netdev - [PATCH v7 15/15] io_uring/zcrx: throttle receive requests

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20241029230521.2385749-16-dw@davidwei.uk>
Date: Tue, 29 Oct 2024 16:05:18 -0700
From: David Wei <dw@...idwei.uk>
To: io-uring@...r.kernel.org,
	netdev@...r.kernel.org
Cc: Jens Axboe <axboe@...nel.dk>,
	Pavel Begunkov <asml.silence@...il.com>,
	Jakub Kicinski <kuba@...nel.org>,
	Paolo Abeni <pabeni@...hat.com>,
	"David S. Miller" <davem@...emloft.net>,
	Eric Dumazet <edumazet@...gle.com>,
	Jesper Dangaard Brouer <hawk@...nel.org>,
	David Ahern <dsahern@...nel.org>,
	Mina Almasry <almasrymina@...gle.com>,
	Stanislav Fomichev <stfomichev@...il.com>,
	Joe Damato <jdamato@...tly.com>,
	Pedro Tammela <pctammela@...atatu.com>
Subject: [PATCH v7 15/15] io_uring/zcrx: throttle receive requests

From: Pavel Begunkov <asml.silence@...il.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.

Signed-off-by: Pavel Begunkov <asml.silence@...il.com>
Signed-off-by: David Wei <dw@...idwei.uk>
---
 io_uring/net.c  |  5 ++++-
 io_uring/zcrx.c | 17 ++++++++++++++---
 io_uring/zcrx.h |  6 ++++--
 3 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/io_uring/net.c b/io_uring/net.c
index 5c015b47582f..f44344942d32 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -1261,10 +1261,13 @@ int io_recvzc(struct io_kiocb *req, unsigned int issue_flags)
 	if (unlikely(!sock))
 		return -ENOTSOCK;
 
-	ret = io_zcrx_recv(req, zc->ifq, sock, zc->msg_flags | MSG_DONTWAIT);
+	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;
+		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 1f4db70e3370..a2c753e8e46e 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -24,10 +24,13 @@
 
 #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;
 };
 
 struct io_zc_refill_data {
@@ -701,6 +704,9 @@ 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;
+
 	if (unlikely(offset < skb_headlen(skb))) {
 		ssize_t copied;
 		size_t to_copy;
@@ -778,7 +784,8 @@ io_zcrx_recv_skb(read_descriptor_t *desc, struct sk_buff *skb,
 }
 
 static int io_zcrx_tcp_recvmsg(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
-				struct sock *sk, int flags)
+				struct sock *sk, int flags,
+				unsigned int issue_flags)
 {
 	struct io_zcrx_args args = {
 		.req = req,
@@ -804,6 +811,9 @@ 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. */
 		ret = -EAGAIN;
@@ -814,7 +824,8 @@ 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)
+		 struct socket *sock, unsigned int flags,
+		 unsigned int issue_flags)
 {
 	struct sock *sk = sock->sk;
 	const struct proto *prot = READ_ONCE(sk->sk_prot);
@@ -823,5 +834,5 @@ 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);
+	return io_zcrx_tcp_recvmsg(req, ifq, sk, flags, issue_flags);
 }
diff --git a/io_uring/zcrx.h b/io_uring/zcrx.h
index 5d7920972e95..45485bdce61a 100644
--- a/io_uring/zcrx.h
+++ b/io_uring/zcrx.h
@@ -48,7 +48,8 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
 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);
+		 struct socket *sock, unsigned int flags,
+		 unsigned int issue_flags);
 #else
 static inline int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
 					struct io_uring_zcrx_ifq_reg __user *arg)
@@ -62,7 +63,8 @@ static inline void io_shutdown_zcrx_ifqs(struct io_ring_ctx *ctx)
 {
 }
 static inline int io_zcrx_recv(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
-			       struct socket *sock, unsigned int flags)
+				struct socket *sock, unsigned int flags,
+				unsigned int issue_flags)
 {
 	return -EOPNOTSUPP;
 }
-- 
2.43.5