add support for xz-compressed roms

using xz embedded (public domain code).
in order to be enable to use ordinary xz files, support for crc64
was activated. (if using crc32 only, one would need to use a command
like

    xz --check=crc32 --lzma2=preset=6e,dict=64KiB

to create the files.

with crc64, one can use files that have been compressed with settings
up to -9 (however, those need 64+1MB for decompression).
since gb/gbc files are small anyway, using compression level 6-8 might
be preferable to keep client memory consumption down.
every step in xz compression level downwards decreases decomp mem usage
by 50% (so level 8 would need 32+1 MB, etc).
This commit is contained in:
rofl0r 2017-11-22 17:17:22 +00:00
parent ced1c92879
commit 5056b238a2
14 changed files with 3666 additions and 7 deletions

View File

@ -60,7 +60,7 @@ install: all
$(INSTALL) -m 755 $(TARGETS) $(bindir)
clean:
rm -f *gnuboy gmon.out *.o sys/*.o sys/*/*.o asm/*/*.o
rm -f *gnuboy gmon.out *.o sys/*.o sys/*/*.o asm/*/*.o $(OBJS)
distclean: clean
rm -f config.* sys/nix/config.h Makefile

4
Rules
View File

@ -1,11 +1,13 @@
include Version
XZ_OBJS = xz/xz_crc32.o xz/xz_crc64.o xz/xz_dec_lzma2.o xz/xz_dec_stream.o xz/xz_dec_bcj.o
OBJS = lcd.o refresh.o lcdc.o palette.o cpu.o mem.o rtc.o hw.o sound.o \
events.o keytable.o \
loader.o save.o debug.o emu.o main.o \
rccmds.o rckeys.o rcvars.o rcfile.o exports.o \
split.o path.o inflate.o
split.o path.o inflate.o $(XZ_OBJS)
INCS = -I.

View File

@ -17,6 +17,7 @@
#include "rc.h"
#include "lcd.h"
#include "inflate.h"
#include "xz/xz.h"
#include "save.h"
#include "sound.h"
#include "sys.h"
@ -142,11 +143,8 @@ static void inflate_callback(byte b)
inf_buf[inf_pos++] = b;
}
static byte *decompress(byte *data, int *len)
{
unsigned long pos = 0;
if (data[0] != 0x1f || data[1] != 0x8b)
return data;
static byte *gunzip(byte *data, int *len) {
long pos = 0;
inf_buf = 0;
inf_pos = inf_len = 0;
if (unzip(data, &pos, inflate_callback) < 0)
@ -155,6 +153,75 @@ static byte *decompress(byte *data, int *len)
return inf_buf;
}
static void write_dec(byte *data, int len) {
int i;
for(i=0; i < len; i++)
inflate_callback(data[i]);
}
static int unxz(byte *data, int len) {
struct xz_buf b;
struct xz_dec *s;
enum xz_ret ret;
unsigned char out[4096];
/*
* Support up to 64 MiB dictionary. The actually needed memory
* is allocated once the headers have been parsed.
*/
s = xz_dec_init(XZ_DYNALLOC, 1 << 26);
if(!s) goto err;
b.in = data;
b.in_pos = 0;
b.in_size = len;
b.out = out;
b.out_pos = 0;
b.out_size = sizeof(out);
while (1) {
ret = xz_dec_run(s, &b);
if(b.out_pos == sizeof(out)) {
write_dec(out, sizeof(out));
b.out_pos = 0;
}
if(ret == XZ_OK) continue;
write_dec(out, b.out_pos);
if(ret == XZ_STREAM_END) {
xz_dec_end(s);
return 0;
}
goto err;
}
err:
xz_dec_end(s);
return -1;
}
static byte *do_unxz(byte *data, int *len) {
xz_crc32_init();
xz_crc64_init();
inf_buf = 0;
inf_pos = inf_len = 0;
if (unxz(data, *len) < 0)
return data;
*len = inf_pos;
return inf_buf;
}
static byte *decompress(byte *data, int *len)
{
if (data[0] == 0x1f && data[1] == 0x8b)
return gunzip(data, len);
if(data[0] == 0xFD && !memcmp(data+1, "7zXZ", 4))
return do_unxz(data, len);
return data;
}
int rom_load()
{

10
xz/COPYING Normal file
View File

@ -0,0 +1,10 @@
Licensing of XZ Embedded
========================
All the files in this package have been written by Lasse Collin
and/or Igor Pavlov. All these files have been put into the
public domain. You can do whatever you want with these files.
As usual, this software is provided "as is", without any warranty.

