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
Cc: bpf@vger.kernel.org, netdev@vger.kernel.org,
Jason Xing <kernelxing@tencent.com>
Subject: [PATCH net-next v2 12/12] net-timestamp: add bpf support for rx software/hardware timestamp
Date: Sat, 12 Oct 2024 12:06:51 +0800 [thread overview]
Message-ID: <20241012040651.95616-13-kerneljasonxing@gmail.com> (raw)
In-Reply-To: <20241012040651.95616-1-kerneljasonxing@gmail.com>
From: Jason Xing <kernelxing@tencent.com>
Now it's time to let the bpf for rx timestamp take effect.
Signed-off-by: Jason Xing <kernelxing@tencent.com>
---
include/net/tcp.h | 14 ++++++++++++++
include/uapi/linux/bpf.h | 5 +++++
net/ipv4/tcp.c | 29 +++++++++++++++++++++++++++--
tools/include/uapi/linux/bpf.h | 5 +++++
4 files changed, 51 insertions(+), 2 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 728db7107074..5a7893379ef7 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2676,6 +2676,14 @@ static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2,
return tcp_call_bpf(sk, op, 3, args);
}
+static inline int tcp_call_bpf_4arg(struct sock *sk, int op, u32 arg1, u32 arg2,
+ u32 arg3, u32 arg4)
+{
+ u32 args[4] = {arg1, arg2, arg3, arg4};
+
+ return tcp_call_bpf(sk, op, 4, args);
+}
+
#else
static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args)
{
@@ -2693,6 +2701,12 @@ static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2,
return -EPERM;
}
+static inline int tcp_call_bpf_4arg(struct sock *sk, int op, u32 arg1, u32 arg2,
+ u32 arg3, u32 arg4)
+{
+ return -EPERM;
+}
+
#endif
static inline u32 tcp_timeout_init(struct sock *sk)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d2754f155cf7..3527c20c8396 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -7037,6 +7037,11 @@ enum {
* feature is on. It indicates the
* recorded timestamp.
*/
+ BPF_SOCK_OPS_TS_RX_OPT_CB, /* Called when tcp layer tries to
+ * receive skbs with timestamps 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/ipv4/tcp.c b/net/ipv4/tcp.c
index 0891b41bc745..14bc7283f574 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2262,10 +2262,35 @@ static int tcp_zerocopy_receive(struct sock *sk,
static void tcp_bpf_recv_timestamp(struct sock *sk, struct scm_timestamping_internal *tss)
{
+ u32 tsflags = READ_ONCE(sk->sk_tsflags[BPFPROG_TS_REQUESTOR]);
struct tcp_sock *tp = tcp_sk(sk);
- if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RX_TIMESTAMPING_OPT_CB_FLAG))
- return;
+ if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RX_TIMESTAMPING_OPT_CB_FLAG)) {
+ u32 hw_sec, hw_nsec, sw_sec, sw_nsec;
+
+ if (!(tsflags & (SOF_TIMESTAMPING_RX_SOFTWARE |
+ SOF_TIMESTAMPING_RX_HARDWARE)))
+ return;
+
+ if (tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) {
+ sw_sec = tss->ts[0].tv_sec;
+ sw_nsec = tss->ts[0].tv_nsec;
+ } else {
+ sw_sec = 0;
+ sw_nsec = 0;
+ }
+
+ if (tsflags & SOF_TIMESTAMPING_RX_HARDWARE) {
+ hw_sec = tss->ts[2].tv_sec;
+ hw_nsec = tss->ts[2].tv_nsec;
+ } else {
+ hw_sec = 0;
+ hw_nsec = 0;
+ }
+
+ tcp_call_bpf_4arg(sk, BPF_SOCK_OPS_TS_RX_OPT_CB,
+ sw_sec, sw_nsec, hw_sec, hw_nsec);
+ }
}
/* Similar to __sock_recv_timestamp, but does not require an skb */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 331e3e6f1ed5..fad942abc36a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -7036,6 +7036,11 @@ enum {
* feature is on. It indicates the
* recorded timestamp.
