[PATCH v2 5/9] perf jevents: Add support for NVIDIA Tegra410 C2C PMU aliasing

[Besar Wicaksono <bwicaksono@nvidia.com>]

Add alias support for NVIDIA Tegra410 C2C PMU events.

Signed-off-by: Besar Wicaksono <bwicaksono@nvidia.com>
---
 .../arm64/nvidia/t410/uncore-nvclink.json     |  67 ++++++++++
 .../arm64/nvidia/t410/uncore-nvdlink.json     |  43 +++++++
 .../arm64/nvidia/t410/uncore-nvlink_c2c.json  | 115 ++++++++++++++++++
 3 files changed, 225 insertions(+)
 create mode 100644 tools/perf/pmu-events/arch/arm64/nvidia/t410/uncore-nvclink.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/nvidia/t410/uncore-nvdlink.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/nvidia/t410/uncore-nvlink_c2c.json

diff --git a/tools/perf/pmu-events/arch/arm64/nvidia/t410/uncore-nvclink.json b/tools/perf/pmu-events/arch/arm64/nvidia/t410/uncore-nvclink.json
new file mode 100644
index 000000000000..1e7f8115ff9c
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/nvidia/t410/uncore-nvclink.json
@@ -0,0 +1,67 @@
+[
+    {
+        "EventCode": "0x0",
+        "EventName": "NVCLINK_CYCLES",
+        "BriefDescription": "Counts NV-CLink interface clock cycles.",
+        "PublicDescription": "Counts NV-CLink interface clock cycles. All NV-CLink instances share this clock, so the count is read from the first instance.",
+        "Unit": "nvidia_nvclink_pmu_"
+    },
+    {
+        "EventCode": "0x1",
+        "EventName": "NVCLINK_IN_RD_CUM_OUTS",
+        "BriefDescription": "Accumulates the outstanding incoming read requests counted by NVCLINK_IN_RD_REQ each NV-CLink interface cycle.",
+        "PublicDescription": "Accumulates the outstanding incoming read requests counted by NVCLINK_IN_RD_REQ each NV-CLink interface cycle. Pair the two for the average read latency.",
+        "Unit": "nvidia_nvclink_pmu_"
+    },
+    {
+        "EventCode": "0x2",
+        "EventName": "NVCLINK_IN_RD_REQ",
+        "BriefDescription": "Counts incoming read requests from the remote Tegra SoC at the NV-CLink interface.",
+        "PublicDescription": "Counts incoming read requests from the remote Tegra SoC at the NV-CLink interface, where local memory or a local device responds with data. Request size can be from 1 to 256 bytes. The count is summed over all NV-CLink instances.",
+        "Unit": "nvidia_nvclink_pmu_"
+    },
+    {
+        "EventCode": "0x5",
+        "EventName": "NVCLINK_OUT_RD_CUM_OUTS",
+        "BriefDescription": "Accumulates the outstanding outgoing read requests counted by NVCLINK_OUT_RD_REQ each NV-CLink interface cycle.",
+        "PublicDescription": "Accumulates the outstanding outgoing read requests counted by NVCLINK_OUT_RD_REQ each NV-CLink interface cycle. Pair the two for the average read latency.",
+        "Unit": "nvidia_nvclink_pmu_"
+    },
+    {
+        "EventCode": "0x6",
+        "EventName": "NVCLINK_OUT_RD_REQ",
+        "BriefDescription": "Counts outgoing read requests from the local Tegra SoC to the remote Tegra SoC at the NV-CLink interface.",
+        "PublicDescription": "Counts outgoing read requests from the local Tegra SoC to the remote Tegra SoC at the NV-CLink interface, where memory on the remote Tegra SoC responds with data. Request size can be from 1 to 256 bytes. The count is summed over all NV-CLink instances.",
+        "Unit": "nvidia_nvclink_pmu_"
+    },
+    {
+        "MetricName": "nvclink_freq",
+        "MetricGroup": "NVCLINK_Frequency;NVCLINK_Latency;NVCLINK_Read_Latency",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(NVCLINK_CYCLES / aggr_nr(NVCLINK_CYCLES)) / 1e9 / duration_time",
+        "ScaleUnit": "1GHz",
+        "BriefDescription": "NV-CLink interface clock frequency.",
+        "PublicDescription": "Average NV-CLink interface clock frequency over the measurement interval.",
+        "Unit": "nvidia_nvclink_pmu_"
+    },
+    {
+        "MetricName": "nvclink_in_avg_rd_latency",
+        "MetricGroup": "NVCLINK_Latency;NVCLINK_Read_Latency;NVCLINK_Incoming",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(NVCLINK_IN_RD_CUM_OUTS / NVCLINK_IN_RD_REQ) / nvclink_freq",
+        "ScaleUnit": "1ns/request",
