Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: (57 commits)
  tidy the trailing symlinks traversal up
  Turn resolution of trailing symlinks iterative everywhere
  simplify link_path_walk() tail
  Make trailing symlink resolution in path_lookupat() iterative
  update nd->inode in __do_follow_link() instead of after do_follow_link()
  pull handling of one pathname component into a helper
  fs: allow AT_EMPTY_PATH in linkat(), limit that to CAP_DAC_READ_SEARCH
  Allow passing O_PATH descriptors via SCM_RIGHTS datagrams
  readlinkat(), fchownat() and fstatat() with empty relative pathnames
  Allow O_PATH for symlinks
  New kind of open files - "location only".
  ext4: Copy fs UUID to superblock
  ext3: Copy fs UUID to superblock.
  vfs: Export file system uuid via /proc/<pid>/mountinfo
  unistd.h: Add new syscalls numbers to asm-generic
  x86: Add new syscalls for x86_64
  x86: Add new syscalls for x86_32
  fs: Remove i_nlink check from file system link callback
  fs: Don't allow to create hardlink for deleted file
  vfs: Add open by file handle support
  ...

33 files changed, 1337 insertions, 1076 deletions

diff --git a/fs/Kconfig b/fs/Kconfig
index 3db9caa57ed..7cb53aafac1 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -47,7 +47,7 @@ config FS_POSIX_ACL
 	def_bool n
 
 config EXPORTFS
-	tristate
+	bool
 
 config FILE_LOCKING
 	bool "Enable POSIX file locking API" if EXPERT
diff --git a/fs/Makefile b/fs/Makefile
index a7f7cef0c0c..ba01202844c 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -48,6 +48,8 @@ obj-$(CONFIG_FS_POSIX_ACL)	+= posix_acl.o xattr_acl.o
 obj-$(CONFIG_NFS_COMMON)	+= nfs_common/
 obj-$(CONFIG_GENERIC_ACL)	+= generic_acl.o
 
+obj-$(CONFIG_FHANDLE)		+= fhandle.o
+
 obj-y				+= quota/
 
 obj-$(CONFIG_PROC_FS)		+= proc/
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index ff27d7a477b..b4ffad859ad 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -21,9 +21,13 @@ static int btrfs_encode_fh(struct dentry *dentry, u32 *fh, int *max_len,
 	int len = *max_len;
 	int type;
 
-	if ((len < BTRFS_FID_SIZE_NON_CONNECTABLE) ||
-	    (connectable && len < BTRFS_FID_SIZE_CONNECTABLE))
+	if (connectable && (len < BTRFS_FID_SIZE_CONNECTABLE)) {
+		*max_len = BTRFS_FID_SIZE_CONNECTABLE;
 		return 255;
+	} else if (len < BTRFS_FID_SIZE_NON_CONNECTABLE) {
+		*max_len = BTRFS_FID_SIZE_NON_CONNECTABLE;
+		return 255;
+	}
 
 	len  = BTRFS_FID_SIZE_NON_CONNECTABLE;
 	type = FILEID_BTRFS_WITHOUT_PARENT;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 9007bbd01db..4a0107e1874 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4806,9 +4806,6 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 	int err;
 	int drop_inode = 0;
 
-	if (inode->i_nlink == 0)
-		return -ENOENT;
-
 	/* do not allow sys_link's with other subvols of the same device */
 	if (root->objectid != BTRFS_I(inode)->root->objectid)
 		return -EPERM;
diff --git a/fs/compat.c b/fs/compat.c
index 691c3fd8ce1..c6d31a3bab8 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -262,35 +262,19 @@ static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs *
  */
 asmlinkage long compat_sys_statfs(const char __user *pathname, struct compat_statfs __user *buf)
 {
-	struct path path;
-	int error;
-
-	error = user_path(pathname, &path);
-	if (!error) {
-		struct kstatfs tmp;
-		error = vfs_statfs(&path, &tmp);
-		if (!error)
-			error = put_compat_statfs(buf, &tmp);
-		path_put(&path);
-	}
+	struct kstatfs tmp;
+	int error = user_statfs(pathname, &tmp);
+	if (!error)
+		error = put_compat_statfs(buf, &tmp);
 	return error;
 }
 
 asmlinkage long compat_sys_fstatfs(unsigned int fd, struct compat_statfs __user *buf)
 {
-	struct file * file;
 	struct kstatfs tmp;
-	int error;
-
-	error = -EBADF;
-	file = fget(fd);
-	if (!file)
-		goto out;
-	error = vfs_statfs(&file->f_path, &tmp);
+	int error = fd_statfs(fd, &tmp);
 	if (!error)
 		error = put_compat_statfs(buf, &tmp);
-	fput(file);
-out:
 	return error;
 }
 
