Add a small version of liblz4 that can be built in statically

Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>

8 files changed, 3736 insertions, 36 deletions

diff --git a/configure.ac b/configure.ac
index e885348..96419b9 100644
--- a/configure.ac
+++ b/configure.ac
@@ -68,6 +68,10 @@ AC_ARG_WITH([lz4],
 	[AS_HELP_STRING([--with-lz4], [Build with lz4 compression support])],
 	[], [with_lz4="check"])
 
+AC_ARG_WITH([builtin-lz4],
+	[AS_HELP_STRING([--with-builtin-lz4], [Use a custom, static liblz4])],
+	[], [with_builtin_lz4="no"])
+
 AC_ARG_WITH([zstd],
 	[AS_HELP_STRING([--with-zstd], [Build with zstd compression support])],
 	[], [with_zstd="check"])
@@ -139,13 +143,15 @@ AS_IF([test "x$with_xz" != "xno"], [
 				     [with_xz="no"])])
 ], [])
 
-AS_IF([test "x$with_lz4" != "xno"], [
+AS_IF([test "x$with_lz4" != "xno" -a "x$with_builtin_lz4" != "xyes"], [
 	PKG_CHECK_MODULES(LZ4, [liblz4], [with_lz4="yes"],
 			       [AS_IF([test "x$with_lz4" = "xyes"],
 				      [AC_MSG_ERROR([cannot find liblz4])],
 				      [with_lz4="no"])])
 ], [])
 
+AS_IF([test "x$with_builtin_lz4" != "xno"], [with_lz4="yes"], [])
+
 AS_IF([test "x$with_zstd" != "xno"], [
 	PKG_CHECK_MODULES(ZSTD, [libzstd], [with_zstd="yes"],
 				[AS_IF([test "x$with_zstd" = "xyes"],
@@ -197,10 +203,14 @@ AM_CONDITIONAL([WITH_LZO], [test "x$with_lzo" = "xyes"])
 AM_CONDITIONAL([WITH_SELINUX], [test "x$with_selinux" = "xyes"])
 AM_CONDITIONAL([HAVE_PTHREAD], [test "x$with_pthread" = "xyes"])
 
+AM_CONDITIONAL([WITH_OWN_LZ4], [test "x$with_builtin_lz4" = "xyes"])
+
 libsqfs_dep_mod=""
+AS_IF([test "x$with_lz4" = "xyes" -a "x$with_builtin_lz4" != "xyes"],
+	[libsqfs_dep_mod="$libsqfs_dep_mod liblz4"], [])
+
 AM_COND_IF([WITH_GZIP], [libsqfs_dep_mod="$libsqfs_dep_mod zlib"], [])
 AM_COND_IF([WITH_XZ], [libsqfs_dep_mod="$libsqfs_dep_mod liblzma >= 5.0.0"], [])
-AM_COND_IF([WITH_LZ4], [libsqfs_dep_mod="$libsqfs_dep_mod liblz4"], [])
 AM_COND_IF([WITH_ZSTD], [libsqfs_dep_mod="$libsqfs_dep_mod libzstd"], [])
 AC_SUBST([LIBSQFS_DEP_MOD], ["$libsqfs_dep_mod"])
 
diff --git a/lib/sqfs/Makemodule.am b/lib/sqfs/Makemodule.am
index 0a3b874..c2b243c 100644
--- a/lib/sqfs/Makemodule.am
+++ b/lib/sqfs/Makemodule.am
@@ -67,6 +67,13 @@ endif
 if WITH_LZ4
 libsquashfs_la_SOURCES += lib/sqfs/comp/lz4.c
 libsquashfs_la_CPPFLAGS += -DWITH_LZ4
+
+if WITH_OWN_LZ4
+libsquashfs_la_CPPFLAGS += -I$(top_srcdir)/lib/sqfs/comp/lz4 -DLZ4_HEAPMODE=1
+
+libsquashfs_la_SOURCES += lib/sqfs/comp/lz4/lz4.c lib/sqfs/comp/lz4/lz4.h
+libsquashfs_la_SOURCES += lib/sqfs/comp/lz4/lz4hc.c lib/sqfs/comp/lz4/lz4hc.h
+endif
 endif
 
 if WITH_ZSTD
@@ -80,3 +87,5 @@ sqfsinclude_HEADERS = $(LIBSQFS_HEARDS)
 lib_LTLIBRARIES += libsquashfs.la
 
