[ro] add TLS patching for runtime NROs

.patch/openssl-cmake/0005-cross-compile.patch

@@ -1,40 +0,0 @@
-diff --git a/cmake/ConfigureOpenSSL.cmake b/cmake/ConfigureOpenSSL.cmake
-index 3012e05..2ae23ff 100644
---- a/cmake/ConfigureOpenSSL.cmake
-+++ b/cmake/ConfigureOpenSSL.cmake
-@@ -108,7 +108,8 @@ function(configure_openssl)
-     )
- 
-     if(NOT "${CONFIGURE_OPTIONS_OLD}" STREQUAL "")
--        if(CONFIGURE_OPTIONS STREQUAL CONFIGURE_OPTIONS_OLD)
-+        # TODO(lizzie): Emscripten has issues with rebuilding due to the wrapper it uses
-+        if(CMAKE_SYSTEM_NAME MATCHES "Emscripten" OR CONFIGURE_OPTIONS STREQUAL CONFIGURE_OPTIONS_OLD)
-             message(STATUS "Found previous configure results. Don't perform configuration")
-             return()
-         endif()
-@@ -134,10 +135,24 @@ function(configure_openssl)
-         set(VERBOSE_OPTION OUTPUT_QUIET)
-     endif()
- 
-+    if (CMAKE_SYSTEM_NAME MATCHES "Emscripten")
-+        set(EMSCRIPTEN_CMAKE_WRAPPER "emcmake")
-+        find_program(EMCC emcc REQUIRED)
-+        set(EMSCRIPTEN_LINKER ${EMCC})
-+        list(APPEND CONFIGURE_COMMAND wasm64)
-+    else()
-+        set(EMSCRIPTEN_CMAKE_WRAPPER "")
-+        set(EMSCRIPTEN_LINKER ${CMAKE_LINKER})
-+    endif ()
-+
-     execute_process(
--        COMMAND ${CMAKE_COMMAND} -E env
-+        COMMAND ${EMSCRIPTEN_CMAKE_WRAPPER} ${CMAKE_COMMAND} -E env
-             "CFLAGS=${CMAKE_C_FLAGS}"
-             "CXXFLAGS=${CMAKE_CXX_FLAGS}"
-+            "LDFLAGS=${CMAKE_CXX_LINK_FLAGS}"
-+            "CC=${CMAKE_C_COMPILER}"
-+            "CXX=${CMAKE_CXX_COMPILER}"
-+            "LD=${EMSCRIPTEN_LINKER}"
-             ${CONFIGURE_COMMAND}
-         WORKING_DIRECTORY ${CONFIGURE_BUILD_DIR}
-         ${VERBOSE_OPTION}

cpmfile.json

@@ -202,8 +202,7 @@
             "0001-cpmutil-compat.patch",
             "0002-use-ccache.patch",
             "0003-use-cmake-compiler-flags.patch",
-            "0004-use-shell-wrapper.patch",
-            "0005-cross-compile.patch"
+            "0004-use-shell-wrapper.patch"
         ],
         "repo": "jimmy-park/openssl-cmake",
         "version": "3.6.2"

docs/CrossCompile.md

@@ -6,31 +6,10 @@ General guide for cross compiling.
 
 A painless guide for cross compilation (or to test NCE) from a x86_64 system without polluting your main.
 
-```sh
-#!/bin/sh
-ISO_FILE="debian-13.0.0-arm64-netinst.iso"
-DISK_FILE="debian-13-arm64-ci.qcow2"
-which -- qemu-system-aarch64 || sudo pkg install qemu
-[ -f "$ISO_FILE" ] || wget https://cdimage.debian.org/debian-cd/current/arm64/iso-cd/$ISO_FILE
-[ -f "$DISK_FILE" ] || qemu-img create -f qcow2 "$DISK_FILE" 30G
-QEMU_FLAGS=(
-    -M virt
-    -m 2G
-    -cpu max
-    -bios /usr/local/share/qemu/edk2-aarch64-code.fd
-    -drive if=none,file=$ISO_FILE,format=raw,id=cdrom
-    -drive if=none,file=$DISK_FILE,id=hd0,format=qcow2
-    -device scsi-cd,drive=cdrom
-    -device virtio-blk-device,drive=hd0
-    -device virtio-gpu-pci
-    -device usb-ehci
-    -device usb-kbd
-    -device intel-hda
-    -device hda-output
-    -nic user,model=virtio-net-pci
-)
-qemu-system-aarch64 "${QEMU_FLAGS[@]}"
-```
+- Install QEMU: `sudo pkg install qemu`
+- Download Debian 13: `wget https://cdimage.debian.org/debian-cd/current/arm64/iso-cd/debian-13.0.0-arm64-netinst.iso`
+- Create a system disk: `qemu-img create -f qcow2 debian-13-arm64-ci.qcow2 30G`
+- Run the VM: `qemu-system-aarch64 -M virt -m 2G -cpu max -bios /usr/local/share/qemu/edk2-aarch64-code.fd -drive if=none,file=debian-13.0.0-arm64-netinst.iso,format=raw,id=cdrom -device scsi-cd,drive=cdrom -drive if=none,file=debian-13-arm64-ci.qcow2,id=hd0,format=qcow2 -device virtio-blk-device,drive=hd0 -device virtio-gpu-pci -device usb-ehci -device usb-kbd -device intel-hda -device hda-output -nic user,model=virtio-net-pci`
 
 ## Gentoo
 

externals/cmake-modules/DetectArchitecture.cmake

@@ -101,11 +101,6 @@ endfunction()
 # ia64 exists
 # the rest exist, but are probably less popular than ia64
 
