diff options
Diffstat (limited to 'lib')
-rw-r--r-- | lib/Kconfig | 6 | ||||
-rw-r--r-- | lib/Makefile | 6 | ||||
-rw-r--r-- | lib/decompress.c | 5 | ||||
-rw-r--r-- | lib/decompress_bunzip2.c | 8 | ||||
-rw-r--r-- | lib/decompress_inflate.c | 23 | ||||
-rw-r--r-- | lib/decompress_unlzma.c | 85 | ||||
-rw-r--r-- | lib/decompress_unlzo.c | 105 | ||||
-rw-r--r-- | lib/decompress_unxz.c | 397 | ||||
-rw-r--r-- | lib/dynamic_debug.c | 9 | ||||
-rw-r--r-- | lib/flex_array.c | 10 | ||||
-rw-r--r-- | lib/hexdump.c | 18 | ||||
-rw-r--r-- | lib/kref.c | 30 | ||||
-rw-r--r-- | lib/percpu_counter.c | 8 | ||||
-rw-r--r-- | lib/vsprintf.c | 38 | ||||
-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 |
25 files changed, 4007 insertions, 85 deletions
diff --git a/lib/Kconfig b/lib/Kconfig index 3116aa6..0ee67e0 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.) @@ -120,6 +122,10 @@ config DECOMPRESS_BZIP2 config DECOMPRESS_LZMA tristate +config DECOMPRESS_XZ + select XZ_DEC + tristate + config DECOMPRESS_LZO select LZO_DECOMPRESS tristate diff --git a/lib/Makefile b/lib/Makefile index d7b6e30a..cbb774f 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -12,7 +12,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ idr.o int_sqrt.o extable.o prio_tree.o \ sha1.o irq_regs.o reciprocal_div.o argv_split.o \ proportions.o prio_heap.o ratelimit.o show_mem.o \ - is_single_threaded.o plist.o decompress.o flex_array.o + is_single_threaded.o plist.o decompress.o lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o @@ -21,7 +21,7 @@ lib-y += kobject.o kref.o klist.o obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \ bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \ - string_helpers.o gcd.o lcm.o list_sort.o uuid.o + string_helpers.o gcd.o lcm.o list_sort.o uuid.o flex_array.o ifeq ($(CONFIG_DEBUG_KOBJECT),y) CFLAGS_kobject.o += -DDEBUG @@ -69,11 +69,13 @@ obj-$(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 lib-$(CONFIG_DECOMPRESS_BZIP2) += decompress_bunzip2.o lib-$(CONFIG_DECOMPRESS_LZMA) += decompress_unlzma.o +lib-$(CONFIG_DECOMPRESS_XZ) += decompress_unxz.o lib-$(CONFIG_DECOMPRESS_LZO) += decompress_unlzo.o obj-$(CONFIG_TEXTSEARCH) += textsearch.o diff --git a/lib/decompress.c b/lib/decompress.c index a760681..3d766b7f 100644 --- a/lib/decompress.c +++ b/lib/decompress.c @@ -8,6 +8,7 @@ #include <linux/decompress/bunzip2.h> #include <linux/decompress/unlzma.h> +#include <linux/decompress/unxz.h> #include <linux/decompress/inflate.h> #include <linux/decompress/unlzo.h> @@ -23,6 +24,9 @@ #ifndef CONFIG_DECOMPRESS_LZMA # define unlzma NULL #endif +#ifndef CONFIG_DECOMPRESS_XZ +# define unxz NULL +#endif #ifndef CONFIG_DECOMPRESS_LZO # define unlzo NULL #endif @@ -36,6 +40,7 @@ static const struct compress_format { { {037, 0236}, "gzip", gunzip }, { {0x42, 0x5a}, "bzip2", bunzip2 }, { {0x5d, 0x00}, "lzma", unlzma }, + { {0xfd, 0x37}, "xz", unxz }, { {0x89, 0x4c}, "lzo", unlzo }, { {0, 0}, NULL, NULL } }; diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c index 81c8bb1..a7b80c1 100644 --- a/lib/decompress_bunzip2.c +++ b/lib/decompress_bunzip2.c @@ -49,7 +49,6 @@ #define PREBOOT #else #include <linux/decompress/bunzip2.h> -#include <linux/slab.h> #endif /* STATIC */ #include <linux/decompress/mm.h> @@ -682,13 +681,12 @@ STATIC int INIT bunzip2(unsigned char *buf, int len, int(*flush)(void*, unsigned int), unsigned char *outbuf, int *pos, - void(*error_fn)(char *x)) + void(*error)(char *x)) { struct bunzip_data *bd; int i = -1; unsigned char *inbuf; - set_error_fn(error_fn); if (flush) outbuf = malloc(BZIP2_IOBUF_SIZE); @@ -751,8 +749,8 @@ STATIC int INIT decompress(unsigned char *buf, int len, int(*flush)(void*, unsigned int), unsigned char *outbuf, int *pos, - void(*error_fn)(char *x)) + void(*error)(char *x)) { - return bunzip2(buf, len - 4, fill, flush, outbuf, pos, error_fn); + return bunzip2(buf, len - 4, fill, flush, outbuf, pos, error); } #endif diff --git a/lib/decompress_inflate.c b/lib/decompress_inflate.c index fc686c7..19ff89e 100644 --- a/lib/decompress_inflate.c +++ b/lib/decompress_inflate.c @@ -19,7 +19,6 @@ #include "zlib_inflate/inflate.h" #include "zlib_inflate/infutil.h" -#include <linux/slab.h> #endif /* STATIC */ @@ -27,7 +26,7 @@ #define GZIP_IOBUF_SIZE (16*1024) -static int nofill(void *buffer, unsigned int len) +static int INIT nofill(void *buffer, unsigned int len) { return -1; } @@ -38,13 +37,12 @@ STATIC int INIT gunzip(unsigned char *buf, int len, int(*flush)(void*, unsigned int), unsigned char *out_buf, int *pos, - void(*error_fn)(char *x)) { + void(*error)(char *x)) { u8 *zbuf; struct z_stream_s *strm; int rc; size_t out_len; - set_error_fn(error_fn); rc = -1; if (flush) { out_len = 0x8000; /* 32 K */ @@ -100,13 +98,22 @@ STATIC int INIT gunzip(unsigned char *buf, int len, * possible asciz filename) */ strm->next_in = zbuf + 10; + strm->avail_in = len - 10; /* skip over asciz filename */ if (zbuf[3] & 0x8) { - while (strm->next_in[0]) - strm->next_in++; - strm->next_in++; + do { + /* + * If the filename doesn't fit into the buffer, + * the file is very probably corrupt. Don't try + * to read more data. + */ + if (strm->avail_in == 0) { + error("header error"); + goto gunzip_5; + } + --strm->avail_in; + } while (*strm->next_in++); } - strm->avail_in = len - (strm->next_in - zbuf); strm->next_out = out_buf; strm->avail_out = out_len; diff --git a/lib/decompress_unlzma.c b/lib/decompress_unlzma.c index ca82fde..476c65a 100644 --- a/lib/decompress_unlzma.c +++ b/lib/decompress_unlzma.c @@ -33,7 +33,6 @@ #define PREBOOT #else #include <linux/decompress/unlzma.h> -#include <linux/slab.h> #endif /* STATIC */ #include <linux/decompress/mm.h> @@ -74,6 +73,7 @@ struct rc { uint32_t code; uint32_t range; uint32_t bound; + void (*error)(char *); }; @@ -82,7 +82,7 @@ struct rc { #define RC_MODEL_TOTAL_BITS 11 -static int nofill(void *buffer, unsigned int len) +static int INIT nofill(void *buffer, unsigned int len) { return -1; } @@ -92,7 +92,7 @@ static void INIT rc_read(struct rc *rc) { rc->buffer_size = rc->fill((char *)rc->buffer, LZMA_IOBUF_SIZE); if (rc->buffer_size <= 0) - error("unexpected EOF"); + rc->error("unexpected EOF"); rc->ptr = rc->buffer; rc->buffer_end = rc->buffer + rc->buffer_size; } @@ -127,12 +127,6 @@ static inline void INIT rc_init_code(struct rc *rc) } -/* Called once. TODO: bb_maybe_free() */ -static inline void INIT rc_free(struct rc *rc) -{ - free(rc->buffer); -} - /* Called twice, but one callsite is in inline'd rc_is_bit_0_helper() */ static void INIT rc_do_normalize(struct rc *rc) { @@ -169,7 +163,7 @@ static inline void INIT rc_update_bit_0(struct rc *rc, uint16_t *p) rc->range = rc->bound; *p += ((1 << RC_MODEL_TOTAL_BITS) - *p) >> RC_MOVE_BITS; } -static inline void rc_update_bit_1(struct rc *rc, uint16_t *p) +static inline void INIT rc_update_bit_1(struct rc *rc, uint16_t *p) { rc->range -= rc->bound; rc->code -= rc->bound; @@ -319,32 +313,38 @@ static inline uint8_t INIT peek_old_byte(struct writer *wr, } -static inline void INIT write_byte(struct writer *wr, uint8_t byte) +static inline int INIT write_byte(struct writer *wr, uint8_t byte) { wr->buffer[wr->buffer_pos++] = wr->previous_byte = byte; if (wr->flush && wr->buffer_pos == wr->header->dict_size) { wr->buffer_pos = 0; wr->global_pos += wr->header->dict_size; - wr->flush((char *)wr->buffer, wr->header->dict_size); + if (wr->flush((char *)wr->buffer, wr->header->dict_size) + != wr->header->dict_size) + return -1; } + return 0; } -static inline void INIT copy_byte(struct writer *wr, uint32_t offs) +static inline int INIT copy_byte(struct writer *wr, uint32_t offs) { - write_byte(wr, peek_old_byte(wr, offs)); + return write_byte(wr, peek_old_byte(wr, offs)); } -static inline void INIT copy_bytes(struct writer *wr, +static inline int INIT copy_bytes(struct writer *wr, uint32_t rep0, int len) { do { - copy_byte(wr, rep0); + if (copy_byte(wr, rep0)) + return -1; len--; } while (len != 0 && wr->buffer_pos < wr->header->dst_size); + + return len; } -static inline void INIT process_bit0(struct writer *wr, struct rc *rc, +static inline int INIT process_bit0(struct writer *wr, struct rc *rc, struct cstate *cst, uint16_t *p, int pos_state, uint16_t *prob, int lc, uint32_t literal_pos_mask) { @@ -378,16 +378,17 @@ static inline void INIT process_bit0(struct writer *wr, struct rc *rc, uint16_t *prob_lit = prob + mi; rc_get_bit(rc, prob_lit, &mi); } - write_byte(wr, mi); if (cst->state < 4) cst->state = 0; else if (cst->state < 10) cst->state -= 3; else cst->state -= 6; + + return write_byte(wr, mi); } -static inline void INIT process_bit1(struct writer *wr, struct rc *rc, +static inline int INIT process_bit1(struct writer *wr, struct rc *rc, struct cstate *cst, uint16_t *p, int pos_state, uint16_t *prob) { int offset; @@ -418,8 +419,7 @@ static inline void INIT process_bit1(struct writer *wr, struct rc *rc, cst->state = cst->state < LZMA_NUM_LIT_STATES ? 