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 2

 Performance counter stats for 'system wide':

              0.00 msec cpu-clock                        #    0.000 CPUs utilized
            77,739      context-switches
            15,033      cpu-migrations
           321,313      page-faults
    14,355,634,225      cpu_atom/instructions/           #    1.40  insn per cycle              (35.37%)
   134,561,560,583      cpu_core/instructions/           #    3.44  insn per cycle              (57.85%)
    10,263,836,145      cpu_atom/cycles/                                                        (35.42%)
    39,138,632,894      cpu_core/cycles/                                                        (57.60%)
     2,989,658,777      cpu_atom/branches/                                                      (42.60%)
    32,170,570,388      cpu_core/branches/                                                      (57.39%)
        29,789,870      cpu_atom/branch-misses/          #    1.00% of all branches             (42.69%)
       165,991,152      cpu_core/branch-misses/          #    0.52% of all branches             (57.19%)
                       (software)                 #      nan cs/sec  cs_per_second
             TopdownL1 (cpu_core)                 #     11.9 %  tma_bad_speculation
                                                  #     19.6 %  tma_frontend_bound       (63.97%)
             TopdownL1 (cpu_core)                 #     18.8 %  tma_backend_bound
                                                  #     49.7 %  tma_retiring             (63.97%)
                       (software)                 #      nan faults/sec  page_faults_per_second
                                                  #      nan GHz  cycles_frequency       (42.88%)
                                                  #      nan GHz  cycles_frequency       (69.88%)
             TopdownL1 (cpu_atom)                 #     11.7 %  tma_bad_speculation
                                                  #     29.9 %  tma_retiring             (50.07%)
             TopdownL1 (cpu_atom)                 #     31.3 %  tma_frontend_bound       (43.09%)
                       (cpu_atom)                 #      nan M/sec  branch_frequency     (43.09%)
                                                  #      nan M/sec  branch_frequency     (70.07%)
                                                  #      nan migrations/sec  migrations_per_second
             TopdownL1 (cpu_atom)                 #     27.1 %  tma_backend_bound        (43.08%)
                       (software)                 #      0.0 CPUs  CPUs_utilized
                                                  #      1.4 instructions  insn_per_cycle  (43.04%)
                                                  #      3.5 instructions  insn_per_cycle  (69.99%)
                                                  #      1.0 %  branch_miss_rate         (35.46%)
                                                  #      0.5 %  branch_miss_rate         (65.02%)

       2.005626564 seconds time elapsed
```

Signed-off-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>

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 (file)
index 0000000..d915be5
--- /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@task\\-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@context\\-switches\\,name\\=context\\-switches@ * 1e9) / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@task\\-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@task\\-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@page\\-faults\\,name\\=page\\-faults@ * 1e9) / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@task\\-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@task\\-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@task\\-clock\\,name\\=task\\-clock@)",
+        "MetricGroup": "Default",
+        "MetricName": "branch_frequency",
+        "ScaleUnit": "1000M/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 2fdf4fbf36e258403fc3964099833016248304ff..e4d00f6b2b5d98ad8ec2c484efb0c022b18895d1 100644 (file)
--- 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=127519 */ "sys_ccn_pmu.read_cycles\000uncore\000ccn read-cycles event\000config=0x2c\0000x01\00000\000\000\000\000\000"
 /* offset=127596 */ "uncore_sys_cmn_pmu\000"
 /* offset=127615 */ "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=127758 */ "CPI\000\0001 / IPC\000\000\000\000\000\000\000\00000"
-/* offset=127780 */ "IPC\000group1\000inst_retired.any / cpu_clk_unhalted.thread\000\000\000\000\000\000\000\00000"
-/* offset=127843 */ "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=128009 */ "dcache_miss_cpi\000\000l1d\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000"
-/* offset=128073 */ "icache_miss_cycles\000\000l1i\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000"
-/* offset=128140 */ "cache_miss_cycles\000group1\000dcache_miss_cpi + icache_miss_cycles\000\000\000\000\000\000\000\00000"
