Crafter.Graphics/interfaces/Crafter.Graphics-ShaderVulkan.cppm

//SPDX-License-Identifier: LGPL-3.0-only
//SPDX-FileCopyrightText: Copyright (C) 2026 Catcrafts®

module;
#ifndef CRAFTER_GRAPHICS_WINDOW_DOM
#include "vulkan/vulkan.h"
#endif // !CRAFTER_GRAPHICS_WINDOW_DOM
export module Crafter.Graphics:ShaderVulkan;
#ifndef CRAFTER_GRAPHICS_WINDOW_DOM
import std;
import :Device;
import :Types;

// ─── BEGIN NVIDIA descriptor-heap AS-read workaround (issue #15 / #7) ─────
// Remove this whole block (and its call below, Device::workaroundDescriptorHeapAS,
// and the RTPass push-data) once NVIDIA ships a driver that fixes the
// VK_EXT_descriptor_heap acceleration-structure read fault.
//
// On the affected driver, reading an `accelerationStructureEXT` out of the
// descriptor heap aborts the device. The build, the heap descriptor write and
// everything else are correct (proven in #7); only the in-shader heap AS read
// is broken — buffers/images through the same heap work. Acceleration
// structures can equally be addressed by their device address, and
// OpConvertUToAccelerationStructureKHR (which reads no descriptor) sidesteps
// the faulting path entirely.
//
// glslang has no GLSL spelling for that conversion, so we rewrite the compiled
// SPIR-V at module-load time: every `OpLoad %accelStruct <heap-ptr>` becomes a
// load of the TLAS device address from a push-constant block followed by
// OpConvertUToAccelerationStructureKHR. RTPass pushes the active frame's TLAS
// address into that push constant. Shaders that never touch an acceleration
// structure (no OpTypeAccelerationStructureKHR) are left untouched.
//
// SPIR-V allows at most one push-constant variable per entry point, so we never
// add a second one: if the shader already declares a push-constant block we
// append a ulong member (the TLAS address) to the *existing* block and read
// from there; only shaders with no push constant of their own get a freshly
// synthesized single-member block. Its byte offset is the offset of that
// member, returned in PatchResult::tlasPushOffset so the caller (RTPass for the
// RT pipeline, ComputeShader::Dispatch for a compute pipeline) can feed it to
// vkCmdPushDataEXT — landing the address exactly where the rewritten load reads
// it. The offset is per-shader rather than a global: a global is clobbered by
// whichever shader was patched last and so cannot serve several shaders whose
// push-constant layouts differ.
//
// Exported so tests/PushConstantRewrite can drive Patch() over real compiled
// SPIR-V and check the result with spirv-val; nothing in the engine calls it
// from outside this file. Goes away with the rest of the workaround.
export namespace WorkaroundNvidiaAS {
    // SPIR-V numeric opcodes / enums used below.
    enum : std::uint32_t {
        OpEntryPoint = 15, OpCapability = 17,
        OpTypeInt = 21, OpTypeFloat = 22, OpTypeVector = 23, OpTypeMatrix = 24,
        OpTypeArray = 28, OpTypeStruct = 30, OpTypePointer = 32,
        OpConstant = 43, OpVariable = 59, OpLoad = 61, OpAccessChain = 65,
        OpDecorate = 71, OpMemberDecorate = 72,
        OpConvertUToAccelerationStructureKHR = 4447,
        OpTypeAccelerationStructureKHR = 5341,
        CapabilityInt64 = 11,
        StorageClassPushConstant = 9,
        DecorationBlock = 2, DecorationMatrixStride = 7,
        DecorationArrayStride = 6, DecorationOffset = 35,
    };

    inline bool IsAnnotation(std::uint32_t op) {
        // OpDecorate/OpMemberDecorate/OpDecorationGroup/OpGroupDecorate/
        // OpGroupMemberDecorate/OpDecorateId/OpDecorate(Member)String.
        return op == 71 || op == 72 || op == 73 || op == 74 || op == 75
            || op == 332 || op == 5632 || op == 5633;
    }

    using Instr = std::vector<std::uint32_t>;

    inline std::uint32_t AlignUp(std::uint32_t v, std::uint32_t a) {
        return (v + a - 1u) & ~(a - 1u);
    }

    // Outcome of patching one shader module. `patched` is true only when the
    // shader read an acceleration structure and was rewritten; `tlasPushOffset`
    // is then the byte offset of the TLAS-address member in the (possibly
    // pre-existing) push-constant block the caller must write.
    struct PatchResult {
        bool patched = false;
        std::uint32_t tlasPushOffset = 0;
    };

    inline PatchResult Patch(std::vector<std::uint32_t>& words) {
        if (words.size() < 5) return {}; // not a SPIR-V module we understand.

        // Split header (5 words) from the instruction stream.
        std::uint32_t bound = words[3];
        std::vector<Instr> instrs;
        for (std::size_t i = 5; i < words.size();) {
            std::uint32_t len = words[i] >> 16;
            if (len == 0 || i + len > words.size()) return {}; // malformed — bail.
            instrs.emplace_back(words.begin() + i, words.begin() + i + len);
            i += len;
        }

        // ── Scan for the AS type, reusable int/long types+constants, any
        //    existing push-constant block, the type/decoration/constant tables
        //    needed to size that block, and the section boundaries to insert into.
        std::uint32_t asTypeId = 0, ulongTypeId = 0, uintTypeId = 0, uintZeroId = 0;
        std::uint32_t existingPcVarId = 0, existingPcStructId = 0, existingPtrUlongId = 0;
        std::size_t lastCapIdx = 0, lastAnnotIdx = 0, firstFuncIdx = instrs.size();
        std::size_t entryIdx = instrs.size();
        std::map<std::uint32_t, const Instr*> typeInstr;          // type-result-id → defining instr
        std::map<std::uint32_t, std::uint32_t> constU32;          // OpConstant id → 32-bit value
        std::map<std::uint32_t, std::uint32_t> uintConstByValue;  // uint value → OpConstant id
        std::map<std::uint32_t, std::uint32_t> arrayStride;       // array type id → ArrayStride
        std::map<std::uint64_t, std::uint32_t> memberOffset;      // (struct<<32|idx) → Offset
        std::map<std::uint64_t, std::uint32_t> memberMatStride;   // (struct<<32|idx) → MatrixStride
        std::map<std::uint32_t, std::uint32_t> ptrPointee;        // pointer type id → pointee type id
        for (std::size_t k = 0; k < instrs.size(); ++k) {
            const Instr& in = instrs[k];
            std::uint32_t op = in[0] & 0xFFFFu;
            switch (op) {
                case OpTypeAccelerationStructureKHR: asTypeId = in[1]; typeInstr[in[1]] = &in; break;
                case OpTypeInt:
                    if (in[2] == 64 && in[3] == 0) ulongTypeId = in[1];
                    else if (in[2] == 32 && in[3] == 0) uintTypeId = in[1];
                    typeInstr[in[1]] = &in;
                    break;
                case OpTypeFloat: case OpTypeVector: case OpTypeMatrix:
                case OpTypeArray:  case OpTypeStruct:
                    typeInstr[in[1]] = &in;
                    break;
                case OpTypePointer:
                    typeInstr[in[1]] = &in; ptrPointee[in[1]] = in[3];
                    if (in[2] == StorageClassPushConstant && in[3] == ulongTypeId)
                        existingPtrUlongId = in[1];
                    break;
                case OpConstant:
                    if (in.size() >= 4) constU32[in[2]] = in[3];
                    if (uintTypeId && in[1] == uintTypeId && in.size() >= 4) {
                        uintConstByValue.emplace(in[3], in[2]);
                        if (in[3] == 0) uintZeroId = in[2];
                    }
                    break;
                case OpVariable:
                    if (in[3] == StorageClassPushConstant) {
                        existingPcVarId = in[2];
                        existingPcStructId = ptrPointee.count(in[1]) ? ptrPointee[in[1]] : 0;
                    }
                    break;
                case OpDecorate:
                    if (in.size() >= 4 && in[2] == DecorationArrayStride) arrayStride[in[1]] = in[3];
                    break;
                case OpMemberDecorate: {
                    std::uint64_t key = (static_cast<std::uint64_t>(in[1]) << 32) | in[2];
                    if (in.size() >= 5 && in[3] == DecorationOffset)      memberOffset[key]   = in[4];
                    if (in.size() >= 5 && in[3] == DecorationMatrixStride) memberMatStride[key] = in[4];
                    break;
                }
                case OpCapability: lastCapIdx = k; break;
                case OpEntryPoint: if (entryIdx == instrs.size()) entryIdx = k; break;
                default: break;
            }
            if (IsAnnotation(op)) lastAnnotIdx = k;
            if (op == 54 /*OpFunction*/ && firstFuncIdx == instrs.size()) firstFuncIdx = k;
        }

        if (asTypeId == 0) return {}; // shader never reads an acceleration structure.

