perf evlist: Rename cpus to user_requested_cpus

evlist contains cpus and all_cpus. all_cpus is the union of the cpu maps
of all evsels.

For non-task targets, cpus is set to be cpus requested from the command
line, defaulting to all online cpus if no cpus are specified.

For an uncore event, all_cpus may be just CPU 0 or every online CPU.

This causes all_cpus to have fewer values than the cpus variable which
is confusing given the 'all' in the name.

To try to make the behavior clearer, rename cpus to user_requested_cpus
and add comments on the two struct variables.

Signed-off-by: Ian Rogers <[e-mail]>
Cc: Adrian Hunter <[e-mail]>
Cc: Alexander Antonov <[e-mail]>
Cc: Alexander Shishkin <[e-mail]>
Cc: Alexei Starovoitov <[e-mail]>
Cc: Alexey Bayduraev <[e-mail]>
Cc: Andi Kleen <[e-mail]>
Cc: Andrii Nakryiko <[e-mail]>
Cc: Daniel Borkmann <[e-mail]>
Cc: German Gomez <[e-mail]>
Cc: James Clark <[e-mail]>
Cc: Jiri Olsa <[e-mail]>
Cc: John Fastabend <[e-mail]>
Cc: John Garry <[e-mail]>
Cc: KP Singh <[e-mail]>
Cc: Kajol Jain <[e-mail]>
Cc: Leo Yan <[e-mail]>
Cc: Mark Rutland <[e-mail]>
Cc: Martin KaFai Lau <[e-mail]>
Cc: Mathieu Poirier <[e-mail]>
Cc: Mike Leach <[e-mail]>
Cc: Namhyung Kim <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Riccardo Mancini <[e-mail]>
Cc: Song Liu <[e-mail]>
Cc: Stephane Eranian <[e-mail]>
Cc: Suzuki Poulouse <[e-mail]>
Cc: Will Deacon <[e-mail]>
Cc: Yonghong Song <[e-mail]>
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Link: http://lore.kernel.org/lkml/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/lib/perf/evlist.c

···
 	 */
 	if (!evsel->own_cpus || evlist->has_user_cpus) {
 		perf_cpu_map__put(evsel->cpus);
-		evsel->cpus = perf_cpu_map__get(evlist->cpus);
-	} else if (!evsel->system_wide && perf_cpu_map__empty(evlist->cpus)) {
+		evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus);
+	} else if (!evsel->system_wide && perf_cpu_map__empty(evlist->user_requested_cpus)) {
 		perf_cpu_map__put(evsel->cpus);
-		evsel->cpus = perf_cpu_map__get(evlist->cpus);
+		evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus);
 	} else if (evsel->cpus != evsel->own_cpus) {
 		perf_cpu_map__put(evsel->cpus);
 		evsel->cpus = perf_cpu_map__get(evsel->own_cpus);
···
 
 void perf_evlist__exit(struct perf_evlist *evlist)
 {
-	perf_cpu_map__put(evlist->cpus);
+	perf_cpu_map__put(evlist->user_requested_cpus);
 	perf_cpu_map__put(evlist->all_cpus);
 	perf_thread_map__put(evlist->threads);
-	evlist->cpus = NULL;
+	evlist->user_requested_cpus = NULL;
 	evlist->all_cpus = NULL;
 	evlist->threads = NULL;
 	fdarray__exit(&evlist->pollfd);
···
 	 * original reference count of 1.  If that is not the case it is up to
 	 * the caller to increase the reference count.
 	 */
-	if (cpus != evlist->cpus) {
-		perf_cpu_map__put(evlist->cpus);
-		evlist->cpus = perf_cpu_map__get(cpus);
+	if (cpus != evlist->user_requested_cpus) {
+		perf_cpu_map__put(evlist->user_requested_cpus);
+		evlist->user_requested_cpus = perf_cpu_map__get(cpus);
 	}
 
 	if (threads != evlist->threads) {
···
 
 int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 {
-	int nr_cpus = perf_cpu_map__nr(evlist->cpus);
+	int nr_cpus = perf_cpu_map__nr(evlist->user_requested_cpus);
 	int nr_threads = perf_thread_map__nr(evlist->threads);
 	int nfds = 0;
 	struct perf_evsel *evsel;
···
 	       int idx, struct perf_mmap_param *mp, int cpu_idx,
 	       int thread, int *_output, int *_output_overwrite)
 {
-	struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->cpus, cpu_idx);
+	struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->user_requested_cpus, cpu_idx);
 	struct perf_evsel *evsel;
 	int revent;
 
