public inbox for [email protected]
 help / color / mirror / Atom feed
From: Dylan Yudaken <[email protected]>
To: Jens Axboe <[email protected]>,
	Pavel Begunkov <[email protected]>,
	<[email protected]>
Cc: <[email protected]>, <[email protected]>,
	Dylan Yudaken <[email protected]>
Subject: [PATCH for-next 8/8] io_uring: multishot recv
Date: Tue, 28 Jun 2022 08:02:28 -0700	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>

Support multishot receive for io_uring.
Typical server applications will run a loop where for each recv CQE it
requeues another recv/recvmsg.

This can be simplified by using the existing multishot functionality
combined with io_uring's provided buffers.
The API is to add the IORING_RECV_MULTISHOT flag to the SQE. CQEs will
then be posted (with IORING_CQE_F_MORE flag set) when data is available
and is read. Once an error occurs or the socket ends, the multishot will
be removed and a completion without IORING_CQE_F_MORE will be posted.

The benefit to this is that the recv is much more performant.
 * Subsequent receives are queued up straight away without requiring the
   application to finish a processing loop.
 * If there are more data in the socket (sat the provided buffer size is
   smaller than the socket buffer) then the data is immediately
   returned, improving batching.
 * Poll is only armed once and reused, saving CPU cycles

Signed-off-by: Dylan Yudaken <[email protected]>
---
 io_uring/net.c | 93 +++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 81 insertions(+), 12 deletions(-)

diff --git a/io_uring/net.c b/io_uring/net.c
index 0268c4603f5d..9bf8c6c0b549 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -389,6 +389,8 @@ int io_recvmsg_prep_async(struct io_kiocb *req)
 	return ret;
 }
 
+#define RECVMSG_FLAGS (IORING_RECVSEND_POLL_FIRST | IORING_RECV_MULTISHOT)
+
 int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req);
@@ -399,13 +401,22 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr));
 	sr->len = READ_ONCE(sqe->len);
 	sr->flags = READ_ONCE(sqe->addr2);
-	if (sr->flags & ~IORING_RECVSEND_POLL_FIRST)
+	if (sr->flags & ~(RECVMSG_FLAGS))
 		return -EINVAL;
 	sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL;
 	if (sr->msg_flags & MSG_DONTWAIT)
 		req->flags |= REQ_F_NOWAIT;
 	if (sr->msg_flags & MSG_ERRQUEUE)
 		req->flags |= REQ_F_CLEAR_POLLIN;
+	if (sr->flags & IORING_RECV_MULTISHOT) {
+		if (!(req->flags & REQ_F_BUFFER_SELECT))
+			return -EINVAL;
+		if (sr->msg_flags & MSG_WAITALL)
+			return -EINVAL;
+		if (req->opcode == IORING_OP_RECV && sr->len)
+			return -EINVAL;
+		req->flags |= REQ_F_APOLL_MULTISHOT;
+	}
 
 #ifdef CONFIG_COMPAT
 	if (req->ctx->compat)
@@ -415,6 +426,14 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	return 0;
 }
 
+static inline void io_recv_prep_retry(struct io_kiocb *req)
+{
+	struct io_sr_msg *sr = io_kiocb_to_cmd(req);
+
+	sr->done_io = 0;
+	sr->len = 0; /* get from the provided buffer */
+}
+
 int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req);
@@ -424,6 +443,7 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 	unsigned flags;
 	int ret, min_ret = 0;
 	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
+	size_t len = sr->len;
 
 	sock = sock_from_file(req->file);
 	if (unlikely(!sock))
@@ -442,16 +462,17 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 	    (sr->flags & IORING_RECVSEND_POLL_FIRST))
 		return io_setup_async_msg(req, kmsg);
 
+retry_multishot:
 	if (io_do_buffer_select(req)) {
 		void __user *buf;
 
-		buf = io_buffer_select(req, &sr->len, issue_flags);
+		buf = io_buffer_select(req, &len, issue_flags);
 		if (!buf)
 			return -ENOBUFS;
 		kmsg->fast_iov[0].iov_base = buf;
-		kmsg->fast_iov[0].iov_len = sr->len;
+		kmsg->fast_iov[0].iov_len = len;
 		iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov, 1,
-				sr->len);
+				len);
 	}
 
