Linux filesystem development
 help / color / mirror / Atom feed
From: Christian Brauner <brauner@kernel.org>
To: linux-fsdevel@vger.kernel.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
	 Chris Mason <mason@kernel.org>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	 Jan Kara <jack@suse.cz>, Jeff Layton <jlayton@kernel.org>,
	 Aleksa Sarai <cyphar@cyphar.com>,
	Amir Goldstein <amir73il@gmail.com>,
	 bpf@vger.kernel.org,
	"Christian Brauner (Amutable)" <brauner@kernel.org>
Subject: [PATCH 07/17] selftests/filesystems: check that OPEN_TREE_NAMESPACE keeps mounts covered
Date: Wed, 30 Sep 2026 15:31:59 +0200	[thread overview]
Message-ID: <20260930-work-mount-fixes-3-v1-7-be34c83956ae@kernel.org> (raw)
In-Reply-To: <20260930-work-mount-fixes-3-v1-0-be34c83956ae@kernel.org>

Add a test for open_tree(OPEN_TREE_NAMESPACE) from a user namespace that
doesn't own the mount namespace it copies from:

- a file covered by a private or an unbindable tmpfs mount
- the non-recursive copy of the parent mount fails with EINVAL
- the recursive copy keeps the file covered in the new mount namespace
- the owner of the mount namespace keeps the bind mount semantics

Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>
---
 .../selftests/filesystems/open_tree_ns/.gitignore  |   1 +
 .../selftests/filesystems/open_tree_ns/Makefile    |   2 +-
 .../open_tree_ns/open_tree_ns_covered_test.c       | 183 +++++++++++++++++++++
 3 files changed, 185 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/filesystems/open_tree_ns/.gitignore b/tools/testing/selftests/filesystems/open_tree_ns/.gitignore
index fb12b93fbcaa..76f95c0ae5ef 100644
--- a/tools/testing/selftests/filesystems/open_tree_ns/.gitignore
+++ b/tools/testing/selftests/filesystems/open_tree_ns/.gitignore
@@ -1 +1,2 @@
 open_tree_ns_test
+open_tree_ns_covered_test
diff --git a/tools/testing/selftests/filesystems/open_tree_ns/Makefile b/tools/testing/selftests/filesystems/open_tree_ns/Makefile
index 4976ed1d7d4a..fb2aa77b6edb 100644
--- a/tools/testing/selftests/filesystems/open_tree_ns/Makefile
+++ b/tools/testing/selftests/filesystems/open_tree_ns/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-TEST_GEN_PROGS := open_tree_ns_test
+TEST_GEN_PROGS := open_tree_ns_test open_tree_ns_covered_test
 
