file may change.
+
+Any open files referring to this inode will access the old data and
+metadata.  Similarly any file locks obtained before copy_up will not
+apply to the copied up file.
+
+On a file opened with O_RDONLY fchmod(2), fchown(2), futimesat(2) and
+fsetxattr(2) will fail with EROFS.
+
+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.
+
+Symlinks in /proc/PID/ and /proc/PID/fd which point to a non-directory
+object in overlayfs will not contain valid absolute paths, only
+relative paths leading up to the filesystem's root.  This will be
+fixed in the future.
+
+Some operations are not atomic, for example a crash during copy_up or
+rename will leave the filesystem in an inconsistent state.  This will
+be addressed in the future.
+
+Changes to underlying filesystems
+---------------------------------
+
+Offline changes, when the overlay is not mounted, are allowed to either
+the upper or the lower trees.
+
+Changes to the underlying filesystems while part of a mounted overlay
+filesystem are not allowed.  If the underlying filesystem is changed,
+the behavior of the overlay is undefined, though it will not result in
+a crash or deadlock.

Documentation/filesystems/vfs.txt

@@ -364,6 +364,7 @@ struct inode_operations {
 	int (*atomic_open)(struct inode *, struct dentry *, struct file *,
 			unsigned open_flag, umode_t create_mode, int *opened);
 	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
+	int (*dentry_open)(struct dentry *, struct file *, const struct cred *);
 };
 
 Again, all methods are called without any locks being held, unless
@@ -696,6 +697,12 @@ struct address_space_operations {
   	but instead uses bmap to find out where the blocks in the file
   	are and uses those addresses directly.
 
+  dentry_open: *WARNING: probably going away soon, do not use!* This is an
+	alternative to f_op->open(), the difference is that this method may open
+	a file not necessarily originating from the same filesystem as the one
+	i_op->open() was called on.  It may be useful for stacking filesystems
+	which want to allow native I/O directly on underlying files.
+
 
   invalidatepage: If a page has PagePrivate set, then invalidatepage
         will be called when part or all of the page is to be removed

MAINTAINERS

@@ -6832,6 +6832,13 @@ F:	drivers/scsi/osd/
 F:	include/scsi/osd_*
 F:	fs/exofs/
 
+OVERLAYFS FILESYSTEM
+M:	Miklos Szeredi <miklos@szeredi.hu>
+L:	linux-fsdevel@vger.kernel.org
+S:	Supported
+F:	fs/overlayfs/*
+F:	Documentation/filesystems/overlayfs.txt
+
 P54 WIRELESS DRIVER
 M:	Christian Lamparter <chunkeey@googlemail.com>
 L:	linux-wireless@vger.kernel.org

fs/Kconfig

@@ -67,6 +67,7 @@ source "fs/quota/Kconfig"
 
 source "fs/autofs4/Kconfig"
 source "fs/fuse/Kconfig"
+source "fs/overlayfs/Kconfig"
 
 menu "Caches"
 

fs/Makefile

@@ -104,6 +104,7 @@ obj-$(CONFIG_QNX6FS_FS)		+= qnx6/
 obj-$(CONFIG_AUTOFS4_FS)	+= autofs4/
 obj-$(CONFIG_ADFS_FS)		+= adfs/
 obj-$(CONFIG_FUSE_FS)		+= fuse/
+obj-$(CONFIG_OVERLAYFS_FS)	+= overlayfs/
 obj-$(CONFIG_UDF_FS)		+= udf/
 obj-$(CONFIG_SUN_OPENPROMFS)	+= openpromfs/
 obj-$(CONFIG_OMFS_FS)		+= omfs/

fs/btrfs/ioctl.c

@@ -765,23 +765,6 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	return ret;
 }
 
-/*  copy of check_sticky in fs/namei.c()
-* It's inline, so penalty for filesystems that don't use sticky bit is
-* minimal.
-*/
-static inline int btrfs_check_sticky(struct inode *dir, struct inode *inode)
-{
-	kuid_t fsuid = current_fsuid();
-
-	if (!(dir->i_mode & S_ISVTX))
-		return 0;
-	if (uid_eq(inode->i_uid, fsuid))
-		return 0;
-	if (uid_eq(dir->i_uid, fsuid))
-		return 0;
-	return !capable(CAP_FOWNER);
-}
-
 /*  copy of may_delete in fs/namei.c()
  *	Check whether we can remove a link victim from directory dir, check
  *  whether the type of victim is right.
@@ -817,8 +800,7 @@ static int btrfs_may_delete(struct inode *dir, struct dentry *victim, int isdir)
 		return error;
 	if (IS_APPEND(dir))
 		return -EPERM;
-	if (btrfs_check_sticky(dir, victim->d_inode)||
-		IS_APPEND(victim->d_inode)||
+	if (check_sticky(dir, victim->d_inode) || IS_APPEND(victim->d_inode) ||
 	    IS_IMMUTABLE(victim->d_inode) || IS_SWAPFILE(victim->d_inode))
 		return -EPERM;
 	if (isdir) {

fs/ecryptfs/main.c

@@ -566,6 +566,13 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 	s->s_maxbytes = path.dentry->d_sb->s_maxbytes;
 	s->s_blocksize = path.dentry->d_sb->s_blocksize;
 	s->s_magic = ECRYPTFS_SUPER_MAGIC;
+	s->s_stack_depth = path.dentry->d_sb->s_stack_depth + 1;
+
+	rc = -EINVAL;
+	if (s->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) {
+		pr_err("eCryptfs: maximum fs stacking depth exceeded\n");
+		goto out_free;
+	}
 
 	inode = ecryptfs_get_inode(path.dentry->d_inode, s);
 	rc = PTR_ERR(inode);

fs/ext4/namei.c

@@ -3190,6 +3190,39 @@ static void ext4_update_dir_count(handle_t *handle, struct ext4_renament *ent)
 	}
 }
 
