sysmo-bts
/
barebox
9
0
Fork 0
Code Releases Activity

Merge branch 'for-next/xz'

This commit is contained in:
Sascha Hauer 2014-11-05 15:47:39 +01:00
parent 7b4cc54579 ccb2816477
commit 592d35a47c
21 changed files with 3782 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
common/Kconfig
View File

@ -582,6 +582,7 @@ choice
prompt "default compression for in-barebox binaries"
default DEFAULT_COMPRESSION_NONE if PBL_IMAGE
default DEFAULT_COMPRESSION_LZO if LZO_DECOMPRESS
default DEFAULT_COMPRESSION_XZ if XZ_DECOMPRESS
default DEFAULT_COMPRESSION_GZIP if ZLIB
default DEFAULT_COMPRESSION_LZ4 if LZ4_DECOMPRESS
default DEFAULT_COMPRESSION_BZIP2 if BZLIB
@ -606,6 +607,10 @@ config DEFAULT_COMPRESSION_LZ4
bool "lz4"
depends on LZ4_DECOMPRESS
config DEFAULT_COMPRESSION_XZ
bool "xz"
depends on XZ_DECOMPRESS
config DEFAULT_COMPRESSION_NONE
bool "no compression"

4
common/filetype.c
View File

@ -58,6 +58,7 @@ static const struct filetype_str filetype_str[] = {
[filetype_ch_image] = { "TI OMAP CH boot image", "ch-image" },
[filetype_ch_image_be] = {
"TI OMAP CH boot image (big endian)", "ch-image-be" },
[filetype_xz_compressed] = { "XZ compressed", "xz" },
[filetype_exe] = { "MS-DOS executable", "exe" },
};
@ -272,6 +273,9 @@ enum filetype file_detect_type(const void *_buf, size_t bufsize)
if (buf8[0] == 'B' && buf8[1] == 'Z' && buf8[2] == 'h' &&
buf8[3] > '0' && buf8[3] <= '9')
return filetype_bzip2;
if (buf8[0] == 0xfd && buf8[1] == 0x37 && buf8[2] == 0x7a &&
buf8[3] == 0x58 && buf8[4] == 0x5a && buf8[5] == 0x00)
return filetype_xz_compressed;
if (buf[0] == be32_to_cpu(0xd00dfeed))
return filetype_oftree;
if (strncmp(buf8, "ANDROID!", 8) == 0)

1
images/Makefile
View File

@ -82,6 +82,7 @@ $(obj)/%.s: $(obj)/% FORCE
suffix_$(CONFIG_IMAGE_COMPRESSION_GZIP) = gzip
suffix_$(CONFIG_IMAGE_COMPRESSION_LZO) = lzo
suffix_$(CONFIG_IMAGE_COMPRESSION_LZ4) = lz4
suffix_$(CONFIG_IMAGE_COMPRESSION_XZKERN) = xzkern
suffix_$(CONFIG_IMAGE_COMPRESSION_NONE) = shipped
# barebox.z - compressed barebox binary

1
include/filetype.h
View File

@ -33,6 +33,7 @@ enum filetype {
filetype_ch_image,
filetype_ch_image_be,
filetype_exe,
filetype_xz_compressed,
filetype_max,
};

271
include/linux/xz.h Normal file
View File

@ -0,0 +1,271 @@
/*
* 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
/* In Linux, this is used to make extern functions static when needed. */
#ifndef XZ_EXTERN
# define XZ_EXTERN extern
#endif
#ifndef STATIC
#define STATIC
#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
# define XZ_INTERNAL_CRC32 1
#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
STATIC int decompress_unxz(unsigned char *in, long in_size,
long (*fill)(void *dest, unsigned long size),
long (*flush)(void *src, unsigned long size),
unsigned char *out, long *in_used,
void (*error)(char *x));
#endif

4
lib/Kconfig
View File

@ -18,6 +18,10 @@ config LZ4_DECOMPRESS
bool "include lz4 uncompression support"
select UNCOMPRESS
config XZ_DECOMPRESS
bool "include xz uncompression support"
select UNCOMPRESS
config GENERIC_FIND_NEXT_BIT
def_bool n

1
lib/Makefile
View File

@ -20,6 +20,7 @@ obj-y += make_directory.o
obj-y += math.o
obj-$(CONFIG_BZLIB) += decompress_bunzip2.o
obj-$(CONFIG_ZLIB) += decompress_inflate.o zlib_inflate/
obj-$(CONFIG_XZ_DECOMPRESS) += decompress_unxz.o xz/
obj-$(CONFIG_CMDLINE_EDITING) += readline.o
obj-$(CONFIG_SIMPLE_READLINE) += readline_simple.o
obj-$(CONFIG_GLOB) += fnmatch.o

