diff --git a/src/kernel/linux/v4.19/fs/namei.c b/src/kernel/linux/v4.19/fs/namei.c
new file mode 100644
index 0000000..484cf99
--- /dev/null
+++ b/src/kernel/linux/v4.19/fs/namei.c
@@ -0,0 +1,5028 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/fs/namei.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+/*
+ * Some corrections by tytso.
+ */
+
+/* [Feb 1997 T. Schoebel-Theuer] Complete rewrite of the pathname
+ * lookup logic.
+ */
+/* [Feb-Apr 2000, AV] Rewrite to the new namespace architecture.
+ */
+
+#include <linux/init.h>
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/namei.h>
+#include <linux/pagemap.h>
+#include <linux/fsnotify.h>
+#include <linux/personality.h>
+#include <linux/security.h>
+#include <linux/ima.h>
+#include <linux/syscalls.h>
+#include <linux/mount.h>
+#include <linux/audit.h>
+#include <linux/capability.h>
+#include <linux/file.h>
+#include <linux/fcntl.h>
+#include <linux/device_cgroup.h>
+#include <linux/fs_struct.h>
+#include <linux/posix_acl.h>
+#include <linux/hash.h>
+#include <linux/bitops.h>
+#include <linux/init_task.h>
+#include <linux/uaccess.h>
+#include <linux/build_bug.h>
+
+#include "internal.h"
+#include "mount.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/namei.h>
+
+/* [Feb-1997 T. Schoebel-Theuer]
+ * Fundamental changes in the pathname lookup mechanisms (namei)
+ * were necessary because of omirr.  The reason is that omirr needs
+ * to know the _real_ pathname, not the user-supplied one, in case
+ * of symlinks (and also when transname replacements occur).
+ *
+ * The new code replaces the old recursive symlink resolution with
+ * an iterative one (in case of non-nested symlink chains).  It does
+ * this with calls to <fs>_follow_link().
+ * As a side effect, dir_namei(), _namei() and follow_link() are now 
+ * replaced with a single function lookup_dentry() that can handle all 
+ * the special cases of the former code.
+ *
+ * With the new dcache, the pathname is stored at each inode, at least as
+ * long as the refcount of the inode is positive.  As a side effect, the
+ * size of the dcache depends on the inode cache and thus is dynamic.
+ *
+ * [29-Apr-1998 C. Scott Ananian] Updated above description of symlink
+ * resolution to correspond with current state of the code.
+ *
+ * Note that the symlink resolution is not *completely* iterative.
+ * There is still a significant amount of tail- and mid- recursion in
+ * the algorithm.  Also, note that <fs>_readlink() is not used in
+ * lookup_dentry(): lookup_dentry() on the result of <fs>_readlink()
+ * may return different results than <fs>_follow_link().  Many virtual
+ * filesystems (including /proc) exhibit this behavior.
+ */
+
+/* [24-Feb-97 T. Schoebel-Theuer] Side effects caused by new implementation:
+ * New symlink semantics: when open() is called with flags O_CREAT | O_EXCL
+ * and the name already exists in form of a symlink, try to create the new
+ * name indicated by the symlink. The old code always complained that the
+ * name already exists, due to not following the symlink even if its target
+ * is nonexistent.  The new semantics affects also mknod() and link() when
+ * the name is a symlink pointing to a non-existent name.
+ *
+ * I don't know which semantics is the right one, since I have no access
+ * to standards. But I found by trial that HP-UX 9.0 has the full "new"
+ * semantics implemented, while SunOS 4.1.1 and Solaris (SunOS 5.4) have the
+ * "old" one. Personally, I think the new semantics is much more logical.
+ * Note that "ln old new" where "new" is a symlink pointing to a non-existing
+ * file does succeed in both HP-UX and SunOs, but not in Solaris
+ * and in the old Linux semantics.
+ */
+
+/* [16-Dec-97 Kevin Buhr] For security reasons, we change some symlink
+ * semantics.  See the comments in "open_namei" and "do_link" below.
+ *
+ * [10-Sep-98 Alan Modra] Another symlink change.
+ */
+
+/* [Feb-Apr 2000 AV] Complete rewrite. Rules for symlinks:
+ *	inside the path - always follow.
+ *	in the last component in creation/removal/renaming - never follow.
+ *	if LOOKUP_FOLLOW passed - follow.
+ *	if the pathname has trailing slashes - follow.
+ *	otherwise - don't follow.
+ * (applied in that order).
+ *
+ * [Jun 2000 AV] Inconsistent behaviour of open() in case if flags==O_CREAT
+ * restored for 2.4. This is the last surviving part of old 4.2BSD bug.
+ * During the 2.4 we need to fix the userland stuff depending on it -
+ * hopefully we will be able to get rid of that wart in 2.5. So far only
+ * XEmacs seems to be relying on it...
+ */
+/*
+ * [Sep 2001 AV] Single-semaphore locking scheme (kudos to David Holland)
+ * implemented.  Let's see if raised priority of ->s_vfs_rename_mutex gives
+ * any extra contention...
+ */
+
+/* In order to reduce some races, while at the same time doing additional
+ * checking and hopefully speeding things up, we copy filenames to the
+ * kernel data space before using them..
+ *
+ * POSIX.1 2.4: an empty pathname is invalid (ENOENT).
+ * PATH_MAX includes the nul terminator --RR.
+ */
+
+#define EMBEDDED_NAME_MAX	(PATH_MAX - offsetof(struct filename, iname))
+
+struct filename *
+getname_flags(const char __user *filename, int flags, int *empty)
+{
+	struct filename *result;
+	char *kname;
+	int len;
+	BUILD_BUG_ON(offsetof(struct filename, iname) % sizeof(long) != 0);
+
+	result = audit_reusename(filename);
+	if (result)
+		return result;
+
+	result = __getname();
+	if (unlikely(!result))
+		return ERR_PTR(-ENOMEM);
+
+	/*
+	 * First, try to embed the struct filename inside the names_cache
+	 * allocation
+	 */
+	kname = (char *)result->iname;
+	result->name = kname;
+
+	len = strncpy_from_user(kname, filename, EMBEDDED_NAME_MAX);
+	if (unlikely(len < 0)) {
+		__putname(result);
+		return ERR_PTR(len);
+	}
+
+	/*
+	 * Uh-oh. We have a name that's approaching PATH_MAX. Allocate a
+	 * separate struct filename so we can dedicate the entire
+	 * names_cache allocation for the pathname, and re-do the copy from
+	 * userland.
+	 */
+	if (unlikely(len == EMBEDDED_NAME_MAX)) {
+		const size_t size = offsetof(struct filename, iname[1]);
+		kname = (char *)result;
+
+		/*
+		 * size is chosen that way we to guarantee that
+		 * result->iname[0] is within the same object and that
+		 * kname can't be equal to result->iname, no matter what.
+		 */
+		result = kzalloc(size, GFP_KERNEL);
+		if (unlikely(!result)) {
+			__putname(kname);
+			return ERR_PTR(-ENOMEM);
+		}
+		result->name = kname;
+		len = strncpy_from_user(kname, filename, PATH_MAX);
+		if (unlikely(len < 0)) {
+			__putname(kname);
+			kfree(result);
+			return ERR_PTR(len);
+		}
+		if (unlikely(len == PATH_MAX)) {
+			__putname(kname);
+			kfree(result);
+			return ERR_PTR(-ENAMETOOLONG);
+		}
+	}
+
+	result->refcnt = 1;
+	/* The empty path is special. */
+	if (unlikely(!len)) {
+		if (empty)
+			*empty = 1;
+		if (!(flags & LOOKUP_EMPTY)) {
+			putname(result);
+			return ERR_PTR(-ENOENT);
+		}
+	}
+
+	result->uptr = filename;
+	result->aname = NULL;
+	audit_getname(result);
+	return result;
+}
+
+struct filename *
+getname(const char __user * filename)
+{
+	return getname_flags(filename, 0, NULL);
+}
+
+struct filename *
+getname_kernel(const char * filename)
+{
+	struct filename *result;
+	int len = strlen(filename) + 1;
+
+	result = __getname();
+	if (unlikely(!result))
+		return ERR_PTR(-ENOMEM);
+
+	if (len <= EMBEDDED_NAME_MAX) {
+		result->name = (char *)result->iname;
+	} else if (len <= PATH_MAX) {
+		const size_t size = offsetof(struct filename, iname[1]);
+		struct filename *tmp;
+
+		tmp = kmalloc(size, GFP_KERNEL);
+		if (unlikely(!tmp)) {
+			__putname(result);
+			return ERR_PTR(-ENOMEM);
+		}
+		tmp->name = (char *)result;
+		result = tmp;
+	} else {
+		__putname(result);
+		return ERR_PTR(-ENAMETOOLONG);
+	}
+	memcpy((char *)result->name, filename, len);
+	result->uptr = NULL;
+	result->aname = NULL;
+	result->refcnt = 1;
+	audit_getname(result);
+
+	return result;
+}
+
+void putname(struct filename *name)
+{
+	BUG_ON(name->refcnt <= 0);
+
+	if (--name->refcnt > 0)
+		return;
+
+	if (name->name != name->iname) {
+		__putname(name->name);
+		kfree(name);
+	} else
+		__putname(name);
+}
+
+static int check_acl(struct inode *inode, int mask)
+{
+#ifdef CONFIG_FS_POSIX_ACL
+	struct posix_acl *acl;
+
+	if (mask & MAY_NOT_BLOCK) {
+		acl = get_cached_acl_rcu(inode, ACL_TYPE_ACCESS);
+	        if (!acl)
+	                return -EAGAIN;
+		/* no ->get_acl() calls in RCU mode... */
+		if (is_uncached_acl(acl))
+			return -ECHILD;
+	        return posix_acl_permission(inode, acl, mask & ~MAY_NOT_BLOCK);
+	}
+
+	acl = get_acl(inode, ACL_TYPE_ACCESS);
+	if (IS_ERR(acl))
+		return PTR_ERR(acl);
+	if (acl) {
+	        int error = posix_acl_permission(inode, acl, mask);
+	        posix_acl_release(acl);
+	        return error;
+	}
+#endif
+
+	return -EAGAIN;
+}
+
+/*
+ * This does the basic permission checking
+ */
+static int acl_permission_check(struct inode *inode, int mask)
+{
+	unsigned int mode = inode->i_mode;
+
+	if (likely(uid_eq(current_fsuid(), inode->i_uid)))
+		mode >>= 6;
+	else {
+		if (IS_POSIXACL(inode) && (mode & S_IRWXG)) {
+			int error = check_acl(inode, mask);
+			if (error != -EAGAIN)
+				return error;
+		}
+
+		if (in_group_p(inode->i_gid))
+			mode >>= 3;
+	}
+
+	/*
+	 * If the DACs are ok we don't need any capability check.
+	 */
+	if ((mask & ~mode & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0)
+		return 0;
+	return -EACCES;
+}
+
+/**
+ * generic_permission -  check for access rights on a Posix-like filesystem
+ * @inode:	inode to check access rights for
+ * @mask:	right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, ...)
+ *
+ * Used to check for read/write/execute permissions on a file.
+ * We use "fsuid" for this, letting us set arbitrary permissions
+ * for filesystem access without changing the "normal" uids which
+ * are used for other things.
+ *
+ * generic_permission is rcu-walk aware. It returns -ECHILD in case an rcu-walk
+ * request cannot be satisfied (eg. requires blocking or too much complexity).
+ * It would then be called again in ref-walk mode.
+ */
+int generic_permission(struct inode *inode, int mask)
+{
+	int ret;
+
+	/*
+	 * Do the basic permission checks.
+	 */
+	ret = acl_permission_check(inode, mask);
+	if (ret != -EACCES)
+		return ret;
+
+	if (S_ISDIR(inode->i_mode)) {
+		/* DACs are overridable for directories */
+		if (!(mask & MAY_WRITE))
+			if (capable_wrt_inode_uidgid(inode,
+						     CAP_DAC_READ_SEARCH))
+				return 0;
+		if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
+			return 0;
+		return -EACCES;
+	}
+
+	/*
+	 * Searching includes executable on directories, else just read.
+	 */
+	mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
+	if (mask == MAY_READ)
+		if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH))
+			return 0;
+	/*
+	 * Read/write DACs are always overridable.
+	 * Executable DACs are overridable when there is
+	 * at least one exec bit set.
+	 */
+	if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO))
+		if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
+			return 0;
+
+	return -EACCES;
+}
+EXPORT_SYMBOL(generic_permission);
+
+/*
+ * We _really_ want to just do "generic_permission()" without
+ * even looking at the inode->i_op values. So we keep a cache
+ * flag in inode->i_opflags, that says "this has not special
+ * permission function, use the fast case".
+ */
+static inline int do_inode_permission(struct vfsmount *mnt, struct inode *inode, int mask)
+{
+	if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) {
+		if (likely(mnt && inode->i_op->permission2))
+			return inode->i_op->permission2(mnt, inode, mask);
+		if (likely(inode->i_op->permission))
+			return inode->i_op->permission(inode, mask);
+
+		/* This gets set once for the inode lifetime */
+		spin_lock(&inode->i_lock);
+		inode->i_opflags |= IOP_FASTPERM;
+		spin_unlock(&inode->i_lock);
+	}
+	return generic_permission(inode, mask);
+}
+
+/**
+ * sb_permission - Check superblock-level permissions
+ * @sb: Superblock of inode to check permission on
+ * @inode: Inode to check permission on
+ * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
+ *
+ * Separate out file-system wide checks from inode-specific permission checks.
+ */
+static int sb_permission(struct super_block *sb, struct inode *inode, int mask)
+{
+	if (unlikely(mask & MAY_WRITE)) {
+		umode_t mode = inode->i_mode;
+
+		/* Nobody gets write access to a read-only fs. */
+		if (sb_rdonly(sb) && (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
+			return -EROFS;
+	}
+	return 0;
+}
+
+/**
+ * inode_permission2 - Check for access rights to a given inode
+ * @mnt:
+ * @inode: Inode to check permission on
+ * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
+ *
+ * Check for read/write/execute permissions on an inode.  We use fs[ug]id for
+ * this, letting us set arbitrary permissions for filesystem access without
+ * changing the "normal" UIDs which are used for other things.
+ *
+ * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask.
+ */
+int inode_permission2(struct vfsmount *mnt, struct inode *inode, int mask)
+{
+	int retval;
+
+	retval = sb_permission(inode->i_sb, inode, mask);
+	if (retval)
+		return retval;
+
+	if (unlikely(mask & MAY_WRITE)) {
+		/*
+		 * Nobody gets write access to an immutable file.
+		 */
+		if (IS_IMMUTABLE(inode))
+			return -EPERM;
+
+		/*
+		 * Updating mtime will likely cause i_uid and i_gid to be
+		 * written back improperly if their true value is unknown
+		 * to the vfs.
+		 */
+		if (HAS_UNMAPPED_ID(inode))
+			return -EACCES;
+	}
+
+	retval = do_inode_permission(mnt, inode, mask);
+	if (retval)
+		return retval;
+
+	retval = devcgroup_inode_permission(inode, mask);
+	if (retval)
+		return retval;
+
+	retval = security_inode_permission(inode, mask);
+	return retval;
+}
+EXPORT_SYMBOL(inode_permission2);
+
+int inode_permission(struct inode *inode, int mask)
+{
+	return inode_permission2(NULL, inode, mask);
+}
+EXPORT_SYMBOL(inode_permission);
+
+/**
+ * path_get - get a reference to a path
+ * @path: path to get the reference to
+ *
+ * Given a path increment the reference count to the dentry and the vfsmount.
+ */
+void path_get(const struct path *path)
+{
+	mntget(path->mnt);
+	dget(path->dentry);
+}
+EXPORT_SYMBOL(path_get);
+
+/**
+ * path_put - put a reference to a path
+ * @path: path to put the reference to
+ *
+ * Given a path decrement the reference count to the dentry and the vfsmount.
+ */
+void path_put(const struct path *path)
+{
+	dput(path->dentry);
+	mntput(path->mnt);
+}
+EXPORT_SYMBOL(path_put);
+
+#define EMBEDDED_LEVELS 2
+struct nameidata {
+	struct path	path;
+	struct qstr	last;
+	struct path	root;
+	struct inode	*inode; /* path.dentry.d_inode */
+	unsigned int	flags;
+	unsigned	seq, m_seq;
+	int		last_type;
+	unsigned	depth;
+	int		total_link_count;
+	struct saved {
+		struct path link;
+		struct delayed_call done;
+		const char *name;
+		unsigned seq;
+	} *stack, internal[EMBEDDED_LEVELS];
+	struct filename	*name;
+	struct nameidata *saved;
+	struct inode	*link_inode;
+	unsigned	root_seq;
+	int		dfd;
+} __randomize_layout;
+
+static void set_nameidata(struct nameidata *p, int dfd, struct filename *name)
+{
+	struct nameidata *old = current->nameidata;
+	p->stack = p->internal;
+	p->dfd = dfd;
+	p->name = name;
+	p->total_link_count = old ? old->total_link_count : 0;
+	p->saved = old;
+	current->nameidata = p;
+}
+
+static void restore_nameidata(void)
+{
+	struct nameidata *now = current->nameidata, *old = now->saved;
+
+	current->nameidata = old;
+	if (old)
+		old->total_link_count = now->total_link_count;
+	if (now->stack != now->internal)
+		kfree(now->stack);
+}
+
+static int __nd_alloc_stack(struct nameidata *nd)
+{
+	struct saved *p;
+
+	if (nd->flags & LOOKUP_RCU) {
+		p= kmalloc_array(MAXSYMLINKS, sizeof(struct saved),
+				  GFP_ATOMIC);
+		if (unlikely(!p))
+			return -ECHILD;
+	} else {
+		p= kmalloc_array(MAXSYMLINKS, sizeof(struct saved),
+				  GFP_KERNEL);
+		if (unlikely(!p))
+			return -ENOMEM;
+	}
+	memcpy(p, nd->internal, sizeof(nd->internal));
+	nd->stack = p;
+	return 0;
+}
+
+/**
+ * path_connected - Verify that a path->dentry is below path->mnt.mnt_root
+ * @path: nameidate to verify
+ *
+ * Rename can sometimes move a file or directory outside of a bind
+ * mount, path_connected allows those cases to be detected.
