[Fix] (DirectVulkan): age-based eviction for the content-addressed cache family - ProgramFactory entries (shader modules/layouts), PipelineFactory graphics pipelines, compute pipelines and per-layout descriptor-set tracking now retire after ~1024 idle frame boundaries (render-pass-manager sweep precedent), render-pass eviction purges pipelines hashed on the dying handle (closes a handle-recycling stale-pipeline hazard), and the program reflection cache is lifetime-id-keyed and cleared at EGL teardown - shader/program churn no longer grows Vulkan objects without bound

This commit is contained in:
2026-07-27 22:05:25 -04:00
parent c540fb88ee
commit 34685b4bb0
13 changed files with 417 additions and 7 deletions
@@ -469,6 +469,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// treat them as signaled/available with zero results from here on.
BumpRendererGeneration();
pVulkanRenderer.reset();
// The reflection cache is file-scope, not renderer-owned; without this the
// deleted programs' reflection strings survive full context teardown.
ClearProgramResourceCaches();
BackendObject::ReleaseEGLResources();
}
@@ -478,6 +481,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// treat them as signaled/available with zero results from here on.
BumpRendererGeneration();
pVulkanRenderer.reset();
// The reflection cache is file-scope, not renderer-owned; without this the
// deleted programs' reflection strings survive full context teardown.
ClearProgramResourceCaches();
}
const RendererInfo& BackendObject_DirectVulkan::GetRendererInfo() const {
@@ -61,6 +61,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
};
struct ProgramResourceCache {
// Lifetime id of the program the cached reflection belongs to. GL names are
// recycled (IndexGenerator hands freed indices straight back), and a
// recreated program's backendStateVersion restarts at the same small values,
// so the version alone can collide; the never-reused lifetime id makes the
// slot's ownership unambiguous.
Uint64 programLifetimeId = 0;
Uint32 backendStateVersion = 0;
Vector<StorageBlockResource> storageBlocks;
Vector<BufferVariableResource> bufferVariables;
@@ -82,6 +88,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Uint32 baseInstance = 0;
};
// Keyed by GL program name so the freed-name reuse in IndexGenerator bounds the
// map at the peak-simultaneous-program high-water mark; each slot's ownership is
// checked against the program's lifetime id before it is served (see
// GetProgramResourceCache). Cleared wholesale at EGL teardown via
// ClearProgramResourceCaches.
UnorderedMap<GLuint, ProgramResourceCache> g_programResourceCaches;
void ClearReadPixelsOutput(GLsizei width, GLsizei height, GLenum format, GLenum type, void* pixels) {
@@ -142,13 +153,19 @@ namespace MobileGL::MG_Backend::DirectVulkan {
ProgramResourceCache& GetProgramResourceCache(const MG_State::GLState::ProgramObject& program) {
auto& cache = g_programResourceCaches[program.GetExternalIndex()];
const Uint64 programLifetimeId = program.GetLifetimeId();
const Uint32 backendStateVersion = program.GetBackendStateVersion();
if (cache.backendStateVersion == backendStateVersion &&
// The lifetime id must match too: a new program that reuses a deleted
// program's name and happens to land on the same backendStateVersion (both
// count from zero) would otherwise be served the dead program's reflection.
if (cache.programLifetimeId == programLifetimeId &&
cache.backendStateVersion == backendStateVersion &&
(!cache.storageBlocks.empty() || !cache.bufferVariables.empty())) {
return cache;
}
cache = {};
cache.programLifetimeId = programLifetimeId;
cache.backendStateVersion = backendStateVersion;
Vector<SpvReflectShaderModule> modules;
@@ -366,6 +383,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
} // namespace
void ClearProgramResourceCaches() {
// Called from EGL teardown while the backend's m_eglStateMutex is held; GL
// calls are serialized in this codebase (contexts migrate threads but never
// run concurrently), so no other thread can be inside the unsynchronized map.
// Live programs in another context self-heal: their entry rebuilds from the
// retained generated SPIR-V on the next resource query.
g_programResourceCaches.clear();
}
GLuint GetShaderStorageBlockIndex(const MG_State::GLState::ProgramObject& program, const String& name) {
auto& cache = GetProgramResourceCache(program);
const auto it = std::find_if(cache.storageBlocks.begin(), cache.storageBlocks.end(),
@@ -23,6 +23,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Uint64 GetRendererGeneration();
void BumpRendererGeneration();
// Drops every cached program-resource reflection entry (CPU-side strings/vectors
// only, no Vulkan handles). Called at EGL teardown next to the renderer reset;
// safe because GL calls are serialized in this codebase, and any still-live
// program rebuilds its entry from the retained generated SPIR-V on demand.
void ClearProgramResourceCaches();
void ClearBufferfi(GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
void ClearBufferfv(GLenum buffer, GLint drawbuffer, const GLfloat* value);
void ClearBufferuiv(GLenum buffer, GLint drawbuffer, const GLuint* value);
@@ -243,23 +243,100 @@ namespace MobileGL::MG_Backend::DirectVulkan {
const HashType hash = ComputeHash(payload);
auto it = m_cache.find(hash);
if (it != m_cache.end()) {
return it->second;
it->second.lastUsedFrame = m_frameCounter;
return it->second.pipeline;
}
VkPipeline pipeline = CreatePipeline(payload);
m_cache.emplace(hash, pipeline);
m_cache.emplace(hash, PipelineCacheEntry{pipeline, payload.programHash, payload.renderPass,
m_frameCounter});
return pipeline;
}
void PipelineFactory::DestroyAll() {
for (auto& pair : m_cache) {
if (pair.second != VK_NULL_HANDLE) {
vkDestroyPipeline(m_device, pair.second, nullptr);
if (pair.second.pipeline != VK_NULL_HANDLE) {
vkDestroyPipeline(m_device, pair.second.pipeline, nullptr);
}
}
m_cache.clear();
}
Uint32 PipelineFactory::OnFrameBoundary() {
++m_frameCounter;
// Sweep cadence and retire age mirror VkRenderPassManager::OnPresent: an entry
// idle for more than kRetireAgeFrames frame boundaries cannot be referenced by
// any in-flight command buffer (frames-in-flight <= MOBILEGL_MAGMA_FRAMESINFLIGHT),
// so immediate vkDestroyPipeline is safe. The caller must drop its "last
// pipeline" memo when this returns non-zero: the memo can return a cached
// handle without touching this cache, so an evicted pipeline may still be
// memoized (present-less flush loops never reset the memo per frame).
constexpr Uint64 kSweepInterval = 256;
constexpr Uint64 kRetireAgeFrames = 1024;
if ((m_frameCounter % kSweepInterval) != 0) {
return 0;
}
Uint32 evicted = 0;
for (auto it = m_cache.begin(); it != m_cache.end();) {
if (m_frameCounter - it->second.lastUsedFrame > kRetireAgeFrames) {
if (it->second.pipeline != VK_NULL_HANDLE) {
vkDestroyPipeline(m_device, it->second.pipeline, nullptr);
}
it = m_cache.erase(it);
++evicted;
} else {
++it;
}
}
if (evicted > 0) {
MGLOG_D("PipelineFactory::OnFrameBoundary: evicted %u idle pipelines (%zu remain)", evicted,
m_cache.size());
}
return evicted;
}
Uint32 PipelineFactory::EvictByRenderPass(VkRenderPass renderPass) {
Uint32 evicted = 0;
for (auto it = m_cache.begin(); it != m_cache.end();) {
if (it->second.renderPass == renderPass) {
if (it->second.pipeline != VK_NULL_HANDLE) {
vkDestroyPipeline(m_device, it->second.pipeline, nullptr);
}
it = m_cache.erase(it);
++evicted;
} else {
++it;
}
}
if (evicted > 0) {
MGLOG_D("PipelineFactory::EvictByRenderPass: evicted %u pipelines for destroyed render pass",
evicted);
}
return evicted;
}
Uint32 PipelineFactory::EvictByProgramHash(HashType programHash) {
Uint32 evicted = 0;
for (auto it = m_cache.begin(); it != m_cache.end();) {
if (it->second.programHash == programHash) {
if (it->second.pipeline != VK_NULL_HANDLE) {
vkDestroyPipeline(m_device, it->second.pipeline, nullptr);
}
it = m_cache.erase(it);
++evicted;
} else {
++it;
}
}
if (evicted > 0) {
MGLOG_D("PipelineFactory::EvictByProgramHash: evicted %u pipelines for program hash 0x%llx",
evicted, static_cast<unsigned long long>(programHash));
}
return evicted;
}
VkPipeline PipelineFactory::CreatePipeline(const PipelineCreatePayload& payload) const {
MOBILEGL_ASSERT(payload.stages != nullptr && !payload.stages->empty(), "PipelineFactory: stages are empty");
MOBILEGL_ASSERT(payload.vertexInputState != nullptr, "PipelineFactory: vertexInputState is null");
@@ -65,6 +65,26 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VkPipeline GetOrCreatePipeline(const PipelineCreatePayload& payload);
void DestroyAll();
// Frame boundary hook: ages the pipeline cache and destroys long-unused entries
// (their command buffers retired many frames ago), mirroring
// VkRenderPassManager::OnPresent's sweep. Returns the number of pipelines
// destroyed so the caller can drop any memoized VkPipeline handle.
Uint32 OnFrameBoundary();
// Destroys every cached pipeline hashed on `renderPass`. Only safe when the
// caller guarantees GPU idleness for them - the render-pass manager calls this
// (via the renderer) for passes its own >1024-boundary-idle sweep just evicted,
// and a pipeline hashed on that handle is only ever bound by draws that also
// hit the render-pass entry. Also closes the handle-recycling hazard: a
// recycled VkRenderPass value must never serve a stale pipeline. Returns the
// number destroyed (callers invalidate memos when non-zero); linear scan is
// fine, evictions are rare.
Uint32 EvictByRenderPass(VkRenderPass renderPass);
// Destroys every cached pipeline built from the program with content hash
// `programHash`. Called from the ProgramFactory eviction path, which proves the
// same >1024-boundary idleness (the program's pipelines are only bound by draws
// that stamp its factory entry). Returns the number destroyed.
Uint32 EvictByProgramHash(HashType programHash);
// Driver quirk: suppress depth writes on accumulation-blended pipelines. Multi-pass
// depth-equality rendering (a blended prepass writes depth that later passes re-test
// with an equality-inclusive compare on the re-rasterized geometry) requires
@@ -87,12 +107,26 @@ namespace MobileGL::MG_Backend::DirectVulkan {
static Bool ShouldSuppressDepthWrite(const PipelineCreatePayload& payload);
private:
struct PipelineCacheEntry {
VkPipeline pipeline = VK_NULL_HANDLE;
// The hashed inputs the eviction paths key on: programHash ties the entry to
// its ProgramFactory entry, renderPass records the exact handle the hash
// folded in (the hash is one-way, so targeted eviction needs them verbatim).
HashType programHash = 0;
VkRenderPass renderPass = VK_NULL_HANDLE;
// Frame-boundary counter value of the last GetOrCreatePipeline hit; drives
// cache eviction (see OnFrameBoundary).
Uint64 lastUsedFrame = 0;
};
VkPipeline CreatePipeline(const PipelineCreatePayload& payload) const;
VkDevice m_device = VK_NULL_HANDLE;
const VulkanRendererConfig& m_config;
VkPipelineCache m_pipelineCache = VK_NULL_HANDLE;
UnorderedMap<HashType, VkPipeline> m_cache;
UnorderedMap<HashType, PipelineCacheEntry> m_cache;
// Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
Uint64 m_frameCounter = 0;
static inline XXH64_state_t* m_hashState = XXH64_createState();
static inline Bool s_suppressBlendedDepthWrite = false;
};
@@ -1950,11 +1950,17 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
auto it = m_cache.find(hash);
if (it != m_cache.end()) {
// Every draw/dispatch funnels through this lookup (the renderer memos only
// skip re-hashing, never the factory lookup), so an actively-used entry is
// stamped at least once per frame boundary and can never be aged out while
// any in-flight command buffer still references it.
