1 files changed, 502 insertions, 605 deletions

diff --git a/fs/open.c b/fs/open.c
index 040cef72bc0..d6fd3acde13 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -8,10 +8,8 @@
 #include <linux/mm.h>
 #include <linux/file.h>
 #include <linux/fdtable.h>
-#include <linux/quotaops.h>
 #include <linux/fsnotify.h>
 #include <linux/module.h>
-#include <linux/slab.h>
 #include <linux/tty.h>
 #include <linux/namei.h>
 #include <linux/backing-dev.h>
@@ -19,8 +17,8 @@
 #include <linux/securebits.h>
 #include <linux/security.h>
 #include <linux/mount.h>
-#include <linux/vfs.h>
 #include <linux/fcntl.h>
+#include <linux/slab.h>
 #include <asm/uaccess.h>
 #include <linux/fs.h>
 #include <linux/personality.h>
@@ -31,174 +29,11 @@
 #include <linux/falloc.h>
 #include <linux/fs_struct.h>
 #include <linux/ima.h>
+#include <linux/dnotify.h>
+#include <linux/compat.h>
 
 #include "internal.h"
 
-int vfs_statfs(struct dentry *dentry, struct kstatfs *buf)
-{
-	int retval = -ENODEV;
-
-	if (dentry) {
-		retval = -ENOSYS;
-		if (dentry->d_sb->s_op->statfs) {
-			memset(buf, 0, sizeof(*buf));
-			retval = security_sb_statfs(dentry);
-			if (retval)
-				return retval;
-			retval = dentry->d_sb->s_op->statfs(dentry, buf);
-			if (retval == 0 && buf->f_frsize == 0)
-				buf->f_frsize = buf->f_bsize;
-		}
-	}
-	return retval;
-}
-
-EXPORT_SYMBOL(vfs_statfs);
-
-static int vfs_statfs_native(struct dentry *dentry, struct statfs *buf)
-{
-	struct kstatfs st;
-	int retval;
-
-	retval = vfs_statfs(dentry, &st);
-	if (retval)
-		return retval;
-
-	if (sizeof(*buf) == sizeof(st))
-		memcpy(buf, &st, sizeof(st));
-	else {
-		if (sizeof buf->f_blocks == 4) {
-			if ((st.f_blocks | st.f_bfree | st.f_bavail |
-			     st.f_bsize | st.f_frsize) &
-			    0xffffffff00000000ULL)
-				return -EOVERFLOW;
-			/*
-			 * f_files and f_ffree may be -1; it's okay to stuff
-			 * that into 32 bits
-			 */
-			if (st.f_files != -1 &&
-			    (st.f_files & 0xffffffff00000000ULL))
-				return -EOVERFLOW;
-			if (st.f_ffree != -1 &&
-			    (st.f_ffree & 0xffffffff00000000ULL))
-				return -EOVERFLOW;
-		}
-
-		buf->f_type = st.f_type;
-		buf->f_bsize = st.f_bsize;
-		buf->f_blocks = st.f_blocks;
-		buf->f_bfree = st.f_bfree;
-		buf->f_bavail = st.f_bavail;
-		buf->f_files = st.f_files;
-		buf->f_ffree = st.f_ffree;
-		buf->f_fsid = st.f_fsid;
-		buf->f_namelen = st.f_namelen;
-		buf->f_frsize = st.f_frsize;
-		memset(buf->f_spare, 0, sizeof(buf->f_spare));
-	}
-	return 0;
-}
-
-static int vfs_statfs64(struct dentry *dentry, struct statfs64 *buf)
-{
-	struct kstatfs st;
-	int retval;
-
-	retval = vfs_statfs(dentry, &st);
-	if (retval)
-		return retval;
-
-	if (sizeof(*buf) == sizeof(st))
-		memcpy(buf, &st, sizeof(st));
-	else {
-		buf->f_type = st.f_type;
-		buf->f_bsize = st.f_bsize;
-		buf->f_blocks = st.f_blocks;
-		buf->f_bfree = st.f_bfree;
-		buf->f_bavail = st.f_bavail;
-		buf->f_files = st.f_files;
-		buf->f_ffree = st.f_ffree;
-		buf->f_fsid = st.f_fsid;
-		buf->f_namelen = st.f_namelen;
-		buf->f_frsize = st.f_frsize;
-		memset(buf->f_spare, 0, sizeof(buf->f_spare));
-	}
-	return 0;
-}
-
-SYSCALL_DEFINE2(statfs, const char __user *, pathname, struct statfs __user *, buf)
-{
-	struct path path;
-	int error;
-
-	error = user_path(pathname, &path);
-	if (!error) {
-		struct statfs tmp;
-		error = vfs_statfs_native(path.dentry, &tmp);
-		if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
-			error = -EFAULT;
-		path_put(&path);
-	}
-	return error;
-}
-
-SYSCALL_DEFINE3(statfs64, const char __user *, pathname, size_t, sz, struct statfs64 __user *, buf)
-{
-	struct path path;
-	long error;
-
-	if (sz != sizeof(*buf))
-		return -EINVAL;
-	error = user_path(pathname, &path);
-	if (!error) {
-		struct statfs64 tmp;
-		error = vfs_statfs64(path.dentry, &tmp);
-		if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
-			error = -EFAULT;
-		path_put(&path);
-	}
-	return error;
-}
-
-SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct statfs __user *, buf)
-{
-	struct file * file;
-	struct statfs tmp;
-	int error;
-
-	error = -EBADF;
-	file = fget(fd);
-	if (!file)
-		goto out;
-	error = vfs_statfs_native(file->f_path.dentry, &tmp);
-	if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
-		error = -EFAULT;
-	fput(file);
-out:
-	return error;
-}
-
-SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, size_t, sz, struct statfs64 __user *, buf)
-{
-	struct file * file;
-	struct statfs64 tmp;
-	int error;
-
-	if (sz != sizeof(*buf))
-		return -EINVAL;
-
-	error = -EBADF;
-	file = fget(fd);
-	if (!file)
-		goto out;
-	error = vfs_statfs64(file->f_path.dentry, &tmp);
-	if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
-		error = -EFAULT;
-	fput(file);
-out:
-	return error;
-}
-
 int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
 	struct file *filp)
 {
@@ -222,38 +57,28 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
 		newattrs.ia_valid |= ret | ATTR_FORCE;
 
 	mutex_lock(&dentry->d_inode->i_mutex);
-	ret = notify_change(dentry, &newattrs);
+	/* Note any delegations or leases have already been broken: */
+	ret = notify_change(dentry, &newattrs, NULL);
 	mutex_unlock(&dentry->d_inode->i_mutex);
 	return ret;
 }
 
