perf tools: Enable on a list of CPUs for hybrid

The 'perf record' and 'perf stat' commands have supported the option
'-C/--cpus' to count or collect only on the list of CPUs provided. This
option needs to be supported for hybrid as well.

For hybrid support, it needs to check that the cpu list are available
on hybrid PMU. One example for AlderLake, cpu0-7 is 'cpu_core', cpu8-11
is 'cpu_atom'.

Before:

  # perf stat -e cpu_core/cycles/ -C11 -- sleep 1

   Performance counter stats for 'CPU(s) 11':

     <not supported>      cpu_core/cycles/

         1.006179431 seconds time elapsed

The 'perf stat' command silently returned "<not supported>" without any
helpful information. It should error out pointing out that that cpu11
was not 'cpu_core'.

After:

  # perf stat -e cpu_core/cycles/ -C11 -- sleep 1
  WARNING: 11 isn't a 'cpu_core', please use a CPU list in the 'cpu_core' range (0-7)
  failed to use cpu list 11

We also need to support the events without pmu prefix specified.

  # perf stat -e cycles -C11 -- sleep 1
  WARNING: 11 isn't a 'cpu_core', please use a CPU list in the 'cpu_core' range (0-7)

   Performance counter stats for 'CPU(s) 11':

           1,067,373      cpu_atom/cycles/

         1.005544738 seconds time elapsed

The perf tool creates two cycles events automatically, cpu_core/cycles/ and
cpu_atom/cycles/. It checks that cpu11 is not 'cpu_core', then shows a warning
for cpu_core/cycles/ and only count the cpu_atom/cycles/.

If part of cpus are 'cpu_core' and part of cpus are 'cpu_atom', for example,

  # perf stat -e cycles -C0,11 -- sleep 1
  WARNING: use 0 in 'cpu_core' for 'cycles', skip other cpus in list.
  WARNING: use 11 in 'cpu_atom' for 'cycles', skip other cpus in list.

   Performance counter stats for 'CPU(s) 0,11':

           1,914,704      cpu_core/cycles/
           2,036,983      cpu_atom/cycles/

         1.005815641 seconds time elapsed

It now automatically selects cpu0 for cpu_core/cycles/, selects cpu11 for
cpu_atom/cycles/, and output with some warnings.

Some more complex examples,

  # perf stat -e cycles,instructions -C0,11 -- sleep 1
  WARNING: use 0 in 'cpu_core' for 'cycles', skip other cpus in list.
  WARNING: use 11 in 'cpu_atom' for 'cycles', skip other cpus in list.
  WARNING: use 0 in 'cpu_core' for 'instructions', skip other cpus in list.
  WARNING: use 11 in 'cpu_atom' for 'instructions', skip other cpus in list.

   Performance counter stats for 'CPU(s) 0,11':

           2,780,387      cpu_core/cycles/
           1,583,432      cpu_atom/cycles/
           3,957,277      cpu_core/instructions/
           1,167,089      cpu_atom/instructions/

         1.006005124 seconds time elapsed

  # perf stat -e cycles,cpu_atom/instructions/ -C0,11 -- sleep 1
  WARNING: use 0 in 'cpu_core' for 'cycles', skip other cpus in list.
  WARNING: use 11 in 'cpu_atom' for 'cycles', skip other cpus in list.
  WARNING: use 11 in 'cpu_atom' for 'cpu_atom/instructions/', skip other cpus in list.

   Performance counter stats for 'CPU(s) 0,11':

           3,290,301      cpu_core/cycles/
           1,953,073      cpu_atom/cycles/
           1,407,869      cpu_atom/instructions/

         1.006260912 seconds time elapsed

Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https //lore.kernel.org/r/20210723063433.7318-4-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

5 files changed, 114 insertions, 0 deletions

diff --git a/tools/perf/util/evlist-hybrid.c b/tools/perf/util/evlist-hybrid.c
index db3f5fbdebe1..7c554234b43d 100644
--- a/tools/perf/util/evlist-hybrid.c
+++ b/tools/perf/util/evlist-hybrid.c
@@ -86,3 +86,76 @@ bool evlist__has_hybrid(struct evlist *evlist)
 
