2020-06-02 21:47:40 +00:00
|
|
|
// SPDX-License-Identifier: GPL-2.0
|
|
|
|
#include <linux/compiler.h>
|
|
|
|
#include <string.h>
|
|
|
|
#include <perf/cpumap.h>
|
|
|
|
#include <perf/evlist.h>
|
|
|
|
#include "metricgroup.h"
|
|
|
|
#include "tests.h"
|
|
|
|
#include "pmu-events/pmu-events.h"
|
|
|
|
#include "evlist.h"
|
|
|
|
#include "rblist.h"
|
|
|
|
#include "debug.h"
|
|
|
|
#include "expr.h"
|
|
|
|
#include "stat.h"
|
2023-05-27 07:22:03 +00:00
|
|
|
#include "pmus.h"
|
2020-06-02 21:47:40 +00:00
|
|
|
|
|
|
|
struct value {
|
|
|
|
const char *event;
|
|
|
|
u64 val;
|
|
|
|
};
|
|
|
|
|
|
|
|
static u64 find_value(const char *name, struct value *values)
|
|
|
|
{
|
|
|
|
struct value *v = values;
|
|
|
|
|
|
|
|
while (v->event) {
|
|
|
|
if (!strcmp(name, v->event))
|
|
|
|
return v->val;
|
|
|
|
v++;
|
2021-02-25 06:07:00 +00:00
|
|
|
}
|
2020-06-02 21:47:40 +00:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2023-02-19 09:28:44 +00:00
|
|
|
static void load_runtime_stat(struct evlist *evlist, struct value *vals)
|
2020-06-02 21:47:40 +00:00
|
|
|
{
|
|
|
|
struct evsel *evsel;
|
|
|
|
u64 count;
|
|
|
|
|
2023-02-19 09:28:46 +00:00
|
|
|
evlist__alloc_aggr_stats(evlist, 1);
|
2020-06-02 21:47:40 +00:00
|
|
|
evlist__for_each_entry(evlist, evsel) {
|
|
|
|
count = find_value(evsel->name, vals);
|
perf metric: Change divide by zero and !support events behavior
Division by zero causes expression parsing to fail and no metric to be
generated. This can mean for short running benchmarks metrics are not
shown. Change the behavior to make the value nan, which gets shown like:
'''
$ perf stat -M TopdownL2 true
Performance counter stats for 'true':
1,031,492 INST_RETIRED.ANY # nan % tma_fetch_bandwidth
# nan % tma_heavy_operations
# nan % tma_light_operations
29,304 CPU_CLK_UNHALTED.REF_XCLK # nan % tma_fetch_latency
# nan % tma_branch_mispredicts
# nan % tma_machine_clears
# nan % tma_core_bound
# nan % tma_memory_bound
2,658,319 IDQ_UOPS_NOT_DELIVERED.CORE
11,167 EXE_ACTIVITY.BOUND_ON_STORES
262,058 EXE_ACTIVITY.1_PORTS_UTIL
<not counted> BR_MISP_RETIRED.ALL_BRANCHES (0.00%)
<not counted> INT_MISC.RECOVERY_CYCLES_ANY (0.00%)
<not counted> CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE (0.00%)
<not counted> CPU_CLK_UNHALTED.THREAD (0.00%)
<not counted> UOPS_RETIRED.RETIRE_SLOTS (0.00%)
<not counted> CYCLE_ACTIVITY.STALLS_MEM_ANY (0.00%)
<not counted> UOPS_RETIRED.MACRO_FUSED (0.00%)
<not counted> IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE (0.00%)
<not counted> EXE_ACTIVITY.2_PORTS_UTIL (0.00%)
<not counted> CYCLE_ACTIVITY.STALLS_TOTAL (0.00%)
<not counted> MACHINE_CLEARS.COUNT (0.00%)
<not counted> UOPS_ISSUED.ANY (0.00%)
0.002864879 seconds time elapsed
0.003012000 seconds user
0.000000000 seconds sys
'''
When events aren't supported a count of 0 can be confusing and make
metrics look meaningful. Change these to be nan also which, with the
next change, gets shown like:
'''
$ perf stat true
Performance counter stats for 'true':
1.25 msec task-clock:u # 0.387 CPUs utilized
0 context-switches:u # 0.000 /sec
0 cpu-migrations:u # 0.000 /sec
46 page-faults:u # 36.702 K/sec
255,942 cycles:u # 0.204 GHz (88.66%)
123,046 instructions:u # 0.48 insn per cycle
28,301 branches:u # 22.580 M/sec
2,489 branch-misses:u # 8.79% of all branches
4,719 CPU_CLK_UNHALTED.REF_XCLK:u # 3.765 M/sec
# nan % tma_frontend_bound
# nan % tma_retiring
# nan % tma_backend_bound
# nan % tma_bad_speculation
344,855 IDQ_UOPS_NOT_DELIVERED.CORE:u # 275.147 M/sec
<not supported> INT_MISC.RECOVERY_CYCLES_ANY:u
<not counted> CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE:u (0.00%)
<not counted> CPU_CLK_UNHALTED.THREAD:u (0.00%)
<not counted> UOPS_RETIRED.RETIRE_SLOTS:u (0.00%)
<not counted> UOPS_ISSUED.ANY:u (0.00%)
0.003238142 seconds time elapsed
0.000000000 seconds user
0.003434000 seconds sys
'''
Ensure that nan metric values are quoted as nan isn't a valid number
in JSON.
