commit 775199d2599981d2c4460c7c1e91a607829e9f0c
author Harshit Aghera <haghera@nvidia.com> Tue May 27 14:20:24 2025 +0530
committer Ed Tanous <ed@tanous.net> Thu Jul 10 15:01:22 2025 +0000
tree df57e4f6a84ed5c663a072a553bdd970d7a0bed1
parent 902c649b631ada141ee5910f7ee2a45026d5b084

nvidia-gpu: add energy sensor

This commit introduces a energy sensor for the 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/energy_NVIDIA_GB200_GPU_0_Energy_0
{
  "@odata.id": "/redfish/v1/Chassis/NVIDIA_GB200_1/Sensors/energy_NVIDIA_GB200_GPU_0_Energy_0",
  "@odata.type": "#Sensor.v1_2_0.Sensor",
  "Id": "energy_NVIDIA_GB200_GPU_0_Energy_0",
  "Name": "NVIDIA GB200 GPU 0 Energy 0",
  "Reading": 269947.856,
  "ReadingRangeMax": 1.8446744073709552e+16,
  "ReadingRangeMin": 0.0,
  "ReadingType": "EnergyJoules",
  "ReadingUnits": "J",
  "Status": {
    "Health": "OK",
    "State": "Enabled"
  }
}%
```

Change-Id: I6f53ab2a83eedd54005bbdcd781dc8d320d7f26a
Signed-off-by: Harshit Aghera <haghera@nvidia.com>

src/nvidia-gpu/NvidiaGpuEnergySensor.hpp

diff --git a/src/nvidia-gpu/NvidiaGpuEnergySensor.hpp b/src/nvidia-gpu/NvidiaGpuEnergySensor.hpp
new file mode 100644
index 0000000..19bb982
--- /dev/null
+++ b/src/nvidia-gpu/NvidiaGpuEnergySensor.hpp
@@ -0,0 +1,58 @@
+/*
+ * SPDX-FileCopyrightText: Copyright (c) 2024-2025 NVIDIA CORPORATION &
+ * AFFILIATES. All rights reserved.
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+#pragma once
+
+#include "MctpRequester.hpp"
+#include "Thresholds.hpp"
+#include "sensor.hpp"
+
+#include <NvidiaGpuMctpVdm.hpp>
+#include <sdbusplus/asio/connection.hpp>
+#include <sdbusplus/asio/object_server.hpp>
+
+#include <array>
+#include <cstdint>
+#include <memory>
+#include <string>
+#include <vector>
+
+constexpr uint8_t gpuEnergySensorId{0};
+
+struct NvidiaGpuEnergySensor : public Sensor
+{
+  public:
+    NvidiaGpuEnergySensor(
+        std::shared_ptr<sdbusplus::asio::connection>& conn,
+        mctp::MctpRequester& mctpRequester, const std::string& name,
+        const std::string& sensorConfiguration, uint8_t eid, uint8_t sensorId,
+        sdbusplus::asio::object_server& objectServer,
+        std::vector<thresholds::Threshold>&& thresholdData);
+
+    ~NvidiaGpuEnergySensor() override;
+
+    void checkThresholds() override;
+
+    void update();
+
+  private:
+    void processResponse(int sendRecvMsgResult);
+
+    uint8_t eid{};
+
+    uint8_t sensorId;
+
+    std::shared_ptr<sdbusplus::asio::connection> conn;
+
+    mctp::MctpRequester& mctpRequester;
+
+    sdbusplus::asio::object_server& objectServer;
+
+    std::array<uint8_t, sizeof(gpu::GetCurrentEnergyCounterRequest)> request{};
+
+    std::array<uint8_t, sizeof(gpu::GetCurrentEnergyCounterResponse)>
+        response{};
+};