seccomp: interrupt SECCOMP_IOCTL_NOTIF_RECV when all users have exited

SECCOMP_IOCTL_NOTIF_RECV promptly returns when a seccomp filter becomes
unused, as a filter without users can't trigger any events.

Previously, event listeners had to rely on epoll to detect when all
processes had exited.

The change is based on the 'commit 99cdb8b9a573 ("seccomp: notify about
unused filter")' which implemented (E)POLLHUP notifications.

Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Andrei Vagin <avagin@google.com>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lore.kernel.org/r/20240628021014.231976-2-avagin@google.com
Reviewed-by: Tycho Andersen <tandersen@netflix.com>
Signed-off-by: Kees Cook <kees@kernel.org>

diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index e30b60b57614ed9f3a07461154180d51941d5186..60990264fef0b3708a73b81a7cb05d4a0ac09ad8 100644 (file)
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -1466,7 +1466,7 @@ 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 +1476,9 @@ 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 +1487,8 @@ 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;