Merge branch 'work.dotdot1' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs pathwalk sanitizing from Al Viro:
 "Massive pathwalk rewrite and cleanups.

  Several iterations have been posted; hopefully this thing is getting
  readable and understandable now. Pretty much all parts of pathname
  resolutions are affected...

  The branch is identical to what has sat in -next, except for commit
  message in "lift all calls of step_into() out of follow_dotdot/
  follow_dotdot_rcu", crediting Qian Cai for reporting the bug; only
  commit message changed there."

* 'work.dotdot1' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (69 commits)
  lookup_open(): don't bother with fallbacks to lookup+create
  atomic_open(): no need to pass struct open_flags anymore
  open_last_lookups(): move complete_walk() into do_open()
  open_last_lookups(): lift O_EXCL|O_CREAT handling into do_open()
  open_last_lookups(): don't abuse complete_walk() when all we want is unlazy
  open_last_lookups(): consolidate fsnotify_create() calls
  take post-lookup part of do_last() out of loop
  link_path_walk(): sample parent's i_uid and i_mode for the last component
  __nd_alloc_stack(): make it return bool
  reserve_stack(): switch to __nd_alloc_stack()
  pick_link(): take reserving space on stack into a new helper
  pick_link(): more straightforward handling of allocation failures
  fold path_to_nameidata() into its only remaining caller
  pick_link(): pass it struct path already with normal refcounting rules
  fs/namei.c: kill follow_mount()
  non-RCU analogue of the previous commit
  helper for mount rootwards traversal
  follow_dotdot(): be lazy about changing nd->path
  follow_dotdot_rcu(): be lazy about changing nd->path
  follow_dotdot{,_rcu}(): massage loops
  ...

5 files changed, 676 insertions, 905 deletions

diff --git a/fs/autofs/dev-ioctl.c b/fs/autofs/dev-ioctl.c
index a3cdb0036c5d..f3a0f412b43b 100644
--- a/fs/autofs/dev-ioctl.c
+++ b/fs/autofs/dev-ioctl.c
@@ -186,7 +186,7 @@ static int find_autofs_mount(const char *pathname,
 	struct path path;
 	int err;
 
-	err = kern_path_mountpoint(AT_FDCWD, pathname, &path, 0);
+	err = kern_path(pathname, LOOKUP_MOUNTPOINT, &path);
 	if (err)
 		return err;
 	err = -ENOENT;
@@ -519,8 +519,8 @@ static int autofs_dev_ioctl_ismountpoint(struct file *fp,
 
 	if (!fp || param->ioctlfd == -1) {
 		if (autofs_type_any(type))
-			err = kern_path_mountpoint(AT_FDCWD,
-						   name, &path, LOOKUP_FOLLOW);
+			err = kern_path(name, LOOKUP_FOLLOW | LOOKUP_MOUNTPOINT,
+					&path);
 		else
 			err = find_autofs_mount(name, &path,
 						test_by_type, &type);
diff --git a/fs/internal.h b/fs/internal.h
index 4d37912a5587..aa5d45524e87 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -60,7 +60,6 @@ extern int finish_clean_context(struct fs_context *fc);
  */
 extern int filename_lookup(int dfd, struct filename *name, unsigned flags,
 			   struct path *path, struct path *root);
-extern int user_path_mountpoint_at(int, const char __user *, unsigned int, struct path *);
 extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
 			   const char *, unsigned int, struct path *);
 long do_mknodat(int dfd, const char __user *filename, umode_t mode,
diff --git a/fs/namei.c b/fs/namei.c
index db6565c99825..61fdb77a7d58 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -503,9 +503,10 @@ struct nameidata {
 	} *stack, internal[EMBEDDED_LEVELS];
 	struct filename	*name;
 	struct nameidata *saved;
-	struct inode	*link_inode;
 	unsigned	root_seq;
 	int		dfd;
+	kuid_t		dir_uid;
+	umode_t		dir_mode;
 } __randomize_layout;
 
 static void set_nameidata(struct nameidata *p, int dfd, struct filename *name)
@@ -530,52 +531,34 @@ static void restore_nameidata(void)
 		kfree(now->stack);
 }
 