 	flags = sr->msg_flags;
@@ -463,8 +484,15 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 	kmsg->msg.msg_get_inq = 1;
 	ret = __sys_recvmsg_sock(sock, &kmsg->msg, sr->umsg, kmsg->uaddr, flags);
 	if (ret < min_ret) {
-		if (ret == -EAGAIN && force_nonblock)
-			return io_setup_async_msg(req, kmsg);
+		if (ret == -EAGAIN && force_nonblock) {
+			ret = io_setup_async_msg(req, kmsg);
+			if (ret == -EAGAIN && (req->flags & IO_APOLL_MULTI_POLLED) ==
+					       IO_APOLL_MULTI_POLLED) {
+				io_kbuf_recycle(req, issue_flags);
+				ret = IOU_ISSUE_SKIP_COMPLETE;
+			}
+			return ret;
+		}
 		if (ret == -ERESTARTSYS)
 			ret = -EINTR;
 		if (ret > 0 && io_net_retry(sock, flags)) {
@@ -491,8 +519,24 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 	cflags = io_put_kbuf(req, issue_flags);
 	if (kmsg->msg.msg_inq)
 		cflags |= IORING_CQE_F_SOCK_NONEMPTY;
+
+	if (!(req->flags & REQ_F_APOLL_MULTISHOT)) {
+		io_req_set_res(req, ret, cflags);
+		return IOU_OK;
+	}
+
+	if (ret > 0) {
+		if (io_post_aux_cqe(req->ctx, req->cqe.user_data, ret,
+				    cflags | IORING_CQE_F_MORE)) {
+			io_recv_prep_retry(req);
+			goto retry_multishot;
+		} else {
+			ret = -ECANCELED;
+		}
+	}
+
 	io_req_set_res(req, ret, cflags);
-	return IOU_OK;
+	return req->flags & REQ_F_POLLED ? IOU_STOP_MULTISHOT : ret;
 }
 
 int io_recv(struct io_kiocb *req, unsigned int issue_flags)
@@ -505,6 +549,7 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 	unsigned flags;
 	int ret, min_ret = 0;
 	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
+	size_t len = sr->len;
 
 	if (!(req->flags & REQ_F_POLLED) &&
 	    (sr->flags & IORING_RECVSEND_POLL_FIRST))
@@ -514,16 +559,17 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 	if (unlikely(!sock))
 		return -ENOTSOCK;
 
+retry_multishot:
 	if (io_do_buffer_select(req)) {
 		void __user *buf;
 
-		buf = io_buffer_select(req, &sr->len, issue_flags);
+		buf = io_buffer_select(req, &len, issue_flags);
 		if (!buf)
 			return -ENOBUFS;
 		sr->buf = buf;
 	}
 
-	ret = import_single_range(READ, sr->buf, sr->len, &iov, &msg.msg_iter);
+	ret = import_single_range(READ, sr->buf, len, &iov, &msg.msg_iter);
 	if (unlikely(ret))
 		goto out_free;
 
@@ -543,8 +589,14 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 
 	ret = sock_recvmsg(sock, &msg, flags);
 	if (ret < min_ret) {
-		if (ret == -EAGAIN && force_nonblock)
-			return -EAGAIN;
+		if (ret == -EAGAIN && force_nonblock) {
+			if ((req->flags & IO_APOLL_MULTI_POLLED) == IO_APOLL_MULTI_POLLED) {
+				io_kbuf_recycle(req, issue_flags);
+				ret = IOU_ISSUE_SKIP_COMPLETE;
+			}
+
+			return ret;
+		}
 		if (ret == -ERESTARTSYS)
 			ret = -EINTR;
 		if (ret > 0 && io_net_retry(sock, flags)) {
@@ -570,8 +622,25 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 	cflags = io_put_kbuf(req, issue_flags);
 	if (msg.msg_inq)
 		cflags |= IORING_CQE_F_SOCK_NONEMPTY;
+
+
+	if (!(req->flags & REQ_F_APOLL_MULTISHOT)) {
+		io_req_set_res(req, ret, cflags);
+		return IOU_OK;
+	}
+
+	if (ret > 0) {
+		if (io_post_aux_cqe(req->ctx, req->cqe.user_data, ret,
+				    cflags | IORING_CQE_F_MORE)) {
+			io_recv_prep_retry(req);
+			goto retry_multishot;
+		} else {
+			ret = -ECANCELED;
+		}
+	}
+
 	io_req_set_res(req, ret, cflags);
-	return IOU_OK;
+	return req->flags & REQ_F_POLLED ? IOU_STOP_MULTISHOT : ret;
 }
 
 int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-- 
2.30.2



  parent reply	other threads:[~2022-06-28 15:03 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-06-28 15:02 [PATCH for-next 0/8] io_uring: multishot recv Dylan Yudaken
2022-06-28 15:02 ` [PATCH for-next 1/8] io_uring: allow 0 length for buffer select Dylan Yudaken
2022-06-28 15:02 ` [PATCH for-next 2/8] io_uring: restore bgid in io_put_kbuf Dylan Yudaken
2022-06-28 15:12   ` Jens Axboe
2022-06-28 15:02 ` [PATCH for-next 3/8] io_uring: allow iov_len = 0 for recvmsg and buffer select Dylan Yudaken
2022-06-28 15:02 ` [PATCH for-next 4/8] io_uring: recycle buffers on error Dylan Yudaken
2022-06-28 15:02 ` [PATCH for-next 5/8] io_uring: clean up io_poll_check_events return values Dylan Yudaken
2022-06-28 15:02 ` [PATCH for-next 6/8] io_uring: add IOU_STOP_MULTISHOT return code Dylan Yudaken
2022-06-28 15:02 ` [PATCH for-next 7/8] io_uring: add IORING_RECV_MULTISHOT flag Dylan Yudaken
2022-06-28 15:12   ` Jens Axboe
2022-06-28 15:02 ` Dylan Yudaken [this message]
2022-06-28 15:17   ` [PATCH for-next 8/8] io_uring: multishot recv Jens Axboe

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox