bpf: cpumap add tracepoints

This adds two tracepoint to the cpumap.  One for the enqueue side
trace_xdp_cpumap_enqueue() and one for the kthread dequeue side
trace_xdp_cpumap_kthread().

To mitigate the tracepoint overhead, these are invoked during the
enqueue/dequeue bulking phases, thus amortizing the cost.

The obvious use-cases are for debugging and monitoring.  The
non-intuitive use-case is using these as a feedback loop to know the
system load.  One can imagine auto-scaling by reducing, adding or
activating more worker CPUs on demand.

V4: tracepoint remove time_limit info, instead add sched info

V8: intro struct bpf_cpu_map_entry members cpu+map_id in this patch

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 70 insertions, 0 deletions

diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index eb2ece96c1a2..0c8dec61987e 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -150,6 +150,76 @@ DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map_err,
 	 trace_xdp_redirect_map_err(dev, xdp, devmap_ifindex(fwd, map),	\
 				    err, map, idx)
 
+TRACE_EVENT(xdp_cpumap_kthread,
+
+	TP_PROTO(int map_id, unsigned int processed,  unsigned int drops,
+		 int sched),
+
+	TP_ARGS(map_id, processed, drops, sched),
+
+	TP_STRUCT__entry(
+		__field(int, map_id)
+		__field(u32, act)
+		__field(int, cpu)
+		__field(unsigned int, drops)
+		__field(unsigned int, processed)
+		__field(int, sched)
+	),
+
+	TP_fast_assign(
+		__entry->map_id		= map_id;
+		__entry->act		= XDP_REDIRECT;
+		__entry->cpu		= smp_processor_id();
+		__entry->drops		= drops;
+		__entry->processed	= processed;
+		__entry->sched	= sched;
+	),
+
+	TP_printk("kthread"
+		  " cpu=%d map_id=%d action=%s"
+		  " processed=%u drops=%u"
+		  " sched=%d",
+		  __entry->cpu, __entry->map_id,
+		  __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
+		  __entry->processed, __entry->drops,
+		  __entry->sched)
+);
+
+TRACE_EVENT(xdp_cpumap_enqueue,
+
+	TP_PROTO(int map_id, unsigned int processed,  unsigned int drops,
+		 int to_cpu),
+
+	TP_ARGS(map_id, processed, drops, to_cpu),
+
+	TP_STRUCT__entry(
+		__field(int, map_id)
+		__field(u32, act)
+		__field(int, cpu)
+		__field(unsigned int, drops)
+		__field(unsigned int, processed)
+		__field(int, to_cpu)
+	),
+
+	TP_fast_assign(
+		__entry->map_id		= map_id;
+		__entry->act		= XDP_REDIRECT;
+		__entry->cpu		= smp_processor_id();
+		__entry->drops		= drops;
+		__entry->processed	= processed;
+		__entry->to_cpu		= to_cpu;
+	),
+
+	TP_printk("enqueue"
+		  " cpu=%d map_id=%d action=%s"
+		  " processed=%u drops=%u"
+		  " to_cpu=%d",
+		  __entry->cpu, __entry->map_id,
+		  __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
+		  __entry->processed, __entry->drops,
+		  __entry->to_cpu)
+);
+
 #endif /* _TRACE_XDP_H */
 
 #include <trace/define_trace.h>