376
lib/decompress_unxz.c Normal file
View File

@ -0,0 +1,376 @@
/*
* Wrapper for decompressing XZ-compressed kernel, initramfs, and initrd
*
* 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.
*/
/*
* Important notes about in-place decompression
*
* At least on x86, the kernel is decompressed in place: the compressed data
* is placed to the end of the output buffer, and the decompressor overwrites
* most of the compressed data. There must be enough safety margin to
* guarantee that the write position is always behind the read position.
*
* The safety margin for XZ with LZMA2 or BCJ+LZMA2 is calculated below.
* Note that the margin with XZ is bigger than with Deflate (gzip)!
*
* The worst case for in-place decompression is that the beginning of
* the file is compressed extremely well, and the rest of the file is
* uncompressible. Thus, we must look for worst-case expansion when the
* compressor is encoding uncompressible data.
*
* The structure of the .xz file in case of a compresed kernel is as follows.
* Sizes (as bytes) of the fields are in parenthesis.
*
* Stream Header (12)
* Block Header:
* Block Header (8-12)
* Compressed Data (N)
* Block Padding (0-3)
* CRC32 (4)
* Index (8-20)
* Stream Footer (12)
*
* Normally there is exactly one Block, but let's assume that there are
* 2-4 Blocks just in case. Because Stream Header and also Block Header
* of the first Block don't make the decompressor produce any uncompressed
* data, we can ignore them from our calculations. Block Headers of possible
* additional Blocks have to be taken into account still. With these
* assumptions, it is safe to assume that the total header overhead is
* less than 128 bytes.
*
* Compressed Data contains LZMA2 or BCJ+LZMA2 encoded data. Since BCJ
* doesn't change the size of the data, it is enough to calculate the
* safety margin for LZMA2.
*
* LZMA2 stores the data in chunks. Each chunk has a header whose size is
* a maximum of 6 bytes, but to get round 2^n numbers, let's assume that
* the maximum chunk header size is 8 bytes. After the chunk header, there
* may be up to 64 KiB of actual payload in the chunk. Often the payload is
* quite a bit smaller though; to be safe, let's assume that an average
* chunk has only 32 KiB of payload.
*
* The maximum uncompressed size of the payload is 2 MiB. The minimum
* uncompressed size of the payload is in practice never less than the
* payload size itself. The LZMA2 format would allow uncompressed size
* to be less than the payload size, but no sane compressor creates such
* files. LZMA2 supports storing uncompressible data in uncompressed form,
* so there's never a need to create payloads whose uncompressed size is
* smaller than the compressed size.
*
* The assumption, that the uncompressed size of the payload is never
* smaller than the payload itself, is valid only when talking about
* the payload as a whole. It is possible that the payload has parts where
* the decompressor consumes more input than it produces output. Calculating
* the worst case for this would be tricky. Instead of trying to do that,
* let's simply make sure that the decompressor never overwrites any bytes
* of the payload which it is currently reading.
*
* Now we have enough information to calculate the safety margin. We need
* - 128 bytes for the .xz file format headers;
* - 8 bytes per every 32 KiB of uncompressed size (one LZMA2 chunk header
* per chunk, each chunk having average payload size of 32 KiB); and
* - 64 KiB (biggest possible LZMA2 chunk payload size) to make sure that
* the decompressor never overwrites anything from the LZMA2 chunk
* payload it is currently reading.
*
* We get the following formula:
*
* safety_margin = 128 + uncompressed_size * 8 / 32768 + 65536
* = 128 + (uncompressed_size >> 12) + 65536
*
* For comparison, according to arch/x86/boot/compressed/misc.c, the
* equivalent formula for Deflate is this:
*
* safety_margin = 18 + (uncompressed_size >> 12) + 32768
*
* Thus, when updating Deflate-only in-place kernel decompressor to
* support XZ, the fixed overhead has to be increased from 18+32768 bytes
* to 128+65536 bytes.
*/
/*
* STATIC is defined to "static" if we are being built for kernel
* decompression (pre-boot code). <linux/decompress/mm.h> will define
* STATIC to empty if it wasn't already defined. Since we will need to
* know later if we are being used for kernel decompression, we define
* XZ_PREBOOT here.
*/
#ifdef STATIC
# define XZ_PREBOOT
#endif
#ifdef __KERNEL__
# include <linux/decompress/mm.h>
#endif
#define XZ_EXTERN STATIC
#ifndef XZ_PREBOOT
# include <malloc.h>
# include <linux/xz.h>
#else
/*
* Use the internal CRC32 code instead of kernel's CRC32 module, which
* is not available in early phase of booting.
*/
#define XZ_INTERNAL_CRC32 1
/*
* For boot time use, we enable only the BCJ filter of the current
* architecture or none if no BCJ filter is available for the architecture.
*/
#ifdef CONFIG_X86
# define XZ_DEC_X86
#endif
#ifdef CONFIG_PPC
# define XZ_DEC_POWERPC
#endif
#ifdef CONFIG_ARM
# define XZ_DEC_ARM
#endif
#ifdef CONFIG_IA64
# define XZ_DEC_IA64
#endif
#ifdef CONFIG_SPARC
# define XZ_DEC_SPARC
#endif
/*
* This will get the basic headers so that memeq() and others
* can be defined.
*/
#include "xz/xz_private.h"
/*
* Replace the normal allocation functions with the versions from
* <linux/decompress/mm.h>. vfree() needs to support vfree(NULL)
* when XZ_DYNALLOC is used, but the pre-boot free() doesn't support it.
* Workaround it here because the other decompressors don't need it.
*/
#undef kmalloc
#undef kfree
#undef vmalloc
#undef vfree
#define kmalloc(size, flags) malloc(size)
#define kfree(ptr) free(ptr)
#define vmalloc(size) malloc(size)
#define vfree(ptr) do { if (ptr != NULL) free(ptr); } while (0)
/*
* FIXME: Not all basic memory functions are provided in architecture-specific
* files (yet). We define our own versions here for now, but this should be
* only a temporary solution.
*
* memeq and memzero are not used much and any remotely sane implementation
* is fast enough. memcpy/memmove speed matters in multi-call mode, but
* the kernel image is decompressed in single-call mode, in which only
* memcpy speed can matter and only if there is a lot of uncompressible data
* (LZMA2 stores uncompressible chunks in uncompressed form). Thus, the
* functions below should just be kept small; it's probably not worth
* optimizing for speed.
*/
#ifndef memeq
static bool memeq(const void *a, const void *b, size_t size)
{
const uint8_t *x = a;
const uint8_t *y = b;
size_t i;
for (i = 0; i < size; ++i)
if (x[i] != y[i])
return false;
return true;
}
#endif
#ifndef memzero
static void memzero(void *buf, size_t size)
{
uint8_t *b = buf;
uint8_t *e = b + size;
while (b != e)
*b++ = '\0';
}
#endif
/*
* Since we need memmove anyway, would use it as memcpy too.
* Commented out for now to avoid breaking things.
*/
/*
#ifndef memcpy
# define memcpy memmove
#endif
*/
#include "xz/xz_crc32.c"
#include "xz/xz_dec_stream.c"
#include "xz/xz_dec_lzma2.c"
#include "xz/xz_dec_bcj.c"
#endif /* XZ_PREBOOT */
/* Size of the input and output buffers in multi-call mode */
#define XZ_IOBUF_SIZE 4096
/*
* This function implements the API defined in <linux/decompress/generic.h>.
*
* This wrapper will automatically choose single-call or multi-call mode
* of the native XZ decoder API. The single-call mode can be used only when
* both input and output buffers are available as a single chunk, i.e. when
* fill() and flush() won't be used.
*/
STATIC int decompress_unxz(unsigned char *in, long in_size,
long (*fill)(void *dest, unsigned long size),
long (*flush)(void *src, unsigned long size),
unsigned char *out, long *in_used,
void (*error)(char *x))
{
struct xz_buf b;
struct xz_dec *s;
enum xz_ret ret;
bool must_free_in = false;
#if XZ_INTERNAL_CRC32
xz_crc32_init();
#endif
if (in_used != NULL)
*in_used = 0;
if (fill == NULL && flush == NULL)
s = xz_dec_init(XZ_SINGLE, 0);
else
s = xz_dec_init(XZ_DYNALLOC, (uint32_t)-1);
if (s == NULL)
goto error_alloc_state;
if (flush == NULL) {
b.out = out;
b.out_size = (size_t)-1;
} else {
b.out_size = XZ_IOBUF_SIZE;
b.out = malloc(XZ_IOBUF_SIZE);
if (b.out == NULL)
goto error_alloc_out;
}
if (in == NULL) {
must_free_in = true;
in = malloc(XZ_IOBUF_SIZE);
if (in == NULL)
goto error_alloc_in;
}
b.in = in;
b.in_pos = 0;
b.in_size = in_size;
b.out_pos = 0;
if (fill == NULL && flush == NULL) {
ret = xz_dec_run(s, &b);
} else {
do {
if (b.in_pos == b.in_size && fill != NULL) {
if (in_used != NULL)
*in_used += b.in_pos;
b.in_pos = 0;
in_size = fill(in, XZ_IOBUF_SIZE);
if (in_size < 0) {
/*
* This isn't an optimal error code
* but it probably isn't worth making
* a new one either.
*/
ret = XZ_BUF_ERROR;
break;
}
b.in_size = in_size;
}
ret = xz_dec_run(s, &b);
if (flush != NULL && (b.out_pos == b.out_size
|| (ret != XZ_OK && b.out_pos > 0))) {
/*
* Setting ret here may hide an error
* returned by xz_dec_run(), but probably
* it's not too bad.
*/
if (flush(b.out, b.out_pos) != (long)b.out_pos)
ret = XZ_BUF_ERROR;
b.out_pos = 0;
}
} while (ret == XZ_OK);
if (must_free_in)
free(in);
if (flush != NULL)
free(b.out);
}
if (in_used != NULL)
*in_used += b.in_pos;
xz_dec_end(s);
switch (ret) {
case XZ_STREAM_END:
return 0;
case XZ_MEM_ERROR:
/* This can occur only in multi-call mode. */
error("XZ decompressor ran out of memory");
break;
case XZ_FORMAT_ERROR:
error("Input is not in the XZ format (wrong magic bytes)");
break;
case XZ_OPTIONS_ERROR:
error("Input was encoded with settings that are not "
"supported by this XZ decoder");
break;
case XZ_DATA_ERROR:
case XZ_BUF_ERROR:
error("XZ-compressed data is corrupt");
break;
default:
error("Bug in the XZ decompressor");
break;
}
return -1;
error_alloc_in:
if (flush != NULL)
free(b.out);
error_alloc_out:
xz_dec_end(s);
error_alloc_state:
error("XZ decompressor ran out of memory");
return -1;
}
/*
* This macro is used by architecture-specific files to decompress
* the kernel image.
*/
#define decompress decompress_unxz

