forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
decompressor: add LZ4 decompressor module
Add support for LZ4 decompression in the Linux Kernel. LZ4 Decompression APIs for kernel are based on LZ4 implementation by Yann Collet. Benchmark Results(PATCH v3) Compiler: Linaro ARM gcc 4.6.2 1. ARMv7, 1.5GHz based board Kernel: linux 3.4 Uncompressed Kernel Size: 14MB Compressed Size Decompression Speed LZO 6.7MB 20.1MB/s, 25.2MB/s(UA) LZ4 7.3MB 29.1MB/s, 45.6MB/s(UA) 2. ARMv7, 1.7GHz based board Kernel: linux 3.7 Uncompressed Kernel Size: 14MB Compressed Size Decompression Speed LZO 6.0MB 34.1MB/s, 52.2MB/s(UA) LZ4 6.5MB 86.7MB/s - UA: Unaligned memory Access support - Latest patch set for LZO applied This patch set is for adding support for LZ4-compressed Kernel. LZ4 is a very fast lossless compression algorithm and it also features an extremely fast decoder [1]. But we have five of decompressors already and one question which does arise, however, is that of where do we stop adding new ones? This issue had been discussed and came to the conclusion [2]. Russell King said that we should have: - one decompressor which is the fastest - one decompressor for the highest compression ratio - one popular decompressor (eg conventional gzip) If we have a replacement one for one of these, then it should do exactly that: replace it. The benchmark shows that an 8% increase in image size vs a 66% increase in decompression speed compared to LZO(which has been known as the fastest decompressor in the Kernel). Therefore the "fast but may not be small" compression title has clearly been taken by LZ4 [3]. [1] http://code.google.com/p/lz4/ [2] http://thread.gmane.org/gmane.linux.kbuild.devel/9157 [3] http://thread.gmane.org/gmane.linux.kbuild.devel/9347 LZ4 homepage: http://fastcompression.blogspot.com/p/lz4.html LZ4 source repository: http://code.google.com/p/lz4/ Signed-off-by: Kyungsik Lee <[email protected]> Signed-off-by: Yann Collet <[email protected]> Cc: "H. Peter Anvin" <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Thomas Gleixner <[email protected]> Cc: Russell King <[email protected]> Cc: Borislav Petkov <[email protected]> Cc: Florian Fainelli <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
- Loading branch information
Showing
3 changed files
with
471 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,51 @@ | ||
#ifndef __LZ4_H__ | ||
#define __LZ4_H__ | ||
/* | ||
* LZ4 Kernel Interface | ||
* | ||
* Copyright (C) 2013, LG Electronics, Kyungsik Lee <[email protected]> | ||
* | ||
* 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. | ||
*/ | ||
|
||
/* | ||
* lz4_compressbound() | ||
* Provides the maximum size that LZ4 may output in a "worst case" scenario | ||
* (input data not compressible) | ||
*/ | ||
static inline size_t lz4_compressbound(size_t isize) | ||
{ | ||
return isize + (isize / 255) + 16; | ||
} | ||
|
||
/* | ||
* lz4_decompress() | ||
* src : source address of the compressed data | ||
* src_len : is the input size, whcih is returned after decompress done | ||
* dest : output buffer address of the decompressed data | ||
* actual_dest_len: is the size of uncompressed data, supposing it's known | ||
* return : Success if return 0 | ||
* Error if return (< 0) | ||
* note : Destination buffer must be already allocated. | ||
* slightly faster than lz4_decompress_unknownoutputsize() | ||
*/ | ||
int lz4_decompress(const char *src, size_t *src_len, char *dest, | ||
size_t actual_dest_len); | ||
|
||
/* | ||
* lz4_decompress_unknownoutputsize() | ||
* src : source address of the compressed data | ||
* src_len : is the input size, therefore the compressed size | ||
* dest : output buffer address of the decompressed data | ||
* dest_len: is the max size of the destination buffer, which is | ||
* returned with actual size of decompressed data after | ||
* decompress done | ||
* return : Success if return 0 | ||
* Error if return (< 0) | ||
* note : Destination buffer must be already allocated. | ||
*/ | ||
int lz4_decompress_unknownoutputsize(const char *src, size_t src_len, | ||
char *dest, size_t *dest_len); | ||
#endif |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,326 @@ | ||
/* | ||
* LZ4 Decompressor for Linux kernel | ||
* | ||
* Copyright (C) 2013 LG Electronics Co., Ltd. (http://www.lge.com/) | ||
* | ||
* Based on LZ4 implementation by Yann Collet. | ||
* | ||
* LZ4 - Fast LZ compression algorithm | ||
* Copyright (C) 2011-2012, 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/ | ||
*/ | ||
|
||
#ifndef STATIC | ||
#include <linux/module.h> | ||
#include <linux/kernel.h> | ||
#endif | ||
#include <linux/lz4.h> | ||
|
||
#include <asm/unaligned.h> | ||
|
||
#include "lz4defs.h" | ||
|
||
static int lz4_uncompress(const char *source, char *dest, int osize) | ||
{ | ||
const BYTE *ip = (const BYTE *) source; | ||
const BYTE *ref; | ||
BYTE *op = (BYTE *) dest; | ||
BYTE * const oend = op + osize; | ||
BYTE *cpy; | ||
unsigned token; | ||
size_t length; | ||
size_t dec32table[] = {0, 3, 2, 3, 0, 0, 0, 0}; | ||
#if LZ4_ARCH64 | ||
size_t dec64table[] = {0, 0, 0, -1, 0, 1, 2, 3}; | ||
#endif | ||
|
||
while (1) { | ||
|
||
/* get runlength */ | ||
token = *ip++; | ||
length = (token >> ML_BITS); | ||
if (length == RUN_MASK) { | ||
size_t len; | ||
|
||
len = *ip++; | ||
for (; len == 255; length += 255) | ||
len = *ip++; | ||
length += len; | ||
} | ||
|
||
/* copy literals */ | ||
cpy = op + length; | ||
if (unlikely(cpy > oend - COPYLENGTH)) { | ||
/* | ||
* Error: not enough place for another match | ||
* (min 4) + 5 literals | ||
*/ | ||
if (cpy != oend) | ||
goto _output_error; | ||
|
||
memcpy(op, ip, length); | ||
ip += length; | ||
break; /* EOF */ | ||
} | ||
LZ4_WILDCOPY(ip, op, cpy); | ||
ip -= (op - cpy); | ||
op = cpy; | ||
|
||
/* get offset */ | ||
LZ4_READ_LITTLEENDIAN_16(ref, cpy, ip); | ||
ip += 2; | ||
|
||
/* Error: offset create reference outside destination buffer */ | ||
if (unlikely(ref < (BYTE *const) dest)) | ||
goto _output_error; | ||
|
||
/* get matchlength */ | ||
length = token & ML_MASK; | ||
if (length == ML_MASK) { | ||
for (; *ip == 255; length += 255) | ||
ip++; | ||
length += *ip++; | ||
} | ||
|
||
/* copy repeated sequence */ | ||
if (unlikely((op - ref) < STEPSIZE)) { | ||
#if LZ4_ARCH64 | ||
size_t dec64 = dec64table[op - ref]; | ||
#else | ||
const int dec64 = 0; | ||
#endif | ||
op[0] = ref[0]; | ||
op[1] = ref[1]; | ||
op[2] = ref[2]; | ||
op[3] = ref[3]; | ||
op += 4; | ||
ref += 4; | ||
ref -= dec32table[op-ref]; | ||
PUT4(ref, op); | ||
op += STEPSIZE - 4; | ||
ref -= dec64; | ||
} else { | ||
LZ4_COPYSTEP(ref, op); | ||
} | ||
cpy = op + length - (STEPSIZE - 4); | ||
if (cpy > (oend - COPYLENGTH)) { | ||
|
||
/* Error: request to write beyond destination buffer */ | ||
if (cpy > oend) | ||
goto _output_error; | ||
LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH)); | ||
while (op < cpy) | ||
*op++ = *ref++; | ||
op = cpy; | ||
/* | ||
* Check EOF (should never happen, since last 5 bytes | ||
* are supposed to be literals) | ||
*/ | ||
if (op == oend) | ||
goto _output_error; | ||
continue; | ||
} | ||
LZ4_SECURECOPY(ref, op, cpy); | ||
op = cpy; /* correction */ | ||
} | ||
/* end of decoding */ | ||
return (int) (((char *)ip) - source); | ||
|
||
/* write overflow error detected */ | ||
_output_error: | ||
return (int) (-(((char *)ip) - source)); | ||
} | ||
|
||
static int lz4_uncompress_unknownoutputsize(const char *source, char *dest, | ||
int isize, size_t maxoutputsize) | ||
{ | ||
const BYTE *ip = (const BYTE *) source; | ||
