//SPDX-License-Identifier: LGPL-3.0-only
//SPDX-FileCopyrightText: Copyright (C) 2026 Catcrafts®

// Issue #160: the swapchain gets as many images as its present mode needs,
// and the frame loop takes however many that is. CreateSwapchain used to ask
// for exactly Window::numFrames (3) images whatever the surface said, read
// them into a three-element array, and key everything a frame in flight
// owns, its command buffer, its fence and the descriptor-heap copy holding
// "its" swapchain image, by the acquired image index. A swapchain of any
// other size fell back to FIFO (asked for MAILBOX or IMMEDIATE) or threw,
// and a surface whose minimum is above three got a create info below it.
// Mesa's MAILBOX needs at least four images: Turnip on phoc, and llvmpipe on
// any Wayland compositor.
//
// Checked here:
//
//   - Window::SwapchainMinImageCount on the numbers drivers report.
//   - For every present mode the surface offers, SetPresentMode makes a
//     swapchain of that mode, with at least the images the window asks for
//     (Window::SwapchainCapabilities, the mode's own count where the device
//     has swapchain_maintenance1).
//   - Every frame draws into the image it presents. A UI pass fills the
//     window with a colour that differs from frame to frame, and a transfer
//     pass after it copies the middle texel of the frame's swapchain image
//     into the frame slot's buffer, read back when the slot comes round
//     again. With an image count other than numFrames, frames and images
//     pair up differently from frame to frame: a heap copy that kept one
//     image would have the UI draw into another frame's image, and the texel
//     would hold an older colour.
//   - A SetPresentMode or Resize from a listener of the frame being recorded
//     takes effect after that frame's present: the rest of the frame indexes
//     the swapchain it acquired from.
//   - A swapchain slot listed during a frame is written for that frame (heap
//     mode, where the descriptor can be read back and compared with the UI's).
//   - Two windows sharing one heap each draw their own colours: a window
//     writes only its own swapchain slots.
//   - No Vulkan validation errors, which only means something with
//     CRAFTER_GRAPHICS_VALIDATION set and the layer loaded.
//
// The GPU this process picks may give every mode numFrames images (NVIDIA
// does), which leaves the case that matters untried, and a process runs one
// binding model. So the frame checks also run in child processes, picked
// with CRAFTER_GRAPHICS_DEVICE, on a GPU whose surface needs more images for
// some mode (this process's own, else llvmpipe, which most Linux machines
// have), in each binding model the parent didn't run there: on the
// descriptor heap, and with CRAFTER_GRAPHICS_NO_DESCRIPTOR_HEAP on descriptor
// sets, the path Turnip takes. Without such a GPU that part is a note, not a
// failure. `--frames heap|sets` runs the frame checks alone on whichever GPU
// the environment picks.
//
// Needs a live Wayland compositor and a Vulkan device, like FrameLoopSync.

#include "vulkan/vulkan.h"
#include "vulkan/vk_enum_string_helper.h"
#include <cstdlib>
#include <cstring>

import Crafter.Graphics;
import Crafter.Event;
import std;

using namespace Crafter;
namespace fs = std::filesystem;

namespace {

int failures = 0;

void Check(bool ok, std::string_view what) {
    std::println("{}  {}", ok ? "PASS" : "FAIL", what);
    if (!ok) ++failures;
}

// The test binary's own directory: the build places the UI kernels (both
// variants) next to it, and the test runner's working directory is not that
// directory.
fs::path ExeDir() {
    return fs::read_symlink("/proc/self/exe").parent_path();
}

int RunCommand(const std::string& cmd) {
    int status = std::system(cmd.c_str());
    if (status == -1) return -1;
    return (status & 0x7f) == 0 ? ((status >> 8) & 0xff) : 128 + (status & 0x7f);
}

struct ModeCase {
    PresentMode      mode;
    VkPresentModeKHR vk;
    std::string_view name;
};
constexpr ModeCase kModes[] = {
    { PresentMode::Fifo,      VK_PRESENT_MODE_FIFO_KHR,      "FIFO" },
    { PresentMode::Mailbox,   VK_PRESENT_MODE_MAILBOX_KHR,   "MAILBOX" },
    { PresentMode::Immediate, VK_PRESENT_MODE_IMMEDIATE_KHR, "IMMEDIATE" },
};

std::vector<VkPresentModeKHR> OfferedModes(VkPhysicalDevice gpu, VkSurfaceKHR surface) {
    std::uint32_t count = 0;
    Device::CheckVkResult(vkGetPhysicalDeviceSurfacePresentModesKHR(gpu, surface, &count, nullptr));
    std::vector<VkPresentModeKHR> modes(count);
    Device::CheckVkResult(vkGetPhysicalDeviceSurfacePresentModesKHR(gpu, surface, &count, modes.data()));
    return modes;
}

bool Offers(const std::vector<VkPresentModeKHR>& offered, VkPresentModeKHR mode) {
    return std::ranges::find(offered, mode) != offered.end();
}

// The most images any present mode under test asks for, for a swapchain of
// `surface` on `gpu`, sized as a window on it would size it.
std::uint32_t MostImagesAsked(VkPhysicalDevice gpu, VkSurfaceKHR surface, bool modePassedAlong) {
    const std::vector<VkPresentModeKHR> offered = OfferedModes(gpu, surface);
    std::uint32_t most = 0;
    for (const ModeCase& m : kModes) {
        if (Offers(offered, m.vk)) {
            most = std::max(most, Window::SwapchainMinImageCount(
                Window::SwapchainCapabilities(gpu, surface, m.vk, modePassedAlong)));
        }
    }
    return most;
}

void CheckMinImageCount() {
    const auto asked = [](std::uint32_t minImageCount, std::uint32_t maxImageCount) {
        VkSurfaceCapabilitiesKHR capabilities{};
        capabilities.minImageCount = minImageCount;
        capabilities.maxImageCount = maxImageCount;
        return Window::SwapchainMinImageCount(capabilities);
    };
    Check(asked(2, 8) == Window::numFrames, "a minimum below numFrames asks for numFrames (NVIDIA: 2, at most 8)");
    Check(asked(3, 0) == 3, "a minimum of numFrames asks for numFrames (Mesa's FIFO: 3, no maximum)");
    Check(asked(4, 0) == 4, "a minimum above numFrames asks for the minimum (Mesa's MAILBOX: 4, no maximum)");
    Check(asked(5, 6) == 5, "a minimum above numFrames within the maximum asks for the minimum");
    Check(asked(1, 2) == 2, "a maximum below numFrames caps the request");
    Check(asked(2, 0) == Window::numFrames, "no maximum leaves numFrames as it is");
}

// A colour for frame `n` that differs from every frame's within 200 of it,
// exact in eight bits.
std::array<std::uint8_t, 3> Colour(std::uint64_t n) {
    return {
        static_cast<std::uint8_t>(40 + (n * 7) % 200),
        static_cast<std::uint8_t>(250 - (n * 13) % 200),
        static_cast<std::uint8_t>((n * 29) % 256),
    };
}

// Copies the middle texel of the frame's swapchain image into the frame
// slot's buffer, after the UI pass drew it: what the frame presents. Added
// only for an 8-bit RGBA or BGRA swapchain, whose texel fits the buffer.
struct ReadbackPass : RenderPass {
    std::array<VulkanBuffer<std::uint32_t, true>, Window::numFrames> texels;

    void Record(VkCommandBuffer cmd, std::uint32_t frameIdx, Window& window) override {
        const VkBufferImageCopy region {
            .imageSubresource = { VK_IMAGE_ASPECT_COLOR_BIT, 0, 0, 1 },
            .imageOffset      = { static_cast<std::int32_t>(window.width / 2), static_cast<std::int32_t>(window.height / 2), 0 },
            .imageExtent      = { 1, 1, 1 },
        };
        vkCmdCopyImageToBuffer(cmd, window.images[window.currentImage], VK_IMAGE_LAYOUT_GENERAL,
                               texels[frameIdx].buffer, 1, &region);
        const VkBufferMemoryBarrier copied {
            .sType               = VK_STRUCTURE_TYPE_BUFFER_MEMORY_BARRIER,
            .srcAccessMask       = VK_ACCESS_TRANSFER_WRITE_BIT,
            .dstAccessMask       = VK_ACCESS_HOST_READ_BIT,
            .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
            .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
            .buffer              = texels[frameIdx].buffer,
            .offset              = 0,
            .size                = VK_WHOLE_SIZE,
        };
        vkCmdPipelineBarrier(cmd, VK_PIPELINE_STAGE_TRANSFER_BIT, VK_PIPELINE_STAGE_HOST_BIT,
                             0, 0, nullptr, 1, &copied, 0, nullptr);
    }