        // Set on whichever path runs below; returned to the caller.
        std::uint32_t tlasPushOffset = 0;

        auto newId = [&] { return bound++; };
        auto mk = [](std::initializer_list<std::uint32_t> ops) {
            Instr in(ops);
            in[0] = static_cast<std::uint32_t>(in.size() << 16) | (in[0] & 0xFFFFu);
            return in;
        };

        // Byte footprint of a type, honouring the explicit Array/Matrix strides
        // glslang emits so the result is correct under both scalar and std140
        // block layout. Used only to find where an existing push block ends.
        std::function<std::uint32_t(std::uint32_t)> footprint =
            [&](std::uint32_t tid) -> std::uint32_t {
            auto it = typeInstr.find(tid);
            if (it == typeInstr.end()) return 0;
            const Instr& t = *it->second;
            switch (t[0] & 0xFFFFu) {
                case OpTypeInt: case OpTypeFloat: return t[2] / 8u;
                case OpTypeVector: return t[3] * footprint(t[2]);
                case OpTypeMatrix: return t[3] * footprint(t[2]); // cols × column-vec
                case OpTypeArray: {
                    std::uint32_t len = constU32.count(t[3]) ? constU32[t[3]] : 0;
                    std::uint32_t stride = arrayStride.count(tid) ? arrayStride[tid]
                                                                  : footprint(t[2]);
                    return len * stride;
                }
                case OpTypeStruct: {
                    std::uint32_t end = 0;
                    for (std::size_t m = 2; m < t.size(); ++m) {
                        std::uint32_t idx = static_cast<std::uint32_t>(m - 2);
                        std::uint64_t key = (static_cast<std::uint64_t>(t[1]) << 32) | idx;
                        std::uint32_t off = memberOffset.count(key) ? memberOffset[key] : 0;
                        std::uint32_t sz;
                        auto mt = typeInstr.find(t[m]);
                        if (mt != typeInstr.end() && (mt->second->at(0) & 0xFFFFu) == OpTypeMatrix
                            && memberMatStride.count(key))
                            sz = memberMatStride[key] * (*mt->second)[3];
                        else
                            sz = footprint(t[m]);
                        end = std::max(end, off + sz);
                    }
                    return end;
                }
                case OpTypePointer: return 8;
                default: return 0;
            }
        };

        bool merge = existingPcVarId != 0 && existingPcStructId != 0
                  && typeInstr.count(existingPcStructId)
                  && (typeInstr[existingPcStructId]->at(0) & 0xFFFFu) == OpTypeStruct;

        // ── Synthesize/ensure the int/long types and constants we need, reusing
        //    any the module already defines (SPIR-V forbids duplicate type defs).
        std::vector<Instr> typeDefs;
        if (uintTypeId == 0) { uintTypeId = newId(); typeDefs.push_back(mk({OpTypeInt, uintTypeId, 32, 0})); }
        if (ulongTypeId == 0) { ulongTypeId = newId(); typeDefs.push_back(mk({OpTypeInt, ulongTypeId, 64, 0})); }

        std::uint32_t pcVarId, ptrPushUlongId, memberIdxConstId, memberIdx;
        std::vector<Instr> decorations;

        if (merge) {
            // Append a ulong member to the user's existing block; read from it.
            pcVarId = existingPcVarId;
            const Instr* structInstr = typeInstr[existingPcStructId];
            memberIdx = static_cast<std::uint32_t>(structInstr->size() - 2);
            tlasPushOffset = AlignUp(footprint(existingPcStructId), 8);

