#include "Application.h"
#include "lodepng.h"
#include <string>

#ifdef _WIN32
	#include <codecvt>
#else
	#include <game-activity/native_app_glue/android_native_app_glue.h>
	#include <game-activity/GameActivity.h>
    #include <vulkan/vulkan_android.h>
	#include "../app/src/main/cpp/AndroidOut.h"
	#include "../app/src/main/cpp/DebugLog.h"
#endif

#ifdef _WIN32
#define FACE_DBG_LOG(...) ((void)0)
#else
#define FACE_DBG_LOG(...) DebugLog::log(__VA_ARGS__)
#endif

static const char* VkResultStr(VkResult r) {
	switch (r) {
		case VK_SUCCESS:                        return "VK_SUCCESS";
		case VK_NOT_READY:                      return "VK_NOT_READY";
		case VK_TIMEOUT:                        return "VK_TIMEOUT";
		case VK_EVENT_SET:                      return "VK_EVENT_SET";
		case VK_EVENT_RESET:                    return "VK_EVENT_RESET";
		case VK_INCOMPLETE:                     return "VK_INCOMPLETE";
		case VK_SUBOPTIMAL_KHR:                 return "VK_SUBOPTIMAL_KHR";
		case VK_ERROR_OUT_OF_HOST_MEMORY:       return "VK_ERROR_OUT_OF_HOST_MEMORY";
		case VK_ERROR_OUT_OF_DEVICE_MEMORY:     return "VK_ERROR_OUT_OF_DEVICE_MEMORY";
		case VK_ERROR_INITIALIZATION_FAILED:    return "VK_ERROR_INITIALIZATION_FAILED";
		case VK_ERROR_DEVICE_LOST:              return "VK_ERROR_DEVICE_LOST";
		case VK_ERROR_MEMORY_MAP_FAILED:        return "VK_ERROR_MEMORY_MAP_FAILED";
		case VK_ERROR_LAYER_NOT_PRESENT:        return "VK_ERROR_LAYER_NOT_PRESENT";
		case VK_ERROR_EXTENSION_NOT_PRESENT:    return "VK_ERROR_EXTENSION_NOT_PRESENT";
		case VK_ERROR_FEATURE_NOT_PRESENT:      return "VK_ERROR_FEATURE_NOT_PRESENT";
		case VK_ERROR_INCOMPATIBLE_DRIVER:      return "VK_ERROR_INCOMPATIBLE_DRIVER";
		case VK_ERROR_TOO_MANY_OBJECTS:         return "VK_ERROR_TOO_MANY_OBJECTS";
		case VK_ERROR_FORMAT_NOT_SUPPORTED:     return "VK_ERROR_FORMAT_NOT_SUPPORTED";
		case VK_ERROR_FRAGMENTED_POOL:          return "VK_ERROR_FRAGMENTED_POOL";
		case VK_ERROR_OUT_OF_DATE_KHR:          return "VK_ERROR_OUT_OF_DATE_KHR";
		case VK_ERROR_SURFACE_LOST_KHR:         return "VK_ERROR_SURFACE_LOST_KHR";
		case VK_ERROR_NATIVE_WINDOW_IN_USE_KHR: return "VK_ERROR_NATIVE_WINDOW_IN_USE_KHR";
		case VK_ERROR_OUT_OF_POOL_MEMORY:       return "VK_ERROR_OUT_OF_POOL_MEMORY";
		case VK_ERROR_INVALID_EXTERNAL_HANDLE:  return "VK_ERROR_INVALID_EXTERNAL_HANDLE";
		case VK_ERROR_FRAGMENTATION:            return "VK_ERROR_FRAGMENTATION";
		case VK_ERROR_UNKNOWN:                  return "VK_ERROR_UNKNOWN";
		default:                                return "VK_UNMAPPED_VALUE";
	}
}



void Application::initWindow()
{
#ifdef _WIN32
	glfwInit();

	glfwWindowHint(GLFW_CLIENT_API, GLFW_NO_API);
	glfwWindowHint(GLFW_RESIZABLE, GLFW_FALSE);

	window = glfwCreateWindow(480, 480, "Vulkan", nullptr, nullptr);
#else

#endif
}


#ifdef _WIN32
#else
	extern android_app* g_android_app;
#endif

void Application::createSurface() {
#ifdef _WIN32
	if (glfwCreateWindowSurface(instance, window, nullptr, &surface) != VK_SUCCESS) {
		throw std::runtime_error("failed to create window surface!");
	}
#else

	//VkSurfaceKHR surface{};

	VkAndroidSurfaceCreateInfoKHR info{VK_STRUCTURE_TYPE_ANDROID_SURFACE_CREATE_INFO_KHR};

	info.window = g_android_app->window;

	VK_CHECK(vkCreateAndroidSurfaceKHR(instance, &info, nullptr, &surface));
#endif
}



void Application::initVulkan()
{
	if (!_applicationInited)
	{
		initWindow();
		createInstance();          // 创建 Vulkan 实例
		setupDebugMessenger(); 		// 在这里调用
		createSurface();           // 创建窗口表面
		pickPhysicalDevice(physicalDevice, surface);      // 选择物理设备
		createLogicalDevice();     // 创建逻辑设备
		createSwapChain();         // 创建交换链
		createImageViews();        // 创建交换链图像视图
		createRenderPass();        // 创建渲染流程
		createPipelineLayout(); // 在这里调用
		createGraphicsPipeline();  // 创建图形管线
		createFramebuffers();      // 创建帧缓冲区
		createCommandPool();       // 创建命令池
		createCommandBuffer();     // 创建命令缓冲区
		createSyncObjects();       // 创建同步对象
		// 复用式 single-time-command 资源：从 commandPool_ex 预分配
		// kTransferSlotCount 个 cmdbuf + 同数 signaled fence，
		// 之后所有 copyBuffer / updateTexture 走 runTransferCommand，
		// 不再每次 vkAllocate/vkFree。
		createTransferResources();
		_lastDrawFrameTime = getCurrentTimeMillis();
		_applicationInited = true;
		// The first branch above already built all of the window-dependent
		// objects. Mark _sceondInited so we don't fall into the recovery
		// branch below and leak a second copy of surface/swapChain/etc.
		_sceondInited = true;
	}
	else if (!_sceondInited) {
		createSurface();
		createSwapChain();
		createImageViews();
		createRenderPass();
		createPipelineLayout();
		createGraphicsPipeline();
		createFramebuffers();
		_sceondInited = true;
	}
}

void Application::cleanupSecondInit()
{
	// ★ 幂等：销毁后立刻把句柄置 VK_NULL_HANDLE / 清空 vector。
	//
	// 这个函数过去在 Android 路径 (android_main 退出) 上被错误地调用过；
	// 由于销毁后没有清零句柄，紧接着重新进入的 reinitForNewWindow() 在
	// extent/format 不变时会跳过重建，让 framebuffer / drawFrame 在
	// 已经销毁的 renderPass 上继续工作，最终在
	// vkCmdBeginRenderPass 内部 (libGLES_mali) 触发 SIGSEGV。
	//
	// 现在 android_main 退出路径已经不再调本函数；本函数只剩 Windows
	// 路径 (mainLoop → cleanupSecondInit → initVulkan 的"二次 session"
	// 复用) 在用。把它写成幂等的可以兜住将来任何对它的误用。
	FACE_DBG_LOG("cleanupSecondInit: begin (swapChain=%s surface=%s renderPass=%s pipelineLayout=%s graphicsPipeline=%s imageViews=%zu framebuffers=%zu)",
	             swapChain == VK_NULL_HANDLE ? "null" : "live",
	             surface == VK_NULL_HANDLE ? "null" : "live",
	             renderPass == VK_NULL_HANDLE ? "null" : "live",
	             pipelineLayout == VK_NULL_HANDLE ? "null" : "live",
	             graphicsPipeline == VK_NULL_HANDLE ? "null" : "live",
	             swapChainImageViews.size(), swapChainFramebuffers.size());

	if (device != VK_NULL_HANDLE) {
		vkDeviceWaitIdle(device);
	}

	if (swapChain != VK_NULL_HANDLE) {
		vkDestroySwapchainKHR(device, swapChain, nullptr);
		swapChain = VK_NULL_HANDLE;
	}
	if (surface != VK_NULL_HANDLE) {
		vkDestroySurfaceKHR(instance, surface, nullptr);
		surface = VK_NULL_HANDLE;
	}
	if (graphicsPipeline != VK_NULL_HANDLE) {
		vkDestroyPipeline(device, graphicsPipeline, nullptr);
		graphicsPipeline = VK_NULL_HANDLE;
	}
	if (pipelineLayout != VK_NULL_HANDLE) {
		vkDestroyPipelineLayout(device, pipelineLayout, nullptr);
		pipelineLayout = VK_NULL_HANDLE;
	}
	if (renderPass != VK_NULL_HANDLE) {
		vkDestroyRenderPass(device, renderPass, nullptr);
		renderPass = VK_NULL_HANDLE;
	}
	for (auto imageView : swapChainImageViews) {
		if (imageView != VK_NULL_HANDLE) {
			vkDestroyImageView(device, imageView, nullptr);
		}
	}
	swapChainImageViews.clear();
	for (auto framebuffer : swapChainFramebuffers)
	{
		if (framebuffer != VK_NULL_HANDLE)
		{
			vkDestroyFramebuffer(device, framebuffer, nullptr);
		}
	}
	swapChainFramebuffers.clear();
	swapChainImages.clear();

	_sceondInited = false;
}

void Application::cleanupForWindowLost()
{
	if (!_applicationInited || !_sceondInited) {
		FACE_DBG_LOG("cleanupForWindowLost: skip (_applicationInited=%d _sceondInited=%d)",
		             (int)_applicationInited, (int)_sceondInited);
		return;
	}
	FACE_DBG_LOG("cleanupForWindowLost: begin (imageCount=%zu MAX_FRAMES_IN_FLIGHT=%d extent=%ux%u format=%d)",
	             swapChainImages.size(), MAX_FRAMES_IN_FLIGHT,
	             swapChainExtent.width, swapChainExtent.height, (int)swapChainImageFormat);

	// Snapshot before we destroy the swapchain so reinitForNewWindow() can
	// decide whether the new swapchain needs renderPass / pipelines rebuilt.
	_prevSwapChainExtent = swapChainExtent;
	_prevSwapChainImageFormat = swapChainImageFormat;

	// Block until GPU is no longer using any of the resources we are about
	// to destroy. Anything weaker than this risks hitting VK_ERROR_DEVICE_LOST
	// on drivers that don't tolerate destroying in-flight resources.
	vkDeviceWaitIdle(device);

	for (auto framebuffer : swapChainFramebuffers) {
		if (framebuffer != VK_NULL_HANDLE) {
			vkDestroyFramebuffer(device, framebuffer, nullptr);
		}
	}
	swapChainFramebuffers.clear();

	for (auto imageView : swapChainImageViews) {
		if (imageView != VK_NULL_HANDLE) {
			vkDestroyImageView(device, imageView, nullptr);
		}
	}
	swapChainImageViews.clear();

	// Free the command buffers allocated from commandPool. The pool itself is
	// kept alive so textures/staging uploads that run concurrently off the
	// render thread (via commandPool_ex) aren't disrupted.
	if (!commandBuffers.empty()) {
		vkFreeCommandBuffers(device, commandPool,
		                     (uint32_t)commandBuffers.size(), commandBuffers.data());
		commandBuffers.clear();
	}

	for (size_t i = 0; i < imageAvailableSemaphores.size(); ++i) {
		if (imageAvailableSemaphores[i] != VK_NULL_HANDLE) {
			vkDestroySemaphore(device, imageAvailableSemaphores[i], nullptr);
		}
	}
	imageAvailableSemaphores.clear();
	for (size_t i = 0; i < renderFinishedSemaphores.size(); ++i) {
		if (renderFinishedSemaphores[i] != VK_NULL_HANDLE) {
			vkDestroySemaphore(device, renderFinishedSemaphores[i], nullptr);
		}
	}
	renderFinishedSemaphores.clear();
	for (size_t i = 0; i < inFlightFences.size(); ++i) {
		if (inFlightFences[i] != VK_NULL_HANDLE) {
			vkDestroyFence(device, inFlightFences[i], nullptr);
		}
	}
	inFlightFences.clear();
	imagesInFlight.clear();

	if (swapChain != VK_NULL_HANDLE) {
		vkDestroySwapchainKHR(device, swapChain, nullptr);
		swapChain = VK_NULL_HANDLE;
	}
	swapChainImages.clear();

	if (surface != VK_NULL_HANDLE) {
		vkDestroySurfaceKHR(instance, surface, nullptr);
		surface = VK_NULL_HANDLE;
	}

	currentFrame = 0;
	_sceondInited = false;
	FACE_DBG_LOG("cleanupForWindowLost: done");
}

bool Application::reinitForNewWindow()
{
	if (!_applicationInited) {
		FACE_DBG_LOG("reinitForNewWindow: skip, _applicationInited=0 (must go through initVulkan first)");
		return false;
	}
	if (_sceondInited) {
		FACE_DBG_LOG("reinitForNewWindow: skip, already _sceondInited=1");
		return false;
	}
	FACE_DBG_LOG("reinitForNewWindow: begin (prev extent=%ux%u format=%d)",
	             _prevSwapChainExtent.width, _prevSwapChainExtent.height,
	             (int)_prevSwapChainImageFormat);

	createSurface();
	createSwapChain();

	const bool extentChanged = (swapChainExtent.width  != _prevSwapChainExtent.width) ||
	                           (swapChainExtent.height != _prevSwapChainExtent.height);
	const bool formatChanged = (swapChainImageFormat != _prevSwapChainImageFormat);
	const bool swapchainIncompatible = extentChanged || formatChanged;

	if (formatChanged) {
		// renderPass bakes in swapChainImageFormat, so it must be rebuilt
		// when the surface chose a different format. The old Application
		// graphicsPipeline is tied to the old renderPass, so destroy it
		// first to make the handle invalidation explicit.
		FACE_DBG_LOG("reinitForNewWindow: format changed (%d -> %d), rebuilding renderPass",
		             (int)_prevSwapChainImageFormat, (int)swapChainImageFormat);
		if (graphicsPipeline != VK_NULL_HANDLE) {
			vkDestroyPipeline(device, graphicsPipeline, nullptr);
			graphicsPipeline = VK_NULL_HANDLE;
		}
		if (pipelineLayout != VK_NULL_HANDLE) {
			vkDestroyPipelineLayout(device, pipelineLayout, nullptr);
			pipelineLayout = VK_NULL_HANDLE;
		}
		if (renderPass != VK_NULL_HANDLE) {
			vkDestroyRenderPass(device, renderPass, nullptr);
			renderPass = VK_NULL_HANDLE;
		}
		createRenderPass();
		createPipelineLayout();
		createGraphicsPipeline();
	} else if (extentChanged) {
		// renderPass is still fine, but the Application pipeline has a static
		// viewport baked to the old extent and must be rebuilt.
		FACE_DBG_LOG("reinitForNewWindow: extent changed (%ux%u -> %ux%u), rebuilding graphicsPipeline",
		             _prevSwapChainExtent.width, _prevSwapChainExtent.height,
		             swapChainExtent.width, swapChainExtent.height);
		if (graphicsPipeline != VK_NULL_HANDLE) {
			vkDestroyPipeline(device, graphicsPipeline, nullptr);
			graphicsPipeline = VK_NULL_HANDLE;
		}
		createGraphicsPipeline();
	}

	createImageViews();
	createFramebuffers();
	createCommandBuffer();
	createSyncObjects();

	_sceondInited = true;
	FACE_DBG_LOG("reinitForNewWindow: done (imageCount=%zu extent=%ux%u format=%d MAX_FRAMES_IN_FLIGHT=%d swapchainIncompatible=%d)",
	             swapChainImages.size(), swapChainExtent.width, swapChainExtent.height,
	             (int)swapChainImageFormat, MAX_FRAMES_IN_FLIGHT, (int)swapchainIncompatible);
	return swapchainIncompatible;
}



void Application::createImageViews() {
	swapChainImageViews.resize(swapChainImages.size());

	for (size_t i = 0; i < swapChainImages.size(); i++) {
		VkImageViewCreateInfo createInfo{};
		createInfo.sType = VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO;
		createInfo.image = swapChainImages[i];
		createInfo.viewType = VK_IMAGE_VIEW_TYPE_2D;
		createInfo.format = swapChainImageFormat;
		createInfo.components.r = VK_COMPONENT_SWIZZLE_IDENTITY;
		createInfo.components.g = VK_COMPONENT_SWIZZLE_IDENTITY;
		createInfo.components.b = VK_COMPONENT_SWIZZLE_IDENTITY;
		createInfo.components.a = VK_COMPONENT_SWIZZLE_IDENTITY;
		createInfo.subresourceRange.aspectMask = VK_IMAGE_ASPECT_COLOR_BIT;
		createInfo.subresourceRange.baseMipLevel = 0;
		createInfo.subresourceRange.levelCount = 1;
		createInfo.subresourceRange.baseArrayLayer = 0;
		createInfo.subresourceRange.layerCount = 1;

		if (vkCreateImageView(device, &createInfo, nullptr, &swapChainImageViews[i]) != VK_SUCCESS) {
			throw std::runtime_error("failed to create image views!");
		}
	}
}

void Application::createFramebuffers() {
	swapChainFramebuffers.resize(swapChainImageViews.size());

	for (size_t i = 0; i < swapChainImageViews.size(); i++) {
		VkImageView attachments[] = {
			swapChainImageViews[i]
		};