+static struct inode *ext4_whiteout_for_rename(struct ext4_renament *ent,
+					      int credits, handle_t **h)
+{
+	struct inode *wh;
+	handle_t *handle;
+	int retries = 0;
+
+	/*
+	 * for inode block, sb block, group summaries,
+	 * and inode bitmap
+	 */
+	credits += (EXT4_MAXQUOTAS_TRANS_BLOCKS(ent->dir->i_sb) +
+		    EXT4_XATTR_TRANS_BLOCKS + 4);
+retry:
+	wh = ext4_new_inode_start_handle(ent->dir, S_IFCHR | WHITEOUT_MODE,
+					 &ent->dentry->d_name, 0, NULL,
+					 EXT4_HT_DIR, credits);
+
+	handle = ext4_journal_current_handle();
+	if (IS_ERR(wh)) {
+		if (handle)
+			ext4_journal_stop(handle);
+		if (PTR_ERR(wh) == -ENOSPC &&
+		    ext4_should_retry_alloc(ent->dir->i_sb, &retries))
+			goto retry;
+	} else {
+		*h = handle;
+		init_special_inode(wh, wh->i_mode, WHITEOUT_DEV);
+		wh->i_op = &ext4_special_inode_operations;
+	}
+	return wh;
+}
+
 /*
  * Anybody can rename anything with this: the permission checks are left to the
  * higher-level routines.
@@ -3199,7 +3232,8 @@ static void ext4_update_dir_count(handle_t *handle, struct ext4_renament *ent)
  * This comes from rename(const char *oldpath, const char *newpath)
  */
 static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
-		       struct inode *new_dir, struct dentry *new_dentry)
+		       struct inode *new_dir, struct dentry *new_dentry,
+		       unsigned int flags)
 {
 	handle_t *handle = NULL;
 	struct ext4_renament old = {
@@ -3214,6 +3248,9 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 	};
 	int force_reread;
 	int retval;
+	struct inode *whiteout = NULL;
+	int credits;
+	u8 old_file_type;
 
 	dquot_initialize(old.dir);
 	dquot_initialize(new.dir);
@@ -3252,11 +3289,17 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (new.inode && !test_opt(new.dir->i_sb, NO_AUTO_DA_ALLOC))
 		ext4_alloc_da_blocks(old.inode);
 
-	handle = ext4_journal_start(old.dir, EXT4_HT_DIR,
-		(2 * EXT4_DATA_TRANS_BLOCKS(old.dir->i_sb) +
-		 EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2));
+	credits = (2 * EXT4_DATA_TRANS_BLOCKS(old.dir->i_sb) +
+		   EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2);
+	if (!(flags & RENAME_WHITEOUT)) {
+		handle = ext4_journal_start(old.dir, EXT4_HT_DIR, credits);
 		if (IS_ERR(handle))
 			return PTR_ERR(handle);
+	} else {
+		whiteout = ext4_whiteout_for_rename(&old, credits, &handle);
+		if (IS_ERR(whiteout))
+			return PTR_ERR(whiteout);
+	}
 
 	if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir))
 		ext4_handle_sync(handle);
@@ -3284,13 +3327,26 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 	 */
 	force_reread = (new.dir->i_ino == old.dir->i_ino &&
 			ext4_test_inode_flag(new.dir, EXT4_INODE_INLINE_DATA));
+
+	old_file_type = old.de->file_type;
+	if (whiteout) {
+		/*
+		 * Do this before adding a new entry, so the old entry is sure
+		 * to be still pointing to the valid old entry.
+		 */
+		retval = ext4_setent(handle, &old, whiteout->i_ino,
+				     EXT4_FT_CHRDEV);
+		if (retval)
+			goto end_rename;
+		ext4_mark_inode_dirty(handle, whiteout);
+	}
 	if (!new.bh) {
 		retval = ext4_add_entry(handle, new.dentry, old.inode);
 		if (retval)
 			goto end_rename;
 	} else {
 		retval = ext4_setent(handle, &new,
-				     old.inode->i_ino, old.de->file_type);
+				     old.inode->i_ino, old_file_type);
 		if (retval)
 			goto end_rename;
 	}
@@ -3305,10 +3361,12 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 	old.inode->i_ctime = ext4_current_time(old.inode);
 	ext4_mark_inode_dirty(handle, old.inode);
 
+	if (!whiteout) {
 		/*
 		 * ok, that's it
 		 */
 		ext4_rename_delete(handle, &old, force_reread);
+	}
 
 	if (new.inode) {
 		ext4_dec_count(handle, new.inode);
@@ -3344,6 +3402,12 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 	brelse(old.dir_bh);
 	brelse(old.bh);
 	brelse(new.bh);
+	if (whiteout) {
+		if (retval)
+			drop_nlink(whiteout);
+		unlock_new_inode(whiteout);
+		iput(whiteout);
+	}
 	if (handle)
 		ext4_journal_stop(handle);
 	return retval;
@@ -3476,18 +3540,15 @@ static int ext4_rename2(struct inode *old_dir, struct dentry *old_dentry,
 			struct inode *new_dir, struct dentry *new_dentry,
 			unsigned int flags)
 {
-	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
+	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
 		return -EINVAL;
 
 	if (flags & RENAME_EXCHANGE) {
 		return ext4_cross_rename(old_dir, old_dentry,
 					 new_dir, new_dentry);
 	}
-	/*
-	 * Existence checking was done by the VFS, otherwise "RENAME_NOREPLACE"
-	 * is equivalent to regular rename.
-	 */
-	return ext4_rename(old_dir, old_dentry, new_dir, new_dentry);
+
+	return ext4_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
 }
 
 /*

fs/internal.h

@@ -47,7 +47,6 @@ extern void __init chrdev_init(void);
 /*
  * namei.c
  */
-extern int __inode_permission(struct inode *, int);
 extern int user_path_mountpoint_at(int, const char __user *, unsigned int, struct path *);
 extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
 			   const char *, unsigned int, struct path *);
@@ -138,12 +137,6 @@ extern long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan,
  */
 extern int rw_verify_area(int, struct file *, const loff_t *, size_t);
 
-/*
- * splice.c
- */
-extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
-		loff_t *opos, size_t len, unsigned int flags);
-
 /*
  * pipe.c
  */

fs/namei.c

@@ -416,6 +416,7 @@ int __inode_permission(struct inode *inode, int mask)
 
 	return security_inode_permission(inode, mask);
 }
+EXPORT_SYMBOL(__inode_permission);
 
 /**
  * sb_permission - Check superblock-level permissions
@@ -2383,22 +2384,17 @@ kern_path_mountpoint(int dfd, const char *name, struct path *path,
 }
 EXPORT_SYMBOL(kern_path_mountpoint);
 
-/*
- * It's inline, so penalty for filesystems that don't use sticky bit is
- * minimal.
- */
-static inline int check_sticky(struct inode *dir, struct inode *inode)
+int __check_sticky(struct inode *dir, struct inode *inode)
 {
 	kuid_t fsuid = current_fsuid();
 
-	if (!(dir->i_mode & S_ISVTX))
-		return 0;
 	if (uid_eq(inode->i_uid, fsuid))
 		return 0;
 	if (uid_eq(dir->i_uid, fsuid))
 		return 0;
 	return !capable_wrt_inode_uidgid(inode, CAP_FOWNER);
 }
+EXPORT_SYMBOL(__check_sticky);
 
 /*
  *	Check whether we can remove a link victim from directory dir, check
@@ -3064,9 +3060,12 @@ static int do_last(struct nameidata *nd, struct path *path,
 	error = may_open(&nd->path, acc_mode, open_flag);
 	if (error)
 		goto out;
-	file->f_path.mnt = nd->path.mnt;
-	error = finish_open(file, nd->path.dentry, NULL, opened);
-	if (error) {
+
+	BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
+	error = vfs_open(&nd->path, file, current_cred());
+	if (!error) {
+		*opened |= FILE_OPENED;
+	} else {
 		if (error == -EOPENSTALE)
 			goto stale_open;
 		goto out;
@@ -4210,12 +4209,16 @@ SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
 	bool should_retry = false;
 	int error;
 
