static void print_aggr(char *prefix);
/* Default events used for perf stat -T */
-static const char * const transaction_attrs[] = {
- "task-clock",
+static const char *transaction_attrs = {
+ "task-clock,"
"{"
"instructions,"
"cycles,"
};
/* More limited version when the CPU does not have all events. */
-static const char * const transaction_limited_attrs[] = {
- "task-clock",
+static const char * transaction_limited_attrs = {
+ "task-clock,"
"{"
"instructions,"
"cycles,"
"}"
};
-/* must match transaction_attrs and the beginning limited_attrs */
-enum {
- T_TASK_CLOCK,
- T_INSTRUCTIONS,
- T_CYCLES,
- T_CYCLES_IN_TX,
- T_TRANSACTION_START,
- T_ELISION_START,
- T_CYCLES_IN_TX_CP,
-};
-
static struct perf_evlist *evsel_list;
static struct target target = {
static volatile int done = 0;
-struct perf_stat {
- struct stats res_stats[3];
-};
-
static inline void diff_timespec(struct timespec *r, struct timespec *a,
struct timespec *b)
{
for (i = 0; i < 3; i++)
init_stats(&ps->res_stats[i]);
+
+ perf_stat_evsel_id_init(evsel);
}
static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
enum {
CTX_BIT_USER = 1 << 0,
CTX_BIT_KERNEL = 1 << 1,
- CTX_BIT_MAX = 1 << 2,
+ CTX_BIT_HV = 1 << 2,
+ CTX_BIT_HOST = 1 << 3,
+ CTX_BIT_IDLE = 1 << 4,
+ CTX_BIT_MAX = 1 << 5,
};
#define NUM_CTX CTX_BIT_MAX
ctx |= CTX_BIT_KERNEL;
if (evsel->attr.exclude_user)
ctx |= CTX_BIT_USER;
+ if (evsel->attr.exclude_hv)
+ ctx |= CTX_BIT_HV;
+ if (evsel->attr.exclude_host)
+ ctx |= CTX_BIT_HOST;
+ if (evsel->attr.exclude_idle)
+ ctx |= CTX_BIT_IDLE;
+
return ctx;
}
-static void perf_stat__reset_stats(struct perf_evlist *evlist)
+static void reset_shadow_stats(void)
{
- struct perf_evsel *evsel;
-
- evlist__for_each(evlist, evsel) {
- perf_evsel__reset_stat_priv(evsel);
- perf_evsel__reset_counts(evsel, perf_evsel__nr_cpus(evsel));
- }
-
memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats));
memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats));
memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats));
memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
}
+static void perf_stat__reset_stats(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel;
+
+ evlist__for_each(evlist, evsel) {
+ perf_evsel__reset_stat_priv(evsel);
+ perf_evsel__reset_counts(evsel, perf_evsel__nr_cpus(evsel));
+ }
+
+ reset_shadow_stats();
+}
+
static int create_perf_stat_counter(struct perf_evsel *evsel)
{
struct perf_event_attr *attr = &evsel->attr;
return 0;
}
-static struct perf_evsel *nth_evsel(int n)
-{
- static struct perf_evsel **array;
- static int array_len;
- struct perf_evsel *ev;
- int j;
-
- /* Assumes this only called when evsel_list does not change anymore. */
- if (!array) {
- evlist__for_each(evsel_list, ev)
- array_len++;
- array = malloc(array_len * sizeof(void *));
- if (!array)
- exit(ENOMEM);
- j = 0;
- evlist__for_each(evsel_list, ev)
- array[j++] = ev;
- }
- if (n < array_len)
- return array[n];
- return NULL;
-}
-
/*
* Update various tracking values we maintain to print
* more semantic information such as miss/hit ratios,
update_stats(&runtime_nsecs_stats[cpu], count[0]);
else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);
- else if (transaction_run &&
- perf_evsel__cmp(counter, nth_evsel(T_CYCLES_IN_TX)))
+ else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
- else if (transaction_run &&
- perf_evsel__cmp(counter, nth_evsel(T_TRANSACTION_START)))
+ else if (perf_stat_evsel__is(counter, TRANSACTION_START))
update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
- else if (transaction_run &&
- perf_evsel__cmp(counter, nth_evsel(T_ELISION_START)))