-static long do_sys_truncate(const char __user *pathname, loff_t length)
+long vfs_truncate(struct path *path, loff_t length)
 {
-	struct path path;
 	struct inode *inode;
-	int error;
-
-	error = -EINVAL;
-	if (length < 0)	/* sorry, but loff_t says... */
-		goto out;
+	long error;
 
-	error = user_path(pathname, &path);
-	if (error)
-		goto out;
-	inode = path.dentry->d_inode;
+	inode = path->dentry->d_inode;
 
 	/* For directories it's -EISDIR, for other non-regulars - -EINVAL */
-	error = -EISDIR;
 	if (S_ISDIR(inode->i_mode))
-		goto dput_and_out;
-
-	error = -EINVAL;
+		return -EISDIR;
 	if (!S_ISREG(inode->i_mode))
-		goto dput_and_out;
+		return -EINVAL;
 
-	error = mnt_want_write(path.mnt);
+	error = mnt_want_write(path->mnt);
 	if (error)
-		goto dput_and_out;
+		goto out;
 
 	error = inode_permission(inode, MAY_WRITE);
 	if (error)
@@ -271,56 +96,82 @@ static long do_sys_truncate(const char __user *pathname, loff_t length)
 	 * Make sure that there are no leases.  get_write_access() protects
 	 * against the truncate racing with a lease-granting setlease().
 	 */
-	error = break_lease(inode, FMODE_WRITE);
+	error = break_lease(inode, O_WRONLY);
 	if (error)
 		goto put_write_and_out;
 
 	error = locks_verify_truncate(inode, NULL, length);
 	if (!error)
-		error = security_path_truncate(&path, length, 0);
-	if (!error) {
-		vfs_dq_init(inode);
-		error = do_truncate(path.dentry, length, 0, NULL);
-	}
+		error = security_path_truncate(path);
+	if (!error)
+		error = do_truncate(path->dentry, length, 0, NULL);
 
 put_write_and_out:
 	put_write_access(inode);
 mnt_drop_write_and_out:
-	mnt_drop_write(path.mnt);
-dput_and_out:
-	path_put(&path);
+	mnt_drop_write(path->mnt);
 out:
 	return error;
 }
+EXPORT_SYMBOL_GPL(vfs_truncate);
+
+static long do_sys_truncate(const char __user *pathname, loff_t length)
+{
+	unsigned int lookup_flags = LOOKUP_FOLLOW;
+	struct path path;
+	int error;
+
+	if (length < 0)	/* sorry, but loff_t says... */
+		return -EINVAL;
+
+retry:
+	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
+	if (!error) {
+		error = vfs_truncate(&path, length);
+		path_put(&path);
+	}
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
+	return error;
+}
 
 SYSCALL_DEFINE2(truncate, const char __user *, path, long, length)
 {
 	return do_sys_truncate(path, length);
 }
 
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE2(truncate, const char __user *, path, compat_off_t, length)
+{
+	return do_sys_truncate(path, length);
+}
+#endif
+
 static long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
 {
-	struct inode * inode;
+	struct inode *inode;
 	struct dentry *dentry;
-	struct file * file;
+	struct fd f;
 	int error;
 
 	error = -EINVAL;
 	if (length < 0)
 		goto out;
 	error = -EBADF;
-	file = fget(fd);
-	if (!file)
+	f = fdget(fd);
+	if (!f.file)
 		goto out;
 
 	/* explicitly opened as large or we are on 64-bit box */
-	if (file->f_flags & O_LARGEFILE)
+	if (f.file->f_flags & O_LARGEFILE)
 		small = 0;
 
-	dentry = file->f_path.dentry;
+	dentry = f.file->f_path.dentry;
 	inode = dentry->d_inode;
 	error = -EINVAL;
-	if (!S_ISREG(inode->i_mode) || !(file->f_mode & FMODE_WRITE))
+	if (!S_ISREG(inode->i_mode) || !(f.file->f_mode & FMODE_WRITE))
 		goto out_putf;
 
 	error = -EINVAL;
@@ -332,71 +183,91 @@ static long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
 	if (IS_APPEND(inode))
 		goto out_putf;
 
-	error = locks_verify_truncate(inode, file, length);
+	sb_start_write(inode->i_sb);
+	error = locks_verify_truncate(inode, f.file, length);
 	if (!error)
-		error = security_path_truncate(&file->f_path, length,
-					       ATTR_MTIME|ATTR_CTIME);
+		error = security_path_truncate(&f.file->f_path);
 	if (!error)
-		error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, file);
+		error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, f.file);
+	sb_end_write(inode->i_sb);
 out_putf:
-	fput(file);
+	fdput(f);
 out:
 	return error;
 }
 
 SYSCALL_DEFINE2(ftruncate, unsigned int, fd, unsigned long, length)
 {
-	long ret = do_sys_ftruncate(fd, length, 1);
-	/* avoid REGPARM breakage on x86: */
-	asmlinkage_protect(2, ret, fd, length);
-	return ret;
+	return do_sys_ftruncate(fd, length, 1);
 }
 
-/* LFS versions of truncate are only needed on 32 bit machines */
-#if BITS_PER_LONG == 32
-SYSCALL_DEFINE(truncate64)(const char __user * path, loff_t length)
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE2(ftruncate, unsigned int, fd, compat_ulong_t, length)
 {
-	return do_sys_truncate(path, length);
+	return do_sys_ftruncate(fd, length, 1);
 }
-#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
-asmlinkage long SyS_truncate64(long path, loff_t length)
-{
-	return SYSC_truncate64((const char __user *) path, length);
-}
-SYSCALL_ALIAS(sys_truncate64, SyS_truncate64);
 #endif
 
