Merge remote-tracking branch 'origin/v3.14/topic/overlayfs' into linux-linaro-lsk-v3.14

102 files changed, 4600 insertions, 435 deletions

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 5b0c083d7c0e..821c8f4d359f 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -47,6 +47,8 @@ prototypes:
 	int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
 	int (*rename) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *);
+	int (*rename2) (struct inode *, struct dentry *,
+			struct inode *, struct dentry *, unsigned int);
 	int (*readlink) (struct dentry *, char __user *,int);
 	void * (*follow_link) (struct dentry *, struct nameidata *);
 	void (*put_link) (struct dentry *, struct nameidata *, void *);
@@ -65,6 +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
@@ -78,6 +81,7 @@ mkdir:		yes
 unlink:		yes (both)
 rmdir:		yes (both)	(see below)
 rename:		yes (all)	(see below)
+rename2:	yes (all)	(see below)
 readlink:	no
 follow_link:	no
 put_link:	no
@@ -93,10 +97,12 @@ fiemap:		no
 update_time:	no
 atomic_open:	yes
 tmpfile:	no
+dentry_open:	no
 
 	Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
 victim.
-	cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem.
+	cross-directory ->rename() and rename2() has (per-superblock)
+->s_vfs_rename_sem.
 
 See Documentation/filesystems/directory-locking for more detailed discussion
 of the locking scheme for directory operations.
diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt
new file mode 100644
index 000000000000..6db0e5d1da07
--- /dev/null
+++ b/Documentation/filesystems/overlayfs.txt
@@ -0,0 +1,226 @@
+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 overlay overlay -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).
+
+
+Multiple lower layers
+---------------------
+
+Multiple lower layers can now be given using the the colon (":") as a
+separator character between the directory names.  For example:
+
+  mount -t overlay overlay -olowerdir=/lower1:/lower2:/lower3 /merged
+
+As the example shows, "upperdir=" and "workdir=" may be omitted.  In
+that case the overlay will be read-only.
+
+The specified lower directories will be stacked beginning from the
+rightmost one and going left.  In the above example lower1 will be the
+top, lower2 the middle and lower3 the bottom layer.
+
+
+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.
+
+Testsuite
+---------
+
+There's testsuite developed by David Howells at:
+
+  git://git.infradead.org/users/dhowells/unionmount-testsuite.git
+
+Run as root:
+
+  # cd unionmount-testsuite
+  # ./run --ov
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index c53784c119c8..5d06f2a19798 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -347,6 +347,8 @@ struct inode_operations {
 	int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
 	int (*rename) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *);
+	int (*rename2) (struct inode *, struct dentry *,
+			struct inode *, struct dentry *, unsigned int);
 	int (*readlink) (struct dentry *, char __user *,int);
         void * (*follow_link) (struct dentry *, struct nameidata *);
         void (*put_link) (struct dentry *, struct nameidata *, void *);
@@ -362,6 +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
@@ -414,6 +417,20 @@ otherwise noted.
   rename: called by the rename(2) system call to rename the object to
 	have the parent and name given by the second inode and dentry.
 
+  rename2: this has an additional flags argument compared to rename.
+	If no flags are supported by the filesystem then this method
+	need not be implemented.  If some flags are supported then the
+	filesystem must return -EINVAL for any unsupported or unknown
+	flags.  Currently the following flags are implemented:
+	(1) RENAME_NOREPLACE: this flag indicates that if the target
+	of the rename exists the rename should fail with -EEXIST
+	instead of replacing the target.  The VFS already checks for
+	existence, so for local filesystems the RENAME_NOREPLACE
+	implementation is equivalent to plain rename.
+	(2) RENAME_EXCHANGE: exchange source and target.  Both must
+	exist; this is checked by the VFS.  Unlike plain rename,
+	source and target may be of different type.
+
   readlink: called by the readlink(2) system call. Only required if
 	you want to support reading symbolic links
 
@@ -681,6 +698,12 @@ 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
diff --git a/MAINTAINERS b/MAINTAINERS
index c701f48b8e00..cad9448ea92d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6468,6 +6468,13 @@ F:	drivers/scsi/osd/
 F:	include/scsi/osd_*
 F:	fs/exofs/
 
+OVERLAY 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
diff --git a/Makefile b/Makefile
index c24acc0d34a1..f09e19d2cc4f 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 14
-SUBLEVEL = 37
+SUBLEVEL = 38
 EXTRAVERSION =
 NAME = Remembering Coco
 
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 1402fcc11c2c..98f57d34923a 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -104,11 +104,12 @@ struct osf_dirent_callback {
 };
 
 static int
-osf_filldir(void *__buf, const char *name, int namlen, loff_t offset,
-	    u64 ino, unsigned int d_type)
+osf_filldir(struct dir_context *ctx, const char *name, int namlen,
+	    loff_t offset, u64 ino, unsigned int d_type)
 {
 	struct osf_dirent __user *dirent;
-	struct osf_dirent_callback *buf = (struct osf_dirent_callback *) __buf;
+	struct osf_dirent_callback *buf =
+		container_of(ctx, struct osf_dirent_callback, ctx);
 	unsigned int reclen = ALIGN(NAME_OFFSET + namlen + 1, sizeof(u32));
 	unsigned int d_ino;
 
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index a9eee33dfa62..101a42bde728 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -151,6 +151,15 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 {
 	unsigned int cpu = smp_processor_id();
 
+	/*
+	 * init_mm.pgd does not contain any user mappings and it is always
+	 * active for kernel addresses in TTBR1. Just set the reserved TTBR0.
+	 */
+	if (next == &init_mm) {
+		cpu_set_reserved_ttbr0();
+		return;
+	}
+
 	if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next)
 		check_and_switch_context(next, tsk);
 }
diff --git a/arch/parisc/hpux/fs.c b/arch/parisc/hpux/fs.c
index 2bedafea3d94..97a7bf8df348 100644
--- a/arch/parisc/hpux/fs.c
+++ b/arch/parisc/hpux/fs.c
@@ -56,11 +56,12 @@ struct getdents_callback {
 
 #define NAME_OFFSET(de) ((int) ((de)->d_name - (char __user *) (de)))
 
-static int filldir(void * __buf, const char * name, int namlen, loff_t offset,
-		u64 ino, unsigned d_type)
+static int filldir(struct dir_context *ctx, const char *name, int namlen,
+		   loff_t offset, u64 ino, unsigned d_type)
 {
 	struct hpux_dirent __user * dirent;
-	struct getdents_callback * buf = (struct getdents_callback *) __buf;
+	struct getdents_callback *buf =
+		container_of(ctx, struct getdents_callback, ctx);
 	ino_t d_ino;
 	int reclen = ALIGN(NAME_OFFSET(dirent) + namlen + 1, sizeof(long));
 
diff --git a/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi b/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi
index 1382fec9e8c5..7fcb1ac0f232 100644
--- a/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi
@@ -50,6 +50,7 @@ ethernet@b0000 {
 	fsl,num_tx_queues = <0x8>;
 	fsl,magic-packet;
 	local-mac-address = [ 00 00 00 00 00 00 ];
+	ranges;
 
 	queue-group@b0000 {
 		#address-cells = <1>;
diff --git a/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi b/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi
index 221cd2ea5b31..9f25427c1527 100644
--- a/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi
+++ b/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi
@@ -50,6 +50,7 @@ ethernet@b1000 {
 	fsl,num_tx_queues = <0x8>;
 	fsl,magic-packet;
 	local-mac-address = [ 00 00 00 00 00 00 ];
+	ranges;
 
 	queue-group@b1000 {
 		#address-cells = <1>;
diff --git a/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi b/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi
index 61456c317609..cd7c318ab131 100644
--- a/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi
+++ b/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi
@@ -49,6 +49,7 @@ ethernet@b2000 {
 	fsl,num_tx_queues = <0x8>;
 	fsl,magic-packet;
 	local-mac-address = [ 00 00 00 00 00 00 ];
+	ranges;
 
 	queue-group@b2000 {
 		#address-cells = <1>;
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 38d507306a11..5193116eadc0 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1422,7 +1422,7 @@ machine_check_handle_early:
 	bne	9f			/* continue in V mode if we are. */
 
 5:
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 	/*
 	 * We are coming from kernel context. Check if we are coming from
 	 * guest. if yes, then we can continue. We will fall through
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index cde4e0a095ae..bf3829242aff 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -24,10 +24,10 @@
 static struct kobject *mobility_kobj;
 
 struct update_props_workarea {
-	u32 phandle;
-	u32 state;
-	u64 reserved;
-	u32 nprops;
+	__be32 phandle;
+	__be32 state;
+	__be64 reserved;
+	__be32 nprops;
 } __packed;
 
 #define NODE_ACTION_MASK	0xff000000
@@ -53,11 +53,11 @@ static int mobility_rtas_call(int token, char *buf, s32 scope)
 	return rc;
 }
 
-static int delete_dt_node(u32 phandle)
+static int delete_dt_node(__be32 phandle)
 {
 	struct device_node *dn;
 
-	dn = of_find_node_by_phandle(phandle);
+	dn = of_find_node_by_phandle(be32_to_cpu(phandle));
 	if (!dn)
 		return -ENOENT;
 
@@ -126,7 +126,7 @@ static int update_dt_property(struct device_node *dn, struct property **prop,
 	return 0;
 }
 
-static int update_dt_node(u32 phandle, s32 scope)
+static int update_dt_node(__be32 phandle, s32 scope)
 {
 	struct update_props_workarea *upwa;
 	struct device_node *dn;
@@ -135,6 +135,7 @@ static int update_dt_node(u32 phandle, s32 scope)
 	char *prop_data;
 	char *rtas_buf;
 	int update_properties_token;
+	u32 nprops;
 	u32 vd;
 
 	update_properties_token = rtas_token("ibm,update-properties");
@@ -145,7 +146,7 @@ static int update_dt_node(u32 phandle, s32 scope)
 	if (!rtas_buf)
 		return -ENOMEM;
 
-	dn = of_find_node_by_phandle(phandle);
+	dn = of_find_node_by_phandle(be32_to_cpu(phandle));
 	if (!dn) {
 		kfree(rtas_buf);
 		return -ENOENT;
@@ -161,6 +162,7 @@ static int update_dt_node(u32 phandle, s32 scope)
 			break;
 
 		prop_data = rtas_buf + sizeof(*upwa);
+		nprops = be32_to_cpu(upwa->nprops);
 
 		/* On the first call to ibm,update-properties for a node the
 		 * the first property value descriptor contains an empty
@@ -169,17 +171,17 @@ static int update_dt_node(u32 phandle, s32 scope)
 		 */
 		if (*prop_data == 0) {
 			prop_data++;
-			vd = *(u32 *)prop_data;
+			vd = be32_to_cpu(*(__be32 *)prop_data);
 			prop_data += vd + sizeof(vd);
-			upwa->nprops--;
+			nprops--;
 		}
 
-		for (i = 0; i < upwa->nprops; i++) {
+		for (i = 0; i < nprops; i++) {
 			char *prop_name;
 
 			prop_name = prop_data;
 			prop_data += strlen(prop_name) + 1;
-			vd = *(u32 *)prop_data;
+			vd = be32_to_cpu(*(__be32 *)prop_data);
 			prop_data += sizeof(vd);
 
 			switch (vd) {
@@ -211,13 +213,13 @@ static int update_dt_node(u32 phandle, s32 scope)
 	return 0;
 }
 
-static int add_dt_node(u32 parent_phandle, u32 drc_index)
+static int add_dt_node(__be32 parent_phandle, __be32 drc_index)
 {
 	struct device_node *dn;
 	struct device_node *parent_dn;
 	int rc;
 
-	parent_dn = of_find_node_by_phandle(parent_phandle);
+	parent_dn = of_find_node_by_phandle(be32_to_cpu(parent_phandle));
 	if (!parent_dn)
 		return -ENOENT;
 
@@ -236,7 +238,7 @@ static int add_dt_node(u32 parent_phandle, u32 drc_index)
 int pseries_devicetree_update(s32 scope)
 {
 	char *rtas_buf;
-	u32 *data;
+	__be32 *data;
 	int update_nodes_token;
 	int rc;
 
@@ -253,17 +255,17 @@ int pseries_devicetree_update(s32 scope)
 		if (rc && rc != 1)
 			break;
 
-		data = (u32 *)rtas_buf + 4;
-		while (*data & NODE_ACTION_MASK) {
+		data = (__be32 *)rtas_buf + 4;
+		while (be32_to_cpu(*data) & NODE_ACTION_MASK) {
 			int i;
-			u32 action = *data & NODE_ACTION_MASK;
-			int node_count = *data & NODE_COUNT_MASK;
+			u32 action = be32_to_cpu(*data) & NODE_ACTION_MASK;
+			u32 node_count = be32_to_cpu(*data) & NODE_COUNT_MASK;
 
 			data++;
 
 			for (i = 0; i < node_count; i++) {
-				u32 phandle = *data++;
-				u32 drc_index;
+				__be32 phandle = *data++;
+				__be32 drc_index;
 
 				switch (action) {
 				case DELETE_DT_NODE:
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index 7f517ca19d32..ec255a1646d2 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -322,6 +322,7 @@
 313	common	finit_module		sys_finit_module
 314	common	sched_setattr		sys_sched_setattr
 315	common	sched_getattr		sys_sched_getattr
+316	common	renameat2		sys_renameat2
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c
index 930cad4e5df8..2b946bc4212d 100644
--- a/drivers/base/regmap/regcache-rbtree.c
+++ b/drivers/base/regmap/regcache-rbtree.c
@@ -313,7 +313,7 @@ static int regcache_rbtree_insert_to_block(struct regmap *map,
 	if (pos == 0) {
 		memmove(blk + offset * map->cache_word_size,
 			blk, rbnode->blklen * map->cache_word_size);
-		bitmap_shift_right(present, present, offset, blklen);
+		bitmap_shift_left(present, present, offset, blklen);
 	}
 
 	/* update the rbnode block, its size and the base register */
diff --git a/drivers/clocksource/time-efm32.c b/drivers/clocksource/time-efm32.c
index 1a6205b7bed3..35b016100673 100644
--- a/drivers/clocksource/time-efm32.c
+++ b/drivers/clocksource/time-efm32.c
@@ -225,12 +225,12 @@ static int __init efm32_clockevent_init(struct device_node *np)
 	clock_event_ddata.base = base;
 	clock_event_ddata.periodic_top = DIV_ROUND_CLOSEST(rate, 1024 * HZ);
 
-	setup_irq(irq, &efm32_clock_event_irq);
-
 	clockevents_config_and_register(&clock_event_ddata.evtdev,
 					DIV_ROUND_CLOSEST(rate, 1024),
 					0xf, 0xffff);
 
+	setup_irq(irq, &efm32_clock_event_irq);
+
 	return 0;
 
 err_get_irq:
diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c
index deebcd6469fc..4f0f3610371a 100644
--- a/drivers/clocksource/timer-sun5i.c
+++ b/drivers/clocksource/timer-sun5i.c
@@ -172,10 +172,6 @@ static void __init sun5i_timer_init(struct device_node *node)
 
 	ticks_per_jiffy = DIV_ROUND_UP(rate, HZ);
 
-	ret = setup_irq(irq, &sun5i_timer_irq);
-	if (ret)
-		pr_warn("failed to setup irq %d\n", irq);
-
 	/* Enable timer0 interrupt */
 	val = readl(timer_base + TIMER_IRQ_EN_REG);
 	writel(val | TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_EN_REG);
@@ -185,6 +181,10 @@ static void __init sun5i_timer_init(struct device_node *node)
 
 	clockevents_config_and_register(&sun5i_clockevent, rate,
 					TIMER_SYNC_TICKS, 0xffffffff);
+
+	ret = setup_irq(irq, &sun5i_timer_irq);
+	if (ret)
+		pr_warn("failed to setup irq %d\n", irq);
 }
 CLOCKSOURCE_OF_DECLARE(sun5i_a13, "allwinner,sun5i-a13-hstimer",
 		       sun5i_timer_init);
diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c
index 453822cc4f9d..fe8b0c991518 100644
--- a/drivers/dma/dw/platform.c
+++ b/drivers/dma/dw/platform.c
@@ -48,6 +48,8 @@ static bool dw_dma_of_filter(struct dma_chan *chan, void *param)
 	return true;
 }
 
+#define DRV_NAME	"dw_dmac"
+
 static struct dma_chan *dw_dma_of_xlate(struct of_phandle_args *dma_spec,
 					struct of_dma *ofdma)
 {
@@ -293,7 +295,7 @@ static struct platform_driver dw_driver = {
 	.remove		= dw_remove,
 	.shutdown	= dw_shutdown,
 	.driver = {
-		.name	= "dw_dmac",
+		.name	= DRV_NAME,
 		.pm	= &dw_dev_pm_ops,
 		.of_match_table = of_match_ptr(dw_dma_of_id_table),
 		.acpi_match_table = ACPI_PTR(dw_dma_acpi_id_table),
@@ -314,3 +316,4 @@ module_exit(dw_exit);
 
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Synopsys DesignWare DMA Controller platform driver");
+MODULE_ALIAS("platform:" DRV_NAME);
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index d2a8d64f8526..080e767250d3 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -291,9 +291,16 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
 	struct request_queue *q = bdev_get_queue(where->bdev);
 	unsigned short logical_block_size = queue_logical_block_size(q);
 	sector_t num_sectors;
+	unsigned int uninitialized_var(special_cmd_max_sectors);
 
-	/* Reject unsupported discard requests */
-	if ((rw & REQ_DISCARD) && !blk_queue_discard(q)) {
+	/*
+	 * Reject unsupported discard and write same requests.
+	 */
+	if (rw & REQ_DISCARD)
+		special_cmd_max_sectors = q->limits.max_discard_sectors;
+	else if (rw & REQ_WRITE_SAME)
+		special_cmd_max_sectors = q->limits.max_write_same_sectors;
+	if ((rw & (REQ_DISCARD | REQ_WRITE_SAME)) && special_cmd_max_sectors == 0) {
 		dec_count(io, region, -EOPNOTSUPP);
 		return;
 	}
@@ -319,7 +326,7 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
 		store_io_and_region_in_bio(bio, io, region);
 
 		if (rw & REQ_DISCARD) {
-			num_sectors = min_t(sector_t, q->limits.max_discard_sectors, remaining);
+			num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining);
 			bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT;
 			remaining -= num_sectors;
 		} else if (rw & REQ_WRITE_SAME) {
@@ -328,7 +335,7 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
 			 */
 			dp->get_page(dp, &page, &len, &offset);
 			bio_add_page(bio, page, logical_block_size, offset);
-			num_sectors = min_t(sector_t, q->limits.max_write_same_sectors, remaining);
+			num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining);
 			bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT;
 
 			offset = 0;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 1582c3dac3ac..e40059143272 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2352,10 +2352,16 @@ static void __dm_destroy(struct mapped_device *md, bool wait)
 	set_bit(DMF_FREEING, &md->flags);
 	spin_unlock(&_minor_lock);
 
+	/*
+	 * Take suspend_lock so that presuspend and postsuspend methods
+	 * do not race with internal suspend.
+	 */
+	mutex_lock(&md->suspend_lock);
 	if (!dm_suspended_md(md)) {
 		dm_table_presuspend_targets(map);
 		dm_table_postsuspend_targets(map);
 	}
+	mutex_unlock(&md->suspend_lock);
 
 	/* dm_put_live_table must be before msleep, otherwise deadlock is possible */
 	dm_put_live_table(md, srcu_idx);
diff --git a/drivers/mfd/kempld-core.c b/drivers/mfd/kempld-core.c
index 38917a822335..2df3cbc968d1 100644
--- a/drivers/mfd/kempld-core.c
+++ b/drivers/mfd/kempld-core.c
@@ -629,7 +629,7 @@ static int __init kempld_init(void)
 	if (force_device_id[0]) {
 		for (id = kempld_dmi_table; id->matches[0].slot != DMI_NONE; id++)
 			if (strstr(id->ident, force_device_id))
-				if (id->callback && id->callback(id))
+				if (id->callback && !id->callback(id))
 					break;
 		if (id->matches[0].slot == DMI_NONE)
 			return -ENODEV;
diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c
index 9339cccfe05a..ad0e71c7a607 100644
--- a/drivers/net/ethernet/amd/pcnet32.c
+++ b/drivers/net/ethernet/amd/pcnet32.c
@@ -1516,7 +1516,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev)
 {
 	struct pcnet32_private *lp;
 	int i, media;
-	int fdx, mii, fset, dxsuflo;
+	int fdx, mii, fset, dxsuflo, sram;
 	int chip_version;
 	char *chipname;
 	struct net_device *dev;
@@ -1553,7 +1553,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev)
 	}
 