+ else if (perf_stat_evsel__is(counter, ELISION_START))
update_stats(&runtime_elision_stats[ctx][cpu], count[0]);
else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count[0]);
return color;
}
-static void print_stalled_cycles_frontend(int cpu,
+static void print_stalled_cycles_frontend(FILE *out, int cpu,
struct perf_evsel *evsel
__maybe_unused, double avg)
{
color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
- fprintf(output, " # ");
- color_fprintf(output, color, "%6.2f%%", ratio);
- fprintf(output, " frontend cycles idle ");
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " frontend cycles idle ");
}
-static void print_stalled_cycles_backend(int cpu,
+static void print_stalled_cycles_backend(FILE *out, int cpu,
struct perf_evsel *evsel
__maybe_unused, double avg)
{
color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
- fprintf(output, " # ");
- color_fprintf(output, color, "%6.2f%%", ratio);
- fprintf(output, " backend cycles idle ");
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " backend cycles idle ");
}
-static void print_branch_misses(int cpu,
+static void print_branch_misses(FILE *out, int cpu,
struct perf_evsel *evsel __maybe_unused,
double avg)
{
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
- fprintf(output, " # ");
- color_fprintf(output, color, "%6.2f%%", ratio);
- fprintf(output, " of all branches ");
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " of all branches ");
}
-static void print_l1_dcache_misses(int cpu,
+static void print_l1_dcache_misses(FILE *out, int cpu,
struct perf_evsel *evsel __maybe_unused,
double avg)
{
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
- fprintf(output, " # ");
- color_fprintf(output, color, "%6.2f%%", ratio);
- fprintf(output, " of all L1-dcache hits ");
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " of all L1-dcache hits ");
}
-static void print_l1_icache_misses(int cpu,
+static void print_l1_icache_misses(FILE *out, int cpu,
struct perf_evsel *evsel __maybe_unused,
double avg)
{
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
- fprintf(output, " # ");
- color_fprintf(output, color, "%6.2f%%", ratio);
- fprintf(output, " of all L1-icache hits ");
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " of all L1-icache hits ");
}
-static void print_dtlb_cache_misses(int cpu,
+static void print_dtlb_cache_misses(FILE *out, int cpu,
struct perf_evsel *evsel __maybe_unused,
double avg)
{
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
- fprintf(output, " # ");
- color_fprintf(output, color, "%6.2f%%", ratio);
- fprintf(output, " of all dTLB cache hits ");
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " of all dTLB cache hits ");
}
-static void print_itlb_cache_misses(int cpu,
+static void print_itlb_cache_misses(FILE *out, int cpu,
struct perf_evsel *evsel __maybe_unused,
double avg)
{
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
- fprintf(output, " # ");
- color_fprintf(output, color, "%6.2f%%", ratio);
- fprintf(output, " of all iTLB cache hits ");
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " of all iTLB cache hits ");
}
-static void print_ll_cache_misses(int cpu,
+static void print_ll_cache_misses(FILE *out, int cpu,
struct perf_evsel *evsel __maybe_unused,
double avg)
{
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
- fprintf(output, " # ");
- color_fprintf(output, color, "%6.2f%%", ratio);
- fprintf(output, " of all LL-cache hits ");
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " of all LL-cache hits ");
}
-static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
+static void print_shadow_stats(FILE *out, struct perf_evsel *evsel,
+ double avg, int cpu, enum aggr_mode aggr)
{
double total, ratio = 0.0, total2;
- double sc = evsel->scale;
- const char *fmt;
- int cpu = cpu_map__id_to_cpu(id);
int ctx = evsel_context(evsel);
- if (csv_output) {
- fmt = sc != 1.0 ? "%.2f%s" : "%.0f%s";
- } else {
- if (big_num)
- fmt = sc != 1.0 ? "%'18.2f%s" : "%'18.0f%s";
- else
- fmt = sc != 1.0 ? "%18.2f%s" : "%18.0f%s";
- }
-
- aggr_printout(evsel, id, nr);
-
- if (aggr_mode == AGGR_GLOBAL)
- cpu = 0;
-
- fprintf(output, fmt, avg, csv_sep);
-
- if (evsel->unit)
- fprintf(output, "%-*s%s",
- csv_output ? 0 : unit_width,
- evsel->unit, csv_sep);
-
- fprintf(output, "%-*s", csv_output ? 0 : 25, perf_evsel__name(evsel));
-
- if (evsel->cgrp)
- fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
-
- if (csv_output || interval)
- return;
-
if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
if (total) {
ratio = avg / total;
- fprintf(output, " # %5.2f insns per cycle ", ratio);
+ fprintf(out, " # %5.2f insns per cycle ", ratio);
} else {
- fprintf(output, " ");
+ fprintf(out, " ");
}
total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]);
total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu]));
if (total && avg) {
ratio = total / avg;
- fprintf(output, "\n");
- if (aggr_mode == AGGR_NONE)
- fprintf(output, " ");
- fprintf(output, " # %5.2f stalled cycles per insn", ratio);
+ fprintf(out, "\n");
+ if (aggr == AGGR_NONE)
+ fprintf(out, " ");
+ fprintf(out, " # %5.2f stalled cycles per insn", ratio);
}
} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
runtime_branches_stats[ctx][cpu].n != 0) {
- print_branch_misses(cpu, evsel, avg);
+ print_branch_misses(out, cpu, evsel, avg);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1D |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
runtime_l1_dcache_stats[ctx][cpu].n != 0) {
- print_l1_dcache_misses(cpu, evsel, avg);
+ print_l1_dcache_misses(out, cpu, evsel, avg);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1I |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
runtime_l1_icache_stats[ctx][cpu].n != 0) {
- print_l1_icache_misses(cpu, evsel, avg);
+ print_l1_icache_misses(out, cpu, evsel, avg);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_DTLB |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
runtime_dtlb_cache_stats[ctx][cpu].n != 0) {
- print_dtlb_cache_misses(cpu, evsel, avg);
+ print_dtlb_cache_misses(out, cpu, evsel, avg);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_ITLB |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
runtime_itlb_cache_stats[ctx][cpu].n != 0) {
- print_itlb_cache_misses(cpu, evsel, avg);
+ print_itlb_cache_misses(out, cpu, evsel, avg);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_LL |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
runtime_ll_cache_stats[ctx][cpu].n != 0) {
- print_ll_cache_misses(cpu, evsel, avg);
+ print_ll_cache_misses(out, cpu, evsel, avg);
} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
runtime_cacherefs_stats[ctx][cpu].n != 0) {
total = avg_stats(&runtime_cacherefs_stats[ctx][cpu]);
if (total)
ratio = avg * 100 / total;
- fprintf(output, " # %8.3f %% of all cache refs ", ratio);
+ fprintf(out, " # %8.3f %% of all cache refs ", ratio);
} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
- print_stalled_cycles_frontend(cpu, evsel, avg);
+ print_stalled_cycles_frontend(out, cpu, evsel, avg);
} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
- print_stalled_cycles_backend(cpu, evsel, avg);
