[Fix] (DirectVulkan): bound the vertex-input and sampler caches and sweep undeleted GL syncs - both caches age out entries idle >1024 frame boundaries (animated LOD bias no longer mints a VkSampler per float value, buffer/VAO churn no longer grows the vertex-input map for the whole session), and library teardown drains the live-sync registry exactly as glDeleteSync would since GL requires syncs to die with their context

This commit is contained in:
2026-07-27 22:16:16 -04:00
parent 930a607bdf
commit d076c29146
8 changed files with 144 additions and 0 deletions
+7
View File
@@ -14,6 +14,7 @@
#include <MG_State/EGLState/Core.h>
#include <MG_Impl/GLImpl/Texture/ProxyTexture.h>
#include <MG_Impl/GLImpl/Framebuffer/GL_Framebuffer.h>
#include <MG_Impl/GLImpl/Sync/GL_Sync.h>
#include <atomic>
#include <mutex>
@@ -37,6 +38,12 @@ namespace MobileGL {
MGLOG_I("MobileGL closing...");
}
glslang::FinalizeProcess();
// GL syncs die with their contexts, and every context is gone by the
// time full teardown runs: drain the live-sync registry while the
// backend function table can still release the backend handles (and
// before a re-initialized library could pair them with the wrong
// backend's DeleteSync).
MG_Impl::GLImpl::DestroyAllSyncObjects();
MG_Backend::pActiveBackendObject.reset();
MG_State::pGLContext.reset();
MG_State::pEGLContext.reset();
@@ -32,6 +32,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
XXHASH_VERIFY(XXH64_update(m_hashState, &attr.IsBgra, sizeof(attr.IsBgra)));
XXHASH_VERIFY(XXH64_update(m_hashState, &attr.Divisor, sizeof(attr.Divisor)));
// The buffer's heap address is an identity component of the key: a freed
// buffer's reused address can alias an old cache entry, but only under a
// byte-identical attribute layout - and the entry payload is a pure function
// of the hashed inputs, with the draw path re-resolving bindingBufferKeys
// against the live VAO attribute pointers, so an aliased hit returns exactly
// what a rebuild would. Address drift only grows the map; the OnFrameBoundary
// aging sweep bounds that.
const SizeT bufferKey = reinterpret_cast<SizeT>(attr.Buffer.get());
XXHASH_VERIFY(XXH64_update(m_hashState, &bufferKey, sizeof(bufferKey)));
}
@@ -58,6 +65,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
const MG_State::GLState::VertexArrayObject& vao, HashType hash) {
auto it = m_cache.find(hash);
if (it != m_cache.end()) {
it->second.lastUsedFrameBoundary = m_frameBoundaryCounter;
return it->second;
}
@@ -166,6 +174,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
auto& entry = m_cache[hash];
entry.hash = hash;
entry.lastUsedFrameBoundary = m_frameBoundaryCounter;
entry.bindings = builder.GetBindings();
entry.attributes = builder.GetAttributes();
entry.bindingBufferKeys = std::move(bindingBufferKeys);
@@ -180,6 +189,30 @@ namespace MobileGL::MG_Backend::DirectVulkan {
return entry;
}
void VertexInputStateFactory::OnFrameBoundary() {
++m_frameBoundaryCounter;
// Sweep occasionally; evict entries whose last hit is far in the past.
// Erasure happens only here, never mid-frame: the draw path holds a
// reference into the current entry across its setup, and unordered_map
// erase would invalidate it. Entries are CPU-side only, so no GPU-idle
// proof is needed; an evicted entry that is used again is simply rebuilt
// from the VAO state (same hash, same content).
constexpr Uint64 kSweepInterval = 256;
constexpr Uint64 kRetireAgeBoundaries = 1024;
if ((m_frameBoundaryCounter % kSweepInterval) != 0) {
return;
}
for (auto it = m_cache.begin(); it != m_cache.end();) {
if (m_frameBoundaryCounter - it->second.lastUsedFrameBoundary > kRetireAgeBoundaries) {
it = m_cache.erase(it);
} else {
++it;
}
}
}
VkFormat VertexInputStateFactory::ToVkVertexFormat(DataType type, Int size, Bool normalized, Bool isInteger,
Bool isBgra) {
if (isBgra) {
@@ -27,6 +27,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
struct BackendVertexInputState {
HashType hash = 0;
// Frame boundary of the last cache hit; entries idle past the
// OnFrameBoundary retirement age are evicted (CPU heap only).