-SYSCALL_DEFINE(ftruncate64)(unsigned int fd, loff_t length)
+/* LFS versions of truncate are only needed on 32 bit machines */
+#if BITS_PER_LONG == 32
+SYSCALL_DEFINE2(truncate64, const char __user *, path, loff_t, length)
 {
-	long ret = do_sys_ftruncate(fd, length, 0);
-	/* avoid REGPARM breakage on x86: */
-	asmlinkage_protect(2, ret, fd, length);
-	return ret;
+	return do_sys_truncate(path, length);
 }
-#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
-asmlinkage long SyS_ftruncate64(long fd, loff_t length)
+
+SYSCALL_DEFINE2(ftruncate64, unsigned int, fd, loff_t, length)
 {
-	return SYSC_ftruncate64((unsigned int) fd, length);
+	return do_sys_ftruncate(fd, length, 0);
 }
-SYSCALL_ALIAS(sys_ftruncate64, SyS_ftruncate64);
-#endif
 #endif /* BITS_PER_LONG == 32 */
 
 
 int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 {
-	struct inode *inode = file->f_path.dentry->d_inode;
+	struct inode *inode = file_inode(file);
 	long ret;
 
 	if (offset < 0 || len <= 0)
 		return -EINVAL;
 
 	/* Return error if mode is not supported */
-	if (mode && !(mode & FALLOC_FL_KEEP_SIZE))
+	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
+		     FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE))
+		return -EOPNOTSUPP;
+
+	/* Punch hole and zero range are mutually exclusive */
+	if ((mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) ==
+	    (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE))
+		return -EOPNOTSUPP;
+
+	/* Punch hole must have keep size set */
+	if ((mode & FALLOC_FL_PUNCH_HOLE) &&
+	    !(mode & FALLOC_FL_KEEP_SIZE))
 		return -EOPNOTSUPP;
 
+	/* Collapse range should only be used exclusively. */
+	if ((mode & FALLOC_FL_COLLAPSE_RANGE) &&
+	    (mode & ~FALLOC_FL_COLLAPSE_RANGE))
+		return -EINVAL;
+
 	if (!(file->f_mode & FMODE_WRITE))
 		return -EBADF;
+
+	/*
+	 * We can only allow pure fallocate on append only files
+	 */
+	if ((mode & ~FALLOC_FL_KEEP_SIZE) && IS_APPEND(inode))
+		return -EPERM;
+
+	if (IS_IMMUTABLE(inode))
+		return -EPERM;
+
+	/*
+	 * We cannot allow any fallocate operation on an active swapfile
+	 */
+	if (IS_SWAPFILE(inode))
+		return -ETXTBSY;
+
 	/*
 	 * Revalidate the write permissions, in case security policy has
 	 * changed since the files were opened.
@@ -419,34 +290,27 @@ int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0))
 		return -EFBIG;
 
-	if (!inode->i_op->fallocate)
+	if (!file->f_op->fallocate)
 		return -EOPNOTSUPP;
 
-	return inode->i_op->fallocate(inode, mode, offset, len);
+	sb_start_write(inode->i_sb);
+	ret = file->f_op->fallocate(file, mode, offset, len);
+	sb_end_write(inode->i_sb);
+	return ret;
 }
 
-SYSCALL_DEFINE(fallocate)(int fd, int mode, loff_t offset, loff_t len)
+SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len)
 {
-	struct file *file;
+	struct fd f = fdget(fd);
 	int error = -EBADF;
 
-	file = fget(fd);
-	if (file) {
-		error = do_fallocate(file, mode, offset, len);
-		fput(file);
+	if (f.file) {
+		error = do_fallocate(f.file, mode, offset, len);
+		fdput(f);
 	}
-
 	return error;
 }
 
-#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
-asmlinkage long SyS_fallocate(long fd, long mode, loff_t offset, loff_t len)
-{
-	return SYSC_fallocate((int)fd, (int)mode, offset, len);
-}
-SYSCALL_ALIAS(sys_fallocate, SyS_fallocate);
-#endif
-
 /*
  * access() needs to use the real uid/gid, not the effective uid/gid.
  * We do this by temporarily clearing all FS-related capabilities and
@@ -459,6 +323,7 @@ SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
 	struct path path;
 	struct inode *inode;
 	int res;
+	unsigned int lookup_flags = LOOKUP_FOLLOW;
 
 	if (mode & ~S_IRWXO)	/* where's F_OK, X_OK, W_OK, R_OK? */
 		return -EINVAL;
@@ -472,7 +337,8 @@ SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
 
 	if (!issecure(SECURE_NO_SETUID_FIXUP)) {
 		/* Clear the capabilities if we switch to a non-root user */
-		if (override_cred->uid)
+		kuid_t root_uid = make_kuid(override_cred->user_ns, 0);
+		if (!uid_eq(override_cred->uid, root_uid))
 			cap_clear(override_cred->cap_effective);
 		else
 			override_cred->cap_effective =
@@ -480,8 +346,8 @@ SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
 	}
 
 	old_cred = override_creds(override_cred);
-
-	res = user_path_at(dfd, filename, LOOKUP_FOLLOW, &path);
+retry:
+	res = user_path_at(dfd, filename, lookup_flags, &path);
 	if (res)
 		goto out;
 
@@ -516,6 +382,10 @@ SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
 
 out_path_release:
 	path_put(&path);
+	if (retry_estale(res, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
 out:
 	revert_creds(old_cred);
 	put_cred(override_cred);
@@ -531,12 +401,13 @@ SYSCALL_DEFINE1(chdir, const char __user *, filename)
 {
 	struct path path;
 	int error;
-
-	error = user_path_dir(filename, &path);
+	unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
+retry:
+	error = user_path_at(AT_FDCWD, filename, lookup_flags, &path);
 	if (error)
 		goto out;
 
-	error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_ACCESS);
+	error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR);
 	if (error)
 		goto dput_and_out;
 
@@ -544,32 +415,35 @@ SYSCALL_DEFINE1(chdir, const char __user *, filename)
 
 dput_and_out:
 	path_put(&path);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
 out:
 	return error;
 }
 
 SYSCALL_DEFINE1(fchdir, unsigned int, fd)
 {
-	struct file *file;
+	struct fd f = fdget_raw(fd);
 	struct inode *inode;
-	int error;
+	int error = -EBADF;
 
 	error = -EBADF;
-	file = fget(fd);
-	if (!file)
+	if (!f.file)
 		goto out;
 
