| 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: <20250322063403.364981-3-irogers@google.com>
Date: Fri, 21 Mar 2025 23:33:30 -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>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>, Jiri Olsa <jolsa@...nel.org>,
Ian Rogers <irogers@...gle.com>, Adrian Hunter <adrian.hunter@...el.com>,
Kan Liang <kan.liang@...ux.intel.com>,
"Andreas Färber" <afaerber@...e.de>, Manivannan Sadhasivam <manivannan.sadhasivam@...aro.org>,
Maxime Coquelin <mcoquelin.stm32@...il.com>, Alexandre Torgue <alexandre.torgue@...s.st.com>,
Caleb Biggers <caleb.biggers@...el.com>, Weilin Wang <weilin.wang@...el.com>,
linux-kernel@...r.kernel.org, linux-perf-users@...r.kernel.org,
Perry Taylor <perry.taylor@...el.com>, Thomas Falcon <thomas.falcon@...el.com>
Subject: [PATCH v1 02/35] perf vendor events: Update AlderlakeN events/metrics
Update events from v1.28 to v1.29.
Update event topics, metrics to be generated from the TMA spreadsheet
and other small clean ups.
Signed-off-by: Ian Rogers <irogers@...gle.com>
---
.../arch/x86/alderlaken/adln-metrics.json | 54 +++++-----
.../pmu-events/arch/x86/alderlaken/cache.json | 50 ++++++++++
.../arch/x86/alderlaken/memory.json | 40 ++++++++
.../pmu-events/arch/x86/alderlaken/other.json | 98 -------------------
.../arch/x86/alderlaken/pipeline.json | 11 ++-
tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +-
6 files changed, 128 insertions(+), 127 deletions(-)
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
index ad04b1e3881e..ce93648043ef 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
@@ -75,7 +75,7 @@
"MetricExpr": "tma_core_bound",
"MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
"MetricName": "tma_allocation_restriction",
- "MetricThreshold": "(tma_allocation_restriction >0.10) & ((tma_core_bound >0.10) & ((tma_backend_bound >0.10)))",
+ "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)",
"ScaleUnit": "100%"
},
{
@@ -84,7 +84,7 @@
"MetricExpr": "TOPDOWN_BE_BOUND.ALL / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "Default;TopdownL1;tma_L1_group",
"MetricName": "tma_backend_bound",
- "MetricThreshold": "(tma_backend_bound >0.10)",
+ "MetricThreshold": "tma_backend_bound > 0.1",
"MetricgroupNoGroup": "TopdownL1;Default",
"PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count",
"ScaleUnit": "100%"
@@ -95,7 +95,7 @@
"MetricExpr": "(5 * CPU_CLK_UNHALTED.CORE - (TOPDOWN_FE_BOUND.ALL + TOPDOWN_BE_BOUND.ALL + TOPDOWN_RETIRING.ALL)) / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "Default;TopdownL1;tma_L1_group",
"MetricName": "tma_bad_speculation",
- "MetricThreshold": "(tma_bad_speculation >0.15)",
+ "MetricThreshold": "tma_bad_speculation > 0.15",
"MetricgroupNoGroup": "TopdownL1;Default",
"PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
"ScaleUnit": "100%"
@@ -105,7 +105,7 @@
"MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
"MetricName": "tma_branch_detect",
- "MetricThreshold": "(tma_branch_detect >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+ "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
"PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
"ScaleUnit": "100%"
},
@@ -114,7 +114,7 @@
"MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
"MetricName": "tma_branch_mispredicts",
- "MetricThreshold": "(tma_branch_mispredicts >0.05) & ((tma_bad_speculation >0.15))",
+ "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15",
"MetricgroupNoGroup": "TopdownL2",
"ScaleUnit": "100%"
},
@@ -123,7 +123,7 @@
"MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
"MetricName": "tma_branch_resteer",
- "MetricThreshold": "(tma_branch_resteer >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+ "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
"ScaleUnit": "100%"
},
{
@@ -131,7 +131,7 @@
"MetricExpr": "TOPDOWN_FE_BOUND.CISC / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
"MetricName": "tma_cisc",
- "MetricThreshold": "(tma_cisc >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+ "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
"ScaleUnit": "100%"
},
{
@@ -139,7 +139,7 @@
"MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
"MetricName": "tma_core_bound",
- "MetricThreshold": "(tma_core_bound >0.10) & ((tma_backend_bound >0.10))",
+ "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1",
"MetricgroupNoGroup": "TopdownL2",
"ScaleUnit": "100%"
},
@@ -148,7 +148,7 @@
"MetricExpr": "TOPDOWN_FE_BOUND.DECODE / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
"MetricName": "tma_decode",
- "MetricThreshold": "(tma_decode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+ "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