it->second.lastUsedFrame = m_frameCounter;
return it->second;
}
auto& entry = m_cache[hash];
entry.hash = hash;
entry.lastUsedFrame = m_frameCounter;
auto& shaders = program.GetAttachedShaders();
auto& spirv = program.GetGeneratedSpirv();
Vector<Vector<Uint>> moduleSpirvs(spirv.size());
@@ -2068,4 +2074,42 @@ namespace MobileGL::MG_Backend::DirectVulkan {
return entry;
}
void ProgramFactory::OnFrameBoundary() {
++m_frameCounter;
// Sweep cadence and retire age mirror VkRenderPassManager::OnPresent: an entry
// idle for more than kRetireAgeFrames frame boundaries cannot be referenced by
// any in-flight command buffer (frames-in-flight <= MOBILEGL_MAGMA_FRAMESINFLIGHT),
// so its shader modules and layouts are destroyed immediately - no deferred-
// destroy machinery needed. Eviction is content-based, never tied to
// glDeleteProgram: the cache is content-hash-shared across GL programs, so a
// delete-driven erase could free an entry another live program still resolves.
// An evicted entry self-heals - the frontend program keeps its generated
// SPIR-V, so the next GetOrCreateProgram rebuilds it (this also covers the
// renderer's internal blit/depth-mipmap programs).
constexpr Uint64 kSweepInterval = 256;
constexpr Uint64 kRetireAgeFrames = 1024;
if ((m_frameCounter % kSweepInterval) != 0) {
return;
}
for (auto it = m_cache.begin(); it != m_cache.end();) {
if (m_frameCounter - it->second.lastUsedFrame > kRetireAgeFrames) {
const HashType hash = it->first;
const VkDescriptorSetLayout descriptorSetLayout = it->second.descriptorSetLayout;
MGLOG_D("ProgramFactory::OnFrameBoundary: evicting idle program entry hash=0x%llx",
static_cast<unsigned long long>(hash));
// erase runs ~VkProgramObject (modules/layouts destroyed); notify after
// so an observer never observes a half-destroyed entry through a lookup.
// Observers only need the handle values to purge their keyed caches.
it = m_cache.erase(it);
if (m_evictionObserver != nullptr) {
m_evictionObserver->OnProgramEvicted(hash, descriptorSetLayout);
}
} else {
++it;
}
}
}
} // namespace MobileGL::MG_Backend::DirectVulkan
@@ -88,6 +88,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// gl_FragDepth); shader-computed depth is immune to the cross-pipeline
// position-invariance quirk (see PipelineFactory::ShouldSuppressDepthWrite).
Bool fragmentReplacesDepth = false;
// Frame-boundary counter value of the last GetOrCreateProgram hit; drives
// cache eviction (see OnFrameBoundary).
Uint64 lastUsedFrame = 0;
static inline VkDevice s_device = VK_NULL_HANDLE;
@@ -124,6 +127,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
producerOutputComponentCount = other.producerOutputComponentCount;
fragmentInputComponentCount = other.fragmentInputComponentCount;
fragmentReplacesDepth = other.fragmentReplacesDepth;
lastUsedFrame = other.lastUsedFrame;
other.hash = 0;
other.descriptorSetLayout = VK_NULL_HANDLE;
other.pipelineLayout = VK_NULL_HANDLE;
@@ -135,6 +139,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
other.producerOutputComponentCount = 0;
other.fragmentInputComponentCount = 0;
other.fragmentReplacesDepth = false;
other.lastUsedFrame = 0;
}
VkProgramObject& operator=(VkProgramObject&& other) noexcept {
if (this == &other) {
@@ -170,6 +175,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
producerOutputComponentCount = other.producerOutputComponentCount;
fragmentInputComponentCount = other.fragmentInputComponentCount;
fragmentReplacesDepth = other.fragmentReplacesDepth;
lastUsedFrame = other.lastUsedFrame;
other.hash = 0;
other.descriptorSetLayout = VK_NULL_HANDLE;
other.pipelineLayout = VK_NULL_HANDLE;
@@ -181,6 +187,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
other.producerOutputComponentCount = 0;
other.fragmentInputComponentCount = 0;
other.fragmentReplacesDepth = false;
other.lastUsedFrame = 0;
return *this;
}
@@ -210,6 +217,18 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
};
// Notified when the OnFrameBoundary sweep destroys an aged-out cache entry,
// carrying the entry's content hash and the VkDescriptorSetLayout it owned.