-static int __nd_alloc_stack(struct nameidata *nd)
+static bool 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;
-	}
+	p= kmalloc_array(MAXSYMLINKS, sizeof(struct saved),
+			 nd->flags & LOOKUP_RCU ? GFP_ATOMIC : GFP_KERNEL);
+	if (unlikely(!p))
+		return false;
 	memcpy(p, nd->internal, sizeof(nd->internal));
 	nd->stack = p;
-	return 0;
+	return true;
 }
 
 /**
- * path_connected - Verify that a path->dentry is below path->mnt.mnt_root
- * @path: nameidate to verify
+ * path_connected - Verify that a dentry is below mnt.mnt_root
  *
  * 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)
+static bool path_connected(struct vfsmount *mnt, struct dentry *dentry)
 {
-	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);
+	return is_subdir(dentry, mnt->mnt_root);
 }
 
 static void drop_links(struct nameidata *nd)
@@ -608,10 +591,9 @@ static void terminate_walk(struct nameidata *nd)
 }
 
 /* path_put is needed afterwards regardless of success or failure */
-static bool legitimize_path(struct nameidata *nd,
-			    struct path *path, unsigned seq)
+static bool __legitimize_path(struct path *path, unsigned seq, unsigned mseq)
 {
-	int res = __legitimize_mnt(path->mnt, nd->m_seq);
+	int res = __legitimize_mnt(path->mnt, mseq);
 	if (unlikely(res)) {
 		if (res > 0)
 			path->mnt = NULL;
@@ -625,6 +607,12 @@ static bool legitimize_path(struct nameidata *nd,
 	return !read_seqcount_retry(&path->dentry->d_seq, seq);
 }
 
+static inline bool legitimize_path(struct nameidata *nd,
+			    struct path *path, unsigned seq)
+{
+	return __legitimize_path(path, nd->m_seq, seq);
+}
+
 static bool legitimize_links(struct nameidata *nd)
 {
 	int i;
@@ -858,25 +846,6 @@ static int set_root(struct nameidata *nd)
 	return 0;
 }
 
-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 (unlikely(nd->flags & LOOKUP_BENEATH))
@@ -969,28 +938,21 @@ int sysctl_protected_regular __read_mostly;
  *
  * Returns 0 if following the symlink is allowed, -ve on error.
  */
-static inline int may_follow_link(struct nameidata *nd)
+static inline int may_follow_link(struct nameidata *nd, const struct inode *inode)
 {
-	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))
+	if ((nd->dir_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))
+	if (uid_valid(nd->dir_uid) && uid_eq(nd->dir_uid, inode->i_uid))
 		return 0;
 
 	if (nd->flags & LOOKUP_RCU)
@@ -1113,63 +1075,6 @@ static int may_create_in_sticky(umode_t dir_mode, kuid_t dir_uid,
 	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 (unlikely(nd->flags & LOOKUP_NO_SYMLINKS))
-		return ERR_PTR(-ELOOP);
-
-	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 == '/') {
-		error = nd_jump_root(nd);
-		if (unlikely(error))
-			return ERR_PTR(error);
-		while (unlikely(*++res == '/'))
-			;
-	}
-	if (!*res)
-		res = NULL;
-	return res;
-}
-
 /*
  * follow_up - Find the mountpoint of path's vfsmount
  *
@@ -1203,19 +1108,59 @@ int follow_up(struct path *path)
 }
 EXPORT_SYMBOL(follow_up);
 