		VkFramebufferCreateInfo framebufferInfo{};
		framebufferInfo.sType = VK_STRUCTURE_TYPE_FRAMEBUFFER_CREATE_INFO;
		framebufferInfo.renderPass = renderPass;
		framebufferInfo.attachmentCount = 1;
		framebufferInfo.pAttachments = attachments;
		framebufferInfo.width = swapChainExtent.width;
		framebufferInfo.height = swapChainExtent.height;
		framebufferInfo.layers = 1;

		if (vkCreateFramebuffer(device, &framebufferInfo, nullptr, &swapChainFramebuffers[i]) != VK_SUCCESS) {
			throw std::runtime_error("failed to create framebuffer!");
		}
	}
}



void Application::mainLoop()
{
#ifdef _WIN32
	static int testFrame = 0;
	while (!glfwWindowShouldClose(window))
	{
		auto cur_time = getCurrentTimeMillis();
		glfwPollEvents();
		auto functionTime = (cur_time - _lastDrawFrameTime);
		_lastDrawFrameTime = getCurrentTimeMillis();
		drawFrame(functionTime); // 在这里调用
		if (testFrame++ == 300) {
			break;
		}
	}
#else

#endif
	vkDeviceWaitIdle(device); // 等待设备空闲
}



void Application::createLogicalDevice() {
	QueueFamilyIndices indices = findQueueFamilies(physicalDevice, surface);

	std::vector<VkDeviceQueueCreateInfo> queueCreateInfos;
	std::set<uint32_t> uniqueQueueFamilies = { indices.graphicsFamily.value(), indices.presentFamily.value() };

	float queuePriority = 1.0f;
	for (uint32_t queueFamily : uniqueQueueFamilies) {
		VkDeviceQueueCreateInfo queueCreateInfo{};
		queueCreateInfo.sType = VK_STRUCTURE_TYPE_DEVICE_QUEUE_CREATE_INFO;
		queueCreateInfo.queueFamilyIndex = queueFamily;
		queueCreateInfo.queueCount = 1;
		queueCreateInfo.pQueuePriorities = &queuePriority;
		queueCreateInfos.push_back(queueCreateInfo);
	}

	VkPhysicalDeviceFeatures deviceFeatures{};

	VkDeviceCreateInfo createInfo{};
	createInfo.sType = VK_STRUCTURE_TYPE_DEVICE_CREATE_INFO;
	createInfo.queueCreateInfoCount = static_cast<uint32_t>(queueCreateInfos.size());
	createInfo.pQueueCreateInfos = queueCreateInfos.data();
	createInfo.pEnabledFeatures = &deviceFeatures;

	// 启用交换链扩展
	const std::vector<const char*> deviceExtensions = {
		VK_KHR_SWAPCHAIN_EXTENSION_NAME
	};
	createInfo.enabledExtensionCount = static_cast<uint32_t>(deviceExtensions.size());
	createInfo.ppEnabledExtensionNames = deviceExtensions.data();

	if (vkCreateDevice(physicalDevice, &createInfo, nullptr, &device) != VK_SUCCESS) {
		throw std::runtime_error("failed to create logical device!");
	}

	vkGetDeviceQueue(device, indices.graphicsFamily.value(), 0, &graphicsQueue);
	vkGetDeviceQueue(device, indices.presentFamily.value(), 0, &presentQueue);
}


void Application::createSwapChain() {
	// 选择交换链格式、颜色空间和分辨率
	VkSurfaceFormatKHR surfaceFormat = { VK_FORMAT_R8G8B8A8_SRGB, VK_COLOR_SPACE_SRGB_NONLINEAR_KHR };
	VkPresentModeKHR presentMode = VK_PRESENT_MODE_FIFO_KHR;
    VkSurfaceCapabilitiesKHR surface_capabilities{};
    vkGetPhysicalDeviceSurfaceCapabilitiesKHR(this->physicalDevice,  this->surface, &surface_capabilities);

    VkExtent2D extent = surface_capabilities.currentExtent;

	uint32_t imageCount = 2;
	// 创建交换链
	VkSwapchainCreateInfoKHR createInfo{};
	createInfo.sType = VK_STRUCTURE_TYPE_SWAPCHAIN_CREATE_INFO_KHR;
	createInfo.surface = surface;
	createInfo.minImageCount = imageCount; // 双缓冲
	createInfo.imageFormat = surfaceFormat.format;
	createInfo.imageColorSpace = surfaceFormat.colorSpace;
	createInfo.imageExtent = extent;
	createInfo.imageArrayLayers = 1;
	createInfo.imageUsage = VK_IMAGE_USAGE_COLOR_ATTACHMENT_BIT;

	QueueFamilyIndices indices = findQueueFamilies(physicalDevice, surface);
	uint32_t queueFamilyIndices[] = { indices.graphicsFamily.value(), indices.presentFamily.value() };

	if (indices.graphicsFamily != indices.presentFamily) {
		createInfo.imageSharingMode = VK_SHARING_MODE_CONCURRENT;
		createInfo.queueFamilyIndexCount = 2;
		createInfo.pQueueFamilyIndices = queueFamilyIndices;
	}
	else {
		createInfo.imageSharingMode = VK_SHARING_MODE_EXCLUSIVE;
		createInfo.queueFamilyIndexCount = 0; // Optional
		createInfo.pQueueFamilyIndices = nullptr; // Optional
	}

	createInfo.preTransform = VK_SURFACE_TRANSFORM_IDENTITY_BIT_KHR;
	createInfo.compositeAlpha = VK_COMPOSITE_ALPHA_OPAQUE_BIT_KHR;
	createInfo.presentMode = presentMode;
	createInfo.clipped = VK_TRUE;
	createInfo.oldSwapchain = VK_NULL_HANDLE;

	if (vkCreateSwapchainKHR(device, &createInfo, nullptr, &swapChain) != VK_SUCCESS) {
		throw std::runtime_error("failed to create swap chain!");
	}


	vkGetSwapchainImagesKHR(device, swapChain, &imageCount, nullptr);
	swapChainImages.resize(imageCount);
	vkGetSwapchainImagesKHR(device, swapChain, &imageCount, swapChainImages.data());

	swapChainImageFormat = surfaceFormat.format;
	swapChainExtent = extent;
	MAX_FRAMES_IN_FLIGHT = imageCount;
}

void Application::createPipelineLayout() {
	VkPipelineLayoutCreateInfo pipelineLayoutInfo{};
	pipelineLayoutInfo.sType = VK_STRUCTURE_TYPE_PIPELINE_LAYOUT_CREATE_INFO;
	pipelineLayoutInfo.setLayoutCount = 0; // 可选：描述符集布局
	pipelineLayoutInfo.pSetLayouts = nullptr; // 可选：描述符集布局
	pipelineLayoutInfo.pushConstantRangeCount = 0; // 可选：推送常量范围
	pipelineLayoutInfo.pPushConstantRanges = nullptr; // 可选：推送常量范围

	if (vkCreatePipelineLayout(device, &pipelineLayoutInfo, nullptr, &pipelineLayout) != VK_SUCCESS) {
		throw std::runtime_error("failed to create pipeline layout!");
	}
}

void Application::createGraphicsPipeline() {
	// 顶点着色器和片段着色器
	auto vertShaderCode = readFile("shaders/simple_shader.vert.spv");
	auto fragShaderCode = readFile("shaders/simple_shader.frag.spv");

	// 创建着色器模块
	VkShaderModule vertShaderModule = createShaderModule(this->device, vertShaderCode);
	VkShaderModule fragShaderModule = createShaderModule(this->device, fragShaderCode);

	// 定义着色器阶段
	VkPipelineShaderStageCreateInfo vertShaderStageInfo{};
	vertShaderStageInfo.sType = VK_STRUCTURE_TYPE_PIPELINE_SHADER_STAGE_CREATE_INFO;
	vertShaderStageInfo.stage = VK_SHADER_STAGE_VERTEX_BIT;
	vertShaderStageInfo.module = vertShaderModule;
	vertShaderStageInfo.pName = "main";

	VkPipelineShaderStageCreateInfo fragShaderStageInfo{};
	fragShaderStageInfo.sType = VK_STRUCTURE_TYPE_PIPELINE_SHADER_STAGE_CREATE_INFO;
	fragShaderStageInfo.stage = VK_SHADER_STAGE_FRAGMENT_BIT;
	fragShaderStageInfo.module = fragShaderModule;
	fragShaderStageInfo.pName = "main";

