1 files changed, 188 insertions, 118 deletions

diff --git a/fs/namei.c b/fs/namei.c
index d6c91d1e88cb..db6565c99825 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -491,7 +491,7 @@ struct nameidata {
 	struct path	root;
 	struct inode	*inode; /* path.dentry.d_inode */
 	unsigned int	flags;
-	unsigned	seq, m_seq;
+	unsigned	seq, m_seq, r_seq;
 	int		last_type;
 	unsigned	depth;
 	int		total_link_count;
@@ -641,6 +641,14 @@ static bool legitimize_links(struct nameidata *nd)
 
 static bool legitimize_root(struct nameidata *nd)
 {
+	/*
+	 * For scoped-lookups (where nd->root has been zeroed), we need to
+	 * restart the whole lookup from scratch -- because set_root() is wrong
+	 * for these lookups (nd->dfd is the root, not the filesystem root).
+	 */
+	if (!nd->root.mnt && (nd->flags & LOOKUP_IS_SCOPED))
+		return false;
+	/* Nothing to do if nd->root is zero or is managed by the VFS user. */
 	if (!nd->root.mnt || (nd->flags & LOOKUP_ROOT))
 		return true;
 	nd->flags |= LOOKUP_ROOT_GRABBED;
@@ -776,12 +784,37 @@ static int complete_walk(struct nameidata *nd)
 	int status;
 
 	if (nd->flags & LOOKUP_RCU) {
-		if (!(nd->flags & LOOKUP_ROOT))
+		/*
+		 * We don't want to zero nd->root for scoped-lookups or
+		 * externally-managed nd->root.
+		 */
+		if (!(nd->flags & (LOOKUP_ROOT | LOOKUP_IS_SCOPED)))
 			nd->root.mnt = NULL;
 		if (unlikely(unlazy_walk(nd)))
 			return -ECHILD;
 	}
 
+	if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) {
+		/*
+		 * While the guarantee of LOOKUP_IS_SCOPED is (roughly) "don't
+		 * ever step outside the root during lookup" and should already
+		 * be guaranteed by the rest of namei, we want to avoid a namei
+		 * BUG resulting in userspace being given a path that was not
+		 * scoped within the root at some point during the lookup.
+		 *
+		 * So, do a final sanity-check to make sure that in the
+		 * worst-case scenario (a complete bypass of LOOKUP_IS_SCOPED)
+		 * we won't silently return an fd completely outside of the
+		 * requested root to userspace.
+		 *
+		 * Userspace could move the path outside the root after this
+		 * check, but as discussed elsewhere this is not a concern (the
+		 * resolved file was inside the root at some point).
+		 */
+		if (!path_is_under(&nd->path, &nd->root))
+			return -EXDEV;
+	}
+
 	if (likely(!(nd->flags & LOOKUP_JUMPED)))
 		return 0;
 
@@ -798,10 +831,18 @@ static int complete_walk(struct nameidata *nd)
 	return status;
 }
 
-static void set_root(struct nameidata *nd)
+static int set_root(struct nameidata *nd)
 {
 	struct fs_struct *fs = current->fs;
 
+	/*
+	 * Jumping to the real root in a scoped-lookup is a BUG in namei, but we
+	 * still have to ensure it doesn't happen because it will cause a breakout
+	 * from the dirfd.
+	 */
+	if (WARN_ON(nd->flags & LOOKUP_IS_SCOPED))
+		return -ENOTRECOVERABLE;
+
 	if (nd->flags & LOOKUP_RCU) {
 		unsigned seq;
 
@@ -814,6 +855,7 @@ static void set_root(struct nameidata *nd)
 		get_fs_root(fs, &nd->root);
 		nd->flags |= LOOKUP_ROOT_GRABBED;
 	}
+	return 0;
 }
 
 static void path_put_conditional(struct path *path, struct nameidata *nd)
@@ -837,6 +879,18 @@ static inline void path_to_nameidata(const struct path *path,
 
 static int nd_jump_root(struct nameidata *nd)
 {
+	if (unlikely(nd->flags & LOOKUP_BENEATH))
+		return -EXDEV;
+	if (unlikely(nd->flags & LOOKUP_NO_XDEV)) {
+		/* Absolute path arguments to path_init() are allowed. */
+		if (nd->path.mnt != NULL && nd->path.mnt != nd->root.mnt)
+			return -EXDEV;
+	}
+	if (!nd->root.mnt) {
+		int error = set_root(nd);
+		if (error)
+			return error;
+	}
 	if (nd->flags & LOOKUP_RCU) {
 		struct dentry *d;
 		nd->path = nd->root;
@@ -859,14 +913,32 @@ static int nd_jump_root(struct nameidata *nd)
  * 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)
+int nd_jump_link(struct path *path)
 {
+	int error = -ELOOP;
 	struct nameidata *nd = current->nameidata;
-	path_put(&nd->path);
 
