Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Tue, 11 Dec 2018 16:24:49 -0600
From:   "Serge E. Hallyn" <serge@hallyn.com>
To:     Tycho Andersen <tycho@tycho.ws>
Cc:     Kees Cook <keescook@chromium.org>,
        Andy Lutomirski <luto@amacapital.net>,
        Oleg Nesterov <oleg@redhat.com>,
        "Eric W . Biederman" <ebiederm@xmission.com>,
        "Serge E . Hallyn" <serge@hallyn.com>,
        Christian Brauner <christian@brauner.io>,
        Tyler Hicks <tyhicks@canonical.com>,
        Akihiro Suda <suda.akihiro@lab.ntt.co.jp>,
        Aleksa Sarai <asarai@suse.de>, Jann Horn <jannh@google.com>,
        linux-kernel@vger.kernel.org,
        containers@lists.linux-foundation.org, linux-api@vger.kernel.org
Subject: Re: [PATCH v10 4/4] samples: add an example of seccomp user trap
Message-ID: <20181211222449.GA937@mail.hallyn.com>
References: <20181209182414.30862-1-tycho@tycho.ws>
 <20181209182414.30862-5-tycho@tycho.ws>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20181209182414.30862-5-tycho@tycho.ws>
User-Agent: Mutt/1.9.4 (2018-02-28)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Sun, Dec 09, 2018 at 11:24:14AM -0700, Tycho Andersen wrote:
> The idea here is just to give a demonstration of how one could safely use
> the SECCOMP_RET_USER_NOTIF feature to do mount policies. This particular
> policy is (as noted in the comment) not very interesting, but it serves to
> illustrate how one might apply a policy dodging the various TOCTOU issues.
> 
> Signed-off-by: Tycho Andersen <tycho@tycho.ws>
> CC: Kees Cook <keescook@chromium.org>
> CC: Andy Lutomirski <luto@amacapital.net>
> CC: Oleg Nesterov <oleg@redhat.com>
> CC: Eric W. Biederman <ebiederm@xmission.com>
> CC: "Serge E. Hallyn" <serge@hallyn.com>
> CC: Christian Brauner <christian@brauner.io>
> CC: Tyler Hicks <tyhicks@canonical.com>
> CC: Akihiro Suda <suda.akihiro@lab.ntt.co.jp>
> ---
> v5: new in v5
> v7: updates for v7 API changes
> v8: * add some more comments about what's happening in main() (Kees)
>     * move from ptrace API to SECCOMP_FILTER_FLAG_NEW_LISTENER
> v9: * s/mknod/mount in error message
>     * switch to the SECCOMP_GET_NOTIF_SIZES API
>     * add a note about getting ENOENT from SECCOMP_IOCTL_NOTIF_SEND
> ---
>  samples/seccomp/.gitignore  |   1 +
>  samples/seccomp/Makefile    |   7 +-
>  samples/seccomp/user-trap.c | 375 ++++++++++++++++++++++++++++++++++++
>  3 files changed, 382 insertions(+), 1 deletion(-)
> 
> diff --git a/samples/seccomp/.gitignore b/samples/seccomp/.gitignore
> index 78fb78184291..d1e2e817d556 100644
> --- a/samples/seccomp/.gitignore
> +++ b/samples/seccomp/.gitignore
> @@ -1,3 +1,4 @@
>  bpf-direct
>  bpf-fancy
>  dropper
> +user-trap
> diff --git a/samples/seccomp/Makefile b/samples/seccomp/Makefile
> index cf34ff6b4065..4920903c8009 100644
> --- a/samples/seccomp/Makefile
> +++ b/samples/seccomp/Makefile
> @@ -1,6 +1,6 @@
>  # SPDX-License-Identifier: GPL-2.0
>  ifndef CROSS_COMPILE
> -hostprogs-$(CONFIG_SAMPLE_SECCOMP) := bpf-fancy dropper bpf-direct
> +hostprogs-$(CONFIG_SAMPLE_SECCOMP) := bpf-fancy dropper bpf-direct user-trap
>  
>  HOSTCFLAGS_bpf-fancy.o += -I$(objtree)/usr/include
>  HOSTCFLAGS_bpf-fancy.o += -idirafter $(objtree)/include
> @@ -16,6 +16,10 @@ HOSTCFLAGS_bpf-direct.o += -I$(objtree)/usr/include
>  HOSTCFLAGS_bpf-direct.o += -idirafter $(objtree)/include
>  bpf-direct-objs := bpf-direct.o
>  
> +HOSTCFLAGS_user-trap.o += -I$(objtree)/usr/include
> +HOSTCFLAGS_user-trap.o += -idirafter $(objtree)/include
> +user-trap-objs := user-trap.o
> +
>  # Try to match the kernel target.
