perf map_groups: Auto sort maps by name, if needed

There are still lots of lookups by name, even if just when loading
vmlinux, till that code is studied to figure out if its possible to do
away with those map lookup by names, provide a way to sort it using
libc's qsort/bsearch.

Doing it at the first lookup defers the sorting a bit, and as the code
stands now, is never done for user maps, just for the kernel ones.

  # perf probe -l
  # perf probe -x ~/bin/perf -L __map_groups__find_by_name
  <__map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0>
        0  static struct map *__map_groups__find_by_name(struct map_groups *mg, const char *name)
        1  {
                  struct map **mapp;

        4         if (mg->maps_by_name == NULL &&
        5             map__groups__sort_by_name_from_rbtree(mg))
        6                 return NULL;

        8         mapp = bsearch(name, mg->maps_by_name, mg->nr_maps, sizeof(*mapp), map__strcmp_name);
        9         if (mapp)
       10                 return *mapp;
       11         return NULL;
       12  }

           struct map *map_groups__find_by_name(struct map_groups *mg, const char *name)
           {

  # perf probe -x ~/bin/perf 'found=__map_groups__find_by_name:10 name:string'
  Added new event:
    probe_perf:found     (on __map_groups__find_by_name:10 in /home/acme/bin/perf with name:string)

  You can now use it in all perf tools, such as:

  	perf record -e probe_perf:found -aR sleep 1

  #
  # perf probe -x ~/bin/perf -L map_groups__find_by_name
  <map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0>
        0  struct map *map_groups__find_by_name(struct map_groups *mg, const char *name)
        1  {
        2         struct maps *maps = &mg->maps;
                  struct map *map;

        5         down_read(&maps->lock);

        7         if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) {
        8                 map = mg->last_search_by_name;
        9                 goto out_unlock;
                  }
                  /*
                   * If we have mg->maps_by_name, then the name isn't in the rbtree,
                   * as mg->maps_by_name mirrors the rbtree when lookups by name are
                   * made.
                   */
       16         map = __map_groups__find_by_name(mg, name);
       17         if (map || mg->maps_by_name != NULL)
       18                 goto out_unlock;

                  /* Fallback to traversing the rbtree... */
       21         maps__for_each_entry(maps, map)
       22                 if (strcmp(map->dso->short_name, name) == 0) {
       23                         mg->last_search_by_name = map;
       24                         goto out_unlock;
                          }

       27         map = NULL;

           out_unlock:
       30         up_read(&maps->lock);
       31         return map;
       32  }

           int dso__load_vmlinux(struct dso *dso, struct map *map,
                                const char *vmlinux, bool vmlinux_allocated)

  # perf probe -x ~/bin/perf 'fallback=map_groups__find_by_name:21 name:string'
  Added new events:
    probe_perf:fallback  (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string)
    probe_perf:fallback_1 (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string)

  You can now use it in all perf tools, such as:

  	perf record -e probe_perf:fallback_1 -aR sleep 1

  #
  # perf probe -l
    probe_perf:fallback  (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string)
    probe_perf:fallback_1 (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string)
    probe_perf:found     (on __map_groups__find_by_name:10@util/symbol.c in /home/acme/bin/perf with name_string)
  #
  # perf stat -e probe_perf:*

Now run 'perf top' in another term and then, after a while, stop 'perf stat':

Furthermore, if we ask for interval printing, we can see that that is done just
at the start of the workload:

  # perf stat -I1000 -e probe_perf:*
  #           time             counts unit events
       1.000319513                  0      probe_perf:found
       1.000319513                  0      probe_perf:fallback_1
       1.000319513                  0      probe_perf:fallback
       2.001868092             23,251      probe_perf:found
       2.001868092                  0      probe_perf:fallback_1
       2.001868092                  0      probe_perf:fallback
       3.002901597                  0      probe_perf:found
       3.002901597                  0      probe_perf:fallback_1
       3.002901597                  0      probe_perf:fallback
       4.003358591                  0      probe_perf:found
       4.003358591                  0      probe_perf:fallback_1
       4.003358591                  0      probe_perf:fallback
  ^C
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-c5lmbyr14x448rcfii7y6t3k@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 59 insertions, 0 deletions

diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index b5ae82a11d4b..db9667aacb88 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1760,6 +1760,56 @@ out:
 	return ret;
 }
 
+static int map__strcmp(const void *a, const void *b)
+{
+	const struct map *ma = *(const struct map **)a, *mb = *(const struct map **)b;
+	return strcmp(ma->dso->short_name, mb->dso->short_name);
+}
+
+static int map__strcmp_name(const void *name, const void *b)
+{
+	const struct map *map = *(const struct map **)b;
+	return strcmp(name, map->dso->short_name);
+}
+
+void __map_groups__sort_by_name(struct map_groups *mg)
+{
+	qsort(mg->maps_by_name, mg->nr_maps, sizeof(struct map *), map__strcmp);
+}
+
+static int map__groups__sort_by_name_from_rbtree(struct map_groups *mg)
+{
+	struct map *map;
+	struct map **maps_by_name = realloc(mg->maps_by_name, mg->nr_maps * sizeof(map));
+	int i = 0;
+
+	if (maps_by_name == NULL)
+		return -1;
+
+	mg->maps_by_name = maps_by_name;
+	mg->nr_maps_allocated = mg->nr_maps;
+
+	maps__for_each_entry(&mg->maps, map)
+		maps_by_name[i++] = map;
+
+	__map_groups__sort_by_name(mg);
+	return 0;
+}
+
+static struct map *__map_groups__find_by_name(struct map_groups *mg, const char *name)
+{
+	struct map **mapp;
+
+	if (mg->maps_by_name == NULL &&
+	    map__groups__sort_by_name_from_rbtree(mg))
+		return NULL;
+
+	mapp = bsearch(name, mg->maps_by_name, mg->nr_maps, sizeof(*mapp), map__strcmp_name);
+	if (mapp)
+		return *mapp;
+	return NULL;
+}
+
 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name)
 {
 	struct maps *maps = &mg->maps;
@@ -1771,7 +1821,16 @@ struct map *map_groups__find_by_name(struct map_groups *mg, const char *name)
 		map = mg->last_search_by_name;
 		goto out_unlock;
 	}
+	/*
+	 * If we have mg->maps_by_name, then the name isn't in the rbtree,
+	 * as mg->maps_by_name mirrors the rbtree when lookups by name are
+	 * made.
+	 */
+	map = __map_groups__find_by_name(mg, name);
+	if (map || mg->maps_by_name != NULL)
+		goto out_unlock;
 
+	/* Fallback to traversing the rbtree... */
 	maps__for_each_entry(maps, map)
 		if (strcmp(map->dso->short_name, name) == 0) {
 			mg->last_search_by_name = map;