 	/* initialize variables */
-	fdx = mii = fset = dxsuflo = 0;
+	fdx = mii = fset = dxsuflo = sram = 0;
 	chip_version = (chip_version >> 12) & 0xffff;
 
 	switch (chip_version) {
@@ -1586,6 +1586,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev)
 		chipname = "PCnet/FAST III 79C973";	/* PCI */
 		fdx = 1;
 		mii = 1;
+		sram = 1;
 		break;
 	case 0x2626:
 		chipname = "PCnet/Home 79C978";	/* PCI */
@@ -1609,6 +1610,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev)
 		chipname = "PCnet/FAST III 79C975";	/* PCI */
 		fdx = 1;
 		mii = 1;
+		sram = 1;
 		break;
 	case 0x2628:
 		chipname = "PCnet/PRO 79C976";
@@ -1637,6 +1639,31 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev)
 		dxsuflo = 1;
 	}
 
+	/*
+	 * The Am79C973/Am79C975 controllers come with 12K of SRAM
+	 * which we can use for the Tx/Rx buffers but most importantly,
+	 * the use of SRAM allow us to use the BCR18:NOUFLO bit to avoid
+	 * Tx fifo underflows.
+	 */
+	if (sram) {
+		/*
+		 * The SRAM is being configured in two steps. First we
+		 * set the SRAM size in the BCR25:SRAM_SIZE bits. According
+		 * to the datasheet, each bit corresponds to a 512-byte
+		 * page so we can have at most 24 pages. The SRAM_SIZE
+		 * holds the value of the upper 8 bits of the 16-bit SRAM size.
+		 * The low 8-bits start at 0x00 and end at 0xff. So the
+		 * address range is from 0x0000 up to 0x17ff. Therefore,
+		 * the SRAM_SIZE is set to 0x17. The next step is to set
+		 * the BCR26:SRAM_BND midway through so the Tx and Rx
+		 * buffers can share the SRAM equally.
+		 */
+		a->write_bcr(ioaddr, 25, 0x17);
+		a->write_bcr(ioaddr, 26, 0xc);
+		/* And finally enable the NOUFLO bit */
+		a->write_bcr(ioaddr, 18, a->read_bcr(ioaddr, 18) | (1 << 11));
+	}
+
 	dev = alloc_etherdev(sizeof(*lp));
 	if (!dev) {
 		ret = -ENOMEM;
diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
index a04174607e97..4a3b8b72c8af 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
@@ -594,7 +594,7 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw,
 
 	ret = iwl_mvm_mac_ctxt_add(mvm, vif);
 	if (ret)
-		goto out_remove_mac;
+		goto out_release;
 
 	iwl_mvm_power_disable(mvm, vif);
 
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 48f20ff1add9..bbff99dcbaea 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -290,7 +290,7 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar
 	struct device_node *p;
 	const __be32 *intspec, *tmp, *addr;
 	u32 intsize, intlen;
-	int i, res = -EINVAL;
+	int i, res;
 
 	pr_debug("of_irq_parse_one: dev=%s, index=%d\n", of_node_full_name(device), index);
 
@@ -323,15 +323,19 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar
 
 	/* Get size of interrupt specifier */
 	tmp = of_get_property(p, "#interrupt-cells", NULL);
-	if (tmp == NULL)
+	if (tmp == NULL) {
+		res = -EINVAL;
 		goto out;
+	}
 	intsize = be32_to_cpu(*tmp);
 
 	pr_debug(" intsize=%d intlen=%d\n", intsize, intlen);
 
 	/* Check index */
-	if ((index + 1) * intsize > intlen)
+	if ((index + 1) * intsize > intlen) {
+		res = -EINVAL;
 		goto out;
+	}
 
 	/* Copy intspec into irq structure */
 	intspec += index * intsize;
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index 34d56f7864d6..86592dd24da5 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -50,7 +50,9 @@ static void devm_phy_consume(struct device *dev, void *res)
 
 static int devm_phy_match(struct device *dev, void *res, void *match_data)
 {
-	return res == match_data;
+	struct phy **phy = res;
+
+	return *phy == match_data;
 }
 
 static struct phy *phy_lookup(struct device *device, const char *port)
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 9d81f7693f99..1817f3f2b02d 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -1515,7 +1515,7 @@ static int tcm_qla2xxx_check_initiator_node_acl(
 	/*
 	 * Finally register the new FC Nexus with TCM
 	 */
-	__transport_register_session(se_nacl->se_tpg, se_nacl, se_sess, sess);
+	transport_register_session(se_nacl->se_tpg, se_nacl, se_sess, sess);
 
 	return 0;
 }
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index fbf3b22efe5a..d6563ec700d4 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -846,13 +846,14 @@ void spi_finalize_current_message(struct spi_master *master)
 				"failed to unprepare message: %d\n", ret);
 		}
 	}
+
+	trace_spi_message_done(mesg);
+
 	master->cur_msg_prepared = false;
 
 	mesg->state = NULL;
 	if (mesg->complete)
 		mesg->complete(mesg->context);
-
-	trace_spi_message_done(mesg);
 }
 EXPORT_SYMBOL_GPL(spi_finalize_current_message);
 
diff --git a/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h b/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h
index eefdb8d061b1..81cc7a0134bb 100644
--- a/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h
+++ b/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h
@@ -105,8 +105,8 @@ static inline void ll_set_fs_pwd(struct fs_struct *fs, struct vfsmount *mnt,
 #define ll_vfs_unlink(inode,entry,mnt)	  vfs_unlink(inode,entry)
 #define ll_vfs_mknod(dir,entry,mnt,mode,dev)    vfs_mknod(dir,entry,mode,dev)
 #define ll_security_inode_unlink(dir,entry,mnt) security_inode_unlink(dir,entry)
-#define ll_vfs_rename(old,old_dir,mnt,new,new_dir,mnt1,delegated_inode) \
-		vfs_rename(old,old_dir,new,new_dir,delegated_inode)
+#define ll_vfs_rename(old, old_dir, mnt, new, new_dir, mnt1) \
+		vfs_rename(old, old_dir, new, new_dir, NULL, 0)
 
 #define cfs_bio_io_error(a,b)   bio_io_error((a))
 #define cfs_bio_endio(a,b,c)    bio_endio((a),(c))
diff --git a/drivers/staging/lustre/lustre/llite/llite_nfs.c b/drivers/staging/lustre/lustre/llite/llite_nfs.c
index 1767c741fb72..ed35a88c6dd9 100644
--- a/drivers/staging/lustre/lustre/llite/llite_nfs.c
+++ b/drivers/staging/lustre/lustre/llite/llite_nfs.c
@@ -205,13 +205,15 @@ static int ll_encode_fh(struct inode *inode, __u32 *fh, int *plen,
 	return LUSTRE_NFS_FID;
 }
 
-static int ll_nfs_get_name_filldir(void *cookie, const char *name, int namelen,
-				   loff_t hash, u64 ino, unsigned type)
+static int ll_nfs_get_name_filldir(struct dir_context *ctx, const char *name,
+				   int namelen, loff_t hash, u64 ino,
+				   unsigned type)
 {
 	/* It is hack to access lde_fid for comparison with lgd_fid.
 	 * So the input 'name' must be part of the 'lu_dirent'. */
 	struct lu_dirent *lde = container_of0(name, struct lu_dirent, lde_name);
-	struct ll_getname_data *lgd = cookie;
+	struct ll_getname_data *lgd =
+		container_of(ctx, struct ll_getname_data, ctx);
 	struct lu_fid fid;
 
 	fid_le_to_cpu(&fid, &lde->lde_fid);
diff --git a/drivers/staging/lustre/lustre/llite/symlink.c b/drivers/staging/lustre/lustre/llite/symlink.c
index ab06891f7fc7..80d48b5ae247 100644
--- a/drivers/staging/lustre/lustre/llite/symlink.c
+++ b/drivers/staging/lustre/lustre/llite/symlink.c
@@ -115,27 +115,6 @@ failed:
 	return rc;
 }
 
-static int ll_readlink(struct dentry *dentry, char *buffer, int buflen)
-{
-	struct inode *inode = dentry->d_inode;
-	struct ptlrpc_request *request;
-	char *symname;
-	int rc;
-
-	CDEBUG(D_VFSTRACE, "VFS Op\n");
-
-	ll_inode_size_lock(inode);
-	rc = ll_readlink_internal(inode, &request, &symname);
-	if (rc)
-		GOTO(out, rc);
-
-	rc = vfs_readlink(dentry, buffer, buflen, symname);
- out:
-	ptlrpc_req_finished(request);
-	ll_inode_size_unlock(inode);
-	return rc;
-}
-
 static void *ll_follow_link(struct dentry *dentry, struct nameidata *nd)
 {
 	struct inode *inode = dentry->d_inode;
@@ -175,7 +154,7 @@ static void ll_put_link(struct dentry *dentry, struct nameidata *nd, void *cooki
 }
 
 struct inode_operations ll_fast_symlink_inode_operations = {
-	.readlink	= ll_readlink,
+	.readlink	= generic_readlink,
 	.setattr	= ll_setattr,
 	.follow_link	= ll_follow_link,
 	.put_link	= ll_put_link,
diff --git a/drivers/staging/lustre/lustre/lvfs/lvfs_linux.c b/drivers/staging/lustre/lustre/lvfs/lvfs_linux.c
index 428ffd8c37b7..d50822be3230 100644
--- a/drivers/staging/lustre/lustre/lvfs/lvfs_linux.c
+++ b/drivers/staging/lustre/lustre/lvfs/lvfs_linux.c
@@ -223,7 +223,7 @@ int lustre_rename(struct dentry *dir, struct vfsmount *mnt,
 		GOTO(put_old, err = PTR_ERR(dchild_new));
 
 	err = ll_vfs_rename(dir->d_inode, dchild_old, mnt,
-			    dir->d_inode, dchild_new, mnt, NULL);
+			    dir->d_inode, dchild_new, mnt);
 
 	dput(dchild_new);
 put_old:
diff --git a/drivers/staging/vt6655/rf.c b/drivers/staging/vt6655/rf.c
index edb1b2768b17..dbd9d44919ac 100644
--- a/drivers/staging/vt6655/rf.c
+++ b/drivers/staging/vt6655/rf.c
@@ -936,6 +936,7 @@ bool RFbSetPower(
 		break;
 	case RATE_6M:
 	case RATE_9M:
+	case RATE_12M:
 	case RATE_18M:
 		byPwr = pDevice->abyOFDMPwrTbl[uCH];
 		if (pDevice->byRFType == RF_UW2452) {
diff --git a/drivers/staging/vt6656/rf.c b/drivers/staging/vt6656/rf.c
index 1e8f64bff03c..2dc48d4ff433 100644
--- a/drivers/staging/vt6656/rf.c
+++ b/drivers/staging/vt6656/rf.c
@@ -752,6 +752,7 @@ int RFbSetPower(struct vnt_private *priv, u32 rate, u32 channel)
 		break;
 	case RATE_6M:
 	case RATE_9M:
+	case RATE_12M:
 	case RATE_18M:
 	case RATE_24M:
 	case RATE_36M:
diff --git a/drivers/target/tcm_fc/tfc_io.c b/drivers/target/tcm_fc/tfc_io.c
index e415af32115a..c67d3795db4a 100644
--- a/drivers/target/tcm_fc/tfc_io.c
+++ b/drivers/target/tcm_fc/tfc_io.c
@@ -346,7 +346,7 @@ void ft_invl_hw_context(struct ft_cmd *cmd)
 		ep = fc_seq_exch(seq);
 		if (ep) {
 			lport = ep->lp;
-			if (lport && (ep->xid <= lport->lro_xid))
+			if (lport && (ep->xid <= lport->lro_xid)) {
 				/*
 				 * "ddp_done" trigger invalidation of HW
 				 * specific DDP context
@@ -361,6 +361,7 @@ void ft_invl_hw_context(struct ft_cmd *cmd)
 				 * identified using ep->xid)
 				 */
 				cmd->was_ddp_setup = 0;
+			}
 		}
 	}
 }
diff --git a/fs/Kconfig b/fs/Kconfig
index 7385e54be4b9..6b40fd8d719e 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -67,6 +67,7 @@ source "fs/quota/Kconfig"
 
 source "fs/autofs4/Kconfig"
 source "fs/fuse/Kconfig"
+source "fs/overlayfs/Kconfig"
 
 menu "Caches"
 
diff --git a/fs/Makefile b/fs/Makefile
index 47ac07bb4acc..b5954404e02d 100644
--- a/fs/Makefile
+++ b/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-$(CONFIG_OVERLAY_FS)	+= overlayfs/
 obj-$(CONFIG_UDF_FS)		+= udf/
 obj-$(CONFIG_SUN_OPENPROMFS)	+= openpromfs/
 obj-$(CONFIG_OMFS_FS)		+= omfs/
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 529300327f45..5479af6de6ce 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -26,7 +26,7 @@ static int afs_readdir(struct file *file, struct dir_context *ctx);
 static int afs_d_revalidate(struct dentry *dentry, unsigned int flags);
 static int afs_d_delete(const struct dentry *dentry);
 static void afs_d_release(struct dentry *dentry);
-static int afs_lookup_filldir(void *_cookie, const char *name, int nlen,
+static int afs_lookup_filldir(struct dir_context *ctx, const char *name, int nlen,
 				  loff_t fpos, u64 ino, unsigned dtype);
 static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 		      bool excl);
@@ -391,10 +391,11 @@ static int afs_readdir(struct file *file, struct dir_context *ctx)
  * - if afs_dir_iterate_block() spots this function, it'll pass the FID
  *   uniquifier through dtype
  */
-static int afs_lookup_filldir(void *_cookie, const char *name, int nlen,
-			      loff_t fpos, u64 ino, unsigned dtype)
+static int afs_lookup_filldir(struct dir_context *ctx, const char *name,
+			      int nlen, loff_t fpos, u64 ino, unsigned dtype)
 {
-	struct afs_lookup_cookie *cookie = _cookie;
+	struct afs_lookup_cookie *cookie =
+		container_of(ctx, struct afs_lookup_cookie, ctx);
 
 	_enter("{%s,%u},%s,%u,,%llu,%u",
 	       cookie->name.name, cookie->name.len, name, nlen,
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 0b72006aecbe..96b95e6f9f91 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -682,23 +682,6 @@ out:
 	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.
@@ -734,8 +717,7 @@ 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) {
diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c
index 622f4696e484..5b99bafc31d1 100644
--- a/fs/cachefiles/bind.c
+++ b/fs/cachefiles/bind.c
@@ -124,7 +124,6 @@ static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache)
 	/* check parameters */
 	ret = -EOPNOTSUPP;
 	if (!root->d_inode ||
-	    !root->d_inode->i_op ||
 	    !root->d_inode->i_op->lookup ||
 	    !root->d_inode->i_op->mkdir ||
 	    !root->d_inode->i_op->setxattr ||
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index ca65f39dc8dc..c0a681705104 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -391,12 +391,12 @@ try_again:
 	path.dentry = dir;
 	path_to_graveyard.mnt = cache->mnt;
 	path_to_graveyard.dentry = cache->graveyard;
-	ret = security_path_rename(&path, rep, &path_to_graveyard, grave);
+	ret = security_path_rename(&path, rep, &path_to_graveyard, grave, 0);
 	if (ret < 0) {
 		cachefiles_io_error(cache, "Rename security error %d", ret);
 	} else {
 		ret = vfs_rename(dir->d_inode, rep,
-				 cache->graveyard->d_inode, grave, NULL);
+				 cache->graveyard->d_inode, grave, NULL, 0);
 		if (ret != 0 && ret != -ENOMEM)
 			cachefiles_io_error(cache,
 					    "Rename failed with error %d", ret);
@@ -779,8 +779,7 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
 	}
 
 	ret = -EPERM;
-	if (!subdir->d_inode->i_op ||
-	    !subdir->d_inode->i_op->setxattr ||
+	if (!subdir->d_inode->i_op->setxattr ||
 	    !subdir->d_inode->i_op->getxattr ||
 	    !subdir->d_inode->i_op->lookup ||
 	    !subdir->d_inode->i_op->mkdir ||
diff --git a/fs/compat.c b/fs/compat.c
index 6af20de2c1a3..14da9b327ffa 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -837,10 +837,12 @@ struct compat_readdir_callback {
 	int result;
 };
 
-static int compat_fillonedir(void *__buf, const char *name, int namlen,
-			loff_t offset, u64 ino, unsigned int d_type)
+static int compat_fillonedir(struct dir_context *ctx, const char *name,
+			     int namlen, loff_t offset, u64 ino,
+			     unsigned int d_type)
 {
-	struct compat_readdir_callback *buf = __buf;
+	struct compat_readdir_callback *buf =
+		container_of(ctx, struct compat_readdir_callback, ctx);
 	struct compat_old_linux_dirent __user *dirent;
 	compat_ulong_t d_ino;
 
@@ -905,11 +907,12 @@ struct compat_getdents_callback {
 	int error;
 };
 
-static int compat_filldir(void *__buf, const char *name, int namlen,
+static int compat_filldir(struct dir_context *ctx, const char *name, int namlen,
 		loff_t offset, u64 ino, unsigned int d_type)
 {
 	struct compat_linux_dirent __user * dirent;
-	struct compat_getdents_callback *buf = __buf;
+	struct compat_getdents_callback *buf =
+		container_of(ctx, struct compat_getdents_callback, ctx);
 	compat_ulong_t d_ino;
 	int reclen = ALIGN(offsetof(struct compat_linux_dirent, d_name) +
 		namlen + 2, sizeof(compat_long_t));
@@ -991,11 +994,13 @@ struct compat_getdents_callback64 {
 	int error;
 };
 
-static int compat_filldir64(void * __buf, const char * name, int namlen, loff_t offset,
-		     u64 ino, unsigned int d_type)
+static int compat_filldir64(struct dir_context *ctx, const char *name,
+			    int namlen, loff_t offset, u64 ino,
+			    unsigned int d_type)
 {
 	struct linux_dirent64 __user *dirent;
-	struct compat_getdents_callback64 *buf = __buf;
+	struct compat_getdents_callback64 *buf =
+		container_of(ctx, struct compat_getdents_callback64, ctx);
 	int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1,
 		sizeof(u64));
 	u64 off;
diff --git a/fs/dcache.c b/fs/dcache.c
index 436612777203..e3c556351810 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2481,12 +2481,14 @@ static void switch_names(struct dentry *dentry, struct dentry *target)
 			dentry->d_name.name = dentry->d_iname;
 		} else {
 			/*
-			 * Both are internal.  Just copy target to dentry
+			 * Both are internal.
 			 */
-			memcpy(dentry->d_iname, target->d_name.name,
-					target->d_name.len + 1);
-			dentry->d_name.len = target->d_name.len;
-			return;
+			unsigned int i;
+			BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long)));
+			for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) {
+				swap(((long *) &dentry->d_iname)[i],
+				     ((long *) &target->d_iname)[i]);
+			}
 		}
 	}
 	swap(dentry->d_name.len, target->d_name.len);
@@ -2543,13 +2545,15 @@ static void dentry_unlock_parents_for_move(struct dentry *dentry,
  * __d_move - move a dentry
  * @dentry: entry to move
  * @target: new dentry
+ * @exchange: exchange the two dentries
  *
  * Update the dcache to reflect the move of a file name. Negative
  * dcache entries should not be moved in this way. Caller must hold
  * rename_lock, the i_mutex of the source and target directories,
  * and the sb->s_vfs_rename_mutex if they differ. See lock_rename().
  */
-static void __d_move(struct dentry * dentry, struct dentry * target)
+static void __d_move(struct dentry *dentry, struct dentry *target,
+		     bool exchange)
 {
 	if (!dentry->d_inode)
 		printk(KERN_WARNING "VFS: moving negative dcache entry\n");
@@ -2571,8 +2575,15 @@ static void __d_move(struct dentry * dentry, struct dentry * target)
 	__d_drop(dentry);
 	__d_rehash(dentry, d_hash(target->d_parent, target->d_name.hash));
 
-	/* Unhash the target: dput() will then get rid of it */
+	/*
+	 * Unhash the target (d_delete() is not usable here).  If exchanging
+	 * the two dentries, then rehash onto the other's hash queue.
+	 */
 	__d_drop(target);
+	if (exchange) {
+		__d_rehash(target,
+			   d_hash(dentry->d_parent, dentry->d_name.hash));
+	}
 
 	list_del(&dentry->d_u.d_child);
 	list_del(&target->d_u.d_child);
@@ -2599,6 +2610,8 @@ static void __d_move(struct dentry * dentry, struct dentry * target)
 	write_seqcount_end(&dentry->d_seq);
 
 	dentry_unlock_parents_for_move(dentry, target);
+	if (exchange)
+		fsnotify_d_move(target);
 	spin_unlock(&target->d_lock);
 	fsnotify_d_move(dentry);
 	spin_unlock(&dentry->d_lock);
@@ -2616,11 +2629,30 @@ static void __d_move(struct dentry * dentry, struct dentry * target)
 void d_move(struct dentry *dentry, struct dentry *target)
 {
 	write_seqlock(&rename_lock);
-	__d_move(dentry, target);
+	__d_move(dentry, target, false);
 	write_sequnlock(&rename_lock);
 }
 EXPORT_SYMBOL(d_move);
 