-	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
+	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
 		return -EINVAL;
 
-	if ((flags & RENAME_NOREPLACE) && (flags & RENAME_EXCHANGE))
+	if ((flags & (RENAME_NOREPLACE | RENAME_WHITEOUT)) &&
+	    (flags & RENAME_EXCHANGE))
 		return -EINVAL;
 
+	if ((flags & RENAME_WHITEOUT) && !capable(CAP_MKNOD))
+		return -EPERM;
+
 retry:
 	from = user_path_parent(olddfd, oldname, &oldnd, lookup_flags);
 	if (IS_ERR(from)) {
@@ -4347,6 +4350,20 @@ SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newna
 	return sys_renameat2(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
 }
 
+int vfs_whiteout(struct inode *dir, struct dentry *dentry)
+{
+	int error = may_create(dir, dentry);
+	if (error)
+		return error;
+
+	if (!dir->i_op->mknod)
+		return -EPERM;
+
+	return dir->i_op->mknod(dir, dentry,
+				S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV);
+}
+EXPORT_SYMBOL(vfs_whiteout);
+
 int readlink_copy(char __user *buffer, int buflen, const char *link)
 {
 	int len = PTR_ERR(link);

fs/namespace.c

@@ -1686,6 +1686,33 @@ void drop_collected_mounts(struct vfsmount *mnt)
 	namespace_unlock();
 }
 
+/**
+ * clone_private_mount - create a private clone of a path
+ *
+ * This creates a new vfsmount, which will be the clone of @path.  The new will
+ * not be attached anywhere in the namespace and will be private (i.e. changes
+ * to the originating mount won't be propagated into this).
+ *
+ * Release with mntput().
+ */
+struct vfsmount *clone_private_mount(struct path *path)
+{
+	struct mount *old_mnt = real_mount(path->mnt);
+	struct mount *new_mnt;
+
+	if (IS_MNT_UNBINDABLE(old_mnt))
+		return ERR_PTR(-EINVAL);
+
+	down_read(&namespace_sem);
+	new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE);
+	up_read(&namespace_sem);
+	if (IS_ERR(new_mnt))
+		return ERR_CAST(new_mnt);
+
+	return &new_mnt->mnt;
+}
+EXPORT_SYMBOL_GPL(clone_private_mount);
+
 int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg,
 		   struct vfsmount *root)
 {

fs/open.c

@@ -823,8 +823,7 @@ struct file *dentry_open(const struct path *path, int flags,
 	f = get_empty_filp();
 	if (!IS_ERR(f)) {
 		f->f_flags = flags;
-		f->f_path = *path;
-		error = do_dentry_open(f, NULL, cred);
+		error = vfs_open(path, f, cred);
 		if (!error) {
 			/* from now on we need fput() to dispose of f */
 			error = open_check_o_direct(f);
@@ -841,6 +840,26 @@ struct file *dentry_open(const struct path *path, int flags,
 }
 EXPORT_SYMBOL(dentry_open);
 
+/**
+ * vfs_open - open the file at the given path
+ * @path: path to open
+ * @filp: newly allocated file with f_flag initialized
+ * @cred: credentials to use
+ */
+int vfs_open(const struct path *path, struct file *filp,
+	     const struct cred *cred)
+{
+	struct inode *inode = path->dentry->d_inode;
+
+	if (inode->i_op->dentry_open)
+		return inode->i_op->dentry_open(path->dentry, filp, cred);
+	else {
+		filp->f_path = *path;
+		return do_dentry_open(filp, NULL, cred);
+	}
+}
+EXPORT_SYMBOL(vfs_open);
+
 static inline int build_open_flags(int flags, umode_t mode, struct open_flags *op)
 {
 	int lookup_flags = 0;

fs/overlayfs/Kconfig

+config OVERLAYFS_FS
+	tristate "Overlay filesystem support"
+	help
+	  An overlay filesystem combines two filesystems - an 'upper' filesystem
+	  and a 'lower' filesystem.  When a name exists in both filesystems, the
+	  object in the 'upper' filesystem is visible while the object in the
+	  'lower' filesystem is either hidden or, in the case of directories,
+	  merged with the 'upper' object.
+
+	  For more information see Documentation/filesystems/overlayfs.txt

fs/overlayfs/Makefile

+#
+# Makefile for the overlay filesystem.
+#
+
+obj-$(CONFIG_OVERLAYFS_FS) += overlayfs.o
+
+overlayfs-objs := super.o inode.o dir.o readdir.o copy_up.o