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ahmad Yasin <ahmad.yasin@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Florian Fischer <florian.fischer@muhq.space>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kang Minchul <tegongkang@gmail.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Samantha Alt <samantha.alt@intel.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Tiezhu Yang <yangtiezhu@loongson.cn>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20230502223851.2234828-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-02 22:38:08 +00:00
|
|
|
evsel->supported = true;
|
2023-02-19 09:28:46 +00:00
|
|
|
evsel->stats->aggr->counts.val = count;
|
2023-04-20 18:54:11 +00:00
|
|
|
if (evsel__name_is(evsel, "duration_time"))
|
2021-01-25 12:47:22 +00:00
|
|
|
update_stats(&walltime_nsecs_stats, count);
|
2020-06-02 21:47:40 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static double compute_single(struct rblist *metric_events, struct evlist *evlist,
|
2023-02-19 09:28:44 +00:00
|
|
|
const char *name)
|
2020-06-02 21:47:40 +00:00
|
|
|
{
|
2020-07-19 18:13:17 +00:00
|
|
|
struct metric_expr *mexp;
|
2020-06-02 21:47:40 +00:00
|
|
|
struct metric_event *me;
|
2020-07-19 18:13:17 +00:00
|
|
|
struct evsel *evsel;
|
2020-06-02 21:47:40 +00:00
|
|
|
|
2020-07-19 18:13:17 +00:00
|
|
|
evlist__for_each_entry(evlist, evsel) {
|
|
|
|
me = metricgroup__lookup(metric_events, evsel, false);
|
|
|
|
if (me != NULL) {
|
|
|
|
list_for_each_entry (mexp, &me->head, nd) {
|
|
|
|
if (strcmp(mexp->metric_name, name))
|
|
|
|
continue;
|
2023-02-19 09:28:44 +00:00
|
|
|
return test_generic_metric(mexp, 0);
|
2020-07-19 18:13:17 +00:00
|
|
|
}
|
|
|
|
}
|
2020-06-02 21:47:40 +00:00
|
|
|
}
|
|
|
|
return 0.;
|
|
|
|
}
|
|
|
|
|
2020-07-19 18:13:18 +00:00
|
|
|
static int __compute_metric(const char *name, struct value *vals,
|
|
|
|
const char *name1, double *ratio1,
|
|
|
|
const char *name2, double *ratio2)
|
2020-06-02 21:47:40 +00:00
|
|
|
{
|
|
|
|
struct rblist metric_events = {
|
|
|
|
.nr_entries = 0,
|
|
|
|
};
|
2023-01-26 23:36:39 +00:00
|
|
|
const struct pmu_metrics_table *pme_test;
|
2020-06-02 21:47:40 +00:00
|
|
|
struct perf_cpu_map *cpus;
|
|
|
|
struct evlist *evlist;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We need to prepare evlist for stat mode running on CPU 0
|
|
|
|
* because that's where all the stats are going to be created.
