4e1a33b105
Patch series "Update LZ4 compressor module", v7. This patchset updates the LZ4 compression module to a version based on LZ4 v1.7.3 allowing to use the fast compression algorithm aka LZ4 fast which provides an "acceleration" parameter as a tradeoff between high compression ratio and high compression speed. We want to use LZ4 fast in order to support compression in lustre and (mostly, based on that) investigate data reduction techniques in behalf of storage systems. Also, it will be useful for other users of LZ4 compression, as with LZ4 fast it is possible to enable applications to use fast and/or high compression depending on the usecase. For instance, ZRAM is offering a LZ4 backend and could benefit from an updated LZ4 in the kernel. LZ4 homepage: http://www.lz4.org/ LZ4 source repository: https://github.com/lz4/lz4 Source version: 1.7.3 Benchmark (taken from [1], Core i5-4300U @1.9GHz): ----------------|--------------|----------------|---------- Compressor | Compression | Decompression | Ratio ----------------|--------------|----------------|---------- memcpy | 4200 MB/s | 4200 MB/s | 1.000 LZ4 fast 50 | 1080 MB/s | 2650 MB/s | 1.375 LZ4 fast 17 | 680 MB/s | 2220 MB/s | 1.607 LZ4 fast 5 | 475 MB/s | 1920 MB/s | 1.886 LZ4 default | 385 MB/s | 1850 MB/s | 2.101 [1] http://fastcompression.blogspot.de/2015/04/sampling-or-faster-lz4.html [PATCH 1/5] lib: Update LZ4 compressor module [PATCH 2/5] lib/decompress_unlz4: Change module to work with new LZ4 module version [PATCH 3/5] crypto: Change LZ4 modules to work with new LZ4 module version [PATCH 4/5] fs/pstore: fs/squashfs: Change usage of LZ4 to work with new LZ4 version [PATCH 5/5] lib/lz4: Remove back-compat wrappers This patch (of 5): Update the LZ4 kernel module to LZ4 v1.7.3 by Yann Collet. The kernel module is inspired by the previous work by Chanho Min. The updated LZ4 module will not break existing code since the patchset contains appropriate changes. API changes: New method LZ4_compress_fast which differs from the variant available in kernel by the new acceleration parameter, allowing to trade compression ratio for more compression speed and vice versa. LZ4_decompress_fast is the respective decompression method, featuring a very fast decoder (multiple GB/s per core), able to reach RAM speed in multi-core systems. The decompressor allows to decompress data compressed with LZ4 fast as well as the LZ4 HC (high compression) algorithm. Also the useful functions LZ4_decompress_safe_partial and LZ4_compress_destsize were added. The latter reverses the logic by trying to compress as much data as possible from source to dest while the former aims to decompress partial blocks of data. A bunch of streaming functions were also added which allow compressig/decompressing data in multiple steps (so called "streaming mode"). The methods lz4_compress and lz4_decompress_unknownoutputsize are now known as LZ4_compress_default respectivley LZ4_decompress_safe. The old methods will be removed since there's no callers left in the code. [arnd@arndb.de: fix KERNEL_LZ4 