+static bool choose_mountpoint_rcu(struct mount *m, const struct path *root,
+				  struct path *path, unsigned *seqp)
+{
+	while (mnt_has_parent(m)) {
+		struct dentry *mountpoint = m->mnt_mountpoint;
+
+		m = m->mnt_parent;
+		if (unlikely(root->dentry == mountpoint &&
+			     root->mnt == &m->mnt))
+			break;
+		if (mountpoint != m->mnt.mnt_root) {
+			path->mnt = &m->mnt;
+			path->dentry = mountpoint;
+			*seqp = read_seqcount_begin(&mountpoint->d_seq);
+			return true;
+		}
+	}
+	return false;
+}
+
+static bool choose_mountpoint(struct mount *m, const struct path *root,
+			      struct path *path)
+{
+	bool found;
+
+	rcu_read_lock();
+	while (1) {
+		unsigned seq, mseq = read_seqbegin(&mount_lock);
+
+		found = choose_mountpoint_rcu(m, root, path, &seq);
+		if (unlikely(!found)) {
+			if (!read_seqretry(&mount_lock, mseq))
+				break;
+		} else {
+			if (likely(__legitimize_path(path, seq, mseq)))
+				break;
+			rcu_read_unlock();
+			path_put(path);
+			rcu_read_lock();
+		}
+	}
+	rcu_read_unlock();
+	return found;
+}
+
 /*
  * 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)
+static int follow_automount(struct path *path, int *count, unsigned lookup_flags)
 {
-	struct vfsmount *mnt;
-	int err;
-
-	if (!path->dentry->d_op || !path->dentry->d_op->d_automount)
-		return -EREMOTE;
+	struct dentry *dentry = path->dentry;
 
 	/* We don't want to mount if someone's just doing a stat -
 	 * unless they're stat'ing a directory and appended a '/' to
@@ -1228,138 +1173,91 @@ static int follow_automount(struct path *path, struct nameidata *nd,
 	 * 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 |
+	if (!(lookup_flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY |
 			   LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) &&
-	    path->dentry->d_inode)
+	    dentry->d_inode)
 		return -EISDIR;
 
-	nd->total_link_count++;
-	if (nd->total_link_count >= 40)
+	if (count && (*count)++ >= MAXSYMLINKS)
 		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;
-	}
-
+	return finish_automount(dentry->d_op->d_automount(path), path);
 }
 
 /*
- * 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.
- * On success path->dentry is known positive.
- *
- * Serialization is taken care of in namespace.c
+ * mount traversal - out-of-line part.  One note on ->d_flags accesses -
+ * dentries are pinned but not locked here, so negative dentry can go
+ * positive right under us.  Use of smp_load_acquire() provides a barrier
+ * sufficient for ->d_inode and ->d_flags consistency.
  */
-static int follow_managed(struct path *path, struct nameidata *nd)
+static int __traverse_mounts(struct path *path, unsigned flags, bool *jumped,
+			     int *count, unsigned lookup_flags)
 {
-	struct vfsmount *mnt = path->mnt; /* held by caller, must be left alone */
-	unsigned flags;
+	struct vfsmount *mnt = path->mnt;
 	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 (flags = smp_load_acquire(&path->dentry->d_flags),
-	       unlikely(flags & DCACHE_MANAGED_DENTRY)) {
+	while (flags & DCACHE_MANAGED_DENTRY) {
 		/* Allow the filesystem to manage the transit without i_mutex
 		 * being held. */
 		if (flags & 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);
 			flags = smp_load_acquire(&path->dentry->d_flags);
 			if (ret < 0)
 				break;
 		}
 
-		/* Transit to a mounted filesystem. */
-		if (flags & DCACHE_MOUNTED) {
+		if (flags & DCACHE_MOUNTED) {	// something's mounted on it..
 			struct vfsmount *mounted = lookup_mnt(path);
-			if (mounted) {
+			if (mounted) {		// ... in our namespace
 				dput(path->dentry);
 				if (need_mntput)
 					mntput(path->mnt);
 				path->mnt = mounted;
 				path->dentry = dget(mounted->mnt_root);
+				// here we know it's positive
+				flags = path->dentry->d_flags;
 				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 (flags & DCACHE_NEED_AUTOMOUNT) {
-			ret = follow_automount(path, nd, &need_mntput);
-			if (ret < 0)
-				break;
-			continue;
-		}
+		if (!(flags & DCACHE_NEED_AUTOMOUNT))
+			break;
 
