tcp: add a tracepoint for tcp retransmission

We need a real-time notification for tcp retransmission
for monitoring.

Of course we could use ftrace to dynamically instrument this
kernel function too, however we can't retrieve the connection
information at the same time, for example perf-tools [1] reads
/proc/net/tcp for socket details, which is slow when we have
a lots of connections.

Therefore, this patch adds a tracepoint for __tcp_retransmit_skb()
and exposes src/dst IP addresses and ports of the connection.
This also makes it easier to integrate into perf.

Note, I expose both IPv4 and IPv6 addresses at the same time:
for a IPv4 socket, v4 mapped address is used as IPv6 addresses,
for a IPv6 socket, LOOPBACK4_IPV6 is already filled by kernel.
Also, add sk and skb pointers as they are useful for BPF.

1. https://github.com/brendangregg/perf-tools/blob/master/net/tcpretrans

Cc: Eric Dumazet <edumazet@google.com>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Brendan Gregg <bgregg@netflix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
new file mode 100644 (file)
index 0000000..3d1cbd0
--- /dev/null
+++ b/include/trace/events/tcp.h
@@ -0,0 +1,68 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM tcp
+
+#if !defined(_TRACE_TCP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_TCP_H
+
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/tracepoint.h>
+#include <net/ipv6.h>
+
+TRACE_EVENT(tcp_retransmit_skb,
+
+       TP_PROTO(struct sock *sk, struct sk_buff *skb),
+
+       TP_ARGS(sk, skb),
+
+       TP_STRUCT__entry(
+               __field(void *, skbaddr)
+               __field(void *, skaddr)
+               __field(__u16, sport)
+               __field(__u16, dport)
+               __array(__u8, saddr, 4)
+               __array(__u8, daddr, 4)
+               __array(__u8, saddr_v6, 16)
+               __array(__u8, daddr_v6, 16)
+       ),
+
+       TP_fast_assign(
+               struct ipv6_pinfo *np = inet6_sk(sk);
+               struct inet_sock *inet = inet_sk(sk);
+               struct in6_addr *pin6;
+               __be32 *p32;
+
+               __entry->skbaddr = skb;
+               __entry->skaddr = sk;
+
+               __entry->sport = ntohs(inet->inet_sport);
+               __entry->dport = ntohs(inet->inet_dport);
+
+               p32 = (__be32 *) __entry->saddr;
+               *p32 = inet->inet_saddr;
+
+               p32 = (__be32 *) __entry->daddr;
+               *p32 =  inet->inet_daddr;
+
+               if (np) {
+                       pin6 = (struct in6_addr *)__entry->saddr_v6;
+                       *pin6 = np->saddr;
+                       pin6 = (struct in6_addr *)__entry->daddr_v6;
+                       *pin6 = *(np->daddr_cache);
+               } else {
+                       pin6 = (struct in6_addr *)__entry->saddr_v6;
+                       ipv6_addr_set_v4mapped(inet->inet_saddr, pin6);
+                       pin6 = (struct in6_addr *)__entry->daddr_v6;
+                       ipv6_addr_set_v4mapped(inet->inet_daddr, pin6);
+               }
+       ),
+
+       TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6 daddrv6=%pI6",
+                 __entry->sport, __entry->dport, __entry->saddr, __entry->daddr,
+                 __entry->saddr_v6, __entry->daddr_v6)
+);
+
+#endif /* _TRACE_TCP_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

diff --git a/net/core/net-traces.c b/net/core/net-traces.c
index 1132820c8e62c362d5437c64a2a53c4b3b8dc381..f4e4fa2db505707215a960ab26a76a316ee77e05 100644 (file)
--- a/net/core/net-traces.c
+++ b/net/core/net-traces.c
@@ -31,6 +31,7 @@
 #include <trace/events/napi.h>
 #include <trace/events/sock.h>
 #include <trace/events/udp.h>
+#include <trace/events/tcp.h>
 #include <trace/events/fib.h>
 #include <trace/events/qdisc.h>
 #if IS_ENABLED(CONFIG_IPV6)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 696b0a168f160a2c7242fcc1f76dfa5e071ef255..6c74f2a3977876e691e7355045d4a84a98af1e30 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -42,6 +42,8 @@
 #include <linux/gfp.h>
 #include <linux/module.h>
 
+#include <trace/events/tcp.h>
+
 /* People can turn this off for buggy TCP's found in printers etc. */
 int sysctl_tcp_retrans_collapse __read_mostly = 1;
 
@@ -2875,6 +2877,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 
        if (likely(!err)) {
                TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
+               trace_tcp_retransmit_skb(sk, skb);
        } else if (err != -EBUSY) {
                NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
        }