	VkPipelineShaderStageCreateInfo shaderStages[] = { vertShaderStageInfo, fragShaderStageInfo };

	// 顶点输入状态
	VkPipelineVertexInputStateCreateInfo vertexInputInfo{};
	vertexInputInfo.sType = VK_STRUCTURE_TYPE_PIPELINE_VERTEX_INPUT_STATE_CREATE_INFO;
	vertexInputInfo.vertexBindingDescriptionCount = 0;
	vertexInputInfo.pVertexBindingDescriptions = nullptr;
	vertexInputInfo.vertexAttributeDescriptionCount = 0;
	vertexInputInfo.pVertexAttributeDescriptions = nullptr;

	// 输入组装状态
	VkPipelineInputAssemblyStateCreateInfo inputAssembly{};
	inputAssembly.sType = VK_STRUCTURE_TYPE_PIPELINE_INPUT_ASSEMBLY_STATE_CREATE_INFO;
	inputAssembly.topology = VK_PRIMITIVE_TOPOLOGY_TRIANGLE_LIST;
	inputAssembly.primitiveRestartEnable = VK_FALSE;

	// 视口状态
	VkViewport viewport{};
	viewport.x = 0.0f;
	viewport.y = 0.0f;
	viewport.width = (float)swapChainExtent.width;
	viewport.height = (float)swapChainExtent.height;
	viewport.minDepth = 0.0f;
	viewport.maxDepth = 1.0f;

	VkRect2D scissor{};
	scissor.offset = { 0, 0 };
	scissor.extent = swapChainExtent;

	VkPipelineViewportStateCreateInfo viewportState{};
	viewportState.sType = VK_STRUCTURE_TYPE_PIPELINE_VIEWPORT_STATE_CREATE_INFO;
	viewportState.viewportCount = 1;
	viewportState.pViewports = &viewport;
	viewportState.scissorCount = 1;
	viewportState.pScissors = &scissor;

	// 光栅化状态
	VkPipelineRasterizationStateCreateInfo rasterizer{};
	rasterizer.sType = VK_STRUCTURE_TYPE_PIPELINE_RASTERIZATION_STATE_CREATE_INFO;
	rasterizer.depthClampEnable = VK_FALSE;
	rasterizer.rasterizerDiscardEnable = VK_FALSE;
	rasterizer.polygonMode = VK_POLYGON_MODE_FILL;
	rasterizer.lineWidth = 1.0f;
	rasterizer.cullMode = VK_CULL_MODE_BACK_BIT;
	rasterizer.frontFace = VK_FRONT_FACE_CLOCKWISE;
	rasterizer.depthBiasEnable = VK_FALSE;

	// 多重采样状态
	VkPipelineMultisampleStateCreateInfo multisampling{};
	multisampling.sType = VK_STRUCTURE_TYPE_PIPELINE_MULTISAMPLE_STATE_CREATE_INFO;
	multisampling.sampleShadingEnable = VK_FALSE;
	multisampling.rasterizationSamples = VK_SAMPLE_COUNT_1_BIT;

	// 颜色混合状态
	VkPipelineColorBlendAttachmentState colorBlendAttachment{};
	colorBlendAttachment.colorWriteMask = VK_COLOR_COMPONENT_R_BIT | VK_COLOR_COMPONENT_G_BIT | VK_COLOR_COMPONENT_B_BIT | VK_COLOR_COMPONENT_A_BIT;
	colorBlendAttachment.blendEnable = VK_FALSE;

	VkPipelineColorBlendStateCreateInfo colorBlending{};
	colorBlending.sType = VK_STRUCTURE_TYPE_PIPELINE_COLOR_BLEND_STATE_CREATE_INFO;
	colorBlending.logicOpEnable = VK_FALSE;
	colorBlending.attachmentCount = 1;
	colorBlending.pAttachments = &colorBlendAttachment;

	// 创建图形管线
	VkGraphicsPipelineCreateInfo pipelineInfo{};
	pipelineInfo.sType = VK_STRUCTURE_TYPE_GRAPHICS_PIPELINE_CREATE_INFO;
	pipelineInfo.stageCount = 2;
	pipelineInfo.pStages = shaderStages;
	pipelineInfo.pVertexInputState = &vertexInputInfo;
	pipelineInfo.pInputAssemblyState = &inputAssembly;
	pipelineInfo.pViewportState = &viewportState;
	pipelineInfo.pRasterizationState = &rasterizer;
	pipelineInfo.pMultisampleState = &multisampling;
	pipelineInfo.pColorBlendState = &colorBlending;
	pipelineInfo.layout = pipelineLayout;
	pipelineInfo.renderPass = renderPass;
	pipelineInfo.subpass = 0;

	if (vkCreateGraphicsPipelines(device, VK_NULL_HANDLE, 1, &pipelineInfo, nullptr, &graphicsPipeline) != VK_SUCCESS) {
		throw std::runtime_error("failed to create graphics pipeline!");
	}

	// 销毁着色器模块
	vkDestroyShaderModule(device, fragShaderModule, nullptr);
	vkDestroyShaderModule(device, vertShaderModule, nullptr);
}

void Application::createRenderPass() {
	VkAttachmentDescription colorAttachment{};
	colorAttachment.format = swapChainImageFormat;
	colorAttachment.samples = VK_SAMPLE_COUNT_1_BIT;
	colorAttachment.loadOp = VK_ATTACHMENT_LOAD_OP_CLEAR;
	colorAttachment.storeOp = VK_ATTACHMENT_STORE_OP_STORE;
	colorAttachment.stencilLoadOp = VK_ATTACHMENT_LOAD_OP_DONT_CARE;
	colorAttachment.stencilStoreOp = VK_ATTACHMENT_STORE_OP_DONT_CARE;
	colorAttachment.initialLayout = VK_IMAGE_LAYOUT_UNDEFINED;
	colorAttachment.finalLayout = VK_IMAGE_LAYOUT_PRESENT_SRC_KHR;

	VkAttachmentReference colorAttachmentRef{};
	colorAttachmentRef.attachment = 0;
	colorAttachmentRef.layout = VK_IMAGE_LAYOUT_COLOR_ATTACHMENT_OPTIMAL;

	VkSubpassDescription subpass{};
	subpass.pipelineBindPoint = VK_PIPELINE_BIND_POINT_GRAPHICS;
	subpass.colorAttachmentCount = 1;
	subpass.pColorAttachments = &colorAttachmentRef;

	VkRenderPassCreateInfo renderPassInfo{};
	renderPassInfo.sType = VK_STRUCTURE_TYPE_RENDER_PASS_CREATE_INFO;
	renderPassInfo.attachmentCount = 1;
	renderPassInfo.pAttachments = &colorAttachment;
	renderPassInfo.subpassCount = 1;
	renderPassInfo.pSubpasses = &subpass;

	if (vkCreateRenderPass(device, &renderPassInfo, nullptr, &renderPass) != VK_SUCCESS) {
		throw std::runtime_error("failed to create render pass!");
	}
}



void Application::createCommandPool() {
	QueueFamilyIndices queueFamilyIndices = findQueueFamilies(physicalDevice, surface);

	VkCommandPoolCreateInfo poolInfo{};
	poolInfo.sType = VK_STRUCTURE_TYPE_COMMAND_POOL_CREATE_INFO;
	poolInfo.queueFamilyIndex = queueFamilyIndices.graphicsFamily.value();
	poolInfo.flags = VK_COMMAND_POOL_CREATE_RESET_COMMAND_BUFFER_BIT; // 添加标志

	if (vkCreateCommandPool(device, &poolInfo, nullptr, &commandPool) != VK_SUCCESS) {
		throw std::runtime_error("failed to create command pool!");
	}

	queueFamilyIndices = findQueueFamilies(physicalDevice, surface);

	VkCommandPoolCreateInfo poolInfo_ex{};
	poolInfo_ex.sType = VK_STRUCTURE_TYPE_COMMAND_POOL_CREATE_INFO;
	poolInfo_ex.queueFamilyIndex = queueFamilyIndices.graphicsFamily.value();
	poolInfo_ex.flags = VK_COMMAND_POOL_CREATE_RESET_COMMAND_BUFFER_BIT; // 添加标志

	if (vkCreateCommandPool(device, &poolInfo_ex, nullptr, &commandPool_ex) != VK_SUCCESS) {
		throw std::runtime_error("failed to create command pool!");
	}
}

void Application::createCommandBuffer()
{
	commandBuffers.resize(MAX_FRAMES_IN_FLIGHT);
	VkCommandBufferAllocateInfo allocInfo{};
	allocInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_ALLOCATE_INFO;
	allocInfo.commandPool = commandPool;
	allocInfo.level = VK_COMMAND_BUFFER_LEVEL_PRIMARY;
	allocInfo.commandBufferCount = (uint32_t)MAX_FRAMES_IN_FLIGHT;

	if (vkAllocateCommandBuffers(device, &allocInfo, commandBuffers.data()) != VK_SUCCESS) {
		throw std::runtime_error("failed to allocate command buffers!");
	}
}

void Application::createSyncObjects() 
{
	imageAvailableSemaphores.resize(MAX_FRAMES_IN_FLIGHT);
	renderFinishedSemaphores.resize(MAX_FRAMES_IN_FLIGHT);
	inFlightFences.resize(MAX_FRAMES_IN_FLIGHT);
	imagesInFlight.resize(MAX_FRAMES_IN_FLIGHT, VK_NULL_HANDLE);