 CFLAGS += -Wall -O0 -g $(KHDR_INCLUDES) $(TOOLS_INCLUDES)
 LDLIBS := -lcap
diff --git a/tools/testing/selftests/filesystems/open_tree_ns/open_tree_ns_covered_test.c b/tools/testing/selftests/filesystems/open_tree_ns/open_tree_ns_covered_test.c
new file mode 100644
index 000000000000..1b2f1385326a
--- /dev/null
+++ b/tools/testing/selftests/filesystems/open_tree_ns/open_tree_ns_covered_test.c
@@ -0,0 +1,183 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * open_tree(OPEN_TREE_NAMESPACE) by a caller that isn't privileged over the
+ * mount namespace it copies from must not reveal what the mounts below the
+ * copied mount cover. Without AT_RECURSIVE the copy is refused when there's
+ * anything mounted below the requested directory. With AT_RECURSIVE
+ * unbindable mounts are copied as well.
+ */
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/wait.h>
+
+#include "../wrappers.h"
+#include "../../kselftest_harness.h"
+
+#ifndef OPEN_TREE_NAMESPACE
+#define OPEN_TREE_NAMESPACE	(1 << 1)
+#endif
+
+#define DIR_LEN 64
+#define PATH_LEN 128
+
+/* Child exit codes. */
+enum {
+	CHILD_OK,
+	CHILD_USERNS,		/* could not create the child user namespace */
+	CHILD_NONREC_ALLOWED,	/* the non-recursive copy was not refused */
+	CHILD_NONREC_ERRNO,	/* it was refused with the wrong error */
+	CHILD_REC_REFUSED,	/* the recursive copy failed */
+	CHILD_SETNS,		/* could not enter the new mount namespace */
+	CHILD_NO_COVER,		/* the covering mount is missing in the copy */
+	CHILD_REVEALED,		/* the covered file is visible in the copy */
+};
+
+static int write_file(const char *path, const char *s)
+{
+	ssize_t n = -1;
+	int fd;
+
+	fd = open(path, O_WRONLY | O_CLOEXEC);
+	if (fd >= 0) {
+		n = write(fd, s, strlen(s));
+		close(fd);
+	}
+	return n == (ssize_t)strlen(s) ? 0 : -1;
+}
+
+static int create_file(const char *path, const char *s)
+{
+	ssize_t n = -1;
+	int fd;
+
+	fd = open(path, O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0644);
+	if (fd >= 0) {
+		n = write(fd, s, strlen(s));
+		close(fd);
+	}
+	return n == (ssize_t)strlen(s) ? 0 : -1;
+}
+
+/* Become root in a new user namespace, the uid @uid is mapped to 0. */
+static int enter_userns(uid_t uid, gid_t gid)
+{
+	char map[32];
+
+	if (unshare(CLONE_NEWUSER))
+		return -1;
+	if (write_file("/proc/self/setgroups", "deny") && errno != ENOENT)
+		return -1;
+	snprintf(map, sizeof(map), "0 %d 1", uid);
+	if (write_file("/proc/self/uid_map", map))
+		return -1;
+	snprintf(map, sizeof(map), "0 %d 1", gid);
+	if (write_file("/proc/self/gid_map", map))
+		return -1;
+	return setgid(0) || setuid(0) ? -1 : 0;
+}
+
+FIXTURE(open_tree_ns_covered) {
+	char dir[DIR_LEN];
+	char cover[PATH_LEN];
+};
+
+FIXTURE_VARIANT(open_tree_ns_covered) {
+	int propagation;
+};
+
+FIXTURE_VARIANT_ADD(open_tree_ns_covered, private_cover) {
+	.propagation = MS_PRIVATE,
+};
+
+FIXTURE_VARIANT_ADD(open_tree_ns_covered, unbindable_cover) {
+	.propagation = MS_UNBINDABLE,
+};
+
+/*
+ * Root in a user namespace owns a private mount namespace with a tmpfs
+ * on @dir and a second tmpfs covering @dir/covered/under.txt.
+ */
+FIXTURE_SETUP(open_tree_ns_covered)
+{
+	char p[PATH_LEN];
+
+	snprintf(self->dir, sizeof(self->dir), "/tmp/open_tree_ns_covered.XXXXXX");
+	ASSERT_NE(mkdtemp(self->dir), NULL);
+	if (enter_userns(getuid(), getgid()) || unshare(CLONE_NEWNS)) {
+		rmdir(self->dir);
+		SKIP(return, "test requires user namespaces");
+	}
+	ASSERT_EQ(mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL), 0);
+	ASSERT_EQ(mount("tmpfs", self->dir, "tmpfs", 0, NULL), 0);
+
+	snprintf(self->cover, sizeof(self->cover), "%s/covered", self->dir);
+	ASSERT_EQ(mkdir(self->cover, 0755), 0);
+	snprintf(p, sizeof(p), "%s/covered/under.txt", self->dir);
+	ASSERT_EQ(create_file(p, "hidden"), 0);
+	ASSERT_EQ(mount("tmpfs", self->cover, "tmpfs", 0, NULL), 0);
+	ASSERT_EQ(mount(NULL, self->cover, NULL, variant->propagation, NULL), 0);
+}
+
+FIXTURE_TEARDOWN(open_tree_ns_covered)
+{
+	umount2(self->dir, MNT_DETACH);
+	rmdir(self->dir);
+}
+
+/* A caller in a new user namespace that doesn't own the mount namespace. */
+static int foreign_child(const char *dir)
+{
+	struct stat st;
+	int fd;
+
+	if (enter_userns(0, 0))
+		return CHILD_USERNS;
+
+	fd = sys_open_tree(AT_FDCWD, dir, OPEN_TREE_NAMESPACE | OPEN_TREE_CLOEXEC);
+	if (fd >= 0)
+		return CHILD_NONREC_ALLOWED;
+	if (errno != EINVAL)
+		return CHILD_NONREC_ERRNO;
+
+	fd = sys_open_tree(AT_FDCWD, dir,
+			   OPEN_TREE_NAMESPACE | OPEN_TREE_CLOEXEC | AT_RECURSIVE);
+	if (fd < 0)
+		return CHILD_REC_REFUSED;
+	if (setns(fd, CLONE_NEWNS))
+		return CHILD_SETNS;
+	if (stat("/covered", &st))
+		return CHILD_NO_COVER;
+	if (!access("/covered/under.txt", F_OK) || errno != ENOENT)
+		return CHILD_REVEALED;
+	return CHILD_OK;
+}
+
+TEST_F(open_tree_ns_covered, foreign_user_namespace)
+{
+	int status, fd;
+	pid_t pid;
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		_exit(foreign_child(self->dir));
+	ASSERT_EQ(waitpid(pid, &status, 0), pid);
+	ASSERT_TRUE(WIFEXITED(status));
+	ASSERT_EQ(WEXITSTATUS(status), CHILD_OK);
+
+	/* the owner of the mount namespace keeps bind mount semantics */
+	fd = sys_open_tree(AT_FDCWD, self->dir,
+			   OPEN_TREE_NAMESPACE | OPEN_TREE_CLOEXEC);
+	ASSERT_GE(fd, 0);
+	close(fd);
+}
+
+TEST_HARNESS_MAIN