+/*
+ * d_exchange - exchange two dentries
+ * @dentry1: first dentry
+ * @dentry2: second dentry
+ */
+void d_exchange(struct dentry *dentry1, struct dentry *dentry2)
+{
+	write_seqlock(&rename_lock);
+
+	WARN_ON(!dentry1->d_inode);
+	WARN_ON(!dentry2->d_inode);
+	WARN_ON(IS_ROOT(dentry1));
+	WARN_ON(IS_ROOT(dentry2));
+
+	__d_move(dentry1, dentry2, true);
+
+	write_sequnlock(&rename_lock);
+}
+
 /**
  * d_ancestor - search for an ancestor
  * @p1: ancestor dentry
@@ -2668,7 +2700,7 @@ static struct dentry *__d_unalias(struct inode *inode,
 	m2 = &alias->d_parent->d_inode->i_mutex;
 out_unalias:
 	if (likely(!d_mountpoint(alias))) {
-		__d_move(alias, dentry);
+		__d_move(alias, dentry, false);
 		ret = alias;
 	}
 out_err:
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 03df50211c48..121a94876d40 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -76,11 +76,11 @@ struct ecryptfs_getdents_callback {
 
 /* Inspired by generic filldir in fs/readdir.c */
 static int
-ecryptfs_filldir(void *dirent, const char *lower_name, int lower_namelen,
-		 loff_t offset, u64 ino, unsigned int d_type)
+ecryptfs_filldir(struct dir_context *ctx, const char *lower_name,
+		 int lower_namelen, loff_t offset, u64 ino, unsigned int d_type)
 {
 	struct ecryptfs_getdents_callback *buf =
-	    (struct ecryptfs_getdents_callback *)dirent;
+		container_of(ctx, struct ecryptfs_getdents_callback, ctx);
 	size_t name_size;
 	char *name;
 	int rc;
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index a85ceb7c91bc..57ee4c53b4f8 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -641,7 +641,7 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	}
 	rc = vfs_rename(lower_old_dir_dentry->d_inode, lower_old_dentry,
 			lower_new_dir_dentry->d_inode, lower_new_dentry,
-			NULL);
+			NULL, 0);
 	if (rc)
 		goto out_lock;
 	if (target_inode)
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 34eb8433d93f..d9eb84bda559 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -576,6 +576,13 @@ 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);
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 48a359dd286e..59d339c417c9 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -241,10 +241,11 @@ struct getdents_callback {
  * A rather strange filldir function to capture
  * the name matching the specified inode number.
  */
-static int filldir_one(void * __buf, const char * name, int len,
+static int filldir_one(struct dir_context *ctx, const char *name, int len,
 			loff_t pos, u64 ino, unsigned int d_type)
 {
-	struct getdents_callback *buf = __buf;
+	struct getdents_callback *buf =
+		container_of(ctx, struct getdents_callback, ctx);
 	int result = 0;
 
 	buf->sequence++;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 2dcbfb6245d8..98de4b391e79 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -3191,6 +3191,16 @@ end_rename:
 	return retval;
 }
 
+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)
+		return -EINVAL;
+
+	return ext4_rename(old_dir, old_dentry, new_dir, new_dentry);
+}
+
 /*
  * directories can handle most operations...
  */
@@ -3204,7 +3214,7 @@ const struct inode_operations ext4_dir_inode_operations = {
 	.rmdir		= ext4_rmdir,
 	.mknod		= ext4_mknod,
 	.tmpfile	= ext4_tmpfile,
-	.rename		= ext4_rename,
+	.rename2	= ext4_rename2,
 	.setattr	= ext4_setattr,
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 3963ede84eb0..c5d6bb939d19 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -702,10 +702,11 @@ static int fat_readdir(struct file *file, struct dir_context *ctx)
 }
 
 #define FAT_IOCTL_FILLDIR_FUNC(func, dirent_type)			   \
-static int func(void *__buf, const char *name, int name_len,		   \
+static int func(struct dir_context *ctx, const char *name, int name_len,   \
 			     loff_t offset, u64 ino, unsigned int d_type)  \
 {									   \
-	struct fat_ioctl_filldir_callback *buf = __buf;			   \
+	struct fat_ioctl_filldir_callback *buf =			   \
+		container_of(ctx, struct fat_ioctl_filldir_callback, ctx); \
 	struct dirent_type __user *d1 = buf->dirent;			   \
 	struct dirent_type __user *d2 = d1 + 1;				   \
 									   \
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 342f0239fcbf..d53a7d91eb07 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -796,6 +796,36 @@ static int fuse_rename(struct inode *olddir, struct dentry *oldent,
 	return err;
 }
 
+static int fuse_rename2(struct inode *olddir, struct dentry *oldent,
+			struct inode *newdir, struct dentry *newent,
+			unsigned int flags)
+{
+	struct fuse_conn *fc = get_fuse_conn(olddir);
+	int err;
+
+	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
+		return -EINVAL;
+
+	if (flags) {
+		if (fc->no_rename2 || fc->minor < 23)
+			return -EINVAL;
+
+		err = fuse_rename_common(olddir, oldent, newdir, newent, flags,
+					 FUSE_RENAME2,
+					 sizeof(struct fuse_rename2_in));
+		if (err == -ENOSYS) {
+			fc->no_rename2 = 1;
+			err = -EINVAL;
+		}
+	} else {
+		err = fuse_rename_common(olddir, oldent, newdir, newent, 0,
+					 FUSE_RENAME,
+					 sizeof(struct fuse_rename_in));
+	}
+
+	return err;
+}
+
 static int fuse_link(struct dentry *entry, struct inode *newdir,
 		     struct dentry *newent)
 {
@@ -1882,7 +1912,7 @@ static const struct inode_operations fuse_dir_inode_operations = {
 	.symlink	= fuse_symlink,
 	.unlink		= fuse_unlink,
 	.rmdir		= fuse_rmdir,
-	.rename		= fuse_rename,
+	.rename2	= fuse_rename2,
 	.link		= fuse_link,
 	.setattr	= fuse_setattr,
 	.create		= fuse_create,
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index 8b9b3775e2e7..c41d255b6a7b 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -69,10 +69,12 @@ struct get_name_filldir {
 	char *name;
 };
 
-static int get_name_filldir(void *opaque, const char *name, int length,
-			    loff_t offset, u64 inum, unsigned int type)
+static int get_name_filldir(struct dir_context *ctx, const char *name,
+			    int length, loff_t offset, u64 inum,
+			    unsigned int type)
 {
-	struct get_name_filldir *gnfd = opaque;
+	struct get_name_filldir *gnfd =
+		container_of(ctx, struct get_name_filldir, ctx);
 
 	if (inum != gnfd->inum.no_addr)
 		return 0;
diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c
index 6e560d56094b..754fdf8c6356 100644
--- a/fs/hfsplus/brec.c
+++ b/fs/hfsplus/brec.c
@@ -131,13 +131,16 @@ skip:
 	hfs_bnode_write(node, entry, data_off + key_len, entry_len);
 	hfs_bnode_dump(node);
 
-	if (new_node) {
-		/* update parent key if we inserted a key
-		 * at the start of the first node
-		 */
-		if (!rec && new_node != node)
-			hfs_brec_update_parent(fd);
+	/*
+	 * update parent key if we inserted a key
+	 * at the start of the node and it is not the new node
+	 */
+	if (!rec && new_node != node) {
+		hfs_bnode_read_key(node, fd->search_key, data_off + size);
+		hfs_brec_update_parent(fd);
+	}
 
+	if (new_node) {
 		hfs_bnode_put(fd->bnode);
 		if (!new_node->parent) {
 			hfs_btree_inc_height(tree);
@@ -168,9 +171,6 @@ skip:
 		goto again;
 	}
 
-	if (!rec)
-		hfs_brec_update_parent(fd);
-
 	return 0;
 }
 
@@ -370,6 +370,8 @@ again:
 	if (IS_ERR(parent))
 		return PTR_ERR(parent);
 	__hfs_brec_find(parent, fd, hfs_find_rec_by_key);
+	if (fd->record < 0)
+		return -ENOENT;
 	hfs_bnode_dump(parent);
 	rec = fd->record;
 
diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c
index 4338ff32959d..5f2755117ce7 100644
--- a/fs/hppfs/hppfs.c
+++ b/fs/hppfs/hppfs.c
@@ -548,10 +548,11 @@ struct hppfs_dirent {
 	struct dentry *dentry;
 };
 
-static int hppfs_filldir(void *d, const char *name, int size,
+static int hppfs_filldir(struct dir_context *ctx, const char *name, int size,
 			 loff_t offset, u64 inode, unsigned int type)
 {
-	struct hppfs_dirent *dirent = d;
+	struct hppfs_dirent *dirent =
+		container_of(ctx, struct hppfs_dirent, ctx);
 
 	if (file_removed(dirent->dentry, name))
 		return 0;
diff --git a/fs/internal.h b/fs/internal.h
index 465742407466..dd41b12c13f1 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -42,7 +42,6 @@ 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 *);
@@ -135,12 +134,6 @@ extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *);
 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
  */
 extern const struct file_operations pipefifo_fops;
diff --git a/fs/namei.c b/fs/namei.c
index 0dd72c8e65fd..0fbf1504fb63 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -415,6 +415,7 @@ int __inode_permission(struct inode *inode, int mask)
 
 	return security_inode_permission(inode, mask);
 }
+EXPORT_SYMBOL(__inode_permission);
 
 /**
  * sb_permission - Check superblock-level permissions
@@ -2359,22 +2360,17 @@ 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
@@ -2477,7 +2473,7 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2)
 	}
 
 	mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
-	mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD);
+	mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_PARENT2);
 	return NULL;
 }
 
@@ -3037,9 +3033,12 @@ finish_open_created:
 	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;
@@ -3977,7 +3976,28 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname
 	return sys_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
 }
 
-/*
+/**
+ * vfs_rename - rename a filesystem object
+ * @old_dir:	parent of source
+ * @old_dentry:	source
+ * @new_dir:	parent of destination
+ * @new_dentry:	destination
+ * @delegated_inode: returns an inode needing a delegation break
+ * @flags:	rename flags
+ *
+ * The caller must hold multiple mutexes--see lock_rename()).
+ *
+ * If vfs_rename discovers a delegation in need of breaking at either
+ * the source or destination, it will return -EWOULDBLOCK and return a
+ * reference to the inode in delegated_inode.  The caller should then
+ * break the delegation and retry.  Because breaking a delegation may
+ * take a long time, the caller should drop all locks before doing
+ * so.
+ *
+ * Alternatively, a caller may pass NULL for delegated_inode.  This may
+ * be appropriate for callers that expect the underlying filesystem not
+ * to be NFS exported.
+ *
  * The worst of all namespace operations - renaming directory. "Perverted"
  * doesn't even start to describe it. Somebody in UCB had a heck of a trip...
  * Problems:
@@ -4005,163 +4025,140 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname
  *	   ->i_mutex on parents, which works but leads to some truly excessive
  *	   locking].
  */
-static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry,
-			  struct inode *new_dir, struct dentry *new_dentry)
+int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+	       struct inode *new_dir, struct dentry *new_dentry,
+	       struct inode **delegated_inode, unsigned int flags)
 {
-	int error = 0;
+	int error;
+	bool is_dir = d_is_dir(old_dentry);
+	const unsigned char *old_name;
+	struct inode *source = old_dentry->d_inode;
 	struct inode *target = new_dentry->d_inode;
+	bool new_is_dir = false;
 	unsigned max_links = new_dir->i_sb->s_max_links;
 
+	if (source == target)
+		return 0;
+
+	error = may_delete(old_dir, old_dentry, is_dir);
+	if (error)
+		return error;
+
+	if (!target) {
+		error = may_create(new_dir, new_dentry);
+	} else {
+		new_is_dir = d_is_dir(new_dentry);
+
+		if (!(flags & RENAME_EXCHANGE))
+			error = may_delete(new_dir, new_dentry, is_dir);
+		else
+			error = may_delete(new_dir, new_dentry, new_is_dir);
+	}
+	if (error)
+		return error;
+
+	if (!old_dir->i_op->rename && !old_dir->i_op->rename2)
+		return -EPERM;
+
+	if (flags && !old_dir->i_op->rename2)
+		return -EINVAL;
+
 	/*
 	 * If we are going to change the parent - check write permissions,
 	 * we'll need to flip '..'.
 	 */
 	if (new_dir != old_dir) {
-		error = inode_permission(old_dentry->d_inode, MAY_WRITE);
-		if (error)
-			return error;
+		if (is_dir) {
+			error = inode_permission(source, MAY_WRITE);
+			if (error)
+				return error;
+		}
+		if ((flags & RENAME_EXCHANGE) && new_is_dir) {
+			error = inode_permission(target, MAY_WRITE);
+			if (error)
+				return error;
+		}
 	}
 
-	error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry);
+	error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry,
+				      flags);
 	if (error)
 		return error;
 
+	old_name = fsnotify_oldname_init(old_dentry->d_name.name);
 	dget(new_dentry);
-	if (target)
+	if (!is_dir || (flags & RENAME_EXCHANGE))
+		lock_two_nondirectories(source, target);
+	else if (target)
 		mutex_lock(&target->i_mutex);
 
 	error = -EBUSY;
 	if (d_mountpoint(old_dentry) || d_mountpoint(new_dentry))
 		goto out;
 
-	error = -EMLINK;
-	if (max_links && !target && new_dir != old_dir &&
-	    new_dir->i_nlink >= max_links)
-		goto out;
-
-	if (target)
+	if (max_links && new_dir != old_dir) {
+		error = -EMLINK;
+		if (is_dir && !new_is_dir && new_dir->i_nlink >= max_links)
+			goto out;
+		if ((flags & RENAME_EXCHANGE) && !is_dir && new_is_dir &&
+		    old_dir->i_nlink >= max_links)
+			goto out;
+	}
+	if (is_dir && !(flags & RENAME_EXCHANGE) && target)
 		shrink_dcache_parent(new_dentry);
-	error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
-	if (error)
-		goto out;
-
-	if (target) {
-		target->i_flags |= S_DEAD;
-		dont_mount(new_dentry);
+	if (!is_dir) {
+		error = try_break_deleg(source, delegated_inode);
+		if (error)
+			goto out;
 	}
-out:
-	if (target)
-		mutex_unlock(&target->i_mutex);
-	dput(new_dentry);
-	if (!error)
-		if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE))
-			d_move(old_dentry,new_dentry);
-	return error;
-}
-
-static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry,
-			    struct inode *new_dir, struct dentry *new_dentry,
-			    struct inode **delegated_inode)
-{
-	struct inode *target = new_dentry->d_inode;
-	struct inode *source = old_dentry->d_inode;
-	int error;
-
-	error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry);
-	if (error)
-		return error;
-
-	dget(new_dentry);
-	lock_two_nondirectories(source, target);
-
-	error = -EBUSY;
-	if (d_mountpoint(old_dentry)||d_mountpoint(new_dentry))
-		goto out;
-
-	error = try_break_deleg(source, delegated_inode);
-	if (error)
-		goto out;
-	if (target) {
+	if (target && !new_is_dir) {
 		error = try_break_deleg(target, delegated_inode);
 		if (error)
 			goto out;
 	}
-	error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
+	if (!old_dir->i_op->rename2) {
+		error = old_dir->i_op->rename(old_dir, old_dentry,
+					      new_dir, new_dentry);
+	} else {
+		WARN_ON(old_dir->i_op->rename != NULL);
+		error = old_dir->i_op->rename2(old_dir, old_dentry,
+					       new_dir, new_dentry, flags);
+	}
 	if (error)
 		goto out;
 
-	if (target)
+	if (!(flags & RENAME_EXCHANGE) && target) {
+		if (is_dir)
+			target->i_flags |= S_DEAD;
 		dont_mount(new_dentry);
-	if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE))
-		d_move(old_dentry, new_dentry);
+	}
+	if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) {
+		if (!(flags & RENAME_EXCHANGE))
+			d_move(old_dentry, new_dentry);
+		else
+			d_exchange(old_dentry, new_dentry);
+	}
 out:
-	unlock_two_nondirectories(source, target);
+	if (!is_dir || (flags & RENAME_EXCHANGE))
+		unlock_two_nondirectories(source, target);
+	else if (target)
+		mutex_unlock(&target->i_mutex);
 	dput(new_dentry);
-	return error;
-}
-
-/**
- * vfs_rename - rename a filesystem object
- * @old_dir:	parent of source
- * @old_dentry:	source
- * @new_dir:	parent of destination
- * @new_dentry:	destination
- * @delegated_inode: returns an inode needing a delegation break
- *
- * The caller must hold multiple mutexes--see lock_rename()).
- *
- * If vfs_rename discovers a delegation in need of breaking at either
- * the source or destination, it will return -EWOULDBLOCK and return a
- * reference to the inode in delegated_inode.  The caller should then
- * break the delegation and retry.  Because breaking a delegation may
- * take a long time, the caller should drop all locks before doing
- * so.
- *
- * Alternatively, a caller may pass NULL for delegated_inode.  This may
- * be appropriate for callers that expect the underlying filesystem not
- * to be NFS exported.
- */
-int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
-	       struct inode *new_dir, struct dentry *new_dentry,
-	       struct inode **delegated_inode)
-{
-	int error;
-	int is_dir = d_is_dir(old_dentry);
-	const unsigned char *old_name;
-
-	if (old_dentry->d_inode == new_dentry->d_inode)
- 		return 0;
- 
-	error = may_delete(old_dir, old_dentry, is_dir);
-	if (error)
-		return error;
-
-	if (!new_dentry->d_inode)
-		error = may_create(new_dir, new_dentry);
-	else
-		error = may_delete(new_dir, new_dentry, is_dir);
-	if (error)
-		return error;
-
-	if (!old_dir->i_op->rename)
-		return -EPERM;
-
-	old_name = fsnotify_oldname_init(old_dentry->d_name.name);
-
-	if (is_dir)
-		error = vfs_rename_dir(old_dir,old_dentry,new_dir,new_dentry);
-	else
-		error = vfs_rename_other(old_dir,old_dentry,new_dir,new_dentry,delegated_inode);
-	if (!error)
+	if (!error) {
 		fsnotify_move(old_dir, new_dir, old_name, is_dir,
-			      new_dentry->d_inode, old_dentry);
+			      !(flags & RENAME_EXCHANGE) ? target : NULL, old_dentry);
+		if (flags & RENAME_EXCHANGE) {
+			fsnotify_move(new_dir, old_dir, old_dentry->d_name.name,
+				      new_is_dir, NULL, new_dentry);
+		}
+	}
 	fsnotify_oldname_free(old_name);
 
 	return error;
 }
 
-SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
-		int, newdfd, const char __user *, newname)
+SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
+		int, newdfd, const char __user *, newname, unsigned int, flags)
 {
 	struct dentry *old_dir, *new_dir;
 	struct dentry *old_dentry, *new_dentry;
@@ -4173,6 +4170,17 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
 	unsigned int lookup_flags = 0;
 	bool should_retry = false;
 	int error;
+
+	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
+		return -EINVAL;
+
+	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)) {
@@ -4196,6 +4204,8 @@ retry:
 		goto exit2;
 
 	new_dir = newnd.path.dentry;
+	if (flags & RENAME_NOREPLACE)
+		error = -EEXIST;
 	if (newnd.last_type != LAST_NORM)
 		goto exit2;
 
@@ -4205,7 +4215,8 @@ retry:
 
 	oldnd.flags &= ~LOOKUP_PARENT;
 	newnd.flags &= ~LOOKUP_PARENT;
-	newnd.flags |= LOOKUP_RENAME_TARGET;
+	if (!(flags & RENAME_EXCHANGE))
+		newnd.flags |= LOOKUP_RENAME_TARGET;
 
 retry_deleg:
 	trap = lock_rename(new_dir, old_dir);
@@ -4218,34 +4229,49 @@ retry_deleg:
 	error = -ENOENT;
 	if (d_is_negative(old_dentry))
 		goto exit4;
+	new_dentry = lookup_hash(&newnd);
+	error = PTR_ERR(new_dentry);
+	if (IS_ERR(new_dentry))
+		goto exit4;
+	error = -EEXIST;
+	if ((flags & RENAME_NOREPLACE) && d_is_positive(new_dentry))
+		goto exit5;
+	if (flags & RENAME_EXCHANGE) {
+		error = -ENOENT;
+		if (d_is_negative(new_dentry))
+			goto exit5;
+
+		if (!d_is_dir(new_dentry)) {
+			error = -ENOTDIR;
+			if (newnd.last.name[newnd.last.len])
+				goto exit5;
+		}
+	}
 	/* unless the source is a directory trailing slashes give -ENOTDIR */
 	if (!d_is_dir(old_dentry)) {
 		error = -ENOTDIR;
 		if (oldnd.last.name[oldnd.last.len])
-			goto exit4;
-		if (newnd.last.name[newnd.last.len])
-			goto exit4;
+			goto exit5;
+		if (!(flags & RENAME_EXCHANGE) && newnd.last.name[newnd.last.len])
+			goto exit5;
 	}
 	/* source should not be ancestor of target */
 	error = -EINVAL;
 	if (old_dentry == trap)
-		goto exit4;
-	new_dentry = lookup_hash(&newnd);
-	error = PTR_ERR(new_dentry);
-	if (IS_ERR(new_dentry))
-		goto exit4;
+		goto exit5;
 	/* target should not be an ancestor of source */
-	error = -ENOTEMPTY;
+	if (!(flags & RENAME_EXCHANGE))
+		error = -ENOTEMPTY;
 	if (new_dentry == trap)
 		goto exit5;
 
 	error = security_path_rename(&oldnd.path, old_dentry,
-				     &newnd.path, new_dentry);
+				     &newnd.path, new_dentry, flags);
 	if (error)
 		goto exit5;
 	error = vfs_rename(old_dir->d_inode, old_dentry,
-				   new_dir->d_inode, new_dentry,
-				   &delegated_inode);
+			   new_dir->d_inode, new_dentry,
+			   &delegated_inode, flags);
 exit5:
 	dput(new_dentry);
 exit4:
@@ -4275,16 +4301,34 @@ exit:
 	return error;
 }
 
+SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
+		int, newdfd, const char __user *, newname)
+{
+	return sys_renameat2(olddfd, oldname, newdfd, newname, 0);
+}
+
 SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname)
 {
-	return sys_renameat(AT_FDCWD, oldname, AT_FDCWD, newname);
+	return sys_renameat2(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
 }
 
-int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen, const char *link)
+int vfs_whiteout(struct inode *dir, struct dentry *dentry)
 {
-	int len;
+	int error = may_create(dir, dentry);
+	if (error)
+		return error;
 
-	len = PTR_ERR(link);
+	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);
 	if (IS_ERR(link))
 		goto out;
 
@@ -4313,7 +4357,7 @@ int generic_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 	if (IS_ERR(cookie))
 		return PTR_ERR(cookie);
 
-	res = vfs_readlink(dentry, buffer, buflen, nd_get_link(&nd));
+	res = readlink_copy(buffer, buflen, nd_get_link(&nd));
 	if (dentry->d_inode->i_op->put_link)
 		dentry->d_inode->i_op->put_link(dentry, &nd, cookie);
 	return res;
@@ -4337,8 +4381,7 @@ static char *page_getlink(struct dentry * dentry, struct page **ppage)
 int page_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 {
 	struct page *page = NULL;
-	char *s = page_getlink(dentry, &page);
-	int res = vfs_readlink(dentry,buffer,buflen,s);
+	int res = readlink_copy(buffer, buflen, page_getlink(dentry, &page));
 	if (page) {
 		kunmap(page);
 		page_cache_release(page);
@@ -4434,7 +4477,6 @@ EXPORT_SYMBOL(vfs_link);
 EXPORT_SYMBOL(vfs_mkdir);
 EXPORT_SYMBOL(vfs_mknod);
 EXPORT_SYMBOL(generic_permission);
-EXPORT_SYMBOL(vfs_readlink);
 EXPORT_SYMBOL(vfs_rename);
 EXPORT_SYMBOL(vfs_rmdir);
 EXPORT_SYMBOL(vfs_symlink);
diff --git a/fs/namespace.c b/fs/namespace.c
index 039f3802d70e..c6533ce9cdee 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1586,6 +1586,33 @@ 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)
 {
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 9c271f42604a..674a5d529e09 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -244,10 +244,11 @@ struct nfs4_dir_ctx {
 };
 
 static int
-nfsd4_build_namelist(void *arg, const char *name, int namlen,
+nfsd4_build_namelist(struct dir_context *__ctx, const char *name, int namlen,
 		loff_t offset, u64 ino, unsigned int d_type)
 {
-	struct nfs4_dir_ctx *ctx = arg;
+	struct nfs4_dir_ctx *ctx =
+		container_of(__ctx, struct nfs4_dir_ctx, ctx);
 	struct name_list *entry;
 
 	if (namlen != HEXDIR_LEN - 1)
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index eea5ad188984..3953a20db16d 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1703,7 +1703,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 	if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry)
 		goto out_dput_new;
 
-	host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL);
+	host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL, 0);
 	if (!host_err) {
 		host_err = commit_metadata(tfhp);
 		if (!host_err)
@@ -1808,10 +1808,12 @@ struct readdir_data {
 	int		full;
 };
 
-static int nfsd_buffered_filldir(void *__buf, const char *name, int namlen,
-				 loff_t offset, u64 ino, unsigned int d_type)
+static int nfsd_buffered_filldir(struct dir_context *ctx, const char *name,
+				 int namlen, loff_t offset, u64 ino,
+				 unsigned int d_type)
 {
-	struct readdir_data *buf = __buf;
+	struct readdir_data *buf =
+		container_of(ctx, struct readdir_data, ctx);
 	struct buffered_dirent *de = (void *)(buf->dirent + buf->used);
 	unsigned int reclen;
 
@@ -1831,7 +1833,7 @@ static int nfsd_buffered_filldir(void *__buf, const char *name, int namlen,
 	return 0;
 }
 
-static __be32 nfsd_buffered_readdir(struct file *file, filldir_t func,
+static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func,
 				    struct readdir_cd *cdp, loff_t *offsetp)
 {
 	struct buffered_dirent *de;
@@ -1915,7 +1917,7 @@ static __be32 nfsd_buffered_readdir(struct file *file, filldir_t func,
  */
 __be32
 nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, 
-	     struct readdir_cd *cdp, filldir_t func)
+	     struct readdir_cd *cdp, nfsd_filldir_t func)
 {
 	__be32		err;
 	struct file	*file;
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index fbe90bdb2214..ea760b17ecbd 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -36,7 +36,7 @@
 /*
  * Callback function for readdir
  */
-typedef int (*nfsd_dirop_t)(struct inode *, struct dentry *, int, int);
+typedef int (*nfsd_filldir_t)(void *, const char *, int, loff_t, u64, unsigned);
 
 /* nfsd/vfs.c */
 int		nfsd_racache_init(int);
@@ -89,7 +89,7 @@ __be32		nfsd_rename(struct svc_rqst *,
 __be32		nfsd_unlink(struct svc_rqst *, struct svc_fh *, int type,
 				char *name, int len);
 __be32		nfsd_readdir(struct svc_rqst *, struct svc_fh *,
-			     loff_t *, struct readdir_cd *, filldir_t);
+			     loff_t *, struct readdir_cd *, nfsd_filldir_t);
 __be32		nfsd_statfs(struct svc_rqst *, struct svc_fh *,
 				struct kstatfs *, int access);
 
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index 91a7e85ac8fd..478e14d7be54 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -2073,10 +2073,12 @@ struct ocfs2_empty_dir_priv {
 	unsigned seen_other;
 	unsigned dx_dir;
 };
-static int ocfs2_empty_dir_filldir(void *priv, const char *name, int name_len,
-				   loff_t pos, u64 ino, unsigned type)
+static int ocfs2_empty_dir_filldir(struct dir_context *ctx, const char *name,
+				   int name_len, loff_t pos, u64 ino,
+				   unsigned type)
 {
-	struct ocfs2_empty_dir_priv *p = priv;
+	struct ocfs2_empty_dir_priv *p =
+		container_of(ctx, struct ocfs2_empty_dir_priv, ctx);
 
 	/*
 	 * Check the positions of "." and ".." records to be sure
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 44fc3e530c3d..a1b7dca075dd 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1981,10 +1981,12 @@ struct ocfs2_orphan_filldir_priv {
 	struct ocfs2_super	*osb;
 };
 
-static int ocfs2_orphan_filldir(void *priv, const char *name, int name_len,
-				loff_t pos, u64 ino, unsigned type)
+static int ocfs2_orphan_filldir(struct dir_context *ctx, const char *name,
+				int name_len, loff_t pos, u64 ino,
+				unsigned type)
 {
-	struct ocfs2_orphan_filldir_priv *p = priv;
+	struct ocfs2_orphan_filldir_priv *p =
+		container_of(ctx, struct ocfs2_orphan_filldir_priv, ctx);
 	struct inode *iter;
 