304
xz/xz.h Normal file
View File

@ -0,0 +1,304 @@
/*
* XZ decompressor
*
* Authors: Lasse Collin <lasse.collin@tukaani.org>
* Igor Pavlov <http://7-zip.org/>
*
* This file has been put into the public domain.
* You can do whatever you want with this file.
*/
#ifndef XZ_H
#define XZ_H
#ifdef __KERNEL__
# include <linux/stddef.h>
# include <linux/types.h>
#else
# include <stddef.h>
# include <stdint.h>
#endif
#ifdef __cplusplus
extern "C" {
#endif
/* In Linux, this is used to make extern functions static when needed. */
#ifndef XZ_EXTERN
# define XZ_EXTERN extern
#endif
/**
* enum xz_mode - Operation mode
*
* @XZ_SINGLE: Single-call mode. This uses less RAM than
* than multi-call modes, because the LZMA2
* dictionary doesn't need to be allocated as
* part of the decoder state. All required data
* structures are allocated at initialization,
* so xz_dec_run() cannot return XZ_MEM_ERROR.
* @XZ_PREALLOC: Multi-call mode with preallocated LZMA2
* dictionary buffer. All data structures are
* allocated at initialization, so xz_dec_run()
* cannot return XZ_MEM_ERROR.
* @XZ_DYNALLOC: Multi-call mode. The LZMA2 dictionary is
* allocated once the required size has been
* parsed from the stream headers. If the
* allocation fails, xz_dec_run() will return
* XZ_MEM_ERROR.
*
* It is possible to enable support only for a subset of the above
* modes at compile time by defining XZ_DEC_SINGLE, XZ_DEC_PREALLOC,
* or XZ_DEC_DYNALLOC. The xz_dec kernel module is always compiled
* with support for all operation modes, but the preboot code may
* be built with fewer features to minimize code size.
*/
enum xz_mode {
XZ_SINGLE,
XZ_PREALLOC,
XZ_DYNALLOC
};
/**
* enum xz_ret - Return codes
* @XZ_OK: Everything is OK so far. More input or more
* output space is required to continue. This
* return code is possible only in multi-call mode
* (XZ_PREALLOC or XZ_DYNALLOC).
* @XZ_STREAM_END: Operation finished successfully.
* @XZ_UNSUPPORTED_CHECK: Integrity check type is not supported. Decoding
* is still possible in multi-call mode by simply
* calling xz_dec_run() again.
* Note that this return value is used only if
* XZ_DEC_ANY_CHECK was defined at build time,
* which is not used in the kernel. Unsupported
* check types return XZ_OPTIONS_ERROR if
* XZ_DEC_ANY_CHECK was not defined at build time.
* @XZ_MEM_ERROR: Allocating memory failed. This return code is
* possible only if the decoder was initialized
* with XZ_DYNALLOC. The amount of memory that was
* tried to be allocated was no more than the
* dict_max argument given to xz_dec_init().
* @XZ_MEMLIMIT_ERROR: A bigger LZMA2 dictionary would be needed than
* allowed by the dict_max argument given to
* xz_dec_init(). This return value is possible
* only in multi-call mode (XZ_PREALLOC or
* XZ_DYNALLOC); the single-call mode (XZ_SINGLE)
* ignores the dict_max argument.
* @XZ_FORMAT_ERROR: File format was not recognized (wrong magic
* bytes).
* @XZ_OPTIONS_ERROR: This implementation doesn't support the requested
* compression options. In the decoder this means
* that the header CRC32 matches, but the header
* itself specifies something that we don't support.
* @XZ_DATA_ERROR: Compressed data is corrupt.
* @XZ_BUF_ERROR: Cannot make any progress. Details are slightly
* different between multi-call and single-call
* mode; more information below.
*
* In multi-call mode, XZ_BUF_ERROR is returned when two consecutive calls
* to XZ code cannot consume any input and cannot produce any new output.
* This happens when there is no new input available, or the output buffer
* is full while at least one output byte is still pending. Assuming your
* code is not buggy, you can get this error only when decoding a compressed
* stream that is truncated or otherwise corrupt.
*
* In single-call mode, XZ_BUF_ERROR is returned only when the output buffer
* is too small or the compressed input is corrupt in a way that makes the
* decoder produce more output than the caller expected. When it is
* (relatively) clear that the compressed input is truncated, XZ_DATA_ERROR
* is used instead of XZ_BUF_ERROR.
*/
enum xz_ret {
XZ_OK,
XZ_STREAM_END,
XZ_UNSUPPORTED_CHECK,
XZ_MEM_ERROR,
XZ_MEMLIMIT_ERROR,
XZ_FORMAT_ERROR,
XZ_OPTIONS_ERROR,
XZ_DATA_ERROR,
XZ_BUF_ERROR
};
/**
* struct xz_buf - Passing input and output buffers to XZ code
* @in: Beginning of the input buffer. This may be NULL if and only
* if in_pos is equal to in_size.
* @in_pos: Current position in the input buffer. This must not exceed
* in_size.
* @in_size: Size of the input buffer
* @out: Beginning of the output buffer. This may be NULL if and only
* if out_pos is equal to out_size.
* @out_pos: Current position in the output buffer. This must not exceed
* out_size.
* @out_size: Size of the output buffer
*
* Only the contents of the output buffer from out[out_pos] onward, and
* the variables in_pos and out_pos are modified by the XZ code.
*/
struct xz_buf {
const uint8_t *in;
size_t in_pos;
size_t in_size;
uint8_t *out;
size_t out_pos;
size_t out_size;
};
/**
* struct xz_dec - Opaque type to hold the XZ decoder state
*/
struct xz_dec;
/**
* xz_dec_init() - Allocate and initialize a XZ decoder state
* @mode: Operation mode
* @dict_max: Maximum size of the LZMA2 dictionary (history buffer) for
* multi-call decoding. This is ignored in single-call mode
* (mode == XZ_SINGLE). LZMA2 dictionary is always 2^n bytes
* or 2^n + 2^(n-1) bytes (the latter sizes are less common
