3rdparty: Update WIL to v1.0.240803.1

Asserts are no longer needed as we check for width offset and adjust width accordingly using the offset.

.github/workflows/cron_update_base_translation.yml

@@ -20,7 +20,7 @@ jobs:
         uses: peter-evans/create-pull-request@v7
         with:
           title: "Qt: Update Base Translation"
-          commit-message: "Qt: Update Base Translation"
+          commit-message: "[ci skip] Qt: Update Base Translation."
           committer: "PCSX2 Bot <PCSX2Bot@users.noreply.github.com>"
           author: "PCSX2 Bot <PCSX2Bot@users.noreply.github.com>"
           body: "Daily update of base translation sources."

.github/workflows/linux_build_flatpak.yml

@@ -108,7 +108,7 @@ jobs:
           branch: beta
           cache: true
           restore-cache: true
-          cache-key: ${{ inputs.os }} ${{ inputs.platform }} ${{ inputs.compiler }} flatpak ${{ hashFiles('.github/workflows/scripts/linux/flatpak/**/*.json') }}
+          cache-key: ${{ inputs.os }} ${{ inputs.platform }} ${{ inputs.compiler }} flatpak ${{ hashFiles('.github/workflows/scripts/linux/flatpak/**/*.json', '.github/workflows/scripts/common/*.patch') }}
 
       - name: Build Flatpak (stable)
         if: ${{ inputs.stableBuild == true || inputs.stableBuild == 'true' }}

.github/workflows/linux_build_qt.yml

@@ -117,7 +117,7 @@ jobs:
         uses: actions/cache@v4
         with:
           path: ~/deps
-          key: ${{ inputs.os }} ${{ inputs.platform }} deps ${{ hashFiles('.github/workflows/scripts/linux/build-dependencies-qt.sh') }}
+          key: ${{ inputs.os }} ${{ inputs.platform }} deps ${{ hashFiles('.github/workflows/scripts/linux/build-dependencies-qt.sh', '.github/workflows/scripts/common/*.patch') }}
 
       - name: Build Dependencies
         if: steps.cache-deps.outputs.cache-hit != 'true'

.github/workflows/macos_build.yml

@@ -85,7 +85,7 @@ jobs:
         uses: actions/cache@v4
         with:
           path: ~/deps
-          key: ${{ inputs.os }} deps ${{ hashFiles('.github/workflows/scripts/macos/build-dependencies.sh') }}
+          key: ${{ inputs.os }} deps ${{ hashFiles('.github/workflows/scripts/macos/build-dependencies.sh', '.github/workflows/scripts/common/*.patch') }}
 
       - name: Build Dependencies
         if: steps.cache-deps.outputs.cache-hit != 'true'

.github/workflows/scripts/common/shaderc-changes.patch

@@ -114,6 +114,15 @@ diff --git a/libshaderc/include/shaderc/shaderc.h b/libshaderc/include/shaderc/s
 index 3a3e97d..65d5b77 100644
 --- a/libshaderc/include/shaderc/shaderc.h
 +++ b/libshaderc/include/shaderc/shaderc.h
+@@ -15,6 +15,8 @@
+ #ifndef SHADERC_SHADERC_H_
+ #define SHADERC_SHADERC_H_
+ 
++#define SHADERC_PCSX2_CUSTOM 1
++
+ #ifdef __cplusplus
+ extern "C" {
+ #endif
 @@ -317,7 +317,7 @@ SHADERC_EXPORT void shaderc_compile_options_set_source_language(
  
  // Sets the compiler mode to generate debug information in the output.
@@ -123,69 +132,6 @@ index 3a3e97d..65d5b77 100644
  
  // Sets the compiler optimization level to the given level. Only the last one
  // takes effect if multiple calls of this function exist.
-@@ -506,6 +506,10 @@ SHADERC_EXPORT void shaderc_compile_options_set_invert_y(
- SHADERC_EXPORT void shaderc_compile_options_set_nan_clamp(
-     shaderc_compile_options_t options, bool enable);
- 
-+// Returns a string representation of the specified compilation status.
-+SHADERC_EXPORT const char* shaderc_compilation_status_to_string(
-+    shaderc_compilation_status status);
-+
- // An opaque handle to the results of a call to any shaderc_compile_into_*()
- // function.
- typedef struct shaderc_compilation_result* shaderc_compilation_result_t;
-@@ -529,28 +533,31 @@ typedef struct shaderc_compilation_result* shaderc_compilation_result_t;
- // present.  May be safely called from multiple threads without explicit
- // synchronization. If there was failure in allocating the compiler object,
- // null will be returned.
--SHADERC_EXPORT shaderc_compilation_result_t shaderc_compile_into_spv(
-+SHADERC_EXPORT shaderc_compilation_status shaderc_compile_into_spv(
-     const shaderc_compiler_t compiler, const char* source_text,
-     size_t source_text_size, shaderc_shader_kind shader_kind,
-     const char* input_file_name, const char* entry_point_name,
--    const shaderc_compile_options_t additional_options);
-+    const shaderc_compile_options_t additional_options,
-+    shaderc_compilation_result_t* result);
- 
- // Like shaderc_compile_into_spv, but the result contains SPIR-V assembly text
- // instead of a SPIR-V binary module.  The SPIR-V assembly syntax is as defined
- // by the SPIRV-Tools open source project.
--SHADERC_EXPORT shaderc_compilation_result_t shaderc_compile_into_spv_assembly(
-+SHADERC_EXPORT shaderc_compilation_status shaderc_compile_into_spv_assembly(
-     const shaderc_compiler_t compiler, const char* source_text,
-     size_t source_text_size, shaderc_shader_kind shader_kind,
-     const char* input_file_name, const char* entry_point_name,
--    const shaderc_compile_options_t additional_options);
-+    const shaderc_compile_options_t additional_options,
-+    shaderc_compilation_result_t* result);
- 
- // Like shaderc_compile_into_spv, but the result contains preprocessed source
- // code instead of a SPIR-V binary module
--SHADERC_EXPORT shaderc_compilation_result_t shaderc_compile_into_preprocessed_text(
-+SHADERC_EXPORT shaderc_compilation_status shaderc_compile_into_preprocessed_text(
-     const shaderc_compiler_t compiler, const char* source_text,
-     size_t source_text_size, shaderc_shader_kind shader_kind,
-     const char* input_file_name, const char* entry_point_name,
--    const shaderc_compile_options_t additional_options);
-+    const shaderc_compile_options_t additional_options,
-+    shaderc_compilation_result_t* result);
- 
- // Takes an assembly string of the format defined in the SPIRV-Tools project
- // (https://github.com/KhronosGroup/SPIRV-Tools/blob/master/syntax.md),
-@@ -561,10 +568,11 @@ SHADERC_EXPORT shaderc_compilation_result_t shaderc_compile_into_preprocessed_te
- // May be safely called from multiple threads without explicit synchronization.
- // If there was failure in allocating the compiler object, null will be
- // returned.
--SHADERC_EXPORT shaderc_compilation_result_t shaderc_assemble_into_spv(
-+SHADERC_EXPORT shaderc_compilation_status shaderc_assemble_into_spv(
-     const shaderc_compiler_t compiler, const char* source_assembly,
-     size_t source_assembly_size,
--    const shaderc_compile_options_t additional_options);
-+    const shaderc_compile_options_t additional_options,
-+    shaderc_compilation_result_t* result);
- 
- // The following functions, operating on shaderc_compilation_result_t objects,
- // offer only the basic thread-safety guarantee.
 diff --git a/libshaderc/include/shaderc/shaderc.hpp b/libshaderc/include/shaderc/shaderc.hpp
 index 3817af8..5592b49 100644
 --- a/libshaderc/include/shaderc/shaderc.hpp
@@ -202,119 +148,6 @@ index 3817af8..5592b49 100644
    }
  
    // Sets the compiler optimization level to the given level. Only the last one
-@@ -425,9 +426,10 @@ class Compiler {
-                                         const char* input_file_name,
-                                         const char* entry_point_name,
-                                         const CompileOptions& options) const {
--    shaderc_compilation_result_t compilation_result = shaderc_compile_into_spv(
-+    shaderc_compilation_result_t compilation_result = nullptr;
-+    shaderc_compile_into_spv(
-         compiler_, source_text, source_text_size, shader_kind, input_file_name,
--        entry_point_name, options.options_);
-+        entry_point_name, options.options_, &compilation_result);
-     return SpvCompilationResult(compilation_result);
-   }
- 
-@@ -451,9 +453,10 @@ class Compiler {
-                                         size_t source_text_size,
-                                         shaderc_shader_kind shader_kind,
-                                         const char* input_file_name) const {
--    shaderc_compilation_result_t compilation_result =
--        shaderc_compile_into_spv(compiler_, source_text, source_text_size,
--                                 shader_kind, input_file_name, "main", nullptr);
-+    shaderc_compilation_result_t compilation_result = nullptr;
-+    shaderc_compile_into_spv(compiler_, source_text, source_text_size,
-+                             shader_kind, input_file_name, "main", nullptr,
-+                             &compilation_result);
-     return SpvCompilationResult(compilation_result);
-   }
- 
-@@ -504,8 +507,11 @@ class Compiler {
-   SpvCompilationResult AssembleToSpv(const char* source_assembly,
-                                      size_t source_assembly_size,
-                                      const CompileOptions& options) const {
--    return SpvCompilationResult(shaderc_assemble_into_spv(
--        compiler_, source_assembly, source_assembly_size, options.options_));
-+    shaderc_compilation_result_t compilation_result = nullptr;
-+    shaderc_assemble_into_spv(
-+        compiler_, source_assembly, source_assembly_size, options.options_,
-+        &compilation_result);
-+    return SpvCompilationResult(compilation_result);
-   }
- 
-   // Assembles the given SPIR-V assembly and returns a SPIR-V binary module
-@@ -513,8 +519,11 @@ class Compiler {
-   // Like the first AssembleToSpv method but uses the default compiler options.
-   SpvCompilationResult AssembleToSpv(const char* source_assembly,
-                                      size_t source_assembly_size) const {
--    return SpvCompilationResult(shaderc_assemble_into_spv(
--        compiler_, source_assembly, source_assembly_size, nullptr));
-+    shaderc_compilation_result_t compilation_result = nullptr;
-+    shaderc_assemble_into_spv(
-+        compiler_, source_assembly, source_assembly_size, nullptr,
-+        &compilation_result);
-+    return SpvCompilationResult(compilation_result);
-   }
- 
-   // Assembles the given SPIR-V assembly and returns a SPIR-V binary module
-@@ -523,9 +532,11 @@ class Compiler {
-   // std::string.
-   SpvCompilationResult AssembleToSpv(const std::string& source_assembly,
-                                      const CompileOptions& options) const {
--    return SpvCompilationResult(
--        shaderc_assemble_into_spv(compiler_, source_assembly.data(),
--                                  source_assembly.size(), options.options_));
-+    shaderc_compilation_result_t compilation_result = nullptr;
-+    shaderc_assemble_into_spv(
-+      compiler_, source_assembly.data(), source_assembly.size(),
-+      options.options_, &compilation_result);
-+    return SpvCompilationResult(compilation_result);
-   }
- 
-   // Assembles the given SPIR-V assembly and returns a SPIR-V binary module
-@@ -533,8 +544,10 @@ class Compiler {
-   // Like the first AssembleToSpv method but the source is provided as a
-   // std::string and also uses default compiler options.
-   SpvCompilationResult AssembleToSpv(const std::string& source_assembly) const {
--    return SpvCompilationResult(shaderc_assemble_into_spv(
--        compiler_, source_assembly.data(), source_assembly.size(), nullptr));
-+    shaderc_compilation_result_t compilation_result = nullptr;
-+    shaderc_assemble_into_spv(compiler_, source_assembly.data(),
-+      source_assembly.size(), nullptr, &compilation_result);
-+    return SpvCompilationResult(compilation_result);
-   }
- 
-   // Compiles the given source GLSL and returns the SPIR-V assembly text
-@@ -544,10 +557,11 @@ class Compiler {
-       const char* source_text, size_t source_text_size,
-       shaderc_shader_kind shader_kind, const char* input_file_name,
-       const char* entry_point_name, const CompileOptions& options) const {
--    shaderc_compilation_result_t compilation_result =
--        shaderc_compile_into_spv_assembly(
--            compiler_, source_text, source_text_size, shader_kind,
--            input_file_name, entry_point_name, options.options_);
-+    shaderc_compilation_result_t compilation_result = nullptr;
-+    shaderc_compile_into_spv_assembly(
-+        compiler_, source_text, source_text_size, shader_kind,
-+        input_file_name, entry_point_name, options.options_,
-+        &compilation_result);
-     return AssemblyCompilationResult(compilation_result);
-   }
- 
-@@ -592,10 +606,10 @@ class Compiler {
-       const char* source_text, size_t source_text_size,
-       shaderc_shader_kind shader_kind, const char* input_file_name,
-       const CompileOptions& options) const {
--    shaderc_compilation_result_t compilation_result =
--        shaderc_compile_into_preprocessed_text(
-+    shaderc_compilation_result_t compilation_result;
-+    shaderc_compile_into_preprocessed_text(
-             compiler_, source_text, source_text_size, shader_kind,
--            input_file_name, "main", options.options_);
-+            input_file_name, "main", options.options_, &compilation_result);
-     return PreprocessedSourceCompilationResult(compilation_result);
-   }
- 
 diff --git a/libshaderc/src/shaderc.cc b/libshaderc/src/shaderc.cc
 index 63f1bbc..c1a9b12 100644
 --- a/libshaderc/src/shaderc.cc
@@ -334,146 +167,6 @@ index 63f1bbc..c1a9b12 100644
  }
  
  void shaderc_compile_options_set_optimization_level(
-@@ -591,8 +595,31 @@ void shaderc_compiler_release(shaderc_compiler_t compiler) {
-   delete compiler;
- }
- 
-+const char* shaderc_compilation_status_to_string(shaderc_compilation_status status)
-+{
-+  static constexpr const std::pair<shaderc_compilation_status, const char*> status_names[] = {
-+    {shaderc_compilation_status_success, "shaderc_compilation_status_success"},
-+    {shaderc_compilation_status_invalid_stage, "shaderc_compilation_status_invalid_stage"},
-+    {shaderc_compilation_status_compilation_error, "shaderc_compilation_status_compilation_error"},
-+    {shaderc_compilation_status_internal_error, "shaderc_compilation_status_internal_error"},
-+    {shaderc_compilation_status_null_result_object, "shaderc_compilation_status_null_result_object"},
-+    {shaderc_compilation_status_invalid_assembly, "shaderc_compilation_status_invalid_assembly"},
-+    {shaderc_compilation_status_validation_error, "shaderc_compilation_status_validation_error"},
-+    {shaderc_compilation_status_transformation_error, "shaderc_compilation_status_transformation_error"},
-+    {shaderc_compilation_status_configuration_error, "shaderc_compilation_status_configuration_error"},
-+  };
-+
-+  for (const auto& it : status_names)
-+  {
-+    if (status == it.first)
-+      return it.second;
-+  }
-+
-+  return "shaderc_compilation_status_unknown";
-+}
-+
- namespace {
--shaderc_compilation_result_t CompileToSpecifiedOutputType(
-+shaderc_compilation_result_vector* CompileToSpecifiedOutputType(
-     const shaderc_compiler_t compiler, const char* source_text,
-     size_t source_text_size, shaderc_shader_kind shader_kind,
-     const char* input_file_name, const char* entry_point_name,
-@@ -669,48 +696,59 @@ shaderc_compilation_result_t CompileToSpecifiedOutputType(
- }
- }  // anonymous namespace
- 
--shaderc_compilation_result_t shaderc_compile_into_spv(
-+shaderc_compilation_status shaderc_compile_into_spv(
-     const shaderc_compiler_t compiler, const char* source_text,
-     size_t source_text_size, shaderc_shader_kind shader_kind,
-     const char* input_file_name, const char* entry_point_name,
--    const shaderc_compile_options_t additional_options) {
--  return CompileToSpecifiedOutputType(
-+    const shaderc_compile_options_t additional_options,
-+    shaderc_compilation_result_t* result) {
-+  shaderc_compilation_result_vector* resultv = CompileToSpecifiedOutputType(
-       compiler, source_text, source_text_size, shader_kind, input_file_name,
-       entry_point_name, additional_options,
-       shaderc_util::Compiler::OutputType::SpirvBinary);
-+  *result = resultv;
-+  return resultv ? resultv->compilation_status : shaderc_compilation_status_internal_error;
- }
- 
--shaderc_compilation_result_t shaderc_compile_into_spv_assembly(
-+shaderc_compilation_status shaderc_compile_into_spv_assembly(
-     const shaderc_compiler_t compiler, const char* source_text,
-     size_t source_text_size, shaderc_shader_kind shader_kind,
-     const char* input_file_name, const char* entry_point_name,
--    const shaderc_compile_options_t additional_options) {
--  return CompileToSpecifiedOutputType(
-+    const shaderc_compile_options_t additional_options,
-+    shaderc_compilation_result_t* result) {
-+  shaderc_compilation_result_vector* resultv = CompileToSpecifiedOutputType(
-       compiler, source_text, source_text_size, shader_kind, input_file_name,
-       entry_point_name, additional_options,
-       shaderc_util::Compiler::OutputType::SpirvAssemblyText);
-+  *result = resultv;
-+  return resultv ? resultv->compilation_status : shaderc_compilation_status_internal_error;
- }
- 
--shaderc_compilation_result_t shaderc_compile_into_preprocessed_text(
-+shaderc_compilation_status shaderc_compile_into_preprocessed_text(
-     const shaderc_compiler_t compiler, const char* source_text,
-     size_t source_text_size, shaderc_shader_kind shader_kind,
-     const char* input_file_name, const char* entry_point_name,
--    const shaderc_compile_options_t additional_options) {
--  return CompileToSpecifiedOutputType(
-+    const shaderc_compile_options_t additional_options,
-+    shaderc_compilation_result_t* result) {
-+  shaderc_compilation_result_vector* resultv = CompileToSpecifiedOutputType(
-       compiler, source_text, source_text_size, shader_kind, input_file_name,
-       entry_point_name, additional_options,
-       shaderc_util::Compiler::OutputType::PreprocessedText);
-+  *result = resultv;
-+  return resultv ? resultv->compilation_status : shaderc_compilation_status_internal_error;
- }
- 
--shaderc_compilation_result_t shaderc_assemble_into_spv(
-+shaderc_compilation_status shaderc_assemble_into_spv(
-     const shaderc_compiler_t compiler, const char* source_assembly,
-     size_t source_assembly_size,
--    const shaderc_compile_options_t additional_options) {
--  auto* result = new (std::nothrow) shaderc_compilation_result_spv_binary;
--  if (!result) return nullptr;
--  result->compilation_status = shaderc_compilation_status_invalid_assembly;
--  if (!compiler->initializer) return result;
--  if (source_assembly == nullptr) return result;
-+    const shaderc_compile_options_t additional_options,
-+    shaderc_compilation_result_t* result) {
-+  auto* bresult = new (std::nothrow) shaderc_compilation_result_spv_binary;
-+  if (!bresult) return shaderc_compilation_status_internal_error;
-+  bresult->compilation_status = shaderc_compilation_status_invalid_assembly;
-+  *result = bresult;
-+  if (!compiler->initializer) return bresult->compilation_status;
-+  if (source_assembly == nullptr) return bresult->compilation_status;
- 
-   TRY_IF_EXCEPTIONS_ENABLED {
-     spv_binary assembling_output_data = nullptr;
-@@ -724,22 +762,22 @@ shaderc_compilation_result_t shaderc_assemble_into_spv(
-         GetCompilerTargetEnvVersion(target_env_version),
-         {source_assembly, source_assembly + source_assembly_size},
-         &assembling_output_data, &errors);
--    result->num_errors = !assembling_succeeded;
-+    bresult->num_errors = !assembling_succeeded;
-     if (assembling_succeeded) {
--      result->SetOutputData(assembling_output_data);
--      result->output_data_size =
-+      bresult->SetOutputData(assembling_output_data);
-+      bresult->output_data_size =
-           assembling_output_data->wordCount * sizeof(uint32_t);
--      result->compilation_status = shaderc_compilation_status_success;
-+      bresult->compilation_status = shaderc_compilation_status_success;
-     } else {
--      result->messages = std::move(errors);
--      result->compilation_status = shaderc_compilation_status_invalid_assembly;
-+      bresult->messages = std::move(errors);
-+      bresult->compilation_status = shaderc_compilation_status_invalid_assembly;
-     }
-   }
-   CATCH_IF_EXCEPTIONS_ENABLED(...) {
--    result->compilation_status = shaderc_compilation_status_internal_error;
-+    bresult->compilation_status = shaderc_compilation_status_internal_error;
-   }
- 
--  return result;
-+  return bresult->compilation_status;
- }
- 
- size_t shaderc_result_get_length(const shaderc_compilation_result_t result) {
 diff --git a/libshaderc_util/include/libshaderc_util/compiler.h b/libshaderc_util/include/libshaderc_util/compiler.h
 index d9d02b9..b076ec8 100644
 --- a/libshaderc_util/include/libshaderc_util/compiler.h

.github/workflows/scripts/linux/build-dependencies-qt.sh

@@ -16,11 +16,11 @@ fi
 
 LIBBACKTRACE=ad106d5fdd5d960bd33fae1c48a351af567fd075
 LIBJPEG=9f
-LIBPNG=1.6.43
+LIBPNG=1.6.44
 LIBWEBP=1.4.0
 LZ4=b8fd2d15309dd4e605070bd4486e26b6ef814e29
-SDL=SDL2-2.30.8
-QT=6.8.0
+SDL=SDL2-2.30.9
+QT=6.8.1
 ZSTD=1.5.6
 
 SHADERC=2024.1
@@ -34,17 +34,17 @@ cd deps-build
 cat > SHASUMS <<EOF
 fd6f417fe9e3a071cf1424a5152d926a34c4a3c5070745470be6cf12a404ed79  $LIBBACKTRACE.zip
 04705c110cb2469caa79fb71fba3d7bf834914706e9641a4589485c1f832565b  jpegsrc.v$LIBJPEG.tar.gz
-6a5ca0652392a2d7c9db2ae5b40210843c0bbc081cbd410825ab00cc59f14a6c  libpng-$LIBPNG.tar.xz
+60c4da1d5b7f0aa8d158da48e8f8afa9773c1c8baa5d21974df61f1886b8ce8e  libpng-$LIBPNG.tar.xz
 61f873ec69e3be1b99535634340d5bde750b2e4447caa1db9f61be3fd49ab1e5  libwebp-$LIBWEBP.tar.gz
 0728800155f3ed0a0c87e03addbd30ecbe374f7b080678bbca1506051d50dec3  $LZ4.tar.gz
-380c295ea76b9bd72d90075793971c8bcb232ba0a69a9b14da4ae8f603350058  $SDL.tar.gz
+24b574f71c87a763f50704bbb630cbe38298d544a1f890f099a4696b1d6beba4  $SDL.tar.gz
 8c29e06cf42aacc1eafc4077ae2ec6c6fcb96a626157e0593d5e82a34fd403c1  zstd-$ZSTD.tar.gz
-1bad481710aa27f872de6c9f72651f89a6107f0077003d0ebfcc9fd15cba3c75  qtbase-everywhere-src-$QT.tar.xz
-595bf8557b91e1f8ebc726f1e09868a3c7e610ff5045068f2d4ea2428c49a5d4  qtimageformats-everywhere-src-$QT.tar.xz
-cf7a593d5e520f8177240610d9e55d5b75b0887fe5f385554ff64377f1646199  qtsvg-everywhere-src-$QT.tar.xz
-403115d8268503c6cc6e43310c8ae28eb9e605072a5d04e4a2de8b6af39981f7  qttools-everywhere-src-$QT.tar.xz
-84bf2b67c243cd0c50a08acd7bfa9df2b1965028511815c1b6b65a0687437cb6  qttranslations-everywhere-src-$QT.tar.xz
-175758591638ebf1c6fbb66ac11c7fa0eb8d4ed52e9243cc59075d06a6a2060a  qtwayland-everywhere-src-$QT.tar.xz
+40b14562ef3bd779bc0e0418ea2ae08fa28235f8ea6e8c0cb3bce1d6ad58dcaf  qtbase-everywhere-src-$QT.tar.xz
+138cc2909aa98f5ff7283e36eb3936eb5e625d3ca3b4febae2ca21d8903dd237  qtimageformats-everywhere-src-$QT.tar.xz
+3d0de73596e36b2daa7c48d77c4426bb091752856912fba720215f756c560dd0  qtsvg-everywhere-src-$QT.tar.xz
+9d43d409be08b8681a0155a9c65114b69c9a3fc11aef6487bb7fdc5b283c432d  qttools-everywhere-src-$QT.tar.xz
+635a6093e99152243b807de51077485ceadd4786d4acb135b9340b2303035a4a  qttranslations-everywhere-src-$QT.tar.xz
+2226fbde4e2ddd12f8bf4b239c8f38fd706a54e789e63467dfddc77129eca203  qtwayland-everywhere-src-$QT.tar.xz
 eb3b5f0c16313d34f208d90c2fa1e588a23283eed63b101edd5422be6165d528  shaderc-$SHADERC.tar.gz
 aa27e4454ce631c5a17924ce0624eac736da19fc6f5a2ab15a6c58da7b36950f  shaderc-glslang-$SHADERC_GLSLANG.tar.gz
 5d866ce34a4b6908e262e5ebfffc0a5e11dd411640b5f24c85a80ad44c0d4697  shaderc-spirv-headers-$SHADERC_SPIRVHEADERS.tar.gz

.github/workflows/scripts/linux/flatpak/modules/10-libpcap.json

@@ -8,8 +8,8 @@
     {
       "type": "git",
       "url": "https://github.com/the-tcpdump-group/libpcap.git",
-      "tag": "libpcap-1.10.4",
-      "commit": "104271ba4a14de6743e43bcf87536786d8fddea4"
+      "tag": "libpcap-1.10.5",
+      "commit": "bbcbc9174df3298a854daee2b3e666a4b6e5383a"
     }
   ],
   "cleanup": [

.github/workflows/scripts/linux/flatpak/modules/20-sdl2.json

@@ -14,8 +14,8 @@
   "sources": [
     {
       "type": "archive",
-      "url": "https://libsdl.org/release/SDL2-2.30.8.tar.gz",
-      "sha256": "380c295ea76b9bd72d90075793971c8bcb232ba0a69a9b14da4ae8f603350058"
+      "url": "https://libsdl.org/release/SDL2-2.30.9.tar.gz",
+      "sha256": "24b574f71c87a763f50704bbb630cbe38298d544a1f890f099a4696b1d6beba4"
     }
   ],
   "cleanup": [

.github/workflows/scripts/linux/flatpak/net.pcsx2.PCSX2.json

@@ -1,15 +1,15 @@
 {
   "app-id": "net.pcsx2.PCSX2",
   "runtime": "org.kde.Platform",
-  "runtime-version": "6.7",
+  "runtime-version": "6.8",
   "sdk": "org.kde.Sdk",
   "sdk-extensions": [
-    "org.freedesktop.Sdk.Extension.llvm17"
+    "org.freedesktop.Sdk.Extension.llvm18"
   ],
   "add-extensions": {
     "org.freedesktop.Platform.ffmpeg-full": {
       "directory": "lib/ffmpeg",
-      "version": "23.08",
+      "version": "24.08",
       "add-ld-path": ".",
       "autodownload": true
     }
@@ -44,8 +44,8 @@
         "config-opts": [
           "-DCMAKE_BUILD_TYPE=Release",
           "-DCMAKE_INTERPROCEDURAL_OPTIMIZATION=ON",
-          "-DCMAKE_C_COMPILER=/usr/lib/sdk/llvm17/bin/clang",
-          "-DCMAKE_CXX_COMPILER=/usr/lib/sdk/llvm17/bin/clang++",
+          "-DCMAKE_C_COMPILER=/usr/lib/sdk/llvm18/bin/clang",
+          "-DCMAKE_CXX_COMPILER=/usr/lib/sdk/llvm18/bin/clang++",
           "-DCMAKE_EXE_LINKER_FLAGS_INIT=-fuse-ld=lld",
           "-DCMAKE_MODULE_LINKER_FLAGS_INIT=-fuse-ld=lld",
           "-DCMAKE_SHARED_LINKER_FLAGS_INIT=-fuse-ld=lld",

.github/workflows/scripts/macos/build-dependencies-universal.sh

@@ -38,12 +38,12 @@ if [ "${INSTALLDIR:0:1}" != "/" ]; then
 	INSTALLDIR="$PWD/$INSTALLDIR"
 fi
 
-FREETYPE=2.13.2
-HARFBUZZ=8.3.1
-SDL=SDL2-2.30.8
+FREETYPE=2.13.3
+HARFBUZZ=10.0.1
+SDL=SDL2-2.30.9
 ZSTD=1.5.6
 LZ4=b8fd2d15309dd4e605070bd4486e26b6ef814e29
-LIBPNG=1.6.43
+LIBPNG=1.6.44
 LIBJPEG=9f
 LIBWEBP=1.4.0
 FFMPEG=6.0
@@ -74,12 +74,12 @@ CMAKE_ARCH_ARM64=-DCMAKE_OSX_ARCHITECTURES="arm64"
 CMAKE_ARCH_UNIVERSAL=-DCMAKE_OSX_ARCHITECTURES="x86_64;arm64"
 
 cat > SHASUMS <<EOF
-12991c4e55c506dd7f9b765933e62fd2be2e06d421505d7950a132e4f1bb484d  freetype-$FREETYPE.tar.xz
-19a54fe9596f7a47c502549fce8e8a10978c697203774008cc173f8360b19a9a  harfbuzz-$HARFBUZZ.tar.gz
-380c295ea76b9bd72d90075793971c8bcb232ba0a69a9b14da4ae8f603350058  $SDL.tar.gz
+0550350666d427c74daeb85d5ac7bb353acba5f76956395995311a9c6f063289  freetype-$FREETYPE.tar.xz
+e7358ea86fe10fb9261931af6f010d4358dac64f7074420ca9bc94aae2bdd542  harfbuzz-$HARFBUZZ.tar.gz
+24b574f71c87a763f50704bbb630cbe38298d544a1f890f099a4696b1d6beba4  $SDL.tar.gz
 8c29e06cf42aacc1eafc4077ae2ec6c6fcb96a626157e0593d5e82a34fd403c1  zstd-$ZSTD.tar.gz
 0728800155f3ed0a0c87e03addbd30ecbe374f7b080678bbca1506051d50dec3  $LZ4.tar.gz
-6a5ca0652392a2d7c9db2ae5b40210843c0bbc081cbd410825ab00cc59f14a6c  libpng-$LIBPNG.tar.xz
+60c4da1d5b7f0aa8d158da48e8f8afa9773c1c8baa5d21974df61f1886b8ce8e  libpng-$LIBPNG.tar.xz
 61f873ec69e3be1b99535634340d5bde750b2e4447caa1db9f61be3fd49ab1e5  libwebp-$LIBWEBP.tar.gz
 04705c110cb2469caa79fb71fba3d7bf834914706e9641a4589485c1f832565b  jpegsrc.v$LIBJPEG.tar.gz
 57be87c22d9b49c112b6d24bc67d42508660e6b718b3db89c44e47e289137082  ffmpeg-$FFMPEG.tar.xz

.github/workflows/scripts/macos/build-dependencies.sh

@@ -20,12 +20,12 @@ if [ "${INSTALLDIR:0:1}" != "/" ]; then
 	INSTALLDIR="$PWD/$INSTALLDIR"
 fi
 
-FREETYPE=2.13.2
-HARFBUZZ=8.3.1
-SDL=SDL2-2.30.8
+FREETYPE=2.13.3
+HARFBUZZ=10.0.1
+SDL=SDL2-2.30.9
 ZSTD=1.5.6
 LZ4=b8fd2d15309dd4e605070bd4486e26b6ef814e29
-LIBPNG=1.6.43
+LIBPNG=1.6.44
 LIBJPEG=9f
 LIBWEBP=1.4.0
 FFMPEG=6.0
@@ -54,12 +54,12 @@ CMAKE_COMMON=(
 )
 
 cat > SHASUMS <<EOF
-12991c4e55c506dd7f9b765933e62fd2be2e06d421505d7950a132e4f1bb484d  freetype-$FREETYPE.tar.xz
-19a54fe9596f7a47c502549fce8e8a10978c697203774008cc173f8360b19a9a  harfbuzz-$HARFBUZZ.tar.gz
-380c295ea76b9bd72d90075793971c8bcb232ba0a69a9b14da4ae8f603350058  $SDL.tar.gz
+0550350666d427c74daeb85d5ac7bb353acba5f76956395995311a9c6f063289  freetype-$FREETYPE.tar.xz
+e7358ea86fe10fb9261931af6f010d4358dac64f7074420ca9bc94aae2bdd542  harfbuzz-$HARFBUZZ.tar.gz
+24b574f71c87a763f50704bbb630cbe38298d544a1f890f099a4696b1d6beba4  $SDL.tar.gz
 8c29e06cf42aacc1eafc4077ae2ec6c6fcb96a626157e0593d5e82a34fd403c1  zstd-$ZSTD.tar.gz
 0728800155f3ed0a0c87e03addbd30ecbe374f7b080678bbca1506051d50dec3  $LZ4.tar.gz
-6a5ca0652392a2d7c9db2ae5b40210843c0bbc081cbd410825ab00cc59f14a6c  libpng-$LIBPNG.tar.xz
+60c4da1d5b7f0aa8d158da48e8f8afa9773c1c8baa5d21974df61f1886b8ce8e  libpng-$LIBPNG.tar.xz
 61f873ec69e3be1b99535634340d5bde750b2e4447caa1db9f61be3fd49ab1e5  libwebp-$LIBWEBP.tar.gz
 04705c110cb2469caa79fb71fba3d7bf834914706e9641a4589485c1f832565b  jpegsrc.v$LIBJPEG.tar.gz
 57be87c22d9b49c112b6d24bc67d42508660e6b718b3db89c44e47e289137082  ffmpeg-$FFMPEG.tar.xz

.github/workflows/scripts/windows/build-dependencies-arm64.bat

@@ -42,14 +42,14 @@ echo INSTALLDIR=%INSTALLDIR%
 
 cd "%BUILDDIR%"
 
-set FREETYPE=2.13.2
-set HARFBUZZ=8.3.1
+set FREETYPE=2.13.3
+set HARFBUZZ=10.0.1
 set LIBJPEG=9f
 set LIBPNG=1643
 set LZ4=b8fd2d15309dd4e605070bd4486e26b6ef814e29
-set QT=6.8.0
+set QT=6.8.1
 set QTMINOR=6.8
-set SDL=SDL2-2.30.8
+set SDL=SDL2-2.30.9
 set WEBP=1.4.0
 set ZLIB=1.3.1
 set ZLIBSHORT=131
@@ -60,21 +60,21 @@ set SHADERC_GLSLANG=142052fa30f9eca191aa9dcf65359fcaed09eeec
 set SHADERC_SPIRVHEADERS=5e3ad389ee56fca27c9705d093ae5387ce404df4
 set SHADERC_SPIRVTOOLS=dd4b663e13c07fea4fbb3f70c1c91c86731099f7
 
-call :downloadfile "freetype-%FREETYPE%.tar.gz" https://sourceforge.net/projects/freetype/files/freetype2/%FREETYPE%/freetype-%FREETYPE%.tar.gz/download 1ac27e16c134a7f2ccea177faba19801131116fd682efc1f5737037c5db224b5 || goto error
-call :downloadfile "harfbuzz-%HARFBUZZ%.zip" https://github.com/harfbuzz/harfbuzz/archive/refs/tags/%HARFBUZZ%.zip b2bc56184ae37324bc4829fde7d3f9e6916866ad711ee85792e457547c9fd127 || goto error
+call :downloadfile "freetype-%FREETYPE%.tar.gz" https://sourceforge.net/projects/freetype/files/freetype2/%FREETYPE%/freetype-%FREETYPE%.tar.gz/download 5c3a8e78f7b24c20b25b54ee575d6daa40007a5f4eea2845861c3409b3021747 || goto error
+call :downloadfile "harfbuzz-%HARFBUZZ%.zip" https://github.com/harfbuzz/harfbuzz/archive/refs/tags/%HARFBUZZ%.zip 8adf9f5a4b6022aa2744f45c89ce347df46fea8403e99f01d650b11c417d0aa8 || goto error
 call :downloadfile "lpng%LIBPNG%.zip" https://download.sourceforge.net/libpng/lpng1643.zip fc466a1e638e635d6c66363bdf3f38555b81b0141d0b06ba45b49ccca327436d || goto error
 call :downloadfile "jpegsr%LIBJPEG%.zip" https://ijg.org/files/jpegsr%LIBJPEG%.zip 6255da8c89e09d694e6800688c76145eb6870a76ac0d36c74fccd61b3940aafa || goto error
 call :downloadfile "libwebp-%WEBP%.tar.gz" "https://storage.googleapis.com/downloads.webmproject.org/releases/webp/libwebp-%WEBP%.tar.gz" 61f873ec69e3be1b99535634340d5bde750b2e4447caa1db9f61be3fd49ab1e5 || goto error
 call :downloadfile "lz4-%LZ4%.zip" "https://github.com/lz4/lz4/archive/%LZ4%.zip" 0c33119688d6b180c7e760b0acd70059222389cfd581632623784bee27e51a31 || goto error
-call :downloadfile "%SDL%.zip" "https://libsdl.org/release/%SDL%.zip" abe2921dffcb25d39d270454810b211a9f47be3e5e802bc45e7d058f286a325e || goto error
-call :downloadfile "qtbase-everywhere-src-%QT%.zip" "https://download.qt.io/official_releases/qt/%QTMINOR%/%QT%/submodules/qtbase-everywhere-src-%QT%.zip" c3b41915341d853b6374cf93f1fcced2c8e4be9360f29c656960e1d0d15046a3 || goto error
-call :downloadfile "qtimageformats-everywhere-src-%QT%.zip" "https://download.qt.io/official_releases/qt/%QTMINOR%/%QT%/submodules/qtimageformats-everywhere-src-%QT%.zip" 809081a7bdf7e48262fbe9437e4e756df6ad2649433e803c4040026e650d7c91 || goto error
-call :downloadfile "qtsvg-everywhere-src-%QT%.zip" "https://download.qt.io/official_releases/qt/%QTMINOR%/%QT%/submodules/qtsvg-everywhere-src-%QT%.zip" 89f1ef4595f68c3d34c63a7c1c4ce475e701e103f0473f3fd0718a2e5234de6e || goto error
-call :downloadfile "qttools-everywhere-src-%QT%.zip" "https://download.qt.io/official_releases/qt/%QTMINOR%/%QT%/submodules/qttools-everywhere-src-%QT%.zip" 3f813f49d6d28c532dc4b104084f60ff382337f184698fcd6e70ab9efad977c1 || goto error
-call :downloadfile "qttranslations-everywhere-src-%QT%.zip" "https://download.qt.io/official_releases/qt/%QTMINOR%/%QT%/submodules/qttranslations-everywhere-src-%QT%.zip" 91c33d9946279c9c613b02e52a33df610cc01d13ea6e321b4c4d8ee708b9a03e || goto error
+call :downloadfile "%SDL%.zip" "https://libsdl.org/release/%SDL%.zip" ec855bcd815b4b63d0c958c42c2923311c656227d6e0c1ae1e721406d346444b || goto error
+call :downloadfile "qtbase-everywhere-src-%QT%.zip" "https://download.qt.io/official_releases/qt/%QTMINOR%/%QT%/submodules/qtbase-everywhere-src-%QT%.zip" e22d997bd15b795a176c8da62c8c1da0a674eb534e02f7c01ca507bf11bce0c3 || goto error
+call :downloadfile "qtimageformats-everywhere-src-%QT%.zip" "https://download.qt.io/official_releases/qt/%QTMINOR%/%QT%/submodules/qtimageformats-everywhere-src-%QT%.zip" 247a0a58039275a5a4fb499a600a90f66dc6e00321bb6f86a9b8d8020344d853 || goto error
+call :downloadfile "qtsvg-everywhere-src-%QT%.zip" "https://download.qt.io/official_releases/qt/%QTMINOR%/%QT%/submodules/qtsvg-everywhere-src-%QT%.zip" 57bd332e5550ff70a852560c591b786b6ba587c5e41cb5ef91038d82db137ab9 || goto error
+call :downloadfile "qttools-everywhere-src-%QT%.zip" "https://download.qt.io/official_releases/qt/%QTMINOR%/%QT%/submodules/qttools-everywhere-src-%QT%.zip" c65a89140f5d68137ffec67d631ec97002fb37077d9b4eb4ee45cbec39b1c38a || goto error
+call :downloadfile "qttranslations-everywhere-src-%QT%.zip" "https://download.qt.io/official_releases/qt/%QTMINOR%/%QT%/submodules/qttranslations-everywhere-src-%QT%.zip" 30a8e7773e1f274557e049a97f158b808f344247da03ae5240e4956c81d51cd5 || goto error
 call :downloadfile "zlib%ZLIBSHORT%.zip" "https://zlib.net/zlib%ZLIBSHORT%.zip" 72af66d44fcc14c22013b46b814d5d2514673dda3d115e64b690c1ad636e7b17 || goto error
 call :downloadfile "zstd-%ZSTD%.zip" "https://github.com/facebook/zstd/archive/refs/tags/v%ZSTD%.zip" 3b1c3b46e416d36931efd34663122d7f51b550c87f74de2d38249516fe7d8be5 || goto error
-call :downloadfile "zstd-fd5f8106a58601a963ee816e6a57aa7c61fafc53.patch" https://github.com/facebook/zstd/commit/fd5f8106a58601a963ee816e6a57aa7c61fafc53.patch 675f144b11f8ab2424b64bed8ccdca5d3f35b9326046fa7a883925dd180f0651 || goto error
+call :downloadfile "zstd-fd5f8106a58601a963ee816e6a57aa7c61fafc53.patch" https://github.com/facebook/zstd/commit/fd5f8106a58601a963ee816e6a57aa7c61fafc53.patch 8df152f4969b308546306c074628de761f0b80265de7de534e3822fab22d7535 || goto error
 
 call :downloadfile "shaderc-%SHADERC%.zip" "https://github.com/google/shaderc/archive/refs/tags/v%SHADERC%.zip" 6c9f42ed6bf42750f5369b089909abfdcf0101488b4a1f41116d5159d00af8e7 || goto error
 call :downloadfile "shaderc-glslang-%SHADERC_GLSLANG%.zip" "https://github.com/KhronosGroup/glslang/archive/%SHADERC_GLSLANG%.zip" 03ad8a6fa987af4653d0cfe6bdaed41bcf617f1366a151fb1574da75950cd3e8 || goto error

.github/workflows/scripts/windows/build-dependencies.bat

@@ -40,14 +40,14 @@ set "PATH=%PATH%;%INSTALLDIR%\bin"
 
 cd "%BUILDDIR%"
 
-set FREETYPE=2.13.2
-set HARFBUZZ=8.3.1
+set FREETYPE=2.13.3
+set HARFBUZZ=10.0.1
 set LIBJPEG=9f
 set LIBPNG=1643
 set LZ4=b8fd2d15309dd4e605070bd4486e26b6ef814e29
-set QT=6.8.0
+set QT=6.8.1
 set QTMINOR=6.8
-set SDL=SDL2-2.30.8
+set SDL=SDL2-2.30.9
 set WEBP=1.4.0
 set ZLIB=1.3.1
 set ZLIBSHORT=131
@@ -58,21 +58,21 @@ set SHADERC_GLSLANG=142052fa30f9eca191aa9dcf65359fcaed09eeec
 set SHADERC_SPIRVHEADERS=5e3ad389ee56fca27c9705d093ae5387ce404df4
 set SHADERC_SPIRVTOOLS=dd4b663e13c07fea4fbb3f70c1c91c86731099f7
 
-call :downloadfile "freetype-%FREETYPE%.tar.gz" https://sourceforge.net/projects/freetype/files/freetype2/%FREETYPE%/freetype-%FREETYPE%.tar.gz/download 1ac27e16c134a7f2ccea177faba19801131116fd682efc1f5737037c5db224b5 || goto error
-call :downloadfile "harfbuzz-%HARFBUZZ%.zip" https://github.com/harfbuzz/harfbuzz/archive/refs/tags/%HARFBUZZ%.zip b2bc56184ae37324bc4829fde7d3f9e6916866ad711ee85792e457547c9fd127 || goto error
+call :downloadfile "freetype-%FREETYPE%.tar.gz" https://sourceforge.net/projects/freetype/files/freetype2/%FREETYPE%/freetype-%FREETYPE%.tar.gz/download 5c3a8e78f7b24c20b25b54ee575d6daa40007a5f4eea2845861c3409b3021747 || goto error
+call :downloadfile "harfbuzz-%HARFBUZZ%.zip" https://github.com/harfbuzz/harfbuzz/archive/refs/tags/%HARFBUZZ%.zip 8adf9f5a4b6022aa2744f45c89ce347df46fea8403e99f01d650b11c417d0aa8 || goto error
 call :downloadfile "lpng%LIBPNG%.zip" https://download.sourceforge.net/libpng/lpng1643.zip fc466a1e638e635d6c66363bdf3f38555b81b0141d0b06ba45b49ccca327436d || goto error
 call :downloadfile "jpegsr%LIBJPEG%.zip" https://ijg.org/files/jpegsr%LIBJPEG%.zip 6255da8c89e09d694e6800688c76145eb6870a76ac0d36c74fccd61b3940aafa || goto error
 call :downloadfile "libwebp-%WEBP%.tar.gz" "https://storage.googleapis.com/downloads.webmproject.org/releases/webp/libwebp-%WEBP%.tar.gz" 61f873ec69e3be1b99535634340d5bde750b2e4447caa1db9f61be3fd49ab1e5 || goto error
 call :downloadfile "lz4-%LZ4%.zip" "https://github.com/lz4/lz4/archive/%LZ4%.zip" 0c33119688d6b180c7e760b0acd70059222389cfd581632623784bee27e51a31 || goto error
-call :downloadfile "%SDL%.zip" "https://libsdl.org/release/%SDL%.zip" abe2921dffcb25d39d270454810b211a9f47be3e5e802bc45e7d058f286a325e || goto error
-call :downloadfile "qtbase-everywhere-src-%QT%.zip" "https://download.qt.io/official_releases/qt/%QTMINOR%/%QT%/submodules/qtbase-everywhere-src-%QT%.zip" c3b41915341d853b6374cf93f1fcced2c8e4be9360f29c656960e1d0d15046a3 || goto error
-call :downloadfile "qtimageformats-everywhere-src-%QT%.zip" "https://download.qt.io/official_releases/qt/%QTMINOR%/%QT%/submodules/qtimageformats-everywhere-src-%QT%.zip" 809081a7bdf7e48262fbe9437e4e756df6ad2649433e803c4040026e650d7c91 || goto error
-call :downloadfile "qtsvg-everywhere-src-%QT%.zip" "https://download.qt.io/official_releases/qt/%QTMINOR%/%QT%/submodules/qtsvg-everywhere-src-%QT%.zip" 89f1ef4595f68c3d34c63a7c1c4ce475e701e103f0473f3fd0718a2e5234de6e || goto error
-call :downloadfile "qttools-everywhere-src-%QT%.zip" "https://download.qt.io/official_releases/qt/%QTMINOR%/%QT%/submodules/qttools-everywhere-src-%QT%.zip" 3f813f49d6d28c532dc4b104084f60ff382337f184698fcd6e70ab9efad977c1 || goto error
-call :downloadfile "qttranslations-everywhere-src-%QT%.zip" "https://download.qt.io/official_releases/qt/%QTMINOR%/%QT%/submodules/qttranslations-everywhere-src-%QT%.zip" 91c33d9946279c9c613b02e52a33df610cc01d13ea6e321b4c4d8ee708b9a03e || goto error
+call :downloadfile "%SDL%.zip" "https://libsdl.org/release/%SDL%.zip" ec855bcd815b4b63d0c958c42c2923311c656227d6e0c1ae1e721406d346444b || goto error
+call :downloadfile "qtbase-everywhere-src-%QT%.zip" "https://download.qt.io/official_releases/qt/%QTMINOR%/%QT%/submodules/qtbase-everywhere-src-%QT%.zip" e22d997bd15b795a176c8da62c8c1da0a674eb534e02f7c01ca507bf11bce0c3 || goto error
+call :downloadfile "qtimageformats-everywhere-src-%QT%.zip" "https://download.qt.io/official_releases/qt/%QTMINOR%/%QT%/submodules/qtimageformats-everywhere-src-%QT%.zip" 247a0a58039275a5a4fb499a600a90f66dc6e00321bb6f86a9b8d8020344d853 || goto error
+call :downloadfile "qtsvg-everywhere-src-%QT%.zip" "https://download.qt.io/official_releases/qt/%QTMINOR%/%QT%/submodules/qtsvg-everywhere-src-%QT%.zip" 57bd332e5550ff70a852560c591b786b6ba587c5e41cb5ef91038d82db137ab9 || goto error
+call :downloadfile "qttools-everywhere-src-%QT%.zip" "https://download.qt.io/official_releases/qt/%QTMINOR%/%QT%/submodules/qttools-everywhere-src-%QT%.zip" c65a89140f5d68137ffec67d631ec97002fb37077d9b4eb4ee45cbec39b1c38a || goto error
+call :downloadfile "qttranslations-everywhere-src-%QT%.zip" "https://download.qt.io/official_releases/qt/%QTMINOR%/%QT%/submodules/qttranslations-everywhere-src-%QT%.zip" 30a8e7773e1f274557e049a97f158b808f344247da03ae5240e4956c81d51cd5 || goto error
 call :downloadfile "zlib%ZLIBSHORT%.zip" "https://zlib.net/zlib%ZLIBSHORT%.zip" 72af66d44fcc14c22013b46b814d5d2514673dda3d115e64b690c1ad636e7b17 || goto error
 call :downloadfile "zstd-%ZSTD%.zip" "https://github.com/facebook/zstd/archive/refs/tags/v%ZSTD%.zip" 3b1c3b46e416d36931efd34663122d7f51b550c87f74de2d38249516fe7d8be5 || goto error
-call :downloadfile "zstd-fd5f8106a58601a963ee816e6a57aa7c61fafc53.patch" https://github.com/facebook/zstd/commit/fd5f8106a58601a963ee816e6a57aa7c61fafc53.patch 675f144b11f8ab2424b64bed8ccdca5d3f35b9326046fa7a883925dd180f0651 || goto error
+call :downloadfile "zstd-fd5f8106a58601a963ee816e6a57aa7c61fafc53.patch" https://github.com/facebook/zstd/commit/fd5f8106a58601a963ee816e6a57aa7c61fafc53.patch 8df152f4969b308546306c074628de761f0b80265de7de534e3822fab22d7535 || goto error
 
 call :downloadfile "shaderc-%SHADERC%.zip" "https://github.com/google/shaderc/archive/refs/tags/v%SHADERC%.zip" 6c9f42ed6bf42750f5369b089909abfdcf0101488b4a1f41116d5159d00af8e7 || goto error
 call :downloadfile "shaderc-glslang-%SHADERC_GLSLANG%.zip" "https://github.com/KhronosGroup/glslang/archive/%SHADERC_GLSLANG%.zip" 03ad8a6fa987af4653d0cfe6bdaed41bcf617f1366a151fb1574da75950cd3e8 || goto error

.github/workflows/windows_build_qt.yml

@@ -100,7 +100,7 @@ jobs:
         uses: actions/cache@v4
         with:
           path: deps
-          key: ${{ inputs.os }} ${{ inputs.platform }} deps ${{ hashFiles('.github/workflows/scripts/windows/build-dependencies.bat') }}
+          key: ${{ inputs.os }} ${{ inputs.platform }} deps ${{ hashFiles('.github/workflows/scripts/windows/build-dependencies.bat', '.github/workflows/scripts/common/*.patch') }}
 
       - name: Build Dependencies
         if: steps.cache-deps.outputs.cache-hit != 'true'

3rdparty/ccc/src/ccc/elf.cpp

@@ -10,34 +10,35 @@ Result<ElfFile> ElfFile::parse(std::vector<u8> image)
 	ElfFile elf;
 	elf.image = std::move(image);
 	
-	const ElfIdentHeader* ident = get_packed<ElfIdentHeader>(elf.image, 0);
+	const ElfIdentHeader* ident = get_unaligned<ElfIdentHeader>(elf.image, 0);
 	CCC_CHECK(ident, "ELF ident header out of range.");
 	CCC_CHECK(ident->magic == CCC_FOURCC("\x7f\x45\x4c\x46"), "Not an ELF file.");
 	CCC_CHECK(ident->e_class == ElfIdentClass::B32, "Wrong ELF class (not 32 bit).");
 	
-	const ElfFileHeader* header = get_packed<ElfFileHeader>(elf.image, sizeof(ElfIdentHeader));
+	const ElfFileHeader* header = get_unaligned<ElfFileHeader>(elf.image, sizeof(ElfIdentHeader));
 	CCC_CHECK(header, "ELF file header out of range.");
 	elf.file_header = *header;
 	
-	const ElfSectionHeader* shstr_section_header = get_packed<ElfSectionHeader>(elf.image, header->shoff + header->shstrndx * sizeof(ElfSectionHeader));
+	const ElfSectionHeader* shstr_section_header =
+		get_unaligned<ElfSectionHeader>(elf.image, header->shoff + header->shstrndx * sizeof(ElfSectionHeader));
 	CCC_CHECK(shstr_section_header, "ELF section name header out of range.");
 	
 	for(u32 i = 0; i < header->shnum; i++) {
 		u64 header_offset = header->shoff + i * sizeof(ElfSectionHeader);
-		const ElfSectionHeader* section_header = get_packed<ElfSectionHeader>(elf.image, header_offset);
+		const ElfSectionHeader* section_header = get_unaligned<ElfSectionHeader>(elf.image, header_offset);
 		CCC_CHECK(section_header, "ELF section header out of range.");
 		
-		const char* name = get_string(elf.image, shstr_section_header->offset + section_header->name);
-		CCC_CHECK(section_header, "ELF section name out of range.");
+		std::optional<std::string_view> name = get_string(elf.image, shstr_section_header->offset + section_header->name);
+		CCC_CHECK(name.has_value(), "ELF section name out of range.");
 		