fs/overlayfs/copy_up.c

+/*
+ *
+ * Copyright (C) 2011 Novell 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/slab.h>
+#include <linux/file.h>
+#include <linux/splice.h>
+#include <linux/xattr.h>
+#include <linux/security.h>
+#include <linux/uaccess.h>
+#include <linux/sched.h>
+#include <linux/namei.h>
+#include "overlayfs.h"
+
+#define OVL_COPY_UP_CHUNK_SIZE (1 << 20)
+
+int ovl_copy_xattr(struct dentry *old, struct dentry *new)
+{
+	ssize_t list_size, size;
+	char *buf, *name, *value;
+	int error;
+
+	if (!old->d_inode->i_op->getxattr ||
+	    !new->d_inode->i_op->getxattr)
+		return 0;
+
+	list_size = vfs_listxattr(old, NULL, 0);
+	if (list_size <= 0) {
+		if (list_size == -EOPNOTSUPP)
+			return 0;
+		return list_size;
+	}
+
+	buf = kzalloc(list_size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	error = -ENOMEM;
+	value = kmalloc(XATTR_SIZE_MAX, GFP_KERNEL);
+	if (!value)
+		goto out;
+
+	list_size = vfs_listxattr(old, buf, list_size);
+	if (list_size <= 0) {
+		error = list_size;
+		goto out_free_value;
+	}
+
+	for (name = buf; name < (buf + list_size); name += strlen(name) + 1) {
+		size = vfs_getxattr(old, name, value, XATTR_SIZE_MAX);
+		if (size <= 0) {
+			error = size;
+			goto out_free_value;
+		}
+		error = vfs_setxattr(new, name, value, size, 0);
+		if (error)
+			goto out_free_value;
+	}
+
+out_free_value:
+	kfree(value);
+out:
+	kfree(buf);
+	return error;
+}
+
+static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len)
+{
+	struct file *old_file;
+	struct file *new_file;
+	loff_t old_pos = 0;
+	loff_t new_pos = 0;
+	int error = 0;
+
+	if (len == 0)
+		return 0;
+
+	old_file = ovl_path_open(old, O_RDONLY);
+	if (IS_ERR(old_file))
+		return PTR_ERR(old_file);
+
+	new_file = ovl_path_open(new, O_WRONLY);
+	if (IS_ERR(new_file)) {
+		error = PTR_ERR(new_file);
+		goto out_fput;
+	}
+
+	/* FIXME: copy up sparse files efficiently */
+	while (len) {
+		size_t this_len = OVL_COPY_UP_CHUNK_SIZE;
+		long bytes;
+
+		if (len < this_len)
+			this_len = len;
+
+		if (signal_pending_state(TASK_KILLABLE, current)) {
+			error = -EINTR;
+			break;
+		}
+
+		bytes = do_splice_direct(old_file, &old_pos,
+					 new_file, &new_pos,
+					 this_len, SPLICE_F_MOVE);
+		if (bytes <= 0) {
+			error = bytes;
+			break;
+		}
+		WARN_ON(old_pos != new_pos);
+
+		len -= bytes;
+	}
+
+	fput(new_file);
+out_fput:
+	fput(old_file);
+	return error;
+}
+
+static char *ovl_read_symlink(struct dentry *realdentry)
+{
+	int res;
+	char *buf;
+	struct inode *inode = realdentry->d_inode;
+	mm_segment_t old_fs;
+
+	res = -EINVAL;
+	if (!inode->i_op->readlink)
+		goto err;
+
+	res = -ENOMEM;
+	buf = (char *) __get_free_page(GFP_KERNEL);
+	if (!buf)
+		goto err;
+
+	old_fs = get_fs();
+	set_fs(get_ds());
+	/* The cast to a user pointer is valid due to the set_fs() */
+	res = inode->i_op->readlink(realdentry,
+				    (char __user *)buf, PAGE_SIZE - 1);
+	set_fs(old_fs);
+	if (res < 0) {
+		free_page((unsigned long) buf);
+		goto err;
+	}
+	buf[res] = '\0';
+
+	return buf;
+
+err:
+	return ERR_PTR(res);
+}
+
+static int ovl_set_timestamps(struct dentry *upperdentry, struct kstat *stat)
+{
+	struct iattr attr = {
+		.ia_valid =
+		     ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET,
+		.ia_atime = stat->atime,
+		.ia_mtime = stat->mtime,
+	};
+
+	return notify_change(upperdentry, &attr, NULL);
+}
+
+int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat)
+{
+	int err = 0;
+
+	if (!S_ISLNK(stat->mode)) {
+		struct iattr attr = {
+			.ia_valid = ATTR_MODE,
+			.ia_mode = stat->mode,
+		};
+		err = notify_change(upperdentry, &attr, NULL);
+	}
+	if (!err) {
+		struct iattr attr = {
+			.ia_valid = ATTR_UID | ATTR_GID,
+			.ia_uid = stat->uid,
+			.ia_gid = stat->gid,
+		};
+		err = notify_change(upperdentry, &attr, NULL);
+	}
+	if (!err)
+		ovl_set_timestamps(upperdentry, stat);
+
+	return err;
+
+}
+
+static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
+			      struct dentry *dentry, struct path *lowerpath,
+			      struct kstat *stat, struct iattr *attr,
+			      const char *link)
+{
+	struct inode *wdir = workdir->d_inode;
+	struct inode *udir = upperdir->d_inode;
+	struct dentry *newdentry = NULL;
+	struct dentry *upper = NULL;
+	umode_t mode = stat->mode;
+	int err;
+
+	newdentry = ovl_lookup_temp(workdir, dentry);
+	err = PTR_ERR(newdentry);
+	if (IS_ERR(newdentry))
+		goto out;
+
+	upper = lookup_one_len(dentry->d_name.name, upperdir,
+			       dentry->d_name.len);
+	err = PTR_ERR(upper);
+	if (IS_ERR(upper))
+		goto out1;
+
+	/* 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;
+	if (err)
+		goto out2;
+
+	if (S_ISREG(stat->mode)) {
+		struct path upperpath;
+		ovl_path_upper(dentry, &upperpath);
+		BUG_ON(upperpath.dentry != NULL);
+		upperpath.dentry = newdentry;
+
+		err = ovl_copy_up_data(lowerpath, &upperpath, stat->size);
+		if (err)
+			goto out_cleanup;
+	}
+
+	err = ovl_copy_xattr(lowerpath->dentry, newdentry);
+	if (err)
+		goto out_cleanup;
+
+	mutex_lock(&newdentry->d_inode->i_mutex);
+	err = ovl_set_attr(newdentry, stat);
+	if (!err && attr)
+		err = notify_change(newdentry, attr, NULL);
+	mutex_unlock(&newdentry->d_inode->i_mutex);
+	if (err)
+		goto out_cleanup;
+
+	err = ovl_do_rename(wdir, newdentry, udir, upper, 0);
+	if (err)
+		goto out_cleanup;
+
+	ovl_dentry_update(dentry, 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:
+	dput(newdentry);
+out:
+	return err;
+
+out_cleanup:
+	ovl_cleanup(wdir, newdentry);
+	goto out;
+}
+
+/*
+ * 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.
+ */
+int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
+		    struct path *lowerpath, struct kstat *stat,
+		    struct iattr *attr)
+{
+	struct dentry *workdir = ovl_workdir(dentry);
+	int err;
+	struct kstat pstat;
+	struct path parentpath;
+	struct dentry *upperdir;
+	struct dentry *upperdentry;
+	const struct cred *old_cred;
+	struct cred *override_cred;
+	char *link = NULL;
+
+	ovl_path_upper(parent, &parentpath);
+	upperdir = parentpath.dentry;
+
+	err = vfs_getattr(&parentpath, &pstat);
+	if (err)
+		return err;
+
+	if (S_ISLNK(stat->mode)) {
+		link = ovl_read_symlink(lowerpath->dentry);
+		if (IS_ERR(link))
+			return PTR_ERR(link);
+	}
+
+	err = -ENOMEM;
+	override_cred = prepare_creds();
+	if (!override_cred)
+		goto out_free_link;
+
+	override_cred->fsuid = stat->uid;
+	override_cred->fsgid = stat->gid;
+	/*
+	 * CAP_SYS_ADMIN for copying up extended attributes
+	 * CAP_DAC_OVERRIDE for create
+	 * CAP_FOWNER for chmod, timestamp update
+	 * CAP_FSETID for chmod
+	 * CAP_CHOWN for chown
+	 * CAP_MKNOD for mknod
+	 */
+	cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN);
+	cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE);
+	cap_raise(override_cred->cap_effective, CAP_FOWNER);
+	cap_raise(override_cred->cap_effective, CAP_FSETID);
+	cap_raise(override_cred->cap_effective, CAP_CHOWN);
+	cap_raise(override_cred->cap_effective, CAP_MKNOD);
+	old_cred = override_creds(override_cred);
+
+	err = -EIO;
+	if (lock_rename(workdir, upperdir) != NULL) {
+		pr_err("overlayfs: failed to lock workdir+upperdir\n");
+		goto out_unlock;
+	}
+	upperdentry = ovl_dentry_upper(dentry);
+	if (upperdentry) {
+		unlock_rename(workdir, upperdir);
+		err = 0;
+		/* Raced with another copy-up?  Do the setattr here */
+		if (attr) {
+			mutex_lock(&upperdentry->d_inode->i_mutex);
+			err = notify_change(upperdentry, attr, NULL);
+			mutex_unlock(&upperdentry->d_inode->i_mutex);
+		}
+		goto out_put_cred;
+	}
+
+	err = ovl_copy_up_locked(workdir, upperdir, dentry, lowerpath,
+				 stat, attr, link);
+	if (!err) {
+		/* Restore timestamps on parent (best effort) */
+		ovl_set_timestamps(upperdir, &pstat);
+	}
+out_unlock:
+	unlock_rename(workdir, upperdir);
+out_put_cred:
+	revert_creds(old_cred);
+	put_cred(override_cred);
+
+out_free_link:
+	if (link)
+		free_page((unsigned long) link);
+
+	return err;
+}
+
+int ovl_copy_up(struct dentry *dentry)
+{
+	int err;
+
+	err = 0;
+	while (!err) {
+		struct dentry *next;
+		struct dentry *parent;
+		struct path lowerpath;
+		struct kstat stat;
+		enum ovl_path_type type = ovl_path_type(dentry);
+
+		if (type != OVL_PATH_LOWER)
+			break;
+
+		next = dget(dentry);
+		/* find the topmost dentry not yet copied up */
+		for (;;) {
+			parent = dget_parent(next);
+
+			type = ovl_path_type(parent);
+			if (type != OVL_PATH_LOWER)
+				break;
+
+			dput(next);
+			next = parent;
+		}
+
+		ovl_path_lower(next, &lowerpath);
+		err = vfs_getattr(&lowerpath, &stat);
+		if (!err)
+			err = ovl_copy_up_one(parent, next, &lowerpath, &stat, NULL);
+
+		dput(parent);
+		dput(next);
+	}
+
+	return err;
+}

