perf arm-spe/cs-etm: Directly iterate CPU maps

Rather than iterate all CPUs and see if they are in CPU maps, directly
iterate the CPU map. Similarly make use of the intersect function
taking care for when "any" CPU is specified. Switch
perf_cpu_map__has_any_cpu_or_is_empty() to more appropriate
alternatives.

Reviewed-by: James Clark <[email protected]>
Signed-off-by: Ian Rogers <[email protected]>
Acked-by: Namhyung Kim <[email protected]>
Cc: Adrian Hunter <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Alexandre Ghiti <[email protected]>
Cc: Andrew Jones <[email protected]>
Cc: André Almeida <[email protected]>
Cc: Athira Rajeev <[email protected]>
Cc: Atish Patra <[email protected]>
Cc: Changbin Du <[email protected]>
Cc: Darren Hart <[email protected]>
Cc: Davidlohr Bueso <[email protected]>
Cc: Huacai Chen <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: John Garry <[email protected]>
Cc: K Prateek Nayak <[email protected]>
Cc: Kajol Jain <[email protected]>
Cc: Kan Liang <[email protected]>
Cc: Leo Yan <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Mike Leach <[email protected]>
Cc: Nick Desaulniers <[email protected]>
Cc: Paolo Bonzini <[email protected]>
Cc: Paran Lee <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Ravi Bangoria <[email protected]>
Cc: Sandipan Das <[email protected]>
Cc: Sean Christopherson <[email protected]>
Cc: Steinar H. Gunderson <[email protected]>
Cc: Suzuki Poulouse <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: Yang Jihong <[email protected]>
Cc: Yang Li <[email protected]>
Cc: Yanteng Si <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

2 files changed, 51 insertions, 67 deletions

diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 77e6663c1703..07be32d99805 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -197,38 +197,37 @@ static int cs_etm_validate_timestamp(struct auxtrace_record *itr,
 static int cs_etm_validate_config(struct auxtrace_record *itr,
 				  struct evsel *evsel)
 {
-	int i, err = -EINVAL;
+	int idx, err = 0;
 	struct perf_cpu_map *event_cpus = evsel->evlist->core.user_requested_cpus;
-	struct perf_cpu_map *online_cpus = perf_cpu_map__new_online_cpus();
-
-	/* Set option of each CPU we have */
-	for (i = 0; i < cpu__max_cpu().cpu; i++) {
-		struct perf_cpu cpu = { .cpu = i, };
+	struct perf_cpu_map *intersect_cpus;
+	struct perf_cpu cpu;
 
-		/*
-		 * In per-cpu case, do the validation for CPUs to work with.
-		 * In per-thread case, the CPU map is empty.  Since the traced
-		 * program can run on any CPUs in this case, thus don't skip
-		 * validation.
-		 */
-		if (!perf_cpu_map__has_any_cpu_or_is_empty(event_cpus) &&
-		    !perf_cpu_map__has(event_cpus, cpu))
-			continue;
+	/*
+	 * Set option of each CPU we have. In per-cpu case, do the validation
+	 * for CPUs to work with. In per-thread case, the CPU map has the "any"
+	 * CPU value. Since the traced program can run on any CPUs in this case,
+	 * thus don't skip validation.
+	 */
+	if (!perf_cpu_map__has_any_cpu(event_cpus)) {
+		struct perf_cpu_map *online_cpus = perf_cpu_map__new_online_cpus();
 
-		if (!perf_cpu_map__has(online_cpus, cpu))
-			continue;
+		intersect_cpus = perf_cpu_map__intersect(event_cpus, online_cpus);
+		perf_cpu_map__put(online_cpus);
+	} else {
+		intersect_cpus = perf_cpu_map__new_online_cpus();
+	}
 
-		err = cs_etm_validate_context_id(itr, evsel, i);
+	perf_cpu_map__for_each_cpu_skip_any(cpu, idx, intersect_cpus) {
+		err = cs_etm_validate_context_id(itr, evsel, cpu.cpu);
 		if (err)
-			goto out;
-		err = cs_etm_validate_timestamp(itr, evsel, i);
+			break;
+
+		err = cs_etm_validate_timestamp(itr, evsel, cpu.cpu);
 		if (err)
-			goto out;
+			break;
 	}
 
-	err = 0;
-out:
-	perf_cpu_map__put(online_cpus);
+	perf_cpu_map__put(intersect_cpus);
 	return err;
 }
 
@@ -435,7 +434,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 	 * Also the case of per-cpu mmaps, need the contextID in order to be notified
 	 * when a context switch happened.
 	 */
-	if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
+	if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus)) {
 		evsel__set_config_if_unset(cs_etm_pmu, cs_etm_evsel,
 					   "timestamp", 1);
 		evsel__set_config_if_unset(cs_etm_pmu, cs_etm_evsel,
@@ -461,7 +460,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 	evsel->core.attr.sample_period = 1;
 