support] Link: http://lkml.kernel.org/r/20170208211946.2839649-1-arnd@arndb.de [akpm@linux-foundation.org: simplify] [akpm@linux-foundation.org: fix the simplification] [4sschmid@informatik.uni-hamburg.de: fix performance regressions] Link: http://lkml.kernel.org/r/1486898178-17125-2-git-send-email-4sschmid@informatik.uni-hamburg.de [4sschmid@informatik.uni-hamburg.de: v8] Link: http://lkml.kernel.org/r/1487182598-15351-2-git-send-email-4sschmid@informatik.uni-hamburg.de Link: http://lkml.kernel.org/r/1486321748-19085-2-git-send-email-4sschmid@informatik.uni-hamburg.de Signed-off-by: Sven Schmidt <4sschmid@informatik.uni-hamburg.de> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Bongkyu Kim <bongkyu.kim@lge.com> Cc: Rui Salvaterra <rsalvaterra@gmail.com> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: David S. Miller <davem@davemloft.net> Cc: Anton Vorontsov <anton@enomsg.org> Cc: Colin Cross <ccross@android.com> Cc: Kees Cook <keescook@chromium.org> Cc: Tony Luck <tony.luck@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
227 lines
5.8 KiB
C
227 lines
5.8 KiB
C
#ifndef __LZ4DEFS_H__
|
|
#define __LZ4DEFS_H__
|
|
|
|
/*
|
|
* lz4defs.h -- common and architecture specific defines for the kernel usage
|
|
|
|
* LZ4 - Fast LZ compression algorithm
|
|
* Copyright (C) 2011-2016, 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
|
|
*
|
|
* Changed for kernel usage by:
|
|
* Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
|
|
*/
|
|
|
|
#include <asm/unaligned.h>
|
|
#include <linux/string.h> /* memset, memcpy */
|
|
|
|
#define FORCE_INLINE __always_inline
|
|
|
|
/*-************************************
|
|
* Basic Types
|
|
**************************************/
|
|
#include <linux/types.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;
|
|
|
|
/*-************************************
|
|
* Architecture specifics
|
|
**************************************/
|
|
#if defined(CONFIG_64BIT)
|
|
#define LZ4_ARCH64 1
|
|
#else
|
|
#define LZ4_ARCH64 0
|
|
#endif
|
|
|
|
#if defined(__LITTLE_ENDIAN)
|
|
#define LZ4_LITTLE_ENDIAN 1
|
|
#else
|
|
#define LZ4_LITTLE_ENDIAN 0
|
|
#endif
|
|
|
|
/*-************************************
|
|
* Constants
|
|
**************************************/
|
|
#define MINMATCH 4
|
|
|
|
#define WILDCOPYLENGTH 8
|
|
#define LASTLITERALS 5
|
|
#define MFLIMIT (WILDCOPYLENGTH + MINMATCH)
|
|
|
|
/* Increase this value ==> compression run slower on incompressible data */
|
|
#define LZ4_SKIPTRIGGER 6
|
|
|
|
#define HASH_UNIT sizeof(size_t)
|
|
|
|
#define KB (1 << 10)
|
|
#define MB (1 << 20)
|
|
#define GB (1U << 30)
|
|
|
|
#define MAXD_LOG 16
|
|
#define MAX_DISTANCE ((1 << MAXD_LOG) - 1)
|
|
#define STEPSIZE sizeof(size_t)
|
|
|
|
#define ML_BITS 4
|
|
#define ML_MASK ((1U << ML_BITS) - 1)
|
|
#define RUN_BITS (8 - ML_BITS)
|
|
#define RUN_MASK ((1U << RUN_BITS) - 1)
|
|
|
|
/*-************************************
|
|
* Reading and writing into memory
|
|
**************************************/
|
|
static FORCE_INLINE U16 LZ4_read16(const void *ptr)
|
|
{
|