6
lib/uncompress.c
View File

@ -21,6 +21,7 @@
#include <bunzip2.h>
#include <gunzip.h>
#include <lzo.h>
#include <linux/xz.h>
#include <linux/decompress/unlz4.h>
#include <errno.h>
#include <filetype.h>
@ -117,6 +118,11 @@ int uncompress(unsigned char *inbuf, int len,
case filetype_lz4_compressed:
compfn = decompress_unlz4;
break;
#endif
#ifdef CONFIG_XZ_DECOMPRESS
case filetype_xz_compressed:
compfn = decompress_unxz;
break;
#endif
default:
err = asprintf("cannot handle filetype %s", file_type_to_string(ft));

2
lib/xz/Makefile Normal file
View File

@ -0,0 +1,2 @@
obj-$(CONFIG_XZ_DECOMPRESS) += xz_crc32.o xz_dec_bcj.o
obj-$(CONFIG_XZ_DECOMPRESS) += xz_dec_lzma2.o xz_dec_stream.o

59
lib/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;
}

574
lib/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
lib/xz/xz_dec_lzma2.c Normal file
View File

File diff suppressed because it is too large Load Diff

821
lib/xz/xz_dec_stream.c Normal file
View File

@ -0,0 +1,821 @@
/*
* .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"
/* 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;
/* CRC32 value in Block or Index */
uint32_t crc32;
/* 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 if presence of the CRC32
* field was indicated in Stream Header.
*
* Once the decoding is finished, validate that the observed sizes match
* the sizes possibly stored in the Block Header. Update the hash and
* Block count, which are later used to validate the Index field.
*/
static enum xz_ret dec_block(struct xz_dec *s, struct xz_buf *b)
{
enum xz_ret ret;
s->in_start = b->in_pos;
s->out_start = b->out_pos;
#ifdef XZ_DEC_BCJ
if (s->bcj_active)
ret = xz_dec_bcj_run(s->bcj, s->lzma2, b);
else
#endif
ret = xz_dec_lzma2_run(s->lzma2, b);
s->block.compressed += b->in_pos - s->in_start;
s->block.uncompressed += b->out_pos - s->out_start;
/*
* There is no need to separately check for VLI_UNKNOWN, since
* the observed sizes are always smaller than VLI_UNKNOWN.
*/
if (s->block.compressed > s->block_header.compressed
|| s->block.uncompressed
> s->block_header.uncompressed)
return XZ_DATA_ERROR;
if (s->check_type == XZ_CHECK_CRC32)
s->crc32 = xz_crc32(b->out + s->out_start,
b->out_pos - s->out_start, s->crc32);
if (ret == XZ_STREAM_END) {
if (s->block_header.compressed != VLI_UNKNOWN
&& s->block_header.compressed
!= s->block.compressed)
return XZ_DATA_ERROR;
if (s->block_header.uncompressed != VLI_UNKNOWN
&& s->block_header.uncompressed
!= s->block.uncompressed)
return XZ_DATA_ERROR;
s->block.hash.unpadded += s->block_header.size
+ s->block.compressed;
#ifdef XZ_DEC_ANY_CHECK
s->block.hash.unpadded += check_sizes[s->check_type];
#else
if (s->check_type == XZ_CHECK_CRC32)
s->block.hash.unpadded += 4;
#endif
s->block.hash.uncompressed += s->block.uncompressed;
s->block.hash.crc32 = xz_crc32(
(const uint8_t *)&s->block.hash,
sizeof(s->block.hash), s->block.hash.crc32);
++s->block.count;
}
return ret;
}
/* Update the Index size and the CRC32 value. */
static void index_update(struct xz_dec *s, const struct xz_buf *b)
{
size_t in_used = b->in_pos - s->in_start;
s->index.size += in_used;
s->crc32 = xz_crc32(b->in + s->in_start, in_used, s->crc32);
}
/*
* Decode the Number of Records, Unpadded Size, and Uncompressed Size
* fields from the Index field. That is, Index Padding and CRC32 are not
* decoded by this function.
*
* This can return XZ_OK (more input needed), XZ_STREAM_END (everything
* successfully decoded), or XZ_DATA_ERROR (input is corrupt).
*/
static enum xz_ret dec_index(struct xz_dec *s, struct xz_buf *b)
{
enum xz_ret ret;
do {
ret = dec_vli(s, b->in, &b->in_pos, b->in_size);
if (ret != XZ_STREAM_END) {
index_update(s, b);
return ret;
}
switch (s->index.sequence) {
case SEQ_INDEX_COUNT:
s->index.count = s->vli;
/*
* Validate that the Number of Records field
* indicates the same number of Records as
* there were Blocks in the Stream.
*/
if (s->index.count != s->block.count)
return XZ_DATA_ERROR;
s->index.sequence = SEQ_INDEX_UNPADDED;
break;
case SEQ_INDEX_UNPADDED:
s->index.hash.unpadded += s->vli;
s->index.sequence = SEQ_INDEX_UNCOMPRESSED;
break;
case SEQ_INDEX_UNCOMPRESSED:
s->index.hash.uncompressed += s->vli;
s->index.hash.crc32 = xz_crc32(
(const uint8_t *)&s->index.hash,
sizeof(s->index.hash),
s->index.hash.crc32);
--s->index.count;
s->index.sequence = SEQ_INDEX_UNPADDED;
break;
}
} while (s->index.count > 0);
return XZ_STREAM_END;
}
/*
* Validate that the next four input bytes match the value of s->crc32.
* s->pos must be zero when starting to validate the first byte.
*/
static enum xz_ret crc32_validate(struct xz_dec *s, struct xz_buf *b)
{
do {
if (b->in_pos == b->in_size)
return XZ_OK;
if (((s->crc32 >> s->pos) & 0xFF) != b->in[b->in_pos++])
return XZ_DATA_ERROR;
s->pos += 8;
} while (s->pos < 32);
s->crc32 = 0;
s->pos = 0;
return XZ_STREAM_END;
}
#ifdef XZ_DEC_ANY_CHECK
/*
* Skip over the Check field when the Check ID is not supported.
* Returns true once the whole Check field has been skipped over.
*/
static bool check_skip(struct xz_dec *s, struct xz_buf *b)
{
while (s->pos < check_sizes[s->check_type]) {
