perf vendor events intel: Update arrowlake events from 1.14 to 1.16

The updated events were published in:
https://github.com/intel/perfmon/commit/f0267f720eeab3b5416886c9e0e132fafcb38bbd
https://github.com/intel/perfmon/commit/d40cfa317e567fb5e8f6cbd92c81feeb7e6bd3dd

Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>

diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/cache.json b/tools/perf/pmu-events/arch/x86/arrowlake/cache.json
index fba4a0672f6c8e05bcf2ce3fc76d8e1d2426bcd1..4c3aa1fab5a86690c8e507185167897801bb446f 100644 (file)
--- a/tools/perf/pmu-events/arch/x86/arrowlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/arrowlake/cache.json
@@ -628,6 +628,15 @@
         "UMask": "0x7f",
         "Unit": "cpu_atom"
     },
+    {
+        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an instruction cache or TLB miss.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x35",
+        "EventName": "MEM_BOUND_STALLS_IFETCH.ALL",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x7f",
+        "Unit": "cpu_lowpower"
+    },
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to an instruction cache or TLB miss which hit in the L2 cache.",
         "Counter": "0,1,2,3,4,5,6,7",
@@ -731,6 +740,24 @@
         "UMask": "0x6",
         "Unit": "cpu_atom"
     },
+    {
+        "BriefDescription": "Counts the number of unhalted cycles that the core is stalled due to a demand load miss which hit in the LLC, no snoop was required, and the LLC provided data",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x34",
+        "EventName": "MEM_BOUND_STALLS_LOAD.LLC_HIT_NOSNOOP",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which hit in the LLC, a snoop was required, the snoop misses or the snoop hits but no fwd. LLC provides the data",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x34",
+        "EventName": "MEM_BOUND_STALLS_LOAD.LLC_HIT_SNOOP",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the local caches.",
         "Counter": "0,1,2,3,4,5,6,7",
@@ -749,6 +776,24 @@
         "UMask": "0x78",
         "Unit": "cpu_lowpower"
     },
+    {
+        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the caches.  DRAM, MMIO or other LOCAL memory type provides the data",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x34",
+        "EventName": "MEM_BOUND_STALLS_LOAD.LLC_MISS_LOCALMEM",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x50",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled to a demand load miss and the data was provided from an unknown source. If the core has access to an L3 cache, an LLC miss refers to an L3 cache miss, otherwise it is an L2 cache miss.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x34",
+        "EventName": "MEM_BOUND_STALLS_LOAD.LLC_MISS_LOCALMEM",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x50",
+        "Unit": "cpu_lowpower"
+    },
     {
         "BriefDescription": "Counts the number of unhalted cycles when the core is stalled to a store buffer full condition",
         "Counter": "0,1,2,3,4,5,6,7",
@@ -1081,6 +1126,15 @@
         "UMask": "0x20",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Counts the number of retired load ops with an unknown source",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xd4",
+        "EventName": "MEM_LOAD_UOPS_MISC_RETIRED.LOCAL_DRAM",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Counts the number of load ops retired that miss the L3 cache and hit in DRAM",
         "Counter": "0,1,2,3,4,5,6,7",
@@ -1181,6 +1235,15 @@
         "UMask": "0x1c",
         "Unit": "cpu_lowpower"
     },
+    {
+        "BriefDescription": "Counts the number of load ops retired that hit in the L3 cache in which no snoop was required",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xd1",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT_NO_SNOOP",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Counts the number of loads that hit in a write combining buffer (WCB), excluding the first load that caused the WCB to allocate.",
         "Counter": "0,1,2,3,4,5,6,7",
@@ -1331,7 +1394,7 @@
         "Unit": "cpu_lowpower"
     },
     {
-        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold of 1024. Only counts with PEBS enabled.",
         "Counter": "0,1",
         "Data_LA": "1",
         "EventCode": "0xd0",
@@ -1343,7 +1406,7 @@
         "Unit": "cpu_lowpower"
     },
     {
-        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled",
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold of 128.",
         "Counter": "0,1",