// Dependent caches (compute pipelines, PipelineFactory entries, UniformManager's
// per-layout descriptor sets) must purge in the same step: after vkDestroy the
// layout handle value may be recycled for an unrelated layout, and the program
// hash may be re-inserted by a later rebuild of the same content.
class IEvictionObserver {
public:
virtual ~IEvictionObserver() = default;
virtual void OnProgramEvicted(HashType programHash, VkDescriptorSetLayout descriptorSetLayout) = 0;
};
explicit ProgramFactory(VkDevice device, const VulkanRendererConfig& config, Uint32 maxBindings = 16,
Bool shaderDrawParametersEnabled = false,
Bool unformattedFloatStorageImagesEnabled = false)
@@ -225,6 +244,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
const VkProgramObject& GetOrCreateProgram(
const MG_State::GLState::ProgramObject& program, CompileOptionFlags flags);
// Observer may be null (no notifications). Not owned.
void SetEvictionObserver(IEvictionObserver* observer) { m_evictionObserver = observer; }
// Frame boundary hook: ages the program cache and evicts long-unused entries
// (their command buffers retired many frames ago), mirroring
// VkRenderPassManager::OnPresent's sweep.
void OnFrameBoundary();
static VkShaderStageFlagBits ToVkStage(ShaderStage stage);
static VkFormat ConvertSpirvImageFormatToVkFormat(SpvImageFormat format);
static SamplerNumericDomain UniformTypeToSamplerNumericDomain(GLenum glType);
@@ -266,6 +292,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// shaderStorageImageReadWithoutFormat and shaderStorageImageWriteWithoutFormat.
Bool m_unformattedFloatStorageImagesEnabled = false;
mutable ProgramLookupCache m_lastLookup;
// Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
Uint64 m_frameCounter = 0;
IEvictionObserver* m_evictionObserver = nullptr;
static inline XXH64_state_t* m_hashState = XXH64_createState();
};
} // namespace MobileGL::MG_Backend::DirectVulkan
@@ -171,6 +171,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
m_programFactory = nullptr;
m_device = VK_NULL_HANDLE;
m_minDynamicOffsetAlignment = 1;
m_frameCounter = 0;
m_frameCount = 0;
m_maxBindings = 0;
m_setsPerFrame = 0;
@@ -211,6 +212,56 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
}
void UniformManager::OnDescriptorSetLayoutDestroyed(VkDescriptorSetLayout descriptorSetLayout) {
SizeT purgedSets = 0;
for (auto& frame : m_frames) {
const auto it = frame.descriptorSetCacheByLayout.find(descriptorSetLayout);
if (it != frame.descriptorSetCacheByLayout.end()) {
purgedSets += it->second.sets.size();
frame.descriptorSetCacheByLayout.erase(it);
}
}
if (purgedSets > 0) {
// The per-draw reuse memo folds the layout handle into its signature; drop
// it so a recycled handle value cannot revive a purged set mid-frame.
m_hasLastDescriptor = false;
MGLOG_D("UniformDescriptorBinder: purged %zu descriptor sets for destroyed layout", purgedSets);
}
}
void UniformManager::OnFrameBoundary() {
++m_frameCounter;
// Sweep cadence and retire age mirror VkRenderPassManager::OnPresent. Only the
// CPU-side tracking is reclaimed here: the sets' pool slots stay occupied until
// Shutdown destroys the pools (no FREE_DESCRIPTOR_SET_BIT, no mid-life pool
// reset), exactly as they would had the entry been kept. What the sweep buys is
// that an idle layout's tracking vectors stop accumulating, and that a
// destroyed-then-recycled layout handle finds no stale entry to hit.