    VkPipelineStageFlags SwapchainStage() const override {
        return VK_PIPELINE_STAGE_TRANSFER_BIT;
    }
};

// One window filled with a colour per frame through a UIRenderer on `heap`,
// and what each frame presented read back. Holds listeners that capture it:
// build it in place and don't move it.
struct ColourScene {
    Window& window;
    GraphicsDescriptorHeap& heap;
    std::string_view name;
    // Added to the frame number: two scenes sharing a heap draw different
    // colours, so one that drew into the other's image is seen.
    std::uint64_t colourOffset;

    UIRenderer ui;
    // One quad buffer per frame slot: the colour changes every frame, and a
    // buffer the frames shared would be overwritten under the frames still
    // in flight.
    std::array<GraphicsBuffer<QuadItem, true>, Window::numFrames> quads;
    std::array<BufferSlot, Window::numFrames> quadSlots;
    ReadbackPass readback;
    bool bgra = false;
    bool checkTexels = false;

    // The frame each slot's texel buffer holds, -1 for none, and what the
    // texel checks found since Reset.
    std::array<std::int64_t, Window::numFrames> frameOfSlot;
    std::uint64_t frame = 0;
    std::uint64_t framesChecked = 0;
    std::uint32_t wrong = 0;
    std::string firstWrong;
    std::set<std::uint32_t> imagesUsed;
    std::set<std::pair<std::uint32_t, std::uint32_t>> pairsUsed;
    // Run once at the start of the next frame's build, then dropped.
    std::function<void()> duringNextFrame;
    EventListener<UIBuildArgs> buildSub;

    ColourScene(Window& window, GraphicsDescriptorHeap& heap, std::string_view name, std::uint64_t colourOffset)
        : window(window), heap(heap), name(name), colourOffset(colourOffset) {
        const fs::path dir = ExeDir();
        VkCommandBuffer init = window.StartInit();
        ui.Initialize(window, heap, init,
                      dir / "ui-quads.comp.spv", dir / "ui-circles.comp.spv",
                      dir / "ui-images.comp.spv", dir / "ui-text.comp.spv",
                      dir / "ui-fused.comp.spv");
        for (std::uint32_t f = 0; f < Window::numFrames; ++f) {
            quads[f].Create(VK_BUFFER_USAGE_STORAGE_BUFFER_BIT | VK_BUFFER_USAGE_SHADER_DEVICE_ADDRESS_BIT,
                            VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT, 1, VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT);
            quadSlots[f] = ui.RegisterBuffer(quads[f]);
        }
        bgra = window.colorFormat == VK_FORMAT_B8G8R8A8_UNORM;
        checkTexels = bgra || window.colorFormat == VK_FORMAT_R8G8B8A8_UNORM;
        window.passes.push_back(&ui);
        if (checkTexels) {
            for (VulkanBuffer<std::uint32_t, true>& texel : readback.texels) {
                texel.Create(VK_BUFFER_USAGE_TRANSFER_DST_BIT,
                             VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT, 1);
            }
            window.passes.push_back(&readback);
        } else {
            std::println("NOTE  {}: the swapchain format {} isn't 8-bit RGBA or BGRA: its colours aren't checked",
                         name, string_VkFormat(window.colorFormat));
        }
        window.FinishInit();
        Reset();

