[PATCH v2] io_uring: add EPOLLEXCLUSIVE flag to aoid thundering herd type behavior

[Jiufei Xue <jiufei.xue@xxxxxxxxxxxxxxxxx>]

From: Jiufei Xue <jiufei.xue@xxxxxxxxxxxxxxxxx>

Applications can use this flag to avoid accept thundering herd.
And poll_events should be changed to 32 bits to cover EPOLLEXCLUSIVE.

Signed-off-by: Jiufei Xue <jiufei.xue@xxxxxxxxxxxxxxxxx>
---
 fs/io_uring.c                 | 13 +++++++++----
 include/uapi/linux/io_uring.h |  2 +-
 tools/io_uring/liburing.h     |  2 +-
 3 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 47790a2..03951ec 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -4289,7 +4289,11 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt,
 
 	pt->error = 0;
 	poll->head = head;
-	add_wait_queue(head, &poll->wait);
+
+	if (poll->events & EPOLLEXCLUSIVE)
+		add_wait_queue_exclusive(head, &poll->wait);
+	else
+		add_wait_queue(head, &poll->wait);
 }
 
 static void io_async_queue_proc(struct file *file, struct wait_queue_head *head,
@@ -4602,7 +4606,7 @@ static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head,
 static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_poll_iocb *poll = &req->poll;
-	u16 events;
+	u32 events;
 
 	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
 		return -EINVAL;
@@ -4612,7 +4616,8 @@ static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe
 		return -EBADF;
 
 	events = READ_ONCE(sqe->poll_events);
-	poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP;
+	poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP |
+		       (events & EPOLLEXCLUSIVE);
 
 	get_task_struct(current);
 	req->task = current;
@@ -8196,7 +8201,7 @@ static int __init io_uring_init(void)
 	BUILD_BUG_SQE_ELEM(28, /* compat */   int, rw_flags);
 	BUILD_BUG_SQE_ELEM(28, /* compat */ __u32, rw_flags);
 	BUILD_BUG_SQE_ELEM(28, __u32,  fsync_flags);
-	BUILD_BUG_SQE_ELEM(28, __u16,  poll_events);
+	BUILD_BUG_SQE_ELEM(28, __u32,  poll_events);
 	BUILD_BUG_SQE_ELEM(28, __u32,  sync_range_flags);
 	BUILD_BUG_SQE_ELEM(28, __u32,  msg_flags);
 	BUILD_BUG_SQE_ELEM(28, __u32,  timeout_flags);
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 92c2269..afc7edd 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -31,7 +31,7 @@ struct io_uring_sqe {
 	union {
 		__kernel_rwf_t	rw_flags;
 		__u32		fsync_flags;
-		__u16		poll_events;
+		__u32		poll_events;
 		__u32		sync_range_flags;
 		__u32		msg_flags;
 		__u32		timeout_flags;
diff --git a/tools/io_uring/liburing.h b/tools/io_uring/liburing.h
index 5f305c8..094b9ec 100644
--- a/tools/io_uring/liburing.h
+++ b/tools/io_uring/liburing.h
@@ -145,7 +145,7 @@ static inline void io_uring_prep_write_fixed(struct io_uring_sqe *sqe, int fd,
 }
 
 static inline void io_uring_prep_poll_add(struct io_uring_sqe *sqe, int fd,
-					  short poll_mask)
+					  unsigned poll_mask)
 {
 	memset(sqe, 0, sizeof(*sqe));
 	sqe->opcode = IORING_OP_POLL_ADD;
-- 
1.8.3.1