[PATCH 3/6] perf jevents: Add support for NVIDIA Tegra410 PCIE PMU aliasing

[Besar Wicaksono <bwicaksono@nvidia.com>]

Add alias support for NVIDIA Tegra410 PCIE PMU events and metrics.

Signed-off-by: Besar Wicaksono <bwicaksono@nvidia.com>
---
 .../arm64/nvidia/t410/sys/uncore-pcie.json    | 247 ++++++++++++++++++
 1 file changed, 247 insertions(+)
 create mode 100644 tools/perf/pmu-events/arch/arm64/nvidia/t410/sys/uncore-pcie.json

diff --git a/tools/perf/pmu-events/arch/arm64/nvidia/t410/sys/uncore-pcie.json b/tools/perf/pmu-events/arch/arm64/nvidia/t410/sys/uncore-pcie.json
new file mode 100644
index 000000000000..37c3eac305e5
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/nvidia/t410/sys/uncore-pcie.json
@@ -0,0 +1,247 @@
+[
+    {
+        "EventCode": "0x100000000",
+        "EventName": "PCIE_CYCLES",
+        "BriefDescription": "Counts cycles at the PCIe interface to the Tegra SoC data fabric.",
+        "PublicDescription": "Counts cycles at the PCIe interface to the Tegra SoC data fabric.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "EventCode": "0x2",
+        "EventName": "PCIE_RD_REQ",
+        "BriefDescription": "Counts read requests from PCIe devices under this PCIe root complex to memory or another PCIe device.",
+        "PublicDescription": "Counts read requests from PCIe devices under this PCIe root complex to memory or another PCIe device, where the target responds with data. Request size can be from 1 to 256 bytes. Filters: src_rp_mask selects the requesting root ports. Alternatively, src_bdf with src_bdf_en selects one requesting device (BDF); it cannot be combined with src_rp_mask and applies to all counters of this PMU. Destination filters select the memory type of the request address: dst_loc_cmem local CMEM, dst_loc_gmem local GMEM, dst_loc_pcie_p2p local PCIe peer addresses, dst_loc_pcie_cxl local CXL memory, dst_rem remote memory. This is the address's home type, not where the data currently resides; local or remote is determined by the home socket of the address. An unset source filter counts all root ports; an unset destination filter counts all destinations.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "EventCode": "0x3",
+        "EventName": "PCIE_WR_REQ",
+        "BriefDescription": "Counts write requests from PCIe devices under this PCIe root complex to memory or another PCIe device.",
+        "PublicDescription": "Counts write requests from PCIe devices under this PCIe root complex to memory or another PCIe device, where the PCIe device sends data. Request size can be from 1 to 256 bytes. Filters: src_rp_mask selects the requesting root ports. Alternatively, src_bdf with src_bdf_en selects one requesting device (BDF); it cannot be combined with src_rp_mask and applies to all counters of this PMU. Destination filters select the memory type of the request address: dst_loc_cmem local CMEM, dst_loc_gmem local GMEM, dst_loc_pcie_p2p local PCIe peer addresses, dst_loc_pcie_cxl local CXL memory, dst_rem remote memory. This is the address's home type, not where the data currently resides; local or remote is determined by the home socket of the address. An unset source filter counts all root ports; an unset destination filter counts all destinations.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "EventCode": "0x0",
+        "EventName": "PCIE_RD_BYTES",
+        "BriefDescription": "Counts bytes transferred by the read requests counted by PCIE_RD_REQ.",
+        "PublicDescription": "Counts bytes transferred by the read requests counted by PCIE_RD_REQ. Source and destination filters work as described for PCIE_RD_REQ.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "EventCode": "0x1",
+        "EventName": "PCIE_WR_BYTES",
+        "BriefDescription": "Counts bytes transferred by the write requests counted by PCIE_WR_REQ.",