9 : 11; - copy_byte(wr, cst->rep0); - return; + return copy_byte(wr, cst->rep0); } else { rc_update_bit_1(rc, prob); } @@ -521,12 +521,15 @@ static inline void INIT process_bit1(struct writer *wr, struct rc *rc, } else cst->rep0 = pos_slot; if (++(cst->rep0) == 0) - return; + return 0; + if (cst->rep0 > wr->header->dict_size + || cst->rep0 > get_pos(wr)) + return -1; } len += LZMA_MATCH_MIN_LEN; - copy_bytes(wr, cst->rep0, len); + return copy_bytes(wr, cst->rep0, len); } @@ -536,7 +539,7 @@ STATIC inline int INIT unlzma(unsigned char *buf, int in_len, int(*flush)(void*, unsigned int), unsigned char *output, int *posp, - void(*error_fn)(char *x) + void(*error)(char *x) ) { struct lzma_header header; @@ -552,7 +555,7 @@ STATIC inline int INIT unlzma(unsigned char *buf, int in_len, unsigned char *inbuf; int ret = -1; - set_error_fn(error_fn); + rc.error = error; if (buf) inbuf = buf; @@ -580,8 +583,10 @@ STATIC inline int INIT unlzma(unsigned char *buf, int in_len, ((unsigned char *)&header)[i] = *rc.ptr++; } - if (header.pos >= (9 * 5 * 5)) + if (header.pos >= (9 * 5 * 5)) { error("bad header"); + goto exit_1; + } mi = 0; lc = header.pos; @@ -627,21 +632,29 @@ STATIC inline int INIT unlzma(unsigned char *buf, int in_len, int pos_state = get_pos(&wr) & pos_state_mask; uint16_t *prob = p + LZMA_IS_MATCH + (cst.state << LZMA_NUM_POS_BITS_MAX) + pos_state; - if (rc_is_bit_0(&rc, prob)) - process_bit0(&wr, &rc, &cst, p, pos_state, prob, - lc, literal_pos_mask); - else { - process_bit1(&wr, &rc, &cst, p, pos_state, prob); + if (rc_is_bit_0(&rc, prob)) { + if (process_bit0(&wr, &rc, &cst, p, pos_state, prob, + lc, literal_pos_mask)) { + error("LZMA data is corrupt"); + goto exit_3; + } + } else { + if (process_bit1(&wr, &rc, &cst, p, pos_state, prob)) { + error("LZMA data is corrupt"); + goto exit_3; + } if (cst.rep0 == 0) break; } + if (rc.buffer_size <= 0) + goto exit_3; } if (posp) *posp = rc.ptr-rc.buffer; - if (wr.flush) - wr.flush(wr.buffer, wr.buffer_pos); - ret = 0; + if (!wr.flush || wr.flush(wr.buffer, wr.buffer_pos) == wr.buffer_pos) + ret = 0; +exit_3: large_free(p); exit_2: if (!output) @@ -659,9 +672,9 @@ STATIC int INIT decompress(unsigned char *buf, int in_len, int(*flush)(void*, unsigned int), unsigned char *output, int *posp, - void(*error_fn)(char *x) + void(*error)(char *x) ) { - return unlzma(buf, in_len - 4, fill, flush, output, posp, error_fn); + return unlzma(buf, in_len - 4, fill, flush, output, posp, error); } #endif diff --git a/lib/decompress_unlzo.c b/lib/decompress_unlzo.c index bcb3a4b..5a7a2ad 100644 --- a/lib/decompress_unlzo.c +++ b/lib/decompress_unlzo.c @@ -33,7 +33,6 @@ #ifdef STATIC #include "lzo/lzo1x_decompress.c" #else -#include <linux/slab.h> #include <linux/decompress/unlzo.h> #endif @@ -49,14 +48,25 @@ static const unsigned char lzop_magic[] = { #define LZO_BLOCK_SIZE (256*1024l) #define HEADER_HAS_FILTER 0x00000800L +#define HEADER_SIZE_MIN (9 + 7 + 4 + 8 + 1 + 4) +#define HEADER_SIZE_MAX (9 + 7 + 1 + 8 + 8 + 4 + 1 + 255 + 4) -STATIC inline int INIT parse_header(u8 *input, u8 *skip) +STATIC inline int INIT parse_header(u8 *input, int *skip, int in_len) { int l; u8 *parse = input; + u8 *end = input + in_len; u8 level = 0; u16 version; + /* + * Check that there's enough input to possibly have a valid header. + * Then it is possible to parse several fields until the minimum + * size may have been used. + */ + if (in_len < HEADER_SIZE_MIN) + return 0; + /* read magic: 9 first bits */ for (l = 0; l < 9; l++) { if (*parse++ != lzop_magic[l]) @@ -74,6 +84,15 @@ STATIC inline int INIT parse_header(u8 *input, u8 *skip) else parse += 4; /* flags */ + /* + * At least mode, mtime_low, filename length, and checksum must + * be left to be parsed. If also mtime_high is present, it's OK + * because the next input buffer check is after reading the + * filename length. + */ + if (end - parse < 8 + 1 + 4) + return 0; + /* skip mode and mtime_low */ parse += 8; if (version >= 0x0940) @@ -81,6 +100,8 @@ STATIC inline int INIT parse_header(u8 *input, u8 *skip) l = *parse++; /* don't care about the file name, and skip checksum */ + if (end - parse < l + 4) + return 0; parse += l + 4; *skip = parse - input; @@ -91,16 +112,15 @@ STATIC inline int INIT unlzo(u8 *input, int in_len, int (*fill) (void *, unsigned int), int (*flush) (void *, unsigned int), u8 *output, int *posp, - void (*error_fn) (char *x)) + void (*error) (char *x)) { - u8 skip = 0, r = 0; + u8 r = 0; + int skip = 0; u32 src_len, dst_len; size_t tmp; u8 *in_buf, *in_buf_save, *out_buf; int ret = -1; - set_error_fn(error_fn); - if (output) { out_buf = output; } else if (!flush) { @@ -119,8 +139,8 @@ STATIC inline int INIT unlzo(u8 *input, int in_len, goto exit_1; } else if (input) { in_buf = input; - } else if (!fill || !posp) { - error("NULL input pointer and missing position pointer or fill function"); + } else if (!fill) { + error("NULL input pointer and missing fill function"); goto exit_1; } else { in_buf = malloc(lzo1x_worst_compress(LZO_BLOCK_SIZE)); @@ -134,22 +154,47 @@ STATIC inline int INIT unlzo(u8 *input, int in_len, if (posp) *posp = 0; - if (fill) - fill(in_buf, lzo1x_worst_compress(LZO_BLOCK_SIZE)); + if (fill) { + /* + * Start from in_buf + HEADER_SIZE_MAX to make it possible + * to use memcpy() to copy the unused data to the beginning + * of the buffer. This way memmove() isn't needed which + * is missing from pre-boot environments of most archs. + */ + in_buf += HEADER_SIZE_MAX; + in_len = fill(in_buf, HEADER_SIZE_MAX); + } - if (!parse_header(input, &skip)) { + if (!parse_header(in_buf, &skip, in_len)) { error("invalid header"); goto exit_2; } in_buf += skip; + in_len -= skip; + + if (fill) { + /* Move the unused data to the beginning of the buffer. */ + memcpy(in_buf_save, in_buf, in_len); + in_buf = in_buf_save; + } if (posp) *posp = skip; for (;;) { /* read uncompressed block size */ + if (fill && in_len < 4) { + skip = fill(in_buf + in_len, 4 - in_len); + if (skip > 0) + in_len += skip; + } + if (in_len < 4) { + error("file corrupted"); + goto exit_2; + } dst_len = get_unaligned_be32(in_buf); in_buf += 4; + in_len -= 4; /* exit if last block */ if (dst_len == 0) { @@ -164,8 +209,18 @@ STATIC inline int INIT unlzo(u8 *input, int in_len, } /* read compressed block size, and skip block checksum info */ + if (fill && in_len < 8) { + skip = fill(in_buf + in_len, 8 - in_len); + if (skip > 0) + in_len += skip; + } + if (in_len < 8) { + error("file corrupted"); + goto exit_2; + } src_len = get_unaligned_be32(in_buf); in_buf += 8; + in_len -= 8; if (src_len <= 0 || src_len > dst_len) { error("file corrupted"); @@ -173,6 +228,15 @@ STATIC inline int INIT unlzo(u8 *input, int in_len, } /* decompress */ + if (fill && in_len < src_len) { + skip = fill(in_buf + in_len, src_len - in_len); + if (skip > 0) + in_len += skip; + } + if (in_len < src_len) { + error("file corrupted"); + goto exit_2; + } tmp = dst_len; /* When the input data is not compressed at all, @@ -190,17 +254,26 @@ STATIC inline int INIT unlzo(u8 *input, int in_len, } } - if (flush) - flush(out_buf, dst_len); + if (flush && flush(out_buf, dst_len) != dst_len) + goto exit_2; if (output) out_buf += dst_len; if (posp) *posp += src_len + 12; + + in_buf += src_len; + in_len -= src_len; if (fill) { + /* + * If there happens to still be unused data left in + * in_buf, move it to the beginning of the buffer. + * Use a loop to avoid memmove() dependency. + */ + if (in_len > 0) + for (skip = 0; skip < in_len; ++skip) + in_buf_save[skip] = in_buf[skip]; in_buf = in_buf_save; - fill(in_buf, lzo1x_worst_compress(LZO_BLOCK_SIZE)); - } else - in_buf += src_len; + } } ret = 0; diff --git a/lib/decompress_unxz.c b/lib/decompress_unxz.c new file mode 100644 index 0000000..cecd23d --- /dev/null +++ b/lib/decompress_unxz.c @@ -0,0 +1,397 @@ +/* + * 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 comparision, 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 <linux/slab.