namei: LOOKUP_BENEATH: O_BENEATH-like scoped resolution

/* Background. */
There are many circumstances when userspace wants to resolve a path and
ensure that it doesn't go outside of a particular root directory during
resolution. Obvious examples include archive extraction tools, as well as
other security-conscious userspace programs. FreeBSD spun out O_BENEATH
from their Capsicum project[1,2], so it also seems reasonable to
implement similar functionality for Linux.

This is part of a refresh of Al's AT_NO_JUMPS patchset[3] (which was a
variation on David Drysdale's O_BENEATH patchset[4], which in turn was
based on the Capsicum project[5]).

/* Userspace API. */
LOOKUP_BENEATH will be exposed to userspace through openat2(2).

/* Semantics. */
Unlike most other LOOKUP flags (most notably LOOKUP_FOLLOW),
LOOKUP_BENEATH applies to all components of the path.

With LOOKUP_BENEATH, any path component which attempts to "escape" the
starting point of the filesystem lookup (the dirfd passed to openat)
will yield -EXDEV. Thus, all absolute paths and symlinks are disallowed.

Due to a security concern brought up by Jann[6], any ".." path
components are also blocked. This restriction will be lifted in a future
patch, but requires more work to ensure that permitting ".." is done
safely.

Magic-link jumps are also blocked, because they can beam the path lookup
across the starting point. It would be possible to detect and block
only the "bad" crossings with path_is_under() checks, but it's unclear
whether it makes sense to permit magic-links at all. However, userspace
is recommended to pass LOOKUP_NO_MAGICLINKS if they want to ensure that
magic-link crossing is entirely disabled.

/* Testing. */
LOOKUP_BENEATH is tested as part of the openat2(2) selftests.

[1]: https://reviews.freebsd.org/D2808
[2]: https://reviews.freebsd.org/D17547
[3]: https://lore.kernel.org/lkml/20170429220414.GT29622@ZenIV.linux.org.uk/
[4]: https://lore.kernel.org/lkml/1415094884-18349-1-git-send-email-drysdale@google.com/
[5]: https://lore.kernel.org/lkml/1404124096-21445-1-git-send-email-drysdale@google.com/
[6]: https://lore.kernel.org/lkml/CAG48ez1jzNvxB+bfOBnERFGp=oMM0vHWuLD6EULmne3R6xa53w@mail.gmail.com/

Cc: Christian Brauner <christian.brauner@ubuntu.com>
Suggested-by: David Drysdale <drysdale@google.com>
Suggested-by: Al Viro <viro@zeniv.linux.org.uk>
Suggested-by: Andy Lutomirski <luto@kernel.org>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Aleksa Sarai <cyphar@cyphar.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
diff --git a/fs/namei.c b/fs/namei.c
index a9ca46e..eaf07f8 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -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;
 
@@ -802,6 +835,14 @@ 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;
 
@@ -838,6 +879,8 @@ 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)
@@ -883,6 +926,9 @@ int nd_jump_link(struct path *path)
 		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;
@@ -1385,8 +1431,11 @@ 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;
@@ -1516,9 +1565,12 @@ 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)
@@ -1741,6 +1793,13 @@ static inline int handle_dots(struct nameidata *nd, int type)
 	if (type == LAST_DOTDOT) {
 		int error = 0;
 
+		/*
+		 * Scoped-lookup flags resolving ".." is not currently safe --
+		 * races can cause our parent to have moved outside of the root
+		 * and us to skip over it.
+		 */
+		if (unlikely(nd->flags & LOOKUP_IS_SCOPED))
+			return -EXDEV;
 		if (!nd->root.mnt) {
 			error = set_root(nd);
 			if (error)
@@ -2258,7 +2317,6 @@ 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);
@@ -2283,8 +2341,18 @@ 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)