perf tools: Add new PERF_RECORD_SWITCH event

Support processing of PERF_RECORD_SWITCH events and
PERF_RECORD_SWITCH_CPU_WIDE events. There is a single
tools callback for them both so that the tool must
check the event type before using the extra members
in PERF_RECORD_SWITCH_CPU_WIDE.

There is still no way to select the events, though.
That is added in a subsequest patch.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Jiri Olsa <jolsa@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Pawel Moll <pawel.moll@arm.com>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1437471846-26995-3-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-inject.c

@@ -561,6 +561,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			.lost		= perf_event__repipe,
 			.aux		= perf_event__repipe,
 			.itrace_start	= perf_event__repipe,
+			.context_switch	= perf_event__repipe,
 			.read		= perf_event__repipe_sample,
 			.throttle	= perf_event__repipe,
 			.unthrottle	= perf_event__repipe,

tools/perf/util/event.c

@@ -26,6 +26,8 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_AUX]			= "AUX",
 	[PERF_RECORD_ITRACE_START]		= "ITRACE_START",
 	[PERF_RECORD_LOST_SAMPLES]		= "LOST_SAMPLES",
+	[PERF_RECORD_SWITCH]			= "SWITCH",
+	[PERF_RECORD_SWITCH_CPU_WIDE]		= "SWITCH_CPU_WIDE",
 	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
 	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",
 	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",
@@ -749,6 +751,14 @@ int perf_event__process_lost_samples(struct perf_tool *tool __maybe_unused,
 	return machine__process_lost_samples_event(machine, event, sample);
 }
 
+int perf_event__process_switch(struct perf_tool *tool __maybe_unused,
+			       union perf_event *event,
+			       struct perf_sample *sample __maybe_unused,
+			       struct machine *machine)
+{
+	return machine__process_switch_event(machine, event);
+}
+
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
 {
 	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n",
@@ -827,6 +837,20 @@ size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp)
 		       event->itrace_start.pid, event->itrace_start.tid);
 }
 
+size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp)
+{
+	bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT;
+	const char *in_out = out ? "OUT" : "IN ";
+
+	if (event->header.type == PERF_RECORD_SWITCH)
+		return fprintf(fp, " %s\n", in_out);
+
+	return fprintf(fp, " %s  %s pid/tid: %5u/%-5u\n",
+		       in_out, out ? "next" : "prev",
+		       event->context_switch.next_prev_pid,
+		       event->context_switch.next_prev_tid);
+}
+
 size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 {
 	size_t ret = fprintf(fp, "PERF_RECORD_%s",
@@ -852,6 +876,10 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 	case PERF_RECORD_ITRACE_START:
 		ret += perf_event__fprintf_itrace_start(event, fp);
 		break;
+	case PERF_RECORD_SWITCH:
+	case PERF_RECORD_SWITCH_CPU_WIDE:
+		ret += perf_event__fprintf_switch(event, fp);
+		break;
 	default:
 		ret += fprintf(fp, "\n");
 	}

tools/perf/util/event.h

@@ -348,6 +348,12 @@ struct itrace_start_event {
 	u32 pid, tid;
 };
 
+struct context_switch_event {
+	struct perf_event_header header;
+	u32 next_prev_pid;
+	u32 next_prev_tid;
+};
+
 union perf_event {
 	struct perf_event_header	header;
 	struct mmap_event		mmap;
@@ -369,6 +375,7 @@ union perf_event {
 	struct auxtrace_error_event	auxtrace_error;
 	struct aux_event		aux;
 	struct itrace_start_event	itrace_start;
+	struct context_switch_event	context_switch;
 };
 
 void perf_event__print_totals(void);
@@ -418,6 +425,10 @@ int perf_event__process_itrace_start(struct perf_tool *tool,
 				     union perf_event *event,
 				     struct perf_sample *sample,
 				     struct machine *machine);
+int perf_event__process_switch(struct perf_tool *tool,
+			       union perf_event *event,
+			       struct perf_sample *sample,
+			       struct machine *machine);
 int perf_event__process_mmap(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_sample *sample,
@@ -480,6 +491,7 @@ size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
 u64 kallsyms__get_function_start(const char *kallsyms_filename,

tools/perf/util/evsel.c

@@ -1127,6 +1127,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	PRINT_ATTRf(mmap2, p_unsigned);
 	PRINT_ATTRf(comm_exec, p_unsigned);
 	PRINT_ATTRf(use_clockid, p_unsigned);
+	PRINT_ATTRf(context_switch, p_unsigned);
 