 pkgconfig_DATA += lib/sqfs/libsquashfs0.pc
+
+EXTRA_DIST += lib/sqfs/comp/lz4/README
diff --git a/lib/sqfs/comp/lz4/README b/lib/sqfs/comp/lz4/README
new file mode 100644
index 0000000..4c15347
--- /dev/null
+++ b/lib/sqfs/comp/lz4/README
@@ -0,0 +1,12 @@
+This source has been extracted from the lz4 release tarball, version 1.9.2
+released on August 20th, 2019.
+
+The source code originates from the "lib" subdirectory. The license is included
+in the subdirectory licenses/LZ4.txt in the tools-ng subdirectory of the
+squashfs-tools-ng source package.
+
+The following modifications have been made:
+ - Always define LZ4LIB_API and LZ4LIB_STATIC_API to set default visibility to
+   hidden, so the LZ4 functions aren't exported from libsquashfs.
+ - Remove the streaming functions and most of the functions that aren't used
+   by libsquashfs.
diff --git a/lib/sqfs/comp/lz4/lz4.c b/lib/sqfs/comp/lz4/lz4.c
new file mode 100644
index 0000000..853d228
--- /dev/null
+++ b/lib/sqfs/comp/lz4/lz4.c
@@ -0,0 +1,1708 @@
+/*
+   LZ4 - Fast LZ compression algorithm
+   Copyright (C) 2011-present, Yann Collet.
+
+   BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+
+   Redistribution and use in source and binary forms, with or without
+   modification, are permitted provided that the following conditions are
+   met:
+
+       * Redistributions of source code must retain the above copyright
+   notice, this list of conditions and the following disclaimer.
+       * Redistributions in binary form must reproduce the above
+   copyright notice, this list of conditions and the following disclaimer
+   in the documentation and/or other materials provided with the
+   distribution.
+
+   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+   You can contact the author at :
+    - LZ4 homepage : http://www.lz4.org
+    - LZ4 source repository : https://github.com/lz4/lz4
+*/
+
+/*-************************************
+*  Tuning parameters
+**************************************/
+/*
+ * LZ4_HEAPMODE :
+ * Select how default compression functions will allocate memory for their hash table,
+ * in memory stack (0:default, fastest), or in memory heap (1:requires malloc()).
+ */
+#ifndef LZ4_HEAPMODE
+#  define LZ4_HEAPMODE 0
+#endif
+
+/*
+ * ACCELERATION_DEFAULT :
+ * Select "acceleration" for LZ4_compress_fast() when parameter value <= 0
+ */
+#define ACCELERATION_DEFAULT 1
+
+
+/*-************************************
+*  CPU Feature Detection
+**************************************/
+/* LZ4_FORCE_MEMORY_ACCESS
+ * By default, access to unaligned memory is controlled by `memcpy()`, which is safe and portable.
+ * Unfortunately, on some target/compiler combinations, the generated assembly is sub-optimal.
+ * The below switch allow to select different access method for improved performance.
+ * Method 0 (default) : use `memcpy()`. Safe and portable.
+ * Method 1 : `__packed` statement. It depends on compiler extension (ie, not portable).
+ *            This method is safe if your compiler supports it, and *generally* as fast or faster than `memcpy`.
+ * Method 2 : direct access. This method is portable but violate C standard.
+ *            It can generate buggy code on targets which assembly generation depends on alignment.
+ *            But in some circumstances, it's the only known way to get the most performance (ie GCC + ARMv6)
+ * See https://fastcompression.blogspot.fr/2015/08/accessing-unaligned-memory.html for details.
+ * Prefer these methods in priority order (0 > 1 > 2)
+ */
+#ifndef LZ4_FORCE_MEMORY_ACCESS   /* can be defined externally */
+#  if defined(__GNUC__) && \
+  ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) \
+  || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) )
+#    define LZ4_FORCE_MEMORY_ACCESS 2
+#  elif (defined(__INTEL_COMPILER) && !defined(_WIN32)) || defined(__GNUC__)
+#    define LZ4_FORCE_MEMORY_ACCESS 1
+#  endif
+#endif
+
+/*
+ * LZ4_FORCE_SW_BITCOUNT
+ * Define this parameter if your target system or compiler does not support hardware bit count
+ */
+#if defined(_MSC_VER) && defined(_WIN32_WCE)   /* Visual Studio for WinCE doesn't support Hardware bit count */
+#  define LZ4_FORCE_SW_BITCOUNT
+#endif
+
+
+
+/*-************************************
+*  Dependency
+**************************************/
+/*
+ * LZ4_SRC_INCLUDED:
+ * Amalgamation flag, whether lz4.c is included
+ */
+#ifndef LZ4_SRC_INCLUDED
+#  define LZ4_SRC_INCLUDED 1
+#endif
+
+#ifndef LZ4_STATIC_LINKING_ONLY
+#define LZ4_STATIC_LINKING_ONLY
+#endif
+
+#ifndef LZ4_DISABLE_DEPRECATE_WARNINGS
+#define LZ4_DISABLE_DEPRECATE_WARNINGS /* due to LZ4_decompress_safe_withPrefix64k */
+#endif
+
+#define LZ4_STATIC_LINKING_ONLY  /* LZ4_DISTANCE_MAX */
+#include "lz4.h"
+/* see also "memory routines" below */
+
+
+/*-************************************
+*  Compiler Options
+**************************************/
+#ifdef _MSC_VER    /* Visual Studio */
+#  include <intrin.h>
+#  pragma warning(disable : 4127)        /* disable: C4127: conditional expression is constant */
+#  pragma warning(disable : 4293)        /* disable: C4293: too large shift (32-bits) */
+#endif  /* _MSC_VER */
+
+#ifndef LZ4_FORCE_INLINE
+#  ifdef _MSC_VER    /* Visual Studio */
+#    define LZ4_FORCE_INLINE static __forceinline
+#  else
+#    if defined (__cplusplus) || defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L   /* C99 */
+#      ifdef __GNUC__
+#        define LZ4_FORCE_INLINE static inline __attribute__((always_inline))
+#      else
+#        define LZ4_FORCE_INLINE static inline
+#      endif
+#    else
+#      define LZ4_FORCE_INLINE static
+#    endif /* __STDC_VERSION__ */
+#  endif  /* _MSC_VER */
+#endif /* LZ4_FORCE_INLINE */
+
+/* LZ4_FORCE_O2_GCC_PPC64LE and LZ4_FORCE_O2_INLINE_GCC_PPC64LE
+ * gcc on ppc64le generates an unrolled SIMDized loop for LZ4_wildCopy8,
+ * together with a simple 8-byte copy loop as a fall-back path.
+ * However, this optimization hurts the decompression speed by >30%,
+ * because the execution does not go to the optimized loop
+ * for typical compressible data, and all of the preamble checks
+ * before going to the fall-back path become useless overhead.
+ * This optimization happens only with the -O3 flag, and -O2 generates
+ * a simple 8-byte copy loop.
+ * With gcc on ppc64le, all of the LZ4_decompress_* and LZ4_wildCopy8
+ * functions are annotated with __attribute__((optimize("O2"))),
+ * and also LZ4_wildCopy8 is forcibly inlined, so that the O2 attribute
+ * of LZ4_wildCopy8 does not affect the compression speed.
+ */
+#if defined(__PPC64__) && defined(__LITTLE_ENDIAN__) && defined(__GNUC__) && !defined(__clang__)
+#  define LZ4_FORCE_O2_GCC_PPC64LE __attribute__((optimize("O2")))
+#  define LZ4_FORCE_O2_INLINE_GCC_PPC64LE __attribute__((optimize("O2"))) LZ4_FORCE_INLINE
+#else
+#  define LZ4_FORCE_O2_GCC_PPC64LE
+#  define LZ4_FORCE_O2_INLINE_GCC_PPC64LE static
+#endif
+
+#if (defined(__GNUC__) && (__GNUC__ >= 3)) || (defined(__INTEL_COMPILER) && (__INTEL_COMPILER >= 800)) || defined(__clang__)
+#  define expect(expr,value)    (__builtin_expect ((expr),(value)) )
+#else
+#  define expect(expr,value)    (expr)
+#endif
+
+#ifndef likely
+#define likely(expr)     expect((expr) != 0, 1)
+#endif
+#ifndef unlikely
+#define unlikely(expr)   expect((expr) != 0, 0)
+#endif
+
+
+/*-************************************
+*  Memory routines
+**************************************/
+#include <stdlib.h>   /* malloc, calloc, free */
+#define ALLOC(s)          malloc(s)
+#define ALLOC_AND_ZERO(s) calloc(1,s)
+#define FREEMEM(p)        free(p)
+#include <string.h>   /* memset, memcpy */
+#define MEM_INIT(p,v,s)   memset((p),(v),(s))
+
+
+/*-************************************
+*  Common Constants
+**************************************/
+#define MINMATCH 4
+
+#define WILDCOPYLENGTH 8
+#define LASTLITERALS   5   /* see ../doc/lz4_Block_format.md#parsing-restrictions */
+#define MFLIMIT       12   /* see ../doc/lz4_Block_format.md#parsing-restrictions */
+#define MATCH_SAFEGUARD_DISTANCE  ((2*WILDCOPYLENGTH) - MINMATCH)   /* ensure it's possible to write 2 x wildcopyLength without overflowing output buffer */
+#define FASTLOOP_SAFE_DISTANCE 64
+static const int LZ4_minLength = (MFLIMIT+1);
+
+#define KB *(1 <<10)
+#define MB *(1 <<20)
+#define GB *(1U<<30)
+
+#define LZ4_DISTANCE_ABSOLUTE_MAX 65535
+#if (LZ4_DISTANCE_MAX > LZ4_DISTANCE_ABSOLUTE_MAX)   /* max supported by LZ4 format */
+#  error "LZ4_DISTANCE_MAX is too big : must be <= 65535"
+#endif
+
+#define ML_BITS  4
+#define ML_MASK  ((1U<<ML_BITS)-1)
+#define RUN_BITS (8-ML_BITS)
+#define RUN_MASK ((1U<<RUN_BITS)-1)
+
+
+/*-************************************
+*  Error detection
+**************************************/
+#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=1)
+#  include <assert.h>
+#else
+#  ifndef assert
+#    define assert(condition) ((void)0)
+#  endif
+#endif
+
+#define LZ4_STATIC_ASSERT(c)   { enum { LZ4_static_assert = 1/(int)(!!(c)) }; }   /* use after variable declarations */
+
+#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=2)
+#  include <stdio.h>
+static int g_debuglog_enable = 1;
+#  define DEBUGLOG(l, ...) {                                  \
+                if ((g_debuglog_enable) && (l<=LZ4_DEBUG)) {  \
+                    fprintf(stderr, __FILE__ ": ");           \
+                    fprintf(stderr, __VA_ARGS__);             \
+                    fprintf(stderr, " \n");                   \
+            }   }
+#else
+#  define DEBUGLOG(l, ...)      {}    /* disabled */
+#endif
+
+
+/*-************************************
+*  Types
+**************************************/
+#if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */)
+# include <stdint.h>
+  typedef  uint8_t BYTE;
+  typedef uint16_t U16;
+  typedef uint32_t U32;
+  typedef  int32_t S32;
+  typedef uint64_t U64;
+  typedef uintptr_t uptrval;
+#else
+  typedef unsigned char       BYTE;
+  typedef unsigned short      U16;
+  typedef unsigned int        U32;
+  typedef   signed int        S32;
+  typedef unsigned long long  U64;
+  typedef size_t              uptrval;   /* generally true, except OpenVMS-64 */
+#endif
+
+#if defined(__x86_64__)
+  typedef U64    reg_t;   /* 64-bits in x32 mode */
+#else
+  typedef size_t reg_t;   /* 32-bits in x32 mode */
+#endif
+
+typedef enum {
+    notLimited = 0,
+    limitedOutput = 1,
+    fillOutput = 2
+} limitedOutput_directive;
+
+
+/*-************************************
+*  Reading and writing into memory
+**************************************/
+static unsigned LZ4_isLittleEndian(void)
+{
+    const union { U32 u; BYTE c[4]; } one = { 1 };   /* don't use static : performance detrimental */
+    return one.c[0];
+}
+
+
+#if defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_FORCE_MEMORY_ACCESS==2)
+/* lie to the compiler about data alignment; use with caution */
+
+static U16 LZ4_read16(const void* memPtr) { return *(const U16*) memPtr; }
+static U32 LZ4_read32(const void* memPtr) { return *(const U32*) memPtr; }
+static reg_t LZ4_read_ARCH(const void* memPtr) { return *(const reg_t*) memPtr; }
+
+static void LZ4_write16(void* memPtr, U16 value) { *(U16*)memPtr = value; }
+static void LZ4_write32(void* memPtr, U32 value) { *(U32*)memPtr = value; }
+
+#elif defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_FORCE_MEMORY_ACCESS==1)
+
+/* __pack instructions are safer, but compiler specific, hence potentially problematic for some compilers */
+/* currently only defined for gcc and icc */
+typedef union { U16 u16; U32 u32; reg_t uArch; } __attribute__((packed)) unalign;
+
+static U16 LZ4_read16(const void* ptr) { return ((const unalign*)ptr)->u16; }
+static U32 LZ4_read32(const void* ptr) { return ((const unalign*)ptr)->u32; }
+static reg_t LZ4_read_ARCH(const void* ptr) { return ((const unalign*)ptr)->uArch; }
+
+static void LZ4_write16(void* memPtr, U16 value) { ((unalign*)memPtr)->u16 = value; }
+static void LZ4_write32(void* memPtr, U32 value) { ((unalign*)memPtr)->u32 = value; }
+
+#else  /* safe and portable access using memcpy() */
+
+static U16 LZ4_read16(const void* memPtr)
+{
+    U16 val; memcpy(&val, memPtr, sizeof(val)); return val;
+}
+
+static U32 LZ4_read32(const void* memPtr)
+{
+    U32 val; memcpy(&val, memPtr, sizeof(val)); return val;
+}
+
+static reg_t LZ4_read_ARCH(const void* memPtr)
+{
+    reg_t val; memcpy(&val, memPtr, sizeof(val)); return val;
+}
+
+static void LZ4_write16(void* memPtr, U16 value)
+{
+    memcpy(memPtr, &value, sizeof(value));
+}
+
+static void LZ4_write32(void* memPtr, U32 value)
+{
+    memcpy(memPtr, &value, sizeof(value));
+}
+
+#endif /* LZ4_FORCE_MEMORY_ACCESS */
+
+
+static U16 LZ4_readLE16(const void* memPtr)
+{
+    if (LZ4_isLittleEndian()) {
+        return LZ4_read16(memPtr);
+    } else {
+        const BYTE* p = (const BYTE*)memPtr;
+        return (U16)((U16)p[0] + (p[1]<<8));
+    }
+}
+
+static void LZ4_writeLE16(void* memPtr, U16 value)
+{
+    if (LZ4_isLittleEndian()) {
+        LZ4_write16(memPtr, value);
+    } else {
+        BYTE* p = (BYTE*)memPtr;
+        p[0] = (BYTE) value;
+        p[1] = (BYTE)(value>>8);
+    }
+}
+
+/* customized variant of memcpy, which can overwrite up to 8 bytes beyond dstEnd */
+LZ4_FORCE_O2_INLINE_GCC_PPC64LE
+void LZ4_wildCopy8(void* dstPtr, const void* srcPtr, void* dstEnd)
+{
+    BYTE* d = (BYTE*)dstPtr;
+    const BYTE* s = (const BYTE*)srcPtr;
+    BYTE* const e = (BYTE*)dstEnd;
+
+    do { memcpy(d,s,8); d+=8; s+=8; } while (d<e);
+}
+
+static const unsigned inc32table[8] = {0, 1, 2,  1,  0,  4, 4, 4};
+static const int      dec64table[8] = {0, 0, 0, -1, -4,  1, 2, 3};
+
+
+#ifndef LZ4_FAST_DEC_LOOP
+#  if defined(__i386__) || defined(__x86_64__)
+#    define LZ4_FAST_DEC_LOOP 1
+#  elif defined(__aarch64__) && !defined(__clang__)
+     /* On aarch64, we disable this optimization for clang because on certain
+      * mobile chipsets and clang, it reduces performance. For more information
+      * refer to https://github.com/lz4/lz4/pull/707. */
+#    define LZ4_FAST_DEC_LOOP 1
+#  else
+#    define LZ4_FAST_DEC_LOOP 0
+#  endif
+#endif
+
+#if LZ4_FAST_DEC_LOOP
+
+LZ4_FORCE_O2_INLINE_GCC_PPC64LE void
+LZ4_memcpy_using_offset_base(BYTE* dstPtr, const BYTE* srcPtr, BYTE* dstEnd, const size_t offset)
+{
+    if (offset < 8) {
+        dstPtr[0] = srcPtr[0];
+        dstPtr[1] = srcPtr[1];
+        dstPtr[2] = srcPtr[2];
+        dstPtr[3] = srcPtr[3];
+        srcPtr += inc32table[offset];
+        memcpy(dstPtr+4, srcPtr, 4);
+        srcPtr -= dec64table[offset];
+        dstPtr += 8;
+    } else {
+        memcpy(dstPtr, srcPtr, 8);
+        dstPtr += 8;
+        srcPtr += 8;
+    }
+
+    LZ4_wildCopy8(dstPtr, srcPtr, dstEnd);
+}
+
+/* customized variant of memcpy, which can overwrite up to 32 bytes beyond dstEnd
+ * this version copies two times 16 bytes (instead of one time 32 bytes)
+ * because it must be compatible with offsets >= 16. */
+LZ4_FORCE_O2_INLINE_GCC_PPC64LE void
+LZ4_wildCopy32(void* dstPtr, const void* srcPtr, void* dstEnd)
+{
+    BYTE* d = (BYTE*)dstPtr;
+    const BYTE* s = (const BYTE*)srcPtr;
+    BYTE* const e = (BYTE*)dstEnd;
+
+    do { memcpy(d,s,16); memcpy(d+16,s+16,16); d+=32; s+=32; } while (d<e);
+}
+
+/* LZ4_memcpy_using_offset()  presumes :
+ * - dstEnd >= dstPtr + MINMATCH
+ * - there is at least 8 bytes available to write after dstEnd */
+LZ4_FORCE_O2_INLINE_GCC_PPC64LE void
+LZ4_memcpy_using_offset(BYTE* dstPtr, const BYTE* srcPtr, BYTE* dstEnd, const size_t offset)
+{
+    BYTE v[8];
+
+    assert(dstEnd >= dstPtr + MINMATCH);
+    LZ4_write32(dstPtr, 0);   /* silence an msan warning when offset==0 */
+
+    switch(offset) {
+    case 1:
+        memset(v, *srcPtr, 8);
+        break;
+    case 2:
+        memcpy(v, srcPtr, 2);
+        memcpy(&v[2], srcPtr, 2);
+        memcpy(&v[4], &v[0], 4);
+        break;
+    case 4:
+        memcpy(v, srcPtr, 4);
+        memcpy(&v[4], srcPtr, 4);
+        break;
+    default:
+        LZ4_memcpy_using_offset_base(dstPtr, srcPtr, dstEnd, offset);
+        return;
+    }
+
+    memcpy(dstPtr, v, 8);
+    dstPtr += 8;
+    while (dstPtr < dstEnd) {
+        memcpy(dstPtr, v, 8);
+        dstPtr += 8;
+    }
+}
+#endif
+
+
+/*-************************************
+*  Common functions
+**************************************/
+static unsigned LZ4_NbCommonBytes (reg_t val)
+{
+    if (LZ4_isLittleEndian()) {
+        if (sizeof(val)==8) {
+#       if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            unsigned long r = 0;
+            _BitScanForward64( &r, (U64)val );
+            return (int)(r>>3);
+#       elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            return (unsigned)__builtin_ctzll((U64)val) >> 3;
+#       else
+            static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2,
+                                                     0, 3, 1, 3, 1, 4, 2, 7,
+                                                     0, 2, 3, 6, 1, 5, 3, 5,
+                                                     1, 3, 4, 4, 2, 5, 6, 7,
+                                                     7, 0, 1, 2, 3, 3, 4, 6,
+                                                     2, 6, 5, 5, 3, 4, 5, 6,
+                                                     7, 1, 2, 4, 6, 4, 4, 5,
+                                                     7, 2, 6, 5, 7, 6, 7, 7 };
+            return DeBruijnBytePos[((U64)((val & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58];
+#       endif
+        } else /* 32 bits */ {
+#       if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            unsigned long r;
+            _BitScanForward( &r, (U32)val );
+            return (int)(r>>3);
+#       elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            return (unsigned)__builtin_ctz((U32)val) >> 3;
+#       else
+            static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0,
+                                                     3, 2, 2, 1, 3, 2, 0, 1,
+                                                     3, 3, 1, 2, 2, 2, 2, 0,
+                                                     3, 1, 2, 0, 1, 0, 1, 1 };
+            return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27];
+#       endif
+        }
+    } else   /* Big Endian CPU */ {
+        if (sizeof(val)==8) {   /* 64-bits */
+#       if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            unsigned long r = 0;
+            _BitScanReverse64( &r, val );
+            return (unsigned)(r>>3);
+#       elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            return (unsigned)__builtin_clzll((U64)val) >> 3;
+#       else
+            static const U32 by32 = sizeof(val)*4;  /* 32 on 64 bits (goal), 16 on 32 bits.
+                Just to avoid some static analyzer complaining about shift by 32 on 32-bits target.
+                Note that this code path is never triggered in 32-bits mode. */
+            unsigned r;
+            if (!(val>>by32)) { r=4; } else { r=0; val>>=by32; }
+            if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; }
+            r += (!val);
+            return r;
+#       endif
+        } else /* 32 bits */ {
+#       if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            unsigned long r = 0;
+            _BitScanReverse( &r, (unsigned long)val );
+            return (unsigned)(r>>3);
+#       elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            return (unsigned)__builtin_clz((U32)val) >> 3;
+#       else
+            unsigned r;
+            if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; }
+            r += (!val);
+            return r;
+#       endif
+        }
+    }
+}
+
+#define STEPSIZE sizeof(reg_t)
+LZ4_FORCE_INLINE
+unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit)
+{
+    const BYTE* const pStart = pIn;
+
+    if (likely(pIn < pInLimit-(STEPSIZE-1))) {
+        reg_t const diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn);
+        if (!diff) {
+            pIn+=STEPSIZE; pMatch+=STEPSIZE;
+        } else {
+            return LZ4_NbCommonBytes(diff);
+    }   }
+
+    while (likely(pIn < pInLimit-(STEPSIZE-1))) {
+        reg_t const diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn);
+        if (!diff) { pIn+=STEPSIZE; pMatch+=STEPSIZE; continue; }
+        pIn += LZ4_NbCommonBytes(diff);
+        return (unsigned)(pIn - pStart);
+    }
+
+    if ((STEPSIZE==8) && (pIn<(pInLimit-3)) && (LZ4_read32(pMatch) == LZ4_read32(pIn))) { pIn+=4; pMatch+=4; }
+    if ((pIn<(pInLimit-1)) && (LZ4_read16(pMatch) == LZ4_read16(pIn))) { pIn+=2; pMatch+=2; }
+    if ((pIn<pInLimit) && (*pMatch == *pIn)) pIn++;
+    return (unsigned)(pIn - pStart);
+}
+
+
+#ifndef LZ4_COMMONDEFS_ONLY
+/*-************************************
+*  Local Constants
+**************************************/
+static const int LZ4_64Klimit = ((64 KB) + (MFLIMIT-1));
+static const U32 LZ4_skipTrigger = 6;  /* Increase this value ==> compression run slower on incompressible data */
+
+
+/*-************************************
+*  Local Structures and types
+**************************************/
+typedef enum { clearedTable = 0, byPtr, byU32, byU16 } tableType_t;
+
+/**
+ * This enum distinguishes several different modes of accessing previous
+ * content in the stream.
+ *
+ * - noDict        : There is no preceding content.
+ * - withPrefix64k : Table entries up to ctx->dictSize before the current blob
+ *                   blob being compressed are valid and refer to the preceding
+ *                   content (of length ctx->dictSize), which is available
+ *                   contiguously preceding in memory the content currently
+ *                   being compressed.
+ * - usingExtDict  : Like withPrefix64k, but the preceding content is somewhere
+ *                   else in memory, starting at ctx->dictionary with length
+ *                   ctx->dictSize.
+ * - usingDictCtx  : Like usingExtDict, but everything concerning the preceding
+ *                   content is in a separate context, pointed to by
+ *                   ctx->dictCtx. ctx->dictionary, ctx->dictSize, and table
+ *                   entries in the current context that refer to positions
+ *                   preceding the beginning of the current compression are
+ *                   ignored. Instead, ctx->dictCtx->dictionary and ctx->dictCtx
+ *                   ->dictSize describe the location and size of the preceding
+ *                   content, and matches are found by looking in the ctx
+ *                   ->dictCtx->hashTable.
+ */
+typedef enum { noDict = 0, withPrefix64k, usingExtDict, usingDictCtx } dict_directive;
+typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive;
+
+
+/*-************************************
+*  Local Utils
+**************************************/
+int LZ4_compressBound(int isize)  { return LZ4_COMPRESSBOUND(isize); }
+
+/*-******************************
+*  Compression functions
+********************************/
+static U32 LZ4_hash4(U32 sequence, tableType_t const tableType)
+{
+    if (tableType == byU16)
+        return ((sequence * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1)));
+    else
+        return ((sequence * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG));
+}
+
+static U32 LZ4_hash5(U64 sequence, tableType_t const tableType)
+{
+    const U32 hashLog = (tableType == byU16) ? LZ4_HASHLOG+1 : LZ4_HASHLOG;
+    if (LZ4_isLittleEndian()) {
+        const U64 prime5bytes = 889523592379ULL;
+        return (U32)(((sequence << 24) * prime5bytes) >> (64 - hashLog));
+    } else {
+        const U64 prime8bytes = 11400714785074694791ULL;
+        return (U32)(((sequence >> 24) * prime8bytes) >> (64 - hashLog));
+    }
+}
+
+LZ4_FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tableType)
+{
+    if ((sizeof(reg_t)==8) && (tableType != byU16)) return LZ4_hash5(LZ4_read_ARCH(p), tableType);
+    return LZ4_hash4(LZ4_read32(p), tableType);
+}
+
+static void LZ4_clearHash(U32 h, void* tableBase, tableType_t const tableType)
+{
+    switch (tableType)
+    {
+    default: /* fallthrough */
+    case clearedTable: { /* illegal! */ assert(0); return; }
+    case byPtr: { const BYTE** hashTable = (const BYTE**)tableBase; hashTable[h] = NULL; return; }
+    case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = 0; return; }
+    case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = 0; return; }
+    }
+}
+
+static void LZ4_putIndexOnHash(U32 idx, U32 h, void* tableBase, tableType_t const tableType)
+{
+    switch (tableType)
+    {
+    default: /* fallthrough */
+    case clearedTable: /* fallthrough */
+    case byPtr: { /* illegal! */ assert(0); return; }
+    case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = idx; return; }
+    case byU16: { U16* hashTable = (U16*) tableBase; assert(idx < 65536); hashTable[h] = (U16)idx; return; }
+    }
+}
+
+static void LZ4_putPositionOnHash(const BYTE* p, U32 h,
+                                  void* tableBase, tableType_t const tableType,
+                            const BYTE* srcBase)
+{
+    switch (tableType)
+    {
+    case clearedTable: { /* illegal! */ assert(0); return; }
+    case byPtr: { const BYTE** hashTable = (const BYTE**)tableBase; hashTable[h] = p; return; }
+    case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = (U32)(p-srcBase); return; }
+    case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = (U16)(p-srcBase); return; }
+    }
+}
+
+LZ4_FORCE_INLINE void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase)
+{
+    U32 const h = LZ4_hashPosition(p, tableType);
+    LZ4_putPositionOnHash(p, h, tableBase, tableType, srcBase);
+}
+
+/* LZ4_getIndexOnHash() :
+ * Index of match position registered in hash table.
+ * hash position must be calculated by using base+index, or dictBase+index.
+ * Assumption 1 : only valid if tableType == byU32 or byU16.
+ * Assumption 2 : h is presumed valid (within limits of hash table)
+ */
+static U32 LZ4_getIndexOnHash(U32 h, const void* tableBase, tableType_t tableType)
+{
+    LZ4_STATIC_ASSERT(LZ4_MEMORY_USAGE > 2);
+    if (tableType == byU32) {
+        const U32* const hashTable = (const U32*) tableBase;
+        assert(h < (1U << (LZ4_MEMORY_USAGE-2)));
+        return hashTable[h];
+    }
+    if (tableType == byU16) {
+        const U16* const hashTable = (const U16*) tableBase;
+        assert(h < (1U << (LZ4_MEMORY_USAGE-1)));
+        return hashTable[h];
+    }
+    assert(0); return 0;  /* forbidden case */
+}
+
+static const BYTE* LZ4_getPositionOnHash(U32 h, const void* tableBase, tableType_t tableType, const BYTE* srcBase)
+{
+    if (tableType == byPtr) { const BYTE* const* hashTable = (const BYTE* const*) tableBase; return hashTable[h]; }
+    if (tableType == byU32) { const U32* const hashTable = (const U32*) tableBase; return hashTable[h] + srcBase; }
+    { const U16* const hashTable = (const U16*) tableBase; return hashTable[h] + srcBase; }   /* default, to ensure a return */
+}
+
+LZ4_FORCE_INLINE const BYTE*
+LZ4_getPosition(const BYTE* p,
+                const void* tableBase, tableType_t tableType,
+                const BYTE* srcBase)
+{
+    U32 const h = LZ4_hashPosition(p, tableType);
+    return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase);
+}
+
+LZ4_FORCE_INLINE void
+LZ4_prepareTable(LZ4_stream_t_internal* const cctx,
+           const int inputSize,
+           const tableType_t tableType) {
+    /* If compression failed during the previous step, then the context
+     * is marked as dirty, therefore, it has to be fully reset.
+     */
+    if (cctx->dirty) {
+        DEBUGLOG(5, "LZ4_prepareTable: Full reset for %p", cctx);
+        MEM_INIT(cctx, 0, sizeof(LZ4_stream_t_internal));
+        return;
+    }
+
+    /* If the table hasn't been used, it's guaranteed to be zeroed out, and is
+     * therefore safe to use no matter what mode we're in. Otherwise, we figure
+     * out if it's safe to leave as is or whether it needs to be reset.
+     */
+    if (cctx->tableType != clearedTable) {
+        assert(inputSize >= 0);
+        if (cctx->tableType != tableType
+          || ((tableType == byU16) && cctx->currentOffset + (unsigned)inputSize >= 0xFFFFU)
+          || ((tableType == byU32) && cctx->currentOffset > 1 GB)
+          || tableType == byPtr
+          || inputSize >= 4 KB)
+        {
+            DEBUGLOG(4, "LZ4_prepareTable: Resetting table in %p", cctx);
+            MEM_INIT(cctx->hashTable, 0, LZ4_HASHTABLESIZE);
+            cctx->currentOffset = 0;
+            cctx->tableType = clearedTable;
+        } else {
+            DEBUGLOG(4, "LZ4_prepareTable: Re-use hash table (no reset)");
+        }
+    }
+
+    /* Adding a gap, so all previous entries are > LZ4_DISTANCE_MAX back, is faster
+     * than compressing without a gap. However, compressing with
+     * currentOffset == 0 is faster still, so we preserve that case.
+     */
+    if (cctx->currentOffset != 0 && tableType == byU32) {
+        DEBUGLOG(5, "LZ4_prepareTable: adding 64KB to currentOffset");
+        cctx->currentOffset += 64 KB;
+    }
+
+    /* Finally, clear history */
+    cctx->dictCtx = NULL;
+    cctx->dictionary = NULL;
+    cctx->dictSize = 0;
+}
+
+/** LZ4_compress_generic() :
+    inlined, to ensure branches are decided at compilation time */
+LZ4_FORCE_INLINE int LZ4_compress_generic(
+                 LZ4_stream_t_internal* const cctx,
+                 const char* const source,
+                 char* const dest,
+                 const int inputSize,
+                 int *inputConsumed, /* only written when outputDirective == fillOutput */
+                 const int maxOutputSize,
+                 const limitedOutput_directive outputDirective,
+                 const tableType_t tableType,
+                 const dict_directive dictDirective,
+                 const dictIssue_directive dictIssue,
+                 const int acceleration)
+{
+    int result;
+    const BYTE* ip = (const BYTE*) source;
+
+    U32 const startIndex = cctx->currentOffset;
+    const BYTE* base = (const BYTE*) source - startIndex;
+    const BYTE* lowLimit;
+
+    const LZ4_stream_t_internal* dictCtx = (const LZ4_stream_t_internal*) cctx->dictCtx;
+    const BYTE* const dictionary =
+        dictDirective == usingDictCtx ? dictCtx->dictionary : cctx->dictionary;
+    const U32 dictSize =
+        dictDirective == usingDictCtx ? dictCtx->dictSize : cctx->dictSize;
+    const U32 dictDelta = (dictDirective == usingDictCtx) ? startIndex - dictCtx->currentOffset : 0;   /* make indexes in dictCtx comparable with index in current context */
+
+    int const maybe_extMem = (dictDirective == usingExtDict) || (dictDirective == usingDictCtx);
+    U32 const prefixIdxLimit = startIndex - dictSize;   /* used when dictDirective == dictSmall */
+    const BYTE* const dictEnd = dictionary + dictSize;
+    const BYTE* anchor = (const BYTE*) source;
+    const BYTE* const iend = ip + inputSize;
+    const BYTE* const mflimitPlusOne = iend - MFLIMIT + 1;
+    const BYTE* const matchlimit = iend - LASTLITERALS;
+
+    /* the dictCtx currentOffset is indexed on the start of the dictionary,
+     * while a dictionary in the current context precedes the currentOffset */
+    const BYTE* dictBase = (dictDirective == usingDictCtx) ?
+                            dictionary + dictSize - dictCtx->currentOffset :
+                            dictionary + dictSize - startIndex;
+
+    BYTE* op = (BYTE*) dest;
+    BYTE* const olimit = op + maxOutputSize;
+
+    U32 offset = 0;
+    U32 forwardH;
+
+    DEBUGLOG(5, "LZ4_compress_generic: srcSize=%i, tableType=%u", inputSize, tableType);