···
 	     struct perf_mmap_param *mp)
 {
 	int nr_threads = perf_thread_map__nr(evlist->threads);
-	int nr_cpus    = perf_cpu_map__nr(evlist->cpus);
+	int nr_cpus    = perf_cpu_map__nr(evlist->user_requested_cpus);
 	int cpu, thread;
 
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
···
 {
 	int nr_mmaps;
 
-	nr_mmaps = perf_cpu_map__nr(evlist->cpus);
-	if (perf_cpu_map__empty(evlist->cpus))
+	nr_mmaps = perf_cpu_map__nr(evlist->user_requested_cpus);
+	if (perf_cpu_map__empty(evlist->user_requested_cpus))
 		nr_mmaps = perf_thread_map__nr(evlist->threads);
 
 	return nr_mmaps;
···
 			  struct perf_mmap_param *mp)
 {
 	struct perf_evsel *evsel;
-	const struct perf_cpu_map *cpus = evlist->cpus;
+	const struct perf_cpu_map *cpus = evlist->user_requested_cpus;
 	const struct perf_thread_map *threads = evlist->threads;
 
 	if (!ops || !ops->get || !ops->mmap)

tools/lib/perf/include/internal/evlist.h

···
 	int			 nr_entries;
 	int			 nr_groups;
 	bool			 has_user_cpus;
-	struct perf_cpu_map	*cpus;
+	/**
+	 * The cpus passed from the command line or all online CPUs by
+	 * default.
+	 */
+	struct perf_cpu_map	*user_requested_cpus;
+	/** The union of all evsel cpu maps. */
 	struct perf_cpu_map	*all_cpus;
 	struct perf_thread_map	*threads;
 	int			 nr_mmaps;

tools/perf/arch/arm/util/cs-etm.c

···
 			     struct evsel *evsel, u32 option)
 {
 	int i, err = -EINVAL;
-	struct perf_cpu_map *event_cpus = evsel->evlist->core.cpus;
+	struct perf_cpu_map *event_cpus = evsel->evlist->core.user_requested_cpus;
 	struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
 
 	/* Set option of each CPU we have */
···
 				container_of(itr, struct cs_etm_recording, itr);
 	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
 	struct evsel *evsel, *cs_etm_evsel = NULL;
-	struct perf_cpu_map *cpus = evlist->core.cpus;
+	struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
 	bool privileged = perf_event_paranoid_check(-1);
 	int err = 0;
 
···
 {
 	int i;
 	int etmv3 = 0, etmv4 = 0, ete = 0;
-	struct perf_cpu_map *event_cpus = evlist->core.cpus;
+	struct perf_cpu_map *event_cpus = evlist->core.user_requested_cpus;
 	struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
 
 	/* cpu map is not empty, we have specific CPUs to work with */
···
 	u32 offset;
 	u64 nr_cpu, type;
 	struct perf_cpu_map *cpu_map;
-	struct perf_cpu_map *event_cpus = session->evlist->core.cpus;
+	struct perf_cpu_map *event_cpus = session->evlist->core.user_requested_cpus;
 	struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
 	struct cs_etm_recording *ptr =
 			container_of(itr, struct cs_etm_recording, itr);

tools/perf/arch/arm64/util/arm-spe.c

···
 			container_of(itr, struct arm_spe_recording, itr);
 	struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu;
 	struct evsel *evsel, *arm_spe_evsel = NULL;
-	struct perf_cpu_map *cpus = evlist->core.cpus;
+	struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
 	bool privileged = perf_event_paranoid_check(-1);
 	struct evsel *tracking_evsel;
 	int err;

