public inbox for io-uring@vger.kernel.org
 help / color / mirror / Atom feed
From: Pavel Begunkov <asml.silence@gmail.com>
To: io-uring@vger.kernel.org, Vadim Fedorenko <vadim.fedorenko@linux.dev>
Cc: asml.silence@gmail.com, netdev@vger.kernel.org,
	Eric Dumazet <edumazet@google.com>,
	Kuniyuki Iwashima <kuniyu@amazon.com>,
	Paolo Abeni <pabeni@redhat.com>,
	Willem de Bruijn <willemb@google.com>,
	"David S . Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>,
	Richard Cochran <richardcochran@gmail.com>
Subject: [PATCH v2 5/5] io_uring/netcmd: add tx timestamping cmd support
Date: Wed,  4 Jun 2025 09:42:31 +0100	[thread overview]
Message-ID: <7b81bb73e639ecfadc1300264eb75e12c925ad76.1749026421.git.asml.silence@gmail.com> (raw)
In-Reply-To: <cover.1749026421.git.asml.silence@gmail.com>

Add a new socket command which returns tx time stamps to the user. It
provide an alternative to the existing error queue recvmsg interface.
The command works in a polled multishot mode, which means io_uring will
poll the socket and keep posting timestamps until the request is
cancelled or fails in any other way (e.g. with no space in the CQ). It
reuses the net infra and grabs timestamps from the socket's error queue.

The command requires IORING_SETUP_CQE32. All non-final CQEs (marked with
IORING_CQE_F_MORE) have cqe->res set to the tskey, and the upper 16 bits
of cqe->flags keep tstype (i.e. offset by IORING_CQE_BUFFER_SHIFT). The
timevalue is store in the upper part of the extended CQE. The final
completion won't have IORING_CQR_F_MORE and will have cqe->res storing
0/error.

Suggested-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 include/uapi/linux/io_uring.h |  6 +++
 io_uring/cmd_net.c            | 77 +++++++++++++++++++++++++++++++++++
 2 files changed, 83 insertions(+)

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index cfd17e382082..0bc156eb96d4 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -960,6 +960,11 @@ struct io_uring_recvmsg_out {
 	__u32 flags;
 };
 
+struct io_timespec {
+	__u64		tv_sec;
+	__u64		tv_nsec;
+};
+
 /*
  * Argument for IORING_OP_URING_CMD when file is a socket
  */
@@ -968,6 +973,7 @@ enum io_uring_socket_op {
 	SOCKET_URING_OP_SIOCOUTQ,
 	SOCKET_URING_OP_GETSOCKOPT,
 	SOCKET_URING_OP_SETSOCKOPT,
+	SOCKET_URING_OP_TX_TIMESTAMP,
 };
 
 /* Zero copy receive refill queue entry */
diff --git a/io_uring/cmd_net.c b/io_uring/cmd_net.c
index e99170c7d41a..dae59aea5847 100644
--- a/io_uring/cmd_net.c
+++ b/io_uring/cmd_net.c
@@ -1,5 +1,6 @@
 #include <asm/ioctls.h>
 #include <linux/io_uring/net.h>
+#include <linux/errqueue.h>
 #include <net/sock.h>
 
 #include "uring_cmd.h"
@@ -51,6 +52,80 @@ static inline int io_uring_cmd_setsockopt(struct socket *sock,
 				  optlen);
 }
 
