BlackMark/CoopAllTheThings
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix Vulkan capture perf collapse: read back off the present thread

Browse Source 
Against Sphere Spectacle (144 FPS, runs without Steam) the implicit-layer
capture dropped the game to ~3 FPS. Measured cause (per-stage trace in the
layer): the read-back ran on the game's PRESENT THREAD and spent ~370 ms per
1080p frame -- not the GPU copy (~2 ms) but the CPU swizzle, because the staging
buffer was a plain HOST_VISIBLE|HOST_COHERENT type (write-combined / uncached on
a discrete GPU), where a scattered CPU read runs at PCIe latency. 3 captures/s =
the 3 FPS the user saw.

Test-first: tests/vk_capture_perf_test reproduces the stall as a deterministic
unit test (372 ms/present, ratio 1.0 -> FAIL via `--sync`), then proves the fix
(0.02 ms/present, byte-correct BGRA->RGBA, ratio ~0 -> PASS).

Fix: extract the near-identical read-back from vk_hook.cpp and coop_vk_layer.cpp
into one shared coop::hook::VkCapture that:
  * has the present thread only record + submit the copy (sub-ms) and return;
  * runs a dedicated reaper thread for the fence wait + swizzle + D3D upload, off
    the critical path, with a ring of in-flight slots (game never waits);
  * allocates HOST_CACHED staging (fast CPU read), invalidating when non-coherent;
  * throttles capture to ~150 Hz (a guest stream is <= the host refresh; no point
    mirroring an uncapped 400+ FPS game and burning reaper CPU).

Real-game A/B: present rate now matches the no-capture baseline (605->470 vs
593->405 over the same ramp) with the mirror at ~130 fps -- no measurable impact.

Also adds present-thread overhead guards to the other GPU backends' hook tests
(present_overhead.hpp): DX11 0.05 ms, DX12 0.34 ms, OpenGL 0.09 ms overhead, all
asserted < one 60 Hz frame, so any future synchronous-stall regression fails.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
BlackMark
2026-06-23 08:19:47 +02:00
parent 60957775b7
commit 304857dcf0
13 changed files with 1564 additions and 799 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vk_layer/CMakeLists.txt
View File

@@ -5,7 +5,9 @@
# manifest copied alongside (the manifest's library_path is relative).
coop_require_submodule("Vulkan-Headers" "third_party/Vulkan-Headers/include/vulkan/vulkan.h")
add_library(coop_vk_layer SHARED coop_vk_layer.cpp)
add_library(coop_vk_layer SHARED
coop_vk_layer.cpp
${CMAKE_SOURCE_DIR}/hook/src/vk_capture.cpp) # shared off-present-thread read-back (also used by vk_hook)
target_include_directories(coop_vk_layer PRIVATE
${CMAKE_SOURCE_DIR}/hook/src # ipc_client.hpp (reused IPC client)

448
vk_layer/coop_vk_layer.cpp
View File

@@ -3,10 +3,9 @@
// A real Vulkan *implicit layer* the loader inserts at vkCreateInstance -- guaranteed to be in
// the chain before the game resolves vkQueuePresentKHR. This is the reliable early-presence path
// for games that initialize Vulkan immediately (which inject-after-launch + the inline-hook
// vk_hook can't catch). It does the same capture as vk_hook -- read the presented image back with
// vkCmdCopyImageToBuffer, swizzle BGRA->RGBA, upload into the shared keyed-mutex texture on a
// hook-owned D3D11 device, and re-chain the present's wait semaphores -- but via proper
// layer-chain dispatch instead of an inline hook.
// vk_hook can't catch). The actual read-back (copy the presented image into the shared keyed-mutex
// texture, off the present thread) is the shared coop::hook::VkCapture; this file only gets the
// layer into the dispatch chain and feeds VkCapture each present.