fs/overlayfs/inode.c

+/*
+ *
+ * Copyright (C) 2011 Novell 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/slab.h>
+#include <linux/xattr.h>
+#include "overlayfs.h"
+
+static int ovl_copy_up_last(struct dentry *dentry, struct iattr *attr,
+			    bool no_data)
+{
+	int err;
+	struct dentry *parent;
+	struct kstat stat;
+	struct path lowerpath;
+
+	parent = dget_parent(dentry);
+	err = ovl_copy_up(parent);
+	if (err)
+		goto out_dput_parent;
+
+	ovl_path_lower(dentry, &lowerpath);
+	err = vfs_getattr(&lowerpath, &stat);
+	if (err)
+		goto out_dput_parent;
+
+	if (no_data)
+		stat.size = 0;
+
+	err = ovl_copy_up_one(parent, dentry, &lowerpath, &stat, attr);
+
+out_dput_parent:
+	dput(parent);
+	return err;
+}
+
+int ovl_setattr(struct dentry *dentry, struct iattr *attr)
+{
+	int err;
+	struct dentry *upperdentry;
+
+	err = ovl_want_write(dentry);
+	if (err)
+		goto out;
+
+	upperdentry = ovl_dentry_upper(dentry);
+	if (upperdentry) {
+		mutex_lock(&upperdentry->d_inode->i_mutex);
+		err = notify_change(upperdentry, attr, NULL);
+		mutex_unlock(&upperdentry->d_inode->i_mutex);
+	} else {
+		err = ovl_copy_up_last(dentry, attr, false);
+	}
+	ovl_drop_write(dentry);
+out:
+	return err;
+}
+
+static int ovl_getattr(struct vfsmount *mnt, struct dentry *dentry,
+			 struct kstat *stat)
+{
+	struct path realpath;
+
+	ovl_path_real(dentry, &realpath);
+	return vfs_getattr(&realpath, stat);
+}
+
+int ovl_permission(struct inode *inode, int mask)
+{
+	struct ovl_entry *oe;
+	struct dentry *alias = NULL;
+	struct inode *realinode;
+	struct dentry *realdentry;
+	bool is_upper;
+	int err;
+
+	if (S_ISDIR(inode->i_mode)) {
+		oe = inode->i_private;
+	} else if (mask & MAY_NOT_BLOCK) {
+		return -ECHILD;
+	} else {
+		/*
+		 * For non-directories find an alias and get the info
+		 * from there.
+		 */
+		alias = d_find_any_alias(inode);
+		if (WARN_ON(!alias))
+			return -ENOENT;
+
+		oe = alias->d_fsdata;
+	}
+
+	realdentry = ovl_entry_real(oe, &is_upper);
+
+	/* Careful in RCU walk mode */
+	realinode = ACCESS_ONCE(realdentry->d_inode);
+	if (!realinode) {
+		WARN_ON(!(mask & MAY_NOT_BLOCK));
+		err = -ENOENT;
+		goto out_dput;
+	}
+
+	if (mask & MAY_WRITE) {
+		umode_t mode = realinode->i_mode;
+
+		/*
+		 * Writes will always be redirected to upper layer, so
+		 * ignore lower layer being read-only.
+		 *
+		 * If the overlay itself is read-only then proceed
+		 * with the permission check, don't return EROFS.
+		 * This will only happen if this is the lower layer of
+		 * another overlayfs.
+		 *
+		 * If upper fs becomes read-only after the overlay was
+		 * constructed return EROFS to prevent modification of
+		 * upper layer.
+		 */
+		err = -EROFS;
+		if (is_upper && !IS_RDONLY(inode) && IS_RDONLY(realinode) &&
+		    (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
+			goto out_dput;
+	}
+
+	err = __inode_permission(realinode, mask);
+out_dput:
+	dput(alias);
+	return err;
+}
+
+
+struct ovl_link_data {
+	struct dentry *realdentry;
+	void *cookie;
+};
+
+static void *ovl_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+	void *ret;
+	struct dentry *realdentry;
+	struct inode *realinode;
+
+	realdentry = ovl_dentry_real(dentry);
+	realinode = realdentry->d_inode;
+
+	if (WARN_ON(!realinode->i_op->follow_link))
+		return ERR_PTR(-EPERM);
+
+	ret = realinode->i_op->follow_link(realdentry, nd);
+	if (IS_ERR(ret))
+		return ret;
+
+	if (realinode->i_op->put_link) {
+		struct ovl_link_data *data;
+
+		data = kmalloc(sizeof(struct ovl_link_data), GFP_KERNEL);
+		if (!data) {
+			realinode->i_op->put_link(realdentry, nd, ret);
+			return ERR_PTR(-ENOMEM);
+		}
+		data->realdentry = realdentry;
+		data->cookie = ret;
+
+		return data;
+	} else {
+		return NULL;
+	}
+}
+
+static void ovl_put_link(struct dentry *dentry, struct nameidata *nd, void *c)
+{
+	struct inode *realinode;
+	struct ovl_link_data *data = c;
+
+	if (!data)
+		return;
+
+	realinode = data->realdentry->d_inode;
+	realinode->i_op->put_link(data->realdentry, nd, data->cookie);
+	kfree(data);
+}
+
+static int ovl_readlink(struct dentry *dentry, char __user *buf, int bufsiz)
+{
+	struct path realpath;
+	struct inode *realinode;
+
+	ovl_path_real(dentry, &realpath);
+	realinode = realpath.dentry->d_inode;
+
+	if (!realinode->i_op->readlink)
+		return -EINVAL;
+
+	touch_atime(&realpath);
+
+	return realinode->i_op->readlink(realpath.dentry, buf, bufsiz);
+}
+
+
+static bool ovl_is_private_xattr(const char *name)
+{
+	return strncmp(name, "trusted.overlay.", 14) == 0;
+}
+
