diff options
Diffstat (limited to 'lib/xz/xz_dec_bcj.c')
| -rw-r--r-- | lib/xz/xz_dec_bcj.c | 284 |
1 files changed, 176 insertions, 108 deletions
diff --git a/lib/xz/xz_dec_bcj.c b/lib/xz/xz_dec_bcj.c index a768e6d28bbb..610d58d947ab 100644 --- a/lib/xz/xz_dec_bcj.c +++ b/lib/xz/xz_dec_bcj.c @@ -1,11 +1,10 @@ +// SPDX-License-Identifier: 0BSD + /* * 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. + * Igor Pavlov <https://7-zip.org/> */ #include "xz_private.h" @@ -21,10 +20,11 @@ struct xz_dec_bcj { 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 */ + BCJ_SPARC = 9, /* Big or little endian */ + BCJ_ARM64 = 10, /* AArch64 */ + BCJ_RISCV = 11 /* RV32GQC_Zfh, RV64GQC_Zfh */ } type; /* @@ -162,7 +162,9 @@ 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) { + size &= ~(size_t)3; + + for (i = 0; i < size; i += 4) { instr = get_unaligned_be32(buf + i); if ((instr & 0xFC000003) == 0x48000001) { instr &= 0x03FFFFFC; @@ -177,97 +179,15 @@ static size_t bcj_powerpc(struct xz_dec_bcj *s, uint8_t *buf, size_t size) } #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) { + size &= ~(size_t)3; + + for (i = 0; i < 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); @@ -290,7 +210,12 @@ 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 (size < 4) + return 0; + + size -= 4; + + for (i = 0; i <= size; i += 2) { if ((buf[i + 1] & 0xF8) == 0xF0 && (buf[i + 3] & 0xF8) == 0xF8) { addr = (((uint32_t)buf[i + 1] & 0x07) << 19) @@ -318,7 +243,9 @@ 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) { + size &= ~(size_t)3; + + for (i = 0; i < size; i += 4) { instr = get_unaligned_be32(buf + i); if ((instr >> 22) == 0x100 || (instr >> 22) == 0x1FF) { instr <<= 2; @@ -334,6 +261,140 @@ static size_t bcj_sparc(struct xz_dec_bcj *s, uint8_t *buf, size_t size) } #endif +#ifdef XZ_DEC_ARM64 +static size_t bcj_arm64(struct xz_dec_bcj *s, uint8_t *buf, size_t size) +{ + size_t i; + uint32_t instr; + uint32_t addr; + + size &= ~(size_t)3; + + for (i = 0; i < size; i += 4) { + instr = get_unaligned_le32(buf + i); + + if ((instr >> 26) == 0x25) { + /* BL instruction */ + addr = instr - ((s->pos + (uint32_t)i) >> 2); + instr = 0x94000000 | (addr & 0x03FFFFFF); + put_unaligned_le32(instr, buf + i); + + } else if ((instr & 0x9F000000) == 0x90000000) { + /* ADRP instruction */ + addr = ((instr >> 29) & 3) | ((instr >> 3) & 0x1FFFFC); + + /* Only convert values in the range +/-512 MiB. */ + if ((addr + 0x020000) & 0x1C0000) + continue; + + addr -= (s->pos + (uint32_t)i) >> 12; + + instr &= 0x9000001F; + instr |= (addr & 3) << 29; + instr |= (addr & 0x03FFFC) << 3; + instr |= (0U - (addr & 0x020000)) & 0xE00000; + + put_unaligned_le32(instr, buf + i); + } + } + + return i; +} +#endif + +#ifdef XZ_DEC_RISCV +static size_t bcj_riscv(struct xz_dec_bcj *s, uint8_t *buf, size_t size) +{ + size_t i; + uint32_t b1; + uint32_t b2; + uint32_t b3; + uint32_t instr; + uint32_t instr2; + uint32_t instr2_rs1; + uint32_t addr; + + if (size < 8) + return 0; + + size -= 8; + + for (i = 0; i <= size; i += 2) { + instr = buf[i]; + + if (instr == 0xEF) { + /* JAL */ + b1 = buf[i + 1]; + if ((b1 & 0x0D) != 0) + continue; + + b2 = buf[i + 2]; + b3 = buf[i + 3]; + + addr = ((b1 & 0xF0) << 