 		ElfSection& section = elf.sections.emplace_back();
-		section.name = name;
+		section.name = *name;
 		section.header = *section_header;
 	}
 	
 	for(u32 i = 0; i < header->phnum; i++) {
 		u64 header_offset = header->phoff + i * sizeof(ElfProgramHeader);
-		const ElfProgramHeader* program_header = get_packed<ElfProgramHeader>(elf.image, header_offset);
+		const ElfProgramHeader* program_header = get_unaligned<ElfProgramHeader>(elf.image, header_offset);
 		CCC_CHECK(program_header, "ELF program header out of range.");
 		
 		elf.segments.emplace_back(*program_header);
@@ -93,7 +94,7 @@ const ElfProgramHeader* ElfFile::entry_point_segment() const
 	return entry_segment;
 }
 
-Result<std::span<const u8>> ElfFile::get_virtual(u32 address, u32 size) const
+std::optional<std::span<const u8>> ElfFile::get_virtual(u32 address, u32 size) const
 {
 	u32 end_address = address + size;
 	
@@ -109,17 +110,19 @@ Result<std::span<const u8>> ElfFile::get_virtual(u32 address, u32 size) const
 		}
 	}
 	
-	return CCC_FAILURE("No ELF segment for address range 0x%x to 0x%x.", address, end_address);
+	return std::nullopt;
 }
 
-Result<void> ElfFile::copy_virtual(u8* dest, u32 address, u32 size) const
+bool ElfFile::copy_virtual(u8* dest, u32 address, u32 size) const
 {
-	Result<std::span<const u8>> block = get_virtual(address, size);
-	CCC_RETURN_IF_ERROR(block);
+	std::optional<std::span<const u8>> block = get_virtual(address, size);
+	if(!block.has_value()) {
+		return false;
+	}
 	
 	memcpy(dest, block->data(), size);
 	
-	return Result<void>();
+	return true;
 }
 
 }

3rdparty/ccc/src/ccc/elf.h

@@ -125,18 +125,20 @@ struct ElfFile {
 	const ElfProgramHeader* entry_point_segment() const;
 	
 	// Retrieve a block of data in an ELF file given its address and size.
-	Result<std::span<const u8>> get_virtual(u32 address, u32 size) const;
+	std::optional<std::span<const u8>> get_virtual(u32 address, u32 size) const;
 	
 	// Copy a block of data in an ELF file to the destination buffer given its
 	// address and size.
-	Result<void> copy_virtual(u8* dest, u32 address, u32 size) const;
+	bool copy_virtual(u8* dest, u32 address, u32 size) const;
 	
 	// Retrieve an object of type T from an ELF file given its address.
 	template <typename T>
-	Result<T> get_object_virtual(u32 address) const
+	std::optional<T> get_object_virtual(u32 address) const
 	{
-		Result<std::span<const u8>> result = get_virtual(address, sizeof(T));
-		CCC_RETURN_IF_ERROR(result);
+		std::optional<std::span<const u8>> result = get_virtual(address, sizeof(T));
+		if(!result.has_value()) {
+			return std::nullopt;
+		}
 		
 		return *(T*) result->data();
 	}
@@ -144,10 +146,12 @@ struct ElfFile {
 	// Retrieve an array of objects of type T from an ELF file given its
 	// address and element count.
 	template <typename T>
-	Result<std::span<const T>> get_array_virtual(u32 address, u32 element_count) const
+	std::optional<std::span<const T>> get_array_virtual(u32 address, u32 element_count) const
 	{
-		Result<std::span<const u8>> result = get_virtual(address, element_count * sizeof(T));
-		CCC_RETURN_IF_ERROR(result);
+		std::optional<std::span<const u8>> result = get_virtual(address, element_count * sizeof(T));
+		if(!result.has_value()) {
+			return std::nullopt;
+		}
 		
 		return std::span<const T>((T*) result->data(), (T*) (result->data() + result->size()));
 	}

3rdparty/ccc/src/ccc/elf_symtab.cpp

@@ -60,7 +60,7 @@ Result<void> import_symbols(
 	DemanglerFunctions demangler)
 {
 	for(u32 i = 0; i < symtab.size() / sizeof(Symbol); i++) {
-		const Symbol* symbol = get_packed<Symbol>(symtab, i * sizeof(Symbol));
+		const Symbol* symbol = get_unaligned<Symbol>(symtab, i * sizeof(Symbol));
 		CCC_ASSERT(symbol);
 		
 		Address address;
@@ -86,13 +86,14 @@ Result<void> import_symbols(
 			}
 		}
 		
-		const char* string = get_string(strtab, symbol->name);
-		CCC_CHECK(string, "Symbol string out of range.");
+		std::optional<std::string_view> string_view = get_string(strtab, symbol->name);
+		CCC_CHECK(string_view.has_value(), "Symbol string out of range.");
+		std::string string(*string_view);
 		
 		switch(symbol->type()) {
 			case SymbolType::NOTYPE: {
 				Result<Label*> label = database.labels.create_symbol(
-					string, group.source, group.module_symbol, address, importer_flags, demangler);
+					std::move(string), group.source, group.module_symbol, address, importer_flags, demangler);
 				CCC_RETURN_IF_ERROR(label);
 				
 				// These symbols get emitted at the same addresses as functions
@@ -108,7 +109,7 @@ Result<void> import_symbols(
 			case SymbolType::OBJECT: {
 				if(symbol->size != 0) {
 					Result<GlobalVariable*> global_variable = database.global_variables.create_symbol(
-						string, group.source, group.module_symbol, address, importer_flags, demangler);
+						std::move(string), group.source, group.module_symbol, address, importer_flags, demangler);
 					CCC_RETURN_IF_ERROR(global_variable);
 					
 					if(*global_variable) {
@@ -116,7 +117,7 @@ Result<void> import_symbols(
 					}
 				} else {
 					Result<Label*> label = database.labels.create_symbol(
-						string, group.source, group.module_symbol, address, importer_flags, demangler);
+						std::move(string), group.source, group.module_symbol, address, importer_flags, demangler);
 					CCC_RETURN_IF_ERROR(label);
 				}
 				
@@ -124,7 +125,7 @@ Result<void> import_symbols(
 			}
 			case SymbolType::FUNC: {
 				Result<Function*> function = database.functions.create_symbol(
-					string, group.source, group.module_symbol, address, importer_flags, demangler);
+					std::move(string), group.source, group.module_symbol, address, importer_flags, demangler);
 				CCC_RETURN_IF_ERROR(function);
 				
 				if(*function) {
@@ -135,7 +136,7 @@ Result<void> import_symbols(
 			}
 			case SymbolType::FILE: {
 				Result<SourceFile*> source_file = database.source_files.create_symbol(
-					string, group.source, group.module_symbol);
+					std::move(string), group.source, group.module_symbol);
 				CCC_RETURN_IF_ERROR(source_file);
 				
 				break;
@@ -153,18 +154,18 @@ Result<void> print_symbol_table(FILE* out, std::span<const u8> symtab, std::span
 	fprintf(out, "   Num:    Value  Size Type    Bind   Vis      Ndx Name\n");
 	
 	for(u32 i = 0; i < symtab.size() / sizeof(Symbol); i++) {
-		const Symbol* symbol = get_packed<Symbol>(symtab, i * sizeof(Symbol));
+		const Symbol* symbol = get_unaligned<Symbol>(symtab, i * sizeof(Symbol));
 		CCC_ASSERT(symbol);
 		
 		const char* type = symbol_type_to_string(symbol->type());
 		const char* bind = symbol_bind_to_string(symbol->bind());
 		const char* visibility = symbol_visibility_to_string(symbol->visibility());
 		
-		const char* string = get_string(strtab, symbol->name);
-		CCC_CHECK(string, "Symbol string out of range.");
+		std::optional<std::string_view> string = get_string(strtab, symbol->name);
+		CCC_CHECK(string.has_value(), "Symbol string out of range.");
 		
 		fprintf(out, "%6u: %08x %5u %-7s %-7s %-7s %3u %s\n",
-			i, symbol->value, symbol->size, type, bind, visibility, symbol->shndx, string);
+			i, symbol->value, symbol->size, type, bind, visibility, symbol->shndx, string->data());
 		
 	}
 	

3rdparty/ccc/src/ccc/mdebug_section.cpp

@@ -90,7 +90,7 @@ Result<void> SymbolTableReader::init(std::span<const u8> elf, s32 section_offset
 	m_elf = elf;
 	m_section_offset = section_offset;
 	
-	m_hdrr = get_packed<SymbolicHeader>(m_elf, m_section_offset);
+	m_hdrr = get_unaligned<SymbolicHeader>(m_elf, m_section_offset);
 	CCC_CHECK(m_hdrr != nullptr, "MIPS debug section header out of bounds.");
 	CCC_CHECK(m_hdrr->magic == 0x7009, "Invalid symbolic header.");
 	
@@ -116,7 +116,7 @@ Result<File> SymbolTableReader::parse_file(s32 index) const
 	File file;
 	
 	u64 fd_offset = m_hdrr->file_descriptors_offset + index * sizeof(FileDescriptor);
-	const FileDescriptor* fd_header = get_packed<FileDescriptor>(m_elf, fd_offset + m_fudge_offset);
+	const FileDescriptor* fd_header = get_unaligned<FileDescriptor>(m_elf, fd_offset + m_fudge_offset);
 	CCC_CHECK(fd_header != nullptr, "MIPS debug file descriptor out of bounds.");
 	CCC_CHECK(fd_header->f_big_endian == 0, "Not little endian or bad file descriptor table.");
 	
@@ -124,16 +124,16 @@ Result<File> SymbolTableReader::parse_file(s32 index) const
 	
 	s32 rel_raw_path_offset = fd_header->strings_offset + fd_header->file_path_string_offset;
 	s32 raw_path_offset = m_hdrr->local_strings_offset + rel_raw_path_offset + m_fudge_offset;
-	const char* command_line_path = get_string(m_elf, raw_path_offset);
-	if(command_line_path) {
-		file.command_line_path = command_line_path;
+	std::optional<std::string_view> command_line_path = get_string(m_elf, raw_path_offset);
+	if(command_line_path.has_value()) {
+		file.command_line_path = *command_line_path;
 	}
 	
 	// Parse local symbols.
 	for(s64 j = 0; j < fd_header->symbol_count; j++) {
 		u64 rel_symbol_offset = (fd_header->isym_base + j) * sizeof(SymbolHeader);
 		u64 symbol_offset = m_hdrr->local_symbols_offset + rel_symbol_offset + m_fudge_offset;
-		const SymbolHeader* symbol_header = get_packed<SymbolHeader>(m_elf, symbol_offset);
+		const SymbolHeader* symbol_header = get_unaligned<SymbolHeader>(m_elf, symbol_offset);
 		CCC_CHECK(symbol_header != nullptr, "Symbol header out of bounds.");
 		
 		s32 strings_offset = m_hdrr->local_strings_offset + fd_header->strings_offset + m_fudge_offset;
@@ -155,7 +155,7 @@ Result<File> SymbolTableReader::parse_file(s32 index) const
 	for(s64 i = 0; i < fd_header->procedure_descriptor_count; i++) {
 		u64 rel_procedure_offset = (fd_header->ipd_first + i) * sizeof(ProcedureDescriptor);
 		u64 procedure_offset = m_hdrr->procedure_descriptors_offset + rel_procedure_offset + m_fudge_offset;
-		const ProcedureDescriptor* procedure_descriptor = get_packed<ProcedureDescriptor>(m_elf, procedure_offset);
+		const ProcedureDescriptor* procedure_descriptor = get_unaligned<ProcedureDescriptor>(m_elf, procedure_offset);
 		CCC_CHECK(procedure_descriptor != nullptr, "Procedure descriptor out of bounds.");
 		
 		CCC_CHECK(procedure_descriptor->symbol_index < file.symbols.size(), "Symbol index out of bounds.");
@@ -175,7 +175,7 @@ Result<std::vector<Symbol>> SymbolTableReader::parse_external_symbols() const
 	std::vector<Symbol> external_symbols;
 	for(s64 i = 0; i < m_hdrr->external_symbols_count; i++) {
 		u64 sym_offset = m_hdrr->external_symbols_offset + i * sizeof(ExternalSymbolHeader);
-		const ExternalSymbolHeader* external_header = get_packed<ExternalSymbolHeader>(m_elf, sym_offset + m_fudge_offset);
+		const ExternalSymbolHeader* external_header = get_unaligned<ExternalSymbolHeader>(m_elf, sym_offset + m_fudge_offset);
 		CCC_CHECK(external_header != nullptr, "External header out of bounds.");
 		
 		Result<Symbol> sym = get_symbol(external_header->symbol, m_elf, m_hdrr->external_strings_offset + m_fudge_offset);
@@ -351,9 +351,9 @@ static Result<Symbol> get_symbol(const SymbolHeader& header, std::span<const u8>
 {
 	Symbol symbol;
 	
-	const char* string = get_string(elf, strings_offset + header.iss);
-	CCC_CHECK(string, "Symbol has invalid string.");
-	symbol.string = string;
+	std::optional<std::string_view> string = get_string(elf, strings_offset + header.iss);
+	CCC_CHECK(string.has_value(), "Symbol has invalid string.");
+	symbol.string = string->data();
 	
 	symbol.value = header.value;
 	symbol.symbol_type = (SymbolType) header.st;

3rdparty/ccc/src/ccc/sndll.cpp

@@ -54,18 +54,19 @@ static const char* sndll_symbol_type_to_string(SNDLLSymbolType type);
 
 Result<SNDLLFile> parse_sndll_file(std::span<const u8> image, Address address, SNDLLType type)
 {
-	const u32* magic = get_packed<u32>(image, 0);
+	std::optional<u32> magic = copy_unaligned<u32>(image, 0);
+	CCC_CHECK(magic.has_value(), "Failed to read SNDLL header.");
 	CCC_CHECK((*magic & 0xffffff) == CCC_FOURCC("SNR\00"), "Not a SNDLL %s.", address.valid() ? "section" : "file");
 	
 	char version = *magic >> 24;
 	switch(version) {
 		case '1': {
-			const SNDLLHeaderV1* header = get_packed<SNDLLHeaderV1>(image, 0);
+			const SNDLLHeaderV1* header = get_unaligned<SNDLLHeaderV1>(image, 0);
 			CCC_CHECK(header, "File too small to contain SNDLL V1 header.");
 			return parse_sndll_common(image, address, type, header->common, SNDLL_V1);
 		}
 		case '2': {
-			const SNDLLHeaderV2* header = get_packed<SNDLLHeaderV2>(image, 0);
+			const SNDLLHeaderV2* header = get_unaligned<SNDLLHeaderV2>(image, 0);
 			CCC_CHECK(header, "File too small to contain SNDLL V2 header.");
 			return parse_sndll_common(image, address, type, header->common, SNDLL_V2);
 		}
@@ -84,10 +85,9 @@ static Result<SNDLLFile> parse_sndll_common(
 	sndll.version = version;
 	
 	if(common.elf_path) {
-		const char* elf_path = get_string(image, common.elf_path);
-		if(elf_path) {
-			sndll.elf_path = elf_path;
-		}
+		std::optional<std::string_view> elf_path = get_string(image, common.elf_path);
+		CCC_CHECK(elf_path.has_value(), "SNDLL header has invalid ELF path field.");
+		sndll.elf_path = *elf_path;
 	}
 	
 	CCC_CHECK(common.symbol_count < (32 * 1024 * 1024) / sizeof(SNDLLSymbol), "SNDLL symbol count is too high.");
@@ -95,10 +95,10 @@ static Result<SNDLLFile> parse_sndll_common(
 	
 	for(u32 i = 0; i < common.symbol_count; i++) {
 		u32 symbol_offset = common.symbols - address.get_or_zero() + i * sizeof(SNDLLSymbolHeader);
-		const SNDLLSymbolHeader* symbol_header = get_packed<SNDLLSymbolHeader>(image, symbol_offset);
+		const SNDLLSymbolHeader* symbol_header = get_unaligned<SNDLLSymbolHeader>(image, symbol_offset);
 		CCC_CHECK(symbol_header, "SNDLL symbol out of range.");
 		
-		const char* string = nullptr;
+		std::optional<std::string_view> string;
 		if(symbol_header->string) {
 			string = get_string(image, symbol_header->string - address.get_or_zero());
 		}
@@ -106,7 +106,9 @@ static Result<SNDLLFile> parse_sndll_common(
 		SNDLLSymbol& symbol = sndll.symbols.emplace_back();
 		symbol.type = symbol_header->type;
 		symbol.value = symbol_header->value;
-		symbol.string = string;
+		if(string.has_value()) {
+			symbol.string = *string;
+		}
 	}
 	
 	return sndll;

3rdparty/ccc/src/ccc/symbol_database.h

@@ -435,7 +435,7 @@ class Label : public Symbol {
 public:
 	static constexpr const SymbolDescriptor DESCRIPTOR = LABEL;
 	static constexpr const char* NAME = "Label";
-	static constexpr u32 FLAGS = WITH_ADDRESS_MAP;
+	static constexpr u32 FLAGS = WITH_ADDRESS_MAP | WITH_NAME_MAP;
 	
 	LabelHandle handle() const { return m_handle; }
 	

3rdparty/ccc/src/ccc/symbol_file.cpp

@@ -7,8 +7,8 @@ namespace ccc {
 
 Result<std::unique_ptr<SymbolFile>> parse_symbol_file(std::vector<u8> image, std::string file_name)
 {
-	const u32* magic = get_packed<u32>(image, 0);
-	CCC_CHECK(magic, "File too small.");
+	const std::optional<u32> magic = copy_unaligned<u32>(image, 0);
+	CCC_CHECK(magic.has_value(), "File too small.");
 	
 	std::unique_ptr<SymbolFile> symbol_file;
 	

3rdparty/ccc/src/ccc/symbol_table.cpp

@@ -100,8 +100,9 @@ Result<std::unique_ptr<SymbolTable>> create_elf_symbol_table(
 
 Result<ModuleHandle> import_symbol_tables(
 	SymbolDatabase& database,
-	std::string module_name,
 	const std::vector<std::unique_ptr<SymbolTable>>& symbol_tables,
+	std::string module_name,
+	Address base_address,
 	u32 importer_flags,
 	DemanglerFunctions demangler,
 	const std::atomic_bool* interrupt)
@@ -109,7 +110,8 @@ Result<ModuleHandle> import_symbol_tables(
 	Result<SymbolSourceHandle> module_source = database.get_symbol_source("Symbol Table Importer");
 	CCC_RETURN_IF_ERROR(module_source);
 	
-	Result<Module*> module_symbol = database.modules.create_symbol(std::move(module_name), *module_source, nullptr);
+	Result<Module*> module_symbol = database.modules.create_symbol(
+		std::move(module_name), base_address, *module_source, nullptr);
 	CCC_RETURN_IF_ERROR(module_symbol);
 	
 	ModuleHandle module_handle = (*module_symbol)->handle();

3rdparty/ccc/src/ccc/symbol_table.h

@@ -71,8 +71,9 @@ Result<std::unique_ptr<SymbolTable>> create_elf_symbol_table(
 // and to generate a module handle.
 Result<ModuleHandle> import_symbol_tables(
 	SymbolDatabase& database,
-	std::string module_name,
 	const std::vector<std::unique_ptr<SymbolTable>>& symbol_tables,
+	std::string module_name,
+	Address base_address,
 	u32 importer_flags,
 	DemanglerFunctions demangler,
 	const std::atomic_bool* interrupt);

3rdparty/ccc/src/ccc/util.cpp

@@ -51,14 +51,17 @@ void set_custom_error_callback(CustomErrorCallback callback)
 	custom_error_callback = callback;
 }
 
-const char* get_string(std::span<const u8> bytes, u64 offset)
+std::optional<std::string_view> get_string(std::span<const u8> bytes, u64 offset)
 {
-	for(const unsigned char* c = bytes.data() + offset; c < bytes.data() + bytes.size(); c++) {
-		if(*c == '\0') {
-			return (const char*) &bytes[offset];
+	for(u64 i = offset; i < bytes.size(); i++) {
+		if(bytes[i] == '\0') {
+			return std::string_view(
+				reinterpret_cast<const char*>(&bytes[offset]),
+				reinterpret_cast<const char*>(&bytes[i]));
 		}
 	}
-	return nullptr;
+	
+	return std::nullopt;
 }
 
 std::string merge_paths(const std::string& base, const std::string& path)

3rdparty/ccc/src/ccc/util.h

@@ -71,8 +71,15 @@ void set_custom_error_callback(CustomErrorCallback callback);
 		exit(1); \
 	}
 
+#define CCC_ABORT_IF_FALSE(condition, ...) \
+	if(!(condition)) { \
+		ccc::Error error = ccc::format_error(__FILE__, __LINE__, __VA_ARGS__); \
+		ccc::report_error(error); \
+		abort(); \
+	}
+
 #define CCC_ASSERT(condition) \
-	CCC_CHECK_FATAL(condition, #condition)
+	CCC_ABORT_IF_FALSE(condition, #condition)
 
 // The main error handling construct in CCC. This class is used to bundle
 // together a return value and a pointer to error information, so that errors
@@ -201,16 +208,38 @@ void warn_impl(const char* source_file, int source_line, const char* format, Arg
 #endif
 
 template <typename T>
-const T* get_packed(std::span<const u8> bytes, u64 offset)
+const T* get_aligned(std::span<const u8> bytes, u64 offset)
 {
-	if(offset + sizeof(T) <= bytes.size()) {
-		return reinterpret_cast<const T*>(&bytes[offset]);
-	} else {
+	if(offset > bytes.size() || bytes.size() - offset < sizeof(T) || offset % alignof(T) != 0) {
 		return nullptr;
 	}
+	
+	return reinterpret_cast<const T*>(&bytes[offset]);
 }
 
-const char* get_string(std::span<const u8> bytes, u64 offset);
+template <typename T>
+const T* get_unaligned(std::span<const u8> bytes, u64 offset)
+{
+	if(offset > bytes.size() || bytes.size() - offset < sizeof(T)) {
+		return nullptr;
+	}
+	
+	return reinterpret_cast<const T*>(&bytes[offset]);
+}
+
+template <typename T>
+std::optional<T> copy_unaligned(std::span<const u8> bytes, u64 offset)
+{
+	if(offset > bytes.size() || bytes.size() - offset < sizeof(T)) {
+		return std::nullopt;
+	}
+	
+	T value;
+	memcpy(&value, &bytes[offset], sizeof(T));
+	return value;
+}
+
+std::optional<std::string_view> get_string(std::span<const u8> bytes, u64 offset);
 
 #define CCC_BEGIN_END(x) (x).begin(), (x).end()
 #define CCC_ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))

3rdparty/cpuinfo/include/cpuinfo-mock.h

@@ -60,7 +60,7 @@ ssize_t CPUINFO_ABI cpuinfo_mock_read(int fd, void* buffer, size_t capacity);
 void CPUINFO_ABI cpuinfo_set_hwcap(uint32_t hwcap);
 #endif
 #if CPUINFO_ARCH_ARM
-void CPUINFO_ABI cpuinfo_set_hwcap2(uint32_t hwcap2);
+void CPUINFO_ABI cpuinfo_set_hwcap2(uint64_t hwcap2);
 #endif
 #endif
 

3rdparty/cpuinfo/include/cpuinfo.h

@@ -496,13 +496,19 @@ enum cpuinfo_uarch {
 	cpuinfo_uarch_cortex_x2 = 0x00300502,
 	/** ARM Cortex-X3. */
 	cpuinfo_uarch_cortex_x3 = 0x00300503,
+	/** ARM Cortex-X4. */
+	cpuinfo_uarch_cortex_x4 = 0x00300504,
 
 	/** ARM Cortex-A510. */
 	cpuinfo_uarch_cortex_a510 = 0x00300551,
+	/** ARM Cortex-A520. */
+	cpuinfo_uarch_cortex_a520 = 0x00300552,
 	/** ARM Cortex-A710. */
 	cpuinfo_uarch_cortex_a710 = 0x00300571,
 	/** ARM Cortex-A715. */
 	cpuinfo_uarch_cortex_a715 = 0x00300572,
+	/** ARM Cortex-A720. */
+	cpuinfo_uarch_cortex_a720 = 0x00300573,
 
 	/** Qualcomm Scorpion. */
 	cpuinfo_uarch_scorpion = 0x00400100,
@@ -1664,6 +1670,14 @@ struct cpuinfo_arm_isa {
 	bool sve;
 	bool sve2;
 	bool i8mm;
+	bool sme;
+	bool sme2;
+	bool sme2p1;
+	bool sme_i16i32;
+	bool sme_bi32i32;
+	bool sme_b16b16;
+	bool sme_f16f16;
+	uint32_t svelen;
 #endif
 	bool rdm;
 	bool fp16arith;
@@ -2036,6 +2050,71 @@ static inline bool cpuinfo_has_arm_sve2(void) {
 #endif
 }
 
+// Function to get the max SVE vector length on ARM CPU's which support SVE.
+static inline uint32_t cpuinfo_get_max_arm_sve_length(void) {
+#if CPUINFO_ARCH_ARM64
+	return cpuinfo_isa.svelen * 8; // bytes * 8 = bit length(vector length)
+#else
+	return 0;
+#endif
+}
+
+static inline bool cpuinfo_has_arm_sme(void) {
+#if CPUINFO_ARCH_ARM64
+	return cpuinfo_isa.sme;
+#else
+	return false;
+#endif
+}
+
+static inline bool cpuinfo_has_arm_sme2(void) {
+#if CPUINFO_ARCH_ARM64
+	return cpuinfo_isa.sme2;
+#else
+	return false;
+#endif
+}
+
+static inline bool cpuinfo_has_arm_sme2p1(void) {
+#if CPUINFO_ARCH_ARM64
+	return cpuinfo_isa.sme2p1;
+#else
+	return false;
+#endif
+}
+
+static inline bool cpuinfo_has_arm_sme_i16i32(void) {
+#if CPUINFO_ARCH_ARM64
+	return cpuinfo_isa.sme_i16i32;
+#else
+	return false;
+#endif
+}
+
+static inline bool cpuinfo_has_arm_sme_bi32i32(void) {
+#if CPUINFO_ARCH_ARM64
+	return cpuinfo_isa.sme_bi32i32;
+#else
+	return false;
+#endif
+}
+
+static inline bool cpuinfo_has_arm_sme_b16b16(void) {
+#if CPUINFO_ARCH_ARM64
+	return cpuinfo_isa.sme_b16b16;
+#else
+	return false;
+#endif
+}
+
+static inline bool cpuinfo_has_arm_sme_f16f16(void) {
+#if CPUINFO_ARCH_ARM64
+	return cpuinfo_isa.sme_f16f16;
+#else
+	return false;
+#endif
+}
+
 #if CPUINFO_ARCH_RISCV32 || CPUINFO_ARCH_RISCV64
 /* This structure is not a part of stable API. Use cpuinfo_has_riscv_* functions
  * instead. */

3rdparty/cpuinfo/src/arm/api.h

@@ -64,6 +64,7 @@ enum cpuinfo_arm_chipset_series {
 	cpuinfo_arm_chipset_series_telechips_tcc,
 	cpuinfo_arm_chipset_series_texas_instruments_omap,
 	cpuinfo_arm_chipset_series_unisoc_t,
+	cpuinfo_arm_chipset_series_unisoc_ums,
 	cpuinfo_arm_chipset_series_wondermedia_wm,
 	cpuinfo_arm_chipset_series_max,
 };

3rdparty/cpuinfo/src/arm/linux/aarch32-isa.c

@@ -24,7 +24,7 @@ void cpuinfo_set_wcid(uint32_t wcid) {
 
 void cpuinfo_arm_linux_decode_isa_from_proc_cpuinfo(
 	uint32_t features,
-	uint32_t features2,
+	uint64_t features2,
 	uint32_t midr,
 	uint32_t architecture_version,
 	uint32_t architecture_flags,
@@ -147,6 +147,8 @@ void cpuinfo_arm_linux_decode_isa_from_proc_cpuinfo(
 				"VDOT instructions disabled: cause occasional SIGILL on Spreadtrum SC9863A");
 		} else if (chipset->series == cpuinfo_arm_chipset_series_unisoc_t && chipset->model == 310) {
 			cpuinfo_log_warning("VDOT instructions disabled: cause occasional SIGILL on Unisoc T310");
+		} else if (chipset->series == cpuinfo_arm_chipset_series_unisoc_ums && chipset->model == 312) {
+			cpuinfo_log_warning("VDOT instructions disabled: cause occasional SIGILL on Unisoc UMS312");
 		} else {
 			switch (midr & (CPUINFO_ARM_MIDR_IMPLEMENTER_MASK | CPUINFO_ARM_MIDR_PART_MASK)) {
 				case UINT32_C(0x4100D0B0): /* Cortex-A76 */

3rdparty/cpuinfo/src/arm/linux/aarch64-isa.c

@@ -3,9 +3,11 @@
 #include <arm/linux/api.h>
 #include <cpuinfo/log.h>
 
+#include <sys/prctl.h>
+
 void cpuinfo_arm64_linux_decode_isa_from_proc_cpuinfo(
 	uint32_t features,
-	uint32_t features2,
+	uint64_t features2,
 	uint32_t midr,
 	const struct cpuinfo_arm_chipset chipset[restrict static 1],
 	struct cpuinfo_arm_isa isa[restrict static 1]) {
@@ -142,6 +144,27 @@ void cpuinfo_arm64_linux_decode_isa_from_proc_cpuinfo(
 	if (features2 & CPUINFO_ARM_LINUX_FEATURE2_SVE2) {
 		isa->sve2 = true;
 	}
+	if (features2 & CPUINFO_ARM_LINUX_FEATURE2_SME) {
+		isa->sme = true;
+	}
+	if (features2 & CPUINFO_ARM_LINUX_FEATURE2_SME2) {
+		isa->sme2 = true;
+	}
+	if (features2 & CPUINFO_ARM_LINUX_FEATURE2_SME2P1) {
+		isa->sme2p1 = true;
+	}
+	if (features2 & CPUINFO_ARM_LINUX_FEATURE2_SME_I16I32) {
+		isa->sme_i16i32 = true;
+	}
+	if (features2 & CPUINFO_ARM_LINUX_FEATURE2_SME_BI32I32) {
+		isa->sme_bi32i32 = true;
+	}
+	if (features2 & CPUINFO_ARM_LINUX_FEATURE2_SME_B16B16) {
+		isa->sme_b16b16 = true;
+	}
+	if (features2 & CPUINFO_ARM_LINUX_FEATURE2_SME_F16F16) {
+		isa->sme_f16f16 = true;
+	}
 	// SVEBF16 is set iff SVE and BF16 are both supported, but the SVEBF16
 	// feature flag was added in Linux kernel before the BF16 feature flag,
 	// so we check for either.
@@ -151,4 +174,21 @@ void cpuinfo_arm64_linux_decode_isa_from_proc_cpuinfo(
 	if (features & CPUINFO_ARM_LINUX_FEATURE_ASIMDFHM) {
 		isa->fhm = true;
 	}
+
+#ifndef PR_SVE_GET_VL
+#define PR_SVE_GET_VL 51
+#endif
+
+#ifndef PR_SVE_VL_LEN_MASK
+#define PR_SVE_VL_LEN_MASK 0xffff
+#endif
+
+	int ret = prctl(PR_SVE_GET_VL);
+	if (ret < 0) {
+		cpuinfo_log_warning("No SVE support on this machine");
+		isa->svelen = 0; // Assume no SVE support if the call fails
+	} else {
+		// Mask out the SVE vector length bits
+		isa->svelen = ret & PR_SVE_VL_LEN_MASK;
+	}
 }

3rdparty/cpuinfo/src/arm/linux/api.h

@@ -137,6 +137,13 @@ struct cpuinfo_arm_linux_proc_cpuinfo_cache {
 #define CPUINFO_ARM_LINUX_FEATURE2_DGH UINT32_C(0x00008000)
 #define CPUINFO_ARM_LINUX_FEATURE2_RNG UINT32_C(0x00010000)
 #define CPUINFO_ARM_LINUX_FEATURE2_BTI UINT32_C(0x00020000)
+#define CPUINFO_ARM_LINUX_FEATURE2_SME UINT32_C(0x00800000)
+#define CPUINFO_ARM_LINUX_FEATURE2_SME2 UINT64_C(0x0000002000000000)
+#define CPUINFO_ARM_LINUX_FEATURE2_SME2P1 UINT64_C(0x0000004000000000)
+#define CPUINFO_ARM_LINUX_FEATURE2_SME_I16I32 UINT64_C(0x0000008000000000)
+#define CPUINFO_ARM_LINUX_FEATURE2_SME_BI32I32 UINT64_C(0x0000010000000000)
+#define CPUINFO_ARM_LINUX_FEATURE2_SME_B16B16 UINT64_C(0x0000020000000000)
+#define CPUINFO_ARM_LINUX_FEATURE2_SME_F16F16 UINT64_C(0x0000040000000000)
 #endif
 
 #define CPUINFO_ARM_LINUX_VALID_ARCHITECTURE UINT32_C(0x00010000)
@@ -172,7 +179,7 @@ struct cpuinfo_arm_linux_processor {
 	struct cpuinfo_arm_linux_proc_cpuinfo_cache proc_cpuinfo_cache;
 #endif
 	uint32_t features;
-	uint32_t features2;
+	uint64_t features2;
 	/**
 	 * Main ID Register value.
 	 */
@@ -295,14 +302,14 @@ CPUINFO_INTERNAL bool cpuinfo_arm_linux_parse_proc_cpuinfo(
 #if CPUINFO_ARCH_ARM
 CPUINFO_INTERNAL bool cpuinfo_arm_linux_hwcap_from_getauxval(
 	uint32_t hwcap[restrict static 1],
-	uint32_t hwcap2[restrict static 1]);
+	uint64_t hwcap2[restrict static 1]);
 CPUINFO_INTERNAL bool cpuinfo_arm_linux_hwcap_from_procfs(
 	uint32_t hwcap[restrict static 1],
-	uint32_t hwcap2[restrict static 1]);
+	uint64_t hwcap2[restrict static 1]);
 
 CPUINFO_INTERNAL void cpuinfo_arm_linux_decode_isa_from_proc_cpuinfo(
 	uint32_t features,
-	uint32_t features2,
+	uint64_t features2,
 	uint32_t midr,
 	uint32_t architecture_version,
 	uint32_t architecture_flags,
@@ -311,11 +318,11 @@ CPUINFO_INTERNAL void cpuinfo_arm_linux_decode_isa_from_proc_cpuinfo(
 #elif CPUINFO_ARCH_ARM64
 CPUINFO_INTERNAL void cpuinfo_arm_linux_hwcap_from_getauxval(
 	uint32_t hwcap[restrict static 1],
-	uint32_t hwcap2[restrict static 1]);
+	uint64_t hwcap2[restrict static 1]);
 
 CPUINFO_INTERNAL void cpuinfo_arm64_linux_decode_isa_from_proc_cpuinfo(
 	uint32_t features,
-	uint32_t features2,
+	uint64_t features2,
 	uint32_t midr,
 	const struct cpuinfo_arm_chipset chipset[restrict static 1],
 	struct cpuinfo_arm_isa isa[restrict static 1]);

3rdparty/cpuinfo/src/arm/linux/chipset.c

@@ -85,6 +85,7 @@ static enum cpuinfo_arm_chipset_vendor chipset_series_vendor[cpuinfo_arm_chipset
 	[cpuinfo_arm_chipset_series_telechips_tcc] = cpuinfo_arm_chipset_vendor_telechips,
 	[cpuinfo_arm_chipset_series_texas_instruments_omap] = cpuinfo_arm_chipset_vendor_texas_instruments,
 	[cpuinfo_arm_chipset_series_unisoc_t] = cpuinfo_arm_chipset_vendor_unisoc,
+	[cpuinfo_arm_chipset_series_unisoc_ums] = cpuinfo_arm_chipset_vendor_unisoc,
 	[cpuinfo_arm_chipset_series_wondermedia_wm] = cpuinfo_arm_chipset_vendor_wondermedia,
 };
 
@@ -959,6 +960,70 @@ static bool match_t(const char* start, const char* end, struct cpuinfo_arm_chips
 	return true;
 }
 
+/**
+ * Tries to match, case-sentitively, /Unisoc UMS\d{3,4}/ signature for Unisoc UMS
+ * chipset. If match successful, extracts model information into \p chipset
+ * argument.
+ *
+ * @param start - start of the platform identifier (/proc/cpuinfo Hardware
+ * string, ro.product.board, ro.board.platform, or ro.chipname) to match.
+ * @param end - end of the platform identifier (/proc/cpuinfo Hardware string,
+ * ro.product.board, ro.board.platform, or ro.chipname) to match.
+ * @param[out] chipset - location where chipset information will be stored upon
+ * a successful match.
+ *
+ * @returns true if signature matched, false otherwise.
+ */
+static bool match_ums(const char* start, const char* end, struct cpuinfo_arm_chipset chipset[restrict static 1]) {
+	/* Expect 13-14 symbols: "Unisoc UMS" (10 symbols) + 3-4-digit model number
+	 */
+	const size_t length = end - start;
+	switch (length) {
+		case 13:
+		case 14:
+			break;
+		default:
+			return false;
+	}
+
+	/* Check that string starts with "Unisoc UMS". The first four characters
+	 * are loaded as 32-bit little endian word */
+	const uint32_t expected_unis = load_u32le(start);
+	if (expected_unis != UINT32_C(0x73696E55) /* "sinU" = reverse("Unis") */) {
+		return false;
+	}
+
+	/* The next four characters are loaded as 32-bit little endian word */
+	const uint32_t expected_oc_u = load_u32le(start + 4);
+	if (expected_oc_u != UINT32_C(0x5520636F) /* "U co" = reverse("oc U") */) {
+		return false;
+	}
+
+	/* The next four characters are loaded as 16-bit little endian word */
+	const uint16_t expected_ms = load_u16le(start + 8);
+	if (expected_ms != UINT16_C(0x534D) /* "SM" = reverse("MS") */) {
+		return false;
+	}
+
+	/* Validate and parse 3-4 digit model number */
+	uint32_t model = 0;
+	for (uint32_t i = 10; i < length; i++) {
+		const uint32_t digit = (uint32_t)(uint8_t)start[i] - '0';
+		if (digit >= 10) {
+			/* Not really a digit */
+			return false;
+		}
+		model = model * 10 + digit;
+	}
+
+	*chipset = (struct cpuinfo_arm_chipset){
+		.vendor = cpuinfo_arm_chipset_vendor_unisoc,
+		.series = cpuinfo_arm_chipset_series_unisoc_ums,
+		.model = model,
+	};
+	return true;
+}
+
 /**
  * Tries to match /lc\d{4}[a-z]?$/ signature for Leadcore LC chipsets.
  * If match successful, extracts model information into \p chipset argument.
@@ -2508,6 +2573,16 @@ struct cpuinfo_arm_chipset cpuinfo_arm_linux_decode_chipset_from_proc_cpuinfo_ha
 			return chipset;
 		}
 
+		/* Check Unisoc UMS signature */
+		if (match_ums(hardware, hardware_end, &chipset)) {
+			cpuinfo_log_debug(
+				"matched Unisoc UMS signature in /proc/cpuinfo Hardware string \"%.*s\"",
+				(int)hardware_length,
+				hardware);
+
+			return chipset;
+		}
+
 #if CPUINFO_ARCH_ARM
 		/* Check Marvell PXA signature */
 		if (match_pxa(hardware, hardware_end, &chipset)) {
@@ -3726,6 +3801,7 @@ static const char* chipset_series_string[cpuinfo_arm_chipset_series_max] = {
 	[cpuinfo_arm_chipset_series_telechips_tcc] = "TCC",
 	[cpuinfo_arm_chipset_series_texas_instruments_omap] = "OMAP",
 	[cpuinfo_arm_chipset_series_unisoc_t] = "T",
+	[cpuinfo_arm_chipset_series_unisoc_ums] = "UMS",
 	[cpuinfo_arm_chipset_series_wondermedia_wm] = "WM",
 };
 

3rdparty/cpuinfo/src/arm/linux/hwcap.c

@@ -31,8 +31,8 @@ void cpuinfo_set_hwcap(uint32_t hwcap) {
 	mock_hwcap = hwcap;
 }
 
-static uint32_t mock_hwcap2 = 0;
-void cpuinfo_set_hwcap2(uint32_t hwcap2) {
+static uint64_t mock_hwcap2 = 0;
+void cpuinfo_set_hwcap2(uint64_t hwcap2) {
 	mock_hwcap2 = hwcap2;
 }
 #endif
@@ -40,7 +40,7 @@ void cpuinfo_set_hwcap2(uint32_t hwcap2) {
 #if CPUINFO_ARCH_ARM
 typedef unsigned long (*getauxval_function_t)(unsigned long);
 
-bool cpuinfo_arm_linux_hwcap_from_getauxval(uint32_t hwcap[restrict static 1], uint32_t hwcap2[restrict static 1]) {
+bool cpuinfo_arm_linux_hwcap_from_getauxval(uint32_t hwcap[restrict static 1], uint64_t hwcap2[restrict static 1]) {
 #if CPUINFO_MOCK
 	*hwcap = mock_hwcap;
 	*hwcap2 = mock_hwcap2;
@@ -83,13 +83,13 @@ cleanup:
 }
 
 #ifdef __ANDROID__
-bool cpuinfo_arm_linux_hwcap_from_procfs(uint32_t hwcap[restrict static 1], uint32_t hwcap2[restrict static 1]) {
+bool cpuinfo_arm_linux_hwcap_from_procfs(uint32_t hwcap[restrict static 1], uint64_t hwcap2[restrict static 1]) {
 #if CPUINFO_MOCK
 	*hwcap = mock_hwcap;
 	*hwcap2 = mock_hwcap2;
 	return true;
 #else
-	uint32_t hwcaps[2] = {0, 0};
+	uint64_t hwcaps[2] = {0, 0};
 	bool result = false;
 	int file = -1;
 
@@ -113,7 +113,7 @@ bool cpuinfo_arm_linux_hwcap_from_procfs(uint32_t hwcap[restrict static 1], uint
 						hwcaps[0] = (uint32_t)elf_auxv.a_un.a_val;
 						break;
 					case AT_HWCAP2:
-						hwcaps[1] = (uint32_t)elf_auxv.a_un.a_val;
+						hwcaps[1] = (uint64_t)elf_auxv.a_un.a_val;
 						break;
 				}
 			} else {
@@ -141,13 +141,13 @@ cleanup:
 }
 #endif /* __ANDROID__ */
 #elif CPUINFO_ARCH_ARM64
-void cpuinfo_arm_linux_hwcap_from_getauxval(uint32_t hwcap[restrict static 1], uint32_t hwcap2[restrict static 1]) {
+void cpuinfo_arm_linux_hwcap_from_getauxval(uint32_t hwcap[restrict static 1], uint64_t hwcap2[restrict static 1]) {
 #if CPUINFO_MOCK
 	*hwcap = mock_hwcap;
 	*hwcap2 = mock_hwcap2;
 #else
 	*hwcap = (uint32_t)getauxval(AT_HWCAP);
-	*hwcap2 = (uint32_t)getauxval(AT_HWCAP2);
+	*hwcap2 = (uint64_t)getauxval(AT_HWCAP2);
 	return;
 #endif
 }

3rdparty/cpuinfo/src/arm/linux/init.c

@@ -247,7 +247,8 @@ void cpuinfo_arm_linux_init(void) {
 #endif
 
 #if CPUINFO_ARCH_ARM
-	uint32_t isa_features = 0, isa_features2 = 0;
+	uint32_t isa_features = 0;
+	uint64_t isa_features2 = 0;
 #ifdef __ANDROID__
 	/*
 	 * On Android before API 20, libc.so does not provide getauxval
@@ -299,7 +300,8 @@ void cpuinfo_arm_linux_init(void) {
 		&chipset,
 		&cpuinfo_isa);
 #elif CPUINFO_ARCH_ARM64
-	uint32_t isa_features = 0, isa_features2 = 0;
+	uint32_t isa_features = 0;
+	uint64_t isa_features2 = 0;
 	/* getauxval is always available on ARM64 Android */
 	cpuinfo_arm_linux_hwcap_from_getauxval(&isa_features, &isa_features2);
 	cpuinfo_arm64_linux_decode_isa_from_proc_cpuinfo(
@@ -333,18 +335,52 @@ void cpuinfo_arm_linux_init(void) {
 	}
 
 	/* Propagate topology group IDs among siblings */
+	bool detected_core_siblings_list_node = false;
+	bool detected_cluster_cpus_list_node = false;
 	for (uint32_t i = 0; i < arm_linux_processors_count; i++) {
 		if (!bitmask_all(arm_linux_processors[i].flags, CPUINFO_LINUX_FLAG_VALID)) {
 			continue;
 		}
 
-		if (arm_linux_processors[i].flags & CPUINFO_LINUX_FLAG_PACKAGE_ID) {
+		if (!bitmask_all(arm_linux_processors[i].flags, CPUINFO_LINUX_FLAG_PACKAGE_ID)) {
+			continue;
+		}
+
+		/* Use the cluster_cpus_list topology node if available. If not
+		 * found, cache the result to avoid repeatedly attempting to
+		 * read the non-existent paths.
+		 * */
+		if (!detected_core_siblings_list_node && !detected_cluster_cpus_list_node) {
+			if (cpuinfo_linux_detect_cluster_cpus(
+				    arm_linux_processors_count,
+				    i,
+				    (cpuinfo_siblings_callback)cluster_siblings_parser,
+				    arm_linux_processors)) {
+				detected_cluster_cpus_list_node = true;
+				continue;
+			} else {
+				detected_core_siblings_list_node = true;
+			}
+		}
+
+		/* The cached result above will guarantee only one of the blocks
+		 * below will execute, with a bias towards cluster_cpus_list.
+		 **/
+		if (detected_core_siblings_list_node) {
 			cpuinfo_linux_detect_core_siblings(
 				arm_linux_processors_count,
 				i,
 				(cpuinfo_siblings_callback)cluster_siblings_parser,
 				arm_linux_processors);
 		}
+
+		if (detected_cluster_cpus_list_node) {
+			cpuinfo_linux_detect_cluster_cpus(
+				arm_linux_processors_count,
+				i,
+				(cpuinfo_siblings_callback)cluster_siblings_parser,
+				arm_linux_processors);
+		}
 	}
 
 	/* Propagate all cluster IDs */

3rdparty/cpuinfo/src/arm/mach/init.c

@@ -399,6 +399,16 @@ void cpuinfo_arm_mach_init(void) {
 		cpuinfo_isa.i8mm = true;
 	}
 
+	const uint32_t has_feat_sme = get_sys_info_by_name("hw.optional.arm.FEAT_SME");
+	if (has_feat_sme != 0) {
+		cpuinfo_isa.sme = true;
+	}
+
+	const uint32_t has_feat_sme2 = get_sys_info_by_name("hw.optional.arm.FEAT_SME2");
+	if (has_feat_sme2 != 0) {
+		cpuinfo_isa.sme2 = true;
+	}
+
 	uint32_t num_clusters = 1;
 	for (uint32_t i = 0; i < mach_topology.cores; i++) {
 		cores[i] = (struct cpuinfo_core){

3rdparty/cpuinfo/src/freebsd/topology.c

@@ -24,8 +24,10 @@ static char* sysctl_str(const char* name) {
 	size_t value_size = 0;
 	if (sysctlbyname(name, NULL, &value_size, NULL, 0) != 0) {
 		cpuinfo_log_error("sysctlbyname(\"%s\") failed: %s", name, strerror(errno));
+		return NULL;
 	} else if (value_size <= 0) {
 		cpuinfo_log_error("sysctlbyname(\"%s\") returned invalid value size %zu", name, value_size);
+		return NULL;
 	}
 	value_size += 1;
 	char* value = calloc(value_size, 1);
@@ -52,29 +54,22 @@ struct cpuinfo_freebsd_topology cpuinfo_freebsd_detect_topology(void) {
 	if (!topology_spec) {
 		return topology;
 	}
-	const char* group_tag = "<group level=\"1\" cache-level=\"0\">";
-	char* p = strstr(topology_spec, group_tag);
-	while (p) {
-		const char* cpu_tag = "cpu count=\"";
-		char* q = strstr(p, cpu_tag);
-		if (q) {
-			p = q + strlen(cpu_tag);
-			topology.packages += atoi(p);
-		} else {
-			break;
-		}
-	}
-	if (topology.packages == 0) {
-		const char* group_tag = "<group level=\"1\"";
+	const char* group_tags[] = {"<group level=\"2\" cache-level=\"0\">", "<group level=\"1\" "};
+	for (size_t i = 0; i < sizeof(group_tags) / sizeof(group_tags[0]); i++) {
+		const char* group_tag = group_tags[i];
 		char* p = strstr(topology_spec, group_tag);
 		while (p) {
 			topology.packages += 1;
 			p++;
 			p = strstr(p, group_tag);
 		}
+		if (topology.packages > 0) {
+			break;
+		}
 	}
+
 	if (topology.packages == 0) {
-		cpuinfo_log_error("failed to parse topology_spec:%s", topology_spec);
+		cpuinfo_log_error("failed to parse topology_spec: %s", topology_spec);
 		free(topology_spec);
 		goto fail;
 	}
@@ -84,6 +79,7 @@ struct cpuinfo_freebsd_topology cpuinfo_freebsd_detect_topology(void) {
 		goto fail;
 	}
 	if (topology.cores < topology.packages) {
+		cpuinfo_log_error("invalid numbers of package and core: %d %d", topology.packages, topology.cores);
 		goto fail;
 	}
 	topology.threads_per_core = sysctl_int("kern.smp.threads_per_core");

3rdparty/cpuinfo/src/x86/freebsd/init.c

@@ -135,6 +135,10 @@ void cpuinfo_x86_freebsd_init(void) {
 	if (x86_processor.cache.l1i.size != 0 || x86_processor.cache.l1d.size != 0) {
 		/* Assume that threads on the same core share L1 */
 		threads_per_l1 = freebsd_topology.threads / freebsd_topology.cores;
+		if (threads_per_l1 == 0) {
+			cpuinfo_log_error("failed to detect threads_per_l1");
+			goto cleanup;
+		}
 		cpuinfo_log_warning(
 			"freebsd kernel did not report number of "
 			"threads sharing L1 cache; assume %" PRIu32,
@@ -154,6 +158,10 @@ void cpuinfo_x86_freebsd_init(void) {
 			 * the same package share L2 */
 			threads_per_l2 = freebsd_topology.threads / freebsd_topology.packages;
 		}
+		if (threads_per_l2 == 0) {
+			cpuinfo_log_error("failed to detect threads_per_l1");
+			goto cleanup;
+		}
 		cpuinfo_log_warning(
 			"freebsd kernel did not report number of "
 			"threads sharing L2 cache; assume %" PRIu32,
@@ -170,6 +178,10 @@ void cpuinfo_x86_freebsd_init(void) {
 		 * may be L4 cache as well)
 		 */
 		threads_per_l3 = freebsd_topology.threads / freebsd_topology.packages;
+		if (threads_per_l3 == 0) {
+			cpuinfo_log_error("failed to detect threads_per_l3");
+			goto cleanup;
+		}
 		cpuinfo_log_warning(
 			"freebsd kernel did not report number of "
 			"threads sharing L3 cache; assume %" PRIu32,
@@ -187,6 +199,10 @@ void cpuinfo_x86_freebsd_init(void) {
 		 * shared L4 (like on IBM POWER8).
 		 */
 		threads_per_l4 = freebsd_topology.threads;
+		if (threads_per_l4 == 0) {
+			cpuinfo_log_error("failed to detect threads_per_l4");
+			goto cleanup;
+		}
 		cpuinfo_log_warning(
 			"freebsd kernel did not report number of "
 			"threads sharing L4 cache; assume %" PRIu32,
@@ -203,7 +219,7 @@ void cpuinfo_x86_freebsd_init(void) {
 				"%" PRIu32 " L1I caches",
 				l1_count * sizeof(struct cpuinfo_cache),
 				l1_count);
-			return;
+			goto cleanup;
 		}
 		for (uint32_t c = 0; c < l1_count; c++) {
 			l1i[c] = (struct cpuinfo_cache){
@@ -230,7 +246,7 @@ void cpuinfo_x86_freebsd_init(void) {
 				"%" PRIu32 " L1D caches",
 				l1_count * sizeof(struct cpuinfo_cache),
 				l1_count);
-			return;
+			goto cleanup;
 		}
 		for (uint32_t c = 0; c < l1_count; c++) {
 			l1d[c] = (struct cpuinfo_cache){
@@ -257,7 +273,7 @@ void cpuinfo_x86_freebsd_init(void) {
 				"%" PRIu32 " L2 caches",
 				l2_count * sizeof(struct cpuinfo_cache),
 				l2_count);
-			return;
+			goto cleanup;
 		}
 		for (uint32_t c = 0; c < l2_count; c++) {
 			l2[c] = (struct cpuinfo_cache){
@@ -284,7 +300,7 @@ void cpuinfo_x86_freebsd_init(void) {
 				"%" PRIu32 " L3 caches",
 				l3_count * sizeof(struct cpuinfo_cache),
 				l3_count);
-			return;
+			goto cleanup;
 		}
 		for (uint32_t c = 0; c < l3_count; c++) {
 			l3[c] = (struct cpuinfo_cache){
@@ -311,7 +327,7 @@ void cpuinfo_x86_freebsd_init(void) {
 				"%" PRIu32 " L4 caches",
 				l4_count * sizeof(struct cpuinfo_cache),
 				l4_count);
-			return;
+			goto cleanup;
 		}
 		for (uint32_t c = 0; c < l4_count; c++) {
 			l4[c] = (struct cpuinfo_cache){

3rdparty/libzip/lib/compat.h

@@ -123,14 +123,64 @@ typedef char bool;
 #endif
 #endif
 
-#ifndef HAVE_FSEEKO
-#define fseeko(s, o, w) (fseek((s), (long int)(o), (w)))
+
+#if defined(HAVE__FSEEKI64) && defined(HAVE__FSTAT64) && defined(HAVE__SEEK64)
+/* Windows API using int64 */
+typedef zip_int64_t zip_off_t;
+typedef struct _stat64 zip_os_stat_t;
+#define zip_os_stat _stat64
+#define zip_os_fstat _fstat64
+#define zip_os_seek _fseeki64
+#define ZIP_FSEEK_MAX ZIP_INT64_MAX
+#define ZIP_FSEEK_MIN ZIP_INT64_MIN
+#else
+
+/* Normal API */
+#include <sys/stat.h>
+typedef struct stat zip_os_stat_t;
+#define zip_os_fstat fstat
+#define zip_os_stat stat
+
+#if defined(HAVE_FTELLO) && defined(HAVE_FSEEKO)
+/* Using off_t */
+typedef off_t zip_off_t;
+#if SIZEOF_OFF_T == 8
+#define ZIP_OFF_MAX ZIP_INT64_MAX
+#define ZIP_OFF_MIN ZIP_INT64_MIN
+#elif SIZEOF_OFF_T == 4
+#define ZIP_OFF_MAX ZIP_INT32_MAX
+#define ZIP_OFF_MIN ZIP_INT32_MIN
+#elif SIZEOF_OFF_T == 2
+#define ZIP_OFF_MAX ZIP_INT16_MAX
+#define ZIP_OFF_MIN ZIP_INT16_MIN
+#else
+#error unsupported size of off_t
+#endif
+
+#define ZIP_FSEEK_MAX ZIP_OFF_MAX
+#define ZIP_FSEEK_MIN ZIP_OFF_MIN
+
+#define zip_os_fseek fseeko
+#define zip_os_ftell ftello
+#else
+
+/* Using long */
+typedef long zip_off_t;
+#include <limits.h>
+#define ZIP_FSEEK_MAX LONG_MAX
+#define ZIP_FSEEK_MIN LONG_MIN
+
+#define zip_os_fseek fseek
+#define zip_os_ftell ftell
+#endif
+
 #endif
 
 #ifndef HAVE_FTELLO
 #define ftello(s) ((long)ftell((s)))
 #endif
 
+
 #ifdef HAVE_LOCALTIME_S
 #ifdef _WIN32
 /* Windows is incompatible to the C11 standard, hurray! */
@@ -179,27 +229,6 @@ typedef char bool;
 #endif
 #endif
 
-#if SIZEOF_OFF_T == 8
-#define ZIP_OFF_MAX ZIP_INT64_MAX
-#define ZIP_OFF_MIN ZIP_INT64_MIN
-#elif SIZEOF_OFF_T == 4
-#define ZIP_OFF_MAX ZIP_INT32_MAX
-#define ZIP_OFF_MIN ZIP_INT32_MIN
-#elif SIZEOF_OFF_T == 2
-#define ZIP_OFF_MAX ZIP_INT16_MAX
-#define ZIP_OFF_MIN ZIP_INT16_MIN
-#else
-#error unsupported size of off_t
-#endif
-
-#if defined(HAVE_FTELLO) && defined(HAVE_FSEEKO)
-#define ZIP_FSEEK_MAX ZIP_OFF_MAX
-#define ZIP_FSEEK_MIN ZIP_OFF_MIN
-#else
-#include <limits.h>
-#define ZIP_FSEEK_MAX LONG_MAX
-#define ZIP_FSEEK_MIN LONG_MIN
-#endif
 
 #ifndef SIZE_MAX
 #if SIZEOF_SIZE_T == 8

3rdparty/libzip/lib/zip_dirent.c

@@ -39,7 +39,6 @@
 #include <time.h>
 #include <zlib.h>
 
-#include "zip.h"
 #include "zipint.h"
 
 static zip_string_t *_zip_dirent_process_ef_utf_8(const zip_dirent_t *de, zip_uint16_t id, zip_string_t *str, bool check_consistency);
@@ -283,6 +282,7 @@ _zip_dirent_init(zip_dirent_t *de) {
     de->cloned = 0;
 
     de->crc_valid = true;
+    de->last_mod_mtime_valid = false;
     de->version_madeby = 63 | (ZIP_OPSYS_DEFAULT << 8);
     de->version_needed = 10; /* 1.0 */
     de->bitflags = 0;
@@ -1264,3 +1264,12 @@ zip_dirent_check_consistency(zip_dirent_t *dirent) {
     }
     return 0;
 }
+
+time_t zip_dirent_get_last_mod_mtime(zip_dirent_t *de) {
+    if (!de->last_mod_mtime_valid) {
+        de->last_mod_mtime = _zip_d2u_time(&de->last_mod);
+        de->last_mod_mtime_valid = true;
+    }
+
+    return de->last_mod_mtime;
+}

3rdparty/libzip/lib/zip_file_set_mtime.c

@@ -33,8 +33,7 @@
 
 #include "zipint.h"
 
-ZIP_EXTERN int
-zip_file_set_dostime(zip_t *za, zip_uint64_t idx, zip_uint16_t dtime, zip_uint16_t ddate, zip_flags_t flags) {
+static int zip_file_set_time(zip_t *za, zip_uint64_t idx, zip_uint16_t dtime, zip_uint16_t ddate, zip_flags_t flags, time_t *mtime) {
     zip_entry_t *e;
 
     if (_zip_get_dirent(za, idx, 0, NULL) == NULL) {
@@ -66,18 +65,29 @@ zip_file_set_dostime(zip_t *za, zip_uint64_t idx, zip_uint16_t dtime, zip_uint16
 
     e->changes->last_mod.time = dtime;
     e->changes->last_mod.date = ddate;
+    if (mtime != NULL) {
+        e->changes->last_mod_mtime = *mtime;
+        e->changes->last_mod_mtime_valid = true;
+    }
+    else {
+        e->changes->last_mod_mtime_valid = false;
+    }
     e->changes->changed |= ZIP_DIRENT_LAST_MOD;
 
     return 0;
 }
 
-ZIP_EXTERN int
-zip_file_set_mtime(zip_t *za, zip_uint64_t idx, time_t mtime, zip_flags_t flags) {
+ZIP_EXTERN int zip_file_set_dostime(zip_t *za, zip_uint64_t idx, zip_uint16_t dtime, zip_uint16_t ddate, zip_flags_t flags) {
+    return zip_file_set_time(za, idx, dtime, ddate, flags, NULL);
+}
+
+
+ZIP_EXTERN int zip_file_set_mtime(zip_t *za, zip_uint64_t idx, time_t mtime, zip_flags_t flags) {
     zip_dostime_t dostime;
 
     if (_zip_u2d_time(mtime, &dostime, &za->error) < 0) {
         return -1;
     }
 
-    return zip_file_set_dostime(za, idx, dostime.time, dostime.date, flags);
+    return zip_file_set_time(za, idx, dostime.time, dostime.date, flags, &mtime);
 }

3rdparty/libzip/lib/zip_new.c

@@ -68,6 +68,7 @@ _zip_new(zip_error_t *error) {
     za->nopen_source = za->nopen_source_alloc = 0;
     za->open_source = NULL;
     za->progress = NULL;
+    za->torrent_mtime = 0;
 
     return za;
 }

3rdparty/libzip/lib/zip_source_file_stdio.c

@@ -39,7 +39,6 @@
 #include <fcntl.h>
 #include <stdio.h>
 #include <stdlib.h>
-#include <sys/stat.h>
 
 #ifdef _WIN32
 #ifndef S_IWUSR
@@ -120,7 +119,7 @@ _zip_stdio_op_seek(zip_source_file_context_t *ctx, void *f, zip_int64_t offset,
     }
 #endif
 
-    if (fseeko((FILE *)f, (off_t)offset, whence) < 0) {
+    if (zip_os_fseek((FILE *)f, (zip_off_t)offset, whence) < 0) {
         zip_error_set(&ctx->error, ZIP_ER_SEEK, errno);
         return false;
     }
@@ -130,15 +129,15 @@ _zip_stdio_op_seek(zip_source_file_context_t *ctx, void *f, zip_int64_t offset,
 
 bool
 _zip_stdio_op_stat(zip_source_file_context_t *ctx, zip_source_file_stat_t *st) {
-    struct stat sb;
+    zip_os_stat_t sb;
 
     int ret;
 
     if (ctx->fname) {
-        ret = stat(ctx->fname, &sb);
+        ret = zip_os_stat(ctx->fname, &sb);
     }
     else {
-        ret = fstat(fileno((FILE *)ctx->f), &sb);
+        ret = zip_os_fstat(fileno((FILE *)ctx->f), &sb);
     }
 
     if (ret < 0) {
@@ -168,7 +167,7 @@ _zip_stdio_op_stat(zip_source_file_context_t *ctx, zip_source_file_stat_t *st) {
 
 zip_int64_t
 _zip_stdio_op_tell(zip_source_file_context_t *ctx, void *f) {
-    off_t offset = ftello((FILE *)f);
+    zip_off_t offset = zip_os_ftell((FILE *)f);
 
     if (offset < 0) {
         zip_error_set(&ctx->error, ZIP_ER_SEEK, errno);

3rdparty/libzip/lib/zip_source_file_stdio_named.c

@@ -178,9 +178,9 @@ _zip_stdio_op_create_temp_output_cloning(zip_source_file_context_t *ctx, zip_uin
     {
         int fd;
         struct file_clone_range range;
-        struct stat st;
+        zip_os_stat_t st;
         
-        if (fstat(fileno(ctx->f), &st) < 0) {
+        if (zip_os_fstat(fileno(ctx->f), &st) < 0) {
             zip_error_set(&ctx->error, ZIP_ER_TMPOPEN, errno);
             return -1;
         }
@@ -223,7 +223,7 @@ _zip_stdio_op_create_temp_output_cloning(zip_source_file_context_t *ctx, zip_uin
         ctx->tmpname = NULL;
         return -1;
     }
-    if (fseeko(tfp, (off_t)offset, SEEK_SET) < 0) {
+    if (zip_os_fseek(tfp, (zip_off_t)offset, SEEK_SET) < 0) {
         zip_error_set(&ctx->error, ZIP_ER_TMPOPEN, errno);
         (void)fclose(tfp);
         (void)remove(ctx->tmpname);
@@ -290,11 +290,11 @@ _zip_stdio_op_write(zip_source_file_context_t *ctx, const void *data, zip_uint64
 static int create_temp_file(zip_source_file_context_t *ctx, bool create_file) {
     char *temp;
     int mode;
-    struct stat st;
+    zip_os_stat_t st;
     int fd = 0;
     char *start, *end;
     
-    if (stat(ctx->fname, &st) == 0) {
+    if (zip_os_stat(ctx->fname, &st) == 0) {
         mode = st.st_mode;
     }
     else {
@@ -344,7 +344,7 @@ static int create_temp_file(zip_source_file_context_t *ctx, bool create_file) {
             }
         }
         else {
-            if (stat(temp, &st) < 0) {
+            if (zip_os_stat(temp, &st) < 0) {
                 if (errno == ENOENT) {
                     break;
                 }

3rdparty/libzip/lib/zip_stat_index.c

@@ -77,7 +77,7 @@ zip_stat_index(zip_t *za, zip_uint64_t index, zip_flags_t flags, zip_stat_t *st)
         }
 
         if (entry->changes != NULL && entry->changes->changed & ZIP_DIRENT_LAST_MOD) {
-            st->mtime = _zip_d2u_time(&de->last_mod);
+            st->mtime = zip_dirent_get_last_mod_mtime(de);
             st->valid |= ZIP_STAT_MTIME;
         }
     }
@@ -86,7 +86,7 @@ zip_stat_index(zip_t *za, zip_uint64_t index, zip_flags_t flags, zip_stat_t *st)
 
         st->crc = de->crc;
         st->size = de->uncomp_size;
-        st->mtime = _zip_d2u_time(&de->last_mod);
+        st->mtime = zip_dirent_get_last_mod_mtime(de);
         st->comp_size = de->comp_size;
         st->comp_method = (zip_uint16_t)de->comp_method;
         st->encryption_method = de->encryption_method;
@@ -97,9 +97,12 @@ zip_stat_index(zip_t *za, zip_uint64_t index, zip_flags_t flags, zip_stat_t *st)
     }
 
     if ((za->ch_flags & ZIP_AFL_WANT_TORRENTZIP) && (flags & ZIP_FL_UNCHANGED) == 0) {
-        zip_dostime_t dostime = {0xbc00, 0x2198};
+        if (za->torrent_mtime == 0) {
+            zip_dostime_t dostime = {0xbc00, 0x2198};
+            za->torrent_mtime = _zip_d2u_time(&dostime);
+        }
         st->comp_method = ZIP_CM_DEFLATE;
-        st->mtime = _zip_d2u_time(&dostime);
+        st->mtime = za->torrent_mtime;
         st->valid |= ZIP_STAT_MTIME | ZIP_STAT_COMP_METHOD;
         st->valid &= ~ZIP_STAT_COMP_SIZE;
     }

3rdparty/libzip/lib/zipint.h

@@ -314,6 +314,7 @@ struct zip {
     zip_progress_t *progress; /* progress callback for zip_close() */
 
     zip_uint32_t* write_crc; /* have _zip_write() compute CRC */
+    time_t torrent_mtime;
 };
 
 /* file in zip archive, part of API */
@@ -346,6 +347,7 @@ struct zip_dirent {
     bool cloned;                  /*      whether this instance is cloned, and thus shares non-changed strings */
 
     bool crc_valid; /*      if CRC is valid (sometimes not for encrypted archives) */
+    bool last_mod_mtime_valid;
 
     zip_uint16_t version_madeby;     /* (c)  version of creator */
     zip_uint16_t version_needed;     /* (cl) version needed to extract */
@@ -366,6 +368,8 @@ struct zip_dirent {
     zip_uint32_t compression_level; /*      level of compression to use (never valid in orig) */
     zip_uint16_t encryption_method; /*      encryption method, computed from other fields */
     char *password;                 /*      file specific encryption password */
+
+    time_t last_mod_mtime;          /*      cached last_mod in Unix time format */
 };
 
 /* zip archive central directory */
@@ -553,6 +557,7 @@ int zip_dirent_check_consistency(zip_dirent_t *dirent);
 zip_dirent_t *_zip_dirent_clone(const zip_dirent_t *);
 void _zip_dirent_free(zip_dirent_t *);
 void _zip_dirent_finalize(zip_dirent_t *);
+time_t zip_dirent_get_last_mod_mtime(zip_dirent_t *de);
 void _zip_dirent_init(zip_dirent_t *);
 bool _zip_dirent_needs_zip64(const zip_dirent_t *, zip_flags_t);
 zip_dirent_t *_zip_dirent_new(void);

3rdparty/lzma/include/7zCrc.h

@@ -1,5 +1,5 @@
 /* 7zCrc.h -- CRC32 calculation
-2023-04-02 : Igor Pavlov : Public domain */
+2024-01-22 : Igor Pavlov : Public domain */
 
 #ifndef ZIP7_INC_7Z_CRC_H
 #define ZIP7_INC_7Z_CRC_H
@@ -20,7 +20,8 @@ void Z7_FASTCALL CrcGenerateTable(void);
 UInt32 Z7_FASTCALL CrcUpdate(UInt32 crc, const void *data, size_t size);
 UInt32 Z7_FASTCALL CrcCalc(const void *data, size_t size);
 
-typedef UInt32 (Z7_FASTCALL *CRC_FUNC)(UInt32 v, const void *data, size_t size, const UInt32 *table);
+typedef UInt32 (Z7_FASTCALL *Z7_CRC_UPDATE_FUNC)(UInt32 v, const void *data, size_t size);
+Z7_CRC_UPDATE_FUNC z7_GetFunc_CrcUpdate(unsigned algo);
 
 EXTERN_C_END
 

3rdparty/lzma/include/7zTypes.h

@@ -1,5 +1,5 @@
 /* 7zTypes.h -- Basic types
-2023-04-02 : Igor Pavlov : Public domain */
+2024-01-24 : Igor Pavlov : Public domain */
 
 #ifndef ZIP7_7Z_TYPES_H
 #define ZIP7_7Z_TYPES_H
@@ -530,20 +530,20 @@ struct ISzAlloc
 #define Z7_CONTAINER_FROM_VTBL_CLS(ptr, type, m) Z7_CONTAINER_FROM_VTBL(ptr, type, m)
 */
 #if defined (__clang__) || defined(__GNUC__)
-#define Z7_DIAGNOSCTIC_IGNORE_BEGIN_CAST_QUAL \
+#define Z7_DIAGNOSTIC_IGNORE_BEGIN_CAST_QUAL \
   _Pragma("GCC diagnostic push") \
   _Pragma("GCC diagnostic ignored \"-Wcast-qual\"")
-#define Z7_DIAGNOSCTIC_IGNORE_END_CAST_QUAL \
+#define Z7_DIAGNOSTIC_IGNORE_END_CAST_QUAL \
   _Pragma("GCC diagnostic pop")
 #else
-#define Z7_DIAGNOSCTIC_IGNORE_BEGIN_CAST_QUAL
-#define Z7_DIAGNOSCTIC_IGNORE_END_CAST_QUAL
+#define Z7_DIAGNOSTIC_IGNORE_BEGIN_CAST_QUAL
+#define Z7_DIAGNOSTIC_IGNORE_END_CAST_QUAL
 #endif
 
 #define Z7_CONTAINER_FROM_VTBL_TO_DECL_VAR(ptr, type, m, p) \
-  Z7_DIAGNOSCTIC_IGNORE_BEGIN_CAST_QUAL \
+  Z7_DIAGNOSTIC_IGNORE_BEGIN_CAST_QUAL \
   type *p = Z7_CONTAINER_FROM_VTBL(ptr, type, m); \
-  Z7_DIAGNOSCTIC_IGNORE_END_CAST_QUAL
+  Z7_DIAGNOSTIC_IGNORE_END_CAST_QUAL
 
 #define Z7_CONTAINER_FROM_VTBL_TO_DECL_VAR_pp_vt_p(type) \
   Z7_CONTAINER_FROM_VTBL_TO_DECL_VAR(pp, type, vt, p)

3rdparty/lzma/include/7zVersion.h

@@ -1,7 +1,7 @@
-#define MY_VER_MAJOR 23
-#define MY_VER_MINOR 01
+#define MY_VER_MAJOR 24
+#define MY_VER_MINOR 8
 #define MY_VER_BUILD 0
-#define MY_VERSION_NUMBERS "23.01"
+#define MY_VERSION_NUMBERS "24.08"
 #define MY_VERSION MY_VERSION_NUMBERS
 
 #ifdef MY_CPU_NAME
@@ -10,12 +10,12 @@
   #define MY_VERSION_CPU MY_VERSION
 #endif
 
-#define MY_DATE "2023-06-20"
+#define MY_DATE "2024-08-11"
 #undef MY_COPYRIGHT
 #undef MY_VERSION_COPYRIGHT_DATE
 #define MY_AUTHOR_NAME "Igor Pavlov"
 #define MY_COPYRIGHT_PD "Igor Pavlov : Public domain"
-#define MY_COPYRIGHT_CR "Copyright (c) 1999-2023 Igor Pavlov"
+#define MY_COPYRIGHT_CR "Copyright (c) 1999-2024 Igor Pavlov"
 
 #ifdef USE_COPYRIGHT_CR
   #define MY_COPYRIGHT MY_COPYRIGHT_CR

3rdparty/lzma/include/Alloc.h

@@ -1,5 +1,5 @@
 /* Alloc.h -- Memory allocation functions
-2023-03-04 : Igor Pavlov : Public domain */
+2024-01-22 : Igor Pavlov : Public domain */
 
 #ifndef ZIP7_INC_ALLOC_H
 #define ZIP7_INC_ALLOC_H
@@ -22,6 +22,9 @@ void *MyAlloc(size_t size);
 void MyFree(void *address);
 void *MyRealloc(void *address, size_t size);
 
+void *z7_AlignedAlloc(size_t size);
+void  z7_AlignedFree(void *p);
+
 #ifdef _WIN32
 
 #ifdef Z7_LARGE_PAGES
@@ -33,12 +36,14 @@ void MidFree(void *address);
 void *BigAlloc(size_t size);
 void BigFree(void *address);
 
+/* #define Z7_BIG_ALLOC_IS_ZERO_FILLED */
+
 #else
 
-#define MidAlloc(size) MyAlloc(size)
-#define MidFree(address) MyFree(address)
-#define BigAlloc(size) MyAlloc(size)
-#define BigFree(address) MyFree(address)
+#define MidAlloc(size)    z7_AlignedAlloc(size)
+#define MidFree(address)  z7_AlignedFree(address)
+#define BigAlloc(size)    z7_AlignedAlloc(size)
+#define BigFree(address)  z7_AlignedFree(address)
 
 #endif
 

3rdparty/lzma/include/Bra.h

@@ -1,5 +1,5 @@
 /* Bra.h -- Branch converters for executables
-2023-04-02 : Igor Pavlov : Public domain */
+2024-01-20 : Igor Pavlov : Public domain */
 
 #ifndef ZIP7_INC_BRA_H
 #define ZIP7_INC_BRA_H
@@ -8,8 +8,12 @@
 
 EXTERN_C_BEGIN
 
-#define Z7_BRANCH_CONV_DEC(name)    z7_BranchConv_   ## name ## _Dec
-#define Z7_BRANCH_CONV_ENC(name)    z7_BranchConv_   ## name ## _Enc
+/* #define PPC BAD_PPC_11 // for debug */
+
+#define Z7_BRANCH_CONV_DEC_2(name)  z7_ ## name ## _Dec
+#define Z7_BRANCH_CONV_ENC_2(name)  z7_ ## name ## _Enc
+#define Z7_BRANCH_CONV_DEC(name)    Z7_BRANCH_CONV_DEC_2(BranchConv_ ## name)
+#define Z7_BRANCH_CONV_ENC(name)    Z7_BRANCH_CONV_ENC_2(BranchConv_ ## name)
 #define Z7_BRANCH_CONV_ST_DEC(name) z7_BranchConvSt_ ## name ## _Dec
 #define Z7_BRANCH_CONV_ST_ENC(name) z7_BranchConvSt_ ## name ## _Enc
 
@@ -20,19 +24,20 @@ typedef Z7_BRANCH_CONV_DECL(   (*z7_Func_BranchConv));
 typedef Z7_BRANCH_CONV_ST_DECL((*z7_Func_BranchConvSt));
 
 #define Z7_BRANCH_CONV_ST_X86_STATE_INIT_VAL 0
-Z7_BRANCH_CONV_ST_DECL(Z7_BRANCH_CONV_ST_DEC(X86));
-Z7_BRANCH_CONV_ST_DECL(Z7_BRANCH_CONV_ST_ENC(X86));
+Z7_BRANCH_CONV_ST_DECL (Z7_BRANCH_CONV_ST_DEC(X86));
+Z7_BRANCH_CONV_ST_DECL (Z7_BRANCH_CONV_ST_ENC(X86));
 
 #define Z7_BRANCH_FUNCS_DECL(name) \
-Z7_BRANCH_CONV_DECL(Z7_BRANCH_CONV_DEC(name)); \
-Z7_BRANCH_CONV_DECL(Z7_BRANCH_CONV_ENC(name));
+Z7_BRANCH_CONV_DECL (Z7_BRANCH_CONV_DEC_2(name)); \
+Z7_BRANCH_CONV_DECL (Z7_BRANCH_CONV_ENC_2(name));
 
-Z7_BRANCH_FUNCS_DECL(ARM64)
-Z7_BRANCH_FUNCS_DECL(ARM)
-Z7_BRANCH_FUNCS_DECL(ARMT)
-Z7_BRANCH_FUNCS_DECL(PPC)
-Z7_BRANCH_FUNCS_DECL(SPARC)
-Z7_BRANCH_FUNCS_DECL(IA64)
+Z7_BRANCH_FUNCS_DECL (BranchConv_ARM64)
+Z7_BRANCH_FUNCS_DECL (BranchConv_ARM)
+Z7_BRANCH_FUNCS_DECL (BranchConv_ARMT)
+Z7_BRANCH_FUNCS_DECL (BranchConv_PPC)
+Z7_BRANCH_FUNCS_DECL (BranchConv_SPARC)
+Z7_BRANCH_FUNCS_DECL (BranchConv_IA64)
+Z7_BRANCH_FUNCS_DECL (BranchConv_RISCV)
 
 /*
 These functions convert data that contain CPU instructions.
@@ -49,14 +54,14 @@ and one for decoding (_Enc/_Dec postfixes in function name).
 In params:
   data  : data buffer
   size  : size of data
-  pc    : current virtual Program Counter (Instruction Pinter) value
+  pc    : current virtual Program Counter (Instruction Pointer) value
 In/Out param:
   state : pointer to state variable (for X86 converter only)
 
 Return:
   The pointer to position in (data) buffer after last byte that was processed.
   If the caller calls converter again, it must call it starting with that position.
-  But the caller is allowed to move data in buffer. so pointer to
+  But the caller is allowed to move data in buffer. So pointer to
   current processed position also will be changed for next call.
   Also the caller must increase internal (pc) value for next call.
   
@@ -65,6 +70,7 @@ Each converter has some characteristics: Endian, Alignment, LookAhead.
   
   X86    little      1          4
   ARMT   little      2          2
+  RISCV  little      2          6
   ARM    little      4          0
   ARM64  little      4          0
   PPC     big        4          0

3rdparty/lzma/include/Compiler.h

@@ -1,5 +1,5 @@
 /* Compiler.h : Compiler specific defines and pragmas
-2023-04-02 : Igor Pavlov : Public domain */
+2024-01-22 : Igor Pavlov : Public domain */
 
 #ifndef ZIP7_INC_COMPILER_H
 #define ZIP7_INC_COMPILER_H
@@ -25,11 +25,79 @@
 #define Z7_MINGW
 #endif
 
+#if defined(__LCC__) && (defined(__MCST__) || defined(__e2k__))
+#define Z7_MCST_LCC
+#define Z7_MCST_LCC_VERSION (__LCC__ * 100 + __LCC_MINOR__)
+#endif
+
+/*
+#if defined(__AVX2__) \
+    || defined(Z7_GCC_VERSION) && (Z7_GCC_VERSION >= 40900) \
+    || defined(Z7_APPLE_CLANG_VERSION) && (Z7_APPLE_CLANG_VERSION >= 40600) \
+    || defined(Z7_LLVM_CLANG_VERSION) && (Z7_LLVM_CLANG_VERSION >= 30100) \
+    || defined(Z7_MSC_VER_ORIGINAL) && (Z7_MSC_VER_ORIGINAL >= 1800) \
+    || defined(__INTEL_COMPILER) && (__INTEL_COMPILER >= 1400)
+    #define Z7_COMPILER_AVX2_SUPPORTED
+  #endif
+#endif
+*/
+
 // #pragma GCC diagnostic ignored "-Wunknown-pragmas"
 
 #ifdef __clang__
 // padding size of '' with 4 bytes to alignment boundary
 #pragma GCC diagnostic ignored "-Wpadded"
+
+#if defined(Z7_LLVM_CLANG_VERSION) && (__clang_major__ == 13) \
+  && defined(__FreeBSD__)
+// freebsd:
+#pragma GCC diagnostic ignored "-Wexcess-padding"
+#endif
+
+#if __clang_major__ >= 16
+#pragma GCC diagnostic ignored "-Wunsafe-buffer-usage"
+#endif
+
+#if __clang_major__ == 13
+#if defined(__SIZEOF_POINTER__) && (__SIZEOF_POINTER__ == 16)
+// cheri
+#pragma GCC diagnostic ignored "-Wcapability-to-integer-cast"
+#endif
+#endif
+
+#if __clang_major__ == 13
+  // for <arm_neon.h>
+  #pragma GCC diagnostic ignored "-Wreserved-identifier"
+#endif
+
+#endif // __clang__
+
+#if defined(_WIN32) && defined(__clang__) && __clang_major__ >= 16
+// #pragma GCC diagnostic ignored "-Wcast-function-type-strict"
+#define Z7_DIAGNOSTIC_IGNORE_CAST_FUNCTION \
+  _Pragma("GCC diagnostic ignored \"-Wcast-function-type-strict\"")
+#else
+#define Z7_DIAGNOSTIC_IGNORE_CAST_FUNCTION
+#endif
+
+typedef void (*Z7_void_Function)(void);
+#if defined(__clang__) || defined(__GNUC__)
+#define Z7_CAST_FUNC_C  (Z7_void_Function)
+#elif defined(_MSC_VER) && _MSC_VER > 1920
+#define Z7_CAST_FUNC_C  (void *)
+// #pragma warning(disable : 4191) // 'type cast': unsafe conversion from 'FARPROC' to 'void (__cdecl *)()'
+#else
+#define Z7_CAST_FUNC_C
+#endif
+/*
+#if (defined(__GNUC__) && (__GNUC__ >= 8)) || defined(__clang__)
+  // #pragma GCC diagnostic ignored "-Wcast-function-type"
+#endif
+*/
+#ifdef __GNUC__
+#if defined(Z7_GCC_VERSION) && (Z7_GCC_VERSION >= 40000) && (Z7_GCC_VERSION < 70000)
+#pragma GCC diagnostic ignored "-Wstrict-aliasing"
+#endif
 #endif
 
 
@@ -101,7 +169,8 @@
     _Pragma("clang loop unroll(disable)") \
     _Pragma("clang loop vectorize(disable)")
   #define Z7_ATTRIB_NO_VECTORIZE
-#elif defined(__GNUC__) && (__GNUC__ >= 5)
+#elif defined(__GNUC__) && (__GNUC__ >= 5) \
+    && (!defined(Z7_MCST_LCC_VERSION) || (Z7_MCST_LCC_VERSION >= 12610))
   #define Z7_ATTRIB_NO_VECTORIZE __attribute__((optimize("no-tree-vectorize")))
   // __attribute__((optimize("no-unroll-loops")));
   #define Z7_PRAGMA_OPT_DISABLE_LOOP_UNROLL_VECTORIZE
@@ -142,15 +211,23 @@
 #endif
 
 
-#if (defined(Z7_CLANG_VERSION) && (Z7_CLANG_VERSION >= 36000))
-#define Z7_DIAGNOSCTIC_IGNORE_BEGIN_RESERVED_MACRO_IDENTIFIER \
+#if (defined(Z7_CLANG_VERSION) && (Z7_CLANG_VERSION >= 30600))
+
+#if (Z7_CLANG_VERSION < 130000)
+#define Z7_DIAGNOSTIC_IGNORE_BEGIN_RESERVED_MACRO_IDENTIFIER \
+  _Pragma("GCC diagnostic push") \
+  _Pragma("GCC diagnostic ignored \"-Wreserved-id-macro\"")
+#else
+#define Z7_DIAGNOSTIC_IGNORE_BEGIN_RESERVED_MACRO_IDENTIFIER \
   _Pragma("GCC diagnostic push") \
   _Pragma("GCC diagnostic ignored \"-Wreserved-macro-identifier\"")
-#define Z7_DIAGNOSCTIC_IGNORE_END_RESERVED_MACRO_IDENTIFIER \
+#endif
+
+#define Z7_DIAGNOSTIC_IGNORE_END_RESERVED_MACRO_IDENTIFIER \
   _Pragma("GCC diagnostic pop")
 #else
-#define Z7_DIAGNOSCTIC_IGNORE_BEGIN_RESERVED_MACRO_IDENTIFIER
-#define Z7_DIAGNOSCTIC_IGNORE_END_RESERVED_MACRO_IDENTIFIER
+#define Z7_DIAGNOSTIC_IGNORE_BEGIN_RESERVED_MACRO_IDENTIFIER
+#define Z7_DIAGNOSTIC_IGNORE_END_RESERVED_MACRO_IDENTIFIER
 #endif
 
 #define UNUSED_VAR(x) (void)x;

3rdparty/lzma/include/CpuArch.h

@@ -1,5 +1,5 @@
 /* CpuArch.h -- CPU specific code
-2023-04-02 : Igor Pavlov : Public domain */
+2024-06-17 : Igor Pavlov : Public domain */
 
 #ifndef ZIP7_INC_CPU_ARCH_H
 #define ZIP7_INC_CPU_ARCH_H
@@ -20,6 +20,7 @@ MY_CPU_64BIT means that processor can work with 64-bit registers.
   MY_CPU_64BIT doesn't mean that (sizeof(void *) == 8)
 */
 
+#if !defined(_M_ARM64EC)
 #if  defined(_M_X64) \
   || defined(_M_AMD64) \
   || defined(__x86_64__) \
@@ -35,6 +36,7 @@ MY_CPU_64BIT means that processor can work with 64-bit registers.
   #endif
   #define MY_CPU_64BIT
 #endif
+#endif
 
 
 #if  defined(_M_IX86) \
@@ -47,17 +49,26 @@ MY_CPU_64BIT means that processor can work with 64-bit registers.
 
 
 #if  defined(_M_ARM64) \
+  || defined(_M_ARM64EC) \
   || defined(__AARCH64EL__) \
   || defined(__AARCH64EB__) \
   || defined(__aarch64__)
   #define MY_CPU_ARM64
-  #ifdef __ILP32__
+#if   defined(__ILP32__) \
+   || defined(__SIZEOF_POINTER__) && (__SIZEOF_POINTER__ == 4)
     #define MY_CPU_NAME "arm64-32"
     #define MY_CPU_SIZEOF_POINTER 4
-  #else
+#elif defined(__SIZEOF_POINTER__) && (__SIZEOF_POINTER__ == 16)
+    #define MY_CPU_NAME "arm64-128"
+    #define MY_CPU_SIZEOF_POINTER 16
+#else
+#if defined(_M_ARM64EC)
+    #define MY_CPU_NAME "arm64ec"
+#else
     #define MY_CPU_NAME "arm64"
+#endif
     #define MY_CPU_SIZEOF_POINTER 8
-  #endif
+#endif
   #define MY_CPU_64BIT
 #endif
 
@@ -133,8 +144,36 @@ MY_CPU_64BIT means that processor can work with 64-bit registers.
 #endif
 
 
+#if   defined(__sparc__) \
+   || defined(__sparc)
+  #define MY_CPU_SPARC
+  #if  defined(__LP64__) \
+    || defined(_LP64) \
+    || defined(__SIZEOF_POINTER__) && (__SIZEOF_POINTER__ == 8)
+    #define MY_CPU_NAME "sparcv9"
+    #define MY_CPU_SIZEOF_POINTER 8
+    #define MY_CPU_64BIT
+  #elif defined(__sparc_v9__) \
+     || defined(__sparcv9)
+    #define MY_CPU_64BIT
+    #if defined(__SIZEOF_POINTER__) && (__SIZEOF_POINTER__ == 4)
+      #define MY_CPU_NAME "sparcv9-32"
+    #else
+      #define MY_CPU_NAME "sparcv9m"
+    #endif
+  #elif defined(__sparc_v8__) \
+     || defined(__sparcv8)
+    #define MY_CPU_NAME "sparcv8"
+    #define MY_CPU_SIZEOF_POINTER 4
+  #else
+    #define MY_CPU_NAME "sparc"
+  #endif
+#endif
+
+
 #if  defined(__riscv) \
   || defined(__riscv__)
+    #define MY_CPU_RISCV
   #if __riscv_xlen == 32
     #define MY_CPU_NAME "riscv32"
   #elif __riscv_xlen == 64
@@ -145,6 +184,39 @@ MY_CPU_64BIT means that processor can work with 64-bit registers.
 #endif
 
 
+#if defined(__loongarch__)
+  #define MY_CPU_LOONGARCH
+  #if defined(__loongarch64) || defined(__loongarch_grlen) && (__loongarch_grlen == 64)
+  #define MY_CPU_64BIT
+  #endif
+  #if defined(__loongarch64)
+  #define MY_CPU_NAME "loongarch64"
+  #define MY_CPU_LOONGARCH64
+  #else
+  #define MY_CPU_NAME "loongarch"
+  #endif
+#endif
+
+
+// #undef MY_CPU_NAME
+// #undef MY_CPU_SIZEOF_POINTER
+// #define __e2k__
+// #define __SIZEOF_POINTER__ 4
+#if  defined(__e2k__)
+  #define MY_CPU_E2K
+  #if defined(__ILP32__) || defined(__SIZEOF_POINTER__) && (__SIZEOF_POINTER__ == 4)
+    #define MY_CPU_NAME "e2k-32"
+    #define MY_CPU_SIZEOF_POINTER 4
+  #else
+    #define MY_CPU_NAME "e2k"
+    #if defined(__LP64__) || defined(__SIZEOF_POINTER__) && (__SIZEOF_POINTER__ == 8)
+      #define MY_CPU_SIZEOF_POINTER 8
+    #endif
+  #endif
+  #define MY_CPU_64BIT
+#endif
+
+
 #if defined(MY_CPU_X86) || defined(MY_CPU_AMD64)
 #define MY_CPU_X86_OR_AMD64
 #endif
@@ -175,6 +247,7 @@ MY_CPU_64BIT means that processor can work with 64-bit registers.
     || defined(MY_CPU_ARM_LE) \
     || defined(MY_CPU_ARM64_LE) \
     || defined(MY_CPU_IA64_LE) \
+    || defined(_LITTLE_ENDIAN) \
     || defined(__LITTLE_ENDIAN__) \
     || defined(__ARMEL__) \
     || defined(__THUMBEL__) \
@@ -251,6 +324,7 @@ MY_CPU_64BIT means that processor can work with 64-bit registers.
 
 
 #ifndef MY_CPU_NAME
+  // #define MY_CPU_IS_UNKNOWN
   #ifdef MY_CPU_LE
     #define MY_CPU_NAME "LE"
   #elif defined(MY_CPU_BE)
@@ -295,9 +369,19 @@ MY_CPU_64BIT means that processor can work with 64-bit registers.
 #define Z7_BSWAP64(v)  _byteswap_uint64(v)
 #define Z7_CPU_FAST_BSWAP_SUPPORTED
 
-#elif  (defined(__GNUC__) && (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 3))) \
-    || (defined(__clang__) && Z7_has_builtin(__builtin_bswap16))
- 
+/* GCC can generate slow code that calls function for __builtin_bswap32() for:
+     - GCC for RISCV, if Zbb/XTHeadBb extension is not used.
+     - GCC for SPARC.
+   The code from CLANG for SPARC also is not fastest.
+   So we don't define Z7_CPU_FAST_BSWAP_SUPPORTED in some cases.
+*/
+#elif (!defined(MY_CPU_RISCV) || defined (__riscv_zbb) || defined(__riscv_xtheadbb)) \
+    && !defined(MY_CPU_SPARC) \
+    && ( \
+       (defined(__GNUC__) && (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 3))) \
+    || (defined(__clang__) && Z7_has_builtin(__builtin_bswap16)) \
+    )
+
 #define Z7_BSWAP16(v)  __builtin_bswap16(v)
 #define Z7_BSWAP32(v)  __builtin_bswap32(v)
 #define Z7_BSWAP64(v)  __builtin_bswap64(v)
@@ -329,13 +413,48 @@ MY_CPU_64BIT means that processor can work with 64-bit registers.
 
 #ifdef MY_CPU_LE
   #if defined(MY_CPU_X86_OR_AMD64) \
-      || defined(MY_CPU_ARM64)
+      || defined(MY_CPU_ARM64) \
+      || defined(MY_CPU_RISCV) && defined(__riscv_misaligned_fast) \
+      || defined(MY_CPU_E2K) && defined(__iset__) && (__iset__ >= 6)
     #define MY_CPU_LE_UNALIGN
     #define MY_CPU_LE_UNALIGN_64
   #elif defined(__ARM_FEATURE_UNALIGNED)
-    /* gcc9 for 32-bit arm can use LDRD instruction that requires 32-bit alignment.
-       So we can't use unaligned 64-bit operations. */
-    #define MY_CPU_LE_UNALIGN
+/* === ALIGNMENT on 32-bit arm and LDRD/STRD/LDM/STM instructions.
+  Description of problems:
+problem-1 : 32-bit ARM architecture:
+  multi-access (pair of 32-bit accesses) instructions (LDRD/STRD/LDM/STM)
+  require 32-bit (WORD) alignment (by 32-bit ARM architecture).
+  So there is "Alignment fault exception", if data is not aligned for 32-bit.
+
+problem-2 : 32-bit kernels and arm64 kernels:
+  32-bit linux kernels provide fixup for these "paired" instruction "Alignment fault exception".
+  So unaligned paired-access instructions work via exception handler in kernel in 32-bit linux.
+ 
+  But some arm64 kernels do not handle these faults in 32-bit programs.
+  So we have unhandled exception for such instructions.
+  Probably some new arm64 kernels have fixed it, and unaligned
+  paired-access instructions work in new kernels?
+
+problem-3 : compiler for 32-bit arm:
+  Compilers use LDRD/STRD/LDM/STM for UInt64 accesses
+  and for another cases where two 32-bit accesses are fused
+  to one multi-access instruction.
+  So UInt64 variables must be aligned for 32-bit, and each
+  32-bit access must be aligned for 32-bit, if we want to
+  avoid "Alignment fault" exception (handled or unhandled).
+
+problem-4 : performace:
+  Even if unaligned access is handled by kernel, it will be slow.
+  So if we allow unaligned access, we can get fast unaligned
+  single-access, and slow unaligned paired-access.
+
+  We don't allow unaligned access on 32-bit arm, because compiler
+  genarates paired-access instructions that require 32-bit alignment,
+  and some arm64 kernels have no handler for these instructions.
+  Also unaligned paired-access instructions will be slow, if kernel handles them.
+*/
+    // it must be disabled:
+    // #define MY_CPU_LE_UNALIGN
   #endif
 #endif
 
@@ -439,11 +558,13 @@ MY_CPU_64BIT means that processor can work with 64-bit registers.
 
 #if defined(MY_CPU_BE)
 
+#define GetBe64a(p)      (*(const UInt64 *)(const void *)(p))
 #define GetBe32a(p)      (*(const UInt32 *)(const void *)(p))
 #define GetBe16a(p)      (*(const UInt16 *)(const void *)(p))
 #define SetBe32a(p, v)   { *(UInt32 *)(void *)(p) = (v); }
 #define SetBe16a(p, v)   { *(UInt16 *)(void *)(p) = (v); }
 
+#define GetUi64a(p)      GetUi64(p)
 #define GetUi32a(p)      GetUi32(p)
 #define GetUi16a(p)      GetUi16(p)
 #define SetUi32a(p, v)   SetUi32(p, v)
@@ -451,11 +572,13 @@ MY_CPU_64BIT means that processor can work with 64-bit registers.
 
 #elif defined(MY_CPU_LE)
 
+#define GetUi64a(p)      (*(const UInt64 *)(const void *)(p))
 #define GetUi32a(p)      (*(const UInt32 *)(const void *)(p))
 #define GetUi16a(p)      (*(const UInt16 *)(const void *)(p))
 #define SetUi32a(p, v)   { *(UInt32 *)(void *)(p) = (v); }
 #define SetUi16a(p, v)   { *(UInt16 *)(void *)(p) = (v); }
 
+#define GetBe64a(p)      GetBe64(p)
 #define GetBe32a(p)      GetBe32(p)
 #define GetBe16a(p)      GetBe16(p)
 #define SetBe32a(p, v)   SetBe32(p, v)
@@ -486,6 +609,7 @@ UInt32 Z7_FASTCALL z7_x86_cpuid_GetMaxFunc(void);
 BoolInt CPU_IsSupported_AES(void);
 BoolInt CPU_IsSupported_AVX(void);
 BoolInt CPU_IsSupported_AVX2(void);
+BoolInt CPU_IsSupported_AVX512F_AVX512VL(void);
 BoolInt CPU_IsSupported_VAES_AVX2(void);
 BoolInt CPU_IsSupported_CMOV(void);
 BoolInt CPU_IsSupported_SSE(void);

3rdparty/lzma/include/LzFind.h

@@ -1,5 +1,5 @@
 /* LzFind.h -- Match finder for LZ algorithms
-2023-03-04 : Igor Pavlov : Public domain */
+2024-01-22 : Igor Pavlov : Public domain */
 
 #ifndef ZIP7_INC_LZ_FIND_H
 #define ZIP7_INC_LZ_FIND_H
@@ -144,7 +144,8 @@ void MatchFinder_CreateVTable(CMatchFinder *p, IMatchFinder2 *vTable);
 void MatchFinder_Init_LowHash(CMatchFinder *p);
 void MatchFinder_Init_HighHash(CMatchFinder *p);
 void MatchFinder_Init_4(CMatchFinder *p);
-void MatchFinder_Init(CMatchFinder *p);
+// void MatchFinder_Init(CMatchFinder *p);
+void MatchFinder_Init(void *p);
 
 UInt32* Bt3Zip_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances);
 UInt32* Hc3Zip_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances);

3rdparty/lzma/include/LzFindMt.h

@@ -1,5 +1,5 @@
 /* LzFindMt.h -- multithreaded Match finder for LZ algorithms
-2023-03-05 : Igor Pavlov : Public domain */
+2024-01-22 : Igor Pavlov : Public domain */
 
 #ifndef ZIP7_INC_LZ_FIND_MT_H
 #define ZIP7_INC_LZ_FIND_MT_H
@@ -31,7 +31,10 @@ typedef struct
   // UInt32 numBlocks_Sent;
 } CMtSync;
 
-typedef UInt32 * (*Mf_Mix_Matches)(void *p, UInt32 matchMinPos, UInt32 *distances);
+
+struct CMatchFinderMt_;
+
+typedef UInt32 * (*Mf_Mix_Matches)(struct CMatchFinderMt_ *p, UInt32 matchMinPos, UInt32 *distances);
 
 /* kMtCacheLineDummy must be >= size_of_CPU_cache_line */
 #define kMtCacheLineDummy 128
@@ -39,7 +42,7 @@ typedef UInt32 * (*Mf_Mix_Matches)(void *p, UInt32 matchMinPos, UInt32 *distance
 typedef void (*Mf_GetHeads)(const Byte *buffer, UInt32 pos,
   UInt32 *hash, UInt32 hashMask, UInt32 *heads, UInt32 numHeads, const UInt32 *crc);
 
-typedef struct
+typedef struct CMatchFinderMt_
 {
   /* LZ */
   const Byte *pointerToCurPos;

3rdparty/lzma/include/Precomp.h

@@ -1,10 +1,127 @@
-/* Precomp.h -- StdAfx
-2023-04-02 : Igor Pavlov : Public domain */
+/* Precomp.h -- precompilation file
+2024-01-25 : Igor Pavlov : Public domain */
 
 #ifndef ZIP7_INC_PRECOMP_H
 #define ZIP7_INC_PRECOMP_H
 
+/*
+  this file must be included before another *.h files and before <windows.h>.
+  this file is included from the following files:
+    C\*.c
+    C\Util\*\Precomp.h   <-  C\Util\*\*.c
+    CPP\Common\Common.h  <-  *\StdAfx.h    <-  *\*.cpp
+
+  this file can set the following macros:
+    Z7_LARGE_PAGES 1
+    Z7_LONG_PATH 1
+    Z7_WIN32_WINNT_MIN  0x0500 (or higher) : we require at least win2000+ for 7-Zip
+    _WIN32_WINNT        0x0500 (or higher)
+    WINVER  _WIN32_WINNT
+    UNICODE 1
+    _UNICODE 1
+*/
+
 #include "Compiler.h"
-/* #include "7zTypes.h" */
+
+#ifdef _MSC_VER
+// #pragma warning(disable : 4206) // nonstandard extension used : translation unit is empty
+#if _MSC_VER >= 1912
+// #pragma warning(disable : 5039) // pointer or reference to potentially throwing function passed to 'extern "C"' function under - EHc.Undefined behavior may occur if this function throws an exception.
+#endif
+#endif
+
+/*
+// for debug:
+#define UNICODE 1
+#define _UNICODE 1
+#define  _WIN32_WINNT  0x0500  // win2000
+#ifndef WINVER
+  #define WINVER  _WIN32_WINNT
+#endif
+*/
+
+#ifdef _WIN32
+/*
+  this "Precomp.h" file must be included before <windows.h>,
+  if we want to define _WIN32_WINNT before <windows.h>.
+*/
+
+#ifndef Z7_LARGE_PAGES
+#ifndef Z7_NO_LARGE_PAGES
+#define Z7_LARGE_PAGES 1
+#endif
+#endif
+
+#ifndef Z7_LONG_PATH
+#ifndef Z7_NO_LONG_PATH
+#define Z7_LONG_PATH 1
+#endif
+#endif
+
+#ifndef Z7_DEVICE_FILE
+#ifndef Z7_NO_DEVICE_FILE
+// #define Z7_DEVICE_FILE 1
+#endif
+#endif
+
+// we don't change macros if included after <windows.h>
+#ifndef _WINDOWS_
+
+#ifndef Z7_WIN32_WINNT_MIN
+  #if defined(_M_ARM64) || defined(__aarch64__)
+    // #define Z7_WIN32_WINNT_MIN  0x0a00  // win10
+    #define Z7_WIN32_WINNT_MIN  0x0600  // vista
+  #elif defined(_M_ARM) && defined(_M_ARMT) && defined(_M_ARM_NT)
+    // #define Z7_WIN32_WINNT_MIN  0x0602  // win8
+    #define Z7_WIN32_WINNT_MIN  0x0600  // vista
+  #elif defined(_M_X64) || defined(_M_AMD64) || defined(__x86_64__) || defined(_M_IA64)
+    #define Z7_WIN32_WINNT_MIN  0x0503  // win2003
+  // #elif defined(_M_IX86) || defined(__i386__)
+  //   #define Z7_WIN32_WINNT_MIN  0x0500  // win2000
+  #else // x86 and another(old) systems
+    #define Z7_WIN32_WINNT_MIN  0x0500  // win2000
+    // #define Z7_WIN32_WINNT_MIN  0x0502  // win2003 // for debug
+  #endif
+#endif // Z7_WIN32_WINNT_MIN
+
+
+#ifndef Z7_DO_NOT_DEFINE_WIN32_WINNT
+#ifdef _WIN32_WINNT
+  // #error Stop_Compiling_Bad_WIN32_WINNT
+#else
+  #ifndef Z7_NO_DEFINE_WIN32_WINNT
+Z7_DIAGNOSTIC_IGNORE_BEGIN_RESERVED_MACRO_IDENTIFIER
+    #define _WIN32_WINNT  Z7_WIN32_WINNT_MIN
+Z7_DIAGNOSTIC_IGNORE_END_RESERVED_MACRO_IDENTIFIER
+  #endif
+#endif // _WIN32_WINNT
+
+#ifndef WINVER
+  #define WINVER  _WIN32_WINNT
+#endif
+#endif // Z7_DO_NOT_DEFINE_WIN32_WINNT
+
+
+#ifndef _MBCS
+#ifndef Z7_NO_UNICODE
+// UNICODE and _UNICODE are used by <windows.h> and by 7-zip code.
+
+#ifndef UNICODE
+#define UNICODE 1
+#endif
+
+#ifndef _UNICODE
+Z7_DIAGNOSTIC_IGNORE_BEGIN_RESERVED_MACRO_IDENTIFIER
+#define _UNICODE 1
+Z7_DIAGNOSTIC_IGNORE_END_RESERVED_MACRO_IDENTIFIER
+#endif
+
+#endif // Z7_NO_UNICODE
+#endif // _MBCS
+#endif // _WINDOWS_
+
+// #include "7zWindows.h"
+
+#endif // _WIN32
 
 #endif

3rdparty/lzma/include/Threads.h

@@ -1,5 +1,5 @@
 /* Threads.h -- multithreading library
-2023-04-02 : Igor Pavlov : Public domain */
+2024-03-28 : Igor Pavlov : Public domain */
 
 #ifndef ZIP7_INC_THREADS_H
 #define ZIP7_INC_THREADS_H
@@ -9,12 +9,21 @@
 
 #else
 
+#include "Compiler.h"
+
+// #define Z7_AFFINITY_DISABLE
 #if defined(__linux__)
 #if !defined(__APPLE__) && !defined(_AIX) && !defined(__ANDROID__)
 #ifndef Z7_AFFINITY_DISABLE
 #define Z7_AFFINITY_SUPPORTED
 // #pragma message(" ==== Z7_AFFINITY_SUPPORTED")
-// #define _GNU_SOURCE
+#if !defined(_GNU_SOURCE)
+// #pragma message(" ==== _GNU_SOURCE set")
+// we need _GNU_SOURCE for cpu_set_t, if we compile for MUSL
+Z7_DIAGNOSTIC_IGNORE_BEGIN_RESERVED_MACRO_IDENTIFIER
+#define _GNU_SOURCE
+Z7_DIAGNOSTIC_IGNORE_END_RESERVED_MACRO_IDENTIFIER
+#endif
 #endif
 #endif
 #endif
@@ -173,7 +182,7 @@ WRes CriticalSection_Init(CCriticalSection *p);
 
 #else // _WIN32
 
-typedef struct _CEvent
+typedef struct
 {
   int _created;
   int _manual_reset;
@@ -199,7 +208,7 @@ WRes Event_Wait(CEvent *p);
 WRes Event_Close(CEvent *p);
 
 
-typedef struct _CSemaphore
+typedef struct
 {
   int _created;
   UInt32 _count;
@@ -219,7 +228,7 @@ WRes Semaphore_Wait(CSemaphore *p);
 WRes Semaphore_Close(CSemaphore *p);
 
 
-typedef struct _CCriticalSection
+typedef struct
 {
   pthread_mutex_t _mutex;
 } CCriticalSection;
@@ -230,6 +239,7 @@ void CriticalSection_Enter(CCriticalSection *cs);
 void CriticalSection_Leave(CCriticalSection *cs);
 
 LONG InterlockedIncrement(LONG volatile *addend);
+LONG InterlockedDecrement(LONG volatile *addend);
 
 #endif  // _WIN32
 

3rdparty/lzma/include/Xz.h

@@ -1,5 +1,5 @@
 /* Xz.h - Xz interface
-2023-04-13 : Igor Pavlov : Public domain */
+2024-01-26 : Igor Pavlov : Public domain */
 
 #ifndef ZIP7_INC_XZ_H
 #define ZIP7_INC_XZ_H
@@ -18,6 +18,7 @@ EXTERN_C_BEGIN
 #define XZ_ID_ARMT  8
 #define XZ_ID_SPARC 9
 #define XZ_ID_ARM64 0xa
+#define XZ_ID_RISCV 0xb
 #define XZ_ID_LZMA2 0x21
 
 unsigned Xz_ReadVarInt(const Byte *p, size_t maxSize, UInt64 *value);
@@ -233,13 +234,13 @@ typedef enum
 typedef struct
 {
   EXzState state;
-  UInt32 pos;
+  unsigned pos;
   unsigned alignPos;
   unsigned indexPreSize;
 
   CXzStreamFlags streamFlags;
   
-  UInt32 blockHeaderSize;
+  unsigned blockHeaderSize;
   UInt64 packSize;
   UInt64 unpackSize;
 

3rdparty/lzma/include/XzCrc64.h

@@ -1,5 +1,5 @@
 /* XzCrc64.h -- CRC64 calculation
-2023-04-02 : Igor Pavlov : Public domain */
+2023-12-08 : Igor Pavlov : Public domain */
 
 #ifndef ZIP7_INC_XZ_CRC64_H
 #define ZIP7_INC_XZ_CRC64_H
@@ -10,16 +10,16 @@
 
 EXTERN_C_BEGIN
 
-extern UInt64 g_Crc64Table[];
+// extern UInt64 g_Crc64Table[];
 
 void Z7_FASTCALL Crc64GenerateTable(void);
 
