[PATCH 5/6] perf jevents: Add support for NVIDIA Tegra410 CPU Memory Latency PMU aliasing

[Besar Wicaksono]

Add alias support for NVIDIA Tegra410 CPU Memory Latency PMU events.

Signed-off-by: Besar Wicaksono <bwicaksono at nvidia.com>
---
 .../arm64/nvidia/t410/sys/uncore-cpu_mem.json | 48 +++++++++++++++++++
 1 file changed, 48 insertions(+)
 create mode 100644 tools/perf/pmu-events/arch/arm64/nvidia/t410/sys/uncore-cpu_mem.json

diff --git a/tools/perf/pmu-events/arch/arm64/nvidia/t410/sys/uncore-cpu_mem.json b/tools/perf/pmu-events/arch/arm64/nvidia/t410/sys/uncore-cpu_mem.json
new file mode 100644
index 000000000000..85ebe6fa20e2
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/nvidia/t410/sys/uncore-cpu_mem.json
@@ -0,0 +1,48 @@
+[
+    {
+        "EventCode": "0x0",
+        "EventName": "CMEM_CYCLES",
+        "BriefDescription": "Counts elapsed MSN bridge cycles for the CMEM read-latency counters.",
+        "PublicDescription": "Counts elapsed Memory Switch Node (MSN) bridge cycles for the CMEM read-latency counters. All MSN instances share this clock, so the count is read from the first instance.",
+        "Compat": "NVDA2021",
+        "Unit": "nvidia_cmem_latency_pmu_"
+    },
+    {
+        "EventCode": "0x1",
+        "EventName": "CMEM_RD_REQ",
+        "BriefDescription": "Counts local CMEM read requests at the edge of the UCF (post SLC), in 32-byte units, from all requesters.",
+        "PublicDescription": "Counts read requests at the edge of the Unified Coherence Fabric (UCF), after the System Level Cache (SLC), to local CPU DRAM (CMEM), at 32-byte granularity. A read of up to 32 bytes adds one; a 64-byte read adds two. It counts reads from all requesters, local and remote, summed over all Memory Switch Node (MSN) instances and channels. There is no requester or security-state filtering.",
+        "Compat": "NVDA2021",
+        "Unit": "nvidia_cmem_latency_pmu_"
+    },
+    {
+        "EventCode": "0x2",
+        "EventName": "CMEM_RD_CUM_OUTS",
+        "BriefDescription": "Accumulates the in-flight read requests counted by CMEM_RD_REQ each MSN bridge cycle.",
+        "PublicDescription": "Accumulates the in-flight read requests counted by CMEM_RD_REQ each Memory Switch Node (MSN) bridge cycle. Pair the two for the average read latency.",
+        "Compat": "NVDA2021",
+        "Unit": "nvidia_cmem_latency_pmu_"
+    },
+    {
+        "MetricName": "cmem_freq",
+        "MetricGroup": "CMEM_Frequency;CMEM_Read_Latency",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(CMEM_CYCLES / aggr_nr(CMEM_CYCLES)) / 1e9 / duration_time",
+        "ScaleUnit": "1GHz",
+        "BriefDescription": "MSN bridge clock frequency of the CMEM read-latency counters.",
+        "PublicDescription": "Average Memory Switch Node (MSN) bridge clock frequency over the measurement interval. This is the clock of the CMEM read-latency counters.",
+        "Compat": "NVDA2021",
+        "Unit": "nvidia_cmem_latency_pmu_"
+    },
+    {
+        "MetricName": "cmem_avg_rd_latency",
+        "MetricGroup": "CMEM_Read_Latency",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(CMEM_RD_CUM_OUTS / CMEM_RD_REQ) / cmem_freq",
+        "ScaleUnit": "1ns/request",
+        "BriefDescription": "Average local CMEM read latency from the edge of the UCF (post SLC) to CPU DRAM, for all requesters.",
+        "PublicDescription": "Average latency of the read requests counted by CMEM_RD_REQ, from the edge of the Unified Coherence Fabric (UCF), after the System Level Cache (SLC), to local CPU DRAM (CMEM).",
+        "Compat": "NVDA2021",
+        "Unit": "nvidia_cmem_latency_pmu_"
+    }
+]
-- 
2.43.0