-		/* We didn't change the current path point */
-		break;
+		// uncovered automount point
+		ret = follow_automount(path, count, lookup_flags);
+		flags = smp_load_acquire(&path->dentry->d_flags);
+		if (ret < 0)
+			break;
 	}
 
-	if (need_mntput) {
-		if (path->mnt == mnt)
-			mntput(path->mnt);
-		if (unlikely(nd->flags & LOOKUP_NO_XDEV))
-			ret = -EXDEV;
-		else
-			nd->flags |= LOOKUP_JUMPED;
-	}
-	if (ret == -EISDIR || !ret)
-		ret = 1;
-	if (ret > 0 && unlikely(d_flags_negative(flags)))
+	if (ret == -EISDIR)
+		ret = 0;
+	// possible if you race with several mount --move
+	if (need_mntput && path->mnt == mnt)
+		mntput(path->mnt);
+	if (!ret && unlikely(d_flags_negative(flags)))
 		ret = -ENOENT;
-	if (unlikely(ret < 0))
-		path_put_conditional(path, nd);
+	*jumped = need_mntput;
 	return ret;
 }
 
+static inline int traverse_mounts(struct path *path, bool *jumped,
+				  int *count, unsigned lookup_flags)
+{
+	unsigned flags = smp_load_acquire(&path->dentry->d_flags);
+
+	/* fastpath */
+	if (likely(!(flags & DCACHE_MANAGED_DENTRY))) {
+		*jumped = false;
+		if (unlikely(d_flags_negative(flags)))
+			return -ENOENT;
+		return 0;
+	}
+	return __traverse_mounts(path, flags, jumped, count, lookup_flags);
+}
+
 int follow_down_one(struct path *path)
 {
 	struct vfsmount *mounted;
@@ -1376,11 +1274,22 @@ int follow_down_one(struct path *path)
 }
 EXPORT_SYMBOL(follow_down_one);
 
-static inline int managed_dentry_rcu(const struct path *path)
+/*
+ * 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)
 {
-	return (path->dentry->d_flags & DCACHE_MANAGE_TRANSIT) ?
-		path->dentry->d_op->d_manage(path, true) : 0;
+	struct vfsmount *mnt = path->mnt;
+	bool jumped;
+	int ret = traverse_mounts(path, &jumped, NULL, 0);
+
+	if (path->mnt != mnt)
+		mntput(mnt);
+	return ret;
 }
+EXPORT_SYMBOL(follow_down);
 