|
|
|
|
*/
|
|
|
|
evlist = evlist__new();
|
|
|
|
if (!evlist)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
cpus = perf_cpu_map__new("0");
|
2020-09-15 03:18:14 +00:00
|
|
|
if (!cpus) {
|
|
|
|
evlist__delete(evlist);
|
2020-06-02 21:47:40 +00:00
|
|
|
return -ENOMEM;
|
2020-09-15 03:18:14 +00:00
|
|
|
}
|
2020-06-02 21:47:40 +00:00
|
|
|
|
|
|
|
perf_evlist__set_maps(&evlist->core, cpus, NULL);
|
|
|
|
|
|
|
|
/* Parse the metric into metric_events list. */
|
2023-01-26 23:36:35 +00:00
|
|
|
pme_test = find_core_metrics_table("testarch", "testcpu");
|
2022-08-12 23:09:41 +00:00
|
|
|
err = metricgroup__parse_groups_test(evlist, pme_test, name,
|
2020-06-02 21:47:40 +00:00
|
|
|
&metric_events);
|
2020-07-19 18:13:16 +00:00
|
|
|
if (err)
|
2020-09-15 03:18:14 +00:00
|
|
|
goto out;
|
2020-06-02 21:47:40 +00:00
|
|
|
|
2022-10-18 02:02:15 +00:00
|
|
|
err = evlist__alloc_stats(/*config=*/NULL, evlist, /*alloc_raw=*/false);
|
2020-09-15 03:18:14 +00:00
|
|
|
if (err)
|
|
|
|
goto out;
|
2020-06-02 21:47:40 +00:00
|
|
|
|
|
|
|
/* Load the runtime stats with given numbers for events. */
|
2023-02-19 09:28:44 +00:00
|
|
|
load_runtime_stat(evlist, vals);
|
2020-06-02 21:47:40 +00:00
|
|
|
|
|
|
|
/* And execute the metric */
|
2020-07-19 18:13:18 +00:00
|
|
|
if (name1 && ratio1)
|
2023-02-19 09:28:44 +00:00
|
|
|
*ratio1 = compute_single(&metric_events, evlist, name1);
|
2020-07-19 18:13:18 +00:00
|
|
|
if (name2 && ratio2)
|
2023-02-19 09:28:44 +00:00
|
|
|
*ratio2 = compute_single(&metric_events, evlist, name2);
|
2020-06-02 21:47:40 +00:00
|
|
|
|
2020-09-15 03:18:14 +00:00
|
|
|
out:
|
2021-03-23 16:09:15 +00:00
|
|
|
/* ... cleanup. */
|
2020-06-02 21:47:40 +00:00
|
|
|
metricgroup__rblist_exit(&metric_events);
|
2020-11-30 12:31:04 +00:00
|
|
|
evlist__free_stats(evlist);
|
2020-06-02 21:47:40 +00:00
|
|
|
perf_cpu_map__put(cpus);
|
|
|
|
evlist__delete(evlist);
|
2020-09-15 03:18:14 +00:00
|
|
|
return err;
|
2020-06-02 21:47:40 +00:00
|
|
|
}
|
|
|
|
|
2020-07-19 18:13:18 +00:00
|
|
|
static int compute_metric(const char *name, struct value *vals, double *ratio)
|
|
|
|
{
|
|
|
|
return __compute_metric(name, vals, name, ratio, NULL, NULL);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int compute_metric_group(const char *name, struct value *vals,
|
|
|
|
const char *name1, double *ratio1,
|
|
|
|
const char *name2, double *ratio2)
|
|
|
|
{
|
|
|
|
return __compute_metric(name, vals, name1, ratio1, name2, ratio2);
|
|
|
|
}
|
|
|
|
|
2020-06-02 21:47:40 +00:00
|
|
|
static int test_ipc(void)
|
|
|
|
{
|
|
|
|
double ratio;
|
|
|
|
struct value vals[] = {
|
|
|
|
{ .event = "inst_retired.any", .val = 300 },
|
|
|
|
{ .event = "cpu_clk_unhalted.thread", .val = 200 },
|
|
|
|
{ .event = NULL, },
|
|
|
|
};
|
|
|
|
|
|
|
|
TEST_ASSERT_VAL("failed to compute metric",
|
|
|
|
compute_metric("IPC", vals, &ratio) == 0);
|
|
|
|
|
|
|
|
TEST_ASSERT_VAL("IPC failed, wrong ratio",
|
|
|
|
ratio == 1.5);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2020-06-02 21:47:41 +00:00
|
|