//
// Scoping: an implicit layer loads into *every* Vulkan app, so the layer only *captures* when it
// recognises the process as the host's target -- env COOP_VK_LAYER_FORCE=1 (tests), or this
@@ -34,6 +33,7 @@
#include "coop/shared_memory.hpp"
#include "ipc_client.hpp"
#include "vk_capture.hpp"
// --- Loader/layer interface (interface version 2) ---------------------------
extern "C"
@@ -104,64 +104,25 @@ constexpr VkStructureType kLoaderInstanceCreateInfo = static_cast<VkStructureTyp
constexpr VkStructureType kLoaderDeviceCreateInfo = static_cast<VkStructureType>(48);
using coop::hook::IpcClient;
using coop::hook::VkCapture;
IpcClient g_ipc;
bool g_ipc_tried = false;
bool g_active = false; // do we capture in this process? (scoping)
std::atomic<bool> g_ipc_tried{false}; // reaper-thread side: connect once on the first published frame
bool g_active = false; // do we capture in this process? (scoping)
// Chain dispatch.
PFN_vkGetInstanceProcAddr g_next_gipa = nullptr;
PFN_vkGetDeviceProcAddr g_next_gdpa = nullptr;
PFN_vkQueuePresentKHR g_real_present = nullptr;
PFN_vkCreateSwapchainKHR g_real_create_swapchain = nullptr;
PFN_vkGetSwapchainImagesKHR g_get_swapchain_images = nullptr; // for our CreateSwapchain image tracking
VkInstance g_instance = VK_NULL_HANDLE;
VkPhysicalDevice g_phys = VK_NULL_HANDLE;
VkDevice g_device = VK_NULL_HANDLE;
std::uint32_t g_qfam = 0;
VkQueue g_queue = VK_NULL_HANDLE;
// Device functions for the read-back (same set as vk_hook).
struct VkFns
{
PFN_vkGetDeviceQueue GetDeviceQueue;
PFN_vkCreateCommandPool CreateCommandPool;
PFN_vkDestroyCommandPool DestroyCommandPool;
PFN_vkAllocateCommandBuffers AllocateCommandBuffers;
PFN_vkBeginCommandBuffer BeginCommandBuffer;
PFN_vkEndCommandBuffer EndCommandBuffer;
PFN_vkResetCommandBuffer ResetCommandBuffer;
PFN_vkCmdPipelineBarrier CmdPipelineBarrier;
PFN_vkCmdCopyImageToBuffer CmdCopyImageToBuffer;
PFN_vkQueueSubmit QueueSubmit;
PFN_vkCreateFence CreateFence;
PFN_vkDestroyFence DestroyFence;
PFN_vkWaitForFences WaitForFences;
PFN_vkResetFences ResetFences;
PFN_vkCreateSemaphore CreateSemaphore;
PFN_vkDestroySemaphore DestroySemaphore;
PFN_vkCreateBuffer CreateBuffer;
PFN_vkDestroyBuffer DestroyBuffer;
PFN_vkGetBufferMemoryRequirements GetBufferMemoryRequirements;
PFN_vkAllocateMemory AllocateMemory;
PFN_vkFreeMemory FreeMemory;
PFN_vkBindBufferMemory BindBufferMemory;
PFN_vkMapMemory MapMemory;
PFN_vkUnmapMemory UnmapMemory;
PFN_vkGetSwapchainImagesKHR GetSwapchainImagesKHR;
PFN_vkDeviceWaitIdle DeviceWaitIdle;
PFN_vkGetPhysicalDeviceMemoryProperties GetPhysicalDeviceMemoryProperties;
};
VkFns g_fns{};
VkCommandPool g_pool = VK_NULL_HANDLE;
VkCommandBuffer g_cmd = VK_NULL_HANDLE;
VkFence g_fence = VK_NULL_HANDLE;
VkSemaphore g_present_sem = VK_NULL_HANDLE;
VkBuffer g_staging = VK_NULL_HANDLE;
VkDeviceMemory g_staging_mem = VK_NULL_HANDLE;
VkDeviceSize g_staging_size = 0;
void* g_staging_mapped = nullptr;
VkCapture g_cap; // the shared, off-present-thread read-back
struct SwapInfo
{
@@ -172,14 +133,6 @@ struct SwapInfo
};
std::vector<SwapInfo> g_swaps;
ID3D11Device* g_d3d = nullptr;
ID3D11DeviceContext* g_d3d_ctx = nullptr;
ID3D11Texture2D* g_shared_tex = nullptr;
IDXGIKeyedMutex* g_shared_mutex = nullptr;
HANDLE g_shared_handle = nullptr;
UINT g_share_w = 0, g_share_h = 0;
std::vector<unsigned char> g_rgba;
bool eq(const char* a, const char* b)
{
return std::strcmp(a, b) == 0;
@@ -256,278 +209,6 @@ bool decide_active()
return _stricmp(self8, want) == 0;
}
bool ensure_d3d()
{
if (g_d3d != nullptr)
{
return true;
}
return SUCCEEDED(D3D11CreateDevice(nullptr, D3D_DRIVER_TYPE_HARDWARE, nullptr, 0, nullptr, 0,
D3D11_SDK_VERSION, &g_d3d, nullptr, &g_d3d_ctx)) &&
g_d3d != nullptr;
}
void release_shared()
{
if (g_shared_mutex)
{
g_shared_mutex->Release();
g_shared_mutex = nullptr;
}
if (g_shared_tex)
{
g_shared_tex->Release();
g_shared_tex = nullptr;
}
if (g_shared_handle)
{
CloseHandle(g_shared_handle);
g_shared_handle = nullptr;
}
g_share_w = g_share_h = 0;
}
bool ensure_shared_texture(UINT w, UINT h)
{
if (g_shared_tex && g_share_w == w && g_share_h == h)
{
return true;
}
release_shared();
D3D11_TEXTURE2D_DESC d{};
d.Width = w;
d.Height = h;
d.MipLevels = 1;
d.ArraySize = 1;
d.Format = DXGI_FORMAT_R8G8B8A8_UNORM;
d.SampleDesc.Count = 1;
d.Usage = D3D11_USAGE_DEFAULT;
d.BindFlags = D3D11_BIND_SHADER_RESOURCE;
d.MiscFlags = D3D11_RESOURCE_MISC_SHARED_NTHANDLE | D3D11_RESOURCE_MISC_SHARED_KEYEDMUTEX;
if (FAILED(g_d3d->CreateTexture2D(&d, nullptr, &g_shared_tex)) || !g_shared_tex)
{
return false;
}
IDXGIResource1* res = nullptr;
if (FAILED(g_shared_tex->QueryInterface(__uuidof(IDXGIResource1), reinterpret_cast<void**>(&res))) || !res)
{
release_shared();
return false;
}
const std::wstring name = coop::video_share_name(GetCurrentProcessId());
const HRESULT hr = res->CreateSharedHandle(
nullptr, DXGI_SHARED_RESOURCE_READ | DXGI_SHARED_RESOURCE_WRITE, name.c_str(), &g_shared_handle);
res->Release();
if (FAILED(hr) || !g_shared_handle ||
FAILED(g_shared_tex->QueryInterface(__uuidof(IDXGIKeyedMutex), reinterpret_cast<void**>(&g_shared_mutex))))
{
release_shared();
return false;
}
g_share_w = w;
g_share_h = h;
return true;
}
bool find_host_visible_memory(std::uint32_t bits, std::uint32_t& out)
{
VkPhysicalDeviceMemoryProperties mp{};
g_fns.GetPhysicalDeviceMemoryProperties(g_phys, &mp);
const VkMemoryPropertyFlags want = VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT;
for (std::uint32_t i = 0; i < mp.memoryTypeCount; ++i)
{
if ((bits & (1u << i)) && (mp.memoryTypes[i].propertyFlags & want) == want)
{
out = i;
return true;
}
}
return false;
}
void release_staging()
{
if (g_staging_mapped && g_staging_mem)
{
g_fns.UnmapMemory(g_device, g_staging_mem);
g_staging_mapped = nullptr;
}
if (g_staging)
{
g_fns.DestroyBuffer(g_device, g_staging, nullptr);
g_staging = VK_NULL_HANDLE;
}
if (g_staging_mem)
{
g_fns.FreeMemory(g_device, g_staging_mem, nullptr);
g_staging_mem = VK_NULL_HANDLE;
