| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20251024175857.808401-9-irogers@google.com>
Date: Fri, 24 Oct 2025 10:58:43 -0700
From: Ian Rogers <irogers@...gle.com>
To: Peter Zijlstra <peterz@...radead.org>, Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>, Namhyung Kim <namhyung@...nel.org>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>, Jiri Olsa <jolsa@...nel.org>,
Ian Rogers <irogers@...gle.com>, Adrian Hunter <adrian.hunter@...el.com>,
James Clark <james.clark@...aro.org>, Xu Yang <xu.yang_2@....com>,
Chun-Tse Shao <ctshao@...gle.com>, Thomas Richter <tmricht@...ux.ibm.com>,
Sumanth Korikkar <sumanthk@...ux.ibm.com>, Collin Funk <collin.funk1@...il.com>,
Thomas Falcon <thomas.falcon@...el.com>, Howard Chu <howardchu95@...il.com>,
Dapeng Mi <dapeng1.mi@...ux.intel.com>, Levi Yun <yeoreum.yun@....com>,
Yang Li <yang.lee@...ux.alibaba.com>, linux-kernel@...r.kernel.org,
linux-perf-users@...r.kernel.org
Subject: [PATCH v1 08/22] perf jevents: Add set of common metrics based on
default ones
Add support to getting a common set of metrics from a default
table. It simplifies the generation to add json metrics at the same
time. The metrics added are CPUs_utilized, cs_per_second,
migrations_per_second, page_faults_per_second, insn_per_cycle,
stalled_cycles_per_instruction, frontend_cycles_idle,
backend_cycles_idle, cycles_frequency, branch_frequency and
branch_miss_rate based on the shadow metric definitions.
Following this change the default perf stat output on an alderlake looks like:
```
$ perf stat -a -- sleep 1
Performance counter stats for 'system wide':
28,165,735,434 cpu-clock # 27.973 CPUs utilized
23,220 context-switches # 824.406 /sec
833 cpu-migrations # 29.575 /sec
35,293 page-faults # 1.253 K/sec
997,341,554 cpu_atom/instructions/ # 0.84 insn per cycle (35.63%)
11,197,053,736 cpu_core/instructions/ # 1.97 insn per cycle (58.21%)
1,184,871,493 cpu_atom/cycles/ # 0.042 GHz (35.64%)
5,676,692,769 cpu_core/cycles/ # 0.202 GHz (58.22%)
150,525,309 cpu_atom/branches/ # 5.344 M/sec (42.80%)
2,277,232,030 cpu_core/branches/ # 80.851 M/sec (58.21%)
5,248,575 cpu_atom/branch-misses/ # 3.49% of all branches (42.82%)
28,829,930 cpu_core/branch-misses/ # 1.27% of all branches (58.22%)
(software) # 824.4 cs/sec cs_per_second
TopdownL1 (cpu_core) # 12.6 % tma_bad_speculation
# 28.8 % tma_frontend_bound (66.57%)
TopdownL1 (cpu_core) # 25.8 % tma_backend_bound
# 32.8 % tma_retiring (66.57%)
(software) # 1253.1 faults/sec page_faults_per_second
# 0.0 GHz cycles_frequency (42.80%)
# 0.2 GHz cycles_frequency (74.92%)
TopdownL1 (cpu_atom) # 22.3 % tma_bad_speculation
# 17.2 % tma_retiring (49.95%)
TopdownL1 (cpu_atom) # 30.6 % tma_backend_bound
# 29.8 % tma_frontend_bound (49.94%)
(cpu_atom) # 6.9 K/sec branch_frequency (42.89%)
# 80.5 K/sec branch_frequency (74.93%)
# 29.6 migrations/sec migrations_per_second
# 28.0 CPUs CPUs_utilized
(cpu_atom) # 0.8 instructions insn_per_cycle (42.91%)
# 2.0 instructions insn_per_cycle (75.14%)
(cpu_atom) # 3.8 % branch_miss_rate (35.75%)
# 1.2 % branch_miss_rate (66.86%)
1.007063529 seconds time elapsed
```
Signed-off-by: Ian Rogers <irogers@...gle.com>
---
.../arch/common/common/metrics.json | 86 +++++++++++++
tools/perf/pmu-events/empty-pmu-events.c | 115 +++++++++++++-----
tools/perf/pmu-events/jevents.py | 21 +++-
tools/perf/pmu-events/pmu-events.h | 1 +
tools/perf/util/metricgroup.c | 31 +++--
5 files changed, 212 insertions(+), 42 deletions(-)
create mode 100644 tools/perf/pmu-events/arch/common/common/metrics.json