 #define CRC64_INIT_VAL UINT64_CONST(0xFFFFFFFFFFFFFFFF)
 #define CRC64_GET_DIGEST(crc) ((crc) ^ CRC64_INIT_VAL)
-#define CRC64_UPDATE_BYTE(crc, b) (g_Crc64Table[((crc) ^ (b)) & 0xFF] ^ ((crc) >> 8))
+// #define CRC64_UPDATE_BYTE(crc, b) (g_Crc64Table[((crc) ^ (b)) & 0xFF] ^ ((crc) >> 8))
 
 UInt64 Z7_FASTCALL Crc64Update(UInt64 crc, const void *data, size_t size);
-UInt64 Z7_FASTCALL Crc64Calc(const void *data, size_t size);
+// UInt64 Z7_FASTCALL Crc64Calc(const void *data, size_t size);
 
 EXTERN_C_END
 

3rdparty/lzma/src/7zArcIn.c

@@ -1,5 +1,5 @@
 /* 7zArcIn.c -- 7z Input functions
-2023-05-11 : Igor Pavlov : Public domain */
+2023-09-07 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
@@ -301,7 +301,7 @@ static SRes RememberBitVector(CSzData *sd, UInt32 numItems, const Byte **v)
 
 static UInt32 CountDefinedBits(const Byte *bits, UInt32 numItems)
 {
-  Byte b = 0;
+  unsigned b = 0;
   unsigned m = 0;
   UInt32 sum = 0;
   for (; numItems != 0; numItems--)
@@ -312,7 +312,7 @@ static UInt32 CountDefinedBits(const Byte *bits, UInt32 numItems)
       m = 8;
     }
     m--;
-    sum += ((b >> m) & 1);
+    sum += (UInt32)((b >> m) & 1);
   }
   return sum;
 }

3rdparty/lzma/src/7zCrc.c

@@ -1,93 +1,96 @@
 /* 7zCrc.c -- CRC32 calculation and init
-2023-04-02 : Igor Pavlov : Public domain */
+2024-03-01 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
 #include "7zCrc.h"
 #include "CpuArch.h"
 
-#define kCrcPoly 0xEDB88320
+// for debug:
+// #define __ARM_FEATURE_CRC32 1
 
-#ifdef MY_CPU_LE
-  #define CRC_NUM_TABLES 8
+#ifdef __ARM_FEATURE_CRC32
+// #pragma message("__ARM_FEATURE_CRC32")
+#define Z7_CRC_HW_FORCE
+#endif
+
+// #define Z7_CRC_DEBUG_BE
+#ifdef Z7_CRC_DEBUG_BE
+#undef MY_CPU_LE
+#define MY_CPU_BE
+#endif
+
+#ifdef Z7_CRC_HW_FORCE
+  #define Z7_CRC_NUM_TABLES_USE  1
 #else
-  #define CRC_NUM_TABLES 9
-
-  UInt32 Z7_FASTCALL CrcUpdateT1_BeT4(UInt32 v, const void *data, size_t size, const UInt32 *table);
-  UInt32 Z7_FASTCALL CrcUpdateT1_BeT8(UInt32 v, const void *data, size_t size, const UInt32 *table);
+#ifdef Z7_CRC_NUM_TABLES
+  #define Z7_CRC_NUM_TABLES_USE  Z7_CRC_NUM_TABLES
+#else
+  #define Z7_CRC_NUM_TABLES_USE  12
+#endif
 #endif
 
-#ifndef MY_CPU_BE
-  UInt32 Z7_FASTCALL CrcUpdateT4(UInt32 v, const void *data, size_t size, const UInt32 *table);
-  UInt32 Z7_FASTCALL CrcUpdateT8(UInt32 v, const void *data, size_t size, const UInt32 *table);
+#if Z7_CRC_NUM_TABLES_USE < 1
+  #error Stop_Compiling_Bad_Z7_CRC_NUM_TABLES
 #endif
 
-/*
-extern
-CRC_FUNC g_CrcUpdateT4;
-CRC_FUNC g_CrcUpdateT4;
-*/
-extern
-CRC_FUNC g_CrcUpdateT8;
-CRC_FUNC g_CrcUpdateT8;
-extern
-CRC_FUNC g_CrcUpdateT0_32;
-CRC_FUNC g_CrcUpdateT0_32;
-extern
-CRC_FUNC g_CrcUpdateT0_64;
-CRC_FUNC g_CrcUpdateT0_64;
-extern
-CRC_FUNC g_CrcUpdate;
-CRC_FUNC g_CrcUpdate;
+#if defined(MY_CPU_LE) || (Z7_CRC_NUM_TABLES_USE == 1)
+  #define Z7_CRC_NUM_TABLES_TOTAL  Z7_CRC_NUM_TABLES_USE
+#else
+  #define Z7_CRC_NUM_TABLES_TOTAL  (Z7_CRC_NUM_TABLES_USE + 1)
+#endif
 
-UInt32 g_CrcTable[256 * CRC_NUM_TABLES];
+#ifndef Z7_CRC_HW_FORCE
 
-UInt32 Z7_FASTCALL CrcUpdate(UInt32 v, const void *data, size_t size)
-{
-  return g_CrcUpdate(v, data, size, g_CrcTable);
-}
-
-UInt32 Z7_FASTCALL CrcCalc(const void *data, size_t size)
-{
-  return g_CrcUpdate(CRC_INIT_VAL, data, size, g_CrcTable) ^ CRC_INIT_VAL;
-}
-
-#if CRC_NUM_TABLES < 4 \
-   || (CRC_NUM_TABLES == 4 && defined(MY_CPU_BE)) \
+#if Z7_CRC_NUM_TABLES_USE == 1 \
    || (!defined(MY_CPU_LE) && !defined(MY_CPU_BE))
-#define CRC_UPDATE_BYTE_2(crc, b) (table[((crc) ^ (b)) & 0xFF] ^ ((crc) >> 8))
-UInt32 Z7_FASTCALL CrcUpdateT1(UInt32 v, const void *data, size_t size, const UInt32 *table);
-UInt32 Z7_FASTCALL CrcUpdateT1(UInt32 v, const void *data, size_t size, const UInt32 *table)
+#define CRC_UPDATE_BYTE_2(crc, b)   (table[((crc) ^ (b)) & 0xFF] ^ ((crc) >> 8))
+#define Z7_CRC_UPDATE_T1_FUNC_NAME  CrcUpdateGT1
+static UInt32 Z7_FASTCALL Z7_CRC_UPDATE_T1_FUNC_NAME(UInt32 v, const void *data, size_t size)
 {
+  const UInt32 *table = g_CrcTable;
   const Byte *p = (const Byte *)data;
-  const Byte *pEnd = p + size;
-  for (; p != pEnd; p++)
+  const Byte *lim = p + size;
+  for (; p != lim; p++)
     v = CRC_UPDATE_BYTE_2(v, *p);
   return v;
 }
 #endif
 
+
+#if Z7_CRC_NUM_TABLES_USE != 1
+#ifndef MY_CPU_BE
+  #define FUNC_NAME_LE_2(s)   CrcUpdateT ## s
+  #define FUNC_NAME_LE_1(s)   FUNC_NAME_LE_2(s)
+  #define FUNC_NAME_LE        FUNC_NAME_LE_1(Z7_CRC_NUM_TABLES_USE)
+  UInt32 Z7_FASTCALL FUNC_NAME_LE (UInt32 v, const void *data, size_t size, const UInt32 *table);
+#endif
+#ifndef MY_CPU_LE
+  #define FUNC_NAME_BE_2(s)   CrcUpdateT1_BeT ## s
+  #define FUNC_NAME_BE_1(s)   FUNC_NAME_BE_2(s)
+  #define FUNC_NAME_BE        FUNC_NAME_BE_1(Z7_CRC_NUM_TABLES_USE)
+  UInt32 Z7_FASTCALL FUNC_NAME_BE (UInt32 v, const void *data, size_t size, const UInt32 *table);
+#endif
+#endif
+
+#endif // Z7_CRC_HW_FORCE
+
 /* ---------- hardware CRC ---------- */
 
 #ifdef MY_CPU_LE
 
 #if defined(MY_CPU_ARM_OR_ARM64)
-
 // #pragma message("ARM*")
 
-  #if defined(_MSC_VER) && !defined(__clang__)
-    #if defined(MY_CPU_ARM64)
-    #if (_MSC_VER >= 1910)
-    #ifndef __clang__
-        #define USE_ARM64_CRC
-        #include <intrin.h>
-    #endif
-    #endif
-    #endif
-  #elif (defined(__clang__) && (__clang_major__ >= 3)) \
-     || (defined(__GNUC__) && (__GNUC__ > 4))
+  #if (defined(__clang__) && (__clang_major__ >= 3)) \
+     || defined(__GNUC__) && (__GNUC__ >= 6) && defined(MY_CPU_ARM64) \
+     || defined(__GNUC__) && (__GNUC__ >= 8)
       #if !defined(__ARM_FEATURE_CRC32)
+//        #pragma message("!defined(__ARM_FEATURE_CRC32)")
+Z7_DIAGNOSTIC_IGNORE_BEGIN_RESERVED_MACRO_IDENTIFIER
         #define __ARM_FEATURE_CRC32 1
+Z7_DIAGNOSTIC_IGNORE_END_RESERVED_MACRO_IDENTIFIER
+        #define Z7_ARM_FEATURE_CRC32_WAS_SET
         #if defined(__clang__)
           #if defined(MY_CPU_ARM64)
             #define ATTRIB_CRC __attribute__((__target__("crc")))
@@ -96,100 +99,120 @@ UInt32 Z7_FASTCALL CrcUpdateT1(UInt32 v, const void *data, size_t size, const UI
           #endif
         #else
           #if defined(MY_CPU_ARM64)
+#if !defined(Z7_GCC_VERSION) || (Z7_GCC_VERSION >= 60000)
             #define ATTRIB_CRC __attribute__((__target__("+crc")))
+#endif
           #else
+#if !defined(Z7_GCC_VERSION) || (__GNUC__  >= 8)
+#if defined(__ARM_FP) && __GNUC__ >= 8
+// for -mfloat-abi=hard: similar to <arm_acle.h>
+            #define ATTRIB_CRC __attribute__((__target__("arch=armv8-a+crc+simd")))
+#else
             #define ATTRIB_CRC __attribute__((__target__("arch=armv8-a+crc")))
+#endif
+#endif
           #endif
         #endif
       #endif
       #if defined(__ARM_FEATURE_CRC32)
-        #define USE_ARM64_CRC
+      // #pragma message("<arm_acle.h>")
+/*
+arm_acle.h (GGC):
+    before Nov 17, 2017:
+#ifdef __ARM_FEATURE_CRC32
+
+    Nov 17, 2017: gcc10.0  (gcc 9.2.0) checked"
+#if __ARM_ARCH >= 8
+#pragma GCC target ("arch=armv8-a+crc")
+
+    Aug 22, 2019: GCC 8.4?, 9.2.1, 10.1:
+#ifdef __ARM_FEATURE_CRC32
+#ifdef __ARM_FP
+#pragma GCC target ("arch=armv8-a+crc+simd")
+#else
+#pragma GCC target ("arch=armv8-a+crc")
+#endif
+*/
+#if defined(__ARM_ARCH) && __ARM_ARCH < 8
+#if defined(Z7_GCC_VERSION) && (__GNUC__ ==   8) && (Z7_GCC_VERSION <  80400) \
+ || defined(Z7_GCC_VERSION) && (__GNUC__ ==   9) && (Z7_GCC_VERSION <  90201) \
+ || defined(Z7_GCC_VERSION) && (__GNUC__ ==  10) && (Z7_GCC_VERSION < 100100)
+Z7_DIAGNOSTIC_IGNORE_BEGIN_RESERVED_MACRO_IDENTIFIER
+// #pragma message("#define __ARM_ARCH 8")
+#undef  __ARM_ARCH
+#define __ARM_ARCH 8
+Z7_DIAGNOSTIC_IGNORE_END_RESERVED_MACRO_IDENTIFIER
+#endif
+#endif
+        #define Z7_CRC_HW_USE
         #include <arm_acle.h>
       #endif
+  #elif defined(_MSC_VER)
+    #if defined(MY_CPU_ARM64)
+    #if (_MSC_VER >= 1910)
+    #ifdef __clang__
+       // #define Z7_CRC_HW_USE
+       // #include <arm_acle.h>
+    #else
+       #define Z7_CRC_HW_USE
+       #include <intrin.h>
+    #endif
+    #endif
+    #endif
   #endif
 
-#else
+#else // non-ARM*
 
-// no hardware CRC
-
-// #define USE_CRC_EMU
-
-#ifdef USE_CRC_EMU
-
-#pragma message("ARM64 CRC emulation")
-
-Z7_FORCE_INLINE
-UInt32 __crc32b(UInt32 v, UInt32 data)
-{
-  const UInt32 *table = g_CrcTable;
-  v = CRC_UPDATE_BYTE_2(v, (Byte)data);
-  return v;
-}
-
-Z7_FORCE_INLINE
-UInt32 __crc32w(UInt32 v, UInt32 data)
-{
-  const UInt32 *table = g_CrcTable;
-  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
-  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
-  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
-  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
-  return v;
-}
-
-Z7_FORCE_INLINE
-UInt32 __crc32d(UInt32 v, UInt64 data)
-{
-  const UInt32 *table = g_CrcTable;
-  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
-  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
-  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
-  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
-  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
-  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
-  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
-  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
-  return v;
-}
-
-#endif // USE_CRC_EMU
-
-#endif // defined(MY_CPU_ARM64) && defined(MY_CPU_LE)
-
-
-
-#if defined(USE_ARM64_CRC) || defined(USE_CRC_EMU)
-
-#define T0_32_UNROLL_BYTES (4 * 4)
-#define T0_64_UNROLL_BYTES (4 * 8)
-
-#ifndef ATTRIB_CRC
-#define ATTRIB_CRC
+// #define Z7_CRC_HW_USE // for debug : we can test HW-branch of code
+#ifdef Z7_CRC_HW_USE
+#include "7zCrcEmu.h"
 #endif
+
+#endif // non-ARM*
+
+
+
+#if defined(Z7_CRC_HW_USE)
+
 // #pragma message("USE ARM HW CRC")
 
-ATTRIB_CRC
-UInt32 Z7_FASTCALL CrcUpdateT0_32(UInt32 v, const void *data, size_t size, const UInt32 *table);
-ATTRIB_CRC
-UInt32 Z7_FASTCALL CrcUpdateT0_32(UInt32 v, const void *data, size_t size, const UInt32 *table)
+#ifdef MY_CPU_64BIT
+  #define CRC_HW_WORD_TYPE  UInt64
+  #define CRC_HW_WORD_FUNC  __crc32d
+#else
+  #define CRC_HW_WORD_TYPE  UInt32
+  #define CRC_HW_WORD_FUNC  __crc32w
+#endif
+
+#define CRC_HW_UNROLL_BYTES (sizeof(CRC_HW_WORD_TYPE) * 4)
+
+#ifdef ATTRIB_CRC
+  ATTRIB_CRC
+#endif
+Z7_NO_INLINE
+#ifdef Z7_CRC_HW_FORCE
+         UInt32 Z7_FASTCALL CrcUpdate
+#else
+  static UInt32 Z7_FASTCALL CrcUpdate_HW
+#endif
+    (UInt32 v, const void *data, size_t size)
 {
   const Byte *p = (const Byte *)data;
-  UNUSED_VAR(table);
-
-  for (; size != 0 && ((unsigned)(ptrdiff_t)p & (T0_32_UNROLL_BYTES - 1)) != 0; size--)
+  for (; size != 0 && ((unsigned)(ptrdiff_t)p & (CRC_HW_UNROLL_BYTES - 1)) != 0; size--)
     v = __crc32b(v, *p++);
-
-  if (size >= T0_32_UNROLL_BYTES)
+  if (size >= CRC_HW_UNROLL_BYTES)
   {
     const Byte *lim = p + size;
-    size &= (T0_32_UNROLL_BYTES - 1);
+    size &= CRC_HW_UNROLL_BYTES - 1;
     lim -= size;
     do
     {
-      v = __crc32w(v, *(const UInt32 *)(const void *)(p));
-      v = __crc32w(v, *(const UInt32 *)(const void *)(p + 4)); p += 2 * 4;
-      v = __crc32w(v, *(const UInt32 *)(const void *)(p));
-      v = __crc32w(v, *(const UInt32 *)(const void *)(p + 4)); p += 2 * 4;
+      v = CRC_HW_WORD_FUNC(v, *(const CRC_HW_WORD_TYPE *)(const void *)(p));
+      v = CRC_HW_WORD_FUNC(v, *(const CRC_HW_WORD_TYPE *)(const void *)(p + sizeof(CRC_HW_WORD_TYPE)));
+      p += 2 * sizeof(CRC_HW_WORD_TYPE);
+      v = CRC_HW_WORD_FUNC(v, *(const CRC_HW_WORD_TYPE *)(const void *)(p));
+      v = CRC_HW_WORD_FUNC(v, *(const CRC_HW_WORD_TYPE *)(const void *)(p + sizeof(CRC_HW_WORD_TYPE)));
+      p += 2 * sizeof(CRC_HW_WORD_TYPE);
     }
     while (p != lim);
   }
@@ -200,141 +223,198 @@ UInt32 Z7_FASTCALL CrcUpdateT0_32(UInt32 v, const void *data, size_t size, const
   return v;
 }
 
-ATTRIB_CRC
-UInt32 Z7_FASTCALL CrcUpdateT0_64(UInt32 v, const void *data, size_t size, const UInt32 *table);
-ATTRIB_CRC
-UInt32 Z7_FASTCALL CrcUpdateT0_64(UInt32 v, const void *data, size_t size, const UInt32 *table)
-{
-  const Byte *p = (const Byte *)data;
-  UNUSED_VAR(table);
-
-  for (; size != 0 && ((unsigned)(ptrdiff_t)p & (T0_64_UNROLL_BYTES - 1)) != 0; size--)
-    v = __crc32b(v, *p++);
-
-  if (size >= T0_64_UNROLL_BYTES)
-  {
-    const Byte *lim = p + size;
-    size &= (T0_64_UNROLL_BYTES - 1);
-    lim -= size;
-    do
-    {
-      v = __crc32d(v, *(const UInt64 *)(const void *)(p));
-      v = __crc32d(v, *(const UInt64 *)(const void *)(p + 8)); p += 2 * 8;
-      v = __crc32d(v, *(const UInt64 *)(const void *)(p));
-      v = __crc32d(v, *(const UInt64 *)(const void *)(p + 8)); p += 2 * 8;
-    }
-    while (p != lim);
-  }
-  
-  for (; size != 0; size--)
-    v = __crc32b(v, *p++);
-
-  return v;
-}
-
-#undef T0_32_UNROLL_BYTES
-#undef T0_64_UNROLL_BYTES
-
-#endif // defined(USE_ARM64_CRC) || defined(USE_CRC_EMU)
+#ifdef Z7_ARM_FEATURE_CRC32_WAS_SET
+Z7_DIAGNOSTIC_IGNORE_BEGIN_RESERVED_MACRO_IDENTIFIER
+#undef __ARM_FEATURE_CRC32
+Z7_DIAGNOSTIC_IGNORE_END_RESERVED_MACRO_IDENTIFIER
+#undef Z7_ARM_FEATURE_CRC32_WAS_SET
+#endif
 
+#endif // defined(Z7_CRC_HW_USE)
 #endif // MY_CPU_LE
 
 
 
+#ifndef Z7_CRC_HW_FORCE
+
+#if defined(Z7_CRC_HW_USE) || defined(Z7_CRC_UPDATE_T1_FUNC_NAME)
+/*
+typedef UInt32 (Z7_FASTCALL *Z7_CRC_UPDATE_WITH_TABLE_FUNC)
+    (UInt32 v, const void *data, size_t size, const UInt32 *table);
+Z7_CRC_UPDATE_WITH_TABLE_FUNC g_CrcUpdate;
+*/
+static unsigned g_Crc_Algo;
+#if (!defined(MY_CPU_LE) && !defined(MY_CPU_BE))
+static unsigned g_Crc_Be;
+#endif
+#endif // defined(Z7_CRC_HW_USE) || defined(Z7_CRC_UPDATE_T1_FUNC_NAME)
+
+
+
+Z7_NO_INLINE
+#ifdef Z7_CRC_HW_USE
+  static UInt32 Z7_FASTCALL CrcUpdate_Base
+#else
+         UInt32 Z7_FASTCALL CrcUpdate
+#endif
+    (UInt32 crc, const void *data, size_t size)
+{
+#if Z7_CRC_NUM_TABLES_USE == 1
+    return Z7_CRC_UPDATE_T1_FUNC_NAME(crc, data, size);
+#else // Z7_CRC_NUM_TABLES_USE != 1
+#ifdef Z7_CRC_UPDATE_T1_FUNC_NAME
+  if (g_Crc_Algo == 1)
+    return Z7_CRC_UPDATE_T1_FUNC_NAME(crc, data, size);
+#endif
+
+#ifdef MY_CPU_LE
+    return FUNC_NAME_LE(crc, data, size, g_CrcTable);
+#elif defined(MY_CPU_BE)
+    return FUNC_NAME_BE(crc, data, size, g_CrcTable);
+#else
+  if (g_Crc_Be)
+    return FUNC_NAME_BE(crc, data, size, g_CrcTable);
+  else
+    return FUNC_NAME_LE(crc, data, size, g_CrcTable);
+#endif
+#endif // Z7_CRC_NUM_TABLES_USE != 1
+}
+
+
+#ifdef Z7_CRC_HW_USE
+Z7_NO_INLINE
+UInt32 Z7_FASTCALL CrcUpdate(UInt32 crc, const void *data, size_t size)
+{
+  if (g_Crc_Algo == 0)
+    return CrcUpdate_HW(crc, data, size);
+  return CrcUpdate_Base(crc, data, size);
+}
+#endif
+
+#endif // !defined(Z7_CRC_HW_FORCE)
+
+
+
+UInt32 Z7_FASTCALL CrcCalc(const void *data, size_t size)
+{
+  return CrcUpdate(CRC_INIT_VAL, data, size) ^ CRC_INIT_VAL;
+}
+
+
+MY_ALIGN(64)
+UInt32 g_CrcTable[256 * Z7_CRC_NUM_TABLES_TOTAL];
+
 
 void Z7_FASTCALL CrcGenerateTable(void)
 {
   UInt32 i;
   for (i = 0; i < 256; i++)
   {
+#if defined(Z7_CRC_HW_FORCE)
+    g_CrcTable[i] = __crc32b(i, 0);
+#else
+    #define kCrcPoly 0xEDB88320
     UInt32 r = i;
     unsigned j;
     for (j = 0; j < 8; j++)
       r = (r >> 1) ^ (kCrcPoly & ((UInt32)0 - (r & 1)));
     g_CrcTable[i] = r;
+#endif
   }
-  for (i = 256; i < 256 * CRC_NUM_TABLES; i++)
+  for (i = 256; i < 256 * Z7_CRC_NUM_TABLES_USE; i++)
   {
     const UInt32 r = g_CrcTable[(size_t)i - 256];
     g_CrcTable[i] = g_CrcTable[r & 0xFF] ^ (r >> 8);
   }
 
-  #if CRC_NUM_TABLES < 4
-    g_CrcUpdate = CrcUpdateT1;
-  #elif defined(MY_CPU_LE)
-    // g_CrcUpdateT4 = CrcUpdateT4;
-    #if CRC_NUM_TABLES < 8
-      g_CrcUpdate = CrcUpdateT4;
-    #else // CRC_NUM_TABLES >= 8
-      g_CrcUpdateT8 = CrcUpdateT8;
-      /*
-      #ifdef MY_CPU_X86_OR_AMD64
-      if (!CPU_Is_InOrder())
-      #endif
-      */
-      g_CrcUpdate = CrcUpdateT8;
-    #endif
-  #else
+#if !defined(Z7_CRC_HW_FORCE) && \
+    (defined(Z7_CRC_HW_USE) || defined(Z7_CRC_UPDATE_T1_FUNC_NAME) || defined(MY_CPU_BE))
+
+#if Z7_CRC_NUM_TABLES_USE <= 1
+    g_Crc_Algo = 1;
+#else // Z7_CRC_NUM_TABLES_USE <= 1
+
+#if defined(MY_CPU_LE)
+    g_Crc_Algo = Z7_CRC_NUM_TABLES_USE;
+#else // !defined(MY_CPU_LE)
   {
-   #ifndef MY_CPU_BE
+#ifndef MY_CPU_BE
     UInt32 k = 0x01020304;
     const Byte *p = (const Byte *)&k;
     if (p[0] == 4 && p[1] == 3)
-    {
-      #if CRC_NUM_TABLES < 8
-        // g_CrcUpdateT4 = CrcUpdateT4;
-        g_CrcUpdate   = CrcUpdateT4;
-      #else  // CRC_NUM_TABLES >= 8
-        g_CrcUpdateT8 = CrcUpdateT8;
-        g_CrcUpdate   = CrcUpdateT8;
-      #endif
-    }
+      g_Crc_Algo = Z7_CRC_NUM_TABLES_USE;
     else if (p[0] != 1 || p[1] != 2)
-      g_CrcUpdate = CrcUpdateT1;
+      g_Crc_Algo = 1;
     else
-   #endif // MY_CPU_BE
+#endif // MY_CPU_BE
     {
-      for (i = 256 * CRC_NUM_TABLES - 1; i >= 256; i--)
+      for (i = 256 * Z7_CRC_NUM_TABLES_TOTAL - 1; i >= 256; i--)
       {
         const UInt32 x = g_CrcTable[(size_t)i - 256];
         g_CrcTable[i] = Z7_BSWAP32(x);
       }
-      #if CRC_NUM_TABLES <= 4
-        g_CrcUpdate = CrcUpdateT1;
-      #elif CRC_NUM_TABLES <= 8
-        // g_CrcUpdateT4 = CrcUpdateT1_BeT4;
-        g_CrcUpdate   = CrcUpdateT1_BeT4;
-      #else  // CRC_NUM_TABLES > 8
-        g_CrcUpdateT8 = CrcUpdateT1_BeT8;
-        g_CrcUpdate   = CrcUpdateT1_BeT8;
-      #endif
+#if defined(Z7_CRC_UPDATE_T1_FUNC_NAME)
+      g_Crc_Algo = Z7_CRC_NUM_TABLES_USE;
+#endif
+#if (!defined(MY_CPU_LE) && !defined(MY_CPU_BE))
+      g_Crc_Be = 1;
+#endif
     }
   }
-  #endif // CRC_NUM_TABLES < 4
+#endif  // !defined(MY_CPU_LE)
 
-  #ifdef MY_CPU_LE
-    #ifdef USE_ARM64_CRC
-      if (CPU_IsSupported_CRC32())
-      {
-        g_CrcUpdateT0_32 = CrcUpdateT0_32;
-        g_CrcUpdateT0_64 = CrcUpdateT0_64;
-        g_CrcUpdate =
-          #if defined(MY_CPU_ARM)
-            CrcUpdateT0_32;
-          #else
-            CrcUpdateT0_64;
-          #endif
-      }
-    #endif
-    
-    #ifdef USE_CRC_EMU
-      g_CrcUpdateT0_32 = CrcUpdateT0_32;
-      g_CrcUpdateT0_64 = CrcUpdateT0_64;
-      g_CrcUpdate = CrcUpdateT0_64;
-    #endif
+#ifdef MY_CPU_LE
+#ifdef Z7_CRC_HW_USE
+  if (CPU_IsSupported_CRC32())
+    g_Crc_Algo = 0;
+#endif // Z7_CRC_HW_USE
+#endif // MY_CPU_LE
+
+#endif // Z7_CRC_NUM_TABLES_USE <= 1
+#endif // g_Crc_Algo was declared
+}
+
+Z7_CRC_UPDATE_FUNC z7_GetFunc_CrcUpdate(unsigned algo)
+{
+  if (algo == 0)
+    return &CrcUpdate;
+
+#if defined(Z7_CRC_HW_USE)
+  if (algo == sizeof(CRC_HW_WORD_TYPE) * 8)
+  {
+#ifdef Z7_CRC_HW_FORCE
+    return &CrcUpdate;
+#else
+    if (g_Crc_Algo == 0)
+      return &CrcUpdate_HW;
+#endif
+  }
+#endif
+
+#ifndef Z7_CRC_HW_FORCE
+  if (algo == Z7_CRC_NUM_TABLES_USE)
+    return
+  #ifdef Z7_CRC_HW_USE
+      &CrcUpdate_Base;
+  #else
+      &CrcUpdate;
   #endif
+#endif
+
+  return NULL;
 }
 
 #undef kCrcPoly
-#undef CRC64_NUM_TABLES
+#undef Z7_CRC_NUM_TABLES_USE
+#undef Z7_CRC_NUM_TABLES_TOTAL
 #undef CRC_UPDATE_BYTE_2
+#undef FUNC_NAME_LE_2
+#undef FUNC_NAME_LE_1
+#undef FUNC_NAME_LE
+#undef FUNC_NAME_BE_2
+#undef FUNC_NAME_BE_1
+#undef FUNC_NAME_BE
+
+#undef CRC_HW_UNROLL_BYTES
+#undef CRC_HW_WORD_FUNC
+#undef CRC_HW_WORD_TYPE

3rdparty/lzma/src/7zCrcOpt.c

@@ -1,117 +1,199 @@
-/* 7zCrcOpt.c -- CRC32 calculation
-2023-04-02 : Igor Pavlov : Public domain */
+/* 7zCrcOpt.c -- CRC32 calculation (optimized functions)
+2023-12-07 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
 #include "CpuArch.h"
 
+#if !defined(Z7_CRC_NUM_TABLES) || Z7_CRC_NUM_TABLES > 1
+
+// for debug only : define Z7_CRC_DEBUG_BE to test big-endian code in little-endian cpu
+// #define Z7_CRC_DEBUG_BE
+#ifdef Z7_CRC_DEBUG_BE
+#undef MY_CPU_LE
+#define MY_CPU_BE
+#endif
+
+// the value Z7_CRC_NUM_TABLES_USE must be defined to same value as in 7zCrc.c
+#ifdef Z7_CRC_NUM_TABLES
+#define Z7_CRC_NUM_TABLES_USE  Z7_CRC_NUM_TABLES
+#else
+#define Z7_CRC_NUM_TABLES_USE  12
+#endif
+
+#if Z7_CRC_NUM_TABLES_USE % 4     || \
+    Z7_CRC_NUM_TABLES_USE < 4 * 1 || \
+    Z7_CRC_NUM_TABLES_USE > 4 * 6
+  #error Stop_Compiling_Bad_Z7_CRC_NUM_TABLES
+#endif
+
+
 #ifndef MY_CPU_BE
 
-#define CRC_UPDATE_BYTE_2(crc, b) (table[((crc) ^ (b)) & 0xFF] ^ ((crc) >> 8))
+#define CRC_UPDATE_BYTE_2(crc, b)  (table[((crc) ^ (b)) & 0xFF] ^ ((crc) >> 8))
 
-UInt32 Z7_FASTCALL CrcUpdateT4(UInt32 v, const void *data, size_t size, const UInt32 *table);
-UInt32 Z7_FASTCALL CrcUpdateT4(UInt32 v, const void *data, size_t size, const UInt32 *table)
+#define Q(n, d) \
+    ( (table + ((n) * 4 + 3) * 0x100)[(Byte)(d)] \
+    ^ (table + ((n) * 4 + 2) * 0x100)[((d) >> 1 * 8) & 0xFF] \
+    ^ (table + ((n) * 4 + 1) * 0x100)[((d) >> 2 * 8) & 0xFF] \
+    ^ (table + ((n) * 4 + 0) * 0x100)[((d) >> 3 * 8)] )
+
+#define R(a)  *((const UInt32 *)(const void *)p + (a))
+
+#define CRC_FUNC_PRE_LE2(step) \
+UInt32 Z7_FASTCALL CrcUpdateT ## step (UInt32 v, const void *data, size_t size, const UInt32 *table)
+
+#define CRC_FUNC_PRE_LE(step)   \
+        CRC_FUNC_PRE_LE2(step); \
+        CRC_FUNC_PRE_LE2(step)
+
+CRC_FUNC_PRE_LE(Z7_CRC_NUM_TABLES_USE)
 {
   const Byte *p = (const Byte *)data;
-  for (; size > 0 && ((unsigned)(ptrdiff_t)p & 3) != 0; size--, p++)
+  const Byte *lim;
+  for (; size && ((unsigned)(ptrdiff_t)p & (7 - (Z7_CRC_NUM_TABLES_USE & 4))) != 0; size--, p++)
     v = CRC_UPDATE_BYTE_2(v, *p);
-  for (; size >= 4; size -= 4, p += 4)
+  lim = p + size;
+  if (size >= Z7_CRC_NUM_TABLES_USE)
   {
-    v ^= *(const UInt32 *)(const void *)p;
-    v =
-          (table + 0x300)[((v      ) & 0xFF)]
-        ^ (table + 0x200)[((v >>  8) & 0xFF)]
-        ^ (table + 0x100)[((v >> 16) & 0xFF)]
-        ^ (table + 0x000)[((v >> 24))];
+    lim -= Z7_CRC_NUM_TABLES_USE;
+    do
+    {
+      v ^= R(0);
+      {
+#if Z7_CRC_NUM_TABLES_USE == 1 * 4
+        v = Q(0, v);
+#else
+#define U2(r, op) \
+        { d = R(r);  x op Q(Z7_CRC_NUM_TABLES_USE / 4 - 1 - (r), d); }
+        UInt32 d, x;
+        U2(1, =)
+#if Z7_CRC_NUM_TABLES_USE >= 3 * 4
+#define U(r)  U2(r, ^=)
+        U(2)
+#if Z7_CRC_NUM_TABLES_USE >= 4 * 4
+        U(3)
+#if Z7_CRC_NUM_TABLES_USE >= 5 * 4
+        U(4)
+#if Z7_CRC_NUM_TABLES_USE >= 6 * 4
+        U(5)
+#if Z7_CRC_NUM_TABLES_USE >= 7 * 4
+#error Stop_Compiling_Bad_Z7_CRC_NUM_TABLES
+#endif
+#endif
+#endif
+#endif
+#endif
+#undef U
+#undef U2
+        v = x ^ Q(Z7_CRC_NUM_TABLES_USE / 4 - 1, v);
+#endif
+      }
+      p += Z7_CRC_NUM_TABLES_USE;
+    }
+    while (p <= lim);
+    lim += Z7_CRC_NUM_TABLES_USE;
   }
-  for (; size > 0; size--, p++)
+  for (; p < lim; p++)
     v = CRC_UPDATE_BYTE_2(v, *p);
   return v;
 }
 
-UInt32 Z7_FASTCALL CrcUpdateT8(UInt32 v, const void *data, size_t size, const UInt32 *table);
-UInt32 Z7_FASTCALL CrcUpdateT8(UInt32 v, const void *data, size_t size, const UInt32 *table)
-{
-  const Byte *p = (const Byte *)data;
-  for (; size > 0 && ((unsigned)(ptrdiff_t)p & 7) != 0; size--, p++)
-    v = CRC_UPDATE_BYTE_2(v, *p);
-  for (; size >= 8; size -= 8, p += 8)
-  {
-    UInt32 d;
-    v ^= *(const UInt32 *)(const void *)p;
-    v =
-          (table + 0x700)[((v      ) & 0xFF)]
-        ^ (table + 0x600)[((v >>  8) & 0xFF)]
-        ^ (table + 0x500)[((v >> 16) & 0xFF)]
-        ^ (table + 0x400)[((v >> 24))];
-    d = *((const UInt32 *)(const void *)p + 1);
-    v ^=
-          (table + 0x300)[((d      ) & 0xFF)]
-        ^ (table + 0x200)[((d >>  8) & 0xFF)]
-        ^ (table + 0x100)[((d >> 16) & 0xFF)]
-        ^ (table + 0x000)[((d >> 24))];
-  }
-  for (; size > 0; size--, p++)
-    v = CRC_UPDATE_BYTE_2(v, *p);
-  return v;
-}
+#undef CRC_UPDATE_BYTE_2
+#undef R
+#undef Q
+#undef CRC_FUNC_PRE_LE
+#undef CRC_FUNC_PRE_LE2
 
 #endif
 
 
+
+
 #ifndef MY_CPU_LE
 
-#define CRC_UINT32_SWAP(v)  Z7_BSWAP32(v)
+#define CRC_UPDATE_BYTE_2_BE(crc, b)  (table[((crc) >> 24) ^ (b)] ^ ((crc) << 8))
 
-#define CRC_UPDATE_BYTE_2_BE(crc, b) (table[(((crc) >> 24) ^ (b))] ^ ((crc) << 8))
+#define Q(n, d) \
+    ( (table + ((n) * 4 + 0) * 0x100)[((d)) & 0xFF] \
+    ^ (table + ((n) * 4 + 1) * 0x100)[((d) >> 1 * 8) & 0xFF] \
+    ^ (table + ((n) * 4 + 2) * 0x100)[((d) >> 2 * 8) & 0xFF] \
+    ^ (table + ((n) * 4 + 3) * 0x100)[((d) >> 3 * 8)] )
 
-UInt32 Z7_FASTCALL CrcUpdateT1_BeT4(UInt32 v, const void *data, size_t size, const UInt32 *table)
+#ifdef Z7_CRC_DEBUG_BE
+  #define R(a)  GetBe32a((const UInt32 *)(const void *)p + (a))
+#else
+  #define R(a)         *((const UInt32 *)(const void *)p + (a))
+#endif
+
+
+#define CRC_FUNC_PRE_BE2(step) \
+UInt32 Z7_FASTCALL CrcUpdateT1_BeT ## step (UInt32 v, const void *data, size_t size, const UInt32 *table)
+
+#define CRC_FUNC_PRE_BE(step)   \
+        CRC_FUNC_PRE_BE2(step); \
+        CRC_FUNC_PRE_BE2(step)
+
+CRC_FUNC_PRE_BE(Z7_CRC_NUM_TABLES_USE)
 {
   const Byte *p = (const Byte *)data;
+  const Byte *lim;
   table += 0x100;
-  v = CRC_UINT32_SWAP(v);
-  for (; size > 0 && ((unsigned)(ptrdiff_t)p & 3) != 0; size--, p++)
+  v = Z7_BSWAP32(v);
+  for (; size && ((unsigned)(ptrdiff_t)p & (7 - (Z7_CRC_NUM_TABLES_USE & 4))) != 0; size--, p++)
     v = CRC_UPDATE_BYTE_2_BE(v, *p);
-  for (; size >= 4; size -= 4, p += 4)
+  lim = p + size;
+  if (size >= Z7_CRC_NUM_TABLES_USE)
   {
-    v ^= *(const UInt32 *)(const void *)p;
-    v =
-          (table + 0x000)[((v      ) & 0xFF)]
-        ^ (table + 0x100)[((v >>  8) & 0xFF)]
-        ^ (table + 0x200)[((v >> 16) & 0xFF)]
-        ^ (table + 0x300)[((v >> 24))];
+    lim -= Z7_CRC_NUM_TABLES_USE;
+    do
+    {
+      v ^= R(0);
+      {
+#if Z7_CRC_NUM_TABLES_USE == 1 * 4
+        v = Q(0, v);
+#else
+#define U2(r, op) \
+        { d = R(r);  x op Q(Z7_CRC_NUM_TABLES_USE / 4 - 1 - (r), d); }
+        UInt32 d, x;
+        U2(1, =)
+#if Z7_CRC_NUM_TABLES_USE >= 3 * 4
+#define U(r)  U2(r, ^=)
+        U(2)
+#if Z7_CRC_NUM_TABLES_USE >= 4 * 4
+        U(3)
+#if Z7_CRC_NUM_TABLES_USE >= 5 * 4
+        U(4)
+#if Z7_CRC_NUM_TABLES_USE >= 6 * 4
+        U(5)
+#if Z7_CRC_NUM_TABLES_USE >= 7 * 4
+#error Stop_Compiling_Bad_Z7_CRC_NUM_TABLES
+#endif
+#endif
+#endif
+#endif
+#endif
+#undef U
+#undef U2
+        v = x ^ Q(Z7_CRC_NUM_TABLES_USE / 4 - 1, v);
+#endif
+      }
+      p += Z7_CRC_NUM_TABLES_USE;
+    }
+    while (p <= lim);
+    lim += Z7_CRC_NUM_TABLES_USE;
   }
-  for (; size > 0; size--, p++)
+  for (; p < lim; p++)
     v = CRC_UPDATE_BYTE_2_BE(v, *p);
-  return CRC_UINT32_SWAP(v);
+  return Z7_BSWAP32(v);
 }
 
-UInt32 Z7_FASTCALL CrcUpdateT1_BeT8(UInt32 v, const void *data, size_t size, const UInt32 *table)
-{
-  const Byte *p = (const Byte *)data;
-  table += 0x100;
-  v = CRC_UINT32_SWAP(v);
-  for (; size > 0 && ((unsigned)(ptrdiff_t)p & 7) != 0; size--, p++)
-    v = CRC_UPDATE_BYTE_2_BE(v, *p);
-  for (; size >= 8; size -= 8, p += 8)
-  {
-    UInt32 d;
-    v ^= *(const UInt32 *)(const void *)p;
-    v =
-          (table + 0x400)[((v      ) & 0xFF)]
-        ^ (table + 0x500)[((v >>  8) & 0xFF)]
-        ^ (table + 0x600)[((v >> 16) & 0xFF)]
-        ^ (table + 0x700)[((v >> 24))];
-    d = *((const UInt32 *)(const void *)p + 1);
-    v ^=
-          (table + 0x000)[((d      ) & 0xFF)]
-        ^ (table + 0x100)[((d >>  8) & 0xFF)]
-        ^ (table + 0x200)[((d >> 16) & 0xFF)]
-        ^ (table + 0x300)[((d >> 24))];
-  }
-  for (; size > 0; size--, p++)
-    v = CRC_UPDATE_BYTE_2_BE(v, *p);
-  return CRC_UINT32_SWAP(v);
-}
+#undef CRC_UPDATE_BYTE_2_BE
+#undef R
+#undef Q
+#undef CRC_FUNC_PRE_BE
+#undef CRC_FUNC_PRE_BE2
 
 #endif
+#undef Z7_CRC_NUM_TABLES_USE
+#endif

3rdparty/lzma/src/7zDec.c

@@ -1,5 +1,5 @@
 /* 7zDec.c -- Decoding from 7z folder
-2023-04-02 : Igor Pavlov : Public domain */
+2024-03-01 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
@@ -51,6 +51,7 @@
 
 #ifndef Z7_NO_METHODS_FILTERS
 #define k_Delta 3
+#define k_RISCV 0xb
 #define k_BCJ   0x3030103
 #define k_PPC   0x3030205
 #define k_IA64  0x3030401
@@ -362,6 +363,7 @@ static SRes CheckSupportedFolder(const CSzFolder *f)
       case k_IA64:
       case k_SPARC:
       case k_ARM:
+      case k_RISCV:
     #endif
     #ifdef Z7_USE_FILTER_ARM64
       case k_ARM64:
@@ -535,10 +537,10 @@ static SRes SzFolder_Decode2(const CSzFolder *folder,
         }
       }
     }
-  #if defined(Z7_USE_BRANCH_FILTER)
+#if defined(Z7_USE_BRANCH_FILTER)
     else if (ci == 1)
     {
-     #if !defined(Z7_NO_METHODS_FILTERS)
+#if !defined(Z7_NO_METHODS_FILTERS)
       if (coder->MethodID == k_Delta)
       {
         if (coder->PropsSize != 1)
@@ -550,22 +552,43 @@ static SRes SzFolder_Decode2(const CSzFolder *folder,
         }
         continue;
       }
-     #endif
+#endif
      
-     #ifdef Z7_USE_FILTER_ARM64
+#ifdef Z7_USE_FILTER_ARM64
       if (coder->MethodID == k_ARM64)
       {
         UInt32 pc = 0;
         if (coder->PropsSize == 4)
+        {
           pc = GetUi32(propsData + coder->PropsOffset);
+          if (pc & 3)
+            return SZ_ERROR_UNSUPPORTED;
+        }
         else if (coder->PropsSize != 0)
           return SZ_ERROR_UNSUPPORTED;
         z7_BranchConv_ARM64_Dec(outBuffer, outSize, pc);
         continue;
       }
-     #endif
-     
-     #if !defined(Z7_NO_METHODS_FILTERS) || defined(Z7_USE_FILTER_ARMT)
+#endif
+
+#if !defined(Z7_NO_METHODS_FILTERS)
+      if (coder->MethodID == k_RISCV)
+      {
+        UInt32 pc = 0;
+        if (coder->PropsSize == 4)
+        {
+          pc = GetUi32(propsData + coder->PropsOffset);
+          if (pc & 1)
+            return SZ_ERROR_UNSUPPORTED;
+        }
+        else if (coder->PropsSize != 0)
+          return SZ_ERROR_UNSUPPORTED;
+        z7_BranchConv_RISCV_Dec(outBuffer, outSize, pc);
+        continue;
+      }
+#endif
+      
+#if !defined(Z7_NO_METHODS_FILTERS) || defined(Z7_USE_FILTER_ARMT)
       {
         if (coder->PropsSize != 0)
           return SZ_ERROR_UNSUPPORTED;
@@ -579,7 +602,8 @@ static SRes SzFolder_Decode2(const CSzFolder *folder,
             z7_BranchConvSt_X86_Dec(outBuffer, outSize, 0, &state); // pc = 0
             break;
           }
-          CASE_BRA_CONV(PPC)
+          case k_PPC: Z7_BRANCH_CONV_DEC_2(BranchConv_PPC)(outBuffer, outSize, 0); break; // pc = 0;
+          // CASE_BRA_CONV(PPC)
           CASE_BRA_CONV(IA64)
           CASE_BRA_CONV(SPARC)
           CASE_BRA_CONV(ARM)
@@ -592,9 +616,9 @@ static SRes SzFolder_Decode2(const CSzFolder *folder,
         }
         continue;
       }
-     #endif
+#endif
     } // (c == 1)
-  #endif
+#endif // Z7_USE_BRANCH_FILTER
     else
       return SZ_ERROR_UNSUPPORTED;
   }

3rdparty/lzma/src/Aes.c

@@ -1,5 +1,5 @@
 /* Aes.c -- AES encryption / decryption
-2023-04-02 : Igor Pavlov : Public domain */
+2024-03-01 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
@@ -13,7 +13,9 @@ AES_CODE_FUNC g_AesCtr_Code;
 UInt32 g_Aes_SupportedFunctions_Flags;
 #endif
 
+MY_ALIGN(64)
 static UInt32 T[256 * 4];
+MY_ALIGN(64)
 static const Byte Sbox[256] = {
   0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5, 0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76,
   0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0, 0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0,
@@ -33,7 +35,9 @@ static const Byte Sbox[256] = {
   0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68, 0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16};
 
 
+MY_ALIGN(64)
 static UInt32 D[256 * 4];
+MY_ALIGN(64)
 static Byte InvS[256];
 
 #define xtime(x) ((((x) << 1) ^ (((x) & 0x80) != 0 ? 0x1B : 0)) & 0xFF)
@@ -54,24 +58,54 @@ static Byte InvS[256];
 // #define Z7_SHOW_AES_STATUS
 
 #ifdef MY_CPU_X86_OR_AMD64
-  #define USE_HW_AES
-#elif defined(MY_CPU_ARM_OR_ARM64) && defined(MY_CPU_LE)
-  #if defined(__clang__)
-    #if (__clang_major__ >= 8) // fix that check
-      #define USE_HW_AES
-    #endif
-  #elif defined(__GNUC__)
-    #if (__GNUC__ >= 6) // fix that check
+
+  #if defined(__INTEL_COMPILER)
+    #if (__INTEL_COMPILER >= 1110)
       #define USE_HW_AES
+      #if (__INTEL_COMPILER >= 1900)
+        #define USE_HW_VAES
+      #endif
     #endif
+  #elif defined(Z7_CLANG_VERSION) && (Z7_CLANG_VERSION >= 30800) \
+     || defined(Z7_GCC_VERSION)   && (Z7_GCC_VERSION   >= 40400)
+    #define USE_HW_AES
+      #if defined(__clang__) && (__clang_major__ >= 8) \
+          || defined(__GNUC__) && (__GNUC__ >= 8)
+        #define USE_HW_VAES
+      #endif
   #elif defined(_MSC_VER)
-    #if _MSC_VER >= 1910
+    #define USE_HW_AES
+    #define USE_HW_VAES
+  #endif
+
+#elif defined(MY_CPU_ARM_OR_ARM64) && defined(MY_CPU_LE)
+  
+  #if   defined(__ARM_FEATURE_AES) \
+     || defined(__ARM_FEATURE_CRYPTO)
+    #define USE_HW_AES
+  #else
+    #if  defined(MY_CPU_ARM64) \
+      || defined(__ARM_ARCH) && (__ARM_ARCH >= 4) \
+      || defined(Z7_MSC_VER_ORIGINAL)
+    #if  defined(__ARM_FP) && \
+          (   defined(Z7_CLANG_VERSION) && (Z7_CLANG_VERSION >= 30800) \
+           || defined(__GNUC__) && (__GNUC__ >= 6) \
+          ) \
+      || defined(Z7_MSC_VER_ORIGINAL) && (_MSC_VER >= 1910)
+    #if  defined(MY_CPU_ARM64) \
+      || !defined(Z7_CLANG_VERSION) \
+      || defined(__ARM_NEON) && \
+          (Z7_CLANG_VERSION < 170000 || \
+           Z7_CLANG_VERSION > 170001)
       #define USE_HW_AES
     #endif
+    #endif
+    #endif
   #endif
 #endif
 
 #ifdef USE_HW_AES
+// #pragma message("=== Aes.c USE_HW_AES === ")
 #ifdef Z7_SHOW_AES_STATUS
 #include <stdio.h>
 #define PRF(x) x
@@ -136,6 +170,7 @@ void AesGenTables(void)
     #endif
 
     #ifdef MY_CPU_X86_OR_AMD64
+    #ifdef USE_HW_VAES
     if (CPU_IsSupported_VAES_AVX2())
     {
       PRF(printf("\n===vaes avx2\n"));
@@ -146,6 +181,7 @@ void AesGenTables(void)
       #endif
     }
     #endif
+    #endif
   }
   #endif
 

3rdparty/lzma/src/AesOpt.c

@@ -1,5 +1,5 @@
 /* AesOpt.c -- AES optimized code for x86 AES hardware instructions
-2023-04-02 : Igor Pavlov : Public domain */
+2024-03-01 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
@@ -15,8 +15,8 @@
         #define USE_INTEL_VAES
       #endif
     #endif
-  #elif defined(__clang__) && (__clang_major__ > 3 || __clang_major__ == 3 && __clang_minor__ >= 8) \
-       || defined(__GNUC__) && (__GNUC__ > 4 || __GNUC__ == 4 && __GNUC_MINOR__ >= 4)
+  #elif defined(Z7_CLANG_VERSION) && (Z7_CLANG_VERSION >= 30800) \
+     || defined(Z7_GCC_VERSION)   && (Z7_GCC_VERSION   >= 40400)
         #define USE_INTEL_AES
         #if !defined(__AES__)
           #define ATTRIB_AES __attribute__((__target__("aes")))
@@ -35,27 +35,37 @@
         #define USE_INTEL_VAES
       #endif
     #endif
+    #ifndef USE_INTEL_AES
+      #define Z7_USE_AES_HW_STUB
+    #endif
+    #ifndef USE_INTEL_VAES
+      #define Z7_USE_VAES_HW_STUB
+    #endif
   #endif
 
-#ifndef ATTRIB_AES
-  #define ATTRIB_AES
-#endif
-#ifndef ATTRIB_VAES
-  #define ATTRIB_VAES
-#endif
+    #ifndef USE_INTEL_AES
+      // #define Z7_USE_AES_HW_STUB // for debug
+    #endif
+    #ifndef USE_INTEL_VAES
+      // #define Z7_USE_VAES_HW_STUB // for debug
+    #endif
 
 
 #ifdef USE_INTEL_AES
 
 #include <wmmintrin.h>
 
-#ifndef USE_INTEL_VAES
+#if !defined(USE_INTEL_VAES) && defined(Z7_USE_VAES_HW_STUB)
 #define AES_TYPE_keys UInt32
 #define AES_TYPE_data Byte
 // #define AES_TYPE_keys __m128i
 // #define AES_TYPE_data __m128i
 #endif
 
+#ifndef ATTRIB_AES
+  #define ATTRIB_AES
+#endif
+
 #define AES_FUNC_START(name) \
     void Z7_FASTCALL name(UInt32 *ivAes, Byte *data8, size_t numBlocks)
     // void Z7_FASTCALL name(__m128i *p, __m128i *data, size_t numBlocks)
@@ -69,8 +79,6 @@ AES_FUNC_START (name)
 #define MM_OP_m(op, src)      MM_OP(op, m, src)
 
 #define MM_XOR( dest, src)    MM_OP(_mm_xor_si128,    dest, src)
-#define AVX_XOR(dest, src)    MM_OP(_mm256_xor_si256, dest, src)
-
 
 AES_FUNC_START2 (AesCbc_Encode_HW)
 {
@@ -139,11 +147,6 @@ AES_FUNC_START2 (AesCbc_Encode_HW)
 #define XOR_data_M1(reg, ii)  MM_XOR (reg, data[ii- 1])
 #endif
 
-#define AVX_DECLARE_VAR(reg, ii)  __m256i reg;
-#define AVX_LOAD_data(  reg, ii)  reg = ((const __m256i *)(const void *)data)[ii];
-#define AVX_STORE_data( reg, ii)  ((__m256i *)(void *)data)[ii] = reg;
-#define AVX_XOR_data_M1(reg, ii)  AVX_XOR (reg, (((const __m256i *)(const void *)(data - 1))[ii]))
-
 #define MM_OP_key(op, reg)  MM_OP(op, reg, key);
 
 #define AES_DEC(      reg, ii)   MM_OP_key (_mm_aesdec_si128,     reg)
@@ -152,27 +155,13 @@ AES_FUNC_START2 (AesCbc_Encode_HW)
 #define AES_ENC_LAST( reg, ii)   MM_OP_key (_mm_aesenclast_si128, reg)
 #define AES_XOR(      reg, ii)   MM_OP_key (_mm_xor_si128,        reg)
 