}
g_staging_size = 0;
}
bool ensure_vk_resources(std::uint32_t w, std::uint32_t h)
{
if (g_queue == VK_NULL_HANDLE)
{
g_fns.GetDeviceQueue(g_device, g_qfam, 0, &g_queue);
}
if (g_pool == VK_NULL_HANDLE)
{
VkCommandPoolCreateInfo pci{VK_STRUCTURE_TYPE_COMMAND_POOL_CREATE_INFO};
pci.flags = VK_COMMAND_POOL_CREATE_RESET_COMMAND_BUFFER_BIT;
pci.queueFamilyIndex = g_qfam;
if (g_fns.CreateCommandPool(g_device, &pci, nullptr, &g_pool) != VK_SUCCESS)
{
return false;
}
VkCommandBufferAllocateInfo ai{VK_STRUCTURE_TYPE_COMMAND_BUFFER_ALLOCATE_INFO};
ai.commandPool = g_pool;
ai.level = VK_COMMAND_BUFFER_LEVEL_PRIMARY;
ai.commandBufferCount = 1;
VkFenceCreateInfo fi{VK_STRUCTURE_TYPE_FENCE_CREATE_INFO};
VkSemaphoreCreateInfo si{VK_STRUCTURE_TYPE_SEMAPHORE_CREATE_INFO};
if (g_fns.AllocateCommandBuffers(g_device, &ai, &g_cmd) != VK_SUCCESS ||
g_fns.CreateFence(g_device, &fi, nullptr, &g_fence) != VK_SUCCESS ||
g_fns.CreateSemaphore(g_device, &si, nullptr, &g_present_sem) != VK_SUCCESS)
{
return false;
}
}
const VkDeviceSize need = static_cast<VkDeviceSize>(w) * h * 4;
if (g_staging != VK_NULL_HANDLE && g_staging_size == need)
{
return true;
}
release_staging();
VkBufferCreateInfo bci{VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO};
bci.size = need;
bci.usage = VK_BUFFER_USAGE_TRANSFER_DST_BIT;
bci.sharingMode = VK_SHARING_MODE_EXCLUSIVE;
if (g_fns.CreateBuffer(g_device, &bci, nullptr, &g_staging) != VK_SUCCESS)
{
return false;
}
VkMemoryRequirements mr{};
g_fns.GetBufferMemoryRequirements(g_device, g_staging, &mr);
std::uint32_t mt = 0;
if (!find_host_visible_memory(mr.memoryTypeBits, mt))
{
release_staging();
return false;
}
VkMemoryAllocateInfo mai{VK_STRUCTURE_TYPE_MEMORY_ALLOCATE_INFO};
mai.allocationSize = mr.size;
mai.memoryTypeIndex = mt;
if (g_fns.AllocateMemory(g_device, &mai, nullptr, &g_staging_mem) != VK_SUCCESS ||
g_fns.BindBufferMemory(g_device, g_staging, g_staging_mem, 0) != VK_SUCCESS ||
g_fns.MapMemory(g_device, g_staging_mem, 0, VK_WHOLE_SIZE, 0, &g_staging_mapped) != VK_SUCCESS)
{
release_staging();
return false;
}
g_staging_size = need;
return true;
}
void barrier(VkCommandBuffer cb, VkImage img, VkImageLayout from, VkImageLayout to, VkAccessFlags s,
VkAccessFlags d)
{
VkImageMemoryBarrier b{VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER};
b.srcAccessMask = s;
b.dstAccessMask = d;
b.oldLayout = from;
b.newLayout = to;
b.srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
b.dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
b.image = img;
b.subresourceRange = {VK_IMAGE_ASPECT_COLOR_BIT, 0, 1, 0, 1};
g_fns.CmdPipelineBarrier(cb, VK_PIPELINE_STAGE_ALL_COMMANDS_BIT, VK_PIPELINE_STAGE_ALL_COMMANDS_BIT, 0, 0,
nullptr, 0, nullptr, 1, &b);
}
bool capture(VkImage image, VkFormat fmt, std::uint32_t w, std::uint32_t h, const VkSemaphore* wait,
std::uint32_t wait_count, VkSemaphore& out_sem)
{
const bool bgra = fmt == VK_FORMAT_B8G8R8A8_UNORM || fmt == VK_FORMAT_B8G8R8A8_SRGB;