diff --git a/tools/perf/pmu-events/arch/common/common/metrics.json b/tools/perf/pmu-events/arch/common/common/metrics.json
new file mode 100644
index 000000000000..d1e37db18dc6
--- /dev/null
+++ b/tools/perf/pmu-events/arch/common/common/metrics.json
@@ -0,0 +1,86 @@
+[
+ {
+ "BriefDescription": "Average CPU utilization",
+ "MetricExpr": "(software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@...k\\-clock\\,name\\=task\\-clock@) / (duration_time * 1e9)",
+ "MetricGroup": "Default",
+ "MetricName": "CPUs_utilized",
+ "ScaleUnit": "1CPUs",
+ "MetricConstraint": "NO_GROUP_EVENTS"
+ },
+ {
+ "BriefDescription": "Context switches per CPU second",
+ "MetricExpr": "(software@...text\\-switches\\,name\\=context\\-switches@ * 1e9) / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@...k\\-clock\\,name\\=task\\-clock@)",
+ "MetricGroup": "Default",
+ "MetricName": "cs_per_second",
+ "ScaleUnit": "1cs/sec",
+ "MetricConstraint": "NO_GROUP_EVENTS"
+ },
+ {
+ "BriefDescription": "Process migrations to a new CPU per CPU second",
+ "MetricExpr": "(software@cpu\\-migrations\\,name\\=cpu\\-migrations@ * 1e9) / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@...k\\-clock\\,name\\=task\\-clock@)",
+ "MetricGroup": "Default",
+ "MetricName": "migrations_per_second",
+ "ScaleUnit": "1migrations/sec",
+ "MetricConstraint": "NO_GROUP_EVENTS"
+ },
+ {
+ "BriefDescription": "Page faults per CPU second",
+ "MetricExpr": "(software@...e\\-faults\\,name\\=page\\-faults@ * 1e9) / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@...k\\-clock\\,name\\=task\\-clock@)",
+ "MetricGroup": "Default",
+ "MetricName": "page_faults_per_second",
+ "ScaleUnit": "1faults/sec",
+ "MetricConstraint": "NO_GROUP_EVENTS"
+ },
+ {
+ "BriefDescription": "Instructions Per Cycle",
+ "MetricExpr": "instructions / cpu\\-cycles",
+ "MetricGroup": "Default",
+ "MetricName": "insn_per_cycle",
+ "MetricThreshold": "insn_per_cycle < 1",
+ "ScaleUnit": "1instructions"
+ },
+ {
+ "BriefDescription": "Max front or backend stalls per instruction",
+ "MetricExpr": "max(stalled\\-cycles\\-frontend, stalled\\-cycles\\-backend) / instructions",
+ "MetricGroup": "Default",
+ "MetricName": "stalled_cycles_per_instruction"
+ },
+ {
+ "BriefDescription": "Frontend stalls per cycle",
+ "MetricExpr": "stalled\\-cycles\\-frontend / cpu\\-cycles",
+ "MetricGroup": "Default",
+ "MetricName": "frontend_cycles_idle",
+ "MetricThreshold": "frontend_cycles_idle > 0.1"
+ },
+ {
+ "BriefDescription": "Backend stalls per cycle",
+ "MetricExpr": "stalled\\-cycles\\-backend / cpu\\-cycles",
+ "MetricGroup": "Default",
+ "MetricName": "backend_cycles_idle",
+ "MetricThreshold": "backend_cycles_idle > 0.2"
+ },
+ {
+ "BriefDescription": "Cycles per CPU second",
+ "MetricExpr": "cpu\\-cycles / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@...k\\-clock\\,name\\=task\\-clock@)",
+ "MetricGroup": "Default",
+ "MetricName": "cycles_frequency",
+ "ScaleUnit": "1GHz",
+ "MetricConstraint": "NO_GROUP_EVENTS"
+ },
+ {
+ "BriefDescription": "Branches per CPU second",
+ "MetricExpr": "branches / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@...k\\-clock\\,name\\=task\\-clock@)",
+ "MetricGroup": "Default",
+ "MetricName": "branch_frequency",
+ "ScaleUnit": "1000K/sec",
+ "MetricConstraint": "NO_GROUP_EVENTS"
+ },
+ {
+ "BriefDescription": "Branch miss rate",
+ "MetricExpr": "branch\\-misses / branches",
+ "MetricGroup": "Default",
+ "MetricName": "branch_miss_rate",
+ "MetricThreshold": "branch_miss_rate > 0.05",
+ "ScaleUnit": "100%"
+ }
+]
diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c
index 5120fb93690e..83a01ecc625e 100644
--- a/tools/perf/pmu-events/empty-pmu-events.c
+++ b/tools/perf/pmu-events/empty-pmu-events.c
@@ -1303,21 +1303,32 @@ static const char *const big_c_string =
/* offset=127503 */ "sys_ccn_pmu.read_cycles\000uncore\000ccn read-cycles event\000config=0x2c\0000x01\00000\000\000\000\000\000"
/* offset=127580 */ "uncore_sys_cmn_pmu\000"
/* offset=127599 */ "sys_cmn_pmu.hnf_cache_miss\000uncore\000Counts total cache misses in first lookup result (high priority)\000eventid=1,type=5\000(434|436|43c|43a).*\00000\000\000\000\000\000"
-/* offset=127742 */ "CPI\000\0001 / IPC\000\000\000\000\000\000\000\00000"
-/* offset=127764 */ "IPC\000group1\000inst_retired.any / cpu_clk_unhalted.thread\000\000\000\000\000\000\000\00000"
-/* offset=127827 */ "Frontend_Bound_SMT\000\000idq_uops_not_delivered.core / (4 * (cpu_clk_unhalted.thread / 2 * (1 + cpu_clk_unhalted.one_thread_active / cpu_clk_unhalted.ref_xclk)))\000\000\000\000\000\000\000\00000"
-/* offset=127993 */ "dcache_miss_cpi\000\000l1d\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000"
-/* offset=128057 */ "icache_miss_cycles\000\000l1i\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000"
-/* offset=128124 */ "cache_miss_cycles\000group1\000dcache_miss_cpi + icache_miss_cycles\000\000\000\000\000\000\000\00000"
-/* offset=128195 */ "DCache_L2_All_Hits\000\000l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hit\000\000\000\000\000\000\000\00000"
-/* offset=128289 */ "DCache_L2_All_Miss\000\000max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) + l2_rqsts.pf_miss + l2_rqsts.rfo_miss\000\000\000\000\000\000\000\00000"
-/* offset=128423 */ "DCache_L2_All\000\000DCache_L2_All_Hits + DCache_L2_All_Miss\000\000\000\000\000\000\000\00000"
-/* offset=128487 */ "DCache_L2_Hits\000\000d_ratio(DCache_L2_All_Hits, DCache_L2_All)\000\000\000\000\000\000\000\00000"
-/* offset=128555 */ "DCache_L2_Misses\000\000d_ratio(DCache_L2_All_Miss, DCache_L2_All)\000\000\000\000\000\000\000\00000"
-/* offset=128625 */ "M1\000\000ipc + M2\000\000\000\000\000\000\000\00000"
-/* offset=128647 */ "M2\000\000ipc + M1\000\000\000\000\000\000\000\00000"
-/* offset=128669 */ "M3\000\0001 / M3\000\000\000\000\000\000\000\00000"
-/* offset=128689 */ "L1D_Cache_Fill_BW\000\00064 * l1d.replacement / 1e9 / duration_time\000\000\000\000\000\000\000\00000"
+/* offset=127742 */ "CPUs_utilized\000Default\000(software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@...k\\-clock\\,name\\=task\\-clock@) / (duration_time * 1e9)\000\000Average CPU utilization\000\0001CPUs\000\000\000\00001"
+/* offset=127927 */ "cs_per_second\000Default\000software@...text\\-switches\\,name\\=context\\-switches@ * 1e9 / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@...k\\-clock\\,name\\=task\\-clock@)\000\000Context switches per CPU second\000\0001cs/sec\000\000\000\00001"
+/* offset=128159 */ "migrations_per_second\000Default\000software@cpu\\-migrations\\,name\\=cpu\\-migrations@ * 1e9 / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@...k\\-clock\\,name\\=task\\-clock@)\000\000Process migrations to a new CPU per CPU second\000\0001migrations/sec\000\000\000\00001"
+/* offset=128418 */ "page_faults_per_second\000Default\000software@...e\\-faults\\,name\\=page\\-faults@ * 1e9 / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@...k\\-clock\\,name\\=task\\-clock@)\000\000Page faults per CPU second\000\0001faults/sec\000\000\000\00001"