-- 
2.53.0


  parent reply	other threads:[~2026-09-30 13:32 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-30 13:31 [PATCH 00/17] mount: more bugfixes, the Oprah edition Christian Brauner
2026-09-30 13:31 ` [PATCH 01/17] namespace: queue a mount only once for mount notifications Christian Brauner
2026-09-30 13:31 ` [PATCH 02/17] namespace: check a submount for references right before unmounting it Christian Brauner
2026-09-30 13:31 ` [PATCH 03/17] selftests/filesystems: check that a busy submount survives a synchronous umount Christian Brauner
2026-09-30 13:31 ` [PATCH 04/17] namespace: check a recursive bind mount for mount namespace loops Christian Brauner
2026-09-30 13:31 ` [PATCH 05/17] selftests/filesystems: check that a recursive bind mount can't pin the caller's mount namespace Christian Brauner
2026-09-30 13:31 ` [PATCH 06/17] namespace: keep covered mounts covered in OPEN_TREE_NAMESPACE Christian Brauner
2026-09-30 13:31 ` Christian Brauner [this message]
2026-09-30 13:32 ` [PATCH 08/17] namespace: look at the topmost mount for a mount namespace file Christian Brauner
2026-09-30 13:32 ` [PATCH 09/17] selftests/filesystems: check that a mount namespace file on top doesn't bury a mount Christian Brauner
2026-09-30 13:32 ` [PATCH 10/17] namespace: check the mounts before reading their parents in pivot_root() Christian Brauner
2026-09-30 13:32 ` [PATCH 11/17] namespace: don't reconfigure internal superblocks via remount and umount Christian Brauner
2026-09-30 13:32 ` [PATCH 12/17] selftests/filesystems: check that the nullfs root can't be reconfigured Christian Brauner
2026-09-30 13:32 ` [PATCH 13/17] namespace: remove the fsnotify marks of a mount namespace in process context Christian Brauner
2026-09-30 15:07   ` Amir Goldstein
2026-09-30 13:32 ` [PATCH 14/17] fsnotify: detach the connector before destroying its marks Christian Brauner
2026-10-01  9:31   ` Christian Brauner
2026-10-01 10:58     ` Amir Goldstein
2026-10-01 12:06       ` Christian Brauner
2026-09-30 13:32 ` [PATCH 15/17] dcache: don't put a mountpoint on a dentry that's being removed Christian Brauner
2026-09-30 13:32 ` [PATCH 16/17] unshare: don't drop active namespace references that were never taken Christian Brauner
2026-09-30 13:32 ` [PATCH 17/17] namespace: don't let a pseudo dentry become the root of a mount Christian Brauner

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=20260930-work-mount-fixes-3-v1-7-be34c83956ae@kernel.org \
    --to=brauner@kernel.org \
    --cc=amir73il@gmail.com \
    --cc=bpf@vger.kernel.org \
    --cc=cyphar@cyphar.com \
    --cc=jack@suse.cz \
    --cc=jlayton@kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=mason@kernel.org \
    --cc=torvalds@linux-foundation.org \
    --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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox