diff options
Diffstat (limited to 'openvpn')
| -rw-r--r-- | openvpn/Android.mk | 4 | ||||
| -rw-r--r-- | openvpn/README.IPv6 | 2 | ||||
| -rw-r--r-- | openvpn/TODO.IPv6 | 4 | ||||
| -rw-r--r-- | openvpn/config.h | 2 | ||||
| -rw-r--r-- | openvpn/configure.ac | 51 | ||||
| -rw-r--r-- | openvpn/src/compat/Makefile.am | 3 | ||||
| -rw-r--r-- | openvpn/src/compat/compat-lz4.c | 830 | ||||
| -rw-r--r-- | openvpn/src/compat/compat-lz4.h | 205 | ||||
| -rw-r--r-- | openvpn/src/openvpn/Makefile.am | 3 | ||||
| -rw-r--r-- | openvpn/src/openvpn/comp-lz4.c | 195 | ||||
| -rw-r--r-- | openvpn/src/openvpn/comp-lz4.h | 40 | ||||
| -rw-r--r-- | openvpn/src/openvpn/comp.c | 11 | ||||
| -rw-r--r-- | openvpn/src/openvpn/comp.h | 11 | ||||
| -rw-r--r-- | openvpn/src/openvpn/init.c | 6 | ||||
| -rw-r--r-- | openvpn/src/openvpn/options.c | 10 | ||||
| -rw-r--r-- | openvpn/src/openvpn/syshead.h | 3 | ||||
| -rw-r--r-- | openvpn/src/openvpn/tun.c | 2 |
17 files changed, 1370 insertions, 12 deletions
diff --git a/openvpn/Android.mk b/openvpn/Android.mk index 98622417..b373497e 100644 --- a/openvpn/Android.mk +++ b/openvpn/Android.mk @@ -35,6 +35,7 @@ LOCAL_SRC_FILES:= \ src/compat/compat-gettimeofday.c \ src/compat/compat-inet_ntop.c \ src/compat/compat-inet_pton.c \ + src/compat/compat-lz4.c \ src/openvpn/base64.c \ src/openvpn/buffer.c \ src/openvpn/clinat.c \ @@ -102,8 +103,9 @@ LOCAL_SRC_FILES:= \ src/openvpn/status.c \ src/openvpn/tun.c \ src/openvpn/snappy.c \ + src/openvpn/comp-lz4.c \ src/openvpn/comp.c \ - src/openvpn/compstub.c + src/openvpn/compstub.c \ ifeq ($(WITH_BREAKPAD),1) diff --git a/openvpn/README.IPv6 b/openvpn/README.IPv6 index 3d8fbeb2..d16a6daf 100644 --- a/openvpn/README.IPv6 +++ b/openvpn/README.IPv6 @@ -35,7 +35,7 @@ over an IPv6 network ("OpenVPN over IPv6"). The code in 2.3.0 supersedes the IPv6 transport patches from JuanJo Ciarlante, formerly located at http://github.com/jjo/openvpn-ipv6 -Android 2.4.0 includes a big overhaul of the IPv6 transport patches +Android 2.4.0 includes a big overhaul of the IPv6 transport patches originally implemented for the Android client (ics-openvpn) IPv4/IPv6 transport is automatically is selected when resolving addresses. diff --git a/openvpn/TODO.IPv6 b/openvpn/TODO.IPv6 index 378358c2..ef2b8463 100644 --- a/openvpn/TODO.IPv6 +++ b/openvpn/TODO.IPv6 @@ -204,7 +204,7 @@ TODO for IPv6 transport support o implement comparison for mapped addesses: server in dual stack listening IPv6 must permit incoming streams from allowed IPv4 peer, currently you need to pass eg: --remote ffff::1.2.3.4 - - OpenVPN will compare all address of a remote + - OpenVPN will compare all address of a remote but will still fail on mapped addresses * win32: @@ -212,5 +212,3 @@ TODO for IPv6 transport support with bound at ::1 and connect to 127.0.0.1 - Should be fixed by 8832c6c - "Implement listing on IPv4/IPv6 dual socket on all platform" - - diff --git a/openvpn/config.h b/openvpn/config.h index 5e2325a2..d281d33d 100644 --- a/openvpn/config.h +++ b/openvpn/config.h @@ -540,6 +540,8 @@ /* Use LZO compression library */ #define ENABLE_LZO 1 #define ENABLE_SNAPPY 1 +#define ENABLE_LZ4 1 +#define NEED_COMPAT_LZ4 1 /* Enable PKCS11 capability */ /* #undef USE_PKCS11 */ diff --git a/openvpn/configure.ac b/openvpn/configure.ac index 23e76f6c..636d4e25 100644 --- a/openvpn/configure.ac +++ b/openvpn/configure.ac @@ -52,6 +52,12 @@ AC_ARG_ENABLE(snappy, [enable_snappy="yes"] ) +AC_ARG_ENABLE(lz4, + [ --disable-lz4 Disable LZ4 compression support], + [enable_lz4="$enableval"], + [enable_lz4="yes"] +) + AC_ARG_ENABLE(comp-stub, [ --enable-comp-stub Don't compile compression support but still allow limited interoperability with compression-enabled peers], [enable_comp_stub="$enableval"], @@ -934,6 +940,48 @@ if test "$enable_snappy" = "yes" && test "$enable_comp_stub" = "no"; then CFLAGS="${saved_CFLAGS}" fi +dnl +dnl check for LZ4 library +dnl + +AC_ARG_VAR([LZ4_CFLAGS], [C compiler flags for lz4]) +AC_ARG_VAR([LZ4_LIBS], [linker flags for lz4]) +if test "$enable_lz4" = "yes" && test "$enable_comp_stub" = "no"; then + AC_CHECKING([for LZ4 Library and Header files]) + havelz4lib=1 + + # if LZ4_LIBS is set, we assume it will work, otherwise test + if test -z "${LZ4_LIBS}"; then + AC_CHECK_LIB(lz4, LZ4_compress, + [ LZ4_LIBS="-llz4" ], + [ + AC_MSG_RESULT([LZ4 library not found.]) + havelz4lib=0 + ]) + fi + + saved_CFLAGS="${CFLAGS}" + CFLAGS="${CFLAGS} ${LZ4_CFLAGS}" + AC_CHECK_HEADER(lz4.h, + , + [ + AC_MSG_RESULT([LZ4 headers not found.]) + havelz4lib=0 + ]) + + if test $havelz4lib = 0 ; then + AC_MSG_RESULT([LZ4 library or header not found, using version in src/compat/compat-lz4.*]) + AC_DEFINE([NEED_COMPAT_LZ4], [1], [use copy of LZ4 source in compat/]) + LZ4_LIBS="" + fi + OPTIONAL_LZ4_CFLAGS="${LZ4_CFLAGS}" + OPTIONAL_LZ4_LIBS="${LZ4_LIBS}" + AC_DEFINE(ENABLE_LZ4, 1, [Enable LZ4 compression library]) + CFLAGS="${saved_CFLAGS}" +fi + + + AC_MSG_CHECKING([git checkout]) GIT_CHECKOUT="no" @@ -1045,6 +1093,7 @@ fi if test "${enable_comp_stub}" = "yes"; then test "${enable_lzo}" = "yes" && AC_MSG_ERROR([Cannot have both comp stub and lzo enabled (use --disable-lzo)]) test "${enable_snappy}" = "yes" && AC_MSG_ERROR([Cannot have both comp stub and snappy enabled (use --disable-snappy)]) + test "${enable_lz4}" = "yes" && AC_MSG_ERROR([Cannot have both comp stub and LZ4 enabled (use --disable-lz4)]) AC_DEFINE([ENABLE_COMP_STUB], [1], [Enable compression stub capability]) fi @@ -1101,6 +1150,8 @@ AC_SUBST([OPTIONAL_LZO_CFLAGS]) AC_SUBST([OPTIONAL_LZO_LIBS]) AC_SUBST([OPTIONAL_SNAPPY_CFLAGS]) AC_SUBST([OPTIONAL_SNAPPY_LIBS]) +AC_SUBST([OPTIONAL_LZ4_CFLAGS]) +AC_SUBST([OPTIONAL_LZ4_LIBS]) AC_SUBST([OPTIONAL_PKCS11_HELPER_CFLAGS]) AC_SUBST([OPTIONAL_PKCS11_HELPER_LIBS]) diff --git a/openvpn/src/compat/Makefile.am b/openvpn/src/compat/Makefile.am index 7ad44525..4591b851 100644 --- a/openvpn/src/compat/Makefile.am +++ b/openvpn/src/compat/Makefile.am @@ -26,4 +26,5 @@ libcompat_la_SOURCES = \ compat-gettimeofday.c \ compat-daemon.c \ compat-inet_ntop.c \ - compat-inet_pton.c + compat-inet_pton.c \ + compat-lz4.c compat-lz4.h diff --git a/openvpn/src/compat/compat-lz4.c b/openvpn/src/compat/compat-lz4.c new file mode 100644 index 00000000..c63c18ba --- /dev/null +++ b/openvpn/src/compat/compat-lz4.c @@ -0,0 +1,830 @@ +/* + LZ4 - Fast LZ compression algorithm + Copyright (C) 2011-2013, 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 : http://code.google.com/p/lz4/ + - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c +*/ + +#ifdef HAVE_CONFIG_H +#include "config.h" +#elif defined(_MSC_VER) +#include "config-msvc.h" +#endif + +#ifdef NEED_COMPAT_LZ4 + +//************************************** +// Tuning parameters +//************************************** +// 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 can improve speed, due to cache effect +// Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache +#define MEMORY_USAGE 14 + +// 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 memory allocation (malloc)). +#define HEAPMODE 0 + + +//************************************** +// CPU Feature Detection +//************************************** +// 32 or 64 bits ? +#if (defined(__x86_64__) || defined(_M_X64) || defined(_WIN64) \ + || defined(__powerpc64__) || defined(__ppc64__) || defined(__PPC64__) \ + || defined(__64BIT__) || defined(_LP64) || defined(__LP64__) \ + || defined(__ia64) || defined(__itanium__) || defined(_M_IA64) ) // Detects 64 bits mode +# define LZ4_ARCH64 1 +#else +# define LZ4_ARCH64 0 +#endif + +// Little Endian or Big Endian ? +// Overwrite the #define below if you know your architecture endianess +#if defined (__GLIBC__) +# include <endian.h> +# if (__BYTE_ORDER == __BIG_ENDIAN) +# define LZ4_BIG_ENDIAN 1 +# endif +#elif (defined(__BIG_ENDIAN__) || defined(__BIG_ENDIAN) || defined(_BIG_ENDIAN)) && !(defined(__LITTLE_ENDIAN__) || defined(__LITTLE_ENDIAN) || defined(_LITTLE_ENDIAN)) +# define LZ4_BIG_ENDIAN 1 +#elif defined(__sparc) || defined(__sparc__) \ + || defined(__powerpc__) || defined(__ppc__) || defined(__PPC__) \ + || defined(__hpux) || defined(__hppa) \ + || defined(_MIPSEB) || defined(__s390__) +# define LZ4_BIG_ENDIAN 1 +#else +// Little Endian assumed. PDP Endian and other very rare endian format are unsupported. +#endif + +// Unaligned memory access is automatically enabled for "common" CPU, such as x86. +// For others CPU, such as ARM, the compiler may be more cautious, inserting unnecessary extra code to ensure aligned access property +// If you know your target CPU supports unaligned memory access, you want to force this option manually to improve performance +#if defined(__ARM_FEATURE_UNALIGNED) +# define LZ4_FORCE_UNALIGNED_ACCESS 1 +#endif + +// 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 Windows CE does not support Hardware bit count +# define LZ4_FORCE_SW_BITCOUNT +#endif + +// BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE : +// This option may provide a small boost to performance for some big endian cpu, although probably modest. +// You may set this option to 1 if data will remain within closed environment. +// This option is useless on Little_Endian CPU (such as x86) +//#define BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE 1 + + +//************************************** +// Compiler Options +//************************************** +#if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) // C99 +/* "restrict" is a known keyword */ +#else +# define restrict // Disable restrict +#endif + +#ifdef _MSC_VER // Visual Studio +# define FORCE_INLINE static __forceinline +# include <intrin.h> // For Visual 2005 +# if LZ4_ARCH64 // 64-bits +# pragma intrinsic(_BitScanForward64) // For Visual 2005 +# pragma intrinsic(_BitScanReverse64) // For Visual 2005 +# else // 32-bits +# pragma intrinsic(_BitScanForward) // For Visual 2005 +# pragma intrinsic(_BitScanReverse) // For Visual 2005 +# endif +# pragma warning(disable : 4127) // disable: C4127: conditional expression is constant +#else +# ifdef __GNUC__ +# define FORCE_INLINE static inline __attribute__((always_inline)) +# else +# define FORCE_INLINE static inline +# endif +#endif + +#ifdef _MSC_VER +# define lz4_bswap16(x) _byteswap_ushort(x) +#else +# define lz4_bswap16(x) ((unsigned short int) ((((x) >> 8) & 0xffu) | (((x) & 0xffu) << 8))) +#endif + +#define GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__) + +#if (GCC_VERSION >= 302) || (__INTEL_COMPILER >= 800) || defined(__clang__) +# define expect(expr,value) (__builtin_expect ((expr),(value)) ) +#else +# define expect(expr,value) (expr) +#endif + +#define likely(expr) expect((expr) != 0, 1) +#define unlikely(expr) expect((expr) != 0, 0) + + +//************************************** +// Memory routines +//************************************** +#include <stdlib.h> // malloc, calloc, free +#define ALLOCATOR(n,s) calloc(n,s) +#define FREEMEM free +#include <string.h> // memset, memcpy +#define MEM_INIT memset + + +//************************************** +// Includes +//************************************** +#include "compat-lz4.h" + + +//************************************** +// Basic Types +//************************************** +#if 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; +#else + typedef unsigned char BYTE; + typedef unsigned short U16; + typedef unsigned int U32; + typedef signed int S32; + typedef unsigned long long U64; +#endif + +#if defined(__GNUC__) && !defined(LZ4_FORCE_UNALIGNED_ACCESS) +# define _PACKED __attribute__ ((packed)) +#else +# define _PACKED +#endif + +#if !defined(LZ4_FORCE_UNALIGNED_ACCESS) && !defined(__GNUC__) +# if defined(__IBMC__) || defined(__SUNPRO_C) || defined(__SUNPRO_CC) +# pragma pack(1) +# else +# pragma pack(push, 1) +# endif +#endif + +typedef struct { U16 v; } _PACKED U16_S; +typedef struct { U32 v; } _PACKED U32_S; +typedef struct { U64 v; } _PACKED U64_S; +typedef struct {size_t v;} _PACKED size_t_S; + +#if !defined(LZ4_FORCE_UNALIGNED_ACCESS) && !defined(__GNUC__) +# if defined(__SUNPRO_C) || defined(__SUNPRO_CC) +# pragma pack(0) +# else +# pragma pack(pop) +# endif +#endif + +#define A16(x) (((U16_S *)(x))->v) +#define A32(x) (((U32_S *)(x))->v) +#define A64(x) (((U64_S *)(x))->v) +#define AARCH(x) (((size_t_S *)(x))->v) + + +//************************************** +// Constants +//************************************** +#define LZ4_HASHLOG (MEMORY_USAGE-2) +#define HASHTABLESIZE (1 << MEMORY_USAGE) +#define HASHNBCELLS4 (1 << LZ4_HASHLOG) + +#define MINMATCH 4 + +#define COPYLENGTH 8 +#define LASTLITERALS 5 +#define MFLIMIT (COPYLENGTH+MINMATCH) +const int LZ4_minLength = (MFLIMIT+1); + +#define LZ4_64KLIMIT ((1<<16) + (MFLIMIT-1)) +#define SKIPSTRENGTH 6 // Increasing this value will make the compression run slower on incompressible data + +#define MAXD_LOG 16 +#define MAX_DISTANCE ((1 << MAXD_LOG) - 1) + +#define ML_BITS 4 +#define ML_MASK ((1U<<ML_BITS)-1) +#define RUN_BITS (8-ML_BITS) +#define RUN_MASK ((1U<<RUN_BITS)-1) + +#define KB *(1U<<10) +#define MB *(1U<<20) +#define GB *(1U<<30) + + +//************************************** +// Structures and local types +//************************************** + +typedef struct { + U32 hashTable[HASHNBCELLS4]; + const BYTE* bufferStart; + const BYTE* base; + const BYTE* nextBlock; +} LZ4_Data_Structure; + +typedef enum { notLimited = 0, limited = 1 } limitedOutput_directive; +typedef enum { byPtr, byU32, byU16 } tableType_t; + +typedef enum { noPrefix = 0, withPrefix = 1 } prefix64k_directive; + +typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive; +typedef enum { full = 0, partial = 1 } earlyEnd_directive; + + +//************************************** +// Architecture-specific macros +//************************************** +#define STEPSIZE sizeof(size_t) +#define LZ4_COPYSTEP(d,s) { AARCH(d) = AARCH(s); d+=STEPSIZE; s+=STEPSIZE; } +#define LZ4_COPY8(d,s) { LZ4_COPYSTEP(d,s); if (STEPSIZE<8) LZ4_COPYSTEP(d,s); } +#define LZ4_SECURECOPY(d,s,e) { if ((STEPSIZE==4)||(d<e)) LZ4_WILDCOPY(d,s,e); } + +#if LZ4_ARCH64 // 64-bit +# define HTYPE U32 +# define INITBASE(base) const BYTE* const base = ip +#else // 32-bit +# define HTYPE const BYTE* +# define INITBASE(base) const int base = 0 +#endif + +#if (defined(LZ4_BIG_ENDIAN) && !defined(BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE)) +# define LZ4_READ_LITTLEENDIAN_16(d,s,p) { U16 v = A16(p); v = lz4_bswap16(v); d = (s) - v; } +# define LZ4_WRITE_LITTLEENDIAN_16(p,i) { U16 v = (U16)(i); v = lz4_bswap16(v); A16(p) = v; p+=2; } +#else // Little Endian +# define LZ4_READ_LITTLEENDIAN_16(d,s,p) { d = (s) - A16(p); } +# define LZ4_WRITE_LITTLEENDIAN_16(p,v) { A16(p) = v; p+=2; } +#endif + + +//************************************** +// Macros +//************************************** +#define LZ4_WILDCOPY(d,s,e) { do { LZ4_COPY8(d,s) } while (d<e); } // at the end, d>=e; + + +//**************************** +// Private functions +//**************************** +#if LZ4_ARCH64 + +FORCE_INLINE int LZ4_NbCommonBytes (register U64 val) +{ +# if defined(LZ4_BIG_ENDIAN) +# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) + unsigned long r = 0; + _BitScanReverse64( &r, val ); + return (int)(r>>3); +# elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT) + return (__builtin_clzll(val) >> 3); +# else + int r; + if (!(val>>32)) { r=4; } else { r=0; val>>=32; } + if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; } + r += (!val); + return r; +# endif +# else +# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) + unsigned long r = 0; + _BitScanForward64( &r, val ); + return (int)(r>>3); +# elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT) + return (__builtin_ctzll(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 +# endif +} + +#else + +FORCE_INLINE int LZ4_NbCommonBytes (register U32 val) +{ +# if defined(LZ4_BIG_ENDIAN) +# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) + unsigned long r = 0; + _BitScanReverse( &r, val ); + return (int)(r>>3); +# elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT) + return (__builtin_clz(val) >> 3); +# else + int r; + if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; } + r += (!val); + return r; +# endif +# else +# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) + unsigned long r; + _BitScanForward( &r, val ); + return (int)(r>>3); +# elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT) + return (__builtin_ctz(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 +# endif +} + +#endif + + +//**************************** +// Compression functions +//**************************** +FORCE_INLINE int LZ4_hashSequence(U32 sequence, tableType_t tableType) +{ + if (tableType == byU16) + return (((sequence) * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1))); + else + return (((sequence) * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG)); +} + +FORCE_INLINE int LZ4_hashPosition(const BYTE* p, tableType_t tableType) { return LZ4_hashSequence(A32(p), tableType); } + +FORCE_INLINE void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase) +{ + switch (tableType) + { + case byPtr: { const BYTE** hashTable = (const BYTE**) tableBase; hashTable[h] = p; break; } + case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = (U32)(p-srcBase); break; } + case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = (U16)(p-srcBase); break; } + } +} + +FORCE_INLINE void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase) +{ + U32 h = LZ4_hashPosition(p, tableType); + LZ4_putPositionOnHash(p, h, tableBase, tableType, srcBase); +} + +FORCE_INLINE const BYTE* LZ4_getPositionOnHash(U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase) +{ + if (tableType == byPtr) { const BYTE** hashTable = (const BYTE**) tableBase; return hashTable[h]; } + if (tableType == byU32) { U32* hashTable = (U32*) tableBase; return hashTable[h] + srcBase; } + { U16* hashTable = (U16*) tableBase; return hashTable[h] + srcBase; } // default, to ensure a return +} + +FORCE_INLINE const BYTE* LZ4_getPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase) +{ + U32 h = LZ4_hashPosition(p, tableType); + return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase); +} + + +FORCE_INLINE int LZ4_compress_generic( + void* ctx, + const char* source, + char* dest, + int inputSize, + int maxOutputSize, + + limitedOutput_directive limitedOutput, + tableType_t tableType, + prefix64k_directive prefix) +{ + const BYTE* ip = (const BYTE*) source; + const BYTE* const base = (prefix==withPrefix) ? ((LZ4_Data_Structure*)ctx)->base : (const BYTE*) source; + const BYTE* const lowLimit = ((prefix==withPrefix) ? ((LZ4_Data_Structure*)ctx)->bufferStart : (const BYTE*)source); + const BYTE* anchor = (const BYTE*) source; + const BYTE* const iend = ip + inputSize; + const BYTE* const mflimit = iend - MFLIMIT; + const BYTE* const matchlimit = iend - LASTLITERALS; + + BYTE* op = (BYTE*) dest; + BYTE* const oend = op + maxOutputSize; + + int length; + const int skipStrength = SKIPSTRENGTH; + U32 forwardH; + + // Init conditions + if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0; // Unsupported input size, too large (or negative) + if ((prefix==withPrefix) && (ip != ((LZ4_Data_Structure*)ctx)->nextBlock)) return 0; // must continue from end of previous block + if (prefix==withPrefix) ((LZ4_Data_Structure*)ctx)->nextBlock=iend; // do it now, due to potential early exit + if ((tableType == byU16) && (inputSize>=LZ4_64KLIMIT)) return 0; // Size too large (not within 64K limit) + if (inputSize<LZ4_minLength) goto _last_literals; // Input too small, no compression (all literals) + + // First Byte + LZ4_putPosition(ip, ctx, tableType, base); + ip++; forwardH = LZ4_hashPosition(ip, tableType); + + // Main Loop + for ( ; ; ) + { + int findMatchAttempts = (1U << skipStrength) + 3; + const BYTE* forwardIp = ip; + const BYTE* ref; + BYTE* token; + + // Find a match + do { + U32 h = forwardH; + int step = findMatchAttempts++ >> skipStrength; + ip = forwardIp; + forwardIp = ip + step; + + if unlikely(forwardIp > mflimit) { goto _last_literals; } + + forwardH = LZ4_hashPosition(forwardIp, tableType); + ref = LZ4_getPositionOnHash(h, ctx, tableType, base); + LZ4_putPositionOnHash(ip, h, ctx, tableType, base); + + } while ((ref + MAX_DISTANCE < ip) || (A32(ref) != A32(ip))); + + // Catch up + while ((ip>anchor) && (ref > lowLimit) && unlikely(ip[-1]==ref[-1])) { ip--; ref--; } + + // Encode Literal length + length = (int)(ip - anchor); + token = op++; + if ((limitedOutput) && unlikely(op + length + (2 + 1 + LASTLITERALS) + (length/255) > oend)) return 0; // Check output limit + if (length>=(int)RUN_MASK) + { + int 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 + { BYTE* end=(op)+(length); LZ4_WILDCOPY(op,anchor,end); op=end; } + +_next_match: + // Encode Offset + LZ4_WRITE_LITTLEENDIAN_16(op,(U16)(ip-ref)); + + // Start Counting + ip+=MINMATCH; ref+=MINMATCH; // MinMatch already verified + anchor = ip; + while likely(ip<matchlimit-(STEPSIZE-1)) + { + size_t diff = AARCH(ref) ^ AARCH(ip); + if (!diff) { ip+=STEPSIZE; ref+=STEPSIZE; continue; } + ip += LZ4_NbCommonBytes(diff); + goto _endCount; + } + if (LZ4_ARCH64) if ((ip<(matchlimit-3)) && (A32(ref) == A32(ip))) { ip+=4; ref+=4; } + if ((ip<(matchlimit-1)) && (A16(ref) == A16(ip))) { ip+=2; ref+=2; } + if ((ip<matchlimit) && (*ref == *ip)) ip++; +_endCount: + + // Encode MatchLength + length = (int)(ip - anchor); + if ((limitedOutput) && unlikely(op + (1 + LASTLITERALS) + (length>>8) > oend)) return 0; // Check output limit + if (length>=(int)ML_MASK) + { + *token += ML_MASK; + length -= ML_MASK; + for (; length > 509 ; length-=510) { *op++ = 255; *op++ = 255; } + if (length >= 255) { length-=255; *op++ = 255; } + *op++ = (BYTE)length; + } + else *token += (BYTE)(length); + + // Test end of chunk + if (ip > mflimit) { anchor = ip; break; } + + // Fill table + LZ4_putPosition(ip-2, ctx, tableType, base); + + // Test next position + ref = LZ4_getPosition(ip, ctx, tableType, base); + LZ4_putPosition(ip, ctx, tableType, base); + if ((ref + MAX_DISTANCE >= ip) && (A32(ref) == A32(ip))) { token = op++; *token=0; goto _next_match; } + + // Prepare next loop + anchor = ip++; + forwardH = LZ4_hashPosition(ip, tableType); + } + +_last_literals: + // Encode Last Literals + { + int lastRun = (int)(iend - anchor); + if ((limitedOutput) && (((char*)op - dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize)) return 0; // Check output limit + if (lastRun>=(int)RUN_MASK) { *op++=(RUN_MASK<<ML_BITS); lastRun-=RUN_MASK; for(; lastRun >= 255 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; } + else *op++ = (BYTE)(lastRun<<ML_BITS); + memcpy(op, anchor, iend - anchor); + op += iend-anchor; + } + + // End + return (int) (((char*)op)-dest); +} + + +int LZ4_compress(const char* source, char* dest, int inputSize) +{ +#if (HEAPMODE) + void* ctx = ALLOCATOR(HASHNBCELLS4, 4); // Aligned on 4-bytes boundaries +#else + U32 ctx[1U<<(MEMORY_USAGE-2)] = {0}; // Ensure data is aligned on 4-bytes boundaries +#endif + int result; + + if (inputSize < (int)LZ4_64KLIMIT) + result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, 0, notLimited, byU16, noPrefix); + else + result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, 0, notLimited, (sizeof(void*)==8) ? byU32 : byPtr, noPrefix); + +#if (HEAPMODE) + FREEMEM(ctx); +#endif + return result; +} + +int LZ4_compress_continue (void* LZ4_Data, const char* source, char* dest, int inputSize) +{ + return LZ4_compress_generic(LZ4_Data, source, dest, inputSize, 0, notLimited, byU32, withPrefix); +} + + +int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize) +{ +#if (HEAPMODE) + void* ctx = ALLOCATOR(HASHNBCELLS4, 4); // Aligned on 4-bytes boundaries +#else + U32 ctx[1U<<(MEMORY_USAGE-2)] = {0}; // Ensure data is aligned on 4-bytes boundaries +#endif + int result; + + if (inputSize < (int)LZ4_64KLIMIT) + result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, maxOutputSize, limited, byU16, noPrefix); + else + result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, maxOutputSize, limited, (sizeof(void*)==8) ? byU32 : byPtr, noPrefix); + +#if (HEAPMODE) + FREEMEM(ctx); +#endif + return result; +} + +int LZ4_compress_limitedOutput_continue (void* LZ4_Data, const char* source, char* dest, int inputSize, int maxOutputSize) +{ + return LZ4_compress_generic(LZ4_Data, source, dest, inputSize, maxOutputSize, limited, byU32, withPrefix); +} + + +//**************************** +// Stream functions +//**************************** + +FORCE_INLINE void LZ4_init(LZ4_Data_Structure* lz4ds, const BYTE* base) +{ + MEM_INIT(lz4ds->hashTable, 0, sizeof(lz4ds->hashTable)); + lz4ds->bufferStart = base; + lz4ds->base = base; + lz4ds->nextBlock = base; +} + + +void* LZ4_create (const char* inputBuffer) +{ + void* lz4ds = ALLOCATOR(1, sizeof(LZ4_Data_Structure)); + LZ4_init ((LZ4_Data_Structure*)lz4ds, (const BYTE*)inputBuffer); + return lz4ds; +} + + +int LZ4_free (void* LZ4_Data) +{ + FREEMEM(LZ4_Data); + return (0); +} + + +char* LZ4_slideInputBuffer (void* LZ4_Data) +{ + LZ4_Data_Structure* lz4ds = (LZ4_Data_Structure*)LZ4_Data; + size_t delta = lz4ds->nextBlock - (lz4ds->bufferStart + 64 KB); + + if ( (lz4ds->base - delta > lz4ds->base) // underflow control + || ((size_t)(lz4ds->nextBlock - lz4ds->base) > 0xE0000000) ) // close to 32-bits limit + { + size_t deltaLimit = (lz4ds->nextBlock - 64 KB) - lz4ds->base; + int nH; + + for (nH=0; nH < HASHNBCELLS4; nH++) + { + if ((size_t)(lz4ds->hashTable[nH]) < deltaLimit) lz4ds->hashTable[nH] = 0; + else lz4ds->hashTable[nH] -= (U32)deltaLimit; + } + memcpy((void*)(lz4ds->bufferStart), (const void*)(lz4ds->nextBlock - 64 KB), 64 KB); + lz4ds->base = lz4ds->bufferStart; + lz4ds->nextBlock = lz4ds->base + 64 KB; + } + else + { + memcpy((void*)(lz4ds->bufferStart), (const void*)(lz4ds->nextBlock - 64 KB), 64 KB); + lz4ds->nextBlock -= delta; + lz4ds->base -= delta; + } + + return (char*)(lz4ds->nextBlock); +} + + +//**************************** +// Decompression functions +//**************************** + +// This generic decompression function cover all use cases. +// It shall be instanciated several times, using different sets of directives +// Note that it is essential this generic function is really inlined, +// in order to remove useless branches during compilation optimisation. +FORCE_INLINE int LZ4_decompress_generic( + const char* source, + char* dest, + int inputSize, // + int outputSize, // If endOnInput==endOnInputSize, this value is the max size of Output Buffer. + + int endOnInput, // endOnOutputSize, endOnInputSize + int prefix64k, // noPrefix, withPrefix + int partialDecoding, // full, partial + int targetOutputSize // only used if partialDecoding==partial + ) +{ + // Local Variables + const BYTE* restrict ip = (const BYTE*) source; + const BYTE* ref; + const BYTE* const iend = ip + inputSize; + + BYTE* op = (BYTE*) dest; + BYTE* const oend = op + outputSize; + BYTE* cpy; + BYTE* oexit = op + targetOutputSize; + + const size_t dec32table[] = {0, 3, 2, 3, 0, 0, 0, 0}; // static reduces speed for LZ4_decompress_safe() on GCC64 + static const size_t dec64table[] = {0, 0, 0, (size_t)-1, 0, 1, 2, 3}; + + + // Special cases + if ((partialDecoding) && (oexit> oend-MFLIMIT)) oexit = oend-MFLIMIT; // targetOutputSize too high => decode everything + if ((endOnInput) && unlikely(outputSize==0)) return ((inputSize==1) && (*ip==0)) ? 0 : -1; // Empty output buffer + if ((!endOnInput) && unlikely(outputSize==0)) return (*ip==0?1:-1); + + + // Main Loop + while (1) + { + unsigned token; + size_t length; + + // get runlength + token = *ip++; + if ((length=(token>>ML_BITS)) == RUN_MASK) + { + unsigned s=255; + while (((endOnInput)?ip<iend:1) && (s==255)) + { + s = *ip++; + length += s; + } + } + + // copy literals + cpy = op+length; + if (((endOnInput) && ((cpy>(partialDecoding?oexit:oend-MFLIMIT)) || (ip+length>iend-(2+1+LASTLITERALS))) ) + || ((!endOnInput) && (cpy>oend-COPYLENGTH))) + { + if (partialDecoding) + { + if (cpy > oend) goto _output_error; // Error : write attempt beyond end of output buffer + if ((endOnInput) && (ip+length > iend)) goto _output_error; // Error : read attempt beyond end of input buffer + } + else + { + if ((!endOnInput) && (cpy != oend)) goto _output_error; // Error : block decoding must stop exactly there + if ((endOnInput) && ((ip+length != iend) || (cpy > oend))) goto _output_error; // Error : input must be consumed + } + memcpy(op, ip, length); + ip += length; + op += length; + break; // Necessarily EOF, due to parsing restrictions + } + LZ4_WILDCOPY(op, ip, cpy); ip -= (op-cpy); op = cpy; + + // get offset + LZ4_READ_LITTLEENDIAN_16(ref,cpy,ip); ip+=2; + if ((prefix64k==noPrefix) && unlikely(ref < (BYTE* const)dest)) goto _output_error; // Error : offset outside destination buffer + + // get matchlength + if ((length=(token&ML_MASK)) == ML_MASK) + { + while ((!endOnInput) || (ip<iend-(LASTLITERALS+1))) // Ensure enough bytes remain for LASTLITERALS + token + { + unsigned s = *ip++; + length += s; + if (s==255) continue; + break; + } + } + + // copy repeated sequence + if unlikely((op-ref)<(int)STEPSIZE) + { + const size_t dec64 = dec64table[(sizeof(void*)==4) ? 0 : op-ref]; + op[0] = ref[0]; + op[1] = ref[1]; + op[2] = ref[2]; + op[3] = ref[3]; + op += 4, ref += 4; ref -= dec32table[op-ref]; + A32(op) = A32(ref); + op += STEPSIZE-4; ref -= dec64; + } else { LZ4_COPYSTEP(op,ref); } + cpy = op + length - (STEPSIZE-4); + + if unlikely(cpy>oend-COPYLENGTH-(STEPSIZE-4)) + { + if (cpy > oend-LASTLITERALS) goto _output_error; // Error : last 5 bytes must be literals + LZ4_SECURECOPY(op, ref, (oend-COPYLENGTH)); + while(op<cpy) *op++=*ref++; + op=cpy; + continue; + } + LZ4_WILDCOPY(op, ref, cpy); + op=cpy; // correction + } + + // end of decoding + if (endOnInput) + return (int) (((char*)op)-dest); // Nb of output bytes decoded + else + return (int) (((char*)ip)-source); // Nb of input bytes read + + // Overflow error detected +_output_error: + return (int) (-(((char*)ip)-source))-1; +} + + +int LZ4_decompress_safe(const char* source, char* dest, int inputSize, int maxOutputSize) +{ + return LZ4_decompress_generic(source, dest, inputSize, maxOutputSize, endOnInputSize, noPrefix, full, 0); +} + +int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int inputSize, int maxOutputSize) +{ + return LZ4_decompress_generic(source, dest, inputSize, maxOutputSize, endOnInputSize, withPrefix, full, 0); +} + +int LZ4_decompress_safe_partial(const char* source, char* dest, int inputSize, int targetOutputSize, int maxOutputSize) +{ + return LZ4_decompress_generic(source, dest, inputSize, maxOutputSize, endOnInputSize, noPrefix, partial, targetOutputSize); +} + +int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int outputSize) +{ + return LZ4_decompress_generic(source, dest, 0, outputSize, endOnOutputSize, withPrefix, full, 0); +} + +int LZ4_decompress_fast(const char* source, char* dest, int outputSize) +{ +#ifdef _MSC_VER // This version is faster with Visual + return LZ4_decompress_generic(source, dest, 0, outputSize, endOnOutputSize, noPrefix, full, 0); +#else + return LZ4_decompress_generic(source, dest, 0, outputSize, endOnOutputSize, withPrefix, full, 0); +#endif +} +#endif diff --git a/openvpn/src/compat/compat-lz4.h b/openvpn/src/compat/compat-lz4.h new file mode 100644 index 00000000..a289fcfd --- /dev/null +++ b/openvpn/src/compat/compat-lz4.h @@ -0,0 +1,205 @@ +/* + LZ4 - Fast LZ compression algorithm + Header File + Copyright (C) 2011-2013, 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://fastcompression.blogspot.com/p/lz4.html + - LZ4 source repository : http://code.google.com/p/lz4/ +*/ +#pragma once + +#if defined (__cplusplus) +extern "C" { +#endif + + +//************************************** +// Compiler Options +//************************************** +#if defined(_MSC_VER) && !defined(__cplusplus) // Visual Studio +# define inline __inline // Visual C is not C99, but supports some kind of inline +#endif + + +//**************************** +// Simple Functions +//**************************** + +int LZ4_compress (const char* source, char* dest, int inputSize); +int LZ4_decompress_safe (const char* source, char* dest, int inputSize, int maxOutputSize); + +/* +LZ4_compress() : + Compresses 'inputSize' bytes from 'source' into 'dest'. + Destination buffer must be already allocated, + and must be sized to handle worst cases situations (input data not compressible) + Worst case size evaluation is provided by function LZ4_compressBound() + inputSize : Max supported value is LZ4_MAX_INPUT_VALUE + return : the number of bytes written in buffer dest + or 0 if the compression fails + +LZ4_decompress_safe() : + maxOutputSize : is the size of the destination buffer (which must be already allocated) + return : the number of bytes decoded in the destination buffer (necessarily <= maxOutputSize) + If the source stream is detected malformed, the function will stop decoding and return a negative result. + This function is protected against buffer overflow exploits (never writes outside of output buffer, and never reads outside of input buffer). Therefore, it is protected against malicious data packets +*/ + + +//**************************** +// Advanced Functions +//**************************** +#define LZ4_MAX_INPUT_SIZE 0x7E000000 // 2 113 929 216 bytes +#define LZ4_COMPRESSBOUND(isize) ((unsigned int)(isize) > (unsigned int)LZ4_MAX_INPUT_SIZE ? 0 : (isize) + ((isize)/255) + 16) +static inline int LZ4_compressBound(int isize) { return LZ4_COMPRESSBOUND(isize); } + +/* +LZ4_compressBound() : + Provides the maximum size that LZ4 may output in a "worst case" scenario (input data not compressible) + primarily useful for memory allocation of output buffer. + inline function is recommended for the general case, + macro is also provided when result needs to be evaluated at compilation (such as stack memory allocation). + + isize : is the input size. Max supported value is LZ4_MAX_INPUT_SIZE + return : maximum output size in a "worst case" scenario + or 0, if input size is too large ( > LZ4_MAX_INPUT_SIZE) +*/ + + +int LZ4_compress_limitedOutput (const char* source, char* dest, int inputSize, int maxOutputSize); + +/* +LZ4_compress_limitedOutput() : + Compress 'inputSize' bytes from 'source' into an output buffer 'dest' of maximum size 'maxOutputSize'. + If it cannot achieve it, compression will stop, and result of the function will be zero. + This function never writes outside of provided output buffer. + + inputSize : Max supported value is LZ4_MAX_INPUT_VALUE + maxOutputSize : is the size of the destination buffer (which must be already allocated) + return : the number of bytes written in buffer 'dest' + or 0 if the compression fails +*/ + + +int LZ4_decompress_fast (const char* source, char* dest, int outputSize); + +/* +LZ4_decompress_fast() : + outputSize : is the original (uncompressed) size + return : the number of bytes read from the source buffer (in other words, the compressed size) + If the source stream is malformed, the function will stop decoding and return a negative result. + note : This function is a bit faster than LZ4_decompress_safe() + This function never writes outside of output buffers, but may read beyond input buffer in case of malicious data packet. + Use this function preferably into a trusted environment (data to decode comes from a trusted source). + Destination buffer must be already allocated. Its size must be a minimum of 'outputSize' bytes. +*/ + +int LZ4_decompress_safe_partial (const char* source, char* dest, int inputSize, int targetOutputSize, int maxOutputSize); + +/* +LZ4_decompress_safe_partial() : + This function decompress a compressed block of size 'inputSize' at position 'source' + into output buffer 'dest' of size 'maxOutputSize'. + The function tries to stop decompressing operation as soon as 'targetOutputSize' has been reached, + reducing decompression time. + return : the number of bytes decoded in the destination buffer (necessarily <= maxOutputSize) + Note : this number can be < 'targetOutputSize' should the compressed block to decode be smaller. + Always control how many bytes were decoded. + If the source stream is detected malformed, the function will stop decoding and return a negative result. + This function never writes outside of output buffer, and never reads outside of input buffer. It is therefore protected against malicious data packets +*/ + + +//**************************** +// Stream Functions +//**************************** + +void* LZ4_create (const char* inputBuffer); +int LZ4_compress_continue (void* LZ4_Data, const char* source, char* dest, int inputSize); +int LZ4_compress_limitedOutput_continue (void* LZ4_Data, const char* source, char* dest, int inputSize, int maxOutputSize); +char* LZ4_slideInputBuffer (void* LZ4_Data); +int LZ4_free (void* LZ4_Data); + +/* +These functions allow the compression of dependent blocks, where each block benefits from prior 64 KB within preceding blocks. +In order to achieve this, it is necessary to start creating the LZ4 Data Structure, thanks to the function : + +void* LZ4_create (const char* inputBuffer); +The result of the function is the (void*) pointer on the LZ4 Data Structure. +This pointer will be needed in all other functions. +If the pointer returned is NULL, then the allocation has failed, and compression must be aborted. +The only parameter 'const char* inputBuffer' must, obviously, point at the beginning of input buffer. +The input buffer must be already allocated, and size at least 192KB. +'inputBuffer' will also be the 'const char* source' of the first block. + +All blocks are expected to lay next to each other within the input buffer, starting from 'inputBuffer'. +To compress each block, use either LZ4_compress_continue() or LZ4_compress_limitedOutput_continue(). +Their behavior are identical to LZ4_compress() or LZ4_compress_limitedOutput(), +but require the LZ4 Data Structure as their first argument, and check that each block starts right after the previous one. +If next block does not begin immediately after the previous one, the compression will fail (return 0). + +When it's no longer possible to lay the next block after the previous one (not enough space left into input buffer), a call to : +char* LZ4_slideInputBuffer(void* LZ4_Data); +must be performed. It will typically copy the latest 64KB of input at the beginning of input buffer. +Note that, for this function to work properly, minimum size of an input buffer must be 192KB. +==> The memory position where the next input data block must start is provided as the result of the function. + +Compression can then resume, using LZ4_compress_continue() or LZ4_compress_limitedOutput_continue(), as usual. + +When compression is completed, a call to LZ4_free() will release the memory used by the LZ4 Data Structure. +*/ + + +int LZ4_decompress_safe_withPrefix64k (const char* source, char* dest, int inputSize, int maxOutputSize); +int LZ4_decompress_fast_withPrefix64k (const char* source, char* dest, int outputSize); + +/* +*_withPrefix64k() : + These decoding functions work the same as their "normal name" versions, + but can use up to 64KB of data in front of 'char* dest'. + These functions are necessary to decode inter-dependant blocks. +*/ + + +//**************************** +// Obsolete Functions +//**************************** + +static inline int LZ4_uncompress (const char* source, char* dest, int outputSize) { return LZ4_decompress_fast(source, dest, outputSize); } +static inline int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize) { return LZ4_decompress_safe(source, dest, isize, maxOutputSize); } + +/* +These functions are deprecated and should no longer be used. +They are provided here for compatibility with existing user programs. +*/ + + + +#if defined (__cplusplus) +} +#endif diff --git a/openvpn/src/openvpn/Makefile.am b/openvpn/src/openvpn/Makefile.am index 70e19c2c..0b79e104 100644 --- a/openvpn/src/openvpn/Makefile.am +++ b/openvpn/src/openvpn/Makefile.am @@ -27,6 +27,7 @@ AM_CFLAGS = \ $(OPTIONAL_CRYPTO_CFLAGS) \ $(OPTIONAL_LZO_CFLAGS) \ $(OPTIONAL_SNAPPY_CFLAGS) \ + $(OPTIONAL_LZ4_CFLAGS) \ $(OPTIONAL_PKCS11_HELPER_CFLAGS) if WIN32 # we want unicode entry point but not the macro @@ -43,6 +44,7 @@ openvpn_SOURCES = \ clinat.c clinat.h \ common.h \ comp.c comp.h compstub.c \ + comp-lz4.c comp-lz4.h \ crypto.c crypto.h crypto_backend.h \ crypto_openssl.c crypto_openssl.h \ crypto_polarssl.c crypto_polarssl.h \ @@ -120,6 +122,7 @@ openvpn_LDADD = \ $(SOCKETS_LIBS) \ $(OPTIONAL_LZO_LIBS) \ $(OPTIONAL_SNAPPY_LIBS) \ + $(OPTIONAL_LZ4_LIBS) \ $(OPTIONAL_PKCS11_HELPER_LIBS) \ $(OPTIONAL_CRYPTO_LIBS) \ $(OPTIONAL_SELINUX_LIBS) \ diff --git a/openvpn/src/openvpn/comp-lz4.c b/openvpn/src/openvpn/comp-lz4.c new file mode 100644 index 00000000..afa43b19 --- /dev/null +++ b/openvpn/src/openvpn/comp-lz4.c @@ -0,0 +1,195 @@ +/* + * OpenVPN -- An application to securely tunnel IP networks + * over a single UDP port, with support for SSL/TLS-based + * session authentication and key exchange, + * packet encryption, packet authentication, and + * packet compression. + * + * Copyright (C) 2002-2012 OpenVPN Technologies, Inc. <sales@openvpn.net> + * Copyright (C) 2013 Gert Doering <gert@greenie.muc.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program (see the file COPYING included with this + * distribution); if not, write to the Free Software Foundation, Inc., + * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifdef HAVE_CONFIG_H +#include "config.h" +#elif defined(_MSC_VER) +#include "config-msvc.h" +#endif + +#include "syshead.h" + +#if defined(ENABLE_LZ4) + +#if defined(NEED_COMPAT_LZ4) +#include "compat-lz4.h" +#else +#include "lz4.h" +#endif + +#include "comp.h" +#include "error.h" + +#include "memdbg.h" + +/* Initial command byte to tell our peer if we compressed */ +#define LZ4_COMPRESS_BYTE 0x69 + +static void +lz4_compress_init (struct compress_context *compctx) +{ + msg (D_INIT_MEDIUM, "LZ4 compression initializing"); + ASSERT(compctx->flags & COMP_F_SWAP); +} + +static void +lz4_compress_uninit (struct compress_context *compctx) +{ +} + +static void +lz4_compress (struct buffer *buf, struct buffer work, + struct compress_context *compctx, + const struct frame* frame) +{ + int result; + bool compressed = false; + + if (buf->len <= 0) + return; + + /* + * In order to attempt compression, length must be at least COMPRESS_THRESHOLD. + */ + if (buf->len >= COMPRESS_THRESHOLD) + { + const size_t ps = PAYLOAD_SIZE (frame); + int zlen_max = ps + COMP_EXTRA_BUFFER (ps); + int zlen; + + ASSERT (buf_init (&work, FRAME_HEADROOM (frame))); + ASSERT (buf_safe (&work, zlen_max)); + + if (buf->len > ps) + { + dmsg (D_COMP_ERRORS, "LZ4 compression buffer overflow"); + buf->len = 0; + return; + } + + zlen = LZ4_compress_limitedOutput((const char *)BPTR(buf), (char *)BPTR(&work), BLEN(buf), zlen_max ); + + if (zlen <= 0) + { + dmsg (D_COMP_ERRORS, "LZ4 compression error"); + buf->len = 0; + return; + } + + ASSERT (buf_safe (&work, zlen)); + work.len = zlen; + compressed = true; + + dmsg (D_COMP, "LZ4 compress %d -> %d", buf->len, work.len); + compctx->pre_compress += buf->len; + compctx->post_compress += work.len; + } + + /* did compression save us anything? */ + { + uint8_t comp_head_byte = NO_COMPRESS_BYTE_SWAP; + if (compressed && work.len < buf->len) + { + *buf = work; + comp_head_byte = LZ4_COMPRESS_BYTE; + } + + { + uint8_t *head = BPTR (buf); + uint8_t *tail = BEND (buf); + ASSERT (buf_safe (buf, 1)); + ++buf->len; + + /* move head byte of payload to tail */ + *tail = *head; + *head = comp_head_byte; + } + } +} + +static void +lz4_decompress (struct buffer *buf, struct buffer work, + struct compress_context *compctx, + const struct frame* frame) +{ + size_t zlen_max = EXPANDED_SIZE (frame); + int uncomp_len; + uint8_t c; /* flag indicating whether or not our peer compressed */ + + if (buf->len <= 0) + return; + + ASSERT (buf_init (&work, FRAME_HEADROOM (frame))); + + /* do unframing/swap (assumes buf->len > 0) */ + { + uint8_t *head = BPTR (buf); + c = *head; + --buf->len; + *head = *BEND (buf); + } + + if (c == LZ4_COMPRESS_BYTE) /* packet was compressed */ + { + ASSERT (buf_safe (&work, zlen_max)); + uncomp_len = LZ4_decompress_safe((const char *)BPTR(buf), (char *)BPTR(&work), (size_t)BLEN(buf), zlen_max); + if (uncomp_len <= 0) + { + dmsg (D_COMP_ERRORS, "LZ4 decompression error: %d", uncomp_len); + buf->len = 0; + return; + } + + ASSERT (buf_safe (&work, uncomp_len)); + work.len = uncomp_len; + + dmsg (D_COMP, "LZ4 decompress %d -> %d", buf->len, work.len); + compctx->pre_decompress += buf->len; + compctx->post_decompress += work.len; + + *buf = work; + } + else if (c == NO_COMPRESS_BYTE_SWAP) /* packet was not compressed */ + { + ; + } + else + { + dmsg (D_COMP_ERRORS, "Bad LZ4 decompression header byte: %d", c); + buf->len = 0; + } +} + +const struct compress_alg lz4_alg = { + "lz4", + lz4_compress_init, + lz4_compress_uninit, + lz4_compress, + lz4_decompress +}; + +#else +static void dummy(void) {} +#endif /* ENABLE_LZ4 */ diff --git a/openvpn/src/openvpn/comp-lz4.h b/openvpn/src/openvpn/comp-lz4.h new file mode 100644 index 00000000..ca1dfa9b --- /dev/null +++ b/openvpn/src/openvpn/comp-lz4.h @@ -0,0 +1,40 @@ +/* + * OpenVPN -- An application to securely tunnel IP networks + * over a single UDP port, with support for SSL/TLS-based + * session authentication and key exchange, + * packet encryption, packet authentication, and + * packet compression. + * + * Copyright (C) 2002-2012 OpenVPN Technologies, Inc. <sales@openvpn.net> + * Copyright (C) 2013 Gert Doering <gert@greenie.muc.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program (see the file COPYING included with this + * distribution); if not, write to the Free Software Foundation, Inc., + * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef OPENVPN_COMP_LZ4_H +#define OPENVPN_COMP_LZ4_H + +#if defined(ENABLE_LZ4) + +#include "buffer.h" + +extern const struct compress_alg lz4_alg; + +struct lz4_workspace +{ +}; + +#endif /* ENABLE_LZ4 */ +#endif diff --git a/openvpn/src/openvpn/comp.c b/openvpn/src/openvpn/comp.c index 96922571..4ac589f9 100644 --- a/openvpn/src/openvpn/comp.c +++ b/openvpn/src/openvpn/comp.c @@ -66,6 +66,14 @@ comp_init(const struct compress_options *opt) (*compctx->alg.compress_init)(compctx); break; #endif +#ifdef ENABLE_LZ4 + case COMP_ALG_LZ4: + ALLOC_OBJ_CLEAR (compctx, struct compress_context); + compctx->flags = opt->flags; + compctx->alg = lz4_alg; + (*compctx->alg.compress_init)(compctx); + break; +#endif } return compctx; } @@ -118,6 +126,9 @@ comp_generate_peer_info_string(const struct compress_options *opt, struct buffer bool lzo_avail = false; if (!(opt->flags & COMP_F_ADVERTISE_STUBS_ONLY)) { +#if defined(ENABLE_LZ4) + buf_printf (out, "IV_LZ4=1\n"); +#endif #if defined(ENABLE_SNAPPY) buf_printf (out, "IV_SNAPPY=1\n"); #endif diff --git a/openvpn/src/openvpn/comp.h b/openvpn/src/openvpn/comp.h index 0d2f1bc9..57764007 100644 --- a/openvpn/src/openvpn/comp.h +++ b/openvpn/src/openvpn/comp.h @@ -24,7 +24,7 @@ /* * Generic compression support. Currently we support - * Snappy and LZO 2. + * Snappy, LZO 2 and LX4. */ #ifndef OPENVPN_COMP_H #define OPENVPN_COMP_H @@ -41,6 +41,7 @@ #define COMP_ALG_STUB 1 /* support compression command byte and framing without actual compression */ #define COMP_ALG_LZO 2 /* LZO algorithm */ #define COMP_ALG_SNAPPY 3 /* Snappy algorithm */ +#define COMP_ALG_LZ4 4 /* LZ4 algorithm */ /* Compression flags */ #define COMP_F_ADAPTIVE (1<<0) /* COMP_ALG_LZO only */ @@ -64,6 +65,7 @@ * * LZO: len + len/8 + 128 + 3 * Snappy: len + len/6 + 32 + * LZ4: len + len/255 + 16 (LZ4_COMPRESSBOUND(len)) */ #define COMP_EXTRA_BUFFER(len) ((len)/6 + 128 + 3 + COMP_PREFIX_LEN) @@ -103,6 +105,10 @@ struct compress_alg #include "snappy.h" #endif +#ifdef ENABLE_LZ4 +#include "comp-lz4.h" +#endif + /* * Information that basically identifies a compression * algorithm and related flags. @@ -124,6 +130,9 @@ union compress_workspace_union #ifdef ENABLE_SNAPPY struct snappy_workspace snappy; #endif +#ifdef ENABLE_LZ4 + struct lz4_workspace lz4; +#endif }; /* diff --git a/openvpn/src/openvpn/init.c b/openvpn/src/openvpn/init.c index d5597362..169f0d3c 100644 --- a/openvpn/src/openvpn/init.c +++ b/openvpn/src/openvpn/init.c @@ -2381,7 +2381,7 @@ do_init_frame (struct context *c) { comp_add_to_extra_frame (&c->c2.frame); -#if !defined(ENABLE_SNAPPY) +#if !defined(ENABLE_SNAPPY) && !defined(ENABLE_LZ4) /* * Compression usage affects buffer alignment when non-swapped algs * such as LZO is used. @@ -2396,7 +2396,7 @@ do_init_frame (struct context *c) * dispatch if packet is uncompressed) at the cost of requiring * decryption output to be written to an unaligned buffer, so * it's more of a tradeoff than an optimal solution and we don't - * include it when we are doing a modern build with Snappy. + * include it when we are doing a modern build with Snappy or LZ4. * Strictly speaking, on the server it would be better to execute * this code for every connection after we decide the compression * method, but currently the frame code doesn't appear to be @@ -3346,7 +3346,7 @@ init_instance (struct context *c, const struct env_set *env, const unsigned int /* inherit environmental variables */ if (env) do_inherit_env (c, env); - + /* signals caught here will abort */ c->sig->signal_received = 0; c->sig->signal_text = NULL; diff --git a/openvpn/src/openvpn/options.c b/openvpn/src/openvpn/options.c index aa06c0a6..b93a67a0 100644 --- a/openvpn/src/openvpn/options.c +++ b/openvpn/src/openvpn/options.c @@ -92,6 +92,9 @@ const char title_string[] = #ifdef ENABLE_SNAPPY " [SNAPPY]" #endif +#ifdef ENABLE_LZ4 + " [LZ4]" +#endif #ifdef ENABLE_COMP_STUB " [COMP_STUB]" #endif @@ -6282,6 +6285,13 @@ add_option (struct options *options, options->comp.flags = COMP_F_SWAP; } #endif +#if defined(ENABLE_LZ4) + else if (streq (p[1], "lz4")) + { + options->comp.alg = COMP_ALG_LZ4; + options->comp.flags = COMP_F_SWAP; + } +#endif else { msg (msglevel, "bad comp option: %s", p[1]); diff --git a/openvpn/src/openvpn/syshead.h b/openvpn/src/openvpn/syshead.h index 51b24028..ab6fa01f 100644 --- a/openvpn/src/openvpn/syshead.h +++ b/openvpn/src/openvpn/syshead.h @@ -715,7 +715,8 @@ socket_defined (const socket_descriptor_t sd) /* * Compression support */ -#if defined(ENABLE_SNAPPY) || defined(ENABLE_LZO) || defined(ENABLE_COMP_STUB) +#if defined(ENABLE_SNAPPY) || defined(ENABLE_LZO) || defined(ENABLE_LZ4) || \ + defined(ENABLE_COMP_STUB) #define USE_COMP #endif diff --git a/openvpn/src/openvpn/tun.c b/openvpn/src/openvpn/tun.c index 9e3e8b9e..6460a369 100644 --- a/openvpn/src/openvpn/tun.c +++ b/openvpn/src/openvpn/tun.c @@ -1525,7 +1525,7 @@ open_tun (const char *dev, const char *dev_type, const char *dev_node, struct tu opentun = true; } else { opentun = management_android_control (management, "OPENTUN", dev); - /* Pick up the fd from management interface after calling the + /* Pick up the fd from management interface after calling the * OPENTUN command */ tt->fd = management->connection.lastfdreceived; management->connection.lastfdreceived=-1; |