Merge branch 'bpf: add mrtt and srtt as ctx->args for BPF_SOCK_OPS_RTT_CB'

Philo Lu says:

====================
These provides more information about tcp RTT estimation. The selftest for
BPF_SOCK_OPS_RTT_CB is extended for the added args.

changelogs
-> v1:
- extend rtt selftest for added args (suggested by Stanislav)
====================

Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>

include/net/tcp.h

@@ -2706,10 +2706,10 @@ static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk)
 	return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN, 0, NULL) == 1);
 }
 
-static inline void tcp_bpf_rtt(struct sock *sk)
+static inline void tcp_bpf_rtt(struct sock *sk, long mrtt, u32 srtt)
 {
 	if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_RTT_CB_FLAG))
-		tcp_call_bpf(sk, BPF_SOCK_OPS_RTT_CB, 0, NULL);
+		tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_RTT_CB, mrtt, srtt);
 }
 
 #if IS_ENABLED(CONFIG_SMC)

include/uapi/linux/bpf.h

@@ -6947,6 +6947,8 @@ enum {
 					 * socket transition to LISTEN state.
 					 */
 	BPF_SOCK_OPS_RTT_CB,		/* Called on every RTT.
+					 * Arg1: measured RTT input (mrtt)
+					 * Arg2: updated srtt
 					 */
 	BPF_SOCK_OPS_PARSE_HDR_OPT_CB,	/* Parse the header option.
 					 * It will be called to handle

net/ipv4/tcp_input.c

@@ -911,7 +911,7 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us)
 			tp->rtt_seq = tp->snd_nxt;
 			tp->mdev_max_us = tcp_rto_min_us(sk);
 
-			tcp_bpf_rtt(sk);
+			tcp_bpf_rtt(sk, mrtt_us, srtt);
 		}
 	} else {
 		/* no previous measure. */
@@ -921,7 +921,7 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us)
 		tp->mdev_max_us = tp->rttvar_us;
 		tp->rtt_seq = tp->snd_nxt;
 
-		tcp_bpf_rtt(sk);
+		tcp_bpf_rtt(sk, mrtt_us, srtt);
 	}
 	tp->srtt_us = max(1U, srtt);
 }

tools/include/uapi/linux/bpf.h

@@ -6947,6 +6947,8 @@ enum {
 					 * socket transition to LISTEN state.
 					 */
 	BPF_SOCK_OPS_RTT_CB,		/* Called on every RTT.
+					 * Arg1: measured RTT input (mrtt)
+					 * Arg2: updated srtt
 					 */
 	BPF_SOCK_OPS_PARSE_HDR_OPT_CB,	/* Parse the header option.
 					 * It will be called to handle

tools/testing/selftests/bpf/prog_tests/tcp_rtt.c

@@ -10,6 +10,9 @@ struct tcp_rtt_storage {
 	__u32 delivered;
 	__u32 delivered_ce;
 	__u32 icsk_retransmits;
+
+	__u32 mrtt_us;	/* args[0] */
+	__u32 srtt;	/* args[1] */
 };
 
 static void send_byte(int fd)
@@ -83,6 +86,17 @@ static int verify_sk(int map_fd, int client_fd, const char *msg, __u32 invoked,
 		err++;
 	}
 
+	/* Precise values of mrtt and srtt are unavailable, just make sure they are nonzero */
+	if (val.mrtt_us == 0) {
+		log_err("%s: unexpected bpf_tcp_sock.args[0] (mrtt_us) %u == 0", msg, val.mrtt_us);
+		err++;
+	}
+
+	if (val.srtt == 0) {
+		log_err("%s: unexpected bpf_tcp_sock.args[1] (srtt) %u == 0", msg, val.srtt);
+		err++;
+	}
+
 	return err;
 }
 

tools/testing/selftests/bpf/progs/tcp_rtt.c

@@ -10,6 +10,9 @@ struct tcp_rtt_storage {
 	__u32 delivered;
 	__u32 delivered_ce;
 	__u32 icsk_retransmits;
+
+	__u32 mrtt_us;	/* args[0] */
+	__u32 srtt;	/* args[1] */
 };
 
 struct {
@@ -55,5 +58,8 @@ int _sockops(struct bpf_sock_ops *ctx)
 	storage->delivered_ce = tcp_sk->delivered_ce;
 	storage->icsk_retransmits = tcp_sk->icsk_retransmits;
 
+	storage->mrtt_us = ctx->args[0];
+	storage->srtt = ctx->args[1];
+
 	return 1;
 }