tcp: SOF_TIMESTAMPING_OPT_STATS option for SO_TIMESTAMPING

This patch exports the sender chronograph stats via the socket
SO_TIMESTAMPING channel. Currently we can instrument how long a
particular application unit of data was queued in TCP by tracking
SOF_TIMESTAMPING_TX_SOFTWARE and SOF_TIMESTAMPING_TX_SCHED. Having
these sender chronograph stats exported simultaneously along with
these timestamps allow further breaking down the various sender
limitation.  For example, a video server can tell if a particular
chunk of video on a connection takes a long time to deliver because
TCP was experiencing small receive window. It is not possible to
tell before this patch without packet traces.

To prepare these stats, the user needs to set
SOF_TIMESTAMPING_OPT_STATS and SOF_TIMESTAMPING_OPT_TSONLY flags
while requesting other SOF_TIMESTAMPING TX timestamps. When the
timestamps are available in the error queue, the stats are returned
in a separate control message of type SCM_TIMESTAMPING_OPT_STATS,
in a list of TLVs (struct nlattr) of types: TCP_NLA_BUSY_TIME,
TCP_NLA_RWND_LIMITED, TCP_NLA_SNDBUF_LIMITED. Unit is microsecond.

Signed-off-by: Francis Yan <francisyyan@gmail.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 44 insertions, 4 deletions

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index d1d1a5a5ad24..ea6fa954c7a0 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3839,10 +3839,18 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 	if (!skb_may_tx_timestamp(sk, tsonly))
 		return;
 
-	if (tsonly)
-		skb = alloc_skb(0, GFP_ATOMIC);
-	else
+	if (tsonly) {
+#ifdef CONFIG_INET
+		if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) &&
+		    sk->sk_protocol == IPPROTO_TCP &&
+		    sk->sk_type == SOCK_STREAM)
+			skb = tcp_get_timestamping_opt_stats(sk);
+		else
+#endif
+			skb = alloc_skb(0, GFP_ATOMIC);
+	} else {
 		skb = skb_clone(orig_skb, GFP_ATOMIC);
+	}
 	if (!skb)
 		return;
 
diff --git a/net/core/sock.c b/net/core/sock.c
index 14e6145be33b..d8c7f8c877ca 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -854,6 +854,13 @@ set_rcvbuf:
 				sk->sk_tskey = 0;
 			}
 		}
+
+		if (val & SOF_TIMESTAMPING_OPT_STATS &&
+		    !(val & SOF_TIMESTAMPING_OPT_TSONLY)) {
+			ret = -EINVAL;
+			break;
+		}
+
 		sk->sk_tsflags = val;
 		if (val & SOF_TIMESTAMPING_RX_SOFTWARE)
 			sock_enable_timestamp(sk,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index cdde20f49999..1149b48700a1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2841,6 +2841,26 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
 
+struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+	struct sk_buff *stats;
+	struct tcp_info info;
+
+	stats = alloc_skb(3 * nla_total_size_64bit(sizeof(u64)), GFP_ATOMIC);
+	if (!stats)
+		return NULL;
+
+	tcp_get_info_chrono_stats(tp, &info);
+	nla_put_u64_64bit(stats, TCP_NLA_BUSY,
+			  info.tcpi_busy_time, TCP_NLA_PAD);
+	nla_put_u64_64bit(stats, TCP_NLA_RWND_LIMITED,
+			  info.tcpi_rwnd_limited, TCP_NLA_PAD);
+	nla_put_u64_64bit(stats, TCP_NLA_SNDBUF_LIMITED,
+			  info.tcpi_sndbuf_limited, TCP_NLA_PAD);
+	return stats;
+}
+
 static int do_tcp_getsockopt(struct sock *sk, int level,
 		int optname, char __user *optval, int __user *optlen)
 {
diff --git a/net/socket.c b/net/socket.c
index e2584c51aa1f..e6318943ad07 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -693,9 +693,14 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 	    (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) &&
 	    ktime_to_timespec_cond(shhwtstamps->hwtstamp, tss.ts + 2))
 		empty = 0;
-	if (!empty)
+	if (!empty) {
 		put_cmsg(msg, SOL_SOCKET,
 			 SCM_TIMESTAMPING, sizeof(tss), &tss);
+
+		if (skb->len && (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS))
+			put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_OPT_STATS,
+				 skb->len, skb->data);
+	}
 }
 EXPORT_SYMBOL_GPL(__sock_recv_timestamp);