Re: [PATCH v4 03/35] perf cpumap: Add equal function

[Arnaldo Carvalho de Melo <acme@kernel.org>]

Em Fri, May 26, 2023 at 10:32:12PM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Fri, May 26, 2023 at 02:53:38PM -0700, Ian Rogers escreveu:
> > Equality is a useful property to compare after merging and
> > intersecting maps.
> > 
> > Signed-off-by: Ian Rogers <irogers@google.com>
> > Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
> > ---
> >  tools/lib/perf/cpumap.c              | 21 ++++++++++++++++
> >  tools/lib/perf/include/perf/cpumap.h |  2 ++
> >  tools/perf/tests/cpumap.c            | 37 ++++++++++++++++++++++++++++
> >  3 files changed, 60 insertions(+)
> > 
> > diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
> > index d4f3a1a12522..48595a3ad69c 100644
> > --- a/tools/lib/perf/cpumap.c
> > +++ b/tools/lib/perf/cpumap.c
> > @@ -321,6 +321,27 @@ bool perf_cpu_map__has(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
> >  	return perf_cpu_map__idx(cpus, cpu) != -1;
> >  }
> >  
> > +bool perf_cpu_map__equal(const struct perf_cpu_map *lhs, const struct perf_cpu_map *rhs)
> > +{
> > +	int nr;
> > +
> > +	if (lhs == rhs)
> > +		return true;
> > +
> > +	if (!lhs || !rhs)
> > +		return false;
> > +
> > +	nr = perf_cpu_map__nr(lhs);
> > +	if (nr != perf_cpu_map__nr(rhs))
> > +		return false;
> > +
> > +	for (int idx = 0; idx < nr; idx++) {
> > +		if (RC_CHK_ACCESS(lhs)->map[idx].cpu != RC_CHK_ACCESS(rhs)->map[idx].cpu)
> > +			return false;
> 
> Don't we have an accessor to avoid this RC_CHK_ACCESS()-> access?
 
 In the following patch you use it:

+bool perf_cpu_map__has_any_cpu(const struct perf_cpu_map *map)
+{
+       return map && perf_cpu_map__cpu(map, 0).cpu == -1;
+}

But it does extra checks you did already:

struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx)
{
        struct perf_cpu result = {
                .cpu = -1
        };

        if (cpus && idx < RC_CHK_ACCESS(cpus)->nr)
                return RC_CHK_ACCESS(cpus)->map[idx];

        return result;
}

Usually we have:

struct perf_cpu __perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx)
{
	return RC_CHK_ACCESS(cpus)->map[idx];
}

struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx)
{
        struct perf_cpu result = {
                .cpu = -1
        };

        if (cpus && idx < __perf_cpu_map__nr(cpus))
                return __perf_cpu_map__cpu(cpus, idx);

        return result;
}

Then you would have:

bool perf_cpu_map__equal(const struct perf_cpu_map *lhs, const struct perf_cpu_map *rhs)
{
	int nr;

	if (lhs == rhs)
		return true;

	if (!lhs || !rhs)
		return false;

	nr = __perf_cpu_map__nr(lhs);  // no need to check lhs again for NULL
	if (nr != __perf_cpu_map__nr(rhs)) // ditto for rhs
		return false;

	for (int idx = 0; idx < nr; idx++) {
		if (__perf_cpu_map__cpu(lhs, idx)->cpu != __perf_cpu_map__cpu(rhs, idx)->cpu)
			return false;


> > +	}
> > +	return true;
> > +}
> > +
> >  struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map)
> >  {
> >  	struct perf_cpu result = {
> > diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
> > index 0466c4216fbb..d0ae9552f8e2 100644
> > --- a/tools/lib/perf/include/perf/cpumap.h
> > +++ b/tools/lib/perf/include/perf/cpumap.h
> > @@ -28,6 +28,8 @@ LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
> >  LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map);
> >  LIBPERF_API struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map);
> >  LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu);
> > +LIBPERF_API bool perf_cpu_map__equal(const struct perf_cpu_map *lhs,
> > +				     const struct perf_cpu_map *rhs);
> >  
> >  #define perf_cpu_map__for_each_cpu(cpu, idx, cpus)		\
> >  	for ((idx) = 0, (cpu) = perf_cpu_map__cpu(cpus, idx);	\
> > diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
> > index 83805690c209..7730fc2ab40b 100644
> > --- a/tools/perf/tests/cpumap.c
> > +++ b/tools/perf/tests/cpumap.c
> > @@ -211,11 +211,48 @@ static int test__cpu_map_intersect(struct test_suite *test __maybe_unused,
> >  	return ret;
> >  }
> >  
> > +static int test__cpu_map_equal(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
> > +{
> > +	struct perf_cpu_map *any = perf_cpu_map__dummy_new();
> > +	struct perf_cpu_map *one = perf_cpu_map__new("1");
> > +	struct perf_cpu_map *two = perf_cpu_map__new("2");
> > +	struct perf_cpu_map *empty = perf_cpu_map__intersect(one, two);
> > +	struct perf_cpu_map *pair = perf_cpu_map__new("1-2");
> > +	struct perf_cpu_map *tmp;
> > +	struct perf_cpu_map *maps[] = {empty, any, one, two, pair};
> > +
> > +	for (size_t i = 0; i < ARRAY_SIZE(maps); i++) {
> > +		/* Maps equal themself. */
> > +		TEST_ASSERT_VAL("equal", perf_cpu_map__equal(maps[i], maps[i]));
> > +		for (size_t j = 0; j < ARRAY_SIZE(maps); j++) {
> > +			/* Maps dont't equal each other. */
> > +			if (i == j)
> > +				continue;
> > +			TEST_ASSERT_VAL("not equal", !perf_cpu_map__equal(maps[i], maps[j]));
> > +		}
> > +	}
> > +
> > +	/* Maps equal made maps. */
> > +	tmp = perf_cpu_map__merge(perf_cpu_map__get(one), two);
> > +	TEST_ASSERT_VAL("pair", perf_cpu_map__equal(pair, tmp));
> > +	perf_cpu_map__put(tmp);
> > +
> > +	tmp = perf_cpu_map__intersect(pair, one);
> > +	TEST_ASSERT_VAL("one", perf_cpu_map__equal(one, tmp));
> > +	perf_cpu_map__put(tmp);
> > +
> > +	for (size_t i = 0; i < ARRAY_SIZE(maps); i++)
> > +		perf_cpu_map__put(maps[i]);
> > +
> > +	return TEST_OK;
> > +}
> > +
> >  static struct test_case tests__cpu_map[] = {
> >  	TEST_CASE("Synthesize cpu map", cpu_map_synthesize),
> >  	TEST_CASE("Print cpu map", cpu_map_print),
> >  	TEST_CASE("Merge cpu map", cpu_map_merge),
> >  	TEST_CASE("Intersect cpu map", cpu_map_intersect),
> > +	TEST_CASE("Equal cpu map", cpu_map_equal),
> >  	{	.name = NULL, }
> >  };
> >  
> > -- 
> > 2.41.0.rc0.172.g3f132b7071-goog
> > 
> 
> -- 
> 
> - Arnaldo

-- 

- Arnaldo