tcp: add tracepoint for checksum errors

Add a tracepoint for capturing TCP segments with
a bad checksum. This makes it easy to identify
sources of bad frames in the fleet (e.g. machines
with faulty NICs).

It should also help tools like IOvisor's tcpdrop.py
which are used today to get detailed information
about such packets.

We don't have a socket in many cases so we must
open code the address extraction based just on
the skb.

v2: add missing export for ipv6=m

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/trace/events/tcp.h

@@ -295,6 +295,82 @@ TRACE_EVENT(tcp_probe,
 		  __entry->srtt, __entry->rcv_wnd, __entry->sock_cookie)
 );
 
+#define TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb)			\
+	do {								\
+		const struct tcphdr *th = (const struct tcphdr *)skb->data; \
+		struct sockaddr_in *v4 = (void *)__entry->saddr;	\
+									\
+		v4->sin_family = AF_INET;				\
+		v4->sin_port = th->source;				\
+		v4->sin_addr.s_addr = ip_hdr(skb)->saddr;		\
+		v4 = (void *)__entry->daddr;				\
+		v4->sin_family = AF_INET;				\
+		v4->sin_port = th->dest;				\
+		v4->sin_addr.s_addr = ip_hdr(skb)->daddr;		\
+	} while (0)
+
+#if IS_ENABLED(CONFIG_IPV6)
+
+#define TP_STORE_ADDR_PORTS_SKB(__entry, skb)				\
+	do {								\
+		const struct iphdr *iph = ip_hdr(skb);			\
+									\
+		if (iph->version == 6) {				\
+			const struct tcphdr *th = (const struct tcphdr *)skb->data; \
+			struct sockaddr_in6 *v6 = (void *)__entry->saddr; \
+									\
+			v6->sin6_family = AF_INET6;			\
+			v6->sin6_port = th->source;			\
+			v6->sin6_addr = ipv6_hdr(skb)->saddr;		\
+			v6 = (void *)__entry->daddr;			\
+			v6->sin6_family = AF_INET6;			\
+			v6->sin6_port = th->dest;			\
+			v6->sin6_addr = ipv6_hdr(skb)->daddr;		\
+		} else							\
+			TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb);	\
+	} while (0)
+
+#else
+
+#define TP_STORE_ADDR_PORTS_SKB(__entry, skb)		\
+	TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb)
+
+#endif
+
+/*
+ * tcp event with only skb
+ */
+DECLARE_EVENT_CLASS(tcp_event_skb,
+
+	TP_PROTO(const struct sk_buff *skb),
+
+	TP_ARGS(skb),
+
+	TP_STRUCT__entry(
+		__field(const void *, skbaddr)
+		__array(__u8, saddr, sizeof(struct sockaddr_in6))
+		__array(__u8, daddr, sizeof(struct sockaddr_in6))
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+
+		memset(__entry->saddr, 0, sizeof(struct sockaddr_in6));
+		memset(__entry->daddr, 0, sizeof(struct sockaddr_in6));
+
+		TP_STORE_ADDR_PORTS_SKB(__entry, skb);
+	),
+
+	TP_printk("src=%pISpc dest=%pISpc", __entry->saddr, __entry->daddr)
+);
+
+DEFINE_EVENT(tcp_event_skb, tcp_bad_csum,
+
+	TP_PROTO(const struct sk_buff *skb),
+
+	TP_ARGS(skb)
+);
+
 #endif /* _TRACE_TCP_H */
 
 /* This part must be outside protection */

net/core/net-traces.c

@@ -60,3 +60,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb);
 EXPORT_TRACEPOINT_SYMBOL_GPL(napi_poll);
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_send_reset);
+EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_bad_csum);

net/ipv4/tcp_input.c

@@ -5885,6 +5885,7 @@ step5:
 	return;
 
 csum_error:
+	trace_tcp_bad_csum(skb);
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS);
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
 

net/ipv4/tcp_ipv4.c

@@ -1731,6 +1731,7 @@ discard:
 	return 0;
 
 csum_err:
+	trace_tcp_bad_csum(skb);
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS);
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
 	goto discard;
@@ -1801,6 +1802,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 
 	if (unlikely(tcp_checksum_complete(skb))) {
 		bh_unlock_sock(sk);
+		trace_tcp_bad_csum(skb);
 		__TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS);
 		__TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
 		return true;
@@ -2098,6 +2100,7 @@ no_tcp_socket:
 
 	if (tcp_checksum_complete(skb)) {
 csum_error:
+		trace_tcp_bad_csum(skb);
 		__TCP_INC_STATS(net, TCP_MIB_CSUMERRORS);
 bad_packet:
 		__TCP_INC_STATS(net, TCP_MIB_INERRS);

net/ipv6/tcp_ipv6.c

@@ -1538,6 +1538,7 @@ discard:
 	kfree_skb(skb);
 	return 0;
 csum_err:
+	trace_tcp_bad_csum(skb);
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS);
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
 	goto discard;
@@ -1754,6 +1755,7 @@ no_tcp_socket:
 
 	if (tcp_checksum_complete(skb)) {
 csum_error:
+		trace_tcp_bad_csum(skb);
 		__TCP_INC_STATS(net, TCP_MIB_CSUMERRORS);
 bad_packet:
 		__TCP_INC_STATS(net, TCP_MIB_INERRS);