netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jason Xing <kerneljasonxing@gmail.com>
To: davem@davemloft.net, edumazet@google.com, kuba@kernel.org,
	pabeni@redhat.com, dsahern@kernel.org,
	willemdebruijn.kernel@gmail.com, willemb@google.com,
	ast@kernel.org, daniel@iogearbox.net, andrii@kernel.org,
	martin.lau@linux.dev, eddyz87@gmail.com, song@kernel.org,
	yonghong.song@linux.dev, john.fastabend@gmail.com,
	kpsingh@kernel.org, sdf@fomichev.me, haoluo@google.com,
	jolsa@kernel.org, horms@kernel.org
Cc: bpf@vger.kernel.org, netdev@vger.kernel.org,
	Jason Xing <kerneljasonxing@gmail.com>
Subject: [RFC PATCH net-next v6 09/13] net-timestamp: support SCM_TSTAMP_ACK for bpf extension
Date: Tue, 21 Jan 2025 09:28:57 +0800	[thread overview]
Message-ID: <20250121012901.87763-10-kerneljasonxing@gmail.com> (raw)
In-Reply-To: <20250121012901.87763-1-kerneljasonxing@gmail.com>

Handle the ACK timestamp case. Actually testing SKBTX_BPF flag
can work, but we need to Introduce a new txstamp_ack_bpf to avoid
cache line misses in tcp_ack_tstamp(). To be more specific, in most
cases, normal flows would not access skb_shinfo as txstamp_ack
is zero, so that this function won't appear in the hot spot lists.
Introducing a new member txstamp_ack_bpf works similarly.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
---
 include/net/tcp.h              | 3 ++-
 include/uapi/linux/bpf.h       | 5 +++++
 net/core/skbuff.c              | 3 +++
 net/ipv4/tcp_input.c           | 3 ++-
 net/ipv4/tcp_output.c          | 5 +++++
 tools/include/uapi/linux/bpf.h | 5 +++++
 6 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 293047694710..88429e422301 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -959,9 +959,10 @@ struct tcp_skb_cb {
 	__u8		sacked;		/* State flags for SACK.	*/
 	__u8		ip_dsfield;	/* IPv4 tos or IPv6 dsfield	*/
 	__u8		txstamp_ack:1,	/* Record TX timestamp for ack? */
+			txstamp_ack_bpf:1,	/* ack timestamp for bpf use */
 			eor:1,		/* Is skb MSG_EOR marked? */
 			has_rxtstamp:1,	/* SKB has a RX timestamp	*/
-			unused:5;
+			unused:4;
 	__u32		ack_seq;	/* Sequence number ACK'd	*/
 	union {
 		struct {
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 8936e1061e71..3b9bfc88345c 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -7037,6 +7037,11 @@ enum {
 					 * It indicates the recorded
 					 * timestamp.
 					 */
+	BPF_SOCK_OPS_TS_ACK_OPT_CB,	/* Called when all the skbs are
+					 * acknowledged when SO_TIMESTAMPING
+					 * feature is on. It indicates the
+					 * recorded timestamp.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c769feae5162..33340e0b094f 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5582,6 +5582,9 @@ static void skb_tstamp_tx_bpf(struct sk_buff *skb, struct sock *sk,
 		if (!sw)
 			*skb_hwtstamps(skb) = *hwtstamps;
 		break;
+	case SCM_TSTAMP_ACK:
+		op = BPF_SOCK_OPS_TS_ACK_OPT_CB;
+		break;
 	default:
 		return;
 	}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 62252702929d..c8945f5be31b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3323,7 +3323,8 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb,
 	const struct skb_shared_info *shinfo;
 
 	/* Avoid cache line misses to get skb_shinfo() and shinfo->tx_flags */
-	if (likely(!TCP_SKB_CB(skb)->txstamp_ack))
+	if (likely(!TCP_SKB_CB(skb)->txstamp_ack &&
+		   !TCP_SKB_CB(skb)->txstamp_ack_bpf))
 		return;
 
 	shinfo = skb_shinfo(skb);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 695749807c09..fc84ca669b76 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1556,6 +1556,7 @@ static void tcp_adjust_pcount(struct sock *sk, const struct sk_buff *skb, int de
 static bool tcp_has_tx_tstamp(const struct sk_buff *skb)
 {
 	return TCP_SKB_CB(skb)->txstamp_ack ||
+	       TCP_SKB_CB(skb)->txstamp_ack_bpf ||
 		(skb_shinfo(skb)->tx_flags & SKBTX_ANY_TSTAMP);
 }
 
@@ -1572,7 +1573,9 @@ static void tcp_fragment_tstamp(struct sk_buff *skb, struct sk_buff *skb2)
 		shinfo2->tx_flags |= tsflags;
 		swap(shinfo->tskey, shinfo2->tskey);
 		TCP_SKB_CB(skb2)->txstamp_ack = TCP_SKB_CB(skb)->txstamp_ack;
+		TCP_SKB_CB(skb2)->txstamp_ack_bpf = TCP_SKB_CB(skb)->txstamp_ack_bpf;
 		TCP_SKB_CB(skb)->txstamp_ack = 0;
+		TCP_SKB_CB(skb)->txstamp_ack_bpf = 0;
 	}
 }
 
