Windows: Update LZMA SDK to version 24.09

2025-11-11 11:08:02 -06:00 · 2025-01-01 10:37:18 +01:00
parent 4e85009f57
commit fcc6302e61
16 changed files with 967 additions and 247 deletions
--- a/src/Common/lzma/7zTypes.h
+++ b/src/Common/lzma/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)
--- a/src/Common/lzma/Alloc.c
+++ b/src/Common/lzma/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
  
  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 */
@@ -434,7 +447,6 @@ static void *SzAlignedAlloc(ISzAllocPtr pp, size_t size)
 #else

  void *p;
-  UNUSED_VAR(pp)
  if (posix_memalign(&p, ALLOC_ALIGN_SIZE, size))
    return NULL;

@@ -447,6 +459,24 @@ static void *SzAlignedAlloc(ISzAllocPtr pp, size_t size)
 }


+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)
@@ -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 *) */
+#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]
-/*
-#define REAL_BLOCK_PTR_VAR(p) ((void **)(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
 }


--- a/src/Common/lzma/Alloc.h
+++ b/src/Common/lzma/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

--- a/src/Common/lzma/Compiler.h
+++ b/src/Common/lzma/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;
--- a/src/Common/lzma/CpuArch.c
+++ b/src/Common/lzma/CpuArch.c
@@ -1,5 +1,5 @@
 /* CpuArch.c -- CPU specific code
-2023-05-18 : Igor Pavlov : Public domain */
+Igor Pavlov : Public domain */

 #include "Precomp.h"

@@ -17,7 +17,7 @@
 /*
  cpuid instruction supports (subFunction) parameter in ECX,
  that is used only with some specific (function) parameter values.
-  But we always use only (subFunction==0).
+  most functions use only (subFunction==0).
 */
 /*
  __cpuid(): MSVC and GCC/CLANG use same function/macro name
@@ -49,43 +49,49 @@
 #if defined(MY_CPU_AMD64) && defined(__PIC__) \
    && ((defined (__GNUC__) && (__GNUC__ < 5)) || defined(__clang__))

-#define x86_cpuid_MACRO(p, func) { \
+  /* "=&r" selects free register. It can select even rbx, if that register is free.
+     "=&D" for (RDI) also works, but the code can be larger with "=&D"
+     "2"(subFun) : 2 is (zero-based) index in the output constraint list "=c" (ECX). */
+
+#define x86_cpuid_MACRO_2(p, func, subFunc) { \
  __asm__ __volatile__ ( \
    ASM_LN   "mov     %%rbx, %q1"  \
    ASM_LN   "cpuid"               \
    ASM_LN   "xchg    %%rbx, %q1"  \
-    : "=a" ((p)[0]), "=&r" ((p)[1]), "=c" ((p)[2]), "=d" ((p)[3]) : "0" (func), "2"(0)); }
-
-  /* "=&r" selects free register. It can select even rbx, if that register is free.
-     "=&D" for (RDI) also works, but the code can be larger with "=&D"
-     "2"(0) means (subFunction = 0),
-     2 is (zero-based) index in the output constraint list "=c" (ECX). */
+    : "=a" ((p)[0]), "=&r" ((p)[1]), "=c" ((p)[2]), "=d" ((p)[3]) : "0" (func), "2"(subFunc)); }

 #elif defined(MY_CPU_X86) && defined(__PIC__) \
    && ((defined (__GNUC__) && (__GNUC__ < 5)) || defined(__clang__))

-#define x86_cpuid_MACRO(p, func) { \
+#define x86_cpuid_MACRO_2(p, func, subFunc) { \
  __asm__ __volatile__ ( \
    ASM_LN   "mov     %%ebx, %k1"  \
    ASM_LN   "cpuid"               \
    ASM_LN   "xchg    %%ebx, %k1"  \
-    : "=a" ((p)[0]), "=&r" ((p)[1]), "=c" ((p)[2]), "=d" ((p)[3]) : "0" (func), "2"(0)); }
+    : "=a" ((p)[0]), "=&r" ((p)[1]), "=c" ((p)[2]), "=d" ((p)[3]) : "0" (func), "2"(subFunc)); }