|
static int test_frontend(void)
|
|
|
|
{
|
|
|
|
double ratio;
|
|
|
|
struct value vals[] = {
|
|
|
|
{ .event = "idq_uops_not_delivered.core", .val = 300 },
|
|
|
|
{ .event = "cpu_clk_unhalted.thread", .val = 200 },
|
|
|
|
{ .event = "cpu_clk_unhalted.one_thread_active", .val = 400 },
|
|
|
|
{ .event = "cpu_clk_unhalted.ref_xclk", .val = 600 },
|
|
|
|
{ .event = NULL, },
|
|
|
|
};
|
|
|
|
|
|
|
|
TEST_ASSERT_VAL("failed to compute metric",
|
|
|
|
compute_metric("Frontend_Bound_SMT", vals, &ratio) == 0);
|
|
|
|
|
|
|
|
TEST_ASSERT_VAL("Frontend_Bound_SMT failed, wrong ratio",
|
|
|
|
ratio == 0.45);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2020-07-19 18:13:14 +00:00
|
|
|
static int test_cache_miss_cycles(void)
|
|
|
|
{
|
|
|
|
double ratio;
|
|
|
|
struct value vals[] = {
|
|
|
|
{ .event = "l1d-loads-misses", .val = 300 },
|
|
|
|
{ .event = "l1i-loads-misses", .val = 200 },
|
|
|
|
{ .event = "inst_retired.any", .val = 400 },
|
|
|
|
{ .event = NULL, },
|
|
|
|
};
|
|
|
|
|
|
|
|
TEST_ASSERT_VAL("failed to compute metric",
|
|
|
|
compute_metric("cache_miss_cycles", vals, &ratio) == 0);
|
|
|
|
|
|
|
|
TEST_ASSERT_VAL("cache_miss_cycles failed, wrong ratio",
|
|
|
|
ratio == 1.25);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2020-07-19 18:13:15 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* DCache_L2_All_Hits = l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hi
|
|
|
|
* DCache_L2_All_Miss = max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) +
|
|
|
|
* l2_rqsts.pf_miss + l2_rqsts.rfo_miss
|
|
|
|
* DCache_L2_All = dcache_l2_all_hits + dcache_l2_all_miss
|
|
|
|
* DCache_L2_Hits = d_ratio(dcache_l2_all_hits, dcache_l2_all)
|
|
|
|
* DCache_L2_Misses = d_ratio(dcache_l2_all_miss, dcache_l2_all)
|
|
|
|
*
|
|
|
|
* l2_rqsts.demand_data_rd_hit = 100
|
|
|
|
* l2_rqsts.pf_hit = 200
|
|
|
|
* l2_rqsts.rfo_hi = 300
|
|
|
|
* l2_rqsts.all_demand_data_rd = 400
|
|
|
|
* l2_rqsts.pf_miss = 500
|
|
|
|
* l2_rqsts.rfo_miss = 600
|
|
|
|
*
|
|
|
|
* DCache_L2_All_Hits = 600
|
|
|
|
* DCache_L2_All_Miss = MAX(400 - 100, 0) + 500 + 600 = 1400
|
|
|
|
* DCache_L2_All = 600 + 1400 = 2000
|
|
|
|
* DCache_L2_Hits = 600 / 2000 = 0.3
|
|
|
|
* DCache_L2_Misses = 1400 / 2000 = 0.7
|
|
|
|
*/
|
|
|
|
static int test_dcache_l2(void)
|
|
|
|
{
|
|
|
|
double ratio;
|
|
|
|
struct value vals[] = {
|
|
|
|
{ .event = "l2_rqsts.demand_data_rd_hit", .val = 100 },
|
|
|
|
{ .event = "l2_rqsts.pf_hit", .val = 200 },
|
|
|
|
{ .event = "l2_rqsts.rfo_hit", .val = 300 },
|
|
|
|
{ .event = "l2_rqsts.all_demand_data_rd", .val = 400 },
|
|
|
|
{ .event = "l2_rqsts.pf_miss", .val = 500 },
|
|
|
|
{ .event = "l2_rqsts.rfo_miss", .val = 600 },
|
|
|
|
{ .event = NULL, },
|
|
|
|
};
|
|
|
|
|
|
|
|
TEST_ASSERT_VAL("failed to compute metric",
|
|
|
|
compute_metric("DCache_L2_Hits", vals, &ratio) == 0);
|
|
|
|
|
|
|
|
TEST_ASSERT_VAL("DCache_L2_Hits failed, wrong ratio",
|
|
|
|
ratio == 0.3);
|
|
|
|
|
|
|
|
TEST_ASSERT_VAL("failed to compute metric",
|
|
|
|
