1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189 |
- /* xz_dec_lzma2.c - LZMA2 decoder */
- /*
- * GRUB -- GRand Unified Bootloader
- * Copyright (C) 2010 Free Software Foundation, Inc.
- *
- * GRUB is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GRUB is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GRUB. If not, see <http://www.gnu.org/licenses/>.
- */
- /*
- * This file is based on code from XZ embedded project
- * http://tukaani.org/xz/embedded.html
- */
- #include "xz_private.h"
- #include "xz_lzma2.h"
- #pragma GCC diagnostic warning "-Wattributes"
- /*
- * 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 <= allocated
- *
- * 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;
- /*
- * Amount of memory allocated for the dictionary. A special
- * value of zero indicates that we are in single-call mode,
- * where the output buffer works as the dictionary.
- */
- uint32_t allocated;
- };
- /* 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 {
- /*
- * 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 */
- /* Types of the most recently seen LZMA symbols */
- enum lzma_state state;
- /* Distances of latest four matches */
- uint32_t rep0;
- uint32_t rep1;
- uint32_t rep2;
- uint32_t rep3;
- /*
- * Length of a match. This is updated so that dict_repeat can
- * be called again to finish repeating the whole match.
- */
- uint32_t len;
- /* 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 xz_dec_lzma2 {
- /* LZMA2 */
- struct {
- /* 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;
- } lzma2;
- /*
- * 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;
- struct dictionary dict;
- struct rc_dec rc;
- struct lzma_dec lzma;
- };
- /**************
- * 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 (dict->allocated == 0) {
- 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 b)
- {
- dict->buf[dict->pos++] = b;
- 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 (dict->allocated != 0) {
- 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 (dict->allocated != 0) {
- 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.
- */
- 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;
- /* Fall through */
- 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;
- /* Fall through */
- 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;
- }
- #ifdef GRUB_EMBED_DECOMPRESSOR
- #include <grub/decompressor.h>
- static struct xz_dec_lzma2 lzma2;
- #endif
- struct xz_dec_lzma2 * xz_dec_lzma2_create(uint32_t dict_max)
- {
- struct xz_dec_lzma2 *s;
- #ifndef GRUB_EMBED_DECOMPRESSOR
- /* Maximum supported dictionary by this implementation is 3 GiB. */
- if (dict_max > ((uint32_t)3 << 30))
- return NULL;
- s = kmalloc(sizeof(*s), GFP_KERNEL);
- if (s == NULL)
- return NULL;
- if (dict_max > 0) {
- s->dict.buf = vmalloc(dict_max);
- if (s->dict.buf == NULL) {
- kfree(s);
- return NULL;
- }
- }
- #else
- s = &lzma2;
- s->dict.buf = grub_decompressor_scratch;
- #endif
- s->dict.allocated = dict_max;
- return s;
- }
- enum xz_ret xz_dec_lzma2_reset(
- struct xz_dec_lzma2 *s, uint8_t props)
- {
- /* This limits dictionary size to 3 GiB (39) to keep parsing simpler. */
- if (props > ( min (DICT_BIT_SIZE,39)) )
- return XZ_OPTIONS_ERROR;
- s->dict.size = 2 + (props & 1);
- s->dict.size <<= (props >> 1) + 11;
- #ifndef GRUB_EMBED_DECOMPRESSOR
- if (s->dict.allocated > 0 && s->dict.allocated < s->dict.size)
- {
- /* enlarge dictionary buffer */
- uint8_t * newdict = realloc(s->dict.buf,s->dict.size);
- if (! newdict)
- return XZ_MEMLIMIT_ERROR;
- s->dict.buf = newdict;
- s->dict.allocated = s->dict.size;
- }
- #endif
- s->dict.end = s->dict.size;
- s->lzma.len = 0;
- s->lzma2.sequence = SEQ_CONTROL;
- s->lzma2.need_dict_reset = true;
- s->temp.size = 0;
- return XZ_OK;
- }
- void xz_dec_lzma2_end(struct xz_dec_lzma2 *s __attribute__ ((unused)))
- {
- #ifndef GRUB_EMBED_DECOMPRESSOR
- if (s->dict.allocated > 0)
- vfree(s->dict.buf);
- kfree(s);
- #endif
- }
|