 	/* In per-cpu case, always need the time of mmap events etc */
-	if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus))
+	if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus))
 		evsel__set_sample_bit(evsel, TIME);
 
 	err = cs_etm_validate_config(itr, cs_etm_evsel);
@@ -533,45 +532,31 @@ static size_t
 cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 		      struct evlist *evlist __maybe_unused)
 {
-	int i;
+	int idx;
 	int etmv3 = 0, etmv4 = 0, ete = 0;
 	struct perf_cpu_map *event_cpus = evlist->core.user_requested_cpus;
-	struct perf_cpu_map *online_cpus = perf_cpu_map__new_online_cpus();
-
-	/* cpu map is not empty, we have specific CPUs to work with */
-	if (!perf_cpu_map__has_any_cpu_or_is_empty(event_cpus)) {
-		for (i = 0; i < cpu__max_cpu().cpu; i++) {
-			struct perf_cpu cpu = { .cpu = i, };
+	struct perf_cpu_map *intersect_cpus;
+	struct perf_cpu cpu;
 
-			if (!perf_cpu_map__has(event_cpus, cpu) ||
-			    !perf_cpu_map__has(online_cpus, cpu))
-				continue;
+	if (!perf_cpu_map__has_any_cpu(event_cpus)) {
+		/* cpu map is not "any" CPU , we have specific CPUs to work with */
+		struct perf_cpu_map *online_cpus = perf_cpu_map__new_online_cpus();
 
-			if (cs_etm_is_ete(itr, i))
-				ete++;
-			else if (cs_etm_is_etmv4(itr, i))
-				etmv4++;
-			else
-				etmv3++;
-		}
+		intersect_cpus = perf_cpu_map__intersect(event_cpus, online_cpus);
+		perf_cpu_map__put(online_cpus);
 	} else {
-		/* get configuration for all CPUs in the system */
-		for (i = 0; i < cpu__max_cpu().cpu; i++) {
-			struct perf_cpu cpu = { .cpu = i, };
-
-			if (!perf_cpu_map__has(online_cpus, cpu))
-				continue;
-
-			if (cs_etm_is_ete(itr, i))
-				ete++;
-			else if (cs_etm_is_etmv4(itr, i))
-				etmv4++;
-			else
-				etmv3++;
-		}
+		/* Event can be "any" CPU so count all online CPUs. */
+		intersect_cpus = perf_cpu_map__new_online_cpus();
 	}
-
-	perf_cpu_map__put(online_cpus);
+	perf_cpu_map__for_each_cpu_skip_any(cpu, idx, intersect_cpus) {
+		if (cs_etm_is_ete(itr, cpu.cpu))
+			ete++;
+		else if (cs_etm_is_etmv4(itr, cpu.cpu))
+			etmv4++;
+		else
+			etmv3++;
+	}
+	perf_cpu_map__put(intersect_cpus);
 
 	return (CS_ETM_HEADER_SIZE +
 	       (ete   * CS_ETE_PRIV_SIZE) +
@@ -813,16 +798,15 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 	if (!session->evlist->core.nr_mmaps)
 		return -EINVAL;
 
-	/* If the cpu_map is empty all online CPUs are involved */
-	if (perf_cpu_map__has_any_cpu_or_is_empty(event_cpus)) {
+	/* If the cpu_map has the "any" CPU all online CPUs are involved */
+	if (perf_cpu_map__has_any_cpu(event_cpus)) {
 		cpu_map = online_cpus;
 	} else {
 		/* Make sure all specified CPUs are online */
-		for (i = 0; i < perf_cpu_map__nr(event_cpus); i++) {
-			struct perf_cpu cpu = { .cpu = i, };
+		struct perf_cpu cpu;
 
-			if (perf_cpu_map__has(event_cpus, cpu) &&
-			    !perf_cpu_map__has(online_cpus, cpu))
+		perf_cpu_map__for_each_cpu(cpu, i, event_cpus) {
+			if (!perf_cpu_map__has(online_cpus, cpu))
 				return -EINVAL;
 		}
 
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 51ccbfd3d246..0b52e67edb3b 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -232,7 +232,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	 * In the case of per-cpu mmaps, sample CPU for AUX event;
 	 * also enable the timestamp tracing for samples correlation.
 	 */
-	if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
+	if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus)) {
 		evsel__set_sample_bit(arm_spe_evsel, CPU);
 		evsel__set_config_if_unset(arm_spe_pmu, arm_spe_evsel,
 					   "ts_enable", 1);
@@ -265,7 +265,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	tracking_evsel->core.attr.sample_period = 1;
 
 	/* In per-cpu case, always need the time of mmap events etc */
-	if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
+	if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus)) {
 		evsel__set_sample_bit(tracking_evsel, TIME);
 		evsel__set_sample_bit(tracking_evsel, CPU);