-
-#define AVX_AES_DEC(      reg, ii)   MM_OP_key (_mm256_aesdec_epi128,     reg)
-#define AVX_AES_DEC_LAST( reg, ii)   MM_OP_key (_mm256_aesdeclast_epi128, reg)
-#define AVX_AES_ENC(      reg, ii)   MM_OP_key (_mm256_aesenc_epi128,     reg)
-#define AVX_AES_ENC_LAST( reg, ii)   MM_OP_key (_mm256_aesenclast_epi128, reg)
-#define AVX_AES_XOR(      reg, ii)   MM_OP_key (_mm256_xor_si256,         reg)
-
 #define CTR_START(reg, ii)  MM_OP (_mm_add_epi64, ctr, one)  reg = ctr;
 #define CTR_END(  reg, ii)  MM_XOR (data[ii], reg)
 
-#define AVX_CTR_START(reg, ii)  MM_OP (_mm256_add_epi64, ctr2, two)  reg = _mm256_xor_si256(ctr2, key);
-#define AVX_CTR_END(  reg, ii)  AVX_XOR (((__m256i *)(void *)data)[ii], reg)
-
 #define WOP_KEY(op, n) { \
     const __m128i key = w[n]; \
     WOP(op); }
 
-#define AVX_WOP_KEY(op, n) { \
-    const __m256i key = w[n]; \
-    WOP(op); }
-
 
 #define WIDE_LOOP_START  \
     dataEnd = data + numBlocks;  \
@@ -190,6 +179,40 @@ AES_FUNC_START2 (AesCbc_Encode_HW)
     for (; data < dataEnd; data++)
 
 
+
+#ifdef USE_INTEL_VAES
+
+#define AVX_XOR(dest, src)    MM_OP(_mm256_xor_si256, dest, src)
+#define AVX_DECLARE_VAR(reg, ii)  __m256i reg;
+#define AVX_LOAD_data(  reg, ii)  reg = ((const __m256i *)(const void *)data)[ii];
+#define AVX_STORE_data( reg, ii)  ((__m256i *)(void *)data)[ii] = reg;
+/*
+AVX_XOR_data_M1() needs unaligned memory load
+if (we don't use _mm256_loadu_si256() here)
+{
+  Most compilers with enabled optimizations generate fused AVX (LOAD + OP)
+  instruction that can load unaligned data.
+  But GCC and CLANG without -O2 or -O1 optimizations can generate separated
+  LOAD-ALIGNED (vmovdqa) instruction that will fail on execution.
+}
+Note: some compilers generate more instructions, if we use _mm256_loadu_si256() here.
+v23.02: we use _mm256_loadu_si256() here, because we need compatibility with any compiler.
+*/
+#define AVX_XOR_data_M1(reg, ii)  AVX_XOR (reg, _mm256_loadu_si256(&(((const __m256i *)(const void *)(data - 1))[ii])))
+// for debug only: the following code will fail on execution, if compiled by some compilers:
+// #define AVX_XOR_data_M1(reg, ii)  AVX_XOR (reg, (((const __m256i *)(const void *)(data - 1))[ii]))
+
+#define AVX_AES_DEC(      reg, ii)   MM_OP_key (_mm256_aesdec_epi128,     reg)
+#define AVX_AES_DEC_LAST( reg, ii)   MM_OP_key (_mm256_aesdeclast_epi128, reg)
+#define AVX_AES_ENC(      reg, ii)   MM_OP_key (_mm256_aesenc_epi128,     reg)
+#define AVX_AES_ENC_LAST( reg, ii)   MM_OP_key (_mm256_aesenclast_epi128, reg)
+#define AVX_AES_XOR(      reg, ii)   MM_OP_key (_mm256_xor_si256,         reg)
+#define AVX_CTR_START(reg, ii)  MM_OP (_mm256_add_epi64, ctr2, two)  reg = _mm256_xor_si256(ctr2, key);
+#define AVX_CTR_END(  reg, ii)  AVX_XOR (((__m256i *)(void *)data)[ii], reg)
+#define AVX_WOP_KEY(op, n) { \
+    const __m256i key = w[n]; \
+    WOP(op); }
+
 #define NUM_AES_KEYS_MAX 15
 
 #define WIDE_LOOP_START_AVX(OP)  \
@@ -214,6 +237,9 @@ AES_FUNC_START2 (AesCbc_Encode_HW)
 /* MSVC for x86: If we don't call _mm256_zeroupper(), and -arch:IA32 is not specified,
    MSVC still can insert vzeroupper instruction. */
 
+#endif
+
+
 
 AES_FUNC_START2 (AesCbc_Decode_HW)
 {
@@ -380,6 +406,9 @@ required that <immintrin.h> must be included before <avxintrin.h>.
   #endif
 #endif  // __clang__ && _MSC_VER
 
+#ifndef ATTRIB_VAES
+  #define ATTRIB_VAES
+#endif
 
 #define VAES_FUNC_START2(name) \
 AES_FUNC_START (name); \
@@ -519,10 +548,18 @@ VAES_FUNC_START2 (AesCtr_Code_HW_256)
 
 /* no USE_INTEL_AES */
 
+#if defined(Z7_USE_AES_HW_STUB)
+// We can compile this file with another C compiler,
+// or we can compile asm version.
+// So we can generate real code instead of this stub function.
+// #if defined(_MSC_VER)
 #pragma message("AES  HW_SW stub was used")
+// #endif
 
+#if !defined(USE_INTEL_VAES) && defined(Z7_USE_VAES_HW_STUB)
 #define AES_TYPE_keys UInt32
 #define AES_TYPE_data Byte
+#endif
 
 #define AES_FUNC_START(name) \
     void Z7_FASTCALL name(UInt32 *p, Byte *data, size_t numBlocks) \
@@ -535,13 +572,16 @@ VAES_FUNC_START2 (AesCtr_Code_HW_256)
 AES_COMPAT_STUB (AesCbc_Encode)
 AES_COMPAT_STUB (AesCbc_Decode)
 AES_COMPAT_STUB (AesCtr_Code)
+#endif // Z7_USE_AES_HW_STUB
 
 #endif // USE_INTEL_AES
 
 
 #ifndef USE_INTEL_VAES
-
+#if defined(Z7_USE_VAES_HW_STUB)
+// #if defined(_MSC_VER)
 #pragma message("VAES HW_SW stub was used")
+// #endif
 
 #define VAES_COMPAT_STUB(name) \
     void Z7_FASTCALL name ## _256(UInt32 *p, Byte *data, size_t numBlocks); \
@@ -550,36 +590,59 @@ AES_COMPAT_STUB (AesCtr_Code)
 
 VAES_COMPAT_STUB (AesCbc_Decode_HW)
 VAES_COMPAT_STUB (AesCtr_Code_HW)
-
+#endif
 #endif // ! USE_INTEL_VAES
 
 
+
+
 #elif defined(MY_CPU_ARM_OR_ARM64) && defined(MY_CPU_LE)
 
-  #if defined(__clang__)
-    #if (__clang_major__ >= 8) // fix that check
+  #if   defined(__ARM_FEATURE_AES) \
+     || defined(__ARM_FEATURE_CRYPTO)
+    #define USE_HW_AES
+  #else
+    #if  defined(MY_CPU_ARM64) \
+      || defined(__ARM_ARCH) && (__ARM_ARCH >= 4) \
+      || defined(Z7_MSC_VER_ORIGINAL)
+    #if  defined(__ARM_FP) && \
+          (   defined(Z7_CLANG_VERSION) && (Z7_CLANG_VERSION >= 30800) \
+           || defined(__GNUC__) && (__GNUC__ >= 6) \
+          ) \
+      || defined(Z7_MSC_VER_ORIGINAL) && (_MSC_VER >= 1910)
+    #if  defined(MY_CPU_ARM64) \
+      || !defined(Z7_CLANG_VERSION) \
+      || defined(__ARM_NEON) && \
+          (Z7_CLANG_VERSION < 170000 || \
+           Z7_CLANG_VERSION > 170001)
       #define USE_HW_AES
     #endif
-  #elif defined(__GNUC__)
-    #if (__GNUC__ >= 6) // fix that check
-      #define USE_HW_AES
     #endif
-  #elif defined(_MSC_VER)
-    #if _MSC_VER >= 1910
-      #define USE_HW_AES
     #endif
   #endif
 
 #ifdef USE_HW_AES
 
 // #pragma message("=== AES HW === ")
+// __ARM_FEATURE_CRYPTO macro is deprecated in favor of the finer grained feature macro __ARM_FEATURE_AES
 
 #if defined(__clang__) || defined(__GNUC__)
+#if !defined(__ARM_FEATURE_AES) && \
+    !defined(__ARM_FEATURE_CRYPTO)
   #ifdef MY_CPU_ARM64
-    #define ATTRIB_AES __attribute__((__target__("+crypto,aes")))
+#if defined(__clang__)
+    #define ATTRIB_AES __attribute__((__target__("crypto")))
+#else
+    #define ATTRIB_AES __attribute__((__target__("+crypto")))
+#endif
   #else
+#if defined(__clang__)
+    #define ATTRIB_AES __attribute__((__target__("armv8-a,aes")))
+#else
     #define ATTRIB_AES __attribute__((__target__("fpu=crypto-neon-fp-armv8")))
+#endif
   #endif
+#endif
 #else
   // _MSC_VER
   // for arm32
@@ -590,11 +653,59 @@ VAES_COMPAT_STUB (AesCtr_Code_HW)
   #define ATTRIB_AES
 #endif
 
-#if defined(_MSC_VER) && !defined(__clang__) && defined(MY_CPU_ARM64)
+#if defined(Z7_MSC_VER_ORIGINAL) && defined(MY_CPU_ARM64)
 #include <arm64_neon.h>
 #else
-#include <arm_neon.h>
+/*
+  clang-17.0.1: error : Cannot select: intrinsic %llvm.arm.neon.aese
+  clang
+   3.8.1 : __ARM_NEON             :                    defined(__ARM_FEATURE_CRYPTO)
+   7.0.1 : __ARM_NEON             : __ARM_ARCH >= 8 && defined(__ARM_FEATURE_CRYPTO)
+  11.?.0 : __ARM_NEON && __ARM_FP : __ARM_ARCH >= 8 && defined(__ARM_FEATURE_CRYPTO)
+  13.0.1 : __ARM_NEON && __ARM_FP : __ARM_ARCH >= 8 && defined(__ARM_FEATURE_AES)
+  16     : __ARM_NEON && __ARM_FP : __ARM_ARCH >= 8
+*/
+#if defined(__clang__) && __clang_major__ < 16
+#if !defined(__ARM_FEATURE_AES) && \
+    !defined(__ARM_FEATURE_CRYPTO)
+//     #pragma message("=== we set __ARM_FEATURE_CRYPTO 1 === ")
+    Z7_DIAGNOSTIC_IGNORE_BEGIN_RESERVED_MACRO_IDENTIFIER
+    #define Z7_ARM_FEATURE_CRYPTO_WAS_SET 1
+// #if defined(__clang__) && __clang_major__ < 13
+    #define __ARM_FEATURE_CRYPTO 1
+// #else
+    #define __ARM_FEATURE_AES 1
+// #endif
+    Z7_DIAGNOSTIC_IGNORE_END_RESERVED_MACRO_IDENTIFIER
 #endif
+#endif // clang
+
+#if defined(__clang__)
+
+#if defined(__ARM_ARCH) && __ARM_ARCH < 8
+    Z7_DIAGNOSTIC_IGNORE_BEGIN_RESERVED_MACRO_IDENTIFIER
+//    #pragma message("#define __ARM_ARCH 8")
+    #undef  __ARM_ARCH
+    #define __ARM_ARCH 8
+    Z7_DIAGNOSTIC_IGNORE_END_RESERVED_MACRO_IDENTIFIER
+#endif
+
+#endif // clang
+
+#include <arm_neon.h>
+
+#if defined(Z7_ARM_FEATURE_CRYPTO_WAS_SET) && \
+    defined(__ARM_FEATURE_CRYPTO) && \
+    defined(__ARM_FEATURE_AES)
+Z7_DIAGNOSTIC_IGNORE_BEGIN_RESERVED_MACRO_IDENTIFIER
+    #undef __ARM_FEATURE_CRYPTO
+    #undef __ARM_FEATURE_AES
+    #undef Z7_ARM_FEATURE_CRYPTO_WAS_SET
+Z7_DIAGNOSTIC_IGNORE_END_RESERVED_MACRO_IDENTIFIER
+//    #pragma message("=== we undefine __ARM_FEATURE_CRYPTO === ")
+#endif
+
+#endif // Z7_MSC_VER_ORIGINAL
 
 typedef uint8x16_t v128;
 
@@ -620,7 +731,7 @@ AES_FUNC_START (name)
 
 AES_FUNC_START2 (AesCbc_Encode_HW)
 {
-  v128 *p = (v128*)(void*)ivAes;
+  v128 * const p = (v128*)(void*)ivAes;
   v128 *data = (v128*)(void*)data8;
   v128 m = *p;
   const v128 k0 = p[2];
@@ -639,7 +750,7 @@ AES_FUNC_START2 (AesCbc_Encode_HW)
   const v128 k_z0 = w[2];
   for (; numBlocks != 0; numBlocks--, data++)
   {
-    MM_XOR_m (*data);
+    MM_XOR_m (*data)
     AES_E_MC_m (k0)
     AES_E_MC_m (k1)
     AES_E_MC_m (k2)
@@ -660,7 +771,7 @@ AES_FUNC_START2 (AesCbc_Encode_HW)
       }
     }
     AES_E_m  (k_z1)
-    MM_XOR_m (k_z0);
+    MM_XOR_m (k_z0)
     *data = m;
   }
   *p = m;
@@ -745,7 +856,7 @@ AES_FUNC_START2 (AesCbc_Decode_HW)
     while (w != p);
     WOP_KEY (AES_D,   1)
     WOP_KEY (AES_XOR, 0)
-    MM_XOR (m0, iv);
+    MM_XOR (m0, iv)
     WOP_M1 (XOR_data_M1)
     iv = data[NUM_WAYS - 1];
     WOP (STORE_data)
@@ -759,14 +870,14 @@ AES_FUNC_START2 (AesCbc_Decode_HW)
     AES_D_IMC_m (w[2])
     do
     {
-      AES_D_IMC_m (w[1]);
-      AES_D_IMC_m (w[0]);
+      AES_D_IMC_m (w[1])
+      AES_D_IMC_m (w[0])
       w -= 2;
     }
     while (w != p);
-    AES_D_m  (w[1]);
-    MM_XOR_m (w[0]);
-    MM_XOR_m (iv);
+    AES_D_m  (w[1])
+    MM_XOR_m (w[0])
+    MM_XOR_m (iv)
     iv = *data;
     *data = m;
   }
@@ -783,6 +894,12 @@ AES_FUNC_START2 (AesCtr_Code_HW)
   const v128 *wEnd = p + ((size_t)*(const UInt32 *)(p + 1)) * 2;
   const v128 *dataEnd;
   uint64x2_t one = vdupq_n_u64(0);
+
+// the bug in clang:
+// __builtin_neon_vsetq_lane_i64(__s0, (int8x16_t)__s1, __p2);
+#if defined(__clang__) && (__clang_major__ <= 9)
+#pragma GCC diagnostic ignored "-Wvector-conversion"
+#endif
   one = vsetq_lane_u64(1, one, 0);
   p += 2;
   
@@ -809,11 +926,11 @@ AES_FUNC_START2 (AesCtr_Code_HW)
   {
     const v128 *w = p;
     v128 m;
-    CTR_START (m, 0);
+    CTR_START (m, 0)
     do
     {
-      AES_E_MC_m (w[0]);
-      AES_E_MC_m (w[1]);
+      AES_E_MC_m (w[0])
+      AES_E_MC_m (w[1])
       w += 2;
     }
     while (w != wEnd);

3rdparty/lzma/src/Alloc.c

@@ -1,5 +1,5 @@
 /* Alloc.c -- Memory allocation functions
-2023-04-02 : Igor Pavlov : Public domain */
+2024-02-18 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
@@ -10,19 +10,18 @@
 
 #include "Alloc.h"
 
-#ifdef _WIN32
-#ifdef Z7_LARGE_PAGES
-#if defined(__clang__) || defined(__GNUC__)
-typedef void (*Z7_voidFunction)(void);
-#define MY_CAST_FUNC (Z7_voidFunction)
-#elif defined(_MSC_VER) && _MSC_VER > 1920
-#define MY_CAST_FUNC  (void *)
-// #pragma warning(disable : 4191) // 'type cast': unsafe conversion from 'FARPROC' to 'void (__cdecl *)()'
-#else
-#define MY_CAST_FUNC
+#if defined(Z7_LARGE_PAGES) && defined(_WIN32) && \
+    (!defined(Z7_WIN32_WINNT_MIN) || Z7_WIN32_WINNT_MIN < 0x0502)  // < Win2003 (xp-64)
+  #define Z7_USE_DYN_GetLargePageMinimum
+#endif
+
+// for debug:
+#if 0
+#if defined(__CHERI__) && defined(__SIZEOF_POINTER__) && (__SIZEOF_POINTER__ == 16)
+// #pragma message("=== Z7_ALLOC_NO_OFFSET_ALLOCATOR === ")
+#define Z7_ALLOC_NO_OFFSET_ALLOCATOR
+#endif
 #endif
-#endif // Z7_LARGE_PAGES
-#endif // _WIN32
 
 // #define SZ_ALLOC_DEBUG
 /* #define SZ_ALLOC_DEBUG */
@@ -146,7 +145,9 @@ static void PrintAddr(void *p)
 #define PRINT_FREE(name, cnt, ptr)
 #define Print(s)
 #define PrintLn()
+#ifndef Z7_ALLOC_NO_OFFSET_ALLOCATOR
 #define PrintHex(v, align)
+#endif
 #define PrintAddr(p)
 
 #endif
@@ -246,9 +247,9 @@ void MidFree(void *address)
 #ifdef Z7_LARGE_PAGES
 
 #ifdef MEM_LARGE_PAGES
-  #define MY__MEM_LARGE_PAGES  MEM_LARGE_PAGES
+  #define MY_MEM_LARGE_PAGES  MEM_LARGE_PAGES
 #else
-  #define MY__MEM_LARGE_PAGES  0x20000000
+  #define MY_MEM_LARGE_PAGES  0x20000000
 #endif
 
 extern
@@ -258,19 +259,23 @@ typedef SIZE_T (WINAPI *Func_GetLargePageMinimum)(VOID);
 
 void SetLargePageSize(void)
 {
-  #ifdef Z7_LARGE_PAGES
   SIZE_T size;
+#ifdef Z7_USE_DYN_GetLargePageMinimum
+Z7_DIAGNOSTIC_IGNORE_CAST_FUNCTION
+
   const
    Func_GetLargePageMinimum fn =
-  (Func_GetLargePageMinimum) MY_CAST_FUNC GetProcAddress(GetModuleHandle(TEXT("kernel32.dll")),
+  (Func_GetLargePageMinimum) Z7_CAST_FUNC_C GetProcAddress(GetModuleHandle(TEXT("kernel32.dll")),
        "GetLargePageMinimum");
   if (!fn)
     return;
   size = fn();
+#else
+  size = GetLargePageMinimum();
+#endif
   if (size == 0 || (size & (size - 1)) != 0)
     return;
   g_LargePageSize = size;
-  #endif
 }
 
 #endif // Z7_LARGE_PAGES
@@ -292,7 +297,7 @@ void *BigAlloc(size_t size)
       size2 = (size + ps) & ~ps;
       if (size2 >= size)
       {
-        void *p = VirtualAlloc(NULL, size2, MEM_COMMIT | MY__MEM_LARGE_PAGES, PAGE_READWRITE);
+        void *p = VirtualAlloc(NULL, size2, MEM_COMMIT | MY_MEM_LARGE_PAGES, PAGE_READWRITE);
         if (p)
         {
           PRINT_ALLOC("Alloc-BM ", g_allocCountMid, size2, p)
@@ -328,20 +333,7 @@ const ISzAlloc g_MidAlloc = { SzMidAlloc, SzMidFree };
 const ISzAlloc g_BigAlloc = { SzBigAlloc, SzBigFree };
 #endif
 
-/*
-  uintptr_t : <stdint.h> C99 (optional)
-            : unsupported in VS6
-*/
-
-#ifdef _WIN32
-  typedef UINT_PTR UIntPtr;
-#else
-  /*
-  typedef uintptr_t UIntPtr;
-  */
-  typedef ptrdiff_t UIntPtr;
-#endif
-
+#ifndef Z7_ALLOC_NO_OFFSET_ALLOCATOR
 
 #define ADJUST_ALLOC_SIZE 0
 /*
@@ -352,14 +344,36 @@ const ISzAlloc g_BigAlloc = { SzBigAlloc, SzBigFree };
      MyAlloc() can return address that is NOT multiple of sizeof(void *).
 */
 
-
 /*
-#define MY_ALIGN_PTR_DOWN(p, align) ((void *)((char *)(p) - ((size_t)(UIntPtr)(p) & ((align) - 1))))
+  uintptr_t : <stdint.h> C99 (optional)
+            : unsupported in VS6
 */
-#define MY_ALIGN_PTR_DOWN(p, align) ((void *)((((UIntPtr)(p)) & ~((UIntPtr)(align) - 1))))
+typedef
+  #ifdef _WIN32
+    UINT_PTR
+  #elif 1
+    uintptr_t
+  #else
+    ptrdiff_t
+  #endif
+    MY_uintptr_t;
 
+#if 0 \
+    || (defined(__CHERI__) \
+    || defined(__SIZEOF_POINTER__) && (__SIZEOF_POINTER__ > 8))
+// for 128-bit pointers (cheri):
+#define MY_ALIGN_PTR_DOWN(p, align)  \
+    ((void *)((char *)(p) - ((size_t)(MY_uintptr_t)(p) & ((align) - 1))))
+#else
+#define MY_ALIGN_PTR_DOWN(p, align) \
+    ((void *)((((MY_uintptr_t)(p)) & ~((MY_uintptr_t)(align) - 1))))
+#endif
 
-#if !defined(_WIN32) && defined(_POSIX_C_SOURCE) && (_POSIX_C_SOURCE >= 200112L)
+#endif
+
+#if !defined(_WIN32) \
+    && (defined(Z7_ALLOC_NO_OFFSET_ALLOCATOR) \
+        || defined(_POSIX_C_SOURCE) && (_POSIX_C_SOURCE >= 200112L))
   #define USE_posix_memalign
 #endif
 
@@ -399,14 +413,13 @@ static int posix_memalign(void **ptr, size_t align, size_t size)
 
 #define ALLOC_ALIGN_SIZE ((size_t)1 << 7)
 
-static void *SzAlignedAlloc(ISzAllocPtr pp, size_t size)
+void *z7_AlignedAlloc(size_t size)
 {
-  #ifndef USE_posix_memalign
+#ifndef USE_posix_memalign
   
   void *p;
   void *pAligned;
   size_t newSize;
-  UNUSED_VAR(pp)
 
   /* also we can allocate additional dummy ALLOC_ALIGN_SIZE bytes after aligned
      block to prevent cache line sharing with another allocated blocks */
@@ -431,10 +444,9 @@ static void *SzAlignedAlloc(ISzAllocPtr pp, size_t size)
 
   return pAligned;
 
-  #else
+#else
 
   void *p;
-  UNUSED_VAR(pp)
   if (posix_memalign(&p, ALLOC_ALIGN_SIZE, size))
     return NULL;
 
@@ -443,19 +455,37 @@ static void *SzAlignedAlloc(ISzAllocPtr pp, size_t size)
 
   return p;
 
-  #endif
+#endif
+}
+
+
+void z7_AlignedFree(void *address)
+{
+#ifndef USE_posix_memalign
+  if (address)
+    MyFree(((void **)address)[-1]);
+#else
+  free(address);
+#endif
+}
+
+
+static void *SzAlignedAlloc(ISzAllocPtr pp, size_t size)
+{
+  UNUSED_VAR(pp)
+  return z7_AlignedAlloc(size);
 }
 
 
 static void SzAlignedFree(ISzAllocPtr pp, void *address)
 {
   UNUSED_VAR(pp)
-  #ifndef USE_posix_memalign
+#ifndef USE_posix_memalign
   if (address)
     MyFree(((void **)address)[-1]);
-  #else
+#else
   free(address);
-  #endif
+#endif
 }
 
 
@@ -463,16 +493,44 @@ const ISzAlloc g_AlignedAlloc = { SzAlignedAlloc, SzAlignedFree };
 
 
 
-#define MY_ALIGN_PTR_DOWN_1(p) MY_ALIGN_PTR_DOWN(p, sizeof(void *))
-
 /* we align ptr to support cases where CAlignOffsetAlloc::offset is not multiply of sizeof(void *) */
-#define REAL_BLOCK_PTR_VAR(p) ((void **)MY_ALIGN_PTR_DOWN_1(p))[-1]
-/*
-#define REAL_BLOCK_PTR_VAR(p) ((void **)(p))[-1]
-*/
+#ifndef Z7_ALLOC_NO_OFFSET_ALLOCATOR
+#if 1
+  #define MY_ALIGN_PTR_DOWN_1(p)  MY_ALIGN_PTR_DOWN(p, sizeof(void *))
+  #define REAL_BLOCK_PTR_VAR(p)  ((void **)MY_ALIGN_PTR_DOWN_1(p))[-1]
+#else
+  // we can use this simplified code,
+  // if (CAlignOffsetAlloc::offset == (k * sizeof(void *))
+  #define REAL_BLOCK_PTR_VAR(p)  (((void **)(p))[-1])
+#endif
+#endif
+
+
+#if 0
+#ifndef Z7_ALLOC_NO_OFFSET_ALLOCATOR
+#include <stdio.h>
+static void PrintPtr(const char *s, const void *p)
+{
+  const Byte *p2 = (const Byte *)&p;
+  unsigned i;
+  printf("%s %p ", s, p);
+  for (i = sizeof(p); i != 0;)
+  {
+    i--;
+    printf("%02x", p2[i]);
+  }
+  printf("\n");
+}
+#endif
+#endif
+
 
 static void *AlignOffsetAlloc_Alloc(ISzAllocPtr pp, size_t size)
 {
+#if defined(Z7_ALLOC_NO_OFFSET_ALLOCATOR)
+  UNUSED_VAR(pp)
+  return z7_AlignedAlloc(size);
+#else
   const CAlignOffsetAlloc *p = Z7_CONTAINER_FROM_VTBL_CONST(pp, CAlignOffsetAlloc, vt);
   void *adr;
   void *pAligned;
@@ -501,6 +559,12 @@ static void *AlignOffsetAlloc_Alloc(ISzAllocPtr pp, size_t size)
   pAligned = (char *)MY_ALIGN_PTR_DOWN((char *)adr +
       alignSize - p->offset + extra + ADJUST_ALLOC_SIZE, alignSize) + p->offset;
 
+#if 0
+  printf("\nalignSize = %6x, offset=%6x, size=%8x \n", (unsigned)alignSize, (unsigned)p->offset, (unsigned)size);
+  PrintPtr("base", adr);
+  PrintPtr("alig", pAligned);
+#endif
+
   PrintLn();
   Print("- Aligned: ");
   Print(" size="); PrintHex(size, 8);
@@ -512,11 +576,16 @@ static void *AlignOffsetAlloc_Alloc(ISzAllocPtr pp, size_t size)
   REAL_BLOCK_PTR_VAR(pAligned) = adr;
 
   return pAligned;
+#endif
 }
 
 
 static void AlignOffsetAlloc_Free(ISzAllocPtr pp, void *address)
 {
+#if defined(Z7_ALLOC_NO_OFFSET_ALLOCATOR)
+  UNUSED_VAR(pp)
+  z7_AlignedFree(address);
+#else
   if (address)
   {
     const CAlignOffsetAlloc *p = Z7_CONTAINER_FROM_VTBL_CONST(pp, CAlignOffsetAlloc, vt);
@@ -525,6 +594,7 @@ static void AlignOffsetAlloc_Free(ISzAllocPtr pp, void *address)
     PrintLn();
     ISzAlloc_Free(p->baseAlloc, REAL_BLOCK_PTR_VAR(address));
   }
+#endif
 }
 
 

3rdparty/lzma/src/Bra.c

@@ -1,11 +1,11 @@
 /* Bra.c -- Branch converters for RISC code
-2023-04-02 : Igor Pavlov : Public domain */
+2024-01-20 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
 #include "Bra.h"
-#include "CpuArch.h"
 #include "RotateDefs.h"
+#include "CpuArch.h"
 
 #if defined(MY_CPU_SIZEOF_POINTER) \
     && ( MY_CPU_SIZEOF_POINTER == 4 \
@@ -26,7 +26,7 @@
 #define BR_CONVERT_VAL(v, c) if (encoding) v += c; else v -= c;
 // #define BR_CONVERT_VAL(v, c) if (!encoding) c = (UInt32)0 - c; v += c;
 
-#define Z7_BRANCH_CONV(name) z7_BranchConv_ ## name
+#define Z7_BRANCH_CONV(name) z7_ ## name
 
 #define Z7_BRANCH_FUNC_MAIN(name) \
 static \
@@ -42,11 +42,11 @@ Byte *m(name)(Byte *data, SizeT size, UInt32 pc) \
 
 #ifdef Z7_EXTRACT_ONLY
 #define Z7_BRANCH_FUNCS_IMP(name) \
-  Z7_BRANCH_FUNC_IMP(name, Z7_BRANCH_CONV_DEC, 0)
+  Z7_BRANCH_FUNC_IMP(name, Z7_BRANCH_CONV_DEC_2, 0)
 #else
 #define Z7_BRANCH_FUNCS_IMP(name) \
-  Z7_BRANCH_FUNC_IMP(name, Z7_BRANCH_CONV_DEC, 0) \
-  Z7_BRANCH_FUNC_IMP(name, Z7_BRANCH_CONV_ENC, 1)
+  Z7_BRANCH_FUNC_IMP(name, Z7_BRANCH_CONV_DEC_2, 0) \
+  Z7_BRANCH_FUNC_IMP(name, Z7_BRANCH_CONV_ENC_2, 1)
 #endif
 
 #if defined(__clang__)
@@ -72,7 +72,7 @@ Byte *m(name)(Byte *data, SizeT size, UInt32 pc) \
 #endif
 
 
-Z7_BRANCH_FUNC_MAIN(ARM64)
+Z7_BRANCH_FUNC_MAIN(BranchConv_ARM64)
 {
   // Byte *p = data;
   const Byte *lim;
@@ -121,10 +121,10 @@ Z7_BRANCH_FUNC_MAIN(ARM64)
     }
   }
 }
-Z7_BRANCH_FUNCS_IMP(ARM64)
+Z7_BRANCH_FUNCS_IMP(BranchConv_ARM64)
 
 
-Z7_BRANCH_FUNC_MAIN(ARM)
+Z7_BRANCH_FUNC_MAIN(BranchConv_ARM)
 {
   // Byte *p = data;
   const Byte *lim;
@@ -152,10 +152,10 @@ Z7_BRANCH_FUNC_MAIN(ARM)
     }
   }
 }
-Z7_BRANCH_FUNCS_IMP(ARM)
+Z7_BRANCH_FUNCS_IMP(BranchConv_ARM)
 
 
-Z7_BRANCH_FUNC_MAIN(PPC)
+Z7_BRANCH_FUNC_MAIN(BranchConv_PPC)
 {
   // Byte *p = data;
   const Byte *lim;
@@ -192,14 +192,14 @@ Z7_BRANCH_FUNC_MAIN(PPC)
     }
   }
 }
-Z7_BRANCH_FUNCS_IMP(PPC)
+Z7_BRANCH_FUNCS_IMP(BranchConv_PPC)
 
 
 #ifdef Z7_CPU_FAST_ROTATE_SUPPORTED
 #define BR_SPARC_USE_ROTATE
 #endif
 
-Z7_BRANCH_FUNC_MAIN(SPARC)
+Z7_BRANCH_FUNC_MAIN(BranchConv_SPARC)
 {
   // Byte *p = data;
   const Byte *lim;
@@ -254,10 +254,10 @@ Z7_BRANCH_FUNC_MAIN(SPARC)
     }
   }
 }
-Z7_BRANCH_FUNCS_IMP(SPARC)
+Z7_BRANCH_FUNCS_IMP(BranchConv_SPARC)
 
 
-Z7_BRANCH_FUNC_MAIN(ARMT)
+Z7_BRANCH_FUNC_MAIN(BranchConv_ARMT)
 {
   // Byte *p = data;
   Byte *lim;
@@ -335,12 +335,12 @@ Z7_BRANCH_FUNC_MAIN(ARMT)
   // return (Byte *)(lim + (((lim[1] ^ ~0xfu) & ~7u) == 0 ? 0 : 2));
   // return (Byte *)(lim + 2 - (((((unsigned)lim[1] ^ 8) + 8) >> 7) & 2));
 }
-Z7_BRANCH_FUNCS_IMP(ARMT)
+Z7_BRANCH_FUNCS_IMP(BranchConv_ARMT)
 
 
 // #define BR_IA64_NO_INLINE
 
-Z7_BRANCH_FUNC_MAIN(IA64)
+Z7_BRANCH_FUNC_MAIN(BranchConv_IA64)
 {
   // Byte *p = data;
   const Byte *lim;
@@ -417,4 +417,293 @@ Z7_BRANCH_FUNC_MAIN(IA64)
     }
   }
 }
-Z7_BRANCH_FUNCS_IMP(IA64)
+Z7_BRANCH_FUNCS_IMP(BranchConv_IA64)
+
+
+#define BR_CONVERT_VAL_ENC(v)  v += BR_PC_GET;
+#define BR_CONVERT_VAL_DEC(v)  v -= BR_PC_GET;
+
+#if 1 && defined(MY_CPU_LE_UNALIGN)
+  #define RISCV_USE_UNALIGNED_LOAD
+#endif
+
+#ifdef RISCV_USE_UNALIGNED_LOAD
+  #define RISCV_GET_UI32(p)      GetUi32(p)
+  #define RISCV_SET_UI32(p, v)   { SetUi32(p, v) }
+#else
+  #define RISCV_GET_UI32(p) \
+    ((UInt32)GetUi16a(p) + \
+    ((UInt32)GetUi16a((p) + 2) << 16))
+  #define RISCV_SET_UI32(p, v) { \
+    SetUi16a(p, (UInt16)(v)) \
+    SetUi16a((p) + 2, (UInt16)(v >> 16)) }
+#endif
+
+#if 1 && defined(MY_CPU_LE)
+  #define RISCV_USE_16BIT_LOAD
+#endif
+
+#ifdef RISCV_USE_16BIT_LOAD
+  #define RISCV_LOAD_VAL(p)  GetUi16a(p)
+#else
+  #define RISCV_LOAD_VAL(p)  (*(p))
+#endif
+
+#define RISCV_INSTR_SIZE  2
+#define RISCV_STEP_1      (4 + RISCV_INSTR_SIZE)
+#define RISCV_STEP_2      4
+#define RISCV_REG_VAL     (2 << 7)
+#define RISCV_CMD_VAL     3
+#if 1
+  // for code size optimization:
+  #define RISCV_DELTA_7F  0x7f
+#else
+  #define RISCV_DELTA_7F  0
+#endif
+
+#define RISCV_CHECK_1(v, b) \
+    (((((b) - RISCV_CMD_VAL) ^ ((v) << 8)) & (0xf8000 + RISCV_CMD_VAL)) == 0)
+
+#if 1
+  #define RISCV_CHECK_2(v, r) \
+    ((((v) - ((RISCV_CMD_VAL << 12) | RISCV_REG_VAL | 8)) \
+           << 18) \
+     < ((r) & 0x1d))
+#else
+  // this branch gives larger code, because
+  // compilers generate larger code for big constants.
+  #define RISCV_CHECK_2(v, r) \
+    ((((v) - ((RISCV_CMD_VAL << 12) | RISCV_REG_VAL)) \
+           & ((RISCV_CMD_VAL << 12) | RISCV_REG_VAL)) \
+     < ((r) & 0x1d))
+#endif
+
+
+#define RISCV_SCAN_LOOP \
+  Byte *lim; \
+  size &= ~(SizeT)(RISCV_INSTR_SIZE - 1); \
+  if (size <= 6) return p; \
+  size -= 6; \
+  lim = p + size; \
+  BR_PC_INIT \
+  for (;;) \
+  { \
+    UInt32 a, v; \
+    /* Z7_PRAGMA_OPT_DISABLE_LOOP_UNROLL_VECTORIZE */ \
+    for (;;) \
+    { \
+      if Z7_UNLIKELY(p >= lim) { return p; } \
+      a = (RISCV_LOAD_VAL(p) ^ 0x10u) + 1; \
+      if ((a & 0x77) == 0) break; \
+      a = (RISCV_LOAD_VAL(p + RISCV_INSTR_SIZE) ^ 0x10u) + 1; \
+      p += RISCV_INSTR_SIZE * 2; \
+      if ((a & 0x77) == 0) \
+      { \
+        p -= RISCV_INSTR_SIZE; \
+        if Z7_UNLIKELY(p >= lim) { return p; } \
+        break; \
+      } \
+    }
+// (xx6f ^ 10) + 1 = xx7f + 1 = xx80       : JAL
+// (xxef ^ 10) + 1 = xxff + 1 = xx00 + 100 : JAL
+// (xx17 ^ 10) + 1 = xx07 + 1 = xx08       : AUIPC
+// (xx97 ^ 10) + 1 = xx87 + 1 = xx88       : AUIPC
+
+Byte * Z7_BRANCH_CONV_ENC(RISCV)(Byte *p, SizeT size, UInt32 pc)
+{
+  RISCV_SCAN_LOOP
+    v = a;
+    a = RISCV_GET_UI32(p);
+#ifndef RISCV_USE_16BIT_LOAD
+    v += (UInt32)p[1] << 8;
+#endif
+
+    if ((v & 8) == 0) // JAL
+    {
+      if ((v - (0x100 /* - RISCV_DELTA_7F */)) & 0xd80)
+      {
+        p += RISCV_INSTR_SIZE;
+        continue;
+      }
+      {
+        v = ((a &    1u << 31) >> 11)
+          | ((a & 0x3ff << 21) >> 20)
+          | ((a &     1 << 20) >> 9)
+          |  (a &  0xff << 12);
+        BR_CONVERT_VAL_ENC(v)
+        // ((v & 1) == 0)
+        // v: bits [1 : 20] contain offset bits
+#if 0 && defined(RISCV_USE_UNALIGNED_LOAD)
+        a &= 0xfff;
+        a |= ((UInt32)(v << 23))
+          |  ((UInt32)(v <<  7) & ((UInt32)0xff << 16))
+          |  ((UInt32)(v >>  5) & ((UInt32)0xf0 << 8));
+        RISCV_SET_UI32(p, a)
+#else // aligned
+#if 0
+        SetUi16a(p, (UInt16)(((v >> 5) & 0xf000) | (a & 0xfff)))
+#else
+        p[1] = (Byte)(((v >> 13) & 0xf0) | ((a >> 8) & 0xf));
+#endif
+
+#if 1 && defined(Z7_CPU_FAST_BSWAP_SUPPORTED) && defined(MY_CPU_LE)
+        v <<= 15;
+        v = Z7_BSWAP32(v);
+        SetUi16a(p + 2, (UInt16)v)
+#else
+        p[2] = (Byte)(v >> 9);
+        p[3] = (Byte)(v >> 1);
+#endif
+#endif // aligned
+      }
+      p += 4;
+      continue;
+    } // JAL
+
+    {
+      // AUIPC
+      if (v & 0xe80)  // (not x0) and (not x2)
+      {
+        const UInt32 b = RISCV_GET_UI32(p + 4);
+        if (RISCV_CHECK_1(v, b))
+        {
+          {
+            const UInt32 temp = (b << 12) | (0x17 + RISCV_REG_VAL);
+            RISCV_SET_UI32(p, temp)
+          }
+          a &= 0xfffff000;
+          {
+#if 1
+          const int t = -1 >> 1;
+          if (t != -1)
+            a += (b >> 20) - ((b >> 19) & 0x1000); // arithmetic right shift emulation
+          else
+#endif
+            a += (UInt32)((Int32)b >> 20); // arithmetic right shift (sign-extension).
+          }
+          BR_CONVERT_VAL_ENC(a)
+#if 1 && defined(Z7_CPU_FAST_BSWAP_SUPPORTED) && defined(MY_CPU_LE)
+          a = Z7_BSWAP32(a);
+          RISCV_SET_UI32(p + 4, a)
+#else
+          SetBe32(p + 4, a)
+#endif
+          p += 8;
+        }
+        else
+          p += RISCV_STEP_1;
+      }
+      else
+      {
+        UInt32 r = a >> 27;
+        if (RISCV_CHECK_2(v, r))
+        {
+          v = RISCV_GET_UI32(p + 4);
+          r = (r << 7) + 0x17 + (v & 0xfffff000);
+          a = (a >> 12) | (v << 20);
+          RISCV_SET_UI32(p, r)
+          RISCV_SET_UI32(p + 4, a)
+          p += 8;
+        }
+        else
+          p += RISCV_STEP_2;
+      }
+    }
+  } // for
+}
+
+
+Byte * Z7_BRANCH_CONV_DEC(RISCV)(Byte *p, SizeT size, UInt32 pc)
+{
+  RISCV_SCAN_LOOP
+#ifdef RISCV_USE_16BIT_LOAD
+    if ((a & 8) == 0)
+    {
+#else
+    v = a;
+    a += (UInt32)p[1] << 8;
+    if ((v & 8) == 0)
+    {
+#endif
+      // JAL
+      a -= 0x100 - RISCV_DELTA_7F;
+      if (a & 0xd80)
+      {
+        p += RISCV_INSTR_SIZE;
+        continue;
+      }
+      {
+        const UInt32 a_old = (a + (0xef - RISCV_DELTA_7F)) & 0xfff;
+#if 0 // unaligned
+        a = GetUi32(p);
+        v = (UInt32)(a >> 23) & ((UInt32)0xff << 1)
+          | (UInt32)(a >>  7) & ((UInt32)0xff << 9)
+#elif 1 && defined(Z7_CPU_FAST_BSWAP_SUPPORTED) && defined(MY_CPU_LE)
+        v = GetUi16a(p + 2);
+        v = Z7_BSWAP32(v) >> 15
+#else
+        v = (UInt32)p[3] << 1
+          | (UInt32)p[2] << 9
+#endif
+          | (UInt32)((a & 0xf000) << 5);
+        BR_CONVERT_VAL_DEC(v)
+        a = a_old
+          | (v << 11 &    1u << 31)
+          | (v << 20 & 0x3ff << 21)
+          | (v <<  9 &     1 << 20)
+          | (v       &  0xff << 12);
+        RISCV_SET_UI32(p, a)
+      }
+      p += 4;
+      continue;
+    } // JAL
+
+    {
+      // AUIPC
+      v = a;
+#if 1 && defined(RISCV_USE_UNALIGNED_LOAD)
+      a = GetUi32(p);
+#else
+      a |= (UInt32)GetUi16a(p + 2) << 16;
+#endif
+      if ((v & 0xe80) == 0)  // x0/x2
+      {
+        const UInt32 r = a >> 27;
+        if (RISCV_CHECK_2(v, r))
+        {
+          UInt32 b;
+#if 1 && defined(Z7_CPU_FAST_BSWAP_SUPPORTED) && defined(MY_CPU_LE)
+          b = RISCV_GET_UI32(p + 4);
+          b = Z7_BSWAP32(b);
+#else
+          b = GetBe32(p + 4);
+#endif
+          v = a >> 12;
+          BR_CONVERT_VAL_DEC(b)
+          a = (r << 7) + 0x17;
+          a += (b + 0x800) & 0xfffff000;
+          v |= b << 20;
+          RISCV_SET_UI32(p, a)
+          RISCV_SET_UI32(p + 4, v)
+          p += 8;
+        }
+        else
+          p += RISCV_STEP_2;
+      }
+      else
+      {
+        const UInt32 b = RISCV_GET_UI32(p + 4);
+        if (!RISCV_CHECK_1(v, b))
+          p += RISCV_STEP_1;
+        else
+        {
+          v = (a & 0xfffff000) | (b >> 20);
+          a = (b << 12) | (0x17 + RISCV_REG_VAL);
+          RISCV_SET_UI32(p, a)
+          RISCV_SET_UI32(p + 4, v)
+          p += 8;
+        }
+      }
+    }
+  } // for
+}

3rdparty/lzma/src/CpuArch.c

@@ -1,5 +1,5 @@
 /* CpuArch.c -- CPU specific code
-2023-05-18 : Igor Pavlov : Public domain */
+2024-07-04 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
@@ -226,7 +226,7 @@ void __declspec(naked) Z7_FASTCALL z7_x86_cpuid(UInt32 p[4], UInt32 func)
 DON'T remove Z7_NO_INLINE and Z7_FASTCALL for MY_cpuidex_HACK(): !!!
 */
 static
-Z7_NO_INLINE void Z7_FASTCALL MY_cpuidex_HACK(UInt32 subFunction, UInt32 func, int *CPUInfo)
+Z7_NO_INLINE void Z7_FASTCALL MY_cpuidex_HACK(Int32 subFunction, Int32 func, Int32 *CPUInfo)
 {
   UNUSED_VAR(subFunction)
   __cpuid(CPUInfo, func);
@@ -242,13 +242,13 @@ Z7_NO_INLINE
 #endif
 void Z7_FASTCALL z7_x86_cpuid(UInt32 p[4], UInt32 func)
 {
-  MY_cpuidex((int *)p, (int)func, 0);
+  MY_cpuidex((Int32 *)p, (Int32)func, 0);
 }
 
 Z7_NO_INLINE
 UInt32 Z7_FASTCALL z7_x86_cpuid_GetMaxFunc(void)
 {
-  int a[4];
+  Int32 a[4];
   MY_cpuidex(a, 0, 0);
   return a[0];
 }
@@ -384,7 +384,7 @@ BoolInt CPU_IsSupported_CMOV(void)
   UInt32 a[4];
   if (!x86cpuid_Func_1(&a[0]))
     return 0;
-  return (a[3] >> 15) & 1;
+  return (BoolInt)(a[3] >> 15) & 1;
 }
 
 BoolInt CPU_IsSupported_SSE(void)
@@ -393,7 +393,7 @@ BoolInt CPU_IsSupported_SSE(void)
   CHECK_SYS_SSE_SUPPORT
   if (!x86cpuid_Func_1(&a[0]))
     return 0;
-  return (a[3] >> 25) & 1;
+  return (BoolInt)(a[3] >> 25) & 1;
 }
 
 BoolInt CPU_IsSupported_SSE2(void)
@@ -402,7 +402,7 @@ BoolInt CPU_IsSupported_SSE2(void)
   CHECK_SYS_SSE_SUPPORT
   if (!x86cpuid_Func_1(&a[0]))
     return 0;
-  return (a[3] >> 26) & 1;
+  return (BoolInt)(a[3] >> 26) & 1;
 }
 
 #endif
@@ -419,17 +419,17 @@ static UInt32 x86cpuid_Func_1_ECX(void)
 
 BoolInt CPU_IsSupported_AES(void)
 {
-  return (x86cpuid_Func_1_ECX() >> 25) & 1;
+  return (BoolInt)(x86cpuid_Func_1_ECX() >> 25) & 1;
 }
 
 BoolInt CPU_IsSupported_SSSE3(void)
 {
-  return (x86cpuid_Func_1_ECX() >> 9) & 1;
+  return (BoolInt)(x86cpuid_Func_1_ECX() >> 9) & 1;
 }
 
 BoolInt CPU_IsSupported_SSE41(void)
 {
-  return (x86cpuid_Func_1_ECX() >> 19) & 1;
+  return (BoolInt)(x86cpuid_Func_1_ECX() >> 19) & 1;
 }
 
 BoolInt CPU_IsSupported_SHA(void)
@@ -441,7 +441,7 @@ BoolInt CPU_IsSupported_SHA(void)
   {
     UInt32 d[4];
     z7_x86_cpuid(d, 7);
-    return (d[1] >> 29) & 1;
+    return (BoolInt)(d[1] >> 29) & 1;
   }
 }
 
@@ -638,10 +638,10 @@ BoolInt CPU_IsSupported_AVX(void)
 
   {
     const UInt32 bm = (UInt32)x86_xgetbv_0(MY_XCR_XFEATURE_ENABLED_MASK);
-    // printf("\n=== XGetBV=%d\n", bm);
+    // printf("\n=== XGetBV=0x%x\n", bm);
     return 1
-        & (bm >> 1)  // SSE state is supported (set by OS) for storing/restoring
-        & (bm >> 2); // AVX state is supported (set by OS) for storing/restoring
+        & (BoolInt)(bm >> 1)  // SSE state is supported (set by OS) for storing/restoring
+        & (BoolInt)(bm >> 2); // AVX state is supported (set by OS) for storing/restoring
   }
   // since Win7SP1: we can use GetEnabledXStateFeatures();
 }
@@ -658,10 +658,39 @@ BoolInt CPU_IsSupported_AVX2(void)
     z7_x86_cpuid(d, 7);
     // printf("\ncpuid(7): ebx=%8x ecx=%8x\n", d[1], d[2]);
     return 1
-      & (d[1] >> 5); // avx2
+      & (BoolInt)(d[1] >> 5); // avx2
   }
 }
 
+#if 0
+BoolInt CPU_IsSupported_AVX512F_AVX512VL(void)
+{
+  if (!CPU_IsSupported_AVX())
+    return False;
+  if (z7_x86_cpuid_GetMaxFunc() < 7)
+    return False;
+  {
+    UInt32 d[4];
+    BoolInt v;
+    z7_x86_cpuid(d, 7);
+    // printf("\ncpuid(7): ebx=%8x ecx=%8x\n", d[1], d[2]);
+    v = 1
+      & (BoolInt)(d[1] >> 16)  // avx512f
+      & (BoolInt)(d[1] >> 31); // avx512vl
+    if (!v)
+      return False;
+  }
+  {
+    const UInt32 bm = (UInt32)x86_xgetbv_0(MY_XCR_XFEATURE_ENABLED_MASK);
+    // printf("\n=== XGetBV=0x%x\n", bm);
+    return 1
+        & (BoolInt)(bm >> 5)  // OPMASK
+        & (BoolInt)(bm >> 6)  // ZMM upper 256-bit
+        & (BoolInt)(bm >> 7); // ZMM16 ... ZMM31
+  }
+}
+#endif
+
 BoolInt CPU_IsSupported_VAES_AVX2(void)
 {
   if (!CPU_IsSupported_AVX())
@@ -673,9 +702,9 @@ BoolInt CPU_IsSupported_VAES_AVX2(void)
     z7_x86_cpuid(d, 7);
     // printf("\ncpuid(7): ebx=%8x ecx=%8x\n", d[1], d[2]);
     return 1
-      & (d[1] >> 5) // avx2
+      & (BoolInt)(d[1] >> 5) // avx2
       // & (d[1] >> 31) // avx512vl
-      & (d[2] >> 9); // vaes // VEX-256/EVEX
+      & (BoolInt)(d[2] >> 9); // vaes // VEX-256/EVEX
   }
 }
 
@@ -688,7 +717,7 @@ BoolInt CPU_IsSupported_PageGB(void)
     if (d[0] < 0x80000001)
       return False;
     z7_x86_cpuid(d, 0x80000001);
-    return (d[3] >> 26) & 1;
+    return (BoolInt)(d[3] >> 26) & 1;
   }
 }
 
@@ -760,33 +789,70 @@ BoolInt CPU_IsSupported_AES (void) { return APPLE_CRYPTO_SUPPORT_VAL; }
 
 #else // __APPLE__
 
-#include <sys/auxv.h>
+#if defined(__GLIBC__) && (__GLIBC__ * 100 + __GLIBC_MINOR__ >= 216)
+  #define Z7_GETAUXV_AVAILABLE
+#else
+// #pragma message("=== is not NEW GLIBC === ")
+  #if defined __has_include
+  #if __has_include (<sys/auxv.h>)
+// #pragma message("=== sys/auxv.h is avail=== ")
+    #define Z7_GETAUXV_AVAILABLE
+  #endif
+  #endif
+#endif
 
+#ifdef Z7_GETAUXV_AVAILABLE
+// #pragma message("=== Z7_GETAUXV_AVAILABLE === ")
+#include <sys/auxv.h>
 #define USE_HWCAP
+#endif
 
 #ifdef USE_HWCAP
 
+#if defined(__FreeBSD__)
+static unsigned long MY_getauxval(int aux)
+{
+  unsigned long val;
+  if (elf_aux_info(aux, &val, sizeof(val)))
+    return 0;
+  return val;
+}
+#else
+#define MY_getauxval  getauxval
+  #if defined __has_include
+  #if __has_include (<asm/hwcap.h>)
 #include <asm/hwcap.h>
+  #endif
+  #endif
+#endif
 
   #define MY_HWCAP_CHECK_FUNC_2(name1, name2) \
-  BoolInt CPU_IsSupported_ ## name1() { return (getauxval(AT_HWCAP)  & (HWCAP_  ## name2)) ? 1 : 0; }
+  BoolInt CPU_IsSupported_ ## name1(void) { return (MY_getauxval(AT_HWCAP)  & (HWCAP_  ## name2)); }
 
 #ifdef MY_CPU_ARM64
   #define MY_HWCAP_CHECK_FUNC(name) \
   MY_HWCAP_CHECK_FUNC_2(name, name)
+#if 1 || defined(__ARM_NEON)
+  BoolInt CPU_IsSupported_NEON(void) { return True; }
+#else
   MY_HWCAP_CHECK_FUNC_2(NEON, ASIMD)
+#endif
 // MY_HWCAP_CHECK_FUNC (ASIMD)
 #elif defined(MY_CPU_ARM)
   #define MY_HWCAP_CHECK_FUNC(name) \
-  BoolInt CPU_IsSupported_ ## name() { return (getauxval(AT_HWCAP2) & (HWCAP2_ ## name)) ? 1 : 0; }
+  BoolInt CPU_IsSupported_ ## name(void) { return (MY_getauxval(AT_HWCAP2) & (HWCAP2_ ## name)); }
   MY_HWCAP_CHECK_FUNC_2(NEON, NEON)
 #endif
 
 #else // USE_HWCAP
 
   #define MY_HWCAP_CHECK_FUNC(name) \
-  BoolInt CPU_IsSupported_ ## name() { return 0; }
+  BoolInt CPU_IsSupported_ ## name(void) { return 0; }
+#if defined(__ARM_NEON)
+  BoolInt CPU_IsSupported_NEON(void) { return True; }
+#else
   MY_HWCAP_CHECK_FUNC(NEON)
+#endif
 
 #endif // USE_HWCAP
 

3rdparty/lzma/src/DllSecur.c

@@ -1,5 +1,5 @@
 /* DllSecur.c -- DLL loading security
-2023-04-02 : Igor Pavlov : Public domain */
+2023-12-03 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
@@ -11,19 +11,7 @@
 