 	if (name_len == 1 && !strncmp(".", name, 1))
diff --git a/fs/open.c b/fs/open.c
index 2ed7325f713e..c92c6ef8bf6d 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -822,8 +822,7 @@ 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);
@@ -840,6 +839,26 @@ 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;
diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig
new file mode 100644
index 000000000000..34355818a2e0
--- /dev/null
+++ b/fs/overlayfs/Kconfig
@@ -0,0 +1,10 @@
+config OVERLAY_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
diff --git a/fs/overlayfs/Makefile b/fs/overlayfs/Makefile
new file mode 100644
index 000000000000..900daed3e91d
--- /dev/null
+++ b/fs/overlayfs/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for the overlay filesystem.
+#
+
+obj-$(CONFIG_OVERLAY_FS) += overlay.o
+
+overlay-objs := super.o inode.o dir.o readdir.o copy_up.o
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
new file mode 100644
index 000000000000..24f640441bd9
--- /dev/null
+++ b/fs/overlayfs/copy_up.c
@@ -0,0 +1,413 @@
+/*
+ *
+ * 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 (OVL_TYPE_UPPER(type))
+			break;
+
+		next = dget(dentry);
+		/* find the topmost dentry not yet copied up */
+		for (;;) {
+			parent = dget_parent(next);
+
+			type = ovl_path_type(parent);
+			if (OVL_TYPE_UPPER(type))
+				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;
+}
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
new file mode 100644
index 000000000000..0dc4c33a0a1b
--- /dev/null
+++ b/fs/overlayfs/dir.c
@@ -0,0 +1,928 @@
+/*
+ *
+ * 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/namei.h>
+#include <linux/xattr.h>
+#include <linux/security.h>
+#include <linux/cred.h>
+#include "overlayfs.h"
+
+void ovl_cleanup(struct inode *wdir, struct dentry *wdentry)
+{
+	int err;
+
+	dget(wdentry);
+	if (S_ISDIR(wdentry->d_inode->i_mode))
+		err = ovl_do_rmdir(wdir, wdentry);
+	else
+		err = ovl_do_unlink(wdir, wdentry);
+	dput(wdentry);
+
+	if (err) {
+		pr_err("overlayfs: cleanup of '%pd2' failed (%i)\n",
+		       wdentry, err);
+	}
+}
+
+struct dentry *ovl_lookup_temp(struct dentry *workdir, struct dentry *dentry)
+{
+	struct dentry *temp;
+	char name[20];
+
+	snprintf(name, sizeof(name), "#%lx", (unsigned long) dentry);
+
+	temp = lookup_one_len(name, workdir, strlen(name));
+	if (!IS_ERR(temp) && temp->d_inode) {
+		pr_err("overlayfs: workdir/%s already exists\n", name);
+		dput(temp);
+		temp = ERR_PTR(-EIO);
+	}
+
+	return temp;
+}
+
+/* caller holds i_mutex on workdir */
+static struct dentry *ovl_whiteout(struct dentry *workdir,
+				   struct dentry *dentry)
+{
+	int err;
+	struct dentry *whiteout;
+	struct inode *wdir = workdir->d_inode;
+
+	whiteout = ovl_lookup_temp(workdir, dentry);
+	if (IS_ERR(whiteout))
+		return whiteout;
+
+	err = ovl_do_whiteout(wdir, whiteout);
+	if (err) {
+		dput(whiteout);
+		whiteout = ERR_PTR(err);
+	}
+
+	return whiteout;
+}
+
+int ovl_create_real(struct inode *dir, struct dentry *newdentry,
+		    struct kstat *stat, const char *link,
+		    struct dentry *hardlink, bool debug)
+{
+	int err;
+
+	if (newdentry->d_inode)
+		return -ESTALE;
+
+	if (hardlink) {
+		err = ovl_do_link(hardlink, dir, newdentry, debug);
+	} else {
+		switch (stat->mode & S_IFMT) {
+		case S_IFREG:
+			err = ovl_do_create(dir, newdentry, stat->mode, debug);
+			break;
+
+		case S_IFDIR:
+			err = ovl_do_mkdir(dir, newdentry, stat->mode, debug);
+			break;
+
+		case S_IFCHR:
+		case S_IFBLK:
+		case S_IFIFO:
+		case S_IFSOCK:
+			err = ovl_do_mknod(dir, newdentry,
+					   stat->mode, stat->rdev, debug);
+			break;
+
+		case S_IFLNK:
+			err = ovl_do_symlink(dir, newdentry, link, debug);
+			break;
+
+		default:
+			err = -EPERM;
+		}
+	}
+	if (!err && WARN_ON(!newdentry->d_inode)) {
+		/*
+		 * Not quite sure if non-instantiated dentry is legal or not.
+		 * VFS doesn't seem to care so check and warn here.
+		 */
+		err = -ENOENT;
+	}
+	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)
+{
+	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);
+	}
+}
+
+static int ovl_dir_getattr(struct vfsmount *mnt, struct dentry *dentry,
+			 struct kstat *stat)
+{
+	int err;
+	enum ovl_path_type type;
+	struct path realpath;
+
+	type = ovl_path_real(dentry, &realpath);
+	err = vfs_getattr(&realpath, stat);
+	if (err)
+		return err;
+
+	stat->dev = dentry->d_sb->s_dev;
+	stat->ino = dentry->d_inode->i_ino;
+
+	/*
+	 * It's probably not worth it to count subdirs to get the
+	 * correct link count.  nlink=1 seems to pacify 'find' and
+	 * other utilities.
+	 */
+	if (OVL_TYPE_MERGE(type))
+		stat->nlink = 1;
+
+	return 0;
+}
+
+static int ovl_create_upper(struct dentry *dentry, struct inode *inode,
+			    struct kstat *stat, const char *link,
+			    struct dentry *hardlink)
+{
+	struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
+	struct inode *udir = upperdir->d_inode;
+	struct dentry *newdentry;
+	int err;
+
+	mutex_lock_nested(&udir->i_mutex, I_MUTEX_PARENT);
+	newdentry = lookup_one_len(dentry->d_name.name, upperdir,
+				   dentry->d_name.len);
+	err = PTR_ERR(newdentry);
+	if (IS_ERR(newdentry))
+		goto out_unlock;
+	err = ovl_create_real(udir, newdentry, stat, link, hardlink, false);
+	if (err)
+		goto out_dput;
+
+	ovl_dentry_version_inc(dentry->d_parent);
+	ovl_dentry_update(dentry, newdentry);
+	ovl_copyattr(newdentry->d_inode, inode);
+	d_instantiate(dentry, inode);
+	newdentry = NULL;
+out_dput:
+	dput(newdentry);
+out_unlock:
+	mutex_unlock(&udir->i_mutex);
+	return err;
+}
+
+static int ovl_lock_rename_workdir(struct dentry *workdir,
+				   struct dentry *upperdir)
+{
+	/* Workdir should not be the same as upperdir */
+	if (workdir == upperdir)
+		goto err;
+
+	/* Workdir should not be subdir of upperdir and vice versa */
+	if (lock_rename(workdir, upperdir) != NULL)
+		goto err_unlock;
+
+	return 0;
+
+err_unlock:
+	unlock_rename(workdir, upperdir);
+err:
+	pr_err("overlayfs: failed to lock workdir+upperdir\n");
+	return -EIO;
+}
+
+static struct dentry *ovl_clear_empty(struct dentry *dentry,
+				      struct list_head *list)
+{
+	struct dentry *workdir = ovl_workdir(dentry);
+	struct inode *wdir = workdir->d_inode;
+	struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
+	struct inode *udir = upperdir->d_inode;
+	struct path upperpath;
+	struct dentry *upper;
+	struct dentry *opaquedir;
+	struct kstat stat;
+	int err;
+
+	err = ovl_lock_rename_workdir(workdir, upperdir);
+	if (err)
+		goto out;
+
+	ovl_path_upper(dentry, &upperpath);
+	err = vfs_getattr(&upperpath, &stat);
+	if (err)
+		goto out_unlock;
+
+	err = -ESTALE;
+	if (!S_ISDIR(stat.mode))
+		goto out_unlock;
+	upper = upperpath.dentry;
+	if (upper->d_parent->d_inode != udir)
+		goto out_unlock;
+
+	opaquedir = ovl_lookup_temp(workdir, dentry);
+	err = PTR_ERR(opaquedir);
+	if (IS_ERR(opaquedir))
+		goto out_unlock;
+
+	err = ovl_create_real(wdir, opaquedir, &stat, NULL, NULL, true);
+	if (err)
+		goto out_dput;
+
+	err = ovl_copy_xattr(upper, opaquedir);
+	if (err)
+		goto out_cleanup;
+
+	err = ovl_set_opaque(opaquedir);
+	if (err)
+		goto out_cleanup;
+
+	mutex_lock(&opaquedir->d_inode->i_mutex);
+	err = ovl_set_attr(opaquedir, &stat);
+	mutex_unlock(&opaquedir->d_inode->i_mutex);
+	if (err)
+		goto out_cleanup;
+
+	err = ovl_do_rename(wdir, opaquedir, udir, upper, RENAME_EXCHANGE);
+	if (err)
+		goto out_cleanup;
+
+	ovl_cleanup_whiteouts(upper, list);
+	ovl_cleanup(wdir, upper);
+	unlock_rename(workdir, upperdir);
+
+	/* dentry's upper doesn't match now, get rid of it */
+	d_drop(dentry);
+
+	return opaquedir;
+
+out_cleanup:
+	ovl_cleanup(wdir, opaquedir);
+out_dput:
+	dput(opaquedir);
+out_unlock:
+	unlock_rename(workdir, upperdir);
+out:
+	return ERR_PTR(err);
+}
+
+static struct dentry *ovl_check_empty_and_clear(struct dentry *dentry)
+{
+	int err;
+	struct dentry *ret = NULL;
+	LIST_HEAD(list);
+
+	err = ovl_check_empty_dir(dentry, &list);
+	if (err)
+		ret = ERR_PTR(err);
+	else {
+		/*
+		 * If no upperdentry then skip clearing whiteouts.
+		 *
+		 * Can race with copy-up, since we don't hold the upperdir
+		 * mutex.  Doesn't matter, since copy-up can't create a
+		 * non-empty directory from an empty one.
+		 */
+		if (ovl_dentry_upper(dentry))
+			ret = ovl_clear_empty(dentry, &list);
+	}
+
+	ovl_cache_free(&list);
+
+	return ret;
+}
+
+static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
+				    struct kstat *stat, const char *link,
+				    struct dentry *hardlink)
+{
+	struct dentry *workdir = ovl_workdir(dentry);
+	struct inode *wdir = workdir->d_inode;
+	struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
+	struct inode *udir = upperdir->d_inode;
+	struct dentry *upper;
+	struct dentry *newdentry;
+	int err;
+
+	err = ovl_lock_rename_workdir(workdir, upperdir);
+	if (err)
+		goto out;
+
+	newdentry = ovl_lookup_temp(workdir, dentry);
+	err = PTR_ERR(newdentry);
+	if (IS_ERR(newdentry))
+		goto out_unlock;
+
+	upper = lookup_one_len(dentry->d_name.name, upperdir,
+			       dentry->d_name.len);
+	err = PTR_ERR(upper);
+	if (IS_ERR(upper))
+		goto out_dput;
+
+	err = ovl_create_real(wdir, newdentry, stat, link, hardlink, true);
+	if (err)
+		goto out_dput2;
+
+	if (S_ISDIR(stat->mode)) {
+		err = ovl_set_opaque(newdentry);
+		if (err)
+			goto out_cleanup;
+
+		err = ovl_do_rename(wdir, newdentry, udir, upper,
+				    RENAME_EXCHANGE);
+		if (err)
+			goto out_cleanup;
+
+		ovl_cleanup(wdir, upper);
+	} else {
+		err = ovl_do_rename(wdir, newdentry, udir, upper, 0);
+		if (err)
+			goto out_cleanup;
+	}
+	ovl_dentry_version_inc(dentry->d_parent);
+	ovl_dentry_update(dentry, newdentry);
+	ovl_copyattr(newdentry->d_inode, inode);
+	d_instantiate(dentry, inode);
+	newdentry = NULL;
+out_dput2:
+	dput(upper);
+out_dput:
+	dput(newdentry);
+out_unlock:
+	unlock_rename(workdir, upperdir);
+out:
+	return err;
+
+out_cleanup:
+	ovl_cleanup(wdir, newdentry);
+	goto out_dput2;
+}
+
+static int ovl_create_or_link(struct dentry *dentry, int mode, dev_t rdev,
+			      const char *link, struct dentry *hardlink)
+{
+	int err;
+	struct inode *inode;
+	struct kstat stat = {
+		.mode = mode,
+		.rdev = rdev,
+	};
+
+	err = -ENOMEM;
+	inode = ovl_new_inode(dentry->d_sb, mode, dentry->d_fsdata);
+	if (!inode)
+		goto out;
+
+	err = ovl_copy_up(dentry->d_parent);
+	if (err)
+		goto out_iput;
+
+	if (!ovl_dentry_is_opaque(dentry)) {
+		err = ovl_create_upper(dentry, inode, &stat, link, hardlink);
+	} else {
+		const struct cred *old_cred;
+		struct cred *override_cred;
+
+		err = -ENOMEM;
+		override_cred = prepare_creds();
+		if (!override_cred)
+			goto out_iput;
+
+		/*
+		 * CAP_SYS_ADMIN for setting opaque xattr
+		 * CAP_DAC_OVERRIDE for create in workdir, rename
+		 * CAP_FOWNER for removing whiteout from sticky dir
+		 */
+		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);
+		old_cred = override_creds(override_cred);
+
+		err = ovl_create_over_whiteout(dentry, inode, &stat, link,
+					       hardlink);
+
+		revert_creds(old_cred);
+		put_cred(override_cred);
+	}
+
+	if (!err)
+		inode = NULL;
+out_iput:
+	iput(inode);
+out:
+	return err;
+}
+
+static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev,
+			     const char *link)
+{
+	int err;
+
+	err = ovl_want_write(dentry);
+	if (!err) {
+		err = ovl_create_or_link(dentry, mode, rdev, link, NULL);
+		ovl_drop_write(dentry);
+	}
+
+	return err;
+}
+
+static int ovl_create(struct inode *dir, struct dentry *dentry, umode_t mode,
+		      bool excl)
+{
+	return ovl_create_object(dentry, (mode & 07777) | S_IFREG, 0, NULL);
+}
+
+static int ovl_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+	return ovl_create_object(dentry, (mode & 07777) | S_IFDIR, 0, NULL);
+}
+
+static int ovl_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
+		     dev_t rdev)
+{
+	/* Don't allow creation of "whiteout" on overlay */
+	if (S_ISCHR(mode) && rdev == WHITEOUT_DEV)
+		return -EPERM;
+
+	return ovl_create_object(dentry, mode, rdev, NULL);
+}
+
+static int ovl_symlink(struct inode *dir, struct dentry *dentry,
+		       const char *link)
+{
+	return ovl_create_object(dentry, S_IFLNK, 0, link);
+}
+
+static int ovl_link(struct dentry *old, struct inode *newdir,
+		    struct dentry *new)
+{
+	int err;
+	struct dentry *upper;
+
+	err = ovl_want_write(old);
+	if (err)
+		goto out;
+
+	err = ovl_copy_up(old);
+	if (err)
+		goto out_drop_write;
+
+	upper = ovl_dentry_upper(old);
+	err = ovl_create_or_link(new, upper->d_inode->i_mode, 0, NULL, upper);
+
+out_drop_write:
+	ovl_drop_write(old);
+out:
+	return err;
+}
+
+static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir)
+{
+	struct dentry *workdir = ovl_workdir(dentry);
+	struct inode *wdir = workdir->d_inode;
+	struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
+	struct inode *udir = upperdir->d_inode;
+	struct dentry *whiteout;
+	struct dentry *upper;
+	struct dentry *opaquedir = NULL;
+	int err;
+
+	if (is_dir && OVL_TYPE_MERGE_OR_LOWER(ovl_path_type(dentry))) {
+		opaquedir = ovl_check_empty_and_clear(dentry);
+		err = PTR_ERR(opaquedir);
+		if (IS_ERR(opaquedir))
+			goto out;
+	}
+
+	err = ovl_lock_rename_workdir(workdir, upperdir);
+	if (err)
+		goto out_dput;
+
+	whiteout = ovl_whiteout(workdir, dentry);
+	err = PTR_ERR(whiteout);
+	if (IS_ERR(whiteout))
+		goto out_unlock;
+
+	upper = ovl_dentry_upper(dentry);
+	if (!upper) {
+		upper = lookup_one_len(dentry->d_name.name, upperdir,
+				       dentry->d_name.len);
+		err = PTR_ERR(upper);
+		if (IS_ERR(upper))
+			goto kill_whiteout;
+
+		err = ovl_do_rename(wdir, whiteout, udir, upper, 0);
+		dput(upper);
+		if (err)
+			goto kill_whiteout;
+	} else {
+		int flags = 0;
+
+		if (opaquedir)
+			upper = opaquedir;
+		err = -ESTALE;
+		if (upper->d_parent != upperdir)
+			goto kill_whiteout;
+
+		if (is_dir)
+			flags |= RENAME_EXCHANGE;
+
+		err = ovl_do_rename(wdir, whiteout, udir, upper, flags);
+		if (err)
+			goto kill_whiteout;
+
+		if (is_dir)
+			ovl_cleanup(wdir, upper);
+	}
+	ovl_dentry_version_inc(dentry->d_parent);
+out_d_drop:
+	d_drop(dentry);
+	dput(whiteout);
+out_unlock:
+	unlock_rename(workdir, upperdir);
+out_dput:
+	dput(opaquedir);
+out:
+	return err;
+
+kill_whiteout:
+	ovl_cleanup(wdir, whiteout);
+	goto out_d_drop;
+}
+
+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 = ovl_dentry_upper(dentry);
+	int err;
+
+	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
+	err = -ESTALE;
+	if (upper->d_parent == upperdir) {
+		/* Don't let d_delete() think it can reset d_inode */
+		dget(upper);
+		if (is_dir)
+			err = vfs_rmdir(dir, upper);
+		else
+			err = vfs_unlink(dir, upper, NULL);
+		dput(upper);
+		ovl_dentry_version_inc(dentry->d_parent);
+	}
+
+	/*
+	 * Keeping this dentry hashed would mean having to release
+	 * upperpath/lowerpath, which could only be done if we are the
+	 * sole user of this dentry.  Too tricky...  Just unhash for
+	 * now.
+	 */
+	d_drop(dentry);
+	mutex_unlock(&dir->i_mutex);
+
+	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;
+
+	err = ovl_check_sticky(dentry);
+	if (err)
+		goto out;
+
+	err = ovl_want_write(dentry);
+	if (err)
+		goto out;
+
+	err = ovl_copy_up(dentry->d_parent);
+	if (err)
+		goto out_drop_write;
+
+	type = ovl_path_type(dentry);
+	if (OVL_TYPE_PURE_UPPER(type)) {
+		err = ovl_remove_upper(dentry, is_dir);
+	} else {
+		const struct cred *old_cred;
+		struct cred *override_cred;
+
+		err = -ENOMEM;
+		override_cred = prepare_creds();
+		if (!override_cred)
+			goto out_drop_write;
+
+		/*
+		 * CAP_SYS_ADMIN for setting xattr on whiteout, opaque dir
+		 * CAP_DAC_OVERRIDE for create in workdir, rename
+		 * CAP_FOWNER for removing whiteout from sticky dir
+		 * CAP_FSETID for chmod of opaque dir
+		 * CAP_CHOWN for chown of opaque dir
+		 */
+		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);
+		old_cred = override_creds(override_cred);
+
+		err = ovl_remove_and_whiteout(dentry, is_dir);
+
+		revert_creds(old_cred);
+		put_cred(override_cred);
+	}
+out_drop_write:
+	ovl_drop_write(dentry);
+out:
+	return err;
+}
+
+static int ovl_unlink(struct inode *dir, struct dentry *dentry)
+{
+	return ovl_do_remove(dentry, false);
+}
+
+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)
+{
+	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;
+	struct dentry *newdentry;
+	struct dentry *trap;
+	bool old_opaque;
+	bool new_opaque;
+	bool new_create = false;
+	bool cleanup_whiteout = false;
+	bool overwrite = !(flags & RENAME_EXCHANGE);
+	bool is_dir = S_ISDIR(old->d_inode->i_mode);
+	bool new_is_dir = false;
+	struct dentry *opaquedir = NULL;
+	const struct cred *old_cred = NULL;
+	struct cred *override_cred = NULL;
+
+	err = -EINVAL;
+	if (flags & ~(RENAME_EXCHANGE | RENAME_NOREPLACE))
+		goto out;
+
+	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)
+		goto out;
+
+	if (new->d_inode) {
+		err = ovl_check_sticky(new);
+		if (err)
+			goto out;
+
+		if (S_ISDIR(new->d_inode->i_mode))
+			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)
+		goto out;
+
+	err = ovl_copy_up(old);
+	if (err)
+		goto out_drop_write;
+
+	err = ovl_copy_up(new->d_parent);
+	if (err)
+		goto out_drop_write;
+	if (!overwrite) {
+		err = ovl_copy_up(new);
+		if (err)
+			goto out_drop_write;
+	}
+
+	old_opaque = !OVL_TYPE_PURE_UPPER(old_type);
+	new_opaque = !OVL_TYPE_PURE_UPPER(new_type);
+
+	if (old_opaque || new_opaque) {
+		err = -ENOMEM;
+		override_cred = prepare_creds();
+		if (!override_cred)
+			goto out_drop_write;
+
+		/*
+		 * CAP_SYS_ADMIN for setting xattr on whiteout, opaque dir
+		 * CAP_DAC_OVERRIDE for create in workdir
+		 * CAP_FOWNER for removing whiteout from sticky dir
+		 * CAP_FSETID for chmod of opaque dir
+		 * CAP_CHOWN for chown of opaque dir
+		 */
+		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);
+		old_cred = override_creds(override_cred);
+	}
+
+	if (overwrite && OVL_TYPE_MERGE_OR_LOWER(new_type) && new_is_dir) {
+		opaquedir = ovl_check_empty_and_clear(new);
+		err = PTR_ERR(opaquedir);
+		if (IS_ERR(opaquedir)) {
+			opaquedir = NULL;
+			goto out_revert_creds;
+		}
+	}
+
+	if (overwrite) {
+		if (old_opaque) {
+			if (new->d_inode || !new_opaque) {
+				/* Whiteout source */
+				flags |= RENAME_WHITEOUT;
+			} else {
+				/* Switch whiteouts */
+				flags |= RENAME_EXCHANGE;
+			}
+		} else if (is_dir && !new->d_inode && new_opaque) {
+			flags |= RENAME_EXCHANGE;
+			cleanup_whiteout = true;
+		}
+	}
+
+	old_upperdir = ovl_dentry_upper(old->d_parent);
+	new_upperdir = ovl_dentry_upper(new->d_parent);
+
+	trap = lock_rename(new_upperdir, old_upperdir);
+
+	olddentry = ovl_dentry_upper(old);
+	newdentry = ovl_dentry_upper(new);
+	if (newdentry) {
+		if (opaquedir) {
+			newdentry = opaquedir;
+			opaquedir = NULL;
+		} else {
+			dget(newdentry);
+		}
+	} else {
+		new_create = true;
+		newdentry = lookup_one_len(new->d_name.name, new_upperdir,
+					   new->d_name.len);
+		err = PTR_ERR(newdentry);
+		if (IS_ERR(newdentry))
+			goto out_unlock;
+	}
+
+	err = -ESTALE;
+	if (olddentry->d_parent != old_upperdir)
+		goto out_dput;
+	if (newdentry->d_parent != new_upperdir)
+		goto out_dput;
+	if (olddentry == trap)
+		goto out_dput;
+	if (newdentry == trap)
+		goto out_dput;
+
+	if (is_dir && !old_opaque && new_opaque) {
+		err = ovl_set_opaque(olddentry);
+		if (err)
+			goto out_dput;
+	}
+	if (!overwrite && new_is_dir && old_opaque && !new_opaque) {
+		err = ovl_set_opaque(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);
+		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);
+
+	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);
+
+	ovl_dentry_version_inc(old->d_parent);
+	ovl_dentry_version_inc(new->d_parent);
+
+out_dput:
+	dput(newdentry);
+out_unlock:
+	unlock_rename(new_upperdir, old_upperdir);
+out_revert_creds:
+	if (old_opaque || new_opaque) {
+		revert_creds(old_cred);
+		put_cred(override_cred);
+	}
+out_drop_write:
+	ovl_drop_write(old);
+out:
+	dput(opaquedir);
+	return err;
+}
+
+const struct inode_operations ovl_dir_inode_operations = {
+	.lookup		= ovl_lookup,
+	.mkdir		= ovl_mkdir,
+	.symlink	= ovl_symlink,
+	.unlink		= ovl_unlink,
+	.rmdir		= ovl_rmdir,
+	.rename2	= ovl_rename2,
+	.link		= ovl_link,
+	.setattr	= ovl_setattr,
+	.create		= ovl_create,
+	.mknod		= ovl_mknod,
+	.permission	= ovl_permission,
+	.getattr	= ovl_dir_getattr,
+	.setxattr	= ovl_setxattr,
+	.getxattr	= ovl_getxattr,
+	.listxattr	= ovl_listxattr,
+	.removexattr	= ovl_removexattr,
+};
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
new file mode 100644
index 000000000000..04f124884687
--- /dev/null
+++ b/fs/overlayfs/inode.c
@@ -0,0 +1,436 @@
+/*
+ *
+ * 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, OVL_XATTR_PRE_NAME, OVL_XATTR_PRE_LEN) == 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;
+}
+
+static bool ovl_need_xattr_filter(struct dentry *dentry,
+				  enum ovl_path_type type)
+{
+	if ((type & (__OVL_PATH_PURE | __OVL_PATH_UPPER)) == __OVL_PATH_UPPER)
+		return S_ISDIR(dentry->d_inode->i_mode);
+	else
+		return false;
+}
+
+ssize_t ovl_getxattr(struct dentry *dentry, const char *name,
+		     void *value, size_t size)
+{
+	struct path realpath;
+	enum ovl_path_type type = ovl_path_real(dentry, &realpath);
+
+	if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name))
+		return -ENODATA;
+
+	return vfs_getxattr(realpath.dentry, name, value, size);
+}
+
+ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
+{
+	struct path realpath;
+	enum ovl_path_type type = ovl_path_real(dentry, &realpath);
+	ssize_t res;
+	int off;
+
+	res = vfs_listxattr(realpath.dentry, list, size);
+	if (res <= 0 || size == 0)
+		return res;
+
+	if (!ovl_need_xattr_filter(dentry, type))
+		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 = ovl_path_real(dentry, &realpath);
+
+	err = ovl_want_write(dentry);
+	if (err)
+		goto out;
+
+	err = -ENODATA;
+	if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name))
+		goto out_drop_write;
+
+	if (!OVL_TYPE_UPPER(type)) {
+		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 (OVL_TYPE_UPPER(type))
+		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;
+}
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
new file mode 100644
index 000000000000..17ac5afc9ffb
--- /dev/null
+++ b/fs/overlayfs/overlayfs.h
@@ -0,0 +1,199 @@
+/*
+ *
+ * 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		= (1 << 0),
+	__OVL_PATH_UPPER	= (1 << 1),
+	__OVL_PATH_MERGE	= (1 << 2),
+};
+
+#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_PRE_NAME "trusted.overlay."
+#define OVL_XATTR_PRE_LEN  16
+#define OVL_XATTR_OPAQUE   OVL_XATTR_PRE_NAME"opaque"
+
+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);
+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 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);
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
new file mode 100644
index 000000000000..907870e81a72
--- /dev/null
+++ b/fs/overlayfs/readdir.c
@@ -0,0 +1,557 @@
+/*
+ *
+ * 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/namei.h>
+#include <linux/file.h>
+#include <linux/xattr.h>
+#include <linux/rbtree.h>
+#include <linux/security.h>
+#include <linux/cred.h>
+#include "overlayfs.h"
+
+struct ovl_cache_entry {
+	unsigned int len;
+	unsigned int type;
+	u64 ino;
+	struct list_head l_node;
+	struct rb_node node;
+	bool is_whiteout;
+	char name[];
+};
+
+struct ovl_dir_cache {
+	long refcount;
+	u64 version;
+	struct list_head entries;
+};
+
+struct ovl_readdir_data {
+	struct dir_context ctx;
+	bool is_merge;
+	struct rb_root root;
+	struct list_head *list;
+	struct list_head middle;
+	struct dentry *dir;
+	int count;
+	int err;
+};
+
+struct ovl_dir_file {
+	bool is_real;
+	bool is_upper;
+	struct ovl_dir_cache *cache;
+	struct list_head *cursor;
+	struct file *realfile;
+	struct file *upperfile;
+};
+
+static struct ovl_cache_entry *ovl_cache_entry_from_node(struct rb_node *n)
+{
+	return container_of(n, struct ovl_cache_entry, node);
+}
+
+static struct ovl_cache_entry *ovl_cache_entry_find(struct rb_root *root,
+						    const char *name, int len)
+{
+	struct rb_node *node = root->rb_node;
+	int cmp;
+
+	while (node) {
+		struct ovl_cache_entry *p = ovl_cache_entry_from_node(node);
+
+		cmp = strncmp(name, p->name, len);
+		if (cmp > 0)
+			node = p->node.rb_right;
+		else if (cmp < 0 || len < p->len)
+			node = p->node.rb_left;
+		else
+			return p;
+	}
+
+	return NULL;
+}
+
+static struct ovl_cache_entry *ovl_cache_entry_new(struct dentry *dir,
+						   const char *name, int len,
+						   u64 ino, unsigned int d_type)
+{
+	struct ovl_cache_entry *p;
+	size_t size = offsetof(struct ovl_cache_entry, name[len + 1]);
+
+	p = kmalloc(size, GFP_KERNEL);
+	if (!p)
+		return NULL;
+
+	memcpy(p->name, name, len);
+	p->name[len] = '\0';
+	p->len = len;
+	p->type = d_type;
+	p->ino = ino;
+	p->is_whiteout = false;
+
+	if (d_type == DT_CHR) {
+		struct dentry *dentry;
+		const struct cred *old_cred;
+		struct cred *override_cred;
+
+		override_cred = prepare_creds();
+		if (!override_cred) {
+			kfree(p);
+			return NULL;
+		}
+
+		/*
+		 * CAP_DAC_OVERRIDE for lookup
+		 */
+		cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE);
+		old_cred = override_creds(override_cred);
+
+		dentry = lookup_one_len(name, dir, len);
+		if (!IS_ERR(dentry)) {
+			p->is_whiteout = ovl_is_whiteout(dentry);
+			dput(dentry);
+		}
+		revert_creds(old_cred);
+		put_cred(override_cred);
+	}
+	return p;
+}
+
+static int ovl_cache_entry_add_rb(struct ovl_readdir_data *rdd,
+				  const char *name, int len, u64 ino,
+				  unsigned int d_type)
+{
+	struct rb_node **newp = &rdd->root.rb_node;
+	struct rb_node *parent = NULL;
+	struct ovl_cache_entry *p;
+
+	while (*newp) {
+		int cmp;
+		struct ovl_cache_entry *tmp;
+
+		parent = *newp;
+		tmp = ovl_cache_entry_from_node(*newp);
+		cmp = strncmp(name, tmp->name, len);
+		if (cmp > 0)
+			newp = &tmp->node.rb_right;
+		else if (cmp < 0 || len < tmp->len)
+			newp = &tmp->node.rb_left;
+		else
+			return 0;
+	}
+
+	p = ovl_cache_entry_new(rdd->dir, name, len, ino, d_type);
+	if (p == NULL)
+		return -ENOMEM;
+
+	list_add_tail(&p->l_node, rdd->list);
+	rb_link_node(&p->node, parent, newp);
