kernel_optimize_test/lib/lzo/lzo1x_decompress.c
Albin Tonnerre 7dd65feb6c lib: add support for LZO-compressed kernels
This patch series adds generic support for creating and extracting
LZO-compressed kernel images, as well as support for using such images on
the x86 and ARM architectures, and support for creating and using
LZO-compressed initrd and initramfs images.

Russell King said:

: Testing on a Cortex A9 model:
: - lzo decompressor is 65% of the time gzip takes to decompress a kernel
: - lzo kernel is 9% larger than a gzip kernel
:
: which I'm happy to say confirms your figures when comparing the two.
:
: However, when comparing your new gzip code to the old gzip code:
: - new is 99% of the size of the old code
: - new takes 42% of the time to decompress than the old code
:
: What this means is that for a proper comparison, the results get even better:
: - lzo is 7.5% larger than the old gzip'd kernel image
: - lzo takes 28% of the time that the old gzip code took
:
: So the expense seems definitely worth the effort.  The only reason I
: can think of ever using gzip would be if you needed the additional
: compression (eg, because you have limited flash to store the image.)
:
: I would argue that the default for ARM should therefore be LZO.

This patch:

The lzo compressor is worse than gzip at compression, but faster at
extraction.  Here are some figures for an ARM board I'm working on:

Uncompressed size: 3.24Mo
gzip  1.61Mo 0.72s
lzo   1.75Mo 0.48s

So for a compression ratio that is still relatively close to gzip, it's
much faster to extract, at least in that case.

This part contains:
 - Makefile routine to support lzo compression
 - Fixes to the existing lzo compressor so that it can be used in
   compressed kernels
 - wrapper around the existing lzo1x_decompress, as it only extracts one
   block at a time, while we need to extract a whole file here
 - config dialog for kernel compression

[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: cleanup]
Signed-off-by: Albin Tonnerre <albin.tonnerre@free-electrons.com>
Tested-by: Wu Zhangjin <wuzhangjin@gmail.com>
Acked-by: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Russell King <rmk@arm.linux.org.uk>
Acked-by: Russell King <rmk@arm.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-01-11 09:34:04 -08:00