 #else

-#define x86_cpuid_MACRO(p, func) { \
+#define x86_cpuid_MACRO_2(p, func, subFunc) { \
  __asm__ __volatile__ ( \
    ASM_LN   "cpuid"               \
-    : "=a" ((p)[0]), "=b" ((p)[1]), "=c" ((p)[2]), "=d" ((p)[3]) : "0" (func), "2"(0)); }
+    : "=a" ((p)[0]), "=b" ((p)[1]), "=c" ((p)[2]), "=d" ((p)[3]) : "0" (func), "2"(subFunc)); }

 #endif

+#define x86_cpuid_MACRO(p, func)  x86_cpuid_MACRO_2(p, func, 0)

 void Z7_FASTCALL z7_x86_cpuid(UInt32 p[4], UInt32 func)
 {
  x86_cpuid_MACRO(p, func)
 }

+static
+void Z7_FASTCALL z7_x86_cpuid_subFunc(UInt32 p[4], UInt32 func, UInt32 subFunc)
+{
+  x86_cpuid_MACRO_2(p, func, subFunc)
+}
+

 Z7_NO_INLINE
 UInt32 Z7_FASTCALL z7_x86_cpuid_GetMaxFunc(void)
@@ -205,11 +211,39 @@ void __declspec(naked) Z7_FASTCALL z7_x86_cpuid(UInt32 p[4], UInt32 func)
  __asm   ret     0
 }

+static
+void __declspec(naked) Z7_FASTCALL z7_x86_cpuid_subFunc(UInt32 p[4], UInt32 func, UInt32 subFunc)
+{
+  UNUSED_VAR(p)
+  UNUSED_VAR(func)
+  UNUSED_VAR(subFunc)
+  __asm   push    ebx
+  __asm   push    edi
+  __asm   mov     edi, ecx    // p
+  __asm   mov     eax, edx    // func
+  __asm   mov     ecx, [esp + 12]  // subFunc
+  __asm   cpuid
+  __asm   mov     [edi     ], eax
+  __asm   mov     [edi +  4], ebx
+  __asm   mov     [edi +  8], ecx
+  __asm   mov     [edi + 12], edx
+  __asm   pop     edi
+  __asm   pop     ebx
+  __asm   ret     4
+}
+
 #else // MY_CPU_AMD64

    #if _MSC_VER >= 1600
      #include <intrin.h>
      #define MY_cpuidex  __cpuidex
+
+static
+void Z7_FASTCALL z7_x86_cpuid_subFunc(UInt32 p[4], UInt32 func, UInt32 subFunc)
+{
+  __cpuidex((int *)p, func, subFunc);
+}
+
    #else
 /*
 __cpuid (func == (0 or 7)) requires subfunction number in ECX.
@@ -219,20 +253,25 @@ void __declspec(naked) Z7_FASTCALL z7_x86_cpuid(UInt32 p[4], UInt32 func)
 We still can use __cpuid for low (func) values that don't require ECX,
 but __cpuid() in old MSVC will be incorrect for some func values: (func == 7).
 So here we use the hack for old MSVC to send (subFunction) in ECX register to cpuid instruction,
- where ECX value is first parameter for FASTCALL / NO_INLINE func,
+ where ECX value is first parameter for FASTCALL / NO_INLINE func.
 So the caller of MY_cpuidex_HACK() sets ECX as subFunction, and
 old MSVC for __cpuid() doesn't change ECX and cpuid instruction gets (subFunction) value.
 
 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);
 }
      #define MY_cpuidex(info, func, func2)  MY_cpuidex_HACK(func2, func, info)
      #pragma message("======== MY_cpuidex_HACK WAS USED ========")
+static
+void Z7_FASTCALL z7_x86_cpuid_subFunc(UInt32 p[4], UInt32 func, UInt32 subFunc)
+{
+  MY_cpuidex_HACK(subFunc, func, (Int32 *)p);
+}
    #endif // _MSC_VER >= 1600

