# NVIDIA Quadro P400 (Pascal, GP108) on the Mac Pro 3,1: proprietary driver for
# the Sway desktop, plus Docker with GPU/CUDA access for containers.
#
# Driver branch: 580 (nvidiaPackages.legacy_580), NOT the nixpkgs default
# (`production`, currently 595.x). 580 is the last branch that supports
# Maxwell/Pascal/Volta -- NVIDIA keeps it as an LTS branch to Aug 2028 -- and a
# newer branch simply will not drive this card.
#
# The driver is unfree, so it is not in the binary cache: the kernel module is
# compiled locally. On this machine's 2008 Xeons expect the first rebuild after
# a kernel bump to take a long while.
{ config, ... }:

{
  # Selects the proprietary driver; the module blacklists nouveau/nvidiafb and
  # loads nvidia-uvm (needed by CUDA) via modprobe softdep. Naming is historical
  # -- this option drives the kernel/driver choice on Wayland hosts too, which
  # is why it is set on a machine that runs no X server.
  services.xserver.videoDrivers = [ "nvidia" ];

  hardware.nvidia = {
    package = config.boot.kernelPackages.nvidiaPackages.legacy_580;
    # Required for Wayland: sets nvidia-drm.modeset=1 (and fbdev=1), without
    # which wlroots gets no GBM device and Sway/cage fail to start.
    modesetting.enable = true;
    # The open kernel modules need Turing or later; Pascal must use the closed
    # ones. Explicit because the option has no default on driver >= 560.
    open = false;
  };

  # The NVIDIA module only puts these in boot.kernelModules when
  # services.xserver.enable is true, which is false on this Wayland-only host --
  # so load them explicitly rather than relying on udev modalias autoloading.
  # nvidia_uvm (needed by CUDA) is deliberately absent: the module's modprobe
  # softdep pulls it in after the GPU device exists, which is the supported
  # ordering.
  boot.kernelModules = [
    "nvidia"
    "nvidia_modeset"
    "nvidia_drm"
  ];

  # wlroots refuses the proprietary NVIDIA driver unless told to proceed. The
  # greeter's compositor (cage) has no such check; only Sway needs the flag,
  # which the module bakes into the wrapper the session's .desktop file runs.
  programs.sway.extraOptions = [ "--unsupported-gpu" ];

  virtualisation.docker.enable = true;

  # CDI-based GPU access for containers: generates /var/run/cdi specs from the
  # host driver at boot and turns on Docker's CDI feature. Run GPU workloads
  # with `docker run --device=nvidia.com/gpu=all ...`. The deprecated
  # virtualisation.docker.enableNvidia runtime wrapper is deliberately not used.
  hardware.nvidia-container-toolkit.enable = true;

  # The generator needs a loaded kernel module: without one it aborts with
  # "failed to initialize NVML: Driver Not Loaded". That is guaranteed after a
  # kernel bump, where the rebuilt module cannot load until reboot -- and since
  # the unit is requiredBy docker.service and wantedBy multi-user.target, the
  # failure takes Docker down and makes `nixos-rebuild switch` exit non-zero.
  # Skip the run instead when no driver is loaded; the toolkit's udev rule
  # restarts the unit as soon as the nvidia device appears, so the CDI specs are
  # still generated on the next boot.
  systemd.services.nvidia-container-toolkit-cdi-generator.unitConfig.ConditionPathExists =
    "/proc/driver/nvidia/version";
}