 	return false;
 }
+
+int evlist__fix_hybrid_cpus(struct evlist *evlist, const char *cpu_list)
+{
+	struct perf_cpu_map *cpus;
+	struct evsel *evsel, *tmp;
+	struct perf_pmu *pmu;
+	int ret, unmatched_count = 0, events_nr = 0;
+
+	if (!perf_pmu__has_hybrid() || !cpu_list)
+		return 0;
+
+	cpus = perf_cpu_map__new(cpu_list);
+	if (!cpus)
+		return -1;
+
+	/*
+	 * The evsels are created with hybrid pmu's cpus. But now we
+	 * need to check and adjust the cpus of evsel by cpu_list because
+	 * cpu_list may cause conflicts with cpus of evsel. For example,
+	 * cpus of evsel is cpu0-7, but the cpu_list is cpu6-8, we need
+	 * to adjust the cpus of evsel to cpu6-7. And then propatate maps
+	 * in evlist__create_maps().
+	 */
+	evlist__for_each_entry_safe(evlist, tmp, evsel) {
+		struct perf_cpu_map *matched_cpus, *unmatched_cpus;
+		char buf1[128], buf2[128];
+
+		pmu = perf_pmu__find_hybrid_pmu(evsel->pmu_name);
+		if (!pmu)
+			continue;
+
+		ret = perf_pmu__cpus_match(pmu, cpus, &matched_cpus,
+					   &unmatched_cpus);
+		if (ret)
+			goto out;
+
+		events_nr++;
+
+		if (matched_cpus->nr > 0 && (unmatched_cpus->nr > 0 ||
+		    matched_cpus->nr < cpus->nr ||
+		    matched_cpus->nr < pmu->cpus->nr)) {
+			perf_cpu_map__put(evsel->core.cpus);
+			perf_cpu_map__put(evsel->core.own_cpus);
+			evsel->core.cpus = perf_cpu_map__get(matched_cpus);
+			evsel->core.own_cpus = perf_cpu_map__get(matched_cpus);
+
+			if (unmatched_cpus->nr > 0) {
+				cpu_map__snprint(matched_cpus, buf1, sizeof(buf1));
+				pr_warning("WARNING: use %s in '%s' for '%s', skip other cpus in list.\n",
+					   buf1, pmu->name, evsel->name);
+			}
+		}
+
+		if (matched_cpus->nr == 0) {
+			evlist__remove(evlist, evsel);
+			evsel__delete(evsel);
+
+			cpu_map__snprint(cpus, buf1, sizeof(buf1));
+			cpu_map__snprint(pmu->cpus, buf2, sizeof(buf2));
+			pr_warning("WARNING: %s isn't a '%s', please use a CPU list in the '%s' range (%s)\n",
+				   buf1, pmu->name, pmu->name, buf2);
+			unmatched_count++;
+		}
+
+		perf_cpu_map__put(matched_cpus);
+		perf_cpu_map__put(unmatched_cpus);
+	}
+
+	ret = (unmatched_count == events_nr) ? -1 : 0;
+out:
+	perf_cpu_map__put(cpus);
+	return ret;
+}
diff --git a/tools/perf/util/evlist-hybrid.h b/tools/perf/util/evlist-hybrid.h
index 19f74b4c340a..aacdb1b0f948 100644
--- a/tools/perf/util/evlist-hybrid.h
+++ b/tools/perf/util/evlist-hybrid.h
@@ -10,5 +10,6 @@
 int evlist__add_default_hybrid(struct evlist *evlist, bool precise);
 void evlist__warn_hybrid_group(struct evlist *evlist);
 bool evlist__has_hybrid(struct evlist *evlist);
+int evlist__fix_hybrid_cpus(struct evlist *evlist, const char *cpu_list);
 
 #endif /* __PERF_EVLIST_HYBRID_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 06f8890816c3..5f92319ce258 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -27,6 +27,7 @@
 #include "util/perf_api_probe.h"
 #include "util/evsel_fprintf.h"
 #include "util/evlist-hybrid.h"
+#include "util/pmu.h"
 #include <signal.h>
 #include <unistd.h>
 #include <sched.h>
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 6cdbee8a12e7..5f486ccb6fe6 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1927,3 +1927,38 @@ int perf_pmu__match(char *pattern, char *name, char *tok)
 
 	return 0;
 }
+
+int perf_pmu__cpus_match(struct perf_pmu *pmu, struct perf_cpu_map *cpus,
+			 struct perf_cpu_map **mcpus_ptr,
+			 struct perf_cpu_map **ucpus_ptr)
+{
+	struct perf_cpu_map *pmu_cpus = pmu->cpus;
+	struct perf_cpu_map *matched_cpus, *unmatched_cpus;
+	int matched_nr = 0, unmatched_nr = 0;
+
+	matched_cpus = perf_cpu_map__default_new();
+	if (!matched_cpus)
+		return -1;
+
+	unmatched_cpus = perf_cpu_map__default_new();
+	if (!unmatched_cpus) {
+		perf_cpu_map__put(matched_cpus);
+		return -1;
+	}
+
+	for (int i = 0; i < cpus->nr; i++) {
+		int cpu;
+
+		cpu = perf_cpu_map__idx(pmu_cpus, cpus->map[i]);
+		if (cpu == -1)
+			unmatched_cpus->map[unmatched_nr++] = cpus->map[i];
+		else
+			matched_cpus->map[matched_nr++] = cpus->map[i];
+	}
+
+	unmatched_cpus->nr = unmatched_nr;
+	matched_cpus->nr = matched_nr;
+	*mcpus_ptr = matched_cpus;
+	*ucpus_ptr = unmatched_cpus;
+	return 0;
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 033e8211c025..5133bc456034 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -11,6 +11,7 @@
 #include "pmu-events/pmu-events.h"
 
 struct evsel_config_term;
+struct perf_cpu_map;
 
 enum {
 	PERF_PMU_FORMAT_VALUE_CONFIG,
@@ -136,4 +137,7 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
 bool perf_pmu__has_hybrid(void);
 int perf_pmu__match(char *pattern, char *name, char *tok);
 
+int perf_pmu__cpus_match(struct perf_pmu *pmu, struct perf_cpu_map *cpus,
+			 struct perf_cpu_map **mcpus_ptr,
+			 struct perf_cpu_map **ucpus_ptr);
 #endif /* __PMU_H */