Configuring GPU passthrough for a virtual machine

After installing a GPU device on the host, follow the steps in this section to complete the relevant configuration to use the GPU device on a virtual machine.

Preparation

Obtain the GPU driver for the virtual machine. You should obtain the GPU driver from the official website of the GPU device manufacturer based on the GPU model, virtual machine operating system, and driver version officially supported by the GPU device manufacturer.

Configuration process

1. If you use an NVIDIA GPU, you need to log in to the host and run commands to disable nouveau drivers.

   1. Run the following commands to create two configuration files:

      cat <<_EOF_ > /etc/modprobe.d/gpu-passthrough-disable-nouveau.conf
      blacklist nouveau
      options nouveau modeset=0
      _EOF_

      cat <<_EOF_ > /usr/lib/modprobe.d/gpu-passthrough-disable-nouveau.conf
      blacklist nouveau
      options nouveau modeset=0
      _EOF_

   2. Run the following command to uninstall the nouveau module:

      modprobe -r nouveau

2. Log in to AOC to enable IOMMU for the host where the GPU device is located and restart the host.

3. Set the GPU mode to passthrough.

   If you are using this GPU device for the first time, the GPU mode is passthrough by default. You can proceed directly to step 4. If the GPU has previously been sliced into vGPUs, you need to first switch the GPU mode to passthrough.

4. Mount the GPU device to the virtual machine.

5. To install GPU drivers for virtual machines, refer to the official technical documentation provided by the GPU device manufacturer.

6. Restart the virtual machine.