diff options
| -rw-r--r-- | Documentation/xz.txt | 121 | ||||
| -rw-r--r-- | include/linux/xz.h | 264 | ||||
| -rw-r--r-- | lib/Kconfig | 2 | ||||
| -rw-r--r-- | lib/Makefile | 1 | ||||
| -rw-r--r-- | lib/xz/Kconfig | 59 | ||||
| -rw-r--r-- | lib/xz/Makefile | 5 | ||||
| -rw-r--r-- | lib/xz/xz_crc32.c | 59 | ||||
| -rw-r--r-- | lib/xz/xz_dec_bcj.c | 561 | ||||
| -rw-r--r-- | lib/xz/xz_dec_lzma2.c | 1171 | ||||
| -rw-r--r-- | lib/xz/xz_dec_stream.c | 821 | ||||
| -rw-r--r-- | lib/xz/xz_dec_syms.c | 26 | ||||
| -rw-r--r-- | lib/xz/xz_dec_test.c | 220 | ||||
| -rw-r--r-- | lib/xz/xz_lzma2.h | 204 | ||||
| -rw-r--r-- | lib/xz/xz_private.h | 156 | ||||
| -rw-r--r-- | lib/xz/xz_stream.h | 62 | ||||
| -rw-r--r-- | scripts/Makefile.lib | 28 | ||||
| -rw-r--r-- | scripts/xz_wrap.sh | 23 |
17 files changed, 3783 insertions, 0 deletions
diff --git a/Documentation/xz.txt b/Documentation/xz.txt new file mode 100644 index 00000000000..2cf3e2608de --- /dev/null +++ b/Documentation/xz.txt @@ -0,0 +1,121 @@ + +XZ data compression in Linux +============================ + +Introduction + + XZ is a general purpose data compression format with high compression + ratio and relatively fast decompression. The primary compression + algorithm (filter) is LZMA2. Additional filters can be used to improve + compression ratio even further. E.g. Branch/Call/Jump (BCJ) filters + improve compression ratio of executable data. + + The XZ decompressor in Linux is called XZ Embedded. It supports + the LZMA2 filter and optionally also BCJ filters. CRC32 is supported + for integrity checking. The home page of XZ Embedded is at + <http://tukaani.org/xz/embedded.html>, where you can find the + latest version and also information about using the code outside + the Linux kernel. + + For userspace, XZ Utils provide a zlib-like compression library + and a gzip-like command line tool. XZ Utils can be downloaded from + <http://tukaani.org/xz/>. + +XZ related components in the kernel + + The xz_dec module provides XZ decompressor with single-call (buffer + to buffer) and multi-call (stateful) APIs. The usage of the xz_dec + module is documented in include/linux/xz.h. + + The xz_dec_test module is for testing xz_dec. xz_dec_test is not + useful unless you are hacking the XZ decompressor. xz_dec_test + allocates a char device major dynamically to which one can write + .xz files from userspace. The decompressed output is thrown away. + Keep an eye on dmesg to see diagnostics printed by xz_dec_test. + See the xz_dec_test source code for the details. + + For decompressing the kernel image, initramfs, and initrd, there + is a wrapper function in lib/decompress_unxz.c. Its API is the + same as in other decompress_*.c files, which is defined in + include/linux/decompress/generic.h. + + scripts/xz_wrap.sh is a wrapper for the xz command line tool found + from XZ Utils. The wrapper sets compression options to values suitable + for compressing the kernel image. + + For kernel makefiles, two commands are provided for use with + $(call if_needed). The kernel image should be compressed with + $(call if_needed,xzkern) which will use a BCJ filter and a big LZMA2 + dictionary. It will also append a four-byte trailer containing the + uncompressed size of the file, which is needed by the boot code. + Other things should be compressed with $(call if_needed,xzmisc) + which will use no BCJ filter and 1 MiB LZMA2 dictionary. + +Notes on compression options + + Since the XZ Embedded supports only streams with no integrity check or + CRC32, make sure that you don't use some other integrity check type + when encoding files that are supposed to be decoded by the kernel. With + liblzma, you need to use either LZMA_CHECK_NONE or LZMA_CHECK_CRC32 + when encoding. With the xz command line tool, use --check=none or + --check=crc32. + + Using CRC32 is strongly recommended unless there is some other layer + which will verify the integrity of the uncompressed data anyway. + Double checking the integrity would probably be waste of CPU cycles. + Note that the headers will always have a CRC32 which will be validated + by the decoder; you can only change the integrity check type (or + disable it) for the actual uncompressed data. + + In userspace, LZMA2 is typically used with dictionary sizes of several + megabytes. The decoder needs to have the dictionary in RAM, thus big + dictionaries cannot be used for files that are intended to be decoded + by the kernel. 