constexpr Uint64 kSweepInterval = 256;
constexpr Uint64 kRetireAgeFrames = 1024;
if ((m_frameCounter % kSweepInterval) != 0) {
return;
}
SizeT purgedSets = 0;
for (auto& frame : m_frames) {
for (auto it = frame.descriptorSetCacheByLayout.begin();
it != frame.descriptorSetCacheByLayout.end();) {
if (m_frameCounter - it->second.lastUsedFrame > kRetireAgeFrames) {
purgedSets += it->second.sets.size();
it = frame.descriptorSetCacheByLayout.erase(it);
} else {
++it;
}
}
}
if (purgedSets > 0) {
m_hasLastDescriptor = false;
MGLOG_D("UniformDescriptorBinder::OnFrameBoundary: dropped %zu idle descriptor sets", purgedSets);
}
}
Bool UniformManager::ResolveSamplerDescriptor(VkCommandBuffer commandBuffer,
const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj,
@@ -989,6 +1040,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VkDescriptorSet& outDescriptorSet) {
auto& frame = m_frames[frameIndex];
auto& cache = frame.descriptorSetCacheByLayout[programObj.descriptorSetLayout];
// Every layout used in a frame is acquired at least once (the per-draw
// descriptor-reuse memo starts each frame invalidated and folds the layout
// into its signature), so an actively-used entry is stamped every frame.
cache.lastUsedFrame = m_frameCounter;
if (cache.cursor < cache.sets.size()) {
outDescriptorSet = cache.sets[cache.cursor++];
} else {
@@ -39,6 +39,18 @@ namespace MobileGL::MG_Backend::DirectVulkan {
void Shutdown();
void BeginFrame(Uint32 frameIndex);
// A ProgramFactory eviction just destroyed this layout: purge every frame
// slot's cached descriptor sets for it, so a recycled handle value can never
// stale-hit sets written for the dead layout's bindings. The sets themselves
// are only dropped, never freed - the frame pools are created without
// FREE_DESCRIPTOR_SET_BIT and are never reset mid-life, so their pool slots
// stay occupied until Shutdown destroys the pools wholesale.
void OnDescriptorSetLayoutDestroyed(VkDescriptorSetLayout descriptorSetLayout);
// Frame boundary hook: ages the per-layout descriptor-set caches and drops
// long-unused entries (mirroring VkRenderPassManager::OnPresent's sweep), so a
// shader-churn session's peak layout population does not pin its tracking
// vectors forever. Same pool-slot caveat as above.
void OnFrameBoundary();
Bool CollectSampledTextures(const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj,
Vector<MG_State::GLState::ITextureObject*>& outTextures);
@@ -68,6 +80,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
struct DescriptorSetCacheEntry {
Vector<VkDescriptorSet> sets;
Uint32 cursor = 0;
// Frame-boundary counter value of the last AcquireDescriptorSet hit; drives
// cache eviction (see OnFrameBoundary).
Uint64 lastUsedFrame = 0;
};
struct FrameResources {
@@ -131,6 +146,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Vector<FrameResources> m_frames;
VkDeviceSize m_minDynamicOffsetAlignment = 1;
// Monotonic frame-boundary counter (bumped in OnFrameBoundary) for
// descriptor-set cache aging.
Uint64 m_frameCounter = 0;
Uint32 m_frameCount = 0;
Uint32 m_maxBindings = 0;
Uint32 m_setsPerFrame = 0;
@@ -1194,6 +1194,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
if (m_rpFastValid && m_rpFastRenderPassHash == it->first) {
m_rpFastValid = false;
}
// Notify while the handle is still alive: pipelines hashed on it share
// the entry's >kRetireAgeFrames idleness (they are only bound by draws
// that hit this entry), so the observer may destroy them immediately.
if (m_evictionObserver != nullptr) {
m_evictionObserver->OnRenderPassDestroyed(it->second.renderPass);
}
it = m_renderPasses.erase(it);
} else {
++it;
@@ -157,11 +157,27 @@ namespace MobileGL::MG_Backend::DirectVulkan {
class VkRenderPassManager {
public:
using HashType = Uint64;
// Notified from the OnPresent sweep for each aged-out entry, BEFORE the entry
// destructor destroys its VkRenderPass: pipelines are hashed on the raw handle,
// and once destroyed the value may be recycled for an incompatible pass, so
// dependent caches must purge everything keyed on it in the same step. The
// wholesale paths (Shutdown/RecreateSwapchain) do not notify - their callers
// already drop every pipeline outright.