+	rb_insert_color(&p->node, &rdd->root);
+
+	return 0;
+}
+
+static int ovl_fill_lower(struct ovl_readdir_data *rdd,
+			  const char *name, int namelen,
+			  loff_t offset, u64 ino, unsigned int d_type)
+{
+	struct ovl_cache_entry *p;
+
+	p = ovl_cache_entry_find(&rdd->root, name, namelen);
+	if (p) {
+		list_move_tail(&p->l_node, &rdd->middle);
+	} else {
+		p = ovl_cache_entry_new(rdd->dir, name, namelen, ino, d_type);
+		if (p == NULL)
+			rdd->err = -ENOMEM;
+		else
+			list_add_tail(&p->l_node, &rdd->middle);
+	}
+
+	return rdd->err;
+}
+
+void ovl_cache_free(struct list_head *list)
+{
+	struct ovl_cache_entry *p;
+	struct ovl_cache_entry *n;
+
+	list_for_each_entry_safe(p, n, list, l_node)
+		kfree(p);
+
+	INIT_LIST_HEAD(list);
+}
+
+static void ovl_cache_put(struct ovl_dir_file *od, struct dentry *dentry)
+{
+	struct ovl_dir_cache *cache = od->cache;
+
+	WARN_ON(cache->refcount <= 0);
+	cache->refcount--;
+	if (!cache->refcount) {
+		if (ovl_dir_cache(dentry) == cache)
+			ovl_set_dir_cache(dentry, NULL);
+
+		ovl_cache_free(&cache->entries);
+		kfree(cache);
+	}
+}
+
+static int ovl_fill_merge(struct dir_context *ctx, const char *name,
+			  int namelen, loff_t offset, u64 ino,
+			  unsigned int d_type)
+{
+	struct ovl_readdir_data *rdd =
+		container_of(ctx, struct ovl_readdir_data, ctx);
+
+	rdd->count++;
+	if (!rdd->is_merge)
+		return ovl_cache_entry_add_rb(rdd, name, namelen, ino, d_type);
+	else
+		return ovl_fill_lower(rdd, name, namelen, offset, ino, d_type);
+}
+
+static inline int ovl_dir_read(struct path *realpath,
+			       struct ovl_readdir_data *rdd)
+{
+	struct file *realfile;
+	int err;
+
+	realfile = ovl_path_open(realpath, O_RDONLY | O_DIRECTORY);
+	if (IS_ERR(realfile))
+		return PTR_ERR(realfile);
+
+	rdd->dir = realpath->dentry;
+	rdd->ctx.pos = 0;
+	do {
+		rdd->count = 0;
+		rdd->err = 0;
+		err = iterate_dir(realfile, &rdd->ctx);
+		if (err >= 0)
+			err = rdd->err;
+	} while (!err && rdd->count);
+	fput(realfile);
+
+	return err;
+}
+
+static void ovl_dir_reset(struct file *file)
+{
+	struct ovl_dir_file *od = file->private_data;
+	struct ovl_dir_cache *cache = od->cache;
+	struct dentry *dentry = file->f_path.dentry;
+	enum ovl_path_type type = ovl_path_type(dentry);
+
+	if (cache && ovl_dentry_version_get(dentry) != cache->version) {
+		ovl_cache_put(od, dentry);
+		od->cache = NULL;
+		od->cursor = NULL;
+	}
+	WARN_ON(!od->is_real && !OVL_TYPE_MERGE(type));
+	if (od->is_real && OVL_TYPE_MERGE(type))
+		od->is_real = false;
+}
+
+static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list)
+{
+	int err;
+	struct path realpath;
+	struct ovl_readdir_data rdd = {
+		.ctx.actor = ovl_fill_merge,
+		.list = list,
+		.root = RB_ROOT,
+		.is_merge = false,
+	};
+	int idx, next;
+
+	for (idx = 0; idx != -1; idx = next) {
+		next = ovl_path_next(idx, dentry, &realpath);
+
+		if (next != -1) {
+			err = ovl_dir_read(&realpath, &rdd);
+			if (err)
+				break;
+		} else {
+			/*
+			 * Insert lowest layer entries before upper ones, this
+			 * allows offsets to be reasonably constant
+			 */
+			list_add(&rdd.middle, rdd.list);
+			rdd.is_merge = true;
+			err = ovl_dir_read(&realpath, &rdd);
+			list_del(&rdd.middle);
+		}
+	}
+	return err;
+}
+
+static void ovl_seek_cursor(struct ovl_dir_file *od, loff_t pos)
+{
+	struct list_head *p;
+	loff_t off = 0;
+
+	list_for_each(p, &od->cache->entries) {
+		if (off >= pos)
+			break;
+		off++;
+	}
+	/* Cursor is safe since the cache is stable */
+	od->cursor = p;
+}
+
+static struct ovl_dir_cache *ovl_cache_get(struct dentry *dentry)
+{
+	int res;
+	struct ovl_dir_cache *cache;
+
+	cache = ovl_dir_cache(dentry);
+	if (cache && ovl_dentry_version_get(dentry) == cache->version) {
+		cache->refcount++;
+		return cache;
+	}
+	ovl_set_dir_cache(dentry, NULL);
+
+	cache = kzalloc(sizeof(struct ovl_dir_cache), GFP_KERNEL);
+	if (!cache)
+		return ERR_PTR(-ENOMEM);
+
+	cache->refcount = 1;
+	INIT_LIST_HEAD(&cache->entries);
+
+	res = ovl_dir_read_merged(dentry, &cache->entries);
+	if (res) {
+		ovl_cache_free(&cache->entries);
+		kfree(cache);
+		return ERR_PTR(res);
+	}
+
+	cache->version = ovl_dentry_version_get(dentry);
+	ovl_set_dir_cache(dentry, cache);
+
+	return cache;
+}
+
+static int ovl_iterate(struct file *file, struct dir_context *ctx)
+{
+	struct ovl_dir_file *od = file->private_data;
+	struct dentry *dentry = file->f_path.dentry;
+	struct ovl_cache_entry *p;
+
+	if (!ctx->pos)
+		ovl_dir_reset(file);
+
+	if (od->is_real)
+		return iterate_dir(od->realfile, ctx);
+
+	if (!od->cache) {
+		struct ovl_dir_cache *cache;
+
+		cache = ovl_cache_get(dentry);
+		if (IS_ERR(cache))
+			return PTR_ERR(cache);
+
+		od->cache = cache;
+		ovl_seek_cursor(od, ctx->pos);
+	}
+
+	while (od->cursor != &od->cache->entries) {
+		p = list_entry(od->cursor, struct ovl_cache_entry, l_node);
+		if (!p->is_whiteout)
+			if (!dir_emit(ctx, p->name, p->len, p->ino, p->type))
+				break;
+		od->cursor = p->l_node.next;
+		ctx->pos++;
+	}
+	return 0;
+}
+
+static loff_t ovl_dir_llseek(struct file *file, loff_t offset, int origin)
+{
+	loff_t res;
+	struct ovl_dir_file *od = file->private_data;
+
+	mutex_lock(&file_inode(file)->i_mutex);
+	if (!file->f_pos)
+		ovl_dir_reset(file);
+
+	if (od->is_real) {
+		res = vfs_llseek(od->realfile, offset, origin);
+		file->f_pos = od->realfile->f_pos;
+	} else {
+		res = -EINVAL;
+
+		switch (origin) {
+		case SEEK_CUR:
+			offset += file->f_pos;
+			break;
+		case SEEK_SET:
+			break;
+		default:
+			goto out_unlock;
+		}
+		if (offset < 0)
+			goto out_unlock;
+
+		if (offset != file->f_pos) {
+			file->f_pos = offset;
+			if (od->cache)
+				ovl_seek_cursor(od, offset);
+		}
+		res = offset;
+	}
+out_unlock:
+	mutex_unlock(&file_inode(file)->i_mutex);
+
+	return res;
+}
+
+static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end,
+			 int datasync)
+{
+	struct ovl_dir_file *od = file->private_data;
+	struct dentry *dentry = file->f_path.dentry;
+	struct file *realfile = od->realfile;
+
+	/*
+	 * Need to check if we started out being a lower dir, but got copied up
+	 */
+	if (!od->is_upper && OVL_TYPE_UPPER(ovl_path_type(dentry))) {
+		struct inode *inode = file_inode(file);
+
+		realfile = lockless_dereference(od->upperfile);
+		if (!realfile) {
+			struct path upperpath;
+
+			ovl_path_upper(dentry, &upperpath);
+			realfile = ovl_path_open(&upperpath, O_RDONLY);
+			smp_mb__before_spinlock();
+			mutex_lock(&inode->i_mutex);
+			if (!od->upperfile) {
+				if (IS_ERR(realfile)) {
+					mutex_unlock(&inode->i_mutex);
+					return PTR_ERR(realfile);
+				}
+				od->upperfile = realfile;
+			} else {
+				/* somebody has beaten us to it */
+				if (!IS_ERR(realfile))
+					fput(realfile);
+				realfile = od->upperfile;
+			}
+			mutex_unlock(&inode->i_mutex);
+		}
+	}
+
+	return vfs_fsync_range(realfile, start, end, datasync);
+}
+
+static int ovl_dir_release(struct inode *inode, struct file *file)
+{
+	struct ovl_dir_file *od = file->private_data;
+
+	if (od->cache) {
+		mutex_lock(&inode->i_mutex);
+		ovl_cache_put(od, file->f_path.dentry);
+		mutex_unlock(&inode->i_mutex);
+	}
+	fput(od->realfile);
+	if (od->upperfile)
+		fput(od->upperfile);
+	kfree(od);
+
+	return 0;
+}
+
+static int ovl_dir_open(struct inode *inode, struct file *file)
+{
+	struct path realpath;
+	struct file *realfile;
+	struct ovl_dir_file *od;
+	enum ovl_path_type type;
+
+	od = kzalloc(sizeof(struct ovl_dir_file), GFP_KERNEL);
+	if (!od)
+		return -ENOMEM;
+
+	type = ovl_path_real(file->f_path.dentry, &realpath);
+	realfile = ovl_path_open(&realpath, file->f_flags);
+	if (IS_ERR(realfile)) {
+		kfree(od);
+		return PTR_ERR(realfile);
+	}
+	od->realfile = realfile;
+	od->is_real = !OVL_TYPE_MERGE(type);
+	od->is_upper = OVL_TYPE_UPPER(type);
+	file->private_data = od;
+
+	return 0;
+}
+
+const struct file_operations ovl_dir_operations = {
+	.read		= generic_read_dir,
+	.open		= ovl_dir_open,
+	.iterate	= ovl_iterate,
+	.llseek		= ovl_dir_llseek,
+	.fsync		= ovl_dir_fsync,
+	.release	= ovl_dir_release,
+};
+
+int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list)
+{
+	int err;
+	struct ovl_cache_entry *p;
+
+	err = ovl_dir_read_merged(dentry, list);
+	if (err)
+		return err;
+
+	err = 0;
+
+	list_for_each_entry(p, list, l_node) {
+		if (p->is_whiteout)
+			continue;
+
+		if (p->name[0] == '.') {
+			if (p->len == 1)
+				continue;
+			if (p->len == 2 && p->name[1] == '.')
+				continue;
+		}
+		err = -ENOTEMPTY;
+		break;
+	}
+
+	return err;
+}
+
+void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list)
+{
+	struct ovl_cache_entry *p;
+
+	mutex_lock_nested(&upper->d_inode->i_mutex, I_MUTEX_CHILD);
+	list_for_each_entry(p, list, l_node) {
+		struct dentry *dentry;
+
+		if (!p->is_whiteout)
+			continue;
+
+		dentry = lookup_one_len(p->name, upper, p->len);
+		if (IS_ERR(dentry)) {
+			pr_err("overlayfs: lookup '%s/%.*s' failed (%i)\n",
+			       upper->d_name.name, p->len, p->name,
+			       (int) PTR_ERR(dentry));
+			continue;
+		}
+		ovl_cleanup(upper->d_inode, dentry);
+		dput(dentry);
+	}
+	mutex_unlock(&upper->d_inode->i_mutex);
+}
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
new file mode 100644
index 000000000000..5f0d1993e6e3
--- /dev/null
+++ b/fs/overlayfs/super.c
@@ -0,0 +1,1046 @@
+/*
+ *
+ * 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/namei.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 "overlayfs.h"
+
+MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
+MODULE_DESCRIPTION("Overlay filesystem");
+MODULE_LICENSE("GPL");
+
+#define OVERLAYFS_SUPER_MAGIC 0x794c7630
+
+struct ovl_config {
+	char *lowerdir;
+	char *upperdir;
+	char *workdir;
+};
+
+/* 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;
+};
+
+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;
+
+		if (oe->numlower) {
+			if (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;
+}
+
+struct dentry *ovl_entry_real(struct ovl_entry *oe, bool *is_upper)
+{
+	struct dentry *realdentry;
+
+	realdentry = ovl_upperdentry_dereference(oe);
+	if (realdentry) {
+		*is_upper = true;
+	} else {
+		realdentry = __ovl_dentry_lower(oe);
+		*is_upper = false;
+	}
+	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;
+}
+
+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(!mutex_is_locked(&upperdentry->d_parent->d_inode->i_mutex));
+	WARN_ON(oe->__upperdentry);
+	BUG_ON(!upperdentry->d_inode);
+	/*
+	 * Make sure upperdentry is consistent before making it visible to
+	 * ovl_upperdentry_dereference().
+	 */
+	smp_wmb();
+	oe->__upperdentry = upperdentry;
+}
+
+void ovl_dentry_version_inc(struct dentry *dentry)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	WARN_ON(!mutex_is_locked(&dentry->d_inode->i_mutex));
+	oe->version++;
+}
+
+u64 ovl_dentry_version_get(struct dentry *dentry)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	WARN_ON(!mutex_is_locked(&dentry->d_inode->i_mutex));
+	return oe->version;
+}
+
+bool ovl_is_whiteout(struct dentry *dentry)
+{
+	struct inode *inode = dentry->d_inode;
+
+	return inode && IS_WHITEOUT(inode);
+}
+
+static bool ovl_is_opaquedir(struct dentry *dentry)
+{
+	int res;
+	char val;
+	struct inode *inode = dentry->d_inode;
+
+	if (!S_ISDIR(inode->i_mode) || !inode->i_op->getxattr)
+		return false;
+
+	res = inode->i_op->getxattr(dentry, OVL_XATTR_OPAQUE, &val, 1);
+	if (res == 1 && val == 'y')
+		return true;
+
+	return false;
+}
+
+static void ovl_dentry_release(struct dentry *dentry)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	if (oe) {
+		unsigned int i;
+
+		dput(oe->__upperdentry);
+		for (i = 0; i < oe->numlower; i++)
+			dput(oe->lowerstack[i].dentry);
+		kfree_rcu(oe, rcu);
+	}
+}
+
+static const struct dentry_operations ovl_dentry_operations = {
+	.d_release = ovl_dentry_release,
+};
+
+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 inline struct dentry *ovl_lookup_real(struct dentry *dir,
+					     struct qstr *name)
+{
+	struct dentry *dentry;
+
+	mutex_lock(&dir->d_inode->i_mutex);
+	dentry = lookup_one_len(name->name, dir, name->len);
+	mutex_unlock(&dir->d_inode->i_mutex);
+
+	if (IS_ERR(dentry)) {
+		if (PTR_ERR(dentry) == -ENOENT)
+			dentry = NULL;
+	} else if (!dentry->d_inode) {
+		dput(dentry);
+		dentry = NULL;
+	}
+	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;
+	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;
+
+	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 (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;
+
+		realdentry = upperdentry ? upperdentry : stack[0].dentry;
+
+		err = -ENOMEM;
+		inode = ovl_new_inode(dentry->d_sb, realdentry->d_inode->i_mode,
+				      oe);
+		if (!inode)
+			goto out_free_oe;
+		ovl_copyattr(realdentry->d_inode, inode);
+	}
+
+	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:
+	return ERR_PTR(err);
+}
+
+struct file *ovl_path_open(struct path *path, int flags)
+{
+	return dentry_open(path, flags, current_cred());
+}
+
+static void ovl_put_super(struct super_block *sb)
+{
+	struct ovl_fs *ufs = sb->s_fs_info;
+	unsigned i;
+
+	dput(ufs->workdir);
+	mntput(ufs->upper_mnt);
+	for (i = 0; i < ufs->numlower; i++)
+		mntput(ufs->lower_mnt[i]);
+
+	kfree(ufs->config.lowerdir);
+	kfree(ufs->config.upperdir);
+	kfree(ufs->config.workdir);
+	kfree(ufs);
+}
+
+/**
+ * ovl_statfs
+ * @sb: The overlayfs super block
+ * @buf: The struct kstatfs to fill in with stats
+ *
+ * Get the filesystem statistics.  As writes always target the upper layer
+ * filesystem pass the statfs to the upper filesystem (if it exists)
+ */
+static int ovl_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+	struct dentry *root_dentry = dentry->d_sb->s_root;
+	struct path path;
+	int err;
+
+	ovl_path_real(root_dentry, &path);
+
+	err = vfs_statfs(&path, buf);
+	if (!err) {
+		buf->f_namelen = max(buf->f_namelen, ofs->lower_namelen);
+		buf->f_type = OVERLAYFS_SUPER_MAGIC;
+	}
+
+	return err;
+}
+
+/**
+ * ovl_show_options
+ *
+ * Prints the mount options for a given superblock.
+ * Returns zero; does not fail.
+ */
+static int ovl_show_options(struct seq_file *m, struct dentry *dentry)
+{
+	struct super_block *sb = dentry->d_sb;
+	struct ovl_fs *ufs = sb->s_fs_info;
+
+	seq_printf(m, ",lowerdir=%s", ufs->config.lowerdir);
+	if (ufs->config.upperdir) {
+		seq_printf(m, ",upperdir=%s", ufs->config.upperdir);
+		seq_printf(m, ",workdir=%s", ufs->config.workdir);
+	}
+	return 0;
+}
+
+static int ovl_remount(struct super_block *sb, int *flags, char *data)
+{
+	struct ovl_fs *ufs = sb->s_fs_info;
+
+	if (!(*flags & MS_RDONLY) && !ufs->upper_mnt)
+		return -EROFS;
+
+	return 0;
+}
+
+static const struct super_operations ovl_super_operations = {
+	.put_super	= ovl_put_super,
+	.statfs		= ovl_statfs,
+	.show_options	= ovl_show_options,
+	.remount_fs	= ovl_remount,
+};
+
+enum {
+	OPT_LOWERDIR,
+	OPT_UPPERDIR,
+	OPT_WORKDIR,
+	OPT_ERR,
+};
+
+static const match_table_t ovl_tokens = {
+	{OPT_LOWERDIR,			"lowerdir=%s"},
+	{OPT_UPPERDIR,			"upperdir=%s"},
+	{OPT_WORKDIR,			"workdir=%s"},
+	{OPT_ERR,			NULL}
+};
+
+static char *ovl_next_opt(char **s)
+{
+	char *sbegin = *s;
+	char *p;
+
+	if (sbegin == NULL)
+		return NULL;
+
+	for (p = sbegin; *p; p++) {
+		if (*p == '\\') {
+			p++;
+			if (!*p)
+				break;
+		} else if (*p == ',') {
+			*p = '\0';
+			*s = p + 1;
+			return sbegin;
+		}
+	}
+	*s = NULL;
+	return sbegin;
+}
+
+static int ovl_parse_opt(char *opt, struct ovl_config *config)
+{
+	char *p;
+
+	while ((p = ovl_next_opt(&opt)) != NULL) {
+		int token;
+		substring_t args[MAX_OPT_ARGS];
+
+		if (!*p)
+			continue;
+
+		token = match_token(p, ovl_tokens, args);
+		switch (token) {
+		case OPT_UPPERDIR:
+			kfree(config->upperdir);
+			config->upperdir = match_strdup(&args[0]);
+			if (!config->upperdir)
+				return -ENOMEM;
+			break;
+
+		case OPT_LOWERDIR:
+			kfree(config->lowerdir);
+			config->lowerdir = match_strdup(&args[0]);
+			if (!config->lowerdir)
+				return -ENOMEM;
+			break;
+
+		case OPT_WORKDIR:
+			kfree(config->workdir);
+			config->workdir = match_strdup(&args[0]);
+			if (!config->workdir)
+				return -ENOMEM;
+			break;
+
+		default:
+			pr_err("overlayfs: unrecognized mount option \"%s\" or missing value\n", p);
+			return -EINVAL;
+		}
+	}
+
+	/* Workdir is useless in non-upper mount */
+	if (!config->upperdir && config->workdir) {
+		pr_info("overlayfs: option \"workdir=%s\" is useless in a non-upper mount, ignore\n",
+			config->workdir);
+		kfree(config->workdir);
+		config->workdir = NULL;
+	}
+
+	return 0;
+}
+
+#define OVL_WORKDIR_NAME "work"
+
+static struct dentry *ovl_workdir_create(struct vfsmount *mnt,
+					 struct dentry *dentry)
+{
+	struct inode *dir = dentry->d_inode;
+	struct dentry *work;
+	int err;
+	bool retried = false;
+
+	err = mnt_want_write(mnt);
+	if (err)
+		return ERR_PTR(err);
+
+	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
+retry:
+	work = lookup_one_len(OVL_WORKDIR_NAME, dentry,
+			      strlen(OVL_WORKDIR_NAME));
+
+	if (!IS_ERR(work)) {
+		struct kstat stat = {
+			.mode = S_IFDIR | 0,
+		};
+
+		if (work->d_inode) {
+			err = -EEXIST;
+			if (retried)
+				goto out_dput;
+
+			retried = true;
+			ovl_cleanup(dir, work);
+			dput(work);
+			goto retry;
+		}
+
+		err = ovl_create_real(dir, work, &stat, NULL, NULL, true);
+		if (err)
+			goto out_dput;
+	}
+out_unlock:
+	mutex_unlock(&dir->i_mutex);
+	mnt_drop_write(mnt);
+
+	return work;
+
+out_dput:
+	dput(work);
+	work = ERR_PTR(err);
+	goto out_unlock;
+}
+
+static void ovl_unescape(char *s)
+{
+	char *d = s;
+
+	for (;; s++, d++) {
+		if (*s == '\\')
+			s++;
+		*d = *s;
+		if (!*s)
+			break;
+	}
+}
+
+static bool ovl_is_allowed_fs_type(struct dentry *root)
+{
+	const struct dentry_operations *dop = root->d_op;
+
+	/*
+	 * We don't support:
+	 *  - automount filesystems
+	 *  - filesystems with revalidate (FIXME for lower layer)
+	 *  - filesystems with case insensitive names
+	 */
+	if (dop &&
+	    (dop->d_manage || dop->d_automount ||
+	     dop->d_revalidate || dop->d_weak_revalidate ||
+	     dop->d_compare || dop->d_hash)) {
+		return false;
+	}
+	return true;
+}
+
+static int ovl_mount_dir_noesc(const char *name, struct path *path)
+{
+	int err = -EINVAL;
+
+	if (!*name) {
+		pr_err("overlayfs: empty lowerdir\n");
+		goto out;
+	}
+	err = kern_path(name, LOOKUP_FOLLOW, path);
+	if (err) {
+		pr_err("overlayfs: failed to resolve '%s': %i\n", name, err);
+		goto out;
+	}
+	err = -EINVAL;
+	if (!ovl_is_allowed_fs_type(path->dentry)) {
+		pr_err("overlayfs: filesystem on '%s' not supported\n", name);
+		goto out_put;
+	}
+	if (!S_ISDIR(path->dentry->d_inode->i_mode)) {
+		pr_err("overlayfs: '%s' not a directory\n", name);
+		goto out_put;
+	}
+	return 0;
+
+out_put:
+	path_put(path);
+out:
+	return err;
+}
+
+static int ovl_mount_dir(const char *name, struct path *path)
+{
+	int err = -ENOMEM;
+	char *tmp = kstrdup(name, GFP_KERNEL);
+
+	if (tmp) {
+		ovl_unescape(tmp);
+		err = ovl_mount_dir_noesc(tmp, path);
+		kfree(tmp);
+	}
+	return err;
+}
+
+static int ovl_lower_dir(const char *name, struct path *path, long *namelen,
+			 int *stack_depth)
+{
+	int err;
+	struct kstatfs statfs;
+
+	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);
+		goto out_put;
+	}
+	*namelen = max(*namelen, statfs.f_namelen);
+	*stack_depth = max(*stack_depth, path->mnt->mnt_sb->s_stack_depth);
+
+	return 0;
+
+out_put:
+	path_put(path);
+out:
+	return err;
+}
+
+/* Workdir should not be subdir of upperdir and vice versa */
+static bool ovl_workdir_ok(struct dentry *workdir, struct dentry *upperdir)
+{
+	bool ok = false;
+
+	if (workdir != upperdir) {
+		ok = (lock_rename(workdir, upperdir) == NULL);
+		unlock_rename(workdir, upperdir);
+	}
+	return ok;
+}
+
+static unsigned int ovl_split_lowerdirs(char *str)
+{
+	unsigned int ctr = 1;
+	char *s, *d;
+
+	for (s = d = str;; s++, d++) {
+		if (*s == '\\') {
+			s++;
+		} else if (*s == ':') {
+			*d = '\0';
+			ctr++;
+			continue;
+		}
+		*d = *s;
+		if (!*s)
+			break;
+	}
+	return ctr;
+}
+
+static int ovl_fill_super(struct super_block *sb, void *data, int silent)
+{
+	struct path upperpath = { NULL, NULL };
+	struct path workpath = { NULL, NULL };
+	struct dentry *root_dentry;
+	struct ovl_entry *oe;
+	struct ovl_fs *ufs;
+	struct path *stack = NULL;
+	char *lowertmp;
+	char *lower;
+	unsigned int numlower;
+	unsigned int stacklen = 0;
+	unsigned int i;
+	int err;
+
+	err = -ENOMEM;
+	ufs = kzalloc(sizeof(struct ovl_fs), GFP_KERNEL);
+	if (!ufs)
+		goto out;
+
+	err = ovl_parse_opt((char *) data, &ufs->config);
+	if (err)
+		goto out_free_config;
+
+	err = -EINVAL;
+	if (!ufs->config.lowerdir) {
+		pr_err("overlayfs: missing 'lowerdir'\n");
+		goto out_free_config;
+	}
+
+	sb->s_stack_depth = 0;
+	if (ufs->config.upperdir) {
+		if (!ufs->config.workdir) {
+			pr_err("overlayfs: missing 'workdir'\n");
+			goto out_free_config;
+		}
+
+		err = ovl_mount_dir(ufs->config.upperdir, &upperpath);
+		if (err)
+			goto out_free_config;
+
+		/* Upper fs should not be r/o */
+		if (upperpath.mnt->mnt_sb->s_flags & MS_RDONLY) {
+			pr_err("overlayfs: upper fs is r/o, try multi-lower layers mount\n");
+			err = -EINVAL;
+			goto out_put_upperpath;
+		}
+
+		err = ovl_mount_dir(ufs->config.workdir, &workpath);
+		if (err)
+			goto out_put_upperpath;
+
+		err = -EINVAL;
+		if (upperpath.mnt != workpath.mnt) {
+			pr_err("overlayfs: workdir and upperdir must reside under the same mount\n");
+			goto out_put_workpath;
+		}
+		if (!ovl_workdir_ok(workpath.dentry, upperpath.dentry)) {
+			pr_err("overlayfs: workdir and upperdir must be separate subtrees\n");
+			goto out_put_workpath;
+		}
+		sb->s_stack_depth = upperpath.mnt->mnt_sb->s_stack_depth;
+	}
+	err = -ENOMEM;
+	lowertmp = kstrdup(ufs->config.lowerdir, GFP_KERNEL);
+	if (!lowertmp)
+		goto out_put_workpath;
+
+	err = -EINVAL;
+	stacklen = ovl_split_lowerdirs(lowertmp);
+	if (stacklen > OVL_MAX_STACK) {
+		pr_err("overlayfs: too many lower directries, limit is %d\n",
+		       OVL_MAX_STACK);
+		goto out_free_lowertmp;
+	} else if (!ufs->config.upperdir && stacklen == 1) {
+		pr_err("overlayfs: at least 2 lowerdir are needed while upperdir nonexistent\n");
+		goto out_free_lowertmp;
+	}
+
+	stack = kcalloc(stacklen, sizeof(struct path), GFP_KERNEL);
+	if (!stack)
+		goto out_free_lowertmp;
+
+	lower = lowertmp;
+	for (numlower = 0; numlower < stacklen; numlower++) {
+		err = ovl_lower_dir(lower, &stack[numlower],
+				    &ufs->lower_namelen, &sb->s_stack_depth);
+		if (err)
+			goto out_put_lowerpath;
+
+		lower = strchr(lower, '\0') + 1;
+	}
+
+	err = -EINVAL;
+	sb->s_stack_depth++;
+	if (sb->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) {
+		pr_err("overlayfs: maximum fs stacking depth exceeded\n");
+		goto out_put_lowerpath;
+	}
+
+	if (ufs->config.upperdir) {
+		ufs->upper_mnt = clone_private_mount(&upperpath);
+		err = PTR_ERR(ufs->upper_mnt);
+		if (IS_ERR(ufs->upper_mnt)) {
+			pr_err("overlayfs: failed to clone upperpath\n");
+			goto out_put_lowerpath;
+		}
+
+		ufs->workdir = ovl_workdir_create(ufs->upper_mnt, workpath.dentry);
+		err = PTR_ERR(ufs->workdir);
+		if (IS_ERR(ufs->workdir)) {
+			pr_err("overlayfs: failed to create directory %s/%s\n",
+			       ufs->config.workdir, OVL_WORKDIR_NAME);
+			goto out_put_upper_mnt;
+		}
+	}
+
+	err = -ENOMEM;
+	ufs->lower_mnt = kcalloc(numlower, sizeof(struct vfsmount *), GFP_KERNEL);
+	if (ufs->lower_mnt == NULL)
+		goto out_put_workdir;
+	for (i = 0; i < numlower; i++) {
+		struct vfsmount *mnt = clone_private_mount(&stack[i]);
+
+		err = PTR_ERR(mnt);
+		if (IS_ERR(mnt)) {
+			pr_err("overlayfs: failed to clone lowerpath\n");
+			goto out_put_lower_mnt;
+		}
+		/*
+		 * Make lower_mnt R/O.  That way fchmod/fchown on lower file
+		 * will fail instead of modifying lower fs.
+		 */
+		mnt->mnt_flags |= MNT_READONLY;
+
+		ufs->lower_mnt[ufs->numlower] = mnt;
+		ufs->numlower++;
+	}
+
+	/* If the upper fs is nonexistent, we mark overlayfs r/o too */
+	if (!ufs->upper_mnt)
+		sb->s_flags |= MS_RDONLY;
+
+	sb->s_d_op = &ovl_dentry_operations;
+
+	err = -ENOMEM;
+	oe = ovl_alloc_entry(numlower);
+	if (!oe)
+		goto out_put_lower_mnt;
+
+	root_dentry = d_make_root(ovl_new_inode(sb, S_IFDIR, oe));
+	if (!root_dentry)
+		goto out_free_oe;
+
+	mntput(upperpath.mnt);
+	for (i = 0; i < numlower; i++)
+		mntput(stack[i].mnt);
+	path_put(&workpath);
+	kfree(lowertmp);
+
+	oe->__upperdentry = upperpath.dentry;
+	for (i = 0; i < numlower; i++) {
+		oe->lowerstack[i].dentry = stack[i].dentry;
+		oe->lowerstack[i].mnt = ufs->lower_mnt[i];
+	}
+
+	root_dentry->d_fsdata = oe;
+
+	sb->s_magic = OVERLAYFS_SUPER_MAGIC;
+	sb->s_op = &ovl_super_operations;
+	sb->s_root = root_dentry;
+	sb->s_fs_info = ufs;
+
+	return 0;
+
+out_free_oe:
+	kfree(oe);
+out_put_lower_mnt:
+	for (i = 0; i < ufs->numlower; i++)
+		mntput(ufs->lower_mnt[i]);
+	kfree(ufs->lower_mnt);
+out_put_workdir:
+	dput(ufs->workdir);
+out_put_upper_mnt:
+	mntput(ufs->upper_mnt);
+out_put_lowerpath:
+	for (i = 0; i < numlower; i++)
+		path_put(&stack[i]);
+	kfree(stack);
+out_free_lowertmp:
+	kfree(lowertmp);
+out_put_workpath:
+	path_put(&workpath);
+out_put_upperpath:
+	path_put(&upperpath);
+out_free_config:
+	kfree(ufs->config.lowerdir);
+	kfree(ufs->config.upperdir);
+	kfree(ufs->config.workdir);
+	kfree(ufs);
+out:
+	return err;
+}
+
+static struct dentry *ovl_mount(struct file_system_type *fs_type, int flags,
+				const char *dev_name, void *raw_data)
+{
+	return mount_nodev(fs_type, flags, raw_data, ovl_fill_super);
+}
+
+static struct file_system_type ovl_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "overlay",
+	.mount		= ovl_mount,
+	.kill_sb	= kill_anon_super,
+};
+MODULE_ALIAS_FS("overlay");
+
+static int __init ovl_init(void)
+{
+	return register_filesystem(&ovl_fs_type);
+}
+
+static void __exit ovl_exit(void)
+{
+	unregister_filesystem(&ovl_fs_type);
+}
+
+module_init(ovl_init);
+module_exit(ovl_exit);
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 9ae46b87470d..89026095f2b5 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -146,7 +146,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl
 	struct task_struct *task;
 	void *ns;
 	char name[50];
-	int len = -EACCES;
+	int res = -EACCES;
 