>  ifndef CONFIG_64BIT
>  
> @@ -33,6 +37,7 @@ HOSTCFLAGS_bpf-fancy.o += $(MFLAG)
>  HOSTLDLIBS_bpf-direct += $(MFLAG)
>  HOSTLDLIBS_bpf-fancy += $(MFLAG)
>  HOSTLDLIBS_dropper += $(MFLAG)
> +HOSTLDLIBS_user-trap += $(MFLAG)
>  endif
>  always := $(hostprogs-m)
>  endif
> diff --git a/samples/seccomp/user-trap.c b/samples/seccomp/user-trap.c
> new file mode 100644
> index 000000000000..61267cb59c8e
> --- /dev/null
> +++ b/samples/seccomp/user-trap.c
> @@ -0,0 +1,375 @@
> +#include <signal.h>
> +#include <stdio.h>
> +#include <stdlib.h>
> +#include <unistd.h>
> +#include <errno.h>
> +#include <fcntl.h>
> +#include <string.h>
> +#include <stddef.h>
> +#include <sys/sysmacros.h>
> +#include <sys/types.h>
> +#include <sys/wait.h>
> +#include <sys/socket.h>
> +#include <sys/stat.h>
> +#include <sys/mman.h>
> +#include <sys/syscall.h>
> +#include <sys/user.h>
> +#include <sys/ioctl.h>
> +#include <sys/ptrace.h>
> +#include <sys/mount.h>
> +#include <linux/limits.h>
> +#include <linux/filter.h>
> +#include <linux/seccomp.h>
> +
> +#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
> +
> +static int seccomp(unsigned int op, unsigned int flags, void *args)
> +{
> +	errno = 0;
> +	return syscall(__NR_seccomp, op, flags, args);
> +}
> +
> +static int send_fd(int sock, int fd)
> +{
> +	struct msghdr msg = {};
> +	struct cmsghdr *cmsg;
> +	char buf[CMSG_SPACE(sizeof(int))] = {0}, c = 'c';
> +	struct iovec io = {
> +		.iov_base = &c,
> +		.iov_len = 1,
> +	};
> +
> +	msg.msg_iov = &io;
> +	msg.msg_iovlen = 1;
> +	msg.msg_control = buf;
> +	msg.msg_controllen = sizeof(buf);
> +	cmsg = CMSG_FIRSTHDR(&msg);
> +	cmsg->cmsg_level = SOL_SOCKET;
> +	cmsg->cmsg_type = SCM_RIGHTS;
> +	cmsg->cmsg_len = CMSG_LEN(sizeof(int));
> +	*((int *)CMSG_DATA(cmsg)) = fd;
> +	msg.msg_controllen = cmsg->cmsg_len;
> +
> +	if (sendmsg(sock, &msg, 0) < 0) {
> +		perror("sendmsg");
> +		return -1;
> +	}
> +
> +	return 0;
> +}
> +
> +static int recv_fd(int sock)
> +{
> +	struct msghdr msg = {};
> +	struct cmsghdr *cmsg;
> +	char buf[CMSG_SPACE(sizeof(int))] = {0}, c = 'c';
> +	struct iovec io = {
> +		.iov_base = &c,
> +		.iov_len = 1,
> +	};
> +
> +	msg.msg_iov = &io;
> +	msg.msg_iovlen = 1;
> +	msg.msg_control = buf;
> +	msg.msg_controllen = sizeof(buf);
> +
> +	if (recvmsg(sock, &msg, 0) < 0) {
> +		perror("recvmsg");
> +		return -1;
> +	}
> +
> +	cmsg = CMSG_FIRSTHDR(&msg);
> +
> +	return *((int *)CMSG_DATA(cmsg));
> +}
> +
> +static int user_trap_syscall(int nr, unsigned int flags)
> +{
> +	struct sock_filter filter[] = {
> +		BPF_STMT(BPF_LD+BPF_W+BPF_ABS,
> +			offsetof(struct seccomp_data, nr)),
> +		BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, nr, 0, 1),
> +		BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_USER_NOTIF),