 #if !defined(MY_CPU_AMD64)
@@ -242,13 +281,13 @@ 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 +423,7 @@ 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 +432,7 @@ 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 +441,7 @@ 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 +458,17 @@ 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 +480,24 @@ BoolInt CPU_IsSupported_SHA(void)
  {
    UInt32 d[4];
    z7_x86_cpuid(d, 7);
-    return (d[1] >> 29) & 1;
+    return (BoolInt)(d[1] >> 29) & 1;
+  }
+}
+
+
+BoolInt CPU_IsSupported_SHA512(void)
+{
+  if (!CPU_IsSupported_AVX2()) return False; // maybe CPU_IsSupported_AVX() is enough here
+
+  if (z7_x86_cpuid_GetMaxFunc() < 7)
+    return False;
+  {
+    UInt32 d[4];
+    z7_x86_cpuid_subFunc(d, 7, 0);
+    if (d[0] < 1) // d[0] - is max supported subleaf value
+      return False;
+    z7_x86_cpuid_subFunc(d, 7, 1);
+    return (BoolInt)(d[0]) & 1;
  }
 }

@@ -638,10 +694,10 @@ 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 +714,39 @@ 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 +758,9 @@ 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 +773,7 @@ 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;
  }
 }

@@ -747,6 +832,18 @@ BoolInt CPU_IsSupported_NEON(void)
  return z7_sysctlbyname_Get_BoolInt("hw.optional.neon");
 }

+BoolInt CPU_IsSupported_SHA512(void)
+{
+  return z7_sysctlbyname_Get_BoolInt("hw.optional.armv8_2_sha512");
+}
+
+/*
+BoolInt CPU_IsSupported_SHA3(void)
+{
+  return z7_sysctlbyname_Get_BoolInt("hw.optional.armv8_2_sha3");
+}
+*/
+
 #ifdef MY_CPU_ARM64
 #define APPLE_CRYPTO_SUPPORT_VAL 1
 #else
@@ -760,33 +857,70 @@ 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

@@ -794,6 +928,19 @@ MY_HWCAP_CHECK_FUNC (CRC32)
 MY_HWCAP_CHECK_FUNC (SHA1)
 MY_HWCAP_CHECK_FUNC (SHA2)
 MY_HWCAP_CHECK_FUNC (AES)
+#ifdef MY_CPU_ARM64
+// <hwcap.h> supports HWCAP_SHA512 and HWCAP_SHA3 since 2017.
+// we define them here, if they are not defined
+#ifndef HWCAP_SHA3
+// #define HWCAP_SHA3    (1 << 17)
+#endif
+#ifndef HWCAP_SHA512
+// #pragma message("=== HWCAP_SHA512 define === ")
+#define HWCAP_SHA512  (1 << 21)
+#endif
+MY_HWCAP_CHECK_FUNC (SHA512)
+// MY_HWCAP_CHECK_FUNC (SHA3)
+#endif

 #endif // __APPLE__
 #endif // _WIN32
--- a/src/Common/lzma/CpuArch.h
+++ b/src/Common/lzma/CpuArch.h
@@ -1,5 +1,5 @@
 /* CpuArch.h -- CPU specific code
-2023-04-02 : Igor Pavlov : Public domain */
+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) \
@@ -47,15 +49,24 @@ 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
+#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
  #define MY_CPU_64BIT
@@ -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)
@@ -295,8 +369,18 @@ 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)
@@ -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

@@ -390,11 +509,19 @@ MY_CPU_64BIT means that processor can work with 64-bit registers.

 #if defined(MY_CPU_LE_UNALIGN) && defined(Z7_CPU_FAST_BSWAP_SUPPORTED)

+#if 0
+// Z7_BSWAP16 can be slow for x86-msvc
+#define GetBe16_to32(p)  (Z7_BSWAP16 (*(const UInt16 *)(const void *)(p)))
+#else
+#define GetBe16_to32(p)  (Z7_BSWAP32 (*(const UInt16 *)(const void *)(p)) >> 16)
+#endif
+
 #define GetBe32(p)  Z7_BSWAP32 (*(const UInt32 *)(const void *)(p))
 #define SetBe32(p, v) { (*(UInt32 *)(void *)(p)) = Z7_BSWAP32(v); }

 #if defined(MY_CPU_LE_UNALIGN_64)
 #define GetBe64(p)  Z7_BSWAP64 (*(const UInt64 *)(const void *)(p))
+#define SetBe64(p, v) { (*(UInt64 *)(void *)(p)) = Z7_BSWAP64(v); }
 #endif

 #else
@@ -417,11 +544,27 @@ MY_CPU_64BIT means that processor can work with 64-bit registers.
 #define GetBe64(p) (((UInt64)GetBe32(p) << 32) | GetBe32(((const Byte *)(p)) + 4))
 #endif

