Introduce tskey_bpf to correlate tcp_sendmsg timestamp with other
three points (SND/SW/ACK). More details can be found in the
selftest.
For TCP, tskey_bpf is used to store the initial write_seq value
the moment tcp_sendmsg is called, so that the last skb of this
call will have the same tskey_bpf with tcp_sendmsg bpf callback.
UDP works similarly because tskey_bpf can increase by one everytime
udp_sendmsg gets called. It will be implemented soon.
Signed-off-by: Jason Xing <kerneljasonxing@xxxxxxxxx>
---
include/linux/skbuff.h | 2 ++
include/uapi/linux/bpf.h | 3 +++
net/core/sock.c | 3 ++-
net/ipv4/tcp.c | 10 ++++++++--
tools/include/uapi/linux/bpf.h | 3 +++
5 files changed, 18 insertions(+), 3 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d3ef8db94a94..3b7b470d5d89 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -609,6 +609,8 @@ struct skb_shared_info {
};
unsigned int gso_type;
u32 tskey;
+ /* For TCP, it records the initial write_seq when sendmsg is called */
+ u32 tskey_bpf;
/*
* Warning : all fields before dataref are cleared in __alloc_skb()
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index a0aff1b4eb61..87420c0f2235 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -7037,6 +7037,9 @@ enum {
* feature is on. It indicates the
* recorded timestamp.
*/
+ BPF_SOCK_OPS_TS_TCP_SND_CB, /* Called when every tcp_sendmsg
+ * syscall is triggered
+ */
};
/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
diff --git a/net/core/sock.c b/net/core/sock.c
index 2f54e60a50d4..e74ab0e2979d 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -958,7 +958,8 @@ void bpf_skops_tx_timestamping(struct sock *sk, struct sk_buff *skb, int op)
if (sk_is_tcp(sk) && sk_fullsock(sk))
sock_ops.is_fullsock = 1;
sock_ops.sk = sk;
- bpf_skops_init_skb(&sock_ops, skb, 0);
+ if (skb)
+ bpf_skops_init_skb(&sock_ops, skb, 0);
sock_ops.timestamp_used = 1;
__cgroup_bpf_run_filter_sock_ops(sk, &sock_ops, CGROUP_SOCK_OPS);
}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0a41006b10d1..b6e0db5e4ead 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -477,7 +477,7 @@ void tcp_init_sock(struct sock *sk)
}
EXPORT_SYMBOL(tcp_init_sock);
-static void tcp_tx_timestamp(struct sock *sk, struct sockcm_cookie *sockc)
+static void tcp_tx_timestamp(struct sock *sk, struct sockcm_cookie *sockc, u32 first_write_seq)
{
struct sk_buff *skb = tcp_write_queue_tail(sk);
u32 tsflags = sockc->tsflags;
@@ -500,6 +500,7 @@ static void tcp_tx_timestamp(struct sock *sk, struct sockcm_cookie *sockc)
tcb->txstamp_ack_bpf = 1;
shinfo->tx_flags |= SKBTX_BPF;
shinfo->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1;
+ shinfo->tskey_bpf = first_write_seq;
}
}
@@ -1067,10 +1068,15 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
int flags, err, copied = 0;
int mss_now = 0, size_goal, copied_syn = 0;
int process_backlog = 0;
+ u32 first_write_seq = 0;
int zc = 0;
long timeo;
flags = msg->msg_flags;
+ if (SK_BPF_CB_FLAG_TEST(sk, SK_BPF_CB_TX_TIMESTAMPING)) {
+ first_write_seq = tp->write_seq;
+ bpf_skops_tx_timestamping(sk, NULL, BPF_SOCK_OPS_TS_TCP_SND_CB);
+ }
if ((flags & MSG_ZEROCOPY) && size) {
if (msg->msg_ubuf) {
@@ -1331,7 +1337,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
out:
if (copied) {
- tcp_tx_timestamp(sk, &sockc);
+ tcp_tx_timestamp(sk, &sockc, first_write_seq);
tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
}
out_nopush:
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0fe7d663a244..3769e38e052d 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -7030,6 +7030,9 @@ enum {
* feature is on. It indicates the
* recorded timestamp.
*/
+ BPF_SOCK_OPS_TS_TCP_SND_CB, /* Called when every tcp_sendmsg
+ * syscall is triggered
+ */
};
/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
--
2.43.5
