diff mbox series

[net-next,v9,17/20] io_uring/zcrx: throttle receive requests

Message ID 20241218003748.796939-18-dw@davidwei.uk (mailing list archive)
State New
Delegated to: Netdev Maintainers
Headers show
Series [net-next,v9,01/20] net: page_pool: don't cast mp param to devmem | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for net-next, async
netdev/apply fail Patch does not apply to net-next-0

Commit Message

David Wei Dec. 18, 2024, 12:37 a.m. UTC 
From: Pavel Begunkov <asml.silence@gmail.com>

io_zc_rx_tcp_recvmsg() continues until it fails or there is nothing to
receive. If the other side sends fast enough, we might get stuck in
io_zc_rx_tcp_recvmsg() producing more and more CQEs but not letting the
user to handle them leading to unbound latencies.

Break out of it based on an arbitrarily chosen limit, the upper layer
will either return to userspace or requeue the request.

Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David Wei <dw@davidwei.uk>
---
 io_uring/net.c  | 2 ++
 io_uring/zcrx.c | 9 +++++++++
 2 files changed, 11 insertions(+)
diff mbox series

Patch

diff --git a/io_uring/net.c b/io_uring/net.c
index 5d8b9a016766..86eaba37e739 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -1267,6 +1267,8 @@  int io_recvzc(struct io_kiocb *req, unsigned int issue_flags)
 	if (unlikely(ret <= 0) && ret != -EAGAIN) {
 		if (ret == -ERESTARTSYS)
 			ret = -EINTR;
+		if (ret == IOU_REQUEUE)
+			return IOU_REQUEUE;
 
 		req_set_fail(req);
 		io_req_set_res(req, ret, 0);
diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index 756c78c0920e..ffa388fbb1e4 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -83,10 +83,13 @@  static int io_zcrx_map_area(struct io_zcrx_ifq *ifq, struct io_zcrx_area *area)
 
 #define IO_RQ_MAX_ENTRIES		32768
 
+#define IO_SKBS_PER_CALL_LIMIT	20
+
 struct io_zcrx_args {
 	struct io_kiocb		*req;
 	struct io_zcrx_ifq	*ifq;
 	struct socket		*sock;
+	unsigned		nr_skbs;
 };
 
 static const struct memory_provider_ops io_uring_pp_zc_ops;
@@ -702,6 +705,9 @@  io_zcrx_recv_skb(read_descriptor_t *desc, struct sk_buff *skb,
 	int i, copy, end, off;
 	int ret = 0;
 
+	if (unlikely(args->nr_skbs++ > IO_SKBS_PER_CALL_LIMIT))
+		return -EAGAIN;
+
 	start = skb_headlen(skb);
 	start_off = offset;
 
@@ -792,6 +798,9 @@  static int io_zcrx_tcp_recvmsg(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
 			ret = -ENOTCONN;
 		else
 			ret = -EAGAIN;
+	} else if (unlikely(args.nr_skbs > IO_SKBS_PER_CALL_LIMIT) &&
+		   (issue_flags & IO_URING_F_MULTISHOT)) {
+		ret = IOU_REQUEUE;
 	} else if (sock_flag(sk, SOCK_DONE)) {
 		/* Make it to retry until it finally gets 0. */
 		if (issue_flags & IO_URING_F_MULTISHOT)