-/* offset=128211 */ "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=128305 */ "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=128439 */ "DCache_L2_All\000\000DCache_L2_All_Hits + DCache_L2_All_Miss\000\000\000\000\000\000\000\00000"
-/* offset=128503 */ "DCache_L2_Hits\000\000d_ratio(DCache_L2_All_Hits, DCache_L2_All)\000\000\000\000\000\000\000\00000"
-/* offset=128571 */ "DCache_L2_Misses\000\000d_ratio(DCache_L2_All_Miss, DCache_L2_All)\000\000\000\000\000\000\000\00000"
-/* offset=128641 */ "M1\000\000ipc + M2\000\000\000\000\000\000\000\00000"
-/* offset=128663 */ "M2\000\000ipc + M1\000\000\000\000\000\000\000\00000"
-/* offset=128685 */ "M3\000\0001 / M3\000\000\000\000\000\000\000\00000"
-/* offset=128705 */ "L1D_Cache_Fill_BW\000\00064 * l1d.replacement / 1e9 / duration_time\000\000\000\000\000\000\000\00000"
+/* offset=127758 */ "CPUs_utilized\000Default\000(software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@task\\-clock\\,name\\=task\\-clock@) / (duration_time * 1e9)\000\000Average CPU utilization\000\0001CPUs\000\000\000\00001"
+/* offset=127943 */ "cs_per_second\000Default\000software@context\\-switches\\,name\\=context\\-switches@ * 1e9 / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@task\\-clock\\,name\\=task\\-clock@)\000\000Context switches per CPU second\000\0001cs/sec\000\000\000\00001"
+/* offset=128175 */ "migrations_per_second\000Default\000software@cpu\\-migrations\\,name\\=cpu\\-migrations@ * 1e9 / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@task\\-clock\\,name\\=task\\-clock@)\000\000Process migrations to a new CPU per CPU second\000\0001migrations/sec\000\000\000\00001"
+/* offset=128434 */ "page_faults_per_second\000Default\000software@page\\-faults\\,name\\=page\\-faults@ * 1e9 / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@task\\-clock\\,name\\=task\\-clock@)\000\000Page faults per CPU second\000\0001faults/sec\000\000\000\00001"
+/* offset=128664 */ "insn_per_cycle\000Default\000instructions / cpu\\-cycles\000insn_per_cycle < 1\000Instructions Per Cycle\000\0001instructions\000\000\000\00000"
+/* offset=128776 */ "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=128939 */ "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=129068 */ "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=129193 */ "cycles_frequency\000Default\000cpu\\-cycles / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@task\\-clock\\,name\\=task\\-clock@)\000\000Cycles per CPU second\000\0001GHz\000\000\000\00001"
+/* offset=129368 */ "branch_frequency\000Default\000branches / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@task\\-clock\\,name\\=task\\-clock@)\000\000Branches per CPU second\000\0001000M/sec\000\000\000\00001"
+/* offset=129547 */ "branch_miss_rate\000Default\000branch\\-misses / branches\000branch_miss_rate > 0.05\000Branch miss rate\000\000100%\000\000\000\00000"
+/* offset=129650 */ "CPI\000\0001 / IPC\000\000\000\000\000\000\000\00000"
+/* offset=129672 */ "IPC\000group1\000inst_retired.any / cpu_clk_unhalted.thread\000\000\000\000\000\000\000\00000"
+/* offset=129735 */ "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=129901 */ "dcache_miss_cpi\000\000l1d\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000"
+/* offset=129965 */ "icache_miss_cycles\000\000l1i\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000"
+/* offset=130032 */ "cache_miss_cycles\000group1\000dcache_miss_cpi + icache_miss_cycles\000\000\000\000\000\000\000\00000"
+/* offset=130103 */ "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=130197 */ "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=130331 */ "DCache_L2_All\000\000DCache_L2_All_Hits + DCache_L2_All_Miss\000\000\000\000\000\000\000\00000"
+/* offset=130395 */ "DCache_L2_Hits\000\000d_ratio(DCache_L2_All_Hits, DCache_L2_All)\000\000\000\000\000\000\000\00000"
+/* offset=130463 */ "DCache_L2_Misses\000\000d_ratio(DCache_L2_All_Miss, DCache_L2_All)\000\000\000\000\000\000\000\00000"
+/* offset=130533 */ "M1\000\000ipc + M2\000\000\000\000\000\000\000\00000"
+/* offset=130555 */ "M2\000\000ipc + M1\000\000\000\000\000\000\000\00000"
+/* offset=130577 */ "M3\000\0001 / M3\000\000\000\000\000\000\000\00000"
+/* offset=130597 */ "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[] = {
+{ 127758 }, /* CPUs_utilized\000Default\000(software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@task\\-clock\\,name\\=task\\-clock@) / (duration_time * 1e9)\000\000Average CPU utilization\000\0001CPUs\000\000\000\00001 */
+{ 129068 }, /* backend_cycles_idle\000Default\000stalled\\-cycles\\-backend / cpu\\-cycles\000backend_cycles_idle > 0.2\000Backend stalls per cycle\000\000\000\000\000\00000 */
+{ 129368 }, /* branch_frequency\000Default\000branches / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@task\\-clock\\,name\\=task\\-clock@)\000\000Branches per CPU second\000\0001000M/sec\000\000\000\00001 */
+{ 129547 }, /* branch_miss_rate\000Default\000branch\\-misses / branches\000branch_miss_rate > 0.05\000Branch miss rate\000\000100%\000\000\000\00000 */
+{ 127943 }, /* cs_per_second\000Default\000software@context\\-switches\\,name\\=context\\-switches@ * 1e9 / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@task\\-clock\\,name\\=task\\-clock@)\000\000Context switches per CPU second\000\0001cs/sec\000\000\000\00001 */
+{ 129193 }, /* cycles_frequency\000Default\000cpu\\-cycles / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@task\\-clock\\,name\\=task\\-clock@)\000\000Cycles per CPU second\000\0001GHz\000\000\000\00001 */
+{ 128939 }, /* frontend_cycles_idle\000Default\000stalled\\-cycles\\-frontend / cpu\\-cycles\000frontend_cycles_idle > 0.1\000Frontend stalls per cycle\000\000\000\000\000\00000 */
+{ 128664 }, /* insn_per_cycle\000Default\000instructions / cpu\\-cycles\000insn_per_cycle < 1\000Instructions Per Cycle\000\0001instructions\000\000\000\00000 */
+{ 128175 }, /* migrations_per_second\000Default\000software@cpu\\-migrations\\,name\\=cpu\\-migrations@ * 1e9 / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@task\\-clock\\,name\\=task\\-clock@)\000\000Process migrations to a new CPU per CPU second\000\0001migrations/sec\000\000\000\00001 */
+{ 128434 }, /* page_faults_per_second\000Default\000software@page\\-faults\\,name\\=page\\-faults@ * 1e9 / (software@cpu\\-clock\\,name\\=cpu\\-clock@ if #target_cpu else software@task\\-clock\\,name\\=task\\-clock@)\000\000Page faults per CPU second\000\0001faults/sec\000\000\000\00001 */
+{ 128776 }, /* 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[] = {
 { 126205 }, /* bp_l1_btb_correct\000branch\000L1 BTB Correction\000event=0x8a\000\00000\000\000\000\000\000 */
 { 126267 }, /* 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[] = {
-{ 127758 }, /* CPI\000\0001 / IPC\000\000\000\000\000\000\000\00000 */
-{ 128439 }, /* DCache_L2_All\000\000DCache_L2_All_Hits + DCache_L2_All_Miss\000\000\000\000\000\000\000\00000 */
-{ 128211 }, /* 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 */
-{ 128305 }, /* 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 */
-{ 128503 }, /* DCache_L2_Hits\000\000d_ratio(DCache_L2_All_Hits, DCache_L2_All)\000\000\000\000\000\000\000\00000 */
-{ 128571 }, /* DCache_L2_Misses\000\000d_ratio(DCache_L2_All_Miss, DCache_L2_All)\000\000\000\000\000\000\000\00000 */
-{ 127843 }, /* 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 */
-{ 127780 }, /* IPC\000group1\000inst_retired.any / cpu_clk_unhalted.thread\000\000\000\000\000\000\000\00000 */
-{ 128705 }, /* L1D_Cache_Fill_BW\000\00064 * l1d.replacement / 1e9 / duration_time\000\000\000\000\000\000\000\00000 */
-{ 128641 }, /* M1\000\000ipc + M2\000\000\000\000\000\000\000\00000 */
-{ 128663 }, /* M2\000\000ipc + M1\000\000\000\000\000\000\000\00000 */
-{ 128685 }, /* M3\000\0001 / M3\000\000\000\000\000\000\000\00000 */
-{ 128140 }, /* cache_miss_cycles\000group1\000dcache_miss_cpi + icache_miss_cycles\000\000\000\000\000\000\000\00000 */
-{ 128009 }, /* dcache_miss_cpi\000\000l1d\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000 */
-{ 128073 }, /* icache_miss_cycles\000\000l1i\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000 */
+{ 129650 }, /* CPI\000\0001 / IPC\000\000\000\000\000\000\000\00000 */
+{ 130331 }, /* DCache_L2_All\000\000DCache_L2_All_Hits + DCache_L2_All_Miss\000\000\000\000\000\000\000\00000 */
+{ 130103 }, /* 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 */
+{ 130197 }, /* 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 */
+{ 130395 }, /* DCache_L2_Hits\000\000d_ratio(DCache_L2_All_Hits, DCache_L2_All)\000\000\000\000\000\000\000\00000 */
+{ 130463 }, /* DCache_L2_Misses\000\000d_ratio(DCache_L2_All_Miss, DCache_L2_All)\000\000\000\000\000\000\000\00000 */
+{ 129735 }, /* 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 */
+{ 129672 }, /* IPC\000group1\000inst_retired.any / cpu_clk_unhalted.thread\000\000\000\000\000\000\000\00000 */
+{ 130597 }, /* L1D_Cache_Fill_BW\000\00064 * l1d.replacement / 1e9 / duration_time\000\000\000\000\000\000\000\00000 */
+{ 130533 }, /* M1\000\000ipc + M2\000\000\000\000\000\000\000\00000 */
+{ 130555 }, /* M2\000\000ipc + M1\000\000\000\000\000\000\000\00000 */
+{ 130577 }, /* M3\000\0001 / M3\000\000\000\000\000\000\000\00000 */
+{ 130032 }, /* cache_miss_cycles\000group1\000dcache_miss_cpi + icache_miss_cycles\000\000\000\000\000\000\000\00000 */
+{ 129901 }, /* dcache_miss_cpi\000\000l1d\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000 */
+{ 129965 }, /* 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 786a7049363fe65e7e25fc4b453682f2323ff0c8..5d3f4b44cfb7f825f4f837c7b29902d791637a23 100755 (executable)
--- 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 e0535380c0b29dc091a82625475984fd12b9d4a8..559265a903c85f2b71c4432a50734ec52796afc0 100644 (file)
--- 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 76092ee2676161950fa7882bd53c77f0a56a78f5..e67e04ce01c99f1faa1e33ee8175ad9add9d2148 100644 (file)
--- 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,