Re: [PATCH v7 3/6] seccomp: add a way to get a listener fd from ptrace

From: Jann Horn
Date: Thu Sep 27 2018 - 12:20:55 EST


On Thu, Sep 27, 2018 at 5:11 PM Tycho Andersen <tycho@xxxxxxxx> wrote:
> As an alternative to SECCOMP_FILTER_FLAG_GET_LISTENER, perhaps a ptrace()
> version which can acquire filters is useful. There are at least two reasons
> this is preferable, even though it uses ptrace:
>
> 1. You can control tasks that aren't cooperating with you
> 2. You can control tasks whose filters block sendmsg() and socket(); if the
> task installs a filter which blocks these calls, there's no way with
> SECCOMP_FILTER_FLAG_GET_LISTENER to get the fd out to the privileged task.
>
> v2: fix a bug where listener mode was not unset when an unused fd was not
> available
> v3: fix refcounting bug (Oleg)
> v4: * change the listener's fd flags to be 0
> * rename GET_LISTENER to NEW_LISTENER (Matthew)
> v5: * add capable(CAP_SYS_ADMIN) requirement
> v7: * point the new listener at the right filter (Jann)
>
> Signed-off-by: Tycho Andersen <tycho@xxxxxxxx>
> CC: Kees Cook <keescook@xxxxxxxxxxxx>
> CC: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
> CC: Oleg Nesterov <oleg@xxxxxxxxxx>
> CC: Eric W. Biederman <ebiederm@xxxxxxxxxxxx>
> CC: "Serge E. Hallyn" <serge@xxxxxxxxxx>
> CC: Christian Brauner <christian.brauner@xxxxxxxxxx>
> CC: Tyler Hicks <tyhicks@xxxxxxxxxxxxx>
> CC: Akihiro Suda <suda.akihiro@xxxxxxxxxxxxx>

If you address the two nits below, you can add:
Reviewed-by: Jann Horn <jannh@xxxxxxxxxx>

> include/linux/seccomp.h | 7 ++
> include/uapi/linux/ptrace.h | 2 +
> kernel/ptrace.c | 4 ++
> kernel/seccomp.c | 31 +++++++++
> tools/testing/selftests/seccomp/seccomp_bpf.c | 68 +++++++++++++++++++
> 5 files changed, 112 insertions(+)
>
> diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
> index 017444b5efed..234c61b37405 100644
> --- a/include/linux/seccomp.h
> +++ b/include/linux/seccomp.h
> @@ -83,6 +83,8 @@ static inline int seccomp_mode(struct seccomp *s)
> #ifdef CONFIG_SECCOMP_FILTER
> extern void put_seccomp_filter(struct task_struct *tsk);
> extern void get_seccomp_filter(struct task_struct *tsk);
> +extern long seccomp_new_listener(struct task_struct *task,
> + unsigned long filter_off);

Nit: Sorry, I only noticed this just now, but this should have return
type int, not long. ptrace_request() returns an int, and an fd is also
normally represented as an int, not a long.

> #else /* CONFIG_SECCOMP_FILTER */
> static inline void put_seccomp_filter(struct task_struct *tsk)
> {
> @@ -92,6 +94,11 @@ static inline void get_seccomp_filter(struct task_struct *tsk)
> {
> return;
> }
> +static inline long seccomp_new_listener(struct task_struct *task,
> + unsigned long filter_off)
> +{
> + return -EINVAL;
> +}
> #endif /* CONFIG_SECCOMP_FILTER */
>
> #if defined(CONFIG_SECCOMP_FILTER) && defined(CONFIG_CHECKPOINT_RESTORE)
> diff --git a/include/uapi/linux/ptrace.h b/include/uapi/linux/ptrace.h
> index d5a1b8a492b9..e80ecb1bd427 100644
> --- a/include/uapi/linux/ptrace.h
> +++ b/include/uapi/linux/ptrace.h
> @@ -73,6 +73,8 @@ struct seccomp_metadata {
> __u64 flags; /* Output: filter's flags */
> };
>
> +#define PTRACE_SECCOMP_NEW_LISTENER 0x420e
> +
> /* Read signals from a shared (process wide) queue */
> #define PTRACE_PEEKSIGINFO_SHARED (1 << 0)
>
> diff --git a/kernel/ptrace.c b/kernel/ptrace.c
> index 21fec73d45d4..289960ac181b 100644
> --- a/kernel/ptrace.c
> +++ b/kernel/ptrace.c
> @@ -1096,6 +1096,10 @@ int ptrace_request(struct task_struct *child, long request,
> ret = seccomp_get_metadata(child, addr, datavp);
> break;
>
> + case PTRACE_SECCOMP_NEW_LISTENER:
> + ret = seccomp_new_listener(child, addr);
> + break;
> +
> default:
> break;
> }
> diff --git a/kernel/seccomp.c b/kernel/seccomp.c
> index 44a31ac8373a..17685803a2af 100644
> --- a/kernel/seccomp.c
> +++ b/kernel/seccomp.c
> @@ -1777,4 +1777,35 @@ static struct file *init_listener(struct task_struct *task,
>
> return ret;
> }
> +
> +long seccomp_new_listener(struct task_struct *task,
> + unsigned long filter_off)
> +{
> + struct seccomp_filter *filter;
> + struct file *listener;
> + int fd;
> +
> + if (!capable(CAP_SYS_ADMIN))
> + return -EACCES;
> +
> + filter = get_nth_filter(task, filter_off);
> + if (IS_ERR(filter))
> + return PTR_ERR(filter);
> +
> + fd = get_unused_fd_flags(0);