+ */
+static bool path_connected(const struct path *path)
+{
+	struct vfsmount *mnt = path->mnt;
+	struct super_block *sb = mnt->mnt_sb;
+
+	/* Bind mounts and multi-root filesystems can have disconnected paths */
+	if (!(sb->s_iflags & SB_I_MULTIROOT) && (mnt->mnt_root == sb->s_root))
+		return true;
+
+	return is_subdir(path->dentry, mnt->mnt_root);
+}
+
+static inline int nd_alloc_stack(struct nameidata *nd)
+{
+	if (likely(nd->depth != EMBEDDED_LEVELS))
+		return 0;
+	if (likely(nd->stack != nd->internal))
+		return 0;
+	return __nd_alloc_stack(nd);
+}
+
+static void drop_links(struct nameidata *nd)
+{
+	int i = nd->depth;
+	while (i--) {
+		struct saved *last = nd->stack + i;
+		do_delayed_call(&last->done);
+		clear_delayed_call(&last->done);
+	}
+}
+
+static void terminate_walk(struct nameidata *nd)
+{
+	drop_links(nd);
+	if (!(nd->flags & LOOKUP_RCU)) {
+		int i;
+		path_put(&nd->path);
+		for (i = 0; i < nd->depth; i++)
+			path_put(&nd->stack[i].link);
+		if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
+			path_put(&nd->root);
+			nd->root.mnt = NULL;
+		}
+	} else {
+		nd->flags &= ~LOOKUP_RCU;
+		if (!(nd->flags & LOOKUP_ROOT))
+			nd->root.mnt = NULL;
+		rcu_read_unlock();
+	}
+	nd->depth = 0;
+}
+
+/* path_put is needed afterwards regardless of success or failure */
+static bool legitimize_path(struct nameidata *nd,
+			    struct path *path, unsigned seq)
+{
+	int res = __legitimize_mnt(path->mnt, nd->m_seq);
+	if (unlikely(res)) {
+		if (res > 0)
+			path->mnt = NULL;
+		path->dentry = NULL;
+		return false;
+	}
+	if (unlikely(!lockref_get_not_dead(&path->dentry->d_lockref))) {
+		path->dentry = NULL;
+		return false;
+	}
+	return !read_seqcount_retry(&path->dentry->d_seq, seq);
+}
+
+static bool legitimize_links(struct nameidata *nd)
+{
+	int i;
+	for (i = 0; i < nd->depth; i++) {
+		struct saved *last = nd->stack + i;
+		if (unlikely(!legitimize_path(nd, &last->link, last->seq))) {
+			drop_links(nd);
+			nd->depth = i + 1;
+			return false;
+		}
+	}
+	return true;
+}
+
+/*
+ * Path walking has 2 modes, rcu-walk and ref-walk (see
+ * Documentation/filesystems/path-lookup.txt).  In situations when we can't
+ * continue in RCU mode, we attempt to drop out of rcu-walk mode and grab
+ * normal reference counts on dentries and vfsmounts to transition to ref-walk
+ * mode.  Refcounts are grabbed at the last known good point before rcu-walk
+ * got stuck, so ref-walk may continue from there. If this is not successful
+ * (eg. a seqcount has changed), then failure is returned and it's up to caller
+ * to restart the path walk from the beginning in ref-walk mode.
+ */
+
+/**
+ * unlazy_walk - try to switch to ref-walk mode.
+ * @nd: nameidata pathwalk data
+ * Returns: 0 on success, -ECHILD on failure
+ *
+ * unlazy_walk attempts to legitimize the current nd->path and nd->root
+ * for ref-walk mode.
+ * Must be called from rcu-walk context.
+ * Nothing should touch nameidata between unlazy_walk() failure and
+ * terminate_walk().
+ */
+static int unlazy_walk(struct nameidata *nd)
+{
+	struct dentry *parent = nd->path.dentry;
+
+	BUG_ON(!(nd->flags & LOOKUP_RCU));
+
+	nd->flags &= ~LOOKUP_RCU;
+	if (unlikely(!legitimize_links(nd)))
+		goto out2;
+	if (unlikely(!legitimize_path(nd, &nd->path, nd->seq)))
+		goto out1;
+	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
+		if (unlikely(!legitimize_path(nd, &nd->root, nd->root_seq)))
+			goto out;
+	}
+	rcu_read_unlock();
+	BUG_ON(nd->inode != parent->d_inode);
+	return 0;
+
+out2:
+	nd->path.mnt = NULL;
+	nd->path.dentry = NULL;
+out1:
+	if (!(nd->flags & LOOKUP_ROOT))
+		nd->root.mnt = NULL;
+out:
+	rcu_read_unlock();
+	return -ECHILD;
+}
+
+/**
+ * unlazy_child - try to switch to ref-walk mode.
+ * @nd: nameidata pathwalk data
+ * @dentry: child of nd->path.dentry
+ * @seq: seq number to check dentry against
+ * Returns: 0 on success, -ECHILD on failure
+ *
+ * unlazy_child attempts to legitimize the current nd->path, nd->root and dentry
+ * for ref-walk mode.  @dentry must be a path found by a do_lookup call on
+ * @nd.  Must be called from rcu-walk context.
+ * Nothing should touch nameidata between unlazy_child() failure and
+ * terminate_walk().
+ */
+static int unlazy_child(struct nameidata *nd, struct dentry *dentry, unsigned seq)
+{
+	BUG_ON(!(nd->flags & LOOKUP_RCU));
+
+	nd->flags &= ~LOOKUP_RCU;
+	if (unlikely(!legitimize_links(nd)))
+		goto out2;
+	if (unlikely(!legitimize_mnt(nd->path.mnt, nd->m_seq)))
+		goto out2;
+	if (unlikely(!lockref_get_not_dead(&nd->path.dentry->d_lockref)))
+		goto out1;
+
+	/*
+	 * We need to move both the parent and the dentry from the RCU domain
+	 * to be properly refcounted. And the sequence number in the dentry
+	 * validates *both* dentry counters, since we checked the sequence
+	 * number of the parent after we got the child sequence number. So we
+	 * know the parent must still be valid if the child sequence number is
+	 */
+	if (unlikely(!lockref_get_not_dead(&dentry->d_lockref)))
+		goto out;
+	if (unlikely(read_seqcount_retry(&dentry->d_seq, seq))) {
+		rcu_read_unlock();
+		dput(dentry);
+		goto drop_root_mnt;
+	}
+	/*
+	 * Sequence counts matched. Now make sure that the root is
+	 * still valid and get it if required.
+	 */
+	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
+		if (unlikely(!legitimize_path(nd, &nd->root, nd->root_seq))) {
+			rcu_read_unlock();
+			dput(dentry);
+			return -ECHILD;
+		}
+	}
+
+	rcu_read_unlock();
+	return 0;
+
+out2:
+	nd->path.mnt = NULL;
+out1:
+	nd->path.dentry = NULL;
+out:
+	rcu_read_unlock();
+drop_root_mnt:
+	if (!(nd->flags & LOOKUP_ROOT))
+		nd->root.mnt = NULL;
+	return -ECHILD;
+}
+
+static inline int d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE))
+		return dentry->d_op->d_revalidate(dentry, flags);
+	else
+		return 1;
+}
+
+#define INIT_PATH_SIZE 64
+
+static void success_walk_trace(struct nameidata *nd)
+{
+	struct path *pt = &nd->path;
+	struct inode *i = nd->inode;
+	char buf[INIT_PATH_SIZE], *try_buf;
+	int cur_path_size;
+	char *p;
+
+	/* When eBPF/ tracepoint is disabled, keep overhead low. */
+	if (!trace_inodepath_enabled())
+		return;
+
+	/* First try stack allocated buffer. */
+	try_buf = buf;
+	cur_path_size = INIT_PATH_SIZE;
+
+	while (cur_path_size <= PATH_MAX) {
+		/* Free previous heap allocation if we are now trying
+		 * a second or later heap allocation.
+		 */
+		if (try_buf != buf)
+			kfree(try_buf);
+
+		/* All but the first alloc are on the heap. */
+		if (cur_path_size != INIT_PATH_SIZE) {
+			try_buf = kmalloc(cur_path_size, GFP_KERNEL);
+			if (!try_buf) {
+				try_buf = buf;
+				sprintf(try_buf, "error:buf_alloc_failed");
+				break;
+			}
+		}
+
+		p = d_path(pt, try_buf, cur_path_size);
+
+		if (!IS_ERR(p)) {
+			char *end = mangle_path(try_buf, p, "\n");
+
+			if (end) {
+				try_buf[end - try_buf] = 0;
+				break;
+			} else {
+				/* On mangle errors, double path size
+				 * till PATH_MAX.
+				 */
+				cur_path_size = cur_path_size << 1;
+				continue;
+			}
+		}
+
+		if (PTR_ERR(p) == -ENAMETOOLONG) {
+			/* If d_path complains that name is too long,
+			 * then double path size till PATH_MAX.
+			 */
+			cur_path_size = cur_path_size << 1;
+			continue;
+		}
+
+		sprintf(try_buf, "error:d_path_failed_%lu",
+			-1 * PTR_ERR(p));
+		break;
+	}
+
+	if (cur_path_size > PATH_MAX)
+		sprintf(try_buf, "error:d_path_name_too_long");
+
+	trace_inodepath(i, try_buf);
+
+	if (try_buf != buf)
+		kfree(try_buf);
+	return;
+}
+
+/**
+ * complete_walk - successful completion of path walk
+ * @nd:  pointer nameidata
+ *
+ * If we had been in RCU mode, drop out of it and legitimize nd->path.
+ * Revalidate the final result, unless we'd already done that during
+ * the path walk or the filesystem doesn't ask for it.  Return 0 on
+ * success, -error on failure.  In case of failure caller does not
+ * need to drop nd->path.
+ */
+static int complete_walk(struct nameidata *nd)
+{
+	struct dentry *dentry = nd->path.dentry;
+	int status;
+
+	if (nd->flags & LOOKUP_RCU) {
+		if (!(nd->flags & LOOKUP_ROOT))
+			nd->root.mnt = NULL;
+		if (unlikely(unlazy_walk(nd)))
+			return -ECHILD;
+	}
+
+	if (likely(!(nd->flags & LOOKUP_JUMPED))) {
+		success_walk_trace(nd);
+		return 0;
+	}
+
+	if (likely(!(dentry->d_flags & DCACHE_OP_WEAK_REVALIDATE))) {
+		success_walk_trace(nd);
+		return 0;
+	}
+
+	status = dentry->d_op->d_weak_revalidate(dentry, nd->flags);
+	if (status > 0) {
+		success_walk_trace(nd);
+		return 0;
+	}
+
+	if (!status)
+		status = -ESTALE;
+
+	return status;
+}
+
+static void set_root(struct nameidata *nd)
+{
+	struct fs_struct *fs = current->fs;
+
+	if (nd->flags & LOOKUP_RCU) {
+		unsigned seq;
+
+		do {
+			seq = read_seqcount_begin(&fs->seq);
+			nd->root = fs->root;
+			nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq);
+		} while (read_seqcount_retry(&fs->seq, seq));
+	} else {
+		get_fs_root(fs, &nd->root);
+	}
+}
+
+static void path_put_conditional(struct path *path, struct nameidata *nd)
+{
+	dput(path->dentry);
+	if (path->mnt != nd->path.mnt)
+		mntput(path->mnt);
+}
+
+static inline void path_to_nameidata(const struct path *path,
+					struct nameidata *nd)
+{
+	if (!(nd->flags & LOOKUP_RCU)) {
+		dput(nd->path.dentry);
+		if (nd->path.mnt != path->mnt)
+			mntput(nd->path.mnt);
+	}
+	nd->path.mnt = path->mnt;
+	nd->path.dentry = path->dentry;
+}
+
+static int nd_jump_root(struct nameidata *nd)
+{
+	if (nd->flags & LOOKUP_RCU) {
+		struct dentry *d;
+		nd->path = nd->root;
+		d = nd->path.dentry;
+		nd->inode = d->d_inode;
+		nd->seq = nd->root_seq;
+		if (unlikely(read_seqcount_retry(&d->d_seq, nd->seq)))
+			return -ECHILD;
+	} else {
+		path_put(&nd->path);
+		nd->path = nd->root;
+		path_get(&nd->path);
+		nd->inode = nd->path.dentry->d_inode;
+	}
+	nd->flags |= LOOKUP_JUMPED;
+	return 0;
+}
+
+/*
+ * Helper to directly jump to a known parsed path from ->get_link,
+ * caller must have taken a reference to path beforehand.
+ */
+void nd_jump_link(struct path *path)
+{
+	struct nameidata *nd = current->nameidata;
+	path_put(&nd->path);
+
+	nd->path = *path;
+	nd->inode = nd->path.dentry->d_inode;
+	nd->flags |= LOOKUP_JUMPED;
+}
+
+static inline void put_link(struct nameidata *nd)
+{
+	struct saved *last = nd->stack + --nd->depth;
+	do_delayed_call(&last->done);
+	if (!(nd->flags & LOOKUP_RCU))
+		path_put(&last->link);
+}
+
+int sysctl_protected_symlinks __read_mostly = 0;
+int sysctl_protected_hardlinks __read_mostly = 0;
+int sysctl_protected_fifos __read_mostly;
+int sysctl_protected_regular __read_mostly;
+
+/**
+ * may_follow_link - Check symlink following for unsafe situations
+ * @nd: nameidata pathwalk data
+ *
+ * In the case of the sysctl_protected_symlinks sysctl being enabled,
+ * CAP_DAC_OVERRIDE needs to be specifically ignored if the symlink is
+ * in a sticky world-writable directory. This is to protect privileged
+ * processes from failing races against path names that may change out
+ * from under them by way of other users creating malicious symlinks.
+ * It will permit symlinks to be followed only when outside a sticky
+ * world-writable directory, or when the uid of the symlink and follower
+ * match, or when the directory owner matches the symlink's owner.
+ *
+ * Returns 0 if following the symlink is allowed, -ve on error.
+ */
+static inline int may_follow_link(struct nameidata *nd)
+{
+	const struct inode *inode;
+	const struct inode *parent;
+	kuid_t puid;
+
+	if (!sysctl_protected_symlinks)
+		return 0;
+
+	/* Allowed if owner and follower match. */
+	inode = nd->link_inode;
+	if (uid_eq(current_cred()->fsuid, inode->i_uid))
+		return 0;
+
+	/* Allowed if parent directory not sticky and world-writable. */
+	parent = nd->inode;
+	if ((parent->i_mode & (S_ISVTX|S_IWOTH)) != (S_ISVTX|S_IWOTH))
+		return 0;
+
+	/* Allowed if parent directory and link owner match. */
+	puid = parent->i_uid;
+	if (uid_valid(puid) && uid_eq(puid, inode->i_uid))
+		return 0;
+
+	if (nd->flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	audit_inode(nd->name, nd->stack[0].link.dentry, 0);
+	audit_log_link_denied("follow_link");
+	return -EACCES;
+}
+
+/**
+ * safe_hardlink_source - Check for safe hardlink conditions
+ * @inode: the source inode to hardlink from
+ *
+ * Return false if at least one of the following conditions:
+ *    - inode is not a regular file
+ *    - inode is setuid
+ *    - inode is setgid and group-exec
+ *    - access failure for read and write
+ *
+ * Otherwise returns true.
+ */
+static bool safe_hardlink_source(struct inode *inode)
+{
+	umode_t mode = inode->i_mode;
+
+	/* Special files should not get pinned to the filesystem. */
+	if (!S_ISREG(mode))
+		return false;
+
+	/* Setuid files should not get pinned to the filesystem. */
+	if (mode & S_ISUID)
+		return false;
+
+	/* Executable setgid files should not get pinned to the filesystem. */
+	if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP))
+		return false;
+
+	/* Hardlinking to unreadable or unwritable sources is dangerous. */
+	if (inode_permission(inode, MAY_READ | MAY_WRITE))
+		return false;
+
+	return true;
+}
+
+/**
+ * may_linkat - Check permissions for creating a hardlink
+ * @link: the source to hardlink from
+ *
+ * Block hardlink when all of:
+ *  - sysctl_protected_hardlinks enabled
+ *  - fsuid does not match inode
+ *  - hardlink source is unsafe (see safe_hardlink_source() above)
+ *  - not CAP_FOWNER in a namespace with the inode owner uid mapped
+ *
+ * Returns 0 if successful, -ve on error.
+ */
+static int may_linkat(struct path *link)
+{
+	struct inode *inode = link->dentry->d_inode;
+
+	/* Inode writeback is not safe when the uid or gid are invalid. */
+	if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid))
+		return -EOVERFLOW;
+
+	if (!sysctl_protected_hardlinks)
+		return 0;
+
+	/* Source inode owner (or CAP_FOWNER) can hardlink all they like,
+	 * otherwise, it must be a safe source.
+	 */
+	if (safe_hardlink_source(inode) || inode_owner_or_capable(inode))
+		return 0;
+
+	audit_log_link_denied("linkat");
+	return -EPERM;
+}
+
+/**
+ * may_create_in_sticky - Check whether an O_CREAT open in a sticky directory
+ *			  should be allowed, or not, on files that already
+ *			  exist.
+ * @dir_mode: mode bits of directory
+ * @dir_uid: owner of directory
+ * @inode: the inode of the file to open
+ *
+ * Block an O_CREAT open of a FIFO (or a regular file) when:
+ *   - sysctl_protected_fifos (or sysctl_protected_regular) is enabled
+ *   - the file already exists
+ *   - we are in a sticky directory
+ *   - we don't own the file
+ *   - the owner of the directory doesn't own the file
+ *   - the directory is world writable
+ * If the sysctl_protected_fifos (or sysctl_protected_regular) is set to 2
+ * the directory doesn't have to be world writable: being group writable will
+ * be enough.
+ *
+ * Returns 0 if the open is allowed, -ve on error.
+ */
+static int may_create_in_sticky(umode_t dir_mode, kuid_t dir_uid,
+				struct inode * const inode)
+{
+	if ((!sysctl_protected_fifos && S_ISFIFO(inode->i_mode)) ||
+	    (!sysctl_protected_regular && S_ISREG(inode->i_mode)) ||
+	    likely(!(dir_mode & S_ISVTX)) ||
+	    uid_eq(inode->i_uid, dir_uid) ||
+	    uid_eq(current_fsuid(), inode->i_uid))
+		return 0;
+
+	if (likely(dir_mode & 0002) ||
+	    (dir_mode & 0020 &&
+	     ((sysctl_protected_fifos >= 2 && S_ISFIFO(inode->i_mode)) ||
+	      (sysctl_protected_regular >= 2 && S_ISREG(inode->i_mode))))) {
+		return -EACCES;
+	}
+	return 0;
+}
+
+static __always_inline
+const char *get_link(struct nameidata *nd)
+{
+	struct saved *last = nd->stack + nd->depth - 1;
+	struct dentry *dentry = last->link.dentry;
+	struct inode *inode = nd->link_inode;
+	int error;
+	const char *res;
+
+	if (!(nd->flags & LOOKUP_RCU)) {
+		touch_atime(&last->link);
+		cond_resched();
+	} else if (atime_needs_update(&last->link, inode)) {
+		if (unlikely(unlazy_walk(nd)))
+			return ERR_PTR(-ECHILD);
+		touch_atime(&last->link);
+	}
+
+	error = security_inode_follow_link(dentry, inode,
+					   nd->flags & LOOKUP_RCU);
+	if (unlikely(error))
+		return ERR_PTR(error);
+
+	nd->last_type = LAST_BIND;
+	res = READ_ONCE(inode->i_link);
+	if (!res) {
+		const char * (*get)(struct dentry *, struct inode *,
+				struct delayed_call *);
+		get = inode->i_op->get_link;
+		if (nd->flags & LOOKUP_RCU) {
+			res = get(NULL, inode, &last->done);
+			if (res == ERR_PTR(-ECHILD)) {
+				if (unlikely(unlazy_walk(nd)))
+					return ERR_PTR(-ECHILD);
+				res = get(dentry, inode, &last->done);
+			}
+		} else {
+			res = get(dentry, inode, &last->done);
+		}
+		if (IS_ERR_OR_NULL(res))
+			return res;
+	}
+	if (*res == '/') {
+		if (!nd->root.mnt)
+			set_root(nd);
+		if (unlikely(nd_jump_root(nd)))
+			return ERR_PTR(-ECHILD);
+		while (unlikely(*++res == '/'))
+			;
+	}
+	if (!*res)
+		res = NULL;
+	return res;
+}
+
+/*
+ * follow_up - Find the mountpoint of path's vfsmount
+ *
+ * Given a path, find the mountpoint of its source file system.
+ * Replace @path with the path of the mountpoint in the parent mount.