+    /* If init conditions are not met, we don't have to mark stream
+     * as having dirty context, since no action was taken yet */
+    if (outputDirective == fillOutput && maxOutputSize < 1) { return 0; } /* Impossible to store anything */
+    if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) { return 0; }           /* Unsupported inputSize, too large (or negative) */
+    if ((tableType == byU16) && (inputSize>=LZ4_64Klimit)) { return 0; }  /* Size too large (not within 64K limit) */
+    if (tableType==byPtr) assert(dictDirective==noDict);      /* only supported use case with byPtr */
+    assert(acceleration >= 1);
+
+    lowLimit = (const BYTE*)source - (dictDirective == withPrefix64k ? dictSize : 0);
+
+    /* Update context state */
+    if (dictDirective == usingDictCtx) {
+        /* Subsequent linked blocks can't use the dictionary. */
+        /* Instead, they use the block we just compressed. */
+        cctx->dictCtx = NULL;
+        cctx->dictSize = (U32)inputSize;
+    } else {
+        cctx->dictSize += (U32)inputSize;
+    }
+    cctx->currentOffset += (U32)inputSize;
+    cctx->tableType = (U16)tableType;
+
+    if (inputSize<LZ4_minLength) goto _last_literals;        /* Input too small, no compression (all literals) */
+
+    /* First Byte */
+    LZ4_putPosition(ip, cctx->hashTable, tableType, base);
+    ip++; forwardH = LZ4_hashPosition(ip, tableType);
+
+    /* Main Loop */
+    for ( ; ; ) {
+        const BYTE* match;
+        BYTE* token;
+        const BYTE* filledIp;
+
+        /* Find a match */
+        if (tableType == byPtr) {
+            const BYTE* forwardIp = ip;
+            int step = 1;
+            int searchMatchNb = acceleration << LZ4_skipTrigger;
+            do {
+                U32 const h = forwardH;
+                ip = forwardIp;
+                forwardIp += step;
+                step = (searchMatchNb++ >> LZ4_skipTrigger);
+
+                if (unlikely(forwardIp > mflimitPlusOne)) goto _last_literals;
+                assert(ip < mflimitPlusOne);
+
+                match = LZ4_getPositionOnHash(h, cctx->hashTable, tableType, base);
+                forwardH = LZ4_hashPosition(forwardIp, tableType);
+                LZ4_putPositionOnHash(ip, h, cctx->hashTable, tableType, base);
+
+            } while ( (match+LZ4_DISTANCE_MAX < ip)
+                   || (LZ4_read32(match) != LZ4_read32(ip)) );
+
+        } else {   /* byU32, byU16 */
+
+            const BYTE* forwardIp = ip;
+            int step = 1;
+            int searchMatchNb = acceleration << LZ4_skipTrigger;
+            do {
+                U32 const h = forwardH;
+                U32 const current = (U32)(forwardIp - base);
+                U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType);
+                assert(matchIndex <= current);
+                assert(forwardIp - base < (ptrdiff_t)(2 GB - 1));
+                ip = forwardIp;
+                forwardIp += step;
+                step = (searchMatchNb++ >> LZ4_skipTrigger);
+
+                if (unlikely(forwardIp > mflimitPlusOne)) goto _last_literals;
+                assert(ip < mflimitPlusOne);
+
+                if (dictDirective == usingDictCtx) {
+                    if (matchIndex < startIndex) {
+                        /* there was no match, try the dictionary */
+                        assert(tableType == byU32);
+                        matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32);
+                        match = dictBase + matchIndex;
+                        matchIndex += dictDelta;   /* make dictCtx index comparable with current context */
+                        lowLimit = dictionary;
+                    } else {
+                        match = base + matchIndex;
+                        lowLimit = (const BYTE*)source;
+                    }
+                } else if (dictDirective==usingExtDict) {
+                    if (matchIndex < startIndex) {
+                        DEBUGLOG(7, "extDict candidate: matchIndex=%5u  <  startIndex=%5u", matchIndex, startIndex);
+                        assert(startIndex - matchIndex >= MINMATCH);
+                        match = dictBase + matchIndex;
+                        lowLimit = dictionary;
+                    } else {
+                        match = base + matchIndex;
+                        lowLimit = (const BYTE*)source;
+                    }
+                } else {   /* single continuous memory segment */
+                    match = base + matchIndex;
+                }
+                forwardH = LZ4_hashPosition(forwardIp, tableType);
+                LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType);
+
+                DEBUGLOG(7, "candidate at pos=%u  (offset=%u \n", matchIndex, current - matchIndex);
+                if ((dictIssue == dictSmall) && (matchIndex < prefixIdxLimit)) { continue; }    /* match outside of valid area */
+                assert(matchIndex < current);
+                if ( ((tableType != byU16) || (LZ4_DISTANCE_MAX < LZ4_DISTANCE_ABSOLUTE_MAX))
+                  && (matchIndex+LZ4_DISTANCE_MAX < current)) {
+                    continue;
+                } /* too far */
+                assert((current - matchIndex) <= LZ4_DISTANCE_MAX);  /* match now expected within distance */
+
+                if (LZ4_read32(match) == LZ4_read32(ip)) {
+                    if (maybe_extMem) offset = current - matchIndex;
+                    break;   /* match found */
+                }
+
+            } while(1);
+        }
+
+        /* Catch up */
+        filledIp = ip;
+        while (((ip>anchor) & (match > lowLimit)) && (unlikely(ip[-1]==match[-1]))) { ip--; match--; }
+
+        /* Encode Literals */
+        {   unsigned const litLength = (unsigned)(ip - anchor);
+            token = op++;
+            if ((outputDirective == limitedOutput) &&  /* Check output buffer overflow */
+                (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)) ) {
+                return 0;   /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */
+            }
+            if ((outputDirective == fillOutput) &&
+                (unlikely(op + (litLength+240)/255 /* litlen */ + litLength /* literals */ + 2 /* offset */ + 1 /* token */ + MFLIMIT - MINMATCH /* min last literals so last match is <= end - MFLIMIT */ > olimit))) {
+                op--;
+                goto _last_literals;
+            }
+            if (litLength >= RUN_MASK) {
+                int len = (int)(litLength - RUN_MASK);
+                *token = (RUN_MASK<<ML_BITS);
+                for(; len >= 255 ; len-=255) *op++ = 255;
+                *op++ = (BYTE)len;
+            }
+            else *token = (BYTE)(litLength<<ML_BITS);
+
+            /* Copy Literals */
+            LZ4_wildCopy8(op, anchor, op+litLength);
+            op+=litLength;
+            DEBUGLOG(6, "seq.start:%i, literals=%u, match.start:%i",
+                        (int)(anchor-(const BYTE*)source), litLength, (int)(ip-(const BYTE*)source));
+        }
+
+_next_match:
+        /* at this stage, the following variables must be correctly set :
+         * - ip : at start of LZ operation
+         * - match : at start of previous pattern occurence; can be within current prefix, or within extDict
+         * - offset : if maybe_ext_memSegment==1 (constant)
+         * - lowLimit : must be == dictionary to mean "match is within extDict"; must be == source otherwise
+         * - token and *token : position to write 4-bits for match length; higher 4-bits for literal length supposed already written
+         */
+
+        if ((outputDirective == fillOutput) &&
+            (op + 2 /* offset */ + 1 /* token */ + MFLIMIT - MINMATCH /* min last literals so last match is <= end - MFLIMIT */ > olimit)) {
+            /* the match was too close to the end, rewind and go to last literals */
+            op = token;
+            goto _last_literals;
+        }
+
+        /* Encode Offset */
+        if (maybe_extMem) {   /* static test */
+            DEBUGLOG(6, "             with offset=%u  (ext if > %i)", offset, (int)(ip - (const BYTE*)source));
+            assert(offset <= LZ4_DISTANCE_MAX && offset > 0);
+            LZ4_writeLE16(op, (U16)offset); op+=2;
+        } else  {
+            DEBUGLOG(6, "             with offset=%u  (same segment)", (U32)(ip - match));
+            assert(ip-match <= LZ4_DISTANCE_MAX);
+            LZ4_writeLE16(op, (U16)(ip - match)); op+=2;
+        }
+
+        /* Encode MatchLength */
+        {   unsigned matchCode;
+
+            if ( (dictDirective==usingExtDict || dictDirective==usingDictCtx)
+              && (lowLimit==dictionary) /* match within extDict */ ) {
+                const BYTE* limit = ip + (dictEnd-match);
+                assert(dictEnd > match);
+                if (limit > matchlimit) limit = matchlimit;
+                matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, limit);
+                ip += (size_t)matchCode + MINMATCH;
+                if (ip==limit) {
+                    unsigned const more = LZ4_count(limit, (const BYTE*)source, matchlimit);
+                    matchCode += more;
+                    ip += more;
+                }
+                DEBUGLOG(6, "             with matchLength=%u starting in extDict", matchCode+MINMATCH);
+            } else {
+                matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit);
+                ip += (size_t)matchCode + MINMATCH;
+                DEBUGLOG(6, "             with matchLength=%u", matchCode+MINMATCH);
+            }
+
+            if ((outputDirective) &&    /* Check output buffer overflow */
+                (unlikely(op + (1 + LASTLITERALS) + (matchCode+240)/255 > olimit)) ) {
+                if (outputDirective == fillOutput) {
+                    /* Match description too long : reduce it */
+                    U32 newMatchCode = 15 /* in token */ - 1 /* to avoid needing a zero byte */ + ((U32)(olimit - op) - 1 - LASTLITERALS) * 255;
+                    ip -= matchCode - newMatchCode;
+                    assert(newMatchCode < matchCode);
+                    matchCode = newMatchCode;
+                    if (unlikely(ip <= filledIp)) {
+                        /* We have already filled up to filledIp so if ip ends up less than filledIp
+                         * we have positions in the hash table beyond the current position. This is
+                         * a problem if we reuse the hash table. So we have to remove these positions
+                         * from the hash table.
+                         */
+                        const BYTE* ptr;
+                        DEBUGLOG(5, "Clearing %u positions", (U32)(filledIp - ip));
+                        for (ptr = ip; ptr <= filledIp; ++ptr) {
+                            U32 const h = LZ4_hashPosition(ptr, tableType);
+                            LZ4_clearHash(h, cctx->hashTable, tableType);
+                        }
+                    }
+                } else {
+                    assert(outputDirective == limitedOutput);
+                    return 0;   /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */
+                }
+            }
+            if (matchCode >= ML_MASK) {
+                *token += ML_MASK;
+                matchCode -= ML_MASK;
+                LZ4_write32(op, 0xFFFFFFFF);
+                while (matchCode >= 4*255) {
+                    op+=4;
+                    LZ4_write32(op, 0xFFFFFFFF);
+                    matchCode -= 4*255;
+                }
+                op += matchCode / 255;
+                *op++ = (BYTE)(matchCode % 255);
+            } else
+                *token += (BYTE)(matchCode);
+        }
+        /* Ensure we have enough space for the last literals. */
+        assert(!(outputDirective == fillOutput && op + 1 + LASTLITERALS > olimit));
+
+        anchor = ip;
+
+        /* Test end of chunk */
+        if (ip >= mflimitPlusOne) break;
+
+        /* Fill table */
+        LZ4_putPosition(ip-2, cctx->hashTable, tableType, base);
+
+        /* Test next position */
+        if (tableType == byPtr) {
+
+            match = LZ4_getPosition(ip, cctx->hashTable, tableType, base);
+            LZ4_putPosition(ip, cctx->hashTable, tableType, base);
+            if ( (match+LZ4_DISTANCE_MAX >= ip)
+              && (LZ4_read32(match) == LZ4_read32(ip)) )
+            { token=op++; *token=0; goto _next_match; }
+
+        } else {   /* byU32, byU16 */
+
+            U32 const h = LZ4_hashPosition(ip, tableType);
+            U32 const current = (U32)(ip-base);
+            U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType);
+            assert(matchIndex < current);
+            if (dictDirective == usingDictCtx) {
+                if (matchIndex < startIndex) {
+                    /* there was no match, try the dictionary */
+                    matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32);
+                    match = dictBase + matchIndex;
+                    lowLimit = dictionary;   /* required for match length counter */
+                    matchIndex += dictDelta;
+                } else {
+                    match = base + matchIndex;
+                    lowLimit = (const BYTE*)source;  /* required for match length counter */
+                }
+            } else if (dictDirective==usingExtDict) {
+                if (matchIndex < startIndex) {
+                    match = dictBase + matchIndex;
+                    lowLimit = dictionary;   /* required for match length counter */
+                } else {
+                    match = base + matchIndex;
+                    lowLimit = (const BYTE*)source;   /* required for match length counter */
+                }
+            } else {   /* single memory segment */
+                match = base + matchIndex;
+            }
+            LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType);
+            assert(matchIndex < current);
+            if ( ((dictIssue==dictSmall) ? (matchIndex >= prefixIdxLimit) : 1)
+              && (((tableType==byU16) && (LZ4_DISTANCE_MAX == LZ4_DISTANCE_ABSOLUTE_MAX)) ? 1 : (matchIndex+LZ4_DISTANCE_MAX >= current))
+              && (LZ4_read32(match) == LZ4_read32(ip)) ) {
+                token=op++;
+                *token=0;
+                if (maybe_extMem) offset = current - matchIndex;
+                DEBUGLOG(6, "seq.start:%i, literals=%u, match.start:%i",
+                            (int)(anchor-(const BYTE*)source), 0, (int)(ip-(const BYTE*)source));
+                goto _next_match;
+            }
+        }
+
+        /* Prepare next loop */
+        forwardH = LZ4_hashPosition(++ip, tableType);
+
+    }
+
+_last_literals:
+    /* Encode Last Literals */
+    {   size_t lastRun = (size_t)(iend - anchor);
+        if ( (outputDirective) &&  /* Check output buffer overflow */
+            (op + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > olimit)) {
+            if (outputDirective == fillOutput) {
+                /* adapt lastRun to fill 'dst' */
+                assert(olimit >= op);
+                lastRun  = (size_t)(olimit-op) - 1;
+                lastRun -= (lastRun+240)/255;
+            } else {
+                assert(outputDirective == limitedOutput);
+                return 0;   /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */
+            }
+        }
+        if (lastRun >= RUN_MASK) {
+            size_t accumulator = lastRun - RUN_MASK;
+            *op++ = RUN_MASK << ML_BITS;
+            for(; accumulator >= 255 ; accumulator-=255) *op++ = 255;
+            *op++ = (BYTE) accumulator;
+        } else {
+            *op++ = (BYTE)(lastRun<<ML_BITS);
+        }
+        memcpy(op, anchor, lastRun);
+        ip = anchor + lastRun;
+        op += lastRun;
+    }
+
+    if (outputDirective == fillOutput) {
+        *inputConsumed = (int) (((const char*)ip)-source);
+    }
+    DEBUGLOG(5, "LZ4_compress_generic: compressed %i bytes into %i bytes", inputSize, (int)(((char*)op) - dest));
+    result = (int)(((char*)op) - dest);
+    assert(result > 0);
+    return result;
+}
+
+
+int LZ4_compress_fast_extState(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
+{
+    LZ4_stream_t_internal* const ctx = & LZ4_initStream(state, sizeof(LZ4_stream_t)) -> internal_donotuse;
+    assert(ctx != NULL);
+    if (acceleration < 1) acceleration = ACCELERATION_DEFAULT;
+    if (maxOutputSize >= LZ4_compressBound(inputSize)) {
+        if (inputSize < LZ4_64Klimit) {
+            return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, 0, notLimited, byU16, noDict, noDictIssue, acceleration);
+        } else {
+            const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > LZ4_DISTANCE_MAX)) ? byPtr : byU32;
+            return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
+        }
+    } else {
+        if (inputSize < LZ4_64Klimit) {
+            return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration);
+        } else {
+            const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > LZ4_DISTANCE_MAX)) ? byPtr : byU32;
+            return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, noDict, noDictIssue, acceleration);
+        }
+    }
+}
+
+static int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
+{
+    int result;
+#if (LZ4_HEAPMODE)
+    LZ4_stream_t* ctxPtr = ALLOC(sizeof(LZ4_stream_t));   /* malloc-calloc always properly aligned */
+    if (ctxPtr == NULL) return 0;
+#else
+    LZ4_stream_t ctx;
+    LZ4_stream_t* const ctxPtr = &ctx;
+#endif
+    result = LZ4_compress_fast_extState(ctxPtr, source, dest, inputSize, maxOutputSize, acceleration);
+
+#if (LZ4_HEAPMODE)
+    FREEMEM(ctxPtr);
+#endif
+    return result;
+}
+
+
+int LZ4_compress_default(const char* src, char* dst, int srcSize, int maxOutputSize)
+{
+    return LZ4_compress_fast(src, dst, srcSize, maxOutputSize, 1);
+}
+
+/*-******************************
+*  Streaming functions
+********************************/
+
+#ifndef _MSC_VER  /* for some reason, Visual fails the aligment test on 32-bit x86 :
+                     it reports an aligment of 8-bytes,
+                     while actually aligning LZ4_stream_t on 4 bytes. */
+static size_t LZ4_stream_t_alignment(void)
+{
+    struct { char c; LZ4_stream_t t; } t_a;
+    return sizeof(t_a) - sizeof(t_a.t);
+}
+#endif
+
+LZ4_stream_t* LZ4_initStream (void* buffer, size_t size)
+{
+    DEBUGLOG(5, "LZ4_initStream");
+    if (buffer == NULL) { return NULL; }
+    if (size < sizeof(LZ4_stream_t)) { return NULL; }
+#ifndef _MSC_VER  /* for some reason, Visual fails the aligment test on 32-bit x86 :
+                     it reports an aligment of 8-bytes,
+                     while actually aligning LZ4_stream_t on 4 bytes. */
+    if (((size_t)buffer) & (LZ4_stream_t_alignment() - 1)) { return NULL; } /* alignment check */
+#endif
+    MEM_INIT(buffer, 0, sizeof(LZ4_stream_t));
+    return (LZ4_stream_t*)buffer;
+}
+
+/*-*******************************
+ *  Decompression functions
+ ********************************/
+
+typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive;
+typedef enum { decode_full_block = 0, partial_decode = 1 } earlyEnd_directive;
+
+#undef MIN
+#define MIN(a,b)    ( (a) < (b) ? (a) : (b) )
+
+/* Read the variable-length literal or match length.
+ *
+ * ip - pointer to use as input.
+ * lencheck - end ip.  Return an error if ip advances >= lencheck.
+ * loop_check - check ip >= lencheck in body of loop.  Returns loop_error if so.
+ * initial_check - check ip >= lencheck before start of loop.  Returns initial_error if so.
+ * error (output) - error code.  Should be set to 0 before call.
+ */
+typedef enum { loop_error = -2, initial_error = -1, ok = 0 } variable_length_error;
+LZ4_FORCE_INLINE unsigned
+read_variable_length(const BYTE**ip, const BYTE* lencheck, int loop_check, int initial_check, variable_length_error* error)
+{
+  unsigned length = 0;
+  unsigned s;
+  if (initial_check && unlikely((*ip) >= lencheck)) {    /* overflow detection */
+    *error = initial_error;
+    return length;
+  }
+  do {
+    s = **ip;
+    (*ip)++;
+    length += s;
+    if (loop_check && unlikely((*ip) >= lencheck)) {    /* overflow detection */
+      *error = loop_error;
+      return length;
+    }
+  } while (s==255);
+
+  return length;
+}
+
+/*! LZ4_decompress_generic() :
+ *  This generic decompression function covers all use cases.
+ *  It shall be instantiated several times, using different sets of directives.
+ *  Note that it is important for performance that this function really get inlined,
+ *  in order to remove useless branches during compilation optimization.
+ */
+LZ4_FORCE_INLINE int
+LZ4_decompress_generic(
+                 const char* const src,
+                 char* const dst,
+                 int srcSize,
+                 int outputSize,         /* If endOnInput==endOnInputSize, this value is `dstCapacity` */
+
+                 endCondition_directive endOnInput,   /* endOnOutputSize, endOnInputSize */
+                 earlyEnd_directive partialDecoding,  /* full, partial */
+                 dict_directive dict,                 /* noDict, withPrefix64k, usingExtDict */
+                 const BYTE* const lowPrefix,  /* always <= dst, == dst when no prefix */
+                 const BYTE* const dictStart,  /* only if dict==usingExtDict */
+                 const size_t dictSize         /* note : = 0 if noDict */
+                 )
+{
+    if (src == NULL) { return -1; }
+
+    {   const BYTE* ip = (const BYTE*) src;
+        const BYTE* const iend = ip + srcSize;
+
+        BYTE* op = (BYTE*) dst;
+        BYTE* const oend = op + outputSize;
+        BYTE* cpy;
+
+        const BYTE* const dictEnd = (dictStart == NULL) ? NULL : dictStart + dictSize;
+
+        const int safeDecode = (endOnInput==endOnInputSize);
+        const int checkOffset = ((safeDecode) && (dictSize < (int)(64 KB)));
+
+
+        /* Set up the "end" pointers for the shortcut. */
+        const BYTE* const shortiend = iend - (endOnInput ? 14 : 8) /*maxLL*/ - 2 /*offset*/;
+        const BYTE* const shortoend = oend - (endOnInput ? 14 : 8) /*maxLL*/ - 18 /*maxML*/;
+
+        const BYTE* match;
+        size_t offset;
+        unsigned token;
+        size_t length;
+
+
+        DEBUGLOG(5, "LZ4_decompress_generic (srcSize:%i, dstSize:%i)", srcSize, outputSize);
+
+        /* Special cases */
+        assert(lowPrefix <= op);
+        if ((endOnInput) && (unlikely(outputSize==0))) {
+            /* Empty output buffer */
+            if (partialDecoding) return 0;
+            return ((srcSize==1) && (*ip==0)) ? 0 : -1;
+        }
+        if ((!endOnInput) && (unlikely(outputSize==0))) { return (*ip==0 ? 1 : -1); }
+        if ((endOnInput) && unlikely(srcSize==0)) { return -1; }
+
+	/* Currently the fast loop shows a regression on qualcomm arm chips. */
+#if LZ4_FAST_DEC_LOOP
+        if ((oend - op) < FASTLOOP_SAFE_DISTANCE) {
+            DEBUGLOG(6, "skip fast decode loop");
+            goto safe_decode;
+        }
+
+        /* Fast loop : decode sequences as long as output < iend-FASTLOOP_SAFE_DISTANCE */
+        while (1) {
+            /* Main fastloop assertion: We can always wildcopy FASTLOOP_SAFE_DISTANCE */
+            assert(oend - op >= FASTLOOP_SAFE_DISTANCE);
+            if (endOnInput) { assert(ip < iend); }
+            token = *ip++;
+            length = token >> ML_BITS;  /* literal length */
+
+            assert(!endOnInput || ip <= iend); /* ip < iend before the increment */
+
+            /* decode literal length */
+            if (length == RUN_MASK) {
+                variable_length_error error = ok;
+                length += read_variable_length(&ip, iend-RUN_MASK, endOnInput, endOnInput, &error);
+                if (error == initial_error) { goto _output_error; }
+                if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)(op))) { goto _output_error; } /* overflow detection */
+                if ((safeDecode) && unlikely((uptrval)(ip)+length<(uptrval)(ip))) { goto _output_error; } /* overflow detection */
+
+                /* copy literals */
+                cpy = op+length;
+                LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH);
+                if (endOnInput) {  /* LZ4_decompress_safe() */
+                    if ((cpy>oend-32) || (ip+length>iend-32)) { goto safe_literal_copy; }
+                    LZ4_wildCopy32(op, ip, cpy);
+                } else {   /* LZ4_decompress_fast() */
+                    if (cpy>oend-8) { goto safe_literal_copy; }
+                    LZ4_wildCopy8(op, ip, cpy); /* LZ4_decompress_fast() cannot copy more than 8 bytes at a time :
+                                                 * it doesn't know input length, and only relies on end-of-block properties */
+                }
+                ip += length; op = cpy;
+            } else {
+                cpy = op+length;
+                if (endOnInput) {  /* LZ4_decompress_safe() */
+                    DEBUGLOG(7, "copy %u bytes in a 16-bytes stripe", (unsigned)length);
+                    /* We don't need to check oend, since we check it once for each loop below */
+                    if (ip > iend-(16 + 1/*max lit + offset + nextToken*/)) { goto safe_literal_copy; }
+                    /* Literals can only be 14, but hope compilers optimize if we copy by a register size */
+                    memcpy(op, ip, 16);
+                } else {  /* LZ4_decompress_fast() */
+                    /* LZ4_decompress_fast() cannot copy more than 8 bytes at a time :
+                     * it doesn't know input length, and relies on end-of-block properties */
+                    memcpy(op, ip, 8);
+                    if (length > 8) { memcpy(op+8, ip+8, 8); }
+                }
+                ip += length; op = cpy;
+            }
+
+            /* get offset */
+            offset = LZ4_readLE16(ip); ip+=2;
+            match = op - offset;
+            assert(match <= op);
+
+            /* get matchlength */
+            length = token & ML_MASK;
+
+            if (length == ML_MASK) {
+              variable_length_error error = ok;
+              if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) { goto _output_error; } /* Error : offset outside buffers */
+              length += read_variable_length(&ip, iend - LASTLITERALS + 1, endOnInput, 0, &error);
+              if (error != ok) { goto _output_error; }
+                if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) { goto _output_error; } /* overflow detection */
+                length += MINMATCH;
+                if (op + length >= oend - FASTLOOP_SAFE_DISTANCE) {
+                    goto safe_match_copy;
+                }
+            } else {
+                length += MINMATCH;
+                if (op + length >= oend - FASTLOOP_SAFE_DISTANCE) {
+                    goto safe_match_copy;
+                }
+
+                /* Fastpath check: Avoids a branch in LZ4_wildCopy32 if true */
+                if ((dict == withPrefix64k) || (match >= lowPrefix)) {
+                    if (offset >= 8) {
+                        assert(match >= lowPrefix);
+                        assert(match <= op);
+                        assert(op + 18 <= oend);
+
+                        memcpy(op, match, 8);
+                        memcpy(op+8, match+8, 8);
+                        memcpy(op+16, match+16, 2);
+                        op += length;
+                        continue;
+            }   }   }
+
+            if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) { goto _output_error; } /* Error : offset outside buffers */
+            /* match starting within external dictionary */
+            if ((dict==usingExtDict) && (match < lowPrefix)) {
+                if (unlikely(op+length > oend-LASTLITERALS)) {
+                    if (partialDecoding) {
+                        length = MIN(length, (size_t)(oend-op));  /* reach end of buffer */
+                    } else {
+                        goto _output_error;  /* end-of-block condition violated */
+                }   }
+
+                if (length <= (size_t)(lowPrefix-match)) {
+                    /* match fits entirely within external dictionary : just copy */
+                    memmove(op, dictEnd - (lowPrefix-match), length);
+                    op += length;
+                } else {
+                    /* match stretches into both external dictionary and current block */
+                    size_t const copySize = (size_t)(lowPrefix - match);
+                    size_t const restSize = length - copySize;
+                    memcpy(op, dictEnd - copySize, copySize);
+                    op += copySize;
+                    if (restSize > (size_t)(op - lowPrefix)) {  /* overlap copy */
+                        BYTE* const endOfMatch = op + restSize;
+                        const BYTE* copyFrom = lowPrefix;
+                        while (op < endOfMatch) { *op++ = *copyFrom++; }
+                    } else {
+                        memcpy(op, lowPrefix, restSize);
+                        op += restSize;
+                }   }
+                continue;
+            }
+
+            /* copy match within block */
+            cpy = op + length;
+
+            assert((op <= oend) && (oend-op >= 32));
+            if (unlikely(offset<16)) {
+                LZ4_memcpy_using_offset(op, match, cpy, offset);
+            } else {
+                LZ4_wildCopy32(op, match, cpy);
+            }
+
+            op = cpy;   /* wildcopy correction */
+        }
+    safe_decode:
+#endif
+
+        /* Main Loop : decode remaining sequences where output < FASTLOOP_SAFE_DISTANCE */
+        while (1) {
+            token = *ip++;
+            length = token >> ML_BITS;  /* literal length */
+
+            assert(!endOnInput || ip <= iend); /* ip < iend before the increment */
+
+            /* A two-stage shortcut for the most common case:
+             * 1) If the literal length is 0..14, and there is enough space,
+             * enter the shortcut and copy 16 bytes on behalf of the literals
+             * (in the fast mode, only 8 bytes can be safely copied this way).
+             * 2) Further if the match length is 4..18, copy 18 bytes in a similar
+             * manner; but we ensure that there's enough space in the output for
+             * those 18 bytes earlier, upon entering the shortcut (in other words,
+             * there is a combined check for both stages).
+             */
+            if ( (endOnInput ? length != RUN_MASK : length <= 8)
+                /* strictly "less than" on input, to re-enter the loop with at least one byte */
+              && likely((endOnInput ? ip < shortiend : 1) & (op <= shortoend)) ) {
+                /* Copy the literals */
+                memcpy(op, ip, endOnInput ? 16 : 8);
+                op += length; ip += length;
+
+                /* The second stage: prepare for match copying, decode full info.
+                 * If it doesn't work out, the info won't be wasted. */
+                length = token & ML_MASK; /* match length */
+                offset = LZ4_readLE16(ip); ip += 2;
+                match = op - offset;
+                assert(match <= op); /* check overflow */
+
+                /* Do not deal with overlapping matches. */
+                if ( (length != ML_MASK)
+                  && (offset >= 8)
+                  && (dict==withPrefix64k || match >= lowPrefix) ) {
+                    /* Copy the match. */
+                    memcpy(op + 0, match + 0, 8);
+                    memcpy(op + 8, match + 8, 8);
+                    memcpy(op +16, match +16, 2);
+                    op += length + MINMATCH;
+                    /* Both stages worked, load the next token. */
+                    continue;
+                }
+
+                /* The second stage didn't work out, but the info is ready.
+                 * Propel it right to the point of match copying. */
+                goto _copy_match;
+            }
+
+            /* decode literal length */
+            if (length == RUN_MASK) {
+                variable_length_error error = ok;
+                length += read_variable_length(&ip, iend-RUN_MASK, endOnInput, endOnInput, &error);
+                if (error == initial_error) { goto _output_error; }
+                if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)(op))) { goto _output_error; } /* overflow detection */
+                if ((safeDecode) && unlikely((uptrval)(ip)+length<(uptrval)(ip))) { goto _output_error; } /* overflow detection */
+            }
+
+            /* copy literals */
+            cpy = op+length;
+#if LZ4_FAST_DEC_LOOP
+        safe_literal_copy:
+#endif
+            LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH);
+            if ( ((endOnInput) && ((cpy>oend-MFLIMIT) || (ip+length>iend-(2+1+LASTLITERALS))) )
+              || ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)) )
+            {
+                /* We've either hit the input parsing restriction or the output parsing restriction.
+                 * If we've hit the input parsing condition then this must be the last sequence.
+                 * If we've hit the output parsing condition then we are either using partialDecoding
+                 * or we've hit the output parsing condition.
+                 */
+                if (partialDecoding) {
+                    /* Since we are partial decoding we may be in this block because of the output parsing
+                     * restriction, which is not valid since the output buffer is allowed to be undersized.
+                     */
+                    assert(endOnInput);
+                    /* If we're in this block because of the input parsing condition, then we must be on the
+                     * last sequence (or invalid), so we must check that we exactly consume the input.
+                     */
+                    if ((ip+length>iend-(2+1+LASTLITERALS)) && (ip+length != iend)) { goto _output_error; }
+                    assert(ip+length <= iend);
+                    /* We are finishing in the middle of a literals segment.
+                     * Break after the copy.
+                     */
+                    if (cpy > oend) {
+                        cpy = oend;
+                        assert(op<=oend);
+                        length = (size_t)(oend-op);
+                    }
+                    assert(ip+length <= iend);
+                } else {
+                    /* We must be on the last sequence because of the parsing limitations so check
+                     * that we exactly regenerate the original size (must be exact when !endOnInput).
+                     */
+                    if ((!endOnInput) && (cpy != oend)) { goto _output_error; }
+                     /* We must be on the last sequence (or invalid) because of the parsing limitations
+                      * so check that we exactly consume the input and don't overrun the output buffer.
+                      */
+                    if ((endOnInput) && ((ip+length != iend) || (cpy > oend))) { goto _output_error; }
+                }
+                memmove(op, ip, length);  /* supports overlapping memory regions, which only matters for in-place decompression scenarios */
+                ip += length;
+                op += length;
+                /* Necessarily EOF when !partialDecoding. When partialDecoding
+                 * it is EOF if we've either filled the output buffer or hit
+                 * the input parsing restriction.
+                 */
+                if (!partialDecoding || (cpy == oend) || (ip == iend)) {
+                    break;
+                }
+            } else {
+                LZ4_wildCopy8(op, ip, cpy);   /* may overwrite up to WILDCOPYLENGTH beyond cpy */
+                ip += length; op = cpy;
+            }
+
+            /* get offset */
+            offset = LZ4_readLE16(ip); ip+=2;
+            match = op - offset;
+
+            /* get matchlength */
+            length = token & ML_MASK;
+
+    _copy_match:
+            if (length == ML_MASK) {
+              variable_length_error error = ok;
+              length += read_variable_length(&ip, iend - LASTLITERALS + 1, endOnInput, 0, &error);
+              if (error != ok) goto _output_error;
+                if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error;   /* overflow detection */
+            }
+            length += MINMATCH;
+
+#if LZ4_FAST_DEC_LOOP
+        safe_match_copy:
+#endif
+            if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error;   /* Error : offset outside buffers */
+            /* match starting within external dictionary */
+            if ((dict==usingExtDict) && (match < lowPrefix)) {
+                if (unlikely(op+length > oend-LASTLITERALS)) {
+                    if (partialDecoding) length = MIN(length, (size_t)(oend-op));
+                    else goto _output_error;   /* doesn't respect parsing restriction */
+                }
+
+                if (length <= (size_t)(lowPrefix-match)) {
+                    /* match fits entirely within external dictionary : just copy */
+                    memmove(op, dictEnd - (lowPrefix-match), length);
+                    op += length;
+                } else {
+                    /* match stretches into both external dictionary and current block */
+                    size_t const copySize = (size_t)(lowPrefix - match);
+                    size_t const restSize = length - copySize;
+                    memcpy(op, dictEnd - copySize, copySize);
+                    op += copySize;
+                    if (restSize > (size_t)(op - lowPrefix)) {  /* overlap copy */
+                        BYTE* const endOfMatch = op + restSize;
+                        const BYTE* copyFrom = lowPrefix;
+                        while (op < endOfMatch) *op++ = *copyFrom++;
+                    } else {
+                        memcpy(op, lowPrefix, restSize);
+                        op += restSize;
+                }   }
+                continue;
+            }
+            assert(match >= lowPrefix);
+
+            /* copy match within block */
+            cpy = op + length;
+
+            /* partialDecoding : may end anywhere within the block */
+            assert(op<=oend);
+            if (partialDecoding && (cpy > oend-MATCH_SAFEGUARD_DISTANCE)) {
+                size_t const mlen = MIN(length, (size_t)(oend-op));
+                const BYTE* const matchEnd = match + mlen;
+                BYTE* const copyEnd = op + mlen;
+                if (matchEnd > op) {   /* overlap copy */
+                    while (op < copyEnd) { *op++ = *match++; }
+                } else {
+                    memcpy(op, match, mlen);
+                }
+                op = copyEnd;
+                if (op == oend) { break; }
+                continue;
+            }
+
+            if (unlikely(offset<8)) {
+                LZ4_write32(op, 0);   /* silence msan warning when offset==0 */
+                op[0] = match[0];
+                op[1] = match[1];
+                op[2] = match[2];
+                op[3] = match[3];
+                match += inc32table[offset];
+                memcpy(op+4, match, 4);
+                match -= dec64table[offset];
+            } else {
+                memcpy(op, match, 8);
+                match += 8;
+            }
+            op += 8;
+
+            if (unlikely(cpy > oend-MATCH_SAFEGUARD_DISTANCE)) {
+                BYTE* const oCopyLimit = oend - (WILDCOPYLENGTH-1);
+                if (cpy > oend-LASTLITERALS) { goto _output_error; } /* Error : last LASTLITERALS bytes must be literals (uncompressed) */
+                if (op < oCopyLimit) {
+                    LZ4_wildCopy8(op, match, oCopyLimit);
+                    match += oCopyLimit - op;
+                    op = oCopyLimit;
+                }
+                while (op < cpy) { *op++ = *match++; }
+            } else {
+                memcpy(op, match, 8);
+                if (length > 16)  { LZ4_wildCopy8(op+8, match+8, cpy); }
+            }
+            op = cpy;   /* wildcopy correction */
+        }
+
+        /* end of decoding */
+        if (endOnInput) {
+           return (int) (((char*)op)-dst);     /* Nb of output bytes decoded */
+       } else {
+           return (int) (((const char*)ip)-src);   /* Nb of input bytes read */
+       }
+
+        /* Overflow error detected */
+    _output_error:
+        return (int) (-(((const char*)ip)-src))-1;
+    }
+}
+
+
+/*===== Instantiate the API decoding functions. =====*/
+
+LZ4_FORCE_O2_GCC_PPC64LE
+int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxDecompressedSize)
+{
+    return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize,
+                                  endOnInputSize, decode_full_block, noDict,
+                                  (BYTE*)dest, NULL, 0);
+}
+
+#endif   /* LZ4_COMMONDEFS_ONLY */
diff --git a/lib/sqfs/comp/lz4/lz4.h b/lib/sqfs/comp/lz4/lz4.h
new file mode 100644
index 0000000..43d3b14
--- /dev/null
+++ b/lib/sqfs/comp/lz4/lz4.h
@@ -0,0 +1,341 @@
+/*
+ *  LZ4 - Fast LZ compression algorithm
+ *  Header File
+ *  Copyright (C) 2011-present, Yann Collet.
+
+   BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+
+   Redistribution and use in source and binary forms, with or without
+   modification, are permitted provided that the following conditions are
+   met:
+
+       * Redistributions of source code must retain the above copyright
+   notice, this list of conditions and the following disclaimer.
+       * Redistributions in binary form must reproduce the above
+   copyright notice, this list of conditions and the following disclaimer
+   in the documentation and/or other materials provided with the
+   distribution.
+
+   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+   You can contact the author at :
+    - LZ4 homepage : http://www.lz4.org
+    - LZ4 source repository : https://github.com/lz4/lz4
+*/
+#if defined (__cplusplus)
+extern "C" {
+#endif
+
+#ifndef LZ4_H_2983827168210
+#define LZ4_H_2983827168210
+
+/* --- Dependency --- */
+#include <stddef.h>   /* size_t */
+
+
+/**
+  Introduction
+
+  LZ4 is lossless compression algorithm, providing compression speed >500 MB/s per core,
+  scalable with multi-cores CPU. It features an extremely fast decoder, with speed in
+  multiple GB/s per core, typically reaching RAM speed limits on multi-core systems.
+
+  The LZ4 compression library provides in-memory compression and decompression functions.
+  It gives full buffer control to user.
+  Compression can be done in:
+    - a single step (described as Simple Functions)
+    - a single step, reusing a context (described in Advanced Functions)
+    - unbounded multiple steps (described as Streaming compression)
+
+  lz4.h generates and decodes LZ4-compressed blocks (doc/lz4_Block_format.md).
+  Decompressing such a compressed block requires additional metadata.
+  Exact metadata depends on exact decompression function.
+  For the typical case of LZ4_decompress_safe(),
+  metadata includes block's compressed size, and maximum bound of decompressed size.
+  Each application is free to encode and pass such metadata in whichever way it wants.
+
+  lz4.h only handle blocks, it can not generate Frames.
+
+  Blocks are different from Frames (doc/lz4_Frame_format.md).
+  Frames bundle both blocks and metadata in a specified manner.
+  Embedding metadata is required for compressed data to be self-contained and portable.
+  Frame format is delivered through a companion API, declared in lz4frame.h.
+  The `lz4` CLI can only manage frames.
+*/
+
+/*^***************************************************************
+*  Export parameters
+*****************************************************************/
+/*
+*  LZ4_DLL_EXPORT :
+*  Enable exporting of functions when building a Windows DLL
+*  LZ4LIB_VISIBILITY :
+*  Control library symbols visibility.
+*/
+#ifndef LZ4LIB_VISIBILITY
+#  if defined(__GNUC__) && (__GNUC__ >= 4)
+#    define LZ4LIB_VISIBILITY __attribute__ ((visibility ("hidden")))
+#  else
+#    define LZ4LIB_VISIBILITY
+#  endif
+#endif
+
+#define LZ4LIB_API LZ4LIB_VISIBILITY
+
+/*------   Version   ------*/
+#define LZ4_QUOTE(str) #str
+#define LZ4_EXPAND_AND_QUOTE(str) LZ4_QUOTE(str)
+#define LZ4_VERSION_STRING LZ4_EXPAND_AND_QUOTE(LZ4_LIB_VERSION)
+
+/*-************************************
+*  Tuning parameter
+**************************************/
+/*!
+ * LZ4_MEMORY_USAGE :
+ * Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.)
+ * Increasing memory usage improves compression ratio.
+ * Reduced memory usage may improve speed, thanks to better cache locality.
+ * Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache
+ */
+#ifndef LZ4_MEMORY_USAGE
+# define LZ4_MEMORY_USAGE 14
+#endif
+
+
+/*-************************************
+*  Simple Functions
+**************************************/
+/*! LZ4_compress_default() :
+ *  Compresses 'srcSize' bytes from buffer 'src'
+ *  into already allocated 'dst' buffer of size 'dstCapacity'.
+ *  Compression is guaranteed to succeed if 'dstCapacity' >= LZ4_compressBound(srcSize).
+ *  It also runs faster, so it's a recommended setting.
+ *  If the function cannot compress 'src' into a more limited 'dst' budget,
+ *  compression stops *immediately*, and the function result is zero.
+ *  In which case, 'dst' content is undefined (invalid).
+ *      srcSize : max supported value is LZ4_MAX_INPUT_SIZE.
+ *      dstCapacity : size of buffer 'dst' (which must be already allocated)
+ *     @return  : the number of bytes written into buffer 'dst' (necessarily <= dstCapacity)
+ *                or 0 if compression fails
+ * Note : This function is protected against buffer overflow scenarios (never writes outside 'dst' buffer, nor read outside 'source' buffer).
+ */
+LZ4LIB_API int LZ4_compress_default(const char* src, char* dst, int srcSize, int dstCapacity);
+
+/*! LZ4_decompress_safe() :
+ *  compressedSize : is the exact complete size of the compressed block.
+ *  dstCapacity : is the size of destination buffer (which must be already allocated), presumed an upper bound of decompressed size.
+ * @return : the number of bytes decompressed into destination buffer (necessarily <= dstCapacity)
+ *           If destination buffer is not large enough, decoding will stop and output an error code (negative value).
+ *           If the source stream is detected malformed, the function will stop decoding and return a negative result.
+ * Note 1 : This function is protected against malicious data packets :
+ *          it will never writes outside 'dst' buffer, nor read outside 'source' buffer,
+ *          even if the compressed block is maliciously modified to order the decoder to do these actions.
+ *          In such case, the decoder stops immediately, and considers the compressed block malformed.
+ * Note 2 : compressedSize and dstCapacity must be provided to the function, the compressed block does not contain them.
+ *          The implementation is free to send / store / derive this information in whichever way is most beneficial.
+ *          If there is a need for a different format which bundles together both compressed data and its metadata, consider looking at lz4frame.h instead.
+ */
+LZ4LIB_API int LZ4_decompress_safe (const char* src, char* dst, int compressedSize, int dstCapacity);
+
+
+/*-************************************
+*  Advanced Functions
+**************************************/
+#define LZ4_MAX_INPUT_SIZE        0x7E000000   /* 2 113 929 216 bytes */
+#define LZ4_COMPRESSBOUND(isize)  ((unsigned)(isize) > (unsigned)LZ4_MAX_INPUT_SIZE ? 0 : (isize) + ((isize)/255) + 16)
+
+/*! LZ4_compressBound() :
+    Provides the maximum size that LZ4 compression may output in a "worst case" scenario (input data not compressible)
+    This function is primarily useful for memory allocation purposes (destination buffer size).
+    Macro LZ4_COMPRESSBOUND() is also provided for compilation-time evaluation (stack memory allocation for example).
+    Note that LZ4_compress_default() compresses faster when dstCapacity is >= LZ4_compressBound(srcSize)
+        inputSize  : max supported value is LZ4_MAX_INPUT_SIZE
+        return : maximum output size in a "worst case" scenario
+              or 0, if input size is incorrect (too large or negative)
+*/
+LZ4LIB_API int LZ4_compressBound(int inputSize);
+
+
+/*! LZ4_compress_fast_extState() :
+ *  Same as LZ4_compress_fast(), using an externally allocated memory space for its state.
+ *  Use LZ4_sizeofState() to know how much memory must be allocated,
+ *  and allocate it on 8-bytes boundaries (using `malloc()` typically).
+ *  Then, provide this buffer as `void* state` to compression function.
+ */
+LZ4LIB_API int LZ4_sizeofState(void);
+LZ4LIB_API int LZ4_compress_fast_extState (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
+
+/*-*********************************************
+*  Streaming Compression Functions
+***********************************************/
+typedef union LZ4_stream_u LZ4_stream_t;  /* incomplete type (defined later) */
+
+/*-**********************************************
+*  Streaming Decompression Functions
+*  Bufferless synchronous API
+************************************************/
+typedef union LZ4_streamDecode_u LZ4_streamDecode_t;   /* tracking context */
+
+#endif /* LZ4_H_2983827168210 */
+
+
+/*^*************************************
+ * !!!!!!   STATIC LINKING ONLY   !!!!!!
+ ***************************************/
+
+/*-****************************************************************************
+ * Experimental section
+ *
+ * Symbols declared in this section must be considered unstable. Their
+ * signatures or semantics may change, or they may be removed altogether in the
+ * future. They are therefore only safe to depend on when the caller is
+ * statically linked against the library.
+ *
+ * To protect against unsafe usage, not only are the declarations guarded,
+ * the definitions are hidden by default
+ * when building LZ4 as a shared/dynamic library.
+ *
+ * In order to access these declarations,
+ * define LZ4_STATIC_LINKING_ONLY in your application
+ * before including LZ4's headers.
+ *
+ * In order to make their implementations accessible dynamically, you must
+ * define LZ4_PUBLISH_STATIC_FUNCTIONS when building the LZ4 library.
+ ******************************************************************************/
+
+#ifdef LZ4_STATIC_LINKING_ONLY
+
+#ifndef LZ4_STATIC_3504398509
+#define LZ4_STATIC_3504398509
+
+#define LZ4LIB_STATIC_API LZ4LIB_API
+
+#ifndef LZ4_DISTANCE_MAX   /* history window size; can be user-defined at compile time */
+#  define LZ4_DISTANCE_MAX 65535   /* set to maximum value by default */
+#endif
+
+#endif   /* LZ4_STATIC_3504398509 */
+#endif   /* LZ4_STATIC_LINKING_ONLY */
+
+
+
+#ifndef LZ4_H_98237428734687
+#define LZ4_H_98237428734687
+
+/*-************************************************************
+ *  PRIVATE DEFINITIONS
+ **************************************************************
+ * Do not use these definitions directly.
+ * They are only exposed to allow static allocation of `LZ4_stream_t` and `LZ4_streamDecode_t`.
+ * Accessing members will expose code to API and/or ABI break in future versions of the library.
+ **************************************************************/
+#define LZ4_HASHLOG   (LZ4_MEMORY_USAGE-2)
+#define LZ4_HASHTABLESIZE (1 << LZ4_MEMORY_USAGE)
+#define LZ4_HASH_SIZE_U32 (1 << LZ4_HASHLOG)       /* required as macro for static allocation */
+
+#if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */)
+#include <stdint.h>
+
+typedef struct LZ4_stream_t_internal LZ4_stream_t_internal;
+struct LZ4_stream_t_internal {
+    uint32_t hashTable[LZ4_HASH_SIZE_U32];
+    uint32_t currentOffset;
+    uint16_t dirty;
+    uint16_t tableType;
+    const uint8_t* dictionary;
+    const LZ4_stream_t_internal* dictCtx;
+    uint32_t dictSize;
+};
+
+typedef struct {
+    const uint8_t* externalDict;
+    size_t extDictSize;
+    const uint8_t* prefixEnd;
+    size_t prefixSize;
+} LZ4_streamDecode_t_internal;
+
+#else
+
+typedef struct LZ4_stream_t_internal LZ4_stream_t_internal;
+struct LZ4_stream_t_internal {
+    unsigned int hashTable[LZ4_HASH_SIZE_U32];
+    unsigned int currentOffset;
+    unsigned short dirty;
+    unsigned short tableType;
+    const unsigned char* dictionary;
+    const LZ4_stream_t_internal* dictCtx;
+    unsigned int dictSize;
+};
+
+typedef struct {
+    const unsigned char* externalDict;
+    const unsigned char* prefixEnd;
+    size_t extDictSize;
+    size_t prefixSize;
+} LZ4_streamDecode_t_internal;
+
+#endif
+
+/*! LZ4_stream_t :
+ *  information structure to track an LZ4 stream.
+ *  LZ4_stream_t can also be created using LZ4_createStream(), which is recommended.
+ *  The structure definition can be convenient for static allocation
+ *  (on stack, or as part of larger structure).
+ *  Init this structure with LZ4_initStream() before first use.
+ *  note : only use this definition in association with static linking !
+ *    this definition is not API/ABI safe, and may change in a future version.
+ */
+#define LZ4_STREAMSIZE_U64 ((1 << (LZ4_MEMORY_USAGE-3)) + 4 + ((sizeof(void*)==16) ? 4 : 0) /*AS-400*/ )
+#define LZ4_STREAMSIZE     (LZ4_STREAMSIZE_U64 * sizeof(unsigned long long))
+union LZ4_stream_u {
+    unsigned long long table[LZ4_STREAMSIZE_U64];
+    LZ4_stream_t_internal internal_donotuse;
+} ;  /* previously typedef'd to LZ4_stream_t */
+
+/*! LZ4_initStream() : v1.9.0+
+ *  An LZ4_stream_t structure must be initialized at least once.
+ *  This is automatically done when invoking LZ4_createStream(),
+ *  but it's not when the structure is simply declared on stack (for example).
+ *
+ *  Use LZ4_initStream() to properly initialize a newly declared LZ4_stream_t.
+ *  It can also initialize any arbitrary buffer of sufficient size,
+ *  and will @return a pointer of proper type upon initialization.
+ *
+ *  Note : initialization fails if size and alignment conditions are not respected.
+ *         In which case, the function will @return NULL.
+ *  Note2: An LZ4_stream_t structure guarantees correct alignment and size.
+ *  Note3: Before v1.9.0, use LZ4_resetStream() instead
+ */
+LZ4LIB_API LZ4_stream_t* LZ4_initStream (void* buffer, size_t size);
+
+
+/*! LZ4_streamDecode_t :
+ *  information structure to track an LZ4 stream during decompression.
+ *  init this structure  using LZ4_setStreamDecode() before first use.
+ *  note : only use in association with static linking !
+ *         this definition is not API/ABI safe,
+ *         and may change in a future version !
+ */
+#define LZ4_STREAMDECODESIZE_U64 (4 + ((sizeof(void*)==16) ? 2 : 0) /*AS-400*/ )
+#define LZ4_STREAMDECODESIZE     (LZ4_STREAMDECODESIZE_U64 * sizeof(unsigned long long))
+union LZ4_streamDecode_u {
+    unsigned long long table[LZ4_STREAMDECODESIZE_U64];
+    LZ4_streamDecode_t_internal internal_donotuse;
+} ;   /* previously typedef'd to LZ4_streamDecode_t */
+
+#endif /* LZ4_H_98237428734687 */
+
+
+#if defined (__cplusplus)
+}
+#endif
diff --git a/lib/sqfs/comp/lz4/lz4hc.c b/lib/sqfs/comp/lz4/lz4hc.c
new file mode 100644
index 0000000..4bdf96e
--- /dev/null
+++ b/lib/sqfs/comp/lz4/lz4hc.c
@@ -0,0 +1,1343 @@
+/*
+    LZ4 HC - High Compression Mode of LZ4
+    Copyright (C) 2011-2017, Yann Collet.
+
+    BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+
+    Redistribution and use in source and binary forms, with or without
+    modification, are permitted provided that the following conditions are
+    met:
+
+    * Redistributions of source code must retain the above copyright
+    notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above
+    copyright notice, this list of conditions and the following disclaimer
+    in the documentation and/or other materials provided with the
+    distribution.
+
+    THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+    "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+    LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+    A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+    OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+    SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+    LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+    DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+    THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+    (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+    OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+    You can contact the author at :
+       - LZ4 source repository : https://github.com/lz4/lz4
+       - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c
+*/
+/* note : lz4hc is not an independent module, it requires lz4.h/lz4.c for proper compilation */
+
+
+/* *************************************
+*  Tuning Parameter
+***************************************/
+
+/*! HEAPMODE :
+ *  Select how default compression function will allocate workplace memory,
+ *  in stack (0:fastest), or in heap (1:requires malloc()).
+ *  Since workplace is rather large, heap mode is recommended.
+ */
+#ifndef LZ4HC_HEAPMODE
+#  define LZ4HC_HEAPMODE 1
+#endif
+
+
+/*===    Dependency    ===*/
+#define LZ4_HC_STATIC_LINKING_ONLY
+#include "lz4hc.h"
+
+
+/*===   Common LZ4 definitions   ===*/
+#if defined(__GNUC__)
+#  pragma GCC diagnostic ignored "-Wunused-function"
+#endif
+#if defined (__clang__)
+#  pragma clang diagnostic ignored "-Wunused-function"
+#endif
+
+/*===   Enums   ===*/
+typedef enum { noDictCtx, usingDictCtxHc } dictCtx_directive;
+
+
+#define LZ4_COMMONDEFS_ONLY
+#ifndef LZ4_SRC_INCLUDED
+#include "lz4.c"   /* LZ4_count, constants, mem */
+#endif
+
+/*===   Constants   ===*/
+#define OPTIMAL_ML (int)((ML_MASK-1)+MINMATCH)
+#define LZ4_OPT_NUM   (1<<12)
+
+
+/*===   Macros   ===*/
+#define MIN(a,b)   ( (a) < (b) ? (a) : (b) )
+#define MAX(a,b)   ( (a) > (b) ? (a) : (b) )
+#define HASH_FUNCTION(i)         (((i) * 2654435761U) >> ((MINMATCH*8)-LZ4HC_HASH_LOG))
+#define DELTANEXTMAXD(p)         chainTable[(p) & LZ4HC_MAXD_MASK]    /* flexible, LZ4HC_MAXD dependent */
+#define DELTANEXTU16(table, pos) table[(U16)(pos)]   /* faster */
+/* Make fields passed to, and updated by LZ4HC_encodeSequence explicit */
+#define UPDATABLE(ip, op, anchor) &ip, &op, &anchor
+
+static U32 LZ4HC_hashPtr(const void* ptr) { return HASH_FUNCTION(LZ4_read32(ptr)); }
+
+
+/**************************************
+*  HC Compression
+**************************************/
+static void LZ4HC_clearTables (LZ4HC_CCtx_internal* hc4)
+{
+    MEM_INIT((void*)hc4->hashTable, 0, sizeof(hc4->hashTable));
+    MEM_INIT(hc4->chainTable, 0xFF, sizeof(hc4->chainTable));
+}
+
+static void LZ4HC_init_internal (LZ4HC_CCtx_internal* hc4, const BYTE* start)
+{
+    uptrval startingOffset = (uptrval)(hc4->end - hc4->base);
+    if (startingOffset > 1 GB) {
+        LZ4HC_clearTables(hc4);
+        startingOffset = 0;
+    }
+    startingOffset += 64 KB;
+    hc4->nextToUpdate = (U32) startingOffset;
+    hc4->base = start - startingOffset;
+    hc4->end = start;
+    hc4->dictBase = start - startingOffset;
+    hc4->dictLimit = (U32) startingOffset;
+    hc4->lowLimit = (U32) startingOffset;
+}
+
+
+/* Update chains up to ip (excluded) */
+LZ4_FORCE_INLINE void LZ4HC_Insert (LZ4HC_CCtx_internal* hc4, const BYTE* ip)
+{
+    U16* const chainTable = hc4->chainTable;
+    U32* const hashTable  = hc4->hashTable;
+    const BYTE* const base = hc4->base;
+    U32 const target = (U32)(ip - base);
+    U32 idx = hc4->nextToUpdate;
+
+    while (idx < target) {
+        U32 const h = LZ4HC_hashPtr(base+idx);
+        size_t delta = idx - hashTable[h];
+        if (delta>LZ4_DISTANCE_MAX) delta = LZ4_DISTANCE_MAX;
+        DELTANEXTU16(chainTable, idx) = (U16)delta;
+        hashTable[h] = idx;
+        idx++;
+    }
+
+    hc4->nextToUpdate = target;
+}
+
+/** LZ4HC_countBack() :
+ * @return : negative value, nb of common bytes before ip/match */
+LZ4_FORCE_INLINE
+int LZ4HC_countBack(const BYTE* const ip, const BYTE* const match,
+                    const BYTE* const iMin, const BYTE* const mMin)
+{
+    int back = 0;
+    int const min = (int)MAX(iMin - ip, mMin - match);
+    assert(min <= 0);
+    assert(ip >= iMin); assert((size_t)(ip-iMin) < (1U<<31));
+    assert(match >= mMin); assert((size_t)(match - mMin) < (1U<<31));
+    while ( (back > min)
+         && (ip[back-1] == match[back-1]) )
+            back--;
+    return back;
+}
+
+#if defined(_MSC_VER)
+#  define LZ4HC_rotl32(x,r) _rotl(x,r)
+#else
+#  define LZ4HC_rotl32(x,r) ((x << r) | (x >> (32 - r)))
+#endif
+
+
+static U32 LZ4HC_rotatePattern(size_t const rotate, U32 const pattern)
+{
+    size_t const bitsToRotate = (rotate & (sizeof(pattern) - 1)) << 3;
+    if (bitsToRotate == 0)
+        return pattern;
+    return LZ4HC_rotl32(pattern, (int)bitsToRotate);
+}
+
+/* LZ4HC_countPattern() :
+ * pattern32 must be a sample of repetitive pattern of length 1, 2 or 4 (but not 3!) */
+static unsigned
+LZ4HC_countPattern(const BYTE* ip, const BYTE* const iEnd, U32 const pattern32)
+{
+    const BYTE* const iStart = ip;
+    reg_t const pattern = (sizeof(pattern)==8) ? (reg_t)pattern32 + (((reg_t)pattern32) << 32) : pattern32;
+
+    while (likely(ip < iEnd-(sizeof(pattern)-1))) {
+        reg_t const diff = LZ4_read_ARCH(ip) ^ pattern;
+        if (!diff) { ip+=sizeof(pattern); continue; }
+        ip += LZ4_NbCommonBytes(diff);
+        return (unsigned)(ip - iStart);
+    }
+
+    if (LZ4_isLittleEndian()) {
+        reg_t patternByte = pattern;
+        while ((ip<iEnd) && (*ip == (BYTE)patternByte)) {
+            ip++; patternByte >>= 8;
+        }
+    } else {  /* big endian */
+        U32 bitOffset = (sizeof(pattern)*8) - 8;
+        while (ip < iEnd) {
+            BYTE const byte = (BYTE)(pattern >> bitOffset);
+            if (*ip != byte) break;
+            ip ++; bitOffset -= 8;
+        }
+    }
+
+    return (unsigned)(ip - iStart);
+}
+
+/* LZ4HC_reverseCountPattern() :
+ * pattern must be a sample of repetitive pattern of length 1, 2 or 4 (but not 3!)
+ * read using natural platform endianess */
+static unsigned
+LZ4HC_reverseCountPattern(const BYTE* ip, const BYTE* const iLow, U32 pattern)
+{
+    const BYTE* const iStart = ip;
+
+    while (likely(ip >= iLow+4)) {
+        if (LZ4_read32(ip-4) != pattern) break;
+        ip -= 4;
+    }
+    {   const BYTE* bytePtr = (const BYTE*)(&pattern) + 3; /* works for any endianess */
+        while (likely(ip>iLow)) {
+            if (ip[-1] != *bytePtr) break;
+            ip--; bytePtr--;
+    }   }
+    return (unsigned)(iStart - ip);
+}
+
+/* LZ4HC_protectDictEnd() :
+ * Checks if the match is in the last 3 bytes of the dictionary, so reading the
+ * 4 byte MINMATCH would overflow.
+ * @returns true if the match index is okay.
+ */
+static int LZ4HC_protectDictEnd(U32 const dictLimit, U32 const matchIndex)
+{
+    return ((U32)((dictLimit - 1) - matchIndex) >= 3);
+}
+
+typedef enum { rep_untested, rep_not, rep_confirmed } repeat_state_e;
