LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Aleksa Sarai <cyphar@cyphar.com>
To: Jeff Layton <jlayton@kernel.org>,
	"J. Bruce Fields" <bfields@fieldses.org>,
	Al Viro <viro@zeniv.linux.org.uk>, Arnd Bergmann <arnd@arndb.de>,
	Shuah Khan <shuah@kernel.org>
Cc: David Howells <dhowells@redhat.com>,
	Andy Lutomirski <luto@kernel.org>,
	Christian Brauner <christian@brauner.io>,
	Eric Biederman <ebiederm@xmission.com>,
	Tycho Andersen <tycho@tycho.ws>,
	linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-arch@vger.kernel.org, linux-kselftest@vger.kernel.org,
	dev@opencontainers.org, containers@lists.linux-foundation.org,
	Aleksa Sarai <cyphar@cyphar.com>
Subject: [PATCH 2/3] namei: implement AT_THIS_ROOT chroot-like path resolution
Date: Sat, 29 Sep 2018 23:15:33 +1000
Message-ID: <20180929131534.24472-1-cyphar@cyphar.com> (raw)
In-Reply-To: <20180929103453.12025-1-cyphar@cyphar.com>

The primary motivation for the need for this flag is container runtimes
which have to interact with malicious root filesystems in the host
namespaces. One of the first requirements for a container runtime to be
secure against a malicious rootfs is that they correctly scope symlinks
(that is, they should be scoped as though they are chroot(2)ed into the
container's rootfs) and ".."-style paths. The already-existing AT_XDEV
and AT_NO_PROCLINKS help defend against other potential attacks in a
malicious rootfs scenario.

Currently most container runtimes try to do this resolution in
userspace[1], causing many potential race conditions. In addition, the
"obvious" alternative (actually performing a {ch,pivot_}root(2))
requires a fork+exec which is *very* costly if necessary for every
filesystem operation involving a container.

The most significant change in semantics with AT_THIS_ROOT is that
*at(2) syscalls now no longer have the property that an absolute
pathname causes the dirfd to be ignored completely (if LOOKUP_CHROOT is
specified). The reasoning behind this is that AT_THIS_ROOT necessarily
has to chroot-scope symlinks with absolute paths to dirfd, and so doing
it for the base path seems to be the most consistent behaviour (and also
avoids foot-gunning users who want to chroot-scope paths that might be
absolute).

Currently this is only enabled for the stat(2) and openat(2) family (the
latter has its own flag O_THISROOT with the same semantics). Ideally
this flag would be supported by all *at(2) syscalls, but this will
require adding flags arguments to many of them (and will be done in a
separate patchset).

[1]: https://github.com/cyphar/filepath-securejoin

Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Christian Brauner <christian@brauner.io>
Signed-off-by: Aleksa Sarai <cyphar@cyphar.com>
---
 fs/fcntl.c                       |   2 +-
 fs/namei.c                       | 121 +++++++++++++++++--------------
 fs/open.c                        |   2 +
 fs/stat.c                        |   4 +-
 include/linux/fcntl.h            |   2 +-
 include/linux/namei.h            |   1 +
 include/uapi/asm-generic/fcntl.h |   3 +
 include/uapi/linux/fcntl.h       |   2 +
 8 files changed, 81 insertions(+), 56 deletions(-)

diff --git a/fs/fcntl.c b/fs/fcntl.c
index e343618736f7..4c36c5b9fdb9 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -1031,7 +1031,7 @@ static int __init fcntl_init(void)
 	 * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
 	 * is defined as O_NONBLOCK on some platforms and not on others.
 	 */
-	BUILD_BUG_ON(25 - 1 /* for O_RDONLY being 0 */ !=
+	BUILD_BUG_ON(26 - 1 /* for O_RDONLY being 0 */ !=
 		HWEIGHT32(
 			(VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) |
 			__FMODE_EXEC | __FMODE_NONOTIFY));
diff --git a/fs/namei.c b/fs/namei.c
index 757dd783771c..1b984f0dbbb4 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2193,9 +2193,64 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 	}
 }
 
+/*
+ * Configure nd->path based on the nd->dfd. This is only used as part of
+ * path_init().
+ */
+static inline int dirfd_path_init(struct nameidata *nd)
+{
+	if (nd->dfd == AT_FDCWD) {
+		if (nd->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;
+		}
+	} 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 -EBADF;
+
+		dentry = f.file->f_path.dentry;
+
+		if (*nd->name->name && unlikely(!d_can_lookup(dentry))) {
+			fdput(f);
+			return -ENOTDIR;
+		}
+
+		nd->path = f.file->f_path;
+		if (nd->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);
+	}
+	if (unlikely(nd->flags & (LOOKUP_CHROOT | LOOKUP_BENEATH))) {
+		nd->root = nd->path;
+		if (!(nd->flags & LOOKUP_RCU))
+			path_get(&nd->root);
+	}
+	return 0;
+}
+
 /* 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)
@@ -2230,65 +2285,25 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 	nd->path.dentry = NULL;
 