-detect_architecture_symbols(
-    ARCH wasm
-    SYMBOLS
-        "__EMSCRIPTEN__")
-
 detect_architecture_symbols(
     ARCH arm64
     SYMBOLS
@@ -208,6 +203,11 @@ detect_architecture_symbols(
         "__loongarch__"
         "__loongarch64")
 
+detect_architecture_symbols(
+    ARCH wasm
+    SYMBOLS
+        "__EMSCRIPTEN__")
+
 # "generic" target
 # If you have reached this point, you're on some as-of-yet unsupported architecture.
 # See the docs up above for known unsupported architectures

src/core/hle/service/ro/ro.cpp

@@ -16,6 +16,10 @@
 #include "core/hle/service/ro/ro_types.h"
 #include "core/hle/service/server_manager.h"
 #include "core/hle/service/service.h"
+#ifdef HAS_NCE
+#include "core/arm/nce/patcher.h"
+#include "core/hle/kernel/k_shared_memory.h"
+#endif
 
 namespace Service::RO {
 
@@ -386,7 +390,7 @@ public:
         R_SUCCEED();
     }
 
-    Result MapManualLoadModuleMemory(u64* out_address, size_t context_id, u64 nro_address,
+    Result MapManualLoadModuleMemory(Kernel::KernelCore& kernel, u64* out_address, size_t context_id, u64 nro_address,
                                      u64 nro_size, u64 bss_address, u64 bss_size) {
         // Get context.
         ProcessContext* context = this->GetContextById(context_id);
@@ -421,7 +425,31 @@ public:
         R_TRY(context->ValidateNro(std::addressof(nro_info->module_id), std::addressof(rx_size),
                                    std::addressof(ro_size), std::addressof(rw_size),
                                    nro_info->base_address, nro_size, bss_size));
+#ifdef HAS_NCE
+        if (Settings::IsNceEnabled()) {
+            auto* process = context->GetProcess();
+            auto& memory = process->GetMemory();
 
+            std::vector<u8> image(total_size);
+            memory.ReadBlock(nro_info->base_address, image.data(), rx_size);
+
+            Kernel::CodeSet::Segment code{.size = static_cast<u32>(rx_size)};
+            Core::NCE::Patcher patch;
+            patch.PatchText(image, code);
+            patch.RelocateAndCopy(nro_info->base_address, code, image, nullptr);
+
+            const u64 patch_address = nro_info->base_address + total_size;
+            const size_t patch_size = patch.GetSectionSize();
+            constexpr auto permission = Kernel::Svc::MemoryPermission::ReadExecute;
+
+            auto* patch_memory = Kernel::KSharedMemory::Create(kernel);
+            R_TRY(patch_memory->Initialize(kernel, kernel.System().DeviceMemory(), process, permission, permission, patch_size));
+            std::memcpy(patch_memory->GetPointer(), image.data() + total_size, patch_size);
+            R_TRY(process->AddSharedMemory(kernel, patch_memory, patch_address, patch_size));
+            R_TRY(patch_memory->Map(*process, patch_address, patch_size, permission));
+            memory.WriteBlock(nro_info->base_address, image.data(), rx_size);
+        }
+#endif
         // Set NRO perms.
         R_TRY(SetNroPerms(context->GetProcess(), nro_info->base_address, rx_size, ro_size,
                           rw_size + bss_size));
@@ -531,7 +559,7 @@ public:
     Result MapManualLoadModuleMemory(Out<u64> out_load_address, ClientProcessId client_pid,
                                      u64 nro_address, u64 nro_size, u64 bss_address, u64 bss_size) {
         R_TRY(m_ro->ValidateProcess(m_context_id, *client_pid));
-        R_RETURN(m_ro->MapManualLoadModuleMemory(out_load_address.Get(), m_context_id, nro_address,
+        R_RETURN(m_ro->MapManualLoadModuleMemory(system.Kernel(), out_load_address.Get(), m_context_id, nro_address,
                                                  nro_size, bss_address, bss_size));
     }
 

src/dynarmic/src/dynarmic/backend/riscv64/emit_riscv64_a32.cpp

@@ -197,15 +197,15 @@ void EmitA32Terminal(biscuit::Assembler& as, EmitContext& ctx, IR::Term::CheckHa
 
 void EmitA32LeafTerminal(biscuit::Assembler& as, EmitContext& ctx, IR::Term::LeafTerminal terminal, IR::LocationDescriptor initial_location, bool is_single_step) {
     if (auto const x = std::get_if<IR::Term::ReturnToDispatch>(&terminal))
-        return EmitA32Terminal(as, ctx, *x, initial_location, is_single_step);
+        return EmitA32LeafTerminal(as, ctx, *x, initial_location, is_single_step);
     if (auto const x = std::get_if<IR::Term::LinkBlock>(&terminal))
-        return EmitA32Terminal(as, ctx, *x, initial_location, is_single_step);
+        return EmitA32LeafTerminal(as, ctx, *x, initial_location, is_single_step);
     if (auto const x = std::get_if<IR::Term::LinkBlockFast>(&terminal))
-        return EmitA32Terminal(as, ctx, *x, initial_location, is_single_step);
+        return EmitA32LeafTerminal(as, ctx, *x, initial_location, is_single_step);
     if (auto const x = std::get_if<IR::Term::PopRSBHint>(&terminal))
-        return EmitA32Terminal(as, ctx, *x, initial_location, is_single_step);
+        return EmitA32LeafTerminal(as, ctx, *x, initial_location, is_single_step);
     if (auto const x = std::get_if<IR::Term::FastDispatchHint>(&terminal))
-        return EmitA32Terminal(as, ctx, *x, initial_location, is_single_step);
+        return EmitA32LeafTerminal(as, ctx, *x, initial_location, is_single_step);
     UNREACHABLE();
 }