 	task = get_proc_task(inode);
 	if (!task)
@@ -155,24 +155,18 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl
 	if (!ptrace_may_access(task, PTRACE_MODE_READ))
 		goto out_put_task;
 
-	len = -ENOENT;
+	res = -ENOENT;
 	ns = ns_ops->get(task);
 	if (!ns)
 		goto out_put_task;
 
 	snprintf(name, sizeof(name), "%s:[%u]", ns_ops->name, ns_ops->inum(ns));
-	len = strlen(name);
-
-	if (len > buflen)
-		len = buflen;
-	if (copy_to_user(buffer, name, len))
-		len = -EFAULT;
-
+	res = readlink_copy(buffer, buflen, name);
 	ns_ops->put(ns);
 out_put_task:
 	put_task_struct(task);
 out:
-	return len;
+	return res;
 }
 
 static const struct inode_operations proc_ns_link_inode_operations = {
diff --git a/fs/proc/self.c b/fs/proc/self.c
index ffeb202ec942..4348bb8907c2 100644
--- a/fs/proc/self.c
+++ b/fs/proc/self.c
@@ -16,7 +16,7 @@ static int proc_self_readlink(struct dentry *dentry, char __user *buffer,
 	if (!tgid)
 		return -ENOENT;
 	sprintf(tmp, "%d", tgid);
-	return vfs_readlink(dentry,buffer,buflen,tmp);
+	return readlink_copy(buffer, buflen, tmp);
 }
 
 static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd)
diff --git a/fs/readdir.c b/fs/readdir.c
index 5b53d995cae6..e21af53ec24e 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -72,10 +72,11 @@ struct readdir_callback {
 	int result;
 };
 
-static int fillonedir(void * __buf, const char * name, int namlen, loff_t offset,
-		      u64 ino, unsigned int d_type)
+static int fillonedir(struct dir_context *ctx, const char *name, int namlen,
+		      loff_t offset, u64 ino, unsigned int d_type)
 {
-	struct readdir_callback *buf = (struct readdir_callback *) __buf;
+	struct readdir_callback *buf =
+		container_of(ctx, struct readdir_callback, ctx);
 	struct old_linux_dirent __user * dirent;
 	unsigned long d_ino;
 
@@ -146,11 +147,12 @@ struct getdents_callback {
 	int error;
 };
 
-static int filldir(void * __buf, const char * name, int namlen, loff_t offset,
-		   u64 ino, unsigned int d_type)
+static int filldir(struct dir_context *ctx, const char *name, int namlen,
+		   loff_t offset, u64 ino, unsigned int d_type)
 {
 	struct linux_dirent __user * dirent;
-	struct getdents_callback * buf = (struct getdents_callback *) __buf;
+	struct getdents_callback *buf =
+		container_of(ctx, struct getdents_callback, ctx);
 	unsigned long d_ino;
 	int reclen = ALIGN(offsetof(struct linux_dirent, d_name) + namlen + 2,
 		sizeof(long));
@@ -230,11 +232,12 @@ struct getdents_callback64 {
 	int error;
 };
 
-static int filldir64(void * __buf, const char * name, int namlen, loff_t offset,
-		     u64 ino, unsigned int d_type)
+static int filldir64(struct dir_context *ctx, const char *name, int namlen,
+		     loff_t offset, u64 ino, unsigned int d_type)
 {
 	struct linux_dirent64 __user *dirent;
-	struct getdents_callback64 * buf = (struct getdents_callback64 *) __buf;
+	struct getdents_callback64 *buf =
+		container_of(ctx, struct getdents_callback64, ctx);
 	int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1,
 		sizeof(u64));
 
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 5cdfbd638b5c..d8b7acfd5066 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -177,10 +177,11 @@ struct reiserfs_dentry_buf {
 };
 
 static int
-fill_with_dentries(void *buf, const char *name, int namelen, loff_t offset,
-		    u64 ino, unsigned int d_type)
+fill_with_dentries(struct dir_context *ctx, const char *name, int namelen,
+		   loff_t offset, u64 ino, unsigned int d_type)
 {
-	struct reiserfs_dentry_buf *dbuf = buf;
+	struct reiserfs_dentry_buf *dbuf =
+		container_of(ctx, struct reiserfs_dentry_buf, ctx);
 	struct dentry *dentry;
 	WARN_ON_ONCE(!mutex_is_locked(&dbuf->xadir->d_inode->i_mutex));
 
@@ -794,10 +795,12 @@ struct listxattr_buf {
 	struct dentry *dentry;
 };
 
-static int listxattr_filler(void *buf, const char *name, int namelen,
-			    loff_t offset, u64 ino, unsigned int d_type)
+static int listxattr_filler(struct dir_context *ctx, const char *name,
+			    int namelen, loff_t offset, u64 ino,
+			    unsigned int d_type)
 {
-	struct listxattr_buf *b = (struct listxattr_buf *)buf;
+	struct listxattr_buf *b =
+		container_of(ctx, struct listxattr_buf, ctx);
 	size_t size;
 	if (name[0] != '.' ||
 	    (namelen != 1 && (name[1] != '.' || namelen != 2))) {
diff --git a/fs/splice.c b/fs/splice.c
index 12028fa41def..ffb92b9d34ba 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1327,6 +1327,7 @@ 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,
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 78e62cc471c5..6152cbe353e8 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -271,32 +271,6 @@ xfs_open_by_handle(
 	return error;
 }
 
-/*
- * This is a copy from fs/namei.c:vfs_readlink(), except for removing it's
- * unused first argument.
- */
-STATIC int
-do_readlink(
-	char __user		*buffer,
-	int			buflen,
-	const char		*link)
-{
-        int len;
-
-	len = PTR_ERR(link);
-	if (IS_ERR(link))
-		goto out;
-
-	len = strlen(link);
-	if (len > (unsigned) buflen)
-		len = buflen;
-	if (copy_to_user(buffer, link, len))
-		len = -EFAULT;
- out:
-	return len;
-}
-
-
 int
 xfs_readlink_by_handle(
 	struct file		*parfilp,
@@ -334,7 +308,7 @@ xfs_readlink_by_handle(
 	error = -xfs_readlink(XFS_I(dentry->d_inode), link);
 	if (error)
 		goto out_kfree;
-	error = do_readlink(hreq->ohandle, olen, link);
+	error = readlink_copy(hreq->ohandle, olen, link);
 	if (error)
 		goto out_kfree;
 
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 3b50cac7ccb3..3b9bfdb83ba6 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -308,6 +308,7 @@ extern void dentry_update_name_case(struct dentry *, struct qstr *);
 
 /* used for rename() and baskets */
 extern void d_move(struct dentry *, struct dentry *);
+extern void d_exchange(struct dentry *, struct dentry *);
 extern struct dentry *d_ancestor(struct dentry *, struct dentry *);
 
 /* appendix may either be NULL or be used for transname suffixes */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 23b2a35d712e..e1cee8b12d1a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -218,6 +218,13 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #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.
  * Also, in this manner, a Filesystem can look at only the values it cares
@@ -249,6 +256,12 @@ 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
  *
@@ -628,11 +641,13 @@ static inline int inode_unhashed(struct inode *inode)
  * 2: child/target
  * 3: xattr
  * 4: second non-directory
- * The last is for certain operations (such as rename) which lock two
+ * 5: second parent (when locking independent directories in rename)
+ *
+ * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two
  * non-directories at once.
  *
  * The locking order between these classes is
- * parent -> child -> normal -> xattr -> second non-directory
+ * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory
  */
 enum inode_i_mutex_lock_class
 {
@@ -640,7 +655,8 @@ enum inode_i_mutex_lock_class
 	I_MUTEX_PARENT,
 	I_MUTEX_CHILD,
 	I_MUTEX_XATTR,
-	I_MUTEX_NONDIR2
+	I_MUTEX_NONDIR2,
+	I_MUTEX_PARENT2,
 };
 
 void lock_two_nondirectories(struct inode *, struct inode*);
@@ -1329,6 +1345,11 @@ 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);
@@ -1460,7 +1481,8 @@ extern int vfs_symlink(struct inode *, struct dentry *, const char *);
 extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **);
 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 **);
+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.
@@ -1508,7 +1530,10 @@ int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
  * This allows the kernel to read directories into kernel space or
  * to have different dirent layouts depending on the binary type.
  */
-typedef int (*filldir_t)(void *, const char *, int, loff_t, u64, unsigned);
+struct dir_context;
+typedef int (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64,
+			 unsigned);
+
 struct dir_context {
 	const filldir_t actor;
 	loff_t pos;
@@ -1571,6 +1596,8 @@ struct inode_operations {
 	int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
 	int (*rename) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *);
+	int (*rename2) (struct inode *, struct dentry *,
+			struct inode *, struct dentry *, unsigned int);
 	int (*setattr) (struct dentry *, struct iattr *);
 	int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
 	int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);
@@ -1585,6 +1612,9 @@ 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,
@@ -1682,6 +1712,9 @@ 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
  *
@@ -2079,6 +2112,7 @@ 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);
 
@@ -2292,7 +2326,9 @@ 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)
 {
@@ -2500,6 +2536,9 @@ extern ssize_t generic_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);
@@ -2564,7 +2603,7 @@ extern const struct file_operations generic_ro_fops;
 
 #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m))
 
-extern int vfs_readlink(struct dentry *, char __user *, int, const char *);
+extern int readlink_copy(char __user *, int, const char *);
 extern int page_readlink(struct dentry *, char __user *, int);
 extern void *page_follow_link_light(struct dentry *, struct nameidata *);
 extern void page_put_link(struct dentry *, struct nameidata *, void *);
@@ -2777,6 +2816,14 @@ 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))
diff --git a/include/linux/mount.h b/include/linux/mount.h
index b0c1e6574e7f..fff78cb99fa1 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -81,6 +81,9 @@ extern void mnt_pin(struct vfsmount *mnt);
 extern void mnt_unpin(struct vfsmount *mnt);
 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,
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 72bf3a01a4ee..a9a98ff6e339 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -555,6 +555,21 @@ static inline void rcu_preempt_sleep_check(void)
 #define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v)
 