	VkSemaphoreCreateInfo semaphoreInfo{};
	semaphoreInfo.sType = VK_STRUCTURE_TYPE_SEMAPHORE_CREATE_INFO;

	VkFenceCreateInfo fenceInfo{};
	fenceInfo.sType = VK_STRUCTURE_TYPE_FENCE_CREATE_INFO;
	fenceInfo.flags = VK_FENCE_CREATE_SIGNALED_BIT;

	for (size_t i = 0; i < MAX_FRAMES_IN_FLIGHT; i++) {
		if (vkCreateSemaphore(device, &semaphoreInfo, nullptr, &imageAvailableSemaphores[i]) != VK_SUCCESS ||
			vkCreateSemaphore(device, &semaphoreInfo, nullptr, &renderFinishedSemaphores[i]) != VK_SUCCESS) {
			throw std::runtime_error("failed to create synchronization objects!");
		}
		if (vkCreateFence(device, &fenceInfo, nullptr, &inFlightFences[i]) != VK_SUCCESS) {
			throw std::runtime_error("failed to create synchronization objects!");
		}
	}
}

void Application::recordCommandBuffer(VkCommandBuffer commandBuffer, uint32_t imageIndex, long long frameTime)
{
	VkCommandBufferBeginInfo beginInfo{};
	beginInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_BEGIN_INFO;
	beginInfo.flags = 0; // 可选标志
	beginInfo.pInheritanceInfo = nullptr; // 仅用于次级命令缓冲区

	if (vkBeginCommandBuffer(commandBuffer, &beginInfo) != VK_SUCCESS) {
		throw std::runtime_error("failed to begin recording command buffer!");
	}

	// 开始渲染流程
	VkRenderPassBeginInfo renderPassInfo{};
	renderPassInfo.sType = VK_STRUCTURE_TYPE_RENDER_PASS_BEGIN_INFO;
	renderPassInfo.renderPass = renderPass;
	renderPassInfo.framebuffer = swapChainFramebuffers[imageIndex]; // 使用正确的imageIndex
	renderPassInfo.renderArea.offset = { 0, 0 };
	renderPassInfo.renderArea.extent = swapChainExtent;

	VkClearValue clearColor = { {{0.0f, 0.0f, 0.0f, 1.0f}} };
	renderPassInfo.clearValueCount = 1;
	renderPassInfo.pClearValues = &clearColor;

	vkCmdBeginRenderPass(commandBuffer, &renderPassInfo, VK_SUBPASS_CONTENTS_INLINE);

	render(commandBuffer, frameTime);

	// 结束渲染流程
	vkCmdEndRenderPass(commandBuffer);

	if (vkEndCommandBuffer(commandBuffer) != VK_SUCCESS) {
		throw std::runtime_error("failed to record command buffer!");
	}
}

void Application::render(VkCommandBuffer commandBuffer, long long frameTime)
{
	// 绑定图形管线
	vkCmdBindPipeline(commandBuffer, VK_PIPELINE_BIND_POINT_GRAPHICS, graphicsPipeline);

	// 绘制三角形
	vkCmdDraw(commandBuffer, 3, 1, 0, 0);
}

void Application::drawFrame(long long frameTime)
{
	static uint64_t s_drawFrameCount = 0;
	++s_drawFrameCount;

	// 1. 等待前一帧完成
	VkResult waitRes = vkWaitForFences(device, 1, &inFlightFences[currentFrame], VK_TRUE, UINT64_MAX);
	if (waitRes != VK_SUCCESS) {
#ifndef _WIN32
		DebugLog::log_throttled("drawFrame.waitFences",
		             "drawFrame[%llu] vkWaitForFences -> %d (%s) currentFrame=%u",
		             (unsigned long long)s_drawFrameCount,
		             (int)waitRes, VkResultStr(waitRes), currentFrame);
#endif
	}

	// 2. 获取交换链图像
	uint32_t imageIndex;
	VkResult result = vkAcquireNextImageKHR(device, swapChain, UINT64_MAX, imageAvailableSemaphores[currentFrame], VK_NULL_HANDLE, &imageIndex);
	if (result != VK_SUCCESS) {
#ifndef _WIN32
		DebugLog::log_throttled("drawFrame.acquire",
		             "drawFrame[%llu] vkAcquireNextImageKHR -> %d (%s) currentFrame=%u",
		             (unsigned long long)s_drawFrameCount,
		             (int)result, VkResultStr(result), currentFrame);
#endif
		throw std::runtime_error("failed to acquire swap chain image!");
	}

	// 3. 检查该图像是否正在被之前的帧使用
	if (imagesInFlight[imageIndex] != VK_NULL_HANDLE) {
		vkWaitForFences(device, 1, &imagesInFlight[imageIndex], VK_TRUE, UINT64_MAX);
	}
	imagesInFlight[imageIndex] = inFlightFences[currentFrame];

	// 4. 重置栅栏
	vkResetFences(device, 1, &inFlightFences[currentFrame]);

	// 5. 记录命令缓冲区
	vkResetCommandBuffer(commandBuffers[currentFrame], 0);
	recordCommandBuffer(commandBuffers[currentFrame], imageIndex, frameTime);

	// 6. 提交命令缓冲区
	VkSubmitInfo submitInfo{};
	submitInfo.sType = VK_STRUCTURE_TYPE_SUBMIT_INFO;
	VkSemaphore waitSemaphores[] = { imageAvailableSemaphores[currentFrame] };
	VkPipelineStageFlags waitStages[] = { VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT };
	submitInfo.waitSemaphoreCount = 1;
	submitInfo.pWaitSemaphores = waitSemaphores;
	submitInfo.pWaitDstStageMask = waitStages;
	submitInfo.commandBufferCount = 1;
	submitInfo.pCommandBuffers = &commandBuffers[currentFrame];
	VkSemaphore signalSemaphores[] = { renderFinishedSemaphores[imageIndex] };
	submitInfo.signalSemaphoreCount = 1;
	submitInfo.pSignalSemaphores = signalSemaphores;

	// 串行化 graphicsQueue/presentQueue 的 submit 与 present，
	// 确保与 copyBuffer / updateTexture 等其它线程的队列提交互斥，
	// 避免驱动内部 pthread_mutex 在长时间并发下被破坏。
	VkResult submitRes;
	{
		std::lock_guard<std::mutex> poolLock(poolQueueMtx);
		submitRes = vkQueueSubmit(graphicsQueue, 1, &submitInfo, inFlightFences[currentFrame]);
	}
	if (submitRes != VK_SUCCESS) {
#ifndef _WIN32
		DebugLog::log_throttled("drawFrame.submit",
		             "drawFrame[%llu] vkQueueSubmit -> %d (%s) currentFrame=%u imageIndex=%u",
		             (unsigned long long)s_drawFrameCount,
		             (int)submitRes, VkResultStr(submitRes),
		             currentFrame, imageIndex);
#endif
		throw std::runtime_error("failed to submit draw command buffer!");
	}
	// 7. 呈现图像
	VkPresentInfoKHR presentInfo{};
	presentInfo.sType = VK_STRUCTURE_TYPE_PRESENT_INFO_KHR;
	presentInfo.waitSemaphoreCount = 1;
	presentInfo.pWaitSemaphores = signalSemaphores;
	VkSwapchainKHR swapChains[] = { swapChain };
	presentInfo.swapchainCount = 1;
	presentInfo.pSwapchains = swapChains;
	presentInfo.pImageIndices = &imageIndex;
	{
		std::lock_guard<std::mutex> poolLock(poolQueueMtx);
		result = vkQueuePresentKHR(presentQueue, &presentInfo);
	}

	if (result != VK_SUCCESS) {
#ifndef _WIN32
		DebugLog::log_throttled("drawFrame.present",
		             "drawFrame[%llu] vkQueuePresentKHR -> %d (%s) currentFrame=%u imageIndex=%u",
		             (unsigned long long)s_drawFrameCount,
		             (int)result, VkResultStr(result),
		             currentFrame, imageIndex);
#endif
		throw std::runtime_error("failed to present swap chain image!");
	}

