namei: LOOKUP_NO_XDEV: block mountpoint crossing

/* Background. */
The need to contain path operations within a mountpoint has been a
long-standing usecase that userspace has historically implemented
manually with liberal usage of stat(). find, rsync, tar and
many other programs implement these semantics -- but it'd be much
simpler to have a fool-proof way of refusing to open a path if it
crosses a mountpoint.

This is part of a refresh of Al's AT_NO_JUMPS patchset[1] (which was a
variation on David Drysdale's O_BENEATH patchset[2], which in turn was
based on the Capsicum project[3]).

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

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

With LOOKUP_NO_XDEV, any path component which crosses a mount-point
during path resolution (including "..") will yield an -EXDEV. Absolute
paths, absolute symlinks, and magic-links will only yield an -EXDEV if
the jump involved changing mount-points.

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

[1]: https://lore.kernel.org/lkml/20170429220414.GT29622@ZenIV.linux.org.uk/
[2]: https://lore.kernel.org/lkml/1415094884-18349-1-git-send-email-drysdale@google.com/
[3]: https://lore.kernel.org/lkml/1404124096-21445-1-git-send-email-drysdale@google.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>

fs/namei.c

@@ -838,6 +838,11 @@ static inline void path_to_nameidata(const struct path *path,
 
 static int nd_jump_root(struct nameidata *nd)
 {
+	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)
@@ -873,6 +878,12 @@ int nd_jump_link(struct path *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;
+	}
+
 	path_put(&nd->path);
 	nd->path = *path;
 	nd->inode = nd->path.dentry->d_inode;
@@ -1284,10 +1295,14 @@ 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)))
@@ -1348,6 +1363,8 @@ 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;
@@ -1394,6 +1411,8 @@ 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;
@@ -1408,6 +1427,8 @@ 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;
@@ -1506,6 +1527,8 @@ 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;

include/linux/namei.h

@@ -42,6 +42,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
 /* Scoping flags for lookup. */
 #define LOOKUP_NO_SYMLINKS	0x010000 /* No symlink crossing. */
 #define LOOKUP_NO_MAGICLINKS	0x020000 /* No nd_jump_link() crossing. */
+#define LOOKUP_NO_XDEV		0x040000 /* No mountpoint crossing. */
 
 extern int path_pts(struct path *path);