fix(agc): accept bound copies of a registered shader header that differ only in user_data

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

core/libs/prx/libSceAgcDriver/Execution/src/Driver/Shaders/ShaderRegistry.cpp

@@ -12,6 +12,7 @@
 #include "CompiledVariant.hpp"
 #include "Optimization/ResourceProgram.hpp"
 #include <cstdio>
+#include <cstddef>
 #include <cstdlib>
 #include <cstring>
 #include <list>
@@ -161,6 +162,18 @@ void ShaderPreparationTransaction::Commit() {
     committed = true;
 }
 
+bool SameHeader(const ShaderSnapshot& snapshot, const Shader* shader) {
+    if (snapshot.headerAddress == reinterpret_cast<std::uintptr_t>(shader)) return true;
+    if (snapshot.header.size() < sizeof(Shader)) return false;
+    GuestMemory::CheckRange(shader, sizeof(Shader), 1);
+    Shader used;
+    Shader registered;
+    std::memcpy(&used, static_cast<const void*>(shader), sizeof(Shader));
+    std::memcpy(&registered, snapshot.header.data(), sizeof(Shader));
+    used.user_data = registered.user_data;
+    return std::memcmp(&used, &registered, offsetof(Shader, num_sh_registers) + sizeof(Shader::num_sh_registers)) == 0;
+}
+
 void PublishRegisteredShader(std::shared_ptr<ShaderRegistry>& registry, const std::shared_ptr<const ShaderSnapshot>& snapshot) {
     ShaderPreparationTransaction transaction;
     if (registry != nullptr) {
@@ -514,7 +527,7 @@ void Driver::ResolveGraphicsStagesAbi(std::span<const Shader* const> stages, std
             require(registry != nullptr && registry->contains(address), "graphics ABI refers to an unregistered shader");
             if (owner == nullptr) owner = registry->at(address);
             const auto& snapshot = *registry->at(address);
-            require(snapshot.headerAddress == reinterpret_cast<std::uintptr_t>(shader), "graphics ABI refers to a replaced shader header");
+            require(SameHeader(snapshot, shader), "graphics ABI refers to a replaced shader header");
             require(snapshot.registeredState != nullptr, "registered shader state is missing");
             const auto& registered = *snapshot.registeredState;
             for (const auto& [offset, value] : registered.shader) state.shader.insert_or_assign(offset, value);
@@ -579,7 +592,7 @@ void Driver::ResolveShaderAbi(const Shader* shader, std::span<const ShaderRegist
         const auto address = reinterpret_cast<std::uintptr_t>(const_cast<const void*>(shader->code));
         require(shaders != nullptr && shaders->contains(address), "static ABI refers to an unregistered shader");
         snapshot = shaders->at(address);
-        require(snapshot->headerAddress == reinterpret_cast<std::uintptr_t>(shader), "static ABI refers to a replaced shader header");
+        require(SameHeader(*snapshot, shader), "static ABI refers to a replaced shader header");
     }
     require(snapshot->registeredState != nullptr, "registered shader state is missing");
     QueueState state{};
@@ -641,7 +654,7 @@ void Driver::ResolveGraphicsAbi(const Shader* vertex, const Shader* pixel, std::
             const auto address = reinterpret_cast<std::uintptr_t>(const_cast<const void*>(shader->code));
             require(shaders != nullptr && shaders->contains(address), "rectangle ABI refers to an unregistered shader");
             const auto snapshot = shaders->at(address);
-            require(snapshot->headerAddress == reinterpret_cast<std::uintptr_t>(shader), "rectangle ABI refers to a replaced shader header");
+            require(SameHeader(*snapshot, shader), "rectangle ABI refers to a replaced shader header");
             return snapshot;
         };
         front = lookup(vertex);

core/libs/prx/libSceAgcDriver/tests/execution/PreparedShaders.cpp

@@ -7,6 +7,8 @@
 #include <spirv/unified1/spirv.hpp>
 #include <algorithm>
 #include <array>
+#include <cstddef>
+#include <cstring>
 #include <iostream>
 #include <stdexcept>
 #include <string>
@@ -297,6 +299,15 @@ void Registration(bool indirect) {
         }));
     }
     for (auto& registration : registrations) registration.get();
+    Shader copy = header.shader;
+    copy.user_data = reinterpret_cast<ShaderUserData*>(&copy);
+    AgcDriverResolveShaderAbi_nid_postfix(&copy, {}, {});
+    alignas(Shader) std::array<std::byte, sizeof(Shader)> padded{};
+    std::memcpy(padded.data(), &copy, sizeof(Shader));
+    padded.back() = std::byte{0x7d};
+    AgcDriverResolveShaderAbi_nid_postfix(reinterpret_cast<Shader*>(padded.data()), {}, {});
+    copy.target ^= 1u;
+    ExpectFailure([&] { AgcDriverResolveShaderAbi_nid_postfix(&copy, {}, {}); }, "replaced shader header");
     header.registers[1].value |= 0x100u;
     ExpectFailure([&] { AgcDriverRegisterShader_nid_postfix(&header.shader); }, "invalid registered program address");
     header.registers[1].value &= 0xffu;