	// 8. 前进到下一帧
	currentFrame = (currentFrame + 1) % MAX_FRAMES_IN_FLIGHT;
}

void DestroyDebugUtilsMessengerEXT(VkInstance instance, VkDebugUtilsMessengerEXT debugMessenger, const VkAllocationCallbacks* pAllocator) {
	auto func = (PFN_vkDestroyDebugUtilsMessengerEXT)vkGetInstanceProcAddr(instance, "vkDestroyDebugUtilsMessengerEXT");
	if (func != nullptr) {
		func(instance, debugMessenger, pAllocator);
	}
}

void Application::cleanup() {
	if (enableValidationLayers) {
		DestroyDebugUtilsMessengerEXT(instance, debugMessenger, nullptr);
	}


	vkDeviceWaitIdle(device);

	for (size_t i = 0; i < MAX_FRAMES_IN_FLIGHT; i++) {
		vkDestroySemaphore(device, imageAvailableSemaphores[i], nullptr);
		vkDestroySemaphore(device, renderFinishedSemaphores[i], nullptr);
		vkDestroyFence(device, inFlightFences[i], nullptr);
	}



	vkDestroyPipeline(device, graphicsPipeline, nullptr);

	vkDestroyPipelineLayout(device, pipelineLayout, nullptr);

	vkDestroyRenderPass(device, renderPass, nullptr);
	for (auto imageView : swapChainImageViews) {
		vkDestroyImageView(device, imageView, nullptr);
	}

	for (auto framebuffer : swapChainFramebuffers)
	{
		if (framebuffer != VK_NULL_HANDLE)
		{
			vkDestroyFramebuffer(device, framebuffer, nullptr);
		}
	}
	swapChainFramebuffers.clear();

	vkDestroySwapchainKHR(device, swapChain, nullptr);

	vkDestroyDevice(device, nullptr);
	vkDestroySurfaceKHR(instance, surface, nullptr);
	vkDestroyInstance(instance, nullptr);

	

#ifdef _WIN32
	glfwDestroyWindow(window);
	glfwTerminate();
#endif
}


uint32_t Application::findMemoryType(VkPhysicalDevice physicalDevice, uint32_t typeFilter,
	VkMemoryPropertyFlags properties)
{
	VkPhysicalDeviceMemoryProperties memProperties;
	vkGetPhysicalDeviceMemoryProperties(physicalDevice, &memProperties);

	for (uint32_t i = 0; i < memProperties.memoryTypeCount; i++)
	{
		if ((typeFilter & (1 << i)) &&
			(memProperties.memoryTypes[i].propertyFlags & properties) == properties)
		{
			return i;
		}
	}

	throw std::runtime_error("Failed to find suitable memory type!");
}

void Application::loadTexture(std::string path, Texture& tex, bool srgb, VkCommandPool pool)
{
	std::vector<unsigned char> data = readFileUnsignedChar(path, false);
	std::vector<unsigned char> image;
	unsigned w, h;
	unsigned error = lodepng::decode(image, w, h, data, LCT_RGBA, 8);
	processWithVulkan(image.data(), w, h, w * 4, image.size(), tex, srgb, pool, path);
	//return tex;
}

void Application::loadTexture(std::vector<unsigned char>& image_data, size_t image_size, int w, int h, Texture& tex, bool srgb, VkCommandPool pool, std::string path)
{
	processWithVulkan(image_data.data(), w, h, w * 4, image_size, tex, srgb, pool, path);
	//return tex;
}

#ifdef _WIN32
void Application::loadTextureExample(std::wstring path, Texture& tex, bool srgb, VkCommandPool pool)
{
	std::vector<unsigned char> data = readFileUnsignedCharWin32(path, true);
	std::vector<unsigned char> image;
	unsigned w, h;
	unsigned error = lodepng::decode(image, w, h, data, LCT_RGBA, 8);
	std::wstring_convert<std::codecvt_utf8<wchar_t>> converter;
	std::string str = converter.to_bytes(path);
	processWithVulkan(image.data(), w, h, w * 4, image.size(), tex, srgb, pool, str);
	//return tex;
}

#endif // _WIN32




void Application::createTexture(VkDevice device, VkPhysicalDevice physicalDevice, int width, int height, Texture& texture, bool srgb, std::string tex_path, size_t dataSize)
{
	texture.width = width;
	texture.height = height;
	texture.mip_levels = 1;

	VkImageCreateInfo imageInfo = {};
	imageInfo.sType = VK_STRUCTURE_TYPE_IMAGE_CREATE_INFO;
	imageInfo.imageType = VK_IMAGE_TYPE_2D;
	if (srgb)
	{
		imageInfo.format = VK_FORMAT_R8G8B8A8_SRGB;
	}
	else
	{
		imageInfo.format = VK_FORMAT_R8G8B8A8_UNORM;// VK_FORMAT_R8G8B8A8_SRGB; //VK_FORMAT_R8G8B8A8_UNORM;
	}
	imageInfo.extent.width = width;
	imageInfo.extent.height = height;
	imageInfo.extent.depth = 1;
	imageInfo.mipLevels = 1;
	imageInfo.arrayLayers = 1;
	imageInfo.samples = VK_SAMPLE_COUNT_1_BIT;
	imageInfo.tiling = VK_IMAGE_TILING_OPTIMAL;
	imageInfo.usage = VK_IMAGE_USAGE_SAMPLED_BIT | VK_IMAGE_USAGE_TRANSFER_DST_BIT;
	imageInfo.sharingMode = VK_SHARING_MODE_EXCLUSIVE;
	imageInfo.initialLayout = VK_IMAGE_LAYOUT_UNDEFINED;

	if (vkCreateImage(device, &imageInfo, nullptr, &texture.image) != VK_SUCCESS)
	{
		throw std::runtime_error("Failed to create image!");
	}

	VkMemoryRequirements memRequirements;
	vkGetImageMemoryRequirements(device, texture.image, &memRequirements);

	VkMemoryAllocateInfo allocInfo = {};
	allocInfo.sType = VK_STRUCTURE_TYPE_MEMORY_ALLOCATE_INFO;
	allocInfo.allocationSize = memRequirements.size;
	allocInfo.memoryTypeIndex = findMemoryType(physicalDevice,
		memRequirements.memoryTypeBits, VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT);

	if (vkAllocateMemory(device, &allocInfo, nullptr, &texture.device_memory) != VK_SUCCESS)
	{
		throw std::runtime_error("Failed to allocate image memory!");
	}

	std::cout << "vkAllocateMemory device_memory " << tex_path << ": " << texture.device_memory <<  std::endl;

	vkBindImageMemory(device, texture.image, texture.device_memory, 0);

	VkImageViewCreateInfo viewInfo = {};
	viewInfo.sType = VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO;
	viewInfo.image = texture.image;
	viewInfo.viewType = VK_IMAGE_VIEW_TYPE_2D;
	if (srgb)
	{
		viewInfo.format = VK_FORMAT_R8G8B8A8_SRGB;
	}
	else
	{
		viewInfo.format = VK_FORMAT_R8G8B8A8_UNORM;// VK_FORMAT_R8G8B8A8_SRGB; // VK_FORMAT_R8G8B8A8_UNORM;
	}
	viewInfo.subresourceRange.aspectMask = VK_IMAGE_ASPECT_COLOR_BIT;
	viewInfo.subresourceRange.baseMipLevel = 0;
	viewInfo.subresourceRange.levelCount = 1;
	viewInfo.subresourceRange.baseArrayLayer = 0;
	viewInfo.subresourceRange.layerCount = 1;

	if (vkCreateImageView(device, &viewInfo, nullptr, &texture.view) != VK_SUCCESS)
	{
		throw std::runtime_error("Failed to create texture image view!");
	}