+ print_stalled_cycles_backend(out, cpu, evsel, avg);
} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
total = avg_stats(&runtime_nsecs_stats[cpu]);
if (total) {
ratio = avg / total;
- fprintf(output, " # %8.3f GHz ", ratio);
+ fprintf(out, " # %8.3f GHz ", ratio);
} else {
- fprintf(output, " ");
+ fprintf(out, " ");
}
- } else if (transaction_run &&
- perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_IN_TX))) {
+ } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
if (total)
- fprintf(output,
+ fprintf(out,
" # %5.2f%% transactional cycles ",
100.0 * (avg / total));
- } else if (transaction_run &&
- perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_IN_TX_CP))) {
+ } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
total2 = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
if (total2 < avg)
total2 = avg;
if (total)
- fprintf(output,
+ fprintf(out,
" # %5.2f%% aborted cycles ",
100.0 * ((total2-avg) / total));
- } else if (transaction_run &&
- perf_evsel__cmp(evsel, nth_evsel(T_TRANSACTION_START)) &&
+ } else if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
avg > 0 &&
runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
if (total)
ratio = total / avg;
- fprintf(output, " # %8.0f cycles / transaction ", ratio);
- } else if (transaction_run &&
- perf_evsel__cmp(evsel, nth_evsel(T_ELISION_START)) &&
+ fprintf(out, " # %8.0f cycles / transaction ", ratio);
+ } else if (perf_stat_evsel__is(evsel, ELISION_START) &&
avg > 0 &&
runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
if (total)
ratio = total / avg;
- fprintf(output, " # %8.0f cycles / elision ", ratio);
+ fprintf(out, " # %8.0f cycles / elision ", ratio);
} else if (runtime_nsecs_stats[cpu].n != 0) {
char unit = 'M';
unit = 'K';
}
- fprintf(output, " # %8.3f %c/sec ", ratio, unit);
+ fprintf(out, " # %8.3f %c/sec ", ratio, unit);
} else {
- fprintf(output, " ");
+ fprintf(out, " ");
}
}
+static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
+{
+ double sc = evsel->scale;
+ const char *fmt;
+ int cpu = cpu_map__id_to_cpu(id);
+
+ if (csv_output) {
+ fmt = sc != 1.0 ? "%.2f%s" : "%.0f%s";
+ } else {
+ if (big_num)
+ fmt = sc != 1.0 ? "%'18.2f%s" : "%'18.0f%s";
+ else
+ fmt = sc != 1.0 ? "%18.2f%s" : "%18.0f%s";
+ }
+
+ aggr_printout(evsel, id, nr);
+
+ if (aggr_mode == AGGR_GLOBAL)
+ cpu = 0;
+
+ fprintf(output, fmt, avg, csv_sep);
+
+ if (evsel->unit)
+ fprintf(output, "%-*s%s",
+ csv_output ? 0 : unit_width,
+ evsel->unit, csv_sep);
+
+ fprintf(output, "%-*s", csv_output ? 0 : 25, perf_evsel__name(evsel));
+
+ if (evsel->cgrp)
+ fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
+
+ if (csv_output || interval)
+ return;
+
+ print_shadow_stats(output, evsel, avg, cpu, aggr_mode);
+}
+
static void print_aggr(char *prefix)
{
struct perf_evsel *counter;
return 0;
}
-static int setup_events(const char * const *attrs, unsigned len)
-{
- unsigned i;
-
- for (i = 0; i < len; i++) {
- if (parse_events(evsel_list, attrs[i], NULL))
- return -1;
- }
- return 0;
-}
-
/*
* Add default attributes, if there were no attributes specified or
* if -d/--detailed, -d -d or -d -d -d is used:
int err;
if (pmu_have_event("cpu", "cycles-ct") &&
pmu_have_event("cpu", "el-start"))
- err = setup_events(transaction_attrs,
- ARRAY_SIZE(transaction_attrs));
+ err = parse_events(evsel_list, transaction_attrs, NULL);
else
- err = setup_events(transaction_limited_attrs,
- ARRAY_SIZE(transaction_limited_attrs));
- if (err < 0) {
+ err = parse_events(evsel_list, transaction_limited_attrs, NULL);
+ if (err) {
fprintf(stderr, "Cannot set up transaction events\n");
return -1;
}