tools/perf/arch/x86/util/intel-bts.c

···
 			container_of(itr, struct intel_bts_recording, itr);
 	struct perf_pmu *intel_bts_pmu = btsr->intel_bts_pmu;
 	struct evsel *evsel, *intel_bts_evsel = NULL;
-	const struct perf_cpu_map *cpus = evlist->core.cpus;
+	const struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
 	bool privileged = perf_event_paranoid_check(-1);
 
 	if (opts->auxtrace_sample_mode) {

tools/perf/arch/x86/util/intel-pt.c

···
 			ui__warning("Intel Processor Trace: TSC not available\n");
 	}
 
-	per_cpu_mmaps = !perf_cpu_map__empty(session->evlist->core.cpus);
+	per_cpu_mmaps = !perf_cpu_map__empty(session->evlist->core.user_requested_cpus);
 
 	auxtrace_info->type = PERF_AUXTRACE_INTEL_PT;
 	auxtrace_info->priv[INTEL_PT_PMU_TYPE] = intel_pt_pmu->type;
···
 	struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu;
 	bool have_timing_info, need_immediate = false;
 	struct evsel *evsel, *intel_pt_evsel = NULL;
-	const struct perf_cpu_map *cpus = evlist->core.cpus;
+	const struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
 	bool privileged = perf_event_paranoid_check(-1);
 	u64 tsc_bit;
 	int err;

tools/perf/bench/evlist-open-close.c

···
 
 	init_stats(&time_stats);
 
-	printf("  Number of cpus:\t%d\n", perf_cpu_map__nr(evlist->core.cpus));
+	printf("  Number of cpus:\t%d\n", perf_cpu_map__nr(evlist->core.user_requested_cpus));
 	printf("  Number of threads:\t%d\n", evlist->core.threads->nr);
 	printf("  Number of events:\t%d (%d fds)\n",
 		evlist->core.nr_entries, evlist__count_evsel_fds(evlist));

tools/perf/builtin-ftrace.c

···
 
 static int set_tracing_cpu(struct perf_ftrace *ftrace)
 {
-	struct perf_cpu_map *cpumap = ftrace->evlist->core.cpus;
+	struct perf_cpu_map *cpumap = ftrace->evlist->core.user_requested_cpus;
 
 	if (!target__has_cpu(&ftrace->target))
 		return 0;

tools/perf/builtin-record.c

···
 	int m, tm, nr_mmaps = evlist->core.nr_mmaps;
 	struct mmap *mmap = evlist->mmap;
 	struct mmap *overwrite_mmap = evlist->overwrite_mmap;
-	struct perf_cpu_map *cpus = evlist->core.cpus;
+	struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
 
 	thread_data->nr_mmaps = bitmap_weight(thread_data->mask->maps.bits,
 					      thread_data->mask->maps.nbits);
···
 		return err;
 	}
 
-	err = perf_event__synthesize_cpu_map(&rec->tool, rec->evlist->core.cpus,
+	err = perf_event__synthesize_cpu_map(&rec->tool, rec->evlist->core.user_requested_cpus,
 					     process_synthesized_event, NULL);
 	if (err < 0) {
 		pr_err("Couldn't synthesize cpu map.\n");
···
 static int record__init_thread_masks(struct record *rec)
 {
 	int ret = 0;
-	struct perf_cpu_map *cpus = rec->evlist->core.cpus;
+	struct perf_cpu_map *cpus = rec->evlist->core.user_requested_cpus;
 
 	if (!record__threads_enabled(rec))
 		return record__init_thread_default_masks(rec, cpus);

tools/perf/builtin-stat.c

···
 	if (group)
 		evlist__set_leader(evsel_list);
 