* in practice), so other values for dict_max don't make sense.
* In the kernel, dictionary sizes of 64 KiB, 128 KiB, 256 KiB,
* 512 KiB, and 1 MiB are probably the only reasonable values,
* except for kernel and initramfs images where a bigger
* dictionary can be fine and useful.
*
* Single-call mode (XZ_SINGLE): xz_dec_run() decodes the whole stream at
* once. The caller must provide enough output space or the decoding will
* fail. The output space is used as the dictionary buffer, which is why
* there is no need to allocate the dictionary as part of the decoder's
* internal state.
*
* Because the output buffer is used as the workspace, streams encoded using
* a big dictionary are not a problem in single-call mode. It is enough that
* the output buffer is big enough to hold the actual uncompressed data; it
* can be smaller than the dictionary size stored in the stream headers.
*
* Multi-call mode with preallocated dictionary (XZ_PREALLOC): dict_max bytes
* of memory is preallocated for the LZMA2 dictionary. This way there is no
* risk that xz_dec_run() could run out of memory, since xz_dec_run() will
* never allocate any memory. Instead, if the preallocated dictionary is too
* small for decoding the given input stream, xz_dec_run() will return
* XZ_MEMLIMIT_ERROR. Thus, it is important to know what kind of data will be
* decoded to avoid allocating excessive amount of memory for the dictionary.
*
* Multi-call mode with dynamically allocated dictionary (XZ_DYNALLOC):
* dict_max specifies the maximum allowed dictionary size that xz_dec_run()
* may allocate once it has parsed the dictionary size from the stream
* headers. This way excessive allocations can be avoided while still
* limiting the maximum memory usage to a sane value to prevent running the
* system out of memory when decompressing streams from untrusted sources.
*
* On success, xz_dec_init() returns a pointer to struct xz_dec, which is
* ready to be used with xz_dec_run(). If memory allocation fails,
* xz_dec_init() returns NULL.
*/
XZ_EXTERN struct xz_dec *xz_dec_init(enum xz_mode mode, uint32_t dict_max);
/**
* xz_dec_run() - Run the XZ decoder
* @s: Decoder state allocated using xz_dec_init()
* @b: Input and output buffers
*
* The possible return values depend on build options and operation mode.
* See enum xz_ret for details.
*
* Note that if an error occurs in single-call mode (return value is not
* XZ_STREAM_END), b->in_pos and b->out_pos are not modified and the
* contents of the output buffer from b->out[b->out_pos] onward are
* undefined. This is true even after XZ_BUF_ERROR, because with some filter
* chains, there may be a second pass over the output buffer, and this pass
* cannot be properly done if the output buffer is truncated. Thus, you
* cannot give the single-call decoder a too small buffer and then expect to
* get that amount valid data from the beginning of the stream. You must use
* the multi-call decoder if you don't want to uncompress the whole stream.
*/
XZ_EXTERN enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b);
/**
* xz_dec_reset() - Reset an already allocated decoder state
* @s: Decoder state allocated using xz_dec_init()
*
* This function can be used to reset the multi-call decoder state without
* freeing and reallocating memory with xz_dec_end() and xz_dec_init().
*
* In single-call mode, xz_dec_reset() is always called in the beginning of
* xz_dec_run(). Thus, explicit call to xz_dec_reset() is useful only in
* multi-call mode.
*/
XZ_EXTERN void xz_dec_reset(struct xz_dec *s);
/**
* xz_dec_end() - Free the memory allocated for the decoder state
* @s: Decoder state allocated using xz_dec_init(). If s is NULL,
* this function does nothing.
*/
XZ_EXTERN void xz_dec_end(struct xz_dec *s);
/*
* Standalone build (userspace build or in-kernel build for boot time use)
* needs a CRC32 implementation. For normal in-kernel use, kernel's own
* CRC32 module is used instead, and users of this module don't need to
* care about the functions below.
*/
#ifndef XZ_INTERNAL_CRC32
# ifdef __KERNEL__
# define XZ_INTERNAL_CRC32 0
# else
# define XZ_INTERNAL_CRC32 1
# endif
#endif
/*
* If CRC64 support has been enabled with XZ_USE_CRC64, a CRC64
* implementation is needed too.
*/
#ifndef XZ_USE_CRC64
# undef XZ_INTERNAL_CRC64
# define XZ_INTERNAL_CRC64 0
#endif
#ifndef XZ_INTERNAL_CRC64
# ifdef __KERNEL__
# error Using CRC64 in the kernel has not been implemented.
# else
# define XZ_INTERNAL_CRC64 1
# endif
#endif
#if XZ_INTERNAL_CRC32
/*
* This must be called before any other xz_* function to initialize
* the CRC32 lookup table.
*/
XZ_EXTERN void xz_crc32_init(void);
/*
* Update CRC32 value using the polynomial from IEEE-802.3. To start a new
* calculation, the third argument must be zero. To continue the calculation,
* the previously returned value is passed as the third argument.
*/
XZ_EXTERN uint32_t xz_crc32(const uint8_t *buf, size_t size, uint32_t crc);
#endif
#if XZ_INTERNAL_CRC64
/*
* This must be called before any other xz_* function (except xz_crc32_init())
* to initialize the CRC64 lookup table.
*/
XZ_EXTERN void xz_crc64_init(void);
/*
* Update CRC64 value using the polynomial from ECMA-182. To start a new
* calculation, the third argument must be zero. To continue the calculation,
* the previously returned value is passed as the third argument.
*/
XZ_EXTERN uint64_t xz_crc64(const uint8_t *buf, size_t size, uint64_t crc);
#endif
#ifdef __cplusplus
}
#endif
#endif

