[Fix, Test] (MG_Backend/DirectVulkan): never bind or cache a null pipeline, and name the modules a failed vkCreateGraphicsPipelines rejected

MobileGL/MG_Backend/DirectVulkan/Renderer/PipelineFactory.cpp

@@ -252,6 +252,19 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
 
         VkPipeline pipeline = CreatePipeline(payload);
+        // A failed creation must never be memoized. Caching VK_NULL_HANDLE served the null back for
+        // the rest of the process, so one transient driver rejection turned every later draw with
+        // the same state into a vkCmdBindPipeline(VK_NULL_HANDLE) - the SIGSEGV behind 9 of the 15
+        // CTS process deaths. Retrying costs one failed vkCreateGraphicsPipelines per draw, which
+        // is the correct price for a broken pipeline and is bounded by the draw itself being
+        // skipped.
+        if (pipeline == VK_NULL_HANDLE) {
+            MGLOG_I("PipelineFactory::GetOrCreatePipeline: creation failed for hash=0x%llx "
+                    "programHash=0x%llx; not caching the failure",
+                    static_cast<unsigned long long>(hash),
+                    static_cast<unsigned long long>(payload.programHash));
+            return VK_NULL_HANDLE;
+        }
         m_cache.emplace(hash, PipelineCacheEntry{pipeline, payload.programHash, payload.renderPass,
                                                  m_frameCounter});
         return pipeline;
@@ -507,6 +520,31 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             MGLOG_F("PipelineFactory::CreatePipeline vertex input: bindingCount=%u attributeCount=%u",
                     payload.vertexInputState->vertexBindingDescriptionCount,
                     payload.vertexInputState->vertexAttributeDescriptionCount);
+            // The driver's own answer is VK_ERROR_UNKNOWN, i.e. no information at all, so the only
+            // way to work out WHICH shader it choked on (the open sampler-array-in-struct
+            // investigation) is to name the modules. MGLOG_I, not _D/_E: this must survive in the
+            // INFO-level builds that CTS actually runs against.
+            if (payload.stageSpirvDigests) {
+                for (SizeT i = 0; i < payload.stageSpirvDigests->size(); ++i) {
+                    const auto& digest = (*payload.stageSpirvDigests)[i];
+                    MGLOG_I("PipelineFactory::CreatePipeline spirv[%zu]: stage=0x%x words=%u bytes=%zu "
+                            "hash=0x%llx",
+                            i, digest.stage, digest.wordCount,
+                            static_cast<SizeT>(digest.wordCount) * sizeof(Uint32),
+                            static_cast<unsigned long long>(digest.hash));
+                }
+            } else {
+                MGLOG_I("PipelineFactory::CreatePipeline: no SPIR-V digests attached to the payload");
+            }
+            if (payload.stages) {
+                for (SizeT i = 0; i < payload.stages->size(); ++i) {
+                    const auto& stage = (*payload.stages)[i];
+                    MGLOG_I("PipelineFactory::CreatePipeline stage[%zu]: stage=0x%x module=%p entry=%s "
+                            "specialization=%d",
+                            i, static_cast<Uint32>(stage.stage), static_cast<const void*>(stage.module),
+                            stage.pName ? stage.pName : "(null)", stage.pSpecializationInfo ? 1 : 0);
+                }
+            }
             for (Uint32 i = 0; i < payload.colorAttachmentCount; ++i) {
                 const auto& attachment = payload.colorBlendAttachments[i];
                 MGLOG_F("PipelineFactory::CreatePipeline colorAttachment[%u]: blend=%d colorWriteMask=0x%x srcColor=%d dstColor=%d colorOp=%d srcAlpha=%d dstAlpha=%d alphaOp=%d",

MobileGL/MG_Backend/DirectVulkan/Renderer/PipelineFactory.h

@@ -14,6 +14,16 @@
 #include <Includes.h>
 
 namespace MobileGL::MG_Backend::DirectVulkan {
+    // Enough of a fingerprint to identify the exact module the driver rejected without keeping the
+    // SPIR-V alive for every program in the cache: a driver that answers VK_ERROR_UNKNOWN tells us
+    // nothing, so the log has to carry the shader's identity itself. Diagnostic only - never part
+    // of any pipeline or program hash.
+    struct ShaderStageSpirvDigest {
+        Uint32 stage = 0; // VkShaderStageFlagBits
+        Uint32 wordCount = 0;
+        Uint64 hash = 0;
+    };
+
     class PipelineFactory {
     public:
         using HashType = Uint64;
@@ -62,6 +72,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             Array<VkPipelineColorBlendAttachmentState, kMaxColorAttachments> colorBlendAttachments{};
             const Vector<VkPipelineShaderStageCreateInfo>* stages = nullptr;
             const VkPipelineVertexInputStateCreateInfo* vertexInputState = nullptr;
+            // Diagnostic only; may be null. Read solely from the pipeline-creation failure path.
+            const Vector<ShaderStageSpirvDigest>* stageSpirvDigests = nullptr;
         };
 
         explicit PipelineFactory(VkDevice device, const VulkanRendererConfig& config);

MobileGL/MG_Backend/DirectVulkan/Renderer/ProgramFactory.cpp

@@ -2568,6 +2568,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
             entry.modules.push_back(module);
             entry.stages.push_back(stage);
+            entry.stageSpirvDigests.push_back(ShaderStageSpirvDigest{
+                static_cast<Uint32>(stage.stage), static_cast<Uint32>(moduleSpv.size()),
+                XXH64(moduleSpv.data(), moduleSpv.size() * sizeof(Uint), 0)});
         }
 
         // Reflect and create layout as part of the program object

MobileGL/MG_Backend/DirectVulkan/Renderer/ProgramFactory.h

@@ -9,6 +9,7 @@
 #pragma once
 
 #include "../VkIncludes.h"
+#include "PipelineFactory.h"
 #include "MG_State/GLState/ProgramState/ProgramObject.h"
 #include "MG_State/GLState/ProgramState/ShaderObject.h"
 #include "MG_State/GLState/TextureState/TextureEnum.h"
@@ -62,6 +63,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             HashType hash = 0;
             Vector<VkPipelineShaderStageCreateInfo> stages;
             Vector<VkShaderModule> modules;
+            // Parallel to stages; identifies the exact module bytes handed to the driver when a
+            // pipeline creation fails. Sixteen bytes per stage instead of keeping the SPIR-V.
+            Vector<ShaderStageSpirvDigest> stageSpirvDigests;
 
             // Layout data (previously in separate VkProgramLayout)
             VkDescriptorSetLayout descriptorSetLayout = VK_NULL_HANDLE;

MobileGL/MG_Backend/DirectVulkan/Renderer/VulkanRenderer.cpp

@@ -4049,7 +4049,8 @@ void main() {
             .depthWriteEnable = false,
             .depthCompareOp = VK_COMPARE_OP_ALWAYS,
             .stages = &programObj.stages,
-            .vertexInputState = &kEmptyVertexInputState
+            .vertexInputState = &kEmptyVertexInputState,
+            .stageSpirvDigests = &programObj.stageSpirvDigests
         };
         static constexpr VkColorComponentFlags kColorWriteMask =
             VK_COLOR_COMPONENT_R_BIT | VK_COLOR_COMPONENT_G_BIT |
@@ -4727,7 +4728,8 @@ void main() {
             .backStencilCompareOp = MG_Util::ConvertDepthTestFuncToVkEnum(backStencil.Func),
             .fragmentReplacesDepth = programObj.fragmentReplacesDepth,
             .stages = &programObj.stages,
-            .vertexInputState = pipelineVertexInputState
+            .vertexInputState = pipelineVertexInputState,
+            .stageSpirvDigests = &programObj.stageSpirvDigests
         };
         if (!payload.stencilTestEnable) {
             payload.frontStencilFailOp = VK_STENCIL_OP_KEEP;
@@ -5911,6 +5913,17 @@ void main() {
         }
 
         auto pipeline = GetOrCreatePipeline(mode, program, programObj, transformFlags, vao, *renderPassEntry);
+        // GetOrCreatePipeline documents a VK_NULL_HANDLE return (empty stages, or a driver that
+        // rejected vkCreateGraphicsPipelines). Binding it dereferences null inside the driver -
+        // 9 of the 15 CTS process deaths were exactly this vkCmdBindPipeline. A draw that has no
+        // pipeline is a skipped draw, which is what every other failure below already does.
+        // MGLOG_I so the skip is visible in the INFO builds CTS runs against.
+        if (pipeline == VK_NULL_HANDLE) {
+            MGLOG_I("SetupDraw skipped: no graphics pipeline for program=%u (creation failed or the "
+                    "program has no shader stages)",
+                    program.GetExternalIndex());
+            return false;
+        }
         activeRenderPass = VkRenderPassManager::GetActiveRenderPass();
 
         // Begin render pass, and handle clear