+/* offset=128648 */ "insn_per_cycle\000Default\000instructions / cpu\\-cycles\000insn_per_cycle < 1\000Instructions Per Cycle\000\0001instructions\000\000\000\00000"
+/* offset=128760 */ "stalled_cycles_per_instruction\000Default\000max(stalled\\-cycles\\-frontend, stalled\\-cycles\\-backend) / instructions\000\000Max front or backend stalls per instruction\000\000\000\000\000\00000"
+/* offset=128923 */ "frontend_cycles_idle\000Default\000stalled\\-cycles\\-frontend / cpu\\-cycles\000frontend_cycles_idle > 0.1\000Frontend stalls per cycle\000\000\000\000\000\00000"
+/* offset=129052 */ "backend_cycles_idle\000Default\000stalled\\-cycles\\-backend / cpu\\-cycles\000backend_cycles_idle > 0.2\000Backend stalls per cycle\000\000\000\000\000\00000"
+/* offset=129177 */ "cycles_frequency\000Default\000cpu\\-cycles / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@...k\\-clock\\,name\\=task\\-clock@)\000\000Cycles per CPU second\000\0001GHz\000\000\000\00001"
+/* offset=129352 */ "branch_frequency\000Default\000branches / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@...k\\-clock\\,name\\=task\\-clock@)\000\000Branches per CPU second\000\0001000K/sec\000\000\000\00001"
+/* offset=129531 */ "branch_miss_rate\000Default\000branch\\-misses / branches\000branch_miss_rate > 0.05\000Branch miss rate\000\000100%\000\000\000\00000"
+/* offset=129634 */ "CPI\000\0001 / IPC\000\000\000\000\000\000\000\00000"
+/* offset=129656 */ "IPC\000group1\000inst_retired.any / cpu_clk_unhalted.thread\000\000\000\000\000\000\000\00000"
+/* offset=129719 */ "Frontend_Bound_SMT\000\000idq_uops_not_delivered.core / (4 * (cpu_clk_unhalted.thread / 2 * (1 + cpu_clk_unhalted.one_thread_active / cpu_clk_unhalted.ref_xclk)))\000\000\000\000\000\000\000\00000"
+/* offset=129885 */ "dcache_miss_cpi\000\000l1d\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000"
+/* offset=129949 */ "icache_miss_cycles\000\000l1i\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000"
+/* offset=130016 */ "cache_miss_cycles\000group1\000dcache_miss_cpi + icache_miss_cycles\000\000\000\000\000\000\000\00000"
+/* offset=130087 */ "DCache_L2_All_Hits\000\000l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hit\000\000\000\000\000\000\000\00000"
+/* offset=130181 */ "DCache_L2_All_Miss\000\000max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) + l2_rqsts.pf_miss + l2_rqsts.rfo_miss\000\000\000\000\000\000\000\00000"
+/* offset=130315 */ "DCache_L2_All\000\000DCache_L2_All_Hits + DCache_L2_All_Miss\000\000\000\000\000\000\000\00000"
+/* offset=130379 */ "DCache_L2_Hits\000\000d_ratio(DCache_L2_All_Hits, DCache_L2_All)\000\000\000\000\000\000\000\00000"
+/* offset=130447 */ "DCache_L2_Misses\000\000d_ratio(DCache_L2_All_Miss, DCache_L2_All)\000\000\000\000\000\000\000\00000"
+/* offset=130517 */ "M1\000\000ipc + M2\000\000\000\000\000\000\000\00000"
+/* offset=130539 */ "M2\000\000ipc + M1\000\000\000\000\000\000\000\00000"
+/* offset=130561 */ "M3\000\0001 / M3\000\000\000\000\000\000\000\00000"
+/* offset=130581 */ "L1D_Cache_Fill_BW\000\00064 * l1d.replacement / 1e9 / duration_time\000\000\000\000\000\000\000\00000"
;
static const struct compact_pmu_event pmu_events__common_default_core[] = {
@@ -2603,6 +2614,29 @@ static const struct pmu_table_entry pmu_events__common[] = {
},
};
+static const struct compact_pmu_event pmu_metrics__common_default_core[] = {
+{ 127742 }, /* CPUs_utilized\000Default\000(software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@...k\\-clock\\,name\\=task\\-clock@) / (duration_time * 1e9)\000\000Average CPU utilization\000\0001CPUs\000\000\000\00001 */