+ * Up is towards /.
+ *
+ * Return 1 if we went up a level and 0 if we were already at the
+ * root.
+ */
+int follow_up(struct path *path)
+{
+	struct mount *mnt = real_mount(path->mnt);
+	struct mount *parent;
+	struct dentry *mountpoint;
+
+	read_seqlock_excl(&mount_lock);
+	parent = mnt->mnt_parent;
+	if (parent == mnt) {
+		read_sequnlock_excl(&mount_lock);
+		return 0;
+	}
+	mntget(&parent->mnt);
+	mountpoint = dget(mnt->mnt_mountpoint);
+	read_sequnlock_excl(&mount_lock);
+	dput(path->dentry);
+	path->dentry = mountpoint;
+	mntput(path->mnt);
+	path->mnt = &parent->mnt;
+	return 1;
+}
+EXPORT_SYMBOL(follow_up);
+
+/*
+ * Perform an automount
+ * - return -EISDIR to tell follow_managed() to stop and return the path we
+ *   were called with.
+ */
+static int follow_automount(struct path *path, struct nameidata *nd,
+			    bool *need_mntput)
+{
+	struct vfsmount *mnt;
+	int err;
+
+	if (!path->dentry->d_op || !path->dentry->d_op->d_automount)
+		return -EREMOTE;
+
+	/* We don't want to mount if someone's just doing a stat -
+	 * unless they're stat'ing a directory and appended a '/' to
+	 * the name.
+	 *
+	 * We do, however, want to mount if someone wants to open or
+	 * create a file of any type under the mountpoint, wants to
+	 * traverse through the mountpoint or wants to open the
+	 * mounted directory.  Also, autofs may mark negative dentries
+	 * as being automount points.  These will need the attentions
+	 * of the daemon to instantiate them before they can be used.
+	 */
+	if (!(nd->flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY |
+			   LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) &&
+	    path->dentry->d_inode)
+		return -EISDIR;
+
+	nd->total_link_count++;
+	if (nd->total_link_count >= 40)
+		return -ELOOP;
+
+	mnt = path->dentry->d_op->d_automount(path);
+	if (IS_ERR(mnt)) {
+		/*
+		 * The filesystem is allowed to return -EISDIR here to indicate
+		 * it doesn't want to automount.  For instance, autofs would do
+		 * this so that its userspace daemon can mount on this dentry.
+		 *
+		 * However, we can only permit this if it's a terminal point in
+		 * the path being looked up; if it wasn't then the remainder of
+		 * the path is inaccessible and we should say so.
+		 */
+		if (PTR_ERR(mnt) == -EISDIR && (nd->flags & LOOKUP_PARENT))
+			return -EREMOTE;
+		return PTR_ERR(mnt);
+	}
+
+	if (!mnt) /* mount collision */
+		return 0;
+
+	if (!*need_mntput) {
+		/* lock_mount() may release path->mnt on error */
+		mntget(path->mnt);
+		*need_mntput = true;
+	}
+	err = finish_automount(mnt, path);
+
+	switch (err) {
+	case -EBUSY:
+		/* Someone else made a mount here whilst we were busy */
+		return 0;
+	case 0:
+		path_put(path);
+		path->mnt = mnt;
+		path->dentry = dget(mnt->mnt_root);
+		return 0;
+	default:
+		return err;
+	}
+
+}
+
+/*
+ * Handle a dentry that is managed in some way.
+ * - Flagged for transit management (autofs)
+ * - Flagged as mountpoint
+ * - Flagged as automount point
+ *
+ * This may only be called in refwalk mode.
+ *
+ * Serialization is taken care of in namespace.c
+ */
+static int follow_managed(struct path *path, struct nameidata *nd)
+{
+	struct vfsmount *mnt = path->mnt; /* held by caller, must be left alone */
+	unsigned managed;
+	bool need_mntput = false;
+	int ret = 0;
+
+	/* Given that we're not holding a lock here, we retain the value in a
+	 * local variable for each dentry as we look at it so that we don't see
+	 * the components of that value change under us */
+	while (managed = READ_ONCE(path->dentry->d_flags),
+	       managed &= DCACHE_MANAGED_DENTRY,
+	       unlikely(managed != 0)) {
+		/* Allow the filesystem to manage the transit without i_mutex
+		 * being held. */
+		if (managed & DCACHE_MANAGE_TRANSIT) {
+			BUG_ON(!path->dentry->d_op);
+			BUG_ON(!path->dentry->d_op->d_manage);
+			ret = path->dentry->d_op->d_manage(path, false);
+			if (ret < 0)
+				break;
+		}
+
+		/* Transit to a mounted filesystem. */
+		if (managed & DCACHE_MOUNTED) {
+			struct vfsmount *mounted = lookup_mnt(path);
+			if (mounted) {
+				dput(path->dentry);
+				if (need_mntput)
+					mntput(path->mnt);
+				path->mnt = mounted;
+				path->dentry = dget(mounted->mnt_root);
+				need_mntput = true;
+				continue;
+			}
+
+			/* Something is mounted on this dentry in another
+			 * namespace and/or whatever was mounted there in this
+			 * namespace got unmounted before lookup_mnt() could
+			 * get it */
+		}
+
+		/* Handle an automount point */
+		if (managed & DCACHE_NEED_AUTOMOUNT) {
+			ret = follow_automount(path, nd, &need_mntput);
+			if (ret < 0)
+				break;
+			continue;
+		}
+
+		/* We didn't change the current path point */
+		break;
+	}
+
+	if (need_mntput && path->mnt == mnt)
+		mntput(path->mnt);
+	if (ret == -EISDIR || !ret)
+		ret = 1;
+	if (need_mntput)
+		nd->flags |= LOOKUP_JUMPED;
+	if (unlikely(ret < 0))
+		path_put_conditional(path, nd);
+	return ret;
+}
+
+int follow_down_one(struct path *path)
+{
+	struct vfsmount *mounted;
+
+	mounted = lookup_mnt(path);
+	if (mounted) {
+		dput(path->dentry);
+		mntput(path->mnt);
+		path->mnt = mounted;
+		path->dentry = dget(mounted->mnt_root);
+		return 1;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(follow_down_one);
+
+static inline int managed_dentry_rcu(const struct path *path)
+{
+	return (path->dentry->d_flags & DCACHE_MANAGE_TRANSIT) ?
+		path->dentry->d_op->d_manage(path, true) : 0;
+}
+
+/*
+ * Try to skip to top of mountpoint pile in rcuwalk mode.  Fail if
+ * we meet a managed dentry that would need blocking.
+ */
+static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
+			       struct inode **inode, unsigned *seqp)
+{
+	for (;;) {
+		struct mount *mounted;
+		/*
+		 * Don't forget we might have a non-mountpoint managed dentry
+		 * that wants to block transit.
+		 */
+		switch (managed_dentry_rcu(path)) {
+		case -ECHILD:
+		default:
+			return false;
+		case -EISDIR:
+			return true;
+		case 0:
+			break;
+		}
+
+		if (!d_mountpoint(path->dentry))
+			return !(path->dentry->d_flags & DCACHE_NEED_AUTOMOUNT);
+
+		mounted = __lookup_mnt(path->mnt, path->dentry);
+		if (!mounted)
+			break;
+		path->mnt = &mounted->mnt;
+		path->dentry = mounted->mnt.mnt_root;
+		nd->flags |= LOOKUP_JUMPED;
+		*seqp = read_seqcount_begin(&path->dentry->d_seq);
+		/*
+		 * Update the inode too. We don't need to re-check the
+		 * dentry sequence number here after this d_inode read,
+		 * because a mount-point is always pinned.
+		 */
+		*inode = path->dentry->d_inode;
+	}
+	return !read_seqretry(&mount_lock, nd->m_seq) &&
+		!(path->dentry->d_flags & DCACHE_NEED_AUTOMOUNT);
+}
+
+static int follow_dotdot_rcu(struct nameidata *nd)
+{
+	struct inode *inode = nd->inode;
+
+	while (1) {
+		if (path_equal(&nd->path, &nd->root))
+			break;
+		if (nd->path.dentry != nd->path.mnt->mnt_root) {
+			struct dentry *old = nd->path.dentry;
+			struct dentry *parent = old->d_parent;
+			unsigned seq;
+
+			inode = parent->d_inode;
+			seq = read_seqcount_begin(&parent->d_seq);
+			if (unlikely(read_seqcount_retry(&old->d_seq, nd->seq)))
+				return -ECHILD;
+			nd->path.dentry = parent;
+			nd->seq = seq;
+			if (unlikely(!path_connected(&nd->path)))
+				return -ENOENT;
+			break;
+		} else {
+			struct mount *mnt = real_mount(nd->path.mnt);
+			struct mount *mparent = mnt->mnt_parent;
+			struct dentry *mountpoint = mnt->mnt_mountpoint;
+			struct inode *inode2 = mountpoint->d_inode;
+			unsigned seq = read_seqcount_begin(&mountpoint->d_seq);
+			if (unlikely(read_seqretry(&mount_lock, nd->m_seq)))
+				return -ECHILD;
+			if (&mparent->mnt == nd->path.mnt)
+				break;
+			/* we know that mountpoint was pinned */
+			nd->path.dentry = mountpoint;
+			nd->path.mnt = &mparent->mnt;
+			inode = inode2;
+			nd->seq = seq;
+		}
+	}
+	while (unlikely(d_mountpoint(nd->path.dentry))) {
+		struct mount *mounted;
+		mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry);
+		if (unlikely(read_seqretry(&mount_lock, nd->m_seq)))
+			return -ECHILD;
+		if (!mounted)
+			break;
+		nd->path.mnt = &mounted->mnt;
+		nd->path.dentry = mounted->mnt.mnt_root;
+		inode = nd->path.dentry->d_inode;
+		nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
+	}
+	nd->inode = inode;
+	return 0;
+}
+
+/*
+ * Follow down to the covering mount currently visible to userspace.  At each
+ * point, the filesystem owning that dentry may be queried as to whether the
+ * caller is permitted to proceed or not.
+ */
+int follow_down(struct path *path)
+{
+	unsigned managed;
+	int ret;
+
+	while (managed = READ_ONCE(path->dentry->d_flags),
+	       unlikely(managed & DCACHE_MANAGED_DENTRY)) {
+		/* Allow the filesystem to manage the transit without i_mutex
+		 * being held.
+		 *
+		 * We indicate to the filesystem if someone is trying to mount
+		 * something here.  This gives autofs the chance to deny anyone
+		 * other than its daemon the right to mount on its
+		 * superstructure.
+		 *
+		 * The filesystem may sleep at this point.
+		 */
+		if (managed & DCACHE_MANAGE_TRANSIT) {
+			BUG_ON(!path->dentry->d_op);
+			BUG_ON(!path->dentry->d_op->d_manage);
+			ret = path->dentry->d_op->d_manage(path, false);
+			if (ret < 0)
+				return ret == -EISDIR ? 0 : ret;
+		}
+
+		/* Transit to a mounted filesystem. */
+		if (managed & DCACHE_MOUNTED) {
+			struct vfsmount *mounted = lookup_mnt(path);
+			if (!mounted)
+				break;
+			dput(path->dentry);
+			mntput(path->mnt);
+			path->mnt = mounted;
+			path->dentry = dget(mounted->mnt_root);
+			continue;
+		}
+
+		/* Don't handle automount points here */
+		break;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(follow_down);
+
+/*
+ * Skip to top of mountpoint pile in refwalk mode for follow_dotdot()
+ */
+static void follow_mount(struct path *path)
+{
+	while (d_mountpoint(path->dentry)) {
+		struct vfsmount *mounted = lookup_mnt(path);
+		if (!mounted)
+			break;
+		dput(path->dentry);
+		mntput(path->mnt);
+		path->mnt = mounted;
+		path->dentry = dget(mounted->mnt_root);
+	}
+}
+
+static int path_parent_directory(struct path *path)
+{
+	struct dentry *old = path->dentry;
+	/* rare case of legitimate dget_parent()... */
+	path->dentry = dget_parent(path->dentry);
+	dput(old);
+	if (unlikely(!path_connected(path)))
+		return -ENOENT;
+	return 0;
+}
+
+static int follow_dotdot(struct nameidata *nd)
+{
+	while(1) {
+		if (path_equal(&nd->path, &nd->root))
+			break;
+		if (nd->path.dentry != nd->path.mnt->mnt_root) {
+			int ret = path_parent_directory(&nd->path);
+			if (ret)
+				return ret;
+			break;
+		}
+		if (!follow_up(&nd->path))
+			break;
+	}
+	follow_mount(&nd->path);
+	nd->inode = nd->path.dentry->d_inode;
+	return 0;
+}
+
+/*
+ * This looks up the name in dcache and possibly revalidates the found dentry.
+ * NULL is returned if the dentry does not exist in the cache.
+ */
+static struct dentry *lookup_dcache(const struct qstr *name,
+				    struct dentry *dir,
+				    unsigned int flags)
+{
+	struct dentry *dentry = d_lookup(dir, name);
+	if (dentry) {
+		int error = d_revalidate(dentry, flags);
+		if (unlikely(error <= 0)) {
+			if (!error)
+				d_invalidate(dentry);
+			dput(dentry);
+			return ERR_PTR(error);
+		}
+	}
+	return dentry;
+}
+
+/*
+ * Parent directory has inode locked exclusive.  This is one
+ * and only case when ->lookup() gets called on non in-lookup
+ * dentries - as the matter of fact, this only gets called
+ * when directory is guaranteed to have no in-lookup children
+ * at all.
+ */
+static struct dentry *__lookup_hash(const struct qstr *name,
+		struct dentry *base, unsigned int flags)
+{
+	struct dentry *dentry = lookup_dcache(name, base, flags);
+	struct dentry *old;
+	struct inode *dir = base->d_inode;
+
+	if (dentry)
+		return dentry;
+
+	/* Don't create child dentry for a dead directory. */
+	if (unlikely(IS_DEADDIR(dir)))
+		return ERR_PTR(-ENOENT);
+
+	dentry = d_alloc(base, name);
+	if (unlikely(!dentry))
+		return ERR_PTR(-ENOMEM);
+
+	old = dir->i_op->lookup(dir, dentry, flags);
+	if (unlikely(old)) {
+		dput(dentry);
+		dentry = old;
+	}
+	return dentry;
+}
+
+static int lookup_fast(struct nameidata *nd,
+		       struct path *path, struct inode **inode,
+		       unsigned *seqp)
+{
+	struct vfsmount *mnt = nd->path.mnt;
+	struct dentry *dentry, *parent = nd->path.dentry;
+	int status = 1;
+	int err;
+
+	/*
+	 * Rename seqlock is not required here because in the off chance
+	 * of a false negative due to a concurrent rename, the caller is
+	 * going to fall back to non-racy lookup.
+	 */
+	if (nd->flags & LOOKUP_RCU) {
+		unsigned seq;
+		bool negative;
+		dentry = __d_lookup_rcu(parent, &nd->last, &seq);
+		if (unlikely(!dentry)) {
+			if (unlazy_walk(nd))
+				return -ECHILD;
+			return 0;
+		}
+
+		/*
+		 * This sequence count validates that the inode matches
+		 * the dentry name information from lookup.
+		 */
+		*inode = d_backing_inode(dentry);
+		negative = d_is_negative(dentry);
+		if (unlikely(read_seqcount_retry(&dentry->d_seq, seq)))
+			return -ECHILD;
+
+		/*
+		 * This sequence count validates that the parent had no
+		 * changes while we did the lookup of the dentry above.
+		 *
+		 * The memory barrier in read_seqcount_begin of child is
+		 *  enough, we can use __read_seqcount_retry here.
+		 */
+		if (unlikely(__read_seqcount_retry(&parent->d_seq, nd->seq)))
+			return -ECHILD;
+
+		*seqp = seq;
+		status = d_revalidate(dentry, nd->flags);
+		if (likely(status > 0)) {
+			/*
+			 * Note: do negative dentry check after revalidation in
+			 * case that drops it.
+			 */
+			if (unlikely(negative))
+				return -ENOENT;
+			path->mnt = mnt;
+			path->dentry = dentry;
+			if (likely(__follow_mount_rcu(nd, path, inode, seqp)))
+				return 1;
+		}
+		if (unlazy_child(nd, dentry, seq))
+			return -ECHILD;
+		if (unlikely(status == -ECHILD))
+			/* we'd been told to redo it in non-rcu mode */
+			status = d_revalidate(dentry, nd->flags);
+	} else {
+		dentry = __d_lookup(parent, &nd->last);
+		if (unlikely(!dentry))
+			return 0;
+		status = d_revalidate(dentry, nd->flags);
+	}
+	if (unlikely(status <= 0)) {
+		if (!status)
+			d_invalidate(dentry);
+		dput(dentry);
+		return status;
+	}
+	if (unlikely(d_is_negative(dentry))) {
+		dput(dentry);
+		return -ENOENT;
+	}
+
+	path->mnt = mnt;
+	path->dentry = dentry;
+	err = follow_managed(path, nd);
+	if (likely(err > 0))
+		*inode = d_backing_inode(path->dentry);
+	return err;
+}
+
+/* Fast lookup failed, do it the slow way */
+static struct dentry *__lookup_slow(const struct qstr *name,
+				    struct dentry *dir,
+				    unsigned int flags)
+{
+	struct dentry *dentry, *old;
+	struct inode *inode = dir->d_inode;
+	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+
+	/* Don't go there if it's already dead */
+	if (unlikely(IS_DEADDIR(inode)))
+		return ERR_PTR(-ENOENT);
+again:
+	dentry = d_alloc_parallel(dir, name, &wq);
+	if (IS_ERR(dentry))
+		return dentry;
+	if (unlikely(!d_in_lookup(dentry))) {
+		if (!(flags & LOOKUP_NO_REVAL)) {
+			int error = d_revalidate(dentry, flags);
+			if (unlikely(error <= 0)) {
+				if (!error) {
+					d_invalidate(dentry);
+					dput(dentry);
+					goto again;
+				}
+				dput(dentry);
+				dentry = ERR_PTR(error);
+			}
+		}
+	} else {
+		old = inode->i_op->lookup(inode, dentry, flags);
+		d_lookup_done(dentry);
+		if (unlikely(old)) {
+			dput(dentry);
+			dentry = old;
+		}
+	}
+	return dentry;
+}
+
+static struct dentry *lookup_slow(const struct qstr *name,
+				  struct dentry *dir,
+				  unsigned int flags)
+{
+	struct inode *inode = dir->d_inode;
+	struct dentry *res;
+	inode_lock_shared(inode);
+	res = __lookup_slow(name, dir, flags);
+	inode_unlock_shared(inode);
+	return res;
+}
+
+static inline int may_lookup(struct nameidata *nd)
+{
+	if (nd->flags & LOOKUP_RCU) {
+		int err = inode_permission2(nd->path.mnt, nd->inode, MAY_EXEC|MAY_NOT_BLOCK);
+		if (err != -ECHILD)
+			return err;
+		if (unlazy_walk(nd))
+			return -ECHILD;
+	}
+	return inode_permission2(nd->path.mnt, nd->inode, MAY_EXEC);
+}
+
+static inline int handle_dots(struct nameidata *nd, int type)
+{
+	if (type == LAST_DOTDOT) {
+		if (!nd->root.mnt)
+			set_root(nd);
+		if (nd->flags & LOOKUP_RCU) {
+			return follow_dotdot_rcu(nd);
+		} else
+			return follow_dotdot(nd);
+	}
+	return 0;
+}
+
+static int pick_link(struct nameidata *nd, struct path *link,
+		     struct inode *inode, unsigned seq)
+{
+	int error;
+	struct saved *last;
+	if (unlikely(nd->total_link_count++ >= MAXSYMLINKS)) {
+		path_to_nameidata(link, nd);
+		return -ELOOP;
+	}
+	if (!(nd->flags & LOOKUP_RCU)) {
+		if (link->mnt == nd->path.mnt)
+			mntget(link->mnt);
+	}
+	error = nd_alloc_stack(nd);
+	if (unlikely(error)) {
+		if (error == -ECHILD) {
+			if (unlikely(!legitimize_path(nd, link, seq))) {
+				drop_links(nd);
+				nd->depth = 0;
+				nd->flags &= ~LOOKUP_RCU;
+				nd->path.mnt = NULL;
+				nd->path.dentry = NULL;
+				if (!(nd->flags & LOOKUP_ROOT))
+					nd->root.mnt = NULL;
+				rcu_read_unlock();
+			} else if (likely(unlazy_walk(nd)) == 0)
+				error = nd_alloc_stack(nd);
+		}
+		if (error) {
+			path_put(link);
+			return error;
+		}
+	}
+
+	last = nd->stack + nd->depth++;
+	last->link = *link;
+	clear_delayed_call(&last->done);
+	nd->link_inode = inode;
+	last->seq = seq;
+	return 1;
+}
+
+enum {WALK_FOLLOW = 1, WALK_MORE = 2};
+
+/*
+ * Do we need to follow links? We _really_ want to be able
+ * to do this check without having to look at inode->i_op,
+ * so we keep a cache of "no, this doesn't need follow_link"
+ * for the common case.
