Merge branch 'tcp-trace-next'

Philo Lu says:

====================
tcp: update TCPCB_EVER_RETRANS after trace_tcp_retransmit_skb()

Move TCPCB_EVER_RETRANS updating after the trace_tcp_retransmit_skb()
in __tcp_retransmit_skb(), and then we are aware of whether the skb has
ever been retransmitted in this tracepoint. This can be used, e.g., to get
retransmission efficiency by counting skbs w/ and w/o TCPCB_EVER_RETRANS
(through bpf tracing programs).

For this purpose, TCPCB_EVER_RETRANS is also needed to be exposed to bpf.
Previously, the flags are defined as macros in struct tcp_skb_cb. I moved them
out into a new enum, and then they can be accessed with vmlinux.h.

We have discussed to achieve this with BPF_SOCK_OPS in [0], and using
tracepoint is thought to be a better solution.

[0]
https://lore.kernel.org/all/20240417124622.35333-1-lulie@linux.alibaba.com/
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 19 insertions, 14 deletions

diff --git a/include/net/tcp.h b/include/net/tcp.h
index b935e1ae4caf8a..ffc9371fe9dea5 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -928,6 +928,19 @@ static inline u32 tcp_rsk_tsval(const struct tcp_request_sock *treq)
 
 #define TCPHDR_SYN_ECN	(TCPHDR_SYN | TCPHDR_ECE | TCPHDR_CWR)
 
+/* State flags for sacked in struct tcp_skb_cb */
+enum tcp_skb_cb_sacked_flags {
+	TCPCB_SACKED_ACKED	= (1 << 0),	/* SKB ACK'd by a SACK block	*/
+	TCPCB_SACKED_RETRANS	= (1 << 1),	/* SKB retransmitted		*/
+	TCPCB_LOST		= (1 << 2),	/* SKB is lost			*/
+	TCPCB_TAGBITS		= (TCPCB_SACKED_ACKED | TCPCB_SACKED_RETRANS |
+				   TCPCB_LOST),	/* All tag bits			*/
+	TCPCB_REPAIRED		= (1 << 4),	/* SKB repaired (no skb_mstamp_ns)	*/
+	TCPCB_EVER_RETRANS	= (1 << 7),	/* Ever retransmitted frame	*/
+	TCPCB_RETRANS		= (TCPCB_SACKED_RETRANS | TCPCB_EVER_RETRANS |
+				   TCPCB_REPAIRED),
+};
+
 /* This is what the send packet queuing engine uses to pass
  * TCP per-packet control information to the transmission code.
  * We also store the host-order sequence numbers in here too.
@@ -950,15 +963,6 @@ struct tcp_skb_cb {
 	__u8		tcp_flags;	/* TCP header flags. (tcp[13])	*/
 
 	__u8		sacked;		/* State flags for SACK.	*/
-#define TCPCB_SACKED_ACKED	0x01	/* SKB ACK'd by a SACK block	*/
-#define TCPCB_SACKED_RETRANS	0x02	/* SKB retransmitted		*/
-#define TCPCB_LOST		0x04	/* SKB is lost			*/
-#define TCPCB_TAGBITS		0x07	/* All tag bits			*/
-#define TCPCB_REPAIRED		0x10	/* SKB repaired (no skb_mstamp_ns)	*/
-#define TCPCB_EVER_RETRANS	0x80	/* Ever retransmitted frame	*/
-#define TCPCB_RETRANS		(TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \
-				TCPCB_REPAIRED)
-
 	__u8		ip_dsfield;	/* IPv4 tos or IPv6 dsfield	*/
 	__u8		txstamp_ack:1,	/* Record TX timestamp for ack? */
 			eor:1,		/* Is skb MSG_EOR marked? */
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 99a1d88f7f47b9..ce59e4499b66df 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3418,11 +3418,6 @@ start:
 		err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 	}
 
-	/* To avoid taking spuriously low RTT samples based on a timestamp
-	 * for a transmit that never happened, always mark EVER_RETRANS
-	 */
-	TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
-
 	if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RETRANS_CB_FLAG))
 		tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RETRANS_CB,
 				  TCP_SKB_CB(skb)->seq, segs, err);
@@ -3432,6 +3427,12 @@ start:
 	} else if (err != -EBUSY) {
 		NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL, segs);
 	}
+
+	/* To avoid taking spuriously low RTT samples based on a timestamp
+	 * for a transmit that never happened, always mark EVER_RETRANS
+	 */
+	TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
+
 	return err;
 }