seccomp updates for v6.11-rc1

- interrupt SECCOMP_IOCTL_NOTIF_RECV when all users exit (Andrei Vagin)
 
 - Update selftests to check for expected NOTIF_RECV exits (Andrei Vagin)
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEpcP2jyKd1g9yPm4TiXL039xtwCYFAmaVTOkACgkQiXL039xt
 wCayUA//fJTZUq+idihdKMql9SEwYh0uIJQpGOxxBEesUksZUM4alTCswzmheLFL
 q9BxlWWJJfUsp3djeZK+0vnDv3izaR+LfA1JPEJf64ImbympbEenVXK0ZkmVrTqg
 bNAlD5c/LVpzYtB7cnOaglq18uUja6/E+EQvNYz5NLHrIhYYCieJZIiFATkHQ9Lj
 3Wq3g9FWEa5pZxpKbEI3UA2HllADnmHeb/Z78Zdvyue5lOOvsBIheQfL4m0pW38x
 xgBWNglIg7b+X+YgwYSv8w50Lhn4SJVtIynWnwzBz19qFJRQL7oJRj1zyFHZPCwZ
 ajHVIj5LOuts/BYxSiGzczxVqZaAqeOyCY5e8G+Mjk5ZD5kLYznbbcrIFIUIaHpx
 rpRD/TVVwJ3PHsOIpWHwrXKgoKnbe/0n8lJT+Ehnm/2lLrlGyZj9hLyl6/+JsizE
 dGIWgE2emykYI+52IRRYSZaw4hLb+CU52d1vd5a35wUk1ie5fcVGZAWnaul23x0I
 maQtXcyB6tYuhX3oPnxoxFVqGvCKGi3Tc5N+Vg4JR/RzTy2H7fZ02DRZq8Vs0QST
 EgO3cpCD3035qxkK6ivaV4ebPJjkL158D/+uFyne+PWQlSfrmXJvhfggPFA+Oqtb
 y8PTUV73+HxDiruXbGZ7MD8C7d+ZvGI/D+xheohYrijhivcXxcc=
 =tlFN
 -----END PGP SIGNATURE-----

Merge tag 'seccomp-v6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux

Pull seccomp updates from Kees Cook:

 - interrupt SECCOMP_IOCTL_NOTIF_RECV when all users exit (Andrei Vagin)

 - Update selftests to check for expected NOTIF_RECV exits (Andrei
   Vagin)

* tag 'seccomp-v6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux:
  selftests/seccomp: check that a zombie leader doesn't affect others
  selftests/seccomp: add test for NOTIF_RECV and unused filters
  seccomp: release task filters when the task exits
  seccomp: interrupt SECCOMP_IOCTL_NOTIF_RECV when all users have exited

kernel/exit.c

@@ -277,7 +277,6 @@ repeat:
 	}
 
 	write_unlock_irq(&tasklist_lock);
-	seccomp_filter_release(p);
 	proc_flush_pid(thread_pid);
 	put_pid(thread_pid);
 	release_thread(p);
@@ -834,6 +833,8 @@ void __noreturn do_exit(long code)
 	io_uring_files_cancel();
 	exit_signals(tsk);  /* sets PF_EXITING */
 
+	seccomp_filter_release(tsk);
+
 	acct_update_integrals(tsk);
 	group_dead = atomic_dec_and_test(&tsk->signal->live);
 	if (group_dead) {

kernel/seccomp.c

@@ -502,6 +502,9 @@ static inline pid_t seccomp_can_sync_threads(void)
 		/* Skip current, since it is initiating the sync. */
 		if (thread == caller)
 			continue;
+		/* Skip exited threads. */
+		if (thread->flags & PF_EXITING)
+			continue;
 
 		if (thread->seccomp.mode == SECCOMP_MODE_DISABLED ||
 		    (thread->seccomp.mode == SECCOMP_MODE_FILTER &&
@@ -563,18 +566,21 @@ static void __seccomp_filter_release(struct seccomp_filter *orig)
  * @tsk: task the filter should be released from.
  *
  * This function should only be called when the task is exiting as
- * it detaches it from its filter tree. As such, READ_ONCE() and
- * barriers are not needed here, as would normally be needed.
+ * it detaches it from its filter tree. PF_EXITING has to be set
+ * for the task.
  */
 void seccomp_filter_release(struct task_struct *tsk)
 {
-	struct seccomp_filter *orig = tsk->seccomp.filter;
+	struct seccomp_filter *orig;
 
-	/* We are effectively holding the siglock by not having any sighand. */
-	WARN_ON(tsk->sighand != NULL);
+	if (WARN_ON((tsk->flags & PF_EXITING) == 0))
+		return;
 
+	spin_lock_irq(&tsk->sighand->siglock);
+	orig = tsk->seccomp.filter;
 	/* Detach task from its filter tree. */
 	tsk->seccomp.filter = NULL;
+	spin_unlock_irq(&tsk->sighand->siglock);
 	__seccomp_filter_release(orig);
 }
 
@@ -602,6 +608,13 @@ static inline void seccomp_sync_threads(unsigned long flags)
 		if (thread == caller)
 			continue;
 
+		/*
+		 * Skip exited threads. seccomp_filter_release could have
+		 * been already called for this task.
+		 */
+		if (thread->flags & PF_EXITING)
+			continue;
+
 		/* Get a task reference for the new leaf node. */
 		get_seccomp_filter(caller);
 