 #ifndef UNDER_CE
 
-#if (defined(__GNUC__) && (__GNUC__ >= 8)) || defined(__clang__)
-  // #pragma GCC diagnostic ignored "-Wcast-function-type"
-#endif
-
-#if defined(__clang__) || defined(__GNUC__)
-typedef void (*Z7_voidFunction)(void);
-#define MY_CAST_FUNC (Z7_voidFunction)
-#elif defined(_MSC_VER) && _MSC_VER > 1920
-#define MY_CAST_FUNC  (void *)
-// #pragma warning(disable : 4191) // 'type cast': unsafe conversion from 'FARPROC' to 'void (__cdecl *)()'
-#else
-#define MY_CAST_FUNC
-#endif
+Z7_DIAGNOSTIC_IGNORE_CAST_FUNCTION
 
 typedef BOOL (WINAPI *Func_SetDefaultDllDirectories)(DWORD DirectoryFlags);
 
@@ -61,7 +49,7 @@ static const char * const g_Dlls =
     if ((UInt16)GetVersion() != 6) { \
       const \
        Func_SetDefaultDllDirectories setDllDirs = \
-      (Func_SetDefaultDllDirectories) MY_CAST_FUNC GetProcAddress(GetModuleHandle(TEXT("kernel32.dll")), \
+      (Func_SetDefaultDllDirectories) Z7_CAST_FUNC_C GetProcAddress(GetModuleHandle(TEXT("kernel32.dll")), \
            "SetDefaultDllDirectories"); \
       if (setDllDirs) if (setDllDirs(MY_LOAD_LIBRARY_SEARCH_SYSTEM32 | MY_LOAD_LIBRARY_SEARCH_USER_DIRS)) return; }
 

3rdparty/lzma/src/LzFind.c

@@ -1,5 +1,5 @@
 /* LzFind.c -- Match finder for LZ algorithms
-2023-03-14 : Igor Pavlov : Public domain */
+2024-03-01 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
@@ -108,9 +108,15 @@ static int LzInWindow_Create2(CMatchFinder *p, UInt32 blockSize, ISzAllocPtr all
   return (p->bufBase != NULL);
 }
 
-static const Byte *MatchFinder_GetPointerToCurrentPos(CMatchFinder *p) { return p->buffer; }
+static const Byte *MatchFinder_GetPointerToCurrentPos(void *p)
+{
+  return ((CMatchFinder *)p)->buffer;
+}
 
-static UInt32 MatchFinder_GetNumAvailableBytes(CMatchFinder *p) { return GET_AVAIL_BYTES(p); }
+static UInt32 MatchFinder_GetNumAvailableBytes(void *p)
+{
+  return GET_AVAIL_BYTES((CMatchFinder *)p);
+}
 
 
 Z7_NO_INLINE
@@ -571,8 +577,9 @@ void MatchFinder_Init_4(CMatchFinder *p)
 #define CYC_TO_POS_OFFSET 0
 // #define CYC_TO_POS_OFFSET 1 // for debug
 
-void MatchFinder_Init(CMatchFinder *p)
+void MatchFinder_Init(void *_p)
 {
+  CMatchFinder *p = (CMatchFinder *)_p;
   MatchFinder_Init_HighHash(p);
   MatchFinder_Init_LowHash(p);
   MatchFinder_Init_4(p);
@@ -607,16 +614,16 @@ void MatchFinder_Init(CMatchFinder *p)
     #endif
   #endif
 
-// #elif defined(MY_CPU_ARM_OR_ARM64)
-#elif defined(MY_CPU_ARM64)
+#elif defined(MY_CPU_ARM64) \
+  /* || (defined(__ARM_ARCH) && (__ARM_ARCH >= 7)) */
 
-  #if defined(__clang__) && (__clang_major__ >= 8) \
-    || defined(__GNUC__) && (__GNUC__ >= 8)
+  #if  defined(Z7_CLANG_VERSION) && (Z7_CLANG_VERSION >= 30800) \
+    || defined(__GNUC__) && (__GNUC__ >= 6)
       #define USE_LZFIND_SATUR_SUB_128
     #ifdef MY_CPU_ARM64
       // #define LZFIND_ATTRIB_SSE41 __attribute__((__target__("")))
     #else
-      // #define LZFIND_ATTRIB_SSE41 __attribute__((__target__("fpu=crypto-neon-fp-armv8")))
+      #define LZFIND_ATTRIB_SSE41 __attribute__((__target__("fpu=neon")))
     #endif
 
   #elif defined(_MSC_VER)
@@ -625,7 +632,7 @@ void MatchFinder_Init(CMatchFinder *p)
     #endif
   #endif
 
-  #if defined(_MSC_VER) && !defined(__clang__) && defined(MY_CPU_ARM64)
+  #if defined(Z7_MSC_VER_ORIGINAL) && defined(MY_CPU_ARM64)
     #include <arm64_neon.h>
   #else
     #include <arm_neon.h>
@@ -1082,9 +1089,11 @@ static void SkipMatchesSpec(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, const
 
 
 #define MOVE_POS \
-  ++p->cyclicBufferPos; \
+  p->cyclicBufferPos++; \
   p->buffer++; \
-  { const UInt32 pos1 = p->pos + 1; p->pos = pos1; if (pos1 == p->posLimit) MatchFinder_CheckLimits(p); }
+  { const UInt32 pos1 = p->pos + 1; \
+    p->pos = pos1; \
+    if (pos1 == p->posLimit) MatchFinder_CheckLimits(p); }
 
 #define MOVE_POS_RET MOVE_POS return distances;
 
@@ -1103,20 +1112,26 @@ static void MatchFinder_MovePos(CMatchFinder *p)
 }
 
 #define GET_MATCHES_HEADER2(minLen, ret_op) \
-  unsigned lenLimit; UInt32 hv; const Byte *cur; UInt32 curMatch; \
-  lenLimit = (unsigned)p->lenLimit; { if (lenLimit < minLen) { MatchFinder_MovePos(p); ret_op; }} \
+  UInt32 hv; const Byte *cur; UInt32 curMatch; \
+  UInt32 lenLimit = p->lenLimit; \
+  if (lenLimit < minLen) { MatchFinder_MovePos(p);  ret_op; } \
   cur = p->buffer;
 
 #define GET_MATCHES_HEADER(minLen) GET_MATCHES_HEADER2(minLen, return distances)
-#define SKIP_HEADER(minLen)   do { GET_MATCHES_HEADER2(minLen, continue)
+#define SKIP_HEADER(minLen)  \
+  do { GET_MATCHES_HEADER2(minLen, continue)
 
-#define MF_PARAMS(p)  lenLimit, curMatch, p->pos, p->buffer, p->son, p->cyclicBufferPos, p->cyclicBufferSize, p->cutValue
+#define MF_PARAMS(p)  lenLimit, curMatch, p->pos, p->buffer, p->son, \
+    p->cyclicBufferPos, p->cyclicBufferSize, p->cutValue
 
-#define SKIP_FOOTER  SkipMatchesSpec(MF_PARAMS(p)); MOVE_POS } while (--num);
+#define SKIP_FOOTER  \
+    SkipMatchesSpec(MF_PARAMS(p)); \
+    MOVE_POS \
+  } while (--num);
 
 #define GET_MATCHES_FOOTER_BASE(_maxLen_, func) \
-  distances = func(MF_PARAMS(p), \
-  distances, (UInt32)_maxLen_); MOVE_POS_RET
+  distances = func(MF_PARAMS(p), distances, (UInt32)_maxLen_); \
+  MOVE_POS_RET
 
 #define GET_MATCHES_FOOTER_BT(_maxLen_) \
   GET_MATCHES_FOOTER_BASE(_maxLen_, GetMatchesSpec1)
@@ -1133,8 +1148,9 @@ static void MatchFinder_MovePos(CMatchFinder *p)
     for (; c != lim; c++) if (*(c + diff) != *c) break; \
     maxLen = (unsigned)(c - cur); }
 
-static UInt32* Bt2_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
+static UInt32* Bt2_MatchFinder_GetMatches(void *_p, UInt32 *distances)
 {
+  CMatchFinder *p = (CMatchFinder *)_p;
   GET_MATCHES_HEADER(2)
   HASH2_CALC
   curMatch = p->hash[hv];
@@ -1158,8 +1174,9 @@ UInt32* Bt3Zip_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
     mmm = pos;
 
 
-static UInt32* Bt3_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
+static UInt32* Bt3_MatchFinder_GetMatches(void *_p, UInt32 *distances)
 {
+  CMatchFinder *p = (CMatchFinder *)_p;
   UInt32 mmm;
   UInt32 h2, d2, pos;
   unsigned maxLen;
@@ -1199,8 +1216,9 @@ static UInt32* Bt3_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
 }
 
 
-static UInt32* Bt4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
+static UInt32* Bt4_MatchFinder_GetMatches(void *_p, UInt32 *distances)
 {
+  CMatchFinder *p = (CMatchFinder *)_p;
   UInt32 mmm;
   UInt32 h2, h3, d2, d3, pos;
   unsigned maxLen;
@@ -1267,10 +1285,12 @@ static UInt32* Bt4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
 }
 
 
-static UInt32* Bt5_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
+static UInt32* Bt5_MatchFinder_GetMatches(void *_p, UInt32 *distances)
 {
+  CMatchFinder *p = (CMatchFinder *)_p;
   UInt32 mmm;
-  UInt32 h2, h3, d2, d3, maxLen, pos;
+  UInt32 h2, h3, d2, d3, pos;
+  unsigned maxLen;
   UInt32 *hash;
   GET_MATCHES_HEADER(5)
 
@@ -1339,8 +1359,9 @@ static UInt32* Bt5_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
 }
 
 
-static UInt32* Hc4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
+static UInt32* Hc4_MatchFinder_GetMatches(void *_p, UInt32 *distances)
 {
+  CMatchFinder *p = (CMatchFinder *)_p;
   UInt32 mmm;
   UInt32 h2, h3, d2, d3, pos;
   unsigned maxLen;
@@ -1407,10 +1428,12 @@ static UInt32* Hc4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
 }
 
 
-static UInt32 * Hc5_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
+static UInt32 * Hc5_MatchFinder_GetMatches(void *_p, UInt32 *distances)
 {
+  CMatchFinder *p = (CMatchFinder *)_p;
   UInt32 mmm;
-  UInt32 h2, h3, d2, d3, maxLen, pos;
+  UInt32 h2, h3, d2, d3, pos;
+  unsigned maxLen;
   UInt32 *hash;
   GET_MATCHES_HEADER(5)
 
@@ -1466,7 +1489,7 @@ static UInt32 * Hc5_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
     if (*(cur - d2 + 3) != cur[3])
       break;
     UPDATE_maxLen
-    distances[-2] = maxLen;
+    distances[-2] = (UInt32)maxLen;
     if (maxLen == lenLimit)
     {
       p->son[p->cyclicBufferPos] = curMatch;
@@ -1489,8 +1512,9 @@ UInt32* Hc3Zip_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
 }
 
 
-static void Bt2_MatchFinder_Skip(CMatchFinder *p, UInt32 num)
+static void Bt2_MatchFinder_Skip(void *_p, UInt32 num)
 {
+  CMatchFinder *p = (CMatchFinder *)_p;
   SKIP_HEADER(2)
   {
     HASH2_CALC
@@ -1511,8 +1535,9 @@ void Bt3Zip_MatchFinder_Skip(CMatchFinder *p, UInt32 num)
   SKIP_FOOTER
 }
 
-static void Bt3_MatchFinder_Skip(CMatchFinder *p, UInt32 num)
+static void Bt3_MatchFinder_Skip(void *_p, UInt32 num)
 {
+  CMatchFinder *p = (CMatchFinder *)_p;
   SKIP_HEADER(3)
   {
     UInt32 h2;
@@ -1526,8 +1551,9 @@ static void Bt3_MatchFinder_Skip(CMatchFinder *p, UInt32 num)
   SKIP_FOOTER
 }
 
-static void Bt4_MatchFinder_Skip(CMatchFinder *p, UInt32 num)
+static void Bt4_MatchFinder_Skip(void *_p, UInt32 num)
 {
+  CMatchFinder *p = (CMatchFinder *)_p;
   SKIP_HEADER(4)
   {
     UInt32 h2, h3;
@@ -1542,8 +1568,9 @@ static void Bt4_MatchFinder_Skip(CMatchFinder *p, UInt32 num)
   SKIP_FOOTER
 }
 
-static void Bt5_MatchFinder_Skip(CMatchFinder *p, UInt32 num)
+static void Bt5_MatchFinder_Skip(void *_p, UInt32 num)
 {
+  CMatchFinder *p = (CMatchFinder *)_p;
   SKIP_HEADER(5)
   {
     UInt32 h2, h3;
@@ -1589,8 +1616,9 @@ static void Bt5_MatchFinder_Skip(CMatchFinder *p, UInt32 num)
     }} while(num); \
 
 
-static void Hc4_MatchFinder_Skip(CMatchFinder *p, UInt32 num)
+static void Hc4_MatchFinder_Skip(void *_p, UInt32 num)
 {
+  CMatchFinder *p = (CMatchFinder *)_p;
   HC_SKIP_HEADER(4)
 
     UInt32 h2, h3;
@@ -1604,8 +1632,9 @@ static void Hc4_MatchFinder_Skip(CMatchFinder *p, UInt32 num)
 }
 
 
-static void Hc5_MatchFinder_Skip(CMatchFinder *p, UInt32 num)
+static void Hc5_MatchFinder_Skip(void *_p, UInt32 num)
 {
+  CMatchFinder *p = (CMatchFinder *)_p;
   HC_SKIP_HEADER(5)
   
     UInt32 h2, h3;
@@ -1634,41 +1663,41 @@ void Hc3Zip_MatchFinder_Skip(CMatchFinder *p, UInt32 num)
 
 void MatchFinder_CreateVTable(CMatchFinder *p, IMatchFinder2 *vTable)
 {
-  vTable->Init = (Mf_Init_Func)MatchFinder_Init;
-  vTable->GetNumAvailableBytes = (Mf_GetNumAvailableBytes_Func)MatchFinder_GetNumAvailableBytes;
-  vTable->GetPointerToCurrentPos = (Mf_GetPointerToCurrentPos_Func)MatchFinder_GetPointerToCurrentPos;
+  vTable->Init = MatchFinder_Init;
+  vTable->GetNumAvailableBytes = MatchFinder_GetNumAvailableBytes;
+  vTable->GetPointerToCurrentPos = MatchFinder_GetPointerToCurrentPos;
   if (!p->btMode)
   {
     if (p->numHashBytes <= 4)
     {
-      vTable->GetMatches = (Mf_GetMatches_Func)Hc4_MatchFinder_GetMatches;
-      vTable->Skip = (Mf_Skip_Func)Hc4_MatchFinder_Skip;
+      vTable->GetMatches = Hc4_MatchFinder_GetMatches;
+      vTable->Skip = Hc4_MatchFinder_Skip;
     }
     else
     {
-      vTable->GetMatches = (Mf_GetMatches_Func)Hc5_MatchFinder_GetMatches;
-      vTable->Skip = (Mf_Skip_Func)Hc5_MatchFinder_Skip;
+      vTable->GetMatches = Hc5_MatchFinder_GetMatches;
+      vTable->Skip = Hc5_MatchFinder_Skip;
     }
   }
   else if (p->numHashBytes == 2)
   {
-    vTable->GetMatches = (Mf_GetMatches_Func)Bt2_MatchFinder_GetMatches;
-    vTable->Skip = (Mf_Skip_Func)Bt2_MatchFinder_Skip;
+    vTable->GetMatches = Bt2_MatchFinder_GetMatches;
+    vTable->Skip = Bt2_MatchFinder_Skip;
   }
   else if (p->numHashBytes == 3)
   {
-    vTable->GetMatches = (Mf_GetMatches_Func)Bt3_MatchFinder_GetMatches;
-    vTable->Skip = (Mf_Skip_Func)Bt3_MatchFinder_Skip;
+    vTable->GetMatches = Bt3_MatchFinder_GetMatches;
+    vTable->Skip = Bt3_MatchFinder_Skip;
   }
   else if (p->numHashBytes == 4)
   {
-    vTable->GetMatches = (Mf_GetMatches_Func)Bt4_MatchFinder_GetMatches;
-    vTable->Skip = (Mf_Skip_Func)Bt4_MatchFinder_Skip;
+    vTable->GetMatches = Bt4_MatchFinder_GetMatches;
+    vTable->Skip = Bt4_MatchFinder_Skip;
   }
   else
   {
-    vTable->GetMatches = (Mf_GetMatches_Func)Bt5_MatchFinder_GetMatches;
-    vTable->Skip = (Mf_Skip_Func)Bt5_MatchFinder_Skip;
+    vTable->GetMatches = Bt5_MatchFinder_GetMatches;
+    vTable->Skip = Bt5_MatchFinder_Skip;
   }
 }
 

3rdparty/lzma/src/LzFindMt.c

@@ -1,5 +1,5 @@
 /* LzFindMt.c -- multithreaded Match finder for LZ algorithms
-2023-04-02 : Igor Pavlov : Public domain */
+2024-01-22 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
@@ -94,7 +94,7 @@ static void MtSync_Construct(CMtSync *p)
 }
 
 
-#define DEBUG_BUFFER_LOCK   // define it to debug lock state
+// #define DEBUG_BUFFER_LOCK   // define it to debug lock state
 
 #ifdef DEBUG_BUFFER_LOCK
 #include <stdlib.h>
@@ -877,8 +877,9 @@ SRes MatchFinderMt_InitMt(CMatchFinderMt *p)
 }
 
 
-static void MatchFinderMt_Init(CMatchFinderMt *p)
+static void MatchFinderMt_Init(void *_p)
 {
+  CMatchFinderMt *p = (CMatchFinderMt *)_p;
   CMatchFinder *mf = MF(p);
   
   p->btBufPos =
@@ -981,8 +982,9 @@ static UInt32 MatchFinderMt_GetNextBlock_Bt(CMatchFinderMt *p)
 
 
 
-static const Byte * MatchFinderMt_GetPointerToCurrentPos(CMatchFinderMt *p)
+static const Byte * MatchFinderMt_GetPointerToCurrentPos(void *_p)
 {
+  CMatchFinderMt *p = (CMatchFinderMt *)_p;
   return p->pointerToCurPos;
 }
 
@@ -990,8 +992,9 @@ static const Byte * MatchFinderMt_GetPointerToCurrentPos(CMatchFinderMt *p)
 #define GET_NEXT_BLOCK_IF_REQUIRED if (p->btBufPos == p->btBufPosLimit) MatchFinderMt_GetNextBlock_Bt(p);
 
 
-static UInt32 MatchFinderMt_GetNumAvailableBytes(CMatchFinderMt *p)
+static UInt32 MatchFinderMt_GetNumAvailableBytes(void *_p)
 {
+  CMatchFinderMt *p = (CMatchFinderMt *)_p;
   if (p->btBufPos != p->btBufPosLimit)
     return p->btNumAvailBytes;
   return MatchFinderMt_GetNextBlock_Bt(p);
@@ -1243,8 +1246,9 @@ static UInt32 * MixMatches4(CMatchFinderMt *p, UInt32 matchMinPos, UInt32 *d)
 }
 
 
-static UInt32 * MatchFinderMt2_GetMatches(CMatchFinderMt *p, UInt32 *d)
+static UInt32 * MatchFinderMt2_GetMatches(void *_p, UInt32 *d)
 {
+  CMatchFinderMt *p = (CMatchFinderMt *)_p;
   const UInt32 *bt = p->btBufPos;
   const UInt32 len = *bt++;
   const UInt32 *btLim = bt + len;
@@ -1267,8 +1271,9 @@ static UInt32 * MatchFinderMt2_GetMatches(CMatchFinderMt *p, UInt32 *d)
 
 
 
-static UInt32 * MatchFinderMt_GetMatches(CMatchFinderMt *p, UInt32 *d)
+static UInt32 * MatchFinderMt_GetMatches(void *_p, UInt32 *d)
 {
+  CMatchFinderMt *p = (CMatchFinderMt *)_p;
   const UInt32 *bt = p->btBufPos;
   UInt32 len = *bt++;
   const UInt32 avail = p->btNumAvailBytes - 1;
@@ -1315,14 +1320,16 @@ static UInt32 * MatchFinderMt_GetMatches(CMatchFinderMt *p, UInt32 *d)
 #define SKIP_HEADER_MT(n) SKIP_HEADER2_MT if (p->btNumAvailBytes-- >= (n)) { const Byte *cur = p->pointerToCurPos; UInt32 *hash = p->hash;
 #define SKIP_FOOTER_MT } INCREASE_LZ_POS p->btBufPos += (size_t)*p->btBufPos + 1; } while (--num != 0);
 
-static void MatchFinderMt0_Skip(CMatchFinderMt *p, UInt32 num)
+static void MatchFinderMt0_Skip(void *_p, UInt32 num)
 {
+  CMatchFinderMt *p = (CMatchFinderMt *)_p;
   SKIP_HEADER2_MT { p->btNumAvailBytes--;
   SKIP_FOOTER_MT
 }
 
-static void MatchFinderMt2_Skip(CMatchFinderMt *p, UInt32 num)
+static void MatchFinderMt2_Skip(void *_p, UInt32 num)
 {
+  CMatchFinderMt *p = (CMatchFinderMt *)_p;
   SKIP_HEADER_MT(2)
       UInt32 h2;
       MT_HASH2_CALC
@@ -1330,8 +1337,9 @@ static void MatchFinderMt2_Skip(CMatchFinderMt *p, UInt32 num)
   SKIP_FOOTER_MT
 }
 
-static void MatchFinderMt3_Skip(CMatchFinderMt *p, UInt32 num)
+static void MatchFinderMt3_Skip(void *_p, UInt32 num)
 {
+  CMatchFinderMt *p = (CMatchFinderMt *)_p;
   SKIP_HEADER_MT(3)
       UInt32 h2, h3;
       MT_HASH3_CALC
@@ -1361,39 +1369,39 @@ static void MatchFinderMt4_Skip(CMatchFinderMt *p, UInt32 num)
 
 void MatchFinderMt_CreateVTable(CMatchFinderMt *p, IMatchFinder2 *vTable)
 {
-  vTable->Init = (Mf_Init_Func)MatchFinderMt_Init;
-  vTable->GetNumAvailableBytes = (Mf_GetNumAvailableBytes_Func)MatchFinderMt_GetNumAvailableBytes;
-  vTable->GetPointerToCurrentPos = (Mf_GetPointerToCurrentPos_Func)MatchFinderMt_GetPointerToCurrentPos;
-  vTable->GetMatches = (Mf_GetMatches_Func)MatchFinderMt_GetMatches;
+  vTable->Init = MatchFinderMt_Init;
+  vTable->GetNumAvailableBytes = MatchFinderMt_GetNumAvailableBytes;
+  vTable->GetPointerToCurrentPos = MatchFinderMt_GetPointerToCurrentPos;
+  vTable->GetMatches = MatchFinderMt_GetMatches;
   
   switch (MF(p)->numHashBytes)
   {
     case 2:
       p->GetHeadsFunc = GetHeads2;
-      p->MixMatchesFunc = (Mf_Mix_Matches)NULL;
-      vTable->Skip = (Mf_Skip_Func)MatchFinderMt0_Skip;
-      vTable->GetMatches = (Mf_GetMatches_Func)MatchFinderMt2_GetMatches;
+      p->MixMatchesFunc = NULL;
+      vTable->Skip = MatchFinderMt0_Skip;
+      vTable->GetMatches = MatchFinderMt2_GetMatches;
       break;
     case 3:
       p->GetHeadsFunc = MF(p)->bigHash ? GetHeads3b : GetHeads3;
-      p->MixMatchesFunc = (Mf_Mix_Matches)MixMatches2;
-      vTable->Skip = (Mf_Skip_Func)MatchFinderMt2_Skip;
+      p->MixMatchesFunc = MixMatches2;
+      vTable->Skip = MatchFinderMt2_Skip;
       break;
     case 4:
       p->GetHeadsFunc = MF(p)->bigHash ? GetHeads4b : GetHeads4;
 
       // it's fast inline version of GetMatches()
-      // vTable->GetMatches = (Mf_GetMatches_Func)MatchFinderMt_GetMatches_Bt4;
+      // vTable->GetMatches = MatchFinderMt_GetMatches_Bt4;
 
-      p->MixMatchesFunc = (Mf_Mix_Matches)MixMatches3;
-      vTable->Skip = (Mf_Skip_Func)MatchFinderMt3_Skip;
+      p->MixMatchesFunc = MixMatches3;
+      vTable->Skip = MatchFinderMt3_Skip;
       break;
     default:
       p->GetHeadsFunc = MF(p)->bigHash ? GetHeads5b : GetHeads5;
-      p->MixMatchesFunc = (Mf_Mix_Matches)MixMatches4;
+      p->MixMatchesFunc = MixMatches4;
       vTable->Skip =
-          (Mf_Skip_Func)MatchFinderMt3_Skip;
-          // (Mf_Skip_Func)MatchFinderMt4_Skip;
+          MatchFinderMt3_Skip;
+          // MatchFinderMt4_Skip;
       break;
   }
 }

3rdparty/lzma/src/Lzma2Dec.c

@@ -1,5 +1,5 @@
 /* Lzma2Dec.c -- LZMA2 Decoder
-2023-03-03 : Igor Pavlov : Public domain */
+2024-03-01 : Igor Pavlov : Public domain */
 
 /* #define SHOW_DEBUG_INFO */
 
@@ -157,8 +157,10 @@ static unsigned Lzma2Dec_UpdateState(CLzma2Dec *p, Byte b)
       p->decoder.prop.lp = (Byte)lp;
       return LZMA2_STATE_DATA;
     }
+    
+    default:
+      return LZMA2_STATE_ERROR;
   }
-  return LZMA2_STATE_ERROR;
 }
 
 static void LzmaDec_UpdateWithUncompressed(CLzmaDec *p, const Byte *src, SizeT size)

3rdparty/lzma/src/LzmaEnc.c

@@ -1,5 +1,5 @@
 /* LzmaEnc.c -- LZMA Encoder
-2023-04-13: Igor Pavlov : Public domain */
+2024-01-24: Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
@@ -195,11 +195,11 @@ unsigned GetPosSlot1(UInt32 pos);
 unsigned GetPosSlot1(UInt32 pos)
 {
   unsigned res;
-  BSR2_RET(pos, res);
+  BSR2_RET(pos, res)
   return res;
 }
-#define GetPosSlot2(pos, res) { BSR2_RET(pos, res); }
-#define GetPosSlot(pos, res) { if (pos < 2) res = pos; else BSR2_RET(pos, res); }
+#define GetPosSlot2(pos, res) { BSR2_RET(pos, res) }
+#define GetPosSlot(pos, res) { if (pos < 2) res = pos; else BSR2_RET(pos, res) }
 
 
 #else // ! LZMA_LOG_BSR
@@ -512,7 +512,7 @@ struct CLzmaEnc
   COPY_ARR(d, s, posEncoders)  \
   (d)->lenProbs = (s)->lenProbs;  \
   (d)->repLenProbs = (s)->repLenProbs;  \
-  memcpy((d)->litProbs, (s)->litProbs, ((UInt32)0x300 << (p)->lclp) * sizeof(CLzmaProb));
+  memcpy((d)->litProbs, (s)->litProbs, ((size_t)0x300 * sizeof(CLzmaProb)) << (p)->lclp);
 
 void LzmaEnc_SaveState(CLzmaEncHandle p)
 {
@@ -1040,14 +1040,14 @@ Z7_NO_INLINE static void Z7_FASTCALL LenPriceEnc_UpdateTables(
         UInt32 price = b;
         do
         {
-          unsigned bit = sym & 1;
+          const unsigned bit = sym & 1;
           sym >>= 1;
           price += GET_PRICEa(probs[sym], bit);
         }
         while (sym >= 2);
 
         {
-          unsigned prob = probs[(size_t)i + (1 << (kLenNumHighBits - 1))];
+          const unsigned prob = probs[(size_t)i + (1 << (kLenNumHighBits - 1))];
           prices[(size_t)i * 2    ] = price + GET_PRICEa_0(prob);
           prices[(size_t)i * 2 + 1] = price + GET_PRICEa_1(prob);
         }
@@ -1056,7 +1056,7 @@ Z7_NO_INLINE static void Z7_FASTCALL LenPriceEnc_UpdateTables(
 
       {
         unsigned posState;
-        size_t num = (p->tableSize - kLenNumLowSymbols * 2) * sizeof(p->prices[0][0]);
+        const size_t num = (p->tableSize - kLenNumLowSymbols * 2) * sizeof(p->prices[0][0]);
         for (posState = 1; posState < numPosStates; posState++)
           memcpy(p->prices[posState] + kLenNumLowSymbols * 2, p->prices[0] + kLenNumLowSymbols * 2, num);
       }
@@ -2696,12 +2696,12 @@ static SRes LzmaEnc_Alloc(CLzmaEnc *p, UInt32 keepWindowSize, ISzAllocPtr alloc,
   #endif
 
   {
-    unsigned lclp = p->lc + p->lp;
+    const unsigned lclp = p->lc + p->lp;
     if (!p->litProbs || !p->saveState.litProbs || p->lclp != lclp)
     {
       LzmaEnc_FreeLits(p, alloc);
-      p->litProbs = (CLzmaProb *)ISzAlloc_Alloc(alloc, ((UInt32)0x300 << lclp) * sizeof(CLzmaProb));
-      p->saveState.litProbs = (CLzmaProb *)ISzAlloc_Alloc(alloc, ((UInt32)0x300 << lclp) * sizeof(CLzmaProb));
+      p->litProbs =           (CLzmaProb *)ISzAlloc_Alloc(alloc, ((size_t)0x300 * sizeof(CLzmaProb)) << lclp);
+      p->saveState.litProbs = (CLzmaProb *)ISzAlloc_Alloc(alloc, ((size_t)0x300 * sizeof(CLzmaProb)) << lclp);
       if (!p->litProbs || !p->saveState.litProbs)
       {
         LzmaEnc_FreeLits(p, alloc);
@@ -2802,8 +2802,8 @@ static void LzmaEnc_Init(CLzmaEnc *p)
   }
 
   {
-    UInt32 num = (UInt32)0x300 << (p->lp + p->lc);
-    UInt32 k;
+    const size_t num = (size_t)0x300 << (p->lp + p->lc);
+    size_t k;
     CLzmaProb *probs = p->litProbs;
     for (k = 0; k < num; k++)
       probs[k] = kProbInitValue;

3rdparty/lzma/src/MtCoder.c

@@ -1,5 +1,5 @@
 /* MtCoder.c -- Multi-thread Coder
-2023-04-13 : Igor Pavlov : Public domain */
+2023-09-07 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
@@ -430,7 +430,7 @@ SRes MtCoder_Code(CMtCoder *p)
   SRes res = SZ_OK;
 
   if (numThreads > MTCODER_THREADS_MAX)
-    numThreads = MTCODER_THREADS_MAX;
+      numThreads = MTCODER_THREADS_MAX;
   numBlocksMax = MTCODER_GET_NUM_BLOCKS_FROM_THREADS(numThreads);
   
   if (p->blockSize < ((UInt32)1 << 26)) numBlocksMax++;
@@ -438,7 +438,7 @@ SRes MtCoder_Code(CMtCoder *p)
   if (p->blockSize < ((UInt32)1 << 22)) numBlocksMax++;
 
   if (numBlocksMax > MTCODER_BLOCKS_MAX)
-    numBlocksMax = MTCODER_BLOCKS_MAX;
+      numBlocksMax = MTCODER_BLOCKS_MAX;
 
   if (p->blockSize != p->allocatedBufsSize)
   {
@@ -469,7 +469,7 @@ SRes MtCoder_Code(CMtCoder *p)
 
   {
     RINOK_THREAD(AutoResetEvent_OptCreate_And_Reset(&p->readEvent))
-    RINOK_THREAD(Semaphore_OptCreateInit(&p->blocksSemaphore, numBlocksMax, numBlocksMax))
+    RINOK_THREAD(Semaphore_OptCreateInit(&p->blocksSemaphore, (UInt32)numBlocksMax, (UInt32)numBlocksMax))
   }
 
   for (i = 0; i < MTCODER_BLOCKS_MAX - 1; i++)

3rdparty/lzma/src/MtDec.c

@@ -1,5 +1,5 @@
 /* MtDec.c -- Multi-thread Decoder
-2023-04-02 : Igor Pavlov : Public domain */
+2024-02-20 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
@@ -809,6 +809,16 @@ static WRes MtDec_ThreadFunc2(CMtDecThread *t)
 #endif
 
 
+typedef
+  #ifdef _WIN32
+    UINT_PTR
+  #elif 1
+    uintptr_t
+  #else
+    ptrdiff_t
+  #endif
+    MY_uintptr_t;
+
 static THREAD_FUNC_DECL MtDec_ThreadFunc1(void *pp)
 {
   WRes res;
@@ -821,7 +831,7 @@ static THREAD_FUNC_DECL MtDec_ThreadFunc1(void *pp)
   res = MtDec_ThreadFunc2(t);
   p = t->mtDec;
   if (res == 0)
-    return (THREAD_FUNC_RET_TYPE)(UINT_PTR)p->exitThreadWRes;
+    return (THREAD_FUNC_RET_TYPE)(MY_uintptr_t)p->exitThreadWRes;
   {
     // it's unexpected situation for some threading function error
     if (p->exitThreadWRes == 0)
@@ -832,7 +842,7 @@ static THREAD_FUNC_DECL MtDec_ThreadFunc1(void *pp)
     Event_Set(&p->threads[0].canWrite);
     MtProgress_SetError(&p->mtProgress, MY_SRes_HRESULT_FROM_WRes(res));
   }
-  return (THREAD_FUNC_RET_TYPE)(UINT_PTR)res;
+  return (THREAD_FUNC_RET_TYPE)(MY_uintptr_t)res;
 }
 
 static Z7_NO_INLINE THREAD_FUNC_DECL MtDec_ThreadFunc(void *pp)
@@ -1072,7 +1082,7 @@ SRes MtDec_Code(CMtDec *p)
     if (wres == 0) { wres = Event_Set(&nextThread->canWrite);
     if (wres == 0) { wres = Event_Set(&nextThread->canRead);
     if (wres == 0) { THREAD_FUNC_RET_TYPE res = MtDec_ThreadFunc(nextThread);
-    wres = (WRes)(UINT_PTR)res;
+    wres = (WRes)(MY_uintptr_t)res;
     if (wres != 0)
     {
       p->needContinue = False;

3rdparty/lzma/src/Ppmd7.c

@@ -1,5 +1,5 @@
 /* Ppmd7.c -- PPMdH codec
-2023-04-02 : Igor Pavlov : Public domain
+2023-09-07 : Igor Pavlov : Public domain
 This code is based on PPMd var.H (2001): Dmitry Shkarin : Public domain */
 
 #include "Precomp.h"
@@ -302,8 +302,17 @@ static void *Ppmd7_AllocUnits(CPpmd7 *p, unsigned indx)
 
 
 #define MEM_12_CPY(dest, src, num) \
-  { UInt32 *d = (UInt32 *)dest; const UInt32 *z = (const UInt32 *)src; UInt32 n = num; \
-    do { d[0] = z[0]; d[1] = z[1]; d[2] = z[2]; z += 3; d += 3; } while (--n); }
+  { UInt32 *d = (UInt32 *)(dest); \
+    const UInt32 *z = (const UInt32 *)(src); \
+    unsigned n = (num); \
+    do { \
+      d[0] = z[0]; \
+      d[1] = z[1]; \
+      d[2] = z[2]; \
+      z += 3; \
+      d += 3; \
+    } while (--n); \
+  }
 
 
 /*
@@ -711,8 +720,8 @@ void Ppmd7_UpdateModel(CPpmd7 *p)
       if ((ns1 & 1) == 0)
       {
         /* Expand for one UNIT */
-        unsigned oldNU = ns1 >> 1;
-        unsigned i = U2I(oldNU);
+        const unsigned oldNU = ns1 >> 1;
+        const unsigned i = U2I(oldNU);
         if (i != U2I((size_t)oldNU + 1))
         {
           void *ptr = Ppmd7_AllocUnits(p, i + 1);
@@ -731,7 +740,7 @@ void Ppmd7_UpdateModel(CPpmd7 *p)
       sum = c->Union2.SummFreq;
       /* max increase of Escape_Freq is 3 here.
          total increase of Union2.SummFreq for all symbols is less than 256 here */
-      sum += (UInt32)(2 * ns1 < ns) + 2 * ((unsigned)(4 * ns1 <= ns) & (sum <= 8 * ns1));
+      sum += (UInt32)(unsigned)((2 * ns1 < ns) + 2 * ((unsigned)(4 * ns1 <= ns) & (sum <= 8 * ns1)));
       /* original PPMdH uses 16-bit variable for (sum) here.
          But (sum < 0x9000). So we don't truncate (sum) to 16-bit */
       // sum = (UInt16)sum;
@@ -761,7 +770,7 @@ void Ppmd7_UpdateModel(CPpmd7 *p)
         // (max(s->freq) == 120), when we convert from 1-symbol into 2-symbol context
         s->Freq = (Byte)freq;
         // max(InitEsc = PPMD7_kExpEscape[*]) is 25. So the max(escapeFreq) is 26 here
-        sum = freq + p->InitEsc + (ns > 3);
+        sum = (UInt32)(freq + p->InitEsc + (ns > 3));
       }
     }
     
@@ -933,10 +942,10 @@ CPpmd_See *Ppmd7_MakeEscFreq(CPpmd7 *p, unsigned numMasked, UInt32 *escFreq)
         p->HiBitsFlag;
     {
       // if (see->Summ) field is larger than 16-bit, we need only low 16 bits of Summ
-      unsigned summ = (UInt16)see->Summ; // & 0xFFFF
-      unsigned r = (summ >> see->Shift);
+      const unsigned summ = (UInt16)see->Summ; // & 0xFFFF
+      const unsigned r = (summ >> see->Shift);
       see->Summ = (UInt16)(summ - r);
-      *escFreq = r + (r == 0);
+      *escFreq = (UInt32)(r + (r == 0));
     }
   }
   else
@@ -981,9 +990,9 @@ void Ppmd7_Update1_0(CPpmd7 *p)
   CPpmd_State *s = p->FoundState;
   CPpmd7_Context *mc = p->MinContext;
   unsigned freq = s->Freq;
-  unsigned summFreq = mc->Union2.SummFreq;
+  const unsigned summFreq = mc->Union2.SummFreq;
   p->PrevSuccess = (2 * freq > summFreq);
-  p->RunLength += (int)p->PrevSuccess;
+  p->RunLength += (Int32)p->PrevSuccess;
   mc->Union2.SummFreq = (UInt16)(summFreq + 4);
   freq += 4;
   s->Freq = (Byte)freq;

3rdparty/lzma/src/Ppmd7Dec.c

@@ -1,5 +1,5 @@
 /* Ppmd7Dec.c -- Ppmd7z (PPMdH with 7z Range Coder) Decoder
-2023-04-02 : Igor Pavlov : Public domain
+2023-09-07 : Igor Pavlov : Public domain
 This code is based on:
   PPMd var.H (2001): Dmitry Shkarin : Public domain */
 
@@ -58,7 +58,7 @@ static void Ppmd7z_RD_Decode(CPpmd7 *p, UInt32 start, UInt32 size)
 #define SUCCESSOR(p) Ppmd_GET_SUCCESSOR(p)
 void Ppmd7_UpdateModel(CPpmd7 *p);
 
-#define MASK(sym) ((unsigned char *)charMask)[sym]
+#define MASK(sym)  ((Byte *)charMask)[sym]
 // Z7_FORCE_INLINE
 // static
 int Ppmd7z_DecodeSymbol(CPpmd7 *p)
@@ -120,8 +120,8 @@ int Ppmd7z_DecodeSymbol(CPpmd7 *p)
       MASK(s->Symbol) = 0;
       do
       {
-        unsigned sym0 = s2[0].Symbol;
-        unsigned sym1 = s2[1].Symbol;
+        const unsigned sym0 = s2[0].Symbol;
+        const unsigned sym1 = s2[1].Symbol;
         s2 += 2;
         MASK(sym0) = 0;
         MASK(sym1) = 0;
@@ -209,17 +209,17 @@ int Ppmd7z_DecodeSymbol(CPpmd7 *p)
       unsigned num2 = num / 2;
       
       num &= 1;
-      hiCnt = (s->Freq & (unsigned)(MASK(s->Symbol))) & (0 - (UInt32)num);
+      hiCnt = (s->Freq & (UInt32)(MASK(s->Symbol))) & (0 - (UInt32)num);
       s += num;
       p->MinContext = mc;
 
       do
       {
-        unsigned sym0 = s[0].Symbol;
-        unsigned sym1 = s[1].Symbol;
+        const unsigned sym0 = s[0].Symbol;
+        const unsigned sym1 = s[1].Symbol;
         s += 2;
-        hiCnt += (s[-2].Freq & (unsigned)(MASK(sym0)));
-        hiCnt += (s[-1].Freq & (unsigned)(MASK(sym1)));
+        hiCnt += (s[-2].Freq & (UInt32)(MASK(sym0)));
+        hiCnt += (s[-1].Freq & (UInt32)(MASK(sym1)));
       }
       while (--num2);
     }
@@ -238,13 +238,13 @@ int Ppmd7z_DecodeSymbol(CPpmd7 *p)
 
       s = Ppmd7_GetStats(p, p->MinContext);
       hiCnt = count;
-      // count -= s->Freq & (unsigned)(MASK(s->Symbol));
+      // count -= s->Freq & (UInt32)(MASK(s->Symbol));
       // if ((Int32)count >= 0)
       {
         for (;;)
         {
-          count -= s->Freq & (unsigned)(MASK((s)->Symbol)); s++; if ((Int32)count < 0) break;
-          // count -= s->Freq & (unsigned)(MASK((s)->Symbol)); s++; if ((Int32)count < 0) break;
+          count -= s->Freq & (UInt32)(MASK((s)->Symbol)); s++; if ((Int32)count < 0) break;
+          // count -= s->Freq & (UInt32)(MASK((s)->Symbol)); s++; if ((Int32)count < 0) break;
         }
       }
       s--;

3rdparty/lzma/src/Ppmd7Enc.c

@@ -1,5 +1,5 @@
 /* Ppmd7Enc.c -- Ppmd7z (PPMdH with 7z Range Coder) Encoder
-2023-04-02 : Igor Pavlov : Public domain
+2023-09-07 : Igor Pavlov : Public domain
 This code is based on:
   PPMd var.H (2001): Dmitry Shkarin : Public domain */
 
@@ -82,7 +82,7 @@ void Ppmd7z_Flush_RangeEnc(CPpmd7 *p)
 
 void Ppmd7_UpdateModel(CPpmd7 *p);
 
-#define MASK(sym) ((unsigned char *)charMask)[sym]
+#define MASK(sym)  ((Byte *)charMask)[sym]
 
 Z7_FORCE_INLINE
 static
@@ -139,8 +139,8 @@ void Ppmd7z_EncodeSymbol(CPpmd7 *p, int symbol)
       MASK(s->Symbol) = 0;
       do
       {
-        unsigned sym0 = s2[0].Symbol;
-        unsigned sym1 = s2[1].Symbol;
+        const unsigned sym0 = s2[0].Symbol;
+        const unsigned sym1 = s2[1].Symbol;
         s2 += 2;
         MASK(sym0) = 0;
         MASK(sym1) = 0;
@@ -265,16 +265,15 @@ void Ppmd7z_EncodeSymbol(CPpmd7 *p, int symbol)
         if (num2 != 0)
         {
           s += i;
-          for (;;)
+          do
           {
-            unsigned sym0 = s[0].Symbol;
-            unsigned sym1 = s[1].Symbol;
+            const unsigned sym0 = s[0].Symbol;
+            const unsigned sym1 = s[1].Symbol;
             s += 2;
             sum += (s[-2].Freq & (unsigned)(MASK(sym0)));
             sum += (s[-1].Freq & (unsigned)(MASK(sym1)));
-            if (--num2 == 0)
-              break;
           }
+          while (--num2);
         }
 
         

3rdparty/lzma/src/Sha256.c

@@ -1,5 +1,5 @@
 /* Sha256.c -- SHA-256 Hash
-2023-04-02 : Igor Pavlov : Public domain
+2024-03-01 : Igor Pavlov : Public domain
 This code is based on public domain code from Wei Dai's Crypto++ library. */
 
 #include "Precomp.h"
@@ -15,35 +15,35 @@ This code is based on public domain code from Wei Dai's Crypto++ library. */
 #endif
 
 #ifdef MY_CPU_X86_OR_AMD64
-  #ifdef _MSC_VER
-    #if _MSC_VER >= 1200
+  #if   defined(Z7_LLVM_CLANG_VERSION)  && (Z7_LLVM_CLANG_VERSION  >= 30800) \
+     || defined(Z7_APPLE_CLANG_VERSION) && (Z7_APPLE_CLANG_VERSION >= 50100) \
+     || defined(Z7_GCC_VERSION)         && (Z7_GCC_VERSION         >= 40900) \
+     || defined(__INTEL_COMPILER) && (__INTEL_COMPILER >= 1600) \
+     || defined(_MSC_VER) && (_MSC_VER >= 1200)
       #define Z7_COMPILER_SHA256_SUPPORTED
-    #endif
-  #elif defined(__clang__)
-    #if (__clang_major__ >= 8) // fix that check
-      #define Z7_COMPILER_SHA256_SUPPORTED
-    #endif
-  #elif defined(__GNUC__)
-    #if (__GNUC__ >= 8) // fix that check
-      #define Z7_COMPILER_SHA256_SUPPORTED
-    #endif
-  #elif defined(__INTEL_COMPILER)
-    #if (__INTEL_COMPILER >= 1800) // fix that check
-      #define Z7_COMPILER_SHA256_SUPPORTED
-    #endif
   #endif
-#elif defined(MY_CPU_ARM_OR_ARM64)
-  #ifdef _MSC_VER
-    #if _MSC_VER >= 1910
+#elif defined(MY_CPU_ARM_OR_ARM64) && defined(MY_CPU_LE)
+
+  #if   defined(__ARM_FEATURE_SHA2) \
+     || defined(__ARM_FEATURE_CRYPTO)
+    #define Z7_COMPILER_SHA256_SUPPORTED
+  #else
+    #if  defined(MY_CPU_ARM64) \
+      || defined(__ARM_ARCH) && (__ARM_ARCH >= 4) \
+      || defined(Z7_MSC_VER_ORIGINAL)
+    #if  defined(__ARM_FP) && \
+          (   defined(Z7_CLANG_VERSION) && (Z7_CLANG_VERSION >= 30800) \
+           || defined(__GNUC__) && (__GNUC__ >= 6) \
+          ) \
+      || defined(Z7_MSC_VER_ORIGINAL) && (_MSC_VER >= 1910)
+    #if  defined(MY_CPU_ARM64) \
+      || !defined(Z7_CLANG_VERSION) \
+      || defined(__ARM_NEON) && \
+          (Z7_CLANG_VERSION < 170000 || \
+           Z7_CLANG_VERSION > 170001)
       #define Z7_COMPILER_SHA256_SUPPORTED
     #endif
-  #elif defined(__clang__)
-    #if (__clang_major__ >= 8) // fix that check
-      #define Z7_COMPILER_SHA256_SUPPORTED
     #endif
-  #elif defined(__GNUC__)
-    #if (__GNUC__ >= 6) // fix that check
-      #define Z7_COMPILER_SHA256_SUPPORTED
     #endif
   #endif
 #endif
@@ -224,8 +224,6 @@ void Sha256_Init(CSha256 *p)
 
 #endif
 
-void Z7_FASTCALL Sha256_UpdateBlocks_HW(UInt32 state[8], const Byte *data, size_t numBlocks);
-
 // static
 extern MY_ALIGN(64)
 const UInt32 SHA256_K_ARRAY[64];

3rdparty/lzma/src/Sha256Opt.c

@@ -1,5 +1,5 @@
 /* Sha256Opt.c -- SHA-256 optimized code for SHA-256 hardware instructions
-2023-04-02 : Igor Pavlov : Public domain */
+2024-03-01 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 #include "Compiler.h"
@@ -11,6 +11,8 @@
 #endif
 #endif
 
+// #define Z7_USE_HW_SHA_STUB // for debug
+
 #ifdef MY_CPU_X86_OR_AMD64
   #if defined(__INTEL_COMPILER) && (__INTEL_COMPILER >= 1600) // fix that check
       #define USE_HW_SHA
@@ -32,9 +34,14 @@
     #endif
     #if (_MSC_VER >= USE_VER_MIN)
       #define USE_HW_SHA
+    #else
+      #define Z7_USE_HW_SHA_STUB
     #endif
   #endif
 // #endif // MY_CPU_X86_OR_AMD64
+#ifndef USE_HW_SHA
+  // #define Z7_USE_HW_SHA_STUB // for debug
+#endif
 
 #ifdef USE_HW_SHA
 
@@ -202,19 +209,28 @@ void Z7_FASTCALL Sha256_UpdateBlocks_HW(UInt32 state[8], const Byte *data, size_
 
 #endif // USE_HW_SHA
 
-#elif defined(MY_CPU_ARM_OR_ARM64)
-
-  #if defined(__clang__)
-    #if (__clang_major__ >= 8) // fix that check
+#elif defined(MY_CPU_ARM_OR_ARM64) && defined(MY_CPU_LE)
+  
+  #if   defined(__ARM_FEATURE_SHA2) \
+     || defined(__ARM_FEATURE_CRYPTO)
+    #define USE_HW_SHA
+  #else
+    #if  defined(MY_CPU_ARM64) \
+      || defined(__ARM_ARCH) && (__ARM_ARCH >= 4) \
+      || defined(Z7_MSC_VER_ORIGINAL)
+    #if  defined(__ARM_FP) && \
+          (   defined(Z7_CLANG_VERSION) && (Z7_CLANG_VERSION >= 30800) \
+           || defined(__GNUC__) && (__GNUC__ >= 6) \
+          ) \
+      || defined(Z7_MSC_VER_ORIGINAL) && (_MSC_VER >= 1910)
+    #if  defined(MY_CPU_ARM64) \
+      || !defined(Z7_CLANG_VERSION) \
+      || defined(__ARM_NEON) && \
+          (Z7_CLANG_VERSION < 170000 || \
+           Z7_CLANG_VERSION > 170001)
       #define USE_HW_SHA
     #endif
-  #elif defined(__GNUC__)
-    #if (__GNUC__ >= 6) // fix that check
-      #define USE_HW_SHA
     #endif
-  #elif defined(_MSC_VER)
-    #if _MSC_VER >= 1910
-      #define USE_HW_SHA
     #endif
   #endif
 
@@ -222,23 +238,87 @@ void Z7_FASTCALL Sha256_UpdateBlocks_HW(UInt32 state[8], const Byte *data, size_
 
 // #pragma message("=== Sha256 HW === ")
 
+
 #if defined(__clang__) || defined(__GNUC__)
+#if !defined(__ARM_FEATURE_SHA2) && \
+    !defined(__ARM_FEATURE_CRYPTO)
   #ifdef MY_CPU_ARM64
-    #define ATTRIB_SHA __attribute__((__target__("+crypto,sha2")))
+#if defined(__clang__)
+    #define ATTRIB_SHA __attribute__((__target__("crypto")))
+#else
+    #define ATTRIB_SHA __attribute__((__target__("+crypto")))
+#endif
   #else
+#if defined(__clang__) && (__clang_major__ >= 1)
+    #define ATTRIB_SHA __attribute__((__target__("armv8-a,sha2")))
+#else
     #define ATTRIB_SHA __attribute__((__target__("fpu=crypto-neon-fp-armv8")))
+#endif
   #endif
+#endif
 #else
   // _MSC_VER
   // for arm32
   #define _ARM_USE_NEW_NEON_INTRINSICS
 #endif
 
-#if defined(_MSC_VER) && !defined(__clang__) && defined(MY_CPU_ARM64)
+
+
+
+
+#if defined(Z7_MSC_VER_ORIGINAL) && defined(MY_CPU_ARM64)
 #include <arm64_neon.h>
 #else
-#include <arm_neon.h>
+
+
+
+
+
+
+
+
+
+#if defined(__clang__) && __clang_major__ < 16
+#if !defined(__ARM_FEATURE_SHA2) && \
+    !defined(__ARM_FEATURE_CRYPTO)
+//     #pragma message("=== we set __ARM_FEATURE_CRYPTO 1 === ")
+    Z7_DIAGNOSTIC_IGNORE_BEGIN_RESERVED_MACRO_IDENTIFIER
+    #define Z7_ARM_FEATURE_CRYPTO_WAS_SET 1
+// #if defined(__clang__) && __clang_major__ < 13
+    #define __ARM_FEATURE_CRYPTO 1
+// #else
+    #define __ARM_FEATURE_SHA2 1
+// #endif
+    Z7_DIAGNOSTIC_IGNORE_END_RESERVED_MACRO_IDENTIFIER
 #endif
+#endif // clang
+
+#if defined(__clang__)
+
+#if defined(__ARM_ARCH) && __ARM_ARCH < 8
+    Z7_DIAGNOSTIC_IGNORE_BEGIN_RESERVED_MACRO_IDENTIFIER
+//    #pragma message("#define __ARM_ARCH 8")
+    #undef  __ARM_ARCH
+    #define __ARM_ARCH 8
+    Z7_DIAGNOSTIC_IGNORE_END_RESERVED_MACRO_IDENTIFIER
+#endif
+
+#endif // clang
+
+#include <arm_neon.h>
+
+#if defined(Z7_ARM_FEATURE_CRYPTO_WAS_SET) && \
+    defined(__ARM_FEATURE_CRYPTO) && \
+    defined(__ARM_FEATURE_SHA2)
+Z7_DIAGNOSTIC_IGNORE_BEGIN_RESERVED_MACRO_IDENTIFIER
+    #undef __ARM_FEATURE_CRYPTO
+    #undef __ARM_FEATURE_SHA2
+    #undef Z7_ARM_FEATURE_CRYPTO_WAS_SET
+Z7_DIAGNOSTIC_IGNORE_END_RESERVED_MACRO_IDENTIFIER
+//    #pragma message("=== we undefine __ARM_FEATURE_CRYPTO === ")
+#endif
+
+#endif // Z7_MSC_VER_ORIGINAL
 
 typedef uint32x4_t v128;
 // typedef __n128 v128; // MSVC
@@ -316,10 +396,10 @@ void Z7_FASTCALL Sha256_UpdateBlocks_HW(UInt32 state[8], const Byte *data, size_
     LOAD_SHUFFLE (m2, 2)
     LOAD_SHUFFLE (m3, 3)
 