> +		BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
> +	};
> +
> +	struct sock_fprog prog = {
> +		.len = (unsigned short)ARRAY_SIZE(filter),
> +		.filter = filter,
> +	};
> +
> +	return seccomp(SECCOMP_SET_MODE_FILTER, flags, &prog);
> +}
> +
> +static int handle_req(struct seccomp_notif *req,
> +		      struct seccomp_notif_resp *resp, int listener)
> +{
> +	char path[PATH_MAX], source[PATH_MAX], target[PATH_MAX];
> +	int ret = -1, mem;
> +
> +	resp->id = req->id;
> +	resp->error = -EPERM;
> +	resp->val = 0;
> +
> +	if (req->data.nr != __NR_mount) {
> +		fprintf(stderr, "huh? trapped something besides mount? %d\n", req->data.nr);
> +		return -1;
> +	}
> +
> +	/* Only allow bind mounts. */
> +	if (!(req->data.args[3] & MS_BIND))
> +		return 0;
> +
> +	/*
> +	 * Ok, let's read the task's memory to see where they wanted their
> +	 * mount to go.
> +	 */
> +	snprintf(path, sizeof(path), "/proc/%d/mem", req->pid);
> +	mem = open(path, O_RDONLY);
> +	if (mem < 0) {
> +		perror("open mem");
> +		return -1;
> +	}
> +
> +	/*
> +	 * Now we avoid a TOCTOU: we referred to a pid by its pid, but since
> +	 * the pid that made the syscall may have died, we need to confirm that
> +	 * the pid is still valid after we open its /proc/pid/mem file. We can
> +	 * ask the listener fd this as follows.
> +	 *
> +	 * Note that this check should occur *after* any task-specific
> +	 * resources are opened, to make sure that the task has not died and
> +	 * we're not wrongly reading someone else's state in order to make
> +	 * decisions.
> +	 */
> +	if (ioctl(listener, SECCOMP_IOCTL_NOTIF_ID_VALID, &req->id) < 0) {
> +		fprintf(stderr, "task died before we could map its memory\n");
> +		goto out;
> +	}
> +
> +	/*
> +	 * Phew, we've got the right /proc/pid/mem. Now we can read it. Note
> +	 * that to avoid another TOCTOU, we should read all of the pointer args
> +	 * before we decide to allow the syscall.
> +	 */
> +	if (lseek(mem, req->data.args[0], SEEK_SET) < 0) {
> +		perror("seek");
> +		goto out;
> +	}
> +
> +	ret = read(mem, source, sizeof(source));
> +	if (ret < 0) {
> +		perror("read");
> +		goto out;
> +	}
> +
> +	if (lseek(mem, req->data.args[1], SEEK_SET) < 0) {
> +		perror("seek");
> +		goto out;
> +	}
> +
> +	ret = read(mem, target, sizeof(target));
> +	if (ret < 0) {
> +		perror("read");
> +		goto out;
> +	}
> +
> +	/*
> +	 * Our policy is to only allow bind mounts inside /tmp. This isn't very
> +	 * interesting, because we could do unprivlieged bind mounts with user
> +	 * namespaces already, but you get the idea.
> +	 */
> +	if (!strncmp(source, "/tmp", 4) && !strncmp(target, "/tmp", 4)) {

Of course the host could have a /tmproot or somesuch, so you might want to
check the first 5 characters :)