 	nd->m_seq = read_seqbegin(&mount_lock);
+	if (unlikely(flags & LOOKUP_CHROOT)) {
+		error = dirfd_path_init(nd);
+		if (unlikely(error))
+			return ERR_PTR(error);
+	}
 	if (*s == '/') {
-		int error;
-		set_root(nd);
+		if (likely(!nd->root.mnt))
+			set_root(nd);
 		error = nd_jump_root(nd);
 		if (unlikely(error))
 			s = ERR_PTR(error);
 		return s;
-	} 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;
-		}
-		if (unlikely(flags & LOOKUP_BENEATH)) {
-			nd->root = nd->path;
-			if (!(flags & LOOKUP_RCU))
-				path_get(&nd->root);
-		}
-		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;
-		}
-		if (unlikely(flags & LOOKUP_BENEATH)) {
-			nd->root = nd->path;
-			if (!(flags & LOOKUP_RCU))
-				path_get(&nd->root);
-		}
-		fdput(f);
-		return s;
 	}
+	if (likely(!nd->path.mnt)) {
+		error = dirfd_path_init(nd);
+		if (unlikely(error))
+			return ERR_PTR(error);
+	}
+	return s;
 }
 
 static const char *trailing_symlink(struct nameidata *nd)
diff --git a/fs/open.c b/fs/open.c
index 80f5f566a5ff..81d148f626cd 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -996,6 +996,8 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
 		lookup_flags |= LOOKUP_NO_PROCLINKS;
 	if (flags & O_NOSYMLINKS)
 		lookup_flags |= LOOKUP_NO_SYMLINKS;
+	if (flags & O_THISROOT)
+		lookup_flags |= LOOKUP_CHROOT;
 	op->lookup_flags = lookup_flags;
 	return 0;
 }
diff --git a/fs/stat.c b/fs/stat.c
index 791e61b916ae..e8366e4812c3 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -172,7 +172,7 @@ int vfs_statx(int dfd, const char __user *filename, int flags,
 
 	if (flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT | AT_EMPTY_PATH |
 		      KSTAT_QUERY_FLAGS | AT_BENEATH | AT_XDEV |
-		      AT_NO_PROCLINKS | AT_NO_SYMLINKS))
+		      AT_NO_PROCLINKS | AT_NO_SYMLINKS | AT_THIS_ROOT))
 		return -EINVAL;
 
 	if (flags & AT_SYMLINK_NOFOLLOW)
@@ -189,6 +189,8 @@ int vfs_statx(int dfd, const char __user *filename, int flags,
 		lookup_flags |= LOOKUP_NO_PROCLINKS;
 	if (flags & AT_NO_SYMLINKS)
 		lookup_flags |= LOOKUP_NO_SYMLINKS;
+	if (flags & AT_THIS_ROOT)
+		lookup_flags |= LOOKUP_CHROOT;
 
 retry:
 	error = user_path_at(dfd, filename, lookup_flags, &path);
diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h
index ad5bba4b5b12..95480cd4c09d 100644
--- a/include/linux/fcntl.h
+++ b/include/linux/fcntl.h
@@ -10,7 +10,7 @@
 	 O_APPEND | O_NDELAY | O_NONBLOCK | O_NDELAY | __O_SYNC | O_DSYNC | \
 	 FASYNC	| O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | \
 	 O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE | O_BENEATH | O_XDEV | \
-	 O_NOPROCLINKS | O_NOSYMLINKS)
+	 O_NOPROCLINKS | O_NOSYMLINKS | O_THISROOT)
 
 #ifndef force_o_largefile
 #define force_o_largefile() (BITS_PER_LONG != 32)
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 5ff7f3362d1b..7ec9e2d84649 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -53,6 +53,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
 #define LOOKUP_NO_PROCLINKS	0x040000 /* No /proc/$pid/fd/ "symlink" crossing. */
 #define LOOKUP_NO_SYMLINKS	0x080000 /* No symlink crossing *at all*.
 					    Implies LOOKUP_NO_PROCLINKS. */
+#define LOOKUP_CHROOT		0x100000 /* Treat dirfd as %current->fs->root. */
 
 extern int path_pts(struct path *path);
 
diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h
index c2bf5983e46a..11206b0e927c 100644
--- a/include/uapi/asm-generic/fcntl.h
+++ b/include/uapi/asm-generic/fcntl.h
@@ -113,6 +113,9 @@
 #ifndef O_NOSYMLINKS
 #define O_NOSYMLINKS	01000000000
 #endif
+#ifndef O_THISROOT
+#define O_THISROOT	02000000000
+#endif
 