+ */
+static inline int step_into(struct nameidata *nd, struct path *path,
+			    int flags, struct inode *inode, unsigned seq)
+{
+	if (!(flags & WALK_MORE) && nd->depth)
+		put_link(nd);
+	if (likely(!d_is_symlink(path->dentry)) ||
+	   !(flags & WALK_FOLLOW || nd->flags & LOOKUP_FOLLOW)) {
+		/* not a symlink or should not follow */
+		path_to_nameidata(path, nd);
+		nd->inode = inode;
+		nd->seq = seq;
+		return 0;
+	}
+	/* make sure that d_is_symlink above matches inode */
+	if (nd->flags & LOOKUP_RCU) {
+		if (read_seqcount_retry(&path->dentry->d_seq, seq))
+			return -ECHILD;
+	}
+	return pick_link(nd, path, inode, seq);
+}
+
+static int walk_component(struct nameidata *nd, int flags)
+{
+	struct path path;
+	struct inode *inode;
+	unsigned seq;
+	int err;
+	/*
+	 * "." and ".." are special - ".." especially so because it has
+	 * to be able to know about the current root directory and
+	 * parent relationships.
+	 */
+	if (unlikely(nd->last_type != LAST_NORM)) {
+		err = handle_dots(nd, nd->last_type);
+		if (!(flags & WALK_MORE) && nd->depth)
+			put_link(nd);
+		return err;
+	}
+	err = lookup_fast(nd, &path, &inode, &seq);
+	if (unlikely(err <= 0)) {
+		if (err < 0)
+			return err;
+		path.dentry = lookup_slow(&nd->last, nd->path.dentry,
+					  nd->flags);
+		if (IS_ERR(path.dentry))
+			return PTR_ERR(path.dentry);
+
+		path.mnt = nd->path.mnt;
+		err = follow_managed(&path, nd);
+		if (unlikely(err < 0))
+			return err;
+
+		if (unlikely(d_is_negative(path.dentry))) {
+			path_to_nameidata(&path, nd);
+			return -ENOENT;
+		}
+
+		seq = 0;	/* we are already out of RCU mode */
+		inode = d_backing_inode(path.dentry);
+	}
+
+	return step_into(nd, &path, flags, inode, seq);
+}
+
+/*
+ * We can do the critical dentry name comparison and hashing
+ * operations one word at a time, but we are limited to:
+ *
+ * - Architectures with fast unaligned word accesses. We could
+ *   do a "get_unaligned()" if this helps and is sufficiently
+ *   fast.
+ *
+ * - non-CONFIG_DEBUG_PAGEALLOC configurations (so that we
+ *   do not trap on the (extremely unlikely) case of a page
+ *   crossing operation.
+ *
+ * - Furthermore, we need an efficient 64-bit compile for the
+ *   64-bit case in order to generate the "number of bytes in
+ *   the final mask". Again, that could be replaced with a
+ *   efficient population count instruction or similar.
+ */
+#ifdef CONFIG_DCACHE_WORD_ACCESS
+
+#include <asm/word-at-a-time.h>
+
+#ifdef HASH_MIX
+
+/* Architecture provides HASH_MIX and fold_hash() in <asm/hash.h> */
+
+#elif defined(CONFIG_64BIT)
+/*
+ * Register pressure in the mixing function is an issue, particularly
+ * on 32-bit x86, but almost any function requires one state value and
+ * one temporary.  Instead, use a function designed for two state values
+ * and no temporaries.
+ *
+ * This function cannot create a collision in only two iterations, so
+ * we have two iterations to achieve avalanche.  In those two iterations,
+ * we have six layers of mixing, which is enough to spread one bit's
+ * influence out to 2^6 = 64 state bits.
+ *
+ * Rotate constants are scored by considering either 64 one-bit input
+ * deltas or 64*63/2 = 2016 two-bit input deltas, and finding the
+ * probability of that delta causing a change to each of the 128 output
+ * bits, using a sample of random initial states.
+ *
+ * The Shannon entropy of the computed probabilities is then summed
+ * to produce a score.  Ideally, any input change has a 50% chance of
+ * toggling any given output bit.
+ *
+ * Mixing scores (in bits) for (12,45):
+ * Input delta: 1-bit      2-bit
+ * 1 round:     713.3    42542.6
+ * 2 rounds:   2753.7   140389.8
+ * 3 rounds:   5954.1   233458.2
+ * 4 rounds:   7862.6   256672.2
+ * Perfect:    8192     258048
+ *            (64*128) (64*63/2 * 128)
+ */
+#define HASH_MIX(x, y, a)	\
+	(	x ^= (a),	\
+	y ^= x,	x = rol64(x,12),\
+	x += y,	y = rol64(y,45),\
+	y *= 9			)
+
+/*
+ * Fold two longs into one 32-bit hash value.  This must be fast, but
+ * latency isn't quite as critical, as there is a fair bit of additional
+ * work done before the hash value is used.
+ */
+static inline unsigned int fold_hash(unsigned long x, unsigned long y)
+{
+	y ^= x * GOLDEN_RATIO_64;
+	y *= GOLDEN_RATIO_64;
+	return y >> 32;
+}
+
+#else	/* 32-bit case */
+
+/*
+ * Mixing scores (in bits) for (7,20):
+ * Input delta: 1-bit      2-bit
+ * 1 round:     330.3     9201.6
+ * 2 rounds:   1246.4    25475.4
+ * 3 rounds:   1907.1    31295.1
+ * 4 rounds:   2042.3    31718.6
+ * Perfect:    2048      31744
+ *            (32*64)   (32*31/2 * 64)
+ */
+#define HASH_MIX(x, y, a)	\
+	(	x ^= (a),	\
+	y ^= x,	x = rol32(x, 7),\
+	x += y,	y = rol32(y,20),\
+	y *= 9			)
+
+static inline unsigned int fold_hash(unsigned long x, unsigned long y)
+{
+	/* Use arch-optimized multiply if one exists */
+	return __hash_32(y ^ __hash_32(x));
+}
+
+#endif
+
+/*
+ * Return the hash of a string of known length.  This is carfully
+ * designed to match hash_name(), which is the more critical function.
+ * In particular, we must end by hashing a final word containing 0..7
+ * payload bytes, to match the way that hash_name() iterates until it
+ * finds the delimiter after the name.
+ */
+unsigned int full_name_hash(const void *salt, const char *name, unsigned int len)
+{
+	unsigned long a, x = 0, y = (unsigned long)salt;
+
+	for (;;) {
+		if (!len)
+			goto done;
+		a = load_unaligned_zeropad(name);
+		if (len < sizeof(unsigned long))
+			break;
+		HASH_MIX(x, y, a);
+		name += sizeof(unsigned long);
+		len -= sizeof(unsigned long);
+	}
+	x ^= a & bytemask_from_count(len);
+done:
+	return fold_hash(x, y);
+}
+EXPORT_SYMBOL(full_name_hash);
+
+/* Return the "hash_len" (hash and length) of a null-terminated string */
+u64 hashlen_string(const void *salt, const char *name)
+{
+	unsigned long a = 0, x = 0, y = (unsigned long)salt;
+	unsigned long adata, mask, len;
+	const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
+
+	len = 0;
+	goto inside;
+
+	do {
+		HASH_MIX(x, y, a);
+		len += sizeof(unsigned long);
+inside:
+		a = load_unaligned_zeropad(name+len);
+	} while (!has_zero(a, &adata, &constants));
+
+	adata = prep_zero_mask(a, adata, &constants);
+	mask = create_zero_mask(adata);
+	x ^= a & zero_bytemask(mask);
+
+	return hashlen_create(fold_hash(x, y), len + find_zero(mask));
+}
+EXPORT_SYMBOL(hashlen_string);
+
+/*
+ * Calculate the length and hash of the path component, and
+ * return the "hash_len" as the result.
+ */
+static inline u64 hash_name(const void *salt, const char *name)
+{
+	unsigned long a = 0, b, x = 0, y = (unsigned long)salt;
+	unsigned long adata, bdata, mask, len;
+	const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
+
+	len = 0;
+	goto inside;
+
+	do {
+		HASH_MIX(x, y, a);
+		len += sizeof(unsigned long);
+inside:
+		a = load_unaligned_zeropad(name+len);
+		b = a ^ REPEAT_BYTE('/');
+	} while (!(has_zero(a, &adata, &constants) | has_zero(b, &bdata, &constants)));
+
+	adata = prep_zero_mask(a, adata, &constants);
+	bdata = prep_zero_mask(b, bdata, &constants);
+	mask = create_zero_mask(adata | bdata);
+	x ^= a & zero_bytemask(mask);
+
+	return hashlen_create(fold_hash(x, y), len + find_zero(mask));
+}
+
+#else	/* !CONFIG_DCACHE_WORD_ACCESS: Slow, byte-at-a-time version */
+
+/* Return the hash of a string of known length */
+unsigned int full_name_hash(const void *salt, const char *name, unsigned int len)
+{
+	unsigned long hash = init_name_hash(salt);
+	while (len--)
+		hash = partial_name_hash((unsigned char)*name++, hash);
+	return end_name_hash(hash);
+}
+EXPORT_SYMBOL(full_name_hash);
+
+/* Return the "hash_len" (hash and length) of a null-terminated string */
+u64 hashlen_string(const void *salt, const char *name)
+{
+	unsigned long hash = init_name_hash(salt);
+	unsigned long len = 0, c;
+
+	c = (unsigned char)*name;
+	while (c) {
+		len++;
+		hash = partial_name_hash(c, hash);
+		c = (unsigned char)name[len];
+	}
+	return hashlen_create(end_name_hash(hash), len);
+}
+EXPORT_SYMBOL(hashlen_string);
+
+/*
+ * We know there's a real path component here of at least
+ * one character.
+ */
+static inline u64 hash_name(const void *salt, const char *name)
+{
+	unsigned long hash = init_name_hash(salt);
+	unsigned long len = 0, c;
+
+	c = (unsigned char)*name;
+	do {
+		len++;
+		hash = partial_name_hash(c, hash);
+		c = (unsigned char)name[len];
+	} while (c && c != '/');
+	return hashlen_create(end_name_hash(hash), len);
+}
+
+#endif
+
+/*
+ * Name resolution.
+ * This is the basic name resolution function, turning a pathname into
+ * the final dentry. We expect 'base' to be positive and a directory.
+ *
+ * Returns 0 and nd will have valid dentry and mnt on success.
+ * Returns error and drops reference to input namei data on failure.
+ */
+static int link_path_walk(const char *name, struct nameidata *nd)
+{
+	int err;
+
+	if (IS_ERR(name))
+		return PTR_ERR(name);
+	while (*name=='/')
+		name++;
+	if (!*name)
+		return 0;
+
+	/* At this point we know we have a real path component. */
+	for(;;) {
+		u64 hash_len;
+		int type;
+
+		err = may_lookup(nd);
+		if (err)
+			return err;
+
+		hash_len = hash_name(nd->path.dentry, name);
+
+		type = LAST_NORM;
+		if (name[0] == '.') switch (hashlen_len(hash_len)) {
+			case 2:
+				if (name[1] == '.') {
+					type = LAST_DOTDOT;
+					nd->flags |= LOOKUP_JUMPED;
+				}
+				break;
+			case 1:
+				type = LAST_DOT;
+		}
+		if (likely(type == LAST_NORM)) {
+			struct dentry *parent = nd->path.dentry;
+			nd->flags &= ~LOOKUP_JUMPED;
+			if (unlikely(parent->d_flags & DCACHE_OP_HASH)) {
+				struct qstr this = { { .hash_len = hash_len }, .name = name };
+				err = parent->d_op->d_hash(parent, &this);
+				if (err < 0)
+					return err;
+				hash_len = this.hash_len;
+				name = this.name;
+			}
+		}
+
+		nd->last.hash_len = hash_len;
+		nd->last.name = name;
+		nd->last_type = type;
+
+		name += hashlen_len(hash_len);
+		if (!*name)
+			goto OK;
+		/*
+		 * If it wasn't NUL, we know it was '/'. Skip that
+		 * slash, and continue until no more slashes.
+		 */
+		do {
+			name++;
+		} while (unlikely(*name == '/'));
+		if (unlikely(!*name)) {
+OK:
+			/* pathname body, done */
+			if (!nd->depth)
+				return 0;
+			name = nd->stack[nd->depth - 1].name;
+			/* trailing symlink, done */
+			if (!name)
+				return 0;
+			/* last component of nested symlink */
+			err = walk_component(nd, WALK_FOLLOW);
+		} else {
+			/* not the last component */
+			err = walk_component(nd, WALK_FOLLOW | WALK_MORE);
+		}
+		if (err < 0)
+			return err;
+
+		if (err) {
+			const char *s = get_link(nd);
+
+			if (IS_ERR(s))
+				return PTR_ERR(s);
+			err = 0;
+			if (unlikely(!s)) {
+				/* jumped */
+				put_link(nd);
+			} else {
+				nd->stack[nd->depth - 1].name = name;
+				name = s;
+				continue;
+			}
+		}
+		if (unlikely(!d_can_lookup(nd->path.dentry))) {
+			if (nd->flags & LOOKUP_RCU) {
+				if (unlazy_walk(nd))
+					return -ECHILD;
+			}
+			return -ENOTDIR;
+		}
+	}
+}
+
+/* must be paired with terminate_walk() */
+static const char *path_init(struct nameidata *nd, unsigned flags)
+{
+	const char *s = nd->name->name;
+
+	if (!*s)
+		flags &= ~LOOKUP_RCU;
+	if (flags & LOOKUP_RCU)
+		rcu_read_lock();
+
+	nd->last_type = LAST_ROOT; /* if there are only slashes... */
+	nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT;
+	nd->depth = 0;
+	if (flags & LOOKUP_ROOT) {
+		struct dentry *root = nd->root.dentry;
+		struct inode *inode = root->d_inode;
+		if (*s && unlikely(!d_can_lookup(root)))
+			return ERR_PTR(-ENOTDIR);
+		nd->path = nd->root;
+		nd->inode = inode;
+		if (flags & LOOKUP_RCU) {
+			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
+			nd->root_seq = nd->seq;
+			nd->m_seq = read_seqbegin(&mount_lock);
+		} else {
+			path_get(&nd->path);
+		}
+		return s;
+	}
+
+	nd->root.mnt = NULL;
+	nd->path.mnt = NULL;
+	nd->path.dentry = NULL;
+
+	nd->m_seq = read_seqbegin(&mount_lock);
+	if (*s == '/') {
+		set_root(nd);
+		if (likely(!nd_jump_root(nd)))
+			return s;
+		return ERR_PTR(-ECHILD);
+	} else if (nd->dfd == AT_FDCWD) {
+		if (flags & LOOKUP_RCU) {
+			struct fs_struct *fs = current->fs;
+			unsigned seq;
+
+			do {
+				seq = read_seqcount_begin(&fs->seq);
+				nd->path = fs->pwd;
+				nd->inode = nd->path.dentry->d_inode;
+				nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
+			} while (read_seqcount_retry(&fs->seq, seq));
+		} else {
+			get_fs_pwd(current->fs, &nd->path);
+			nd->inode = nd->path.dentry->d_inode;
+		}
+		return s;
+	} else {
+		/* Caller must check execute permissions on the starting path component */
+		struct fd f = fdget_raw(nd->dfd);
+		struct dentry *dentry;
+
+		if (!f.file)
+			return ERR_PTR(-EBADF);
+
+		dentry = f.file->f_path.dentry;
+
+		if (*s && unlikely(!d_can_lookup(dentry))) {
+			fdput(f);
+			return ERR_PTR(-ENOTDIR);
+		}
+
+		nd->path = f.file->f_path;
+		if (flags & LOOKUP_RCU) {
+			nd->inode = nd->path.dentry->d_inode;
+			nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
+		} else {
+			path_get(&nd->path);
+			nd->inode = nd->path.dentry->d_inode;
+		}
+		fdput(f);
+		return s;
+	}
+}
+
+static const char *trailing_symlink(struct nameidata *nd)
+{
+	const char *s;
+	int error = may_follow_link(nd);
+	if (unlikely(error))
+		return ERR_PTR(error);
+	nd->flags |= LOOKUP_PARENT;
+	nd->stack[0].name = NULL;
+	s = get_link(nd);
+	return s ? s : "";
+}
+
+static inline int lookup_last(struct nameidata *nd)
+{
+	if (nd->last_type == LAST_NORM && nd->last.name[nd->last.len])
+		nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
+
+	nd->flags &= ~LOOKUP_PARENT;
+	return walk_component(nd, 0);
+}
+
+static int handle_lookup_down(struct nameidata *nd)
+{
+	struct path path = nd->path;
+	struct inode *inode = nd->inode;
+	unsigned seq = nd->seq;
+	int err;
+
+	if (nd->flags & LOOKUP_RCU) {
+		/*
+		 * don't bother with unlazy_walk on failure - we are
+		 * at the very beginning of walk, so we lose nothing
+		 * if we simply redo everything in non-RCU mode
+		 */
+		if (unlikely(!__follow_mount_rcu(nd, &path, &inode, &seq)))
+			return -ECHILD;
+	} else {
+		dget(path.dentry);
+		err = follow_managed(&path, nd);
+		if (unlikely(err < 0))
+			return err;
+		inode = d_backing_inode(path.dentry);
+		seq = 0;
+	}
+	path_to_nameidata(&path, nd);
+	nd->inode = inode;
+	nd->seq = seq;
+	return 0;
+}
+
+/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
+static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path)
+{
+	const char *s = path_init(nd, flags);
+	int err;
+
+	if (unlikely(flags & LOOKUP_DOWN) && !IS_ERR(s)) {
+		err = handle_lookup_down(nd);
+		if (unlikely(err < 0))
+			s = ERR_PTR(err);
+	}
+
+	while (!(err = link_path_walk(s, nd))
+		&& ((err = lookup_last(nd)) > 0)) {
+		s = trailing_symlink(nd);
+	}
+	if (!err)
+		err = complete_walk(nd);
+
+	if (!err && nd->flags & LOOKUP_DIRECTORY)
+		if (!d_can_lookup(nd->path.dentry))
+			err = -ENOTDIR;
+	if (!err) {
+		*path = nd->path;
+		nd->path.mnt = NULL;
+		nd->path.dentry = NULL;
+	}
+	terminate_walk(nd);
+	return err;
+}
+
+static int filename_lookup(int dfd, struct filename *name, unsigned flags,
+			   struct path *path, struct path *root)
+{
+	int retval;
+	struct nameidata nd;
+	if (IS_ERR(name))
+		return PTR_ERR(name);
+	if (unlikely(root)) {
+		nd.root = *root;
+		flags |= LOOKUP_ROOT;
+	}
+	set_nameidata(&nd, dfd, name);
+	retval = path_lookupat(&nd, flags | LOOKUP_RCU, path);
+	if (unlikely(retval == -ECHILD))
+		retval = path_lookupat(&nd, flags, path);
+	if (unlikely(retval == -ESTALE))
+		retval = path_lookupat(&nd, flags | LOOKUP_REVAL, path);
+
+	if (likely(!retval))
+		audit_inode(name, path->dentry, flags & LOOKUP_PARENT);
+	restore_nameidata();
+	putname(name);
+	return retval;
+}
+
+/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
+static int path_parentat(struct nameidata *nd, unsigned flags,
+				struct path *parent)
+{
+	const char *s = path_init(nd, flags);
+	int err = link_path_walk(s, nd);
+	if (!err)
+		err = complete_walk(nd);
+	if (!err) {
+		*parent = nd->path;
+		nd->path.mnt = NULL;
+		nd->path.dentry = NULL;
+	}
+	terminate_walk(nd);
+	return err;
+}
+
+static struct filename *filename_parentat(int dfd, struct filename *name,
+				unsigned int flags, struct path *parent,
+				struct qstr *last, int *type)
+{
+	int retval;
+	struct nameidata nd;
+
+	if (IS_ERR(name))
+		return name;
+	set_nameidata(&nd, dfd, name);
+	retval = path_parentat(&nd, flags | LOOKUP_RCU, parent);
+	if (unlikely(retval == -ECHILD))
+		retval = path_parentat(&nd, flags, parent);
+	if (unlikely(retval == -ESTALE))
+		retval = path_parentat(&nd, flags | LOOKUP_REVAL, parent);
+	if (likely(!retval)) {
+		*last = nd.last;
+		*type = nd.last_type;
+		audit_inode(name, parent->dentry, LOOKUP_PARENT);
+	} else {
+		putname(name);
+		name = ERR_PTR(retval);
+	}
+	restore_nameidata();
+	return name;
+}
+
+/* does lookup, returns the object with parent locked */
+struct dentry *kern_path_locked(const char *name, struct path *path)
+{
+	struct filename *filename;
+	struct dentry *d;
+	struct qstr last;
+	int type;
+
+	filename = filename_parentat(AT_FDCWD, getname_kernel(name), 0, path,
+				    &last, &type);
+	if (IS_ERR(filename))
+		return ERR_CAST(filename);
+	if (unlikely(type != LAST_NORM)) {
+		path_put(path);
+		putname(filename);
+		return ERR_PTR(-EINVAL);
+	}
+	inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT);
+	d = __lookup_hash(&last, path->dentry, 0);
+	if (IS_ERR(d)) {
+		inode_unlock(path->dentry->d_inode);
+		path_put(path);
+	}
+	putname(filename);
+	return d;
+}
+
+int kern_path(const char *name, unsigned int flags, struct path *path)
+{
+	return filename_lookup(AT_FDCWD, getname_kernel(name),
+			       flags, path, NULL);
+}
+EXPORT_SYMBOL(kern_path);
+
+/**
+ * vfs_path_lookup - lookup a file path relative to a dentry-vfsmount pair
+ * @dentry:  pointer to dentry of the base directory
+ * @mnt: pointer to vfs mount of the base directory
+ * @name: pointer to file name
+ * @flags: lookup flags
+ * @path: pointer to struct path to fill
+ */
+int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
+		    const char *name, unsigned int flags,
+		    struct path *path)
+{
+	struct path root = {.mnt = mnt, .dentry = dentry};
+	/* the first argument of filename_lookup() is ignored with root */
+	return filename_lookup(AT_FDCWD, getname_kernel(name),
+			       flags , path, &root);
+}
+EXPORT_SYMBOL(vfs_path_lookup);
+
+static int lookup_one_len_common(const char *name, struct vfsmount *mnt,
+				 struct dentry *base, int len, struct qstr *this)
+{
+	this->name = name;
+	this->len = len;
+	this->hash = full_name_hash(base, name, len);
+	if (!len)
+		return -EACCES;
+
+	if (unlikely(name[0] == '.')) {
+		if (len < 2 || (len == 2 && name[1] == '.'))