const bool rgba = fmt == VK_FORMAT_R8G8B8A8_UNORM || fmt == VK_FORMAT_R8G8B8A8_SRGB;
if ((!bgra && !rgba) || !ensure_d3d() || !ensure_shared_texture(w, h) || !ensure_vk_resources(w, h))
{
return false;
}
g_fns.ResetCommandBuffer(g_cmd, 0);
VkCommandBufferBeginInfo bi{VK_STRUCTURE_TYPE_COMMAND_BUFFER_BEGIN_INFO};
bi.flags = VK_COMMAND_BUFFER_USAGE_ONE_TIME_SUBMIT_BIT;
g_fns.BeginCommandBuffer(g_cmd, &bi);
barrier(g_cmd, image, VK_IMAGE_LAYOUT_PRESENT_SRC_KHR, VK_IMAGE_LAYOUT_TRANSFER_SRC_OPTIMAL,
VK_ACCESS_MEMORY_READ_BIT, VK_ACCESS_TRANSFER_READ_BIT);
VkBufferImageCopy region{};
region.imageSubresource = {VK_IMAGE_ASPECT_COLOR_BIT, 0, 0, 1};
region.imageExtent = {w, h, 1};
g_fns.CmdCopyImageToBuffer(g_cmd, image, VK_IMAGE_LAYOUT_TRANSFER_SRC_OPTIMAL, g_staging, 1, &region);
barrier(g_cmd, image, VK_IMAGE_LAYOUT_TRANSFER_SRC_OPTIMAL, VK_IMAGE_LAYOUT_PRESENT_SRC_KHR,
VK_ACCESS_TRANSFER_READ_BIT, VK_ACCESS_MEMORY_READ_BIT);
g_fns.EndCommandBuffer(g_cmd);
std::vector<VkPipelineStageFlags> stages(wait_count, VK_PIPELINE_STAGE_ALL_COMMANDS_BIT);
VkSubmitInfo si{VK_STRUCTURE_TYPE_SUBMIT_INFO};
si.waitSemaphoreCount = wait_count;
si.pWaitSemaphores = wait;
si.pWaitDstStageMask = wait_count ? stages.data() : nullptr;
si.commandBufferCount = 1;
si.pCommandBuffers = &g_cmd;
si.signalSemaphoreCount = 1;
si.pSignalSemaphores = &g_present_sem;
g_fns.ResetFences(g_device, 1, &g_fence);
if (g_fns.QueueSubmit(g_queue, 1, &si, g_fence) != VK_SUCCESS)
{
return false;
}
g_fns.WaitForFences(g_device, 1, &g_fence, VK_TRUE, UINT64_MAX);
const size_t row = static_cast<size_t>(w) * 4;
if (g_rgba.size() != row * h)
{
g_rgba.resize(row * h);
}
const auto* src = static_cast<const unsigned char*>(g_staging_mapped);
for (std::uint32_t y = 0; y < h; ++y)
{
const unsigned char* s = src + static_cast<size_t>(y) * row;
unsigned char* o = g_rgba.data() + static_cast<size_t>(y) * row;
if (bgra)
{
for (std::uint32_t x = 0; x < w; ++x)
{
o[x * 4 + 0] = s[x * 4 + 2];
o[x * 4 + 1] = s[x * 4 + 1];
o[x * 4 + 2] = s[x * 4 + 0];
o[x * 4 + 3] = 255;
}
}
else
{
std::memcpy(o, s, row);
}
}
out_sem = g_present_sem;
if (g_shared_mutex->AcquireSync(coop::kVideoMutexKey, 8) == S_OK)
{
g_d3d_ctx->UpdateSubresource(g_shared_tex, 0, nullptr, g_rgba.data(), static_cast<UINT>(row), 0);
g_d3d_ctx->Flush();
g_shared_mutex->ReleaseSync(coop::kVideoMutexKey);
if (!g_ipc_tried)
{
g_ipc_tried = true;
g_ipc.connect(/*attempts=*/40, /*delay_ms=*/25);
}
if (g_ipc.connected())
{
g_ipc.publish_video_frame(w, h, static_cast<std::uint32_t>(DXGI_FORMAT_R8G8B8A8_UNORM));
}
}
return true;
}
const SwapInfo* find_swap(VkSwapchainKHR sc)
{
for (const SwapInfo& s : g_swaps)
@@ -540,8 +221,47 @@ const SwapInfo* find_swap(VkSwapchainKHR sc)
return nullptr;
}
// Per-second present-rate trace (enable with COOP_VK_LAYER_LOG): confirms the game keeps its frame
// rate while capturing (the whole point of the off-present-thread read-back) and how many of those
// presents the reaper actually mirrored.