133
xz/xz_config.h Normal file
View File

@ -0,0 +1,133 @@
/*
* Private includes and definitions for userspace use of XZ Embedded
*
* Author: Lasse Collin <lasse.collin@tukaani.org>
*
* This file has been put into the public domain.
* You can do whatever you want with this file.
*/
#ifndef XZ_CONFIG_H
#define XZ_CONFIG_H
/* Uncomment to enable CRC64 support. */
#define XZ_USE_CRC64
/* Uncomment as needed to enable BCJ filter decoders. */
#if 0
#define XZ_DEC_X86
#define XZ_DEC_POWERPC
#define XZ_DEC_IA64
#define XZ_DEC_ARM
#define XZ_DEC_ARMTHUMB
#define XZ_DEC_SPARC
#endif
/*
* MSVC doesn't support modern C but XZ Embedded is mostly C89
* so these are enough.
*/
#ifdef _MSC_VER
typedef unsigned char bool;
# define true 1
# define false 0
# define inline __inline
#else
# if !defined(__STDC_VERSION__) || __STDC_VERSION__ < 199901L
# if defined(__GNUC__)
# define inline __inline
# else
# define inline
# endif
# endif
# include <stdbool.h>
#endif
#include <stdlib.h>
#include <string.h>
#include "xz.h"
#define kmalloc(size, flags) malloc(size)
#define kfree(ptr) free(ptr)
#define vmalloc(size) malloc(size)
#define vfree(ptr) free(ptr)
#define memeq(a, b, size) (memcmp(a, b, size) == 0)
#define memzero(buf, size) memset(buf, 0, size)
#ifndef min
# define min(x, y) ((x) < (y) ? (x) : (y))
#endif
#define min_t(type, x, y) min(x, y)
/*
* Some functions have been marked with __always_inline to keep the
* performance reasonable even when the compiler is optimizing for
* small code size. You may be able to save a few bytes by #defining
* __always_inline to plain inline, but don't complain if the code
* becomes slow.
*
* NOTE: System headers on GNU/Linux may #define this macro already,
* so if you want to change it, you need to #undef it first.
*/
#ifndef __always_inline
# ifdef __GNUC__
# define __always_inline \
inline __attribute__((__always_inline__))
# else
# define __always_inline inline
# endif
#endif
/* Inline functions to access unaligned unsigned 32-bit integers */
#ifndef get_unaligned_le32
static inline uint32_t get_unaligned_le32(const uint8_t *buf)
{
return (uint32_t)buf[0]
| ((uint32_t)buf[1] << 8)
| ((uint32_t)buf[2] << 16)
| ((uint32_t)buf[3] << 24);
}
#endif
#ifndef get_unaligned_be32
static inline uint32_t get_unaligned_be32(const uint8_t *buf)
{
return (uint32_t)(buf[0] << 24)
| ((uint32_t)buf[1] << 16)
| ((uint32_t)buf[2] << 8)
| (uint32_t)buf[3];
}
#endif
#ifndef put_unaligned_le32
static inline void put_unaligned_le32(uint32_t val, uint8_t *buf)
{
buf[0] = (uint8_t)val;
buf[1] = (uint8_t)(val >> 8);
buf[2] = (uint8_t)(val >> 16);
buf[3] = (uint8_t)(val >> 24);
}
#endif
#ifndef put_unaligned_be32
static inline void put_unaligned_be32(uint32_t val, uint8_t *buf)
{
buf[0] = (uint8_t)(val >> 24);
buf[1] = (uint8_t)(val >> 16);
buf[2] = (uint8_t)(val >> 8);
buf[3] = (uint8_t)val;
}
#endif
/*
* Use get_unaligned_le32() also for aligned access for simplicity. On
* little endian systems, #define get_le32(ptr) (*(const uint32_t *)(ptr))
* could save a few bytes in code size.
*/
#ifndef get_le32
# define get_le32 get_unaligned_le32
#endif
#endif

59
xz/xz_crc32.c Normal file
View File

@ -0,0 +1,59 @@
/*
* CRC32 using the polynomial from IEEE-802.3
*
* Authors: Lasse Collin <lasse.collin@tukaani.org>
* Igor Pavlov <http://7-zip.org/>
*
* This file has been put into the public domain.
* You can do whatever you want with this file.
*/
/*
* This is not the fastest implementation, but it is pretty compact.
* The fastest versions of xz_crc32() on modern CPUs without hardware
* accelerated CRC instruction are 3-5 times as fast as this version,
* but they are bigger and use more memory for the lookup table.
*/
#include "xz_private.h"
/*
* STATIC_RW_DATA is used in the pre-boot environment on some architectures.
* See <linux/decompress/mm.h> for details.
*/
#ifndef STATIC_RW_DATA
# define STATIC_RW_DATA static
#endif
STATIC_RW_DATA uint32_t xz_crc32_table[256];
XZ_EXTERN void xz_crc32_init(void)
{
const uint32_t poly = 0xEDB88320;
uint32_t i;
uint32_t j;
uint32_t r;
for (i = 0; i < 256; ++i) {
r = i;
for (j = 0; j < 8; ++j)
r = (r >> 1) ^ (poly & ~((r & 1) - 1));
xz_crc32_table[i] = r;
}
return;
}
XZ_EXTERN uint32_t xz_crc32(const uint8_t *buf, size_t size, uint32_t crc)
{
crc = ~crc;
while (size != 0) {
crc = xz_crc32_table[*buf++ ^ (crc & 0xFF)] ^ (crc >> 8);
--size;
}
return ~crc;
}

50
xz/xz_crc64.c Normal file
View File

@ -0,0 +1,50 @@
/*
* CRC64 using the polynomial from ECMA-182
*
* This file is similar to xz_crc32.c. See the comments there.
*
* Authors: Lasse Collin <lasse.collin@tukaani.org>
* Igor Pavlov <http://7-zip.org/>
*
* This file has been put into the public domain.
* You can do whatever you want with this file.
*/
#include "xz_private.h"
#ifndef STATIC_RW_DATA
# define STATIC_RW_DATA static
#endif
STATIC_RW_DATA uint64_t xz_crc64_table[256];
XZ_EXTERN void xz_crc64_init(void)
{
const uint64_t poly = 0xC96C5795D7870F42;
uint32_t i;
uint32_t j;
uint64_t r;
for (i = 0; i < 256; ++i) {
r = i;
for (j = 0; j < 8; ++j)
r = (r >> 1) ^ (poly & ~((r & 1) - 1));
xz_crc64_table[i] = r;
}
return;
}
XZ_EXTERN uint64_t xz_crc64(const uint8_t *buf, size_t size, uint64_t crc)
{
crc = ~crc;
while (size != 0) {
crc = xz_crc64_table[*buf++ ^ (crc & 0xFF)] ^ (crc >> 8);
--size;
}
return ~crc;
}

574
xz/xz_dec_bcj.c Normal file
View File

@ -0,0 +1,574 @@
/*
* Branch/Call/Jump (BCJ) filter decoders
*
* Authors: Lasse Collin <lasse.collin@tukaani.org>
* Igor Pavlov <http://7-zip.org/>
*
* This file has been put into the public domain.
* You can do whatever you want with this file.
*/
#include "xz_private.h"
/*
* The rest of the file is inside this ifdef. It makes things a little more
* convenient when building without support for any BCJ filters.
*/
#ifdef XZ_DEC_BCJ
struct xz_dec_bcj {
/* Type of the BCJ filter being used */
enum {
BCJ_X86 = 4, /* x86 or x86-64 */
BCJ_POWERPC = 5, /* Big endian only */
BCJ_IA64 = 6, /* Big or little endian */
BCJ_ARM = 7, /* Little endian only */
BCJ_ARMTHUMB = 8, /* Little endian only */
BCJ_SPARC = 9 /* Big or little endian */
} type;
/*
* Return value of the next filter in the chain. We need to preserve
* this information across calls, because we must not call the next
* filter anymore once it has returned XZ_STREAM_END.
*/
enum xz_ret ret;
/* True if we are operating in single-call mode. */
bool single_call;
/*
* Absolute position relative to the beginning of the uncompressed
* data (in a single .xz Block). We care only about the lowest 32
* bits so this doesn't need to be uint64_t even with big files.
*/
uint32_t pos;
/* x86 filter state */
uint32_t x86_prev_mask;
/* Temporary space to hold the variables from struct xz_buf */
uint8_t *out;
size_t out_pos;
size_t out_size;
struct {
/* Amount of already filtered data in the beginning of buf */
size_t filtered;
/* Total amount of data currently stored in buf */
size_t size;
/*
* Buffer to hold a mix of filtered and unfiltered data. This
* needs to be big enough to hold Alignment + 2 * Look-ahead:
*
* Type Alignment Look-ahead
* x86 1 4
* PowerPC 4 0
* IA-64 16 0
* ARM 4 0
* ARM-Thumb 2 2
* SPARC 4 0
*/
uint8_t buf[16];
} temp;
};
#ifdef XZ_DEC_X86
/*
* This is used to test the most significant byte of a memory address
* in an x86 instruction.
*/
static inline int bcj_x86_test_msbyte(uint8_t b)
{
return b == 0x00 || b == 0xFF;
}
static size_t bcj_x86(struct xz_dec_bcj *s, uint8_t *buf, size_t size)
{
static const bool mask_to_allowed_status[8]
= { true, true, true, false, true, false, false, false };
static const uint8_t mask_to_bit_num[8] = { 0, 1, 2, 2, 3, 3, 3, 3 };
size_t i;
size_t prev_pos = (size_t)-1;
uint32_t prev_mask = s->x86_prev_mask;
uint32_t src;
uint32_t dest;
uint32_t j;
uint8_t b;
if (size <= 4)
return 0;
size -= 4;
for (i = 0; i < size; ++i) {
if ((buf[i] & 0xFE) != 0xE8)
continue;
prev_pos = i - prev_pos;
if (prev_pos > 3) {
prev_mask = 0;
} else {
prev_mask = (prev_mask << (prev_pos - 1)) & 7;
if (prev_mask != 0) {
b = buf[i + 4 - mask_to_bit_num[prev_mask]];
if (!mask_to_allowed_status[prev_mask]
|| bcj_x86_test_msbyte(b)) {
prev_pos = i;
prev_mask = (prev_mask << 1) | 1;
continue;
}
}
}
prev_pos = i;
if (bcj_x86_test_msbyte(buf[i + 4])) {
src = get_unaligned_le32(buf + i + 1);
while (true) {
dest = src - (s->pos + (uint32_t)i + 5);
if (prev_mask == 0)
break;
j = mask_to_bit_num[prev_mask] * 8;
b = (uint8_t)(dest >> (24 - j));
if (!bcj_x86_test_msbyte(b))
break;
src = dest ^ (((uint32_t)1 << (32 - j)) - 1);
}
dest &= 0x01FFFFFF;
dest |= (uint32_t)0 - (dest & 0x01000000);
put_unaligned_le32(dest, buf + i + 1);
i += 4;
} else {
prev_mask = (prev_mask << 1) | 1;
}
}
prev_pos = i - prev_pos;
s->x86_prev_mask = prev_pos > 3 ? 0 : prev_mask << (prev_pos - 1);
return i;
}
#endif
#ifdef XZ_DEC_POWERPC
static size_t bcj_powerpc(struct xz_dec_bcj *s, uint8_t *buf, size_t size)
{
size_t i;
uint32_t instr;
for (i = 0; i + 4 <= size; i += 4) {
instr = get_unaligned_be32(buf + i);
if ((instr & 0xFC000003) == 0x48000001) {
instr &= 0x03FFFFFC;
instr -= s->pos + (uint32_t)i;
instr &= 0x03FFFFFC;
instr |= 0x48000001;
put_unaligned_be32(instr, buf + i);
}
}
return i;
}
#endif
#ifdef XZ_DEC_IA64
static size_t bcj_ia64(struct xz_dec_bcj *s, uint8_t *buf, size_t size)
{
static const uint8_t branch_table[32] = {
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
4, 4, 6, 6, 0, 0, 7, 7,
4, 4, 0, 0, 4, 4, 0, 0
};
/*
* The local variables take a little bit stack space, but it's less
* than what LZMA2 decoder takes, so it doesn't make sense to reduce
* stack usage here without doing that for the LZMA2 decoder too.
*/