-	inode = file->f_path.dentry->d_inode;
+	inode = file_inode(f.file);
 
 	error = -ENOTDIR;
 	if (!S_ISDIR(inode->i_mode))
 		goto out_putf;
 
-	error = inode_permission(inode, MAY_EXEC | MAY_ACCESS);
+	error = inode_permission(inode, MAY_EXEC | MAY_CHDIR);
 	if (!error)
-		set_fs_pwd(current->fs, &file->f_path);
+		set_fs_pwd(current->fs, &f.file->f_path);
 out_putf:
-	fput(file);
+	fdput(f);
 out:
 	return error;
 }
@@ -578,17 +452,18 @@ SYSCALL_DEFINE1(chroot, const char __user *, filename)
 {
 	struct path path;
 	int error;
-
-	error = user_path_dir(filename, &path);
+	unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
+retry:
+	error = user_path_at(AT_FDCWD, filename, lookup_flags, &path);
 	if (error)
 		goto out;
 
-	error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_ACCESS);
+	error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR);
 	if (error)
 		goto dput_and_out;
 
 	error = -EPERM;
-	if (!capable(CAP_SYS_CHROOT))
+	if (!ns_capable(current_user_ns(), CAP_SYS_CHROOT))
 		goto dput_and_out;
 	error = security_path_chroot(&path);
 	if (error)
@@ -598,82 +473,75 @@ SYSCALL_DEFINE1(chroot, const char __user *, filename)
 	error = 0;
 dput_and_out:
 	path_put(&path);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
 out:
 	return error;
 }
 
-SYSCALL_DEFINE2(fchmod, unsigned int, fd, mode_t, mode)
+static int chmod_common(struct path *path, umode_t mode)
 {
-	struct inode * inode;
-	struct dentry * dentry;
-	struct file * file;
-	int err = -EBADF;
+	struct inode *inode = path->dentry->d_inode;
+	struct inode *delegated_inode = NULL;
 	struct iattr newattrs;
+	int error;
 
-	file = fget(fd);
-	if (!file)
-		goto out;
-
-	dentry = file->f_path.dentry;
-	inode = dentry->d_inode;
-
-	audit_inode(NULL, dentry);
-
-	err = mnt_want_write_file(file);
-	if (err)
-		goto out_putf;
+	error = mnt_want_write(path->mnt);
+	if (error)
+		return error;
+retry_deleg:
 	mutex_lock(&inode->i_mutex);
-	err = security_path_chmod(dentry, file->f_vfsmnt, mode);
-	if (err)
+	error = security_path_chmod(path, mode);
+	if (error)
 		goto out_unlock;
-	if (mode == (mode_t) -1)
-		mode = inode->i_mode;
 	newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
 	newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
-	err = notify_change(dentry, &newattrs);
+	error = notify_change(path->dentry, &newattrs, &delegated_inode);
 out_unlock:
 	mutex_unlock(&inode->i_mutex);
-	mnt_drop_write(file->f_path.mnt);
-out_putf:
-	fput(file);
-out:
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
+	mnt_drop_write(path->mnt);
+	return error;
+}
+
+SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode)
+{
+	struct fd f = fdget(fd);
+	int err = -EBADF;
+
+	if (f.file) {
+		audit_inode(NULL, f.file->f_path.dentry, 0);
+		err = chmod_common(&f.file->f_path, mode);
+		fdput(f);
+	}
 	return err;
 }
 
-SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename, mode_t, mode)
+SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename, umode_t, mode)
 {
 	struct path path;
-	struct inode *inode;
 	int error;
-	struct iattr newattrs;
-
-	error = user_path_at(dfd, filename, LOOKUP_FOLLOW, &path);
-	if (error)
-		goto out;
-	inode = path.dentry->d_inode;
-
-	error = mnt_want_write(path.mnt);
-	if (error)
-		goto dput_and_out;
-	mutex_lock(&inode->i_mutex);
-	error = security_path_chmod(path.dentry, path.mnt, mode);
-	if (error)
-		goto out_unlock;
-	if (mode == (mode_t) -1)
-		mode = inode->i_mode;
-	newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
-	newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
-	error = notify_change(path.dentry, &newattrs);
-out_unlock:
-	mutex_unlock(&inode->i_mutex);
-	mnt_drop_write(path.mnt);
-dput_and_out:
-	path_put(&path);
-out:
+	unsigned int lookup_flags = LOOKUP_FOLLOW;
+retry:
+	error = user_path_at(dfd, filename, lookup_flags, &path);
+	if (!error) {
+		error = chmod_common(&path, mode);
+		path_put(&path);
+		if (retry_estale(error, lookup_flags)) {
+			lookup_flags |= LOOKUP_REVAL;
+			goto retry;
+		}
+	}
 	return error;
 }
 
-SYSCALL_DEFINE2(chmod, const char __user *, filename, mode_t, mode)
+SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode)
 {
 	return sys_fchmodat(AT_FDCWD, filename, mode);
 }
@@ -681,46 +549,42 @@ SYSCALL_DEFINE2(chmod, const char __user *, filename, mode_t, mode)
 static int chown_common(struct path *path, uid_t user, gid_t group)
 {
 	struct inode *inode = path->dentry->d_inode;
+	struct inode *delegated_inode = NULL;
 	int error;
 	struct iattr newattrs;
+	kuid_t uid;
+	kgid_t gid;
+
+	uid = make_kuid(current_user_ns(), user);
+	gid = make_kgid(current_user_ns(), group);
 
 	newattrs.ia_valid =  ATTR_CTIME;
 	if (user != (uid_t) -1) {
+		if (!uid_valid(uid))
+			return -EINVAL;
 		newattrs.ia_valid |= ATTR_UID;
-		newattrs.ia_uid = user;
+		newattrs.ia_uid = uid;
 	}
 	if (group != (gid_t) -1) {
+		if (!gid_valid(gid))
+			return -EINVAL;
 		newattrs.ia_valid |= ATTR_GID;
-		newattrs.ia_gid = group;
+		newattrs.ia_gid = gid;
 	}
 	if (!S_ISDIR(inode->i_mode))
 		newattrs.ia_valid |=
 			ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
+retry_deleg:
 	mutex_lock(&inode->i_mutex);
-	error = security_path_chown(path, user, group);
+	error = security_path_chown(path, uid, gid);
 	if (!error)
-		error = notify_change(path->dentry, &newattrs);
+		error = notify_change(path->dentry, &newattrs, &delegated_inode);
 	mutex_unlock(&inode->i_mutex);
-
-	return error;
-}
-
-SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group)
-{
-	struct path path;
-	int error;
-
-	error = user_path(filename, &path);
-	if (error)
-		goto out;
-	error = mnt_want_write(path.mnt);
-	if (error)
-		goto out_release;
-	error = chown_common(&path, user, group);
-	mnt_drop_write(path.mnt);
-out_release:
-	path_put(&path);
-out:
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
 	return error;
 }
 