if (b->in_pos == b->in_size)
return false;
++b->in_pos;
++s->pos;
}
s->pos = 0;
return true;
}
#endif
/* Decode the Stream Header field (the first 12 bytes of the .xz Stream). */
static enum xz_ret dec_stream_header(struct xz_dec *s)
{
if (!memeq(s->temp.buf, HEADER_MAGIC, HEADER_MAGIC_SIZE))
return XZ_FORMAT_ERROR;
if (xz_crc32(s->temp.buf + HEADER_MAGIC_SIZE, 2, 0)
!= get_le32(s->temp.buf + HEADER_MAGIC_SIZE + 2))
return XZ_DATA_ERROR;
if (s->temp.buf[HEADER_MAGIC_SIZE] != 0)
return XZ_OPTIONS_ERROR;
/*
* Of integrity checks, we support only none (Check ID = 0) and
* CRC32 (Check ID = 1). However, if XZ_DEC_ANY_CHECK is defined,
* we will accept other check types too, but then the check won't
* be verified and a warning (XZ_UNSUPPORTED_CHECK) will be given.
*/
s->check_type = s->temp.buf[HEADER_MAGIC_SIZE + 1];
#ifdef XZ_DEC_ANY_CHECK
if (s->check_type > XZ_CHECK_MAX)
return XZ_OPTIONS_ERROR;
if (s->check_type > XZ_CHECK_CRC32)
return XZ_UNSUPPORTED_CHECK;
#else
if (s->check_type > XZ_CHECK_CRC32)
return XZ_OPTIONS_ERROR;
#endif
return XZ_OK;
}
/* Decode the Stream Footer field (the last 12 bytes of the .xz Stream) */
static enum xz_ret dec_stream_footer(struct xz_dec *s)
{
if (!memeq(s->temp.buf + 10, FOOTER_MAGIC, FOOTER_MAGIC_SIZE))
return XZ_DATA_ERROR;
if (xz_crc32(s->temp.buf + 4, 6, 0) != get_le32(s->temp.buf))
return XZ_DATA_ERROR;
/*
* Validate Backward Size. Note that we never added the size of the
* Index CRC32 field to s->index.size, thus we use s->index.size / 4
* instead of s->index.size / 4 - 1.
*/
if ((s->index.size >> 2) != get_le32(s->temp.buf + 4))
return XZ_DATA_ERROR;
if (s->temp.buf[8] != 0 || s->temp.buf[9] != s->check_type)
return XZ_DATA_ERROR;
/*
* Use XZ_STREAM_END instead of XZ_OK to be more convenient
* for the caller.
*/
return XZ_STREAM_END;
}
/* Decode the Block Header and initialize the filter chain. */
static enum xz_ret dec_block_header(struct xz_dec *s)
{
enum xz_ret ret;
/*
* Validate the CRC32. We know that the temp buffer is at least
* eight bytes so this is safe.
*/
s->temp.size -= 4;
if (xz_crc32(s->temp.buf, s->temp.size, 0)
!= get_le32(s->temp.buf + s->temp.size))
return XZ_DATA_ERROR;
s->temp.pos = 2;
/*
* Catch unsupported Block Flags. We support only one or two filters
* in the chain, so we catch that with the same test.
*/
#ifdef XZ_DEC_BCJ
if (s->temp.buf[1] & 0x3E)
#else
if (s->temp.buf[1] & 0x3F)
#endif
return XZ_OPTIONS_ERROR;
/* Compressed Size */
if (s->temp.buf[1] & 0x40) {
if (dec_vli(s, s->temp.buf, &s->temp.pos, s->temp.size)
!= XZ_STREAM_END)
return XZ_DATA_ERROR;
s->block_header.compressed = s->vli;
} else {
s->block_header.compressed = VLI_UNKNOWN;
}
/* Uncompressed Size */
if (s->temp.buf[1] & 0x80) {
if (dec_vli(s, s->temp.buf, &s->temp.pos, s->temp.size)
!= XZ_STREAM_END)
return XZ_DATA_ERROR;
s->block_header.uncompressed = s->vli;
} else {
s->block_header.uncompressed = VLI_UNKNOWN;
}
#ifdef XZ_DEC_BCJ
/* If there are two filters, the first one must be a BCJ filter. */
s->bcj_active = s->temp.buf[1] & 0x01;
if (s->bcj_active) {
if (s->temp.size - s->temp.pos < 2)
return XZ_OPTIONS_ERROR;
ret = xz_dec_bcj_reset(s->bcj, s->temp.buf[s->temp.pos++]);
if (ret != XZ_OK)
return ret;
/*
* We don't support custom start offset,
* so Size of Properties must be zero.
*/
if (s->temp.buf[s->temp.pos++] != 0x00)
return XZ_OPTIONS_ERROR;
}
#endif
/* Valid Filter Flags always take at least two bytes. */
if (s->temp.size - s->temp.pos < 2)
return XZ_DATA_ERROR;
/* Filter ID = LZMA2 */
if (s->temp.buf[s->temp.pos++] != 0x21)
return XZ_OPTIONS_ERROR;
/* Size of Properties = 1-byte Filter Properties */
if (s->temp.buf[s->temp.pos++] != 0x01)
return XZ_OPTIONS_ERROR;
/* Filter Properties contains LZMA2 dictionary size. */
if (s->temp.size - s->temp.pos < 1)
return XZ_DATA_ERROR;
ret = xz_dec_lzma2_reset(s->lzma2, s->temp.buf[s->temp.pos++]);
if (ret != XZ_OK)
return ret;
/* The rest must be Header Padding. */
while (s->temp.pos < s->temp.size)
if (s->temp.buf[s->temp.pos++] != 0x00)
return XZ_OPTIONS_ERROR;
s->temp.pos = 0;
s->block.compressed = 0;
s->block.uncompressed = 0;
return XZ_OK;
}
static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b)
{
enum xz_ret ret;
/*
* Store the start position for the case when we are in the middle
* of the Index field.
*/
s->in_start = b->in_pos;
while (true) {
switch (s->sequence) {
case SEQ_STREAM_HEADER:
/*
* Stream Header is copied to s->temp, and then
* decoded from there. This way if the caller
* gives us only little input at a time, we can
* still keep the Stream Header decoding code
* simple. Similar approach is used in many places
* in this file.
*/
if (!fill_temp(s, b))
return XZ_OK;
/*
* If dec_stream_header() returns
* XZ_UNSUPPORTED_CHECK, it is still possible
* to continue decoding if working in multi-call
* mode. Thus, update s->sequence before calling
* dec_stream_header().
*/
s->sequence = SEQ_BLOCK_START;
ret = dec_stream_header(s);
if (ret != XZ_OK)
return ret;
case SEQ_BLOCK_START:
/* We need one byte of input to continue. */
if (b->in_pos == b->in_size)
return XZ_OK;