+			return -EACCES;
+	}
+
+	while (len--) {
+		unsigned int c = *(const unsigned char *)name++;
+		if (c == '/' || c == '\0')
+			return -EACCES;
+	}
+	/*
+	 * See if the low-level filesystem might want
+	 * to use its own hash..
+	 */
+	if (base->d_flags & DCACHE_OP_HASH) {
+		int err = base->d_op->d_hash(base, this);
+		if (err < 0)
+			return err;
+	}
+
+	return inode_permission2(mnt, base->d_inode, MAY_EXEC);
+}
+
+/**
+ * try_lookup_one_len - filesystem helper to lookup single pathname component
+ * @name:	pathname component to lookup
+ * @base:	base directory to lookup from
+ * @len:	maximum length @len should be interpreted to
+ *
+ * Look up a dentry by name in the dcache, returning NULL if it does not
+ * currently exist.  The function does not try to create a dentry.
+ *
+ * Note that this routine is purely a helper for filesystem usage and should
+ * not be called by generic code.
+ *
+ * The caller must hold base->i_mutex.
+ */
+struct dentry *try_lookup_one_len(const char *name, struct dentry *base, int len)
+{
+	struct qstr this;
+	int err;
+
+	WARN_ON_ONCE(!inode_is_locked(base->d_inode));
+
+	err = lookup_one_len_common(name, NULL, base, len, &this);
+	if (err)
+		return ERR_PTR(err);
+
+	return lookup_dcache(&this, base, 0);
+}
+EXPORT_SYMBOL(try_lookup_one_len);
+
+/**
+ * lookup_one_len - filesystem helper to lookup single pathname component
+ * @name:	pathname component to lookup
+ * @base:	base directory to lookup from
+ * @len:	maximum length @len should be interpreted to
+ *
+ * Note that this routine is purely a helper for filesystem usage and should
+ * not be called by generic code.
+ *
+ * The caller must hold base->i_mutex.
+ */
+struct dentry *lookup_one_len2(const char *name, struct vfsmount *mnt, struct dentry *base, int len)
+{
+	struct dentry *dentry;
+	struct qstr this;
+	int err;
+
+	WARN_ON_ONCE(!inode_is_locked(base->d_inode));
+
+	err = lookup_one_len_common(name, mnt, base, len, &this);
+	if (err)
+		return ERR_PTR(err);
+
+	dentry = lookup_dcache(&this, base, 0);
+	return dentry ? dentry : __lookup_slow(&this, base, 0);
+}
+EXPORT_SYMBOL(lookup_one_len2);
+
+struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
+{
+	return lookup_one_len2(name, NULL, base, len);
+}
+EXPORT_SYMBOL(lookup_one_len);
+
+/**
+ * lookup_one_len_unlocked - filesystem helper to lookup single pathname component
+ * @name:	pathname component to lookup
+ * @base:	base directory to lookup from
+ * @len:	maximum length @len should be interpreted to
+ *
+ * Note that this routine is purely a helper for filesystem usage and should
+ * not be called by generic code.
+ *
+ * Unlike lookup_one_len, it should be called without the parent
+ * i_mutex held, and will take the i_mutex itself if necessary.
+ */
+struct dentry *lookup_one_len_unlocked(const char *name,
+				       struct dentry *base, int len)
+{
+	struct qstr this;
+	int err;
+	struct dentry *ret;
+
+	err = lookup_one_len_common(name, NULL, base, len, &this);
+	if (err)
+		return ERR_PTR(err);
+
+	ret = lookup_dcache(&this, base, 0);
+	if (!ret)
+		ret = lookup_slow(&this, base, 0);
+	return ret;
+}
+EXPORT_SYMBOL(lookup_one_len_unlocked);
+
+#ifdef CONFIG_UNIX98_PTYS
+int path_pts(struct path *path)
+{
+	/* Find something mounted on "pts" in the same directory as
+	 * the input path.
+	 */
+	struct dentry *child, *parent;
+	struct qstr this;
+	int ret;
+
+	ret = path_parent_directory(path);
+	if (ret)
+		return ret;
+
+	parent = path->dentry;
+	this.name = "pts";
+	this.len = 3;
+	child = d_hash_and_lookup(parent, &this);
+	if (!child)
+		return -ENOENT;
+
+	path->dentry = child;
+	dput(parent);
+	follow_mount(path);
+	return 0;
+}
+#endif
+
+int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
+		 struct path *path, int *empty)
+{
+	return filename_lookup(dfd, getname_flags(name, flags, empty),
+			       flags, path, NULL);
+}
+EXPORT_SYMBOL(user_path_at_empty);
+
+/**
+ * mountpoint_last - look up last component for umount
+ * @nd:   pathwalk nameidata - currently pointing at parent directory of "last"
+ *
+ * This is a special lookup_last function just for umount. In this case, we
+ * need to resolve the path without doing any revalidation.
+ *
+ * The nameidata should be the result of doing a LOOKUP_PARENT pathwalk. Since
+ * mountpoints are always pinned in the dcache, their ancestors are too. Thus,
+ * in almost all cases, this lookup will be served out of the dcache. The only
+ * cases where it won't are if nd->last refers to a symlink or the path is
+ * bogus and it doesn't exist.
+ *
+ * Returns:
+ * -error: if there was an error during lookup. This includes -ENOENT if the
+ *         lookup found a negative dentry.
+ *
+ * 0:      if we successfully resolved nd->last and found it to not to be a
+ *         symlink that needs to be followed.
+ *
+ * 1:      if we successfully resolved nd->last and found it to be a symlink
+ *         that needs to be followed.
+ */
+static int
+mountpoint_last(struct nameidata *nd)
+{
+	int error = 0;
+	struct dentry *dir = nd->path.dentry;
+	struct path path;
+
+	/* If we're in rcuwalk, drop out of it to handle last component */
+	if (nd->flags & LOOKUP_RCU) {
+		if (unlazy_walk(nd))
+			return -ECHILD;
+	}
+
+	nd->flags &= ~LOOKUP_PARENT;
+
+	if (unlikely(nd->last_type != LAST_NORM)) {
+		error = handle_dots(nd, nd->last_type);
+		if (error)
+			return error;
+		path.dentry = dget(nd->path.dentry);
+	} else {
+		path.dentry = d_lookup(dir, &nd->last);
+		if (!path.dentry) {
+			/*
+			 * No cached dentry. Mounted dentries are pinned in the
+			 * cache, so that means that this dentry is probably
+			 * a symlink or the path doesn't actually point
+			 * to a mounted dentry.
+			 */
+			path.dentry = lookup_slow(&nd->last, dir,
+					     nd->flags | LOOKUP_NO_REVAL);
+			if (IS_ERR(path.dentry))
+				return PTR_ERR(path.dentry);
+		}
+	}
+	if (d_is_negative(path.dentry)) {
+		dput(path.dentry);
+		return -ENOENT;
+	}
+	path.mnt = nd->path.mnt;
+	return step_into(nd, &path, 0, d_backing_inode(path.dentry), 0);
+}
+
+/**
+ * path_mountpoint - look up a path to be umounted
+ * @nd:		lookup context
+ * @flags:	lookup flags
+ * @path:	pointer to container for result
+ *
+ * Look up the given name, but don't attempt to revalidate the last component.
+ * Returns 0 and "path" will be valid on success; Returns error otherwise.
+ */
+static int
+path_mountpoint(struct nameidata *nd, unsigned flags, struct path *path)
+{
+	const char *s = path_init(nd, flags);
+	int err;
+
+	while (!(err = link_path_walk(s, nd)) &&
+		(err = mountpoint_last(nd)) > 0) {
+		s = trailing_symlink(nd);
+	}
+	if (!err) {
+		*path = nd->path;
+		nd->path.mnt = NULL;
+		nd->path.dentry = NULL;
+		follow_mount(path);
+	}
+	terminate_walk(nd);
+	return err;
+}
+
+static int
+filename_mountpoint(int dfd, struct filename *name, struct path *path,
+			unsigned int flags)
+{
+	struct nameidata nd;
+	int error;
+	if (IS_ERR(name))
+		return PTR_ERR(name);
+	set_nameidata(&nd, dfd, name);
+	error = path_mountpoint(&nd, flags | LOOKUP_RCU, path);
+	if (unlikely(error == -ECHILD))
+		error = path_mountpoint(&nd, flags, path);
+	if (unlikely(error == -ESTALE))
+		error = path_mountpoint(&nd, flags | LOOKUP_REVAL, path);
+	if (likely(!error))
+		audit_inode(name, path->dentry, 0);
+	restore_nameidata();
+	putname(name);
+	return error;
+}
+
+/**
+ * user_path_mountpoint_at - lookup a path from userland in order to umount it
+ * @dfd:	directory file descriptor
+ * @name:	pathname from userland
+ * @flags:	lookup flags
+ * @path:	pointer to container to hold result
+ *
+ * A umount is a special case for path walking. We're not actually interested
+ * in the inode in this situation, and ESTALE errors can be a problem. We
+ * simply want track down the dentry and vfsmount attached at the mountpoint
+ * and avoid revalidating the last component.
+ *
+ * Returns 0 and populates "path" on success.
+ */
+int
+user_path_mountpoint_at(int dfd, const char __user *name, unsigned int flags,
+			struct path *path)
+{
+	return filename_mountpoint(dfd, getname(name), path, flags);
+}
+
+int
+kern_path_mountpoint(int dfd, const char *name, struct path *path,
+			unsigned int flags)
+{
+	return filename_mountpoint(dfd, getname_kernel(name), path, flags);
+}
+EXPORT_SYMBOL(kern_path_mountpoint);
+
+int __check_sticky(struct inode *dir, struct inode *inode)
+{
+	kuid_t fsuid = current_fsuid();
+
+	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
+ *  whether the type of victim is right.
+ *  1. We can't do it if dir is read-only (done in permission())
+ *  2. We should have write and exec permissions on dir
+ *  3. We can't remove anything from append-only dir
+ *  4. We can't do anything with immutable dir (done in permission())
+ *  5. If the sticky bit on dir is set we should either
+ *	a. be owner of dir, or
+ *	b. be owner of victim, or
+ *	c. have CAP_FOWNER capability
+ *  6. If the victim is append-only or immutable we can't do antyhing with
+ *     links pointing to it.
+ *  7. If the victim has an unknown uid or gid we can't change the inode.
+ *  8. If we were asked to remove a directory and victim isn't one - ENOTDIR.
+ *  9. If we were asked to remove a non-directory and victim isn't one - EISDIR.
+ * 10. We can't remove a root or mountpoint.
+ * 11. We don't allow removal of NFS sillyrenamed files; it's handled by
+ *     nfs_async_unlink().
+ */
+static int may_delete(struct vfsmount *mnt, struct inode *dir, struct dentry *victim, bool isdir)
+{
+	struct inode *inode = d_backing_inode(victim);
+	int error;
+
+	if (d_is_negative(victim))
+		return -ENOENT;
+	BUG_ON(!inode);
+
+	BUG_ON(victim->d_parent->d_inode != dir);
+
+	/* Inode writeback is not safe when the uid or gid are invalid. */
+	if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid))
+		return -EOVERFLOW;
+
+	audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
+
+	error = inode_permission2(mnt, dir, MAY_WRITE | MAY_EXEC);
+	if (error)
+		return error;
+	if (IS_APPEND(dir))
+		return -EPERM;
+
+	if (check_sticky(dir, inode) || IS_APPEND(inode) ||
+	    IS_IMMUTABLE(inode) || IS_SWAPFILE(inode) || HAS_UNMAPPED_ID(inode))
+		return -EPERM;
+	if (isdir) {
+		if (!d_is_dir(victim))
+			return -ENOTDIR;
+		if (IS_ROOT(victim))
+			return -EBUSY;
+	} else if (d_is_dir(victim))
+		return -EISDIR;
+	if (IS_DEADDIR(dir))
+		return -ENOENT;
+	if (victim->d_flags & DCACHE_NFSFS_RENAMED)
+		return -EBUSY;
+	return 0;
+}
+
+/*	Check whether we can create an object with dentry child in directory
+ *  dir.
+ *  1. We can't do it if child already exists (open has special treatment for
+ *     this case, but since we are inlined it's OK)
+ *  2. We can't do it if dir is read-only (done in permission())
+ *  3. We can't do it if the fs can't represent the fsuid or fsgid.
+ *  4. We should have write and exec permissions on dir
+ *  5. We can't do it if dir is immutable (done in permission())
+ */
+static inline int may_create(struct vfsmount *mnt, struct inode *dir, struct dentry *child)
+{
+	struct user_namespace *s_user_ns;
+	audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE);
+	if (child->d_inode)
+		return -EEXIST;
+	if (IS_DEADDIR(dir))
+		return -ENOENT;
+	s_user_ns = dir->i_sb->s_user_ns;
+	if (!kuid_has_mapping(s_user_ns, current_fsuid()) ||
+	    !kgid_has_mapping(s_user_ns, current_fsgid()))
+		return -EOVERFLOW;
+	return inode_permission2(mnt, dir, MAY_WRITE | MAY_EXEC);
+}
+
+/*
+ * p1 and p2 should be directories on the same fs.