@@ -729,13 +593,16 @@ SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user,
 {
 	struct path path;
 	int error = -EINVAL;
-	int follow;
+	int lookup_flags;
 
-	if ((flag & ~AT_SYMLINK_NOFOLLOW) != 0)
+	if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
 		goto out;
 
-	follow = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
-	error = user_path_at(dfd, filename, follow, &path);
+	lookup_flags = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
+	if (flag & AT_EMPTY_PATH)
+		lookup_flags |= LOOKUP_EMPTY;
+retry:
+	error = user_path_at(dfd, filename, lookup_flags, &path);
 	if (error)
 		goto out;
 	error = mnt_want_write(path.mnt);
@@ -745,229 +612,204 @@ SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user,
 	mnt_drop_write(path.mnt);
 out_release:
 	path_put(&path);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
 out:
 	return error;
 }
 
-SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group)
+SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group)
 {
-	struct path path;
-	int error;
+	return sys_fchownat(AT_FDCWD, filename, user, group, 0);
+}
 
-	error = user_lpath(filename, &path);
-	if (error)
-		goto out;
-	error = mnt_want_write(path.mnt);
-	if (error)
-		goto out_release;
-	error = chown_common(&path, user, group);
-	mnt_drop_write(path.mnt);
-out_release:
-	path_put(&path);
-out:
-	return error;
+SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group)
+{
+	return sys_fchownat(AT_FDCWD, filename, user, group,
+			    AT_SYMLINK_NOFOLLOW);
 }
 
 SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group)
 {
-	struct file * file;
+	struct fd f = fdget(fd);
 	int error = -EBADF;
-	struct dentry * dentry;
 
-	file = fget(fd);
-	if (!file)
+	if (!f.file)
 		goto out;
 
-	error = mnt_want_write_file(file);
+	error = mnt_want_write_file(f.file);
 	if (error)
 		goto out_fput;
-	dentry = file->f_path.dentry;
-	audit_inode(NULL, dentry);
-	error = chown_common(&file->f_path, user, group);
-	mnt_drop_write(file->f_path.mnt);
+	audit_inode(NULL, f.file->f_path.dentry, 0);
+	error = chown_common(&f.file->f_path, user, group);
+	mnt_drop_write_file(f.file);
 out_fput:
-	fput(file);
+	fdput(f);
 out:
 	return error;
 }
 
-/*
- * You have to be very careful that these write
- * counts get cleaned up in error cases and
- * upon __fput().  This should probably never
- * be called outside of __dentry_open().
- */
-static inline int __get_file_write_access(struct inode *inode,
-					  struct vfsmount *mnt)
+int open_check_o_direct(struct file *f)
 {
-	int error;
-	error = get_write_access(inode);
-	if (error)
-		return error;
-	/*
-	 * Do not take mount writer counts on
-	 * special files since no writes to
-	 * the mount itself will occur.
-	 */
-	if (!special_file(inode->i_mode)) {
-		/*
-		 * Balanced in __fput()
-		 */
-		error = mnt_want_write(mnt);
-		if (error)
-			put_write_access(inode);
+	/* NB: we're sure to have correct a_ops only after f_op->open */
+	if (f->f_flags & O_DIRECT) {
+		if (!f->f_mapping->a_ops ||
+		    ((!f->f_mapping->a_ops->direct_IO) &&
+		    (!f->f_mapping->a_ops->get_xip_mem))) {
+			return -EINVAL;
+		}
 	}
-	return error;
+	return 0;
 }
 
-static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
-					struct file *f,
-					int (*open)(struct inode *, struct file *),
-					const struct cred *cred)
+static int do_dentry_open(struct file *f,
+			  int (*open)(struct inode *, struct file *),
+			  const struct cred *cred)
 {
+	static const struct file_operations empty_fops = {};
 	struct inode *inode;
 	int error;
 
 	f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK |
 				FMODE_PREAD | FMODE_PWRITE;
-	inode = dentry->d_inode;
-	if (f->f_mode & FMODE_WRITE) {
-		error = __get_file_write_access(inode, mnt);
-		if (error)
+
+	path_get(&f->f_path);
+	inode = f->f_inode = f->f_path.dentry->d_inode;
+	f->f_mapping = inode->i_mapping;
+
+	if (unlikely(f->f_flags & O_PATH)) {
+		f->f_mode = FMODE_PATH;
+		f->f_op = &empty_fops;
+		return 0;
+	}
+
+	if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) {
+		error = get_write_access(inode);
+		if (unlikely(error))
 			goto cleanup_file;
-		if (!special_file(inode->i_mode))
-			file_take_write(f);
+		error = __mnt_want_write(f->f_path.mnt);
+		if (unlikely(error)) {
+			put_write_access(inode);
+			goto cleanup_file;
+		}
+		f->f_mode |= FMODE_WRITER;
 	}
 
-	f->f_mapping = inode->i_mapping;
-	f->f_path.dentry = dentry;
-	f->f_path.mnt = mnt;
-	f->f_pos = 0;
+	/* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */
+	if (S_ISREG(inode->i_mode))
+		f->f_mode |= FMODE_ATOMIC_POS;
+
 	f->f_op = fops_get(inode->i_fop);
-	file_move(f, &inode->i_sb->s_files);
+	if (unlikely(WARN_ON(!f->f_op))) {
+		error = -ENODEV;
+		goto cleanup_all;
+	}
+
+	error = security_file_open(f, cred);
+	if (error)
+		goto cleanup_all;
 