void trace_present_rate()
{
static int enabled = -1;
if (enabled < 0)
{
enabled = GetEnvironmentVariableW(L"COOP_VK_LAYER_LOG", nullptr, 0) != 0 ? 1 : 0;
}
if (enabled == 0)
{
return;
}
static LARGE_INTEGER freq{};
static LARGE_INTEGER last{};
static int count = 0;
static std::uint64_t last_published = 0;
if (freq.QuadPart == 0)
{
QueryPerformanceFrequency(&freq);
QueryPerformanceCounter(&last);
}
++count;
LARGE_INTEGER now;
QueryPerformanceCounter(&now);
const double sec = static_cast<double>(now.QuadPart - last.QuadPart) / static_cast<double>(freq.QuadPart);
if (sec >= 1.0)
{
const std::uint64_t pub = g_cap.frames_published();
logvk("present rate %.1f/s captured %.1f/s (game keeps its rate; capture is off the present thread)",
count / sec, (pub - last_published) / sec);
last = now;
count = 0;
last_published = pub;
}
}
VKAPI_ATTR VkResult VKAPI_CALL layer_QueuePresentKHR(VkQueue queue, const VkPresentInfoKHR* pi)
{
trace_present_rate(); // unconditional so an inactive (pass-through) run gives a baseline to compare
if (g_active && g_ipc.connected())
{
g_ipc.note_present();
@@ -552,8 +272,8 @@ VKAPI_ATTR VkResult VKAPI_CALL layer_QueuePresentKHR(VkQueue queue, const VkPres
if (s != nullptr && pi->pImageIndices[0] < s->images.size())
{
VkSemaphore chained = VK_NULL_HANDLE;
if (capture(s->images[pi->pImageIndices[0]], s->fmt, s->w, s->h, pi->pWaitSemaphores,
pi->waitSemaphoreCount, chained))
if (g_cap.present(s->images[pi->pImageIndices[0]], s->fmt, s->w, s->h, pi->pWaitSemaphores,
pi->waitSemaphoreCount, chained))
{
VkPresentInfoKHR p = *pi;
p.waitSemaphoreCount = 1;
@@ -569,7 +289,7 @@ VKAPI_ATTR VkResult VKAPI_CALL layer_CreateSwapchainKHR(VkDevice device, const V
const VkAllocationCallbacks* a, VkSwapchainKHR* out)
{
const VkResult r = g_real_create_swapchain(device, ci, a, out);
if (g_active && r == VK_SUCCESS && out && g_fns.GetSwapchainImagesKHR)
if (g_active && r == VK_SUCCESS && out && g_get_swapchain_images)
{
SwapInfo info{};
info.sc = *out;
@@ -577,17 +297,19 @@ VKAPI_ATTR VkResult VKAPI_CALL layer_CreateSwapchainKHR(VkDevice device, const V
info.w = ci->imageExtent.width;
info.h = ci->imageExtent.height;
std::uint32_t n = 0;
g_fns.GetSwapchainImagesKHR(device, *out, &n, nullptr);
g_get_swapchain_images(device, *out, &n, nullptr);
info.images.resize(n);
g_fns.GetSwapchainImagesKHR(device, *out, &n, info.images.data());
g_get_swapchain_images(device, *out, &n, info.images.data());
g_swaps.push_back(std::move(info));
}
return r;
}
void load_device_fns(VkDevice dev)
// Resolve the device functions the read-back needs and start the capture component.