        buildSub.SetEvent(&ui.onBuild, [this](UIBuildArgs a) {
            if (duringNextFrame) {
                std::function<void()> run = std::move(duringNextFrame);
                duringNextFrame = nullptr;
                run();
            }
            // The slot's fence has been waited: its buffer holds what the
            // frame numFrames ago presented. This frame's copy comes after.
            CheckSlot(a.frameIdx);
            frameOfSlot[a.frameIdx] = static_cast<std::int64_t>(frame);
            imagesUsed.insert(this->window.currentImage);
            pairsUsed.insert({ a.frameIdx, this->window.currentImage });

            const std::array<std::uint8_t, 3> colour = Colour(frame + this->colourOffset);
            quads[a.frameIdx].value[0] = QuadItem{ 0, 0, 4096, 4096,
                colour[0] / 255.0f, colour[1] / 255.0f, colour[2] / 255.0f, 1.0f,
                0, 0, 0, 0,  0, 0, 0, 0 };
            quads[a.frameIdx].FlushDevice(a.cmd, VK_ACCESS_SHADER_READ_BIT, VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT);
            ui.DispatchQuads(a.cmd, quadSlots[a.frameIdx], 1);
        });
    }

    ~ColourScene() {
        std::erase(window.passes, &ui);
        std::erase(window.passes, &readback);
    }

    void Reset() {
        frameOfSlot.fill(-1);
        framesChecked = 0;
        wrong = 0;
        firstWrong.clear();
        imagesUsed.clear();
        pairsUsed.clear();
    }

    void CheckSlot(std::uint32_t slot) {
        if (!checkTexels || frameOfSlot[slot] < 0) return;
        const std::uint32_t texel = readback.texels[slot].value[0];
        const std::array<std::uint8_t, 3> rgb = bgra
            ? std::array<std::uint8_t, 3>{ static_cast<std::uint8_t>(texel >> 16), static_cast<std::uint8_t>(texel >> 8), static_cast<std::uint8_t>(texel) }
            : std::array<std::uint8_t, 3>{ static_cast<std::uint8_t>(texel), static_cast<std::uint8_t>(texel >> 8), static_cast<std::uint8_t>(texel >> 16) };
        const std::array<std::uint8_t, 3> expected = Colour(static_cast<std::uint64_t>(frameOfSlot[slot]) + colourOffset);
        bool same = true;
        for (std::size_t c = 0; c < 3; ++c) {
            same = same && std::abs(static_cast<int>(rgb[c]) - static_cast<int>(expected[c])) <= 1;
        }
        ++framesChecked;
        if (!same && wrong++ == 0) {
            firstWrong = std::format("frame {} presented ({}, {}, {}), drew ({}, {}, {})", frameOfSlot[slot],
                                     rgb[0], rgb[1], rgb[2], expected[0], expected[1], expected[2]);
        }
    }

    // One frame of this scene's window.
    void Render() {
        window.Render();
        ++frame;
    }

    // After the frames since Reset: settles the queue, reads the slots not
    // read yet, and reports.
    void Report(std::string_view what) {
        Device::CheckVkResult(vkQueueWaitIdle(Device::queue));
        for (std::uint32_t slot = 0; slot < Window::numFrames; ++slot) {
            CheckSlot(slot);
            frameOfSlot[slot] = -1;
        }
        if (checkTexels) {
            Check(wrong == 0, std::format("{}: each of {} frames presented the colour it drew{}", what, framesChecked,
                                          wrong == 0 ? std::string() : std::format(" ({} didn't; {})", wrong, firstWrong)));
        }
    }
};