/* See if this is the beginning of the Index field. */
if (b->in[b->in_pos] == 0) {
s->in_start = b->in_pos++;
s->sequence = SEQ_INDEX;
break;
}
/*
* Calculate the size of the Block Header and
* prepare to decode it.
*/
s->block_header.size
= ((uint32_t)b->in[b->in_pos] + 1) * 4;
s->temp.size = s->block_header.size;
s->temp.pos = 0;
s->sequence = SEQ_BLOCK_HEADER;
case SEQ_BLOCK_HEADER:
if (!fill_temp(s, b))
return XZ_OK;
ret = dec_block_header(s);
if (ret != XZ_OK)
return ret;
s->sequence = SEQ_BLOCK_UNCOMPRESS;
case SEQ_BLOCK_UNCOMPRESS:
ret = dec_block(s, b);
if (ret != XZ_STREAM_END)
return ret;
s->sequence = SEQ_BLOCK_PADDING;
case SEQ_BLOCK_PADDING:
/*
* Size of Compressed Data + Block Padding
* must be a multiple of four. We don't need
* s->block.compressed for anything else
* anymore, so we use it here to test the size
* of the Block Padding field.
*/
while (s->block.compressed & 3) {
if (b->in_pos == b->in_size)
return XZ_OK;
if (b->in[b->in_pos++] != 0)
return XZ_DATA_ERROR;
++s->block.compressed;
}
s->sequence = SEQ_BLOCK_CHECK;
case SEQ_BLOCK_CHECK:
if (s->check_type == XZ_CHECK_CRC32) {
ret = crc32_validate(s, b);
if (ret != XZ_STREAM_END)
return ret;
}
#ifdef XZ_DEC_ANY_CHECK
else if (!check_skip(s, b)) {
return XZ_OK;
}
#endif
s->sequence = SEQ_BLOCK_START;
break;
case SEQ_INDEX:
ret = dec_index(s, b);
if (ret != XZ_STREAM_END)
return ret;
s->sequence = SEQ_INDEX_PADDING;
case SEQ_INDEX_PADDING:
while ((s->index.size + (b->in_pos - s->in_start))
& 3) {
if (b->in_pos == b->in_size) {
index_update(s, b);
return XZ_OK;
}
if (b->in[b->in_pos++] != 0)
return XZ_DATA_ERROR;
}
/* Finish the CRC32 value and Index size. */
index_update(s, b);
/* Compare the hashes to validate the Index field. */
if (!memeq(&s->block.hash, &s->index.hash,
sizeof(s->block.hash)))
return XZ_DATA_ERROR;
s->sequence = SEQ_INDEX_CRC32;
case SEQ_INDEX_CRC32:
ret = crc32_validate(s, b);
if (ret != XZ_STREAM_END)
return ret;
s->temp.size = STREAM_HEADER_SIZE;
s->sequence = SEQ_STREAM_FOOTER;
case SEQ_STREAM_FOOTER:
if (!fill_temp(s, b))
return XZ_OK;
return dec_stream_footer(s);
}
}
/* Never reached */
}
/*
* xz_dec_run() is a wrapper for dec_main() to handle some special cases in
* multi-call and single-call decoding.
*
* In multi-call mode, we must return XZ_BUF_ERROR when it seems clear that we
* are not going to make any progress anymore. This is to prevent the caller
* from calling us infinitely when the input file is truncated or otherwise
* corrupt. Since zlib-style API allows that the caller fills the input buffer
* only when the decoder doesn't produce any new output, we have to be careful
* to avoid returning XZ_BUF_ERROR too easily: XZ_BUF_ERROR is returned only
* after the second consecutive call to xz_dec_run() that makes no progress.
*
* In single-call mode, if we couldn't decode everything and no error
* occurred, either the input is truncated or the output buffer is too small.
* Since we know that the last input byte never produces any output, we know
* that if all the input was consumed and decoding wasn't finished, the file
* must be corrupt. Otherwise the output buffer has to be too small or the
* file is corrupt in a way that decoding it produces too big output.
*
* If single-call decoding fails, we reset b->in_pos and b->out_pos back to
* their original values. This is because with some filter chains there won't
* be any valid uncompressed data in the output buffer unless the decoding
* actually succeeds (that's the price to pay of using the output buffer as
* the workspace).
*/
XZ_EXTERN enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b)
{
size_t in_start;
size_t out_start;
enum xz_ret ret;
if (DEC_IS_SINGLE(s->mode))
xz_dec_reset(s);
in_start = b->in_pos;
out_start = b->out_pos;
ret = dec_main(s, b);
if (DEC_IS_SINGLE(s->mode)) {
if (ret == XZ_OK)
ret = b->in_pos == b->in_size
? XZ_DATA_ERROR : XZ_BUF_ERROR;
if (ret != XZ_STREAM_END) {
b->in_pos = in_start;
b->out_pos = out_start;
}
} else if (ret == XZ_OK && in_start == b->in_pos
&& out_start == b->out_pos) {
if (s->allow_buf_error)
ret = XZ_BUF_ERROR;
s->allow_buf_error = true;
} else {
s->allow_buf_error = false;
}
return ret;
}
XZ_EXTERN struct xz_dec *xz_dec_init(enum xz_mode mode, uint32_t dict_max)
{
struct xz_dec *s = kmalloc(sizeof(*s), GFP_KERNEL);
if (s == NULL)
return NULL;
s->mode = mode;
#ifdef XZ_DEC_BCJ
s->bcj = xz_dec_bcj_create(DEC_IS_SINGLE(mode));
if (s->bcj == NULL)
goto error_bcj;
#endif
s->lzma2 = xz_dec_lzma2_create(mode, dict_max);
if (s->lzma2 == NULL)
goto error_lzma2;
xz_dec_reset(s);
return s;
error_lzma2:
#ifdef XZ_DEC_BCJ
xz_dec_bcj_end(s->bcj);
error_bcj:
#endif
kfree(s);
return NULL;
}
XZ_EXTERN void xz_dec_reset(struct xz_dec *s)
{
s->sequence = SEQ_STREAM_HEADER;
s->allow_buf_error = false;
s->pos = 0;
s->crc32 = 0;
memzero(&s->block, sizeof(s->block));
memzero(&s->index, sizeof(s->index));
s->temp.pos = 0;
s->temp.size = STREAM_HEADER_SIZE;
}
XZ_EXTERN void xz_dec_end(struct xz_dec *s)
{
if (s != NULL) {
xz_dec_lzma2_end(s->lzma2);
#ifdef XZ_DEC_BCJ
xz_dec_bcj_end(s->bcj);
#endif
kfree(s);
}
}