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 + +#ifndef memmove +/* Not static to avoid a conflict with the prototype in the Linux headers. */ +void *memmove(void *dest, const void *src, size_t size) +{ + uint8_t *d = dest; + const uint8_t *s = src; + size_t i; + + if (d < s) { + for (i = 0; i < size; ++i) + d[i] = s[i]; + } else if (d > s) { + i = size; + while (i-- > 0) + d[i] = s[i]; + } + + return dest; +} +#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 INIT unxz(unsigned char *in, int in_size, + int (*fill)(void *dest, unsigned int size), + int (*flush)(void *src, unsigned int size), + unsigned char *out, int *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) != (int)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 unxz diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c index 3094318..b335acb 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -141,11 +141,10 @@ static void ddebug_change(const struct ddebug_query *query, else if (!dp->flags) dt->num_enabled++; dp->flags = newflags; - if (newflags) { - jump_label_enable(&dp->enabled); - } else { - jump_label_disable(&dp->enabled); - } + if (newflags) + dp->enabled = 1; + else + dp->enabled = 0; if (verbose) printk(KERN_INFO "ddebug: changed %s:%d [%s]%s %s\n", diff --git a/lib/flex_array.c b/lib/flex_array.c index 77a6fea..c0ea40b 100644 --- a/lib/flex_array.c +++ b/lib/flex_array.c @@ -23,6 +23,7 @@ #include <linux/flex_array.h> #include <linux/slab.h> #include <linux/stddef.h> +#include <linux/module.h> struct flex_array_part { char elements[FLEX_ARRAY_PART_SIZE]; @@ -103,6 +104,7 @@ struct flex_array *flex_array_alloc(int element_size, unsigned int total, FLEX_ARRAY_BASE_BYTES_LEFT); return ret; } +EXPORT_SYMBOL(flex_array_alloc); static int fa_element_to_part_nr(struct flex_array *fa, unsigned int element_nr) @@ -126,12 +128,14 @@ void flex_array_free_parts(struct flex_array *fa) for (part_nr = 0; part_nr < FLEX_ARRAY_NR_BASE_PTRS; part_nr++) kfree(fa->parts[part_nr]); } +EXPORT_SYMBOL(flex_array_free_parts); void flex_array_free(struct flex_array *fa) { flex_array_free_parts(fa); kfree(fa); } +EXPORT_SYMBOL(flex_array_free); static unsigned int index_inside_part(struct flex_array *fa, unsigned int element_nr) @@ -196,6 +200,7 @@ int flex_array_put(struct flex_array *fa, unsigned int element_nr, void *src, memcpy(dst, src, fa->element_size); return 0; } +EXPORT_SYMBOL(flex_array_put); /** * flex_array_clear - clear element in array at @element_nr @@ -223,6 +228,7 @@ int flex_array_clear(struct flex_array *fa, unsigned int element_nr) memset(dst, FLEX_ARRAY_FREE, fa->element_size); return 0; } +EXPORT_SYMBOL(flex_array_clear); /** * flex_array_prealloc - guarantee that array space exists @@ -259,6 +265,7 @@ int flex_array_prealloc(struct flex_array *fa, unsigned int start, } return 0; } +EXPORT_SYMBOL(flex_array_prealloc); /** * flex_array_get - pull data back out of the array @@ -288,6 +295,7 @@ void *flex_array_get(struct flex_array *fa, unsigned int element_nr) } return &part->elements[index_inside_part(fa, element_nr)]; } +EXPORT_SYMBOL(flex_array_get); /** * flex_array_get_ptr - pull a ptr back out of the array @@ -308,6 +316,7 @@ void *flex_array_get_ptr(struct flex_array *fa, unsigned int element_nr) return *tmp; } +EXPORT_SYMBOL(flex_array_get_ptr); static int part_is_free(struct flex_array_part *part) { @@ -348,3 +357,4 @@ int flex_array_shrink(struct flex_array *fa) } return ret; } +EXPORT_SYMBOL(flex_array_shrink); diff --git a/lib/hexdump.c b/lib/hexdump.c index 5d7a480..f5fe6ba 100644 --- a/lib/hexdump.c +++ b/lib/hexdump.c @@ -34,6 +34,22 @@ int hex_to_bin(char ch) EXPORT_SYMBOL(hex_to_bin); /** + * hex2bin - convert an ascii hexadecimal string to its binary representation + * @dst: binary result + * @src: ascii hexadecimal string + * @count: result length + */ +void hex2bin(u8 *dst, const char *src, size_t count) +{ + while (count--) { + *dst = hex_to_bin(*src++) << 4; + *dst += hex_to_bin(*src++); + dst++; + } +} +EXPORT_SYMBOL(hex2bin); + +/** * hex_dump_to_buffer - convert a blob of data to "hex ASCII" in memory * @buf: data blob to dump * @len: number of bytes in the @buf @@ -138,6 +154,7 @@ nil: } EXPORT_SYMBOL(hex_dump_to_buffer); +#ifdef CONFIG_PRINTK /** * print_hex_dump - print a text hex dump to syslog for a binary blob of data * @level: kernel log level (e.g. KERN_DEBUG) @@ -222,3 +239,4 @@ void print_hex_dump_bytes(const char *prefix_str, int prefix_type, buf, len, true); } EXPORT_SYMBOL(print_hex_dump_bytes); +#endif @@ -62,6 +62,36 @@ int kref_put(struct kref *kref, void (*release)(struct kref *kref)) return 0; } + +/** + * kref_sub - subtract a number of refcounts for object. + * @kref: object. + * @count: Number of recounts to subtract. + * @release: pointer to the function that will clean up the object when the + * last reference to the object is released. + * This pointer is required, and it is not acceptable to pass kfree + * in as this function. + * + * Subtract @count from the refcount, and if 0, call release(). + * Return 1 if the object was removed, otherwise return 0. Beware, if this + * function returns 0, you still can not count on the kref from remaining in + * memory. Only use the return value if you want to see if the kref is now + * gone, not present. + */ +int kref_sub(struct kref *kref, unsigned int count, + void (*release)(struct kref *kref)) +{ + WARN_ON(release == NULL); + WARN_ON(release == (void (*)(struct kref *))kfree); + + if (atomic_sub_and_test((int) count, &kref->refcount)) { + release(kref); + return 1; + } + return 0; +} + EXPORT_SYMBOL(kref_init); EXPORT_SYMBOL(kref_get); EXPORT_SYMBOL(kref_put); +EXPORT_SYMBOL(kref_sub); diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index 604678d..28f2c33 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -72,18 +72,16 @@ EXPORT_SYMBOL(percpu_counter_set); void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; - s32 *pcount; preempt_disable(); - pcount = this_cpu_ptr(fbc->counters); - count = *pcount + amount; + count = __this_cpu_read(*fbc->counters) + amount; if (count >= batch || count <= -batch) { spin_lock(&fbc->lock); fbc->count += count; - *pcount = 0; + __this_cpu_write(*fbc->counters, 0); spin_unlock(&fbc->lock); } else { - *pcount = count; + __this_cpu_write(*fbc->counters, count); } preempt_enable(); } diff --git a/lib/vsprintf.c b/lib/vsprintf.c index c150d3d..d3023df 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -936,6 +936,8 @@ char *uuid_string(char *buf, char *end, const u8 *addr, return string(buf, end, uuid, spec); } +int kptr_restrict = 1; + /* * Show a '%p' thing. A kernel extension is that the '%p' is followed * by an extra set of alphanumeric characters that are extended format @@ -979,6 +981,7 @@ char *uuid_string(char *buf, char *end, const u8 *addr, * Implements a "recursive vsnprintf". * Do not use this feature without some mechanism to verify the * correctness of the format string and va_list arguments. + * - 'K' For a kernel pointer that should be hidden from unprivileged users * * Note: The difference between 'S' and 'F' is that on ia64 and ppc64 * function pointers are really function descriptors, which contain a @@ -1035,6 +1038,25 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr, return buf + vsnprintf(buf, end - buf, ((struct va_format *)ptr)->fmt, *(((struct va_format *)ptr)->va)); + case 'K': + /* + * %pK cannot be used in IRQ context because its test + * for CAP_SYSLOG would be meaningless. + */ + if (in_irq() || in_serving_softirq() || in_nmi()) { + if (spec.field_width == -1) + spec.field_width = 2 * sizeof(void *); + return string(buf, end, "pK-error", spec); + } else if ((kptr_restrict == 0) || + (kptr_restrict == 1 && + has_capability_noaudit(current, CAP_SYSLOG))) + break; + + if (spec.field_width == -1) { + spec.field_width = 2 * sizeof(void *); + spec.flags |= ZEROPAD; + } + return number(buf, end, 0, spec); } spec.flags |= SMALL; if (spec.field_width == -1) { @@ -1451,7 +1473,7 @@ EXPORT_SYMBOL(vsnprintf); * @args: Arguments for the format string * * The return value is the number of characters which have been written into - * the @buf not including the trailing '\0'. If @size is <= 0 the function + * the @buf not including the trailing '\0'. If @size is == 0 the function * returns 0. * * Call this function if you are already dealing with a va_list. @@ -1465,7 +1487,11 @@ int vscnprintf(char *buf, size_t size, const char *fmt, va_list args) i = vsnprintf(buf, size, fmt, args); - return (i >= size) ? (size - 1) : i; + if (likely(i < size)) + return i; + if (size != 0) + return size - 1; + return 0; } EXPORT_SYMBOL(vscnprintf); @@ -1513,14 +1539,10 @@ int scnprintf(char *buf, size_t size, const char *fmt, ...) int i; va_start(args, fmt); - i = vsnprintf(buf, size, fmt, args); + i = vscnprintf(buf, size, fmt, args); va_end(args); - if (likely(i < size)) - return i; - if (size != 0) - return size - 1; - return 0; + return i; } EXPORT_SYMBOL(scnprintf); diff --git a/lib/xz/Kconfig b/lib/xz/Kconfig new file mode 100644 index 0000000..e3b6e18 --- /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 0000000..a7fa769 --- /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 0000000..34532d1 --- /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 0000000..e51e255 --- /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); + 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. + */ + if (s->temp.size < b->out_size - b->out_pos) { + 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 we have unfiltered data in temp, try to fill 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 (s->temp.size > 0) { + /* 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 diff --git a/lib/xz/xz_dec_lzma2.c b/lib/xz/xz_dec_lzma2.c new file mode 100644 index 0000000..ea5fa4f --- /dev/null +++ b/lib/xz/xz_dec_lzma2.c @@ -0,0 +1,1171 @@ +/* + * LZMA2 decoder + * + * 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" +#include "xz_lzma2.h" + +/* + * Range decoder initialization eats the first five bytes of each LZMA chunk. + */ +#define RC_INIT_BYTES 5 + +/* + * Minimum number of usable input buffer to safely decode one LZMA symbol. + * The worst case is that we decode 22 bits using probabilities and 26 + * direct bits. This may decode at maximum of 20 bytes of input. However, + * lzma_main() does an extra normalization before returning, thus we + * need to put 21 here. + */ +#define LZMA_IN_REQUIRED 21 + +/* + * Dictionary (history buffer) + * + * These are always true: + * start <= pos <= full <= end + * pos <= limit <= end + * + * In multi-call mode, also these are true: + * end == size + * size <= size_max + * allocated <= size + * + * Most of these variables are size_t to support single-call mode, + * in which the dictionary variables address the actual output + * buffer directly. + */ +struct dictionary { + /* Beginning of the history buffer */ + uint8_t *buf; + + /* Old position in buf (before decoding more data) */ + size_t start; + + /* Position in buf */ + size_t pos; + + /* + * How full dictionary is. This is used to detect corrupt input that + * would read beyond the beginning of the uncompressed stream. + */ + size_t full; + + /* Write limit; we don't write to buf[limit] or later bytes. */ + size_t limit; + + /* + * End of the dictionary buffer. In multi-call mode, this is + * the same as the dictionary size. In single-call mode, this + * indicates the size of the output buffer. + */ + size_t end; + + /* + * Size of the dictionary as specified in Block Header. This is used + * together with "full" to detect corrupt input that would make us + * read beyond the beginning of the uncompressed stream. + */ + uint32_t size; + + /* + * Maximum allowed dictionary size in multi-call mode. + * This is ignored in single-call mode. + */ + uint32_t size_max; + + /* + * Amount of memory currently allocated for the dictionary. + * This is used only with XZ_DYNALLOC. (With XZ_PREALLOC, + * size_max is always the same as the allocated size.) + */ + uint32_t allocated; + + /* Operation mode */ + enum xz_mode mode; +}; + +/* Range decoder */ +struct rc_dec { + uint32_t range; + uint32_t code; + + /* + * Number of initializing bytes remaining to be read + * by rc_read_init(). + */ + uint32_t init_bytes_left; + + /* + * Buffer from which we read our input. It can be either + * temp.buf or the caller-provided input buffer. + */ + const uint8_t *in; + size_t in_pos; + size_t in_limit; +}; + +/* Probabilities for a length decoder. */ +struct lzma_len_dec { + /* Probability of match length being at least 10 */ + uint16_t choice; + + /* Probability of match length being at least 18 */ + uint16_t choice2; + + /* Probabilities for match lengths 2-9 */ + uint16_t low[POS_STATES_MAX][LEN_LOW_SYMBOLS]; + + /* Probabilities for match lengths 10-17 */ + uint16_t mid[POS_STATES_MAX][LEN_MID_SYMBOLS]; + + /* Probabilities for match lengths 18-273 */ + uint16_t high[LEN_HIGH_SYMBOLS]; +}; + +struct lzma_dec { + /* Distances of latest four matches */ + uint32_t rep0; + uint32_t rep1; + uint32_t rep2; + uint32_t rep3; + + /* Types of the most recently seen LZMA symbols */ + enum lzma_state state; + + /* + * Length of a match. This is updated so that dict_repeat can + * be called again to finish repeating the whole match. + */ + uint32_t len; + + /* + * LZMA properties or related bit masks (number of literal + * context bits, a mask dervied from the number of literal + * position bits, and a mask dervied from the number + * position bits) + */ + uint32_t lc; + uint32_t literal_pos_mask; /* (1 << lp) - 1 */ + uint32_t pos_mask; /* (1 << pb) - 1 */ + + /* If 1, it's a match. Otherwise it's a single 8-bit literal. */ + uint16_t is_match[STATES][POS_STATES_MAX]; + + /* If 1, it's a repeated match. The distance is one of rep0 .. rep3. */ + uint16_t is_rep[STATES]; + + /* + * If 0, distance of a repeated match is rep0. + * Otherwise check is_rep1. + */ + uint16_t is_rep0[STATES]; + + /* + * If 0, distance of a repeated match is rep1. + * Otherwise check is_rep2. + */ + uint16_t is_rep1[STATES]; + + /* If 0, distance of a repeated match is rep2. Otherwise it is rep3. */ + uint16_t is_rep2[STATES]; + + /* + * If 1, the repeated match has length of one byte. Otherwise + * the length is decoded from rep_len_decoder. + */ + uint16_t is_rep0_long[STATES][POS_STATES_MAX]; + + /* + * Probability tree for the highest two bits of the match + * distance. There is a separate probability tree for match + * lengths of 2 (i.e. MATCH_LEN_MIN), 3, 4, and [5, 273]. + */ + uint16_t dist_slot[DIST_STATES][DIST_SLOTS]; + + /* + * Probility trees for additional bits for match distance + * when the distance is in the range [4, 