+#ifndef SetBe64
+#define SetBe64(p, v) { Byte *_ppp_ = (Byte *)(p); UInt64 _vvv_ = (v); \
+    _ppp_[0] = (Byte)(_vvv_ >> 56); \
+    _ppp_[1] = (Byte)(_vvv_ >> 48); \
+    _ppp_[2] = (Byte)(_vvv_ >> 40); \
+    _ppp_[3] = (Byte)(_vvv_ >> 32); \
+    _ppp_[4] = (Byte)(_vvv_ >> 24); \
+    _ppp_[5] = (Byte)(_vvv_ >> 16); \
+    _ppp_[6] = (Byte)(_vvv_ >> 8); \
+    _ppp_[7] = (Byte)_vvv_; }
+#endif
+
 #ifndef GetBe16
+#ifdef GetBe16_to32
+#define GetBe16(p) ( (UInt16) GetBe16_to32(p))
+#else
 #define GetBe16(p) ( (UInt16) ( \
    ((UInt16)((const Byte *)(p))[0] << 8) | \
             ((const Byte *)(p))[1] ))
 #endif
+#endif


 #if defined(MY_CPU_BE)
@@ -439,11 +582,13 @@ 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 +596,13 @@ 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)
@@ -466,6 +613,11 @@ MY_CPU_64BIT means that processor can work with 64-bit registers.
 #endif


+#ifndef GetBe16_to32
+#define GetBe16_to32(p) GetBe16(p)
+#endif
+
+
 #if defined(MY_CPU_X86_OR_AMD64) \
  || defined(MY_CPU_ARM_OR_ARM64) \
  || defined(MY_CPU_PPC_OR_PPC64)
@@ -486,6 +638,7 @@ 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);
@@ -493,6 +646,7 @@ BoolInt CPU_IsSupported_SSE2(void);
 BoolInt CPU_IsSupported_SSSE3(void);
 BoolInt CPU_IsSupported_SSE41(void);
 BoolInt CPU_IsSupported_SHA(void);
+BoolInt CPU_IsSupported_SHA512(void);
 BoolInt CPU_IsSupported_PageGB(void);

 #elif defined(MY_CPU_ARM_OR_ARM64)
@@ -510,6 +664,7 @@ BoolInt CPU_IsSupported_SHA1(void);
 BoolInt CPU_IsSupported_SHA2(void);
 BoolInt CPU_IsSupported_AES(void);
 #endif
+BoolInt CPU_IsSupported_SHA512(void);

 #endif

--- a/src/Common/lzma/LzFind.c
+++ b/src/Common/lzma/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(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;
  }
 }

--- a/src/Common/lzma/LzFind.h
+++ b/src/Common/lzma/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);
--- a/src/Common/lzma/LzFindMt.c
+++ b/src/Common/lzma/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;
  }
 }
--- a/src/Common/lzma/LzFindMt.h
+++ b/src/Common/lzma/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;
--- a/src/Common/lzma/LzmaEnc.c
+++ b/src/Common/lzma/LzmaEnc.c
@@ -1,5 +1,5 @@
 /* LzmaEnc.c -- LZMA Encoder
-2023-04-13: Igor Pavlov : Public domain */
+Igor Pavlov : Public domain */

 #include "Precomp.h"

@@ -72,11 +72,11 @@ void LzmaEncProps_Normalize(CLzmaEncProps *p)
  p->level = level;
  
  if (p->dictSize == 0)
-    p->dictSize =
-      ( level <= 3 ? ((UInt32)1 << (level * 2 + 16)) :
-      ( level <= 6 ? ((UInt32)1 << (level + 19)) :
-      ( level <= 7 ? ((UInt32)1 << 25) : ((UInt32)1 << 26)
-      )));
+    p->dictSize = (unsigned)level <= 4 ?
+        (UInt32)1 << (level * 2 + 16) :
+        (unsigned)level <= sizeof(size_t) / 2 + 4 ?
+          (UInt32)1 << (level + 20) :
+          (UInt32)1 << (sizeof(size_t) / 2 + 24);

  if (p->dictSize > p->reduceSize)
  {
@@ -92,8 +92,8 @@ void LzmaEncProps_Normalize(CLzmaEncProps *p)
  if (p->lp < 0) p->lp = 0;
  if (p->pb < 0) p->pb = 2;