1 MiB is probably the maximum reasonable dictionary + size for in-kernel use (maybe more is OK for initramfs). The presets + in XZ Utils may not be optimal when creating files for the kernel, + so don't hesitate to use custom settings. Example: + + xz --check=crc32 --lzma2=dict=512KiB inputfile + + An exception to above dictionary size limitation is when the decoder + is used in single-call mode. Decompressing the kernel itself is an + example of this situation. In single-call mode, the memory usage + doesn't depend on the dictionary size, and it is perfectly fine to + use a big dictionary: for maximum compression, the dictionary should + be at least as big as the uncompressed data itself. + +Future plans + + Creating a limited XZ encoder may be considered if people think it is + useful. LZMA2 is slower to compress than e.g. Deflate or LZO even at + the fastest settings, so it isn't clear if LZMA2 encoder is wanted + into the kernel. + + Support for limited random-access reading is planned for the + decompression code. I don't know if it could have any use in the + kernel, but I know that it would be useful in some embedded projects + outside the Linux kernel. + +Conformance to the .xz file format specification + + There are a couple of corner cases where things have been simplified + at expense of detecting errors as early as possible. These should not + matter in practice all, since they don't cause security issues. But + it is good to know this if testing the code e.g. with the test files + from XZ Utils. + +Reporting bugs + + Before reporting a bug, please check that it's not fixed already + at upstream. See <http://tukaani.org/xz/embedded.html> to get the + latest code. + + Report bugs to <lasse.collin@tukaani.org> or visit #tukaani on + Freenode and talk to Larhzu. I don't actively read LKML or other + kernel-related mailing lists, so if there's something I should know, + you should email to me personally or use IRC. + + Don't bother Igor Pavlov with questions about the XZ implementation + in the kernel or about XZ Utils. While these two implementations + include essential code that is directly based on Igor Pavlov's code, + these implementations aren't maintained nor supported by him. diff --git a/include/linux/xz.h b/include/linux/xz.h new file mode 100644 index 00000000000..64cffa6ddfc --- /dev/null +++ b/include/linux/xz.h @@ -0,0 +1,264 @@ +/* + * 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 + +/** + * 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 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 +#endif diff --git a/lib/Kconfig b/lib/Kconfig index 3116aa631af..2b8f8540d67 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -106,6 +106,8 @@ config LZO_COMPRESS config LZO_DECOMPRESS tristate +source "lib/xz/Kconfig" + # # These all provide a common interface (hence the apparent duplication with # ZLIB_INFLATE; DECOMPRESS_GZIP is just a wrapper.) diff --git a/lib/Makefile b/lib/Makefile index 2f59e0a1dd8..4df2d029772 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -69,6 +69,7 @@ obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate/ obj-$(CONFIG_REED_SOLOMON) += reed_solomon/ obj-$(CONFIG_LZO_COMPRESS) += lzo/ obj-$(CONFIG_LZO_DECOMPRESS) += lzo/ +obj-$(CONFIG_XZ_DEC) += xz/ obj-$(CONFIG_RAID6_PQ) += raid6/ lib-$(CONFIG_DECOMPRESS_GZIP) += decompress_inflate.o diff --git a/lib/xz/Kconfig b/lib/xz/Kconfig new file mode 100644 index 00000000000..e3b6e18fdac --- /dev/null +++ b/lib/xz/Kconfig @@ -0,0 +1,59 @@ +config XZ_DEC + tristate "XZ decompression support" + select CRC32 + help + LZMA2 compression algorithm and BCJ filters are supported using + the .xz file format as the container. For integrity checking, + CRC32 is supported. See Documentation/xz.txt for more information. + +config XZ_DEC_X86 + bool "x86 BCJ filter decoder" if EMBEDDED + default y + depends on XZ_DEC + select XZ_DEC_BCJ + +config XZ_DEC_POWERPC + bool "PowerPC BCJ filter decoder" if EMBEDDED + default y + depends on XZ_DEC + select XZ_DEC_BCJ + +config XZ_DEC_IA64 + bool "IA-64 BCJ filter decoder" if EMBEDDED + default y + depends on XZ_DEC + select XZ_DEC_BCJ + +config XZ_DEC_ARM + bool "ARM BCJ filter decoder" if EMBEDDED + default y + depends on XZ_DEC + select XZ_DEC_BCJ + +config XZ_DEC_ARMTHUMB + bool "ARM-Thumb BCJ filter decoder" if EMBEDDED + default y + depends on XZ_DEC + select XZ_DEC_BCJ + +config XZ_DEC_SPARC + bool "SPARC BCJ filter decoder" if EMBEDDED + default y + depends on XZ_DEC + select XZ_DEC_BCJ + +config XZ_DEC_BCJ + bool + default n + +config XZ_DEC_TEST + tristate "XZ decompressor tester" + default n + depends on XZ_DEC + help + This allows passing .xz files to the in-kernel XZ decoder via + a character special file. It calculates CRC32 of the decompressed + data and writes diagnostics to the system log. + + Unless you are developing the XZ decoder, you don't need this + and should say N. diff --git a/lib/xz/Makefile b/lib/xz/Makefile new file mode 100644 index 00000000000..a7fa7693f0f --- /dev/null +++ b/lib/xz/Makefile @@ -0,0 +1,5 @@ +obj-$(CONFIG_XZ_DEC) += xz_dec.o +xz_dec-y := xz_dec_syms.o xz_dec_stream.o xz_dec_lzma2.o +xz_dec-$(CONFIG_XZ_DEC_BCJ) += xz_dec_bcj.o + +obj-$(CONFIG_XZ_DEC_TEST) += xz_dec_test.o diff --git a/lib/xz/xz_crc32.c b/lib/xz/xz_crc32.c new file mode 100644 index 00000000000..34532d14fd4 --- /dev/null +++ b/lib/xz/xz_crc32.c @@ -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; +} diff --git a/lib/xz/xz_dec_bcj.c b/lib/xz/xz_dec_bcj.c new file mode 100644 index 00000000000..e51e2558ca9 --- /dev/null +++ b/lib/xz/xz_dec_bcj.c @@ -0,0 +1,561 @@ +/* + * 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); + |