commit 902c649b631ada141ee5910f7ee2a45026d5b084
author Harshit Aghera <haghera@nvidia.com> Thu May 08 15:57:42 2025 +0530
committer Ed Tanous <ed@tanous.net> Thu Jul 10 15:01:22 2025 +0000
tree aa5fcb68fbd3b0cbaa298440ec9cd04b708d5376
parent 5e7deccd14dcac790028a6641291cc019c1c4e52

nvidia-gpu: add power sensor

This patch adds support to fetch power sensor value from gpu

Tested: Build an image for gb200nvl-obmc machine with the following
patches cherry picked. This patches are needed to enable the mctp stack.

https://gerrit.openbmc.org/c/openbmc/openbmc/+/79422

```
$ curl -s -k -u 'root:0penBmc' https://10.137.203.137/redfish/v1/Chassis/NVIDIA_GB200_1/Sensors/power_NVIDIA_GB200_GPU_0_Power_0
{
  "@odata.id": "/redfish/v1/Chassis/NVIDIA_GB200_1/Sensors/power_NVIDIA_GB200_GPU_0_Power_0",
  "@odata.type": "#Sensor.v1_2_0.Sensor",
  "Id": "power_NVIDIA_GB200_GPU_0_Power_0",
  "Name": "NVIDIA GB200 GPU 0 Power 0",
  "Reading": 27.181,
  "ReadingRangeMax": 4294967.295,
  "ReadingRangeMin": 0.0,
  "ReadingType": "Power",
  "ReadingUnits": "W",
  "Status": {
    "Health": "OK",
    "State": "Enabled"
  }
}%
```

Change-Id: Ic227a0056daa68ab2239a609ed20c7ed2f6bd2c5
Signed-off-by: Harshit Aghera <haghera@nvidia.com>

src/nvidia-gpu/NvidiaGpuMctpVdm.hpp

diff --git a/src/nvidia-gpu/NvidiaGpuMctpVdm.hpp b/src/nvidia-gpu/NvidiaGpuMctpVdm.hpp
index f7c78b8..c7f7511 100644
--- a/src/nvidia-gpu/NvidiaGpuMctpVdm.hpp
+++ b/src/nvidia-gpu/NvidiaGpuMctpVdm.hpp
@@ -31,6 +31,7 @@
 {
     GET_TEMPERATURE_READING = 0x00,
     READ_THERMAL_PARAMETERS = 0x02,
+    GET_CURRENT_POWER_DRAW = 0x03,
 };
 
 enum class DeviceIdentification : uint8_t
@@ -60,6 +61,13 @@
 
 using ReadThermalParametersRequest = GetNumericSensorReadingRequest;
 
+struct GetCurrentPowerDrawRequest
+{
+    ocp::accelerator_management::CommonRequest hdr;
+    uint8_t sensorId;
+    uint8_t averagingInterval;
+} __attribute__((packed));
+
 struct GetTemperatureReadingResponse
 {
     ocp::accelerator_management::CommonResponse hdr;
@@ -72,6 +80,12 @@
     int32_t threshold;
 } __attribute__((packed));
 
+struct GetCurrentPowerDrawResponse
+{
+    ocp::accelerator_management::CommonResponse hdr;
+    uint32_t power;
+} __attribute__((packed));
+
 int packHeader(const ocp::accelerator_management::BindingPciVidInfo& hdr,
                ocp::accelerator_management::BindingPciVid& msg);
 
@@ -99,4 +113,12 @@
     ocp::accelerator_management::CompletionCode& cc, uint16_t& reasonCode,
     int32_t& threshold);
 
+int encodeGetCurrentPowerDrawRequest(uint8_t instanceId, uint8_t sensorId,
+                                     uint8_t averagingInterval,
+                                     std::span<uint8_t> buf);
+
+int decodeGetCurrentPowerDrawResponse(
+    std::span<const uint8_t> buf,
+    ocp::accelerator_management::CompletionCode& cc, uint16_t& reasonCode,
+    uint32_t& power);
 } // namespace gpu