// The present modes on the scene's window, then a rebuild asked for during a
// frame, then a slot listed during one. Sets `moreImagesThanFrames` when some
// mode's swapchain had more images than numFrames.
void CheckModes(ColourScene& scene, bool& moreImagesThanFrames) {
    Window& window = scene.window;
    const std::vector<VkPresentModeKHR> offered = OfferedModes(Device::physDevice, window.vulkanSurface);
    for (const ModeCase& m : kModes) {
        if (!Offers(offered, m.vk)) {
            std::println("NOTE  the surface doesn't offer {}", m.name);
            continue;
        }
        // Asked before the swapchain is made, which asks again: the
        // validation layer checks the image count against the last answer.
        const VkSurfaceCapabilitiesKHR capabilities = Window::SwapchainCapabilities(
            Device::physDevice, window.vulkanSurface, m.vk, Device::swapchainMaintenance1Supported);
        const std::uint32_t asked = Window::SwapchainMinImageCount(capabilities);
        window.SetPresentMode(m.mode);
        Check(window.swapchainPresentMode == m.vk,
              std::format("{}: the swapchain was made with it, not a fallback ({})", m.name, string_VkPresentModeKHR(window.swapchainPresentMode)));
        const std::size_t images = window.images.size();
        Check(images >= asked && images >= capabilities.minImageCount,
              std::format("{}: {} images, at least the {} asked for and the mode's minimum of {}", m.name, images, asked, capabilities.minImageCount));
        Check(window.imageViewInfos.size() == images && window.imageViews.size() == images
                  && window.imageInitialised.size() == images && window.renderFinishedSemaphores.size() >= images,
              std::format("{}: the per-image state covers all {} images", m.name, images));
        moreImagesThanFrames = moreImagesThanFrames || images > Window::numFrames;

        scene.Reset();
        // Enough frames for every frame slot to meet several images.
        const std::uint64_t frames = 4 * std::max<std::uint64_t>(images, Window::numFrames);
        for (std::uint64_t i = 0; i < frames; ++i) {
            scene.Render();
        }
        scene.Report(m.name);
        Check(scene.imagesUsed.size() > 1, std::format("{}: the frames went round {} of the {} images", m.name, scene.imagesUsed.size(), images));
        std::println("      {}: {} images, {} pairings of frame slot and image", m.name, images, scene.pairsUsed.size());
    }

    // A present mode set, and a resize asked for, from a listener of the
    // frame being recorded: the frame goes on with the swapchain it
    // acquired from, and the new one is made after its present.
    const ModeCase* first = nullptr;
    const ModeCase* second = nullptr;
    for (const ModeCase& m : kModes) {
        if (!Offers(offered, m.vk)) continue;
        (first == nullptr ? first : second) = &m;
        if (second != nullptr) break;
    }
    if (second != nullptr) {
        window.SetPresentMode(first->mode);
        const VkSwapchainKHR before = window.swapChain;
        const std::uint32_t widthBefore = window.width;
        const std::uint32_t heightBefore = window.height;
        bool unchangedInFrame = false;
        scene.duringNextFrame = [&] {
            window.SetPresentMode(second->mode);
            window.Resize(widthBefore + 16, heightBefore + 8);
            unchangedInFrame = window.swapChain == before && window.swapchainPresentMode == first->vk
                && window.width == widthBefore && window.height == heightBefore && window.currentImage < window.images.size();
        };
        scene.Reset();
        scene.Render();
        Check(unchangedInFrame, std::format("a {} -> {} switch and a resize asked for during a frame leave that frame's swapchain and size alone",
                                            first->name, second->name));
        Check(window.swapChain != before && window.swapchainPresentMode == second->vk,
              std::format("after the frame the swapchain is made again, with {} ({})", second->name, string_VkPresentModeKHR(window.swapchainPresentMode)));
        Check(window.width == widthBefore + 16 && window.height == heightBefore + 8,
              std::format("after the frame the window has the size asked for ({}x{})", window.width, window.height));
        for (int i = 0; i < 2 * Window::numFrames; ++i) {
            scene.Render();
        }
        scene.Report("after the rebuild a frame asked for");
    } else {
        std::println("NOTE  the surface offers one present mode: no mid-frame switch to check");
    }

    // A swapchain slot listed during a frame holds that frame's image at
    // once: in heap mode the descriptor bytes match the UI output slot's,
    // which the frame wrote before onUpdate.
    if (Device::descriptorHeapSupported) {
        const ImageSlotRange spare = scene.heap.AllocateImageSlots(1);
        bool same = false;
        scene.duringNextFrame = [&] {
            scene.heap.AddSwapchainSlot(spare.firstElement, window);
            const std::uint8_t* copy = scene.heap.resourceHeap[window.currentFrame].value;
            same = std::memcmp(copy + scene.heap.ImageByteOffset(spare.firstElement),
                               copy + scene.heap.ImageByteOffset(scene.ui.OutImageSlot()),
                               Device::descriptorHeapProperties.imageDescriptorSize) == 0;
        };
        scene.Render();
        Device::CheckVkResult(vkQueueWaitIdle(Device::queue));
        scene.heap.FreeImageSlots(spare);
        Check(same, "a swapchain slot listed during a frame holds that frame's image at once");
    }
}

