perf vendor events amd: Add Zen 5 uncore events

Add uncore events taken from Section 1.5 "L3 Cache Performance Monitor
Counters" and Section 2 "UMC Performance Monitors" of the Performance
Monitor Counters for AMD Family 1Ah Model 00h-0Fh Processors document
available at the link below.

This constitutes events which capture L3 cache and UMC command activity.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ananth Narayan <ananth.narayan@amd.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Link: https://bugzilla.kernel.org/attachment.cgi?id=305974
Link: https://lore.kernel.org/r/e11e8d9d1af34a0fb565fc9d1c4a05f569c39ddc.1714717230.git.sandipan.das@amd.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/pmu-events/arch/x86/amdzen5/l3-cache.json b/tools/perf/pmu-events/arch/x86/amdzen5/l3-cache.json
new file mode 100644 (file)
index 0000000..b50fe14
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/amdzen5/l3-cache.json
@@ -0,0 +1,177 @@
+[
+  {
+    "EventName": "l3_lookup_state.l3_miss",
+    "EventCode": "0x04",
+    "BriefDescription": "L3 cache misses.",
+    "UMask": "0x01",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "l3_lookup_state.l3_hit",
+    "EventCode": "0x04",
+    "BriefDescription": "L3 cache hits.",
+    "UMask": "0xfe",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "l3_lookup_state.all_coherent_accesses_to_l3",
+    "EventCode": "0x04",
+    "BriefDescription": "L3 cache requests for all coherent accesses.",
+    "UMask": "0xff",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "l3_xi_sampled_latency.dram_near",
+    "EventCode": "0xac",
+    "BriefDescription": "Average sampled latency when data is sourced from DRAM in the same NUMA node.",
+    "UMask": "0x01",
+    "EnAllCores": "0x1",
+    "EnAllSlices": "0x1",
+    "SliceId": "0x3",
+    "ThreadMask": "0x3",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "l3_xi_sampled_latency.dram_far",
+    "EventCode": "0xac",
+    "BriefDescription": "Average sampled latency when data is sourced from DRAM in a different NUMA node.",
+    "UMask": "0x02",
+    "EnAllCores": "0x1",
+    "EnAllSlices": "0x1",
+    "SliceId": "0x3",
+    "ThreadMask": "0x3",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "l3_xi_sampled_latency.near_cache",
+    "EventCode": "0xac",
+    "BriefDescription": "Average sampled latency when data is sourced from another CCX's cache when the address was in the same NUMA node.",
+    "UMask": "0x04",
+    "EnAllCores": "0x1",
+    "EnAllSlices": "0x1",
+    "SliceId": "0x3",
+    "ThreadMask": "0x3",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "l3_xi_sampled_latency.far_cache",
+    "EventCode": "0xac",
+    "BriefDescription": "Average sampled latency when data is sourced from another CCX's cache when the address was in a different NUMA node.",
+    "UMask": "0x08",
+    "EnAllCores": "0x1",
+    "EnAllSlices": "0x1",
+    "SliceId": "0x3",
+    "ThreadMask": "0x3",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "l3_xi_sampled_latency.ext_near",
+    "EventCode": "0xac",
+    "BriefDescription": "Average sampled latency when data is sourced from extension memory (CXL) in the same NUMA node.",
+    "UMask": "0x10",
+    "EnAllCores": "0x1",
+    "EnAllSlices": "0x1",
+    "SliceId": "0x3",
+    "ThreadMask": "0x3",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "l3_xi_sampled_latency.ext_far",
+    "EventCode": "0xac",
+    "BriefDescription": "Average sampled latency when data is sourced from extension memory (CXL) in a different NUMA node.",
+    "UMask": "0x20",
+    "EnAllCores": "0x1",
+    "EnAllSlices": "0x1",
+    "SliceId": "0x3",
+    "ThreadMask": "0x3",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "l3_xi_sampled_latency.all",
+    "EventCode": "0xac",
+    "BriefDescription": "Average sampled latency from all data sources.",
+    "UMask": "0x3f",
+    "EnAllCores": "0x1",
+    "EnAllSlices": "0x1",
+    "SliceId": "0x3",
+    "ThreadMask": "0x3",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "l3_xi_sampled_latency_requests.dram_near",
+    "EventCode": "0xad",
+    "BriefDescription": "L3 cache fill requests sourced from DRAM in the same NUMA node.",
+    "UMask": "0x01",
+    "EnAllCores": "0x1",
+    "EnAllSlices": "0x1",
+    "SliceId": "0x3",
+    "ThreadMask": "0x3",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "l3_xi_sampled_latency_requests.dram_far",
+    "EventCode": "0xad",
+    "BriefDescription": "L3 cache fill requests sourced from DRAM in a different NUMA node.",
+    "UMask": "0x02",
+    "EnAllCores": "0x1",
+    "EnAllSlices": "0x1",
+    "SliceId": "0x3",
+    "ThreadMask": "0x3",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "l3_xi_sampled_latency_requests.near_cache",
+    "EventCode": "0xad",
+    "BriefDescription": "L3 cache fill requests sourced from another CCX's cache when the address was in the same NUMA node.",
+    "UMask": "0x04",
+    "EnAllCores": "0x1",
+    "EnAllSlices": "0x1",
+    "SliceId": "0x3",
+    "ThreadMask": "0x3",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "l3_xi_sampled_latency_requests.far_cache",
+    "EventCode": "0xad",
+    "BriefDescription": "L3 cache fill requests sourced from another CCX's cache when the address was in a different NUMA node.",
+    "UMask": "0x08",
+    "EnAllCores": "0x1",
+    "EnAllSlices": "0x1",
+    "SliceId": "0x3",
+    "ThreadMask": "0x3",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "l3_xi_sampled_latency_requests.ext_near",
+    "EventCode": "0xad",
+    "BriefDescription": "L3 cache fill requests sourced from extension memory (CXL) in the same NUMA node.",
+    "UMask": "0x10",
+    "EnAllCores": "0x1",
+    "EnAllSlices": "0x1",
+    "SliceId": "0x3",
+    "ThreadMask": "0x3",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "l3_xi_sampled_latency_requests.ext_far",
+    "EventCode": "0xad",
+    "BriefDescription": "L3 cache fill requests sourced from extension memory (CXL) in a different NUMA node.",
+    "UMask": "0x20",
+    "EnAllCores": "0x1",
+    "EnAllSlices": "0x1",
+    "SliceId": "0x3",
+    "ThreadMask": "0x3",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "l3_xi_sampled_latency_requests.all",
+    "EventCode": "0xad",
+    "BriefDescription": "L3 cache fill requests sourced from all data sources.",
+    "UMask": "0x3f",
+    "EnAllCores": "0x1",
+    "EnAllSlices": "0x1",
+    "SliceId": "0x3",
+    "ThreadMask": "0x3",
+    "Unit": "L3PMC"
+  }
+]