+        "BriefDescription": "Average latency of incoming read requests from the remote Tegra SoC at the NV-CLink interface.",
+        "PublicDescription": "Average latency of the incoming read requests counted by NVCLINK_IN_RD_REQ, measured at the NV-CLink interface.",
+        "Unit": "nvidia_nvclink_pmu_"
+    },
+    {
+        "MetricName": "nvclink_out_avg_rd_latency",
+        "MetricGroup": "NVCLINK_Latency;NVCLINK_Read_Latency;NVCLINK_Outgoing",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(NVCLINK_OUT_RD_CUM_OUTS / NVCLINK_OUT_RD_REQ) / nvclink_freq",
+        "ScaleUnit": "1ns/request",
+        "BriefDescription": "Average latency of outgoing read requests sent by the local Tegra SoC to the remote Tegra SoC at the NV-CLink interface.",
+        "PublicDescription": "Average latency of the outgoing read requests counted by NVCLINK_OUT_RD_REQ, measured at the NV-CLink interface.",
+        "Unit": "nvidia_nvclink_pmu_"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/nvidia/t410/uncore-nvdlink.json b/tools/perf/pmu-events/arch/arm64/nvidia/t410/uncore-nvdlink.json
new file mode 100644
index 000000000000..7777add3741d
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/nvidia/t410/uncore-nvdlink.json
@@ -0,0 +1,43 @@
+[
+    {
+        "EventCode": "0x0",
+        "EventName": "NVDLINK_CYCLES",
+        "BriefDescription": "Counts NV-DLink interface clock cycles.",
+        "PublicDescription": "Counts NV-DLink interface clock cycles. All NV-DLink instances share this clock, so the count is read from the first instance.",
+        "Unit": "nvidia_nvdlink_pmu_"
+    },
+    {
+        "EventCode": "0x1",
+        "EventName": "NVDLINK_IN_RD_CUM_OUTS",
+        "BriefDescription": "Accumulates the outstanding read requests counted by NVDLINK_IN_RD_REQ each NV-DLink interface cycle.",
+        "PublicDescription": "Accumulates the outstanding read requests counted by NVDLINK_IN_RD_REQ each NV-DLink interface cycle. Pair the two for the average read latency.",
+        "Unit": "nvidia_nvdlink_pmu_"
+    },
+    {
+        "EventCode": "0x2",
+        "EventName": "NVDLINK_IN_RD_REQ",
+        "BriefDescription": "Counts read requests to local CXL memory at the NV-DLink interface.",
+        "PublicDescription": "Counts read requests to local CXL memory at the NV-DLink interface, from all requesters, local and remote. Request size can be from 1 to 256 bytes. The count is summed over all NV-DLink instances.",
+        "Unit": "nvidia_nvdlink_pmu_"
+    },
+    {
+        "MetricName": "nvdlink_freq",
+        "MetricGroup": "NVDLINK_Frequency;NVDLINK_Latency;NVDLINK_Read_Latency",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(NVDLINK_CYCLES / aggr_nr(NVDLINK_CYCLES)) / 1e9 / duration_time",
+        "ScaleUnit": "1GHz",
+        "BriefDescription": "NV-DLink interface clock frequency.",
+        "PublicDescription": "Average NV-DLink interface clock frequency over the measurement interval.",
+        "Unit": "nvidia_nvdlink_pmu_"
+    },
+    {
+        "MetricName": "nvdlink_in_avg_rd_latency",
+        "MetricGroup": "NVDLINK_Latency;NVDLINK_Read_Latency",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(NVDLINK_IN_RD_CUM_OUTS / NVDLINK_IN_RD_REQ) / nvdlink_freq",
+        "ScaleUnit": "1ns/request",
+        "BriefDescription": "Average latency of read requests to local CXL memory at the NV-DLink interface.",
+        "PublicDescription": "Average latency of the read requests counted by NVDLINK_IN_RD_REQ, measured at the NV-DLink interface.",
+        "Unit": "nvidia_nvdlink_pmu_"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/nvidia/t410/uncore-nvlink_c2c.json b/tools/perf/pmu-events/arch/arm64/nvidia/t410/uncore-nvlink_c2c.json
new file mode 100644
index 000000000000..48a64caaba61
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/nvidia/t410/uncore-nvlink_c2c.json
@@ -0,0 +1,115 @@
+[
+    {
+        "EventCode": "0x0",
+        "EventName": "NVLINK_C2C_CYCLES",
+        "BriefDescription": "Counts NVLink-C2C interface clock cycles.",
+        "PublicDescription": "Counts NVLink-C2C interface clock cycles. All NVLink-C2C instances share this clock, so the count is read from the first instance.",
