[Fix] (MG_Backend/DirectVulkan): fence-backed GL sync objects and per-frame descriptor rewind

- Track every graphics-queue submission with a real fence: pooled fences
  for mid-frame flushes, the frame slot's fence for Present and readback.
  Completion advances a submit counter via vkGetFenceStatus polls,
  slot-fence waits, and device-idle points, and raises the buffer-manager
  serial floor from the frame serial each submission carried.
- GL sync objects now capture the submission index that will carry the
  commands recorded so far; ClientWaitSync honors
  GL_SYNC_FLUSH_COMMANDS_BIT with a mid-frame submit (gated on the index
  still being unsubmitted so poll loops cannot split the render pass), and
  blocking waits flush then vkWaitForFences with the caller timeout.
- FlushPendingCommands retires the submitted command buffer and restarts
  recording on a fresh one; retired buffers are freed once the slot fence
  is next waited, so an executing buffer is never reset.
- Rewind descriptor-set cursors exactly once per frame in Present (after
  the slot-fence wait), plus after the synchronous readback drain,
  replacing the ten lazy per-draw-path rewinds.

Verified: host tests 168/168, trace-replay 70/70.
This commit is contained in:
2026-07-10 10:55:10 +00:00
parent 7b00255b11
commit eb090c6170
7 changed files with 436 additions and 58 deletions
@@ -13,6 +13,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Destroy(device, commandPool);
m_frames.assign(frameCount, {});
currentFrameIndex = 0;
m_device = device;
m_commandPool = commandPool;
Vector<VkCommandBuffer> commandBuffers(frameCount, VK_NULL_HANDLE);
VkCommandBufferAllocateInfo allocInfo{};
@@ -55,10 +57,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
DestroySwapchainSemaphores(device);
if (device != VK_NULL_HANDLE && commandPool != VK_NULL_HANDLE && !m_frames.empty()) {
for (auto& frame : m_frames) {
FreeRetiredCommandBuffers(frame);
}
vkFreeCommandBuffers(device, commandPool, frameCount, commandBuffers.data());
}
m_frames.clear();
currentFrameIndex = 0;
m_device = VK_NULL_HANDLE;
m_commandPool = VK_NULL_HANDLE;
}
FrameContext::FrameData& FrameContext::GetCurrent() {
@@ -214,6 +221,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
if (result != VK_SUCCESS) {
return result;
}
// The slot's fence has been waited: every command buffer this slot
// submitted (including mid-frame flushes) has finished executing.
FreeRetiredCommandBuffers(frame);
result = vkAcquireNextImageKHR(device, swapchain, timeout, frame.imageAvailableSemaphore, acquireFence,
&outImageIndex);
@@ -237,6 +247,39 @@ namespace MobileGL::MG_Backend::DirectVulkan {
m_recordingObserver = observer;
}
VkResult FrameContext::RetireCurrentCommandBuffer() {
MOBILEGL_ASSERT(m_device != VK_NULL_HANDLE && m_commandPool != VK_NULL_HANDLE,
"RetireCurrentCommandBuffer requires an initialized FrameContext");
auto& frame = GetCurrent();
MOBILEGL_ASSERT(!frame.isCommandRecording,
"RetireCurrentCommandBuffer called while the command buffer is still recording");
VkCommandBufferAllocateInfo allocInfo{};
allocInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_ALLOCATE_INFO;
allocInfo.commandPool = m_commandPool;
allocInfo.level = VK_COMMAND_BUFFER_LEVEL_PRIMARY;
allocInfo.commandBufferCount = 1;
VkCommandBuffer replacement = VK_NULL_HANDLE;
const VkResult result = vkAllocateCommandBuffers(m_device, &allocInfo, &replacement);
if (result != VK_SUCCESS) {
return result;
}
frame.retiredCommandBuffers.push_back(frame.commandBuffer);
frame.commandBuffer = replacement;
return VK_SUCCESS;
}
void FrameContext::FreeRetiredCommandBuffers(FrameData& frame) {
if (frame.retiredCommandBuffers.empty()) {
return;
}
if (m_device != VK_NULL_HANDLE && m_commandPool != VK_NULL_HANDLE) {
vkFreeCommandBuffers(m_device, m_commandPool, static_cast<Uint32>(frame.retiredCommandBuffers.size()),
frame.retiredCommandBuffers.data());
}
frame.retiredCommandBuffers.clear();
}
void FrameContext::AssertValidFrameIndex(Uint32 frameIndex) const {
MOBILEGL_ASSERT(frameIndex < m_frames.size(), "FrameContext index out of range");
}