 /**
+ * lockless_dereference() - safely load a pointer for later dereference
+ * @p: The pointer to load
+ *
+ * Similar to rcu_dereference(), but for situations where the pointed-to
+ * object's lifetime is managed by something other than RCU.  That
+ * "something other" might be reference counting or simple immortality.
+ */
+#define lockless_dereference(p) \
+({ \
+	typeof(p) _________p1 = ACCESS_ONCE(p); \
+	smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
+	(_________p1); \
+})
+
+/**
  * rcu_assign_pointer() - assign to RCU-protected pointer
  * @p: pointer to assign to
  * @v: value to assign (publish)
diff --git a/include/linux/security.h b/include/linux/security.h
index 2fc42d191f79..6478ce3252c7 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1793,7 +1793,8 @@ int security_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 int security_inode_rmdir(struct inode *dir, struct dentry *dentry);
 int security_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev);
 int security_inode_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);
 int security_inode_readlink(struct dentry *dentry);
 int security_inode_follow_link(struct dentry *dentry, struct nameidata *nd);
 int security_inode_permission(struct inode *inode, int mask);
@@ -2161,7 +2162,8 @@ static inline int security_inode_mknod(struct inode *dir,
 static inline int security_inode_rename(struct inode *old_dir,
 					 struct dentry *old_dentry,
 					 struct inode *new_dir,
-					 struct dentry *new_dentry)
+					 struct dentry *new_dentry,
+					 unsigned int flags)
 {
 	return 0;
 }
@@ -2955,7 +2957,8 @@ int security_path_symlink(struct path *dir, struct dentry *dentry,
 int security_path_link(struct dentry *old_dentry, struct path *new_dir,
 		       struct dentry *new_dentry);
 int security_path_rename(struct path *old_dir, struct dentry *old_dentry,
-			 struct path *new_dir, struct dentry *new_dentry);
+			 struct path *new_dir, struct dentry *new_dentry,
+			 unsigned int flags);
 int security_path_chmod(struct path *path, umode_t mode);
 int security_path_chown(struct path *path, kuid_t uid, kgid_t gid);
 int security_path_chroot(struct path *path);
@@ -3003,7 +3006,8 @@ static inline int security_path_link(struct dentry *old_dentry,
 static inline int security_path_rename(struct path *old_dir,
 				       struct dentry *old_dentry,
 				       struct path *new_dir,
-				       struct dentry *new_dentry)
+				       struct dentry *new_dentry,
+				       unsigned int flags)
 {
 	return 0;
 }
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 6c28b61bb690..3735fa0a6784 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -35,6 +35,10 @@
 #define SEEK_HOLE	4	/* seek to the next hole */
 #define SEEK_MAX	SEEK_HOLE
 
+#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;
 	__u64 len;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 69cffb46db17..60146febb9b3 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4232,6 +4232,13 @@ static void perf_pending_event(struct irq_work *entry)
 {
 	struct perf_event *event = container_of(entry,
 			struct perf_event, pending);
+	int rctx;
+
+	rctx = perf_swevent_get_recursion_context();
+	/*
+	 * If we 'fail' here, that's OK, it means recursion is already disabled
+	 * and we won't recurse 'further'.
+	 */
 
 	if (event->pending_disable) {
 		event->pending_disable = 0;
@@ -4242,6 +4249,9 @@ static void perf_pending_event(struct irq_work *entry)
 		event->pending_wakeup = 0;
 		perf_event_wakeup(event);
 	}
+
+	if (rctx >= 0)
+		perf_swevent_put_recursion_context(rctx);
 }
 
 /*
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index bf7a1bbb975f..e278c64572de 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -57,13 +57,24 @@ struct ieee80211_local;
 #define IEEE80211_UNSET_POWER_LEVEL	INT_MIN
 
 /*
- * Some APs experience problems when working with U-APSD. Decrease the
- * probability of that happening by using legacy mode for all ACs but VO.
- * The AP that caused us trouble was a Cisco 4410N. It ignores our
- * setting, and always treats non-VO ACs as legacy.
+ * Some APs experience problems when working with U-APSD. Decreasing the
+ * probability of that happening by using legacy mode for all ACs but VO isn't
+ * enough.
+ *
+ * Cisco 4410N originally forced us to enable VO by default only because it
+ * treated non-VO ACs as legacy.
+ *
+ * However some APs (notably Netgear R7000) silently reclassify packets to
+ * different ACs. Since u-APSD ACs require trigger frames for frame retrieval
+ * clients would never see some frames (e.g. ARP responses) or would fetch them
+ * accidentally after a long time.
+ *
+ * It makes little sense to enable u-APSD queues by default because it needs
+ * userspace applications to be aware of it to actually take advantage of the
+ * possible additional powersavings. Implicitly depending on driver autotrigger
+ * frame support doesn't make much sense.
  */
-#define IEEE80211_DEFAULT_UAPSD_QUEUES \
-	IEEE80211_WMM_IE_STA_QOSINFO_AC_VO
+#define IEEE80211_DEFAULT_UAPSD_QUEUES 0
 
 #define IEEE80211_DEFAULT_MAX_SP_LEN		\
 	IEEE80211_WMM_IE_STA_QOSINFO_SP_ALL
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 815ca56b39e7..9abb445ea261 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2107,6 +2107,9 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx)
 	hdr = (struct ieee80211_hdr *) skb->data;
 	mesh_hdr = (struct ieee80211s_hdr *) (skb->data + hdrlen);
 
+	if (ieee80211_drop_unencrypted(rx, hdr->frame_control))
+		return RX_DROP_MONITOR;
+
 	/* frame is in RMC, don't forward */
 	if (ieee80211_is_data(hdr->frame_control) &&
 	    is_multicast_ether_addr(hdr->addr1) &&
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 18d73df72531..c260243dbe07 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4190,6 +4190,16 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info)
 	if (parse_station_flags(info, dev->ieee80211_ptr->iftype, &params))
 		return -EINVAL;
 
+	/* HT/VHT requires QoS, but if we don't have that just ignore HT/VHT
+	 * as userspace might just pass through the capabilities from the IEs
+	 * directly, rather than enforcing this restriction and returning an
+	 * error in this case.
+	 */
+	if (!(params.sta_flags_set & BIT(NL80211_STA_FLAG_WME))) {
+		params.ht_capa = NULL;
+		params.vht_capa = NULL;
+	}
+
 	/* When you run into this, adjust the code below for the new flag */
 	BUILD_BUG_ON(NL80211_STA_FLAG_MAX != 7);
 
diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c
index 3bab89eb21d6..e90ab0e20db8 100644
--- a/security/integrity/evm/evm_crypto.c
+++ b/security/integrity/evm/evm_crypto.c
@@ -137,7 +137,7 @@ static int evm_calc_hmac_or_hash(struct dentry *dentry,
 	int error;
 	int size;
 
-	if (!inode->i_op || !inode->i_op->getxattr)
+	if (!inode->i_op->getxattr)
 		return -EOPNOTSUPP;
 	desc = init_desc(type);
 	if (IS_ERR(desc))
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index 7e71e066198f..690cd632bd5b 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -62,7 +62,7 @@ static int evm_find_protected_xattrs(struct dentry *dentry)
 	int error;
 	int count = 0;
 
-	if (!inode->i_op || !inode->i_op->getxattr)
+	if (!inode->i_op->getxattr)
 		return -EOPNOTSUPP;
 
 	for (xattr = evm_config_xattrnames; *xattr != NULL; xattr++) {
diff --git a/security/security.c b/security/security.c
index 919cad93ac82..8b774f362a3d 100644
--- a/security/security.c
+++ b/security/security.c
@@ -433,11 +433,20 @@ int security_path_link(struct dentry *old_dentry, struct path *new_dir,
 }
 
 int security_path_rename(struct path *old_dir, struct dentry *old_dentry,
-			 struct path *new_dir, struct dentry *new_dentry)
+			 struct path *new_dir, struct dentry *new_dentry,
+			 unsigned int flags)
 {
 	if (unlikely(IS_PRIVATE(old_dentry->d_inode) ||
 		     (new_dentry->d_inode && IS_PRIVATE(new_dentry->d_inode))))
 		return 0;
+
+	if (flags & RENAME_EXCHANGE) {
+		int err = security_ops->path_rename(new_dir, new_dentry,
+						    old_dir, old_dentry);
+		if (err)
+			return err;
+	}
+
 	return security_ops->path_rename(old_dir, old_dentry, new_dir,
 					 new_dentry);
 }
@@ -524,11 +533,20 @@ int security_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
 }
 
 int security_inode_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)
 {
         if (unlikely(IS_PRIVATE(old_dentry->d_inode) ||
             (new_dentry->d_inode && IS_PRIVATE(new_dentry->d_inode))))
 		return 0;
+
+	if (flags & RENAME_EXCHANGE) {
+		int err = security_ops->inode_rename(new_dir, new_dentry,
+						     old_dir, old_dentry);
+		if (err)
+			return err;
+	}
+
 	return security_ops->inode_rename(old_dir, old_dentry,
 					   new_dir, new_dentry);
 }
diff --git a/security/tomoyo/realpath.c b/security/tomoyo/realpath.c
index 80a09c37cac8..bed745c8b1a3 100644
--- a/security/tomoyo/realpath.c
+++ b/security/tomoyo/realpath.c
@@ -173,7 +173,7 @@ static char *tomoyo_get_local_path(struct dentry *dentry, char * const buffer,
 		 * Use filesystem name if filesystem does not support rename()
 		 * operation.
 		 */
-		if (inode->i_op && !inode->i_op->rename)
+		if (!inode->i_op->rename && !inode->i_op->rename2)
 			goto prepend_filesystem_name;
 	}
 	/* Prepend device name. */
@@ -282,7 +282,8 @@ char *tomoyo_realpath_from_path(struct path *path)
 		 * Get local name for filesystems without rename() operation
 		 * or dentry without vfsmount.
 		 */
-		if (!path->mnt || (inode->i_op && !inode->i_op->rename))
+		if (!path->mnt ||
+		    (!inode->i_op->rename && !inode->i_op->rename2))
 			pos = tomoyo_get_local_path(path->dentry, buf,
 						    buf_len - 1);
 		/* Get absolute name for the rest. */
diff --git a/sound/soc/codecs/adav80x.c b/sound/soc/codecs/adav80x.c
index f78b27a7c461..23454e9a5d3a 100644
--- a/sound/soc/codecs/adav80x.c
+++ b/sound/soc/codecs/adav80x.c
@@ -319,7 +319,7 @@ static int adav80x_put_deemph(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct adav80x *adav80x = snd_soc_codec_get_drvdata(codec);
-	unsigned int deemph = ucontrol->value.enumerated.item[0];
+	unsigned int deemph = ucontrol->value.integer.value[0];
 
 	if (deemph > 1)
 		return -EINVAL;
@@ -335,7 +335,7 @@ static int adav80x_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct adav80x *adav80x = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = adav80x->deemph;
+	ucontrol->value.integer.value[0] = adav80x->deemph;
 	return 0;
 };
 
diff --git a/sound/soc/codecs/ak4641.c b/sound/soc/codecs/ak4641.c
index 94cbe508dd37..d7184726f8a0 100644
--- a/sound/soc/codecs/ak4641.c
+++ b/sound/soc/codecs/ak4641.c
@@ -76,7 +76,7 @@ static int ak4641_put_deemph(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct ak4641_priv *ak4641 = snd_soc_codec_get_drvdata(codec);
-	int deemph = ucontrol->value.enumerated.item[0];
+	int deemph = ucontrol->value.integer.value[0];
 
 	if (deemph > 1)
 		return -EINVAL;
@@ -92,7 +92,7 @@ static int ak4641_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct ak4641_priv *ak4641 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = ak4641->deemph;
+	ucontrol->value.integer.value[0] = ak4641->deemph;
 	return 0;
 };
 
diff --git a/sound/soc/codecs/cs4271.c b/sound/soc/codecs/cs4271.c
index ce05fd93dc74..a0ad41ac5574 100644
--- a/sound/soc/codecs/cs4271.c
+++ b/sound/soc/codecs/cs4271.c
@@ -288,7 +288,7 @@ static int cs4271_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct cs4271_private *cs4271 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = cs4271->deemph;
+	ucontrol->value.integer.value[0] = cs4271->deemph;
 	return 0;
 }
 
@@ -298,7 +298,7 @@ static int cs4271_put_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct cs4271_private *cs4271 = snd_soc_codec_get_drvdata(codec);
 
-	cs4271->deemph = ucontrol->value.enumerated.item[0];
+	cs4271->deemph = ucontrol->value.integer.value[0];
 	return cs4271_set_deemph(codec);
 }
 
diff --git a/sound/soc/codecs/pcm1681.c b/sound/soc/codecs/pcm1681.c
index 73f9c3630e2c..651e2fe2c31f 100644
--- a/sound/soc/codecs/pcm1681.c
+++ b/sound/soc/codecs/pcm1681.c
@@ -118,7 +118,7 @@ static int pcm1681_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct pcm1681_private *priv = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = priv->deemph;
+	ucontrol->value.integer.value[0] = priv->deemph;
 
 	return 0;
 }
@@ -129,7 +129,7 @@ static int pcm1681_put_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct pcm1681_private *priv = snd_soc_codec_get_drvdata(codec);
 
-	priv->deemph = ucontrol->value.enumerated.item[0];
+	priv->deemph = ucontrol->value.integer.value[0];
 
 	return pcm1681_set_deemph(codec);
 }
diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c
index 715589ff0eda..e93c36fd3073 100644
--- a/sound/soc/codecs/sgtl5000.c
+++ b/sound/soc/codecs/sgtl5000.c
@@ -1198,13 +1198,7 @@ static int sgtl5000_set_power_regs(struct snd_soc_codec *codec)
 		/* Enable VDDC charge pump */
 		ana_pwr |= SGTL5000_VDDC_CHRGPMP_POWERUP;
 	} else if (vddio >= 3100 && vdda >= 3100) {
-		/*
-		 * if vddio and vddd > 3.1v,
-		 * charge pump should be clean before set ana_pwr
-		 */
-		snd_soc_update_bits(codec, SGTL5000_CHIP_ANA_POWER,
-				SGTL5000_VDDC_CHRGPMP_POWERUP, 0);
-
+		ana_pwr &= ~SGTL5000_VDDC_CHRGPMP_POWERUP;
 		/* VDDC use VDDIO rail */
 		lreg_ctrl |= SGTL5000_VDDC_ASSN_OVRD;
 		lreg_ctrl |= SGTL5000_VDDC_MAN_ASSN_VDDIO <<
diff --git a/sound/soc/codecs/tas5086.c b/sound/soc/codecs/tas5086.c
index a895a5e4bdf2..c6c65001457d 100644
--- a/sound/soc/codecs/tas5086.c
+++ b/sound/soc/codecs/tas5086.c
@@ -275,7 +275,7 @@ static int tas5086_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct tas5086_private *priv = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = priv->deemph;
+	ucontrol->value.integer.value[0] = priv->deemph;
 
 	return 0;
 }
@@ -286,7 +286,7 @@ static int tas5086_put_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct tas5086_private *priv = snd_soc_codec_get_drvdata(codec);
 
-	priv->deemph = ucontrol->value.enumerated.item[0];
+	priv->deemph = ucontrol->value.integer.value[0];
 
 	return tas5086_set_deemph(codec);
 }
diff --git a/sound/soc/codecs/wm2000.c b/sound/soc/codecs/wm2000.c
index 8ae50274ea8f..1a9f4574b65b 100644
--- a/sound/soc/codecs/wm2000.c
+++ b/sound/soc/codecs/wm2000.c
@@ -610,7 +610,7 @@ static int wm2000_anc_mode_get(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev);
 
-	ucontrol->value.enumerated.item[0] = wm2000->anc_active;
+	ucontrol->value.integer.value[0] = wm2000->anc_active;
 
 	return 0;
 }
@@ -620,7 +620,7 @@ static int wm2000_anc_mode_put(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev);
-	int anc_active = ucontrol->value.enumerated.item[0];
+	int anc_active = ucontrol->value.integer.value[0];
 	int ret;
 
 	if (anc_active > 1)
@@ -643,7 +643,7 @@ static int wm2000_speaker_get(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev);
 
-	ucontrol->value.enumerated.item[0] = wm2000->spk_ena;
+	ucontrol->value.integer.value[0] = wm2000->spk_ena;
 
 	return 0;
 }
@@ -653,7 +653,7 @@ static int wm2000_speaker_put(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev);
-	int val = ucontrol->value.enumerated.item[0];
+	int val = ucontrol->value.integer.value[0];
 	int ret;
 
 	if (val > 1)
diff --git a/sound/soc/codecs/wm8731.c b/sound/soc/codecs/wm8731.c
index 029720366ff8..e593722574de 100644
--- a/sound/soc/codecs/wm8731.c
+++ b/sound/soc/codecs/wm8731.c
@@ -122,7 +122,7 @@ static int wm8731_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct wm8731_priv *wm8731 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = wm8731->deemph;
+	ucontrol->value.integer.value[0] = wm8731->deemph;
 
 	return 0;
 }
@@ -132,7 +132,7 @@ static int wm8731_put_deemph(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct wm8731_priv *wm8731 = snd_soc_codec_get_drvdata(codec);
-	int deemph = ucontrol->value.enumerated.item[0];
+	int deemph = ucontrol->value.integer.value[0];
 	int ret = 0;
 
 	if (deemph > 1)
diff --git a/sound/soc/codecs/wm8903.c b/sound/soc/codecs/wm8903.c
index eebcb1da3b7b..ae7d76efe063 100644
--- a/sound/soc/codecs/wm8903.c
+++ b/sound/soc/codecs/wm8903.c
@@ -442,7 +442,7 @@ static int wm8903_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct wm8903_priv *wm8903 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = wm8903->deemph;
+	ucontrol->value.integer.value[0] = wm8903->deemph;
 
 	return 0;
 }
@@ -452,7 +452,7 @@ static int wm8903_put_deemph(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct wm8903_priv *wm8903 = snd_soc_codec_get_drvdata(codec);
-	int deemph = ucontrol->value.enumerated.item[0];
+	int deemph = ucontrol->value.integer.value[0];
 	int ret = 0;
 
 	if (deemph > 1)
diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c
index 53bbfac6a83a..66cb9e95b5eb 100644
--- a/sound/soc/codecs/wm8904.c
+++ b/sound/soc/codecs/wm8904.c
@@ -523,7 +523,7 @@ static int wm8904_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct wm8904_priv *wm8904 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = wm8904->deemph;
+	ucontrol->value.integer.value[0] = wm8904->deemph;
 	return 0;
 }
 
@@ -532,7 +532,7 @@ static int wm8904_put_deemph(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct wm8904_priv *wm8904 = snd_soc_codec_get_drvdata(codec);
-	int deemph = ucontrol->value.enumerated.item[0];
+	int deemph = ucontrol->value.integer.value[0];
 
 	if (deemph > 1)
 		return -EINVAL;
diff --git a/sound/soc/codecs/wm8955.c b/sound/soc/codecs/wm8955.c
index 82c8ba975720..1c1fc6119758 100644
--- a/sound/soc/codecs/wm8955.c
+++ b/sound/soc/codecs/wm8955.c
@@ -393,7 +393,7 @@ static int wm8955_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct wm8955_priv *wm8955 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = wm8955->deemph;
+	ucontrol->value.integer.value[0] = wm8955->deemph;
 	return 0;
 }
 
@@ -402,7 +402,7 @@ static int wm8955_put_deemph(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct wm8955_priv *wm8955 = snd_soc_codec_get_drvdata(codec);
-	int deemph = ucontrol->value.enumerated.item[0];
+	int deemph = ucontrol->value.integer.value[0];
 
 	if (deemph > 1)
 		return -EINVAL;
diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c
index 942ef8427347..2a0bfb848512 100644
--- a/sound/soc/codecs/wm8960.c
+++ b/sound/soc/codecs/wm8960.c
@@ -181,7 +181,7 @@ static int wm8960_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct wm8960_priv *wm8960 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = wm8960->deemph;
+	ucontrol->value.integer.value[0] = wm8960->deemph;
 	return 0;
 }
 
@@ -190,7 +190,7 @@ static int wm8960_put_deemph(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct wm8960_priv *wm8960 = snd_soc_codec_get_drvdata(codec);
-	int deemph = ucontrol->value.enumerated.item[0];
+	int deemph = ucontrol->value.integer.value[0];
 
 	if (deemph > 1)
 		return -EINVAL;
diff --git a/sound/soc/jz4740/Makefile b/sound/soc/jz4740/Makefile
index be873c1b0c20..d32c540555c4 100644
--- a/sound/soc/jz4740/Makefile
+++ b/sound/soc/jz4740/Makefile
@@ -1,10 +1,8 @@
 #
 # Jz4740 Platform Support
 #
-snd-soc-jz4740-objs := jz4740-pcm.o
 snd-soc-jz4740-i2s-objs := jz4740-i2s.o
 
-obj-$(CONFIG_SND_JZ4740_SOC) += snd-soc-jz4740.o
 obj-$(CONFIG_SND_JZ4740_SOC_I2S) += snd-soc-jz4740-i2s.o
 
 # Jz4740 Machine Support