+typedef enum { favorCompressionRatio=0, favorDecompressionSpeed } HCfavor_e;
+
+LZ4_FORCE_INLINE int
+LZ4HC_InsertAndGetWiderMatch (
+    LZ4HC_CCtx_internal* hc4,
+    const BYTE* const ip,
+    const BYTE* const iLowLimit,
+    const BYTE* const iHighLimit,
+    int longest,
+    const BYTE** matchpos,
+    const BYTE** startpos,
+    const int maxNbAttempts,
+    const int patternAnalysis,
+    const int chainSwap,
+    const dictCtx_directive dict,
+    const HCfavor_e favorDecSpeed)
+{
+    U16* const chainTable = hc4->chainTable;
+    U32* const HashTable = hc4->hashTable;
+    const LZ4HC_CCtx_internal * const dictCtx = hc4->dictCtx;
+    const BYTE* const base = hc4->base;
+    const U32 dictLimit = hc4->dictLimit;
+    const BYTE* const lowPrefixPtr = base + dictLimit;
+    const U32 ipIndex = (U32)(ip - base);
+    const U32 lowestMatchIndex = (hc4->lowLimit + (LZ4_DISTANCE_MAX + 1) > ipIndex) ? hc4->lowLimit : ipIndex - LZ4_DISTANCE_MAX;
+    const BYTE* const dictBase = hc4->dictBase;
+    int const lookBackLength = (int)(ip-iLowLimit);
+    int nbAttempts = maxNbAttempts;
+    U32 matchChainPos = 0;
+    U32 const pattern = LZ4_read32(ip);
+    U32 matchIndex;
+    repeat_state_e repeat = rep_untested;
+    size_t srcPatternLength = 0;
+
+    DEBUGLOG(7, "LZ4HC_InsertAndGetWiderMatch");
+    /* First Match */
+    LZ4HC_Insert(hc4, ip);
+    matchIndex = HashTable[LZ4HC_hashPtr(ip)];
+    DEBUGLOG(7, "First match at index %u / %u (lowestMatchIndex)",
+                matchIndex, lowestMatchIndex);
+
+    while ((matchIndex>=lowestMatchIndex) && (nbAttempts)) {
+        int matchLength=0;
+        nbAttempts--;
+        assert(matchIndex < ipIndex);
+        if (favorDecSpeed && (ipIndex - matchIndex < 8)) {
+            /* do nothing */
+        } else if (matchIndex >= dictLimit) {   /* within current Prefix */
+            const BYTE* const matchPtr = base + matchIndex;
+            assert(matchPtr >= lowPrefixPtr);
+            assert(matchPtr < ip);
+            assert(longest >= 1);
+            if (LZ4_read16(iLowLimit + longest - 1) == LZ4_read16(matchPtr - lookBackLength + longest - 1)) {
+                if (LZ4_read32(matchPtr) == pattern) {
+                    int const back = lookBackLength ? LZ4HC_countBack(ip, matchPtr, iLowLimit, lowPrefixPtr) : 0;
+                    matchLength = MINMATCH + (int)LZ4_count(ip+MINMATCH, matchPtr+MINMATCH, iHighLimit);
+                    matchLength -= back;
+                    if (matchLength > longest) {
+                        longest = matchLength;
+                        *matchpos = matchPtr + back;
+                        *startpos = ip + back;
+            }   }   }
+        } else {   /* lowestMatchIndex <= matchIndex < dictLimit */
+            const BYTE* const matchPtr = dictBase + matchIndex;
+            if (LZ4_read32(matchPtr) == pattern) {
+                const BYTE* const dictStart = dictBase + hc4->lowLimit;
+                int back = 0;
+                const BYTE* vLimit = ip + (dictLimit - matchIndex);
+                if (vLimit > iHighLimit) vLimit = iHighLimit;
+                matchLength = (int)LZ4_count(ip+MINMATCH, matchPtr+MINMATCH, vLimit) + MINMATCH;
+                if ((ip+matchLength == vLimit) && (vLimit < iHighLimit))
+                    matchLength += LZ4_count(ip+matchLength, lowPrefixPtr, iHighLimit);
+                back = lookBackLength ? LZ4HC_countBack(ip, matchPtr, iLowLimit, dictStart) : 0;
+                matchLength -= back;
+                if (matchLength > longest) {
+                    longest = matchLength;
+                    *matchpos = base + matchIndex + back;   /* virtual pos, relative to ip, to retrieve offset */
+                    *startpos = ip + back;
+        }   }   }
+
+        if (chainSwap && matchLength==longest) {    /* better match => select a better chain */
+            assert(lookBackLength==0);   /* search forward only */
+            if (matchIndex + (U32)longest <= ipIndex) {
+                int const kTrigger = 4;
+                U32 distanceToNextMatch = 1;
+                int const end = longest - MINMATCH + 1;
+                int step = 1;
+                int accel = 1 << kTrigger;
+                int pos;
+                for (pos = 0; pos < end; pos += step) {
+                    U32 const candidateDist = DELTANEXTU16(chainTable, matchIndex + (U32)pos);
+                    step = (accel++ >> kTrigger);
+                    if (candidateDist > distanceToNextMatch) {
+                        distanceToNextMatch = candidateDist;
+                        matchChainPos = (U32)pos;
+                        accel = 1 << kTrigger;
+                    }
+                }
+                if (distanceToNextMatch > 1) {
+                    if (distanceToNextMatch > matchIndex) break;   /* avoid overflow */
+                    matchIndex -= distanceToNextMatch;
+                    continue;
+        }   }   }
+
+        {   U32 const distNextMatch = DELTANEXTU16(chainTable, matchIndex);
+            if (patternAnalysis && distNextMatch==1 && matchChainPos==0) {
+                U32 const matchCandidateIdx = matchIndex-1;
+                /* may be a repeated pattern */
+                if (repeat == rep_untested) {
+                    if ( ((pattern & 0xFFFF) == (pattern >> 16))
+                      &  ((pattern & 0xFF)   == (pattern >> 24)) ) {
+                        repeat = rep_confirmed;
+                        srcPatternLength = LZ4HC_countPattern(ip+sizeof(pattern), iHighLimit, pattern) + sizeof(pattern);
+                    } else {
+                        repeat = rep_not;
+                }   }
+                if ( (repeat == rep_confirmed) && (matchCandidateIdx >= lowestMatchIndex)
+                  && LZ4HC_protectDictEnd(dictLimit, matchCandidateIdx) ) {
+                    const int extDict = matchCandidateIdx < dictLimit;
+                    const BYTE* const matchPtr = (extDict ? dictBase : base) + matchCandidateIdx;
+                    if (LZ4_read32(matchPtr) == pattern) {  /* good candidate */
+                        const BYTE* const dictStart = dictBase + hc4->lowLimit;
+                        const BYTE* const iLimit = extDict ? dictBase + dictLimit : iHighLimit;
+                        size_t forwardPatternLength = LZ4HC_countPattern(matchPtr+sizeof(pattern), iLimit, pattern) + sizeof(pattern);
+                        if (extDict && matchPtr + forwardPatternLength == iLimit) {
+                            U32 const rotatedPattern = LZ4HC_rotatePattern(forwardPatternLength, pattern);
+                            forwardPatternLength += LZ4HC_countPattern(lowPrefixPtr, iHighLimit, rotatedPattern);
+                        }
+                        {   const BYTE* const lowestMatchPtr = extDict ? dictStart : lowPrefixPtr;
+                            size_t backLength = LZ4HC_reverseCountPattern(matchPtr, lowestMatchPtr, pattern);
+                            size_t currentSegmentLength;
+                            if (!extDict && matchPtr - backLength == lowPrefixPtr && hc4->lowLimit < dictLimit) {
+                                U32 const rotatedPattern = LZ4HC_rotatePattern((U32)(-(int)backLength), pattern);
+                                backLength += LZ4HC_reverseCountPattern(dictBase + dictLimit, dictStart, rotatedPattern);
+                            }
+                            /* Limit backLength not go further than lowestMatchIndex */
+                            backLength = matchCandidateIdx - MAX(matchCandidateIdx - (U32)backLength, lowestMatchIndex);
+                            assert(matchCandidateIdx - backLength >= lowestMatchIndex);
+                            currentSegmentLength = backLength + forwardPatternLength;
+                            /* Adjust to end of pattern if the source pattern fits, otherwise the beginning of the pattern */
+                            if ( (currentSegmentLength >= srcPatternLength)   /* current pattern segment large enough to contain full srcPatternLength */
+                              && (forwardPatternLength <= srcPatternLength) ) { /* haven't reached this position yet */
+                                U32 const newMatchIndex = matchCandidateIdx + (U32)forwardPatternLength - (U32)srcPatternLength;  /* best position, full pattern, might be followed by more match */
+                                if (LZ4HC_protectDictEnd(dictLimit, newMatchIndex))
+                                    matchIndex = newMatchIndex;
+                                else {
+                                    /* Can only happen if started in the prefix */
+                                    assert(newMatchIndex >= dictLimit - 3 && newMatchIndex < dictLimit && !extDict);
+                                    matchIndex = dictLimit;
+                                }
+                            } else {
+                                U32 const newMatchIndex = matchCandidateIdx - (U32)backLength;   /* farthest position in current segment, will find a match of length currentSegmentLength + maybe some back */
+                                if (!LZ4HC_protectDictEnd(dictLimit, newMatchIndex)) {
+                                    assert(newMatchIndex >= dictLimit - 3 && newMatchIndex < dictLimit && !extDict);
+                                    matchIndex = dictLimit;
+                                } else {
+                                    matchIndex = newMatchIndex;
+                                    if (lookBackLength==0) {  /* no back possible */
+                                        size_t const maxML = MIN(currentSegmentLength, srcPatternLength);
+                                        if ((size_t)longest < maxML) {
+                                            assert(base + matchIndex < ip);
+                                            if (ip - (base+matchIndex) > LZ4_DISTANCE_MAX) break;
+                                            assert(maxML < 2 GB);
+                                            longest = (int)maxML;
+                                            *matchpos = base + matchIndex;   /* virtual pos, relative to ip, to retrieve offset */
+                                            *startpos = ip;
+                                        }
+                                        {   U32 const distToNextPattern = DELTANEXTU16(chainTable, matchIndex);
+                                            if (distToNextPattern > matchIndex) break;  /* avoid overflow */
+                                            matchIndex -= distToNextPattern;
+                        }   }   }   }   }
+                        continue;
+                }   }
+        }   }   /* PA optimization */
+
+        /* follow current chain */
+        matchIndex -= DELTANEXTU16(chainTable, matchIndex + matchChainPos);
+
+    }  /* while ((matchIndex>=lowestMatchIndex) && (nbAttempts)) */
+
+    if ( dict == usingDictCtxHc
+      && nbAttempts
+      && ipIndex - lowestMatchIndex < LZ4_DISTANCE_MAX) {
+        size_t const dictEndOffset = (size_t)(dictCtx->end - dictCtx->base);
+        U32 dictMatchIndex = dictCtx->hashTable[LZ4HC_hashPtr(ip)];
+        assert(dictEndOffset <= 1 GB);
+        matchIndex = dictMatchIndex + lowestMatchIndex - (U32)dictEndOffset;
+        while (ipIndex - matchIndex <= LZ4_DISTANCE_MAX && nbAttempts--) {
+            const BYTE* const matchPtr = dictCtx->base + dictMatchIndex;
+
+            if (LZ4_read32(matchPtr) == pattern) {
+                int mlt;
+                int back = 0;
+                const BYTE* vLimit = ip + (dictEndOffset - dictMatchIndex);
+                if (vLimit > iHighLimit) vLimit = iHighLimit;
+                mlt = (int)LZ4_count(ip+MINMATCH, matchPtr+MINMATCH, vLimit) + MINMATCH;
+                back = lookBackLength ? LZ4HC_countBack(ip, matchPtr, iLowLimit, dictCtx->base + dictCtx->dictLimit) : 0;
+                mlt -= back;
+                if (mlt > longest) {
+                    longest = mlt;
+                    *matchpos = base + matchIndex + back;
+                    *startpos = ip + back;
+            }   }
+
+            {   U32 const nextOffset = DELTANEXTU16(dictCtx->chainTable, dictMatchIndex);
+                dictMatchIndex -= nextOffset;
+                matchIndex -= nextOffset;
+    }   }   }
+
+    return longest;
+}
+
+LZ4_FORCE_INLINE
+int LZ4HC_InsertAndFindBestMatch(LZ4HC_CCtx_internal* const hc4,   /* Index table will be updated */
+                                 const BYTE* const ip, const BYTE* const iLimit,
+                                 const BYTE** matchpos,
+                                 const int maxNbAttempts,
+                                 const int patternAnalysis,
+                                 const dictCtx_directive dict)
+{
+    const BYTE* uselessPtr = ip;
+    /* note : LZ4HC_InsertAndGetWiderMatch() is able to modify the starting position of a match (*startpos),
+     * but this won't be the case here, as we define iLowLimit==ip,
+     * so LZ4HC_InsertAndGetWiderMatch() won't be allowed to search past ip */
+    return LZ4HC_InsertAndGetWiderMatch(hc4, ip, ip, iLimit, MINMATCH-1, matchpos, &uselessPtr, maxNbAttempts, patternAnalysis, 0 /*chainSwap*/, dict, favorCompressionRatio);
+}
+
+/* LZ4HC_encodeSequence() :
+ * @return : 0 if ok,
+ *           1 if buffer issue detected */
+LZ4_FORCE_INLINE int LZ4HC_encodeSequence (
+    const BYTE** ip,
+    BYTE** op,
+    const BYTE** anchor,
+    int matchLength,
+    const BYTE* const match,
+    limitedOutput_directive limit,
+    BYTE* oend)
+{
+    size_t length;
+    BYTE* const token = (*op)++;
+
+#if defined(LZ4_DEBUG) && (LZ4_DEBUG >= 6)
+    static const BYTE* start = NULL;
+    static U32 totalCost = 0;
+    U32 const pos = (start==NULL) ? 0 : (U32)(*anchor - start);
+    U32 const ll = (U32)(*ip - *anchor);
+    U32 const llAdd = (ll>=15) ? ((ll-15) / 255) + 1 : 0;
+    U32 const mlAdd = (matchLength>=19) ? ((matchLength-19) / 255) + 1 : 0;
+    U32 const cost = 1 + llAdd + ll + 2 + mlAdd;
+    if (start==NULL) start = *anchor;  /* only works for single segment */
+    /* g_debuglog_enable = (pos >= 2228) & (pos <= 2262); */
+    DEBUGLOG(6, "pos:%7u -- literals:%3u, match:%4i, offset:%5u, cost:%3u + %u",
+                pos,
+                (U32)(*ip - *anchor), matchLength, (U32)(*ip-match),
+                cost, totalCost);
+    totalCost += cost;
+#endif
+
+    /* Encode Literal length */
+    length = (size_t)(*ip - *anchor);
+    if ((limit) && ((*op + (length / 255) + length + (2 + 1 + LASTLITERALS)) > oend)) return 1;   /* Check output limit */
+    if (length >= RUN_MASK) {
+        size_t len = length - RUN_MASK;
+        *token = (RUN_MASK << ML_BITS);
+        for(; len >= 255 ; len -= 255) *(*op)++ = 255;
+        *(*op)++ = (BYTE)len;
+    } else {
+        *token = (BYTE)(length << ML_BITS);
+    }
+
+    /* Copy Literals */
+    LZ4_wildCopy8(*op, *anchor, (*op) + length);
+    *op += length;
+
+    /* Encode Offset */
+    assert( (*ip - match) <= LZ4_DISTANCE_MAX );   /* note : consider providing offset as a value, rather than as a pointer difference */
+    LZ4_writeLE16(*op, (U16)(*ip-match)); *op += 2;
+
+    /* Encode MatchLength */
+    assert(matchLength >= MINMATCH);
+    length = (size_t)matchLength - MINMATCH;
+    if ((limit) && (*op + (length / 255) + (1 + LASTLITERALS) > oend)) return 1;   /* Check output limit */
+    if (length >= ML_MASK) {
+        *token += ML_MASK;
+        length -= ML_MASK;
+        for(; length >= 510 ; length -= 510) { *(*op)++ = 255; *(*op)++ = 255; }
+        if (length >= 255) { length -= 255; *(*op)++ = 255; }
+        *(*op)++ = (BYTE)length;
+    } else {
+        *token += (BYTE)(length);
+    }
+
+    /* Prepare next loop */
+    *ip += matchLength;
+    *anchor = *ip;
+
+    return 0;
+}
+
+LZ4_FORCE_INLINE int LZ4HC_compress_hashChain (
+    LZ4HC_CCtx_internal* const ctx,
+    const char* const source,
+    char* const dest,
+    int* srcSizePtr,
+    int const maxOutputSize,
+    unsigned maxNbAttempts,
+    const limitedOutput_directive limit,
+    const dictCtx_directive dict
+    )
+{
+    const int inputSize = *srcSizePtr;
+    const int patternAnalysis = (maxNbAttempts > 128);   /* levels 9+ */
+
+    const BYTE* ip = (const BYTE*) source;
+    const BYTE* anchor = ip;
+    const BYTE* const iend = ip + inputSize;
+    const BYTE* const mflimit = iend - MFLIMIT;
+    const BYTE* const matchlimit = (iend - LASTLITERALS);
+
+    BYTE* optr = (BYTE*) dest;
+    BYTE* op = (BYTE*) dest;
+    BYTE* oend = op + maxOutputSize;
+
+    int   ml0, ml, ml2, ml3;
+    const BYTE* start0;
+    const BYTE* ref0;
+    const BYTE* ref = NULL;
+    const BYTE* start2 = NULL;
+    const BYTE* ref2 = NULL;
+    const BYTE* start3 = NULL;
+    const BYTE* ref3 = NULL;
+
+    /* init */
+    *srcSizePtr = 0;
+    if (limit == fillOutput) oend -= LASTLITERALS;                  /* Hack for support LZ4 format restriction */
+    if (inputSize < LZ4_minLength) goto _last_literals;                  /* Input too small, no compression (all literals) */
+
+    /* Main Loop */
+    while (ip <= mflimit) {
+        ml = LZ4HC_InsertAndFindBestMatch(ctx, ip, matchlimit, &ref, maxNbAttempts, patternAnalysis, dict);
+        if (ml<MINMATCH) { ip++; continue; }
+
+        /* saved, in case we would skip too much */
+        start0 = ip; ref0 = ref; ml0 = ml;
+
+_Search2:
+        if (ip+ml <= mflimit) {
+            ml2 = LZ4HC_InsertAndGetWiderMatch(ctx,
+                            ip + ml - 2, ip + 0, matchlimit, ml, &ref2, &start2,
+                            maxNbAttempts, patternAnalysis, 0, dict, favorCompressionRatio);
+        } else {
+            ml2 = ml;
+        }
+
+        if (ml2 == ml) { /* No better match => encode ML1 */
+            optr = op;
+            if (LZ4HC_encodeSequence(UPDATABLE(ip, op, anchor), ml, ref, limit, oend)) goto _dest_overflow;
+            continue;
+        }
+
+        if (start0 < ip) {   /* first match was skipped at least once */
+            if (start2 < ip + ml0) {  /* squeezing ML1 between ML0(original ML1) and ML2 */
+                ip = start0; ref = ref0; ml = ml0;  /* restore initial ML1 */
+        }   }
+
+        /* Here, start0==ip */
+        if ((start2 - ip) < 3) {  /* First Match too small : removed */
+            ml = ml2;
+            ip = start2;
+            ref =ref2;
+            goto _Search2;
+        }
+
+_Search3:
+        /* At this stage, we have :
+        *  ml2 > ml1, and
+        *  ip1+3 <= ip2 (usually < ip1+ml1) */
+        if ((start2 - ip) < OPTIMAL_ML) {
+            int correction;
+            int new_ml = ml;
+            if (new_ml > OPTIMAL_ML) new_ml = OPTIMAL_ML;
+            if (ip+new_ml > start2 + ml2 - MINMATCH) new_ml = (int)(start2 - ip) + ml2 - MINMATCH;
+            correction = new_ml - (int)(start2 - ip);
+            if (correction > 0) {
+                start2 += correction;
+                ref2 += correction;
+                ml2 -= correction;
+            }
+        }
+        /* Now, we have start2 = ip+new_ml, with new_ml = min(ml, OPTIMAL_ML=18) */
+
+        if (start2 + ml2 <= mflimit) {
+            ml3 = LZ4HC_InsertAndGetWiderMatch(ctx,
+                            start2 + ml2 - 3, start2, matchlimit, ml2, &ref3, &start3,
+                            maxNbAttempts, patternAnalysis, 0, dict, favorCompressionRatio);
+        } else {
+            ml3 = ml2;
+        }
+
+        if (ml3 == ml2) {  /* No better match => encode ML1 and ML2 */
+            /* ip & ref are known; Now for ml */
+            if (start2 < ip+ml)  ml = (int)(start2 - ip);
+            /* Now, encode 2 sequences */
+            optr = op;
+            if (LZ4HC_encodeSequence(UPDATABLE(ip, op, anchor), ml, ref, limit, oend)) goto _dest_overflow;
+            ip = start2;
+            optr = op;
+            if (LZ4HC_encodeSequence(UPDATABLE(ip, op, anchor), ml2, ref2, limit, oend)) goto _dest_overflow;
+            continue;
+        }
+
+        if (start3 < ip+ml+3) {  /* Not enough space for match 2 : remove it */
+            if (start3 >= (ip+ml)) {  /* can write Seq1 immediately ==> Seq2 is removed, so Seq3 becomes Seq1 */
+                if (start2 < ip+ml) {
+                    int correction = (int)(ip+ml - start2);
+                    start2 += correction;
+                    ref2 += correction;
+                    ml2 -= correction;
+                    if (ml2 < MINMATCH) {
+                        start2 = start3;
+                        ref2 = ref3;
+                        ml2 = ml3;
+                    }
+                }
+
+                optr = op;
+                if (LZ4HC_encodeSequence(UPDATABLE(ip, op, anchor), ml, ref, limit, oend)) goto _dest_overflow;
+                ip  = start3;
+                ref = ref3;
+                ml  = ml3;
+
+                start0 = start2;
+                ref0 = ref2;
+                ml0 = ml2;
+                goto _Search2;
+            }
+
+            start2 = start3;
+            ref2 = ref3;
+            ml2 = ml3;
+            goto _Search3;
+        }
+
+        /*
+        * OK, now we have 3 ascending matches;
+        * let's write the first one ML1.
+        * ip & ref are known; Now decide ml.
+        */
+        if (start2 < ip+ml) {
+            if ((start2 - ip) < OPTIMAL_ML) {
+                int correction;
+                if (ml > OPTIMAL_ML) ml = OPTIMAL_ML;
+                if (ip + ml > start2 + ml2 - MINMATCH) ml = (int)(start2 - ip) + ml2 - MINMATCH;
+                correction = ml - (int)(start2 - ip);
+                if (correction > 0) {
+                    start2 += correction;
+                    ref2 += correction;
+                    ml2 -= correction;
+                }
+            } else {
+                ml = (int)(start2 - ip);
+            }
+        }
+        optr = op;
+        if (LZ4HC_encodeSequence(UPDATABLE(ip, op, anchor), ml, ref, limit, oend)) goto _dest_overflow;
+
+        /* ML2 becomes ML1 */
+        ip = start2; ref = ref2; ml = ml2;
+
+        /* ML3 becomes ML2 */
+        start2 = start3; ref2 = ref3; ml2 = ml3;
+
+        /* let's find a new ML3 */
+        goto _Search3;
+    }
+
+_last_literals:
+    /* Encode Last Literals */
+    {   size_t lastRunSize = (size_t)(iend - anchor);  /* literals */
+        size_t litLength = (lastRunSize + 255 - RUN_MASK) / 255;
+        size_t const totalSize = 1 + litLength + lastRunSize;
+        if (limit == fillOutput) oend += LASTLITERALS;  /* restore correct value */
+        if (limit && (op + totalSize > oend)) {
+            if (limit == limitedOutput) return 0;  /* Check output limit */
+            /* adapt lastRunSize to fill 'dest' */
+            lastRunSize  = (size_t)(oend - op) - 1;
+            litLength = (lastRunSize + 255 - RUN_MASK) / 255;
+            lastRunSize -= litLength;
+        }
+        ip = anchor + lastRunSize;
+
+        if (lastRunSize >= RUN_MASK) {
+            size_t accumulator = lastRunSize - RUN_MASK;
+            *op++ = (RUN_MASK << ML_BITS);
+            for(; accumulator >= 255 ; accumulator -= 255) *op++ = 255;
+            *op++ = (BYTE) accumulator;
+        } else {
+            *op++ = (BYTE)(lastRunSize << ML_BITS);
+        }
+        memcpy(op, anchor, lastRunSize);
+        op += lastRunSize;
+    }
+
+    /* End */
+    *srcSizePtr = (int) (((const char*)ip) - source);
+    return (int) (((char*)op)-dest);
+
+_dest_overflow:
+    if (limit == fillOutput) {
+        op = optr;  /* restore correct out pointer */
+        goto _last_literals;
+    }
+    return 0;
+}
+
+
+static int LZ4HC_compress_optimal( LZ4HC_CCtx_internal* ctx,
+    const char* const source, char* dst,
+    int* srcSizePtr, int dstCapacity,
+    int const nbSearches, size_t sufficient_len,
+    const limitedOutput_directive limit, int const fullUpdate,
+    const dictCtx_directive dict,
+    HCfavor_e favorDecSpeed);
+
+
+LZ4_FORCE_INLINE int LZ4HC_compress_generic_internal (
+    LZ4HC_CCtx_internal* const ctx,
+    const char* const src,
+    char* const dst,
+    int* const srcSizePtr,
+    int const dstCapacity,
+    int cLevel,
+    const limitedOutput_directive limit,
+    const dictCtx_directive dict
+    )
+{
+    typedef enum { lz4hc, lz4opt } lz4hc_strat_e;
+    typedef struct {
+        lz4hc_strat_e strat;
+        U32 nbSearches;
+        U32 targetLength;
+    } cParams_t;
+    static const cParams_t clTable[LZ4HC_CLEVEL_MAX+1] = {
+        { lz4hc,     2, 16 },  /* 0, unused */
+        { lz4hc,     2, 16 },  /* 1, unused */
+        { lz4hc,     2, 16 },  /* 2, unused */
+        { lz4hc,     4, 16 },  /* 3 */
+        { lz4hc,     8, 16 },  /* 4 */
+        { lz4hc,    16, 16 },  /* 5 */
+        { lz4hc,    32, 16 },  /* 6 */
+        { lz4hc,    64, 16 },  /* 7 */
+        { lz4hc,   128, 16 },  /* 8 */
+        { lz4hc,   256, 16 },  /* 9 */
+        { lz4opt,   96, 64 },  /*10==LZ4HC_CLEVEL_OPT_MIN*/
+        { lz4opt,  512,128 },  /*11 */
+        { lz4opt,16384,LZ4_OPT_NUM },  /* 12==LZ4HC_CLEVEL_MAX */
+    };
+
+    DEBUGLOG(4, "LZ4HC_compress_generic(ctx=%p, src=%p, srcSize=%d)", ctx, src, *srcSizePtr);
+
+    if (limit == fillOutput && dstCapacity < 1) return 0;   /* Impossible to store anything */
+    if ((U32)*srcSizePtr > (U32)LZ4_MAX_INPUT_SIZE) return 0;    /* Unsupported input size (too large or negative) */
+
+    ctx->end += *srcSizePtr;
+    if (cLevel < 1) cLevel = LZ4HC_CLEVEL_DEFAULT;   /* note : convention is different from lz4frame, maybe something to review */
+    cLevel = MIN(LZ4HC_CLEVEL_MAX, cLevel);
+    {   cParams_t const cParam = clTable[cLevel];
+        HCfavor_e const favor = ctx->favorDecSpeed ? favorDecompressionSpeed : favorCompressionRatio;
+        int result;
+
+        if (cParam.strat == lz4hc) {
+            result = LZ4HC_compress_hashChain(ctx,
+                                src, dst, srcSizePtr, dstCapacity,
+                                cParam.nbSearches, limit, dict);
+        } else {
+            assert(cParam.strat == lz4opt);
+            result = LZ4HC_compress_optimal(ctx,
+                                src, dst, srcSizePtr, dstCapacity,
+                                (int)cParam.nbSearches, cParam.targetLength, limit,
+                                cLevel == LZ4HC_CLEVEL_MAX,   /* ultra mode */
+                                dict, favor);
+        }
+        if (result <= 0) ctx->dirty = 1;
+        return result;
+    }
+}
+
+static void LZ4HC_setExternalDict(LZ4HC_CCtx_internal* ctxPtr, const BYTE* newBlock);
+
+static int
+LZ4HC_compress_generic_noDictCtx (
+        LZ4HC_CCtx_internal* const ctx,
+        const char* const src,
+        char* const dst,
+        int* const srcSizePtr,
+        int const dstCapacity,
+        int cLevel,
+        limitedOutput_directive limit
+        )
+{
+    assert(ctx->dictCtx == NULL);
+    return LZ4HC_compress_generic_internal(ctx, src, dst, srcSizePtr, dstCapacity, cLevel, limit, noDictCtx);
+}
+
+static int
+LZ4HC_compress_generic_dictCtx (
+        LZ4HC_CCtx_internal* const ctx,
+        const char* const src,
+        char* const dst,
+        int* const srcSizePtr,
+        int const dstCapacity,
+        int cLevel,
+        limitedOutput_directive limit
+        )
+{
+    const size_t position = (size_t)(ctx->end - ctx->base) - ctx->lowLimit;
+    assert(ctx->dictCtx != NULL);
+    if (position >= 64 KB) {
+        ctx->dictCtx = NULL;
+        return LZ4HC_compress_generic_noDictCtx(ctx, src, dst, srcSizePtr, dstCapacity, cLevel, limit);
+    } else if (position == 0 && *srcSizePtr > 4 KB) {
+        memcpy(ctx, ctx->dictCtx, sizeof(LZ4HC_CCtx_internal));
+        LZ4HC_setExternalDict(ctx, (const BYTE *)src);
+        ctx->compressionLevel = (short)cLevel;
+        return LZ4HC_compress_generic_noDictCtx(ctx, src, dst, srcSizePtr, dstCapacity, cLevel, limit);
+    } else {
+        return LZ4HC_compress_generic_internal(ctx, src, dst, srcSizePtr, dstCapacity, cLevel, limit, usingDictCtxHc);
+    }
+}
+
+static int
+LZ4HC_compress_generic (
+        LZ4HC_CCtx_internal* const ctx,
+        const char* const src,
+        char* const dst,
+        int* const srcSizePtr,
+        int const dstCapacity,
+        int cLevel,
+        limitedOutput_directive limit
+        )
+{
+    if (ctx->dictCtx == NULL) {
+        return LZ4HC_compress_generic_noDictCtx(ctx, src, dst, srcSizePtr, dstCapacity, cLevel, limit);
+    } else {
+        return LZ4HC_compress_generic_dictCtx(ctx, src, dst, srcSizePtr, dstCapacity, cLevel, limit);
+    }
+}
+
+
+int LZ4_sizeofStateHC(void) { return (int)sizeof(LZ4_streamHC_t); }
+
+#ifndef _MSC_VER  /* for some reason, Visual fails the aligment test on 32-bit x86 :
+                   * it reports an aligment of 8-bytes,
+                   * while actually aligning LZ4_streamHC_t on 4 bytes. */
+static size_t LZ4_streamHC_t_alignment(void)
+{
+    struct { char c; LZ4_streamHC_t t; } t_a;
+    return sizeof(t_a) - sizeof(t_a.t);
+}
+#endif
+
+/* state is presumed correctly initialized,
+ * in which case its size and alignment have already been validate */
+static int LZ4_compress_HC_extStateHC_fastReset (void* state, const char* src, char* dst, int srcSize,
+						 int dstCapacity, int compressionLevel)
+{
+    LZ4HC_CCtx_internal* const ctx = &((LZ4_streamHC_t*)state)->internal_donotuse;
+#ifndef _MSC_VER  /* for some reason, Visual fails the aligment test on 32-bit x86 :
+                   * it reports an aligment of 8-bytes,
+                   * while actually aligning LZ4_streamHC_t on 4 bytes. */
+    assert(((size_t)state & (LZ4_streamHC_t_alignment() - 1)) == 0);  /* check alignment */
+#endif
+    if (((size_t)(state)&(sizeof(void*)-1)) != 0) return 0;   /* Error : state is not aligned for pointers (32 or 64 bits) */
+    LZ4_resetStreamHC_fast((LZ4_streamHC_t*)state, compressionLevel);
+    LZ4HC_init_internal (ctx, (const BYTE*)src);
+    if (dstCapacity < LZ4_compressBound(srcSize))
+        return LZ4HC_compress_generic (ctx, src, dst, &srcSize, dstCapacity, compressionLevel, limitedOutput);
+    else
+        return LZ4HC_compress_generic (ctx, src, dst, &srcSize, dstCapacity, compressionLevel, notLimited);
+}
+
+int LZ4_compress_HC_extStateHC (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int compressionLevel)
+{
+    LZ4_streamHC_t* const ctx = LZ4_initStreamHC(state, sizeof(*ctx));
+    if (ctx==NULL) return 0;   /* init failure */
+    return LZ4_compress_HC_extStateHC_fastReset(state, src, dst, srcSize, dstCapacity, compressionLevel);
+}
+
+int LZ4_compress_HC(const char* src, char* dst, int srcSize, int dstCapacity, int compressionLevel)
+{
+#if defined(LZ4HC_HEAPMODE) && LZ4HC_HEAPMODE==1
+    LZ4_streamHC_t* const statePtr = (LZ4_streamHC_t*)ALLOC(sizeof(LZ4_streamHC_t));
+#else
+    LZ4_streamHC_t state;
+    LZ4_streamHC_t* const statePtr = &state;
+#endif
+    int const cSize = LZ4_compress_HC_extStateHC(statePtr, src, dst, srcSize, dstCapacity, compressionLevel);
+#if defined(LZ4HC_HEAPMODE) && LZ4HC_HEAPMODE==1
+    FREEMEM(statePtr);
+#endif
+    return cSize;
+}
+
+/* state is presumed sized correctly (>= sizeof(LZ4_streamHC_t)) */
+int LZ4_compress_HC_destSize(void* state, const char* source, char* dest, int* sourceSizePtr, int targetDestSize, int cLevel)
+{
+    LZ4_streamHC_t* const ctx = LZ4_initStreamHC(state, sizeof(*ctx));
+    if (ctx==NULL) return 0;   /* init failure */
+    LZ4HC_init_internal(&ctx->internal_donotuse, (const BYTE*) source);
+    LZ4_setCompressionLevel(ctx, cLevel);