/* Loop counters */
size_t i;
size_t j;
/* Instruction slot (0, 1, or 2) in the 128-bit instruction word */
uint32_t slot;
/* Bitwise offset of the instruction indicated by slot */
uint32_t bit_pos;
/* bit_pos split into byte and bit parts */
uint32_t byte_pos;
uint32_t bit_res;
/* Address part of an instruction */
uint32_t addr;
/* Mask used to detect which instructions to convert */
uint32_t mask;
/* 41-bit instruction stored somewhere in the lowest 48 bits */
uint64_t instr;
/* Instruction normalized with bit_res for easier manipulation */
uint64_t norm;
for (i = 0; i + 16 <= size; i += 16) {
mask = branch_table[buf[i] & 0x1F];
for (slot = 0, bit_pos = 5; slot < 3; ++slot, bit_pos += 41) {
if (((mask >> slot) & 1) == 0)
continue;
byte_pos = bit_pos >> 3;
bit_res = bit_pos & 7;
instr = 0;
for (j = 0; j < 6; ++j)
instr |= (uint64_t)(buf[i + j + byte_pos])
<< (8 * j);
norm = instr >> bit_res;
if (((norm >> 37) & 0x0F) == 0x05
&& ((norm >> 9) & 0x07) == 0) {
addr = (norm >> 13) & 0x0FFFFF;
addr |= ((uint32_t)(norm >> 36) & 1) << 20;
addr <<= 4;
addr -= s->pos + (uint32_t)i;
addr >>= 4;
norm &= ~((uint64_t)0x8FFFFF << 13);
norm |= (uint64_t)(addr & 0x0FFFFF) << 13;
norm |= (uint64_t)(addr & 0x100000)
<< (36 - 20);
instr &= (1 << bit_res) - 1;
instr |= norm << bit_res;
for (j = 0; j < 6; j++)
buf[i + j + byte_pos]
= (uint8_t)(instr >> (8 * j));
}
}
}
return i;
}
#endif
#ifdef XZ_DEC_ARM
static size_t bcj_arm(struct xz_dec_bcj *s, uint8_t *buf, size_t size)
{
size_t i;
uint32_t addr;
for (i = 0; i + 4 <= size; i += 4) {
if (buf[i + 3] == 0xEB) {
addr = (uint32_t)buf[i] | ((uint32_t)buf[i + 1] << 8)
| ((uint32_t)buf[i + 2] << 16);
addr <<= 2;
addr -= s->pos + (uint32_t)i + 8;
addr >>= 2;
buf[i] = (uint8_t)addr;
buf[i + 1] = (uint8_t)(addr >> 8);
buf[i + 2] = (uint8_t)(addr >> 16);
}
}
return i;
}
#endif
#ifdef XZ_DEC_ARMTHUMB
static size_t bcj_armthumb(struct xz_dec_bcj *s, uint8_t *buf, size_t size)
{
size_t i;
uint32_t addr;
for (i = 0; i + 4 <= size; i += 2) {
if ((buf[i + 1] & 0xF8) == 0xF0
&& (buf[i + 3] & 0xF8) == 0xF8) {
addr = (((uint32_t)buf[i + 1] & 0x07) << 19)
| ((uint32_t)buf[i] << 11)
| (((uint32_t)buf[i + 3] & 0x07) << 8)
| (uint32_t)buf[i + 2];
addr <<= 1;
addr -= s->pos + (uint32_t)i + 4;
addr >>= 1;
buf[i + 1] = (uint8_t)(0xF0 | ((addr >> 19) & 0x07));
buf[i] = (uint8_t)(addr >> 11);
buf[i + 3] = (uint8_t)(0xF8 | ((addr >> 8) & 0x07));
buf[i + 2] = (uint8_t)addr;
i += 2;
}
}
return i;
}
#endif
#ifdef XZ_DEC_SPARC
static size_t bcj_sparc(struct xz_dec_bcj *s, uint8_t *buf, size_t size)
{
size_t i;
uint32_t instr;
for (i = 0; i + 4 <= size; i += 4) {
instr = get_unaligned_be32(buf + i);
if ((instr >> 22) == 0x100 || (instr >> 22) == 0x1FF) {
instr <<= 2;
instr -= s->pos + (uint32_t)i;
instr >>= 2;
instr = ((uint32_t)0x40000000 - (instr & 0x400000))
| 0x40000000 | (instr & 0x3FFFFF);
put_unaligned_be32(instr, buf + i);
}
}
return i;
}
#endif
/*
* Apply the selected BCJ filter. Update *pos and s->pos to match the amount
* of data that got filtered.
*
* NOTE: This is implemented as a switch statement to avoid using function
* pointers, which could be problematic in the kernel boot code, which must
* avoid pointers to static data (at least on x86).
*/
static void bcj_apply(struct xz_dec_bcj *s,
uint8_t *buf, size_t *pos, size_t size)
{
size_t filtered;
buf += *pos;
size -= *pos;
switch (s->type) {
#ifdef XZ_DEC_X86
case BCJ_X86:
filtered = bcj_x86(s, buf, size);
break;
#endif
#ifdef XZ_DEC_POWERPC
case BCJ_POWERPC:
filtered = bcj_powerpc(s, buf, size);
break;
#endif
#ifdef XZ_DEC_IA64
case BCJ_IA64:
filtered = bcj_ia64(s, buf, size);
break;
#endif
#ifdef XZ_DEC_ARM
case BCJ_ARM:
filtered = bcj_arm(s, buf, size);
break;
#endif
#ifdef XZ_DEC_ARMTHUMB
case BCJ_ARMTHUMB:
filtered = bcj_armthumb(s, buf, size);
break;
#endif
#ifdef XZ_DEC_SPARC
case BCJ_SPARC:
filtered = bcj_sparc(s, buf, size);
break;
#endif
default:
/* Never reached but silence compiler warnings. */
filtered = 0;
break;
}
*pos += filtered;
s->pos += filtered;
}
/*
* Flush pending filtered data from temp to the output buffer.
* Move the remaining mixture of possibly filtered and unfiltered
* data to the beginning of temp.
*/
static void bcj_flush(struct xz_dec_bcj *s, struct xz_buf *b)
{
size_t copy_size;
copy_size = min_t(size_t, s->temp.filtered, b->out_size - b->out_pos);
