}
}
-struct perf_counts *perf_counts__new(int ncpus, int nthreads)
-{
- struct perf_counts *counts = zalloc(sizeof(*counts));
-
- if (counts) {
- struct xyarray *values;
-
- values = xyarray__new(ncpus, nthreads, sizeof(struct perf_counts_values));
- if (!values) {
- free(counts);
- return NULL;
- }
-
- counts->values = values;
- }
-
- return counts;
-}
-
-void perf_counts__delete(struct perf_counts *counts)
-{
- if (counts) {
- xyarray__delete(counts->values);
- free(counts);
- }
-}
-
-static void perf_counts__reset(struct perf_counts *counts)
-{
- xyarray__reset(counts->values);
-}
-
-void perf_evsel__reset_counts(struct perf_evsel *evsel)
-{
- perf_counts__reset(evsel->counts);
-}
-
-int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads)
-{
- evsel->counts = perf_counts__new(ncpus, nthreads);
- return evsel->counts != NULL ? 0 : -ENOMEM;
-}
-
-void perf_evsel__free_counts(struct perf_evsel *evsel)
-{
- perf_counts__delete(evsel->counts);
- evsel->counts = NULL;
-}
-
void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
{
int i;
perf_evsel__reset_counts(evsel);
}
}
+
+static void zero_per_pkg(struct perf_evsel *counter)
+{
+ if (counter->per_pkg_mask)
+ memset(counter->per_pkg_mask, 0, MAX_NR_CPUS);
+}
+
+static int check_per_pkg(struct perf_evsel *counter,
+ struct perf_counts_values *vals, int cpu, bool *skip)
+{
+ unsigned long *mask = counter->per_pkg_mask;
+ struct cpu_map *cpus = perf_evsel__cpus(counter);
+ int s;
+
+ *skip = false;
+
+ if (!counter->per_pkg)
+ return 0;
+
+ if (cpu_map__empty(cpus))
+ return 0;
+
+ if (!mask) {
+ mask = zalloc(MAX_NR_CPUS);
+ if (!mask)
+ return -ENOMEM;
+
+ counter->per_pkg_mask = mask;
+ }
+
+ /*
+ * we do not consider an event that has not run as a good
+ * instance to mark a package as used (skip=1). Otherwise
+ * we may run into a situation where the first CPU in a package
+ * is not running anything, yet the second is, and this function
+ * would mark the package as used after the first CPU and would
+ * not read the values from the second CPU.
+ */
+ if (!(vals->run && vals->ena))
+ return 0;
+
+ s = cpu_map__get_socket(cpus, cpu);
+ if (s < 0)
+ return -1;
+
+ *skip = test_and_set_bit(s, mask) == 1;
+ return 0;
+}
+
+static int
+process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel,
+ int cpu, int thread,
+ struct perf_counts_values *count)
+{
+ struct perf_counts_values *aggr = &evsel->counts->aggr;
+ static struct perf_counts_values zero;
+ bool skip = false;
+
+ if (check_per_pkg(evsel, count, cpu, &skip)) {
+ pr_err("failed to read per-pkg counter\n");
+ return -1;
+ }
+
+ if (skip)
+ count = &zero;
+
+ switch (config->aggr_mode) {
+ case AGGR_THREAD:
+ case AGGR_CORE:
+ case AGGR_SOCKET:
+ case AGGR_NONE:
+ if (!evsel->snapshot)
+ perf_evsel__compute_deltas(evsel, cpu, thread, count);
+ perf_counts_values__scale(count, config->scale, NULL);
+ if (config->aggr_mode == AGGR_NONE)
+ perf_stat__update_shadow_stats(evsel, count->values, cpu);
+ break;
+ case AGGR_GLOBAL:
+ aggr->val += count->val;
+ if (config->scale) {
+ aggr->ena += count->ena;
+ aggr->run += count->run;
+ }
+ default:
+ break;
+ }
+
+ return 0;
+}
+
+static int process_counter_maps(struct perf_stat_config *config,
+ struct perf_evsel *counter)
+{
+ int nthreads = thread_map__nr(counter->threads);
+ int ncpus = perf_evsel__nr_cpus(counter);
+ int cpu, thread;
+
+ if (counter->system_wide)
+ nthreads = 1;
+
+ for (thread = 0; thread < nthreads; thread++) {
+ for (cpu = 0; cpu < ncpus; cpu++) {
+ if (process_counter_values(config, counter, cpu, thread,
+ perf_counts(counter->counts, cpu, thread)))
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
+int perf_stat_process_counter(struct perf_stat_config *config,
+ struct perf_evsel *counter)
+{
+ struct perf_counts_values *aggr = &counter->counts->aggr;
+ struct perf_stat *ps = counter->priv;
+ u64 *count = counter->counts->aggr.values;
+ int i, ret;
+
+ aggr->val = aggr->ena = aggr->run = 0;
+ init_stats(ps->res_stats);
+
+ if (counter->per_pkg)
+ zero_per_pkg(counter);
+
+ ret = process_counter_maps(config, counter);
+ if (ret)
+ return ret;
+
+ if (config->aggr_mode != AGGR_GLOBAL)
+ return 0;
+
+ if (!counter->snapshot)
+ perf_evsel__compute_deltas(counter, -1, -1, aggr);
+ perf_counts_values__scale(aggr, config->scale, &counter->counts->scaled);
+
+ for (i = 0; i < 3; i++)
+ update_stats(&ps->res_stats[i], count[i]);
+
+ if (verbose) {
+ fprintf(config->output, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
+ perf_evsel__name(counter), count[0], count[1], count[2]);
+ }
+
+ /*
+ * Save the full runtime - to allow normalization during printout:
+ */
+ perf_stat__update_shadow_stats(counter, count, 0);
+
+ return 0;
+}
projects / linux-drm-fsl-dcu.git / blobdiff