+{ 129052 }, /* backend_cycles_idle\000Default\000stalled\\-cycles\\-backend / cpu\\-cycles\000backend_cycles_idle > 0.2\000Backend stalls per cycle\000\000\000\000\000\00000 */
+{ 129352 }, /* branch_frequency\000Default\000branches / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@...k\\-clock\\,name\\=task\\-clock@)\000\000Branches per CPU second\000\0001000K/sec\000\000\000\00001 */
+{ 129531 }, /* branch_miss_rate\000Default\000branch\\-misses / branches\000branch_miss_rate > 0.05\000Branch miss rate\000\000100%\000\000\000\00000 */
+{ 127927 }, /* cs_per_second\000Default\000software@...text\\-switches\\,name\\=context\\-switches@ * 1e9 / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@...k\\-clock\\,name\\=task\\-clock@)\000\000Context switches per CPU second\000\0001cs/sec\000\000\000\00001 */
+{ 129177 }, /* cycles_frequency\000Default\000cpu\\-cycles / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@...k\\-clock\\,name\\=task\\-clock@)\000\000Cycles per CPU second\000\0001GHz\000\000\000\00001 */
+{ 128923 }, /* frontend_cycles_idle\000Default\000stalled\\-cycles\\-frontend / cpu\\-cycles\000frontend_cycles_idle > 0.1\000Frontend stalls per cycle\000\000\000\000\000\00000 */
+{ 128648 }, /* insn_per_cycle\000Default\000instructions / cpu\\-cycles\000insn_per_cycle < 1\000Instructions Per Cycle\000\0001instructions\000\000\000\00000 */
+{ 128159 }, /* migrations_per_second\000Default\000software@cpu\\-migrations\\,name\\=cpu\\-migrations@ * 1e9 / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@...k\\-clock\\,name\\=task\\-clock@)\000\000Process migrations to a new CPU per CPU second\000\0001migrations/sec\000\000\000\00001 */
+{ 128418 }, /* page_faults_per_second\000Default\000software@...e\\-faults\\,name\\=page\\-faults@ * 1e9 / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@...k\\-clock\\,name\\=task\\-clock@)\000\000Page faults per CPU second\000\0001faults/sec\000\000\000\00001 */
+{ 128760 }, /* stalled_cycles_per_instruction\000Default\000max(stalled\\-cycles\\-frontend, stalled\\-cycles\\-backend) / instructions\000\000Max front or backend stalls per instruction\000\000\000\000\000\00000 */
+
+};
+
+static const struct pmu_table_entry pmu_metrics__common[] = {
+{
+ .entries = pmu_metrics__common_default_core,
+ .num_entries = ARRAY_SIZE(pmu_metrics__common_default_core),
+ .pmu_name = { 0 /* default_core\000 */ },
+},
+};
+
static const struct compact_pmu_event pmu_events__test_soc_cpu_default_core[] = {
{ 126189 }, /* bp_l1_btb_correct\000branch\000L1 BTB Correction\000event=0x8a\000\00000\000\000\000\000\000 */
{ 126251 }, /* bp_l2_btb_correct\000branch\000L2 BTB Correction\000event=0x8b\000\00000\000\000\000\000\000 */
@@ -2664,21 +2698,21 @@ static const struct pmu_table_entry pmu_events__test_soc_cpu[] = {
};
static const struct compact_pmu_event pmu_metrics__test_soc_cpu_default_core[] = {
-{ 127742 }, /* CPI\000\0001 / IPC\000\000\000\000\000\000\000\00000 */
-{ 128423 }, /* DCache_L2_All\000\000DCache_L2_All_Hits + DCache_L2_All_Miss\000\000\000\000\000\000\000\00000 */
-{ 128195 }, /* DCache_L2_All_Hits\000\000l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hit\000\000\000\000\000\000\000\00000 */
-{ 128289 }, /* DCache_L2_All_Miss\000\000max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) + l2_rqsts.pf_miss + l2_rqsts.rfo_miss\000\000\000\000\000\000\000\00000 */
-{ 128487 }, /* DCache_L2_Hits\000\000d_ratio(DCache_L2_All_Hits, DCache_L2_All)\000\000\000\000\000\000\000\00000 */
