If multiple threads call kevent() to get AIO events on same kqueue fd,

it is possible that a single AIO event will be reported to multiple
threads, it is not threading friendly, and the existing API can not
control this behavior.
Allocate a kevent flags field sigev_notify_kevent_flags for AIO event
notification in sigevent, and allow user to pass EV_CLEAR, EV_DISPATCH
or EV_ONESHOT to AIO kernel code, user can control whether the event
should be cleared once it is retrieved by a thread. This change should
be comptaible with existing application, because the field should have
already been zero-filled, and no additional action will be taken by
kernel.

PR:	kern/156567

2 files changed, 9 insertions, 1 deletions

diff --git a/sys/kern/vfs_aio.c b/sys/kern/vfs_aio.c
index 2d9994f2266d..eaadf1314646 100644
--- a/sys/kern/vfs_aio.c
+++ b/sys/kern/vfs_aio.c
@@ -1524,6 +1524,7 @@ aio_aqueue(struct thread *td, struct aiocb *job, struct aioliojob *lj,
 	int error;
 	int fd, kqfd;
 	int jid;
+	u_short evflags;
 
 	if (p->p_aioinfo == NULL)
 		aio_init_aioinfo(p);
@@ -1646,10 +1647,15 @@ aio_aqueue(struct thread *td, struct aiocb *job, struct aioliojob *lj,
 
 	if (aiocbe->uaiocb.aio_sigevent.sigev_notify != SIGEV_KEVENT)
 		goto no_kqueue;
+	evflags = aiocbe->uaiocb.aio_sigevent.sigev_notify_kevent_flags;
+	if ((evflags & ~(EV_CLEAR | EV_DISPATCH | EV_ONESHOT)) != 0) {
+		error = EINVAL;
+		goto aqueue_fail;
+	}
 	kqfd = aiocbe->uaiocb.aio_sigevent.sigev_notify_kqueue;
 	kev.ident = (uintptr_t)aiocbe->uuaiocb;
 	kev.filter = EVFILT_AIO;
-	kev.flags = EV_ADD | EV_ENABLE | EV_FLAG1;
+	kev.flags = EV_ADD | EV_ENABLE | EV_FLAG1 | evflags;
 	kev.data = (intptr_t)aiocbe;
 	kev.udata = aiocbe->uaiocb.aio_sigevent.sigev_value.sival_ptr;
 	error = kqfd_register(kqfd, &kev, td, 1);
diff --git a/sys/sys/signal.h b/sys/sys/signal.h
index 971683516e3c..73aeea117f7d 100644
--- a/sys/sys/signal.h
+++ b/sys/sys/signal.h
@@ -169,12 +169,14 @@ struct sigevent {
 			void (*_function)(union sigval);
 			void *_attribute; /* pthread_attr_t * */
 		} _sigev_thread;
+		unsigned short _kevent_flags;
 		long __spare__[8];
 	} _sigev_un;
 };
 
 #if __BSD_VISIBLE
 #define	sigev_notify_kqueue		sigev_signo
+#define	sigev_notify_kevent_flags	_sigev_un._kevent_flags
 #define	sigev_notify_thread_id		_sigev_un._threadid
 #endif
 #define	sigev_notify_function		_sigev_un._sigev_thread._function