-	if (!cpu_map__is_dummy(evsel_list->core.cpus)) {
+	if (!cpu_map__is_dummy(evsel_list->core.user_requested_cpus)) {
 		if (affinity__setup(&saved_affinity) < 0)
 			return -1;
 		affinity = &saved_affinity;
···
 	aggr_cpu_id_get_t get_id = aggr_mode__get_aggr(stat_config.aggr_mode);
 
 	if (get_id) {
-		stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.cpus,
+		stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.user_requested_cpus,
 							 get_id, /*data=*/NULL);
 		if (!stat_config.aggr_map) {
 			pr_err("cannot build %s map", aggr_mode__string[stat_config.aggr_mode]);
···
 	 * taking the highest cpu number to be the size of
 	 * the aggregation translate cpumap.
 	 */
-	if (evsel_list->core.cpus)
-		nr = perf_cpu_map__max(evsel_list->core.cpus).cpu;
+	if (evsel_list->core.user_requested_cpus)
+		nr = perf_cpu_map__max(evsel_list->core.user_requested_cpus).cpu;
 	else
 		nr = 0;
 	stat_config.cpus_aggr_map = cpu_aggr_map__empty_new(nr + 1);
···
 	if (!get_id)
 		return 0;
 
-	stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.cpus, get_id, env);
+	stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.user_requested_cpus, get_id, env);
 	if (!stat_config.aggr_map) {
 		pr_err("cannot build %s map", aggr_mode__string[stat_config.aggr_mode]);
 		return -1;

tools/perf/builtin-top.c

···
 
 	evlist__for_each_entry(evlist, counter) {
 try_again:
-		if (evsel__open(counter, top->evlist->core.cpus,
+		if (evsel__open(counter, top->evlist->core.user_requested_cpus,
 				     top->evlist->core.threads) < 0) {
 
 			/*

tools/perf/util/auxtrace.c

···
 	mp->idx = idx;
 
 	if (per_cpu) {
-		mp->cpu = perf_cpu_map__cpu(evlist->core.cpus, idx);
+		mp->cpu = perf_cpu_map__cpu(evlist->core.user_requested_cpus, idx);
 		if (evlist->core.threads)
 			mp->tid = perf_thread_map__pid(evlist->core.threads, 0);
 		else

tools/perf/util/bpf_ftrace.c

···
 
 	/* don't need to set cpu filter for system-wide mode */
 	if (ftrace->target.cpu_list) {
-		ncpus = perf_cpu_map__nr(ftrace->evlist->core.cpus);
+		ncpus = perf_cpu_map__nr(ftrace->evlist->core.user_requested_cpus);
 		bpf_map__set_max_entries(skel->maps.cpu_filter, ncpus);
 	}
 
···
 		fd = bpf_map__fd(skel->maps.cpu_filter);
 
 		for (i = 0; i < ncpus; i++) {
-			cpu = perf_cpu_map__cpu(ftrace->evlist->core.cpus, i).cpu;
+			cpu = perf_cpu_map__cpu(ftrace->evlist->core.user_requested_cpus, i).cpu;
 			bpf_map_update_elem(fd, &cpu, &val, BPF_ANY);
 		}
 	}

tools/perf/util/evlist.c

···
 	bool has_imm = false;
 
 	// See explanation in evlist__close()
-	if (!cpu_map__is_dummy(evlist->core.cpus)) {
+	if (!cpu_map__is_dummy(evlist->core.user_requested_cpus)) {
 		if (affinity__setup(&saved_affinity) < 0)
 			return;
 		affinity = &saved_affinity;
···
 	struct affinity saved_affinity, *affinity = NULL;
 
 	// See explanation in evlist__close()
-	if (!cpu_map__is_dummy(evlist->core.cpus)) {
+	if (!cpu_map__is_dummy(evlist->core.user_requested_cpus)) {
 		if (affinity__setup(&saved_affinity) < 0)
 			return;
 		affinity = &saved_affinity;
···
 static int evlist__enable_event_thread(struct evlist *evlist, struct evsel *evsel, int thread)
 {
 	int cpu;
-	int nr_cpus = perf_cpu_map__nr(evlist->core.cpus);
+	int nr_cpus = perf_cpu_map__nr(evlist->core.user_requested_cpus);
 
 	if (!evsel->core.fd)
 		return -EINVAL;
···
 
 int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, int idx)
 {
-	bool per_cpu_mmaps = !perf_cpu_map__empty(evlist->core.cpus);
+	bool per_cpu_mmaps = !perf_cpu_map__empty(evlist->core.user_requested_cpus);
 
 	if (per_cpu_mmaps)
 		return evlist__enable_event_cpu(evlist, evsel, idx);
···
 	struct affinity affinity;
 