+int ovl_setxattr(struct dentry *dentry, const char *name,
+		 const void *value, size_t size, int flags)
+{
+	int err;
+	struct dentry *upperdentry;
+
+	err = ovl_want_write(dentry);
+	if (err)
+		goto out;
+
+	err = -EPERM;
+	if (ovl_is_private_xattr(name))
+		goto out_drop_write;
+
+	err = ovl_copy_up(dentry);
+	if (err)
+		goto out_drop_write;
+
+	upperdentry = ovl_dentry_upper(dentry);
+	err = vfs_setxattr(upperdentry, name, value, size, flags);
+
+out_drop_write:
+	ovl_drop_write(dentry);
+out:
+	return err;
+}
+
+ssize_t ovl_getxattr(struct dentry *dentry, const char *name,
+		     void *value, size_t size)
+{
+	if (ovl_path_type(dentry->d_parent) == OVL_PATH_MERGE &&
+	    ovl_is_private_xattr(name))
+		return -ENODATA;
+
+	return vfs_getxattr(ovl_dentry_real(dentry), name, value, size);
+}
+
+ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
+{
+	ssize_t res;
+	int off;
+
+	res = vfs_listxattr(ovl_dentry_real(dentry), list, size);
+	if (res <= 0 || size == 0)
+		return res;
+
+	if (ovl_path_type(dentry->d_parent) != OVL_PATH_MERGE)
+		return res;
+
+	/* filter out private xattrs */
+	for (off = 0; off < res;) {
+		char *s = list + off;
+		size_t slen = strlen(s) + 1;
+
+		BUG_ON(off + slen > res);
+
+		if (ovl_is_private_xattr(s)) {
+			res -= slen;
+			memmove(s, s + slen, res - off);
+		} else {
+			off += slen;
+		}
+	}
+
+	return res;
+}
+
+int ovl_removexattr(struct dentry *dentry, const char *name)
+{
+	int err;
+	struct path realpath;
+	enum ovl_path_type type;
+
+	err = ovl_want_write(dentry);
+	if (err)
+		goto out;
+
+	if (ovl_path_type(dentry->d_parent) == OVL_PATH_MERGE &&
+	    ovl_is_private_xattr(name))
+		goto out_drop_write;
+
+	type = ovl_path_real(dentry, &realpath);
+	if (type == OVL_PATH_LOWER) {
+		err = vfs_getxattr(realpath.dentry, name, NULL, 0);
+		if (err < 0)
+			goto out_drop_write;
+
+		err = ovl_copy_up(dentry);
+		if (err)
+			goto out_drop_write;
+
+		ovl_path_upper(dentry, &realpath);
+	}
+
+	err = vfs_removexattr(realpath.dentry, name);
+out_drop_write:
+	ovl_drop_write(dentry);
+out:
+	return err;
+}
+
+static bool ovl_open_need_copy_up(int flags, enum ovl_path_type type,
+				  struct dentry *realdentry)
+{
+	if (type != OVL_PATH_LOWER)
+		return false;
+
+	if (special_file(realdentry->d_inode->i_mode))
+		return false;
+
+	if (!(OPEN_FMODE(flags) & FMODE_WRITE) && !(flags & O_TRUNC))
+		return false;
+
+	return true;
+}
+
+static int ovl_dentry_open(struct dentry *dentry, struct file *file,
+		    const struct cred *cred)
+{
+	int err;
+	struct path realpath;
+	enum ovl_path_type type;
+	bool want_write = false;
+
+	type = ovl_path_real(dentry, &realpath);
+	if (ovl_open_need_copy_up(file->f_flags, type, realpath.dentry)) {
+		want_write = true;
+		err = ovl_want_write(dentry);
+		if (err)
+			goto out;
+
+		if (file->f_flags & O_TRUNC)
+			err = ovl_copy_up_last(dentry, NULL, true);
+		else
+			err = ovl_copy_up(dentry);
+		if (err)
+			goto out_drop_write;
+
+		ovl_path_upper(dentry, &realpath);
+	}
+
+	err = vfs_open(&realpath, file, cred);
+out_drop_write:
+	if (want_write)
+		ovl_drop_write(dentry);
+out:
+	return err;
+}
+
+static const struct inode_operations ovl_file_inode_operations = {
+	.setattr	= ovl_setattr,
+	.permission	= ovl_permission,
+	.getattr	= ovl_getattr,
+	.setxattr	= ovl_setxattr,
+	.getxattr	= ovl_getxattr,
+	.listxattr	= ovl_listxattr,
+	.removexattr	= ovl_removexattr,
+	.dentry_open	= ovl_dentry_open,
+};
+
+static const struct inode_operations ovl_symlink_inode_operations = {
+	.setattr	= ovl_setattr,
+	.follow_link	= ovl_follow_link,
+	.put_link	= ovl_put_link,
+	.readlink	= ovl_readlink,
+	.getattr	= ovl_getattr,
+	.setxattr	= ovl_setxattr,
+	.getxattr	= ovl_getxattr,
+	.listxattr	= ovl_listxattr,
+	.removexattr	= ovl_removexattr,
+};
+
+struct inode *ovl_new_inode(struct super_block *sb, umode_t mode,
+			    struct ovl_entry *oe)
+{
+	struct inode *inode;
+
+	inode = new_inode(sb);
+	if (!inode)
+		return NULL;
+
+	mode &= S_IFMT;
+
+	inode->i_ino = get_next_ino();
+	inode->i_mode = mode;
+	inode->i_flags |= S_NOATIME | S_NOCMTIME;
+
+	switch (mode) {
+	case S_IFDIR:
+		inode->i_private = oe;
+		inode->i_op = &ovl_dir_inode_operations;
+		inode->i_fop = &ovl_dir_operations;
+		break;
+
+	case S_IFLNK:
+		inode->i_op = &ovl_symlink_inode_operations;
+		break;
+
+	case S_IFREG:
+	case S_IFSOCK:
+	case S_IFBLK:
+	case S_IFCHR:
+	case S_IFIFO:
+		inode->i_op = &ovl_file_inode_operations;
+		break;
+
+	default:
+		WARN(1, "illegal file type: %i\n", mode);
+		iput(inode);
+		inode = NULL;
+	}
+
+	return inode;
+
+}