+        "PublicDescription": "Counts bytes transferred by the write requests counted by PCIE_WR_REQ. Source and destination filters work as described for PCIE_WR_REQ.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "EventCode": "0x4",
+        "EventName": "PCIE_RD_CUM_OUTS",
+        "BriefDescription": "Accumulates the outstanding read requests counted by PCIE_RD_REQ each cycle at the PCIe interface.",
+        "PublicDescription": "Accumulates the outstanding read requests counted by PCIE_RD_REQ each cycle at the PCIe interface. Pair the two under the same filters for the average read latency. Source and destination filters work as described for PCIE_RD_REQ.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "MetricName": "pcie_freq",
+        "MetricGroup": "PCIE_Frequency;PCIE_Read_Latency",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(PCIE_CYCLES / aggr_nr(PCIE_CYCLES)) / 1e9 / duration_time",
+        "ScaleUnit": "1GHz",
+        "BriefDescription": "Frequency of the cycles at the PCIe interface to the Tegra SoC data fabric.",
+        "PublicDescription": "Average frequency of the cycles at the PCIe interface to the Tegra SoC data fabric over the measurement interval.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "MetricName": "pcie_avg_rd_bandwidth_to_all_dst",
+        "MetricGroup": "PCIE_Bandwidth;PCIE_To_All_Destinations",
+        "MetricExpr": "PCIE_RD_BYTES@dst_loc_cmem=1,dst_loc_gmem=1,dst_loc_pcie_p2p=1,dst_loc_pcie_cxl=1,dst_rem=1@ / 1e6 / duration_time",
+        "ScaleUnit": "1MB/s",
+        "BriefDescription": "Average read bandwidth from PCIe devices under this PCIe root complex to all destinations.",
+        "PublicDescription": "Average read bandwidth of requests from all PCIe devices under this PCIe root complex to all destinations: local CMEM, local GMEM, local PCIe peer addresses, local CXL memory and remote memory.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "MetricName": "pcie_avg_wr_bandwidth_to_all_dst",
+        "MetricGroup": "PCIE_Bandwidth;PCIE_To_All_Destinations",
+        "MetricExpr": "PCIE_WR_BYTES@dst_loc_cmem=1,dst_loc_gmem=1,dst_loc_pcie_p2p=1,dst_loc_pcie_cxl=1,dst_rem=1@ / 1e6 / duration_time",
+        "ScaleUnit": "1MB/s",
+        "BriefDescription": "Average write bandwidth from PCIe devices under this PCIe root complex to all destinations.",
+        "PublicDescription": "Average write bandwidth of requests from all PCIe devices under this PCIe root complex to all destinations: local CMEM, local GMEM, local PCIe peer addresses, local CXL memory and remote memory.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "MetricName": "pcie_avg_rd_latency_to_all_dst",
+        "MetricGroup": "PCIE_Read_Latency;PCIE_To_All_Destinations",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(PCIE_RD_CUM_OUTS@dst_loc_cmem=1,dst_loc_gmem=1,dst_loc_pcie_p2p=1,dst_loc_pcie_cxl=1,dst_rem=1@ / PCIE_RD_REQ@dst_loc_cmem=1,dst_loc_gmem=1,dst_loc_pcie_p2p=1,dst_loc_pcie_cxl=1,dst_rem=1@) / pcie_freq",
+        "ScaleUnit": "1ns/request",
+        "BriefDescription": "Average read latency from PCIe devices under this PCIe root complex to all destinations.",
+        "PublicDescription": "Average latency of read requests from all PCIe devices under this PCIe root complex to all destinations: local CMEM, local GMEM, local PCIe peer addresses, local CXL memory and remote memory.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "MetricName": "pcie_avg_rd_bandwidth_to_local_cmem",
+        "MetricGroup": "PCIE_Bandwidth;PCIE_Read;PCIE_To_Local_CMEM",
+        "MetricExpr": "PCIE_RD_BYTES@dst_loc_cmem=1@ / 1e6 / duration_time",
+        "ScaleUnit": "1MB/s",
+        "BriefDescription": "Average read bandwidth from PCIe devices under this PCIe root complex to local CMEM.",
+        "PublicDescription": "Average read bandwidth of requests from all PCIe devices under this PCIe root complex to local CMEM.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "MetricName": "pcie_avg_wr_bandwidth_to_local_cmem",
+        "MetricGroup": "PCIE_Bandwidth;PCIE_Write;PCIE_To_Local_CMEM",