 	/*
-	 * With perf record core.cpus is usually NULL.
+	 * With perf record core.user_requested_cpus is usually NULL.
 	 * Use the old method to handle this for now.
 	 */
-	if (!evlist->core.cpus || cpu_map__is_dummy(evlist->core.cpus)) {
+	if (!evlist->core.user_requested_cpus ||
+	    cpu_map__is_dummy(evlist->core.user_requested_cpus)) {
 		evlist__for_each_entry_reverse(evlist, evsel)
 			evsel__close(evsel);
 		return;
···
 	 * Default: one fd per CPU, all threads, aka systemwide
 	 * as sys_perf_event_open(cpu = -1, thread = -1) is EINVAL
 	 */
-	if (evlist->core.threads == NULL && evlist->core.cpus == NULL) {
+	if (evlist->core.threads == NULL && evlist->core.user_requested_cpus == NULL) {
 		err = evlist__create_syswide_maps(evlist);
 		if (err < 0)
 			goto out_err;

tools/perf/util/record.c

···
 	if (opts->group)
 		evlist__set_leader(evlist);
 
-	if (perf_cpu_map__cpu(evlist->core.cpus, 0).cpu < 0)
+	if (perf_cpu_map__cpu(evlist->core.user_requested_cpus, 0).cpu < 0)
 		opts->no_inherit = true;
 
 	use_comm_exec = perf_can_comm_exec();
···
 
 	evsel = evlist__last(temp_evlist);
 
-	if (!evlist || perf_cpu_map__empty(evlist->core.cpus)) {
+	if (!evlist || perf_cpu_map__empty(evlist->core.user_requested_cpus)) {
 		struct perf_cpu_map *cpus = perf_cpu_map__new(NULL);
 
 		if (cpus)
···
 
 		perf_cpu_map__put(cpus);
 	} else {
-		cpu = perf_cpu_map__cpu(evlist->core.cpus, 0);
+		cpu = perf_cpu_map__cpu(evlist->core.user_requested_cpus, 0);
 	}
 
 	while (1) {

tools/perf/util/sideband_evlist.c

···
 	}
 
 	evlist__for_each_entry(evlist, counter) {
-		if (evsel__open(counter, evlist->core.cpus, evlist->core.threads) < 0)
+		if (evsel__open(counter, evlist->core.user_requested_cpus,
+				evlist->core.threads) < 0)
 			goto out_delete_evlist;
 	}
 

tools/perf/util/stat-display.c

···
 	int all_idx;
 	struct perf_cpu cpu;
 
-	perf_cpu_map__for_each_cpu(cpu, all_idx, evlist->core.cpus) {
+	perf_cpu_map__for_each_cpu(cpu, all_idx, evlist->core.user_requested_cpus) {
 		struct evsel *counter;
 		bool first = true;
 

tools/perf/util/synthetic-events.c

···
 		return err;
 	}
 
-	err = perf_event__synthesize_cpu_map(tool, evlist->core.cpus, process, NULL);
+	err = perf_event__synthesize_cpu_map(tool, evlist->core.user_requested_cpus, process, NULL);
 	if (err < 0) {
 		pr_err("Couldn't synthesize thread map.\n");
 		return err;

tools/perf/util/top.c

···
 
 	if (target->cpu_list)
 		ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)",
-				perf_cpu_map__nr(top->evlist->core.cpus) > 1 ? "s" : "",
+				perf_cpu_map__nr(top->evlist->core.user_requested_cpus) > 1
+				? "s" : "",
 				target->cpu_list);
 	else {
 		if (target->tid)
 			ret += SNPRINTF(bf + ret, size - ret, ")");
 		else
 			ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)",
-					perf_cpu_map__nr(top->evlist->core.cpus),
-					perf_cpu_map__nr(top->evlist->core.cpus) > 1 ? "s" : "");
+					perf_cpu_map__nr(top->evlist->core.user_requested_cpus),
+					perf_cpu_map__nr(top->evlist->core.user_requested_cpus) > 1
+					? "s" : "");
 	}
 
 	perf_top__reset_sample_counters(top);