[PATCH v1 01/12] perf vendor events intel: Update alderlake events from 1.39 to 1.40

[Chun-Tse Shao <ctshao@google.com>]

The updated events were published in:
https://github.com/intel/perfmon/commit/7a14cc8feaf86772deb6708e96c8e9fee6d5b1ca

Signed-off-by: Chun-Tse Shao <ctshao@google.com>
---
 .../arch/x86/alderlake/adl-metrics.json       | 80 ++++++++++---------
 .../pmu-events/arch/x86/alderlake/cache.json  | 36 +++++++++
 .../arch/x86/alderlake/metricgroups.json      |  2 +-
 .../arch/x86/alderlake/pipeline.json          |  6 +-
 tools/perf/pmu-events/arch/x86/mapfile.csv    |  2 +-
 5 files changed, 82 insertions(+), 44 deletions(-)

diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
index cae7c0cf02f2..e76d679a784b 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
@@ -800,16 +800,16 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_miss_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
         "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_bottleneck_data_cache_memory_bandwidth",
         "MetricThreshold": "tma_bottleneck_data_cache_memory_bandwidth > 20",
-        "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full",
+        "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_uc_bound",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_miss_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_bottleneck_data_cache_memory_latency",
         "MetricThreshold": "tma_bottleneck_data_cache_memory_latency > 20",
@@ -835,7 +835,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_bottleneck_memory_data_tlbs",
         "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
@@ -844,7 +844,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
         "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
         "MetricName": "tma_bottleneck_memory_synchronization",
         "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
@@ -1012,13 +1012,13 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
+        "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to L3 data-sharing accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "24 * tma_info_system_core_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
         "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to L3 data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1042,16 +1042,6 @@
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
-    {
-        "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
-        "MetricExpr": "cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@ / tma_info_thread_clks",
-        "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
-        "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
-        "ScaleUnit": "100%",
-        "Unit": "cpu_core"
-    },
     {
         "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline",
         "MetricExpr": "(cpu_core@IDQ.DSB_CYCLES_ANY@ - cpu_core@IDQ.DSB_CYCLES_OK@) / tma_info_core_core_clks / 2",
@@ -1108,7 +1098,7 @@
         "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
         "MetricThreshold": "tma_fb_full > 0.3",
-        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
+        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores, tma_uc_bound",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1426,7 +1416,7 @@
     },
     {
         "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
-        "MetricExpr": "cpu_core@IDQ.DSB_UOPS@ / cpu_core@UOPS_ISSUED.ANY@",
+        "MetricExpr": "cpu_core@IDQ.DSB_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@LSD.UOPS@ + cpu_core@IDQ.MITE_UOPS@ + cpu_core@IDQ.MS_UOPS@)",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_frontend_dsb_coverage",
         "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 6 > 0.35",
@@ -1485,7 +1475,7 @@
     },
     {
         "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)",
-        "MetricExpr": "cpu_core@LSD.UOPS@ / cpu_core@UOPS_ISSUED.ANY@",
+        "MetricExpr": "cpu_core@LSD.UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@LSD.UOPS@ + cpu_core@IDQ.MITE_UOPS@ + cpu_core@IDQ.MS_UOPS@)",
         "MetricGroup": "Fed;LSD",
         "MetricName": "tma_info_frontend_lsd_coverage",
         "Unit": "cpu_core"
@@ -1629,6 +1619,15 @@
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "AVX preserve/restore assists per kilo instruction",
+        "MetricExpr": "1e3 * cpu_core@ASSISTS.SSE_AVX_MIX@ / cpu_core@INST_RETIRED.ANY@",
+        "MetricGroup": "tma_issueMV",
+        "MetricName": "tma_info_inst_mix_vectormixpki",
+        "MetricThreshold": "tma_info_inst_mix_vectormixpki > 0.05",
+        "PublicDescription": "AVX preserve/restore assists per kilo instruction. Related metrics: tma_mixing_vectors, tma_ms_switches",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
         "MetricExpr": "tma_info_memory_l1d_cache_fill_bw",
@@ -1850,7 +1849,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Mem;Backend;CacheHits",
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per physical core",
         "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute",
@@ -1935,7 +1934,7 @@
         "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / tma_info_system_time / 1e3",
         "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW",
         "MetricName": "tma_info_system_dram_bw_use",
-        "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full",
+        "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full, tma_uc_bound",
         "Unit": "cpu_core"
     },
     {
@@ -2029,13 +2028,6 @@
         "MetricName": "tma_info_system_turbo_utilization",
         "Unit": "cpu_core"
     },
-    {
-        "BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]",
-        "MetricExpr": "tma_info_system_socket_clks / 1e9 / tma_info_system_time",
-        "MetricGroup": "SoC",
-        "MetricName": "tma_info_system_uncore_frequency",
-        "Unit": "cpu_core"
-    },
     {
         "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@",
@@ -2204,6 +2196,16 @@
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
+        "MetricExpr": "cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@ / tma_info_thread_clks",
+        "MetricGroup": "MemoryBound;Offcore;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
+        "MetricName": "tma_l3_miss_bound",
+        "MetricThreshold": "tma_l3_miss_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
+        "ScaleUnit": "100%",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)",
         "MetricExpr": "cpu_core@DECODE.LCP@ / tma_info_thread_clks",
@@ -2283,7 +2285,7 @@
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(16 * max(0, cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ - cpu_core@L2_RQSTS.ALL_RFO@) + cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@ * (10 * cpu_core@L2_RQSTS.RFO_HIT@ + min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@))) / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@LOCK_CYCLES.CACHE_LOCK_DURATION@ / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
         "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
@@ -2315,19 +2317,19 @@
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
         "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
-        "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
+        "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_miss_bound_group",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_l3_miss_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full, tma_uc_bound",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM)",
         "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD@) / tma_info_thread_clks - tma_mem_bandwidth",