13) | (b2 << 9) | (b3 << 1); + addr -= s->pos + (uint32_t)i; + + buf[i + 1] = (uint8_t)((b1 & 0x0F) + | ((addr >> 8) & 0xF0)); + + buf[i + 2] = (uint8_t)(((addr >> 16) & 0x0F) + | ((addr >> 7) & 0x10) + | ((addr << 4) & 0xE0)); + + buf[i + 3] = (uint8_t)(((addr >> 4) & 0x7F) + | ((addr >> 13) & 0x80)); + + i += 4 - 2; + + } else if ((instr & 0x7F) == 0x17) { + /* AUIPC */ + instr |= (uint32_t)buf[i + 1] << 8; + instr |= (uint32_t)buf[i + 2] << 16; + instr |= (uint32_t)buf[i + 3] << 24; + + if (instr & 0xE80) { + /* AUIPC's rd doesn't equal x0 or x2. */ + instr2 = get_unaligned_le32(buf + i + 4); + + if (((instr << 8) ^ (instr2 - 3)) & 0xF8003) { + i += 6 - 2; + continue; + } + + addr = (instr & 0xFFFFF000) + (instr2 >> 20); + + instr = 0x17 | (2 << 7) | (instr2 << 12); + instr2 = addr; + } else { + /* AUIPC's rd equals x0 or x2. */ + instr2_rs1 = instr >> 27; + + if ((uint32_t)((instr - 0x3117) << 18) + >= (instr2_rs1 & 0x1D)) { + i += 4 - 2; + continue; + } + + addr = get_unaligned_be32(buf + i + 4); + addr -= s->pos + (uint32_t)i; + + instr2 = (instr >> 12) | (addr << 20); + + instr = 0x17 | (instr2_rs1 << 7) + | ((addr + 0x800) & 0xFFFFF000); + } + + put_unaligned_le32(instr, buf + i); + put_unaligned_le32(instr2, buf + i + 4); + + i += 8 - 2; + } + } + + return i; +} +#endif + /* * Apply the selected BCJ filter. Update *pos and s->pos to match the amount * of data that got filtered. @@ -361,11 +422,6 @@ static void bcj_apply(struct xz_dec_bcj *s, 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); @@ -381,6 +437,16 @@ static void bcj_apply(struct xz_dec_bcj *s, filtered = bcj_sparc(s, buf, size); break; #endif +#ifdef XZ_DEC_ARM64 + case BCJ_ARM64: + filtered = bcj_arm64(s, buf, size); + break; +#endif +#ifdef XZ_DEC_RISCV + case BCJ_RISCV: + filtered = bcj_riscv(s, buf, size); + break; +#endif default: /* Never reached but silence compiler warnings. */ filtered = 0; @@ -414,15 +480,14 @@ static void bcj_flush(struct xz_dec_bcj *s, struct xz_buf *b) * 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) +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 + * immediately 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) { @@ -524,7 +589,7 @@ XZ_EXTERN enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s, return s->ret; } -XZ_EXTERN struct xz_dec_bcj *xz_dec_bcj_create(bool single_call) +struct xz_dec_bcj *xz_dec_bcj_create(bool single_call) { struct xz_dec_bcj *s = kmalloc(sizeof(*s), GFP_KERNEL); if (s != NULL) @@ -533,7 +598,7 @@ XZ_EXTERN struct xz_dec_bcj *xz_dec_bcj_create(bool single_call) return s; } -XZ_EXTERN enum xz_ret xz_dec_bcj_reset(struct xz_dec_bcj *s, uint8_t id) +enum xz_ret xz_dec_bcj_reset(struct xz_dec_bcj *s, uint8_t id) { switch (id) { #ifdef XZ_DEC_X86 @@ -542,9 +607,6 @@ XZ_EXTERN enum xz_ret xz_dec_bcj_reset(struct xz_dec_bcj *s, uint8_t id) #ifdef XZ_DEC_POWERPC case BCJ_POWERPC: #endif -#ifdef XZ_DEC_IA64 - case BCJ_IA64: -#endif #ifdef XZ_DEC_ARM case BCJ_ARM: #endif @@ -554,6 +616,12 @@ XZ_EXTERN enum xz_ret xz_dec_bcj_reset(struct xz_dec_bcj *s, uint8_t id) #ifdef XZ_DEC_SPARC case BCJ_SPARC: #endif +#ifdef XZ_DEC_ARM64 + case BCJ_ARM64: +#endif +#ifdef XZ_DEC_RISCV + case BCJ_RISCV: +#endif break; default: |