+	if (unlikely(nd->flags & LOOKUP_NO_MAGICLINKS))
+		goto err;
+
+	error = -EXDEV;
+	if (unlikely(nd->flags & LOOKUP_NO_XDEV)) {
+		if (nd->path.mnt != path->mnt)
+			goto err;
+	}
+	/* Not currently safe for scoped-lookups. */
+	if (unlikely(nd->flags & LOOKUP_IS_SCOPED))
+		goto err;
+
+	path_put(&nd->path);
 	nd->path = *path;
 	nd->inode = nd->path.dentry->d_inode;
 	nd->flags |= LOOKUP_JUMPED;
+	return 0;
+
+err:
+	path_put(path);
+	return error;
 }
 
 static inline void put_link(struct nameidata *nd)
@@ -1001,7 +1073,8 @@ static int may_linkat(struct path *link)
  * 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: the sticky parent directory
+ * @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:
@@ -1017,18 +1090,18 @@ static int may_linkat(struct path *link)
  *
  * Returns 0 if the open is allowed, -ve on error.
  */
-static int may_create_in_sticky(struct dentry * const dir,
+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->d_inode->i_mode & S_ISVTX)) ||
-	    uid_eq(inode->i_uid, dir->d_inode->i_uid) ||
+	    likely(!(dir_mode & S_ISVTX)) ||
+	    uid_eq(inode->i_uid, dir_uid) ||
 	    uid_eq(current_fsuid(), inode->i_uid))
 		return 0;
 
-	if (likely(dir->d_inode->i_mode & 0002) ||
-	    (dir->d_inode->i_mode & 0020 &&
+	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))))) {
 		const char *operation = S_ISFIFO(inode->i_mode) ?
@@ -1049,6 +1122,9 @@ const char *get_link(struct nameidata *nd)
 	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();
@@ -1083,10 +1159,9 @@ const char *get_link(struct nameidata *nd)
 			return res;
 	}
 	if (*res == '/') {
-		if (!nd->root.mnt)
-			set_root(nd);
-		if (unlikely(nd_jump_root(nd)))
-			return ERR_PTR(-ECHILD);
+		error = nd_jump_root(nd);
+		if (unlikely(error))
+			return ERR_PTR(error);
 		while (unlikely(*++res == '/'))
 			;
 	}
@@ -1232,6 +1307,7 @@ static int follow_managed(struct path *path, struct nameidata *nd)
 			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;
 		}
@@ -1267,10 +1343,14 @@ static int follow_managed(struct path *path, struct nameidata *nd)
 		break;
 	}
 
-	if (need_mntput && path->mnt == mnt)
-		mntput(path->mnt);
-	if (need_mntput)
-		nd->flags |= LOOKUP_JUMPED;
+	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)))
@@ -1331,6 +1411,8 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 		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;
@@ -1351,8 +1433,11 @@ static int follow_dotdot_rcu(struct nameidata *nd)
 	struct inode *inode = nd->inode;
 
 	while (1) {
-		if (path_equal(&nd->path, &nd->root))
+		if (path_equal(&nd->path, &nd->root)) {
+			if (unlikely(nd->flags & LOOKUP_BENEATH))
+				return -ECHILD;
 			break;
+		}
 		if (nd->path.dentry != nd->path.mnt->mnt_root) {
 			struct dentry *old = nd->path.dentry;
 			struct dentry *parent = old->d_parent;
@@ -1365,7 +1450,7 @@ static int follow_dotdot_rcu(struct nameidata *nd)
 			nd->path.dentry = parent;
 			nd->seq = seq;
 			if (unlikely(!path_connected(&nd->path)))
-				return -ENOENT;
+				return -ECHILD;
 			break;
 		} else {
 			struct mount *mnt = real_mount(nd->path.mnt);
@@ -1377,6 +1462,8 @@ static int follow_dotdot_rcu(struct nameidata *nd)
 				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;
@@ -1391,6 +1478,8 @@ static int follow_dotdot_rcu(struct nameidata *nd)
 			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;
@@ -1478,9 +1567,12 @@ static int path_parent_directory(struct path *path)
 