"ScaleUnit": "100%"
},
{
@@ -156,7 +156,7 @@
"MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
"MetricName": "tma_fast_nuke",
- "MetricThreshold": "(tma_fast_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))",
+ "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
"ScaleUnit": "100%"
},
{
@@ -165,7 +165,7 @@
"MetricExpr": "TOPDOWN_FE_BOUND.ALL / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "Default;TopdownL1;tma_L1_group",
"MetricName": "tma_frontend_bound",
- "MetricThreshold": "(tma_frontend_bound >0.20)",
+ "MetricThreshold": "tma_frontend_bound > 0.2",
"MetricgroupNoGroup": "TopdownL1;Default",
"ScaleUnit": "100%"
},
@@ -174,7 +174,7 @@
"MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
"MetricName": "tma_icache_misses",
- "MetricThreshold": "(tma_icache_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+ "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
"ScaleUnit": "100%"
},
{
@@ -182,7 +182,7 @@
"MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
"MetricName": "tma_ifetch_bandwidth",
- "MetricThreshold": "(tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20))",
+ "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2",
"MetricgroupNoGroup": "TopdownL2",
"ScaleUnit": "100%"
},
@@ -191,7 +191,7 @@
"MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
"MetricName": "tma_ifetch_latency",
- "MetricThreshold": "(tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20))",
+ "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2",
"MetricgroupNoGroup": "TopdownL2",
"ScaleUnit": "100%"
},
@@ -473,7 +473,7 @@
"BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
"MetricExpr": "CPU_CLK_UNHALTED.CORE_P / CPU_CLK_UNHALTED.CORE",
"MetricName": "tma_info_system_mux",
- "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))"
+ "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9"
},
{
"BriefDescription": "Average Frequency Utilization relative nominal frequency",
@@ -506,7 +506,7 @@
"MetricExpr": "TOPDOWN_FE_BOUND.ITLB / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
"MetricName": "tma_itlb_misses",
- "MetricThreshold": "(tma_itlb_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+ "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
"ScaleUnit": "100%"
},
{
@@ -514,7 +514,7 @@
"MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
"MetricName": "tma_machine_clears",
- "MetricThreshold": "(tma_machine_clears >0.05) & ((tma_bad_speculation >0.15))",
+ "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15",
"MetricgroupNoGroup": "TopdownL2",
"ScaleUnit": "100%"
},
@@ -523,7 +523,7 @@
"MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
"MetricName": "tma_mem_scheduler",
- "MetricThreshold": "(tma_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+ "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
"ScaleUnit": "100%"
},
{
@@ -531,7 +531,7 @@
"MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
"MetricName": "tma_non_mem_scheduler",
- "MetricThreshold": "(tma_non_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+ "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
"ScaleUnit": "100%"
},
{
@@ -539,7 +539,7 @@
"MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
"MetricName": "tma_nuke",
- "MetricThreshold": "(tma_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))",
+ "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
"ScaleUnit": "100%"
},
{
@@ -547,7 +547,7 @@
"MetricExpr": "TOPDOWN_FE_BOUND.OTHER / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
"MetricName": "tma_other_fb",
- "MetricThreshold": "(tma_other_fb >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+ "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
"ScaleUnit": "100%"
},
{
@@ -555,7 +555,7 @@
"MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
"MetricName": "tma_predecode",
- "MetricThreshold": "(tma_predecode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+ "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
"ScaleUnit": "100%"
},
{
@@ -563,7 +563,7 @@
"MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
"MetricName": "tma_register",
- "MetricThreshold": "(tma_register >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+ "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
"ScaleUnit": "100%"
},
{
@@ -571,7 +571,7 @@
"MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
"MetricName": "tma_reorder_buffer",
- "MetricThreshold": "(tma_reorder_buffer >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+ "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
"ScaleUnit": "100%"
},
{
@@ -579,7 +579,7 @@
"MetricExpr": "tma_backend_bound - tma_core_bound",
"MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
"MetricName": "tma_resource_bound",
- "MetricThreshold": "(tma_resource_bound >0.20) & ((tma_backend_bound >0.10))",
+ "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1",
"MetricgroupNoGroup": "TopdownL2",
"ScaleUnit": "100%"
},
@@ -589,7 +589,7 @@
"MetricExpr": "TOPDOWN_RETIRING.ALL / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "Default;TopdownL1;tma_L1_group",
"MetricName": "tma_retiring",
- "MetricThreshold": "(tma_retiring >0.75)",
+ "MetricThreshold": "tma_retiring > 0.75",
"MetricgroupNoGroup": "TopdownL1;Default",
"ScaleUnit": "100%"
},
@@ -598,7 +598,7 @@
"MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / (5 * CPU_CLK_UNHALTED.CORE)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
"MetricName": "tma_serialization",
- "MetricThreshold": "(tma_serialization >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+ "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
"ScaleUnit": "100%"
}
]
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/cache.json b/tools/perf/pmu-events/arch/x86/alderlaken/cache.json
index fd9ed58c2f90..605d56311dfc 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/cache.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/cache.json
@@ -396,6 +396,26 @@
"SampleAfterValue": "1000003",
"UMask": "0x6"
},
+ {
+ "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.COREWB_M.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x10008",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
+ },
+ {
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x10004",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
+ },
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache.",
"Counter": "0,1,2,3,4,5",
@@ -436,6 +456,16 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
+ {
+ "BriefDescription": "Counts demand data reads that have any type of response.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x10001",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
+ },
{
"BriefDescription": "Counts demand data reads that were supplied by the L3 cache.",
"Counter": "0,1,2,3,4,5",
@@ -476,6 +506,16 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
+ {
+ "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x10002",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
+ },
{
"BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache.",
"Counter": "0,1,2,3,4,5",
@@ -516,6 +556,16 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
+ {
+ "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.SWPF_RD.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x14000",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
+ },
{
"BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache.",
"Counter": "0,1,2,3,4,5",
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/memory.json b/tools/perf/pmu-events/arch/x86/alderlaken/memory.json
index 3b46b048dfb2..06eca0a45c18 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/memory.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/memory.json
@@ -56,6 +56,16 @@
"SampleAfterValue": "20003",
"UMask": "0x2"
},
+ {
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_CODE_RD.DRAM",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x784000004",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
+ },
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache.",
"Counter": "0,1,2,3,4,5",
@@ -66,6 +76,16 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
+ {
+ "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x784000001",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
+ },
{
"BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
"Counter": "0,1,2,3,4,5",
@@ -86,6 +106,16 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
+ {
+ "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_RFO.DRAM",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x784000002",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
+ },
{
"BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.",
"Counter": "0,1,2,3,4,5",
@@ -106,6 +136,16 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
+ {
+ "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM.",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0xB7",
+ "EventName": "OCR.SWPF_RD.DRAM",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x784004000",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1"
+ },
{
"BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were not supplied by the L3 cache.",
"Counter": "0,1,2,3,4,5",
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/other.json b/tools/perf/pmu-events/arch/x86/alderlaken/other.json