 	PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
 	PRINT_ATTRf(bp_type, p_unsigned);

tools/perf/util/machine.c

@@ -550,6 +550,14 @@ int machine__process_itrace_start_event(struct machine *machine __maybe_unused,
 	return 0;
 }
 
+int machine__process_switch_event(struct machine *machine __maybe_unused,
+				  union perf_event *event)
+{
+	if (dump_trace)
+		perf_event__fprintf_switch(event, stdout);
+	return 0;
+}
+
 struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 					const char *filename)
 {
@@ -1451,6 +1459,9 @@ int machine__process_event(struct machine *machine, union perf_event *event,
 		ret = machine__process_itrace_start_event(machine, event); break;
 	case PERF_RECORD_LOST_SAMPLES:
 		ret = machine__process_lost_samples_event(machine, event, sample); break;
+	case PERF_RECORD_SWITCH:
+	case PERF_RECORD_SWITCH_CPU_WIDE:
+		ret = machine__process_switch_event(machine, event); break;
 	default:
 		ret = -1;
 		break;

tools/perf/util/machine.h

@@ -87,6 +87,8 @@ int machine__process_aux_event(struct machine *machine,
 			       union perf_event *event);
 int machine__process_itrace_start_event(struct machine *machine,
 					union perf_event *event);
+int machine__process_switch_event(struct machine *machine __maybe_unused,
+				  union perf_event *event);
 int machine__process_mmap_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
 int machine__process_mmap2_event(struct machine *machine, union perf_event *event,

tools/perf/util/session.c

@@ -333,6 +333,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->aux = perf_event__process_aux;
 	if (tool->itrace_start == NULL)
 		tool->itrace_start = perf_event__process_itrace_start;
+	if (tool->context_switch == NULL)
+		tool->context_switch = perf_event__process_switch;
 	if (tool->read == NULL)
 		tool->read = process_event_sample_stub;
 	if (tool->throttle == NULL)
@@ -471,6 +473,19 @@ static void perf_event__itrace_start_swap(union perf_event *event,
 		swap_sample_id_all(event, &event->itrace_start + 1);
 }
 
+static void perf_event__switch_swap(union perf_event *event, bool sample_id_all)
+{
+	if (event->header.type == PERF_RECORD_SWITCH_CPU_WIDE) {
+		event->context_switch.next_prev_pid =
+				bswap_32(event->context_switch.next_prev_pid);
+		event->context_switch.next_prev_tid =
+				bswap_32(event->context_switch.next_prev_tid);
+	}
+
+	if (sample_id_all)
+		swap_sample_id_all(event, &event->context_switch + 1);
+}
+
 static void perf_event__throttle_swap(union perf_event *event,
 				      bool sample_id_all)
 {
@@ -633,6 +648,8 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_AUX]		  = perf_event__aux_swap,
 	[PERF_RECORD_ITRACE_START]	  = perf_event__itrace_start_swap,
 	[PERF_RECORD_LOST_SAMPLES]	  = perf_event__all64_swap,
+	[PERF_RECORD_SWITCH]		  = perf_event__switch_swap,
+	[PERF_RECORD_SWITCH_CPU_WIDE]	  = perf_event__switch_swap,
 	[PERF_RECORD_HEADER_ATTR]	  = perf_event__hdr_attr_swap,
 	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,
 	[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
@@ -1094,6 +1111,9 @@ static int machines__deliver_event(struct machines *machines,
 		return tool->aux(tool, event, sample, machine);
 	case PERF_RECORD_ITRACE_START:
 		return tool->itrace_start(tool, event, sample, machine);
+	case PERF_RECORD_SWITCH:
+	case PERF_RECORD_SWITCH_CPU_WIDE:
+		return tool->context_switch(tool, event, sample, machine);
 	default:
 		++evlist->stats.nr_unknown_events;
 		return -1;

tools/perf/util/tool.h

@@ -46,6 +46,7 @@ struct perf_tool {
 			lost_samples,
 			aux,
 			itrace_start,
+			context_switch,
 			throttle,
 			unthrottle;
 	event_attr_op	attr;