samples/bpf: xdp_monitor include cpumap tracepoints in monitoring

The xdp_redirect_cpu sample have some "builtin" monitoring of the
tracepoints for xdp_cpumap_*, but it is practical to have an external
tool that can monitor these transpoint as an easy way to troubleshoot
an application using XDP + cpumap.

Specifically I need such external tool when working on Suricata and
XDP cpumap redirect. Extend the xdp_monitor tool sample with
monitoring of these xdp_cpumap_* tracepoints.  Model the output format
like xdp_redirect_cpu.

Given I needed to handle per CPU decoding for cpumap, this patch also
add per CPU info on the existing monitor events.  This resembles part
of the builtin monitoring output from sample xdp_rxq_info.  Thus, also
covering part of that sample in an external monitoring tool.

Performance wise, the cpumap tracepoints uses bulking, which cause
them to have very little overhead.  Thus, they are enabled by default.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

samples/bpf/xdp_monitor_kern.c

-/* XDP monitor tool, based on tracepoints
+/* SPDX-License-Identifier: GPL-2.0
+ *  Copyright(c) 2017-2018 Jesper Dangaard Brouer, Red Hat Inc.
  *
- *  Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
+ * XDP monitor tool, based on tracepoints
  */
 #include <uapi/linux/bpf.h>
 #include "bpf_helpers.h"
@@ -118,3 +119,92 @@ int trace_xdp_exception(struct xdp_exception_ctx *ctx)
 
 	return 0;
 }
+
+/* Common stats data record shared with _user.c */
+struct datarec {
+	u64 processed;
+	u64 dropped;
+	u64 info;
+};
+#define MAX_CPUS 64
+
+struct bpf_map_def SEC("maps") cpumap_enqueue_cnt = {
+	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size	= sizeof(u32),
+	.value_size	= sizeof(struct datarec),
+	.max_entries	= MAX_CPUS,
+};
+
+struct bpf_map_def SEC("maps") cpumap_kthread_cnt = {
+	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size	= sizeof(u32),
+	.value_size	= sizeof(struct datarec),
+	.max_entries	= 1,
+};
+
+/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_cpumap_enqueue/format
+ * Code in:         kernel/include/trace/events/xdp.h
+ */
+struct cpumap_enqueue_ctx {
+	u64 __pad;		// First 8 bytes are not accessible by bpf code
+	int map_id;		//	offset:8;  size:4; signed:1;
+	u32 act;		//	offset:12; size:4; signed:0;
+	int cpu;		//	offset:16; size:4; signed:1;
+	unsigned int drops;	//	offset:20; size:4; signed:0;
+	unsigned int processed;	//	offset:24; size:4; signed:0;
+	int to_cpu;		//	offset:28; size:4; signed:1;
+};
+
+SEC("tracepoint/xdp/xdp_cpumap_enqueue")
+int trace_xdp_cpumap_enqueue(struct cpumap_enqueue_ctx *ctx)
+{
+	u32 to_cpu = ctx->to_cpu;
+	struct datarec *rec;
+
+	if (to_cpu >= MAX_CPUS)
+		return 1;
+
+	rec = bpf_map_lookup_elem(&cpumap_enqueue_cnt, &to_cpu);
+	if (!rec)
+		return 0;
+	rec->processed += ctx->processed;
+	rec->dropped   += ctx->drops;
+
+	/* Record bulk events, then userspace can calc average bulk size */
+	if (ctx->processed > 0)
+		rec->info += 1;
+
+	return 0;
+}
+
+/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_cpumap_kthread/format
+ * Code in:         kernel/include/trace/events/xdp.h
+ */
+struct cpumap_kthread_ctx {
+	u64 __pad;		// First 8 bytes are not accessible by bpf code
+	int map_id;		//	offset:8;  size:4; signed:1;
+	u32 act;		//	offset:12; size:4; signed:0;
+	int cpu;		//	offset:16; size:4; signed:1;
+	unsigned int drops;	//	offset:20; size:4; signed:0;
+	unsigned int processed;	//	offset:24; size:4; signed:0;
+	int sched;		//	offset:28; size:4; signed:1;
+};
+
+SEC("tracepoint/xdp/xdp_cpumap_kthread")
+int trace_xdp_cpumap_kthread(struct cpumap_kthread_ctx *ctx)
+{
+	struct datarec *rec;
+	u32 key = 0;
+
+	rec = bpf_map_lookup_elem(&cpumap_kthread_cnt, &key);
+	if (!rec)
+		return 0;
+	rec->processed += ctx->processed;
+	rec->dropped   += ctx->drops;
+
+	/* Count times kthread yielded CPU via schedule call */
+	if (ctx->sched)
+		rec->info++;
+
+	return 0;
+}