            ptrPushUlongId = existingPtrUlongId;
            if (ptrPushUlongId == 0) {
                ptrPushUlongId = newId();
                typeDefs.push_back(mk({OpTypePointer, ptrPushUlongId, StorageClassPushConstant, ulongTypeId}));
            }
            // Member index constant for the access chain — reuse an existing
            // uint constant of the right value, else mint one (must be an
            // integer constant, so only uint-typed ones qualify for reuse).
            auto found = uintConstByValue.find(memberIdx);
            if (found != uintConstByValue.end()) {
                memberIdxConstId = found->second;
            } else {
                memberIdxConstId = newId();
                typeDefs.push_back(mk({OpConstant, uintTypeId, memberIdxConstId, memberIdx}));
            }
            decorations.push_back(mk({OpMemberDecorate, existingPcStructId, memberIdx, DecorationOffset, tlasPushOffset}));
        } else {
            // No user push constant — synthesize a fresh single-member block.
            if (uintZeroId == 0) { uintZeroId = newId(); typeDefs.push_back(mk({OpConstant, uintTypeId, uintZeroId, 0})); }
            std::uint32_t pcStructId = newId();
            std::uint32_t ptrPushStructId = newId();
            ptrPushUlongId = newId();
            pcVarId = newId();
            typeDefs.push_back(mk({OpTypeStruct, pcStructId, ulongTypeId}));
            typeDefs.push_back(mk({OpTypePointer, ptrPushStructId, StorageClassPushConstant, pcStructId}));
            typeDefs.push_back(mk({OpTypePointer, ptrPushUlongId, StorageClassPushConstant, ulongTypeId}));
            typeDefs.push_back(mk({OpVariable, ptrPushStructId, pcVarId, StorageClassPushConstant}));
            decorations.push_back(mk({OpMemberDecorate, pcStructId, 0, DecorationOffset, 0}));
            decorations.push_back(mk({OpDecorate, pcStructId, DecorationBlock}));
            memberIdxConstId = uintZeroId;
            tlasPushOffset = 0;
        }

        // ── Rewrite each `OpLoad %asType <ptr>` into address-load + convert, and
        //    (when merging) append the ulong member to the existing struct type.
        std::vector<Instr> rebuilt;
        rebuilt.reserve(instrs.size() + 8);
        for (Instr in : instrs) {
            std::uint32_t op = in[0] & 0xFFFFu;
            if (op == OpLoad && in[1] == asTypeId) {
                std::uint32_t resultId = in[2];
                std::uint32_t chainId = newId();
                std::uint32_t addrId = newId();
                rebuilt.push_back(mk({OpAccessChain, ptrPushUlongId, chainId, pcVarId, memberIdxConstId}));
                rebuilt.push_back(mk({OpLoad, ulongTypeId, addrId, chainId}));
                rebuilt.push_back(mk({OpConvertUToAccelerationStructureKHR, asTypeId, resultId, addrId}));
            } else {
                if (merge && op == OpTypeStruct && in[1] == existingPcStructId) {
                    in.push_back(ulongTypeId);
                    in[0] = static_cast<std::uint32_t>(in.size() << 16) | OpTypeStruct;
                }
                rebuilt.push_back(std::move(in));
            }
        }
        instrs.swap(rebuilt);

        // Recompute structural anchors (the rewrite above shifted indices).
        lastCapIdx = 0; lastAnnotIdx = 0; firstFuncIdx = instrs.size(); entryIdx = instrs.size();
        std::size_t structIdx = instrs.size();
        for (std::size_t k = 0; k < instrs.size(); ++k) {
            std::uint32_t op = instrs[k][0] & 0xFFFFu;
            if (op == OpCapability) lastCapIdx = k;
            if (op == OpEntryPoint && entryIdx == instrs.size()) entryIdx = k;
            if (IsAnnotation(op)) lastAnnotIdx = k;
            if (op == 54 && firstFuncIdx == instrs.size()) firstFuncIdx = k;
            if (merge && op == OpTypeStruct && instrs[k][1] == existingPcStructId) structIdx = k;
        }

        // The newly-defined types (notably ulong) must precede every use. When
        // merging, the user's struct — now carrying the appended ulong member —
        // already sits in the type section, so the defs go in just before it;
        // for a fresh block the whole bundle can go at the end of the type
        // section (right before the first function).
        std::size_t typeDefsIdx = (merge && structIdx != instrs.size()) ? structIdx : firstFuncIdx;

        // A freshly synthesized push-constant variable must join the entry
        // point's interface list (required for SPIR-V ≥ 1.4 — raygen is 1.4).
        // A merged-into variable is already used, so it is already listed.
        if (!merge && entryIdx != instrs.size() && words[1] >= 0x00010400u) {
            instrs[entryIdx].push_back(pcVarId);
            instrs[entryIdx][0] = static_cast<std::uint32_t>(instrs[entryIdx].size() << 16)
                                  | OpEntryPoint;
        }