@@ -329,41 +313,29 @@ static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstat
 
 asmlinkage long compat_sys_statfs64(const char __user *pathname, compat_size_t sz, struct compat_statfs64 __user *buf)
 {
-	struct path path;
+	struct kstatfs tmp;
 	int error;
 
 	if (sz != sizeof(*buf))
 		return -EINVAL;
 
-	error = user_path(pathname, &path);
-	if (!error) {
-		struct kstatfs tmp;
-		error = vfs_statfs(&path, &tmp);
-		if (!error)
-			error = put_compat_statfs64(buf, &tmp);
-		path_put(&path);
-	}
+	error = user_statfs(pathname, &tmp);
+	if (!error)
+		error = put_compat_statfs64(buf, &tmp);
 	return error;
 }
 
 asmlinkage long compat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user *buf)
 {
-	struct file * file;
 	struct kstatfs tmp;
 	int error;
 
 	if (sz != sizeof(*buf))
 		return -EINVAL;
 
-	error = -EBADF;
-	file = fget(fd);
-	if (!file)
-		goto out;
-	error = vfs_statfs(&file->f_path, &tmp);
+	error = fd_statfs(fd, &tmp);
 	if (!error)
 		error = put_compat_statfs64(buf, &tmp);
-	fput(file);
-out:
 	return error;
 }
 
@@ -2312,3 +2284,16 @@ asmlinkage long compat_sys_timerfd_gettime(int ufd,
 }
 
 #endif /* CONFIG_TIMERFD */
+
+#ifdef CONFIG_FHANDLE
+/*
+ * Exactly like fs/open.c:sys_open_by_handle_at(), except that it
+ * doesn't set the O_LARGEFILE flag.
+ */
+asmlinkage long
+compat_sys_open_by_handle_at(int mountdirfd,
+			     struct file_handle __user *handle, int flags)
+{
+	return do_handle_open(mountdirfd, handle, flags);
+}
+#endif
diff --git a/fs/exec.c b/fs/exec.c
index 52a447d9b6a..ba99e1abb1a 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -115,13 +115,16 @@ SYSCALL_DEFINE1(uselib, const char __user *, library)
 	struct file *file;
 	char *tmp = getname(library);
 	int error = PTR_ERR(tmp);
+	static const struct open_flags uselib_flags = {
+		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
+		.acc_mode = MAY_READ | MAY_EXEC | MAY_OPEN,
+		.intent = LOOKUP_OPEN
+	};
 
 	if (IS_ERR(tmp))
 		goto out;
 
-	file = do_filp_open(AT_FDCWD, tmp,
-				O_LARGEFILE | O_RDONLY | __FMODE_EXEC, 0,
-				MAY_READ | MAY_EXEC | MAY_OPEN);
+	file = do_filp_open(AT_FDCWD, tmp, &uselib_flags, LOOKUP_FOLLOW);
 	putname(tmp);
 	error = PTR_ERR(file);
 	if (IS_ERR(file))
@@ -721,10 +724,13 @@ struct file *open_exec(const char *name)
 {
 	struct file *file;
 	int err;
+	static const struct open_flags open_exec_flags = {
+		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
+		.acc_mode = MAY_EXEC | MAY_OPEN,
+		.intent = LOOKUP_OPEN
+	};
 
-	file = do_filp_open(AT_FDCWD, name,
-				O_LARGEFILE | O_RDONLY | __FMODE_EXEC, 0,
-				MAY_EXEC | MAY_OPEN);
+	file = do_filp_open(AT_FDCWD, name, &open_exec_flags, LOOKUP_FOLLOW);
 	if (IS_ERR(file))
 		goto out;
 