compute_metric("DCache_L2_Misses", vals, &ratio) == 0);
|
|
|
|
|
|
|
|
TEST_ASSERT_VAL("DCache_L2_Misses failed, wrong ratio",
|
|
|
|
ratio == 0.7);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2020-07-19 18:13:16 +00:00
|
|
|
static int test_recursion_fail(void)
|
|
|
|
{
|
|
|
|
double ratio;
|
|
|
|
struct value vals[] = {
|
|
|
|
{ .event = "inst_retired.any", .val = 300 },
|
|
|
|
{ .event = "cpu_clk_unhalted.thread", .val = 200 },
|
|
|
|
{ .event = NULL, },
|
|
|
|
};
|
|
|
|
|
|
|
|
TEST_ASSERT_VAL("failed to find recursion",
|
|
|
|
compute_metric("M1", vals, &ratio) == -1);
|
|
|
|
|
|
|
|
TEST_ASSERT_VAL("failed to find recursion",
|
|
|
|
compute_metric("M3", vals, &ratio) == -1);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2021-01-25 12:47:22 +00:00
|
|
|
static int test_memory_bandwidth(void)
|
|
|
|
{
|
|
|
|
double ratio;
|
|
|
|
struct value vals[] = {
|
|
|
|
{ .event = "l1d.replacement", .val = 4000000 },
|
|
|
|
{ .event = "duration_time", .val = 200000000 },
|
|
|
|
{ .event = NULL, },
|
|
|
|
};
|
|
|
|
|
|
|
|
TEST_ASSERT_VAL("failed to compute metric",
|
|
|
|
compute_metric("L1D_Cache_Fill_BW", vals, &ratio) == 0);
|
|
|
|
TEST_ASSERT_VAL("L1D_Cache_Fill_BW, wrong ratio",
|
|
|
|
1.28 == ratio);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2020-07-19 18:13:18 +00:00
|
|
|
static int test_metric_group(void)
|
|
|
|
{
|
|
|
|
double ratio1, ratio2;
|
|
|
|
struct value vals[] = {
|
|
|
|
{ .event = "cpu_clk_unhalted.thread", .val = 200 },
|
|
|
|
{ .event = "l1d-loads-misses", .val = 300 },
|
|
|
|
{ .event = "l1i-loads-misses", .val = 200 },
|
|
|
|
{ .event = "inst_retired.any", .val = 400 },
|
|
|
|
{ .event = NULL, },
|
|
|
|
};
|
|
|
|
|
|
|
|
TEST_ASSERT_VAL("failed to find recursion",
|
|
|
|
compute_metric_group("group1", vals,
|
|
|
|
"IPC", &ratio1,
|
|
|
|
"cache_miss_cycles", &ratio2) == 0);
|
|
|
|
|
|
|
|
TEST_ASSERT_VAL("group IPC failed, wrong ratio",
|
|
|
|
ratio1 == 2.0);
|
|
|
|
|
|
|
|
TEST_ASSERT_VAL("group cache_miss_cycles failed, wrong ratio",
|
|
|
|
ratio2 == 1.25);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2021-11-04 06:41:51 +00:00
|
|
|
static int test__parse_metric(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
|
2020-06-02 21:47:40 +00:00
|
|
|
{
|
|
|
|
TEST_ASSERT_VAL("IPC failed", test_ipc() == 0);
|
2020-06-02 21:47:41 +00:00
|
|
|
TEST_ASSERT_VAL("frontend failed", test_frontend() == 0);
|
2020-07-19 18:13:15 +00:00
|
|
|
TEST_ASSERT_VAL("DCache_L2 failed", test_dcache_l2() == 0);
|
2020-07-19 18:13:16 +00:00
|
|
|
TEST_ASSERT_VAL("recursion fail failed", test_recursion_fail() == 0);
|
2021-01-25 12:47:22 +00:00
|
|
|
TEST_ASSERT_VAL("Memory bandwidth", test_memory_bandwidth() == 0);
|
2023-05-27 07:22:09 +00:00
|
|
|
TEST_ASSERT_VAL("cache_miss_cycles failed", test_cache_miss_cycles() == 0);
|
|
|
|
TEST_ASSERT_VAL("test metric group", test_metric_group() == 0);
|
2020-06-02 21:47:40 +00:00
|
|
|
return 0;
|
|
|
|
}
|
2021-11-04 06:41:50 +00:00
|
|
|
|
|
|
|
DEFINE_SUITE("Parse and process metrics", parse_metric);
|