+ */
+struct dentry *lock_rename(struct dentry *p1, struct dentry *p2)
+{
+	struct dentry *p;
+
+	if (p1 == p2) {
+		inode_lock_nested(p1->d_inode, I_MUTEX_PARENT);
+		return NULL;
+	}
+
+	mutex_lock(&p1->d_sb->s_vfs_rename_mutex);
+
+	p = d_ancestor(p2, p1);
+	if (p) {
+		inode_lock_nested(p2->d_inode, I_MUTEX_PARENT);
+		inode_lock_nested(p1->d_inode, I_MUTEX_CHILD);
+		return p;
+	}
+
+	p = d_ancestor(p1, p2);
+	if (p) {
+		inode_lock_nested(p1->d_inode, I_MUTEX_PARENT);
+		inode_lock_nested(p2->d_inode, I_MUTEX_CHILD);
+		return p;
+	}
+
+	inode_lock_nested(p1->d_inode, I_MUTEX_PARENT);
+	inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2);
+	return NULL;
+}
+EXPORT_SYMBOL(lock_rename);
+
+void unlock_rename(struct dentry *p1, struct dentry *p2)
+{
+	inode_unlock(p1->d_inode);
+	if (p1 != p2) {
+		inode_unlock(p2->d_inode);
+		mutex_unlock(&p1->d_sb->s_vfs_rename_mutex);
+	}
+}
+EXPORT_SYMBOL(unlock_rename);
+
+int vfs_create2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry,
+		umode_t mode, bool want_excl)
+{
+	int error = may_create(mnt, dir, dentry);
+	if (error)
+		return error;
+
+	if (!dir->i_op->create)
+		return -EACCES;	/* shouldn't it be ENOSYS? */
+	mode &= S_IALLUGO;
+	mode |= S_IFREG;
+	error = security_inode_create(dir, dentry, mode);
+	if (error)
+		return error;
+	error = dir->i_op->create(dir, dentry, mode, want_excl);
+	if (!error)
+		fsnotify_create(dir, dentry);
+	return error;
+}
+EXPORT_SYMBOL(vfs_create2);
+
+int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
+		bool want_excl)
+{
+	return vfs_create2(NULL, dir, dentry, mode, want_excl);
+}
+EXPORT_SYMBOL(vfs_create);
+
+int vfs_mkobj2(struct vfsmount *mnt, struct dentry *dentry, umode_t mode,
+		int (*f)(struct dentry *, umode_t, void *),
+		void *arg)
+{
+	struct inode *dir = dentry->d_parent->d_inode;
+	int error = may_create(mnt, dir, dentry);
+	if (error)
+		return error;
+
+	mode &= S_IALLUGO;
+	mode |= S_IFREG;
+	error = security_inode_create(dir, dentry, mode);
+	if (error)
+		return error;
+	error = f(dentry, mode, arg);
+	if (!error)
+		fsnotify_create(dir, dentry);
+	return error;
+}
+EXPORT_SYMBOL(vfs_mkobj2);
+
+
+int vfs_mkobj(struct dentry *dentry, umode_t mode,
+		int (*f)(struct dentry *, umode_t, void *),
+		void *arg)
+{
+	return vfs_mkobj2(NULL, dentry, mode, f, arg);
+}
+EXPORT_SYMBOL(vfs_mkobj);
+
+bool may_open_dev(const struct path *path)
+{
+	return !(path->mnt->mnt_flags & MNT_NODEV) &&
+		!(path->mnt->mnt_sb->s_iflags & SB_I_NODEV);
+}
+
+static int may_open(const struct path *path, int acc_mode, int flag)
+{
+	struct dentry *dentry = path->dentry;
+	struct vfsmount *mnt = path->mnt;
+	struct inode *inode = dentry->d_inode;
+	int error;
+
+	if (!inode)
+		return -ENOENT;
+
+	switch (inode->i_mode & S_IFMT) {
+	case S_IFLNK:
+		return -ELOOP;
+	case S_IFDIR:
+		if (acc_mode & MAY_WRITE)
+			return -EISDIR;
+		break;
+	case S_IFBLK:
+	case S_IFCHR:
+		if (!may_open_dev(path))
+			return -EACCES;
+		/*FALLTHRU*/
+	case S_IFIFO:
+	case S_IFSOCK:
+		flag &= ~O_TRUNC;
+		break;
+	}
+
+	error = inode_permission2(mnt, inode, MAY_OPEN | acc_mode);
+	if (error)
+		return error;
+
+	/*
+	 * An append-only file must be opened in append mode for writing.
+	 */
+	if (IS_APPEND(inode)) {
+		if  ((flag & O_ACCMODE) != O_RDONLY && !(flag & O_APPEND))
+			return -EPERM;
+		if (flag & O_TRUNC)
+			return -EPERM;
+	}
+
+	/* O_NOATIME can only be set by the owner or superuser */
+	if (flag & O_NOATIME && !inode_owner_or_capable(inode))
+		return -EPERM;
+
+	return 0;
+}
+
+static int handle_truncate(struct file *filp)
+{
+	const struct path *path = &filp->f_path;
+	struct inode *inode = path->dentry->d_inode;
+	int error = get_write_access(inode);
+	if (error)
+		return error;
+	/*
+	 * Refuse to truncate files with mandatory locks held on them.
+	 */
+	error = locks_verify_locked(filp);
+	if (!error)
+		error = security_path_truncate(path);
+	if (!error) {
+		error = do_truncate2(path->mnt, path->dentry, 0,
+				    ATTR_MTIME|ATTR_CTIME|ATTR_OPEN,
+				    filp);
+	}
+	put_write_access(inode);
+	return error;
+}
+
+static inline int open_to_namei_flags(int flag)
+{
+	if ((flag & O_ACCMODE) == 3)
+		flag--;
+	return flag;
+}
+
+static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t mode)
+{
+	struct user_namespace *s_user_ns;
+	int error = security_path_mknod(dir, dentry, mode, 0);
+	if (error)
+		return error;
+
+	s_user_ns = dir->dentry->d_sb->s_user_ns;
+	if (!kuid_has_mapping(s_user_ns, current_fsuid()) ||
+	    !kgid_has_mapping(s_user_ns, current_fsgid()))
+		return -EOVERFLOW;
+
+	error = inode_permission2(dir->mnt, dir->dentry->d_inode, MAY_WRITE | MAY_EXEC);
+	if (error)
+		return error;
+
+	return security_inode_create(dir->dentry->d_inode, dentry, mode);
+}
+
+/*
+ * Attempt to atomically look up, create and open a file from a negative
+ * dentry.
+ *
+ * Returns 0 if successful.  The file will have been created and attached to
+ * @file by the filesystem calling finish_open().
+ *
+ * If the file was looked up only or didn't need creating, FMODE_OPENED won't
+ * be set.  The caller will need to perform the open themselves.  @path will
+ * have been updated to point to the new dentry.  This may be negative.
+ *
+ * Returns an error code otherwise.
+ */
+static int atomic_open(struct nameidata *nd, struct dentry *dentry,
+			struct path *path, struct file *file,
+			const struct open_flags *op,
+			int open_flag, umode_t mode)
+{
+	struct dentry *const DENTRY_NOT_SET = (void *) -1UL;
+	struct inode *dir =  nd->path.dentry->d_inode;
+	int error;
+
+	if (!(~open_flag & (O_EXCL | O_CREAT)))	/* both O_EXCL and O_CREAT */
+		open_flag &= ~O_TRUNC;
+
+	if (nd->flags & LOOKUP_DIRECTORY)
+		open_flag |= O_DIRECTORY;
+
+	file->f_path.dentry = DENTRY_NOT_SET;
+	file->f_path.mnt = nd->path.mnt;
+	error = dir->i_op->atomic_open(dir, dentry, file,
+				       open_to_namei_flags(open_flag), mode);
+	d_lookup_done(dentry);
+	if (!error) {
+		if (file->f_mode & FMODE_OPENED) {
+			/*
+			 * We didn't have the inode before the open, so check open
+			 * permission here.
+			 */
+			int acc_mode = op->acc_mode;
+			if (file->f_mode & FMODE_CREATED) {
+				WARN_ON(!(open_flag & O_CREAT));
+				fsnotify_create(dir, dentry);
+				acc_mode = 0;
+			}
+			error = may_open(&file->f_path, acc_mode, open_flag);
+			if (WARN_ON(error > 0))
+				error = -EINVAL;
+		} else if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) {
+			error = -EIO;
+		} else {
+			if (file->f_path.dentry) {
+				dput(dentry);
+				dentry = file->f_path.dentry;
+			}
+			if (file->f_mode & FMODE_CREATED)
+				fsnotify_create(dir, dentry);
+			if (unlikely(d_is_negative(dentry))) {
+				error = -ENOENT;
+			} else {
+				path->dentry = dentry;
+				path->mnt = nd->path.mnt;
+				return 0;
+			}
+		}
+	}
+	dput(dentry);
+	return error;
+}
+
+/*
+ * Look up and maybe create and open the last component.
+ *
+ * Must be called with parent locked (exclusive in O_CREAT case).
+ *
+ * Returns 0 on success, that is, if
+ *  the file was successfully atomically created (if necessary) and opened, or
+ *  the file was not completely opened at this time, though lookups and
+ *  creations were performed.
+ * These case are distinguished by presence of FMODE_OPENED on file->f_mode.
+ * In the latter case dentry returned in @path might be negative if O_CREAT
+ * hadn't been specified.
+ *
+ * An error code is returned on failure.
+ */
+static int lookup_open(struct nameidata *nd, struct path *path,
+			struct file *file,
+			const struct open_flags *op,
+			bool got_write)
+{
+	struct dentry *dir = nd->path.dentry;
+	struct inode *dir_inode = dir->d_inode;
+	int open_flag = op->open_flag;
+	struct dentry *dentry;
+	int error, create_error = 0;
+	umode_t mode = op->mode;
+	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+
+	if (unlikely(IS_DEADDIR(dir_inode)))
+		return -ENOENT;
+
+	file->f_mode &= ~FMODE_CREATED;
+	dentry = d_lookup(dir, &nd->last);
+	for (;;) {
+		if (!dentry) {
+			dentry = d_alloc_parallel(dir, &nd->last, &wq);
+			if (IS_ERR(dentry))
+				return PTR_ERR(dentry);
+		}
+		if (d_in_lookup(dentry))
+			break;
+
+		error = d_revalidate(dentry, nd->flags);
+		if (likely(error > 0))
+			break;
+		if (error)
+			goto out_dput;
+		d_invalidate(dentry);
+		dput(dentry);
+		dentry = NULL;
+	}
+	if (dentry->d_inode) {
+		/* Cached positive dentry: will open in f_op->open */
+		goto out_no_open;
+	}
+
+	/*
+	 * Checking write permission is tricky, bacuse we don't know if we are
+	 * going to actually need it: O_CREAT opens should work as long as the
+	 * file exists.  But checking existence breaks atomicity.  The trick is
+	 * to check access and if not granted clear O_CREAT from the flags.
+	 *
+	 * Another problem is returing the "right" error value (e.g. for an
+	 * O_EXCL open we want to return EEXIST not EROFS).
+	 */
+	if (open_flag & O_CREAT) {
+		if (!IS_POSIXACL(dir->d_inode))
+			mode &= ~current_umask();
+		if (unlikely(!got_write)) {
+			create_error = -EROFS;
+			open_flag &= ~O_CREAT;
+			if (open_flag & (O_EXCL | O_TRUNC))
+				goto no_open;
+			/* No side effects, safe to clear O_CREAT */
+		} else {
+			create_error = may_o_create(&nd->path, dentry, mode);
+			if (create_error) {
+				open_flag &= ~O_CREAT;
+				if (open_flag & O_EXCL)
+					goto no_open;
+			}
+		}
+	} else if ((open_flag & (O_TRUNC|O_WRONLY|O_RDWR)) &&
+		   unlikely(!got_write)) {
+		/*
+		 * No O_CREATE -> atomicity not a requirement -> fall
+		 * back to lookup + open
+		 */
+		goto no_open;
+	}
+
+	if (dir_inode->i_op->atomic_open) {
+		error = atomic_open(nd, dentry, path, file, op, open_flag,
+				    mode);
+		if (unlikely(error == -ENOENT) && create_error)
+			error = create_error;
+		return error;
+	}
+
+no_open:
+	if (d_in_lookup(dentry)) {
+		struct dentry *res = dir_inode->i_op->lookup(dir_inode, dentry,
+							     nd->flags);
+		d_lookup_done(dentry);
+		if (unlikely(res)) {
+			if (IS_ERR(res)) {
+				error = PTR_ERR(res);
+				goto out_dput;
+			}
+			dput(dentry);
+			dentry = res;
+		}
+	}
+
+	/* Negative dentry, just create the file */
+	if (!dentry->d_inode && (open_flag & O_CREAT)) {
+		file->f_mode |= FMODE_CREATED;
+		audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE);
+		if (!dir_inode->i_op->create) {
+			error = -EACCES;
+			goto out_dput;
+		}
+		error = dir_inode->i_op->create(dir_inode, dentry, mode,
+						open_flag & O_EXCL);
+		if (error)
+			goto out_dput;
+		fsnotify_create(dir_inode, dentry);
+	}
+	if (unlikely(create_error) && !dentry->d_inode) {
+		error = create_error;
+		goto out_dput;
+	}
+out_no_open:
+	path->dentry = dentry;
+	path->mnt = nd->path.mnt;
+	return 0;
+
+out_dput:
+	dput(dentry);
+	return error;
+}
+
+/*
+ * Handle the last step of open()
+ */
+static int do_last(struct nameidata *nd,
+		   struct file *file, const struct open_flags *op)
+{
+	struct dentry *dir = nd->path.dentry;
+	kuid_t dir_uid = nd->inode->i_uid;
+	umode_t dir_mode = nd->inode->i_mode;
+	int open_flag = op->open_flag;
+	bool will_truncate = (open_flag & O_TRUNC) != 0;
+	bool got_write = false;
+	int acc_mode = op->acc_mode;
+	unsigned seq;
+	struct inode *inode;
+	struct path path;
+	int error;
+
+	nd->flags &= ~LOOKUP_PARENT;
+	nd->flags |= op->intent;
+
+	if (nd->last_type != LAST_NORM) {
+		error = handle_dots(nd, nd->last_type);
+		if (unlikely(error))
+			return error;
+		goto finish_open;
+	}
+
+	if (!(open_flag & O_CREAT)) {
+		if (nd->last.name[nd->last.len])
+			nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
+		/* we _can_ be in RCU mode here */
+		error = lookup_fast(nd, &path, &inode, &seq);
+		if (likely(error > 0))
+			goto finish_lookup;
+
+		if (error < 0)
+			return error;
+
+		BUG_ON(nd->inode != dir->d_inode);
+		BUG_ON(nd->flags & LOOKUP_RCU);
+	} else {
+		/* create side of things */
+		/*
+		 * This will *only* deal with leaving RCU mode - LOOKUP_JUMPED
+		 * has been cleared when we got to the last component we are
+		 * about to look up
+		 */
+		error = complete_walk(nd);
+		if (error)
+			return error;
+
+		audit_inode(nd->name, dir, LOOKUP_PARENT);
+		/* trailing slashes? */
+		if (unlikely(nd->last.name[nd->last.len]))
+			return -EISDIR;
+	}
+
+	if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) {
+		error = mnt_want_write(nd->path.mnt);
+		if (!error)
+			got_write = true;
+		/*
+		 * do _not_ fail yet - we might not need that or fail with
+		 * a different error; let lookup_open() decide; we'll be
+		 * dropping this one anyway.
+		 */
+	}
+	if (open_flag & O_CREAT)
+		inode_lock(dir->d_inode);
+	else
+		inode_lock_shared(dir->d_inode);
+	error = lookup_open(nd, &path, file, op, got_write);
+	if (open_flag & O_CREAT)
+		inode_unlock(dir->d_inode);
+	else
+		inode_unlock_shared(dir->d_inode);
+
+	if (error)
+		goto out;
+
+	if (file->f_mode & FMODE_OPENED) {
+		if ((file->f_mode & FMODE_CREATED) ||
+		    !S_ISREG(file_inode(file)->i_mode))
+			will_truncate = false;
+
+		audit_inode(nd->name, file->f_path.dentry, 0);
+		goto opened;
+	}
+
+	if (file->f_mode & FMODE_CREATED) {
+		/* Don't check for write permission, don't truncate */
+		open_flag &= ~O_TRUNC;
+		will_truncate = false;
+		acc_mode = 0;
+		path_to_nameidata(&path, nd);
+		goto finish_open_created;
+	}
+
+	/*
+	 * If atomic_open() acquired write access it is dropped now due to
+	 * possible mount and symlink following (this might be optimized away if
+	 * necessary...)
+	 */
+	if (got_write) {
+		mnt_drop_write(nd->path.mnt);
+		got_write = false;
+	}
+
+	error = follow_managed(&path, nd);
+	if (unlikely(error < 0))
+		return error;
+
+	if (unlikely(d_is_negative(path.dentry))) {
+		path_to_nameidata(&path, nd);
+		return -ENOENT;
+	}
+
+	/*
+	 * create/update audit record if it already exists.