 /*
  * Try to skip to top of mountpoint pile in rcuwalk mode.  Fail if
@@ -1389,204 +1298,88 @@ static inline int managed_dentry_rcu(const struct path *path)
 static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 			       struct inode **inode, unsigned *seqp)
 {
+	struct dentry *dentry = path->dentry;
+	unsigned int flags = dentry->d_flags;
+
+	if (likely(!(flags & DCACHE_MANAGED_DENTRY)))
+		return true;
+
+	if (unlikely(nd->flags & LOOKUP_NO_XDEV))
+		return false;
+
 	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;
-		if (unlikely(nd->flags & LOOKUP_NO_XDEV))
-			return false;
-		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)) {
-			if (unlikely(nd->flags & LOOKUP_BENEATH))
-				return -ECHILD;
-			break;
+		if (unlikely(flags & DCACHE_MANAGE_TRANSIT)) {
+			int res = dentry->d_op->d_manage(path, true);
+			if (res)
+				return res == -EISDIR;
+			flags = dentry->d_flags;
 		}
-		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 -ECHILD;
-			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;
-			if (unlikely(nd->flags & LOOKUP_NO_XDEV))
-				return -ECHILD;
-			/* we know that mountpoint was pinned */
-			nd->path.dentry = mountpoint;
-			nd->path.mnt = &mparent->mnt;
-			inode = inode2;
-			nd->seq = seq;
+		if (flags & DCACHE_MOUNTED) {
+			struct mount *mounted = __lookup_mnt(path->mnt, dentry);
+			if (mounted) {
+				path->mnt = &mounted->mnt;
+				dentry = path->dentry = mounted->mnt.mnt_root;
+				nd->flags |= LOOKUP_JUMPED;
+				*seqp = read_seqcount_begin(&dentry->d_seq);
+				*inode = dentry->d_inode;
+				/*
+				 * We don't need to re-check ->d_seq after this
+				 * ->d_inode read - there will be an RCU delay
+				 * between mount hash removal and ->mnt_root
+				 * becoming unpinned.
+				 */
+				flags = dentry->d_flags;
+				continue;
+			}
+			if (read_seqretry(&mount_lock, nd->m_seq))
+				return false;
 		}
+		return !(flags & DCACHE_NEED_AUTOMOUNT);
 	}
-	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;
-		if (unlikely(nd->flags & LOOKUP_NO_XDEV))
-			return -ECHILD;
-		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)
+static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry,
+			  struct path *path, struct inode **inode,
+			  unsigned int *seqp)
 {
-	unsigned managed;
+	bool jumped;
 	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);
+	path->mnt = nd->path.mnt;
+	path->dentry = dentry;
+	if (nd->flags & LOOKUP_RCU) {
+		unsigned int seq = *seqp;
+		if (unlikely(!*inode))
+			return -ENOENT;
+		if (likely(__follow_mount_rcu(nd, path, inode, seqp)))
+			return 0;
+		if (unlazy_child(nd, dentry, seq))
+			return -ECHILD;
+		// *path might've been clobbered by __follow_mount_rcu()
+		path->mnt = nd->path.mnt;
+		path->dentry = dentry;
 	}
-}
-
-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)) {
-			if (unlikely(nd->flags & LOOKUP_BENEATH))
-				return -EXDEV;
-			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;
+	ret = traverse_mounts(path, &jumped, &nd->total_link_count, nd->flags);
+	if (jumped) {
 		if (unlikely(nd->flags & LOOKUP_NO_XDEV))
-			return -EXDEV;
+			ret = -EXDEV;
+		else
+			nd->flags |= LOOKUP_JUMPED;
 	}
-	follow_mount(&nd->path);
-	nd->inode = nd->path.dentry->d_inode;
-	return 0;
+	if (unlikely(ret)) {
+		dput(path->dentry);
+		if (path->mnt != nd->path.mnt)
+			mntput(path->mnt);
+	} else {
+		*inode = d_backing_inode(path->dentry);
+		*seqp = 0; /* out of RCU mode, so the value doesn't matter */
+	}
+	return ret;
 }
 
 /*
@@ -1643,14 +1436,12 @@ static struct dentry *__lookup_hash(const struct qstr *name,
 	return dentry;
 }
 
-static int lookup_fast(struct nameidata *nd,
-		       struct path *path, struct inode **inode,
-		       unsigned *seqp)
+static struct dentry *lookup_fast(struct nameidata *nd,
+				  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
@@ -1659,12 +1450,11 @@ static int lookup_fast(struct nameidata *nd,
 	 */
 	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;
+				return ERR_PTR(-ECHILD);
+			return NULL;
 		}
 
 		/*
@@ -1672,9 +1462,8 @@ static int lookup_fast(struct nameidata *nd,
 		 * 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;
+			return ERR_PTR(-ECHILD);
 
 		/*
 		 * This sequence count validates that the parent had no
@@ -1684,46 +1473,30 @@ static int lookup_fast(struct nameidata *nd,
 		 *  enough, we can use __read_seqcount_retry here.
 		 */
 		if (unlikely(__read_seqcount_retry(&parent->d_seq, nd->seq)))
-			return -ECHILD;
+			return ERR_PTR(-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 (likely(status > 0))
+			return dentry;
 		if (unlazy_child(nd, dentry, seq))
-			return -ECHILD;
+			return ERR_PTR(-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;
+			return NULL;
 		status = d_revalidate(dentry, nd->flags);
 	}
 	if (unlikely(status <= 0)) {
 		if (!status)
 			d_invalidate(dentry);
 		dput(dentry);
-		return status;
+		return ERR_PTR(status);
 	}
-
-	path->mnt = mnt;
-	path->dentry = dentry;
-	err = follow_managed(path, nd);
-	if (likely(err > 0))
-		*inode = d_backing_inode(path->dentry);
-	return err;
+	return dentry;
 }
 