+        "Unit": "nvidia_nvlink_c2c_pmu_"
+    },
+    {
+        "EventCode": "0x1",
+        "EventName": "NVLINK_C2C_IN_RD_CUM_OUTS",
+        "BriefDescription": "Accumulates the outstanding incoming read requests counted by NVLINK_C2C_IN_RD_REQ each NVLink-C2C interface cycle.",
+        "PublicDescription": "Accumulates the outstanding incoming read requests counted by NVLINK_C2C_IN_RD_REQ each NVLink-C2C interface cycle. Pair the two for the average read latency. The gpu_mask filter works as described for NVLINK_C2C_IN_RD_REQ.",
+        "Unit": "nvidia_nvlink_c2c_pmu_"
+    },
+    {
+        "EventCode": "0x2",
+        "EventName": "NVLINK_C2C_IN_RD_REQ",
+        "BriefDescription": "Counts incoming read requests from connected GPUs or a remote Tegra SoC at the NVLink-C2C interface.",
+        "PublicDescription": "Counts incoming read requests sent by connected GPUs or a remote Tegra SoC to the local Tegra SoC at the NVLink-C2C interface, where the local Tegra SoC responds with data. Request size can be from 1 to 256 bytes. The count is summed over all NVLink-C2C instances. Filters: the gpu_mask filter selects GPUs by index, one bit per GPU. This filter is available only when GPUs are connected. An unset gpu_mask counts all GPUs.",
+        "Unit": "nvidia_nvlink_c2c_pmu_"
+    },
+    {
+        "EventCode": "0x3",
+        "EventName": "NVLINK_C2C_IN_WR_CUM_OUTS",
+        "BriefDescription": "Accumulates the outstanding incoming write requests counted by NVLINK_C2C_IN_WR_REQ each NVLink-C2C interface cycle.",
+        "PublicDescription": "Accumulates the outstanding incoming write requests counted by NVLINK_C2C_IN_WR_REQ each NVLink-C2C interface cycle. Available only when GPUs are connected. Pair the two for the average write latency. The gpu_mask filter works as described for NVLINK_C2C_IN_WR_REQ.",
+        "Unit": "nvidia_nvlink_c2c_pmu_"
+    },
+    {
+        "EventCode": "0x4",
+        "EventName": "NVLINK_C2C_IN_WR_REQ",
+        "BriefDescription": "Counts incoming write requests from connected GPUs to the local Tegra SoC at the NVLink-C2C interface.",
+        "PublicDescription": "Counts incoming write requests sent by connected GPUs to the local Tegra SoC at the NVLink-C2C interface, where the GPU sends the data. Request size can be from 1 to 256 bytes. Available only when GPUs are connected. The count is summed over all NVLink-C2C instances. Filters: the gpu_mask filter selects GPUs by index, one bit per GPU. An unset gpu_mask counts all GPUs.",
+        "Unit": "nvidia_nvlink_c2c_pmu_"
+    },
+    {
+        "EventCode": "0x5",
+        "EventName": "NVLINK_C2C_OUT_RD_CUM_OUTS",
+        "BriefDescription": "Accumulates the outstanding outgoing read requests counted by NVLINK_C2C_OUT_RD_REQ each NVLink-C2C interface cycle.",
+        "PublicDescription": "Accumulates the outstanding outgoing read requests counted by NVLINK_C2C_OUT_RD_REQ each NVLink-C2C interface cycle. Pair the two for the average read latency. The gpu_mask filter works as described for NVLINK_C2C_OUT_RD_REQ.",
+        "Unit": "nvidia_nvlink_c2c_pmu_"
+    },
+    {
+        "EventCode": "0x6",
+        "EventName": "NVLINK_C2C_OUT_RD_REQ",
+        "BriefDescription": "Counts outgoing read requests to connected GPUs or a remote Tegra SoC at the NVLink-C2C interface.",
+        "PublicDescription": "Counts outgoing read requests from all requesters to connected GPUs or a remote Tegra SoC at the NVLink-C2C interface, where the GPU or remote Tegra SoC responds with data. Request size can be from 1 to 256 bytes. The count is summed over all NVLink-C2C instances. Filters: the gpu_mask filter selects GPUs by index, one bit per GPU. This filter is available only when GPUs are connected. An unset gpu_mask counts all GPUs.",
+        "Unit": "nvidia_nvlink_c2c_pmu_"
+    },
+    {
+        "EventCode": "0x7",
+        "EventName": "NVLINK_C2C_OUT_WR_CUM_OUTS",
+        "BriefDescription": "Accumulates the outstanding outgoing write requests counted by NVLINK_C2C_OUT_WR_REQ each NVLink-C2C interface cycle.",