+static bool io_process_timestamp_skb(struct io_uring_cmd *cmd, struct sock *sk,
+				     struct sk_buff *skb, unsigned issue_flags)
+{
+	struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
+	struct io_uring_cqe cqe[2];
+	struct io_timespec *iots;
+	struct timespec64 ts;
+	u32 tskey;
+
+	BUILD_BUG_ON(sizeof(struct io_uring_cqe) != sizeof(struct io_timespec));
+
+	if (!skb_get_tx_timestamp(skb, sk, &ts))
+		return false;
+
+	tskey = serr->ee.ee_data;
+
+	cqe->user_data = 0;
+	cqe->res = tskey;
+	cqe->flags = IORING_CQE_F_MORE;
+	cqe->flags |= (u32)serr->ee.ee_info << IORING_CQE_BUFFER_SHIFT;
+
+	iots = (struct io_timespec *)&cqe[1];
+	iots->tv_sec = ts.tv_sec;
+	iots->tv_nsec = ts.tv_nsec;
+	return io_uring_cmd_post_mshot_cqe32(cmd, issue_flags, cqe);
+}
+
+static int io_uring_cmd_timestamp(struct socket *sock,
+				  struct io_uring_cmd *cmd,
+				  unsigned int issue_flags)
+{
+	struct sock *sk = sock->sk;
+	struct sk_buff_head *q = &sk->sk_error_queue;
+	struct sk_buff *skb, *tmp;
+	struct sk_buff_head list;
+	int ret;
+
+	if (!(issue_flags & IO_URING_F_CQE32))
+		return -EINVAL;
+	ret = io_cmd_poll_multishot(cmd, issue_flags, EPOLLERR);
+	if (unlikely(ret))
+		return ret;
+
+	if (skb_queue_empty_lockless(q))
+		return -EAGAIN;
+	__skb_queue_head_init(&list);
+
+	scoped_guard(spinlock_irq, &q->lock) {
+		skb_queue_walk_safe(q, skb, tmp) {
+			/* don't support skbs with payload */
+			if (!skb_has_tx_timestamp(skb, sk) || skb->len)
+				continue;
+			__skb_unlink(skb, q);
+			__skb_queue_tail(&list, skb);
+		}
+	}
+
+	while (1) {
+		skb = skb_peek(&list);
+		if (!skb)
+			break;
+		if (!io_process_timestamp_skb(cmd, sk, skb, issue_flags))
+			break;
+		__skb_dequeue(&list);
+		consume_skb(skb);
+	}
+
+	if (!unlikely(skb_queue_empty(&list))) {
+		scoped_guard(spinlock_irqsave, &q->lock)
+			skb_queue_splice(q, &list);
+	}
+	return -EAGAIN;
+}
+
 int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags)
 {
 	struct socket *sock = cmd->file->private_data;
@@ -76,6 +151,8 @@ int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags)
 		return io_uring_cmd_getsockopt(sock, cmd, issue_flags);
 	case SOCKET_URING_OP_SETSOCKOPT:
 		return io_uring_cmd_setsockopt(sock, cmd, issue_flags);
+	case SOCKET_URING_OP_TX_TIMESTAMP:
+		return io_uring_cmd_timestamp(sock, cmd, issue_flags);
 	default:
 		return -EOPNOTSUPP;
 	}
-- 
2.49.0


  parent reply	other threads:[~2025-06-04  8:41 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-06-04  8:42 [PATCH v2 0/5] io_uring cmd for tx timestamps Pavel Begunkov
2025-06-04  8:42 ` [PATCH v2 1/5] net: timestamp: add helper returning skb's tx tstamp Pavel Begunkov
2025-06-04 15:37   ` Stanislav Fomichev
2025-06-05  0:52   ` Willem de Bruijn
2025-06-05  3:51   ` Jason Xing
2025-06-04  8:42 ` [PATCH v2 2/5] io_uring/poll: introduce io_arm_apoll() Pavel Begunkov
2025-06-04  8:42 ` [PATCH v2 3/5] io_uring/cmd: allow multishot polled commands Pavel Begunkov
2025-06-04  8:42 ` [PATCH v2 4/5] io_uring: add mshot helper for posting CQE32 Pavel Begunkov
2025-06-04  8:42 ` Pavel Begunkov [this message]
2025-06-04 12:04   ` [PATCH v2 5/5] io_uring/netcmd: add tx timestamping cmd support Jens Axboe
2025-06-04 12:33     ` Pavel Begunkov
2025-06-05  0:59   ` Willem de Bruijn
2025-06-05 10:25     ` Vadim Fedorenko
2025-06-05 11:01       ` Pavel Begunkov
2025-06-05 23:54       ` Willem de Bruijn
2025-06-06  0:17         ` Jason Xing
2025-06-06  0:02       ` Jason Xing
2025-06-06  8:12         ` Pavel Begunkov
2025-06-06  8:33           ` Jason Xing
2025-06-06  9:08             ` Pavel Begunkov
2025-06-04  8:53 ` [PATCH v2 0/5] io_uring cmd for tx timestamps Pavel Begunkov
2025-06-04 12:06 ` Jens Axboe
2025-06-04 12:38   ` Pavel Begunkov

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 \
    --in-reply-to=7b81bb73e639ecfadc1300264eb75e12c925ad76.1749026421.git.asml.silence@gmail.com \
    --to=asml.silence@gmail.com \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=io-uring@vger.kernel.org \
    --cc=kuba@kernel.org \
    --cc=kuniyu@amazon.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=richardcochran@gmail.com \
    --cc=vadim.fedorenko@linux.dev \
    --cc=willemb@google.com \
    /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