index f8c21b7f8f40..0ebcb3e20e1d 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/other.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/other.json
@@ -8,76 +8,6 @@
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
- {
- "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.",
- "Counter": "0,1,2,3,4,5",
- "EventCode": "0xB7",
- "EventName": "OCR.COREWB_M.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x10008",
- "SampleAfterValue": "100003",
- "UMask": "0x1"
- },
- {
- "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
- "Counter": "0,1,2,3,4,5",
- "EventCode": "0xB7",
- "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x10004",
- "SampleAfterValue": "100003",
- "UMask": "0x1"
- },
- {
- "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
- "Counter": "0,1,2,3,4,5",
- "EventCode": "0xB7",
- "EventName": "OCR.DEMAND_CODE_RD.DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x784000004",
- "SampleAfterValue": "100003",
- "UMask": "0x1"
- },
- {
- "BriefDescription": "Counts demand data reads that have any type of response.",
- "Counter": "0,1,2,3,4,5",
- "EventCode": "0xB7",
- "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x10001",
- "SampleAfterValue": "100003",
- "UMask": "0x1"
- },
- {
- "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
- "Counter": "0,1,2,3,4,5",
- "EventCode": "0xB7",
- "EventName": "OCR.DEMAND_DATA_RD.DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x784000001",
- "SampleAfterValue": "100003",
- "UMask": "0x1"
- },
- {
- "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
- "Counter": "0,1,2,3,4,5",
- "EventCode": "0xB7",
- "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x10002",
- "SampleAfterValue": "100003",
- "UMask": "0x1"
- },
- {
- "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
- "Counter": "0,1,2,3,4,5",
- "EventCode": "0xB7",
- "EventName": "OCR.DEMAND_RFO.DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x784000002",
- "SampleAfterValue": "100003",
- "UMask": "0x1"
- },
{
"BriefDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response.",
"Counter": "0,1,2,3,4,5",
@@ -107,33 +37,5 @@
"MSRValue": "0x10800",
"SampleAfterValue": "100003",
"UMask": "0x1"
- },
- {
- "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response.",
- "Counter": "0,1,2,3,4,5",
- "EventCode": "0xB7",
- "EventName": "OCR.SWPF_RD.ANY_RESPONSE",
- "MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x14000",
- "SampleAfterValue": "100003",
- "UMask": "0x1"
- },
- {
- "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM.",
- "Counter": "0,1,2,3,4,5",
- "EventCode": "0xB7",
- "EventName": "OCR.SWPF_RD.DRAM",
- "MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x784004000",
- "SampleAfterValue": "100003",
- "UMask": "0x1"
- },
- {
- "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state)",
- "Counter": "0,1,2,3,4,5",
- "EventCode": "0x75",
- "EventName": "SERIALIZATION.C01_MS_SCB",
- "SampleAfterValue": "200003",
- "UMask": "0x4"
}
]
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json b/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json
index 713ebc21cec0..0cc8cd203fc3 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json
@@ -399,8 +399,9 @@
"UMask": "0x20"
},
{
- "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine with the use of microcode due to SMC, MEMORY_ORDERING, FP_ASSISTS, PAGE_FAULT, DISAMBIGUATION, and FPC_VIRTUAL_TRAP.",
+ "BriefDescription": "This event is deprecated.",
"Counter": "0,1,2,3,4,5",
+ "Deprecated": "1",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.SLOW",
"SampleAfterValue": "20003",
@@ -423,6 +424,14 @@
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
+ {
+ "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state)",
+ "Counter": "0,1,2,3,4,5",
+ "EventCode": "0x75",
+ "EventName": "SERIALIZATION.C01_MS_SCB",
+ "SampleAfterValue": "200003",
+ "UMask": "0x4"
+ },
{
"BriefDescription": "Counts the number of issue slots not consumed by the backend due to a micro-sequencer (MS) scoreboard, which stalls the front-end from issuing from the UROM until a specified older uop retires.",
"Counter": "0,1,2,3,4,5",
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 881f418137fd..0ef31b65f8df 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -1,6 +1,6 @@
Family-model,Version,Filename,EventType
GenuineIntel-6-(97|9A|B7|BA|BF),v1.29,alderlake,core
-GenuineIntel-6-BE,v1.28,alderlaken,core
+GenuineIntel-6-BE,v1.29,alderlaken,core
GenuineIntel-6-C[56],v1.07,arrowlake,core
GenuineIntel-6-(1C|26|27|35|36),v5,bonnell,core
GenuineIntel-6-(3D|47),v30,broadwell,core
--
2.49.0.395.g12beb8f557-goog
Powered by blists - more mailing lists