From: Ian Rogers Date: Mon, 30 Jun 2025 16:30:52 +0000 (-0700) Subject: perf vendor events: Update GraniteRapids events X-Git-Url: https://www.infradead.org/git/?a=commitdiff_plain;h=81699249168750fd7bf9101d2e98b5133d5c23f2;p=users%2Fjedix%2Flinux-maple.git perf vendor events: Update GraniteRapids events Update events from v1.08 to v1.10. Bring in the event updates v1.10 https://github.com/intel/perfmon/commit/96259a932e2ce5f70ed7d347ca92fdeb78f83aa5 https://github.com/intel/perfmon/commit/19e315c8d2e0b44e170a6e60de44c9359062a6aa Signed-off-by: Ian Rogers Tested-by: Thomas Falcon Link: https://lore.kernel.org/r/20250630163101.1920170-8-irogers@google.com Signed-off-by: Namhyung Kim --- diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/cache.json b/tools/perf/pmu-events/arch/x86/graniterapids/cache.json index 32f99a8a3871b..dbdeade6fe6ff 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/cache.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/cache.json @@ -977,6 +977,15 @@ "SampleAfterValue": "100003", "UMask": "0x4" }, + { + "BriefDescription": "Offcore Uncacheable memory data read transactions.", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.MEM_UC", + "PublicDescription": "This event counts noncacheable memory data read transactions. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, { "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", "Counter": "0,1,2,3", diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/counter.json b/tools/perf/pmu-events/arch/x86/graniterapids/counter.json index 5d3b202eadd36..d97211a0227e4 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/counter.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/counter.json @@ -59,6 +59,11 @@ "CountersNumFixed": "0", "CountersNumGeneric": 4 }, + { + "Unit": "UBOX", + "CountersNumFixed": "0", + "CountersNumGeneric": "2" + }, { "Unit": "PCU", "CountersNumFixed": "0", @@ -73,10 +78,5 @@ "Unit": "MDF", "CountersNumFixed": "0", "CountersNumGeneric": "4" - }, - { - "Unit": "UBOX", - "CountersNumFixed": "0", - "CountersNumGeneric": "2" } ] \ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json b/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json index af527f7f9d0ca..9a620e1b8de89 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json @@ -95,6 +95,12 @@ "MetricName": "io_bandwidth_read", "ScaleUnit": "1MB/s" }, + { + "BriefDescription": "Bandwidth of inbound IO reads that are initiated by end device controllers that are requesting memory from the CPU and miss the L3 cache", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_read_l3_miss", + "ScaleUnit": "1MB/s" + }, { "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the local CPU socket", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_LOCAL * 64 / 1e6 / duration_time", @@ -113,6 +119,12 @@ "MetricName": "io_bandwidth_write", "ScaleUnit": "1MB/s" }, + { + "BriefDescription": "Bandwidth of inbound IO writes that are initiated by end device controllers that are writing memory to the CPU", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_MISS_ITOM + UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR) * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_write_l3_miss", + "ScaleUnit": "1MB/s" + }, { "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the local CPU socket", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM_LOCAL + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_LOCAL) * 64 / 1e6 / duration_time", @@ -125,6 +137,30 @@ "MetricName": "io_bandwidth_write_remote", "ScaleUnit": "1MB/s" }, + { + "BriefDescription": "The percent of inbound full cache line writes initiated by IO that miss the L3 cache", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM / UNC_CHA_TOR_INSERTS.IO_ITOM", + "MetricName": "io_full_write_l3_miss", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Message Signaled Interrupts (MSI) per second sent by the integrated I/O traffic controller (IIO) to System Configuration Controller (Ubox)", + "MetricExpr": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.UBOX_POSTED / duration_time", + "MetricName": "io_msi", + "ScaleUnit": "1per_sec" + }, + { + "BriefDescription": "The percent of inbound partial writes initiated by IO that miss the L3 cache", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_MISS_RFO) / (UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_RFO)", + "MetricName": "io_partial_write_l3_miss", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "The percent of inbound reads initiated by IO that miss the L3 cache", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR / UNC_CHA_TOR_INSERTS.IO_PCIRDCUR", + "MetricName": "io_read_l3_miss", + "ScaleUnit": "100%" + }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json b/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json index 1edfdad1600d5..27af3bd6bacf9 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json @@ -738,7 +738,7 @@ "Counter": "0,1,2,3", "EventCode": "0x4c", "EventName": "LOAD_HIT_PREFETCH.SWPF", - "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions. Available PDIST counters: 0", + "PublicDescription": "Counts all software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json index e5bd11b27bcd4..6667fbc504528 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json @@ -1915,24 +1915,6 @@ "UMask": "0x4", "Unit": "UPI" }, - { - "BriefDescription": "Tx Flit Buffer Allocations : Number of allocations into the UPI Tx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "Counter": "0,1,2,3", - "EventCode": "0x40", - "EventName": "UNC_UPI_TxL_INSERTS", - "Experimental": "1", - "PerPkg": "1", - "Unit": "UPI" - }, - { - "BriefDescription": "Tx Flit Buffer Occupancy : Accumulates the number of flits in the TxQ. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This can be used with the cycles not empty event to track average occupancy, or the allocations event to track average lifetime in the TxQ.", - "Counter": "0,1,2,3", - "EventCode": "0x42", - "EventName": "UNC_UPI_TxL_OCCUPANCY", - "Experimental": "1", - "PerPkg": "1", - "Unit": "UPI" - }, { "BriefDescription": "Message Received : Doorbell", "Counter": "0,1", @@ -1970,7 +1952,6 @@ "Counter": "0,1", "EventCode": "0x42", "EventName": "UNC_U_EVENT_MSG.MSI_RCVD", - "Experimental": "1", "PerPkg": "1", "PublicDescription": "Message Received : MSI : Message Signaled Interrupts - interrupts sent by devices (including PCIe via IOxAPIC) (Socket Mode only)", "UMask": "0x2", diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-io.json b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-io.json index 886b99a971bea..f4f956966e168 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-io.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-io.json @@ -1121,8 +1121,9 @@ "Unit": "IIO" }, { - "BriefDescription": "Occupancy of outbound request queue : To device : Counts number of outbound requests/completions IIO is currently processing", + "BriefDescription": "This event is deprecated. [This event is alias to UNC_IIO_NUM_OUTSTANDING_REQ_FROM_CPU.TO_IO]", "Counter": "2,3", + "Deprecated": "1", "EventCode": "0xc5", "EventName": "UNC_IIO_NUM_OUSTANDING_REQ_FROM_CPU.TO_IO", "Experimental": "1", @@ -1132,6 +1133,18 @@ "UMask": "0x8", "Unit": "IIO" }, + { + "BriefDescription": "Occupancy of outbound request queue : To device : Counts number of outbound requests/completions IIO is currently processing [This event is alias to UNC_IIO_NUM_OUSTANDING_REQ_FROM_CPU.TO_IO]", + "Counter": "2,3", + "EventCode": "0xc5", + "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_FROM_CPU.TO_IO", + "Experimental": "1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0FF", + "UMask": "0x8", + "Unit": "IIO" + }, { "BriefDescription": "Passing data to be written", "Counter": "0,1,2,3", @@ -1300,6 +1313,18 @@ "UMask": "0x4", "Unit": "IIO" }, + { + "BriefDescription": "Posted requests sent by the integrated IO (IIO) controller to the Ubox, useful for counting message signaled interrupts (MSI).", + "Counter": "0,1,2,3", + "EventCode": "0x8e", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.UBOX_POSTED", + "FCMask": "0x01", + "PerPkg": "1", + "PortMask": "0x0FF", + "PublicDescription": "-", + "UMask": "0x4", + "Unit": "IIO" + }, { "BriefDescription": "All 9 bits of Page Walk Tracker Occupancy", "Counter": "0,1,2,3", diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index f3fe686b66304..960076e3f66f2 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -13,7 +13,7 @@ GenuineIntel-6-CF,v1.14,emeraldrapids,core GenuineIntel-6-5[CF],v13,goldmont,core GenuineIntel-6-7A,v1.01,goldmontplus,core GenuineIntel-6-B6,v1.09,grandridge,core -GenuineIntel-6-A[DE],v1.08,graniterapids,core +GenuineIntel-6-A[DE],v1.10,graniterapids,core GenuineIntel-6-(3C|45|46),v36,haswell,core GenuineIntel-6-3F,v29,haswellx,core GenuineIntel-6-7[DE],v1.24,icelake,core