fs/overlayfs/overlayfs.h

+/*
+ *
+ * Copyright (C) 2011 Novell 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/kernel.h>
+
+struct ovl_entry;
+
+enum ovl_path_type {
+	OVL_PATH_PURE_UPPER,
+	OVL_PATH_UPPER,
+	OVL_PATH_MERGE,
+	OVL_PATH_LOWER,
+};
+
+extern const char *ovl_opaque_xattr;
+
+static inline int ovl_do_rmdir(struct inode *dir, struct dentry *dentry)
+{
+	int err = vfs_rmdir(dir, dentry);
+	pr_debug("rmdir(%pd2) = %i\n", dentry, err);
+	return err;
+}
+
+static inline int ovl_do_unlink(struct inode *dir, struct dentry *dentry)
+{
+	int err = vfs_unlink(dir, dentry, NULL);
+	pr_debug("unlink(%pd2) = %i\n", dentry, err);
+	return err;
+}
+
+static inline int ovl_do_link(struct dentry *old_dentry, struct inode *dir,
+			      struct dentry *new_dentry, bool debug)
+{
+	int err = vfs_link(old_dentry, dir, new_dentry, NULL);
+	if (debug) {
+		pr_debug("link(%pd2, %pd2) = %i\n",
+			 old_dentry, new_dentry, err);
+	}
+	return err;
+}
+
+static inline int ovl_do_create(struct inode *dir, struct dentry *dentry,
+			     umode_t mode, bool debug)
+{
+	int err = vfs_create(dir, dentry, mode, true);
+	if (debug)
+		pr_debug("create(%pd2, 0%o) = %i\n", dentry, mode, err);
+	return err;
+}
+
+static inline int ovl_do_mkdir(struct inode *dir, struct dentry *dentry,
+			       umode_t mode, bool debug)
+{
+	int err = vfs_mkdir(dir, dentry, mode);
+	if (debug)
+		pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, err);
+	return err;
+}
+
+static inline int ovl_do_mknod(struct inode *dir, struct dentry *dentry,
+			       umode_t mode, dev_t dev, bool debug)
+{
+	int err = vfs_mknod(dir, dentry, mode, dev);
+	if (debug) {
+		pr_debug("mknod(%pd2, 0%o, 0%o) = %i\n",
+			 dentry, mode, dev, err);
+	}
+	return err;
+}
+
+static inline int ovl_do_symlink(struct inode *dir, struct dentry *dentry,
+				 const char *oldname, bool debug)
+{
+	int err = vfs_symlink(dir, dentry, oldname);
+	if (debug)
+		pr_debug("symlink(\"%s\", %pd2) = %i\n", oldname, dentry, err);
+	return err;
+}
+
+static inline int ovl_do_setxattr(struct dentry *dentry, const char *name,
+				  const void *value, size_t size, int flags)
+{
+	int err = vfs_setxattr(dentry, name, value, size, flags);
+	pr_debug("setxattr(%pd2, \"%s\", \"%*s\", 0x%x) = %i\n",
+		 dentry, name, (int) size, (char *) value, flags, err);
+	return err;
+}
+
+static inline int ovl_do_removexattr(struct dentry *dentry, const char *name)
+{
+	int err = vfs_removexattr(dentry, name);
+	pr_debug("removexattr(%pd2, \"%s\") = %i\n", dentry, name, err);
+	return err;
+}
+
+static inline int ovl_do_rename(struct inode *olddir, struct dentry *olddentry,
+				struct inode *newdir, struct dentry *newdentry,
+				unsigned int flags)
+{
+	int err;
+
+	pr_debug("rename2(%pd2, %pd2, 0x%x)\n",
+		 olddentry, newdentry, flags);
+
+	err = vfs_rename(olddir, olddentry, newdir, newdentry, NULL, flags);
+
+	if (err) {
+		pr_debug("...rename2(%pd2, %pd2, ...) = %i\n",
+			 olddentry, newdentry, err);
+	}
+	return err;
+}
+
+static inline int ovl_do_whiteout(struct inode *dir, struct dentry *dentry)
+{
+	int err = vfs_whiteout(dir, dentry);
+	pr_debug("whiteout(%pd2) = %i\n", dentry, err);
+	return err;
+}
+
+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);
+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 dentry *ovl_entry_real(struct ovl_entry *oe, 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);
+void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry);
+struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
+			  unsigned int flags);
+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);
+
+/* readdir.c */
+extern const struct file_operations ovl_dir_operations;
+int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list);
+void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list);
+void ovl_cache_free(struct list_head *list);
+
+/* inode.c */
+int ovl_setattr(struct dentry *dentry, struct iattr *attr);
+int ovl_permission(struct inode *inode, int mask);
+int ovl_setxattr(struct dentry *dentry, const char *name,
+		 const void *value, size_t size, int flags);
+ssize_t ovl_getxattr(struct dentry *dentry, const char *name,
+		     void *value, size_t size);
+ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size);
+int ovl_removexattr(struct dentry *dentry, const char *name);
+
+struct inode *ovl_new_inode(struct super_block *sb, umode_t mode,
+			    struct ovl_entry *oe);
+static inline void ovl_copyattr(struct inode *from, struct inode *to)
+{
+	to->i_uid = from->i_uid;
+	to->i_gid = from->i_gid;
+}
+
+/* dir.c */
+extern const struct inode_operations ovl_dir_inode_operations;
+struct dentry *ovl_lookup_temp(struct dentry *workdir, struct dentry *dentry);
+int ovl_create_real(struct inode *dir, struct dentry *newdentry,
+		    struct kstat *stat, const char *link,
+		    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,
+		    struct iattr *attr);
+int ovl_copy_xattr(struct dentry *old, struct dentry *new);
+int ovl_set_attr(struct dentry *upper, struct kstat *stat);

fs/splice.c

@@ -1330,6 +1330,7 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
 
 	return ret;
 }
+EXPORT_SYMBOL(do_splice_direct);
 
 static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
 			       struct pipe_inode_info *opipe,

include/linux/fs.h

@@ -222,6 +222,13 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define ATTR_OPEN	(1 << 15) /* Truncating from open(O_TRUNC) */
 #define ATTR_TIMES_SET	(1 << 16)
 
