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 bpf-next v11 09/12] bpf: add BPF_SOCK_OPS_TS_ACK_OPT_CB callback
Date: Fri, 14 Feb 2025 09:00:35 +0800 [thread overview]
Message-ID: <20250214010038.54131-10-kerneljasonxing@gmail.com> (raw)
In-Reply-To: <20250214010038.54131-1-kerneljasonxing@gmail.com>
Support the ACK case for bpf timestamping.
Add a new sock_ops callback, BPF_SOCK_OPS_TS_ACK_OPT_CB. This
callback will occur at the same timestamping point as the user
space's SCM_TSTAMP_ACK. The BPF program can use it to get the
same SCM_TSTAMP_ACK timestamp without modifying the user-space
application.
This patch extends txstamp_ack to two bits: 1 stands for
SO_TIMESTAMPING mode, 2 bpf extension.
Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
---
include/net/tcp.h | 6 ++++--
include/uapi/linux/bpf.h | 5 +++++
net/core/skbuff.c | 5 ++++-
net/dsa/user.c | 2 +-
net/ipv4/tcp.c | 2 +-
net/socket.c | 2 +-
tools/include/uapi/linux/bpf.h | 5 +++++
7 files changed, 21 insertions(+), 6 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 4c4dca59352b..2e2fc72e115b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -958,10 +958,12 @@ 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? */
+#define TSTAMP_ACK_SK 0x1
+#define TSTAMP_ACK_BPF 0x2
+ __u8 txstamp_ack:2, /* Record TX timestamp for ack? */
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 f70edd067edf..9355d617767f 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -7047,6 +7047,11 @@ enum {
* SK_BPF_CB_TX_TIMESTAMPING feature
* is on.
*/
+ BPF_SOCK_OPS_TS_ACK_OPT_CB, /* Called when all the skbs in the
+ * same sendmsg call are acked
+ * when SK_BPF_CB_TX_TIMESTAMPING
+ * feature is on.
+ */
};
/* 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 acafa05f7f58..f096ca6c2ced 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5550,7 +5550,7 @@ static bool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb,
return skb_shinfo(skb)->tx_flags & (hwtstamps ? SKBTX_HW_TSTAMP_NOBPF :
SKBTX_SW_TSTAMP);
case SCM_TSTAMP_ACK:
- return TCP_SKB_CB(skb)->txstamp_ack;
+ return TCP_SKB_CB(skb)->txstamp_ack & TSTAMP_ACK_SK;
}
return false;
@@ -5575,6 +5575,9 @@ static void skb_tstamp_tx_report_bpf_timestamping(struct sk_buff *skb,
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/dsa/user.c b/net/dsa/user.c
index 291ab1b4acc4..794fe553dd77 100644
--- a/net/dsa/user.c
+++ b/net/dsa/user.c
@@ -897,7 +897,7 @@ static void dsa_skb_tx_timestamp(struct dsa_user_priv *p,
{
struct dsa_switch *ds = p->dp->ds;
- if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
+ if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_NOBPF))
return;
if (!ds->ops->port_txtstamp)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0d704bda6c41..12b9c4f9c151 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -488,7 +488,7 @@ static void tcp_tx_timestamp(struct sock *sk, struct sockcm_cookie *sockc)
sock_tx_timestamp(sk, sockc, &shinfo->tx_flags);
if (tsflags & SOF_TIMESTAMPING_TX_ACK)
- tcb->txstamp_ack = 1;
+ tcb->txstamp_ack |= TSTAMP_ACK_SK;
if (tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK)
shinfo->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1;
}
diff --git a/net/socket.c b/net/socket.c
index 262a28b59c7f..517de433d4bb 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -676,7 +676,7 @@ void __sock_tx_timestamp(__u32 tsflags, __u8 *tx_flags)
u8 flags = *tx_flags;
if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE) {
- flags |= SKBTX_HW_TSTAMP;
+ flags |= SKBTX_HW_TSTAMP_NOBPF;
/* PTP hardware clocks can provide a free running cycle counter
* as a time base for virtual clocks. Tell driver to use the
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 7b9652ce7e3c..d3e2988b3b4c 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -7037,6 +7037,11 @@ enum {
* SK_BPF_CB_TX_TIMESTAMPING feature
* is on.
