Files
android_kernel_samsung_msm8…/lib/lz4/lz4_decompress.c
T
Kyungsik Lee e5bbc41c31 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 <kyungsik.lee@lge.com>
Signed-off-by: Yann Collet <yann.collet.73@gmail.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Florian Fainelli <florian@openwrt.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

lib: add support for LZ4-compressed kernel

Add support for extracting LZ4-compressed kernel images, as well as
LZ4-compressed ramdisk images in the kernel boot process.

Signed-off-by: Kyungsik Lee <kyungsik.lee@lge.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Florian Fainelli <florian@openwrt.org>
Cc: Yann Collet <yann.collet.73@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

lib: add lz4 compressor module

This patchset is for supporting LZ4 compression and the crypto API using
it.

As shown below, the size of data is a little bit bigger but compressing
speed is faster under the enabled unaligned memory access.  We can use
lz4 de/compression through crypto API as well.  Also, It will be useful
for another potential user of lz4 compression.

lz4 Compression Benchmark:
Compiler: ARM gcc 4.6.4
ARMv7, 1 GHz based board
   Kernel: linux 3.4
   Uncompressed data Size: 101 MB
         Compressed Size  compression Speed
   LZO   72.1MB		  32.1MB/s, 33.0MB/s(UA)
   LZ4   75.1MB		  30.4MB/s, 35.9MB/s(UA)
   LZ4HC 59.8MB		   2.4MB/s,  2.5MB/s(UA)
- UA: Unaligned memory Access support
- Latest patch set for LZO applied

This patch:

Add support for LZ4 compression in the Linux Kernel.  LZ4 Compression APIs
for kernel are based on LZ4 implementation by Yann Collet and were changed
for kernel coding style.

LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
LZ4 source repository : http://code.google.com/p/lz4/
svn revision : r90

Two APIs are added:

lz4_compress() support basic lz4 compression whereas lz4hc_compress()
support high compression or CPU performance get lower but compression
ratio get higher.  Also, we require the pre-allocated working memory with
the defined size and destination buffer must be allocated with the size of
lz4_compressbound.

[akpm@linux-foundation.org: make lz4_compresshcctx() static]
Signed-off-by: Chanho Min <chanho.min@lge.com>
Cc: "Darrick J. Wong" <djwong@us.ibm.com>
Cc: Bob Pearson <rpearson@systemfabricworks.com>
Cc: Richard Weinberger <richard@nod.at>
Cc: Herbert Xu <herbert@gondor.hengli.com.au>
Cc: Yann Collet <yann.collet.73@gmail.com>
Cc: Kyungsik Lee <kyungsik.lee@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

lib/lz4: correct the LZ4 license

The LZ4 code is listed as using the "BSD 2-Clause License".

Signed-off-by: Richard Laager <rlaager@wiktel.com>
Acked-by: Kyungsik Lee <kyungsik.lee@lge.com>
Cc: Chanho Min <chanho.min@lge.com>
Cc: Richard Yao <ryao@gentoo.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
[ The 2-clause BSD can be just converted into GPL, but that's rude and
  pointless, so don't do it   - Linus ]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

lz4: fix compression/decompression signedness mismatch

LZ4 compression and decompression functions require different in
signedness input/output parameters: unsigned char for compression and
signed char for decompression.

Change decompression API to require "(const) unsigned char *".

Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Kyungsik Lee <kyungsik.lee@lge.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Yann Collet <yann.collet.73@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

lz4: ensure length does not wrap

Given some pathologically compressed data, lz4 could possibly decide to
wrap a few internal variables, causing unknown things to happen.  Catch
this before the wrapping happens and abort the decompression.

Reported-by: "Don A. Bailey" <donb@securitymouse.com>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

lz4: fix another possible overrun

There is one other possible overrun in the lz4 code as implemented by
Linux at this point in time (which differs from the upstream lz4
codebase, but will get synced at in a future kernel release.)  As
pointed out by Don, we also need to check the overflow in the data
itself.

While we are at it, replace the odd error return value with just a
"simple" -1 value as the return value is never used for anything other
than a basic "did this work or not" check.

Reported-by: "Don A. Bailey" <donb@securitymouse.com>
Reported-by: Willy Tarreau <w@1wt.eu>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

lz4: add overrun checks to lz4_uncompress_unknownoutputsize()

Jan points out that I forgot to make the needed fixes to the
lz4_uncompress_unknownoutputsize() function to mirror the changes done
in lz4_decompress() with regards to potential pointer overflows.

The only in-kernel user of this function is the zram code, which only
takes data from a valid compressed buffer that it made itself, so it's
not a big issue.  But due to external kernel modules using this
function, it's better to be safe here.

Reported-by: Jan Beulich <JBeulich@suse.com>
Cc: "Don A. Bailey" <donb@securitymouse.com>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

LZ4 : fix the data abort issue

If the part of the compression data are corrupted, or the compression
data is totally fake, the memory access over the limit is possible.

This is the log from my system usning lz4 decompression.
   [6502]data abort, halting
   [6503]r0  0x00000000 r1  0x00000000 r2  0xdcea0ffc r3  0xdcea0ffc
   [6509]r4  0xb9ab0bfd r5  0xdcea0ffc r6  0xdcea0ff8 r7  0xdce80000
   [6515]r8  0x00000000 r9  0x00000000 r10 0x00000000 r11 0xb9a98000
   [6522]r12 0xdcea1000 usp 0x00000000 ulr 0x00000000 pc  0x820149bc
   [6528]spsr 0x400001f3
and the memory addresses of some variables at the moment are
    ref:0xdcea0ffc, op:0xdcea0ffc, oend:0xdcea1000

As you can see, COPYLENGH is 8bytes, so @ref and @op can access the momory
over @oend.

Change-Id: I9919c9bcfca9ae9e26d83fa49afff99e74295d3b
Signed-off-by: JeHyeon Yeon <tom.yeon@windriver.com>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Kevin F. Haggerty <haggertk@lineageos.org>
2019-08-05 14:22:45 +02:00

338 lines
7.9 KiB
C

/*
* LZ4 Decompressor for Linux kernel
*
* Copyright (C) 2013, LG Electronics, Kyungsik Lee <kyungsik.lee@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++;
if (unlikely(length > (size_t)(length + len)))
goto _output_error;
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++;
if (unlikely(length > (size_t)(length + *ip)))
goto _output_error;
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;
if ((ref + COPYLENGTH) > oend ||
(op + COPYLENGTH) > 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 -1;
}
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++;
if (unlikely(length > (size_t)(length + s)))
goto _output_error;
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++;
if (unlikely(length > (size_t)(length + s)))
goto _output_error;
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 -1;
}
int lz4_decompress(const unsigned char *src, size_t *src_len,
unsigned 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(lz4_decompress);
#endif
int lz4_decompress_unknownoutputsize(const unsigned char *src, size_t src_len,
unsigned 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(lz4_decompress_unknownoutputsize);
MODULE_LICENSE("Dual BSD/GPL");
MODULE_DESCRIPTION("LZ4 Decompressor");
#endif