	VkSamplerCreateInfo samplerInfo = {};
	samplerInfo.sType = VK_STRUCTURE_TYPE_SAMPLER_CREATE_INFO;
	samplerInfo.magFilter = VK_FILTER_LINEAR;
	samplerInfo.minFilter = VK_FILTER_LINEAR;
	samplerInfo.addressModeU = VK_SAMPLER_ADDRESS_MODE_CLAMP_TO_EDGE;
	samplerInfo.addressModeV = VK_SAMPLER_ADDRESS_MODE_CLAMP_TO_EDGE;
	samplerInfo.addressModeW = VK_SAMPLER_ADDRESS_MODE_CLAMP_TO_EDGE;
	samplerInfo.anisotropyEnable = VK_FALSE;
	samplerInfo.maxAnisotropy = 1.0f;
	samplerInfo.borderColor = VK_BORDER_COLOR_INT_OPAQUE_BLACK;
	samplerInfo.unnormalizedCoordinates = VK_FALSE;
	samplerInfo.compareEnable = VK_FALSE;
	samplerInfo.compareOp = VK_COMPARE_OP_ALWAYS;
	samplerInfo.mipmapMode = VK_SAMPLER_MIPMAP_MODE_LINEAR;
	samplerInfo.mipLodBias = 0.0f;
	samplerInfo.minLod = 0.0f;
	samplerInfo.maxLod = 0.0f;

	if (vkCreateSampler(device, &samplerInfo, nullptr, &texture.sampler) != VK_SUCCESS)
	{
		throw std::runtime_error("Failed to create texture sampler!");
	}

	if (texture.stagingBuffer == nullptr)
	{
		VkBufferCreateInfo bufferInfo = {};
		bufferInfo.sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO;
		bufferInfo.size = dataSize;
		bufferInfo.usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT;
		bufferInfo.sharingMode = VK_SHARING_MODE_EXCLUSIVE;

		if (vkCreateBuffer(device, &bufferInfo, nullptr, &texture.stagingBuffer) != VK_SUCCESS)
		{
			throw std::runtime_error("Failed to create staging buffer!");
		}
	}

	if (texture.stagingBufferMemory == nullptr)
	{
		VkMemoryRequirements memRequirements;
		vkGetBufferMemoryRequirements(device, texture.stagingBuffer, &memRequirements);

		VkMemoryAllocateInfo allocInfo = {};
		allocInfo.sType = VK_STRUCTURE_TYPE_MEMORY_ALLOCATE_INFO;
		allocInfo.allocationSize = memRequirements.size;
		allocInfo.memoryTypeIndex = findMemoryType(physicalDevice,
			memRequirements.memoryTypeBits, VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT);

		if (vkAllocateMemory(device, &allocInfo, nullptr, &texture.stagingBufferMemory) != VK_SUCCESS)
		{
			throw std::runtime_error("Failed to allocate staging buffer memory!");
		}

		std::cout << "vkAllocateMemory stagingBufferMemory " << tex_path << ": " << texture.stagingBufferMemory << std::endl;

		vkBindBufferMemory(device, texture.stagingBuffer, texture.stagingBufferMemory, 0);
	}

	texture.image_layout = VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL;
	texture.device = device;
	texture.texture_path = tex_path;
}

void Application::processWithVulkan(uint8_t* data, int width, int height, int rowStride, size_t dataSize, Texture& texture, bool srgb, VkCommandPool pool, std::string tex_path)
{
	std::unique_lock<std::mutex> lock(createTextureMtx);
	if (texture.image == VK_NULL_HANDLE)
	{
		createTexture(device, physicalDevice, width, height, texture, srgb, tex_path, dataSize);
	}

	updateTexture(device, physicalDevice, pool, graphicsQueue, data, width, height,
		rowStride, dataSize, texture);
}


VkCommandBuffer Application::beginSingleTimeCommands(VkDevice device, VkCommandPool commandPool)
{
	VkCommandBufferAllocateInfo allocInfo = {};
	allocInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_ALLOCATE_INFO;
	allocInfo.level = VK_COMMAND_BUFFER_LEVEL_PRIMARY;
	allocInfo.commandPool = commandPool;
	allocInfo.commandBufferCount = 1;

	VkCommandBuffer commandBuffer;
	vkAllocateCommandBuffers(device, &allocInfo, &commandBuffer);

	VkCommandBufferBeginInfo beginInfo = {};
	beginInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_BEGIN_INFO;
	beginInfo.flags = VK_COMMAND_BUFFER_USAGE_ONE_TIME_SUBMIT_BIT;

	vkBeginCommandBuffer(commandBuffer, &beginInfo);

	return commandBuffer;
}

void Application::endSingleTimeCommands(VkDevice device, VkCommandPool commandPool,
	VkQueue queue, VkCommandBuffer commandBuffer)
{
	vkEndCommandBuffer(commandBuffer);

	VkSubmitInfo submitInfo = {};
	submitInfo.sType = VK_STRUCTURE_TYPE_SUBMIT_INFO;
	submitInfo.commandBufferCount = 1;
	submitInfo.pCommandBuffers = &commandBuffer;

	vkQueueSubmit(queue, 1, &submitInfo, VK_NULL_HANDLE);
	vkQueueWaitIdle(queue);

	vkFreeCommandBuffers(device, commandPool, 1, &commandBuffer);
}

void Application::createTransferResources()
{
	if (m_xferInited) {
#ifndef _WIN32
		DebugLog::log("createTransferResources: already inited, skip");
#endif
		return;
	}
	if (commandPool_ex == VK_NULL_HANDLE) {
#ifndef _WIN32
		DebugLog::log("createTransferResources: commandPool_ex is null, abort");
#endif
		throw std::runtime_error("createTransferResources: commandPool_ex not created yet");
	}

	VkCommandBufferAllocateInfo allocInfo{};
	allocInfo.sType              = VK_STRUCTURE_TYPE_COMMAND_BUFFER_ALLOCATE_INFO;
	allocInfo.level              = VK_COMMAND_BUFFER_LEVEL_PRIMARY;
	allocInfo.commandPool        = commandPool_ex;
	allocInfo.commandBufferCount = kTransferSlotCount;
	if (vkAllocateCommandBuffers(device, &allocInfo, m_xferCmd) != VK_SUCCESS) {
		throw std::runtime_error("createTransferResources: vkAllocateCommandBuffers failed");
	}

	// fence 创建为 SIGNALED：第一次 runTransferCommand 的 vkWaitForFences
	// 会立刻返回，避免冷启动卡顿。
	VkFenceCreateInfo fenceInfo{};
	fenceInfo.sType = VK_STRUCTURE_TYPE_FENCE_CREATE_INFO;
	fenceInfo.flags = VK_FENCE_CREATE_SIGNALED_BIT;
	for (uint32_t i = 0; i < kTransferSlotCount; ++i) {
		if (vkCreateFence(device, &fenceInfo, nullptr, &m_xferFence[i]) != VK_SUCCESS) {
			for (uint32_t j = 0; j < i; ++j) {
				vkDestroyFence(device, m_xferFence[j], nullptr);
				m_xferFence[j] = VK_NULL_HANDLE;
			}
			vkFreeCommandBuffers(device, commandPool_ex, kTransferSlotCount, m_xferCmd);
			for (uint32_t j = 0; j < kTransferSlotCount; ++j) m_xferCmd[j] = VK_NULL_HANDLE;
			throw std::runtime_error("createTransferResources: vkCreateFence failed");
		}
	}

	m_xferIdx    = 0;
	m_xferInited = true;
#ifndef _WIN32
	DebugLog::log("createTransferResources: done, slots=%u pool=commandPool_ex",
	              (unsigned)kTransferSlotCount);
#endif
}

void Application::destroyTransferResources()
{
	if (!m_xferInited) {
		return;
	}
	// 调用方必须保证 GPU 已 idle 且没有线程正在 runTransferCommand。
	// 这里再加一道 m_xferMtx，串行化潜在的最后一次 transfer。
	std::lock_guard<std::mutex> xferLock(m_xferMtx);

	for (uint32_t i = 0; i < kTransferSlotCount; ++i) {
		if (m_xferFence[i] != VK_NULL_HANDLE) {
			vkDestroyFence(device, m_xferFence[i], nullptr);
			m_xferFence[i] = VK_NULL_HANDLE;
		}
	}
	if (m_xferCmd[0] != VK_NULL_HANDLE && commandPool_ex != VK_NULL_HANDLE) {
		vkFreeCommandBuffers(device, commandPool_ex, kTransferSlotCount, m_xferCmd);
	}
	for (uint32_t i = 0; i < kTransferSlotCount; ++i) {
		m_xferCmd[i] = VK_NULL_HANDLE;
	}
	m_xferIdx    = 0;
	m_xferInited = false;
#ifndef _WIN32
	DebugLog::log("destroyTransferResources: done");
#endif
}

void Application::runTransferCommand(const std::function<void(VkCommandBuffer)>& record)
{
	if (!m_xferInited) {
#ifndef _WIN32
		DebugLog::log_throttled("runTransferCommand.notInited",
		                        "runTransferCommand: not inited, skip");
#endif
		return;
	}

	// 串行化所有 transfer 调用：
	// - 保证 m_xferIdx 推进 / m_xferCmd[idx] 录制 / m_xferFence[idx] 等待
	//   形成一组原子动作；
	// - 同时也保证 commandPool_ex 的「外部同步」语义（同一时刻只允许一个
	//   线程对它做 record/reset）。
	std::lock_guard<std::mutex> xferLock(m_xferMtx);

	const uint32_t  idx   = m_xferIdx;
	VkFence         fence = m_xferFence[idx];
	VkCommandBuffer cmd   = m_xferCmd[idx];