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 4b6825740dd..b05acb79613 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -320,9 +320,14 @@ static int export_encode_fh(struct dentry *dentry, struct fid *fid,
 	struct inode * inode = dentry->d_inode;
 	int len = *max_len;
 	int type = FILEID_INO32_GEN;
-	
-	if (len < 2 || (connectable && len < 4))
+
+	if (connectable && (len < 4)) {
+		*max_len = 4;
+		return 255;
+	} else if (len < 2) {
+		*max_len = 2;
 		return 255;
+	}
 
 	len = 2;
 	fid->i32.ino = inode->i_ino;
@@ -369,6 +374,8 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
 	/*
 	 * Try to get any dentry for the given file handle from the filesystem.
 	 */
+	if (!nop || !nop->fh_to_dentry)
+		return ERR_PTR(-ESTALE);
 	result = nop->fh_to_dentry(mnt->mnt_sb, fid, fh_len, fileid_type);
 	if (!result)
 		result = ERR_PTR(-ESTALE);
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index b27ba71810e..561f6925626 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -2253,13 +2253,6 @@ static int ext3_link (struct dentry * old_dentry,
 
 	dquot_initialize(dir);
 
-	/*
-	 * Return -ENOENT if we've raced with unlink and i_nlink is 0.  Doing
-	 * otherwise has the potential to corrupt the orphan inode list.
-	 */
-	if (inode->i_nlink == 0)
-		return -ENOENT;
-
 retry:
 	handle = ext3_journal_start(dir, EXT3_DATA_TRANS_BLOCKS(dir->i_sb) +
 					EXT3_INDEX_EXTRA_TRANS_BLOCKS);
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 85c8cc8f247..9cc19a1dea8 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -1936,6 +1936,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
 	sb->s_qcop = &ext3_qctl_operations;
 	sb->dq_op = &ext3_quota_operations;
 #endif
+	memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid));
 	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
 	mutex_init(&sbi->s_orphan_lock);
 	mutex_init(&sbi->s_resize_lock);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 5485390d32c..e781b7ea563 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2304,13 +2304,6 @@ static int ext4_link(struct dentry *old_dentry,
 
 	dquot_initialize(dir);
 
-	/*
-	 * Return -ENOENT if we've raced with unlink and i_nlink is 0.  Doing
-	 * otherwise has the potential to corrupt the orphan inode list.
-	 */
-	if (inode->i_nlink == 0)
-		return -ENOENT;
-
 retry:
 	handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
 					EXT4_INDEX_EXTRA_TRANS_BLOCKS);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index f6a318f836b..5977b356a43 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3415,6 +3415,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_qcop = &ext4_qctl_operations;
 	sb->dq_op = &ext4_quota_operations;
 #endif
+	memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid));
+
 	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
 	mutex_init(&sbi->s_orphan_lock);
 	mutex_init(&sbi->s_resize_lock);
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 86753fe10bd..0e277ec4b61 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -757,8 +757,10 @@ fat_encode_fh(struct dentry *de, __u32 *fh, int *lenp, int connectable)
 	struct inode *inode =  de->d_inode;
 	u32 ipos_h, ipos_m, ipos_l;
 
-	if (len < 5)
+	if (len < 5) {
+		*lenp = 5;
 		return 255; /* no room */
+	}
 
 	ipos_h = MSDOS_I(inode)->i_pos >> 8;
 	ipos_m = (MSDOS_I(inode)->i_pos & 0xf0) << 24;
diff --git a/fs/fcntl.c b/fs/fcntl.c
index cb1026181bd..6c82e5bac03 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -131,7 +131,7 @@ SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd)
 SYSCALL_DEFINE1(dup, unsigned int, fildes)
 {
 	int ret = -EBADF;
-	struct file *file = fget(fildes);
+	struct file *file = fget_raw(fildes);
 
 	if (file) {
 		ret = get_unused_fd();
@@ -426,15 +426,35 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 	return err;
 }
 