+/*
+ * Whiteout is represented by a char device.  The following constants define the
+ * mode and device number to use.
+ */
+#define WHITEOUT_MODE 0
+#define WHITEOUT_DEV 0
+
 /*
  * This is the Inode Attributes structure, used for notify_change().  It
  * uses the above definitions as flags, to know which values have changed.
@@ -254,6 +261,12 @@ struct iattr {
  */
 #include <linux/quota.h>
 
+/*
+ * Maximum number of layers of fs stack.  Needs to be limited to
+ * prevent kernel stack overflow
+ */
+#define FILESYSTEM_MAX_STACK_DEPTH 2
+
 /** 
  * enum positive_aop_returns - aop return codes with specific semantics
  *
@@ -1266,6 +1279,11 @@ struct super_block {
 	struct list_lru		s_dentry_lru ____cacheline_aligned_in_smp;
 	struct list_lru		s_inode_lru ____cacheline_aligned_in_smp;
 	struct rcu_head		rcu;
+
+	/*
+	 * Indicates how deep in a filesystem stack this SB is
+	 */
+	int s_stack_depth;
 };
 
 extern struct timespec current_fs_time(struct super_block *sb);
@@ -1398,6 +1416,7 @@ extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct ino
 extern int vfs_rmdir(struct inode *, struct dentry *);
 extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
 extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int);
+extern int vfs_whiteout(struct inode *, struct dentry *);
 
 /*
  * VFS dentry helper functions.
@@ -1528,6 +1547,9 @@ struct inode_operations {
 			   umode_t create_mode, int *opened);
 	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
 	int (*set_acl)(struct inode *, struct posix_acl *, int);
+
+	/* WARNING: probably going away soon, do not use! */
+	int (*dentry_open)(struct dentry *, struct file *, const struct cred *);
 } ____cacheline_aligned;
 
 ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
@@ -1625,6 +1647,9 @@ struct super_operations {
 #define IS_AUTOMOUNT(inode)	((inode)->i_flags & S_AUTOMOUNT)
 #define IS_NOSEC(inode)		((inode)->i_flags & S_NOSEC)
 
+#define IS_WHITEOUT(inode)	(S_ISCHR(inode->i_mode) && \
+				 (inode)->i_rdev == WHITEOUT_DEV)
+
 /*
  * Inode state bits.  Protected by inode->i_lock
  *
@@ -2040,6 +2065,7 @@ extern struct file *file_open_name(struct filename *, int, umode_t);
 extern struct file *filp_open(const char *, int, umode_t);
 extern struct file *file_open_root(struct dentry *, struct vfsmount *,
 				   const char *, int);
+extern int vfs_open(const struct path *, struct file *, const struct cred *);
 extern struct file * dentry_open(const struct path *, int, const struct cred *);
 extern int filp_close(struct file *, fl_owner_t id);
 
@@ -2253,7 +2279,9 @@ extern sector_t bmap(struct inode *, sector_t);
 #endif
 extern int notify_change(struct dentry *, struct iattr *, struct inode **);
 extern int inode_permission(struct inode *, int);
+extern int __inode_permission(struct inode *, int);
 extern int generic_permission(struct inode *, int);
+extern int __check_sticky(struct inode *dir, struct inode *inode);
 
 static inline bool execute_ok(struct inode *inode)
 {
@@ -2452,6 +2480,9 @@ extern ssize_t iter_file_splice_write(struct pipe_inode_info *,
 		struct file *, loff_t *, size_t, unsigned int);
 extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
 		struct file *out, loff_t *, size_t len, unsigned int flags);
+extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
+		loff_t *opos, size_t len, unsigned int flags);
+
 
 extern void
 file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
@@ -2737,6 +2768,14 @@ static inline int is_sxid(umode_t mode)
 	return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP));
 }
 
+static inline int check_sticky(struct inode *dir, struct inode *inode)
+{
+	if (!(dir->i_mode & S_ISVTX))
+		return 0;
+
+	return __check_sticky(dir, inode);
+}
+
 static inline void inode_has_no_xattr(struct inode *inode)
 {
 	if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & MS_NOSEC))

include/linux/mount.h

@@ -81,6 +81,9 @@ extern struct vfsmount *mntget(struct vfsmount *mnt);
 extern struct vfsmount *mnt_clone_internal(struct path *path);
 extern int __mnt_is_readonly(struct vfsmount *mnt);
 
+struct path;
+extern struct vfsmount *clone_private_mount(struct path *path);
+
 struct file_system_type;
 extern struct vfsmount *vfs_kern_mount(struct file_system_type *type,
 				      int flags, const char *name,

include/uapi/linux/fs.h

@@ -37,6 +37,7 @@
 
 #define RENAME_NOREPLACE	(1 << 0)	/* Don't overwrite target */
 #define RENAME_EXCHANGE		(1 << 1)	/* Exchange source and dest */
+#define RENAME_WHITEOUT		(1 << 2)	/* Whiteout source */
 
 struct fstrim_range {
 	__u64 start;

mm/shmem.c

@@ -2345,6 +2345,32 @@ static int shmem_exchange(struct inode *old_dir, struct dentry *old_dentry, stru
 	return 0;
 }
 
+static int shmem_whiteout(struct inode *old_dir, struct dentry *old_dentry)
+{
+	struct dentry *whiteout;
+	int error;
+
+	whiteout = d_alloc(old_dentry->d_parent, &old_dentry->d_name);
+	if (!whiteout)
+		return -ENOMEM;
+
+	error = shmem_mknod(old_dir, whiteout,
+			    S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV);
+	dput(whiteout);
+	if (error)
+		return error;
+
+	/*
+	 * Cheat and hash the whiteout while the old dentry is still in
+	 * place, instead of playing games with FS_RENAME_DOES_D_MOVE.
+	 *
+	 * d_lookup() will consistently find one of them at this point,
+	 * not sure which one, but that isn't even important.
+	 */
+	d_rehash(whiteout);
+	return 0;
+}
+
 /*
  * The VFS layer already does all the dentry stuff for rename,
  * we just have to decrement the usage count for the target if
@@ -2356,7 +2382,7 @@ static int shmem_rename2(struct inode *old_dir, struct dentry *old_dentry, struc
 	struct inode *inode = old_dentry->d_inode;
 	int they_are_dirs = S_ISDIR(inode->i_mode);
 
-	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
+	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
 		return -EINVAL;
 
 	if (flags & RENAME_EXCHANGE)
@@ -2365,6 +2391,14 @@ static int shmem_rename2(struct inode *old_dir, struct dentry *old_dentry, struc
 	if (!simple_empty(new_dentry))
 		return -ENOTEMPTY;
 
+	if (flags & RENAME_WHITEOUT) {
+		int error;
+
+		error = shmem_whiteout(old_dir, old_dentry);
+		if (error)
+			return error;
+	}
+
 	if (new_dentry->d_inode) {
 		(void) shmem_unlink(new_dir, new_dentry);
 		if (they_are_dirs) {