 static int follow_dotdot(struct nameidata *nd)
 {
-	while(1) {
-		if (path_equal(&nd->path, &nd->root))
+	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)
@@ -1489,6 +1581,8 @@ static int follow_dotdot(struct nameidata *nd)
 		}
 		if (!follow_up(&nd->path))
 			break;
+		if (unlikely(nd->flags & LOOKUP_NO_XDEV))
+			return -EXDEV;
 	}
 	follow_mount(&nd->path);
 	nd->inode = nd->path.dentry->d_inode;
@@ -1649,17 +1743,15 @@ again:
 	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;
-				}
+		int error = d_revalidate(dentry, flags);
+		if (unlikely(error <= 0)) {
+			if (!error) {
+				d_invalidate(dentry);
 				dput(dentry);
-				dentry = ERR_PTR(error);
+				goto again;
 			}
+			dput(dentry);
+			dentry = ERR_PTR(error);
 		}
 	} else {
 		old = inode->i_op->lookup(inode, dentry, flags);
@@ -1699,12 +1791,33 @@ static inline int may_lookup(struct nameidata *nd)
 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);
+		int error = 0;
+
+		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 (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;
+		}
 	}
 	return 0;
 }
@@ -2158,6 +2271,7 @@ OK:
 /* must be paired with terminate_walk() */
 static const char *path_init(struct nameidata *nd, unsigned flags)
 {
+	int error;
 	const char *s = nd->name->name;
 
 	if (!*s)
@@ -2168,6 +2282,11 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 	nd->last_type = LAST_ROOT; /* if there are only slashes... */
 	nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT;
 	nd->depth = 0;
+
+	nd->m_seq = __read_seqcount_begin(&mount_lock.seqcount);
+	nd->r_seq = __read_seqcount_begin(&rename_lock.seqcount);
+	smp_rmb();
+
 	if (flags & LOOKUP_ROOT) {
 		struct dentry *root = nd->root.dentry;
 		struct inode *inode = root->d_inode;
@@ -2176,9 +2295,8 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 		nd->path = nd->root;
 		nd->inode = inode;
 		if (flags & LOOKUP_RCU) {
-			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
+			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);
 		}
@@ -2189,13 +2307,16 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 	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) {
+	/* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */
+	if (*s == '/' && !(flags & LOOKUP_IN_ROOT)) {
+		error = nd_jump_root(nd);
+		if (unlikely(error))
+			return ERR_PTR(error);
+		return s;
+	}
+
+	/* Relative pathname -- get the starting-point it is relative to. */
+	if (nd->dfd == AT_FDCWD) {
 		if (flags & LOOKUP_RCU) {
 			struct fs_struct *fs = current->fs;
 			unsigned seq;
@@ -2210,7 +2331,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 			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);
@@ -2235,8 +2355,19 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 			nd->inode = nd->path.dentry->d_inode;
 		}
 		fdput(f);
-		return s;
 	}
+
+	/* For scoped-lookups we need to set the root to the dirfd as well. */
+	if (flags & LOOKUP_IS_SCOPED) {
+		nd->root = nd->path;
+		if (flags & LOOKUP_RCU) {
+			nd->root_seq = nd->seq;
+		} else {
+			path_get(&nd->root);
+			nd->flags |= LOOKUP_ROOT_GRABBED;
+		}
+	}
+	return s;
 }
 
 static const char *trailing_symlink(struct nameidata *nd)
@@ -2618,72 +2749,6 @@ int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
 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_flags_negative(smp_load_acquire(&path.dentry->d_flags))) {
-		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
@@ -2699,14 +2764,17 @@ path_mountpoint(struct nameidata *nd, unsigned flags, struct path *path)
 	int err;
 
 	while (!(err = link_path_walk(s, nd)) &&
-		(err = mountpoint_last(nd)) > 0) {
+		(err = lookup_last(nd)) > 0) {
 		s = trailing_symlink(nd);
 	}
+	if (!err && (nd->flags & LOOKUP_RCU))
+		err = unlazy_walk(nd);
+	if (!err)
+		err = handle_lookup_down(nd);
 	if (!err) {
 		*path = nd->path;
 		nd->path.mnt = NULL;
 		nd->path.dentry = NULL;
-		follow_mount(path);
 	}
 	terminate_walk(nd);
 	return err;
@@ -3265,6 +3333,8 @@ 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;
@@ -3395,7 +3465,7 @@ finish_open:
 		error = -EISDIR;
 		if (d_is_dir(nd->path.dentry))
 			goto out;
-		error = may_create_in_sticky(dir,
+		error = may_create_in_sticky(dir_mode, dir_uid,
 					     d_backing_inode(nd->path.dentry));
 		if (unlikely(error))
 			goto out;