127]. + */ + uint16_t dist_special[FULL_DISTANCES - DIST_MODEL_END]; + + /* + * Probability tree for the lowest four bits of a match + * distance that is equal to or greater than 128. + */ + uint16_t dist_align[ALIGN_SIZE]; + + /* Length of a normal match */ + struct lzma_len_dec match_len_dec; + + /* Length of a repeated match */ + struct lzma_len_dec rep_len_dec; + + /* Probabilities of literals */ + uint16_t literal[LITERAL_CODERS_MAX][LITERAL_CODER_SIZE]; +}; + +struct lzma2_dec { + /* Position in xz_dec_lzma2_run(). */ + enum lzma2_seq { + SEQ_CONTROL, + SEQ_UNCOMPRESSED_1, + SEQ_UNCOMPRESSED_2, + SEQ_COMPRESSED_0, + SEQ_COMPRESSED_1, + SEQ_PROPERTIES, + SEQ_LZMA_PREPARE, + SEQ_LZMA_RUN, + SEQ_COPY + } sequence; + + /* Next position after decoding the compressed size of the chunk. */ + enum lzma2_seq next_sequence; + + /* Uncompressed size of LZMA chunk (2 MiB at maximum) */ + uint32_t uncompressed; + + /* + * Compressed size of LZMA chunk or compressed/uncompressed + * size of uncompressed chunk (64 KiB at maximum) + */ + uint32_t compressed; + + /* + * True if dictionary reset is needed. This is false before + * the first chunk (LZMA or uncompressed). + */ + bool need_dict_reset; + + /* + * True if new LZMA properties are needed. This is false + * before the first LZMA chunk. + */ + bool need_props; +}; + +struct xz_dec_lzma2 { + /* + * The order below is important on x86 to reduce code size and + * it shouldn't hurt on other platforms. Everything up to and + * including lzma.pos_mask are in the first 128 bytes on x86-32, + * which allows using smaller instructions to access those + * variables. On x86-64, fewer variables fit into the first 128 + * bytes, but this is still the best order without sacrificing + * the readability by splitting the structures. + */ + struct rc_dec rc; + struct dictionary dict; + struct lzma2_dec lzma2; + struct lzma_dec lzma; + + /* + * Temporary buffer which holds small number of input bytes between + * decoder calls. See lzma2_lzma() for details. + */ + struct { + uint32_t size; + uint8_t buf[3 * LZMA_IN_REQUIRED]; + } temp; +}; + +/************** + * Dictionary * + **************/ + +/* + * Reset the dictionary state. When in single-call mode, set up the beginning + * of the dictionary to point to the actual output buffer. + */ +static void dict_reset(struct dictionary *dict, struct xz_buf *b) +{ + if (DEC_IS_SINGLE(dict->mode)) { + dict->buf = b->out + b->out_pos; + dict->end = b->out_size - b->out_pos; + } + + dict->start = 0; + dict->pos = 0; + dict->limit = 0; + dict->full = 0; +} + +/* Set dictionary write limit */ +static void dict_limit(struct dictionary *dict, size_t out_max) +{ + if (dict->end - dict->pos <= out_max) + dict->limit = dict->end; + else + dict->limit = dict->pos + out_max; +} + +/* Return true if at least one byte can be written into the dictionary. */ +static inline bool dict_has_space(const struct dictionary *dict) +{ + return dict->pos < dict->limit; +} + +/* + * Get a byte from the dictionary at the given distance. The distance is + * assumed to valid, or as a special case, zero when the dictionary is + * still empty. This special case is needed for single-call decoding to + * avoid writing a '\0' to the end of the destination buffer. + */ +static inline uint32_t dict_get(const struct dictionary *dict, uint32_t dist) +{ + size_t offset = dict->pos - dist - 1; + + if (dist >= dict->pos) + offset += dict->end; + + return dict->full > 0 ? dict->buf[offset] : 0; +} + +/* + * Put one byte into the dictionary. It is assumed that there is space for it. + */ +static inline void dict_put(struct dictionary *dict, uint8_t byte) +{ + dict->buf[dict->pos++] = byte; + + if (dict->full < dict->pos) + dict->full = dict->pos; +} + +/* + * Repeat given number of bytes from the given distance. If the distance is + * invalid, false is returned. On success, true is returned and *len is + * updated to indicate how many bytes were left to be repeated. + */ +static bool dict_repeat(struct dictionary *dict, uint32_t *len, uint32_t dist) +{ + size_t back; + uint32_t left; + + if (dist >= dict->full || dist >= dict->size) + return false; + + left = min_t(size_t, dict->limit - dict->pos, *len); + *len -= left; + + back = dict->pos - dist - 1; + if (dist >= dict->pos) + back += dict->end; + + do { + dict->buf[dict->pos++] = dict->buf[back++]; + if (back == dict->end) + back = 0; + } while (--left > 0); + + if (dict->full < dict->pos) + dict->full = dict->pos; + + return true; +} + +/* Copy uncompressed data as is from input to dictionary and output buffers. */ +static void dict_uncompressed(struct dictionary *dict, struct xz_buf *b, + uint32_t *left) +{ + size_t copy_size; + + while (*left > 0 && b->in_pos < b->in_size + && b->out_pos < b->out_size) { + copy_size = min(b->in_size - b->in_pos, + b->out_size - b->out_pos); + if (copy_size > dict->end - dict->pos) + copy_size = dict->end - dict->pos; + if (copy_size > *left) + copy_size = *left; + + *left -= copy_size; + + memcpy(dict->buf + dict->pos, b->in + b->in_pos, copy_size); + dict->pos += copy_size; + + if (dict->full < dict->pos) + dict->full = dict->pos; + + if (DEC_IS_MULTI(dict->mode)) { + if (dict->pos == dict->end) + dict->pos = 0; + + memcpy(b->out + b->out_pos, b->in + b->in_pos, + copy_size); + } + + dict->start = dict->pos; + + b->out_pos += copy_size; + b->in_pos += copy_size; + } +} + +/* + * Flush pending data from dictionary to b->out. It is assumed that there is + * enough space in b->out. This is guaranteed because caller uses dict_limit() + * before decoding data into the dictionary. + */ +static uint32_t dict_flush(struct dictionary *dict, struct xz_buf *b) +{ + size_t copy_size = dict->pos - dict->start; + + if (DEC_IS_MULTI(dict->mode)) { + if (dict->pos == dict->end) + dict->pos = 0; + + memcpy(b->out + b->out_pos, dict->buf + dict->start, + copy_size); + } + + dict->start = dict->pos; + b->out_pos += copy_size; + return copy_size; +} + +/***************** + * Range decoder * + *****************/ + +/* Reset the range decoder. */ +static void rc_reset(struct rc_dec *rc) +{ + rc->range = (uint32_t)-1; + rc->code = 0; + rc->init_bytes_left = RC_INIT_BYTES; +} + +/* + * Read the first five initial bytes into rc->code if they haven't been + * read already. (Yes, the first byte gets completely ignored.) + */ +static bool rc_read_init(struct rc_dec *rc, struct xz_buf *b) +{ + while (rc->init_bytes_left > 0) { + if (b->in_pos == b->in_size) + return false; + + rc->code = (rc->code << 8) + b->in[b->in_pos++]; + --rc->init_bytes_left; + } + + return true; +} + +/* Return true if there may not be enough input for the next decoding loop. */ +static inline bool rc_limit_exceeded(const struct rc_dec *rc) +{ + return rc->in_pos > rc->in_limit; +} + +/* + * Return true if it is possible (from point of view of range decoder) that + * we have reached the end of the LZMA chunk. + */ +static inline bool rc_is_finished(const struct rc_dec *rc) +{ + return rc->code == 0; +} + +/* Read the next input byte if needed. */ +static __always_inline void rc_normalize(struct rc_dec *rc) +{ + if (rc->range < RC_TOP_VALUE) { + rc->range <<= RC_SHIFT_BITS; + rc->code = (rc->code << RC_SHIFT_BITS) + rc->in[rc->in_pos++]; + } +} + +/* + * Decode one bit. In some versions, this function has been splitted in three + * functions so that the compiler is supposed to be able to more easily avoid + * an extra branch. In this particular version of the LZMA decoder, this + * doesn't seem to be a good idea (tested with GCC 3.3.6, 3.4.6, and 4.3.3 + * on x86). Using a non-splitted version results in nicer looking code too. + * + * NOTE: This must return an int. Do not make it return a bool or the speed + * of the code generated by GCC 3.x decreases 10-15 %. (GCC 4.3 doesn't care, + * and it generates 10-20 % faster code than GCC 3.x from this file anyway.) + */ +static __always_inline