class IEvictionObserver {
public:
virtual ~IEvictionObserver() = default;
virtual void OnRenderPassDestroyed(VkRenderPass renderPass) = 0;
};
VkRenderPassManager(VkDevice device,
VkPhysicalDevice physicalDevice, VmaAllocator allocator, const VulkanRendererConfig& config,
VkClearManager& clearManager, VkTextureManager& textureManager, SwapchainObject& swapchainObject);
~VkRenderPassManager();
// Observer may be null (no notifications). Not owned.
void SetEvictionObserver(IEvictionObserver* observer) { m_evictionObserver = observer; }
Bool Initialize();
void Shutdown();
@@ -192,6 +208,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
UnorderedMap<Uint64, RenderPassEntry> m_renderPasses;
// Monotonic frame counter (bumped in OnPresent) for render-pass cache aging.
Uint64 m_frameCounter = 0;
IEvictionObserver* m_evictionObserver = nullptr;
// Bumped whenever a renderbuffer VkImage is (re)created; together with the texture
// manager's image epoch this invalidates the render-pass fast path on any attachment
@@ -2529,6 +2529,11 @@ void main() {
m_shaderDrawParametersFeatureEnabled,
m_unformattedFloatStorageImagesEnabled);
MOBILEGL_ASSERT(m_programFactory != nullptr, "ProgramFactory creation failed.");
// Aging evictions (render passes and program entries) must purge the dependent
// pipeline / compute-pipeline / descriptor-set caches in the same step; both
// sweeps only run from the frame-boundary seams, long after initialization.
m_renderPassManager->SetEvictionObserver(this);
m_programFactory->SetEvictionObserver(this);
m_samplerManager = MakeUnique<VkSamplerManager>();
MOBILEGL_ASSERT(m_samplerManager != nullptr, "VkSamplerManager creation failed.");
@@ -2589,6 +2594,15 @@ void main() {
DestroyDeferredDepthMipmapCleanup();
DestroyComputePipelines();
// No sweep runs during teardown, but the observers point at this renderer
// and the factories die at different times below; disconnect them first.
if (m_renderPassManager) {
m_renderPassManager->SetEvictionObserver(nullptr);
}
if (m_programFactory) {
m_programFactory->SetEvictionObserver(nullptr);
}
m_pipelineFactory.reset();
ShutdownBlitResources();
ShutdownDepthMipmapResources();
@@ -7241,6 +7255,20 @@ void main() {
if (m_renderPassManager) {
m_renderPassManager->OnPresent();
}
// Present-less loops cross frame boundaries here, so the content-addressed
// caches age on the same cadence as Present's tail. The pipeline memo can
// survive across these boundaries (no per-frame reset on this path), so it
// must drop whenever the sweep destroys anything.
if (m_programFactory) {
m_programFactory->OnFrameBoundary();
}
if (m_pipelineFactory && m_pipelineFactory->OnFrameBoundary() > 0) {
m_lastPipelineValid = false;
m_lastPipelineResult = VK_NULL_HANDLE;
}
if (m_uniformManager) {
m_uniformManager->OnFrameBoundary();
}
return true;
}
@@ -7496,6 +7524,16 @@ void main() {
MOBILEGL_ASSERT(m_imageIndexAcquired < m_swapchainObject.GetImageCount(),
"Present, acquired image index out of range");
m_renderPassManager->OnPresent();
// Age the content-addressed caches on the same frame-boundary cadence. Each
// keeps its own internal 256-sweep gate, so the per-frame cost is one counter
// increment and compare per cache; entries used by this frame's still-
// unsubmitted recording were stamped this boundary and can never age out.