+    return LZ4HC_compress_generic(&ctx->internal_donotuse, source, dest, sourceSizePtr, targetDestSize, cLevel, fillOutput);
+}
+
+
+
+/**************************************
+*  Streaming Functions
+**************************************/
+
+LZ4_streamHC_t* LZ4_initStreamHC (void* buffer, size_t size)
+{
+    LZ4_streamHC_t* const LZ4_streamHCPtr = (LZ4_streamHC_t*)buffer;
+    if (buffer == NULL) return NULL;
+    if (size < sizeof(LZ4_streamHC_t)) return NULL;
+#ifndef _MSC_VER  /* for some reason, Visual fails the aligment test on 32-bit x86 :
+                   * it reports an aligment of 8-bytes,
+                   * while actually aligning LZ4_streamHC_t on 4 bytes. */
+    if (((size_t)buffer) & (LZ4_streamHC_t_alignment() - 1)) return NULL;  /* alignment check */
+#endif
+    /* if compilation fails here, LZ4_STREAMHCSIZE must be increased */
+    LZ4_STATIC_ASSERT(sizeof(LZ4HC_CCtx_internal) <= LZ4_STREAMHCSIZE);
+    DEBUGLOG(4, "LZ4_initStreamHC(%p, %u)", LZ4_streamHCPtr, (unsigned)size);
+    /* end-base will trigger a clearTable on starting compression */
+    LZ4_streamHCPtr->internal_donotuse.end = (const BYTE *)(ptrdiff_t)-1;
+    LZ4_streamHCPtr->internal_donotuse.base = NULL;
+    LZ4_streamHCPtr->internal_donotuse.dictCtx = NULL;
+    LZ4_streamHCPtr->internal_donotuse.favorDecSpeed = 0;
+    LZ4_streamHCPtr->internal_donotuse.dirty = 0;
+    LZ4_setCompressionLevel(LZ4_streamHCPtr, LZ4HC_CLEVEL_DEFAULT);
+    return LZ4_streamHCPtr;
+}
+
+/* just a stub */
+void LZ4_resetStreamHC_fast (LZ4_streamHC_t* LZ4_streamHCPtr, int compressionLevel)
+{
+    DEBUGLOG(4, "LZ4_resetStreamHC_fast(%p, %d)", LZ4_streamHCPtr, compressionLevel);
+    if (LZ4_streamHCPtr->internal_donotuse.dirty) {
+        LZ4_initStreamHC(LZ4_streamHCPtr, sizeof(*LZ4_streamHCPtr));
+    } else {
+        /* preserve end - base : can trigger clearTable's threshold */
+        LZ4_streamHCPtr->internal_donotuse.end -= (uptrval)LZ4_streamHCPtr->internal_donotuse.base;
+        LZ4_streamHCPtr->internal_donotuse.base = NULL;
+        LZ4_streamHCPtr->internal_donotuse.dictCtx = NULL;
+    }
+    LZ4_setCompressionLevel(LZ4_streamHCPtr, compressionLevel);
+}
+
+void LZ4_setCompressionLevel(LZ4_streamHC_t* LZ4_streamHCPtr, int compressionLevel)
+{
+    DEBUGLOG(5, "LZ4_setCompressionLevel(%p, %d)", LZ4_streamHCPtr, compressionLevel);
+    if (compressionLevel < 1) compressionLevel = LZ4HC_CLEVEL_DEFAULT;
+    if (compressionLevel > LZ4HC_CLEVEL_MAX) compressionLevel = LZ4HC_CLEVEL_MAX;
+    LZ4_streamHCPtr->internal_donotuse.compressionLevel = (short)compressionLevel;
+}
+
+/* compression */
+
+static void LZ4HC_setExternalDict(LZ4HC_CCtx_internal* ctxPtr, const BYTE* newBlock)
+{
+    DEBUGLOG(4, "LZ4HC_setExternalDict(%p, %p)", ctxPtr, newBlock);
+    if (ctxPtr->end >= ctxPtr->base + ctxPtr->dictLimit + 4)
+        LZ4HC_Insert (ctxPtr, ctxPtr->end-3);   /* Referencing remaining dictionary content */
+
+    /* Only one memory segment for extDict, so any previous extDict is lost at this stage */
+    ctxPtr->lowLimit  = ctxPtr->dictLimit;
+    ctxPtr->dictLimit = (U32)(ctxPtr->end - ctxPtr->base);
+    ctxPtr->dictBase  = ctxPtr->base;
+    ctxPtr->base = newBlock - ctxPtr->dictLimit;
+    ctxPtr->end  = newBlock;
+    ctxPtr->nextToUpdate = ctxPtr->dictLimit;   /* match referencing will resume from there */
+
+    /* cannot reference an extDict and a dictCtx at the same time */
+    ctxPtr->dictCtx = NULL;
+}
+
+/* ================================================
+ *  LZ4 Optimal parser (levels [LZ4HC_CLEVEL_OPT_MIN - LZ4HC_CLEVEL_MAX])
+ * ===============================================*/
+typedef struct {
+    int price;
+    int off;
+    int mlen;
+    int litlen;
+} LZ4HC_optimal_t;
+
+/* price in bytes */
+LZ4_FORCE_INLINE int LZ4HC_literalsPrice(int const litlen)
+{
+    int price = litlen;
+    assert(litlen >= 0);
+    if (litlen >= (int)RUN_MASK)
+        price += 1 + ((litlen-(int)RUN_MASK) / 255);
+    return price;
+}
+
+
+/* requires mlen >= MINMATCH */
+LZ4_FORCE_INLINE int LZ4HC_sequencePrice(int litlen, int mlen)
+{
+    int price = 1 + 2 ; /* token + 16-bit offset */
+    assert(litlen >= 0);
+    assert(mlen >= MINMATCH);
+
+    price += LZ4HC_literalsPrice(litlen);
+
+    if (mlen >= (int)(ML_MASK+MINMATCH))
+        price += 1 + ((mlen-(int)(ML_MASK+MINMATCH)) / 255);
+
+    return price;
+}
+
+
+typedef struct {
+    int off;
+    int len;
+} LZ4HC_match_t;
+
+LZ4_FORCE_INLINE LZ4HC_match_t
+LZ4HC_FindLongerMatch(LZ4HC_CCtx_internal* const ctx,
+                      const BYTE* ip, const BYTE* const iHighLimit,
+                      int minLen, int nbSearches,
+                      const dictCtx_directive dict,
+                      const HCfavor_e favorDecSpeed)
+{
+    LZ4HC_match_t match = { 0 , 0 };
+    const BYTE* matchPtr = NULL;
+    /* note : LZ4HC_InsertAndGetWiderMatch() is able to modify the starting position of a match (*startpos),
+     * but this won't be the case here, as we define iLowLimit==ip,
+     * so LZ4HC_InsertAndGetWiderMatch() won't be allowed to search past ip */
+    int matchLength = LZ4HC_InsertAndGetWiderMatch(ctx, ip, ip, iHighLimit, minLen, &matchPtr, &ip, nbSearches, 1 /*patternAnalysis*/, 1 /*chainSwap*/, dict, favorDecSpeed);
+    if (matchLength <= minLen) return match;
+    if (favorDecSpeed) {
+        if ((matchLength>18) & (matchLength<=36)) matchLength=18;   /* favor shortcut */
+    }
+    match.len = matchLength;
+    match.off = (int)(ip-matchPtr);
+    return match;
+}
+
+
+static int LZ4HC_compress_optimal ( LZ4HC_CCtx_internal* ctx,
+                                    const char* const source,
+                                    char* dst,
+                                    int* srcSizePtr,
+                                    int dstCapacity,
+                                    int const nbSearches,
+                                    size_t sufficient_len,
+                                    const limitedOutput_directive limit,
+                                    int const fullUpdate,
+                                    const dictCtx_directive dict,
+                                    const HCfavor_e favorDecSpeed)
+{
+#define TRAILING_LITERALS 3
+    LZ4HC_optimal_t opt[LZ4_OPT_NUM + TRAILING_LITERALS];   /* ~64 KB, which is a bit large for stack... */
+
+    const BYTE* ip = (const BYTE*) source;
+    const BYTE* anchor = ip;
+    const BYTE* const iend = ip + *srcSizePtr;
+    const BYTE* const mflimit = iend - MFLIMIT;
+    const BYTE* const matchlimit = iend - LASTLITERALS;
+    BYTE* op = (BYTE*) dst;
+    BYTE* opSaved = (BYTE*) dst;
+    BYTE* oend = op + dstCapacity;
+
+    /* init */
+    DEBUGLOG(5, "LZ4HC_compress_optimal(dst=%p, dstCapa=%u)", dst, (unsigned)dstCapacity);
+    *srcSizePtr = 0;
+    if (limit == fillOutput) oend -= LASTLITERALS;   /* Hack for support LZ4 format restriction */
+    if (sufficient_len >= LZ4_OPT_NUM) sufficient_len = LZ4_OPT_NUM-1;
+
+    /* Main Loop */
+    assert(ip - anchor < LZ4_MAX_INPUT_SIZE);
+    while (ip <= mflimit) {
+         int const llen = (int)(ip - anchor);
+         int best_mlen, best_off;
+         int cur, last_match_pos = 0;
+
+         LZ4HC_match_t const firstMatch = LZ4HC_FindLongerMatch(ctx, ip, matchlimit, MINMATCH-1, nbSearches, dict, favorDecSpeed);
+         if (firstMatch.len==0) { ip++; continue; }
+
+         if ((size_t)firstMatch.len > sufficient_len) {
+             /* good enough solution : immediate encoding */
+             int const firstML = firstMatch.len;
+             const BYTE* const matchPos = ip - firstMatch.off;
+             opSaved = op;
+             if ( LZ4HC_encodeSequence(UPDATABLE(ip, op, anchor), firstML, matchPos, limit, oend) )   /* updates ip, op and anchor */
+                 goto _dest_overflow;
+             continue;
+         }
+
+         /* set prices for first positions (literals) */
+         {   int rPos;
+             for (rPos = 0 ; rPos < MINMATCH ; rPos++) {
+                 int const cost = LZ4HC_literalsPrice(llen + rPos);
+                 opt[rPos].mlen = 1;
+                 opt[rPos].off = 0;
+                 opt[rPos].litlen = llen + rPos;
+                 opt[rPos].price = cost;
+                 DEBUGLOG(7, "rPos:%3i => price:%3i (litlen=%i) -- initial setup",
+                             rPos, cost, opt[rPos].litlen);
+         }   }
+         /* set prices using initial match */
+         {   int mlen = MINMATCH;
+             int const matchML = firstMatch.len;   /* necessarily < sufficient_len < LZ4_OPT_NUM */
+             int const offset = firstMatch.off;
+             assert(matchML < LZ4_OPT_NUM);
+             for ( ; mlen <= matchML ; mlen++) {
+                 int const cost = LZ4HC_sequencePrice(llen, mlen);
+                 opt[mlen].mlen = mlen;
+                 opt[mlen].off = offset;
+                 opt[mlen].litlen = llen;
+                 opt[mlen].price = cost;
+                 DEBUGLOG(7, "rPos:%3i => price:%3i (matchlen=%i) -- initial setup",
+                             mlen, cost, mlen);
+         }   }
+         last_match_pos = firstMatch.len;
+         {   int addLit;
+             for (addLit = 1; addLit <= TRAILING_LITERALS; addLit ++) {
+                 opt[last_match_pos+addLit].mlen = 1; /* literal */
+                 opt[last_match_pos+addLit].off = 0;
+                 opt[last_match_pos+addLit].litlen = addLit;
+                 opt[last_match_pos+addLit].price = opt[last_match_pos].price + LZ4HC_literalsPrice(addLit);
+                 DEBUGLOG(7, "rPos:%3i => price:%3i (litlen=%i) -- initial setup",
+                             last_match_pos+addLit, opt[last_match_pos+addLit].price, addLit);
+         }   }
+
+         /* check further positions */
+         for (cur = 1; cur < last_match_pos; cur++) {
+             const BYTE* const curPtr = ip + cur;
+             LZ4HC_match_t newMatch;
+
+             if (curPtr > mflimit) break;
+             DEBUGLOG(7, "rPos:%u[%u] vs [%u]%u",
+                     cur, opt[cur].price, opt[cur+1].price, cur+1);
+             if (fullUpdate) {
+                 /* not useful to search here if next position has same (or lower) cost */
+                 if ( (opt[cur+1].price <= opt[cur].price)
+                   /* in some cases, next position has same cost, but cost rises sharply after, so a small match would still be beneficial */
+                   && (opt[cur+MINMATCH].price < opt[cur].price + 3/*min seq price*/) )
+                     continue;
+             } else {
+                 /* not useful to search here if next position has same (or lower) cost */
+                 if (opt[cur+1].price <= opt[cur].price) continue;
+             }
+
+             DEBUGLOG(7, "search at rPos:%u", cur);
+             if (fullUpdate)
+                 newMatch = LZ4HC_FindLongerMatch(ctx, curPtr, matchlimit, MINMATCH-1, nbSearches, dict, favorDecSpeed);
+             else
+                 /* only test matches of minimum length; slightly faster, but misses a few bytes */
+                 newMatch = LZ4HC_FindLongerMatch(ctx, curPtr, matchlimit, last_match_pos - cur, nbSearches, dict, favorDecSpeed);
+             if (!newMatch.len) continue;
+
+             if ( ((size_t)newMatch.len > sufficient_len)
+               || (newMatch.len + cur >= LZ4_OPT_NUM) ) {
+                 /* immediate encoding */
+                 best_mlen = newMatch.len;
+                 best_off = newMatch.off;
+                 last_match_pos = cur + 1;
+                 goto encode;
+             }
+
+             /* before match : set price with literals at beginning */
+             {   int const baseLitlen = opt[cur].litlen;
+                 int litlen;
+                 for (litlen = 1; litlen < MINMATCH; litlen++) {
+                     int const price = opt[cur].price - LZ4HC_literalsPrice(baseLitlen) + LZ4HC_literalsPrice(baseLitlen+litlen);
+                     int const pos = cur + litlen;
+                     if (price < opt[pos].price) {
+                         opt[pos].mlen = 1; /* literal */
+                         opt[pos].off = 0;
+                         opt[pos].litlen = baseLitlen+litlen;
+                         opt[pos].price = price;
+                         DEBUGLOG(7, "rPos:%3i => price:%3i (litlen=%i)",
+                                     pos, price, opt[pos].litlen);
+             }   }   }
+
+             /* set prices using match at position = cur */
+             {   int const matchML = newMatch.len;
+                 int ml = MINMATCH;
+
+                 assert(cur + newMatch.len < LZ4_OPT_NUM);
+                 for ( ; ml <= matchML ; ml++) {
+                     int const pos = cur + ml;
+                     int const offset = newMatch.off;
+                     int price;
+                     int ll;
+                     DEBUGLOG(7, "testing price rPos %i (last_match_pos=%i)",
+                                 pos, last_match_pos);
+                     if (opt[cur].mlen == 1) {
+                         ll = opt[cur].litlen;
+                         price = ((cur > ll) ? opt[cur - ll].price : 0)
+                               + LZ4HC_sequencePrice(ll, ml);
+                     } else {
+                         ll = 0;
+                         price = opt[cur].price + LZ4HC_sequencePrice(0, ml);
+                     }
+
+                    assert((U32)favorDecSpeed <= 1);
+                     if (pos > last_match_pos+TRAILING_LITERALS
+                      || price <= opt[pos].price - (int)favorDecSpeed) {
+                         DEBUGLOG(7, "rPos:%3i => price:%3i (matchlen=%i)",
+                                     pos, price, ml);
+                         assert(pos < LZ4_OPT_NUM);
+                         if ( (ml == matchML)  /* last pos of last match */
+                           && (last_match_pos < pos) )
+                             last_match_pos = pos;
+                         opt[pos].mlen = ml;
+                         opt[pos].off = offset;
+                         opt[pos].litlen = ll;
+                         opt[pos].price = price;
+             }   }   }
+             /* complete following positions with literals */
+             {   int addLit;
+                 for (addLit = 1; addLit <= TRAILING_LITERALS; addLit ++) {
+                     opt[last_match_pos+addLit].mlen = 1; /* literal */
+                     opt[last_match_pos+addLit].off = 0;
+                     opt[last_match_pos+addLit].litlen = addLit;
+                     opt[last_match_pos+addLit].price = opt[last_match_pos].price + LZ4HC_literalsPrice(addLit);
+                     DEBUGLOG(7, "rPos:%3i => price:%3i (litlen=%i)", last_match_pos+addLit, opt[last_match_pos+addLit].price, addLit);
+             }   }
+         }  /* for (cur = 1; cur <= last_match_pos; cur++) */
+
+         assert(last_match_pos < LZ4_OPT_NUM + TRAILING_LITERALS);
+         best_mlen = opt[last_match_pos].mlen;
+         best_off = opt[last_match_pos].off;
+         cur = last_match_pos - best_mlen;
+
+ encode: /* cur, last_match_pos, best_mlen, best_off must be set */
+         assert(cur < LZ4_OPT_NUM);
+         assert(last_match_pos >= 1);  /* == 1 when only one candidate */
+         DEBUGLOG(6, "reverse traversal, looking for shortest path (last_match_pos=%i)", last_match_pos);
+         {   int candidate_pos = cur;
+             int selected_matchLength = best_mlen;
+             int selected_offset = best_off;
+             while (1) {  /* from end to beginning */
+                 int const next_matchLength = opt[candidate_pos].mlen;  /* can be 1, means literal */
+                 int const next_offset = opt[candidate_pos].off;
+                 DEBUGLOG(7, "pos %i: sequence length %i", candidate_pos, selected_matchLength);
+                 opt[candidate_pos].mlen = selected_matchLength;
+                 opt[candidate_pos].off = selected_offset;
+                 selected_matchLength = next_matchLength;
+                 selected_offset = next_offset;
+                 if (next_matchLength > candidate_pos) break; /* last match elected, first match to encode */
+                 assert(next_matchLength > 0);  /* can be 1, means literal */
+                 candidate_pos -= next_matchLength;
+         }   }
+
+         /* encode all recorded sequences in order */
+         {   int rPos = 0;  /* relative position (to ip) */
+             while (rPos < last_match_pos) {
+                 int const ml = opt[rPos].mlen;
+                 int const offset = opt[rPos].off;
+                 if (ml == 1) { ip++; rPos++; continue; }  /* literal; note: can end up with several literals, in which case, skip them */
+                 rPos += ml;
+                 assert(ml >= MINMATCH);
+                 assert((offset >= 1) && (offset <= LZ4_DISTANCE_MAX));
+                 opSaved = op;
+                 if ( LZ4HC_encodeSequence(UPDATABLE(ip, op, anchor), ml, ip - offset, limit, oend) )   /* updates ip, op and anchor */
+                     goto _dest_overflow;
+         }   }
+     }  /* while (ip <= mflimit) */
+
+ _last_literals:
+     /* Encode Last Literals */
+     {   size_t lastRunSize = (size_t)(iend - anchor);  /* literals */
+         size_t litLength = (lastRunSize + 255 - RUN_MASK) / 255;
+         size_t const totalSize = 1 + litLength + lastRunSize;
+         if (limit == fillOutput) oend += LASTLITERALS;  /* restore correct value */
+         if (limit && (op + totalSize > oend)) {
+             if (limit == limitedOutput) return 0;  /* Check output limit */
+             /* adapt lastRunSize to fill 'dst' */
+             lastRunSize  = (size_t)(oend - op) - 1;
+             litLength = (lastRunSize + 255 - RUN_MASK) / 255;
+             lastRunSize -= litLength;
+         }
+         ip = anchor + lastRunSize;
+
+         if (lastRunSize >= RUN_MASK) {
+             size_t accumulator = lastRunSize - RUN_MASK;
+             *op++ = (RUN_MASK << ML_BITS);
+             for(; accumulator >= 255 ; accumulator -= 255) *op++ = 255;
+             *op++ = (BYTE) accumulator;
+         } else {
+             *op++ = (BYTE)(lastRunSize << ML_BITS);
+         }
+         memcpy(op, anchor, lastRunSize);
+         op += lastRunSize;
+     }
+
+     /* End */
+     *srcSizePtr = (int) (((const char*)ip) - source);
+     return (int) ((char*)op-dst);
+
+ _dest_overflow:
+     if (limit == fillOutput) {
+         op = opSaved;  /* restore correct out pointer */
+         goto _last_literals;
+     }
+     return 0;
+ }
diff --git a/lib/sqfs/comp/lz4/lz4hc.h b/lib/sqfs/comp/lz4/lz4hc.h
new file mode 100644
index 0000000..157d813
--- /dev/null
+++ b/lib/sqfs/comp/lz4/lz4hc.h
@@ -0,0 +1,307 @@
+/*
+   LZ4 HC - High Compression Mode of LZ4
+   Header File
+   Copyright (C) 2011-2017, Yann Collet.
+   BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+
+   Redistribution and use in source and binary forms, with or without
+   modification, are permitted provided that the following conditions are
+   met:
+
+       * Redistributions of source code must retain the above copyright
+   notice, this list of conditions and the following disclaimer.
+       * Redistributions in binary form must reproduce the above
+   copyright notice, this list of conditions and the following disclaimer
+   in the documentation and/or other materials provided with the
+   distribution.
+
+   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+   You can contact the author at :
+   - LZ4 source repository : https://github.com/lz4/lz4
+   - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c
+*/
+#ifndef LZ4_HC_H_19834876238432
+#define LZ4_HC_H_19834876238432
+
+#if defined (__cplusplus)
+extern "C" {
+#endif
+
+/* --- Dependency --- */
+/* note : lz4hc requires lz4.h/lz4.c for compilation */
+#include "lz4.h"   /* stddef, LZ4LIB_API, LZ4_DEPRECATED */
+
+
+/* --- Useful constants --- */
+#define LZ4HC_CLEVEL_MIN         3
+#define LZ4HC_CLEVEL_DEFAULT     9
+#define LZ4HC_CLEVEL_OPT_MIN    10
+#define LZ4HC_CLEVEL_MAX        12
+
+
+/*-************************************
+ *  Block Compression
+ **************************************/
+/*! LZ4_compress_HC() :
+ *  Compress data from `src` into `dst`, using the powerful but slower "HC" algorithm.
+ * `dst` must be already allocated.
+ *  Compression is guaranteed to succeed if `dstCapacity >= LZ4_compressBound(srcSize)` (see "lz4.h")
+ *  Max supported `srcSize` value is LZ4_MAX_INPUT_SIZE (see "lz4.h")
+ * `compressionLevel` : any value between 1 and LZ4HC_CLEVEL_MAX will work.
+ *                      Values > LZ4HC_CLEVEL_MAX behave the same as LZ4HC_CLEVEL_MAX.
+ * @return : the number of bytes written into 'dst'
+ *           or 0 if compression fails.
+ */
+LZ4LIB_API int LZ4_compress_HC (const char* src, char* dst, int srcSize, int dstCapacity, int compressionLevel);
+
+
+/* Note :
+ *   Decompression functions are provided within "lz4.h" (BSD license)
+ */
+
+
+/*! LZ4_compress_HC_extStateHC() :
+ *  Same as LZ4_compress_HC(), but using an externally allocated memory segment for `state`.
+ * `state` size is provided by LZ4_sizeofStateHC().
+ *  Memory segment must be aligned on 8-bytes boundaries (which a normal malloc() should do properly).
+ */
+LZ4LIB_API int LZ4_sizeofStateHC(void);
+LZ4LIB_API int LZ4_compress_HC_extStateHC(void* stateHC, const char* src, char* dst, int srcSize, int maxDstSize, int compressionLevel);
+
+
+/*! LZ4_compress_HC_destSize() : v1.9.0+
+ *  Will compress as much data as possible from `src`
+ *  to fit into `targetDstSize` budget.
+ *  Result is provided in 2 parts :
+ * @return : the number of bytes written into 'dst' (necessarily <= targetDstSize)
+ *           or 0 if compression fails.
+ * `srcSizePtr` : on success, *srcSizePtr is updated to indicate how much bytes were read from `src`
+ */
+LZ4LIB_API int LZ4_compress_HC_destSize(void* stateHC,
+                                  const char* src, char* dst,
+                                        int* srcSizePtr, int targetDstSize,
+                                        int compressionLevel);
+
+
+/*-************************************
+ *  Streaming Compression
+ *  Bufferless synchronous API
+ **************************************/
+ typedef union LZ4_streamHC_u LZ4_streamHC_t;   /* incomplete type (defined later) */
+
+/*
+  These functions compress data in successive blocks of any size,
+  using previous blocks as dictionary, to improve compression ratio.
+  One key assumption is that previous blocks (up to 64 KB) remain read-accessible while compressing next blocks.
+  There is an exception for ring buffers, which can be smaller than 64 KB.
+  Ring-buffer scenario is automatically detected and handled within LZ4_compress_HC_continue().
+
+  Before starting compression, state must be allocated and properly initialized.
+  LZ4_createStreamHC() does both, though compression level is set to LZ4HC_CLEVEL_DEFAULT.
+
+  Selecting the compression level can be done with LZ4_resetStreamHC_fast() (starts a new stream)
+  or LZ4_setCompressionLevel() (anytime, between blocks in the same stream) (experimental).
+  LZ4_resetStreamHC_fast() only works on states which have been properly initialized at least once,
+  which is automatically the case when state is created using LZ4_createStreamHC().
+
+  After reset, a first "fictional block" can be designated as initial dictionary,
+  using LZ4_loadDictHC() (Optional).
+
+  Invoke LZ4_compress_HC_continue() to compress each successive block.
+  The number of blocks is unlimited.
+  Previous input blocks, including initial dictionary when present,
+  must remain accessible and unmodified during compression.
+
+  It's allowed to update compression level anytime between blocks,
+  using LZ4_setCompressionLevel() (experimental).
+
+  'dst' buffer should be sized to handle worst case scenarios
+  (see LZ4_compressBound(), it ensures compression success).
+  In case of failure, the API does not guarantee recovery,
+  so the state _must_ be reset.
+  To ensure compression success
+  whenever `dst` buffer size cannot be made >= LZ4_compressBound(),
+  consider using LZ4_compress_HC_continue_destSize().
+
+  Whenever previous input blocks can't be preserved unmodified in-place during compression of next blocks,
+  it's possible to copy the last blocks into a more stable memory space, using LZ4_saveDictHC().
+  Return value of LZ4_saveDictHC() is the size of dictionary effectively saved into 'safeBuffer' (<= 64 KB)
+
+  After completing a streaming compression,
+  it's possible to start a new stream of blocks, using the same LZ4_streamHC_t state,
+  just by resetting it, using LZ4_resetStreamHC_fast().
+*/
+
+LZ4LIB_API void LZ4_resetStreamHC_fast(LZ4_streamHC_t* streamHCPtr, int compressionLevel);   /* v1.9.0+ */
+
+/*^**********************************************
+ * !!!!!!   STATIC LINKING ONLY   !!!!!!
+ ***********************************************/
+
+/*-******************************************************************
+ * PRIVATE DEFINITIONS :
+ * Do not use these definitions directly.
+ * They are merely exposed to allow static allocation of `LZ4_streamHC_t`.
+ * Declare an `LZ4_streamHC_t` directly, rather than any type below.
+ * Even then, only do so in the context of static linking, as definitions may change between versions.
+ ********************************************************************/
+
+#define LZ4HC_DICTIONARY_LOGSIZE 16
+#define LZ4HC_MAXD (1<<LZ4HC_DICTIONARY_LOGSIZE)
+#define LZ4HC_MAXD_MASK (LZ4HC_MAXD - 1)
+
+#define LZ4HC_HASH_LOG 15
+#define LZ4HC_HASHTABLESIZE (1 << LZ4HC_HASH_LOG)
+#define LZ4HC_HASH_MASK (LZ4HC_HASHTABLESIZE - 1)
+
+
+#if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */)
+#include <stdint.h>
+
+typedef struct LZ4HC_CCtx_internal LZ4HC_CCtx_internal;
+struct LZ4HC_CCtx_internal
+{
+    uint32_t   hashTable[LZ4HC_HASHTABLESIZE];
+    uint16_t   chainTable[LZ4HC_MAXD];
+    const uint8_t* end;         /* next block here to continue on current prefix */
+    const uint8_t* base;        /* All index relative to this position */
+    const uint8_t* dictBase;    /* alternate base for extDict */
+    uint32_t   dictLimit;       /* below that point, need extDict */
+    uint32_t   lowLimit;        /* below that point, no more dict */
+    uint32_t   nextToUpdate;    /* index from which to continue dictionary update */
+    short      compressionLevel;
+    int8_t     favorDecSpeed;   /* favor decompression speed if this flag set,
+                                   otherwise, favor compression ratio */
+    int8_t     dirty;           /* stream has to be fully reset if this flag is set */
+    const LZ4HC_CCtx_internal* dictCtx;
+};
+
+#else
+
+typedef struct LZ4HC_CCtx_internal LZ4HC_CCtx_internal;
+struct LZ4HC_CCtx_internal
+{
+    unsigned int   hashTable[LZ4HC_HASHTABLESIZE];
+    unsigned short chainTable[LZ4HC_MAXD];
+    const unsigned char* end;        /* next block here to continue on current prefix */
+    const unsigned char* base;       /* All index relative to this position */
+    const unsigned char* dictBase;   /* alternate base for extDict */
+    unsigned int   dictLimit;        /* below that point, need extDict */
+    unsigned int   lowLimit;         /* below that point, no more dict */
+    unsigned int   nextToUpdate;     /* index from which to continue dictionary update */
+    short          compressionLevel;
+    char           favorDecSpeed;    /* favor decompression speed if this flag set,
+                                        otherwise, favor compression ratio */
+    char           dirty;            /* stream has to be fully reset if this flag is set */
+    const LZ4HC_CCtx_internal* dictCtx;
+};
+
+#endif
+
+
+/* Do not use these definitions directly !
+ * Declare or allocate an LZ4_streamHC_t instead.
+ */
+#define LZ4_STREAMHCSIZE       (4*LZ4HC_HASHTABLESIZE + 2*LZ4HC_MAXD + 56 + ((sizeof(void*)==16) ? 56 : 0) /* AS400*/ ) /* 262200 or 262256*/
+#define LZ4_STREAMHCSIZE_SIZET (LZ4_STREAMHCSIZE / sizeof(size_t))
+union LZ4_streamHC_u {
+    size_t table[LZ4_STREAMHCSIZE_SIZET];
+    LZ4HC_CCtx_internal internal_donotuse;
+}; /* previously typedef'd to LZ4_streamHC_t */
+
+/* LZ4_streamHC_t :
+ * This structure allows static allocation of LZ4 HC streaming state.
+ * This can be used to allocate statically, on state, or as part of a larger structure.
+ *
+ * Such state **must** be initialized using LZ4_initStreamHC() before first use.
+ *
+ * Note that invoking LZ4_initStreamHC() is not required when
+ * the state was created using LZ4_createStreamHC() (which is recommended).
+ * Using the normal builder, a newly created state is automatically initialized.
+ *
+ * Static allocation shall only be used in combination with static linking.
+ */
+
+/* LZ4_initStreamHC() : v1.9.0+
+ * Required before first use of a statically allocated LZ4_streamHC_t.
+ * Before v1.9.0 : use LZ4_resetStreamHC() instead
+ */
+LZ4LIB_API LZ4_streamHC_t* LZ4_initStreamHC (void* buffer, size_t size);
+
+#if defined (__cplusplus)
+}
+#endif
+
+#endif /* LZ4_HC_H_19834876238432 */
+
+
+/*-**************************************************
+ * !!!!!     STATIC LINKING ONLY     !!!!!
+ * Following definitions are considered experimental.
+ * They should not be linked from DLL,
+ * as there is no guarantee of API stability yet.
+ * Prototypes will be promoted to "stable" status
+ * after successfull usage in real-life scenarios.
+ ***************************************************/
+#ifdef LZ4_HC_STATIC_LINKING_ONLY   /* protection macro */
+#ifndef LZ4_HC_SLO_098092834
+#define LZ4_HC_SLO_098092834
+
+#define LZ4_STATIC_LINKING_ONLY   /* LZ4LIB_STATIC_API */
+#include "lz4.h"
+
+#if defined (__cplusplus)
+extern "C" {
+#endif
+
+/*! LZ4_setCompressionLevel() : v1.8.0+ (experimental)
+ *  It's possible to change compression level
+ *  between successive invocations of LZ4_compress_HC_continue*()
+ *  for dynamic adaptation.
+ */
+LZ4LIB_STATIC_API void LZ4_setCompressionLevel(
+    LZ4_streamHC_t* LZ4_streamHCPtr, int compressionLevel);
+
+/*! LZ4_resetStreamHC_fast() : v1.9.0+
+ *  When an LZ4_streamHC_t is known to be in a internally coherent state,
+ *  it can often be prepared for a new compression with almost no work, only
+ *  sometimes falling back to the full, expensive reset that is always required
+ *  when the stream is in an indeterminate state (i.e., the reset performed by
+ *  LZ4_resetStreamHC()).
+ *
+ *  LZ4_streamHCs are guaranteed to be in a valid state when:
+ *  - returned from LZ4_createStreamHC()
+ *  - reset by LZ4_resetStreamHC()
+ *  - memset(stream, 0, sizeof(LZ4_streamHC_t))
+ *  - the stream was in a valid state and was reset by LZ4_resetStreamHC_fast()
+ *  - the stream was in a valid state and was then used in any compression call
+ *    that returned success
+ *  - the stream was in an indeterminate state and was used in a compression
+ *    call that fully reset the state (LZ4_compress_HC_extStateHC()) and that
+ *    returned success
+ *
+ *  Note:
+ *  A stream that was last used in a compression call that returned an error
+ *  may be passed to this function. However, it will be fully reset, which will
+ *  clear any existing history and settings from the context.
+ */
+LZ4LIB_STATIC_API void LZ4_resetStreamHC_fast(
+    LZ4_streamHC_t* LZ4_streamHCPtr, int compressionLevel);
+
+#if defined (__cplusplus)
+}
+#endif
+
+#endif   /* LZ4_HC_SLO_098092834 */
+#endif   /* LZ4_HC_STATIC_LINKING_ONLY */
diff --git a/mkwinbins.sh b/mkwinbins.sh
index ef899eb..efb1411 100755
--- a/mkwinbins.sh
+++ b/mkwinbins.sh
@@ -100,36 +100,6 @@ make -j
 make install-strip
 popd
 
