forked from Minki/linux
perf stat: Move counter processing code into stat object
Moving counter processing code into stat object as perf_stat__process_counter. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1437481927-29538-8-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
parent
5e5fe748be
commit
f80010eb23
@ -179,145 +179,6 @@ static inline int nsec_counter(struct perf_evsel *evsel)
|
||||
return 0;
|
||||
}
|
||||
|
||||
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, 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;
|
||||
}
|
||||
|
||||
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, 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;
|
||||
}
|
||||
|
||||
static int 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(&stat_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;
|
||||
}
|
||||
|
||||
/*
|
||||
* Read out the results of a single counter:
|
||||
* do not aggregate counts across CPUs in system-wide mode
|
||||
@ -355,7 +216,7 @@ static void read_counters(bool close_counters)
|
||||
if (read_counter(counter))
|
||||
pr_warning("failed to read counter %s\n", counter->name);
|
||||
|
||||
if (process_counter(&stat_config, counter))
|
||||
if (perf_stat_process_counter(&stat_config, counter))
|
||||
pr_warning("failed to process counter %s\n", counter->name);
|
||||
|
||||
if (close_counters) {
|
||||
|
@ -238,3 +238,142 @@ void perf_evlist__reset_stats(struct perf_evlist *evlist)
|
||||
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, 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;
|
||||
}
|
||||
|
||||
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, 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;
|
||||
}
|
||||
|
@ -116,4 +116,7 @@ int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw);
|
||||
int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
|
||||
void perf_evlist__free_stats(struct perf_evlist *evlist);
|
||||
void perf_evlist__reset_stats(struct perf_evlist *evlist);
|
||||
|
||||
int perf_stat_process_counter(struct perf_stat_config *config,
|
||||
struct perf_evsel *counter);
|
||||
#endif
|
||||
|
Loading…
Reference in New Issue
Block a user