-{ 128555 }, /* DCache_L2_Misses\000\000d_ratio(DCache_L2_All_Miss, DCache_L2_All)\000\000\000\000\000\000\000\00000 */
-{ 127827 }, /* Frontend_Bound_SMT\000\000idq_uops_not_delivered.core / (4 * (cpu_clk_unhalted.thread / 2 * (1 + cpu_clk_unhalted.one_thread_active / cpu_clk_unhalted.ref_xclk)))\000\000\000\000\000\000\000\00000 */
-{ 127764 }, /* IPC\000group1\000inst_retired.any / cpu_clk_unhalted.thread\000\000\000\000\000\000\000\00000 */
-{ 128689 }, /* L1D_Cache_Fill_BW\000\00064 * l1d.replacement / 1e9 / duration_time\000\000\000\000\000\000\000\00000 */
-{ 128625 }, /* M1\000\000ipc + M2\000\000\000\000\000\000\000\00000 */
-{ 128647 }, /* M2\000\000ipc + M1\000\000\000\000\000\000\000\00000 */
-{ 128669 }, /* M3\000\0001 / M3\000\000\000\000\000\000\000\00000 */
-{ 128124 }, /* cache_miss_cycles\000group1\000dcache_miss_cpi + icache_miss_cycles\000\000\000\000\000\000\000\00000 */
-{ 127993 }, /* dcache_miss_cpi\000\000l1d\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000 */
-{ 128057 }, /* icache_miss_cycles\000\000l1i\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000 */
+{ 129634 }, /* CPI\000\0001 / IPC\000\000\000\000\000\000\000\00000 */
+{ 130315 }, /* DCache_L2_All\000\000DCache_L2_All_Hits + DCache_L2_All_Miss\000\000\000\000\000\000\000\00000 */
+{ 130087 }, /* DCache_L2_All_Hits\000\000l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hit\000\000\000\000\000\000\000\00000 */
+{ 130181 }, /* DCache_L2_All_Miss\000\000max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) + l2_rqsts.pf_miss + l2_rqsts.rfo_miss\000\000\000\000\000\000\000\00000 */
+{ 130379 }, /* DCache_L2_Hits\000\000d_ratio(DCache_L2_All_Hits, DCache_L2_All)\000\000\000\000\000\000\000\00000 */
+{ 130447 }, /* DCache_L2_Misses\000\000d_ratio(DCache_L2_All_Miss, DCache_L2_All)\000\000\000\000\000\000\000\00000 */
+{ 129719 }, /* Frontend_Bound_SMT\000\000idq_uops_not_delivered.core / (4 * (cpu_clk_unhalted.thread / 2 * (1 + cpu_clk_unhalted.one_thread_active / cpu_clk_unhalted.ref_xclk)))\000\000\000\000\000\000\000\00000 */
+{ 129656 }, /* IPC\000group1\000inst_retired.any / cpu_clk_unhalted.thread\000\000\000\000\000\000\000\00000 */
+{ 130581 }, /* L1D_Cache_Fill_BW\000\00064 * l1d.replacement / 1e9 / duration_time\000\000\000\000\000\000\000\00000 */
+{ 130517 }, /* M1\000\000ipc + M2\000\000\000\000\000\000\000\00000 */
+{ 130539 }, /* M2\000\000ipc + M1\000\000\000\000\000\000\000\00000 */
+{ 130561 }, /* M3\000\0001 / M3\000\000\000\000\000\000\000\00000 */
+{ 130016 }, /* cache_miss_cycles\000group1\000dcache_miss_cpi + icache_miss_cycles\000\000\000\000\000\000\000\00000 */
+{ 129885 }, /* dcache_miss_cpi\000\000l1d\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000 */
+{ 129949 }, /* icache_miss_cycles\000\000l1i\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000 */
};
@@ -2759,7 +2793,10 @@ static const struct pmu_events_map pmu_events_map[] = {
.pmus = pmu_events__common,
.num_pmus = ARRAY_SIZE(pmu_events__common),
},
- .metric_table = {},
+ .metric_table = {
+ .pmus = pmu_metrics__common,
+ .num_pmus = ARRAY_SIZE(pmu_metrics__common),
+ },
},
{
.arch = "testarch",
@@ -3208,6 +3245,22 @@ const struct pmu_metrics_table *pmu_metrics_table__find(void)
return map ? &map->metric_table : NULL;
}
+const struct pmu_metrics_table *pmu_metrics_table__default(void)
+{
+ int i = 0;
+
+ for (;;) {
+ const struct pmu_events_map *map = &pmu_events_map[i++];
+
+ if (!map->arch)
+ break;
+
+ if (!strcmp(map->cpuid, "common"))
+ return &map->metric_table;
+ }
+ return NULL;