-################################## get lz4 ###################################
-
-PKG_DIR="lz4-1.9.2"
-PKG_TAR="${PKG_DIR}.tar.gz"
-PKG_HASH="658ba6191fa44c92280d4aa2c271b0f4fbc0e34d249578dd05e50e76d0e5efcc"
-
-download
-
-pushd "$PKG_DIR"
-make -j BUILD_STATIC="no" BUILD_SHARED="yes" CC="${W32_PREFIX}-gcc" \
-     DLLTOOL="${W32_PREFIX}-dlltool" WINDRES="${W32_PREFIX}-windres" \
-     OS="Windows_NT" WINBASED="yes" PREFIX="$W32_DIR" \
-     lib-release
-make BUILD_STATIC="no" BUILD_SHARED="yes" CC="${W32_PREFIX}-gcc" \
-     DLLTOOL="${W32_PREFIX}-dlltool" WINDRES="${W32_PREFIX}-windres" \
-     OS="Windows_NT" WINBASED="yes" PREFIX="$W32_DIR" \
-     -C "lib" install
-
-make clean
-
-make -j BUILD_STATIC="no" BUILD_SHARED="yes" CC="${W64_PREFIX}-gcc" \
-     DLLTOOL="${W64_PREFIX}-dlltool" WINDRES="${W64_PREFIX}-windres" \
-     OS="Windows_NT" WINBASED="yes" PREFIX="$W64_DIR" \
-     lib-release
-make BUILD_STATIC="no" BUILD_SHARED="yes" CC="${W64_PREFIX}-gcc" \
-     DLLTOOL="${W64_PREFIX}-dlltool" WINDRES="${W64_PREFIX}-windres" \
-     OS="Windows_NT" WINBASED="yes" PREFIX="$W64_DIR" \
-     -C "lib" install
-popd
-
 ################################## get zstd ##################################
 