	// 等上一次该 slot 的提交真正完成。fence 是独立同步对象，不需要持
	// poolQueueMtx 就可以等待，drawFrame 的 submit 不会被阻塞。
	VkResult wr = vkWaitForFences(device, 1, &fence, VK_TRUE, UINT64_MAX);
	if (wr != VK_SUCCESS) {
#ifndef _WIN32
		DebugLog::log_throttled("runTransferCommand.wait",
		                        "runTransferCommand: vkWaitForFences slot=%u -> %d",
		                        idx, (int)wr);
#endif
	}

	vkResetFences(device, 1, &fence);
	vkResetCommandBuffer(cmd, 0);

	VkCommandBufferBeginInfo beginInfo{};
	beginInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_BEGIN_INFO;
	beginInfo.flags = VK_COMMAND_BUFFER_USAGE_ONE_TIME_SUBMIT_BIT;
	if (vkBeginCommandBuffer(cmd, &beginInfo) != VK_SUCCESS) {
#ifndef _WIN32
		DebugLog::log_throttled("runTransferCommand.begin",
		                        "runTransferCommand: vkBeginCommandBuffer slot=%u failed", idx);
#endif
		return;
	}

	// 调用方在这里 record 命令：vkCmdCopyBuffer / vkCmdCopyBufferToImage /
	// transitionImageLayout 等。这些是纯 record 操作，在 m_xferMtx 持有
	// 且 cmd 独占的前提下不需要再额外加锁。
	record(cmd);

	if (vkEndCommandBuffer(cmd) != VK_SUCCESS) {
#ifndef _WIN32
		DebugLog::log_throttled("runTransferCommand.end",
		                        "runTransferCommand: vkEndCommandBuffer slot=%u failed", idx);
#endif
		return;
	}

	VkSubmitInfo submitInfo{};
	submitInfo.sType              = VK_STRUCTURE_TYPE_SUBMIT_INFO;
	submitInfo.commandBufferCount = 1;
	submitInfo.pCommandBuffers    = &cmd;

	// vkQueueSubmit 必须和 drawFrame 的 vkQueueSubmit / vkQueuePresentKHR
	// 互斥（队列要求外部同步）。其它步骤只占 m_xferMtx 即可。
	{
		std::lock_guard<std::mutex> poolLock(poolQueueMtx);
		VkResult sr = vkQueueSubmit(graphicsQueue, 1, &submitInfo, fence);
		if (sr != VK_SUCCESS) {
#ifndef _WIN32
			DebugLog::log_throttled("runTransferCommand.submit",
			                        "runTransferCommand: vkQueueSubmit slot=%u -> %d",
			                        idx, (int)sr);
#endif
		}
	}

	// ★ 关键：调用方代码（FaceApp::uploadVertexData / Application::updateTexture）
	// 在 runTransferCommand 之后会立刻 vkMapMemory + memcpy 覆写共享的
	// staging buffer，去做下一次拷贝。所以本接口必须像旧的 vkQueueWaitIdle
	// 一样保证 GPU **已读完** staging 才能返回，否则覆写会 race 上 GPU
	// 还在执行的 vkCmdCopyBuffer / vkCmdCopyBufferToImage，导致顶点 / 纹理
	// 数据被错位拼接（外观就是模型畸形 / 纹理花屏）。
	//
	// 这里只等自己这一次的 fence，不像旧实现 vkQueueWaitIdle 那样等整个
	// graphicsQueue（包括 drawFrame 的提交），所以不会拖慢渲染主路径。
	//
	// 不持 poolQueueMtx：fence 是独立同步对象，等它不需要外部互斥。
	VkResult er = vkWaitForFences(device, 1, &fence, VK_TRUE, UINT64_MAX);
	if (er != VK_SUCCESS) {
#ifndef _WIN32
		DebugLog::log_throttled("runTransferCommand.endWait",
		                        "runTransferCommand: end vkWaitForFences slot=%u -> %d",
		                        idx, (int)er);
#endif
	}

	m_xferIdx = (idx + 1) % kTransferSlotCount;
}


void Application::updateTexture(VkDevice device, VkPhysicalDevice physicalDevice,
	VkCommandPool commandPool, VkQueue queue,
	uint8_t* data, int width, int height,
	int rowStride, size_t dataSize, Texture& texture)
{
	//VkBuffer       stagingBuffer;
	//VkDeviceMemory stagingBufferMemory;

	void* mappedData;
	vkMapMemory(device, texture.stagingBufferMemory, 0, dataSize, 0, &mappedData);

	if (rowStride == width * 4)
	{
		memcpy(mappedData, data, dataSize);
	}
	else
	{
		uint8_t* dst = static_cast<uint8_t*>(mappedData);
		const uint8_t* src = data;
		size_t         dstRowStride = width * 4;

		for (int y = 0; y < height; y++)
		{
			memcpy(dst, src, dstRowStride);
			dst += dstRowStride;
			src += rowStride;
		}
	}

	vkUnmapMemory(device, texture.stagingBufferMemory);

	// 走 runTransferCommand：复用 commandPool_ex 上预分配的 cmdbuf + fence，
	// 不再每帧 vkAllocate/vkFree，也不再 vkQueueWaitIdle。
	// 注意：传入的 commandPool / queue 参数保留只是为了兼容旧接口，
	// 实际命令池一律换成 commandPool_ex（与渲染主管线物理隔离）。
	(void)commandPool;
	(void)queue;
	runTransferCommand([&](VkCommandBuffer commandBuffer) {
		transitionImageLayout(commandBuffer, texture.image,
			VK_IMAGE_LAYOUT_UNDEFINED,
			VK_IMAGE_LAYOUT_TRANSFER_DST_OPTIMAL);

		VkBufferImageCopy region = {};
		region.bufferOffset                    = 0;
		region.bufferRowLength                 = 0;
		region.bufferImageHeight               = 0;
		region.imageSubresource.aspectMask     = VK_IMAGE_ASPECT_COLOR_BIT;
		region.imageSubresource.mipLevel       = 0;
		region.imageSubresource.baseArrayLayer = 0;
		region.imageSubresource.layerCount     = 1;
		region.imageOffset                     = { 0, 0, 0 };
		region.imageExtent                     = { static_cast<uint32_t>(width),
		                                           static_cast<uint32_t>(height), 1 };

		vkCmdCopyBufferToImage(commandBuffer, texture.stagingBuffer, texture.image,
			VK_IMAGE_LAYOUT_TRANSFER_DST_OPTIMAL, 1, &region);

		transitionImageLayout(commandBuffer, texture.image,
			VK_IMAGE_LAYOUT_TRANSFER_DST_OPTIMAL,
			VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL);
	});

	texture.image_layout = VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL;
}


void Application::transitionImageLayout(VkCommandBuffer commandBuffer, VkImage image,
	VkImageLayout oldLayout, VkImageLayout newLayout)
{
	VkImageMemoryBarrier barrier = {};
	barrier.sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER;
	barrier.oldLayout = oldLayout;
	barrier.newLayout = newLayout;
	barrier.srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
	barrier.dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
	barrier.image = image;
	barrier.subresourceRange.aspectMask = VK_IMAGE_ASPECT_COLOR_BIT;
	barrier.subresourceRange.baseMipLevel = 0;
	barrier.subresourceRange.levelCount = 1;
	barrier.subresourceRange.baseArrayLayer = 0;
	barrier.subresourceRange.layerCount = 1;

	VkPipelineStageFlags sourceStage;
	VkPipelineStageFlags destinationStage;

	if (oldLayout == VK_IMAGE_LAYOUT_UNDEFINED &&
		newLayout == VK_IMAGE_LAYOUT_TRANSFER_DST_OPTIMAL)
	{
		barrier.srcAccessMask = 0;
		barrier.dstAccessMask = VK_ACCESS_TRANSFER_WRITE_BIT;

		sourceStage = VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT;
		destinationStage = VK_PIPELINE_STAGE_TRANSFER_BIT;
	}
	else if (oldLayout == VK_IMAGE_LAYOUT_TRANSFER_DST_OPTIMAL &&
		newLayout == VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL)
	{
		barrier.srcAccessMask = VK_ACCESS_TRANSFER_WRITE_BIT;
		barrier.dstAccessMask = VK_ACCESS_SHADER_READ_BIT;

		sourceStage = VK_PIPELINE_STAGE_TRANSFER_BIT;
		destinationStage = VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT;
	}
	else
	{
		throw std::invalid_argument("Unsupported layout transition!");
	}

	vkCmdPipelineBarrier(commandBuffer, sourceStage, destinationStage, 0,
		0, nullptr, 0, nullptr, 1, &barrier);
}

void Application::destroy_texture(Texture texture)
{
	vkDestroyImageView(device, texture.view, nullptr);
	vkDestroyImage(device, texture.image, nullptr);
	vkDestroySampler(device, texture.sampler, nullptr);
	vkFreeMemory(device, texture.device_memory, nullptr);
}