diff --git a/tools/perf/pmu-events/arch/x86/amdzen5/memory-controller.json b/tools/perf/pmu-events/arch/x86/amdzen5/memory-controller.json
new file mode 100644 (file)
index 0000000..1a629fc
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/amdzen5/memory-controller.json
@@ -0,0 +1,101 @@
+[
+  {
+    "EventName": "umc_mem_clk",
+    "PublicDescription": "Number of memory clock (MEMCLK) cycles.",
+    "EventCode": "0x00",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_act_cmd.all",
+    "PublicDescription": "Number of ACTIVATE commands sent.",
+    "EventCode": "0x05",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_act_cmd.rd",
+    "PublicDescription": "Number of ACTIVATE commands sent for reads.",
+    "EventCode": "0x05",
+    "RdWrMask": "0x1",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_act_cmd.wr",
+    "PublicDescription": "Number of ACTIVATE commands sent for writes.",
+    "EventCode": "0x05",
+    "RdWrMask": "0x2",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_pchg_cmd.all",
+    "PublicDescription": "Number of PRECHARGE commands sent.",
+    "EventCode": "0x06",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_pchg_cmd.rd",
+    "PublicDescription": "Number of PRECHARGE commands sent for reads.",
+    "EventCode": "0x06",
+    "RdWrMask": "0x1",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_pchg_cmd.wr",
+    "PublicDescription": "Number of PRECHARGE commands sent for writes.",
+    "EventCode": "0x06",
+    "RdWrMask": "0x2",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_cas_cmd.all",
+    "PublicDescription": "Number of CAS commands sent.",
+    "EventCode": "0x0a",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_cas_cmd.rd",
+    "PublicDescription": "Number of CAS commands sent for reads.",
+    "EventCode": "0x0a",
+    "RdWrMask": "0x1",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_cas_cmd.wr",
+    "PublicDescription": "Number of CAS commands sent for writes.",
+    "EventCode": "0x0a",
+    "RdWrMask": "0x2",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_data_slot_clks.all",
+    "PublicDescription": "Number of clock cycles used by the data bus.",
+    "EventCode": "0x14",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_data_slot_clks.rd",
+    "PublicDescription": "Number of clock cycles used by the data bus for reads.",
+    "EventCode": "0x14",
+    "RdWrMask": "0x1",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  },
+  {
+    "EventName": "umc_data_slot_clks.wr",
+    "PublicDescription": "Number of clock cycles used by the data bus for writes.",
+    "EventCode": "0x14",
+    "RdWrMask": "0x2",
+    "PerPkg": "1",
+    "Unit": "UMCPMC"
+  }
+]