memcpy(b->out + b->out_pos, s->temp.buf, copy_size);
b->out_pos += copy_size;
s->temp.filtered -= copy_size;
s->temp.size -= copy_size;
memmove(s->temp.buf, s->temp.buf + copy_size, s->temp.size);
}
/*
* The BCJ filter functions are primitive in sense that they process the
* data in chunks of 1-16 bytes. To hide this issue, this function does
* some buffering.
*/
XZ_EXTERN enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s,
struct xz_dec_lzma2 *lzma2,
struct xz_buf *b)
{
size_t out_start;
/*
* Flush pending already filtered data to the output buffer. Return
* immediatelly if we couldn't flush everything, or if the next
* filter in the chain had already returned XZ_STREAM_END.
*/
if (s->temp.filtered > 0) {
bcj_flush(s, b);
if (s->temp.filtered > 0)
return XZ_OK;
if (s->ret == XZ_STREAM_END)
return XZ_STREAM_END;
}
/*
* If we have more output space than what is currently pending in
* temp, copy the unfiltered data from temp to the output buffer
* and try to fill the output buffer by decoding more data from the
* next filter in the chain. Apply the BCJ filter on the new data
* in the output buffer. If everything cannot be filtered, copy it
* to temp and rewind the output buffer position accordingly.
*
* This needs to be always run when temp.size == 0 to handle a special
* case where the output buffer is full and the next filter has no
* more output coming but hasn't returned XZ_STREAM_END yet.
*/
if (s->temp.size < b->out_size - b->out_pos || s->temp.size == 0) {
out_start = b->out_pos;
memcpy(b->out + b->out_pos, s->temp.buf, s->temp.size);
b->out_pos += s->temp.size;
s->ret = xz_dec_lzma2_run(lzma2, b);
if (s->ret != XZ_STREAM_END
&& (s->ret != XZ_OK || s->single_call))
return s->ret;
bcj_apply(s, b->out, &out_start, b->out_pos);
/*
* As an exception, if the next filter returned XZ_STREAM_END,
* we can do that too, since the last few bytes that remain
* unfiltered are meant to remain unfiltered.
*/
if (s->ret == XZ_STREAM_END)
return XZ_STREAM_END;
s->temp.size = b->out_pos - out_start;
b->out_pos -= s->temp.size;
memcpy(s->temp.buf, b->out + b->out_pos, s->temp.size);
/*
* If there wasn't enough input to the next filter to fill
* the output buffer with unfiltered data, there's no point
* to try decoding more data to temp.
*/
if (b->out_pos + s->temp.size < b->out_size)
return XZ_OK;
}
/*
* We have unfiltered data in temp. If the output buffer isn't full
* yet, try to fill the temp buffer by decoding more data from the
* next filter. Apply the BCJ filter on temp. Then we hopefully can
* fill the actual output buffer by copying filtered data from temp.
* A mix of filtered and unfiltered data may be left in temp; it will
* be taken care on the next call to this function.
*/
if (b->out_pos < b->out_size) {
/* Make b->out{,_pos,_size} temporarily point to s->temp. */
s->out = b->out;
s->out_pos = b->out_pos;
s->out_size = b->out_size;
b->out = s->temp.buf;
b->out_pos = s->temp.size;
b->out_size = sizeof(s->temp.buf);
s->ret = xz_dec_lzma2_run(lzma2, b);
s->temp.size = b->out_pos;
b->out = s->out;
b->out_pos = s->out_pos;
b->out_size = s->out_size;
if (s->ret != XZ_OK && s->ret != XZ_STREAM_END)
return s->ret;
bcj_apply(s, s->temp.buf, &s->temp.filtered, s->temp.size);
/*
* If the next filter returned XZ_STREAM_END, we mark that
* everything is filtered, since the last unfiltered bytes
* of the stream are meant to be left as is.
*/
if (s->ret == XZ_STREAM_END)
s->temp.filtered = s->temp.size;
bcj_flush(s, b);
if (s->temp.filtered > 0)
return XZ_OK;
}
return s->ret;
}
XZ_EXTERN struct xz_dec_bcj *xz_dec_bcj_create(bool single_call)
{
struct xz_dec_bcj *s = kmalloc(sizeof(*s), GFP_KERNEL);
if (s != NULL)
s->single_call = single_call;
return s;
}
XZ_EXTERN enum xz_ret xz_dec_bcj_reset(struct xz_dec_bcj *s, uint8_t id)
{
switch (id) {
#ifdef XZ_DEC_X86
case BCJ_X86:
#endif
#ifdef XZ_DEC_POWERPC
case BCJ_POWERPC:
#endif
#ifdef XZ_DEC_IA64
case BCJ_IA64:
#endif
#ifdef XZ_DEC_ARM
case BCJ_ARM:
#endif
#ifdef XZ_DEC_ARMTHUMB
case BCJ_ARMTHUMB:
#endif
#ifdef XZ_DEC_SPARC
case BCJ_SPARC:
#endif
break;
default:
/* Unsupported Filter ID */
return XZ_OPTIONS_ERROR;
}
s->type = id;
s->ret = XZ_OK;
s->pos = 0;
s->x86_prev_mask = 0;
s->temp.filtered = 0;
s->temp.size = 0;
return XZ_OK;
}
#endif