*/
+ BPF_SOCK_OPS_TS_ACK_OPT_CB, /* Called when all the skbs in the
+ * same sendmsg call are acked
+ * when SK_BPF_CB_TX_TIMESTAMPING
+ * feature is on.
+ */
};
/* 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:[~2025-02-14 1:01 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-14 1:00 [PATCH bpf-next v11 00/12] net-timestamp: bpf extension to equip applications transparently Jason Xing
2025-02-14 1:00 ` [PATCH bpf-next v11 01/12] bpf: add networking timestamping support to bpf_get/setsockopt() Jason Xing
2025-02-14 1:00 ` [PATCH bpf-next v11 02/12] bpf: prepare the sock_ops ctx and call bpf prog for TX timestamping Jason Xing
2025-02-14 1:00 ` [PATCH bpf-next v11 03/12] bpf: prevent unsafe access to the sock fields in the BPF timestamping callback Jason Xing
2025-02-14 1:00 ` [PATCH bpf-next v11 04/12] bpf: disable unsafe helpers in TX timestamping callbacks Jason Xing
2025-02-14 1:00 ` [PATCH bpf-next v11 05/12] net-timestamp: prepare for isolating two modes of SO_TIMESTAMPING Jason Xing
2025-02-14 1:00 ` [PATCH bpf-next v11 06/12] bpf: add BPF_SOCK_OPS_TS_SCHED_OPT_CB callback Jason Xing
2025-02-14 1:00 ` [PATCH bpf-next v11 07/12] bpf: add BPF_SOCK_OPS_TS_SW_OPT_CB callback Jason Xing
2025-02-14 1:00 ` [PATCH bpf-next v11 08/12] bpf: add BPF_SOCK_OPS_TS_HW_OPT_CB callback Jason Xing
2025-02-15 15:06 ` Willem de Bruijn
2025-02-15 16:20 ` Jason Xing
2025-02-15 18:08 ` Willem de Bruijn
2025-02-15 22:23 ` Jason Xing
2025-02-15 22:58 ` Martin KaFai Lau
2025-02-15 23:10 ` Jason Xing
2025-02-16 14:36 ` Willem de Bruijn
2025-02-16 14:45 ` Jason Xing
2025-02-16 14:48 ` Jason Xing
2025-02-16 16:17 ` Jason Xing
2025-02-18 0:56 ` Willem de Bruijn
2025-02-18 4:51 ` Jason Xing
2025-02-18 0:55 ` Willem de Bruijn
2025-02-14 1:00 ` Jason Xing [this message]
2025-02-14 20:33 ` [PATCH bpf-next v11 09/12] bpf: add BPF_SOCK_OPS_TS_ACK_OPT_CB callback Martin KaFai Lau
2025-02-14 23:16 ` Jason Xing
2025-02-14 23:41 ` Martin KaFai Lau
2025-02-15 15:16 ` Willem de Bruijn
2025-02-14 1:00 ` [PATCH bpf-next v11 10/12] bpf: add BPF_SOCK_OPS_TS_SND_CB callback Jason Xing
2025-02-14 1:00 ` [PATCH bpf-next v11 11/12] bpf: support selective sampling for bpf timestamping Jason Xing
2025-02-15 15:10 ` Willem de Bruijn
2025-02-15 16:17 ` Jason Xing
2025-02-15 18:01 ` Willem de Bruijn
2025-02-15 21:11 ` Jason Xing
2025-02-14 1:00 ` [PATCH bpf-next v11 12/12] selftests/bpf: add simple bpf tests in the tx path for timestamping feature Jason Xing
2025-02-14 20:40 ` Martin KaFai Lau
2025-02-14 23:18 ` Jason Xing
2025-02-15 15:15 ` Willem de Bruijn
2025-02-15 16:17 ` Jason Xing
2025-02-15 18:01 ` Willem de Bruijn
2025-02-14 20:42 ` [PATCH bpf-next v11 00/12] net-timestamp: bpf extension to equip applications transparently Martin KaFai Lau
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=20250214010038.54131-10-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).