-  if (p->algo < 0) p->algo = (level < 5 ? 0 : 1);
-  if (p->fb < 0) p->fb = (level < 7 ? 32 : 64);
+  if (p->algo < 0) p->algo = (unsigned)level < 5 ? 0 : 1;
+  if (p->fb < 0) p->fb = (unsigned)level < 7 ? 32 : 64;
  if (p->btMode < 0) p->btMode = (p->algo == 0 ? 0 : 1);
  if (p->numHashBytes < 0) p->numHashBytes = (p->btMode ? 4 : 5);
  if (p->mc == 0) p->mc = (16 + ((unsigned)p->fb >> 1)) >> (p->btMode ? 0 : 1);
@@ -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;
--- a/src/Common/lzma/Precomp.h
+++ b/src/Common/lzma/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
--- a/src/Common/lzma/Threads.c
+++ b/src/Common/lzma/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;
@@ -369,14 +369,21 @@ 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);
+  {
+    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)
--- a/src/Common/lzma/Threads.h
+++ b/src/Common/lzma/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

--- a/src/Common/lzma/lzma-history.txt
+++ b/src/Common/lzma/lzma-history.txt
@@ -1,6 +1,80 @@
 HISTORY of the LZMA SDK
 -----------------------

+24.09          2024-11-29
+-------------------------
+- The default dictionary size values for LZMA/LZMA2 compression methods were increased:
+         dictionary size   compression level
+  v24.08  v24.09  v24.09   
+          32-bit  64-bit    
+    8 MB   16 MB   16 MB   -mx4
+   16 MB   32 MB   32 MB   -mx5 : Normal
+   32 MB   64 MB   64 MB   -mx6
+   32 MB   64 MB  128 MB   -mx7 : Maximum
+   64 MB   64 MB  256 MB   -mx8
+   64 MB   64 MB  256 MB   -mx9 : Ultra
+  The default dictionary size values for 32-bit versions of LZMA/LZMA2 don't exceed 64 MB.
+- If an archive update operation uses a temporary archive folder and 
+  the archive is moved to the destination folder, 7-Zip shows the progress of moving 
+  the archive file, as this operation can take a long time if the archive is large.
+- Some bugs were fixed.
+
+
+24.07          2024-06-19
+-------------------------
+- Changes in files:
+    Asm/x86/Sha256Opt.asm
+  Now it uses "READONLY" flag for constant array segment.
+  It fixes an issue where ".rodata" section in 7-Zip for x86/x64 Linux had a "WRITE" attribute.
+
+
+24.05          2024-05-14
+-------------------------
+- New switch -myv={MMNN} to set decoder compatibility version for 7z archive creating.
+  {MMNN} is 4-digit number that represents the version of 7-Zip without a dot.
+  If -myv={MMNN} switch is specified, 7-Zip will only use compression methods that can 
+  be decoded by the specified version {MMNN} of 7-Zip and newer versions.
+  If -myv={MMNN} switch is not specified, -myv=2300 is used, and 7-Zip will only
+  use compression methods that can be decoded by 7-Zip 23.00 and newer versions.
+- New switch -myfa={FilterID} to    allow 7-Zip to use the specified filter method for 7z archive creating.
+- New switch -myfd={FilterID} to disallow 7-Zip to use the specified filter method for 7z archive creating.
+
+
+24.03          2024-03-23
+-------------------------
+- 7-Zip now can use new RISCV filter for compression to 7z and xz archives.
+  RISCV filter can increase compression ratio for data containing executable
+  files compiled for RISC-V architecture.
+- The speed for LZMA and LZMA2 decompression in ARM64 version for Windows
+  was increased by 20%-60%.
+  It uses arm64 assembler code, and clang-cl is required for arm64 assembler code compiling.
+- -slmu switch : to show timestamps as UTC instead of LOCAL TIME.
+- -slsl switch : in console 7-Zip for Windows : to show file paths with 
+  linux path separator slash '/' instead of backslash separator '\'.
+- 7-Zip supports .sha256 files that use backslash path separator '\'.
+- Some bugs were fixed.
+
+
+24.01          2024-01-31
+-------------------------
+- 7-Zip uses file C/Precomp.h that is included to all c and c++ files.
+  CPP/Common/Common.h also includes C/Precomp.h.
+  C/Precomp.h defines the following macros (if _WIN32 is defined):
+    Z7_LARGE_PAGES 1
+    Z7_LONG_PATH 1
+    Z7_WIN32_WINNT_MIN  0x0500 (or higher)
+    _WIN32_WINNT        0x0500 (or higher)
+    WINVER  _WIN32_WINNT
+    UNICODE 1
+    _UNICODE 1
+  if _WIN32_WINNT is defined already, C/Precomp.h doesn't redefine it.
+
+- Speed optimizations for hash caclulation: CRC-32, CRC-64.
+- The bug was fixed: 7-Zip for Linux could fail for multivolume creation in some cases.
+- 7zr.exe for arm64 is included to LZMA SDK package.
+- Some bugs were fixed.
+
+
 23.01          2023-06-20
 -------------------------
 - 7-Zip now can use new ARM64 filter for compression to 7z and xz archives.
--- a/src/Common/lzma/lzma-sdk.txt
+++ b/src/Common/lzma/lzma-sdk.txt
@@ -1,4 +1,4 @@
-LZMA SDK 23.01
+LZMA SDK 24.09
 --------------

