public inbox for [email protected]
 help / color / mirror / Atom feed
From: David Wei <[email protected]>
To: [email protected], [email protected]
Cc: Jens Axboe <[email protected]>,
	Pavel Begunkov <[email protected]>,
	Jakub Kicinski <[email protected]>, Paolo Abeni <[email protected]>,
	"David S. Miller" <[email protected]>,
	Eric Dumazet <[email protected]>,
	Jesper Dangaard Brouer <[email protected]>,
	David Ahern <[email protected]>,
	Mina Almasry <[email protected]>,
	Stanislav Fomichev <[email protected]>,
	Joe Damato <[email protected]>,
	Pedro Tammela <[email protected]>
Subject: [PATCH v7 15/15] io_uring/zcrx: throttle receive requests
Date: Tue, 29 Oct 2024 16:05:18 -0700	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>

From: Pavel Begunkov <[email protected]>

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 <[email protected]>
Signed-off-by: David Wei <[email protected]>
---
 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


      parent reply	other threads:[~2024-10-29 23:06 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-10-29 23:05 [PATCH v7 00/15] io_uring zero copy rx David Wei
2024-10-29 23:05 ` [PATCH v7 01/15] net: prefix devmem specific helpers David Wei
2024-10-29 23:05 ` [PATCH v7 02/15] net: generalise net_iov chunk owners David Wei
2024-10-29 23:05 ` [PATCH v7 03/15] net: page_pool: create hooks for custom page providers David Wei
2024-10-29 23:05 ` [PATCH v7 04/15] net: prepare for non devmem TCP memory providers David Wei
2024-10-29 23:05 ` [PATCH v7 05/15] net: page_pool: add ->scrub mem provider callback David Wei
2024-10-29 23:05 ` [PATCH v7 06/15] net: page pool: add helper creating area from pages David Wei
2024-10-29 23:05 ` [PATCH v7 07/15] net: page_pool: introduce page_pool_mp_return_in_cache David Wei
2024-10-29 23:05 ` [PATCH v7 08/15] net: add helper executing custom callback from napi David Wei
2024-10-29 23:05 ` [PATCH v7 09/15] io_uring/zcrx: add interface queue and refill queue David Wei
2024-10-29 23:05 ` [PATCH v7 10/15] io_uring/zcrx: add io_zcrx_area David Wei
2024-10-29 23:05 ` [PATCH v7 11/15] io_uring/zcrx: implement zerocopy receive pp memory provider David Wei
2024-10-29 23:05 ` [PATCH v7 12/15] io_uring/zcrx: add io_recvzc request David Wei
2024-10-29 23:05 ` [PATCH v7 13/15] io_uring/zcrx: set pp memory provider for an rx queue David Wei
2024-10-29 23:05 ` [PATCH v7 14/15] io_uring/zcrx: add copy fallback David Wei
2024-10-29 23:05 ` David Wei [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox