[v1,1/2] io_uring/zcrx: add single shot recvzc

Commit Message

David Wei Feb. 18, 2025, 4:57 p.m. UTC

Currently only multishot recvzc requests are supported, but sometimes
there is a need to do a single recv e.g. peeking at some data in the
socket. Add single shot recvzc requests where IORING_RECV_MULTISHOT is
_not_ set and the sqe->len field is set to the number of bytes to read
N.

There could be multiple completions containing data, like the multishot
case, since N bytes could be split across multiple frags. This is
followed by a final completion with res and cflags both set to 0 that
indicate the completion of the request, or a -res that indicate an
error.

Signed-off-by: David Wei <[e-mail]>
---
 io_uring/net.c  | 26 ++++++++++++++++++--------
 io_uring/zcrx.c | 17 ++++++++++++++---
 io_uring/zcrx.h |  2 +-
 3 files changed, 33 insertions(+), 12 deletions(-)

Patch

diff --git a/io_uring/net.c b/io_uring/net.c
index 000dc70d08d0..d3a9aaa52a13 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -94,6 +94,7 @@  struct io_recvzc {
 	struct file			*file;
 	unsigned			msg_flags;
 	u16				flags;
+	u32				len;
 	struct io_zcrx_ifq		*ifq;
 };
 
@@ -1241,7 +1242,7 @@  int io_recvzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	unsigned ifq_idx;
 
 	if (unlikely(sqe->file_index || sqe->addr2 || sqe->addr ||
-		     sqe->len || sqe->addr3))
+		     sqe->addr3))
 		return -EINVAL;
 
 	ifq_idx = READ_ONCE(sqe->zcrx_ifq_idx);
@@ -1250,6 +1251,9 @@  int io_recvzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	zc->ifq = req->ctx->ifq;
 	if (!zc->ifq)
 		return -EINVAL;
+	zc->len = READ_ONCE(sqe->len);
+	if (zc->len == UINT_MAX)
+		return -EINVAL;
 
 	zc->flags = READ_ONCE(sqe->ioprio);
 	zc->msg_flags = READ_ONCE(sqe->msg_flags);
@@ -1257,12 +1261,14 @@  int io_recvzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return -EINVAL;
 	if (zc->flags & ~(IORING_RECVSEND_POLL_FIRST | IORING_RECV_MULTISHOT))
 		return -EINVAL;
-	/* multishot required */
-	if (!(zc->flags & IORING_RECV_MULTISHOT))
-		return -EINVAL;
-	/* All data completions are posted as aux CQEs. */
-	req->flags |= REQ_F_APOLL_MULTISHOT;
-
+	if (zc->flags & IORING_RECV_MULTISHOT) {
+		if (zc->len)
+			return -EINVAL;
+		/* All data completions are posted as aux CQEs. */
+		req->flags |= REQ_F_APOLL_MULTISHOT;
+	}
+	if (!zc->len)
+		zc->len = UINT_MAX;
 	return 0;
 }
 
@@ -1281,7 +1287,7 @@  int io_recvzc(struct io_kiocb *req, unsigned int issue_flags)
 		return -ENOTSOCK;
 
 	ret = io_zcrx_recv(req, zc->ifq, sock, zc->msg_flags | MSG_DONTWAIT,
-			   issue_flags);
+			   issue_flags, zc->len);
 	if (unlikely(ret <= 0) && ret != -EAGAIN) {
 		if (ret == -ERESTARTSYS)
 			ret = -EINTR;
@@ -1296,6 +1302,10 @@  int io_recvzc(struct io_kiocb *req, unsigned int issue_flags)
 		return IOU_OK;
 	}
 
+	if (zc->len != UINT_MAX) {
+		io_req_set_res(req, ret, 0);
+		return IOU_OK;
+	}
 	if (issue_flags & IO_URING_F_MULTISHOT)
 		return IOU_ISSUE_SKIP_COMPLETE;
 	return -EAGAIN;
diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index ea099f746599..834c887743c8 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -106,6 +106,7 @@  struct io_zcrx_args {
 	struct io_zcrx_ifq	*ifq;
 	struct socket		*sock;
 	unsigned		nr_skbs;
+	unsigned long		len;
 };
 
 static const struct memory_provider_ops io_uring_pp_zc_ops;
@@ -826,6 +827,10 @@  io_zcrx_recv_skb(read_descriptor_t *desc, struct sk_buff *skb,
 	int i, copy, end, off;
 	int ret = 0;
 
+	if (args->len == 0)
+		return -EINTR;
+	len = (args->len != UINT_MAX) ? min_t(size_t, len, args->len) : len;
+
 	if (unlikely(args->nr_skbs++ > IO_SKBS_PER_CALL_LIMIT))
 		return -EAGAIN;
 
@@ -920,17 +925,21 @@  io_zcrx_recv_skb(read_descriptor_t *desc, struct sk_buff *skb,
 out:
 	if (offset == start_off)
 		return ret;
+	args->len -= (offset - start_off);
+	if (args->len == 0)
+		desc->count = 0;
 	return offset - start_off;
 }
 
 static int io_zcrx_tcp_recvmsg(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
 				struct sock *sk, int flags,
-				unsigned issue_flags)
+				unsigned issue_flags, unsigned long len)
 {
 	struct io_zcrx_args args = {
 		.req = req,
 		.ifq = ifq,
 		.sock = sk->sk_socket,
+		.len = len,
 	};
 	read_descriptor_t rd_desc = {
 		.count = 1,
@@ -956,6 +965,8 @@  static int io_zcrx_tcp_recvmsg(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
 		ret = IOU_REQUEUE;
 	} else if (sock_flag(sk, SOCK_DONE)) {
 		/* Make it to retry until it finally gets 0. */
+		if (len != UINT_MAX)
+			goto out;
 		if (issue_flags & IO_URING_F_MULTISHOT)
 			ret = IOU_REQUEUE;
 		else
@@ -968,7 +979,7 @@  static int io_zcrx_tcp_recvmsg(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
 
 int io_zcrx_recv(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
 		 struct socket *sock, unsigned int flags,
-		 unsigned issue_flags)
+		 unsigned issue_flags, unsigned long len)
 {
 	struct sock *sk = sock->sk;
 	const struct proto *prot = READ_ONCE(sk->sk_prot);
@@ -977,7 +988,7 @@  int io_zcrx_recv(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
 		return -EPROTONOSUPPORT;
 
 	sock_rps_record_flow(sk);
-	return io_zcrx_tcp_recvmsg(req, ifq, sk, flags, issue_flags);
+	return io_zcrx_tcp_recvmsg(req, ifq, sk, flags, issue_flags, len);
 }
 
 #include <linux/io_uring/net.h>
diff --git a/io_uring/zcrx.h b/io_uring/zcrx.h
index a16bdd921f03..85da6a14543f 100644
--- a/io_uring/zcrx.h
+++ b/io_uring/zcrx.h
@@ -46,7 +46,7 @@  void io_unregister_zcrx_ifqs(struct io_ring_ctx *ctx);
 void io_shutdown_zcrx_ifqs(struct io_ring_ctx *ctx);
 int io_zcrx_recv(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
 		 struct socket *sock, unsigned int flags,
-		 unsigned issue_flags);
+		 unsigned issue_flags, unsigned long len);
 #else
 static inline int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
 					struct io_uring_zcrx_ifq_reg __user *arg)