 PKG_DIR="zstd-v1.4.4-win32"
@@ -181,14 +151,14 @@ _EOF
 ./autogen.sh
 ./configure CFLAGS="-O2" LZO_CFLAGS="-I$W32_DIR/include" \
 	    LZO_LIBS="-L$W32_DIR/lib -llzo2" \
-	    --prefix="$W32_DIR" --host="$W32_PREFIX"
+	    --prefix="$W32_DIR" --host="$W32_PREFIX" --with-builtin-lz4
 cp "$W32_DIR/bin/"*.dll .
 make -j check
 rm *.dll
 
 ./configure CFLAGS="-O2 -DNDEBUG" LZO_CFLAGS="-I$W32_DIR/include" \
 	    LZO_LIBS="-L$W32_DIR/lib -llzo2" \
-	    --prefix="$W32_DIR" --host="$W32_PREFIX"
+	    --prefix="$W32_DIR" --host="$W32_PREFIX" --with-builtin-lz4
 make clean
 make -j
 make install-strip
@@ -197,7 +167,7 @@ make install-strip
 
 ./configure CFLAGS="-O2" LZO_CFLAGS="-I$W64_DIR/include" \
 	    LZO_LIBS="-L$W64_DIR/lib -llzo2" \
-	    --prefix="$W64_DIR" --host="$W64_PREFIX"
+	    --prefix="$W64_DIR" --host="$W64_PREFIX" --with-builtin-lz4
 make clean
 cp "$W64_DIR/bin/"*.dll .
 make -j check
@@ -205,7 +175,7 @@ rm *.dll
 
 ./configure CFLAGS="-O2 -DNDEBUG" LZO_CFLAGS="-I$W64_DIR/include" \
 	    LZO_LIBS="-L$W64_DIR/lib -llzo2" \
-	    --prefix="$W64_DIR" --host="$W64_PREFIX"
+	    --prefix="$W64_DIR" --host="$W64_PREFIX" --with-builtin-lz4
 make clean
 make -j
 make install-strip