io_uring/net: switch io_recv() to using io_async_msghdr

No functional changes in this patch, just in preparation for carrying
more state than what is available now, if necessary.
Signed-off-by: Jens Axboe <axboe@kernel.dk>

io_uring/net.c

@@ -320,7 +320,7 @@ static int io_sendmsg_copy_hdr(struct io_kiocb *req,
 	return ret;
 }
 
-int io_send_prep_async(struct io_kiocb *req)
+int io_sendrecv_prep_async(struct io_kiocb *req)
 {
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
 	struct io_async_msghdr *io;
@@ -703,13 +703,13 @@ static inline void io_recv_prep_retry(struct io_kiocb *req)
  * again (for multishot).
  */
 static inline bool io_recv_finish(struct io_kiocb *req, int *ret,
-				  struct msghdr *msg, bool mshot_finished,
-				  unsigned issue_flags)
+				  struct io_async_msghdr *kmsg,
+				  bool mshot_finished, unsigned issue_flags)
 {
 	unsigned int cflags;
 
 	cflags = io_put_kbuf(req, issue_flags);
-	if (msg->msg_inq > 0)
+	if (kmsg->msg.msg_inq > 0)
 		cflags |= IORING_CQE_F_SOCK_NONEMPTY;
 
 	/*
@@ -723,7 +723,7 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret,
 
 		io_recv_prep_retry(req);
 		/* Known not-empty or unknown state, retry */
-		if (cflags & IORING_CQE_F_SOCK_NONEMPTY || msg->msg_inq < 0) {
+		if (cflags & IORING_CQE_F_SOCK_NONEMPTY || kmsg->msg.msg_inq < 0) {
 			if (sr->nr_multishot_loops++ < MULTISHOT_MAX_RETRY)
 				return false;
 			/* mshot retries exceeded, force a requeue */
@@ -924,7 +924,7 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 	else
 		io_kbuf_recycle(req, issue_flags);
 
-	if (!io_recv_finish(req, &ret, &kmsg->msg, mshot_finished, issue_flags))
+	if (!io_recv_finish(req, &ret, kmsg, mshot_finished, issue_flags))
 		goto retry_multishot;
 
 	if (mshot_finished)
@@ -938,29 +938,42 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
-	struct msghdr msg;
+	struct io_async_msghdr iomsg, *kmsg;
 	struct socket *sock;
 	unsigned flags;
 	int ret, min_ret = 0;
 	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
 	size_t len = sr->len;
 
+	if (req_has_async_data(req)) {
+		kmsg = req->async_data;
+	} else {
+		kmsg = &iomsg;
+		kmsg->free_iov = NULL;
+		kmsg->msg.msg_name = NULL;
+		kmsg->msg.msg_namelen = 0;
+		kmsg->msg.msg_control = NULL;
+		kmsg->msg.msg_get_inq = 1;
+		kmsg->msg.msg_controllen = 0;
+		kmsg->msg.msg_iocb = NULL;
+		kmsg->msg.msg_ubuf = NULL;
+
+		if (!io_do_buffer_select(req)) {
+			ret = import_ubuf(ITER_DEST, sr->buf, sr->len,
+					  &kmsg->msg.msg_iter);
+			if (unlikely(ret))
+				return ret;
+		}
+	}
+
 	if (!(req->flags & REQ_F_POLLED) &&
 	    (sr->flags & IORING_RECVSEND_POLL_FIRST))
-		return -EAGAIN;
+		return io_setup_async_msg(req, kmsg, issue_flags);
 
 	sock = sock_from_file(req->file);
 	if (unlikely(!sock))
 		return -ENOTSOCK;
 
-	msg.msg_name = NULL;
-	msg.msg_namelen = 0;
-	msg.msg_control = NULL;
-	msg.msg_get_inq = 1;
-	msg.msg_controllen = 0;
-	msg.msg_iocb = NULL;
-	msg.msg_ubuf = NULL;
-
 	flags = sr->msg_flags;
 	if (force_nonblock)
 		flags |= MSG_DONTWAIT;
@@ -974,22 +987,23 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 			return -ENOBUFS;
 		sr->buf = buf;
 		sr->len = len;
+		ret = import_ubuf(ITER_DEST, sr->buf, sr->len,
+				  &kmsg->msg.msg_iter);
+		if (unlikely(ret))
+			goto out_free;
 	}
 