204
lib/xz/xz_lzma2.h Normal file
View File

@ -0,0 +1,204 @@
/*
* LZMA2 definitions
*
* 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_LZMA2_H
#define XZ_LZMA2_H
/* Range coder constants */
#define RC_SHIFT_BITS 8
#define RC_TOP_BITS 24
#define RC_TOP_VALUE (1 << RC_TOP_BITS)
#define RC_BIT_MODEL_TOTAL_BITS 11
#define RC_BIT_MODEL_TOTAL (1 << RC_BIT_MODEL_TOTAL_BITS)
#define RC_MOVE_BITS 5
/*
* Maximum number of position states. A position state is the lowest pb
* number of bits of the current uncompressed offset. In some places there
* are different sets of probabilities for different position states.
*/
#define POS_STATES_MAX (1 << 4)
/*
* This enum is used to track which LZMA symbols have occurred most recently
* and in which order. This information is used to predict the next symbol.
*
* Symbols:
* - Literal: One 8-bit byte
* - Match: Repeat a chunk of data at some distance
* - Long repeat: Multi-byte match at a recently seen distance
* - Short repeat: One-byte repeat at a recently seen distance
*
* The symbol names are in from STATE_oldest_older_previous. REP means
* either short or long repeated match, and NONLIT means any non-literal.
*/
enum lzma_state {
STATE_LIT_LIT,
STATE_MATCH_LIT_LIT,
STATE_REP_LIT_LIT,
STATE_SHORTREP_LIT_LIT,
STATE_MATCH_LIT,
STATE_REP_LIT,
STATE_SHORTREP_LIT,
STATE_LIT_MATCH,
STATE_LIT_LONGREP,
STATE_LIT_SHORTREP,
STATE_NONLIT_MATCH,
STATE_NONLIT_REP
};
/* Total number of states */
#define STATES 12
/* The lowest 7 states indicate that the previous state was a literal. */
#define LIT_STATES 7
/* Indicate that the latest symbol was a literal. */
static inline void lzma_state_literal(enum lzma_state *state)
{
if (*state <= STATE_SHORTREP_LIT_LIT)
*state = STATE_LIT_LIT;
else if (*state <= STATE_LIT_SHORTREP)
*state -= 3;
else
*state -= 6;
}
/* Indicate that the latest symbol was a match. */
static inline void lzma_state_match(enum lzma_state *state)
{
*state = *state < LIT_STATES ? STATE_LIT_MATCH : STATE_NONLIT_MATCH;
}
/* Indicate that the latest state was a long repeated match. */
static inline void lzma_state_long_rep(enum lzma_state *state)
{
*state = *state < LIT_STATES ? STATE_LIT_LONGREP : STATE_NONLIT_REP;
}
/* Indicate that the latest symbol was a short match. */
static inline void lzma_state_short_rep(enum lzma_state *state)
{
*state = *state < LIT_STATES ? STATE_LIT_SHORTREP : STATE_NONLIT_REP;
}
/* Test if the previous symbol was a literal. */
static inline bool lzma_state_is_literal(enum lzma_state state)
{
return state < LIT_STATES;
}
/* Each literal coder is divided in three sections:
* - 0x001-0x0FF: Without match byte
* - 0x101-0x1FF: With match byte; match bit is 0
* - 0x201-0x2FF: With match byte; match bit is 1
*
* Match byte is used when the previous LZMA symbol was something else than
* a literal (that is, it was some kind of match).
*/
#define LITERAL_CODER_SIZE 0x300
/* Maximum number of literal coders */
#define LITERAL_CODERS_MAX (1 << 4)
/* Minimum length of a match is two bytes. */
#define MATCH_LEN_MIN 2
/* Match length is encoded with 4, 5, or 10 bits.
*
* Length Bits
* 2-9 4 = Choice=0 + 3 bits
* 10-17 5 = Choice=1 + Choice2=0 + 3 bits
* 18-273 10 = Choice=1 + Choice2=1 + 8 bits
*/
#define LEN_LOW_BITS 3
#define LEN_LOW_SYMBOLS (1 << LEN_LOW_BITS)
#define LEN_MID_BITS 3
#define LEN_MID_SYMBOLS (1 << LEN_MID_BITS)
#define LEN_HIGH_BITS 8
#define LEN_HIGH_SYMBOLS (1 << LEN_HIGH_BITS)
#define LEN_SYMBOLS (LEN_LOW_SYMBOLS + LEN_MID_SYMBOLS + LEN_HIGH_SYMBOLS)
/*
* Maximum length of a match is 273 which is a result of the encoding
* described above.
*/
#define MATCH_LEN_MAX (MATCH_LEN_MIN + LEN_SYMBOLS - 1)
/*
* Different sets of probabilities are used for match distances that have
* very short match length: Lengths of 2, 3, and 4 bytes have a separate
* set of probabilities for each length. The matches with longer length
* use a shared set of probabilities.
*/
#define DIST_STATES 4
/*
* Get the index of the appropriate probability array for decoding
* the distance slot.
*/
static inline uint32_t lzma_get_dist_state(uint32_t len)
{
return len < DIST_STATES + MATCH_LEN_MIN
? len - MATCH_LEN_MIN : DIST_STATES - 1;
}
/*
* The highest two bits of a 32-bit match distance are encoded using six bits.
* This six-bit value is called a distance slot. This way encoding a 32-bit
* value takes 6-36 bits, larger values taking more bits.
*/
#define DIST_SLOT_BITS 6
#define DIST_SLOTS (1 << DIST_SLOT_BITS)
/* Match distances up to 127 are fully encoded using probabilities. Since
* the highest two bits (distance slot) are always encoded using six bits,
* the distances 0-3 don't need any additional bits to encode, since the
* distance slot itself is the same as the actual distance. DIST_MODEL_START
* indicates the first distance slot where at least one additional bit is
* needed.
*/
#define DIST_MODEL_START 4
/*
* Match distances greater than 127 are encoded in three pieces:
* - distance slot: the highest two bits
* - direct bits: 2-26 bits below the highest two bits
* - alignment bits: four lowest bits
*
* Direct bits don't use any probabilities.
*
* The distance slot value of 14 is for distances 128-191.
*/
#define DIST_MODEL_END 14
/* Distance slots that indicate a distance <= 127. */
#define FULL_DISTANCES_BITS (DIST_MODEL_END / 2)
#define FULL_DISTANCES (1 << FULL_DISTANCES_BITS)
/*
* For match distances greater than 127, only the highest two bits and the
* lowest four bits (alignment) is encoded using probabilities.
*/
#define ALIGN_BITS 4
#define ALIGN_SIZE (1 << ALIGN_BITS)
#define ALIGN_MASK (ALIGN_SIZE - 1)
/* Total number of all probability variables */
#define PROBS_TOTAL (1846 + LITERAL_CODERS_MAX * LITERAL_CODER_SIZE)
/*
* LZMA remembers the four most recent match distances. Reusing these
* distances tends to take less space than re-encoding the actual
* distance value.
*/
#define REPS 4
#endif