+static int check_fcntl_cmd(unsigned cmd)
+{
+	switch (cmd) {
+	case F_DUPFD:
+	case F_DUPFD_CLOEXEC:
+	case F_GETFD:
+	case F_SETFD:
+	case F_GETFL:
+		return 1;
+	}
+	return 0;
+}
+
 SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
 {	
 	struct file *filp;
 	long err = -EBADF;
 
-	filp = fget(fd);
+	filp = fget_raw(fd);
 	if (!filp)
 		goto out;
 
+	if (unlikely(filp->f_mode & FMODE_PATH)) {
+		if (!check_fcntl_cmd(cmd)) {
+			fput(filp);
+			goto out;
+		}
+	}
+
 	err = security_file_fcntl(filp, cmd, arg);
 	if (err) {
 		fput(filp);
@@ -456,10 +476,17 @@ SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
 	long err;
 
 	err = -EBADF;
-	filp = fget(fd);
+	filp = fget_raw(fd);
 	if (!filp)
 		goto out;
 
+	if (unlikely(filp->f_mode & FMODE_PATH)) {
+		if (!check_fcntl_cmd(cmd)) {
+			fput(filp);
+			goto out;
+		}
+	}
+
 	err = security_file_fcntl(filp, cmd, arg);
 	if (err) {
 		fput(filp);
@@ -808,14 +835,14 @@ static int __init fcntl_init(void)
 	 * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
 	 * is defined as O_NONBLOCK on some platforms and not on others.
 	 */
-	BUILD_BUG_ON(18 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
+	BUILD_BUG_ON(19 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
 		O_RDONLY	| O_WRONLY	| O_RDWR	|
 		O_CREAT		| O_EXCL	| O_NOCTTY	|
 		O_TRUNC		| O_APPEND	| /* O_NONBLOCK	| */
 		__O_SYNC	| O_DSYNC	| FASYNC	|
 		O_DIRECT	| O_LARGEFILE	| O_DIRECTORY	|
 		O_NOFOLLOW	| O_NOATIME	| O_CLOEXEC	|
-		__FMODE_EXEC
+		__FMODE_EXEC	| O_PATH
 		));
 