@@ -3213,6 +3216,8 @@ void tcp_skb_collapse_tstamp(struct sk_buff *skb,
 		shinfo->tskey = next_shinfo->tskey;
 		TCP_SKB_CB(skb)->txstamp_ack |=
 			TCP_SKB_CB(next_skb)->txstamp_ack;
+		TCP_SKB_CB(skb)->txstamp_ack_bpf |=
+			TCP_SKB_CB(next_skb)->txstamp_ack_bpf;
 	}
 }
 
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index f1583b5814ea..b463aa9c27da 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -7030,6 +7030,11 @@ enum {
 					 * It indicates the recorded
 					 * timestamp.
 					 */
+	BPF_SOCK_OPS_TS_ACK_OPT_CB,	/* Called when all the skbs are
+					 * acknowledged when SO_TIMESTAMPING
+					 * feature is on. It indicates the
+					 * recorded timestamp.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
-- 
2.43.5


  parent reply	other threads:[~2025-01-21  1:30 UTC|newest]

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-01-21  1:28 [RFC PATCH net-next v6 00/13] net-timestamp: bpf extension to equip applications transparently Jason Xing
2025-01-21  1:28 ` [RFC PATCH net-next v6 01/13] net-timestamp: add support for bpf_setsockopt() Jason Xing
2025-01-21  1:28 ` [RFC PATCH net-next v6 02/13] net-timestamp: prepare for timestamping callbacks use Jason Xing
2025-01-21  5:08   ` Jason Xing
2025-01-21  1:28 ` [RFC PATCH net-next v6 03/13] bpf: stop UDP sock accessing TCP fields in bpf callbacks Jason Xing
2025-01-24 23:40   ` Martin KaFai Lau
2025-01-25  0:28     ` Jason Xing
2025-01-28  1:34       ` Jason Xing
2025-01-21  1:28 ` [RFC PATCH net-next v6 04/13] bpf: stop UDP sock accessing TCP fields in sock_op BPF CALLs Jason Xing
2025-01-25  0:28   ` Martin KaFai Lau
2025-01-25  1:15     ` Jason Xing
2025-01-25  1:32       ` Jason Xing
2025-01-25  2:25       ` Martin KaFai Lau
2025-01-25  2:58         ` Jason Xing
2025-01-25  3:12         ` Martin KaFai Lau
2025-01-25  3:43           ` Jason Xing
2025-01-21  1:28 ` [RFC PATCH net-next v6 05/13] net-timestamp: prepare for isolating two modes of SO_TIMESTAMPING Jason Xing
2025-01-21  1:28 ` [RFC PATCH net-next v6 06/13] net-timestamp: support SCM_TSTAMP_SCHED for bpf extension Jason Xing
2025-01-25  0:38   ` Martin KaFai Lau
2025-01-25  1:16     ` Jason Xing
2025-01-21  1:28 ` [RFC PATCH net-next v6 07/13] net-timestamp: support sw SCM_TSTAMP_SND " Jason Xing
2025-01-25  0:40   ` Martin KaFai Lau
2025-01-25  1:17     ` Jason Xing
2025-01-21  1:28 ` [RFC PATCH net-next v6 08/13] net-timestamp: support hw " Jason Xing
2025-01-25  0:46   ` Martin KaFai Lau
2025-01-25  1:18     ` Jason Xing
2025-01-25  1:29       ` Martin KaFai Lau
2025-01-25  1:35         ` Jason Xing
2025-01-25  2:36           ` Martin KaFai Lau
2025-01-25  2:59             ` Jason Xing
2025-01-21  1:28 ` Jason Xing [this message]
2025-01-21  1:28 ` [RFC PATCH net-next v6 10/13] net-timestamp: make TCP tx timestamp bpf extension work Jason Xing
2025-01-21  1:28 ` [RFC PATCH net-next v6 11/13] net-timestamp: add a new callback in tcp_tx_timestamp() Jason Xing
2025-01-25  0:50   ` Martin KaFai Lau
2025-01-25  1:21     ` Jason Xing
2025-01-21  1:29 ` [RFC PATCH net-next v6 12/13] net-timestamp: introduce cgroup lock to avoid affecting non-bpf cases Jason Xing
2025-01-25  1:09   ` Martin KaFai Lau
2025-01-25  1:25     ` Jason Xing
2025-01-21  1:29 ` [RFC PATCH net-next v6 13/13] bpf: add simple bpf tests in the tx path for so_timestamping feature Jason Xing
2025-01-25  3:07   ` Martin KaFai Lau
2025-01-25  3:42     ` Jason Xing
2025-01-27 23:49       ` Martin KaFai Lau
2025-01-28  0:19         ` Jason Xing

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=20250121012901.87763-10-kerneljasonxing@gmail.com \
    --to=kerneljasonxing@gmail.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=dsahern@kernel.org \
    --cc=eddyz87@gmail.com \
    --cc=edumazet@google.com \
    --cc=haoluo@google.com \
    --cc=horms@kernel.org \
    --cc=john.fastabend@gmail.com \
    --cc=jolsa@kernel.org \
    --cc=kpsingh@kernel.org \
    --cc=kuba@kernel.org \
    --cc=martin.lau@linux.dev \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=sdf@fomichev.me \
    --cc=song@kernel.org \
    --cc=willemb@google.com \
    --cc=willemdebruijn.kernel@gmail.com \
    --cc=yonghong.song@linux.dev \
    /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;
as well as URLs for NNTP newsgroup(s).