perf stat: Support per-die aggregation

It is useful to aggregate counts per die. E.g. Uncore becomes die-scope
on Xeon Cascade Lake-AP.

Introduce a new option "--per-die" to support per-die aggregation.

The global id for each core has been changed to socket + die id + core
id. The global id for each die is socket + die id.

Add die information for per-core aggregation. The output of per-core
aggregation will be changed from "S0-C0" to "S0-D0-C0". Any scripts
which rely on the output format of per-core aggregation probably be
broken.

For 'perf stat record/report', there is no die information when
processing the old perf.data. The per-die result will be the same as
per-socket.

Committer notes:

Renamed 'die' variable to 'die_id' to fix the build in some systems:

    CC       /tmp/build/perf/builtin-script.o
  cc1: warnings being treated as errors
  builtin-stat.c: In function 'perf_env__get_die':
  builtin-stat.c:963: error: declaration of 'die' shadows a global declaration
  util/util.h:19: error: shadowed declaration is here
  mv: cannot stat `/tmp/build/perf/.builtin-stat.o.tmp': No such file or directory

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lkml.kernel.org/n/tip-bsnhx7vgsuu6ei307mw60mbj@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 25 insertions, 4 deletions

diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 4c53bae5644b..a6b9de3e83fc 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -69,8 +69,9 @@ static void aggr_printout(struct perf_stat_config *config,
 {
 	switch (config->aggr_mode) {
 	case AGGR_CORE:
-		fprintf(config->output, "S%d-C%*d%s%*d%s",
+		fprintf(config->output, "S%d-D%d-C%*d%s%*d%s",
 			cpu_map__id_to_socket(id),
+			cpu_map__id_to_die(id),
 			config->csv_output ? 0 : -8,
 			cpu_map__id_to_cpu(id),
 			config->csv_sep,
@@ -78,6 +79,16 @@ static void aggr_printout(struct perf_stat_config *config,
 			nr,
 			config->csv_sep);
 		break;
+	case AGGR_DIE:
+		fprintf(config->output, "S%d-D%*d%s%*d%s",
+			cpu_map__id_to_socket(id << 16),
+			config->csv_output ? 0 : -8,
+			cpu_map__id_to_die(id << 16),
+			config->csv_sep,
+			config->csv_output ? 0 : 4,
+			nr,
+			config->csv_sep);
+		break;
 	case AGGR_SOCKET:
 		fprintf(config->output, "S%*d%s%*d%s",
 			config->csv_output ? 0 : -5,
@@ -89,8 +100,9 @@ static void aggr_printout(struct perf_stat_config *config,
 			break;
 	case AGGR_NONE:
 		if (evsel->percore) {
-			fprintf(config->output, "S%d-C%*d%s",
+			fprintf(config->output, "S%d-D%d-C%*d%s",
 				cpu_map__id_to_socket(id),
+				cpu_map__id_to_die(id),
 				config->csv_output ? 0 : -5,
 				cpu_map__id_to_cpu(id), config->csv_sep);
 		} else {
@@ -407,6 +419,7 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 			[AGGR_THREAD] = 1,
 			[AGGR_NONE] = 1,
 			[AGGR_SOCKET] = 2,
+			[AGGR_DIE] = 2,
 			[AGGR_CORE] = 2,
 		};
 
@@ -879,7 +892,8 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
 }
 
 static int aggr_header_lens[] = {
-	[AGGR_CORE] = 18,
+	[AGGR_CORE] = 24,
+	[AGGR_DIE] = 18,
 	[AGGR_SOCKET] = 12,
 	[AGGR_NONE] = 6,
 	[AGGR_THREAD] = 24,
@@ -888,6 +902,7 @@ static int aggr_header_lens[] = {
 
 static const char *aggr_header_csv[] = {
 	[AGGR_CORE] 	= 	"core,cpus,",
+	[AGGR_DIE] 	= 	"die,cpus",
 	[AGGR_SOCKET] 	= 	"socket,cpus",
 	[AGGR_NONE] 	= 	"cpu,",
 	[AGGR_THREAD] 	= 	"comm-pid,",
@@ -954,8 +969,13 @@ static void print_interval(struct perf_stat_config *config,
 			if (!metric_only)
 				fprintf(output, "             counts %*s events\n", unit_width, "unit");
 			break;
+		case AGGR_DIE:
+			fprintf(output, "#           time die          cpus");
+			if (!metric_only)
+				fprintf(output, "             counts %*s events\n", unit_width, "unit");
+			break;
 		case AGGR_CORE:
-			fprintf(output, "#           time core         cpus");
+			fprintf(output, "#           time core            cpus");
 			if (!metric_only)
 				fprintf(output, "             counts %*s events\n", unit_width, "unit");
 			break;
@@ -1165,6 +1185,7 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 
 	switch (config->aggr_mode) {
 	case AGGR_CORE:
+	case AGGR_DIE:
 	case AGGR_SOCKET:
 		print_aggr(config, evlist, prefix);
 		break;