+}
+
const struct pmu_events_table *find_core_events_table(const char *arch, const char *cpuid)
{
for (const struct pmu_events_map *tables = &pmu_events_map[0];
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 786a7049363f..5d3f4b44cfb7 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -755,7 +755,10 @@ static const struct pmu_events_map pmu_events_map[] = {
\t\t.pmus = pmu_events__common,
\t\t.num_pmus = ARRAY_SIZE(pmu_events__common),
\t},
-\t.metric_table = {},
+\t.metric_table = {
+\t\t.pmus = pmu_metrics__common,
+\t\t.num_pmus = ARRAY_SIZE(pmu_metrics__common),
+\t},
},
""")
else:
@@ -1237,6 +1240,22 @@ const struct pmu_metrics_table *pmu_metrics_table__find(void)
return map ? &map->metric_table : NULL;
}
+const struct pmu_metrics_table *pmu_metrics_table__default(void)
+{
+ int i = 0;
+
+ for (;;) {
+ const struct pmu_events_map *map = &pmu_events_map[i++];
+
+ if (!map->arch)
+ break;
+
+ if (!strcmp(map->cpuid, "common"))
+ return &map->metric_table;
+ }
+ return NULL;
+}
+
const struct pmu_events_table *find_core_events_table(const char *arch, const char *cpuid)
{
for (const struct pmu_events_map *tables = &pmu_events_map[0];
diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index e0535380c0b2..559265a903c8 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/tools/perf/pmu-events/pmu-events.h
@@ -127,6 +127,7 @@ int pmu_metrics_table__find_metric(const struct pmu_metrics_table *table,
const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu);
const struct pmu_events_table *perf_pmu__default_core_events_table(void);
const struct pmu_metrics_table *pmu_metrics_table__find(void);
+const struct pmu_metrics_table *pmu_metrics_table__default(void);
const struct pmu_events_table *find_core_events_table(const char *arch, const char *cpuid);
const struct pmu_metrics_table *find_core_metrics_table(const char *arch, const char *cpuid);
int pmu_for_each_core_event(pmu_event_iter_fn fn, void *data);
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 76092ee26761..e67e04ce01c9 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -424,10 +424,18 @@ int metricgroup__for_each_metric(const struct pmu_metrics_table *table, pmu_metr
.fn = fn,
.data = data,
};
+ const struct pmu_metrics_table *tables[2] = {
+ table,
+ pmu_metrics_table__default(),
+ };
+
+ for (size_t i = 0; i < ARRAY_SIZE(tables); i++) {
+ int ret;
- if (table) {
- int ret = pmu_metrics_table__for_each_metric(table, fn, data);
+ if (!tables[i])
+ continue;
+ ret = pmu_metrics_table__for_each_metric(tables[i], fn, data);
if (ret)
return ret;
}
@@ -1581,19 +1589,22 @@ static int metricgroup__has_metric_or_groups_callback(const struct pmu_metric *p
bool metricgroup__has_metric_or_groups(const char *pmu, const char *metric_or_groups)
{
- const struct pmu_metrics_table *table = pmu_metrics_table__find();
+ const struct pmu_metrics_table *tables[2] = {
+ pmu_metrics_table__find(),
+ pmu_metrics_table__default(),
+ };
struct metricgroup__has_metric_data data = {
.pmu = pmu,
.metric_or_groups = metric_or_groups,
};
- if (!table)
- return false;
-
- return pmu_metrics_table__for_each_metric(table,
- metricgroup__has_metric_or_groups_callback,
- &data)
- ? true : false;
+ for (size_t i = 0; i < ARRAY_SIZE(tables); i++) {
+ if (pmu_metrics_table__for_each_metric(tables[i],
+ metricgroup__has_metric_or_groups_callback,
+ &data))
+ return true;
+ }
+ return false;
}
static int metricgroup__topdown_max_level_callback(const struct pmu_metric *pm,
--
2.51.1.821.gb6fe4d2222-goog
Powered by blists - more mailing lists