[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20250212061855.71154-10-kerneljasonxing@gmail.com>
Date: Wed, 12 Feb 2025 14:18:52 +0800
From: Jason Xing <kerneljasonxing@...il.com>
To: davem@...emloft.net,
edumazet@...gle.com,
kuba@...nel.org,
pabeni@...hat.com,
dsahern@...nel.org,
willemdebruijn.kernel@...il.com,
willemb@...gle.com,
ast@...nel.org,
daniel@...earbox.net,
andrii@...nel.org,
martin.lau@...ux.dev,
eddyz87@...il.com,
song@...nel.org,
yonghong.song@...ux.dev,
john.fastabend@...il.com,
kpsingh@...nel.org,
sdf@...ichev.me,
haoluo@...gle.com,
jolsa@...nel.org,
shuah@...nel.org,
ykolal@...com
Cc: bpf@...r.kernel.org,
netdev@...r.kernel.org,
Jason Xing <kerneljasonxing@...il.com>
Subject: [PATCH bpf-next v10 09/12] bpf: add BPF_SOCK_OPS_TS_ACK_OPT_CB callback
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@...il.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 4930c43ee77b..9f01dde12e3a 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 & (hwts ? 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;
@@ -5572,6 +5572,9 @@ static void skb_tstamp_tx_report_bpf_timestamping(struct sk_buff *skb,
if (hwts)
*skb_hwtstamps(skb) = *hwts;
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..aa080f7ccea4 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
Powered by blists - more mailing lists