 	fasync_cache = kmem_cache_create("fasync_cache",
diff --git a/fs/fhandle.c b/fs/fhandle.c
new file mode 100644
index 00000000000..bf93ad2bee0
--- /dev/null
+++ b/fs/fhandle.c
@@ -0,0 +1,265 @@
+#include <linux/syscalls.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/exportfs.h>
+#include <linux/fs_struct.h>
+#include <linux/fsnotify.h>
+#include <asm/uaccess.h>
+#include "internal.h"
+
+static long do_sys_name_to_handle(struct path *path,
+				  struct file_handle __user *ufh,
+				  int __user *mnt_id)
+{
+	long retval;
+	struct file_handle f_handle;
+	int handle_dwords, handle_bytes;
+	struct file_handle *handle = NULL;
+
+	/*
+	 * We need t make sure wether the file system
+	 * support decoding of the file handle
+	 */
+	if (!path->mnt->mnt_sb->s_export_op ||
+	    !path->mnt->mnt_sb->s_export_op->fh_to_dentry)
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle)))
+		return -EFAULT;
+
+	if (f_handle.handle_bytes > MAX_HANDLE_SZ)
+		return -EINVAL;
+
+	handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes,
+			 GFP_KERNEL);
+	if (!handle)
+		return -ENOMEM;
+
+	/* convert handle size to  multiple of sizeof(u32) */
+	handle_dwords = f_handle.handle_bytes >> 2;
+
+	/* we ask for a non connected handle */
+	retval = exportfs_encode_fh(path->dentry,
+				    (struct fid *)handle->f_handle,
+				    &handle_dwords,  0);
+	handle->handle_type = retval;
+	/* convert handle size to bytes */
+	handle_bytes = handle_dwords * sizeof(u32);
+	handle->handle_bytes = handle_bytes;
+	if ((handle->handle_bytes > f_handle.handle_bytes) ||
+	    (retval == 255) || (retval == -ENOSPC)) {
+		/* As per old exportfs_encode_fh documentation
+		 * we could return ENOSPC to indicate overflow
+		 * But file system returned 255 always. So handle
+		 * both the values
+		 */
+		/*
+		 * set the handle size to zero so we copy only
+		 * non variable part of the file_handle
+		 */
+		handle_bytes = 0;
+		retval = -EOVERFLOW;
+	} else
+		retval = 0;
+	/* copy the mount id */
+	if (copy_to_user(mnt_id, &path->mnt->mnt_id, sizeof(*mnt_id)) ||
+	    copy_to_user(ufh, handle,
+			 sizeof(struct file_handle) + handle_bytes))
+		retval = -EFAULT;
+	kfree(handle);
+	return retval;
+}
+
+/**
+ * sys_name_to_handle_at: convert name to handle
+ * @dfd: directory relative to which name is interpreted if not absolute
+ * @name: name that should be converted to handle.
+ * @handle: resulting file handle
+ * @mnt_id: mount id of the file system containing the file
+ * @flag: flag value to indicate whether to follow symlink or not
+ *
+ * @handle->handle_size indicate the space available to store the
+ * variable part of the file handle in bytes. If there is not
+ * enough space, the field is updated to return the minimum
+ * value required.
+ */
+SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name,
+		struct file_handle __user *, handle, int __user *, mnt_id,
+		int, flag)
+{
+	struct path path;
+	int lookup_flags;
+	int err;
+
+	if ((flag & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0)
+		return -EINVAL;
+
+	lookup_flags = (flag & AT_SYMLINK_FOLLOW) ? LOOKUP_FOLLOW : 0;
+	if (flag & AT_EMPTY_PATH)
+		lookup_flags |= LOOKUP_EMPTY;
+	err = user_path_at(dfd, name, lookup_flags, &path);
+	if (!err) {
+		err = do_sys_name_to_handle(&path, handle, mnt_id);
+		path_put(&path);
+	}
+	return err;
+}
+
+static struct vfsmount *get_vfsmount_from_fd(int fd)
+{
+	struct path path;
+
+	if (fd == AT_FDCWD) {
+		struct fs_struct *fs = current->fs;
+		spin_lock(&fs->lock);
+		path = fs->pwd;
+		mntget(path.mnt);
+		spin_unlock(&fs->lock);
+	} else {
+		int fput_needed;
+		struct file *file = fget_light(fd, &fput_needed);
+		if (!file)
+			return ERR_PTR(-EBADF);
+		path = file->f_path;
+		mntget(path.mnt);
+		fput_light(file, fput_needed);
+	}
+	return path.mnt;
+}
+
+static int vfs_dentry_acceptable(void *context, struct dentry *dentry)
+{
+	return 1;
+}
+
+static int do_handle_to_path(int mountdirfd, struct file_handle *handle,
+			     struct path *path)
+{
+	int retval = 0;
+	int handle_dwords;
+
+	path->mnt = get_vfsmount_from_fd(mountdirfd);
+	if (IS_ERR(path->mnt)) {
+		retval = PTR_ERR(path->mnt);
+		goto out_err;
+	}
+	/* change the handle size to multiple of sizeof(u32) */
+	handle_dwords = handle->handle_bytes >> 2;
+	path->dentry = exportfs_decode_fh(path->mnt,
+					  (struct fid *)handle->f_handle,
+					  handle_dwords, handle->handle_type,
+					  vfs_dentry_acceptable, NULL);
+	if (IS_ERR(path->dentry)) {
+		retval = PTR_ERR(path->dentry);
+		goto out_mnt;
+	}
+	return 0;
+out_mnt:
+	mntput(path->mnt);
+out_err:
+	return retval;
+}
+
+static int handle_to_path(int mountdirfd, struct file_handle __user *ufh,
+		   struct path *path)
+{
+	int retval = 0;
+	struct file_handle f_handle;
+	struct file_handle *handle = NULL;
+
+	/*
+	 * With handle we don't look at the execute bit on the
+	 * the directory. Ideally we would like CAP_DAC_SEARCH.
+	 * But we don't have that
+	 */
+	if (!capable(CAP_DAC_READ_SEARCH)) {
+		retval = -EPERM;
+		goto out_err;
+	}
+	if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle))) {
+		retval = -EFAULT;
+		goto out_err;
+	}
+	if ((f_handle.handle_bytes > MAX_HANDLE_SZ) ||
+	    (f_handle.handle_bytes == 0)) {
+		retval = -EINVAL;
+		goto out_err;
+	}
+	handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes,
+			 GFP_KERNEL);
+	if (!handle) {
+		retval = -ENOMEM;
+		goto out_err;
+	}
+	/* copy the full handle */
+	if (copy_from_user(handle, ufh,
+			   sizeof(struct file_handle) +
+			   f_handle.handle_bytes)) {
+		retval = -EFAULT;
+		goto out_handle;
+	}
+
+	retval = do_handle_to_path(mountdirfd, handle, path);
+
+out_handle:
+	kfree(handle);
+out_err:
+	return retval;
+}
+
+long do_handle_open(int mountdirfd,
+		    struct file_handle __user *ufh, int open_flag)
+{
+	long retval = 0;
+	struct path path;
+	struct file *file;
+	int fd;
+
+	retval = handle_to_path(mountdirfd, ufh, &path);
+	if (retval)
+		return retval;
+
+	fd = get_unused_fd_flags(open_flag);
+	if (fd < 0) {
+		path_put(&path);
+		return fd;
+	}
+	file = file_open_root(path.dentry, path.mnt, "", open_flag);
+	if (IS_ERR(file)) {
+		put_unused_fd(fd);
+		retval =  PTR_ERR(file);
+	} else {
+		retval = fd;
+		fsnotify_open(file);
+		fd_install(fd, file);
+	}
+	path_put(&path);
+	return retval;
+}
+
+/**
+ * sys_open_by_handle_at: Open the file handle
+ * @mountdirfd: directory file descriptor
+ * @handle: file handle to be opened
+ * @flag: open flags.
+ *
+ * @mountdirfd indicate the directory file descriptor
+ * of the mount point. file handle is decoded relative
+ * to the vfsmount pointed by the @mountdirfd. @flags
+ * value is same as the open(2) flags.
+ */
+SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd,
+		struct file_handle __user *, handle,
+		int, flags)
+{
+	long ret;
+
+	if (force_o_largefile())
+		flags |= O_LARGEFILE;
+
+	ret = do_handle_open(mountdirfd, handle, flags);
+	return ret;
+}
diff --git a/fs/file_table.c b/fs/file_table.c
index eb36b6b17e2..74a9544ac77 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -276,11 +276,10 @@ struct file *fget(unsigned int fd)
 	rcu_read_lock();
 	file = fcheck_files(files, fd);
 	if (file) {
-		if (!atomic_long_inc_not_zero(&file->f_count)) {
-			/* File object ref couldn't be taken */
-			rcu_read_unlock();
-			return NULL;
-		}
+		/* File object ref couldn't be taken */
+		if (file->f_mode & FMODE_PATH ||
+		    !atomic_long_inc_not_zero(&file->f_count))
+			file = NULL;
 	}
 	rcu_read_unlock();
 