-    R16 ( 0, NNN, NNN, SM1, NNN, SM1, SM2, SM1, SM2 );
-    R16 ( 1, SM1, SM2, SM1, SM2, SM1, SM2, SM1, SM2 );
-    R16 ( 2, SM1, SM2, SM1, SM2, SM1, SM2, SM1, SM2 );
-    R16 ( 3, SM1, SM2, NNN, SM2, NNN, NNN, NNN, NNN );
+    R16 ( 0, NNN, NNN, SM1, NNN, SM1, SM2, SM1, SM2 )
+    R16 ( 1, SM1, SM2, SM1, SM2, SM1, SM2, SM1, SM2 )
+    R16 ( 2, SM1, SM2, SM1, SM2, SM1, SM2, SM1, SM2 )
+    R16 ( 3, SM1, SM2, NNN, SM2, NNN, NNN, NNN, NNN )
     
     state0 = vaddq_u32(state0, state0_save);
     state1 = vaddq_u32(state1, state1_save);
@@ -337,16 +417,17 @@ void Z7_FASTCALL Sha256_UpdateBlocks_HW(UInt32 state[8], const Byte *data, size_
 #endif // MY_CPU_ARM_OR_ARM64
 
 
-#ifndef USE_HW_SHA
-
+#if !defined(USE_HW_SHA) && defined(Z7_USE_HW_SHA_STUB)
 // #error Stop_Compiling_UNSUPPORTED_SHA
 // #include <stdlib.h>
-
+// We can compile this file with another C compiler,
+// or we can compile asm version.
+// So we can generate real code instead of this stub function.
 // #include "Sha256.h"
-void Z7_FASTCALL Sha256_UpdateBlocks(UInt32 state[8], const Byte *data, size_t numBlocks);
-
+// #if defined(_MSC_VER)
 #pragma message("Sha256 HW-SW stub was used")
-
+// #endif
+void Z7_FASTCALL Sha256_UpdateBlocks   (UInt32 state[8], const Byte *data, size_t numBlocks);
 void Z7_FASTCALL Sha256_UpdateBlocks_HW(UInt32 state[8], const Byte *data, size_t numBlocks);
 void Z7_FASTCALL Sha256_UpdateBlocks_HW(UInt32 state[8], const Byte *data, size_t numBlocks)
 {
@@ -359,7 +440,6 @@ void Z7_FASTCALL Sha256_UpdateBlocks_HW(UInt32 state[8], const Byte *data, size_
   return;
   */
 }
-
 #endif
 
 
@@ -384,3 +464,4 @@ void Z7_FASTCALL Sha256_UpdateBlocks_HW(UInt32 state[8], const Byte *data, size_
 #undef USE_HW_SHA
 #undef ATTRIB_SHA
 #undef USE_VER_MIN
+#undef Z7_USE_HW_SHA_STUB

3rdparty/lzma/src/SwapBytes.c

@@ -1,5 +1,5 @@
 /* SwapBytes.c -- Byte Swap conversion filter
-2023-04-07 : Igor Pavlov : Public domain */
+2024-03-01 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
@@ -305,11 +305,12 @@ ShufBytes_256(void *items8, const void *lim8, const void *mask128_ptr)
      msvc 19.30+ (VS2022): replaces _mm256_set_m128i(m,m) to vbroadcastf128(m) as we want
   */
   // _mm256_broadcastsi128_si256(*mask128_ptr);
-  /*
+#if defined(Z7_GCC_VERSION) && (Z7_GCC_VERSION < 80000)
   #define MY_mm256_set_m128i(hi, lo)  _mm256_insertf128_si256(_mm256_castsi128_si256(lo), (hi), 1)
-  MY_mm256_set_m128i
-  */
-      _mm256_set_m128i(
+#else
+  #define MY_mm256_set_m128i  _mm256_set_m128i
+#endif
+      MY_mm256_set_m128i(
         *(const __m128i *)mask128_ptr,
         *(const __m128i *)mask128_ptr);
  #endif
@@ -330,32 +331,59 @@ ShufBytes_256(void *items8, const void *lim8, const void *mask128_ptr)
 
 
 // compile message "NEON intrinsics not available with the soft-float ABI"
-#elif defined(MY_CPU_ARM_OR_ARM64) || \
-    (defined(__ARM_ARCH) && (__ARM_ARCH >= 7))
-// #elif defined(MY_CPU_ARM64)
+#elif defined(MY_CPU_ARM_OR_ARM64) \
+    && defined(MY_CPU_LE) \
+    && !defined(Z7_DISABLE_ARM_NEON)
 
   #if defined(__clang__) && (__clang_major__ >= 8) \
-    || defined(__GNUC__) && (__GNUC__ >= 8)
-    #if (defined(__ARM_ARCH) && (__ARM_ARCH >= 7)) \
+    || defined(__GNUC__) && (__GNUC__ >= 6)
+    #if defined(__ARM_FP)
+    #if (defined(__ARM_ARCH) && (__ARM_ARCH >= 4)) \
         || defined(MY_CPU_ARM64)
+    #if  defined(MY_CPU_ARM64) \
+      || !defined(Z7_CLANG_VERSION) \
+      || defined(__ARM_NEON)
       #define USE_SWAP_128
-    #endif
     #ifdef MY_CPU_ARM64
       // #define SWAP_ATTRIB_NEON __attribute__((__target__("")))
     #else
-      // #define SWAP_ATTRIB_NEON __attribute__((__target__("fpu=crypto-neon-fp-armv8")))
-    #endif
+#if defined(Z7_CLANG_VERSION)
+      // #define SWAP_ATTRIB_NEON __attribute__((__target__("neon")))
+#else
+      // #pragma message("SWAP_ATTRIB_NEON __attribute__((__target__(fpu=neon))")
+      #define SWAP_ATTRIB_NEON __attribute__((__target__("fpu=neon")))
+#endif
+    #endif // MY_CPU_ARM64
+    #endif // __ARM_NEON
+    #endif // __ARM_ARCH
+    #endif // __ARM_FP
+
   #elif defined(_MSC_VER)
     #if (_MSC_VER >= 1910)
       #define USE_SWAP_128
     #endif
   #endif
 
-  #if defined(_MSC_VER) && defined(MY_CPU_ARM64)
+  #ifdef USE_SWAP_128
+  #if defined(Z7_MSC_VER_ORIGINAL) && defined(MY_CPU_ARM64)
     #include <arm64_neon.h>
   #else
+
+/*
+#if !defined(__ARM_NEON)
+#if defined(Z7_GCC_VERSION) && (__GNUC__  <   5) \
+ || defined(Z7_GCC_VERSION) && (__GNUC__ ==   5) && (Z7_GCC_VERSION <  90201) \
+ || defined(Z7_GCC_VERSION) && (__GNUC__ ==   5) && (Z7_GCC_VERSION < 100100)
+Z7_DIAGNOSTIC_IGNORE_BEGIN_RESERVED_MACRO_IDENTIFIER
+#pragma message("#define __ARM_NEON 1")
+// #define __ARM_NEON 1
+Z7_DIAGNOSTIC_IGNORE_END_RESERVED_MACRO_IDENTIFIER
+#endif
+#endif
+*/
     #include <arm_neon.h>
   #endif
+  #endif
 
 #ifndef USE_SWAP_128
   #define FORCE_SWAP_MODE
@@ -464,6 +492,13 @@ Z7_ATTRIB_NO_VECTOR  \
 void Z7_FASTCALL
 
 
+#if defined(MY_CPU_ARM_OR_ARM64)
+#if defined(__clang__)
+#pragma GCC diagnostic ignored "-Wlanguage-extension-token"
+#endif
+#endif
+
+
 #ifdef MY_CPU_64BIT
 
 #if defined(MY_CPU_ARM64) \

3rdparty/lzma/src/Threads.c

@@ -1,5 +1,5 @@
 /* Threads.c -- multithreading library
-2023-03-04 : Igor Pavlov : Public domain */
+2024-03-28 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
@@ -195,20 +195,19 @@ WRes CriticalSection_Init(CCriticalSection *p)
 
 // ---------- POSIX ----------
 
-#ifndef __APPLE__
+#if defined(__linux__) && !defined(__APPLE__) && !defined(_AIX) && !defined(__ANDROID__)
 #ifndef Z7_AFFINITY_DISABLE
 // _GNU_SOURCE can be required for pthread_setaffinity_np() / CPU_ZERO / CPU_SET
 // clang < 3.6       : unknown warning group '-Wreserved-id-macro'
 // clang 3.6 - 12.01 : gives warning "macro name is a reserved identifier"
 // clang >= 13       : do not give warning
 #if !defined(_GNU_SOURCE)
-  #if defined(__clang__) && (__clang_major__ >= 4) && (__clang_major__ <= 12)
-    #pragma GCC diagnostic ignored "-Wreserved-id-macro"
-  #endif
-#define _GNU_SOURCE
+Z7_DIAGNOSTIC_IGNORE_BEGIN_RESERVED_MACRO_IDENTIFIER
+// #define _GNU_SOURCE
+Z7_DIAGNOSTIC_IGNORE_END_RESERVED_MACRO_IDENTIFIER
 #endif // !defined(_GNU_SOURCE)
 #endif // Z7_AFFINITY_DISABLE
-#endif // __APPLE__
+#endif // __linux__
 
 #include "Threads.h"
 
@@ -244,8 +243,9 @@ WRes Thread_Create_With_CpuSet(CThread *p, THREAD_FUNC_TYPE func, LPVOID param,
   {
     if (cpuSet)
     {
-      #ifdef Z7_AFFINITY_SUPPORTED
-      
+      // pthread_attr_setaffinity_np() is not supported for MUSL compile.
+      // so we check for __GLIBC__ here
+#if defined(Z7_AFFINITY_SUPPORTED) && defined( __GLIBC__)
       /*
       printf("\n affinity :");
       unsigned i;
@@ -267,7 +267,7 @@ WRes Thread_Create_With_CpuSet(CThread *p, THREAD_FUNC_TYPE func, LPVOID param,
       // ret2 =
       pthread_attr_setaffinity_np(&attr, sizeof(*cpuSet), cpuSet);
       // if (ret2) ret = ret2;
-      #endif
+#endif
     }
     
     ret = pthread_create(&p->_tid, &attr, func, param);
@@ -369,13 +369,20 @@ WRes AutoResetEvent_CreateNotSignaled(CAutoResetEvent *p)
   { return AutoResetEvent_Create(p, 0); }
 
 
+#if defined(Z7_LLVM_CLANG_VERSION) && (__clang_major__ == 13)
+// freebsd:
+#pragma GCC diagnostic ignored "-Wthread-safety-analysis"
+#endif
+
 WRes Event_Set(CEvent *p)
 {
   RINOK(pthread_mutex_lock(&p->_mutex))
   p->_state = True;
-  int res1 = pthread_cond_broadcast(&p->_cond);
-  int res2 = pthread_mutex_unlock(&p->_mutex);
-  return (res2 ? res2 : res1);
+  {
+    const int res1 = pthread_cond_broadcast(&p->_cond);
+    const int res2 = pthread_mutex_unlock(&p->_mutex);
+    return (res2 ? res2 : res1);
+  }
 }
 
 WRes Event_Reset(CEvent *p)
@@ -408,8 +415,8 @@ WRes Event_Close(CEvent *p)
     return 0;
   p->_created = 0;
   {
-    int res1 = pthread_mutex_destroy(&p->_mutex);
-    int res2 = pthread_cond_destroy(&p->_cond);
+    const int res1 = pthread_mutex_destroy(&p->_mutex);
+    const int res2 = pthread_cond_destroy(&p->_cond);
     return (res1 ? res1 : res2);
   }
 }
@@ -487,8 +494,8 @@ WRes Semaphore_Close(CSemaphore *p)
     return 0;
   p->_created = 0;
   {
-    int res1 = pthread_mutex_destroy(&p->_mutex);
-    int res2 = pthread_cond_destroy(&p->_cond);
+    const int res1 = pthread_mutex_destroy(&p->_mutex);
+    const int res2 = pthread_cond_destroy(&p->_cond);
     return (res1 ? res1 : res2);
   }
 }
@@ -549,6 +556,18 @@ LONG InterlockedIncrement(LONG volatile *addend)
   #endif
 }
 
+LONG InterlockedDecrement(LONG volatile *addend)
+{
+  // Print("InterlockedDecrement")
+  #ifdef USE_HACK_UNSAFE_ATOMIC
+    LONG val = *addend - 1;
+    *addend = val;
+    return val;
+  #else
+    return __sync_sub_and_fetch(addend, 1);
+  #endif
+}
+
 #endif // _WIN32
 
 WRes AutoResetEvent_OptCreate_And_Reset(CAutoResetEvent *p)

3rdparty/lzma/src/Xz.c

@@ -1,5 +1,5 @@
 /* Xz.c - Xz
-2023-04-02 : Igor Pavlov : Public domain */
+2024-03-01 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
@@ -52,6 +52,7 @@ void XzCheck_Init(CXzCheck *p, unsigned mode)
     case XZ_CHECK_CRC32: p->crc = CRC_INIT_VAL; break;
     case XZ_CHECK_CRC64: p->crc64 = CRC64_INIT_VAL; break;
     case XZ_CHECK_SHA256: Sha256_Init(&p->sha); break;
+    default: break;
   }
 }
 
@@ -62,6 +63,7 @@ void XzCheck_Update(CXzCheck *p, const void *data, size_t size)
     case XZ_CHECK_CRC32: p->crc = CrcUpdate(p->crc, data, size); break;
     case XZ_CHECK_CRC64: p->crc64 = Crc64Update(p->crc64, data, size); break;
     case XZ_CHECK_SHA256: Sha256_Update(&p->sha, (const Byte *)data, size); break;
+    default: break;
   }
 }
 

3rdparty/lzma/src/XzCrc64.c

@@ -1,5 +1,5 @@
 /* XzCrc64.c -- CRC64 calculation
-2023-04-02 : Igor Pavlov : Public domain */
+2023-12-08 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
@@ -8,36 +8,76 @@
 
 #define kCrc64Poly UINT64_CONST(0xC96C5795D7870F42)
 
-#ifdef MY_CPU_LE
-  #define CRC64_NUM_TABLES 4
-#else
-  #define CRC64_NUM_TABLES 5
-
-  UInt64 Z7_FASTCALL XzCrc64UpdateT1_BeT4(UInt64 v, const void *data, size_t size, const UInt64 *table);
+// for debug only : define Z7_CRC64_DEBUG_BE to test big-endian code in little-endian cpu
+// #define Z7_CRC64_DEBUG_BE
+#ifdef Z7_CRC64_DEBUG_BE
+#undef MY_CPU_LE
+#define MY_CPU_BE
 #endif
 
+#ifdef Z7_CRC64_NUM_TABLES
+  #define Z7_CRC64_NUM_TABLES_USE  Z7_CRC64_NUM_TABLES
+#else
+  #define Z7_CRC64_NUM_TABLES_USE  12
+#endif
+
+#if Z7_CRC64_NUM_TABLES_USE < 1
+  #error Stop_Compiling_Bad_Z7_CRC_NUM_TABLES
+#endif
+
+
+#if Z7_CRC64_NUM_TABLES_USE != 1
+
 #ifndef MY_CPU_BE
-  UInt64 Z7_FASTCALL XzCrc64UpdateT4(UInt64 v, const void *data, size_t size, const UInt64 *table);
+  #define FUNC_NAME_LE_2(s)   XzCrc64UpdateT ## s
+  #define FUNC_NAME_LE_1(s)   FUNC_NAME_LE_2(s)
+  #define FUNC_NAME_LE        FUNC_NAME_LE_1(Z7_CRC64_NUM_TABLES_USE)
+  UInt64 Z7_FASTCALL FUNC_NAME_LE (UInt64 v, const void *data, size_t size, const UInt64 *table);
+#endif
+#ifndef MY_CPU_LE
+  #define FUNC_NAME_BE_2(s)   XzCrc64UpdateBeT ## s
+  #define FUNC_NAME_BE_1(s)   FUNC_NAME_BE_2(s)
+  #define FUNC_NAME_BE        FUNC_NAME_BE_1(Z7_CRC64_NUM_TABLES_USE)
+  UInt64 Z7_FASTCALL FUNC_NAME_BE (UInt64 v, const void *data, size_t size, const UInt64 *table);
 #endif
 
-typedef UInt64 (Z7_FASTCALL *CRC64_FUNC)(UInt64 v, const void *data, size_t size, const UInt64 *table);
+#if defined(MY_CPU_LE)
+  #define FUNC_REF  FUNC_NAME_LE
+#elif defined(MY_CPU_BE)
+  #define FUNC_REF  FUNC_NAME_BE
+#else
+  #define FUNC_REF  g_Crc64Update
+  static UInt64 (Z7_FASTCALL *FUNC_REF)(UInt64 v, const void *data, size_t size, const UInt64 *table);
+#endif
+
+#endif
+
+
+MY_ALIGN(64)
+static UInt64 g_Crc64Table[256 * Z7_CRC64_NUM_TABLES_USE];
 
-static CRC64_FUNC g_Crc64Update;
-UInt64 g_Crc64Table[256 * CRC64_NUM_TABLES];
 
 UInt64 Z7_FASTCALL Crc64Update(UInt64 v, const void *data, size_t size)
 {
-  return g_Crc64Update(v, data, size, g_Crc64Table);
+#if Z7_CRC64_NUM_TABLES_USE == 1
+  #define CRC64_UPDATE_BYTE_2(crc, b)  (table[((crc) ^ (b)) & 0xFF] ^ ((crc) >> 8))
+  const UInt64 *table = g_Crc64Table;
+  const Byte *p = (const Byte *)data;
+  const Byte *lim = p + size;
+  for (; p != lim; p++)
+    v = CRC64_UPDATE_BYTE_2(v, *p);
+  return v;
+  #undef CRC64_UPDATE_BYTE_2
+#else
+  return FUNC_REF (v, data, size, g_Crc64Table);
+#endif
 }
 
-UInt64 Z7_FASTCALL Crc64Calc(const void *data, size_t size)
-{
-  return g_Crc64Update(CRC64_INIT_VAL, data, size, g_Crc64Table) ^ CRC64_INIT_VAL;
-}
 
+Z7_NO_INLINE
 void Z7_FASTCALL Crc64GenerateTable(void)
 {
-  UInt32 i;
+  unsigned i;
   for (i = 0; i < 256; i++)
   {
     UInt64 r = i;
@@ -46,35 +86,55 @@ void Z7_FASTCALL Crc64GenerateTable(void)
       r = (r >> 1) ^ (kCrc64Poly & ((UInt64)0 - (r & 1)));
     g_Crc64Table[i] = r;
   }
-  for (i = 256; i < 256 * CRC64_NUM_TABLES; i++)
+
+#if Z7_CRC64_NUM_TABLES_USE != 1
+#if 1 || 1 && defined(MY_CPU_X86) // low register count
+  for (i = 0; i < 256 * (Z7_CRC64_NUM_TABLES_USE - 1); i++)
   {
-    const UInt64 r = g_Crc64Table[(size_t)i - 256];
-    g_Crc64Table[i] = g_Crc64Table[r & 0xFF] ^ (r >> 8);
+    const UInt64 r0 = g_Crc64Table[(size_t)i];
+    g_Crc64Table[(size_t)i + 256] = g_Crc64Table[(Byte)r0] ^ (r0 >> 8);
   }
-  
-  #ifdef MY_CPU_LE
-
-  g_Crc64Update = XzCrc64UpdateT4;
-
-  #else
+#else
+  for (i = 0; i < 256 * (Z7_CRC64_NUM_TABLES_USE - 1); i += 2)
   {
-    #ifndef MY_CPU_BE
+    UInt64 r0 = g_Crc64Table[(size_t)(i)    ];
+    UInt64 r1 = g_Crc64Table[(size_t)(i) + 1];
+    r0 = g_Crc64Table[(Byte)r0] ^ (r0 >> 8);
+    r1 = g_Crc64Table[(Byte)r1] ^ (r1 >> 8);
+    g_Crc64Table[(size_t)i + 256    ] = r0;
+    g_Crc64Table[(size_t)i + 256 + 1] = r1;
+  }
+#endif
+
+#ifndef MY_CPU_LE
+  {
+#ifndef MY_CPU_BE
     UInt32 k = 1;
     if (*(const Byte *)&k == 1)
-      g_Crc64Update = XzCrc64UpdateT4;
+      FUNC_REF = FUNC_NAME_LE;
     else
-    #endif
+#endif
     {
-      for (i = 256 * CRC64_NUM_TABLES - 1; i >= 256; i--)
+#ifndef MY_CPU_BE
+      FUNC_REF = FUNC_NAME_BE;
+#endif
+      for (i = 0; i < 256 * Z7_CRC64_NUM_TABLES_USE; i++)
       {
-        const UInt64 x = g_Crc64Table[(size_t)i - 256];
+        const UInt64 x = g_Crc64Table[i];
         g_Crc64Table[i] = Z7_BSWAP64(x);
       }
-      g_Crc64Update = XzCrc64UpdateT1_BeT4;
     }
   }
-  #endif
+#endif // ndef MY_CPU_LE
+#endif // Z7_CRC64_NUM_TABLES_USE != 1
 }
 
 #undef kCrc64Poly
-#undef CRC64_NUM_TABLES
+#undef Z7_CRC64_NUM_TABLES_USE
+#undef FUNC_REF
+#undef FUNC_NAME_LE_2
+#undef FUNC_NAME_LE_1
+#undef FUNC_NAME_LE
+#undef FUNC_NAME_BE_2
+#undef FUNC_NAME_BE_1
+#undef FUNC_NAME_BE

3rdparty/lzma/src/XzCrc64Opt.c

@@ -1,61 +1,261 @@
-/* XzCrc64Opt.c -- CRC64 calculation
-2023-04-02 : Igor Pavlov : Public domain */
+/* XzCrc64Opt.c -- CRC64 calculation (optimized functions)
+2023-12-08 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
 #include "CpuArch.h"
 
+#if !defined(Z7_CRC64_NUM_TABLES) || Z7_CRC64_NUM_TABLES > 1
+
+// for debug only : define Z7_CRC64_DEBUG_BE to test big-endian code in little-endian cpu
+// #define Z7_CRC64_DEBUG_BE
+#ifdef Z7_CRC64_DEBUG_BE
+#undef MY_CPU_LE
+#define MY_CPU_BE
+#endif
+
+#if defined(MY_CPU_64BIT)
+#define Z7_CRC64_USE_64BIT
+#endif
+
+// the value Z7_CRC64_NUM_TABLES_USE must be defined to same value as in XzCrc64.c
+#ifdef Z7_CRC64_NUM_TABLES
+#define Z7_CRC64_NUM_TABLES_USE  Z7_CRC64_NUM_TABLES
+#else
+#define Z7_CRC64_NUM_TABLES_USE  12
+#endif
+
+#if Z7_CRC64_NUM_TABLES_USE % 4 || \
+    Z7_CRC64_NUM_TABLES_USE < 4 || \
+    Z7_CRC64_NUM_TABLES_USE > 4 * 4
+  #error Stop_Compiling_Bad_CRC64_NUM_TABLES
+#endif
+
+
 #ifndef MY_CPU_BE
 
-#define CRC64_UPDATE_BYTE_2(crc, b) (table[((crc) ^ (b)) & 0xFF] ^ ((crc) >> 8))
+#define CRC64_UPDATE_BYTE_2(crc, b)  (table[((crc) ^ (b)) & 0xFF] ^ ((crc) >> 8))
 
-UInt64 Z7_FASTCALL XzCrc64UpdateT4(UInt64 v, const void *data, size_t size, const UInt64 *table);
-UInt64 Z7_FASTCALL XzCrc64UpdateT4(UInt64 v, const void *data, size_t size, const UInt64 *table)
+#if defined(Z7_CRC64_USE_64BIT) && (Z7_CRC64_NUM_TABLES_USE % 8 == 0)
+
+#define Q64LE(n, d) \
+    ( (table + ((n) * 8 + 7) * 0x100)[((d)         ) & 0xFF] \
+    ^ (table + ((n) * 8 + 6) * 0x100)[((d) >> 1 * 8) & 0xFF] \
+    ^ (table + ((n) * 8 + 5) * 0x100)[((d) >> 2 * 8) & 0xFF] \
+    ^ (table + ((n) * 8 + 4) * 0x100)[((d) >> 3 * 8) & 0xFF] \
+    ^ (table + ((n) * 8 + 3) * 0x100)[((d) >> 4 * 8) & 0xFF] \
+    ^ (table + ((n) * 8 + 2) * 0x100)[((d) >> 5 * 8) & 0xFF] \
+    ^ (table + ((n) * 8 + 1) * 0x100)[((d) >> 6 * 8) & 0xFF] \
+    ^ (table + ((n) * 8 + 0) * 0x100)[((d) >> 7 * 8)] )
+
+#define R64(a)  *((const UInt64 *)(const void *)p + (a))
+
+#else
+
+#define Q32LE(n, d) \
+    ( (table + ((n) * 4 + 3) * 0x100)[((d)         ) & 0xFF] \
+    ^ (table + ((n) * 4 + 2) * 0x100)[((d) >> 1 * 8) & 0xFF] \
+    ^ (table + ((n) * 4 + 1) * 0x100)[((d) >> 2 * 8) & 0xFF] \
+    ^ (table + ((n) * 4 + 0) * 0x100)[((d) >> 3 * 8)] )
+
+#define R32(a)  *((const UInt32 *)(const void *)p + (a))
+
+#endif
+
+
+#define CRC64_FUNC_PRE_LE2(step) \
+UInt64 Z7_FASTCALL XzCrc64UpdateT ## step (UInt64 v, const void *data, size_t size, const UInt64 *table)
+
+#define CRC64_FUNC_PRE_LE(step)   \
+        CRC64_FUNC_PRE_LE2(step); \
+        CRC64_FUNC_PRE_LE2(step)
+
+CRC64_FUNC_PRE_LE(Z7_CRC64_NUM_TABLES_USE)
 {
   const Byte *p = (const Byte *)data;
-  for (; size > 0 && ((unsigned)(ptrdiff_t)p & 3) != 0; size--, p++)
+  const Byte *lim;
+  for (; size && ((unsigned)(ptrdiff_t)p & (7 - (Z7_CRC64_NUM_TABLES_USE & 4))) != 0; size--, p++)
     v = CRC64_UPDATE_BYTE_2(v, *p);
-  for (; size >= 4; size -= 4, p += 4)
+  lim = p + size;
+  if (size >= Z7_CRC64_NUM_TABLES_USE)
   {
-    const UInt32 d = (UInt32)v ^ *(const UInt32 *)(const void *)p;
-    v = (v >> 32)
-        ^ (table + 0x300)[((d      ) & 0xFF)]
-        ^ (table + 0x200)[((d >>  8) & 0xFF)]
-        ^ (table + 0x100)[((d >> 16) & 0xFF)]
-        ^ (table + 0x000)[((d >> 24))];
+    lim -= Z7_CRC64_NUM_TABLES_USE;
+    do
+    {
+#if Z7_CRC64_NUM_TABLES_USE == 4
+      const UInt32 d = (UInt32)v ^ R32(0);
+      v = (v >> 32) ^ Q32LE(0, d);
+#elif Z7_CRC64_NUM_TABLES_USE == 8
+#ifdef Z7_CRC64_USE_64BIT
+      v ^= R64(0);
+      v = Q64LE(0, v);
+#else
+      UInt32 v0, v1;
+      v0 = (UInt32)v         ^ R32(0);
+      v1 = (UInt32)(v >> 32) ^ R32(1);
+      v = Q32LE(1, v0) ^ Q32LE(0, v1);
+#endif
+#elif Z7_CRC64_NUM_TABLES_USE == 12
+      UInt32 w;
+      UInt32 v0, v1;
+      v0 = (UInt32)v         ^ R32(0);
+      v1 = (UInt32)(v >> 32) ^ R32(1);
+      w = R32(2);
+      v = Q32LE(0, w);
+      v ^= Q32LE(2, v0) ^ Q32LE(1, v1);
+#elif Z7_CRC64_NUM_TABLES_USE == 16
+#ifdef Z7_CRC64_USE_64BIT
+      UInt64 w;
+      UInt64 x;
+      w  = R64(1);      x = Q64LE(0, w);
+      v ^= R64(0);  v = x ^ Q64LE(1, v);
+#else
+      UInt32 v0, v1;
+      UInt32 r0, r1;
+      v0 = (UInt32)v         ^ R32(0);
+      v1 = (UInt32)(v >> 32) ^ R32(1);
+      r0 =                     R32(2);
+      r1 =                     R32(3);
+      v  = Q32LE(1, r0) ^ Q32LE(0, r1);
+      v ^= Q32LE(3, v0) ^ Q32LE(2, v1);
+#endif
+#else
+#error Stop_Compiling_Bad_CRC64_NUM_TABLES
+#endif
+      p += Z7_CRC64_NUM_TABLES_USE;
+    }
+    while (p <= lim);
+    lim += Z7_CRC64_NUM_TABLES_USE;
   }
-  for (; size > 0; size--, p++)
+  for (; p < lim; p++)
     v = CRC64_UPDATE_BYTE_2(v, *p);
   return v;
 }
 
+#undef CRC64_UPDATE_BYTE_2
+#undef R32
+#undef R64
+#undef Q32LE
+#undef Q64LE
+#undef CRC64_FUNC_PRE_LE
+#undef CRC64_FUNC_PRE_LE2
+
 #endif
 
 
+
+
 #ifndef MY_CPU_LE
 
-#define CRC64_UPDATE_BYTE_2_BE(crc, b) (table[(Byte)((crc) >> 56) ^ (b)] ^ ((crc) << 8))
+#define CRC64_UPDATE_BYTE_2_BE(crc, b)  (table[((crc) >> 56) ^ (b)] ^ ((crc) << 8))
 
-UInt64 Z7_FASTCALL XzCrc64UpdateT1_BeT4(UInt64 v, const void *data, size_t size, const UInt64 *table);
-UInt64 Z7_FASTCALL XzCrc64UpdateT1_BeT4(UInt64 v, const void *data, size_t size, const UInt64 *table)
+#if defined(Z7_CRC64_USE_64BIT) && (Z7_CRC64_NUM_TABLES_USE % 8 == 0)
+
+#define Q64BE(n, d) \
+    ( (table + ((n) * 8 + 0) * 0x100)[(Byte)(d)] \
+    ^ (table + ((n) * 8 + 1) * 0x100)[((d) >> 1 * 8) & 0xFF] \
+    ^ (table + ((n) * 8 + 2) * 0x100)[((d) >> 2 * 8) & 0xFF] \
+    ^ (table + ((n) * 8 + 3) * 0x100)[((d) >> 3 * 8) & 0xFF] \
+    ^ (table + ((n) * 8 + 4) * 0x100)[((d) >> 4 * 8) & 0xFF] \
+    ^ (table + ((n) * 8 + 5) * 0x100)[((d) >> 5 * 8) & 0xFF] \
+    ^ (table + ((n) * 8 + 6) * 0x100)[((d) >> 6 * 8) & 0xFF] \
+    ^ (table + ((n) * 8 + 7) * 0x100)[((d) >> 7 * 8)] )
+
+#ifdef Z7_CRC64_DEBUG_BE
+  #define R64BE(a)  GetBe64a((const UInt64 *)(const void *)p + (a))
+#else
+  #define R64BE(a)         *((const UInt64 *)(const void *)p + (a))
+#endif
+
+#else
+
+#define Q32BE(n, d) \
+    ( (table + ((n) * 4 + 0) * 0x100)[(Byte)(d)] \
+    ^ (table + ((n) * 4 + 1) * 0x100)[((d) >> 1 * 8) & 0xFF] \
+    ^ (table + ((n) * 4 + 2) * 0x100)[((d) >> 2 * 8) & 0xFF] \
+    ^ (table + ((n) * 4 + 3) * 0x100)[((d) >> 3 * 8)] )
+
+#ifdef Z7_CRC64_DEBUG_BE
+  #define R32BE(a)  GetBe32a((const UInt32 *)(const void *)p + (a))
+#else
+  #define R32BE(a)         *((const UInt32 *)(const void *)p + (a))
+#endif
+
+#endif
+
+#define CRC64_FUNC_PRE_BE2(step) \
+UInt64 Z7_FASTCALL XzCrc64UpdateBeT ## step (UInt64 v, const void *data, size_t size, const UInt64 *table)
+
+#define CRC64_FUNC_PRE_BE(step)   \
+        CRC64_FUNC_PRE_BE2(step); \
+        CRC64_FUNC_PRE_BE2(step)
+
+CRC64_FUNC_PRE_BE(Z7_CRC64_NUM_TABLES_USE)
 {
   const Byte *p = (const Byte *)data;
-  table += 0x100;
+  const Byte *lim;
   v = Z7_BSWAP64(v);
-  for (; size > 0 && ((unsigned)(ptrdiff_t)p & 3) != 0; size--, p++)
+  for (; size && ((unsigned)(ptrdiff_t)p & (7 - (Z7_CRC64_NUM_TABLES_USE & 4))) != 0; size--, p++)
     v = CRC64_UPDATE_BYTE_2_BE(v, *p);
-  for (; size >= 4; size -= 4, p += 4)
+  lim = p + size;
+  if (size >= Z7_CRC64_NUM_TABLES_USE)
   {
-    const UInt32 d = (UInt32)(v >> 32) ^ *(const UInt32 *)(const void *)p;
-    v = (v << 32)
-        ^ (table + 0x000)[((d      ) & 0xFF)]
-        ^ (table + 0x100)[((d >>  8) & 0xFF)]
-        ^ (table + 0x200)[((d >> 16) & 0xFF)]
-        ^ (table + 0x300)[((d >> 24))];
+    lim -= Z7_CRC64_NUM_TABLES_USE;
+    do
+    {
+#if   Z7_CRC64_NUM_TABLES_USE == 4
+      const UInt32 d = (UInt32)(v >> 32) ^ R32BE(0);
+      v = (v << 32) ^ Q32BE(0, d);
+#elif Z7_CRC64_NUM_TABLES_USE == 12
+      const UInt32 d1 = (UInt32)(v >> 32) ^ R32BE(0);
+      const UInt32 d0 = (UInt32)(v      ) ^ R32BE(1);
+      const UInt32 w =                      R32BE(2);
+      v  = Q32BE(0, w);
+      v ^= Q32BE(2, d1) ^ Q32BE(1, d0);
+
+#elif Z7_CRC64_NUM_TABLES_USE == 8
+  #ifdef Z7_CRC64_USE_64BIT
+      v ^= R64BE(0);
+      v  = Q64BE(0, v);
+  #else
+      const UInt32 d1 = (UInt32)(v >> 32) ^ R32BE(0);
+      const UInt32 d0 = (UInt32)(v      ) ^ R32BE(1);
+      v = Q32BE(1, d1) ^ Q32BE(0, d0);
+  #endif
+#elif Z7_CRC64_NUM_TABLES_USE == 16
+  #ifdef Z7_CRC64_USE_64BIT
+      const UInt64 w = R64BE(1);
+      v ^= R64BE(0);
+      v  = Q64BE(0, w) ^ Q64BE(1, v);
+  #else
+      const UInt32 d1 = (UInt32)(v >> 32) ^ R32BE(0);
+      const UInt32 d0 = (UInt32)(v      ) ^ R32BE(1);
+      const UInt32 w1 =                     R32BE(2);
+      const UInt32 w0 =                     R32BE(3);
+      v  = Q32BE(1, w1) ^ Q32BE(0, w0);
+      v ^= Q32BE(3, d1) ^ Q32BE(2, d0);
+  #endif
+#elif
+#error Stop_Compiling_Bad_CRC64_NUM_TABLES
+#endif
+      p += Z7_CRC64_NUM_TABLES_USE;
+    }
+    while (p <= lim);
+    lim += Z7_CRC64_NUM_TABLES_USE;
   }
-  for (; size > 0; size--, p++)
+  for (; p < lim; p++)
     v = CRC64_UPDATE_BYTE_2_BE(v, *p);
   return Z7_BSWAP64(v);
 }
 
+#undef CRC64_UPDATE_BYTE_2_BE
+#undef R32BE
+#undef R64BE
+#undef Q32BE
+#undef Q64BE
+#undef CRC64_FUNC_PRE_BE
+#undef CRC64_FUNC_PRE_BE2
+
+#endif
+#undef Z7_CRC64_NUM_TABLES_USE
 #endif

3rdparty/lzma/src/XzDec.c

@@ -1,5 +1,5 @@
 /* XzDec.c -- Xz Decode
-2023-04-13 : Igor Pavlov : Public domain */
+2024-03-01 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
@@ -105,30 +105,32 @@ static SRes XzBcFilterState_SetProps(void *pp, const Byte *props, size_t propSiz
   {
     if (propSize != 1)
       return SZ_ERROR_UNSUPPORTED;
-    p->delta = (unsigned)props[0] + 1;
+    p->delta = (UInt32)props[0] + 1;
   }
   else
   {
     if (propSize == 4)
     {
-      UInt32 v = GetUi32(props);
+      const UInt32 v = GetUi32(props);
       switch (p->methodId)
       {
         case XZ_ID_PPC:
         case XZ_ID_ARM:
         case XZ_ID_SPARC:
         case XZ_ID_ARM64:
-          if ((v & 3) != 0)
+          if (v & 3)
             return SZ_ERROR_UNSUPPORTED;
           break;
         case XZ_ID_ARMT:
-          if ((v & 1) != 0)
+        case XZ_ID_RISCV:
+          if (v & 1)
             return SZ_ERROR_UNSUPPORTED;
           break;
         case XZ_ID_IA64:
-          if ((v & 0xF) != 0)
+          if (v & 0xf)
             return SZ_ERROR_UNSUPPORTED;
           break;
+        default: break;
       }
       p->ip = v;
     }
@@ -151,12 +153,13 @@ static void XzBcFilterState_Init(void *pp)
 
 static const z7_Func_BranchConv g_Funcs_BranchConv_RISC_Dec[] =
 {
-  Z7_BRANCH_CONV_DEC(PPC),
-  Z7_BRANCH_CONV_DEC(IA64),
-  Z7_BRANCH_CONV_DEC(ARM),
-  Z7_BRANCH_CONV_DEC(ARMT),
-  Z7_BRANCH_CONV_DEC(SPARC),
-  Z7_BRANCH_CONV_DEC(ARM64)
+  Z7_BRANCH_CONV_DEC_2 (BranchConv_PPC),
+  Z7_BRANCH_CONV_DEC_2 (BranchConv_IA64),
+  Z7_BRANCH_CONV_DEC_2 (BranchConv_ARM),
+  Z7_BRANCH_CONV_DEC_2 (BranchConv_ARMT),
+  Z7_BRANCH_CONV_DEC_2 (BranchConv_SPARC),
+  Z7_BRANCH_CONV_DEC_2 (BranchConv_ARM64),
+  Z7_BRANCH_CONV_DEC_2 (BranchConv_RISCV)
 };
 
 static SizeT XzBcFilterStateBase_Filter_Dec(CXzBcFilterStateBase *p, Byte *data, SizeT size)
@@ -262,7 +265,7 @@ static SRes XzBcFilterState_Code2(void *pp,
 
 
 #define XZ_IS_SUPPORTED_FILTER_ID(id) \
-    ((id) >= XZ_ID_Delta && (id) <= XZ_ID_ARM64)
+    ((id) >= XZ_ID_Delta && (id) <= XZ_ID_RISCV)
      
 SRes Xz_StateCoder_Bc_SetFromMethod_Func(IStateCoder *p, UInt64 id,
     Xz_Func_BcFilterStateBase_Filter func, ISzAllocPtr alloc)
@@ -541,13 +544,12 @@ static SRes MixCoder_SetFromMethod(CMixCoder *p, unsigned coderIndex, UInt64 met
 {
   IStateCoder *sc = &p->coders[coderIndex];
   p->ids[coderIndex] = methodId;
-  switch (methodId)
-  {
-    case XZ_ID_LZMA2: return Lzma2State_SetFromMethod(sc, outBuf, outBufSize, p->alloc);
-    #ifdef USE_SUBBLOCK
-    case XZ_ID_Subblock: return SbState_SetFromMethod(sc, p->alloc);
-    #endif
-  }
+  if (methodId == XZ_ID_LZMA2)
+    return Lzma2State_SetFromMethod(sc, outBuf, outBufSize, p->alloc);
+#ifdef USE_SUBBLOCK
+  if (methodId == XZ_ID_Subblock)
+    return SbState_SetFromMethod(sc, p->alloc);
+#endif
   if (coderIndex == 0)
     return SZ_ERROR_UNSUPPORTED;
   return Xz_StateCoder_Bc_SetFromMethod_Func(sc, methodId,
@@ -558,10 +560,8 @@ static SRes MixCoder_SetFromMethod(CMixCoder *p, unsigned coderIndex, UInt64 met
 static SRes MixCoder_ResetFromMethod(CMixCoder *p, unsigned coderIndex, UInt64 methodId, Byte *outBuf, size_t outBufSize)
 {
   IStateCoder *sc = &p->coders[coderIndex];
-  switch (methodId)
-  {
-    case XZ_ID_LZMA2: return Lzma2State_ResetOutBuf(sc, outBuf, outBufSize);
-  }
+  if (methodId == XZ_ID_LZMA2)
+    return Lzma2State_ResetOutBuf(sc, outBuf, outBufSize);
   return SZ_ERROR_UNSUPPORTED;
 }
 
@@ -804,7 +804,7 @@ static BoolInt Xz_CheckFooter(CXzStreamFlags flags, UInt64 indexSize, const Byte
 }
 
 #define READ_VARINT_AND_CHECK(buf, pos, size, res) \
-  { unsigned s = Xz_ReadVarInt(buf + pos, size - pos, res); \
+  { const unsigned s = Xz_ReadVarInt(buf + pos, size - pos, res); \
   if (s == 0) return SZ_ERROR_ARCHIVE; \
   pos += s; }
 
@@ -1034,7 +1034,7 @@ SRes XzUnpacker_Code(CXzUnpacker *p, Byte *dest, SizeT *destLen,
       SRes res;
 
       ECoderFinishMode finishMode2 = finishMode;
-      BoolInt srcFinished2 = srcFinished;
+      BoolInt srcFinished2 = (BoolInt)srcFinished;
       BoolInt destFinish = False;
 
       if (p->block.packSize != (UInt64)(Int64)-1)
@@ -1127,7 +1127,7 @@ SRes XzUnpacker_Code(CXzUnpacker *p, Byte *dest, SizeT *destLen,
       return SZ_OK;
     }
 
-    switch (p->state)
+    switch ((int)p->state)
     {
       case XZ_STATE_STREAM_HEADER:
       {
@@ -1172,15 +1172,15 @@ SRes XzUnpacker_Code(CXzUnpacker *p, Byte *dest, SizeT *destLen,
             p->state = XZ_STATE_STREAM_INDEX;
             break;
           }
-          p->blockHeaderSize = ((UInt32)p->buf[0] << 2) + 4;
+          p->blockHeaderSize = ((unsigned)p->buf[0] << 2) + 4;
           break;
         }
         
         if (p->pos != p->blockHeaderSize)
         {
-          UInt32 cur = p->blockHeaderSize - p->pos;
+          unsigned cur = p->blockHeaderSize - p->pos;
           if (cur > srcRem)
-            cur = (UInt32)srcRem;
+            cur = (unsigned)srcRem;
           memcpy(p->buf + p->pos, src, cur);
           p->pos += cur;
           (*srcLen) += cur;
@@ -1222,8 +1222,8 @@ SRes XzUnpacker_Code(CXzUnpacker *p, Byte *dest, SizeT *destLen,
         }
         else
         {
-          UInt32 checkSize = XzFlags_GetCheckSize(p->streamFlags);
-          UInt32 cur = checkSize - p->pos;
+          const unsigned checkSize = XzFlags_GetCheckSize(p->streamFlags);
+          unsigned cur = checkSize - p->pos;
           if (cur != 0)
           {
             if (srcRem == 0)
@@ -1232,7 +1232,7 @@ SRes XzUnpacker_Code(CXzUnpacker *p, Byte *dest, SizeT *destLen,
               return SZ_OK;
             }
             if (cur > srcRem)
-              cur = (UInt32)srcRem;
+              cur = (unsigned)srcRem;
             memcpy(p->buf + p->pos, src, cur);
             p->pos += cur;
             (*srcLen) += cur;
@@ -1321,9 +1321,9 @@ SRes XzUnpacker_Code(CXzUnpacker *p, Byte *dest, SizeT *destLen,
 
       case XZ_STATE_STREAM_FOOTER:
       {
-        UInt32 cur = XZ_STREAM_FOOTER_SIZE - p->pos;
+        unsigned cur = XZ_STREAM_FOOTER_SIZE - p->pos;
         if (cur > srcRem)
-          cur = (UInt32)srcRem;
+          cur = (unsigned)srcRem;
         memcpy(p->buf + p->pos, src, cur);
         p->pos += cur;
         (*srcLen) += cur;
@@ -1358,6 +1358,8 @@ SRes XzUnpacker_Code(CXzUnpacker *p, Byte *dest, SizeT *destLen,
       }
       
       case XZ_STATE_BLOCK: break; /* to disable GCC warning */
+      
+      default: return SZ_ERROR_FAIL;
     }
   }
   /*
@@ -1773,10 +1775,10 @@ static void XzDecMt_Callback_Parse(void *obj, unsigned coderIndex, CMtDecCallbac
           }
         }
         {
-        UInt64 packSize = block->packSize;
-        UInt64 packSizeAligned = packSize + ((0 - (unsigned)packSize) & 3);
-        UInt32 checkSize = XzFlags_GetCheckSize(coder->dec.streamFlags);
-        UInt64 blockPackSum = coder->inPreSize + packSizeAligned + checkSize;
+        const UInt64 packSize = block->packSize;
+        const UInt64 packSizeAligned = packSize + ((0 - (unsigned)packSize) & 3);
+        const unsigned checkSize = XzFlags_GetCheckSize(coder->dec.streamFlags);
+        const UInt64 blockPackSum = coder->inPreSize + packSizeAligned + checkSize;
         // if (blockPackSum <= me->props.inBlockMax)
         // unpackBlockMaxSize
         {
@@ -2381,7 +2383,7 @@ static SRes XzDecMt_Decode_ST(CXzDecMt *p
   if (tMode)
   {
     XzDecMt_FreeOutBufs(p);
-    tMode = MtDec_PrepareRead(&p->mtc);
+    tMode = (BoolInt)MtDec_PrepareRead(&p->mtc);
   }
   #endif
 
@@ -2644,7 +2646,7 @@ SRes XzDecMt_Decode(CXzDecMtHandle p,
     p->outSize = *outDataSize;
   }
 
-  p->finishMode = finishMode;
+  p->finishMode = (BoolInt)finishMode;
 
   // p->outSize = 457; p->outSize_Defined = True; p->finishMode = False; // for test
 

3rdparty/lzma/src/XzEnc.c

@@ -1,5 +1,5 @@
 /* XzEnc.c -- Xz Encode
-2023-04-13 : Igor Pavlov : Public domain */
+2024-03-01 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
@@ -29,8 +29,9 @@
 
 #define XZ_GET_PAD_SIZE(dataSize) ((4 - ((unsigned)(dataSize) & 3)) & 3)
 
-/* max pack size for LZMA2 block + check-64bytrs: */
-#define XZ_GET_MAX_BLOCK_PACK_SIZE(unpackSize) ((unpackSize) + ((unpackSize) >> 10) + 16 + 64)
+#define XZ_CHECK_SIZE_MAX 64
+/* max pack size for LZMA2 block + pad4 + check_size: */
+#define XZ_GET_MAX_BLOCK_PACK_SIZE(unpackSize) ((unpackSize) + ((unpackSize) >> 10) + 16 + XZ_CHECK_SIZE_MAX)
 
 #define XZ_GET_ESTIMATED_BLOCK_TOTAL_PACK_SIZE(unpackSize) (XZ_BLOCK_HEADER_SIZE_MAX + XZ_GET_MAX_BLOCK_PACK_SIZE(unpackSize))
 
@@ -325,12 +326,13 @@ typedef struct
 
 static const z7_Func_BranchConv g_Funcs_BranchConv_RISC_Enc[] =
 {
-  Z7_BRANCH_CONV_ENC(PPC),
-  Z7_BRANCH_CONV_ENC(IA64),
-  Z7_BRANCH_CONV_ENC(ARM),
-  Z7_BRANCH_CONV_ENC(ARMT),
-  Z7_BRANCH_CONV_ENC(SPARC),
-  Z7_BRANCH_CONV_ENC(ARM64)
+  Z7_BRANCH_CONV_ENC_2 (BranchConv_PPC),
+  Z7_BRANCH_CONV_ENC_2 (BranchConv_IA64),
+  Z7_BRANCH_CONV_ENC_2 (BranchConv_ARM),
+  Z7_BRANCH_CONV_ENC_2 (BranchConv_ARMT),
+  Z7_BRANCH_CONV_ENC_2 (BranchConv_SPARC),
+  Z7_BRANCH_CONV_ENC_2 (BranchConv_ARM64),
+  Z7_BRANCH_CONV_ENC_2 (BranchConv_RISCV)
 };
 
 static SizeT XzBcFilterStateBase_Filter_Enc(CXzBcFilterStateBase *p, Byte *data, SizeT size)
@@ -888,9 +890,9 @@ static SRes Xz_CompressBlock(
     blockSizes->unpackSize = checkInStream.processed;
   }
   {
-    Byte buf[4 + 64];
-    unsigned padSize = XZ_GET_PAD_SIZE(seqSizeOutStream.processed);
-    UInt64 packSize = seqSizeOutStream.processed;
+    Byte buf[4 + XZ_CHECK_SIZE_MAX];
+    const unsigned padSize = XZ_GET_PAD_SIZE(seqSizeOutStream.processed);
+    const UInt64 packSize = seqSizeOutStream.processed;
     
     buf[0] = 0;
     buf[1] = 0;
@@ -898,7 +900,8 @@ static SRes Xz_CompressBlock(
     buf[3] = 0;
     
     SeqCheckInStream_GetDigest(&checkInStream, buf + 4);
-    RINOK(WriteBytes(&seqSizeOutStream.vt, buf + (4 - padSize), padSize + XzFlags_GetCheckSize((CXzStreamFlags)props->checkId)))
+    RINOK(WriteBytes(&seqSizeOutStream.vt, buf + (4 - padSize),
+        padSize + XzFlags_GetCheckSize((CXzStreamFlags)props->checkId)))
     
     blockSizes->totalSize = seqSizeOutStream.processed - padSize;
     
@@ -1083,18 +1086,19 @@ static SRes XzEnc_MtCallback_Code(void *pp, unsigned coderIndex, unsigned outBuf
   CXzEnc *me = (CXzEnc *)pp;
   SRes res;
   CMtProgressThunk progressThunk;
-
-  Byte *dest = me->outBufs[outBufIndex];
-
+  Byte *dest;
   UNUSED_VAR(finished)
-
   {
     CXzEncBlockInfo *bInfo = &me->EncBlocks[outBufIndex];
     bInfo->totalSize = 0;
     bInfo->unpackSize = 0;
     bInfo->headerSize = 0;
+    // v23.02: we don't compress empty blocks
+    // also we must ignore that empty block in XzEnc_MtCallback_Write()
+    if (srcSize == 0)
+      return SZ_OK;
   }
-
+  dest = me->outBufs[outBufIndex];
   if (!dest)
   {
     dest = (Byte *)ISzAlloc_Alloc(me->alloc, me->outBufSize);
@@ -1140,18 +1144,20 @@ static SRes XzEnc_MtCallback_Code(void *pp, unsigned coderIndex, unsigned outBuf
 static SRes XzEnc_MtCallback_Write(void *pp, unsigned outBufIndex)
 {
   CXzEnc *me = (CXzEnc *)pp;
-
   const CXzEncBlockInfo *bInfo = &me->EncBlocks[outBufIndex];
-  const Byte *data = me->outBufs[outBufIndex];
-
-  RINOK(WriteBytes(me->outStream, data, bInfo->headerSize))
-
+  // v23.02: we don't write empty blocks
+  // note: if (bInfo->unpackSize == 0) then there is no compressed data of block
+  if (bInfo->unpackSize == 0)
+    return SZ_OK;
   {
-    UInt64 totalPackFull = bInfo->totalSize + XZ_GET_PAD_SIZE(bInfo->totalSize);
-    RINOK(WriteBytes(me->outStream, data + XZ_BLOCK_HEADER_SIZE_MAX, (size_t)totalPackFull - bInfo->headerSize))
+    const Byte *data = me->outBufs[outBufIndex];
+    RINOK(WriteBytes(me->outStream, data, bInfo->headerSize))
+    {
+      const UInt64 totalPackFull = bInfo->totalSize + XZ_GET_PAD_SIZE(bInfo->totalSize);
+      RINOK(WriteBytes(me->outStream, data + XZ_BLOCK_HEADER_SIZE_MAX, (size_t)totalPackFull - bInfo->headerSize))
+    }
+    return XzEncIndex_AddIndexRecord(&me->xzIndex, bInfo->unpackSize, bInfo->totalSize, me->alloc);
   }
-
-  return XzEncIndex_AddIndexRecord(&me->xzIndex, bInfo->unpackSize, bInfo->totalSize, me->alloc);
 }
 
 #endif

3rdparty/lzma/src/XzIn.c

@@ -1,5 +1,5 @@
 /* XzIn.c - Xz input
-2023-04-02 : Igor Pavlov : Public domain */
+2023-09-07 : Igor Pavlov : Public domain */
 
 #include "Precomp.h"
 
@@ -27,7 +27,7 @@ SRes Xz_ReadHeader(CXzStreamFlags *p, ISeqInStreamPtr inStream)
 }
 
 #define READ_VARINT_AND_CHECK(buf, pos, size, res) \
-  { unsigned s = Xz_ReadVarInt(buf + pos, size - pos, res); \
+  { const unsigned s = Xz_ReadVarInt(buf + pos, size - pos, res); \
   if (s == 0) return SZ_ERROR_ARCHIVE; \
   pos += s; }
 
@@ -37,7 +37,7 @@ SRes XzBlock_ReadHeader(CXzBlock *p, ISeqInStreamPtr inStream, BoolInt *isIndex,
   unsigned headerSize;
   *headerSizeRes = 0;
   RINOK(SeqInStream_ReadByte(inStream, &header[0]))
-  headerSize = (unsigned)header[0];
+  headerSize = header[0];
   if (headerSize == 0)
   {
     *headerSizeRes = 1;
@@ -47,7 +47,7 @@ SRes XzBlock_ReadHeader(CXzBlock *p, ISeqInStreamPtr inStream, BoolInt *isIndex,
 