-	ret = import_ubuf(ITER_DEST, sr->buf, len, &msg.msg_iter);
-	if (unlikely(ret))
-		goto out_free;
-
-	msg.msg_inq = -1;
-	msg.msg_flags = 0;
+	kmsg->msg.msg_inq = -1;
+	kmsg->msg.msg_flags = 0;
 
 	if (flags & MSG_WAITALL)
-		min_ret = iov_iter_count(&msg.msg_iter);
+		min_ret = iov_iter_count(&kmsg->msg.msg_iter);
 
-	ret = sock_recvmsg(sock, &msg, flags);
+	ret = sock_recvmsg(sock, &kmsg->msg, flags);
 	if (ret < min_ret) {
 		if (ret == -EAGAIN && force_nonblock) {
-			if (issue_flags & IO_URING_F_MULTISHOT) {
+			ret = io_setup_async_msg(req, kmsg, issue_flags);
+			if (ret == -EAGAIN && issue_flags & IO_URING_F_MULTISHOT) {
 				io_kbuf_recycle(req, issue_flags);
 				return IOU_ISSUE_SKIP_COMPLETE;
 			}
@@ -1001,12 +1015,12 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 			sr->buf += ret;
 			sr->done_io += ret;
 			req->flags |= REQ_F_BL_NO_RECYCLE;
-			return -EAGAIN;
+			return io_setup_async_msg(req, kmsg, issue_flags);
 		}
 		if (ret == -ERESTARTSYS)
 			ret = -EINTR;
 		req_set_fail(req);
-	} else if ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) {
+	} else if ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) {
 out_free:
 		req_set_fail(req);
 	}
@@ -1018,9 +1032,14 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 	else
 		io_kbuf_recycle(req, issue_flags);
 
-	if (!io_recv_finish(req, &ret, &msg, ret <= 0, issue_flags))
+	if (!io_recv_finish(req, &ret, kmsg, ret <= 0, issue_flags))
 		goto retry_multishot;
 
+	if (ret == -EAGAIN)
+		return io_setup_async_msg(req, kmsg, issue_flags);
+	else if (ret != IOU_OK && ret != IOU_STOP_MULTISHOT)
+		io_req_msg_cleanup(req, kmsg, issue_flags);
+
 	return ret;
 }
 

io_uring/net.h

@@ -40,7 +40,7 @@ int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
 int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags);
 
 int io_send(struct io_kiocb *req, unsigned int issue_flags);
-int io_send_prep_async(struct io_kiocb *req);
+int io_sendrecv_prep_async(struct io_kiocb *req);
 
 int io_recvmsg_prep_async(struct io_kiocb *req);
 int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);

io_uring/opdef.c

@@ -604,13 +604,16 @@ const struct io_cold_def io_cold_defs[] = {
 		.async_size		= sizeof(struct io_async_msghdr),
 		.cleanup		= io_sendmsg_recvmsg_cleanup,
 		.fail			= io_sendrecv_fail,
-		.prep_async		= io_send_prep_async,
+		.prep_async		= io_sendrecv_prep_async,
 #endif
 	},
 	[IORING_OP_RECV] = {
 		.name			= "RECV",
 #if defined(CONFIG_NET)
+		.async_size		= sizeof(struct io_async_msghdr),
+		.cleanup		= io_sendmsg_recvmsg_cleanup,
 		.fail			= io_sendrecv_fail,
+		.prep_async		= io_sendrecv_prep_async,
 #endif
 	},
 	[IORING_OP_OPENAT2] = {
@@ -687,7 +690,7 @@ const struct io_cold_def io_cold_defs[] = {
 		.name			= "SEND_ZC",
 #if defined(CONFIG_NET)
 		.async_size		= sizeof(struct io_async_msghdr),
-		.prep_async		= io_send_prep_async,
+		.prep_async		= io_sendrecv_prep_async,
 		.cleanup		= io_send_zc_cleanup,
 		.fail			= io_sendrecv_fail,
 #endif