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: [PATCH net-next v5 09/15] net-timestamp: support SCM_TSTAMP_ACK for bpf extension
Date: Sun, 12 Jan 2025 19:37:42 +0800 [thread overview]
Message-ID: <20250112113748.73504-10-kerneljasonxing@gmail.com> (raw)
In-Reply-To: <20250112113748.73504-1-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 5b2b04835688..f00a8e3f9b31 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 a6d761f07f67..a0aff1b4eb61 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -7032,6 +7032,11 @@ enum {
* feature is on. 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 0fb31df4ed95..17b9d8061f04 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5581,6 +5581,9 @@ static void __skb_tstamp_tx_bpf(struct sk_buff *skb, struct sock *sk, int tstype
case SCM_TSTAMP_SND:
op = BPF_SOCK_OPS_TS_SW_OPT_CB;
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 c2cdd0acb504..0f2e6e73de9f 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 7b4d1dfd57d4..aa1da7c89383 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 73fc0a95c9ca..0fe7d663a244 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -7025,6 +7025,11 @@ enum {
* feature is on. 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
next prev parent reply other threads:[~2025-01-12 11:38 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-01-12 11:37 [PATCH net-next v5 00/15] net-timestamp: bpf extension to equip applications transparently Jason Xing
2025-01-12 11:37 ` [PATCH net-next v5 01/15] net-timestamp: add support for bpf_setsockopt() Jason Xing
2025-01-12 14:49 ` kernel test robot
2025-01-13 0:11 ` Jason Xing
2025-01-13 7:32 ` Jason Xing
2025-01-14 23:20 ` Martin KaFai Lau
2025-01-14 23:29 ` Jason Xing
2025-01-12 11:37 ` [PATCH net-next v5 02/15] net-timestamp: prepare for bpf prog use Jason Xing
2025-01-14 23:39 ` Martin KaFai Lau
2025-01-15 0:09 ` Jason Xing
2025-01-15 0:15 ` Jason Xing
2025-01-15 0:26 ` Martin KaFai Lau
2025-01-15 0:37 ` Jason Xing
2025-01-15 0:43 ` Jason Xing
2025-01-12 11:37 ` [PATCH net-next v5 03/15] bpf: introduce timestamp_used to allow UDP socket fetched in bpf prog Jason Xing
2025-01-15 1:17 ` Martin KaFai Lau
2025-01-15 2:28 ` Jason Xing
2025-01-15 2:54 ` Jason Xing
2025-01-16 0:51 ` Martin KaFai Lau
2025-01-16 1:12 ` Jason Xing
2025-01-18 1:42 ` Martin KaFai Lau
2025-01-18 1:58 ` Jason Xing
2025-01-18 2:16 ` Martin KaFai Lau
2025-01-18 2:37 ` Jason Xing
2025-01-12 11:37 ` [PATCH net-next v5 04/15] net-timestamp: support SK_BPF_CB_FLAGS only in bpf_sock_ops_setsockopt Jason Xing
2025-01-15 21:22 ` Martin KaFai Lau
2025-01-15 23:26 ` Jason Xing
2025-01-12 11:37 ` [PATCH net-next v5 05/15] net-timestamp: add strict check in some BPF calls Jason Xing
2025-01-12 14:37 ` kernel test robot
2025-01-13 0:28 ` Jason Xing
2025-01-15 21:48 ` Martin KaFai Lau
2025-01-15 23:32 ` Jason Xing
2025-01-18 2:15 ` Martin KaFai Lau
2025-01-18 6:28 ` Jason Xing
2025-01-17 10:18 ` kernel test robot
2025-01-12 11:37 ` [PATCH net-next v5 06/15] net-timestamp: prepare for isolating two modes of SO_TIMESTAMPING Jason Xing
2025-01-15 22:11 ` Martin KaFai Lau
2025-01-15 23:50 ` Jason Xing
2025-01-12 11:37 ` [PATCH net-next v5 07/15] net-timestamp: support SCM_TSTAMP_SCHED for bpf extension Jason Xing
2025-01-15 22:32 ` Martin KaFai Lau
2025-01-15 23:57 ` Jason Xing
2025-01-12 11:37 ` [PATCH net-next v5 08/15] net-timestamp: support sw SCM_TSTAMP_SND " Jason Xing
2025-01-15 22:48 ` Martin KaFai Lau
2025-01-15 23:56 ` Jason Xing
2025-01-18 0:46 ` Martin KaFai Lau
2025-01-18 1:43 ` Jason Xing
2025-01-19 13:38 ` Jason Xing
2025-01-12 11:37 ` Jason Xing [this message]
2025-01-15 23:02 ` [PATCH net-next v5 09/15] net-timestamp: support SCM_TSTAMP_ACK " Martin KaFai Lau
2025-01-12 11:37 ` [PATCH net-next v5 10/15] net-timestamp: support hw SCM_TSTAMP_SND " Jason Xing
2025-01-12 11:37 ` [PATCH net-next v5 11/15] net-timestamp: support export skb to the userspace Jason Xing
2025-01-15 23:05 ` Martin KaFai Lau
2025-01-15 23:59 ` Jason Xing
2025-01-12 11:37 ` [PATCH net-next v5 12/15] net-timestamp: make TCP tx timestamp bpf extension work Jason Xing
2025-01-12 11:37 ` [PATCH net-next v5 13/15] net-timestamp: support tcp_sendmsg for bpf extension Jason Xing
2025-01-16 0:03 ` Martin KaFai Lau
2025-01-16 0:41 ` Jason Xing
2025-01-16 1:18 ` Martin KaFai Lau
2025-01-16 1:22 ` Jason Xing
2025-01-12 11:37 ` [PATCH net-next v5 14/15] net-timestamp: introduce cgroup lock to avoid affecting non-bpf cases Jason Xing
2025-01-12 11:37 ` [PATCH net-next v5 15/15] bpf: add simple bpf tests in the tx path for so_timestamping feature 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=20250112113748.73504-10-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).