+        "MetricExpr": "PCIE_WR_BYTES@dst_loc_cmem=1@ / 1e6 / duration_time",
+        "ScaleUnit": "1MB/s",
+        "BriefDescription": "Average write bandwidth from PCIe devices under this PCIe root complex to local CMEM.",
+        "PublicDescription": "Average write bandwidth of requests from all PCIe devices under this PCIe root complex to local CMEM.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "MetricName": "pcie_avg_rd_latency_to_local_cmem",
+        "MetricGroup": "PCIE_Read_Latency;PCIE_Read;PCIE_To_Local_CMEM",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(PCIE_RD_CUM_OUTS@dst_loc_cmem=1@ / PCIE_RD_REQ@dst_loc_cmem=1@) / pcie_freq",
+        "ScaleUnit": "1ns/request",
+        "BriefDescription": "Average read latency from PCIe devices under this PCIe root complex to local CMEM.",
+        "PublicDescription": "Average latency of read requests from all PCIe devices under this PCIe root complex to local CMEM.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "MetricName": "pcie_avg_rd_bandwidth_to_local_gmem",
+        "MetricGroup": "PCIE_Bandwidth;PCIE_Read;PCIE_To_Local_GMEM",
+        "MetricExpr": "PCIE_RD_BYTES@dst_loc_gmem=1@ / 1e6 / duration_time",
+        "ScaleUnit": "1MB/s",
+        "BriefDescription": "Average read bandwidth from PCIe devices under this PCIe root complex to local GMEM.",
+        "PublicDescription": "Average read bandwidth of requests from all PCIe devices under this PCIe root complex to local GMEM.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "MetricName": "pcie_avg_wr_bandwidth_to_local_gmem",
+        "MetricGroup": "PCIE_Bandwidth;PCIE_Write;PCIE_To_Local_GMEM",
+        "MetricExpr": "PCIE_WR_BYTES@dst_loc_gmem=1@ / 1e6 / duration_time",
+        "ScaleUnit": "1MB/s",
+        "BriefDescription": "Average write bandwidth from PCIe devices under this PCIe root complex to local GMEM.",
+        "PublicDescription": "Average write bandwidth of requests from all PCIe devices under this PCIe root complex to local GMEM.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "MetricName": "pcie_avg_rd_latency_to_local_gmem",
+        "MetricGroup": "PCIE_Read_Latency;PCIE_Read;PCIE_To_Local_GMEM",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(PCIE_RD_CUM_OUTS@dst_loc_gmem=1@ / PCIE_RD_REQ@dst_loc_gmem=1@) / pcie_freq",
+        "ScaleUnit": "1ns/request",
+        "BriefDescription": "Average read latency from PCIe devices under this PCIe root complex to local GMEM.",
+        "PublicDescription": "Average latency of read requests from all PCIe devices under this PCIe root complex to local GMEM.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "MetricName": "pcie_avg_rd_bandwidth_to_local_cxlmem",
+        "MetricGroup": "PCIE_Bandwidth;PCIE_Read;PCIE_To_Local_CXLMEM",
+        "MetricExpr": "PCIE_RD_BYTES@dst_loc_pcie_cxl=1@ / 1e6 / duration_time",
+        "ScaleUnit": "1MB/s",
+        "BriefDescription": "Average read bandwidth from PCIe devices under this PCIe root complex to local CXL memory.",
+        "PublicDescription": "Average read bandwidth of requests from all PCIe devices under this PCIe root complex to local CXL memory.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "MetricName": "pcie_avg_wr_bandwidth_to_local_cxlmem",
+        "MetricGroup": "PCIE_Bandwidth;PCIE_Write;PCIE_To_Local_CXLMEM",
+        "MetricExpr": "PCIE_WR_BYTES@dst_loc_pcie_cxl=1@ / 1e6 / duration_time",
+        "ScaleUnit": "1MB/s",
+        "BriefDescription": "Average write bandwidth from PCIe devices under this PCIe root complex to local CXL memory.",
+        "PublicDescription": "Average write bandwidth of requests from all PCIe devices under this PCIe root complex to local CXL memory.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "MetricName": "pcie_avg_rd_latency_to_local_cxlmem",
+        "MetricGroup": "PCIE_Read_Latency;PCIE_Read;PCIE_To_Local_CXLMEM",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(PCIE_RD_CUM_OUTS@dst_loc_pcie_cxl=1@ / PCIE_RD_REQ@dst_loc_pcie_cxl=1@) / pcie_freq",