|
return get_unaligned((const U16 *)ptr);
|
|
}
|
|
|
|
static FORCE_INLINE U32 LZ4_read32(const void *ptr)
|
|
{
|
|
return get_unaligned((const U32 *)ptr);
|
|
}
|
|
|
|
static FORCE_INLINE size_t LZ4_read_ARCH(const void *ptr)
|
|
{
|
|
return get_unaligned((const size_t *)ptr);
|
|
}
|
|
|
|
static FORCE_INLINE void LZ4_write16(void *memPtr, U16 value)
|
|
{
|
|
put_unaligned(value, (U16 *)memPtr);
|
|
}
|
|
|
|
static FORCE_INLINE void LZ4_write32(void *memPtr, U32 value)
|
|
{
|
|
put_unaligned(value, (U32 *)memPtr);
|
|
}
|
|
|
|
static FORCE_INLINE U16 LZ4_readLE16(const void *memPtr)
|
|
{
|
|
return get_unaligned_le16(memPtr);
|
|
}
|
|
|
|
static FORCE_INLINE void LZ4_writeLE16(void *memPtr, U16 value)
|
|
{
|
|
return put_unaligned_le16(value, memPtr);
|
|
}
|
|
|
|
static FORCE_INLINE void LZ4_copy8(void *dst, const void *src)
|
|
{
|
|
#if LZ4_ARCH64
|
|
U64 a = get_unaligned((const U64 *)src);
|
|
|
|
put_unaligned(a, (U64 *)dst);
|
|
#else
|
|
U32 a = get_unaligned((const U32 *)src);
|
|
U32 b = get_unaligned((const U32 *)src + 1);
|
|
|
|
put_unaligned(a, (U32 *)dst);
|
|
put_unaligned(b, (U32 *)dst + 1);
|
|
#endif
|
|
}
|
|
|
|
/*
|
|
* customized variant of memcpy,
|
|
* which can overwrite up to 7 bytes beyond dstEnd
|
|
*/
|
|
static FORCE_INLINE void LZ4_wildCopy(void *dstPtr,
|
|
const void *srcPtr, void *dstEnd)
|
|
{
|
|
BYTE *d = (BYTE *)dstPtr;
|
|
const BYTE *s = (const BYTE *)srcPtr;
|
|
BYTE *const e = (BYTE *)dstEnd;
|
|
|
|
do {
|
|
LZ4_copy8(d, s);
|
|
d += 8;
|
|
s += 8;
|
|
} while (d < e);
|
|
}
|
|
|
|
static FORCE_INLINE unsigned int LZ4_NbCommonBytes(register size_t val)
|
|
{
|
|
#if LZ4_LITTLE_ENDIAN
|
|
return __ffs(val) >> 3;
|
|
#else
|
|
return (BITS_PER_LONG - 1 - __fls(val)) >> 3;
|
|
#endif
|
|
}
|
|
|
|
static FORCE_INLINE unsigned int LZ4_count(
|
|
const BYTE *pIn,
|
|
const BYTE *pMatch,
|
|
const BYTE *pInLimit)
|
|
{
|
|
const BYTE *const pStart = pIn;
|
|
|
|
while (likely(pIn < pInLimit - (STEPSIZE - 1))) {
|
|
size_t const diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn);
|
|
|
|
if (!diff) {
|
|
pIn += STEPSIZE;
|
|
pMatch += STEPSIZE;
|
|
continue;
|
|
}
|
|
|
|
pIn += LZ4_NbCommonBytes(diff);
|
|
|
|
return (unsigned int)(pIn - pStart);
|
|
}
|
|
|
|
#if LZ4_ARCH64
|
|
if ((pIn < (pInLimit - 3))
|
|
&& (LZ4_read32(pMatch) == LZ4_read32(pIn))) {
|
|
pIn += 4;
|
|
pMatch += 4;
|
|
}
|
|
#endif
|
|
|
|
if ((pIn < (pInLimit - 1))
|
|
&& (LZ4_read16(pMatch) == LZ4_read16(pIn))) {
|
|
pIn += 2;
|
|
pMatch += 2;
|
|
}
|
|
|
|
if ((pIn < pInLimit) && (*pMatch == *pIn))
|
|
pIn++;
|
|
|
|
return (unsigned int)(pIn - pStart);
|
|
}
|
|
|
|
typedef enum { noLimit = 0, limitedOutput = 1 } limitedOutput_directive;
|
|
typedef enum { byPtr, byU32, byU16 } tableType_t;
|
|
|
|
typedef enum { noDict = 0, withPrefix64k, usingExtDict } dict_directive;
|
|
typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive;
|
|
|
|
typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive;
|
|
typedef enum { full = 0, partial = 1 } earlyEnd_directive;
|
|
|
|
#endif
|