int rc_bit(struct rc_dec *rc, uint16_t *prob) +{ + uint32_t bound; + int bit; + + rc_normalize(rc); + bound = (rc->range >> RC_BIT_MODEL_TOTAL_BITS) * *prob; + if (rc->code < bound) { + rc->range = bound; + *prob += (RC_BIT_MODEL_TOTAL - *prob) >> RC_MOVE_BITS; + bit = 0; + } else { + rc->range -= bound; + rc->code -= bound; + *prob -= *prob >> RC_MOVE_BITS; + bit = 1; + } + + return bit; +} + +/* Decode a bittree starting from the most significant bit. */ +static __always_inline uint32_t rc_bittree(struct rc_dec *rc, + uint16_t *probs, uint32_t limit) +{ + uint32_t symbol = 1; + + do { + if (rc_bit(rc, &probs[symbol])) + symbol = (symbol << 1) + 1; + else + symbol <<= 1; + } while (symbol < limit); + + return symbol; +} + +/* Decode a bittree starting from the least significant bit. */ +static __always_inline void rc_bittree_reverse(struct rc_dec *rc, + uint16_t *probs, + uint32_t *dest, uint32_t limit) +{ + uint32_t symbol = 1; + uint32_t i = 0; + + do { + if (rc_bit(rc, &probs[symbol])) { + symbol = (symbol << 1) + 1; + *dest += 1 << i; + } else { + symbol <<= 1; + } + } while (++i < limit); +} + +/* Decode direct bits (fixed fifty-fifty probability) */ +static inline void rc_direct(struct rc_dec *rc, uint32_t *dest, uint32_t limit) +{ + uint32_t mask; + + do { + rc_normalize(rc); + rc->range >>= 1; + rc->code -= rc->range; + mask = (uint32_t)0 - (rc->code >> 31); + rc->code += rc->range & mask; + *dest = (*dest << 1) + (mask + 1); + } while (--limit > 0); +} + +/******** + * LZMA * + ********/ + +/* Get pointer to literal coder probability array. */ +static uint16_t *lzma_literal_probs(struct xz_dec_lzma2 *s) +{ + uint32_t prev_byte = dict_get(&s->dict, 0); + uint32_t low = prev_byte >> (8 - s->lzma.lc); + uint32_t high = (s->dict.pos & s->lzma.literal_pos_mask) << s->lzma.lc; + return s->lzma.literal[low + high]; +} + +/* Decode a literal (one 8-bit byte) */ +static void lzma_literal(struct xz_dec_lzma2 *s) +{ + uint16_t *probs; + uint32_t symbol; + uint32_t match_byte; + uint32_t match_bit; + uint32_t offset; + uint32_t i; + + probs = lzma_literal_probs(s); + + if (lzma_state_is_literal(s->lzma.state)) { + symbol = rc_bittree(&s->rc, probs, 0x100); + } else { + symbol = 1; + match_byte = dict_get(&s->dict, s->lzma.rep0) << 1; + offset = 0x100; + + do { + match_bit = match_byte & offset; + match_byte <<= 1; + i = offset + match_bit + symbol; + + if (rc_bit(&s->rc, &probs[i])) { + symbol = (symbol << 1) + 1; + offset &= match_bit; + } else { + symbol <<= 1; + offset &= ~match_bit; + } + } while (symbol < 0x100); + } + + dict_put(&s->dict, (uint8_t)symbol); + lzma_state_literal(&s->lzma.state); +} + +/* Decode the length of the match into s->lzma.len. */ +static void lzma_len(struct xz_dec_lzma2 *s, struct lzma_len_dec *l, + uint32_t pos_state) +{ + uint16_t *probs; + uint32_t limit; + + if (!rc_bit(&s->rc, &l->choice)) { + probs = l->low[pos_state]; + limit = LEN_LOW_SYMBOLS; + s->lzma.len = MATCH_LEN_MIN; + } else { + if (!rc_bit(&s->rc, &l->choice2)) { + probs = l->mid[pos_state]; + limit = LEN_MID_SYMBOLS; + s->lzma.len = MATCH_LEN_MIN + LEN_LOW_SYMBOLS; + } else { + probs = l->high; + limit = LEN_HIGH_SYMBOLS; + s->lzma.len = MATCH_LEN_MIN + LEN_LOW_SYMBOLS + + LEN_MID_SYMBOLS; + } + } + + s->lzma.len += rc_bittree(&s->rc, probs, limit) - limit; +} + +/* Decode a match. The distance will be stored in s->lzma.rep0. */ +static void lzma_match(struct xz_dec_lzma2 *s, uint32_t pos_state) +{ + uint16_t *probs; + uint32_t dist_slot; + uint32_t limit; + + lzma_state_match(&s->lzma.state); + + s->lzma.rep3 = s->lzma.rep2; + s->lzma.rep2 = s->lzma.rep1; + s->lzma.rep1 = s->lzma.rep0; + + lzma_len(s, &s->lzma.match_len_dec, pos_state); + + probs = s->lzma.dist_slot[lzma_get_dist_state(s->lzma.len)]; + dist_slot = rc_bittree(&s->rc, probs, DIST_SLOTS) - DIST_SLOTS; + + if (dist_slot < DIST_MODEL_START) { + s->lzma.rep0 = dist_slot; + } else { + limit = (dist_slot >> 1) - 1; + s->lzma.rep0 = 2 + (dist_slot & 1); + + if (dist_slot < DIST_MODEL_END) { + s->lzma.rep0 <<= limit; + probs = s->lzma.dist_special + s->lzma.rep0 + - dist_slot - 1; + rc_bittree_reverse(&s->rc, probs, + &s->lzma.rep0, limit); + } else { + rc_direct(&s->rc, &s->lzma.rep0, limit - ALIGN_BITS); + s->lzma.rep0 <<= ALIGN_BITS; + rc_bittree_reverse(&s->rc, s->lzma.dist_align, + &s->lzma.rep0, ALIGN_BITS); + } + } +} + +/* + * Decode a repeated match. The distance is one of the four most recently + * seen matches. The distance will be stored in s->lzma.rep0. + */ +static void lzma_rep_match(struct xz_dec_lzma2 *s, uint32_t pos_state) +{ + uint32_t tmp; + + if (!rc_bit(&s->rc, &s->lzma.is_rep0[s->lzma.state])) { + if (!rc_bit(&s->rc, &s->lzma.is_rep0_long[ + s->lzma.state][pos_state])) { + lzma_state_short_rep(&s->lzma.state); + s->lzma.len = 1; + return; + } + } else { + if (!rc_bit(&s->rc, &s->lzma.is_rep1[s->lzma.state])) { + tmp = s->lzma.rep1; + } else { + if (!rc_bit(&s->rc, &s->lzma.is_rep2[s->lzma.state])) { + tmp = s->lzma.rep2; + } else { + tmp = s->lzma.rep3; + s->lzma.rep3 = s->lzma.rep2; + } + + s->lzma.rep2 = s->lzma.rep1; + } + + s->lzma.rep1 = s->lzma.rep0; + s->lzma.rep0 = tmp; + } + + lzma_state_long_rep(&s->lzma.state); + lzma_len(s, &s->lzma.rep_len_dec, pos_state); +} + +/* LZMA decoder core */ +static bool lzma_main(struct xz_dec_lzma2 *s) +{ + uint32_t pos_state; + + /* + * If the dictionary was reached during the previous call, try to + * finish the possibly pending repeat in the dictionary. + */ + if (dict_has_space(&s->dict) && s->lzma.len > 0) + dict_repeat(&s->dict, &s->lzma.len, s->lzma.rep0); + + /* + * Decode more LZMA symbols. One iteration may consume up to + * LZMA_IN_REQUIRED - 1 bytes. + */ + while (dict_has_space(&s->dict) && !rc_limit_exceeded(&s->rc)) { + pos_state = s->dict.pos & s->lzma.pos_mask; + + if (!rc_bit(&s->rc, &s->lzma.is_match[ + s->lzma.state][pos_state])) { + lzma_literal(s); + } else { + if (rc_bit(&s->rc, &s->lzma.is_rep[s->lzma.state])) + lzma_rep_match(s, pos_state); + else + lzma_match(s, pos_state); + + if (!dict_repeat(&s->dict, &s->lzma.len, s->lzma.rep0)) + return false; + } + } + + /* + * Having the range decoder always normalized when we are outside + * this function makes it easier to correctly handle end of the chunk. + */ + rc_normalize(&s->rc); + + return true; +} + +/* + * Reset the LZMA decoder and range decoder state. Dictionary is nore reset + * here, because LZMA state may be reset without resetting the dictionary. + */ +static void lzma_reset(struct xz_dec_lzma2 *s) +{ + uint16_t *probs; + size_t i; + + s->lzma.state = STATE_LIT_LIT; + s->lzma.rep0 = 0; + s->lzma.rep1 = 0; + s->lzma.rep2 = 0; + s->lzma.rep3 = 0; + + /* + * All probabilities are initialized to the same value. This hack + * makes the code smaller by avoiding a separate loop for each + * probability array. + * + * This could be optimized so that only that part of literal + * probabilities that are actually required. In the common case + * we would write 12 KiB less. + */ + probs = s->lzma.is_match[0]; + for (i = 0; i < PROBS_TOTAL; ++i) + probs[i] = RC_BIT_MODEL_TOTAL / 2; + + rc_reset(&s->rc); +} + +/* + * Decode and validate LZMA properties (lc/lp/pb) and calculate the bit masks + * from the decoded lp and pb values. On success, the LZMA decoder state is + * reset and true is returned. + */ +static bool lzma_props(struct xz_dec_lzma2 *s, uint8_t props) +{ + if (props > (4 * 5 + 4) * 9 + 8) + return false; + + s->lzma.pos_mask = 0; + while (props >= 9 * 5) { + props -= 9 * 5; + ++s->lzma.pos_mask; + } + + s->lzma.pos_mask = (1 << s->lzma.pos_mask) - 1; + + s->lzma.literal_pos_mask = 0; + while (props >= 9) { + props -= 9; + ++s->lzma.literal_pos_mask; + } + + s->lzma.lc = props; + + if (s->lzma.lc + s->lzma.literal_pos_mask > 4) + return false; + + s->lzma.literal_pos_mask = (1 << s->lzma.literal_pos_mask) - 1; + + lzma_reset(s); + + return