   *isIndex = False;
   headerSize = (headerSize << 2) + 4;
-  *headerSizeRes = headerSize;
+  *headerSizeRes = (UInt32)headerSize;
   {
     size_t processedSize = headerSize - 1;
     RINOK(SeqInStream_ReadMax(inStream, header + 1, &processedSize))
@@ -58,7 +58,7 @@ SRes XzBlock_ReadHeader(CXzBlock *p, ISeqInStreamPtr inStream, BoolInt *isIndex,
 }
 
 #define ADD_SIZE_CHECK(size, val) \
-  { UInt64 newSize = size + (val); if (newSize < size) return XZ_SIZE_OVERFLOW; size = newSize; }
+  { const UInt64 newSize = size + (val); if (newSize < size) return XZ_SIZE_OVERFLOW; size = newSize; }
 
 UInt64 Xz_GetUnpackSize(const CXzStream *p)
 {

3rdparty/rcheevos/include/rc_api_runtime.h

@@ -220,6 +220,8 @@ typedef struct rc_api_award_achievement_request_t {
   uint32_t hardcore;
   /* The hash associated to the game being played */
   const char* game_hash;
+  /* The number of seconds since the achievement was unlocked */
+  uint32_t seconds_since_unlock;
 }
 rc_api_award_achievement_request_t;
 
@@ -263,6 +265,8 @@ typedef struct rc_api_submit_lboard_entry_request_t {
   int32_t score;
   /* The hash associated to the game being played */
   const char* game_hash;
+  /* The number of seconds since the leaderboard attempt was completed */
+  uint32_t seconds_since_completion;
 }
 rc_api_submit_lboard_entry_request_t;
 

3rdparty/rcheevos/src/rapi/rc_api_runtime.c

@@ -412,6 +412,8 @@ int rc_api_init_award_achievement_request(rc_api_request_t* request, const rc_ap
     rc_url_builder_append_unum_param(&builder, "h", api_params->hardcore ? 1 : 0);
     if (api_params->game_hash && *api_params->game_hash)
       rc_url_builder_append_str_param(&builder, "m", api_params->game_hash);
+    if (api_params->seconds_since_unlock)
+      rc_url_builder_append_unum_param(&builder, "o", api_params->seconds_since_unlock);
 
     /* Evaluate the signature. */
     md5_init(&md5);
@@ -420,6 +422,14 @@ int rc_api_init_award_achievement_request(rc_api_request_t* request, const rc_ap
     md5_append(&md5, (md5_byte_t*)api_params->username, (int)strlen(api_params->username));
     snprintf(buffer, sizeof(buffer), "%d", api_params->hardcore ? 1 : 0);
     md5_append(&md5, (md5_byte_t*)buffer, (int)strlen(buffer));
+    if (api_params->seconds_since_unlock) {
+      /* second achievement id is needed by delegated unlock. including it here allows overloading
+       * the hash generating code on the server */
+      snprintf(buffer, sizeof(buffer), "%u", api_params->achievement_id);
+      md5_append(&md5, (md5_byte_t*)buffer, (int)strlen(buffer));
+      snprintf(buffer, sizeof(buffer), "%u", api_params->seconds_since_unlock);
+      md5_append(&md5, (md5_byte_t*)buffer, (int)strlen(buffer));
+    }
     md5_finish(&md5, digest);
     rc_format_md5(buffer, digest);
     rc_url_builder_append_str_param(&builder, "v", buffer);
@@ -505,6 +515,9 @@ int rc_api_init_submit_lboard_entry_request(rc_api_request_t* request, const rc_
     if (api_params->game_hash && *api_params->game_hash)
       rc_url_builder_append_str_param(&builder, "m", api_params->game_hash);
 
+    if (api_params->seconds_since_completion)
+      rc_url_builder_append_unum_param(&builder, "o", api_params->seconds_since_completion);
+
     /* Evaluate the signature. */
     md5_init(&md5);
     snprintf(buffer, sizeof(buffer), "%u", api_params->leaderboard_id);
@@ -512,6 +525,10 @@ int rc_api_init_submit_lboard_entry_request(rc_api_request_t* request, const rc_
     md5_append(&md5, (md5_byte_t*)api_params->username, (int)strlen(api_params->username));
     snprintf(buffer, sizeof(buffer), "%d", api_params->score);
     md5_append(&md5, (md5_byte_t*)buffer, (int)strlen(buffer));
+    if (api_params->seconds_since_completion) {
+      snprintf(buffer, sizeof(buffer), "%u", api_params->seconds_since_completion);
+      md5_append(&md5, (md5_byte_t*)buffer, (int)strlen(buffer));
+    }
     md5_finish(&md5, digest);
     rc_format_md5(buffer, digest);
     rc_url_builder_append_str_param(&builder, "v", buffer);

3rdparty/rcheevos/src/rc_client.c

@@ -578,13 +578,7 @@ static int rc_client_get_image_url(char buffer[], size_t buffer_size, int image_
   image_request.image_name = image_name;
   result = rc_api_init_fetch_image_request(&request, &image_request);
   if (result == RC_OK)
-  {
-    const size_t url_length = strlen(request.url);
-    if (url_length >= buffer_size)
-      result = RC_INSUFFICIENT_BUFFER;
-    else
-      memcpy(buffer, request.url, url_length + 1);
-  }
+    snprintf(buffer, buffer_size, "%s", request.url);
 
   rc_api_destroy_request(&request);
   return result;
@@ -1440,7 +1434,6 @@ static void rc_client_activate_game(rc_client_load_state_t* load_state, rc_api_s
   rc_mutex_lock(&client->state.mutex);
   load_state->progress = (client->state.load == load_state) ?
       RC_CLIENT_LOAD_GAME_STATE_DONE : RC_CLIENT_LOAD_GAME_STATE_ABORTED;
-  client->state.load = NULL;
   rc_mutex_unlock(&client->state.mutex);
 
   if (load_state->progress != RC_CLIENT_LOAD_GAME_STATE_DONE) {
@@ -1461,17 +1454,15 @@ static void rc_client_activate_game(rc_client_load_state_t* load_state, rc_api_s
           start_session_response->num_unlocks, RC_CLIENT_ACHIEVEMENT_UNLOCKED_SOFTCORE);
     }
 
+    /* make the loaded game active if another game is not aleady being loaded. */
     rc_mutex_lock(&client->state.mutex);
-    if (client->state.load == NULL)
+    if (client->state.load == load_state)
       client->game = load_state->game;
+    else
+      load_state->progress = RC_CLIENT_LOAD_GAME_STATE_ABORTED;
     rc_mutex_unlock(&client->state.mutex);
 
-    if (client->game != load_state->game) {
-      /* previous load state was aborted */
-      if (load_state->callback)
-        load_state->callback(RC_ABORTED, "The requested game is no longer active", client, load_state->callback_userdata);
-    }
-    else {
+    if (load_state->progress != RC_CLIENT_LOAD_GAME_STATE_ABORTED) {
       /* if a change media request is pending, kick it off */
       rc_client_pending_media_t* pending_media;
 
@@ -1481,6 +1472,9 @@ static void rc_client_activate_game(rc_client_load_state_t* load_state, rc_api_s
       rc_mutex_unlock(&load_state->client->state.mutex);
 
       if (pending_media) {
+        /* rc_client_check_pending_media will fail if it can't find the game in client->game or
+         * client->state.load->game. since we've detached the load_state, this has to occur after
+         * we've made the game active. */
         if (pending_media->hash) {
           rc_client_begin_change_media_from_hash(client, pending_media->hash,
             pending_media->callback, pending_media->callback_userdata);
@@ -1494,12 +1488,50 @@ static void rc_client_activate_game(rc_client_load_state_t* load_state, rc_api_s
         rc_client_free_pending_media(pending_media);
       }
 
-      /* client->game must be set before calling this function so it can query the console_id */
+      rc_mutex_lock(&client->state.mutex);
+      if (client->state.load != load_state)
+        load_state->progress = RC_CLIENT_LOAD_GAME_STATE_ABORTED;
+      rc_mutex_unlock(&client->state.mutex);
+    }
+
+    /* if the game is still being loaded, make sure all the required memory addresses are accessible
+     * so we can mark achievements as unsupported before loading them into the runtime. */
+    if (load_state->progress != RC_CLIENT_LOAD_GAME_STATE_ABORTED) {
+      /* TODO: it is desirable to not do memory reads from a background thread. Some emulators (like Dolphin) don't
+       *       allow it. Dolphin's solution is to use a dummy read function that says all addresses are valid and
+       *       switches to the actual read function after the callback is called. latter invalid reads will
+       *       mark achievements as unsupported. */
+
+      /* ASSERT: client->game must be set before calling this function so the read_memory callback can query the console_id */
       rc_client_validate_addresses(load_state->game, client);
 
+      rc_mutex_lock(&client->state.mutex);
+      if (client->state.load != load_state)
+        load_state->progress = RC_CLIENT_LOAD_GAME_STATE_ABORTED;
+      rc_mutex_unlock(&client->state.mutex);
+    }
+
+    /* if the game is still being loaded, load any active acheivements/leaderboards into the runtime */
+    if (load_state->progress != RC_CLIENT_LOAD_GAME_STATE_ABORTED) {
       rc_client_activate_achievements(load_state->game, client);
       rc_client_activate_leaderboards(load_state->game, client);
 
+      /* detach the load state to indicate that loading is fully complete */
+      rc_mutex_lock(&client->state.mutex);
+      if (client->state.load == load_state)
+        client->state.load = NULL;
+      else
+        load_state->progress = RC_CLIENT_LOAD_GAME_STATE_ABORTED;
+      rc_mutex_unlock(&client->state.mutex);
+    }
+
+    /* one last sanity check to make sure the game is still being loaded. */
+    if (load_state->progress == RC_CLIENT_LOAD_GAME_STATE_ABORTED) {
+      /* game has been unloaded, or another game is being loaded over the top of this game */
+      if (load_state->callback)
+        load_state->callback(RC_ABORTED, "The requested game is no longer active", client, load_state->callback_userdata);
+    }
+    else {
       if (load_state->hash->hash[0] != '[') {
         if (load_state->client->state.spectator_mode != RC_CLIENT_SPECTATOR_MODE_LOCKED) {
           /* schedule the periodic ping */
@@ -2007,7 +2039,6 @@ static int rc_client_attach_load_state(rc_client_t* client, rc_client_load_state
 {
   if (client->state.load == NULL) {
     rc_client_unload_game(client);
-    client->state.load = load_state;
 
     if (load_state->game == NULL) {
       load_state->game = rc_client_allocate_game();
@@ -2018,6 +2049,10 @@ static int rc_client_attach_load_state(rc_client_t* client, rc_client_load_state
         return 0;
       }
     }
+
+    rc_mutex_lock(&client->state.mutex);
+    client->state.load = load_state;
+    rc_mutex_unlock(&client->state.mutex);
   }
   else if (client->state.load != load_state) {
     /* previous load was aborted */
@@ -2621,8 +2656,6 @@ static void rc_client_game_mark_ui_to_be_hidden(rc_client_t* client, rc_client_g
 void rc_client_unload_game(rc_client_t* client)
 {
   rc_client_game_info_t* game;
-  rc_client_scheduled_callback_data_t** last;
-  rc_client_scheduled_callback_data_t* next;
 
   if (!client)
     return;
@@ -2649,29 +2682,38 @@ void rc_client_unload_game(rc_client_t* client)
   if (client->state.load) {
     /* this mimics rc_client_abort_async without nesting the lock */
     client->state.load->async_handle.aborted = RC_CLIENT_ASYNC_ABORTED;
+
+    /* if the game is still being loaded, let the load process clean it up */
+    if (client->state.load->game == game)
+      game = NULL;
+
     client->state.load = NULL;
   }
 
   if (client->state.spectator_mode == RC_CLIENT_SPECTATOR_MODE_LOCKED)
     client->state.spectator_mode = RC_CLIENT_SPECTATOR_MODE_ON;
 
-  if (game != NULL)
+  if (game != NULL) {
+    rc_client_scheduled_callback_data_t** last;
+    rc_client_scheduled_callback_data_t* next;
+
     rc_client_game_mark_ui_to_be_hidden(client, game);
 
-  last = &client->state.scheduled_callbacks;
-  do {
-    next = *last;
-    if (!next)
-      break;
+    last = &client->state.scheduled_callbacks;
+    do {
+      next = *last;
+      if (!next)
+        break;
 
-    /* remove rich presence ping scheduled event for game */
-    if (next->callback == rc_client_ping && game && next->related_id == game->public_.id) {
-      *last = next->next;
-      continue;
-    }
+      /* remove rich presence ping scheduled event for game */
+      if (next->callback == rc_client_ping && next->related_id == game->public_.id) {
+        *last = next->next;
+        continue;
+      }
 
-    last = &next->next;
-  } while (1);
+      last = &next->next;
+    } while (1);
+  }
 
   rc_mutex_unlock(&client->state.mutex);
 
@@ -3534,7 +3576,7 @@ typedef struct rc_client_award_achievement_callback_data_t
   uint32_t retry_count;
   uint8_t hardcore;
   const char* game_hash;
-  time_t unlock_time;
+  rc_clock_t unlock_time;
   rc_client_t* client;
   rc_client_scheduled_callback_data_t* scheduled_callback_data;
 } rc_client_award_achievement_callback_data_t;
@@ -3685,6 +3727,11 @@ static void rc_client_award_achievement_server_call(rc_client_award_achievement_
   api_params.hardcore = ach_data->hardcore;
   api_params.game_hash = ach_data->game_hash;
 
+  if (ach_data->retry_count) {
+    const rc_clock_t now = ach_data->client->callbacks.get_time_millisecs(ach_data->client);
+    api_params.seconds_since_unlock = (uint32_t)((now - ach_data->unlock_time) / 1000);
+  }
+
   result = rc_api_init_award_achievement_request(&request, &api_params);
   if (result != RC_OK) {
     RC_CLIENT_LOG_ERR_FORMATTED(ach_data->client, "Error constructing unlock request for achievement %u: %s", ach_data->id, rc_error_str(result));
@@ -3751,7 +3798,8 @@ static void rc_client_award_achievement(rc_client_t* client, rc_client_achieveme
   callback_data->client = client;
   callback_data->id = achievement->public_.id;
   callback_data->hardcore = client->state.hardcore;
-  callback_data->unlock_time = achievement->public_.unlock_time;
+  callback_data->game_hash = client->game->public_.hash;
+  callback_data->unlock_time = client->callbacks.get_time_millisecs(client);
 
   if (client->game) /* may be NULL if this gets called while unloading the game (from another thread - events are raised outside the lock) */
     callback_data->game_hash = client->game->public_.hash;
@@ -4185,7 +4233,7 @@ typedef struct rc_client_submit_leaderboard_entry_callback_data_t
   int32_t score;
   uint32_t retry_count;
   const char* game_hash;
-  time_t submit_time;
+  rc_clock_t submit_time;
   rc_client_t* client;
   rc_client_scheduled_callback_data_t* scheduled_callback_data;
 } rc_client_submit_leaderboard_entry_callback_data_t;
@@ -4340,6 +4388,11 @@ static void rc_client_submit_leaderboard_entry_server_call(rc_client_submit_lead
   api_params.score = lboard_data->score;
   api_params.game_hash = lboard_data->game_hash;
 
+  if (lboard_data->retry_count) {
+    const rc_clock_t now = lboard_data->client->callbacks.get_time_millisecs(lboard_data->client);
+    api_params.seconds_since_completion = (uint32_t)((now - lboard_data->submit_time) / 1000);
+  }
+
   result = rc_api_init_submit_lboard_entry_request(&request, &api_params);
   if (result != RC_OK) {
     RC_CLIENT_LOG_ERR_FORMATTED(lboard_data->client, "Error constructing submit leaderboard entry for leaderboard %u: %s", lboard_data->id, rc_error_str(result));
@@ -4383,7 +4436,7 @@ static void rc_client_submit_leaderboard_entry(rc_client_t* client, rc_client_le
   callback_data->id = leaderboard->public_.id;
   callback_data->score = leaderboard->value;
   callback_data->game_hash = client->game->public_.hash;
-  callback_data->submit_time = time(NULL);
+  callback_data->submit_time = client->callbacks.get_time_millisecs(client);
 
   RC_CLIENT_LOG_INFO_FORMATTED(client, "Submitting %s (%d) for leaderboard %u: %s",
       leaderboard->public_.tracker_value, leaderboard->value, leaderboard->public_.id, leaderboard->public_.title);

3rdparty/rcheevos/src/rc_libretro.c

@@ -36,6 +36,17 @@ typedef struct rc_disallowed_core_settings_t
   const rc_disallowed_setting_t* disallowed_settings;
 } rc_disallowed_core_settings_t;
 
+
+static const rc_disallowed_setting_t _rc_disallowed_beetle_psx_settings[] = {
+  { "beetle_psx_cpu_freq_scale", "<100" },
+  { NULL, NULL }
+};
+
+static const rc_disallowed_setting_t _rc_disallowed_beetle_psx_hw_settings[] = {
+  { "beetle_psx_hw_cpu_freq_scale", "<100" },
+  { NULL, NULL }
+};
+
 static const rc_disallowed_setting_t _rc_disallowed_bsnes_settings[] = {
   { "bsnes_region", "pal" },
   { NULL, NULL }
@@ -80,6 +91,11 @@ static const rc_disallowed_setting_t _rc_disallowed_fceumm_settings[] = {
   { NULL, NULL }
 };
 
+static const rc_disallowed_setting_t _rc_disallowed_flycast_settings[] = {
+  { "reicast_sh4clock", "<200" },
+  { NULL, NULL }
+};
+
 static const rc_disallowed_setting_t _rc_disallowed_gpgx_settings[] = {
   { "genesis_plus_gx_lock_on", ",action replay (pro),game genie" },
   { "genesis_plus_gx_region_detect", "pal" },
@@ -108,6 +124,7 @@ static const rc_disallowed_setting_t _rc_disallowed_neocd_settings[] = {
 };
 
 static const rc_disallowed_setting_t _rc_disallowed_pcsx_rearmed_settings[] = {
+  { "pcsx_rearmed_psxclock", "<55" },
   { "pcsx_rearmed_region", "pal" },
   { NULL, NULL }
 };
@@ -140,6 +157,11 @@ static const rc_disallowed_setting_t _rc_disallowed_snes9x_settings[] = {
   { NULL, NULL }
 };
 
+static const rc_disallowed_setting_t _rc_disallowed_swanstation_settings[] = {
+  { "swanstation_CPU_Overclock", "<100" },
+  { NULL, NULL }
+};
+
 static const rc_disallowed_setting_t _rc_disallowed_vice_settings[] = {
   { "vice_autostart", "disabled" }, /* autostart dictates initial load and reset from menu */
   { "vice_reset", "!autostart" }, /* reset dictates behavior when pressing reset button (END) */
@@ -152,6 +174,8 @@ static const rc_disallowed_setting_t _rc_disallowed_virtual_jaguar_settings[] =
 };
 
 static const rc_disallowed_core_settings_t rc_disallowed_core_settings[] = {
+  { "Beetle PSX", _rc_disallowed_beetle_psx_settings },
+  { "Beetle PSX HW", _rc_disallowed_beetle_psx_hw_settings },
   { "bsnes-mercury", _rc_disallowed_bsnes_settings },
   { "cap32", _rc_disallowed_cap32_settings },
   { "dolphin-emu", _rc_disallowed_dolphin_settings },
@@ -160,6 +184,7 @@ static const rc_disallowed_core_settings_t rc_disallowed_core_settings[] = {
   { "ecwolf", _rc_disallowed_ecwolf_settings },
   { "FCEUmm", _rc_disallowed_fceumm_settings },
   { "FinalBurn Neo", _rc_disallowed_fbneo_settings },
+  { "Flycast", _rc_disallowed_flycast_settings },
   { "Genesis Plus GX", _rc_disallowed_gpgx_settings },
   { "Genesis Plus GX Wide", _rc_disallowed_gpgx_wide_settings },
   { "Mesen", _rc_disallowed_mesen_settings },
@@ -171,6 +196,7 @@ static const rc_disallowed_core_settings_t rc_disallowed_core_settings[] = {
   { "QUASI88", _rc_disallowed_quasi88_settings },
   { "SMS Plus GX", _rc_disallowed_smsplus_settings },
   { "Snes9x", _rc_disallowed_snes9x_settings },
+  { "SwanStation", _rc_disallowed_swanstation_settings },
   { "VICE x64", _rc_disallowed_vice_settings },
   { "Virtual Jaguar", _rc_disallowed_virtual_jaguar_settings },
   { NULL, NULL }
@@ -186,6 +212,12 @@ static int rc_libretro_string_equal_nocase_wildcard(const char* test, const char
   return (*value == '\0');
 }
 
+static int rc_libretro_numeric_less_than(const char* test, const char* value) {
+  int test_num = atoi(test);
+  int value_num = atoi(value);
+  return (test_num < value_num);
+}
+
 static int rc_libretro_match_value(const char* val, const char* match) {
   /* if value starts with a comma, it's a CSV list of potential matches */
   if (*match == ',') {
@@ -218,6 +250,10 @@ static int rc_libretro_match_value(const char* val, const char* match) {
   if (*match == '!')
     return !rc_libretro_match_value(val, &match[1]);
 
+  /* a leading less tahn means the provided value is the minimum allowed */
+  if (*match == '<')
+    return rc_libretro_numeric_less_than(val, &match[1]);
+
   /* just a single value, attempt to match it */
   return rc_libretro_string_equal_nocase_wildcard(val, match);
 }

3rdparty/rcheevos/src/rc_version.h

@@ -8,7 +8,7 @@
 RC_BEGIN_C_DECLS
 
 #define RCHEEVOS_VERSION_MAJOR 11
-#define RCHEEVOS_VERSION_MINOR 5
+#define RCHEEVOS_VERSION_MINOR 6
 #define RCHEEVOS_VERSION_PATCH 0
 
 #define RCHEEVOS_MAKE_VERSION(major, minor, patch) (major * 1000000 + minor * 1000 + patch)

3rdparty/rcheevos/src/rcheevos/consoleinfo.c

@@ -721,16 +721,29 @@ static const rc_memory_regions_t rc_memory_regions_n64 = { _rc_memory_regions_n6
 /* ===== Nintendo DS ===== */
 /* https://www.akkit.org/info/gbatek.htm#dsmemorymaps */
 static const rc_memory_region_t _rc_memory_regions_nintendo_ds[] = {
-    { 0x000000U, 0x3FFFFFU, 0x02000000U, RC_MEMORY_TYPE_SYSTEM_RAM, "System RAM" }
+    { 0x0000000U, 0x03FFFFFU, 0x02000000U, RC_MEMORY_TYPE_SYSTEM_RAM, "System RAM" },
+    /* To keep DS/DSi memory maps aligned, padding is set here for the DSi's extra RAM */
+    { 0x0400000U, 0x0FFFFFFU, 0x02400000U, RC_MEMORY_TYPE_UNUSED, "Unused (DSi exclusive)" },
+    /* The DS/DSi have "tightly coupled memory": very fast memory directly connected to the CPU.
+     * This memory has an instruction variant (ITCM) and a data variant (DTCM).
+     * For achievement purposes it is useful to be able to access the data variant.
+     * This memory does not have a fixed address on console, being able to be moved to any $0xxxx000 region.
+     * While normally this kind of memory is addressed outside of the possible native addressing space, this is simply not possible,
+     * as the DS/DSi's address space covers all possible uint32_t values.
+     * $0E000000 is used here as a "pseudo-end," as this is nearly the end of all the memory actually mapped to addresses
+     * This means that (with the exception of $FFFF0000 onwards, which has the ARM9 BIOS mapped) $0E000000 onwards has nothing mapped to it
+     */
+    { 0x1000000U, 0x1003FFFU, 0x0E000000U, RC_MEMORY_TYPE_SYSTEM_RAM, "Data TCM" }
 };
-static const rc_memory_regions_t rc_memory_regions_nintendo_ds = { _rc_memory_regions_nintendo_ds, 1 };
+static const rc_memory_regions_t rc_memory_regions_nintendo_ds = { _rc_memory_regions_nintendo_ds, 3 };
 
 /* ===== Nintendo DSi ===== */
 /* https://problemkaputt.de/gbatek.htm#dsiiomap */
 static const rc_memory_region_t _rc_memory_regions_nintendo_dsi[] = {
-    { 0x000000U, 0xFFFFFFU, 0x02000000U, RC_MEMORY_TYPE_SYSTEM_RAM, "System RAM" }
+    { 0x0000000U, 0x0FFFFFFU, 0x02000000U, RC_MEMORY_TYPE_SYSTEM_RAM, "System RAM" },
+    { 0x1000000U, 0x1003FFFU, 0x0E000000U, RC_MEMORY_TYPE_SYSTEM_RAM, "Data TCM" }
 };
-static const rc_memory_regions_t rc_memory_regions_nintendo_dsi = { _rc_memory_regions_nintendo_dsi, 1 };
+static const rc_memory_regions_t rc_memory_regions_nintendo_dsi = { _rc_memory_regions_nintendo_dsi, 2 };
 
 /* ===== Oric ===== */
 static const rc_memory_region_t _rc_memory_regions_oric[] = {
@@ -956,6 +969,31 @@ static const rc_memory_region_t _rc_memory_regions_wonderswan[] = {
 };
 static const rc_memory_regions_t rc_memory_regions_wonderswan = { _rc_memory_regions_wonderswan, 2 };
 
+/* ===== ZX Spectrum ===== */
+/* https://github.com/TASEmulators/BizHawk/blob/3a3b22c/src/BizHawk.Emulation.Cores/Computers/SinclairSpectrum/Machine/ZXSpectrum16K/ZX16.cs
+ * https://github.com/TASEmulators/BizHawk/blob/3a3b22c/src/BizHawk.Emulation.Cores/Computers/SinclairSpectrum/Machine/ZXSpectrum48K/ZX48.Memory.cs
+ * https://worldofspectrum.org/faq/reference/128kreference.htm */
+static const rc_memory_region_t _rc_memory_regions_zx_spectrum[] = {
+    /* ZX Spectrum is complicated as multiple models exist with varying amounts of memory.
+     * In practice, this can be reduced to two categories: 16K/48K units, and 128K units.
+     * 16K/48K units have RAM starting at $4000 onwards, 16K ending at $7FFF, 48K ending at $FFFF.
+     * 128K units have banked memory, with $4000-$7FFF normally having RAM bank 5, and $8000-$BFFF normally having RAM bank 2.
+     * $C000-$FFFF is normally reserved for banked RAM, having any of banks 0-7.
+     * For the purposes of the RAM map, $C000-$FFFF is assumed to be bank 0, and $10000 onwards has the other banks in order (1, 3, 4, 6, 7)
+     * Doing it this way always for 16K/48K games to have the same memory map on the 128K, and thus avoid issues due to the model selected.
+     * Later 128K units also have a special banking mode that changes up banking completely, but for 16K/48K compatibility purposes this doesn't matter, and so is irrelevant.
+     */
+    { 0x00000U, 0x03FFFU, 0x04000U, RC_MEMORY_TYPE_SYSTEM_RAM, "Screen RAM" }, /* RAM bank 5 on 128K units */
+    { 0x04000U, 0x07FFFU, 0x08000U, RC_MEMORY_TYPE_SYSTEM_RAM, "System RAM" }, /* RAM bank 2 on 128K units */
+    { 0x08000U, 0x0BFFFU, 0x0C000U, RC_MEMORY_TYPE_SYSTEM_RAM, "System RAM" }, /* RAM bank 0-7 on 128K units, assumed to be bank 0 here */
+    { 0x0C000U, 0x0FFFFU, 0x10000U, RC_MEMORY_TYPE_SYSTEM_RAM, "System RAM" }, /* RAM bank 1 on 128K units */
+    { 0x10000U, 0x13FFFU, 0x14000U, RC_MEMORY_TYPE_SYSTEM_RAM, "System RAM" }, /* RAM bank 3 on 128K units */
+    { 0x14000U, 0x17FFFU, 0x18000U, RC_MEMORY_TYPE_SYSTEM_RAM, "System RAM" }, /* RAM bank 4 on 128K units */
+    { 0x18000U, 0x1BFFFU, 0x1C000U, RC_MEMORY_TYPE_SYSTEM_RAM, "System RAM" }, /* RAM bank 6 on 128K units */
+    { 0x1C000U, 0x1FFFFU, 0x20000U, RC_MEMORY_TYPE_SYSTEM_RAM, "Screen RAM" } /* RAM bank 7 on 128K units */
+};
+static const rc_memory_regions_t rc_memory_regions_zx_spectrum = { _rc_memory_regions_zx_spectrum, 8 };
+
 /* ===== default ===== */
 static const rc_memory_regions_t rc_memory_regions_none = { 0, 0 };
 
@@ -1141,6 +1179,9 @@ const rc_memory_regions_t* rc_console_memory_regions(uint32_t console_id)
     case RC_CONSOLE_WONDERSWAN:
       return &rc_memory_regions_wonderswan;
 
+    case RC_CONSOLE_ZX_SPECTRUM:
+      return &rc_memory_regions_zx_spectrum;
+
     default:
       return &rc_memory_regions_none;
   }

3rdparty/rcheevos/src/rcheevos/lboard.c

@@ -199,19 +199,19 @@ int rc_evaluate_lboard(rc_lboard_t* self, int32_t* value, rc_peek_t peek, void*
           /* start and submit are both true in the same frame, just submit without announcing the leaderboard is available */
           self->state = RC_LBOARD_STATE_TRIGGERED;
         }
-        else if (self->start.requirement == 0 && self->start.alternative == 0) {
-          /* start condition is empty - this leaderboard is submit-only with no measured progress */
+        else if (!self->start.requirement && !self->start.alternative) {
+          /* start trigger is empty. assume the leaderboard is in development and ignore */
         }
         else {
           /* start the leaderboard attempt */
           self->state = RC_LBOARD_STATE_STARTED;
-
-          /* reset any hit counts in the value */
-          if (self->progress)
-            rc_reset_value(self->progress);
-
-          rc_reset_value(&self->value);
         }
+
+        /* reset any hit counts in the value */
+        if (self->progress)
+          rc_reset_value(self->progress);
+
+        rc_reset_value(&self->value);
       }
       break;
 

3rdparty/rcheevos/src/rcheevos/rc_validate.c

@@ -726,6 +726,7 @@ static int rc_validate_conflicting_conditions(const rc_condset_t* conditions, co
   const rc_condition_t* condition;
   const rc_condition_t* condition_chain_start;
   int overlap;
+  int chain_matches;
 
   /* empty group */
   if (conditions == NULL || compare_conditions == NULL)
@@ -777,9 +778,9 @@ static int rc_validate_conflicting_conditions(const rc_condset_t* conditions, co
 
       /* if combining conditions exist, make sure the same combining conditions exist in the
        * compare logic. conflicts can only occur if the combinining conditions match. */
+      chain_matches = 1;
       if (condition_chain_start != condition)
       {
-        int chain_matches = 1;
         const rc_condition_t* condition_chain_iter = condition_chain_start;
         while (condition_chain_iter != condition)
         {
@@ -795,11 +796,8 @@ static int rc_validate_conflicting_conditions(const rc_condset_t* conditions, co
           if (compare_condition->oper != RC_OPERATOR_NONE &&
             !rc_validate_are_operands_equal(&compare_condition->operand2, &condition_chain_iter->operand2))
           {
-            if (compare_condition->operand2.type != condition_chain_iter->operand2.type)
-            {
-              chain_matches = 0;
-              break;
-            }
+            chain_matches = 0;
+            break;
           }
 
           if (!compare_condition->next)
@@ -808,17 +806,27 @@ static int rc_validate_conflicting_conditions(const rc_condset_t* conditions, co
             break;
           }
 
+          if (compare_condition->type != RC_CONDITION_ADD_ADDRESS &&
+              compare_condition->type != RC_CONDITION_ADD_SOURCE &&
+              compare_condition->type != RC_CONDITION_SUB_SOURCE &&
+              compare_condition->type != RC_CONDITION_AND_NEXT)
+          {
+            /* things like AddHits and OrNext are hard to definitively detect conflicts. ignore them. */
+            chain_matches = 0;
+            break;
+          }
+
           compare_condition = compare_condition->next;
           condition_chain_iter = condition_chain_iter->next;
         }
+      }
 
-        /* combining field didn't match, or there's more unmatched combining fields. ignore this condition */
-        if (!chain_matches || rc_validate_is_combining_condition(compare_condition))
-        {
-          while (compare_condition->next && rc_validate_is_combining_condition(compare_condition))
-            compare_condition = compare_condition->next;
-          continue;
-        }
+      /* combining field didn't match, or there's more unmatched combining fields. ignore this condition */
+      if (!chain_matches || rc_validate_is_combining_condition(compare_condition))
+      {
+        while (compare_condition->next && rc_validate_is_combining_condition(compare_condition))
+          compare_condition = compare_condition->next;
+        continue;
       }
 
       if (compare_condition->required_hits)

3rdparty/rcheevos/src/rcheevos/richpresence.c

@@ -360,6 +360,9 @@ static const char* rc_parse_richpresence_lookup(rc_richpresence_lookup_t* lookup
   do
   {
     line = nextline;
+    if (line == NULL)
+      break;
+
     nextline = rc_parse_line(line, &endline, parse);
 
     if (endline - line < 2) {
@@ -438,6 +441,9 @@ static const char* rc_parse_richpresence_lookup(rc_richpresence_lookup_t* lookup
 
       /* insert the current item and continue scanning the next one */
       rc_insert_richpresence_lookup_item(lookup, first, last, label, (int)(endline - label), parse);
+      if (parse->offset < 0)
+        break;
+
       line = endptr + 1;
     } while (line < endline);
 

3rdparty/rcheevos/src/rhash/hash.c

@@ -3113,6 +3113,7 @@ int rc_hash_generate_from_buffer(char hash[33], uint32_t console_id, const uint8
     case RC_CONSOLE_VIRTUAL_BOY:
     case RC_CONSOLE_WASM4:
     case RC_CONSOLE_WONDERSWAN:
+    case RC_CONSOLE_ZX_SPECTRUM:
       return rc_hash_buffer(hash, buffer, buffer_size);
 
     case RC_CONSOLE_ARDUBOY:
@@ -3411,6 +3412,7 @@ int rc_hash_generate_from_file(char hash[33], uint32_t console_id, const char* p
     case RC_CONSOLE_VIRTUAL_BOY:
     case RC_CONSOLE_WASM4:
     case RC_CONSOLE_WONDERSWAN:
+    case RC_CONSOLE_ZX_SPECTRUM:
       /* generic whole-file hash - don't buffer */
       return rc_hash_whole_file(hash, path);
 
@@ -3466,6 +3468,9 @@ int rc_hash_generate_from_file(char hash[33], uint32_t console_id, const char* p
     case RC_CONSOLE_NINTENDO_64:
       return rc_hash_n64(hash, path);
 
+    case RC_CONSOLE_NINTENDO_3DS:
+      return rc_hash_nintendo_3ds(hash, path);
+
     case RC_CONSOLE_NINTENDO_DS:
     case RC_CONSOLE_NINTENDO_DSI:
       return rc_hash_nintendo_ds(hash, path);
@@ -3573,6 +3578,7 @@ static void rc_hash_initialize_dsk_iterator(struct rc_hash_iterator* iterator, c
   /* check MSX first, as Apple II isn't supported by RetroArch, and RAppleWin won't use the iterator */
   rc_hash_iterator_append_console(iterator, RC_CONSOLE_MSX);
   rc_hash_iterator_append_console(iterator, RC_CONSOLE_AMSTRAD_PC);
+  rc_hash_iterator_append_console(iterator, RC_CONSOLE_ZX_SPECTRUM);
   rc_hash_iterator_append_console(iterator, RC_CONSOLE_APPLE_II);
 }
 
@@ -3725,6 +3731,10 @@ void rc_hash_initialize_iterator(struct rc_hash_iterator* iterator, const char*
         {
           iterator->consoles[0] = RC_CONSOLE_NINTENDO_3DS;
         }
+        else if (rc_path_compare_extension(ext, "csw"))
+        {
+          iterator->consoles[0] = RC_CONSOLE_ZX_SPECTRUM;
+        }
         break;
 
       case 'd':
@@ -3808,6 +3818,7 @@ void rc_hash_initialize_iterator(struct rc_hash_iterator* iterator, const char*
           iterator->consoles[1] = RC_CONSOLE_PSP;
           iterator->consoles[2] = RC_CONSOLE_3DO;
           iterator->consoles[3] = RC_CONSOLE_SEGA_CD; /* ASSERT: handles both Sega CD and Saturn */
+          iterator->consoles[4] = RC_CONSOLE_GAMECUBE;
           need_path = 1;
         }
         break;
@@ -3909,6 +3920,10 @@ void rc_hash_initialize_iterator(struct rc_hash_iterator* iterator, const char*
         {
           iterator->consoles[0] = RC_CONSOLE_ELEKTOR_TV_GAMES_COMPUTER;
         }
+        else if (rc_path_compare_extension(ext, "pzx"))
+        {
+          iterator->consoles[0] = RC_CONSOLE_ZX_SPECTRUM;
+        }
         break;
 
       case 'r':
@@ -3947,11 +3962,16 @@ void rc_hash_initialize_iterator(struct rc_hash_iterator* iterator, const char*
         {
           iterator->consoles[0] = RC_CONSOLE_THOMSONTO8; /* disk */
         }
+        else if (rc_path_compare_extension(ext, "scl"))
+        {
+          iterator->consoles[0] = RC_CONSOLE_ZX_SPECTRUM;
+        }
         break;
 
       case 't':
         if (rc_path_compare_extension(ext, "tap"))
         {
+          /* also Commodore 64 and ZX Spectrum, but all are full file hashes */
           iterator->consoles[0] = RC_CONSOLE_ORIC;
         }
         else if (rc_path_compare_extension(ext, "tic"))
@@ -3962,6 +3982,11 @@ void rc_hash_initialize_iterator(struct rc_hash_iterator* iterator, const char*
         {
           iterator->consoles[0] = RC_CONSOLE_ELEKTOR_TV_GAMES_COMPUTER;
         }
+        else if (rc_path_compare_extension(ext, "trd") ||
+                 rc_path_compare_extension(ext, "tzx"))
+        {
+          iterator->consoles[0] = RC_CONSOLE_ZX_SPECTRUM;
+        }
         break;
 
       case 'u':

3rdparty/vulkan/include/vk_video/vulkan_video_codec_av1std.h

@@ -132,7 +132,7 @@ typedef enum StdVideoAV1FrameRestorationType {
 
 typedef enum StdVideoAV1ColorPrimaries {
     STD_VIDEO_AV1_COLOR_PRIMARIES_BT_709 = 1,
-    STD_VIDEO_AV1_COLOR_PRIMARIES_BT_UNSPECIFIED = 2,
+    STD_VIDEO_AV1_COLOR_PRIMARIES_UNSPECIFIED = 2,
     STD_VIDEO_AV1_COLOR_PRIMARIES_BT_470_M = 4,
     STD_VIDEO_AV1_COLOR_PRIMARIES_BT_470_B_G = 5,
     STD_VIDEO_AV1_COLOR_PRIMARIES_BT_601 = 6,
@@ -144,6 +144,8 @@ typedef enum StdVideoAV1ColorPrimaries {
     STD_VIDEO_AV1_COLOR_PRIMARIES_SMPTE_432 = 12,
     STD_VIDEO_AV1_COLOR_PRIMARIES_EBU_3213 = 22,
     STD_VIDEO_AV1_COLOR_PRIMARIES_INVALID = 0x7FFFFFFF,
+  // STD_VIDEO_AV1_COLOR_PRIMARIES_BT_UNSPECIFIED is a deprecated alias
+    STD_VIDEO_AV1_COLOR_PRIMARIES_BT_UNSPECIFIED = STD_VIDEO_AV1_COLOR_PRIMARIES_UNSPECIFIED,
     STD_VIDEO_AV1_COLOR_PRIMARIES_MAX_ENUM = 0x7FFFFFFF
 } StdVideoAV1ColorPrimaries;
 

3rdparty/vulkan/include/vk_video/vulkan_video_codec_av1std_encode.h

@@ -0,0 +1,143 @@
+#ifndef VULKAN_VIDEO_CODEC_AV1STD_ENCODE_H_
+#define VULKAN_VIDEO_CODEC_AV1STD_ENCODE_H_ 1
+
+/*
+** Copyright 2015-2024 The Khronos Group Inc.
+**
+** SPDX-License-Identifier: Apache-2.0
+*/
+
+/*
+** This header is generated from the Khronos Vulkan XML API Registry.
+**
+*/
+
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+
+
+// vulkan_video_codec_av1std_encode is a preprocessor guard. Do not pass it to API calls.
+#define vulkan_video_codec_av1std_encode 1
+#include "vulkan_video_codec_av1std.h"
+
+#define VK_STD_VULKAN_VIDEO_CODEC_AV1_ENCODE_API_VERSION_1_0_0 VK_MAKE_VIDEO_STD_VERSION(1, 0, 0)
+
+#define VK_STD_VULKAN_VIDEO_CODEC_AV1_ENCODE_SPEC_VERSION VK_STD_VULKAN_VIDEO_CODEC_AV1_ENCODE_API_VERSION_1_0_0
+#define VK_STD_VULKAN_VIDEO_CODEC_AV1_ENCODE_EXTENSION_NAME "VK_STD_vulkan_video_codec_av1_encode"
+typedef struct StdVideoEncodeAV1DecoderModelInfo {
+    uint8_t     buffer_delay_length_minus_1;
+    uint8_t     buffer_removal_time_length_minus_1;
+    uint8_t     frame_presentation_time_length_minus_1;
+    uint8_t     reserved1;
+    uint32_t    num_units_in_decoding_tick;
+} StdVideoEncodeAV1DecoderModelInfo;
+
+typedef struct StdVideoEncodeAV1ExtensionHeader {
+    uint8_t    temporal_id;
+    uint8_t    spatial_id;
+} StdVideoEncodeAV1ExtensionHeader;
+
+typedef struct StdVideoEncodeAV1OperatingPointInfoFlags {
+    uint32_t    decoder_model_present_for_this_op : 1;
+    uint32_t    low_delay_mode_flag : 1;
+    uint32_t    initial_display_delay_present_for_this_op : 1;
+    uint32_t    reserved : 29;
+} StdVideoEncodeAV1OperatingPointInfoFlags;
+
+typedef struct StdVideoEncodeAV1OperatingPointInfo {
+    StdVideoEncodeAV1OperatingPointInfoFlags    flags;
+    uint16_t                                    operating_point_idc;
+    uint8_t                                     seq_level_idx;
+    uint8_t                                     seq_tier;
+    uint32_t                                    decoder_buffer_delay;
+    uint32_t                                    encoder_buffer_delay;
+    uint8_t                                     initial_display_delay_minus_1;
+} StdVideoEncodeAV1OperatingPointInfo;
+
+typedef struct StdVideoEncodeAV1PictureInfoFlags {
+    uint32_t    error_resilient_mode : 1;
+    uint32_t    disable_cdf_update : 1;
+    uint32_t    use_superres : 1;
+    uint32_t    render_and_frame_size_different : 1;
+    uint32_t    allow_screen_content_tools : 1;
+    uint32_t    is_filter_switchable : 1;
+    uint32_t    force_integer_mv : 1;
+    uint32_t    frame_size_override_flag : 1;
+    uint32_t    buffer_removal_time_present_flag : 1;
+    uint32_t    allow_intrabc : 1;
+    uint32_t    frame_refs_short_signaling : 1;
+    uint32_t    allow_high_precision_mv : 1;
+    uint32_t    is_motion_mode_switchable : 1;
+    uint32_t    use_ref_frame_mvs : 1;
+    uint32_t    disable_frame_end_update_cdf : 1;
+    uint32_t    allow_warped_motion : 1;
+    uint32_t    reduced_tx_set : 1;
+    uint32_t    skip_mode_present : 1;
+    uint32_t    delta_q_present : 1;
+    uint32_t    delta_lf_present : 1;
+    uint32_t    delta_lf_multi : 1;
+    uint32_t    segmentation_enabled : 1;
+    uint32_t    segmentation_update_map : 1;
+    uint32_t    segmentation_temporal_update : 1;
+    uint32_t    segmentation_update_data : 1;
+    uint32_t    UsesLr : 1;
+    uint32_t    usesChromaLr : 1;
+    uint32_t    show_frame : 1;
+    uint32_t    showable_frame : 1;
+    uint32_t    reserved : 3;
+} StdVideoEncodeAV1PictureInfoFlags;
+
+typedef struct StdVideoEncodeAV1PictureInfo {
+    StdVideoEncodeAV1PictureInfoFlags          flags;
+    StdVideoAV1FrameType                       frame_type;
+    uint32_t                                   frame_presentation_time;
+    uint32_t                                   current_frame_id;
+    uint8_t                                    order_hint;
+    uint8_t                                    primary_ref_frame;
+    uint8_t                                    refresh_frame_flags;
+    uint8_t                                    coded_denom;
+    uint16_t                                   render_width_minus_1;
+    uint16_t                                   render_height_minus_1;
+    StdVideoAV1InterpolationFilter             interpolation_filter;
+    StdVideoAV1TxMode                          TxMode;
+    uint8_t                                    delta_q_res;
+    uint8_t                                    delta_lf_res;
+    uint8_t                                    ref_order_hint[STD_VIDEO_AV1_NUM_REF_FRAMES];
+    int8_t                                     ref_frame_idx[STD_VIDEO_AV1_REFS_PER_FRAME];
+    uint8_t                                    reserved1[3];
+    uint32_t                                   delta_frame_id_minus_1[STD_VIDEO_AV1_REFS_PER_FRAME];
+    const StdVideoAV1TileInfo*                 pTileInfo;
+    const StdVideoAV1Quantization*             pQuantization;
+    const StdVideoAV1Segmentation*             pSegmentation;
+    const StdVideoAV1LoopFilter*               pLoopFilter;
+    const StdVideoAV1CDEF*                     pCDEF;
+    const StdVideoAV1LoopRestoration*          pLoopRestoration;
+    const StdVideoAV1GlobalMotion*             pGlobalMotion;
+    const StdVideoEncodeAV1ExtensionHeader*    pExtensionHeader;
+    const uint32_t*                            pBufferRemovalTimes;
+} StdVideoEncodeAV1PictureInfo;
+
+typedef struct StdVideoEncodeAV1ReferenceInfoFlags {
+    uint32_t    disable_frame_end_update_cdf : 1;
+    uint32_t    segmentation_enabled : 1;
+    uint32_t    reserved : 30;
+} StdVideoEncodeAV1ReferenceInfoFlags;
+
+typedef struct StdVideoEncodeAV1ReferenceInfo {
+    StdVideoEncodeAV1ReferenceInfoFlags        flags;
+    uint32_t                                   RefFrameId;
+    StdVideoAV1FrameType                       frame_type;
+    uint8_t                                    OrderHint;
+    uint8_t                                    reserved1[3];
+    const StdVideoEncodeAV1ExtensionHeader*    pExtensionHeader;
+} StdVideoEncodeAV1ReferenceInfo;
+
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif

3rdparty/vulkan/include/vulkan/vulkan_beta.h

@@ -53,13 +53,14 @@ typedef struct VkPhysicalDevicePortabilitySubsetPropertiesKHR {
 
 // VK_AMDX_shader_enqueue is a preprocessor guard. Do not pass it to API calls.
 #define VK_AMDX_shader_enqueue 1
-#define VK_AMDX_SHADER_ENQUEUE_SPEC_VERSION 1
+#define VK_AMDX_SHADER_ENQUEUE_SPEC_VERSION 2
 #define VK_AMDX_SHADER_ENQUEUE_EXTENSION_NAME "VK_AMDX_shader_enqueue"
 #define VK_SHADER_INDEX_UNUSED_AMDX       (~0U)
 typedef struct VkPhysicalDeviceShaderEnqueueFeaturesAMDX {
     VkStructureType    sType;
     void*              pNext;
     VkBool32           shaderEnqueue;
+    VkBool32           shaderMeshEnqueue;
 } VkPhysicalDeviceShaderEnqueueFeaturesAMDX;
 
 typedef struct VkPhysicalDeviceShaderEnqueuePropertiesAMDX {
@@ -70,12 +71,16 @@ typedef struct VkPhysicalDeviceShaderEnqueuePropertiesAMDX {
     uint32_t           maxExecutionGraphShaderPayloadSize;
     uint32_t           maxExecutionGraphShaderPayloadCount;
     uint32_t           executionGraphDispatchAddressAlignment;
+    uint32_t           maxExecutionGraphWorkgroupCount[3];
+    uint32_t           maxExecutionGraphWorkgroups;
 } VkPhysicalDeviceShaderEnqueuePropertiesAMDX;
 
 typedef struct VkExecutionGraphPipelineScratchSizeAMDX {
     VkStructureType    sType;
     void*              pNext;
-    VkDeviceSize       size;
+    VkDeviceSize       minSize;
+    VkDeviceSize       maxSize;
+    VkDeviceSize       sizeGranularity;
 } VkExecutionGraphPipelineScratchSizeAMDX;
 
 typedef struct VkExecutionGraphPipelineCreateInfoAMDX {
@@ -116,12 +121,12 @@ typedef struct VkPipelineShaderStageNodeCreateInfoAMDX {
 } VkPipelineShaderStageNodeCreateInfoAMDX;
 
 typedef VkResult (VKAPI_PTR *PFN_vkCreateExecutionGraphPipelinesAMDX)(VkDevice                                        device, VkPipelineCache                 pipelineCache, uint32_t                                        createInfoCount, const VkExecutionGraphPipelineCreateInfoAMDX* pCreateInfos, const VkAllocationCallbacks*    pAllocator, VkPipeline*               pPipelines);
-typedef VkResult (VKAPI_PTR *PFN_vkGetExecutionGraphPipelineScratchSizeAMDX)(VkDevice                                        device, VkPipeline                                      executionGraph, VkExecutionGraphPipelineScratchSizeAMDX*         pSizeInfo);
-typedef VkResult (VKAPI_PTR *PFN_vkGetExecutionGraphPipelineNodeIndexAMDX)(VkDevice                                        device, VkPipeline                                      executionGraph, const VkPipelineShaderStageNodeCreateInfoAMDX*   pNodeInfo, uint32_t*                                       pNodeIndex);
-typedef void (VKAPI_PTR *PFN_vkCmdInitializeGraphScratchMemoryAMDX)(VkCommandBuffer                                 commandBuffer, VkDeviceAddress                                 scratch);
-typedef void (VKAPI_PTR *PFN_vkCmdDispatchGraphAMDX)(VkCommandBuffer                                 commandBuffer, VkDeviceAddress                                 scratch, const VkDispatchGraphCountInfoAMDX*              pCountInfo);
-typedef void (VKAPI_PTR *PFN_vkCmdDispatchGraphIndirectAMDX)(VkCommandBuffer                                 commandBuffer, VkDeviceAddress                                 scratch, const VkDispatchGraphCountInfoAMDX*              pCountInfo);
-typedef void (VKAPI_PTR *PFN_vkCmdDispatchGraphIndirectCountAMDX)(VkCommandBuffer                                 commandBuffer, VkDeviceAddress                                 scratch, VkDeviceAddress                                 countInfo);
+typedef VkResult (VKAPI_PTR *PFN_vkGetExecutionGraphPipelineScratchSizeAMDX)(VkDevice                                        device, VkPipeline                                      executionGraph, VkExecutionGraphPipelineScratchSizeAMDX*        pSizeInfo);
+typedef VkResult (VKAPI_PTR *PFN_vkGetExecutionGraphPipelineNodeIndexAMDX)(VkDevice                                        device, VkPipeline                                      executionGraph, const VkPipelineShaderStageNodeCreateInfoAMDX*  pNodeInfo, uint32_t*                                       pNodeIndex);
+typedef void (VKAPI_PTR *PFN_vkCmdInitializeGraphScratchMemoryAMDX)(VkCommandBuffer                                 commandBuffer, VkPipeline                                      executionGraph, VkDeviceAddress                                 scratch, VkDeviceSize                                    scratchSize);
+typedef void (VKAPI_PTR *PFN_vkCmdDispatchGraphAMDX)(VkCommandBuffer                                 commandBuffer, VkDeviceAddress                                 scratch, VkDeviceSize                                    scratchSize, const VkDispatchGraphCountInfoAMDX*             pCountInfo);
+typedef void (VKAPI_PTR *PFN_vkCmdDispatchGraphIndirectAMDX)(VkCommandBuffer                                 commandBuffer, VkDeviceAddress                                 scratch, VkDeviceSize                                    scratchSize, const VkDispatchGraphCountInfoAMDX*             pCountInfo);
+typedef void (VKAPI_PTR *PFN_vkCmdDispatchGraphIndirectCountAMDX)(VkCommandBuffer                                 commandBuffer, VkDeviceAddress                                 scratch, VkDeviceSize                                    scratchSize, VkDeviceAddress                                 countInfo);
 
 #ifndef VK_NO_PROTOTYPES
 VKAPI_ATTR VkResult VKAPI_CALL vkCreateExecutionGraphPipelinesAMDX(
@@ -145,21 +150,26 @@ VKAPI_ATTR VkResult VKAPI_CALL vkGetExecutionGraphPipelineNodeIndexAMDX(
 
 VKAPI_ATTR void VKAPI_CALL vkCmdInitializeGraphScratchMemoryAMDX(
     VkCommandBuffer                             commandBuffer,
-    VkDeviceAddress                             scratch);
+    VkPipeline                                  executionGraph,
+    VkDeviceAddress                             scratch,
+    VkDeviceSize                                scratchSize);
 
 VKAPI_ATTR void VKAPI_CALL vkCmdDispatchGraphAMDX(
     VkCommandBuffer                             commandBuffer,
     VkDeviceAddress                             scratch,
+    VkDeviceSize                                scratchSize,
     const VkDispatchGraphCountInfoAMDX*         pCountInfo);
 
 VKAPI_ATTR void VKAPI_CALL vkCmdDispatchGraphIndirectAMDX(
     VkCommandBuffer                             commandBuffer,
     VkDeviceAddress                             scratch,
+    VkDeviceSize                                scratchSize,
     const VkDispatchGraphCountInfoAMDX*         pCountInfo);
 
 VKAPI_ATTR void VKAPI_CALL vkCmdDispatchGraphIndirectCountAMDX(
     VkCommandBuffer                             commandBuffer,
     VkDeviceAddress                             scratch,
+    VkDeviceSize                                scratchSize,
     VkDeviceAddress                             countInfo);
 #endif