m_programFactory->OnFrameBoundary();
if (m_pipelineFactory->OnFrameBoundary() > 0) {
m_lastPipelineValid = false; // an aged-out pipeline may still be memoized
m_lastPipelineResult = VK_NULL_HANDLE;
}
m_uniformManager->OnFrameBoundary();
auto& frame = m_frameContext.GetCurrent();
auto* activeRenderPass = VkRenderPassManager::GetActiveRenderPass();
if (activeRenderPass)
@@ -8528,6 +8566,43 @@ void main() {
m_computePipelines.clear();
}
void VulkanRenderer::OnRenderPassDestroyed(VkRenderPass renderPass) {
if (m_pipelineFactory == nullptr) {
return;
}
// The render-pass sweep's >1024-boundary idle guarantee covers these pipelines
// too (they are only bound by draws that hit the dying entry), so the factory
// destroys them immediately. The memo must drop as well: it can hand out a
// cached handle without touching the factory.
if (m_pipelineFactory->EvictByRenderPass(renderPass) > 0) {
m_lastPipelineValid = false;
m_lastPipelineResult = VK_NULL_HANDLE;
}
}
void VulkanRenderer::OnProgramEvicted(ProgramFactory::HashType programHash,
VkDescriptorSetLayout descriptorSetLayout) {
// Same >1024-boundary idleness as the program entry: its compute pipeline is
// only dispatched, and its graphics pipelines only bound, through paths that
// stamp the entry, so immediate destruction is GPU-safe. (The graphics memo
// never holds compute pipelines; it only needs invalidating for the factory
// eviction below.)
const auto computeIt = m_computePipelines.find(programHash);
if (computeIt != m_computePipelines.end()) {
if (computeIt->second != VK_NULL_HANDLE && m_device != VK_NULL_HANDLE) {
vkDestroyPipeline(m_device, computeIt->second, nullptr);
}
m_computePipelines.erase(computeIt);
}
if (m_pipelineFactory != nullptr && m_pipelineFactory->EvictByProgramHash(programHash) > 0) {
m_lastPipelineValid = false;
m_lastPipelineResult = VK_NULL_HANDLE;
}
if (m_uniformManager != nullptr) {
m_uniformManager->OnDescriptorSetLayoutDestroyed(descriptorSetLayout);
}
}
VkPipeline VulkanRenderer::GetOrCreateComputePipeline(const ProgramFactory::VkProgramObject& programObj) {
const auto it = m_computePipelines.find(programObj.hash);
if (it != m_computePipelines.end()) {
@@ -114,7 +114,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
};
class VulkanRenderer : public IBufferCopyCommandProvider, public FrameContext::IRecordingObserver {
class VulkanRenderer : public IBufferCopyCommandProvider,
public FrameContext::IRecordingObserver,
public VkRenderPassManager::IEvictionObserver,
public ProgramFactory::IEvictionObserver {
public:
VulkanRenderer(NativeWindowType window, const VulkanRendererConfig& cfg = {});
~VulkanRenderer();
@@ -131,6 +134,20 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// recording, before any render pass.
void OnFrameCommandRecordingBegan(VkCommandBuffer commandBuffer) override;
// VkRenderPassManager::IEvictionObserver: the render-pass aging sweep is
// destroying a VkRenderPass; evict every graphics pipeline hashed on the
// dying handle (they share its >1024-boundary idleness, so immediate
// destruction is safe) and drop the last-pipeline memo if any went.
void OnRenderPassDestroyed(VkRenderPass renderPass) override;
// ProgramFactory::IEvictionObserver: an aged-out program entry was
// destroyed; evict its compute pipeline and graphics pipelines (same
// idleness guarantee - they are only bound through draws/dispatches that
// stamp the program entry) and purge the descriptor-set cache entries
// keyed by its now-recyclable VkDescriptorSetLayout handle.
void OnProgramEvicted(ProgramFactory::HashType programHash,
VkDescriptorSetLayout descriptorSetLayout) override;
Bool SetupDraw(FrameContext::FrameData& frame, GLenum mode, Flags<DrawSetupAspect> aspects,
const DrawCmdParam& drawParams,
const IndexBufferView* pIndexBufferView = nullptr);