const BYTE *const iend = ip + isize; | ||
const BYTE *ref; | ||
|
||
|
||
BYTE *op = (BYTE *) dest; | ||
BYTE * const oend = op + maxoutputsize; | ||
BYTE *cpy; | ||
|
||
size_t dec32table[] = {0, 3, 2, 3, 0, 0, 0, 0}; | ||
#if LZ4_ARCH64 | ||
size_t dec64table[] = {0, 0, 0, -1, 0, 1, 2, 3}; | ||
#endif | ||
|
||
/* Main Loop */ | ||
while (ip < iend) { | ||
|
||
unsigned token; | ||
size_t length; | ||
|
||
/* get runlength */ | ||
token = *ip++; | ||
length = (token >> ML_BITS); | ||
if (length == RUN_MASK) { | ||
int s = 255; | ||
while ((ip < iend) && (s == 255)) { | ||
s = *ip++; | ||
length += s; | ||
} | ||
} | ||
/* copy literals */ | ||
cpy = op + length; | ||
if ((cpy > oend - COPYLENGTH) || | ||
(ip + length > iend - COPYLENGTH)) { | ||
|
||
if (cpy > oend) | ||
goto _output_error;/* writes beyond buffer */ | ||
|
||
if (ip + length != iend) | ||
goto _output_error;/* | ||
* Error: LZ4 format requires | ||
* to consume all input | ||
* at this stage | ||
*/ | ||
memcpy(op, ip, length); | ||
op += length; | ||
break;/* Necessarily EOF, due to parsing restrictions */ | ||
} | ||
LZ4_WILDCOPY(ip, op, cpy); | ||
ip -= (op - cpy); | ||
op = cpy; | ||
|
||
/* get offset */ | ||
LZ4_READ_LITTLEENDIAN_16(ref, cpy, ip); | ||
ip += 2; | ||
if (ref < (BYTE * const) dest) | ||
goto _output_error; | ||
/* | ||
* Error : offset creates reference | ||
* outside of destination buffer | ||
*/ | ||
|
||
/* get matchlength */ | ||
length = (token & ML_MASK); | ||
if (length == ML_MASK) { | ||
while (ip < iend) { | ||
int s = *ip++; | ||
length += s; | ||
if (s == 255) | ||
continue; | ||
break; | ||
} | ||
} | ||
|
||
/* copy repeated sequence */ | ||
if (unlikely((op - ref) < STEPSIZE)) { | ||
#if LZ4_ARCH64 | ||
size_t dec64 = dec64table[op - ref]; | ||
#else | ||
const int dec64 = 0; | ||
#endif | ||
op[0] = ref[0]; | ||
op[1] = ref[1]; | ||
op[2] = ref[2]; | ||
op[3] = ref[3]; | ||
op += 4; | ||
ref += 4; | ||
ref -= dec32table[op - ref]; | ||
PUT4(ref, op); | ||
op += STEPSIZE - 4; | ||
ref -= dec64; | ||
} else { | ||
LZ4_COPYSTEP(ref, op); | ||
} | ||
cpy = op + length - (STEPSIZE-4); | ||
if (cpy > oend - COPYLENGTH) { | ||
if (cpy > oend) | ||
goto _output_error; /* write outside of buf */ | ||
|
||
LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH)); | ||
while (op < cpy) | ||
*op++ = *ref++; | ||
op = cpy; | ||
/* | ||
* Check EOF (should never happen, since last 5 bytes | ||
* are supposed to be literals) | ||
*/ | ||
if (op == oend) | ||
goto _output_error; | ||
continue; | ||
} | ||
LZ4_SECURECOPY(ref, op, cpy); | ||
op = cpy; /* correction */ | ||
} | ||
/* end of decoding */ | ||
return (int) (((char *) op) - dest); | ||
|
||
/* write overflow error detected */ | ||
_output_error: | ||
return (int) (-(((char *) ip) - source)); | ||
} | ||
|
||
int lz4_decompress(const char *src, size_t *src_len, char *dest, | ||
size_t actual_dest_len) | ||
{ | ||
int ret = -1; | ||
int input_len = 0; | ||
|
||
input_len = lz4_uncompress(src, dest, actual_dest_len); | ||
if (input_len < 0) | ||
goto exit_0; | ||
*src_len = input_len; | ||
|
||
return 0; | ||
exit_0: | ||
return ret; | ||
} | ||
#ifndef STATIC | ||
EXPORT_SYMBOL_GPL(lz4_decompress); | ||
#endif | ||
|
||
int lz4_decompress_unknownoutputsize(const char *src, size_t src_len, | ||
char *dest, size_t *dest_len) | ||
{ | ||
int ret = -1; | ||
int out_len = 0; | ||
|
||
out_len = lz4_uncompress_unknownoutputsize(src, dest, src_len, | ||
*dest_len); | ||
if (out_len < 0) | ||
goto exit_0; | ||
*dest_len = out_len; | ||
|
||
return 0; | ||
exit_0: | ||
return ret; | ||
} | ||
#ifndef STATIC | ||
EXPORT_SYMBOL_GPL(lz4_decompress_unknownoutputsize); | ||
|
||
MODULE_LICENSE("GPL"); | ||
MODULE_DESCRIPTION("LZ4 Decompressor"); | ||
#endif |
Oops, something went wrong.