         "Data_LA": "1",
         "EventCode": "0xd0",
@@ -1355,7 +1418,7 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold of 128. Only counts with PEBS enabled.",
         "Counter": "0,1",
         "Data_LA": "1",
         "EventCode": "0xd0",
@@ -1367,7 +1430,7 @@
         "Unit": "cpu_lowpower"
     },
     {
-        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled",
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold of 16.",
         "Counter": "0,1",
         "Data_LA": "1",
         "EventCode": "0xd0",
@@ -1379,7 +1442,7 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold of 16. Only counts with PEBS enabled.",
         "Counter": "0,1",
         "Data_LA": "1",
         "EventCode": "0xd0",
@@ -1391,7 +1454,7 @@
         "Unit": "cpu_lowpower"
     },
     {
-        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold of 2048. Only counts with PEBS enabled.",
         "Counter": "0,1",
         "Data_LA": "1",
         "EventCode": "0xd0",
@@ -1403,7 +1466,7 @@
         "Unit": "cpu_lowpower"
     },
     {
-        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled",
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold of 256.",
         "Counter": "0,1",
         "Data_LA": "1",
         "EventCode": "0xd0",
@@ -1415,7 +1478,7 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold of 256. Only counts with PEBS enabled.",
         "Counter": "0,1",
         "Data_LA": "1",
         "EventCode": "0xd0",
@@ -1427,7 +1490,7 @@
         "Unit": "cpu_lowpower"
     },
     {
-        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled",
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold of 32.",
         "Counter": "0,1",
         "Data_LA": "1",
         "EventCode": "0xd0",
@@ -1439,7 +1502,7 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold of 32. Only counts with PEBS enabled.",
         "Counter": "0,1",
         "Data_LA": "1",
         "EventCode": "0xd0",
@@ -1451,7 +1514,7 @@
         "Unit": "cpu_lowpower"
     },
     {
-        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled",
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold of 4.",
         "Counter": "0,1",
         "Data_LA": "1",
         "EventCode": "0xd0",
@@ -1463,7 +1526,7 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold of 4. Only counts with PEBS enabled.",
         "Counter": "0,1",
         "Data_LA": "1",
         "EventCode": "0xd0",
@@ -1475,7 +1538,7 @@
         "Unit": "cpu_lowpower"
     },
     {
-        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled",
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold of 512.",
         "Counter": "0,1",
         "Data_LA": "1",
         "EventCode": "0xd0",
@@ -1487,7 +1550,7 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold of 512. Only counts with PEBS enabled.",
         "Counter": "0,1",
         "Data_LA": "1",
         "EventCode": "0xd0",
@@ -1499,7 +1562,7 @@
         "Unit": "cpu_lowpower"
     },
     {
-        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled",
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold of 64.",
         "Counter": "0,1",
         "Data_LA": "1",
         "EventCode": "0xd0",
@@ -1511,7 +1574,7 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold of 64. Only counts with PEBS enabled.",
         "Counter": "0,1",
         "Data_LA": "1",
         "EventCode": "0xd0",
@@ -1523,7 +1586,7 @@
         "Unit": "cpu_lowpower"
     },
     {
-        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled",
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold of 8.",
         "Counter": "0,1",
         "Data_LA": "1",
         "EventCode": "0xd0",
@@ -1535,7 +1598,7 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold of 8. Only counts with PEBS enabled.",
         "Counter": "0,1",
         "Data_LA": "1",
         "EventCode": "0xd0",
@@ -1707,7 +1770,7 @@
         "Unit": "cpu_lowpower"
     },
     {
-        "BriefDescription": "Counts the number of  stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES",
+        "BriefDescription": "Counts the number of stores uops retired.",
         "Counter": "0,1,2,3,4,5,6,7",
         "Data_LA": "1",
         "EventCode": "0xd0",
@@ -1717,7 +1780,7 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number of  stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES",
+        "BriefDescription": "Counts the number of stores uops retired.",
         "Counter": "0,1,2,3,4,5,6,7",
         "Data_LA": "1",
         "EventCode": "0xd0",

diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json b/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json
index a15de050a76cf5cd14b068442b400dbf90f6990a..21f00eafa98a674dc2b3cfbc14540597fbd48123 100644 (file)
--- a/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json
@@ -627,6 +627,24 @@
         "UMask": "0x4",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache In use-full",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0x83",
+        "EventName": "ICACHE_TAG.STALLS_INUSE",
+        "SampleAfterValue": "200003",
+        "UMask": "0x10",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache ISB-full",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0x83",
+        "EventName": "ICACHE_TAG.STALLS_ISB",
+        "SampleAfterValue": "200003",
+        "UMask": "0x8",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
         "Counter": "0,1,2,3,4,5,6,7,8,9",

diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json b/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json
index 80561605292555d2df1fabc02f56adeb9bba97c2..fb973c75be577da9df88664eec67fcaf04837f54 100644 (file)
--- a/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json
@@ -822,7 +822,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles.",
+        "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles. [This event is alias to CPU_CLK_UNHALTED.THREAD]",
         "Counter": "Fixed counter 1",
         "EventName": "CPU_CLK_UNHALTED.CORE",
         "SampleAfterValue": "2000003",
@@ -839,7 +839,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles",
+        "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles. [This event is alias to CPU_CLK_UNHALTED.THREAD]",
         "Counter": "Fixed counter 1",
         "EventName": "CPU_CLK_UNHALTED.CORE",
         "SampleAfterValue": "2000003",
@@ -909,7 +909,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Fixed Counter: Counts the number of unhalted reference clock cycles",
+        "BriefDescription": "Fixed Counter: Counts the number of unhalted reference clock cycles.",
         "Counter": "Fixed counter 2",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
         "SampleAfterValue": "2000003",
@@ -947,7 +947,7 @@
         "Unit": "cpu_lowpower"
     },
     {
-        "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles.",
+        "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles. [This event is alias to CPU_CLK_UNHALTED.CORE]",
         "Counter": "Fixed counter 1",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
         "SampleAfterValue": "2000003",
@@ -964,7 +964,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles",
+        "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles. [This event is alias to CPU_CLK_UNHALTED.CORE]",
         "Counter": "Fixed counter 1",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
         "SampleAfterValue": "2000003",
@@ -1134,10 +1134,10 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Fixed Counter: Counts the number of instructions retired",
+        "BriefDescription": "Fixed Counter: Counts the number of instructions retired.",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
-        "PublicDescription": "Fixed Counter: Counts the number of instructions retired Available PDIST counters: 32",
+        "PublicDescription": "Fixed Counter: Counts the number of instructions retired. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_lowpower"
@@ -1607,6 +1607,14 @@
         "SampleAfterValue": "20003",
         "Unit": "cpu_atom"
     },
+    {
+        "BriefDescription": "Counts the total number of machine clears for any reason including, but not limited to, memory ordering, memory disambiguation, SMC, and FP assist.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc3",
+        "EventName": "MACHINE_CLEARS.ANY",
+        "SampleAfterValue": "20003",
+        "Unit": "cpu_lowpower"
+    },
     {
         "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine without the use of microcode.",
         "Counter": "0,1,2,3,4,5,6,7",
@@ -1813,6 +1821,15 @@
         "UMask": "0xff",
         "Unit": "cpu_atom"
     },
+    {
+        "BriefDescription": "Counts the number of CLFLUSH, CLWB, and CLDEMOTE instructions retired.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xe0",
+        "EventName": "MISC_RETIRED1.CL_INST",
+        "SampleAfterValue": "1000003",
+        "UMask": "0xff",
+        "Unit": "cpu_lowpower"
+    },
     {
         "BriefDescription": "Counts the number of LFENCE instructions retired.",
         "Counter": "0,1,2,3,4,5,6,7",
@@ -1822,6 +1839,15 @@
         "UMask": "0x2",
         "Unit": "cpu_atom"
     },
+    {
+        "BriefDescription": "Counts the number of LFENCE instructions retired.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xe0",
+        "EventName": "MISC_RETIRED1.LFENCE",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2",
+        "Unit": "cpu_lowpower"
+    },
     {
         "BriefDescription": "Counts the number of RDPMC, RDTSC, and RDTSCP instructions retired.",
         "Counter": "0,1,2,3,4,5,6,7",

diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 9370722dc5647f291e336bf6f9b0d696264e45a7..7e9bc4241c6186f3a365ea824b40def9bd07213c 100644 (file)
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -1,7 +1,7 @@
 Family-model,Version,Filename,EventType
 GenuineIntel-6-(97|9A|B7|BA|BF),v1.37,alderlake,core
 GenuineIntel-6-BE,v1.37,alderlaken,core
-GenuineIntel-6-C[56],v1.14,arrowlake,core
+GenuineIntel-6-C[56],v1.16,arrowlake,core
 GenuineIntel-6-(1C|26|27|35|36),v5,bonnell,core
 GenuineIntel-6-(3D|47),v30,broadwell,core
 GenuineIntel-6-56,v12,broadwellde,core