[PATCH 1/2] io_uring/net: support registered buffer for plain send and recv

[Ming Lei <tom.leiming@gmail.com>]

From: Ming Lei <tom.leiming@gmail.com>

So far IORING_RECVSEND_FIXED_BUF is only honoured on the SEND_ZC path,
even though the import wiring is already present for plain send and
completely absent for recv. Targets such as ublk's NBD backend want to
push/pull I/O data directly to/from an io_uring registered buffer over a
plain send/recv on a TCP socket, without the SEND_ZC notification
machinery.

Wire IORING_RECVSEND_FIXED_BUF into the plain IORING_OP_SEND and
IORING_OP_RECV paths:

 - Accept the flag in SENDMSG_FLAGS / RECVMSG_FLAGS and, at prep time,
   restrict it to the non-vectorized IORING_OP_SEND / IORING_OP_RECV
   opcodes. It is mutually exclusive with buffer select, bundles and
   (for recv) multishot, and records sqe->buf_index.

 - For recv, set REQ_F_IMPORT_BUFFER in setup so the registered buffer
   is imported lazily at issue time, mirroring the send path.

 - In io_send()/io_recv(), import the registered buffer via
   io_import_reg_buf() (ITER_SOURCE for send, ITER_DEST for recv) and
   clear REQ_F_IMPORT_BUFFER. The resulting bvec iter persists in
   async_data, so MSG_WAITALL partial send/recv retries resume at the
   right offset.

Signed-off-by: Ming Lei <tom.leiming@gmail.com>
---
 io_uring/net.c | 46 ++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 44 insertions(+), 2 deletions(-)

diff --git a/io_uring/net.c b/io_uring/net.c
index f01f1d25e930..9c42c3dbccd7 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -418,7 +418,8 @@ static int io_sendmsg_setup(struct io_kiocb *req, const struct io_uring_sqe *sqe
 	return io_net_import_vec(req, kmsg, msg.msg_iov, msg.msg_iovlen, ITER_SOURCE);
 }
 
-#define SENDMSG_FLAGS (IORING_RECVSEND_POLL_FIRST | IORING_RECVSEND_BUNDLE | IORING_SEND_VECTORIZED)
+#define SENDMSG_FLAGS (IORING_RECVSEND_POLL_FIRST | IORING_RECVSEND_BUNDLE | \
+			IORING_SEND_VECTORIZED | IORING_RECVSEND_FIXED_BUF)
 
 int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
@@ -431,6 +432,14 @@ int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	sr->flags = READ_ONCE(sqe->ioprio);
 	if (sr->flags & ~SENDMSG_FLAGS)
 		return -EINVAL;
+	if (sr->flags & IORING_RECVSEND_FIXED_BUF) {
+		/* registered buffer send only supported for plain IORING_OP_SEND */
+		if (req->opcode != IORING_OP_SEND ||
+		    (sr->flags & IORING_RECVSEND_BUNDLE) ||
+		    (req->flags & REQ_F_BUFFER_SELECT))
+			return -EINVAL;
+		req->buf_index = READ_ONCE(sqe->buf_index);
+	}
 	sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL;
 	if (sr->msg_flags & MSG_DONTWAIT)
 		req->flags |= REQ_F_NOWAIT;
@@ -662,6 +671,15 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags)
 	    (sr->flags & IORING_RECVSEND_POLL_FIRST))
 		return -EAGAIN;
 
+	if (req->flags & REQ_F_IMPORT_BUFFER) {
+		ret = io_import_reg_buf(req, &kmsg->msg.msg_iter,
+					(u64)(uintptr_t)sr->buf, sr->len,
+					ITER_SOURCE, issue_flags);
+		if (unlikely(ret))
+			return ret;
+		req->flags &= ~REQ_F_IMPORT_BUFFER;
+	}
+
 	flags = sr->msg_flags;
 	if (issue_flags & IO_URING_F_NONBLOCK)
 		flags |= MSG_DONTWAIT;
@@ -777,6 +795,10 @@ static int io_recvmsg_prep_setup(struct io_kiocb *req)
 
 		if (req->flags & REQ_F_BUFFER_SELECT)
 			return 0;
+		if (sr->flags & IORING_RECVSEND_FIXED_BUF) {
+			req->flags |= REQ_F_IMPORT_BUFFER;
+			return 0;
+		}
 		return import_ubuf(ITER_DEST, sr->buf, sr->len,
 				   &kmsg->msg.msg_iter);
 	}
@@ -785,7 +807,7 @@ static int io_recvmsg_prep_setup(struct io_kiocb *req)
 }
 
 #define RECVMSG_FLAGS (IORING_RECVSEND_POLL_FIRST | IORING_RECV_MULTISHOT | \
-			IORING_RECVSEND_BUNDLE)
+			IORING_RECVSEND_BUNDLE | IORING_RECVSEND_FIXED_BUF)
 
 int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
@@ -803,6 +825,14 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	sr->flags = READ_ONCE(sqe->ioprio);
 	if (sr->flags & ~RECVMSG_FLAGS)
 		return -EINVAL;
+	if (sr->flags & IORING_RECVSEND_FIXED_BUF) {
+		/* registered buffer recv only for plain IORING_OP_RECV */
+		if (req->opcode != IORING_OP_RECV ||
+		    (sr->flags & (IORING_RECV_MULTISHOT | IORING_RECVSEND_BUNDLE)) ||
+		    (req->flags & REQ_F_BUFFER_SELECT))
+			return -EINVAL;
+		req->buf_index = READ_ONCE(sqe->buf_index);
+	}
 	sr->msg_flags = READ_ONCE(sqe->msg_flags);
 	if (sr->msg_flags & MSG_DONTWAIT)
 		req->flags |= REQ_F_NOWAIT;
@@ -1199,6 +1229,18 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 	if (force_nonblock)
 		flags |= MSG_DONTWAIT;
 
+	if (req->flags & REQ_F_IMPORT_BUFFER) {
+		ret = io_import_reg_buf(req, &kmsg->msg.msg_iter,
+					(u64)(uintptr_t)sr->buf, sr->len,
+					ITER_DEST, issue_flags);
+		if (unlikely(ret)) {
+			kmsg->msg.msg_inq = -1;
+			sel.buf_list = NULL;
+			goto out_free;
+		}
+		req->flags &= ~REQ_F_IMPORT_BUFFER;
+	}
+
 retry_multishot:
 	sel.buf_list = NULL;
 	if (io_do_buffer_select(req)) {
-- 
2.54.0