samples: bpf: Add cpumap tracepoint statistics support

This consolidates retrieval and printing into the XDP sample helper. For
the kthread stats, it expands xdp_stats separately with its own per-CPU
stats. For cpumap enqueue, we display FROM->TO stats also with its
per-CPU stats.

The help out explains in detail the various aspects of the output.
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210821002010.845777-10-memxor@gmail.com

samples/bpf/xdp_sample_user.h

@@ -11,6 +11,8 @@ enum stats_mask {
 	_SAMPLE_REDIRECT_MAP        = 1U << 0,
 	SAMPLE_RX_CNT               = 1U << 1,
 	SAMPLE_REDIRECT_ERR_CNT     = 1U << 2,
+	SAMPLE_CPUMAP_ENQUEUE_CNT   = 1U << 3,
+	SAMPLE_CPUMAP_KTHREAD_CNT   = 1U << 4,
 	SAMPLE_EXCEPTION_CNT        = 1U << 5,
 	SAMPLE_REDIRECT_CNT         = 1U << 7,
 	SAMPLE_REDIRECT_MAP_CNT     = SAMPLE_REDIRECT_CNT | _SAMPLE_REDIRECT_MAP,
@@ -76,6 +78,10 @@ static inline char *safe_strncpy(char *dst, const char *src, size_t size)
 			__attach_tp(tp_xdp_redirect_map_err);                  \
 		if (mask & SAMPLE_REDIRECT_ERR_CNT)                            \
 			__attach_tp(tp_xdp_redirect_err);                      \
+		if (mask & SAMPLE_CPUMAP_ENQUEUE_CNT)                          \
+			__attach_tp(tp_xdp_cpumap_enqueue);                    \
+		if (mask & SAMPLE_CPUMAP_KTHREAD_CNT)                          \
+			__attach_tp(tp_xdp_cpumap_kthread);                    \
 		if (mask & SAMPLE_EXCEPTION_CNT)                               \
 			__attach_tp(tp_xdp_exception);                         \
 		return 0;                                                      \