+        "PublicDescription": "Accumulates the outstanding outgoing write requests counted by NVLINK_C2C_OUT_WR_REQ each NVLink-C2C interface cycle. Available only when GPUs are connected. Pair the two for the average write latency. The gpu_mask filter works as described for NVLINK_C2C_OUT_WR_REQ.",
+        "Unit": "nvidia_nvlink_c2c_pmu_"
+    },
+    {
+        "EventCode": "0x8",
+        "EventName": "NVLINK_C2C_OUT_WR_REQ",
+        "BriefDescription": "Counts outgoing write requests to connected GPUs at the NVLink-C2C interface.",
+        "PublicDescription": "Counts outgoing write requests from all requesters to connected GPUs at the NVLink-C2C interface, where the requester sends the data. Request size can be from 1 to 256 bytes. Available only when GPUs are connected. The count is summed over all NVLink-C2C instances. Filters: the gpu_mask filter selects GPUs by index, one bit per GPU. An unset gpu_mask counts all GPUs.",
+        "Unit": "nvidia_nvlink_c2c_pmu_"
+    },
+    {
+        "MetricName": "nvlink_c2c_freq",
+        "MetricGroup": "NVLINK_C2C_Frequency;NVLINK_C2C_Latency;NVLINK_C2C_Read_Latency;NVLINK_C2C_Write_Latency",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(NVLINK_C2C_CYCLES / aggr_nr(NVLINK_C2C_CYCLES)) / 1e9 / duration_time",
+        "ScaleUnit": "1GHz",
+        "BriefDescription": "NVLink-C2C interface clock frequency.",
+        "PublicDescription": "Average NVLink-C2C interface clock frequency over the measurement interval.",
+        "Unit": "nvidia_nvlink_c2c_pmu_"
+    },
+    {
+        "MetricName": "nvlink_c2c_in_avg_rd_latency",
+        "MetricGroup": "NVLINK_C2C_Latency;NVLINK_C2C_Read_Latency;NVLINK_C2C_Incoming",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(NVLINK_C2C_IN_RD_CUM_OUTS / NVLINK_C2C_IN_RD_REQ) / nvlink_c2c_freq",
+        "ScaleUnit": "1ns/request",
+        "BriefDescription": "Average latency of incoming read requests at the NVLink-C2C interface.",
+        "PublicDescription": "Average latency of the incoming read requests counted by NVLINK_C2C_IN_RD_REQ, measured at the NVLink-C2C interface.",
+        "Unit": "nvidia_nvlink_c2c_pmu_"
+    },
+    {
+        "MetricName": "nvlink_c2c_in_avg_wr_latency",
+        "MetricGroup": "NVLINK_C2C_Latency;NVLINK_C2C_Write_Latency;NVLINK_C2C_Incoming",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(NVLINK_C2C_IN_WR_CUM_OUTS / NVLINK_C2C_IN_WR_REQ) / nvlink_c2c_freq",
+        "ScaleUnit": "1ns/request",
+        "BriefDescription": "Average latency of incoming write requests from connected GPUs at the NVLink-C2C interface.",
+        "PublicDescription": "Average latency of the incoming write requests counted by NVLINK_C2C_IN_WR_REQ, measured at the NVLink-C2C interface. Available only when GPUs are connected.",
+        "Unit": "nvidia_nvlink_c2c_pmu_"
+    },
+    {
+        "MetricName": "nvlink_c2c_out_avg_rd_latency",
+        "MetricGroup": "NVLINK_C2C_Latency;NVLINK_C2C_Read_Latency;NVLINK_C2C_Outgoing",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(NVLINK_C2C_OUT_RD_CUM_OUTS / NVLINK_C2C_OUT_RD_REQ) / nvlink_c2c_freq",
+        "ScaleUnit": "1ns/request",
+        "BriefDescription": "Average latency of outgoing read requests at the NVLink-C2C interface.",
+        "PublicDescription": "Average latency of the outgoing read requests counted by NVLINK_C2C_OUT_RD_REQ, measured at the NVLink-C2C interface.",
+        "Unit": "nvidia_nvlink_c2c_pmu_"
+    },
+    {
+        "MetricName": "nvlink_c2c_out_avg_wr_latency",
+        "MetricGroup": "NVLINK_C2C_Latency;NVLINK_C2C_Write_Latency;NVLINK_C2C_Outgoing",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(NVLINK_C2C_OUT_WR_CUM_OUTS / NVLINK_C2C_OUT_WR_REQ) / nvlink_c2c_freq",
+        "ScaleUnit": "1ns/request",
+        "BriefDescription": "Average latency of outgoing write requests to connected GPUs at the NVLink-C2C interface.",
+        "PublicDescription": "Average latency of the outgoing write requests counted by NVLINK_C2C_OUT_WR_REQ, measured at the NVLink-C2C interface. Available only when GPUs are connected.",
+        "Unit": "nvidia_nvlink_c2c_pmu_"
+    }
+]
-- 
2.43.0