 #define F_DUPFD		0	/* dup */
 #define F_GETFD		1	/* get close_on_exec */
diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h
index 551a9e2166a8..ea978457b68f 100644
--- a/include/uapi/linux/fcntl.h
+++ b/include/uapi/linux/fcntl.h
@@ -99,6 +99,8 @@
 #define AT_NO_PROCLINKS		0x40000 /* No /proc/$pid/fd/... "symlinks". */
 #define AT_NO_SYMLINKS		0x80000 /* No symlinks *at all*.
 					   Implies AT_NO_PROCLINKS. */
+#define AT_THIS_ROOT		0x100000 /* Path resolution acts as though
+					   it is chroot-ed into dirfd. */
 
 
 #endif /* _UAPI_LINUX_FCNTL_H */
-- 
2.19.0


  parent reply index

Thread overview: 53+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-09-29 10:34 [PATCH 0/3] namei: implement various scoping AT_* flags Aleksa Sarai
2018-09-29 10:34 ` [PATCH 1/3] namei: implement O_BENEATH-style " Aleksa Sarai
2018-09-29 14:48   ` Christian Brauner
2018-09-29 15:34     ` Aleksa Sarai
2018-09-30  4:38   ` Aleksa Sarai
2018-10-01 12:28   ` Jann Horn
2018-10-01 13:00     ` Christian Brauner
2018-10-01 16:04       ` Aleksa Sarai
2018-10-04 17:20         ` Christian Brauner
2018-09-29 13:15 ` Aleksa Sarai [this message]
2018-09-29 13:15   ` [PATCH 3/3] selftests: vfs: add AT_* path resolution tests Aleksa Sarai
2018-09-29 16:35   ` [PATCH 2/3] namei: implement AT_THIS_ROOT chroot-like path resolution Jann Horn
2018-09-29 17:25     ` Andy Lutomirski
2018-10-01  9:46       ` Aleksa Sarai
2018-10-01  5:44     ` Aleksa Sarai
2018-10-01 10:13       ` Jann Horn
2018-10-01 16:18         ` Aleksa Sarai
2018-10-04 17:27           ` Christian Brauner
2018-10-01 10:42       ` Christian Brauner
2018-10-01 11:29         ` Jann Horn
2018-10-01 12:35           ` Christian Brauner
2018-10-01 13:55       ` Bruce Fields
2018-10-01 14:28       ` Andy Lutomirski
2018-10-02  7:32         ` Aleksa Sarai
2018-10-03 22:09           ` Andy Lutomirski
2018-10-06 20:56           ` Florian Weimer
2018-10-06 21:49             ` Christian Brauner
2018-10-01 14:00     ` Christian Brauner
2018-10-04 16:26     ` Aleksa Sarai
2018-10-04 17:31       ` Christian Brauner
2018-10-04 18:26       ` Jann Horn
2018-10-05 15:07         ` Aleksa Sarai
2018-10-05 15:55           ` Jann Horn
2018-10-06  2:10             ` Aleksa Sarai
2018-10-08 10:50               ` Jann Horn
2018-09-29 14:25 ` [PATCH 0/3] namei: implement various scoping AT_* flags Andy Lutomirski
2018-09-29 15:45   ` Aleksa Sarai
2018-09-29 16:34     ` Andy Lutomirski
2018-09-29 19:44       ` Matthew Wilcox
2018-09-29 14:38 ` Christian Brauner
2018-09-30  4:44   ` Aleksa Sarai
2018-09-30 13:54 ` Alban Crequy
2018-09-30 14:02   ` Christian Brauner
2018-09-30 19:45 ` Mickaël Salaün
2018-09-30 21:46   ` Jann Horn
2018-09-30 22:37     ` Mickaël Salaün
2018-10-01 20:14       ` James Morris
2018-10-01  4:08 ` Dave Chinner
2018-10-01  5:47   ` Aleksa Sarai
2018-10-01  6:14     ` Dave Chinner
2018-10-01 13:28 ` David Laight
2018-10-01 16:15   ` Aleksa Sarai
2018-10-03 13:21     ` David Laight

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20180929131534.24472-1-cyphar@cyphar.com \
    --to=cyphar@cyphar.com \
    --cc=arnd@arndb.de \
    --cc=bfields@fieldses.org \
    --cc=christian@brauner.io \
    --cc=containers@lists.linux-foundation.org \
    --cc=dev@opencontainers.org \
    --cc=dhowells@redhat.com \
    --cc=ebiederm@xmission.com \
    --cc=jlayton@kernel.org \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=luto@kernel.org \
    --cc=shuah@kernel.org \
    --cc=tycho@tycho.ws \
    --cc=viro@zeniv.linux.org.uk \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git