*/
+ BPF_SOCK_OPS_TS_RX_OPT_CB, /* Called when tcp layer tries to
+ * receive skbs with timestamps 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
--
2.37.3
next prev parent reply other threads:[~2024-10-12 4:07 UTC|newest]
Thread overview: 73+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-12 4:06 [PATCH net-next v2 00/12] net-timestamp: bpf extension to equip applications transparently Jason Xing
2024-10-12 4:06 ` [PATCH net-next v2 01/12] net-timestamp: introduce socket tsflag requestors Jason Xing
2024-10-15 1:30 ` Willem de Bruijn
2024-10-15 1:50 ` Jason Xing
2024-10-12 4:06 ` [PATCH net-next v2 02/12] net-timestamp: open gate for bpf_setsockopt Jason Xing
2024-10-15 1:34 ` Willem de Bruijn
2024-10-15 2:05 ` Jason Xing
2024-10-15 21:32 ` Martin KaFai Lau
2024-10-15 21:55 ` Willem de Bruijn
2024-10-22 13:22 ` Jason Xing
2024-10-23 0:06 ` Willem de Bruijn
2024-10-23 3:49 ` Jason Xing
2024-10-16 0:45 ` Jason Xing
2024-10-15 23:54 ` Martin KaFai Lau
2024-10-16 0:49 ` Jason Xing
2024-10-12 4:06 ` [PATCH net-next v2 03/12] net-timestamp: reorganize in skb_tstamp_tx_output() Jason Xing
2024-10-12 4:06 ` [PATCH net-next v2 04/12] net-timestamp: add static key to control the whole bpf extension Jason Xing
2024-10-15 1:36 ` Willem de Bruijn
2024-10-15 2:25 ` Jason Xing
2024-10-16 0:09 ` Martin KaFai Lau
2024-10-16 1:04 ` Jason Xing
2024-10-16 1:32 ` Jason Xing
2024-10-16 6:13 ` Martin KaFai Lau
2024-10-16 6:30 ` Jason Xing
2024-10-16 7:01 ` Martin KaFai Lau
2024-10-16 7:54 ` Jason Xing
2024-10-16 8:31 ` Martin KaFai Lau
2024-10-16 10:36 ` Jason Xing
2024-10-17 0:48 ` Martin KaFai Lau
2024-10-17 2:28 ` Jason Xing
2024-10-17 20:43 ` Martin KaFai Lau
2024-10-18 2:52 ` Jason Xing
2024-10-18 3:05 ` Jason Xing
2024-10-16 6:31 ` Martin KaFai Lau
2024-10-16 6:45 ` Jason Xing
2024-10-16 13:13 ` Willem de Bruijn
2024-10-16 13:22 ` Jason Xing
2024-10-20 21:51 ` Willem de Bruijn
2024-10-21 3:21 ` Jason Xing
2024-10-21 14:49 ` Willem de Bruijn
2024-10-21 15:05 ` Jason Xing
2024-10-22 0:53 ` Martin KaFai Lau
2024-10-22 2:30 ` Jason Xing
2024-10-23 0:17 ` Willem de Bruijn
2024-10-23 2:31 ` Willem de Bruijn
2024-10-12 4:06 ` [PATCH net-next v2 05/12] net-timestamp: add bpf infrastructure to allow exposing timestamp later Jason Xing
2024-10-12 4:06 ` [PATCH net-next v2 06/12] net-timestamp: introduce TS_SCHED_OPT_CB to generate dev xmit timestamp Jason Xing
2024-10-16 1:01 ` Martin KaFai Lau
2024-10-16 1:24 ` Jason Xing
2024-10-16 5:35 ` Martin KaFai Lau
2024-10-16 6:08 ` Jason Xing
2024-10-12 4:06 ` [PATCH net-next v2 07/12] net-timestamp: introduce TS_SW_OPT_CB to generate driver timestamp Jason Xing
2024-10-12 4:06 ` [PATCH net-next v2 08/12] net-timestamp: introduce TS_ACK_OPT_CB to generate tcp acked timestamp Jason Xing
2024-10-12 4:06 ` [PATCH net-next v2 09/12] net-timestamp: add tx OPT_ID_TCP support for bpf case Jason Xing
2024-10-15 1:38 ` Willem de Bruijn
2024-10-15 2:25 ` Jason Xing
2024-10-15 2:38 ` Willem de Bruijn
2024-10-15 2:59 ` Jason Xing
2024-10-15 8:40 ` kernel test robot
2024-10-15 9:36 ` Jason Xing
2024-10-12 4:06 ` [PATCH net-next v2 10/12] net-timestamp: make bpf for tx timestamp work Jason Xing
2024-10-12 4:06 ` [PATCH net-next v2 11/12] net-timestamp: add bpf framework for rx timestamps Jason Xing
2024-10-15 1:44 ` Willem de Bruijn
2024-10-15 2:18 ` Jason Xing
2024-10-12 4:06 ` Jason Xing [this message]
2024-10-12 17:48 ` [PATCH net-next v2 00/12] net-timestamp: bpf extension to equip applications transparently Willem de Bruijn
2024-10-13 3:28 ` Jason Xing
2024-10-13 3:43 ` Jason Xing
2024-10-13 6:05 ` Jason Xing
2024-10-15 1:28 ` Willem de Bruijn
2024-10-15 2:52 ` Jason Xing
2024-10-15 2:59 ` Willem de Bruijn
2024-10-15 3:02 ` 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=20241012040651.95616-13-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=john.fastabend@gmail.com \
--cc=jolsa@kernel.org \
--cc=kernelxing@tencent.com \
--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).