        // Insert highest-index-first so earlier anchors stay valid (typeDefsIdx
        // ≥ lastAnnotIdx+1 ≥ lastCapIdx+1 in both the merge and synthesize cases).
        instrs.insert(instrs.begin() + typeDefsIdx, typeDefs.begin(), typeDefs.end());
        instrs.insert(instrs.begin() + lastAnnotIdx + 1, decorations.begin(), decorations.end());
        instrs.insert(instrs.begin() + lastCapIdx + 1, mk({OpCapability, CapabilityInt64}));

        // ── Reassemble: header (with updated bound) + instruction stream.
        std::vector<std::uint32_t> out(words.begin(), words.begin() + 5);
        out[3] = bound;
        for (const Instr& in : instrs) out.insert(out.end(), in.begin(), in.end());
        words.swap(out);

        return {true, tlasPushOffset};
    }
}
// ─── END NVIDIA descriptor-heap AS-read workaround ────────────────────────

export namespace Crafter {
    class VulkanShader {
        public:
        std::vector<VkSpecializationMapEntry> specilizations;
        VkSpecializationInfo* specilizationInfo;
        VkShaderStageFlagBits stage;
        std::string entrypoint;
        VkShaderModule shader;
        // NVIDIA descriptor-heap AS-read workaround (issue #15 / #7): set when
        // this module read an acceleration structure and was rewritten to fetch
        // the TLAS device address from a push constant. `tlasPushOffset` is the
        // byte offset of that member, which whoever records the dispatch
        // (RTPass / ComputeShader) must write with vkCmdPushDataEXT. Per-shader
        // rather than a global because each shader's push-constant layout — and
        // therefore the offset — can differ. Both false/0 on every other driver.
        bool patchedAS = false;
        std::uint32_t tlasPushOffset = 0;
        VulkanShader(const std::filesystem::path& path, std::string entrypoint, VkShaderStageFlagBits stage, VkSpecializationInfo* specilizationInfo) : stage(stage), entrypoint(entrypoint), specilizationInfo(specilizationInfo) {
            // A ray tracing stage is the first thing every RT setup creates.
            // Stop here on a device without ray tracing: its shaders are
            // descriptor-heap SPIR-V, which must not reach a driver that never
            // enabled the heap or untyped pointers.
            constexpr VkShaderStageFlags rayTracingStages =
                VK_SHADER_STAGE_RAYGEN_BIT_KHR | VK_SHADER_STAGE_ANY_HIT_BIT_KHR
              | VK_SHADER_STAGE_CLOSEST_HIT_BIT_KHR | VK_SHADER_STAGE_MISS_BIT_KHR
              | VK_SHADER_STAGE_INTERSECTION_BIT_KHR | VK_SHADER_STAGE_CALLABLE_BIT_KHR;
            if ((stage & rayTracingStages) != 0) {
                Device::RequireRayTracing();
            }
            std::ifstream file(path, std::ios::binary);
            if (!file) {
                std::cerr << "Error: Could not open file " << path << std::endl;
            }
    
            // Move to the end of the file to determine its size
            file.seekg(0, std::ios::end);
            std::streamsize size = file.tellg();
            file.seekg(0, std::ios::beg);
    
            std::vector<std::uint32_t> spirv(size / sizeof(std::uint32_t));
    
            // Read the data into the vector
            if (!file.read(reinterpret_cast<char*>(spirv.data()), size)) {
                std::cerr << "Error: Could not read data from file" << std::endl;
            }
    
            file.close();

            // NVIDIA descriptor-heap AS-read workaround (issue #15 / #7).
            // No-op on every other driver and on shaders that don't read an
            // acceleration structure. Remove with the rest of the workaround
            // once a fixed NVIDIA driver ships.
            if (Device::workaroundDescriptorHeapAS) {
                WorkaroundNvidiaAS::PatchResult patch = WorkaroundNvidiaAS::Patch(spirv);
                patchedAS = patch.patched;
                tlasPushOffset = patch.tlasPushOffset;
            }

            VkShaderModuleCreateInfo module_info{VK_STRUCTURE_TYPE_SHADER_MODULE_CREATE_INFO};
            module_info.codeSize = spirv.size() * sizeof(uint32_t);
            module_info.pCode    = spirv.data();
        
            Device::CheckVkResult(vkCreateShaderModule(Device::device, &module_info, nullptr, &shader));
        }
    };
}
#endif // !CRAFTER_GRAPHICS_WINDOW_DOM