-	error = security_dentry_open(f, cred);
+	error = break_lease(inode, f->f_flags);
 	if (error)
 		goto cleanup_all;
 
-	if (!open && f->f_op)
+	if (!open)
 		open = f->f_op->open;
 	if (open) {
 		error = open(inode, f);
 		if (error)
 			goto cleanup_all;
 	}
-	ima_counts_get(f);
+	if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
+		i_readcount_inc(inode);
+	if ((f->f_mode & FMODE_READ) &&
+	     likely(f->f_op->read || f->f_op->aio_read || f->f_op->read_iter))
+		f->f_mode |= FMODE_CAN_READ;
+	if ((f->f_mode & FMODE_WRITE) &&
+	     likely(f->f_op->write || f->f_op->aio_write || f->f_op->write_iter))
+		f->f_mode |= FMODE_CAN_WRITE;
 
 	f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
 
 	file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
 
-	/* NB: we're sure to have correct a_ops only after f_op->open */
-	if (f->f_flags & O_DIRECT) {
-		if (!f->f_mapping->a_ops ||
-		    ((!f->f_mapping->a_ops->direct_IO) &&
-		    (!f->f_mapping->a_ops->get_xip_mem))) {
-			fput(f);
-			f = ERR_PTR(-EINVAL);
-		}
-	}
-
-	return f;
+	return 0;
 
 cleanup_all:
 	fops_put(f->f_op);
-	if (f->f_mode & FMODE_WRITE) {
+	if (f->f_mode & FMODE_WRITER) {
 		put_write_access(inode);
-		if (!special_file(inode->i_mode)) {
-			/*
-			 * We don't consider this a real
-			 * mnt_want/drop_write() pair
-			 * because it all happenend right
-			 * here, so just reset the state.
-			 */
-			file_reset_write(f);
-			mnt_drop_write(mnt);
-		}
+		__mnt_drop_write(f->f_path.mnt);
 	}
-	file_kill(f);
-	f->f_path.dentry = NULL;
-	f->f_path.mnt = NULL;
 cleanup_file:
-	put_filp(f);
-	dput(dentry);
-	mntput(mnt);
-	return ERR_PTR(error);
+	path_put(&f->f_path);
+	f->f_path.mnt = NULL;
+	f->f_path.dentry = NULL;
+	f->f_inode = NULL;
+	return error;
 }
 
 /**
- * lookup_instantiate_filp - instantiates the open intent filp
- * @nd: pointer to nameidata
+ * finish_open - finish opening a file
+ * @file: file pointer
  * @dentry: pointer to dentry
  * @open: open callback
+ * @opened: state of open
+ *
+ * This can be used to finish opening a file passed to i_op->atomic_open().
  *
- * Helper for filesystems that want to use lookup open intents and pass back
- * a fully instantiated struct file to the caller.
- * This function is meant to be called from within a filesystem's
- * lookup method.
- * Beware of calling it for non-regular files! Those ->open methods might block
- * (e.g. in fifo_open), leaving you with parent locked (and in case of fifo,
- * leading to a deadlock, as nobody can open that fifo anymore, because
- * another process to open fifo will block on locked parent when doing lookup).
- * Note that in case of error, nd->intent.open.file is destroyed, but the
- * path information remains valid.
  * If the open callback is set to NULL, then the standard f_op->open()
  * filesystem callback is substituted.
+ *
+ * NB: the dentry reference is _not_ consumed.  If, for example, the dentry is
+ * the return value of d_splice_alias(), then the caller needs to perform dput()
+ * on it after finish_open().
+ *
+ * On successful return @file is a fully instantiated open file.  After this, if
+ * an error occurs in ->atomic_open(), it needs to clean up with fput().
+ *
+ * Returns zero on success or -errno if the open failed.
  */
-struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry,
-		int (*open)(struct inode *, struct file *))
+int finish_open(struct file *file, struct dentry *dentry,
+		int (*open)(struct inode *, struct file *),
+		int *opened)
 {
-	const struct cred *cred = current_cred();
+	int error;
+	BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
 
-	if (IS_ERR(nd->intent.open.file))
-		goto out;
-	if (IS_ERR(dentry))
-		goto out_err;
-	nd->intent.open.file = __dentry_open(dget(dentry), mntget(nd->path.mnt),
-					     nd->intent.open.file,
-					     open, cred);
-out:
-	return nd->intent.open.file;
-out_err:
-	release_open_intent(nd);
-	nd->intent.open.file = (struct file *)dentry;
-	goto out;
+	file->f_path.dentry = dentry;
+	error = do_dentry_open(file, open, current_cred());
+	if (!error)
+		*opened |= FILE_OPENED;
+
+	return error;
 }
-EXPORT_SYMBOL_GPL(lookup_instantiate_filp);
+EXPORT_SYMBOL(finish_open);
 
 /**
- * nameidata_to_filp - convert a nameidata to an open filp.
- * @nd: pointer to nameidata
- * @flags: open flags
+ * finish_no_open - finish ->atomic_open() without opening the file
+ *
+ * @file: file pointer
+ * @dentry: dentry or NULL (as returned from ->lookup())
  *
- * Note that this function destroys the original nameidata
+ * This can be used to set the result of a successful lookup in ->atomic_open().
+ *
+ * NB: unlike finish_open() this function does consume the dentry reference and
+ * the caller need not dput() it.
+ *
+ * Returns "1" which must be the return value of ->atomic_open() after having
+ * called this function.
  */
-struct file *nameidata_to_filp(struct nameidata *nd)
+int finish_no_open(struct file *file, struct dentry *dentry)
 {
-	const struct cred *cred = current_cred();
-	struct file *filp;
-
-	/* Pick up the filp from the open intent */
-	filp = nd->intent.open.file;
-	/* Has the filesystem initialised the file for us? */
-	if (filp->f_path.dentry == NULL)
-		filp = __dentry_open(nd->path.dentry, nd->path.mnt, filp,
-				     NULL, cred);
-	else
-		path_put(&nd->path);
-	return filp;
+	file->f_path.dentry = dentry;
+	return 1;
 }
+EXPORT_SYMBOL(finish_no_open);
 