Uint64 lastUsedFrameBoundary = 0;
Vector<VkVertexInputBindingDescription> bindings;
Vector<VkVertexInputAttributeDescription> attributes;
Vector<SizeT> bindingBufferKeys;
@@ -55,6 +58,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
const BackendVertexInputState& GetOrCreateVertexInputState(
const MG_State::GLState::VertexArrayObject& vao, HashType hash);
const BackendVertexInputState& GetOrCreateVertexInputState(const MG_State::GLState::VertexArrayObject& vao);
// Frame boundary hook: ages the cache and evicts entries not hit for many
// frames. The key mixes buffer heap addresses, so buffer/VAO churn keeps
// minting fresh keys; without eviction the map grows for the whole session.
// Entries hold no Vulkan handles (pipeline creation copies the descriptions)
// and the draw path's entry reference never spans a frame boundary, so
// eviction here needs no GPU-idle proof. Self-gated: one counter bump and
// compare except on sweep boundaries.
void OnFrameBoundary();
static SizeT GetComponentSize(DataType type);
// Tightly-packed byte size of one vertex element for this attribute: componentSize * size for
// normal types, and 4 (one packed word) for the 2_10_10_10 types and GL_BGRA. Returns 0 for
@@ -70,6 +81,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
const VulkanRendererConfig& m_config;
VkPhysicalDevice m_physicalDevice = VK_NULL_HANDLE;
UnorderedMap<HashType, BackendVertexInputState> m_cache;
// Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
Uint64 m_frameBoundaryCounter = 0;
static inline XXH64_state_t* m_hashState = XXH64_createState();
};
} // namespace MobileGL::MG_Backend::DirectVulkan
@@ -89,6 +89,33 @@ namespace MobileGL::MG_Backend::DirectVulkan {
m_device = VK_NULL_HANDLE;
m_config = nullptr;
m_frameBoundaryCounter = 0;
}
void VkSamplerManager::OnFrameBoundary() {
++m_frameBoundaryCounter;
// Sweep occasionally; destroy samplers whose last use is far past every
// in-flight frame. Destroy and erase must stay atomic, or Shutdown would
// double-free the handle; an evicted key that recurs simply re-creates
// its sampler on the next miss.
constexpr Uint64 kSweepInterval = 256;
constexpr Uint64 kRetireAgeBoundaries = 1024;
if ((m_frameBoundaryCounter % kSweepInterval) != 0) {
return;
}
for (auto it = m_samplers.begin(); it != m_samplers.end();) {
auto& entry = it->second;
if (m_frameBoundaryCounter - entry.lastUsedFrameBoundary > kRetireAgeBoundaries) {
if (m_device != VK_NULL_HANDLE && entry.handle != VK_NULL_HANDLE) {
vkDestroySampler(m_device, entry.handle, nullptr);
}
it = m_samplers.erase(it);
} else {
++it;
}
}
}
Uint64 VkSamplerManager::BuildSamplerKey(const MG_State::GLState::SamplerObject& sampler,
@@ -137,6 +164,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
const Uint64 key = BuildSamplerKey(sampler, texture, forceNearestFiltering);
auto it = m_samplers.find(key);
if (it != m_samplers.end()) {
it->second.lastUsedFrameBoundary = m_frameBoundaryCounter;
return it->second.handle;
}
@@ -169,6 +197,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
entry.handle = vkSampler;
entry.externalIndex = sampler.GetExternalIndex();
entry.version = sampler.GetVersion();
entry.lastUsedFrameBoundary = m_frameBoundaryCounter;
m_samplers[key] = entry;
return vkSampler;
}
@@ -36,12 +36,27 @@ public:
VkSampler GetOrCreateSampler(const MG_State::GLState::SamplerObject& sampler,
const MG_State::GLState::ITextureObject& texture,
Bool forceNearestFiltering = false);
// Frame boundary hook: ages the sampler cache and destroys samplers not used
// for many frames. The key hashes continuous float state (lodBias, LOD clamps,
// anisotropy), so an app animating those would otherwise mint an unbounded
// stream of never-destroyed VkSamplers and eventually exhaust the device's
// maxSamplerAllocationCount. A sampler idle for over a thousand frame
// boundaries cannot be referenced by any in-flight command buffer (frames in
// flight are single digits), and every descriptor set the GPU consumes is
// written that same frame with live handles (the per-binding resolve memo and
// descriptor-set reuse are both frame-reset), so destruction here needs no
// fence wait. Self-gated: one counter bump and compare except on sweep
// boundaries.
void OnFrameBoundary();
private:
struct SamplerCacheEntry {
VkSampler handle = VK_NULL_HANDLE;
Uint externalIndex = 0;
Uint16 version = 0;
// Frame boundary of the last cache hit; entries idle past the
// OnFrameBoundary retirement age have their VkSampler destroyed.