void start_capture(VkDevice dev)
{
#define LOAD(field, vkname) g_fns.field = reinterpret_cast<PFN_##vkname>(g_next_gdpa(dev, #vkname))
VkCapture::Fns f{};
#define LOAD(field, vkname) f.field = reinterpret_cast<PFN_##vkname>(g_next_gdpa(dev, #vkname))
LOAD(GetDeviceQueue, vkGetDeviceQueue);
LOAD(CreateCommandPool, vkCreateCommandPool);
LOAD(DestroyCommandPool, vkDestroyCommandPool);
@@ -602,6 +324,7 @@ void load_device_fns(VkDevice dev)
LOAD(DestroyFence, vkDestroyFence);
LOAD(WaitForFences, vkWaitForFences);
LOAD(ResetFences, vkResetFences);
LOAD(GetFenceStatus, vkGetFenceStatus);
LOAD(CreateSemaphore, vkCreateSemaphore);
LOAD(DestroySemaphore, vkDestroySemaphore);
LOAD(CreateBuffer, vkCreateBuffer);
@@ -612,11 +335,27 @@ void load_device_fns(VkDevice dev)
LOAD(BindBufferMemory, vkBindBufferMemory);
LOAD(MapMemory, vkMapMemory);
LOAD(UnmapMemory, vkUnmapMemory);
LOAD(GetSwapchainImagesKHR, vkGetSwapchainImagesKHR);
LOAD(InvalidateMappedMemoryRanges, vkInvalidateMappedMemoryRanges);
LOAD(DeviceWaitIdle, vkDeviceWaitIdle);
#undef LOAD
g_fns.GetPhysicalDeviceMemoryProperties = reinterpret_cast<PFN_vkGetPhysicalDeviceMemoryProperties>(
f.GetPhysicalDeviceMemoryProperties = reinterpret_cast<PFN_vkGetPhysicalDeviceMemoryProperties>(
g_next_gipa(g_instance, "vkGetPhysicalDeviceMemoryProperties"));
g_get_swapchain_images =
reinterpret_cast<PFN_vkGetSwapchainImagesKHR>(g_next_gdpa(dev, "vkGetSwapchainImagesKHR"));
g_cap.init(g_phys, dev, g_qfam, f, GetCurrentProcessId(), [](std::uint32_t w, std::uint32_t h) {
// Runs on the reaper thread after each frame is published to the shared texture. Connect the
// IPC channel lazily here (the host may not have created it yet at device-create time), then
// publish the frame so the host's generation counter advances.
if (!g_ipc_tried.exchange(true))
{
g_ipc.connect(/*attempts=*/40, /*delay_ms=*/25);
}
if (g_ipc.connected())
{
g_ipc.publish_video_frame(w, h, static_cast<std::uint32_t>(DXGI_FORMAT_R8G8B8A8_UNORM));
}
});
}
VKAPI_ATTR PFN_vkVoidFunction VKAPI_CALL layer_gdpa(VkDevice device, const char* name);
@@ -651,7 +390,7 @@ VKAPI_ATTR VkResult VKAPI_CALL layer_CreateDevice(VkPhysicalDevice phys, const V
g_real_create_swapchain = reinterpret_cast<PFN_vkCreateSwapchainKHR>(next_gdpa(*out, "vkCreateSwapchainKHR"));
if (g_active)
{
load_device_fns(*out);
start_capture(*out);
}
}
return r;
@@ -688,40 +427,11 @@ VKAPI_ATTR VkResult VKAPI_CALL layer_CreateInstance(const VkInstanceCreateInfo*
VKAPI_ATTR void VKAPI_CALL layer_DestroyDevice(VkDevice device, const VkAllocationCallbacks* a)
{
auto destroy = reinterpret_cast<PFN_vkDestroyDevice>(g_next_gdpa(device, "vkDestroyDevice"));
if (g_active && device == g_device && g_fns.DeviceWaitIdle != nullptr)
if (g_active && device == g_device)
{
g_fns.DeviceWaitIdle(device);
release_staging();
if (g_present_sem)
{
g_fns.DestroySemaphore(device, g_present_sem, nullptr);
g_present_sem = VK_NULL_HANDLE;
}
if (g_fence)
{
g_fns.DestroyFence(device, g_fence, nullptr);
g_fence = VK_NULL_HANDLE;
}
if (g_pool)
{
g_fns.DestroyCommandPool(device, g_pool, nullptr);
g_pool = VK_NULL_HANDLE;
}
release_shared();
if (g_d3d_ctx)
{
g_d3d_ctx->Release();
g_d3d_ctx = nullptr;
}
if (g_d3d)
{
g_d3d->Release();
g_d3d = nullptr;
}
g_cap.shutdown(); // joins the reaper, drains the device, frees the read-back resources
g_swaps.clear();
g_device = VK_NULL_HANDLE;
g_queue = VK_NULL_HANDLE;
g_cmd = VK_NULL_HANDLE;
}
destroy(device, a);
}