@@ -289,6 +288,25 @@ struct file *fget(unsigned int fd)
 
 EXPORT_SYMBOL(fget);
 
+struct file *fget_raw(unsigned int fd)
+{
+	struct file *file;
+	struct files_struct *files = current->files;
+
+	rcu_read_lock();
+	file = fcheck_files(files, fd);
+	if (file) {
+		/* File object ref couldn't be taken */
+		if (!atomic_long_inc_not_zero(&file->f_count))
+			file = NULL;
+	}
+	rcu_read_unlock();
+
+	return file;
+}
+
+EXPORT_SYMBOL(fget_raw);
+
 /*
  * Lightweight file lookup - no refcnt increment if fd table isn't shared.
  *
@@ -313,6 +331,33 @@ struct file *fget_light(unsigned int fd, int *fput_needed)
 	*fput_needed = 0;
 	if (atomic_read(&files->count) == 1) {
 		file = fcheck_files(files, fd);
+		if (file && (file->f_mode & FMODE_PATH))
+			file = NULL;
+	} else {
+		rcu_read_lock();
+		file = fcheck_files(files, fd);
+		if (file) {
+			if (!(file->f_mode & FMODE_PATH) &&
+			    atomic_long_inc_not_zero(&file->f_count))
+				*fput_needed = 1;
+			else
+				/* Didn't get the reference, someone's freed */
+				file = NULL;
+		}
+		rcu_read_unlock();
+	}
+
+	return file;
+}
+
+struct file *fget_raw_light(unsigned int fd, int *fput_needed)
+{
+	struct file *file;
+	struct files_struct *files = current->files;
+
+	*fput_needed = 0;
+	if (atomic_read(&files->count) == 1) {
+		file = fcheck_files(files, fd);
 	} else {
 		rcu_read_lock();
 		file = fcheck_files(files, fd);
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 9e3f68cc1bd..051b1a08452 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -637,8 +637,10 @@ static int fuse_encode_fh(struct dentry *dentry, u32 *fh, int *max_len,
 	u64 nodeid;
 	u32 generation;
 
-	if (*max_len < len)
+	if (*max_len < len) {
+		*max_len = len;
 		return  255;
+	}
 
 	nodeid = get_fuse_inode(inode)->nodeid;
 	generation = inode->i_generation;
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index 9023db8184f..b5a5e60df0d 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -36,9 +36,13 @@ static int gfs2_encode_fh(struct dentry *dentry, __u32 *p, int *len,
 	struct super_block *sb = inode->i_sb;
 	struct gfs2_inode *ip = GFS2_I(inode);
 
-	if (*len < GFS2_SMALL_FH_SIZE ||
-	    (connectable && *len < GFS2_LARGE_FH_SIZE))
+	if (connectable && (*len < GFS2_LARGE_FH_SIZE)) {
+		*len = GFS2_LARGE_FH_SIZE;
 		return 255;
+	} else if (*len < GFS2_SMALL_FH_SIZE) {
+		*len = GFS2_SMALL_FH_SIZE;
+		return 255;
+	}
 
 	fh[0] = cpu_to_be32(ip->i_no_formal_ino >> 32);
 	fh[1] = cpu_to_be32(ip->i_no_formal_ino & 0xFFFFFFFF);
diff --git a/fs/internal.h b/fs/internal.h
index 9b976b57d7f..f3d15de44b1 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -106,6 +106,19 @@ extern void put_super(struct super_block *sb);
 struct nameidata;
 extern struct file *nameidata_to_filp(struct nameidata *);
 extern void release_open_intent(struct nameidata *);
+struct open_flags {
+	int open_flag;
+	int mode;
+	int acc_mode;
+	int intent;
+};
+extern struct file *do_filp_open(int dfd, const char *pathname,
+		const struct open_flags *op, int lookup_flags);
+extern struct file *do_file_open_root(struct dentry *, struct vfsmount *,
+		const char *, const struct open_flags *, int lookup_flags);
+
+extern long do_handle_open(int mountdirfd,
+			   struct file_handle __user *ufh, int open_flag);
 
 /*
  * inode.c
diff --git a/fs/isofs/export.c b/fs/isofs/export.c
index ed752cb3847..dd4687ff30d 100644
--- a/fs/isofs/export.c
+++ b/fs/isofs/export.c
@@ -124,9 +124,13 @@ isofs_export_encode_fh(struct dentry *dentry,
 	 * offset of the inode and the upper 16 bits of fh32[1] to
 	 * hold the offset of the parent.
 	 */
-
-	if (len < 3 || (connectable && len < 5))
+	if (connectable && (len < 5)) {
+		*max_len = 5;
+		return 255;
+	} else if (len < 3) {
+		*max_len = 3;
 		return 255;
+	}
 
 	len = 3;
 	fh32[0] = ei->i_iget5_block;
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index 5a2b269428a..3f04a180493 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -809,9 +809,6 @@ static int jfs_link(struct dentry *old_dentry,
 	if (ip->i_nlink == JFS_LINK_MAX)
 		return -EMLINK;
 
-	if (ip->i_nlink == 0)
-		return -ENOENT;
-
 	dquot_initialize(dir);
 
 	tid = txBegin(ip->i_sb, 0);