@@ -1466,7 +1479,7 @@ static int recv_wake_function(wait_queue_entry_t *wait, unsigned int mode, int s
 				  void *key)
 {
 	/* Avoid a wakeup if event not interesting for us. */
-	if (key && !(key_to_poll(key) & (EPOLLIN | EPOLLERR)))
+	if (key && !(key_to_poll(key) & (EPOLLIN | EPOLLERR | EPOLLHUP)))
 		return 0;
 	return autoremove_wake_function(wait, mode, sync, key);
 }
@@ -1476,6 +1489,9 @@ static int recv_wait_event(struct seccomp_filter *filter)
 	DEFINE_WAIT_FUNC(wait, recv_wake_function);
 	int ret;
 
+	if (refcount_read(&filter->users) == 0)
+		return 0;
+
 	if (atomic_dec_if_positive(&filter->notif->requests) >= 0)
 		return 0;
 
@@ -1484,6 +1500,8 @@ static int recv_wait_event(struct seccomp_filter *filter)
 
 		if (atomic_dec_if_positive(&filter->notif->requests) >= 0)
 			break;
+		if (refcount_read(&filter->users) == 0)
+			break;
 
 		if (ret)
 			return ret;

tools/testing/selftests/seccomp/seccomp_bpf.c

@@ -3954,6 +3954,60 @@ TEST(user_notification_filter_empty)
 	EXPECT_GT((pollfd.revents & POLLHUP) ?: 0, 0);
 }
 
+TEST(user_ioctl_notification_filter_empty)
+{
+	pid_t pid;
+	long ret;
+	int status, p[2];
+	struct __clone_args args = {
+		.flags = CLONE_FILES,
+		.exit_signal = SIGCHLD,
+	};
+	struct seccomp_notif req = {};
+
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+	}
+
+	if (__NR_clone3 < 0)
+		SKIP(return, "Test not built with clone3 support");
+
+	ASSERT_EQ(0, pipe(p));
+
+	pid = sys_clone3(&args, sizeof(args));
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		int listener;
+
+		listener = user_notif_syscall(__NR_mknodat, SECCOMP_FILTER_FLAG_NEW_LISTENER);
+		if (listener < 0)
+			_exit(EXIT_FAILURE);
+
+		if (dup2(listener, 200) != 200)
+			_exit(EXIT_FAILURE);
+		close(p[1]);
+		close(listener);
+		sleep(1);
+
+		_exit(EXIT_SUCCESS);
+	}
+	if (read(p[0], &status, 1) != 0)
+		_exit(EXIT_SUCCESS);
+	close(p[0]);
+	/*
+	 * The seccomp filter has become unused so we should be notified once
+	 * the kernel gets around to cleaning up task struct.
+	 */
+	EXPECT_EQ(ioctl(200, SECCOMP_IOCTL_NOTIF_RECV, &req), -1);
+	EXPECT_EQ(errno, ENOENT);
+
+	EXPECT_EQ(waitpid(pid, &status, 0), pid);
+	EXPECT_EQ(true, WIFEXITED(status));
+	EXPECT_EQ(0, WEXITSTATUS(status));
+}
+
 static void *do_thread(void *data)
 {
 	return NULL;
@@ -4755,6 +4809,83 @@ TEST(user_notification_wait_killable_fatal)
 	EXPECT_EQ(SIGTERM, WTERMSIG(status));
 }
 
+struct tsync_vs_thread_leader_args {
+	pthread_t leader;
+};
+
+static void *tsync_vs_dead_thread_leader_sibling(void *_args)
+{
+	struct sock_filter allow_filter[] = {
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+	};
+	struct sock_fprog allow_prog = {
+		.len = (unsigned short)ARRAY_SIZE(allow_filter),
+		.filter = allow_filter,
+	};
+	struct tsync_vs_thread_leader_args *args = _args;
+	void *retval;
+	long ret;
+
+	ret = pthread_join(args->leader, &retval);
+	if (ret)
+		exit(1);
+	if (retval != _args)
+		exit(2);
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC, &allow_prog);
+	if (ret)
+		exit(3);
+
+	exit(0);
+}
+
+/*
+ * Ensure that a dead thread leader doesn't prevent installing new filters with
+ * SECCOMP_FILTER_FLAG_TSYNC from other threads.
+ */
+TEST(tsync_vs_dead_thread_leader)
+{
+	int status;
+	pid_t pid;
+	long ret;
+
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+	}
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		struct sock_filter allow_filter[] = {
+			BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+		};
+		struct sock_fprog allow_prog = {
+			.len = (unsigned short)ARRAY_SIZE(allow_filter),
+			.filter = allow_filter,
+		};
+		struct  tsync_vs_thread_leader_args *args;
+		pthread_t sibling;
+
+		args = malloc(sizeof(*args));
+		ASSERT_NE(NULL, args);
+		args->leader = pthread_self();
+
+		ret = pthread_create(&sibling, NULL,
+				     tsync_vs_dead_thread_leader_sibling, args);
+		ASSERT_EQ(0, ret);
+
+		/* Install a new filter just to the leader thread. */
+		ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &allow_prog);
+		ASSERT_EQ(0, ret);
+		pthread_exit(args);
+		exit(1);
+	}
+
+	EXPECT_EQ(pid, waitpid(pid, &status, 0));
+	EXPECT_EQ(0, status);
+}
+
 /*
  * TODO:
  * - expand NNP testing