156
lib/xz/xz_private.h Normal file
View File

@ -0,0 +1,156 @@
/*
* Private includes and definitions
*
* 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_PRIVATE_H
#define XZ_PRIVATE_H
#ifdef __KERNEL__
# include <linux/xz.h>
# include <linux/kernel.h>
# include <asm/unaligned.h>
/* XZ_PREBOOT may be defined only via decompress_unxz.c. */
# ifndef XZ_PREBOOT
# include <string.h>
# include <malloc.h>
# include <asm/byteorder.h>
# ifdef CONFIG_XZ_DEC_X86
# define XZ_DEC_X86
# endif
# ifdef CONFIG_XZ_DEC_POWERPC
# define XZ_DEC_POWERPC
# endif
# ifdef CONFIG_XZ_DEC_IA64
# define XZ_DEC_IA64
# endif
# ifdef CONFIG_XZ_DEC_ARM
# define XZ_DEC_ARM
# endif
# ifdef CONFIG_XZ_DEC_ARMTHUMB
# define XZ_DEC_ARMTHUMB
# endif
# ifdef CONFIG_XZ_DEC_SPARC
# define XZ_DEC_SPARC
# endif
# define memeq(a, b, size) (memcmp(a, b, size) == 0)
# define memzero(buf, size) memset(buf, 0, size)
# endif
# define get_le32(p) le32_to_cpup((const uint32_t *)(p))
#else
/*
* For userspace builds, use a separate header to define the required
* macros and functions. This makes it easier to adapt the code into
* different environments and avoids clutter in the Linux kernel tree.
*/
# include "xz_config.h"
#endif
/* If no specific decoding mode is requested, enable support for all modes. */
#if !defined(XZ_DEC_SINGLE) && !defined(XZ_DEC_PREALLOC) \
&& !defined(XZ_DEC_DYNALLOC)
# define XZ_DEC_SINGLE
# define XZ_DEC_PREALLOC
# define XZ_DEC_DYNALLOC
#endif
/*
* The DEC_IS_foo(mode) macros are used in "if" statements. If only some
* of the supported modes are enabled, these macros will evaluate to true or
* false at compile time and thus allow the compiler to omit unneeded code.
*/
#ifdef XZ_DEC_SINGLE
# define DEC_IS_SINGLE(mode) ((mode) == XZ_SINGLE)
#else
# define DEC_IS_SINGLE(mode) (false)
#endif
#ifdef XZ_DEC_PREALLOC
# define DEC_IS_PREALLOC(mode) ((mode) == XZ_PREALLOC)
#else
# define DEC_IS_PREALLOC(mode) (false)
#endif
#ifdef XZ_DEC_DYNALLOC
# define DEC_IS_DYNALLOC(mode) ((mode) == XZ_DYNALLOC)
#else
# define DEC_IS_DYNALLOC(mode) (false)
#endif
#if !defined(XZ_DEC_SINGLE)
# define DEC_IS_MULTI(mode) (true)
#elif defined(XZ_DEC_PREALLOC) || defined(XZ_DEC_DYNALLOC)
# define DEC_IS_MULTI(mode) ((mode) != XZ_SINGLE)
#else
# define DEC_IS_MULTI(mode) (false)
#endif
/*
* If any of the BCJ filter decoders are wanted, define XZ_DEC_BCJ.
* XZ_DEC_BCJ is used to enable generic support for BCJ decoders.
*/
#ifndef XZ_DEC_BCJ
# if defined(XZ_DEC_X86) || defined(XZ_DEC_POWERPC) \
|| defined(XZ_DEC_IA64) || defined(XZ_DEC_ARM) \
|| defined(XZ_DEC_ARM) || defined(XZ_DEC_ARMTHUMB) \
|| defined(XZ_DEC_SPARC)
# define XZ_DEC_BCJ
# endif
#endif
/*
* Allocate memory for LZMA2 decoder. xz_dec_lzma2_reset() must be used
* before calling xz_dec_lzma2_run().
*/
XZ_EXTERN struct xz_dec_lzma2 *xz_dec_lzma2_create(enum xz_mode mode,
uint32_t dict_max);
/*
* Decode the LZMA2 properties (one byte) and reset the decoder. Return
* XZ_OK on success, XZ_MEMLIMIT_ERROR if the preallocated dictionary is not
* big enough, and XZ_OPTIONS_ERROR if props indicates something that this
* decoder doesn't support.
*/
XZ_EXTERN enum xz_ret xz_dec_lzma2_reset(struct xz_dec_lzma2 *s,
uint8_t props);
/* Decode raw LZMA2 stream from b->in to b->out. */
XZ_EXTERN enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s,
struct xz_buf *b);
/* Free the memory allocated for the LZMA2 decoder. */
XZ_EXTERN void xz_dec_lzma2_end(struct xz_dec_lzma2 *s);
#ifdef XZ_DEC_BCJ
/*
* Allocate memory for BCJ decoders. xz_dec_bcj_reset() must be used before
* calling xz_dec_bcj_run().
*/
XZ_EXTERN struct xz_dec_bcj *xz_dec_bcj_create(bool single_call);
/*
* Decode the Filter ID of a BCJ filter. This implementation doesn't
* support custom start offsets, so no decoding of Filter Properties
* is needed. Returns XZ_OK if the given Filter ID is supported.
* Otherwise XZ_OPTIONS_ERROR is returned.
*/
XZ_EXTERN enum xz_ret xz_dec_bcj_reset(struct xz_dec_bcj *s, uint8_t id);
/*
* Decode raw BCJ + LZMA2 stream. This must be used only if there actually is
* a BCJ filter in the chain. If the chain has only LZMA2, xz_dec_lzma2_run()
* must be called directly.
*/
XZ_EXTERN enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s,
struct xz_dec_lzma2 *lzma2,
struct xz_buf *b);
/* Free the memory allocated for the BCJ filters. */
#define xz_dec_bcj_end(s) kfree(s)
#endif
#endif