-/*
- * dentry_open() will have done dput(dentry) and mntput(mnt) if it returns an
- * error.
- */
-struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags,
+struct file *dentry_open(const struct path *path, int flags,
 			 const struct cred *cred)
 {
 	int error;
@@ -975,122 +817,193 @@ struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags,
 
 	validate_creds(cred);
 
-	/*
-	 * We must always pass in a valid mount pointer.   Historically
-	 * callers got away with not passing it, but we must enforce this at
-	 * the earliest possible point now to avoid strange problems deep in the
-	 * filesystem stack.
-	 */
-	if (!mnt) {
-		printk(KERN_WARNING "%s called with NULL vfsmount\n", __func__);
-		dump_stack();
-		return ERR_PTR(-EINVAL);
-	}
+	/* We must always pass in a valid mount pointer. */
+	BUG_ON(!path->mnt);
 
-	error = -ENFILE;
 	f = get_empty_filp();
-	if (f == NULL) {
-		dput(dentry);
-		mntput(mnt);
-		return ERR_PTR(error);
+	if (!IS_ERR(f)) {
+		f->f_flags = flags;
+		f->f_path = *path;
+		error = do_dentry_open(f, NULL, cred);
+		if (!error) {
+			/* from now on we need fput() to dispose of f */
+			error = open_check_o_direct(f);
+			if (error) {
+				fput(f);
+				f = ERR_PTR(error);
+			}
+		} else { 
+			put_filp(f);
+			f = ERR_PTR(error);
+		}
 	}
-
-	f->f_flags = flags;
-	return __dentry_open(dentry, mnt, f, NULL, cred);
+	return f;
 }
 EXPORT_SYMBOL(dentry_open);
 
-static void __put_unused_fd(struct files_struct *files, unsigned int fd)
+static inline int build_open_flags(int flags, umode_t mode, struct open_flags *op)
 {
-	struct fdtable *fdt = files_fdtable(files);
-	__FD_CLR(fd, fdt->open_fds);
-	if (fd < files->next_fd)
-		files->next_fd = fd;
+	int lookup_flags = 0;
+	int acc_mode;
+
+	if (flags & (O_CREAT | __O_TMPFILE))
+		op->mode = (mode & S_IALLUGO) | S_IFREG;
+	else
+		op->mode = 0;
+
+	/* Must never be set by userspace */
+	flags &= ~FMODE_NONOTIFY & ~O_CLOEXEC;
+
+	/*
+	 * O_SYNC is implemented as __O_SYNC|O_DSYNC.  As many places only
+	 * check for O_DSYNC if the need any syncing at all we enforce it's
+	 * always set instead of having to deal with possibly weird behaviour
+	 * for malicious applications setting only __O_SYNC.
+	 */
+	if (flags & __O_SYNC)
+		flags |= O_DSYNC;
+
+	if (flags & __O_TMPFILE) {
+		if ((flags & O_TMPFILE_MASK) != O_TMPFILE)
+			return -EINVAL;
+		acc_mode = MAY_OPEN | ACC_MODE(flags);
+		if (!(acc_mode & MAY_WRITE))
+			return -EINVAL;
+	} else if (flags & O_PATH) {
+		/*
+		 * If we have O_PATH in the open flag. Then we
+		 * cannot have anything other than the below set of flags
+		 */
+		flags &= O_DIRECTORY | O_NOFOLLOW | O_PATH;
+		acc_mode = 0;
+	} else {
+		acc_mode = MAY_OPEN | ACC_MODE(flags);
+	}
+
+	op->open_flag = flags;
+
+	/* O_TRUNC implies we need access checks for write permissions */
+	if (flags & O_TRUNC)
+		acc_mode |= MAY_WRITE;
+
+	/* Allow the LSM permission hook to distinguish append
+	   access from general write access. */
+	if (flags & O_APPEND)
+		acc_mode |= MAY_APPEND;
+
+	op->acc_mode = acc_mode;
+
+	op->intent = flags & O_PATH ? 0 : LOOKUP_OPEN;
+
+	if (flags & O_CREAT) {
+		op->intent |= LOOKUP_CREATE;
+		if (flags & O_EXCL)
+			op->intent |= LOOKUP_EXCL;
+	}
+
+	if (flags & O_DIRECTORY)
+		lookup_flags |= LOOKUP_DIRECTORY;
+	if (!(flags & O_NOFOLLOW))
+		lookup_flags |= LOOKUP_FOLLOW;
+	op->lookup_flags = lookup_flags;
+	return 0;
 }
 
-void put_unused_fd(unsigned int fd)
+/**
+ * file_open_name - open file and return file pointer
+ *
+ * @name:	struct filename containing path to open
+ * @flags:	open flags as per the open(2) second argument
+ * @mode:	mode for the new file if O_CREAT is set, else ignored
+ *
+ * This is the helper to open a file from kernelspace if you really
+ * have to.  But in generally you should not do this, so please move
+ * along, nothing to see here..
+ */
+struct file *file_open_name(struct filename *name, int flags, umode_t mode)
 {
-	struct files_struct *files = current->files;
-	spin_lock(&files->file_lock);
-	__put_unused_fd(files, fd);
-	spin_unlock(&files->file_lock);
+	struct open_flags op;
+	int err = build_open_flags(flags, mode, &op);
+	return err ? ERR_PTR(err) : do_filp_open(AT_FDCWD, name, &op);
 }
 
-EXPORT_SYMBOL(put_unused_fd);
-
-/*
- * Install a file pointer in the fd array.
+/**
+ * filp_open - open file and return file pointer
  *
- * The VFS is full of places where we drop the files lock between
- * setting the open_fds bitmap and installing the file in the file
- * array.  At any such point, we are vulnerable to a dup2() race
- * installing a file in the array before us.  We need to detect this and
- * fput() the struct file we are about to overwrite in this case.
+ * @filename:	path to open
+ * @flags:	open flags as per the open(2) second argument
+ * @mode:	mode for the new file if O_CREAT is set, else ignored
  *
- * It should never happen - if we allow dup2() do it, _really_ bad things
- * will follow.
+ * This is the helper to open a file from kernelspace if you really
+ * have to.  But in generally you should not do this, so please move
+ * along, nothing to see here..
  */
-
-void fd_install(unsigned int fd, struct file *file)
+struct file *filp_open(const char *filename, int flags, umode_t mode)
 {
-	struct files_struct *files = current->files;
-	struct fdtable *fdt;
-	spin_lock(&files->file_lock);
-	fdt = files_fdtable(files);
-	BUG_ON(fdt->fd[fd] != NULL);
-	rcu_assign_pointer(fdt->fd[fd], file);
-	spin_unlock(&files->file_lock);
+	struct filename name = {.name = filename};
+	return file_open_name(&name, flags, mode);
 }
+EXPORT_SYMBOL(filp_open);
 