// Renders on this process's GPU: every offered mode on one window, then two
// windows sharing the heap. Sets `moreImagesThanFrames` when some mode's
// swapchain had more images than numFrames.
int RenderFrames(bool& moreImagesThanFrames) {
    // Two scenes' output slots, one spare for the mid-frame slot, and each
    // scene's quad buffers.
    GraphicsDescriptorHeap heap;
    heap.Initialize(/*images*/ 3, /*buffers*/ 2 * Window::numFrames, /*samplers*/ 1);
    {
        Window window(160, 120, "SwapchainImageCount test");
        window.descriptorHeap = &heap;
        {
            ColourScene scene(window, heap, "first window", 0);
            CheckModes(scene, moreImagesThanFrames);

            // A second window on the same heap. Interleaved frames: one
            // window's slot writes land in copies the other's frames in
            // flight are bound to, and must not touch its slots.
            Window second(160, 120, "SwapchainImageCount second window");
            second.descriptorHeap = &heap;
            {
                ColourScene other(second, heap, "second window", 100);
                scene.Reset();
                for (int i = 0; i < 4 * Window::numFrames; ++i) {
                    scene.Render();
                    other.Render();
                }
                scene.Report("two windows on one heap, the first");
                other.Report("two windows on one heap, the second");
            }
            Device::CheckVkResult(vkQueueWaitIdle(Device::queue));
        }
        Device::CheckVkResult(vkQueueWaitIdle(Device::queue));
    }

    if (std::getenv("CRAFTER_GRAPHICS_VALIDATION") != nullptr) {
        Check(Device::validationErrorCount == 0,
              std::format("no Vulkan validation errors ({} seen)", Device::validationErrorCount));
    }
    return failures == 0 ? EXIT_SUCCESS : EXIT_FAILURE;
}

// A child's run of the frame checks in binding model `model` ("heap" or
// "sets") on whatever GPU its environment picks.
int FramesOnly(std::string_view model) {
    try {
        Device::Initialize();
    } catch (const std::runtime_error& error) {
        // A missing capability is a skip; anything else that failed is a
        // failure of the run that was asked for.
        if (std::string_view(error.what()).find("can't run this application") != std::string_view::npos) {
            std::println("SKIP  this GPU can't run the library: {}", error.what());
            return 77;
        }
        std::println("FAIL  Device::Initialize: {}", error.what());
        return EXIT_FAILURE;
    }
    std::println("      on {}, {}", std::string_view(Device::deviceProperties.deviceName),
                 Device::descriptorHeapSupported ? "descriptor heap" : "descriptor sets");
    if (model == "heap" && !Device::descriptorHeapSupported) {
        std::println("SKIP  this GPU has no descriptor heap");
        return 77;
    }
    Check(Device::descriptorHeapSupported == (model == "heap"),
          std::format("the run is on {}, as asked", model == "heap" ? "the descriptor heap" : "descriptor sets"));
    bool moreImagesThanFrames = false;
    return RenderFrames(moreImagesThanFrames);
}

// The number CRAFTER_GRAPHICS_DEVICE gives the GPU `gpu` is one of.
std::optional<std::size_t> GpuNumber(const std::vector<std::vector<VkPhysicalDevice>>& gpus, VkPhysicalDevice gpu) {
    for (std::size_t i = 0; i < gpus.size(); ++i) {
        if (std::ranges::find(gpus[i], gpu) != gpus[i].end()) return i;
    }
    return std::nullopt;
}

bool PresentsTo(VkPhysicalDevice gpu, VkSurfaceKHR surface) {
    std::uint32_t families = 0;
    vkGetPhysicalDeviceQueueFamilyProperties(gpu, &families, nullptr);
    for (std::uint32_t family = 0; family < families; ++family) {
        VkBool32 supported = VK_FALSE;
        if (vkGetPhysicalDeviceSurfaceSupportKHR(gpu, family, surface, &supported) == VK_SUCCESS && supported) {
            return true;
        }
    }
    return false;
}

