[PATCH 2/4] seccomp: wake poll waiters after interrupted addfd send

[Andrea Parri <parri.andrea@gmail.com>]

An atomic SECCOMP_IOCTL_NOTIF_ADDFD request stops the listener from
reporting EPOLLOUT for its notification while the request is pending.  If
a signal interrupts the request before the target dequeues it, the
notification becomes writable again, but poll waiters are not woken.  A
supervisor waiting for EPOLLOUT can then remain asleep, leaving the target
blocked in the trapped syscall.

This affects edge-triggered epoll if the supervisor consumed the event
before the request, and level-triggered epoll, poll() and select() if a
concurrent waiter found no EPOLLOUT while the request was pending.

seccomp_notify_addfd() restores the state from REPLIED to SENT on this
path, but unlike seccomp_notify_recv() and seccomp_handle_addfd(), it does
not wake poll waiters.

Wake EPOLLOUT waiters when restoring SENT.  Extend the interrupted
ADDFD+SEND test to consume the initial edge and require another after the
interrupted request.

The bug was found and the fix was written with the help of an LLM.

Fixes: 832b9b176be06 ("seccomp: restore knotif->state when SECCOMP_ADDFD_FLAG_SEND is interrupted")
Cc: stable@vger.kernel.org
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
---
 kernel/seccomp.c                              |  4 +++-
 tools/testing/selftests/seccomp/seccomp_bpf.c | 15 ++++++++++++++-
 2 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index d74e66bcb5211..ee94a071736ef 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -1824,8 +1824,10 @@ static long seccomp_notify_addfd(struct seccomp_filter *filter,
 		ret = kaddfd.ret;
 	} else {
 		list_del(&kaddfd.list);
-		if (addfd.flags & SECCOMP_ADDFD_FLAG_SEND)
+		if (addfd.flags & SECCOMP_ADDFD_FLAG_SEND) {
 			knotif->state = SECCOMP_NOTIFY_SENT;
+			wake_up_poll(&filter->wqh, EPOLLOUT | EPOLLWRNORM);
+		}
 	}
 
 out_unlock:
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 6dd51efe8dff1..123eddb0c0d64 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -4485,6 +4485,7 @@ static void empty_handler(int signo)
  *      returning 0 from the trapped syscall without the FD installed.
  *   2. The supervisor can retry SECCOMP_IOCTL_NOTIF_ADDFD (or
  *      SECCOMP_IOCTL_NOTIF_SEND) instead of failing with -EINPROGRESS.
+ *   3. Poll waiters see a new EPOLLOUT edge for the notification.
  *
  * To deterministically hit the race window where the supervisor sleeps in
  * wait_for_completion_interruptible(&kaddfd.completion) after waking the
@@ -4504,7 +4505,10 @@ TEST(user_notification_addfd_send_interrupted)
 	 */
 	pid_t tracee_pid, sig_pid, parent_pid = getpid();
 	long ret;
-	int status, listener, memfd, err;
+	int epollfd, status, listener, memfd, err;
+	struct epoll_event event = {
+		.events = EPOLLOUT | EPOLLET,
+	};
 	struct seccomp_notif_addfd addfd = {};
 	struct seccomp_notif req = {};
 	struct sigaction sa = {};
@@ -4563,6 +4567,12 @@ TEST(user_notification_addfd_send_interrupted)
 	/* Wait for the tracee to trap in do_user_notif(). */
 	ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
 
+	epollfd = epoll_create1(EPOLL_CLOEXEC);
+	ASSERT_GE(epollfd, 0);
+	ASSERT_EQ(epoll_ctl(epollfd, EPOLL_CTL_ADD, listener, &event), 0);
+	ASSERT_EQ(epoll_wait(epollfd, &event, 1, 1000), 1);
+	ASSERT_NE(event.events & EPOLLOUT, 0);
+
 	/*
 	 * Demote the tracee to SCHED_IDLE and promote the supervisor to
 	 * SCHED_FIFO(99) on the same CPU.
@@ -4630,6 +4640,8 @@ TEST(user_notification_addfd_send_interrupted)
 	EXPECT_EQ(waitpid(sig_pid, &status, 0), sig_pid);
 	EXPECT_EQ(true, WIFEXITED(status));
 	EXPECT_EQ(0, WEXITSTATUS(status));
+	EXPECT_EQ(epoll_wait(epollfd, &event, 1, 1000), 1);
+	EXPECT_NE(event.events & EPOLLOUT, 0);
 
 	nanosleep(&delay, NULL);
 
@@ -4645,6 +4657,7 @@ TEST(user_notification_addfd_send_interrupted)
 	EXPECT_EQ(true, WIFEXITED(status));
 	EXPECT_EQ(0, WEXITSTATUS(status));
 
+	close(epollfd);
 	close(listener);
 	close(memfd);
 }
-- 
2.53.0