Uint64 lastUsedFrameBoundary = 0;
};
Uint64 BuildSamplerKey(const MG_State::GLState::SamplerObject& sampler,
@@ -67,6 +82,8 @@ private:
Bool m_samplerAnisotropySupported = false;
Float m_maxSamplerAnisotropy = 1.0f;
UnorderedMap<Uint64, SamplerCacheEntry> m_samplers;
// Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
Uint64 m_frameBoundaryCounter = 0;
static inline XXH64_state_t* m_hashState = XXH64_createState();
};
} // namespace MobileGL::MG_Backend::DirectVulkan
@@ -7269,6 +7269,12 @@ void main() {
if (m_uniformManager) {
m_uniformManager->OnFrameBoundary();
}
if (m_vertexInputStateFactory) {
m_vertexInputStateFactory->OnFrameBoundary();
}
if (m_samplerManager) {
m_samplerManager->OnFrameBoundary();
}
return true;
}
@@ -7534,6 +7540,8 @@ void main() {
m_lastPipelineResult = VK_NULL_HANDLE;
}
m_uniformManager->OnFrameBoundary();
m_vertexInputStateFactory->OnFrameBoundary();
m_samplerManager->OnFrameBoundary();
auto& frame = m_frameContext.GetCurrent();
auto* activeRenderPass = VkRenderPassManager::GetActiveRenderPass();
if (activeRenderPass)
+29
View File
@@ -133,4 +133,33 @@ namespace MobileGL::MG_Impl::GLImpl {
values[0] = value;
}
}
void DestroyAllSyncObjects() {
// Detach the registry under the lock, release outside it. Entries the app
// already deleted were erased by DeleteSync, so nothing here double-frees;
// a DeleteSync racing this sweep finds an empty registry and returns. A
// thread still blocked inside ClientWaitSync/GetSynciv during teardown
// holds a raw SyncObject* these deletes invalidate - the same undefined
// race an app-driven DeleteSync already has.
UnorderedMap<GLsync, SyncObject*> orphans;
{
const std::lock_guard<std::mutex> lock(g_syncObjectsMutex);
orphans.swap(g_liveSyncObjects);
}
if (orphans.empty()) {
return;
}
// Both backends' DeleteSync only free the heap wrapper once their GL
// context/renderer is gone (generation/current-thread guards), so this is
// safe after the backend has released its EGL resources - but not after
// the function table itself is cleared.
const auto backendDeleteSync = MG_Backend::gBackendFunctionsTable.GL.DeleteSync;
for (const auto& [_, syncObject] : orphans) {
if (backendDeleteSync && syncObject->backendHandle) {
backendDeleteSync(syncObject->backendHandle);
}
delete syncObject;
}
MGLOG_D("DestroyAllSyncObjects: reclaimed %zu sync object(s) the app left undeleted", orphans.size());
}
} // namespace MobileGL::MG_Impl::GLImpl
+8
View File
@@ -16,4 +16,12 @@ namespace MobileGL::MG_Impl::GLImpl {
void WaitSync(GLsync sync, GLbitfield flags, GLuint64 timeout);
void DeleteSync(GLsync sync);
void GetSynciv(GLsync sync, GLenum pname, GLsizei bufSize, GLsizei* length, GLint* values);
// Destroys every still-registered sync object exactly as DeleteSync would.
// GL requires syncs to die with their context; called only from full library
// teardown (DestroyImpl), where no context survives on any thread, so the
// process-global registry can be drained wholesale. Must run while the
// backend function table is still populated: each backend handle has to be
// released by the backend that created it, never by a later re-initialized
// one.
void DestroyAllSyncObjects();
} // namespace MobileGL::MG_Impl::GLImpl