s/0/O_CLOEXEC/ ? If userspace needs a non-cloexec fd, userspace can
easily unset O_CLOEXEC; but the reverse isn't true, because it'd be
racy.

> + if (fd < 0) {
> + __put_seccomp_filter(filter);
> + return fd;
> + }
> +
> + listener = init_listener(task, filter);
> + __put_seccomp_filter(filter);
> + if (IS_ERR(listener)) {
> + put_unused_fd(fd);
> + return PTR_ERR(listener);
> + }
> +
> + fd_install(fd, listener);
> + return fd;
> +}
> #endif
> diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
> index 5f4b836a6792..c6ba3ed5392e 100644
> --- a/tools/testing/selftests/seccomp/seccomp_bpf.c
> +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
> @@ -193,6 +193,10 @@ int seccomp(unsigned int op, unsigned int flags, void *args)
> }
> #endif
>
> +#ifndef PTRACE_SECCOMP_NEW_LISTENER
> +#define PTRACE_SECCOMP_NEW_LISTENER 0x420e
> +#endif
> +
> #if __BYTE_ORDER == __LITTLE_ENDIAN
> #define syscall_arg(_n) (offsetof(struct seccomp_data, args[_n]))
> #elif __BYTE_ORDER == __BIG_ENDIAN
> @@ -3175,6 +3179,70 @@ TEST(get_user_notification_syscall)
> EXPECT_EQ(0, WEXITSTATUS(status));
> }
>
> +TEST(get_user_notification_ptrace)
> +{
> + pid_t pid;
> + int status, listener;
> + int sk_pair[2];
> + char c;
> + struct seccomp_notif req = {};
> + struct seccomp_notif_resp resp = {};
> +
> + ASSERT_EQ(socketpair(PF_LOCAL, SOCK_SEQPACKET, 0, sk_pair), 0);
> +
> + pid = fork();
> + ASSERT_GE(pid, 0);
> +
> + if (pid == 0) {
> + EXPECT_EQ(user_trap_syscall(__NR_getpid, 0), 0);
> +
> + /* Test that we get ENOSYS while not attached */
> + EXPECT_EQ(syscall(__NR_getpid), -1);
> + EXPECT_EQ(errno, ENOSYS);
> +
> + /* Signal we're ready and have installed the filter. */
> + EXPECT_EQ(write(sk_pair[1], "J", 1), 1);
> +
> + EXPECT_EQ(read(sk_pair[1], &c, 1), 1);
> + EXPECT_EQ(c, 'H');
> +
> + exit(syscall(__NR_getpid) != USER_NOTIF_MAGIC);
> + }
> +
> + EXPECT_EQ(read(sk_pair[0], &c, 1), 1);
> + EXPECT_EQ(c, 'J');
> +
> + EXPECT_EQ(ptrace(PTRACE_ATTACH, pid), 0);
> + EXPECT_EQ(waitpid(pid, NULL, 0), pid);
> + listener = ptrace(PTRACE_SECCOMP_NEW_LISTENER, pid, 0);
> + EXPECT_GE(listener, 0);
> +
> + /* EBUSY for second listener */
> + EXPECT_EQ(ptrace(PTRACE_SECCOMP_NEW_LISTENER, pid, 0), -1);
> + EXPECT_EQ(errno, EBUSY);
> +
> + EXPECT_EQ(ptrace(PTRACE_DETACH, pid, NULL, 0), 0);
> +
> + /* Now signal we are done and respond with magic */
> + EXPECT_EQ(write(sk_pair[0], "H", 1), 1);
> +
> + req.len = sizeof(req);
> + EXPECT_EQ(ioctl(listener, SECCOMP_NOTIF_RECV, &req), sizeof(req));
> +
> + resp.len = sizeof(resp);
> + resp.id = req.id;
> + resp.error = 0;
> + resp.val = USER_NOTIF_MAGIC;
> +
> + EXPECT_EQ(ioctl(listener, SECCOMP_NOTIF_SEND, &resp), sizeof(resp));
> +
> + EXPECT_EQ(waitpid(pid, &status, 0), pid);
> + EXPECT_EQ(true, WIFEXITED(status));
> + EXPECT_EQ(0, WEXITSTATUS(status));
> +
> + close(listener);
> +}
> +
> /*
> * Check that a pid in a child namespace still shows up as valid in ours.
> */
> --
> 2.17.1
>