io_uring/zcrx: add io_recvzc request

Add io_uring opcode OP_RECV_ZC for doing zero copy reads out of a
socket. Only the connection should be land on the specific rx queue set
up for zero copy, and the socket must be handled by the io_uring
instance that the rx queue was registered for zero copy with. That's
because neither net_iovs / buffers from our queue can be read by outside
applications, nor zero copy is possible if traffic for the zero copy
connection goes to another queue. This coordination is outside of the
scope of this patch series. Also, any traffic directed to the zero copy
enabled queue is immediately visible to the application, which is why
CAP_NET_ADMIN is required at the registration step.

Of course, no data is actually read out of the socket, it has already
been copied by the netdev into userspace memory via DMA. OP_RECV_ZC
reads skbs out of the socket and checks that its frags are indeed
net_iovs that belong to io_uring. A cqe is queued for each one of these
frags.

Recall that each cqe is a big cqe, with the top half being an
io_uring_zcrx_cqe. The cqe res field contains the len or error. The
lower IORING_ZCRX_AREA_SHIFT bits of the struct io_uring_zcrx_cqe::off
field contain the offset relative to the start of the zero copy area.
The upper part of the off field is trivially zero, and will be used
to carry the area id.

For now, there is no limit as to how much work each OP_RECV_ZC request
does. It will attempt to drain a socket of all available data. This
request always operates in multishot mode.

Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: David Wei <dw@davidwei.uk>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20250215000947.789731-7-dw@davidwei.uk
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 72 insertions, 0 deletions

diff --git a/io_uring/net.c b/io_uring/net.c
index 10344b3a6d89..260eb73a5854 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -16,6 +16,7 @@
 #include "net.h"
 #include "notif.h"
 #include "rsrc.h"
+#include "zcrx.h"
 
 #if defined(CONFIG_NET)
 struct io_shutdown {
@@ -89,6 +90,13 @@ struct io_sr_msg {
  */
 #define MULTISHOT_MAX_RETRY	32
 
+struct io_recvzc {
+	struct file			*file;
+	unsigned			msg_flags;
+	u16				flags;
+	struct io_zcrx_ifq		*ifq;
+};
+
 int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_shutdown *shutdown = io_kiocb_to_cmd(req, struct io_shutdown);
@@ -1227,6 +1235,70 @@ out_free:
 	return ret;
 }
 
+int io_recvzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_recvzc *zc = io_kiocb_to_cmd(req, struct io_recvzc);
+	unsigned ifq_idx;
+
+	if (unlikely(sqe->file_index || sqe->addr2 || sqe->addr ||
+		     sqe->len || sqe->addr3))
+		return -EINVAL;
+
+	ifq_idx = READ_ONCE(sqe->zcrx_ifq_idx);
+	if (ifq_idx != 0)
+		return -EINVAL;
+	zc->ifq = req->ctx->ifq;
+	if (!zc->ifq)
+		return -EINVAL;
+
+	zc->flags = READ_ONCE(sqe->ioprio);
+	zc->msg_flags = READ_ONCE(sqe->msg_flags);
+	if (zc->msg_flags)
+		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;
+
+	return 0;
+}
+
+int io_recvzc(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_recvzc *zc = io_kiocb_to_cmd(req, struct io_recvzc);
+	struct socket *sock;
+	int ret;
+
+	if (!(req->flags & REQ_F_POLLED) &&
+	    (zc->flags & IORING_RECVSEND_POLL_FIRST))
+		return -EAGAIN;
+
+	sock = sock_from_file(req->file);
+	if (unlikely(!sock))
+		return -ENOTSOCK;
+
+	ret = io_zcrx_recv(req, zc->ifq, sock, zc->msg_flags | MSG_DONTWAIT,
+			   issue_flags);
+	if (unlikely(ret <= 0) && ret != -EAGAIN) {
+		if (ret == -ERESTARTSYS)
+			ret = -EINTR;
+
+		req_set_fail(req);
+		io_req_set_res(req, ret, 0);
+
+		if (issue_flags & IO_URING_F_MULTISHOT)
+			return IOU_STOP_MULTISHOT;
+		return IOU_OK;
+	}
+
+	if (issue_flags & IO_URING_F_MULTISHOT)
+		return IOU_ISSUE_SKIP_COMPLETE;
+	return -EAGAIN;
+}
+
 void io_send_zc_cleanup(struct io_kiocb *req)
 {
 	struct io_sr_msg *zc = io_kiocb_to_cmd(req, struct io_sr_msg);