Subject: [PATCH net-next v4] net/ipv4: add tracepoint for icmp_send

[xu.xin16]

From: hepeilin <he.peilin@xxxxxxxxxx>

Introduce a tracepoint for icmp_send, which can help users to get more
detail information conveniently when icmp abnormal events happen.

1. Giving an usecase example:
=============================
When an application experiences packet loss due to an unreachable UDP
destination port, the kernel will send an exception message through the
icmp_send function. By adding a trace point for icmp_send, developers or
system administrators can obtain detailed information about the UDP
packet loss, including the type, code, source address, destination address,
source port, and destination port. This facilitates the trouble-shooting
of UDP packet loss issues especially for those network-service
applications.

2. Operation Instructions:
==========================
Switch to the tracing directory.
        cd /sys/kernel/tracing
Filter for destination port unreachable.
        echo "type==3 && code==3" > events/icmp/icmp_send/filter
Enable trace event.
        echo 1 > events/icmp/icmp_send/enable

3. Result View:
================
 udp_client_erro-11370   [002] ...s.12   124.728002:
 icmp_send: icmp_send: type=3, code=3.
 From 127.0.0.1:41895 to 127.0.0.1:6666 ulen=23
 skbaddr=00000000589b167a

v3->v4:
Some fixes according to
https://lore.kernel.org/all/CANn89i+EFEr7VHXNdOi59Ba_R1nFKSBJzBzkJFVgCTdXBx=YBg@xxxxxxxxxxxxxx/
1.Add legality check for UDP header in SKB.
2.Target this patch for net-next.

v2->v3:
Some fixes according to
https://lore.kernel.org/all/20240319102549.7f7f6f53@xxxxxxxxxxxxxxxxxx/
1. Change the tracking directory to/sys/kernel/tracking.
2. Adjust the layout of the TP-STRUCT_entry parameter structure.

v1->v2:
Some fixes according to
https://lore.kernel.org/all/CANn89iL-y9e_VFpdw=sZtRnKRu_tnUwqHuFQTJvJsv-nz1xPDw@xxxxxxxxxxxxxx/
1. adjust the trace_icmp_send() to more protocols than UDP.
2. move the calling of trace_icmp_send after sanity checks
in __icmp_send().

Signed-off-by: Peilin He<he.peilin@xxxxxxxxxx>
Reviewed-by: xu xin <xu.xin16@xxxxxxxxxx>
Reviewed-by: Yunkai Zhang <zhang.yunkai@xxxxxxxxxx>
Cc: Yang Yang <yang.yang29@xxxxxxxxxx>
Cc: Liu Chun <liu.chun2@xxxxxxxxxx>
Cc: Xuexin Jiang <jiang.xuexin@xxxxxxxxxx>
---
 include/trace/events/icmp.h | 65 +++++++++++++++++++++++++++++++++++++
 net/ipv4/icmp.c             |  4 +++
 2 files changed, 69 insertions(+)
 create mode 100644 include/trace/events/icmp.h

diff --git a/include/trace/events/icmp.h b/include/trace/events/icmp.h
new file mode 100644
index 000000000000..7d5190f48a28
--- /dev/null
+++ b/include/trace/events/icmp.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM icmp
+
+#if !defined(_TRACE_ICMP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_ICMP_H
+
+#include <linux/icmp.h>
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(icmp_send,
+
+		TP_PROTO(const struct sk_buff *skb, int type, int code),
+
+		TP_ARGS(skb, type, code),
+
+		TP_STRUCT__entry(
+			__field(const void *, skbaddr)
+			__field(int, type)
+			__field(int, code)
+			__array(__u8, saddr, 4)
+			__array(__u8, daddr, 4)
+			__field(__u16, sport)
+			__field(__u16, dport)
+			__field(unsigned short, ulen)
+		),
+
+		TP_fast_assign(
+			struct iphdr *iph = ip_hdr(skb);
+			int proto_4 = iph->protocol;
+			__be32 *p32;
+
+			__entry->skbaddr = skb;
+			__entry->type = type;
+			__entry->code = code;
+
+			struct udphdr *uh = udp_hdr(skb);
+			if (proto_4 != IPPROTO_UDP || (u8 *)uh < skb->head ||
+				(u8 *)uh + sizeof(struct udphdr) > skb_tail_pointer(skb)) {
+				__entry->sport = 0;
+				__entry->dport = 0;
+				__entry->ulen = 0;
+			} else {
+				__entry->sport = ntohs(uh->source);
+				__entry->dport = ntohs(uh->dest);
+				__entry->ulen = ntohs(uh->len);
+			}
+
+			p32 = (__be32 *) __entry->saddr;
+			*p32 = iph->saddr;
+
+			p32 = (__be32 *) __entry->daddr;
+			*p32 = iph->daddr;
+		),
+
+		TP_printk("icmp_send: type=%d, code=%d. From %pI4:%u to %pI4:%u ulen=%d skbaddr=%p",
+			__entry->type, __entry->code,
+			__entry->saddr, __entry->sport, __entry->daddr,
+			__entry->dport, __entry->ulen, __entry->skbaddr)
+);
+
+#endif /* _TRACE_ICMP_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
\ No newline at end of file
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 8cebb476b3ab..224551d75c02 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -92,6 +92,8 @@
 #include <net/inet_common.h>
 #include <net/ip_fib.h>
 #include <net/l3mdev.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/icmp.h>

 /*
  *	Build xmit assembly blocks
@@ -672,6 +674,8 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 		}
 	}

+	trace_icmp_send(skb_in, type, code);
+
 	/* Needed by both icmp_global_allow and icmp_xmit_lock */
 	local_bh_disable();

-- 
2.25.1