docs/dev/TechnicalDebt.md

@@ -245,6 +245,7 @@ Throughout the project, every function at every stage either **does exactly what
 - [sceAgcDcbSetZPassPredicationEnableGetSize, sceAgcDcbSetPredicationDisableGetSize, sceAgcDcbSetBoolPredicationEnableGetSize](../../core/libs/prx/libSceAgc/DcbState/src/Predication.cpp) (libSceAgc) - the builders are inline in the SDK and not exported; the size is assumed to be that of the SET_PREDICATION packet `sceAgcDcbSetPredication` writes (16 bytes)
 - [Resource registration](../../core/libs/prx/libSceAgcDriver/Resource/src/Registration.cpp) (libSceAgcDriver) - registration always fails with `RESOURCE_REGISTRATION_UNAVAILABLE`, so the owner and resource queries, `sceAgcDriverSetResourceUserData`, `sceAgcDriverFindResourcesPublic` and `sceAgcDriverUnregisterAllResourcesForOwner` return the same error without reading their arguments. Their parameter lists follow the libSceGnmDriver counterparts and are unverified. `sceAgcDriverGetResourceRegistrationMaxNameLength` writes 0xfc and returns 0, as [prosper](https://github.com/mattias800/prosper) does from a title's registration configuration; the `uint32_t*` parameter matches the SDK wrapper `sce::Agc::ResourceRegistration::getMaxNameLength(unsigned int*)`. sharpemu writes 256 and KytyPS5 returns `RESOURCE_REGISTRATION_UNAVAILABLE`, so the value is unverified; a null output throws
 - [Shader registration](../../core/libs/prx/libSceAgcDriver/Execution/src/Driver/Shaders/ShaderRegistry.cpp) (libSceAgcDriver) - a shader header is accepted at any address: PPSA26344 passes headers 4 and 1 bytes past an 8-byte boundary; whether the console refuses an alignment is unknown
+- [Shader header copies](../../core/libs/prx/libSceAgcDriver/Execution/src/Driver/Shaders/ShaderRegistry.cpp) (libSceAgcDriver) - a header bound for a draw or dispatch at another address than the registered one is accepted when its fixed fields match the registered header except `user_data`; the registered header's metadata is used. PPSA21567 binds such a copy of a vertex shader header with `user_data` set to null. Whether the console reads the copy's `user_data` is unknown
 - [sceNgs2VoiceControl sampler filter](../../core/libs/prx/libSceNgs2.native/src/Voice.cpp) (libSceNgs2.native) - param `0x1000000a`, its layout and meaning follow KytyPS5 only: location 1 type 1 is an RBJ low-pass biquad at the system sample rate after resampling, scaled by `level`, a set `channel_mask` bit bypasses that channel, type 0 turns the filter off. Other locations and types throw. The voice keeps playing a filter tail after its last block until the history is zero, with outputs below 1e-20 flushed to zero (a KytyPS5 choice); the console's tail length is unknown
 - [sceNgs2PanInit / sceNgs2PanGetVolumeMatrix](../../core/libs/prx/libSceNgs2.native/src/Pan.cpp) (libSceNgs2.native) - follow the PS4 firmware 11.00 `libSceNgs2.sprx`, read and checked against its output for 2, 4, 5 and 7 speakers into 1, 2, 6 and 8 channels; not yet confirmed on the PS5 library. Speakers are taken in the order L R, L R Ls Rs, L R C Ls Rs or L R C Ls Rs Lb Rb and kept in a fixed circular order, not sorted; without angles the defaults are 90/270, 40/110/250/320, 0/40/110/250/320 and 0/40/110/150/210/250/320 degrees. As in that library, defaults converted to radians keep the wrap-around entry in degrees, so angles past the last speaker pan almost fully to it. Error codes are not known for the PS5, so invalid arguments throw, including a speaker angle equal to the unit angle, on which that library loops forever. Angles so large that adding or subtracting a turn leaves them unchanged throw for the same reason
 - [sceRtcGetDosTime, sceRtcSetDosTime](../../core/libs/prx/libSceRtc/Export.cpp) (libSceRtc) - bit layout from shadPS4 (PS4, the standard FAT date/time). A year outside 1980-2107 makes `GetDosTime` return `INVALID_YEAR` after writing 0 for an earlier one and `0xff9fbf7d` (2107-12-31 23:59:58, the largest encodable time) for a later one, and `SetDosTime` decodes the year as the unsigned 7-bit FAT field (1980-2107) without validating the fields, as the disassembly-derived [fpPS4](https://github.com/red-prig/fpPS4) reimplementation of the PS4 library does; not confirmed on a PS5 title, and shadPS4 instead masks out-of-range years into the packed value and sign-extends the 16-bit date