 LZMA SDK provides the documentation, samples, header files,
@@ -137,9 +137,12 @@ DOC/Methods.txt      - Compression method IDs for .7z

 bin/installer/   - example script to create installer that uses SFX module,

-bin/7zdec.exe    - simplified 7z archive decoder
-bin/7zr.exe      - 7-Zip console program (reduced version)
+bin/7zdec.exe    - simplified 7z archive decoder (x86 32-bit version)
+bin/7zr.exe      - 7-Zip console program (reduced version) (x86 32-bit version)
 bin/x64/7zr.exe  - 7-Zip console program (reduced version) (x64 version)
+bin/x64/7zdec.exe  - simplified 7z archive decoder (x64 version)
+bin/arm64/7zr.exe  - 7-Zip console program (reduced version) (arm64 version)
+bin/arm64/7zdec.exe  - simplified 7z archive decoder (arm64 version)
 bin/lzma.exe     - file->file LZMA encoder/decoder for Windows
 bin/7zS2.sfx     - small SFX module for installers (GUI version)
 bin/7zS2con.sfx  - small SFX module for installers (Console version)
@@ -235,7 +238,7 @@ Note:

 LZMA features
 -------------
-  - Variable dictionary size (up to 1 GB)
+  - Variable dictionary size (up to 4 GB)
  - Estimated compressing speed: about 2 MB/s on 2 GHz CPU
  - Estimated decompressing speed: 
      - 20-30 MB/s on modern 2 GHz cpu
@@ -285,8 +288,8 @@ Usage:  LZMA <e|d> inputFile outputFile [<switches>...]
  -a{N}:  set compression mode 0 = fast, 1 = normal
          default: 1 (normal)

-  d{N}:   Sets Dictionary size - [0, 30], default: 23 (8MB)
-          The maximum value for dictionary size is 1 GB = 2^30 bytes.
+  d{N}:   Sets Dictionary size - [0, 31], default: N=24 (32 MB)
+          The maximum value for dictionary size is N=31 (2 GB).
          Dictionary size is calculated as DictionarySize = 2^N bytes. 
          For decompressing file compressed by LZMA method with dictionary 
          size D = 2^N you need about D bytes of memory (RAM).
@@ -321,7 +324,9 @@ Usage:  LZMA <e|d> inputFile outputFile [<switches>...]
                bt2    d *  9.5 + 4MB  Binary Tree with 2 bytes hashing.
                bt3    d * 11.5 + 4MB  Binary Tree with 3 bytes hashing.
                bt4    d * 11.5 + 4MB  Binary Tree with 4 bytes hashing.
+                bt5    d * 11.5 + 4MB  Binary Tree with 5 bytes hashing.
                hc4    d *  7.5 + 4MB  Hash Chain with 4 bytes hashing.
+                hc5    d *  7.5 + 4MB  Hash Chain with 5 bytes hashing.

  -eos:   write End Of Stream marker. By default LZMA doesn't write 
          eos marker, since LZMA decoder knows uncompressed size