-EXPORT_SYMBOL(fd_install);
+struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt,
+			    const char *filename, int flags)
+{
+	struct open_flags op;
+	int err = build_open_flags(flags, 0, &op);
+	if (err)
+		return ERR_PTR(err);
+	if (flags & O_CREAT)
+		return ERR_PTR(-EINVAL);
+	if (!filename && (flags & O_DIRECTORY))
+		if (!dentry->d_inode->i_op->lookup)
+			return ERR_PTR(-ENOTDIR);
+	return do_file_open_root(dentry, mnt, filename, &op);
+}
+EXPORT_SYMBOL(file_open_root);
 
-long do_sys_open(int dfd, const char __user *filename, int flags, int mode)
+long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
 {
-	char *tmp = getname(filename);
-	int fd = PTR_ERR(tmp);
-
-	if (!IS_ERR(tmp)) {
-		fd = get_unused_fd_flags(flags);
-		if (fd >= 0) {
-			struct file *f = do_filp_open(dfd, tmp, flags, mode, 0);
-			if (IS_ERR(f)) {
-				put_unused_fd(fd);
-				fd = PTR_ERR(f);
-			} else {
-				fsnotify_open(f->f_path.dentry);
-				fd_install(fd, f);
-			}
+	struct open_flags op;
+	int fd = build_open_flags(flags, mode, &op);
+	struct filename *tmp;
+
+	if (fd)
+		return fd;
+
+	tmp = getname(filename);
+	if (IS_ERR(tmp))
+		return PTR_ERR(tmp);
+
+	fd = get_unused_fd_flags(flags);
+	if (fd >= 0) {
+		struct file *f = do_filp_open(dfd, tmp, &op);
+		if (IS_ERR(f)) {
+			put_unused_fd(fd);
+			fd = PTR_ERR(f);
+		} else {
+			fsnotify_open(f);
+			fd_install(fd, f);
 		}
-		putname(tmp);
 	}
+	putname(tmp);
 	return fd;
 }
 
-SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, int, mode)
+SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode)
 {
-	long ret;
-
 	if (force_o_largefile())
 		flags |= O_LARGEFILE;
 
-	ret = do_sys_open(AT_FDCWD, filename, flags, mode);
-	/* avoid REGPARM breakage on x86: */
-	asmlinkage_protect(3, ret, filename, flags, mode);
-	return ret;
+	return do_sys_open(AT_FDCWD, filename, flags, mode);
 }
 
 SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags,
-		int, mode)
+		umode_t, mode)
 {
-	long ret;
-
 	if (force_o_largefile())
 		flags |= O_LARGEFILE;
 
-	ret = do_sys_open(dfd, filename, flags, mode);
-	/* avoid REGPARM breakage on x86: */
-	asmlinkage_protect(4, ret, dfd, filename, flags, mode);
-	return ret;
+	return do_sys_open(dfd, filename, flags, mode);
 }
 
 #ifndef __alpha__
@@ -1099,7 +1012,7 @@ SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags,
  * For backward compatibility?  Maybe this should be moved
  * into arch/i386 instead?
  */
-SYSCALL_DEFINE2(creat, const char __user *, pathname, int, mode)
+SYSCALL_DEFINE2(creat, const char __user *, pathname, umode_t, mode)
 {
 	return sys_open(pathname, O_CREAT | O_WRONLY | O_TRUNC, mode);
 }
@@ -1119,11 +1032,13 @@ int filp_close(struct file *filp, fl_owner_t id)
 		return 0;
 	}
 
-	if (filp->f_op && filp->f_op->flush)
+	if (filp->f_op->flush)
 		retval = filp->f_op->flush(filp, id);
 
-	dnotify_flush(filp, id);
-	locks_remove_posix(filp, id);
+	if (likely(!(filp->f_mode & FMODE_PATH))) {
+		dnotify_flush(filp, id);
+		locks_remove_posix(filp, id);
+	}
 	fput(filp);
 	return retval;
 }
@@ -1137,23 +1052,7 @@ EXPORT_SYMBOL(filp_close);
  */
 SYSCALL_DEFINE1(close, unsigned int, fd)
 {
-	struct file * filp;
-	struct files_struct *files = current->files;
-	struct fdtable *fdt;
-	int retval;
-
-	spin_lock(&files->file_lock);
-	fdt = files_fdtable(files);
-	if (fd >= fdt->max_fds)
-		goto out_unlock;
-	filp = fdt->fd[fd];
-	if (!filp)
-		goto out_unlock;
-	rcu_assign_pointer(fdt->fd[fd], NULL);
-	FD_CLR(fd, fdt->close_on_exec);
-	__put_unused_fd(files, fd);
-	spin_unlock(&files->file_lock);
-	retval = filp_close(filp, files);
+	int retval = __close_fd(current->files, fd);
 
 	/* can't restart close syscall because file table entry was cleared */
 	if (unlikely(retval == -ERESTARTSYS ||
@@ -1163,10 +1062,6 @@ SYSCALL_DEFINE1(close, unsigned int, fd)
 		retval = -EINTR;
 
 	return retval;
-
-out_unlock:
-	spin_unlock(&files->file_lock);
-	return -EBADF;
 }
 EXPORT_SYMBOL(sys_close);
 
@@ -1200,7 +1095,9 @@ EXPORT_SYMBOL(generic_file_open);
 
 /*
  * This is used by subsystems that don't want seekable
- * file descriptors
+ * file descriptors. The function is not supposed to ever fail, the only
+ * reason it returns an 'int' and not 'void' is so that it can be plugged
+ * directly into file_operations structure.
  */
 int nonseekable_open(struct inode *inode, struct file *filp)
 {