61
lib/xz/xz_stream.h Normal file
View File

@ -0,0 +1,61 @@
/*
* Definitions for handling the .xz file format
*
* 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_STREAM_H
#define XZ_STREAM_H
#if defined(__KERNEL__) && !XZ_INTERNAL_CRC32
# undef crc32
# define xz_crc32(buf, size, crc) \
(~crc32_le(~(uint32_t)(crc), buf, size))
#endif
/*
* See the .xz file format specification at
* http://tukaani.org/xz/xz-file-format.txt
* to understand the container format.
*/
#define STREAM_HEADER_SIZE 12
#define HEADER_MAGIC "\3757zXZ"
#define HEADER_MAGIC_SIZE 6
#define FOOTER_MAGIC "YZ"
#define FOOTER_MAGIC_SIZE 2
/*
* Variable-length integer can hold a 63-bit unsigned integer or a special
* value indicating that the value is unknown.
*
* Experimental: vli_type can be defined to uint32_t to save a few bytes
* in code size (no effect on speed). Doing so limits the uncompressed and
* compressed size of the file to less than 256 MiB and may also weaken
* error detection slightly.
*/
typedef uint64_t vli_type;
#define VLI_MAX ((vli_type)-1 / 2)
#define VLI_UNKNOWN ((vli_type)-1)
/* Maximum encoded size of a VLI */
#define VLI_BYTES_MAX (sizeof(vli_type) * 8 / 7)
/* Integrity Check types */
enum xz_check {
XZ_CHECK_NONE = 0,
XZ_CHECK_CRC32 = 1,
XZ_CHECK_CRC64 = 4,
XZ_CHECK_SHA256 = 10
};
/* Maximum possible Check ID */
#define XZ_CHECK_MAX 15
#endif

3
pbl/Kconfig
View File

@ -64,6 +64,9 @@ config IMAGE_COMPRESSION_LZO
config IMAGE_COMPRESSION_GZIP
bool "gzip"
config IMAGE_COMPRESSION_XZKERN
bool "xz"
config IMAGE_COMPRESSION_NONE
bool "none"

4
pbl/decomp.c
View File

@ -22,6 +22,10 @@
#include "../../../lib/decompress_inflate.c"
#endif
#ifdef CONFIG_IMAGE_COMPRESSION_XZKERN
#include "../../../lib/decompress_unxz.c"
#endif
#ifdef CONFIG_IMAGE_COMPRESSION_NONE
STATIC int decompress(u8 *input, int in_len,
int (*fill) (void *, unsigned int),

31
scripts/Makefile.lib
View File

@ -205,6 +205,37 @@ cmd_gzip = (cat $(filter-out FORCE,$^) | gzip -n -f -9 > $@) || \
%.gz: %
$(call if_changed,gzip)
# XZ
# ---------------------------------------------------------------------------
# Use xzkern to compress the kernel image and xzmisc to compress other things.
#
# xzkern uses a big LZMA2 dictionary since it doesn't increase memory usage
# of the kernel decompressor. A BCJ filter is used if it is available for
# the target architecture. xzkern also appends uncompressed size of the data
# using size_append. The .xz format has the size information available at
# the end of the file too, but it's in more complex format and it's good to
# avoid changing the part of the boot code that reads the uncompressed size.
# Note that the bytes added by size_append will make the xz tool think that
# the file is corrupt. This is expected.
#
# xzmisc doesn't use size_append, so it can be used to create normal .xz
# files. xzmisc uses smaller LZMA2 dictionary than xzkern, because a very
# big dictionary would increase the memory usage too much in the multi-call
# decompression mode. A BCJ filter isn't used either.
quiet_cmd_xzkern = XZKERN $@
cmd_xzkern = (cat $(filter-out FORCE,$^) | \
sh $(srctree)/scripts/xz_wrap.sh && \
$(call size_append, $(filter-out FORCE,$^))) > $@ || \
(rm -f $@ ; false)
quiet_cmd_xzmisc = XZMISC $@
cmd_xzmisc = (cat $(filter-out FORCE,$^) | \
xz --check=crc32 --lzma2=dict=1MiB) > $@ || \
(rm -f $@ ; false)
%.xzkern: %
$(call if_changed,xzkern)
# DTC
# ---------------------------------------------------------------------------

23
scripts/xz_wrap.sh Executable file
View File

@ -0,0 +1,23 @@
#!/bin/sh
#
# This is a wrapper for xz to compress the kernel image using appropriate
# compression options depending on the architecture.
#
# 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.
#
BCJ=
LZMA2OPTS=
case $SRCARCH in
x86) BCJ=--x86 ;;
powerpc) BCJ=--powerpc ;;
ia64) BCJ=--ia64; LZMA2OPTS=pb=4 ;;
arm) BCJ=--arm ;;
sparc) BCJ=--sparc ;;
esac
exec xz --check=crc32 $BCJ --lzma2=$LZMA2OPTS,dict=32MiB