1175
xz/xz_dec_lzma2.c Normal file

File diff suppressed because it is too large Load Diff

863
xz/xz_dec_stream.c Normal file
View File

@ -0,0 +1,863 @@
/*
* .xz Stream decoder
*
* Author: Lasse Collin <lasse.collin@tukaani.org>
*
* This file has been put into the public domain.
* You can do whatever you want with this file.
*/
#include "xz_private.h"
#include "xz_stream.h"
#ifdef XZ_USE_CRC64
# define IS_CRC64(check_type) ((check_type) == XZ_CHECK_CRC64)
#else
# define IS_CRC64(check_type) false
#endif
/* Hash used to validate the Index field */
struct xz_dec_hash {
vli_type unpadded;
vli_type uncompressed;
uint32_t crc32;
};
struct xz_dec {
/* Position in dec_main() */
enum {
SEQ_STREAM_HEADER,
SEQ_BLOCK_START,
SEQ_BLOCK_HEADER,
SEQ_BLOCK_UNCOMPRESS,
SEQ_BLOCK_PADDING,
SEQ_BLOCK_CHECK,
SEQ_INDEX,
SEQ_INDEX_PADDING,
SEQ_INDEX_CRC32,
SEQ_STREAM_FOOTER
} sequence;
/* Position in variable-length integers and Check fields */
uint32_t pos;
/* Variable-length integer decoded by dec_vli() */
vli_type vli;
/* Saved in_pos and out_pos */
size_t in_start;
size_t out_start;
#ifdef XZ_USE_CRC64
/* CRC32 or CRC64 value in Block or CRC32 value in Index */
uint64_t crc;
#else
/* CRC32 value in Block or Index */
uint32_t crc;
#endif
/* Type of the integrity check calculated from uncompressed data */
enum xz_check check_type;
/* Operation mode */
enum xz_mode mode;
/*
* True if the next call to xz_dec_run() is allowed to return
* XZ_BUF_ERROR.
*/
bool allow_buf_error;
/* Information stored in Block Header */
struct {
/*
* Value stored in the Compressed Size field, or
* VLI_UNKNOWN if Compressed Size is not present.
*/
vli_type compressed;
/*
* Value stored in the Uncompressed Size field, or
* VLI_UNKNOWN if Uncompressed Size is not present.
*/
vli_type uncompressed;
/* Size of the Block Header field */
uint32_t size;
} block_header;
/* Information collected when decoding Blocks */
struct {
/* Observed compressed size of the current Block */
vli_type compressed;
/* Observed uncompressed size of the current Block */
vli_type uncompressed;
/* Number of Blocks decoded so far */
vli_type count;
/*
* Hash calculated from the Block sizes. This is used to
* validate the Index field.
*/
struct xz_dec_hash hash;
} block;
/* Variables needed when verifying the Index field */
struct {
/* Position in dec_index() */
enum {
SEQ_INDEX_COUNT,
SEQ_INDEX_UNPADDED,
SEQ_INDEX_UNCOMPRESSED
} sequence;
/* Size of the Index in bytes */
vli_type size;
/* Number of Records (matches block.count in valid files) */
vli_type count;
/*
* Hash calculated from the Records (matches block.hash in
* valid files).
*/
struct xz_dec_hash hash;
} index;
/*
* Temporary buffer needed to hold Stream Header, Block Header,
* and Stream Footer. The Block Header is the biggest (1 KiB)
* so we reserve space according to that. buf[] has to be aligned
* to a multiple of four bytes; the size_t variables before it
* should guarantee this.
*/
struct {
size_t pos;
size_t size;
uint8_t buf[1024];
} temp;
struct xz_dec_lzma2 *lzma2;
#ifdef XZ_DEC_BCJ
struct xz_dec_bcj *bcj;
bool bcj_active;
#endif
};
#ifdef XZ_DEC_ANY_CHECK
/* Sizes of the Check field with different Check IDs */
static const uint8_t check_sizes[16] = {
0,
4, 4, 4,
8, 8, 8,
16, 16, 16,
32, 32, 32,
64, 64, 64
};
#endif
/*
* Fill s->temp by copying data starting from b->in[b->in_pos]. Caller
* must have set s->temp.pos to indicate how much data we are supposed
* to copy into s->temp.buf. Return true once s->temp.pos has reached
* s->temp.size.
*/
static bool fill_temp(struct xz_dec *s, struct xz_buf *b)
{
size_t copy_size = min_t(size_t,
b->in_size - b->in_pos, s->temp.size - s->temp.pos);
memcpy(s->temp.buf + s->temp.pos, b->in + b->in_pos, copy_size);
b->in_pos += copy_size;
s->temp.pos += copy_size;
if (s->temp.pos == s->temp.size) {
s->temp.pos = 0;
return true;
}
return false;
}
/* Decode a variable-length integer (little-endian base-128 encoding) */
static enum xz_ret dec_vli(struct xz_dec *s, const uint8_t *in,
size_t *in_pos, size_t in_size)
{
uint8_t byte;
if (s->pos == 0)
s->vli = 0;
while (*in_pos < in_size) {
byte = in[*in_pos];
++*in_pos;
s->vli |= (vli_type)(byte & 0x7F) << s->pos;
if ((byte & 0x80) == 0) {
/* Don't allow non-minimal encodings. */
if (byte == 0 && s->pos != 0)
return XZ_DATA_ERROR;
s->pos = 0;
return XZ_STREAM_END;
}
s->pos += 7;
if (s->pos == 7 * VLI_BYTES_MAX)
return XZ_DATA_ERROR;
}
return XZ_OK;
}
/*
* Decode the Compressed Data field from a Block. Update and validate
* the observed compressed and uncompressed sizes of the Block so that
* they don't exceed the values possibly stored in the Block Header
* (validation assumes that no integer overflow occurs, since vli_type
* is normally uint64_t). Update the CRC32 or CRC64 value if presence of