Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

  - Enable per-event perf_event_attr.inherit setting by config terms, i.e.
    this becomes possible:

        $ perf record -e cycles/inherit/ -e instructions/no-inherit/

    This affects the default, that can be changed globally using the --no-inherit
    option.

    This fine grained control appeared in the eBPF patchkit, but this added
    flexibility may end up being useful in other scenarios. (Wang Nan)

  - Setup pager when printing usage and help, we have long lists of options,
    better use the pager like we do with normal tooling output, i.e. when needed,
    and including any error messages in the paged output. (Namhyung Kim)

  - Search for more options when passing args to -h, e.g.: (Arnaldo Carvalho de Melo)

    $ perf report -h interface

     Usage: perf report [<options>]

      --gtk    Use the GTK2 interface
      --stdio  Use the stdio interface
      --tui    Use the TUI interface

  - Fix reading separate debuginfo files based on a build-id, problem
    found on a Debian system. (Dima Kogan)

  - Fix endless loop when splitting kallsyms symbols per section for
    handling kcore files, problem found on a s390x system. (Jiri Olsa)

Infrastructure changes:

  - Prep work for the 'perf stat record' work that will allow generating
    perf.data files with counting data in addition to the sampling mode
    we have now (Jiri Olsa)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 55 insertions, 4 deletions

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 91e793a76929..2f438f76cceb 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -100,6 +100,8 @@ static struct target target = {
 	.uid	= UINT_MAX,
 };
 
+typedef int (*aggr_get_id_t)(struct cpu_map *m, int cpu);
+
 static int			run_count			=  1;
 static bool			no_inherit			= false;
 static volatile pid_t		child_pid			= -1;
@@ -119,7 +121,7 @@ static unsigned int		unit_width			= 4; /* strlen("unit") */
 static bool			forever				= false;
 static struct timespec		ref_time;
 static struct cpu_map		*aggr_map;
-static int			(*aggr_get_id)(struct cpu_map *m, int cpu);
+static aggr_get_id_t		aggr_get_id;
 
 static volatile int done = 0;
 
@@ -954,22 +956,63 @@ static int perf_stat__get_core(struct cpu_map *map, int cpu)
 	return cpu_map__get_core(map, cpu, NULL);
 }
 
+static int cpu_map__get_max(struct cpu_map *map)
+{
+	int i, max = -1;
+
+	for (i = 0; i < map->nr; i++) {
+		if (map->map[i] > max)
+			max = map->map[i];
+	}
+
+	return max;
+}
+
+static struct cpu_map *cpus_aggr_map;
+
+static int perf_stat__get_aggr(aggr_get_id_t get_id, struct cpu_map *map, int idx)
+{
+	int cpu;
+
+	if (idx >= map->nr)
+		return -1;
+
+	cpu = map->map[idx];
+
+	if (cpus_aggr_map->map[cpu] == -1)
+		cpus_aggr_map->map[cpu] = get_id(map, idx);
+
+	return cpus_aggr_map->map[cpu];
+}
+
+static int perf_stat__get_socket_cached(struct cpu_map *map, int idx)
+{
+	return perf_stat__get_aggr(perf_stat__get_socket, map, idx);
+}
+
+static int perf_stat__get_core_cached(struct cpu_map *map, int idx)
+{
+	return perf_stat__get_aggr(perf_stat__get_core, map, idx);
+}
+
 static int perf_stat_init_aggr_mode(void)
 {
+	int nr;
+
 	switch (stat_config.aggr_mode) {
 	case AGGR_SOCKET:
 		if (cpu_map__build_socket_map(evsel_list->cpus, &aggr_map)) {
 			perror("cannot build socket map");
 			return -1;
 		}
-		aggr_get_id = perf_stat__get_socket;
+		aggr_get_id = perf_stat__get_socket_cached;
 		break;
 	case AGGR_CORE:
 		if (cpu_map__build_core_map(evsel_list->cpus, &aggr_map)) {
 			perror("cannot build core map");
 			return -1;
 		}
-		aggr_get_id = perf_stat__get_core;
+		aggr_get_id = perf_stat__get_core_cached;
 		break;
 	case AGGR_NONE:
 	case AGGR_GLOBAL:
@@ -978,7 +1021,15 @@ static int perf_stat_init_aggr_mode(void)
 	default:
 		break;
 	}
-	return 0;
+
+	/*
+	 * The evsel_list->cpus is the base we operate on,
+	 * taking the highest cpu number to be the size of
+	 * the aggregation translate cpumap.
+	 */
+	nr = cpu_map__get_max(evsel_list->cpus);
+	cpus_aggr_map = cpu_map__empty_new(nr + 1);
+	return cpus_aggr_map ? 0 : -ENOMEM;
 }
 
 /*