perf evlist: Maintain evlist->all_cpus

Maintain a cpumap in the evlist that is the union of all the cpus of the
events.

This needs a cpumap merge operation, which is added together with tests.

v2:
Add tests for cpu map merge
Fix handling of duplicates
Rename _update to _merge
Factor out sorting.
Fix handling of NULL maps in merge

v3:
Add comments and empty lines to _merge

Committer testing:

  # perf test "Merge cpu map"
  52: Merge cpu map                                         : Ok
  #

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: http://lore.kernel.org/lkml/20191121001522.180827-5-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/lib/cpumap.c b/tools/perf/lib/cpumap.c
index d81656b4635eb2009676cf343dd38fecea1ea774..f93f4e703e4c76e44a0341ca1273646fd53ece7d 100644 (file)
--- a/tools/perf/lib/cpumap.c
+++ b/tools/perf/lib/cpumap.c
@@ -286,3 +286,60 @@ int perf_cpu_map__max(struct perf_cpu_map *map)
 
        return max;
 }
+
+/*
+ * Merge two cpumaps
+ *
+ * orig either gets freed and replaced with a new map, or reused
+ * with no reference count change (similar to "realloc")
+ * other has its reference count increased.
+ */
+
+struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
+                                        struct perf_cpu_map *other)
+{
+       int *tmp_cpus;
+       int tmp_len;
+       int i, j, k;
+       struct perf_cpu_map *merged;
+
+       if (!orig && !other)
+               return NULL;
+       if (!orig) {
+               perf_cpu_map__get(other);
+               return other;
+       }
+       if (!other)
+               return orig;
+       if (orig->nr == other->nr &&
+           !memcmp(orig->map, other->map, orig->nr * sizeof(int)))
+               return orig;
+
+       tmp_len = orig->nr + other->nr;
+       tmp_cpus = malloc(tmp_len * sizeof(int));
+       if (!tmp_cpus)
+               return NULL;
+
+       /* Standard merge algorithm from wikipedia */
+       i = j = k = 0;
+       while (i < orig->nr && j < other->nr) {
+               if (orig->map[i] <= other->map[j]) {
+                       if (orig->map[i] == other->map[j])
+                               j++;
+                       tmp_cpus[k++] = orig->map[i++];
+               } else
+                       tmp_cpus[k++] = other->map[j++];
+       }
+
+       while (i < orig->nr)
+               tmp_cpus[k++] = orig->map[i++];
+
+       while (j < other->nr)
+               tmp_cpus[k++] = other->map[j++];
+       assert(k <= tmp_len);
+
+       merged = cpu_map__trim_new(k, tmp_cpus);
+       free(tmp_cpus);
+       perf_cpu_map__put(orig);
+       return merged;
+}

diff --git a/tools/perf/lib/evlist.c b/tools/perf/lib/evlist.c
index 205ddbb80bc1fab0745406438add906e57671519..ae9e65aa249180cb30391edc802d37df3e238fb8 100644 (file)
--- a/tools/perf/lib/evlist.c
+++ b/tools/perf/lib/evlist.c
@@ -54,6 +54,7 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
 
        perf_thread_map__put(evsel->threads);
        evsel->threads = perf_thread_map__get(evlist->threads);
+       evlist->all_cpus = perf_cpu_map__merge(evlist->all_cpus, evsel->cpus);
 }
 
 static void perf_evlist__propagate_maps(struct perf_evlist *evlist)

diff --git a/tools/perf/lib/include/internal/evlist.h b/tools/perf/lib/include/internal/evlist.h
index a2fbccf1922f2894e8380234c740afe0952dfd20..74dc8c3f0b667f06f6f6c71d53b05b96e7ac11f1 100644 (file)
--- a/tools/perf/lib/include/internal/evlist.h
+++ b/tools/perf/lib/include/internal/evlist.h
@@ -18,6 +18,7 @@ struct perf_evlist {
        int                      nr_entries;
        bool                     has_user_cpus;
        struct perf_cpu_map     *cpus;
+       struct perf_cpu_map     *all_cpus;
        struct perf_thread_map  *threads;
        int                      nr_mmaps;
        size_t                   mmap_len;

diff --git a/tools/perf/lib/include/perf/cpumap.h b/tools/perf/lib/include/perf/cpumap.h
index ac9aa497f84ab3151799e1bc4689b5e0b0fd1dc4..6a17ad730cbc112b7e3e5938a4cc47b688d09440 100644 (file)
--- a/tools/perf/lib/include/perf/cpumap.h
+++ b/tools/perf/lib/include/perf/cpumap.h
@@ -12,6 +12,8 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__read(FILE *file);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
+LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
+                                                    struct perf_cpu_map *other);
 LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
 LIBPERF_API int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
 LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);

diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 7115aa32a51ee4b0ee4d2a270eeae5420fe277be..82d19a8fcac7c0585f28bf04b92691f462430913 100644 (file)
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -259,6 +259,11 @@ static struct test generic_tests[] = {
                .desc = "Print cpu map",
                .func = test__cpu_map_print,
        },
+       {
+               .desc = "Merge cpu map",
+               .func = test__cpu_map_merge,
+       },
+
        {
                .desc = "Probe SDT events",
                .func = test__sdt_event,

diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index 8a0d236202b05ba179199b2709080b949c5d52d3..4ac56741ac5fe6375fb4e0a1171b7bbd5a7f7c42 100644 (file)
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -120,3 +120,19 @@ int test__cpu_map_print(struct test *test __maybe_unused, int subtest __maybe_un
        TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1-10,12-20,22-30,32-40"));
        return 0;
 }
+
+int test__cpu_map_merge(struct test *test __maybe_unused, int subtest __maybe_unused)
+{
+       struct perf_cpu_map *a = perf_cpu_map__new("4,2,1");
+       struct perf_cpu_map *b = perf_cpu_map__new("4,5,7");
+       struct perf_cpu_map *c = perf_cpu_map__merge(a, b);
+       char buf[100];
+
+       TEST_ASSERT_VAL("failed to merge map: bad nr", c->nr == 5);
+       cpu_map__snprint(c, buf, sizeof(buf));
+       TEST_ASSERT_VAL("failed to merge map: bad result", !strcmp(buf, "1-2,4-5,7"));
+       perf_cpu_map__put(a);
+       perf_cpu_map__put(b);
+       perf_cpu_map__put(c);
+       return 0;
+}

diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 25aea387e2bf0ed13afde728df4ad906556557a8..4f9ae6af78ecb234eed77a43b3b13e36928eaf3a 100644 (file)
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -98,6 +98,7 @@ int test__event_update(struct test *test, int subtest);
 int test__event_times(struct test *test, int subtest);
 int test__backward_ring_buffer(struct test *test, int subtest);
 int test__cpu_map_print(struct test *test, int subtest);
+int test__cpu_map_merge(struct test *test, int subtest);
 int test__sdt_event(struct test *test, int subtest);
 int test__is_printable_array(struct test *test, int subtest);
 int test__bitmap_print(struct test *test, int subtest);