true; +} + +/********* + * LZMA2 * + *********/ + +/* + * The LZMA decoder assumes that if the input limit (s->rc.in_limit) hasn't + * been exceeded, it is safe to read up to LZMA_IN_REQUIRED bytes. This + * wrapper function takes care of making the LZMA decoder's assumption safe. + * + * As long as there is plenty of input left to be decoded in the current LZMA + * chunk, we decode directly from the caller-supplied input buffer until + * there's LZMA_IN_REQUIRED bytes left. Those remaining bytes are copied into + * s->temp.buf, which (hopefully) gets filled on the next call to this + * function. We decode a few bytes from the temporary buffer so that we can + * continue decoding from the caller-supplied input buffer again. + */ +static bool lzma2_lzma(struct xz_dec_lzma2 *s, struct xz_buf *b) +{ + size_t in_avail; + uint32_t tmp; + + in_avail = b->in_size - b->in_pos; + if (s->temp.size > 0 || s->lzma2.compressed == 0) { + tmp = 2 * LZMA_IN_REQUIRED - s->temp.size; + if (tmp > s->lzma2.compressed - s->temp.size) + tmp = s->lzma2.compressed - s->temp.size; + if (tmp > in_avail) + tmp = in_avail; + + memcpy(s->temp.buf + s->temp.size, b->in + b->in_pos, tmp); + + if (s->temp.size + tmp == s->lzma2.compressed) { + memzero(s->temp.buf + s->temp.size + tmp, + sizeof(s->temp.buf) + - s->temp.size - tmp); + s->rc.in_limit = s->temp.size + tmp; + } else if (s->temp.size + tmp < LZMA_IN_REQUIRED) { + s->temp.size += tmp; + b->in_pos += tmp; + return true; + } else { + s->rc.in_limit = s->temp.size + tmp - LZMA_IN_REQUIRED; + } + + s->rc.in = s->temp.buf; + s->rc.in_pos = 0; + + if (!lzma_main(s) || s->rc.in_pos > s->temp.size + tmp) + return false; + + s->lzma2.compressed -= s->rc.in_pos; + + if (s->rc.in_pos < s->temp.size) { + s->temp.size -= s->rc.in_pos; + memmove(s->temp.buf, s->temp.buf + s->rc.in_pos, + s->temp.size); + return true; + } + + b->in_pos += s->rc.in_pos - s->temp.size; + s->temp.size = 0; + } + + in_avail = b->in_size - b->in_pos; + if (in_avail >= LZMA_IN_REQUIRED) { + s->rc.in = b->in; + s->rc.in_pos = b->in_pos; + + if (in_avail >= s->lzma2.compressed + LZMA_IN_REQUIRED) + s->rc.in_limit = b->in_pos + s->lzma2.compressed; + else + s->rc.in_limit = b->in_size - LZMA_IN_REQUIRED; + + if (!lzma_main(s)) + return false; + + in_avail = s->rc.in_pos - b->in_pos; + if (in_avail > s->lzma2.compressed) + return false; + + s->lzma2.compressed -= in_avail; + b->in_pos = s->rc.in_pos; + } + + in_avail = b->in_size - b->in_pos; + if (in_avail < LZMA_IN_REQUIRED) { + if (in_avail > s->lzma2.compressed) + in_avail = s->lzma2.compressed; + + memcpy(s->temp.buf, b->in + b->in_pos, in_avail); + s->temp.size = in_avail; + b->in_pos += in_avail; + } + + return true; +} + +/* + * Take care of the LZMA2 control layer, and forward the job of actual LZMA + * decoding or copying of uncompressed chunks to other functions. + */ +XZ_EXTERN enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s, + struct xz_buf *b) +{ + uint32_t tmp; + + while (b->in_pos < b->in_size || s->lzma2.sequence == SEQ_LZMA_RUN) { + switch (s->lzma2.sequence) { + case SEQ_CONTROL: + /* + * LZMA2 control byte + * + * Exact values: + * 0x00 End marker + * 0x01 Dictionary reset followed by + * an uncompressed chunk + * 0x02 Uncompressed chunk (no dictionary reset) + * + * Highest three bits (s->control & 0xE0): + * 0xE0 Dictionary reset, new properties and state + * reset, followed by LZMA compressed chunk + * 0xC0 New properties and state reset, followed + * by LZMA compressed chunk (no dictionary + * reset) + * 0xA0 State reset using old properties, + * followed by LZMA compressed chunk (no + * dictionary reset) + * 0x80 LZMA chunk (no dictionary or state reset) + * + * For LZMA compressed chunks, the lowest five bits + * (s->control & 1F) are the highest bits of the + * uncompressed size (bits 16-20). + * + * A new LZMA2 stream must begin with a dictionary + * reset. The first LZMA chunk must set new + * properties and reset the LZMA state. + * + * Values that don't match anything described above + * are invalid and we return XZ_DATA_ERROR. + */ + tmp = b->in[b->in_pos++]; + + if (tmp >= 0xE0 || tmp == 0x01) { + s->lzma2.need_props = true; + s->lzma2.need_dict_reset = false; + dict_reset(&s->dict, b); + } else if (s->lzma2.need_dict_reset) { + return XZ_DATA_ERROR; + } + + if (tmp >= 0x80) { + s->lzma2.uncompressed = (tmp & 0x1F) << 16; + s->lzma2.sequence = SEQ_UNCOMPRESSED_1; + + if (tmp >= 0xC0) { + /* + * When there are new properties, + * state reset is done at + * SEQ_PROPERTIES. + */ + s->lzma2.need_props = false; + s->lzma2.next_sequence + = SEQ_PROPERTIES; + + } else if (s->lzma2.need_props) { + return XZ_DATA_ERROR; + + } else { + s->lzma2.next_sequence + = SEQ_LZMA_PREPARE; + if (tmp >= 0xA0) + lzma_reset(s); + } + } else { + if (tmp == 0x00) + return XZ_STREAM_END; + + if (tmp > 0x02) + return XZ_DATA_ERROR; + + s->lzma2.sequence = SEQ_COMPRESSED_0; + s->lzma2.next_sequence = SEQ_COPY; + } + + break; + + case SEQ_UNCOMPRESSED_1: + s->lzma2.uncompressed + += (uint32_t)b->in[b->in_pos++] << 8; + s->lzma2.sequence = SEQ_UNCOMPRESSED_2; + break; + + case SEQ_UNCOMPRESSED_2: + s->lzma2.uncompressed + += (uint32_t)b->in[b->in_pos++] + 1; + s->lzma2.sequence = SEQ_COMPRESSED_0; + break; + + case SEQ_COMPRESSED_0: + s->lzma2.compressed + = (uint32_t)b->in[b->in_pos++] << 8; + s->lzma2.sequence = SEQ_COMPRESSED_1; + break; + + case SEQ_COMPRESSED_1: + s->lzma2.compressed + += (uint32_t)b->in[b->in_pos++] + 1; + s->lzma2.sequence = s->lzma2.next_sequence; + break; + + case SEQ_PROPERTIES: + if (!lzma_props(s, b->in[b->in_pos++])) + return XZ_DATA_ERROR; + + s->lzma2.sequence = SEQ_LZMA_PREPARE; + + case SEQ_LZMA_PREPARE: + if (s->lzma2.compressed < RC_INIT_BYTES) + return XZ_DATA_ERROR; + + if (!rc_read_init(&s->rc, b)) + return XZ_OK; + + s->lzma2.compressed -= RC_INIT_BYTES; + s->lzma2.sequence = SEQ_LZMA_RUN; + + case SEQ_LZMA_RUN: + /* + * Set dictionary limit to indicate how much we want + * to be encoded at maximum. Decode new data into the + * dictionary. Flush the new data from dictionary to + * b->out. Check if we finished decoding this chunk. + * In case the dictionary got full but we didn't fill + * the output buffer yet, we may run this loop + * multiple times without changing s->lzma2.sequence. + */ + dict_limit(&s->dict, min_t(size_t, + b->out_size - b->out_pos, + s->lzma2.uncompressed)); + if (!lzma2_lzma(s, b)) + return XZ_DATA_ERROR; + + s->lzma2.uncompressed -= dict_flush(&s->dict, b); + + if (s->lzma2.uncompressed == 0) { + if (s->lzma2.compressed > 0 || s->lzma.len > 0 + || !rc_is_finished(&s->rc)) + return XZ_DATA_ERROR; + + rc_reset(&s->rc); + s->lzma2.sequence = SEQ_CONTROL; + + } else if (b->out_pos == b->out_size + || (b->in_pos == b->in_size + && s->temp.size + < s->lzma2.compressed)) { + return XZ_OK; + } + + break; + + case SEQ_COPY: + dict_uncompressed(&s->dict, b, &s->lzma2.compressed); + if (s->lzma2.compressed > 0) + return XZ_OK; + + s->lzma2.sequence = SEQ_CONTROL; + break; + } + } + + return XZ_OK; +} + +XZ_EXTERN struct xz_dec_lzma2 *xz_dec_lzma2_create(enum xz_mode mode, + uint32_t dict_max) +{ + struct xz_dec_lzma2 *s = kmalloc(sizeof(*s), GFP_KERNEL); + if (s == NULL) + return NULL; + + s->dict.mode = mode; + s->dict.size_max = dict_max; + + if (DEC_IS_PREALLOC(mode)) { + s->dict.buf = vmalloc(dict_max); + if (s->dict.buf == NULL) { + kfree(s); + return NULL; + } + } else if (DEC_IS_DYNALLOC(mode)) { + s->dict.buf = NULL; + s->dict.allocated = 0; + } + + return s; +} + +XZ_EXTERN enum xz_ret xz_dec_lzma2_reset(struct xz_dec_lzma2 *s, uint8_t props) +{ + /* This limits dictionary size to 3 GiB to keep parsing simpler. */ + if (props > 39) + return XZ_OPTIONS_ERROR; + + s->dict.size = 2 + (props & 1); + s->dict.size <<= (props >> 1) + 11; + + if (DEC_IS_MULTI(s->dict.mode)) { + if (s->dict.size > s->dict.size_max) + return XZ_MEMLIMIT_ERROR; + + s->dict.end = s->dict.size; + + if (DEC_IS_DYNALLOC(s->dict.mode)) { + if (s->dict.allocated < s->dict.size) { + vfree(s->dict.buf); + s->dict.buf = vmalloc(s->dict.size); + if (s->dict.buf == NULL) { + s->dict.allocated = 0; + return XZ_MEM_ERROR; + } + } + } + } + + s->lzma.len = 0; + + s->lzma2.sequence = SEQ_CONTROL; + s->lzma2.need_dict_reset = true; + + s->temp.size = 0; + + return XZ_OK; +} + +XZ_EXTERN void xz_dec_lzma2_end(struct xz_dec_lzma2 *s) +{ + if (DEC_IS_MULTI(s->dict.mode)) + vfree(s->dict.buf); + + kfree(s); +} diff --git a/lib/xz/xz_dec_stream.c b/lib/xz/xz_dec_stream.c new file mode 100644 index 0000000..ac809b1 --- /dev/null +++ b/lib/xz/xz_dec_stream.c @@ -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); + } +} diff --git a/lib/xz/xz_dec_syms.c b/lib/xz/xz_dec_syms.c new file mode 100644 index 0000000..32eb3c0 --- /dev/null +++ b/lib/xz/xz_dec_syms.c @@ -0,0 +1,26 @@ +/* + * XZ decoder module information + * + * 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 <linux/module.h> +#include <linux/xz.h> + +EXPORT_SYMBOL(xz_dec_init); +EXPORT_SYMBOL(xz_dec_reset); +EXPORT_SYMBOL(xz_dec_run); +EXPORT_SYMBOL(xz_dec_end); + +MODULE_DESCRIPTION("XZ decompressor"); +MODULE_VERSION("1.0"); +MODULE_AUTHOR("Lasse Collin <lasse.collin@tukaani.org> and Igor Pavlov"); + +/* + * This code is in the public domain, but in Linux it's simplest to just + * say it's GPL and consider the authors as the copyright holders. + */ +MODULE_LICENSE("GPL"); diff --git a/lib/xz/xz_dec_test.c b/lib/xz/xz_dec_test.c new file mode 100644 index 0000000..da28a19 --- /dev/null +++ b/lib/xz/xz_dec_test.c @@ -0,0 +1,220 @@ +/* + * XZ decoder tester + * + * 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 <linux/kernel.h> +#include <linux/module.h> +#include <linux/fs.h> +#include <linux/uaccess.h> +#include <linux/crc32.h> +#include <linux/xz.h> + +/* Maximum supported dictionary size */ +#define DICT_MAX (1 << 20) + +/* Device name to pass to register_chrdev(). */ +#define DEVICE_NAME "xz_dec_test" + +/* Dynamically allocated device major number */ +static int device_major; + +/* + * We reuse the same decoder state, and thus can decode only one + * file at a time. + */ +static bool device_is_open; + +/* XZ decoder state */ +static struct xz_dec *state; + +/* + * Return value of xz_dec_run(). We need to avoid calling xz_dec_run() after + * it has returned XZ_STREAM_END, so we make this static. + */ +static enum xz_ret ret; + +/* + * Input and output buffers. The input buffer is used as a temporary safe + * place for the data coming from the userspace. + */ +static uint8_t buffer_in[1024]; +static uint8_t buffer_out[1024]; + +/* + * Structure to pass the input and output buffers to the XZ decoder. + * A few of the fields are never modified so we initialize them here. + */ +static struct xz_buf buffers = { + .in = buffer_in, + .out = buffer_out, + .out_size = sizeof(buffer_out) +}; + +/* + * CRC32 of uncompressed data. This is used to give the user a simple way + * to check that the decoder produces correct output. + */ +static uint32_t crc; + +static int xz_dec_test_open(struct inode *i, struct file *f) +{ + if (device_is_open) + return -EBUSY; + + device_is_open = true; + + xz_dec_reset(state); + ret = XZ_OK; + crc = 0xFFFFFFFF; + + buffers.in_pos = 0; + buffers.in_size = 0; + buffers.out_pos = 0; + + printk(KERN_INFO DEVICE_NAME ": opened\n"); + return 0; +} + +static int xz_dec_test_release(struct inode *i, struct file *f) +{ + device_is_open = false; + + if (ret == XZ_OK) + printk(KERN_INFO DEVICE_NAME ": input was truncated\n"); + + printk(KERN_INFO DEVICE_NAME ": closed\n"); + return 0; +} + +/* + * Decode the data given to us from the userspace. CRC32 of the uncompressed + * data is calculated and is printed at the end of successful decoding. The + * uncompressed data isn't stored anywhere for further use. + * + * The .xz file must have exactly one Stream and no Stream Padding. The data + * after the first Stream is considered to be garbage. + */ +static ssize_t xz_dec_test_write(struct file *file, const char __user *buf, + size_t size, loff_t *pos) +{ + size_t remaining; + + if (ret != XZ_OK) { + if (size > 0) + printk(KERN_INFO DEVICE_NAME ": %zu bytes of " + "garbage at the end of the file\n", + size); + + return -ENOSPC; + } + + printk(KERN_INFO DEVICE_NAME ": decoding %zu bytes of input\n", + size); + + remaining = size; + while ((remaining > 0 || buffers.out_pos == buffers.out_size) + && ret == XZ_OK) { + if (buffers.in_pos == buffers.in_size) { + buffers.in_pos = 0; + buffers.in_size = min(remaining, sizeof(buffer_in)); + if (copy_from_user(buffer_in, buf, buffers.in_size)) + return -EFAULT; + + buf += buffers.in_size; + remaining -= buffers.in_size; + } + + buffers.out_pos = 0; + ret = xz_dec_run(state, &buffers); + crc = crc32(crc, buffer_out, buffers.out_pos); + } + + switch (ret) { + case XZ_OK: + printk(KERN_INFO DEVICE_NAME ": XZ_OK\n"); + return size; + + case XZ_STREAM_END: + printk(KERN_INFO DEVICE_NAME ": XZ_STREAM_END, " + "CRC32 = 0x%08X\n", ~crc); + return size - remaining - (buffers.in_size - buffers.in_pos); + + case XZ_MEMLIMIT_ERROR: + printk(KERN_INFO DEVICE_NAME ": XZ_MEMLIMIT_ERROR\n"); + break; + + case XZ_FORMAT_ERROR: + printk(KERN_INFO DEVICE_NAME ": XZ_FORMAT_ERROR\n"); + break; + + case XZ_OPTIONS_ERROR: + printk(KERN_INFO DEVICE_NAME ": XZ_OPTIONS_ERROR\n"); + break; + + case XZ_DATA_ERROR: + printk(KERN_INFO DEVICE_NAME ": XZ_DATA_ERROR\n"); + break; + + case XZ_BUF_ERROR: + printk(KERN_INFO DEVICE_NAME ": XZ_BUF_ERROR\n"); + break; + + default: + printk(KERN_INFO DEVICE_NAME ": Bug detected!\n"); + break; + } + + return -EIO; +} + +/* Allocate the XZ decoder state and register the character device. */ +static int __init xz_dec_test_init(void) +{ + static const struct file_operations fileops = { + .owner = THIS_MODULE, + .open = &xz_dec_test_open, + .release = &xz_dec_test_release, + .write = &xz_dec_test_write + }; + + state = xz_dec_init(XZ_PREALLOC, DICT_MAX); + if (state == NULL) + return -ENOMEM; + + device_major = register_chrdev(0, DEVICE_NAME, &fileops); + if (device_major < 0) { + xz_dec_end(state); + return device_major; + } + + printk(KERN_INFO DEVICE_NAME ": module loaded\n"); + printk(KERN_INFO DEVICE_NAME ": Create a device node with " + "'mknod " DEVICE_NAME " c %d 0' and write .xz files " + "to it.\n", device_major); + return 0; +} + +static void __exit xz_dec_test_exit(void) +{ + unregister_chrdev(device_major, DEVICE_NAME); + xz_dec_end(state); + printk(KERN_INFO DEVICE_NAME ": module unloaded\n"); +} + +module_init(xz_dec_test_init); +module_exit(xz_dec_test_exit); + +MODULE_DESCRIPTION("XZ decompressor tester"); +MODULE_VERSION("1.0"); +MODULE_AUTHOR("Lasse Collin <lasse.collin@tukaani.org>"); + +/* + * This code is in the public domain, but in Linux it's simplest to just + * say it's GPL and consider the authors as the copyright holders. + */ +MODULE_LICENSE("GPL"); diff --git a/lib/xz/xz_lzma2.h b/lib/xz/xz_lzma2.h new file mode 100644 index 0000000..071d67b --- /dev/null +++ b/lib/xz/xz_lzma2.h @@ -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 diff --git a/lib/xz/xz_private.h b/lib/xz/xz_private.h new file mode 100644 index 0000000..a65633e --- /dev/null +++ b/lib/xz/xz_private.h @@ -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 <asm/byteorder.h> +# include <asm/unaligned.h> + /* XZ_PREBOOT may be defined only via decompress_unxz.c. */ +# ifndef XZ_PREBOOT +# include <linux/slab.h> +# include <linux/vmalloc.h> +# include <linux/string.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 diff --git a/lib/xz/xz_stream.h b/lib/xz/xz_stream.h new file mode 100644 index 0000000..66cb5a7 --- /dev/null +++ b/lib/xz/xz_stream.h @@ -0,0 +1,62 @@ +/* + * 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 +# include <linux/crc32.h> +# 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 |