256 lines
4.9 KiB
C

/*
* LZO1X Decompressor from MiniLZO
*
* Copyright (C) 1996-2005 Markus F.X.J. Oberhumer <markus@oberhumer.com>
*
* The full LZO package can be found at:
* http://www.oberhumer.com/opensource/lzo/
*
* Changed for kernel use by:
* Nitin Gupta <nitingupta910@gmail.com>
* Richard Purdie <rpurdie@openedhand.com>
*/
#ifndef STATIC
#include <linux/module.h>
#include <linux/kernel.h>
#endif
#include <asm/unaligned.h>
#include <linux/lzo.h>
#include "lzodefs.h"
#define HAVE_IP(x, ip_end, ip) ((size_t)(ip_end - ip) < (x))
#define HAVE_OP(x, op_end, op) ((size_t)(op_end - op) < (x))
#define HAVE_LB(m_pos, out, op) (m_pos < out || m_pos >= op)
#define COPY4(dst, src) \
put_unaligned(get_unaligned((const u32 *)(src)), (u32 *)(dst))
int lzo1x_decompress_safe(const unsigned char *in, size_t in_len,
unsigned char *out, size_t *out_len)
{
const unsigned char * const ip_end = in + in_len;
unsigned char * const op_end = out + *out_len;
const unsigned char *ip = in, *m_pos;
unsigned char *op = out;
size_t t;
*out_len = 0;
if (*ip > 17) {
t = *ip++ - 17;
if (t < 4)
goto match_next;
if (HAVE_OP(t, op_end, op))
goto output_overrun;
if (HAVE_IP(t + 1, ip_end, ip))
goto input_overrun;
do {
*op++ = *ip++;
} while (--t > 0);
goto first_literal_run;
}
while ((ip < ip_end)) {
t = *ip++;
if (t >= 16)
goto match;
if (t == 0) {
if (HAVE_IP(1, ip_end, ip))
goto input_overrun;
while (*ip == 0) {
t += 255;
ip++;
if (HAVE_IP(1, ip_end, ip))
goto input_overrun;
}
t += 15 + *ip++;
}
if (HAVE_OP(t + 3, op_end, op))
goto output_overrun;
if (HAVE_IP(t + 4, ip_end, ip))
goto input_overrun;
COPY4(op, ip);
op += 4;
ip += 4;
if (--t > 0) {
if (t >= 4) {
do {
COPY4(op, ip);
op += 4;
ip += 4;
t -= 4;
} while (t >= 4);
if (t > 0) {
do {
*op++ = *ip++;
} while (--t > 0);
}
} else {
do {
*op++ = *ip++;
} while (--t > 0);
}
}
first_literal_run:
t = *ip++;
if (t >= 16)
goto match;
m_pos = op - (1 + M2_MAX_OFFSET);
m_pos -= t >> 2;
m_pos -= *ip++ << 2;
if (HAVE_LB(m_pos, out, op))
goto lookbehind_overrun;
if (HAVE_OP(3, op_end, op))
goto output_overrun;
*op++ = *m_pos++;
*op++ = *m_pos++;
*op++ = *m_pos;
goto match_done;
do {
match:
if (t >= 64) {
m_pos = op - 1;
m_pos -= (t >> 2) & 7;
m_pos -= *ip++ << 3;
t = (t >> 5) - 1;
if (HAVE_LB(m_pos, out, op))
goto lookbehind_overrun;
if (HAVE_OP(t + 3 - 1, op_end, op))
goto output_overrun;
goto copy_match;
} else if (t >= 32) {
t &= 31;
if (t == 0) {
if (HAVE_IP(1, ip_end, ip))
goto input_overrun;
while (*ip == 0) {
t += 255;
ip++;
if (HAVE_IP(1, ip_end, ip))
goto input_overrun;
}
t += 31 + *ip++;
}
m_pos = op - 1;
m_pos -= get_unaligned_le16(ip) >> 2;
ip += 2;
} else if (t >= 16) {
m_pos = op;
m_pos -= (t & 8) << 11;
t &= 7;
if (t == 0) {
if (HAVE_IP(1, ip_end, ip))
goto input_overrun;
while (*ip == 0) {
t += 255;
ip++;
if (HAVE_IP(1, ip_end, ip))
goto input_overrun;
}
t += 7 + *ip++;
}
m_pos -= get_unaligned_le16(ip) >> 2;
ip += 2;
if (m_pos == op)
goto eof_found;
m_pos -= 0x4000;
} else {
m_pos = op - 1;
m_pos -= t >> 2;
m_pos -= *ip++ << 2;
if (HAVE_LB(m_pos, out, op))
goto lookbehind_overrun;
if (HAVE_OP(2, op_end, op))
goto output_overrun;
*op++ = *m_pos++;
*op++ = *m_pos;
goto match_done;
}
if (HAVE_LB(m_pos, out, op))
goto lookbehind_overrun;
if (HAVE_OP(t + 3 - 1, op_end, op))
goto output_overrun;
if (t >= 2 * 4 - (3 - 1) && (op - m_pos) >= 4) {
COPY4(op, m_pos);
op += 4;
m_pos += 4;
t -= 4 - (3 - 1);
do {
COPY4(op, m_pos);
op += 4;
m_pos += 4;
t -= 4;
} while (t >= 4);
if (t > 0)
do {
*op++ = *m_pos++;
} while (--t > 0);
} else {
copy_match:
*op++ = *m_pos++;
*op++ = *m_pos++;
do {
*op++ = *m_pos++;
} while (--t > 0);
}
match_done:
t = ip[-2] & 3;
if (t == 0)
break;
match_next:
if (HAVE_OP(t, op_end, op))
goto output_overrun;
if (HAVE_IP(t + 1, ip_end, ip))
goto input_overrun;
*op++ = *ip++;
if (t > 1) {
*op++ = *ip++;
if (t > 2)
*op++ = *ip++;
}
t = *ip++;
} while (ip < ip_end);
}
*out_len = op - out;
return LZO_E_EOF_NOT_FOUND;
eof_found:
*out_len = op - out;
return (ip == ip_end ? LZO_E_OK :
(ip < ip_end ? LZO_E_INPUT_NOT_CONSUMED : LZO_E_INPUT_OVERRUN));
input_overrun:
*out_len = op - out;
return LZO_E_INPUT_OVERRUN;
output_overrun:
*out_len = op - out;
return LZO_E_OUTPUT_OVERRUN;
lookbehind_overrun:
*out_len = op - out;
return LZO_E_LOOKBEHIND_OVERRUN;
}
#ifndef STATIC
EXPORT_SYMBOL_GPL(lzo1x_decompress_safe);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("LZO1X Decompressor");
#endif