// The number of a GPU, other than `own`, whose swapchain for `surface` would
// have more images than numFrames in some mode. Whether it has
// swapchain_maintenance1 isn't known without a device, so its counts are
// taken as without: at most an overestimate, and that GPU's MAILBOX needs the
// most either way.
std::optional<std::size_t> GpuWithMoreImages(const std::vector<std::vector<VkPhysicalDevice>>& gpus,
                                             std::size_t own, VkSurfaceKHR surface) {
    for (std::size_t i = 0; i < gpus.size(); ++i) {
        if (i == own || !PresentsTo(gpus[i].front(), surface)) continue;
        if (MostImagesAsked(gpus[i].front(), surface, /*modePassedAlong*/ false) > Window::numFrames) {
            return i;
        }
    }
    return std::nullopt;
}

int Drive() {
    CheckMinImageCount();

    Device::Initialize();
    const bool ownHeap = Device::descriptorHeapSupported;
    std::println("      on {}, {}, swapchain_maintenance1 {}", std::string_view(Device::deviceProperties.deviceName),
                 ownHeap ? "descriptor heap" : "descriptor sets", Device::swapchainMaintenance1Supported ? "on" : "off");
    bool moreImagesThanFrames = false;
    RenderFrames(moreImagesThanFrames);

    // Where frames and images pair up differently, on each binding model:
    // this process covered its own GPU's model if that GPU makes more images
    // than frames; the children cover the rest.
    const std::vector<std::vector<VkPhysicalDevice>> gpus = Device::DistinctGpus(Device::instance);
    const std::optional<std::size_t> own = GpuNumber(gpus, Device::physDevice);
    std::optional<std::size_t> target = moreImagesThanFrames ? own : std::nullopt;
    if (!target && own) {
        Window probe(160, 120, "SwapchainImageCount probe");
        target = GpuWithMoreImages(gpus, *own, probe.vulkanSurface);
    }
    if (!target) {
        std::println("NOTE  no GPU here makes a swapchain with more than {} images, "
                     "so frames and images were never paired differently", Window::numFrames);
        return failures == 0 ? EXIT_SUCCESS : EXIT_FAILURE;
    }

    const fs::path exe = fs::read_symlink("/proc/self/exe");
    const auto child = [&](std::string_view model) {
        // `env -u` so a CRAFTER_GRAPHICS_NO_DESCRIPTOR_HEAP inherited from
        // the caller's environment can't turn the heap run into a sets run.
        // LP_NUM_THREADS keeps llvmpipe, the usual target, off most of the
        // machine's cores while the other tests run, timing ones among them.
        // env reads its options before the first assignment.
        const int exit = RunCommand(std::format("env {} LP_NUM_THREADS=4 CRAFTER_GRAPHICS_DEVICE={} '{}' --frames {}",
            model == "heap" ? "-u CRAFTER_GRAPHICS_NO_DESCRIPTOR_HEAP" : "CRAFTER_GRAPHICS_NO_DESCRIPTOR_HEAP=1",
            *target, exe.string(), model));
        if (exit == 77) {
            std::println("NOTE  GPU {} skipped the run on {} (above)", *target, model);
        } else {
            Check(exit == 0, std::format("GPU {} draws the frames right on {} (exit {})", *target, model, exit));
        }
    };
    const bool coveredHere = moreImagesThanFrames;
    if (!(coveredHere && ownHeap)) child("heap");
    if (!(coveredHere && !ownHeap)) child("sets");
    return failures == 0 ? EXIT_SUCCESS : EXIT_FAILURE;
}

} // namespace

int main(int argc, char** argv) {
    // It would override every present mode under test.
    unsetenv("CRAFTER_PRESENT_IMMEDIATE");
    const int result = argc == 3 && std::string_view(argv[1]) == "--frames" ? FramesOnly(argv[2]) : Drive();
    std::println("{}", result == EXIT_SUCCESS ? "all checks passed" : result == 77 ? "skipped" : "check(s) failed");
    return result;
}