+	 */
+	audit_inode(nd->name, path.dentry, 0);
+
+	if (unlikely((open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT))) {
+		path_to_nameidata(&path, nd);
+		return -EEXIST;
+	}
+
+	seq = 0;	/* out of RCU mode, so the value doesn't matter */
+	inode = d_backing_inode(path.dentry);
+finish_lookup:
+	error = step_into(nd, &path, 0, inode, seq);
+	if (unlikely(error))
+		return error;
+finish_open:
+	/* Why this, you ask?  _Now_ we might have grown LOOKUP_JUMPED... */
+	error = complete_walk(nd);
+	if (error)
+		return error;
+	audit_inode(nd->name, nd->path.dentry, 0);
+	if (open_flag & O_CREAT) {
+		error = -EISDIR;
+		if (d_is_dir(nd->path.dentry))
+			goto out;
+		error = may_create_in_sticky(dir_mode, dir_uid,
+					     d_backing_inode(nd->path.dentry));
+		if (unlikely(error))
+			goto out;
+	}
+	error = -ENOTDIR;
+	if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry))
+		goto out;
+	if (!d_is_reg(nd->path.dentry))
+		will_truncate = false;
+
+	if (will_truncate) {
+		error = mnt_want_write(nd->path.mnt);
+		if (error)
+			goto out;
+		got_write = true;
+	}
+finish_open_created:
+	error = may_open(&nd->path, acc_mode, open_flag);
+	if (error)
+		goto out;
+	BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */
+	error = vfs_open(&nd->path, file);
+	if (error)
+		goto out;
+opened:
+	error = ima_file_check(file, op->acc_mode);
+	if (!error && will_truncate)
+		error = handle_truncate(file);
+out:
+	if (unlikely(error > 0)) {
+		WARN_ON(1);
+		error = -EINVAL;
+	}
+	if (got_write)
+		mnt_drop_write(nd->path.mnt);
+	return error;
+}
+
+struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag)
+{
+	struct dentry *child = NULL;
+	struct inode *dir = dentry->d_inode;
+	struct inode *inode;
+	int error;
+
+	/* we want directory to be writable */
+	error = inode_permission2(ERR_PTR(-EOPNOTSUPP), dir,
+					MAY_WRITE | MAY_EXEC);
+	if (error)
+		goto out_err;
+	error = -EOPNOTSUPP;
+	if (!dir->i_op->tmpfile)
+		goto out_err;
+	error = -ENOMEM;
+	child = d_alloc(dentry, &slash_name);
+	if (unlikely(!child))
+		goto out_err;
+	error = dir->i_op->tmpfile(dir, child, mode);
+	if (error)
+		goto out_err;
+	error = -ENOENT;
+	inode = child->d_inode;
+	if (unlikely(!inode))
+		goto out_err;
+	if (!(open_flag & O_EXCL)) {
+		spin_lock(&inode->i_lock);
+		inode->i_state |= I_LINKABLE;
+		spin_unlock(&inode->i_lock);
+	}
+	return child;
+
+out_err:
+	dput(child);
+	return ERR_PTR(error);
+}
+EXPORT_SYMBOL(vfs_tmpfile);
+
+static int do_tmpfile(struct nameidata *nd, unsigned flags,
+		const struct open_flags *op,
+		struct file *file)
+{
+	struct dentry *child;
+	struct path path;
+	int error = path_lookupat(nd, flags | LOOKUP_DIRECTORY, &path);
+	if (unlikely(error))
+		return error;
+	error = mnt_want_write(path.mnt);
+	if (unlikely(error))
+		goto out;
+	child = vfs_tmpfile(path.dentry, op->mode, op->open_flag);
+	error = PTR_ERR(child);
+	if (IS_ERR(child))
+		goto out2;
+	dput(path.dentry);
+	path.dentry = child;
+	audit_inode(nd->name, child, 0);
+	/* Don't check for other permissions, the inode was just created */
+	error = may_open(&path, 0, op->open_flag);
+	if (error)
+		goto out2;
+	file->f_path.mnt = path.mnt;
+	error = finish_open(file, child, NULL);
+out2:
+	mnt_drop_write(path.mnt);
+out:
+	path_put(&path);
+	return error;
+}
+
+static int do_o_path(struct nameidata *nd, unsigned flags, struct file *file)
+{
+	struct path path;
+	int error = path_lookupat(nd, flags, &path);
+	if (!error) {
+		audit_inode(nd->name, path.dentry, 0);
+		error = vfs_open(&path, file);
+		path_put(&path);
+	}
+	return error;
+}
+
+static struct file *path_openat(struct nameidata *nd,
+			const struct open_flags *op, unsigned flags)
+{
+	struct file *file;
+	int error;
+
+	file = alloc_empty_file(op->open_flag, current_cred());
+	if (IS_ERR(file))
+		return file;
+
+	if (unlikely(file->f_flags & __O_TMPFILE)) {
+		error = do_tmpfile(nd, flags, op, file);
+	} else if (unlikely(file->f_flags & O_PATH)) {
+		error = do_o_path(nd, flags, file);
+	} else {
+		const char *s = path_init(nd, flags);
+		while (!(error = link_path_walk(s, nd)) &&
+			(error = do_last(nd, file, op)) > 0) {
+			nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
+			s = trailing_symlink(nd);
+		}
+		terminate_walk(nd);
+	}
+	if (likely(!error)) {
+		if (likely(file->f_mode & FMODE_OPENED))
+			return file;
+		WARN_ON(1);
+		error = -EINVAL;
+	}
+	fput(file);
+	if (error == -EOPENSTALE) {
+		if (flags & LOOKUP_RCU)
+			error = -ECHILD;
+		else
+			error = -ESTALE;
+	}
+	return ERR_PTR(error);
+}
+
+struct file *do_filp_open(int dfd, struct filename *pathname,
+		const struct open_flags *op)
+{
+	struct nameidata nd;
+	int flags = op->lookup_flags;
+	struct file *filp;
+
+	set_nameidata(&nd, dfd, pathname);
+	filp = path_openat(&nd, op, flags | LOOKUP_RCU);
+	if (unlikely(filp == ERR_PTR(-ECHILD)))
+		filp = path_openat(&nd, op, flags);
+	if (unlikely(filp == ERR_PTR(-ESTALE)))
+		filp = path_openat(&nd, op, flags | LOOKUP_REVAL);
+	restore_nameidata();
+	return filp;
+}
+
+struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt,
+		const char *name, const struct open_flags *op)
+{
+	struct nameidata nd;
+	struct file *file;
+	struct filename *filename;
+	int flags = op->lookup_flags | LOOKUP_ROOT;
+
+	nd.root.mnt = mnt;
+	nd.root.dentry = dentry;
+
+	if (d_is_symlink(dentry) && op->intent & LOOKUP_OPEN)
+		return ERR_PTR(-ELOOP);
+
+	filename = getname_kernel(name);
+	if (IS_ERR(filename))
+		return ERR_CAST(filename);
+
+	set_nameidata(&nd, -1, filename);
+	file = path_openat(&nd, op, flags | LOOKUP_RCU);
+	if (unlikely(file == ERR_PTR(-ECHILD)))
+		file = path_openat(&nd, op, flags);
+	if (unlikely(file == ERR_PTR(-ESTALE)))
+		file = path_openat(&nd, op, flags | LOOKUP_REVAL);
+	restore_nameidata();
+	putname(filename);
+	return file;
+}
+
+static struct dentry *filename_create(int dfd, struct filename *name,
+				struct path *path, unsigned int lookup_flags)
+{
+	struct dentry *dentry = ERR_PTR(-EEXIST);
+	struct qstr last;
+	int type;
+	int err2;
+	int error;
+	bool is_dir = (lookup_flags & LOOKUP_DIRECTORY);
+
+	/*
+	 * Note that only LOOKUP_REVAL and LOOKUP_DIRECTORY matter here. Any
+	 * other flags passed in are ignored!
+	 */
+	lookup_flags &= LOOKUP_REVAL;
+
+	name = filename_parentat(dfd, name, lookup_flags, path, &last, &type);
+	if (IS_ERR(name))
+		return ERR_CAST(name);
+
+	/*
+	 * Yucky last component or no last component at all?
+	 * (foo/., foo/.., /////)
+	 */
+	if (unlikely(type != LAST_NORM))
+		goto out;
+
+	/* don't fail immediately if it's r/o, at least try to report other errors */
+	err2 = mnt_want_write(path->mnt);
+	/*
+	 * Do the final lookup.
+	 */
+	lookup_flags |= LOOKUP_CREATE | LOOKUP_EXCL;
+	inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT);
+	dentry = __lookup_hash(&last, path->dentry, lookup_flags);
+	if (IS_ERR(dentry))
+		goto unlock;
+
+	error = -EEXIST;
+	if (d_is_positive(dentry))
+		goto fail;
+
+	/*
+	 * Special case - lookup gave negative, but... we had foo/bar/
+	 * From the vfs_mknod() POV we just have a negative dentry -
+	 * all is fine. Let's be bastards - you had / on the end, you've
+	 * been asking for (non-existent) directory. -ENOENT for you.
+	 */
+	if (unlikely(!is_dir && last.name[last.len])) {
+		error = -ENOENT;
+		goto fail;
+	}
+	if (unlikely(err2)) {
+		error = err2;
+		goto fail;
+	}
+	putname(name);
+	return dentry;
+fail:
+	dput(dentry);
+	dentry = ERR_PTR(error);
+unlock:
+	inode_unlock(path->dentry->d_inode);
+	if (!err2)
+		mnt_drop_write(path->mnt);
+out:
+	path_put(path);
+	putname(name);
+	return dentry;
+}
+
+struct dentry *kern_path_create(int dfd, const char *pathname,
+				struct path *path, unsigned int lookup_flags)
+{
+	return filename_create(dfd, getname_kernel(pathname),
+				path, lookup_flags);
+}
+EXPORT_SYMBOL(kern_path_create);
+
+void done_path_create(struct path *path, struct dentry *dentry)
+{
+	dput(dentry);
+	inode_unlock(path->dentry->d_inode);
+	mnt_drop_write(path->mnt);
+	path_put(path);
+}
+EXPORT_SYMBOL(done_path_create);
+
+inline struct dentry *user_path_create(int dfd, const char __user *pathname,
+				struct path *path, unsigned int lookup_flags)
+{
+	return filename_create(dfd, getname(pathname), path, lookup_flags);
+}
+EXPORT_SYMBOL(user_path_create);
+
+int vfs_mknod2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
+{
+	int error = may_create(mnt, dir, dentry);
+
+	if (error)
+		return error;
+
+	if ((S_ISCHR(mode) || S_ISBLK(mode)) && !capable(CAP_MKNOD))
+		return -EPERM;
+
+	if (!dir->i_op->mknod)
+		return -EPERM;
+
+	error = devcgroup_inode_mknod(mode, dev);
+	if (error)
+		return error;
+
+	error = security_inode_mknod(dir, dentry, mode, dev);
+	if (error)
+		return error;
+
+	error = dir->i_op->mknod(dir, dentry, mode, dev);
+	if (!error)
+		fsnotify_create(dir, dentry);
+	return error;
+}
+EXPORT_SYMBOL(vfs_mknod2);
+
+int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
+{
+	return vfs_mknod2(NULL, dir, dentry, mode, dev);
+}
+EXPORT_SYMBOL(vfs_mknod);
+
+static int may_mknod(umode_t mode)
+{
+	switch (mode & S_IFMT) {
+	case S_IFREG:
+	case S_IFCHR:
+	case S_IFBLK:
+	case S_IFIFO:
+	case S_IFSOCK:
+	case 0: /* zero mode translates to S_IFREG */
+		return 0;
+	case S_IFDIR:
+		return -EPERM;
+	default:
+		return -EINVAL;
+	}
+}
+
+long do_mknodat(int dfd, const char __user *filename, umode_t mode,
+		unsigned int dev)
+{
+	struct dentry *dentry;
+	struct path path;
+	int error;
+	unsigned int lookup_flags = 0;
+
+	error = may_mknod(mode);
+	if (error)
+		return error;
+retry:
+	dentry = user_path_create(dfd, filename, &path, lookup_flags);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	if (!IS_POSIXACL(path.dentry->d_inode))
+		mode &= ~current_umask();
+	error = security_path_mknod(&path, dentry, mode, dev);
+	if (error)
+		goto out;
+	switch (mode & S_IFMT) {
+		case 0: case S_IFREG:
+			error = vfs_create2(path.mnt, path.dentry->d_inode,dentry,mode,true);
+			if (!error)
+				ima_post_path_mknod(dentry);
+			break;
+		case S_IFCHR: case S_IFBLK:
+			error = vfs_mknod2(path.mnt, path.dentry->d_inode,dentry,mode,
+					new_decode_dev(dev));
+			break;
+		case S_IFIFO: case S_IFSOCK:
+			error = vfs_mknod(path.dentry->d_inode,dentry,mode,0);
+			break;
+	}
+out:
+	done_path_create(&path, dentry);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
+	return error;
+}
+
+SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode,
+		unsigned int, dev)
+{
+	return do_mknodat(dfd, filename, mode, dev);
+}
+
+SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev)
+{
+	return do_mknodat(AT_FDCWD, filename, mode, dev);
+}
+
+int vfs_mkdir2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+	int error = may_create(mnt, dir, dentry);
+	unsigned max_links = dir->i_sb->s_max_links;
+
+	if (error)
+		return error;
+
+	if (!dir->i_op->mkdir)
+		return -EPERM;
+
+	mode &= (S_IRWXUGO|S_ISVTX);
+	error = security_inode_mkdir(dir, dentry, mode);
+	if (error)
+		return error;
+
+	if (max_links && dir->i_nlink >= max_links)
+		return -EMLINK;
+
+	error = dir->i_op->mkdir(dir, dentry, mode);
+	if (!error)
+		fsnotify_mkdir(dir, dentry);
+	return error;
+}
+EXPORT_SYMBOL(vfs_mkdir2);
+
+int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+	return vfs_mkdir2(NULL, dir, dentry, mode);
+}
+EXPORT_SYMBOL(vfs_mkdir);
+
+long do_mkdirat(int dfd, const char __user *pathname, umode_t mode)
+{
+	struct dentry *dentry;
+	struct path path;
+	int error;
+	unsigned int lookup_flags = LOOKUP_DIRECTORY;
+
+retry:
+	dentry = user_path_create(dfd, pathname, &path, lookup_flags);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	if (!IS_POSIXACL(path.dentry->d_inode))
+		mode &= ~current_umask();
+	error = security_path_mkdir(&path, dentry, mode);
+	if (!error)
+		error = vfs_mkdir2(path.mnt, path.dentry->d_inode, dentry, mode);
+	done_path_create(&path, dentry);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
+	return error;
+}
+
+SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode)
+{
+	return do_mkdirat(dfd, pathname, mode);
+}
+
+SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode)
+{
+	return do_mkdirat(AT_FDCWD, pathname, mode);
+}
+
+int vfs_rmdir2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry)
+{
+	int error = may_delete(mnt, dir, dentry, 1);
+
+	if (error)
+		return error;
+
+	if (!dir->i_op->rmdir)
+		return -EPERM;
+
+	dget(dentry);
+	inode_lock(dentry->d_inode);
+
+	error = -EBUSY;
+	if (is_local_mountpoint(dentry))
+		goto out;
+
+	error = security_inode_rmdir(dir, dentry);
+	if (error)
+		goto out;
+
+	error = dir->i_op->rmdir(dir, dentry);
+	if (error)
+		goto out;
+
+	shrink_dcache_parent(dentry);
+	dentry->d_inode->i_flags |= S_DEAD;
+	dont_mount(dentry);
+	detach_mounts(dentry);
+
+out:
+	inode_unlock(dentry->d_inode);
+	dput(dentry);
+	if (!error)
+		d_delete(dentry);
+	return error;
+}
+EXPORT_SYMBOL(vfs_rmdir2);
+
+int vfs_rmdir(struct inode *dir, struct dentry *dentry)
+{
+	return vfs_rmdir2(NULL, dir, dentry);
+}
+EXPORT_SYMBOL(vfs_rmdir);
+
+long do_rmdir(int dfd, const char __user *pathname)
+{
+	int error = 0;
+	struct filename *name;
+	struct dentry *dentry;
+	struct path path;
+	struct qstr last;
+	int type;
+	unsigned int lookup_flags = 0;
+retry:
+	name = filename_parentat(dfd, getname(pathname), lookup_flags,
+				&path, &last, &type);
+	if (IS_ERR(name))
+		return PTR_ERR(name);
+
+	switch (type) {
+	case LAST_DOTDOT:
+		error = -ENOTEMPTY;
+		goto exit1;
+	case LAST_DOT:
+		error = -EINVAL;
+		goto exit1;
+	case LAST_ROOT:
+		error = -EBUSY;
+		goto exit1;
+	}
+
+	error = mnt_want_write(path.mnt);
+	if (error)
+		goto exit1;
+
+	inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT);
+	dentry = __lookup_hash(&last, path.dentry, lookup_flags);
+	error = PTR_ERR(dentry);
+	if (IS_ERR(dentry))
+		goto exit2;
+	if (!dentry->d_inode) {
+		error = -ENOENT;
+		goto exit3;
+	}
+	error = security_path_rmdir(&path, dentry);
+	if (error)
+		goto exit3;
+	error = vfs_rmdir2(path.mnt, path.dentry->d_inode, dentry);
+exit3:
+	dput(dentry);
+exit2:
+	inode_unlock(path.dentry->d_inode);
+	mnt_drop_write(path.mnt);
+exit1:
+	path_put(&path);
+	putname(name);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
+	return error;
+}
+
+SYSCALL_DEFINE1(rmdir, const char __user *, pathname)
+{
+	return do_rmdir(AT_FDCWD, pathname);
+}
+
+/**
+ * vfs_unlink - unlink a filesystem object
+ * @dir:	parent directory
+ * @dentry:	victim
+ * @delegated_inode: returns victim inode, if the inode is delegated.
+ *
+ * The caller must hold dir->i_mutex.
+ *
+ * If vfs_unlink discovers a delegation, it will return -EWOULDBLOCK and
+ * return a reference to the inode in delegated_inode.  The caller
+ * should then break the delegation on that inode and retry.  Because
+ * breaking a delegation may take a long time, the caller should drop
+ * dir->i_mutex 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_unlink2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry, struct inode **delegated_inode)
+{
+	struct inode *target = dentry->d_inode;
+	int error = may_delete(mnt, dir, dentry, 0);
+
+	if (error)
+		return error;
+
+	if (!dir->i_op->unlink)
+		return -EPERM;
+
+	inode_lock(target);
+	if (is_local_mountpoint(dentry))
+		error = -EBUSY;
+	else {
+		error = security_inode_unlink(dir, dentry);
+		if (!error) {
+			error = try_break_deleg(target, delegated_inode);
+			if (error)
+				goto out;
+			error = dir->i_op->unlink(dir, dentry);
+			if (!error) {
+				dont_mount(dentry);
+				detach_mounts(dentry);
+			}
+		}
+	}
+out:
+	inode_unlock(target);
+
+	/* We don't d_delete() NFS sillyrenamed files--they still exist. */
+	if (!error && !(dentry->d_flags & DCACHE_NFSFS_RENAMED)) {
+		fsnotify_link_count(target);
+		d_delete(dentry);
+	}
+
+	return error;
+}
+EXPORT_SYMBOL(vfs_unlink2);
+
+int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode)
+{
+	return vfs_unlink2(NULL, dir, dentry, delegated_inode);
+}
+EXPORT_SYMBOL(vfs_unlink);
+
+/*
+ * Make sure that the actual truncation of the file will occur outside its
+ * directory's i_mutex.  Truncate can take a long time if there is a lot of
+ * writeout happening, and we don't want to prevent access to the directory
+ * while waiting on the I/O.
+ */
+long do_unlinkat(int dfd, struct filename *name)
+{
+	int error;
+	struct dentry *dentry;
+	struct path path;
+	struct qstr last;
+	int type;
+	struct inode *inode = NULL;
+	struct inode *delegated_inode = NULL;
+	unsigned int lookup_flags = 0;
+retry:
+	name = filename_parentat(dfd, name, lookup_flags, &path, &last, &type);
+	if (IS_ERR(name))
+		return PTR_ERR(name);
+
+	error = -EISDIR;
+	if (type != LAST_NORM)
+		goto exit1;
+
+	error = mnt_want_write(path.mnt);
+	if (error)
+		goto exit1;
+retry_deleg:
+	inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT);
+	dentry = __lookup_hash(&last, path.dentry, lookup_flags);
+	error = PTR_ERR(dentry);
+	if (!IS_ERR(dentry)) {
+		/* Why not before? Because we want correct error value */
+		if (last.name[last.len])
+			goto slashes;
+		inode = dentry->d_inode;
+		if (d_is_negative(dentry))
+			goto slashes;
+		ihold(inode);
+		error = security_path_unlink(&path, dentry);
+		if (error)
+			goto exit2;
+		error = vfs_unlink2(path.mnt, path.dentry->d_inode, dentry, &delegated_inode);
+exit2:
+		dput(dentry);
+	}
+	inode_unlock(path.dentry->d_inode);
+	if (inode)
+		iput(inode);	/* truncate the inode here */
+	inode = NULL;
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
+	mnt_drop_write(path.mnt);
+exit1:
+	path_put(&path);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		inode = NULL;
+		goto retry;
+	}
+	putname(name);
+	return error;
+
+slashes:
+	if (d_is_negative(dentry))
+		error = -ENOENT;
+	else if (d_is_dir(dentry))
+		error = -EISDIR;
+	else
+		error = -ENOTDIR;
+	goto exit2;
+}
+
+SYSCALL_DEFINE3(unlinkat, int, dfd, const char __user *, pathname, int, flag)
+{
+	if ((flag & ~AT_REMOVEDIR) != 0)
+		return -EINVAL;
+
+	if (flag & AT_REMOVEDIR)
+		return do_rmdir(dfd, pathname);
+
+	return do_unlinkat(dfd, getname(pathname));
+}
+
+SYSCALL_DEFINE1(unlink, const char __user *, pathname)
+{
+	return do_unlinkat(AT_FDCWD, getname(pathname));
+}
+
+int vfs_symlink2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry, const char *oldname)
+{
+	int error = may_create(mnt, dir, dentry);
+
+	if (error)
+		return error;
+
+	if (!dir->i_op->symlink)
+		return -EPERM;
+
+	error = security_inode_symlink(dir, dentry, oldname);
+	if (error)
+		return error;
+
+	error = dir->i_op->symlink(dir, dentry, oldname);
+	if (!error)
+		fsnotify_create(dir, dentry);
+	return error;
+}
+EXPORT_SYMBOL(vfs_symlink2);
+
+int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname)
+{
+	return vfs_symlink2(NULL, dir, dentry, oldname);
+}
+EXPORT_SYMBOL(vfs_symlink);
+
+long do_symlinkat(const char __user *oldname, int newdfd,
+		  const char __user *newname)
+{
+	int error;
+	struct filename *from;
+	struct dentry *dentry;
+	struct path path;
+	unsigned int lookup_flags = 0;
+
+	from = getname(oldname);
+	if (IS_ERR(from))
+		return PTR_ERR(from);
+retry:
+	dentry = user_path_create(newdfd, newname, &path, lookup_flags);
+	error = PTR_ERR(dentry);
+	if (IS_ERR(dentry))
+		goto out_putname;
+
+	error = security_path_symlink(&path, dentry, from->name);
+	if (!error)
+		error = vfs_symlink2(path.mnt, path.dentry->d_inode, dentry, from->name);
+	done_path_create(&path, dentry);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
+out_putname:
+	putname(from);
+	return error;
+}
+
+SYSCALL_DEFINE3(symlinkat, const char __user *, oldname,
+		int, newdfd, const char __user *, newname)
+{
+	return do_symlinkat(oldname, newdfd, newname);
+}
+
+SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newname)
+{
+	return do_symlinkat(oldname, AT_FDCWD, newname);
+}
+
+/**
+ * vfs_link - create a new link
+ * @old_dentry:	object to be linked
+ * @dir:	new parent
+ * @new_dentry:	where to create the new link
+ * @delegated_inode: returns inode needing a delegation break
+ *
+ * The caller must hold dir->i_mutex
+ *
+ * If vfs_link discovers a delegation on the to-be-linked file in need
+ * of breaking, 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 the i_mutex 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_link2(struct vfsmount *mnt, struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode)
+{
+	struct inode *inode = old_dentry->d_inode;
+	unsigned max_links = dir->i_sb->s_max_links;
+	int error;
+
+	if (!inode)
+		return -ENOENT;
+
+	error = may_create(mnt, dir, new_dentry);
+	if (error)
+		return error;
+
+	if (dir->i_sb != inode->i_sb)
+		return -EXDEV;
+
+	/*
+	 * A link to an append-only or immutable file cannot be created.
+	 */
+	if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
+		return -EPERM;
+	/*
+	 * Updating the link count will likely cause i_uid and i_gid to
+	 * be writen back improperly if their true value is unknown to
+	 * the vfs.
+	 */
+	if (HAS_UNMAPPED_ID(inode))
+		return -EPERM;
+	if (!dir->i_op->link)
+		return -EPERM;
+	if (S_ISDIR(inode->i_mode))
+		return -EPERM;
+
+	error = security_inode_link(old_dentry, dir, new_dentry);
+	if (error)
+		return error;
+
+	inode_lock(inode);
+	/* Make sure we don't allow creating hardlink to an unlinked file */
+	if (inode->i_nlink == 0 && !(inode->i_state & I_LINKABLE))
+		error =  -ENOENT;
+	else if (max_links && inode->i_nlink >= max_links)
+		error = -EMLINK;
+	else {
+		error = try_break_deleg(inode, delegated_inode);
+		if (!error)
+			error = dir->i_op->link(old_dentry, dir, new_dentry);
+	}
+
+	if (!error && (inode->i_state & I_LINKABLE)) {
+		spin_lock(&inode->i_lock);
+		inode->i_state &= ~I_LINKABLE;
+		spin_unlock(&inode->i_lock);
+	}
+	inode_unlock(inode);
+	if (!error)
+		fsnotify_link(dir, inode, new_dentry);
+	return error;
+}
+EXPORT_SYMBOL(vfs_link2);
+
+int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode)
+{
+	return vfs_link2(NULL, old_dentry, dir, new_dentry, delegated_inode);
+}
+EXPORT_SYMBOL(vfs_link);
+
+/*
+ * Hardlinks are often used in delicate situations.  We avoid
+ * security-related surprises by not following symlinks on the
+ * newname.  --KAB
+ *
+ * We don't follow them on the oldname either to be compatible
+ * with linux 2.0, and to avoid hard-linking to directories
+ * and other special files.  --ADM
+ */
+int do_linkat(int olddfd, const char __user *oldname, int newdfd,
+	      const char __user *newname, int flags)
+{
+	struct dentry *new_dentry;
+	struct path old_path, new_path;
+	struct inode *delegated_inode = NULL;
+	int how = 0;
+	int error;
+
+	if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0)
+		return -EINVAL;
+	/*
+	 * To use null names we require CAP_DAC_READ_SEARCH
+	 * This ensures that not everyone will be able to create
+	 * handlink using the passed filedescriptor.
+	 */
+	if (flags & AT_EMPTY_PATH) {
+		if (!capable(CAP_DAC_READ_SEARCH))
+			return -ENOENT;
+		how = LOOKUP_EMPTY;
+	}
+
+	if (flags & AT_SYMLINK_FOLLOW)
+		how |= LOOKUP_FOLLOW;
+retry:
+	error = user_path_at(olddfd, oldname, how, &old_path);
+	if (error)
+		return error;
+
+	new_dentry = user_path_create(newdfd, newname, &new_path,
+					(how & LOOKUP_REVAL));
+	error = PTR_ERR(new_dentry);
+	if (IS_ERR(new_dentry))
+		goto out;
+
+	error = -EXDEV;
+	if (old_path.mnt != new_path.mnt)
+		goto out_dput;
+	error = may_linkat(&old_path);
+	if (unlikely(error))
+		goto out_dput;
+	error = security_path_link(old_path.dentry, &new_path, new_dentry);
+	if (error)
+		goto out_dput;
+	error = vfs_link2(old_path.mnt, old_path.dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode);
+out_dput:
+	done_path_create(&new_path, new_dentry);
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error) {
+			path_put(&old_path);
+			goto retry;
+		}
+	}
+	if (retry_estale(error, how)) {
+		path_put(&old_path);
+		how |= LOOKUP_REVAL;
+		goto retry;
+	}
+out:
+	path_put(&old_path);
+
+	return error;
+}
+
+SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname,
+		int, newdfd, const char __user *, newname, int, flags)
+{
+	return do_linkat(olddfd, oldname, newdfd, newname, flags);
+}
+
+SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname)
+{
+	return do_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:
+ *
+ *	a) we can get into loop creation.
+ *	b) race potential - two innocent renames can create a loop together.
+ *	   That's where 4.4 screws up. Current fix: serialization on
+ *	   sb->s_vfs_rename_mutex. We might be more accurate, but that's another
+ *	   story.
+ *	c) we have to lock _four_ objects - parents and victim (if it exists),
+ *	   and source (if it is not a directory).
+ *	   And that - after we got ->i_mutex on parents (until then we don't know
+ *	   whether the target exists).  Solution: try to be smart with locking
+ *	   order for inodes.  We rely on the fact that tree topology may change
+ *	   only under ->s_vfs_rename_mutex _and_ that parent of the object we
+ *	   move will be locked.  Thus we can rank directories by the tree
+ *	   (ancestors first) and rank all non-directories after them.
+ *	   That works since everybody except rename does "lock parent, lookup,
+ *	   lock child" and rename is under ->s_vfs_rename_mutex.
+ *	   HOWEVER, it relies on the assumption that any object with ->lookup()
+ *	   has no more than 1 dentry.  If "hybrid" objects will ever appear,
+ *	   we'd better make sure that there's no link(2) for them.
+ *	d) conversion from fhandle to dentry may come in the wrong moment - when
+ *	   we are removing the target. Solution: we will have to grab ->i_mutex
+ *	   in the fhandle_to_dentry code. [FIXME - current nfsfh.c relies on
+ *	   ->i_mutex on parents, which works but leads to some truly excessive
+ *	   locking].
+ */
+int vfs_rename2(struct vfsmount *mnt,
+	       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;
+	bool is_dir = d_is_dir(old_dentry);
+	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;
+	struct name_snapshot old_name;
+
+	if (source == target)
+		return 0;
+
+	error = may_delete(mnt, old_dir, old_dentry, is_dir);
+	if (error)
+		return error;
+
+	if (!target) {
+		error = may_create(mnt, new_dir, new_dentry);
+	} else {
+		new_is_dir = d_is_dir(new_dentry);
+
+		if (!(flags & RENAME_EXCHANGE))
+			error = may_delete(mnt, new_dir, new_dentry, is_dir);
+		else
+			error = may_delete(mnt, new_dir, new_dentry, new_is_dir);
+	}
+	if (error)
+		return error;
+
+	if (!old_dir->i_op->rename)
+		return -EPERM;
+
+	/*
+	 * If we are going to change the parent - check write permissions,
+	 * we'll need to flip '..'.
+	 */
+	if (new_dir != old_dir) {
+		if (is_dir) {
+			error = inode_permission2(mnt, source, MAY_WRITE);
+			if (error)
+				return error;
+		}
+		if ((flags & RENAME_EXCHANGE) && new_is_dir) {
+			error = inode_permission2(mnt, target, MAY_WRITE);
+			if (error)
+				return error;
+		}
+	}
+
+	error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry,
+				      flags);
+	if (error)
+		return error;
+
+	take_dentry_name_snapshot(&old_name, old_dentry);
+	dget(new_dentry);
+	if (!is_dir || (flags & RENAME_EXCHANGE))
+		lock_two_nondirectories(source, target);
+	else if (target)
+		inode_lock(target);
+
+	error = -EBUSY;
+	if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry))
+		goto out;
+
+	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) {
+		error = try_break_deleg(source, delegated_inode);
+		if (error)
+			goto out;
+	}
+	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, flags);
+	if (error)
+		goto out;
+
+	if (!(flags & RENAME_EXCHANGE) && target) {
+		if (is_dir) {
+			shrink_dcache_parent(new_dentry);
+			target->i_flags |= S_DEAD;
+		}
+		dont_mount(new_dentry);
+		detach_mounts(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:
+	if (!is_dir || (flags & RENAME_EXCHANGE))
+		unlock_two_nondirectories(source, target);
+	else if (target)
+		inode_unlock(target);
+	dput(new_dentry);
+	if (!error) {
+		fsnotify_move(old_dir, new_dir, old_name.name, is_dir,
+			      !(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);
+		}
+	}
+	release_dentry_name_snapshot(&old_name);
+
+	return error;
+}
+EXPORT_SYMBOL(vfs_rename2);
+
+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)
+{
+	return vfs_rename2(NULL, old_dir, old_dentry, new_dir, new_dentry, delegated_inode, flags);
+}
+EXPORT_SYMBOL(vfs_rename);
+
+static int do_renameat2(int olddfd, const char __user *oldname, int newdfd,
+			const char __user *newname, unsigned int flags)
+{
+	struct dentry *old_dentry, *new_dentry;
+	struct dentry *trap;
+	struct path old_path, new_path;
+	struct qstr old_last, new_last;
+	int old_type, new_type;
+	struct inode *delegated_inode = NULL;
+	struct filename *from;
+	struct filename *to;
+	unsigned int lookup_flags = 0, target_flags = LOOKUP_RENAME_TARGET;
+	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;
+
+	if (flags & RENAME_EXCHANGE)
+		target_flags = 0;
+
+retry:
+	from = filename_parentat(olddfd, getname(oldname), lookup_flags,
+				&old_path, &old_last, &old_type);
+	if (IS_ERR(from)) {
+		error = PTR_ERR(from);
+		goto exit;
+	}
+
+	to = filename_parentat(newdfd, getname(newname), lookup_flags,
+				&new_path, &new_last, &new_type);
+	if (IS_ERR(to)) {
+		error = PTR_ERR(to);
+		goto exit1;
+	}
+
+	error = -EXDEV;
+	if (old_path.mnt != new_path.mnt)
+		goto exit2;
+
+	error = -EBUSY;
+	if (old_type != LAST_NORM)
+		goto exit2;
+
+	if (flags & RENAME_NOREPLACE)
+		error = -EEXIST;
+	if (new_type != LAST_NORM)
+		goto exit2;
+
+	error = mnt_want_write(old_path.mnt);
+	if (error)
+		goto exit2;
+
+retry_deleg:
+	trap = lock_rename(new_path.dentry, old_path.dentry);
+
+	old_dentry = __lookup_hash(&old_last, old_path.dentry, lookup_flags);
+	error = PTR_ERR(old_dentry);
+	if (IS_ERR(old_dentry))
+		goto exit3;
+	/* source must exist */
+	error = -ENOENT;
+	if (d_is_negative(old_dentry))
+		goto exit4;
+	new_dentry = __lookup_hash(&new_last, new_path.dentry, lookup_flags | target_flags);
+	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 (new_last.name[new_last.len])
+				goto exit5;
+		}
+	}
+	/* unless the source is a directory trailing slashes give -ENOTDIR */
+	if (!d_is_dir(old_dentry)) {
+		error = -ENOTDIR;
+		if (old_last.name[old_last.len])
+			goto exit5;
+		if (!(flags & RENAME_EXCHANGE) && new_last.name[new_last.len])
+			goto exit5;
+	}
+	/* source should not be ancestor of target */
+	error = -EINVAL;
+	if (old_dentry == trap)
+		goto exit5;
+	/* target should not be an ancestor of source */
+	if (!(flags & RENAME_EXCHANGE))
+		error = -ENOTEMPTY;
+	if (new_dentry == trap)
+		goto exit5;
+
+	error = security_path_rename(&old_path, old_dentry,
+				     &new_path, new_dentry, flags);
+	if (error)
+		goto exit5;
+	error = vfs_rename2(old_path.mnt, old_path.dentry->d_inode, old_dentry,
+			   new_path.dentry->d_inode, new_dentry,
+			   &delegated_inode, flags);
+exit5:
+	dput(new_dentry);
+exit4:
+	dput(old_dentry);
+exit3:
+	unlock_rename(new_path.dentry, old_path.dentry);
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
+	mnt_drop_write(old_path.mnt);
+exit2:
+	if (retry_estale(error, lookup_flags))
+		should_retry = true;
+	path_put(&new_path);
+	putname(to);
+exit1:
+	path_put(&old_path);
+	putname(from);
+	if (should_retry) {
+		should_retry = false;
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
+exit:
+	return error;
+}
+
+SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
+		int, newdfd, const char __user *, newname, unsigned int, flags)
+{
+	return do_renameat2(olddfd, oldname, newdfd, newname, flags);
+}
+
+SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
+		int, newdfd, const char __user *, newname)
+{
+	return do_renameat2(olddfd, oldname, newdfd, newname, 0);
+}
+
+SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname)
+{
+	return do_renameat2(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
+}
+
+int vfs_whiteout(struct inode *dir, struct dentry *dentry)
+{
+	int error = may_create(NULL, dir, dentry);
+	if (error)
+		return error;
+
+	if (!dir->i_op->mknod)
+		return -EPERM;
+
+	return dir->i_op->mknod(dir, dentry,
+				S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV);
+}
+EXPORT_SYMBOL(vfs_whiteout);
+
+int readlink_copy(char __user *buffer, int buflen, const char *link)
+{
+	int len = PTR_ERR(link);
+	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;
+}
+
+/**
+ * vfs_readlink - copy symlink body into userspace buffer
+ * @dentry: dentry on which to get symbolic link
+ * @buffer: user memory pointer
+ * @buflen: size of buffer
+ *
+ * Does not touch atime.  That's up to the caller if necessary
+ *
+ * Does not call security hook.
+ */
+int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen)
+{
+	struct inode *inode = d_inode(dentry);
+	DEFINE_DELAYED_CALL(done);
+	const char *link;
+	int res;
+
+	if (unlikely(!(inode->i_opflags & IOP_DEFAULT_READLINK))) {
+		if (unlikely(inode->i_op->readlink))
+			return inode->i_op->readlink(dentry, buffer, buflen);
+
+		if (!d_is_symlink(dentry))
+			return -EINVAL;
+
+		spin_lock(&inode->i_lock);
+		inode->i_opflags |= IOP_DEFAULT_READLINK;
+		spin_unlock(&inode->i_lock);
+	}
+
+	link = READ_ONCE(inode->i_link);
+	if (!link) {
+		link = inode->i_op->get_link(dentry, inode, &done);
+		if (IS_ERR(link))
+			return PTR_ERR(link);
+	}
+	res = readlink_copy(buffer, buflen, link);
+	do_delayed_call(&done);
+	return res;
+}
+EXPORT_SYMBOL(vfs_readlink);
+
+/**
+ * vfs_get_link - get symlink body
+ * @dentry: dentry on which to get symbolic link
+ * @done: caller needs to free returned data with this
+ *
+ * Calls security hook and i_op->get_link() on the supplied inode.
+ *
+ * It does not touch atime.  That's up to the caller if necessary.
+ *
+ * Does not work on "special" symlinks like /proc/$$/fd/N
+ */
+const char *vfs_get_link(struct dentry *dentry, struct delayed_call *done)
+{
+	const char *res = ERR_PTR(-EINVAL);
+	struct inode *inode = d_inode(dentry);
+
+	if (d_is_symlink(dentry)) {
+		res = ERR_PTR(security_inode_readlink(dentry));
+		if (!res)
+			res = inode->i_op->get_link(dentry, inode, done);
+	}
+	return res;
+}
+EXPORT_SYMBOL(vfs_get_link);
+
+/* get the link contents into pagecache */
+const char *page_get_link(struct dentry *dentry, struct inode *inode,
+			  struct delayed_call *callback)
+{
+	char *kaddr;
+	struct page *page;
+	struct address_space *mapping = inode->i_mapping;
+
+	if (!dentry) {
+		page = find_get_page(mapping, 0);
+		if (!page)
+			return ERR_PTR(-ECHILD);
+		if (!PageUptodate(page)) {
+			put_page(page);
+			return ERR_PTR(-ECHILD);
+		}
+	} else {
+		page = read_mapping_page(mapping, 0, NULL);
+		if (IS_ERR(page))
+			return (char*)page;
+	}
+	set_delayed_call(callback, page_put_link, page);
+	BUG_ON(mapping_gfp_mask(mapping) & __GFP_HIGHMEM);
+	kaddr = page_address(page);
+	nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1);
+	return kaddr;
+}
+
+EXPORT_SYMBOL(page_get_link);
+
+void page_put_link(void *arg)
+{
+	put_page(arg);
+}
+EXPORT_SYMBOL(page_put_link);
+
+int page_readlink(struct dentry *dentry, char __user *buffer, int buflen)
+{
+	DEFINE_DELAYED_CALL(done);
+	int res = readlink_copy(buffer, buflen,
+				page_get_link(dentry, d_inode(dentry),
+					      &done));
+	do_delayed_call(&done);
+	return res;
+}
+EXPORT_SYMBOL(page_readlink);
+
+/*
+ * The nofs argument instructs pagecache_write_begin to pass AOP_FLAG_NOFS
+ */
+int __page_symlink(struct inode *inode, const char *symname, int len, int nofs)
+{
+	struct address_space *mapping = inode->i_mapping;
+	struct page *page;
+	void *fsdata;
+	int err;
+	unsigned int flags = 0;
+	if (nofs)
+		flags |= AOP_FLAG_NOFS;
+
+retry:
+	err = pagecache_write_begin(NULL, mapping, 0, len-1,
+				flags, &page, &fsdata);
+	if (err)
+		goto fail;
+
+	memcpy(page_address(page), symname, len-1);
+
+	err = pagecache_write_end(NULL, mapping, 0, len-1, len-1,
+							page, fsdata);
+	if (err < 0)
+		goto fail;
+	if (err < len-1)
+		goto retry;
+
+	mark_inode_dirty(inode);
+	return 0;
+fail:
+	return err;
+}
+EXPORT_SYMBOL(__page_symlink);
+
+int page_symlink(struct inode *inode, const char *symname, int len)
+{
+	return __page_symlink(inode, symname, len,
+			!mapping_gfp_constraint(inode->i_mapping, __GFP_FS));
+}
+EXPORT_SYMBOL(page_symlink);
+
+const struct inode_operations page_symlink_inode_operations = {
+	.get_link	= page_get_link,
+};
+EXPORT_SYMBOL(page_symlink_inode_operations);