+        "ScaleUnit": "1ns/request",
+        "BriefDescription": "Average read latency from PCIe devices under this PCIe root complex to local CXL memory.",
+        "PublicDescription": "Average latency of read requests from all PCIe devices under this PCIe root complex to local CXL memory.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "MetricName": "pcie_avg_rd_bandwidth_to_remote_mem",
+        "MetricGroup": "PCIE_Bandwidth;PCIE_Read;PCIE_To_Remote_Memory",
+        "MetricExpr": "PCIE_RD_BYTES@dst_rem=1@ / 1e6 / duration_time",
+        "ScaleUnit": "1MB/s",
+        "BriefDescription": "Average read bandwidth from PCIe devices under this PCIe root complex to remote memory.",
+        "PublicDescription": "Average read bandwidth of requests from all PCIe devices under this PCIe root complex to remote memory.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "MetricName": "pcie_avg_wr_bandwidth_to_remote_mem",
+        "MetricGroup": "PCIE_Bandwidth;PCIE_Write;PCIE_To_Remote_Memory",
+        "MetricExpr": "PCIE_WR_BYTES@dst_rem=1@ / 1e6 / duration_time",
+        "ScaleUnit": "1MB/s",
+        "BriefDescription": "Average write bandwidth from PCIe devices under this PCIe root complex to remote memory.",
+        "PublicDescription": "Average write bandwidth of requests from all PCIe devices under this PCIe root complex to remote memory.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "MetricName": "pcie_avg_rd_latency_to_remote_mem",
+        "MetricGroup": "PCIE_Read_Latency;PCIE_Read;PCIE_To_Remote_Memory",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(PCIE_RD_CUM_OUTS@dst_rem=1@ / PCIE_RD_REQ@dst_rem=1@) / pcie_freq",
+        "ScaleUnit": "1ns/request",
+        "BriefDescription": "Average read latency from PCIe devices under this PCIe root complex to remote memory.",
+        "PublicDescription": "Average latency of read requests from all PCIe devices under this PCIe root complex to remote memory.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "MetricName": "pcie_avg_rd_bandwidth_to_local_pcie_peer",
+        "MetricGroup": "PCIE_Bandwidth;PCIE_Read;PCIE_To_Local_PCIE_Peer",
+        "MetricExpr": "PCIE_RD_BYTES@dst_loc_pcie_p2p=1@ / 1e6 / duration_time",
+        "ScaleUnit": "1MB/s",
+        "BriefDescription": "Average read bandwidth from PCIe devices under this PCIe root complex to local PCIe peer addresses.",
+        "PublicDescription": "Average read bandwidth of requests from all PCIe devices under this PCIe root complex to local PCIe peer addresses.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "MetricName": "pcie_avg_wr_bandwidth_to_local_pcie_peer",
+        "MetricGroup": "PCIE_Bandwidth;PCIE_Write;PCIE_To_Local_PCIE_Peer",
+        "MetricExpr": "PCIE_WR_BYTES@dst_loc_pcie_p2p=1@ / 1e6 / duration_time",
+        "ScaleUnit": "1MB/s",
+        "BriefDescription": "Average write bandwidth from PCIe devices under this PCIe root complex to local PCIe peer addresses.",
+        "PublicDescription": "Average write bandwidth of requests from all PCIe devices under this PCIe root complex to local PCIe peer addresses.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    },
+    {
+        "MetricName": "pcie_avg_rd_latency_to_local_pcie_peer",
+        "MetricGroup": "PCIE_Read_Latency;PCIE_Read;PCIE_To_Local_PCIE_Peer",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(PCIE_RD_CUM_OUTS@dst_loc_pcie_p2p=1@ / PCIE_RD_REQ@dst_loc_pcie_p2p=1@) / pcie_freq",
+        "ScaleUnit": "1ns/request",
+        "BriefDescription": "Average read latency from PCIe devices under this PCIe root complex to local PCIe peer addresses.",
+        "PublicDescription": "Average latency of read requests from all PCIe devices under this PCIe root complex to local PCIe peer addresses.",
+        "Compat": "1030136b",
+        "Unit": "nvidia_pcie_pmu_,rc_"
+    }
+]
-- 
2.43.0