 /* Fast lookup failed, do it the slow way */
@@ -1788,81 +1561,107 @@ static inline int may_lookup(struct nameidata *nd)
 	return inode_permission(nd->inode, MAY_EXEC);
 }
 
-static inline int handle_dots(struct nameidata *nd, int type)
+static int reserve_stack(struct nameidata *nd, struct path *link, unsigned seq)
 {
-	if (type == LAST_DOTDOT) {
-		int error = 0;
+	if (unlikely(nd->total_link_count++ >= MAXSYMLINKS))
+		return -ELOOP;
 
-		if (!nd->root.mnt) {
-			error = set_root(nd);
-			if (error)
-				return error;
-		}
-		if (nd->flags & LOOKUP_RCU)
-			error = follow_dotdot_rcu(nd);
-		else
-			error = follow_dotdot(nd);
-		if (error)
-			return error;
+	if (likely(nd->depth != EMBEDDED_LEVELS))
+		return 0;
+	if (likely(nd->stack != nd->internal))
+		return 0;
+	if (likely(nd_alloc_stack(nd)))
+		return 0;
 
-		if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) {
-			/*
-			 * If there was a racing rename or mount along our
-			 * path, then we can't be sure that ".." hasn't jumped
-			 * above nd->root (and so userspace should retry or use
-			 * some fallback).
-			 */
-			smp_rmb();
-			if (unlikely(__read_seqcount_retry(&mount_lock.seqcount, nd->m_seq)))
-				return -EAGAIN;
-			if (unlikely(__read_seqcount_retry(&rename_lock.seqcount, nd->r_seq)))
-				return -EAGAIN;
-		}
+	if (nd->flags & LOOKUP_RCU) {
+		// we need to grab link before we do unlazy.  And we can't skip
+		// unlazy even if we fail to grab the link - cleanup needs it
+		bool grabbed_link = legitimize_path(nd, link, seq);
+
+		if (unlazy_walk(nd) != 0 || !grabbed_link)
+			return -ECHILD;
+
+		if (nd_alloc_stack(nd))
+			return 0;
 	}
-	return 0;
+	return -ENOMEM;
 }
 
-static int pick_link(struct nameidata *nd, struct path *link,
-		     struct inode *inode, unsigned seq)
+enum {WALK_TRAILING = 1, WALK_MORE = 2, WALK_NOFOLLOW = 4};
+
+static const char *pick_link(struct nameidata *nd, struct path *link,
+		     struct inode *inode, unsigned seq, int flags)
 {
-	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);
+	const char *res;
+	int error = reserve_stack(nd, link, seq);
+
 	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;
-				rcu_read_unlock();
-			} else if (likely(unlazy_walk(nd)) == 0)
-				error = nd_alloc_stack(nd);
-		}
-		if (error) {
+		if (!(nd->flags & LOOKUP_RCU))
 			path_put(link);
-			return error;
-		}
+		return ERR_PTR(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};
+	if (flags & WALK_TRAILING) {
+		error = may_follow_link(nd, inode);
+		if (unlikely(error))
+			return ERR_PTR(error);
+	}
+
+	if (unlikely(nd->flags & LOOKUP_NO_SYMLINKS))
+		return ERR_PTR(-ELOOP);
+
+	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(link->dentry, inode,
+					   nd->flags & LOOKUP_RCU);
+	if (unlikely(error))
+		return ERR_PTR(error);
+
+	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(link->dentry, inode, &last->done);
+			}
+		} else {
+			res = get(link->dentry, inode, &last->done);
+		}
+		if (!res)
+			goto all_done;
+		if (IS_ERR(res))
+			return res;
+	}
+	if (*res == '/') {
+		error = nd_jump_root(nd);
+		if (unlikely(error))
+			return ERR_PTR(error);
+		while (unlikely(*++res == '/'))
+			;
+	}
+	if (*res)
+		return res;
+all_done: // pure jump
+	put_link(nd);
+	return NULL;