-        "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
+        "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_miss_bound_group",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_l3_miss_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_latency, tma_l3_hit_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2397,7 +2399,7 @@
         "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
         "MetricName": "tma_mixing_vectors",
         "MetricThreshold": "tma_mixing_vectors > 0.05",
-        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_info_inst_mix_vectormixpki, tma_ms_switches",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2416,7 +2418,7 @@
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
         "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
-        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
+        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_info_inst_mix_vectormixpki, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2606,7 +2608,7 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary",
-        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu_core@LD_BLOCKS.NO_SR@ / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * tma_info_memory_load_miss_real_latency / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
@@ -2630,7 +2632,7 @@
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
         "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
+        "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_uc_bound",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/cache.json b/tools/perf/pmu-events/arch/x86/alderlake/cache.json
index e44e6b651d55..6c09da7b69e8 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/cache.json
@@ -1,4 +1,13 @@
 [
+    {
+        "BriefDescription": "Counts the number of core requests (demand and L1 prefetchers) rejected by the L2 queue (L2Q) due to a full condition.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0x31",
+        "EventName": "CORE_REJECT_L2Q.ANY",
+        "PublicDescription": "Counts the number of (demand and L1 prefetchers) core requests rejected by the L2 queue (L2Q) due to a full or nearly full condition, which likely indicates back pressure from L2Q.  It also counts requests that would have gone directly to the External Queue (XQ), but are rejected due to a full or nearly full condition, indicating back pressure from the IDI link.  The L2Q may also reject transactions  from a core to ensure fairness between cores, or to delay a cores dirty eviction when the address conflicts incoming external snoops.  (Note that L2 prefetcher requests that are dropped are not counted by this event).  Counts on a per core basis.",
+        "SampleAfterValue": "200003",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "L1D.HWPF_MISS",
         "Counter": "0,1,2,3",
@@ -121,6 +130,15 @@
         "UMask": "0x4",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Counts the number of demand and prefetch transactions that the External Queue (XQ) rejects due to a full or near full condition.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0x30",
+        "EventName": "L2_REJECT_XQ.ANY",
+        "PublicDescription": "Counts the number of demand and prefetch transactions that the External Queue (XQ) rejects due to a full or near full condition which likely indicates back pressure from the IDI link.  The XQ may reject transactions from the L2Q (non-cacheable requests), BBL (L2 misses) and WOB (L2 write-back victims).",
+        "SampleAfterValue": "200003",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Counts the total number of L2 Cache accesses. Counts on a per core basis.",
         "Counter": "0,1,2,3,4,5",
@@ -438,6 +456,15 @@
         "UMask": "0x8",
         "Unit": "cpu_atom"
     },
+    {
+        "BriefDescription": "Counts the number of cycles the core is stalled due to an instruction cache or TLB miss which missed in the L2 cache.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0x34",
+        "EventName": "MEM_BOUND_STALLS.IFETCH_L2_MISS",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x30",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to an instruction cache or TLB miss which hit in the LLC or other core with HITE/F/M.",
         "Counter": "0,1,2,3,4,5",
@@ -475,6 +502,15 @@
         "UMask": "0x1",
         "Unit": "cpu_atom"
     },
+    {
+        "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load which missed in the L2 cache.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0x34",
+        "EventName": "MEM_BOUND_STALLS.LOAD_L2_MISS",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x6",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load which hit in the LLC or other core with HITE/F/M.",
         "Counter": "0,1,2,3,4,5",
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/metricgroups.json b/tools/perf/pmu-events/arch/x86/alderlake/metricgroups.json
index 855585fe6fae..9acbda612c25 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/metricgroups.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/metricgroups.json
@@ -93,7 +93,6 @@
     "tma_code_stlb_miss_group": "Metrics contributing to tma_code_stlb_miss category",
     "tma_core_bound_group": "Metrics contributing to tma_core_bound category",
     "tma_divider_group": "Metrics contributing to tma_divider category",
-    "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category",
     "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category",
     "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category",
     "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category",
@@ -129,6 +128,7 @@
     "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category",
     "tma_l2_bound_group": "Metrics contributing to tma_l2_bound category",
     "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category",
+    "tma_l3_miss_bound_group": "Metrics contributing to tma_l3_miss_bound category",
     "tma_light_operations_group": "Metrics contributing to tma_light_operations category",
     "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category",
     "tma_load_stlb_miss_group": "Metrics contributing to tma_load_stlb_miss category",
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json b/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json
index 1c292f29b0aa..eb840066a5a7 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json
@@ -550,11 +550,11 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS",
+        "BriefDescription": "This event counts the number of mispredicted ret instructions retired.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RET",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0",
+        "PublicDescription": "This event counts the number of mispredicted ret instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -988,7 +988,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.REP_ITERATION",
-        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.",
+        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note: Since the number of iterations within a REP instruction can be significantly affected by fast strings, this event may vary run to run and not match the architectural number of iterations (specified by RCX)",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index a7f870669827..414744811c00 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -1,5 +1,5 @@
 Family-model,Version,Filename,EventType
-GenuineIntel-6-(97|9A|B7|BA|BF),v1.39,alderlake,core
+GenuineIntel-6-(97|9A|B7|BA|BF),v1.40,alderlake,core
 GenuineIntel-6-BE,v1.39,alderlaken,core
 GenuineIntel-6-C[56],v1.19,arrowlake,core
 GenuineIntel-6-(1C|26|27|35|36),v5,bonnell,core
-- 
2.55.0.795.g602f6c329a-goog