diff options
Diffstat (limited to 'src/liblzma')
47 files changed, 126 insertions, 110 deletions
diff --git a/src/liblzma/api/lzma.h b/src/liblzma/api/lzma.h index aa88e4243a29..122dab80d357 100644 --- a/src/liblzma/api/lzma.h +++ b/src/liblzma/api/lzma.h @@ -224,7 +224,8 @@ # else # define lzma_nothrow throw() # endif -# elif __GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 3) +# elif defined(__GNUC__) && (__GNUC__ > 3 \ + || (__GNUC__ == 3 && __GNUC_MINOR__ >= 3)) # define lzma_nothrow __attribute__((__nothrow__)) # else # define lzma_nothrow @@ -241,7 +242,7 @@ * break anything if these are sometimes enabled and sometimes not, only * affects warnings and optimizations. */ -#if __GNUC__ >= 3 +#if defined(__GNUC__) && __GNUC__ >= 3 # ifndef lzma_attribute # define lzma_attribute(attr) __attribute__(attr) # endif diff --git a/src/liblzma/api/lzma/block.h b/src/liblzma/api/lzma/block.h index 7bdcfd7cbe0c..962f38779cc7 100644 --- a/src/liblzma/api/lzma/block.h +++ b/src/liblzma/api/lzma/block.h @@ -448,7 +448,7 @@ extern LZMA_API(lzma_vli) lzma_block_total_size(const lzma_block *block) * - LZMA_MEM_ERROR * - LZMA_OPTIONS_ERROR * - LZMA_UNSUPPORTED_CHECK: block->check specifies a Check ID - * that is not supported by this buid of liblzma. Initializing + * that is not supported by this build of liblzma. Initializing * the encoder failed. * - LZMA_PROG_ERROR */ diff --git a/src/liblzma/api/lzma/filter.h b/src/liblzma/api/lzma/filter.h index 4e78752b8f79..8c8593147658 100644 --- a/src/liblzma/api/lzma/filter.h +++ b/src/liblzma/api/lzma/filter.h @@ -341,9 +341,10 @@ extern LZMA_API(lzma_ret) lzma_properties_encode( * \param filter filter->id must have been set to the correct * Filter ID. filter->options doesn't need to be * initialized (it's not freed by this function). The - * decoded options will be stored to filter->options. - * filter->options is set to NULL if there are no - * properties or if an error occurs. + * decoded options will be stored in filter->options; + * it's application's responsibility to free it when + * appropriate. filter->options is set to NULL if + * there are no properties or if an error occurs. * \param allocator Custom memory allocator used to allocate the * options. Set to NULL to use the default malloc(), * and in case of an error, also free(). diff --git a/src/liblzma/api/lzma/hardware.h b/src/liblzma/api/lzma/hardware.h index 5321d9af8e46..47481f2581f7 100644 --- a/src/liblzma/api/lzma/hardware.h +++ b/src/liblzma/api/lzma/hardware.h @@ -6,7 +6,7 @@ * ways to limit the resource usage. Applications linking against liblzma * need to do the actual decisions how much resources to let liblzma to use. * To ease making these decisions, liblzma provides functions to find out - * the relevant capabilities of the underlaying hardware. Currently there + * the relevant capabilities of the underlying hardware. Currently there * is only a function to find out the amount of RAM, but in the future there * will be also a function to detect how many concurrent threads the system * can run. diff --git a/src/liblzma/api/lzma/lzma12.h b/src/liblzma/api/lzma/lzma12.h index 4e32fa3a214a..df5f23b61a43 100644 --- a/src/liblzma/api/lzma/lzma12.h +++ b/src/liblzma/api/lzma/lzma12.h @@ -301,7 +301,7 @@ typedef struct { * (2^ pb =2^2=4), which is often a good choice when there's * no better guess. * - * When the aligment is known, setting pb accordingly may reduce + * When the alignment is known, setting pb accordingly may reduce * the file size a little. E.g. with text files having one-byte * alignment (US-ASCII, ISO-8859-*, UTF-8), setting pb=0 can * improve compression slightly. For UTF-16 text, pb=1 is a good diff --git a/src/liblzma/api/lzma/version.h b/src/liblzma/api/lzma/version.h index 143c7dea69f5..2bf3eaed24fa 100644 --- a/src/liblzma/api/lzma/version.h +++ b/src/liblzma/api/lzma/version.h @@ -22,7 +22,7 @@ */ #define LZMA_VERSION_MAJOR 5 #define LZMA_VERSION_MINOR 2 -#define LZMA_VERSION_PATCH 4 +#define LZMA_VERSION_PATCH 5 #define LZMA_VERSION_STABILITY LZMA_VERSION_STABILITY_STABLE #ifndef LZMA_VERSION_COMMIT diff --git a/src/liblzma/api/lzma/vli.h b/src/liblzma/api/lzma/vli.h index 9ad13f2e2fc4..1b7a952a406d 100644 --- a/src/liblzma/api/lzma/vli.h +++ b/src/liblzma/api/lzma/vli.h @@ -54,7 +54,7 @@ * * Valid VLI values are in the range [0, LZMA_VLI_MAX]. Unknown value is * indicated with LZMA_VLI_UNKNOWN, which is the maximum value of the - * underlaying integer type. + * underlying integer type. * * lzma_vli will be uint64_t for the foreseeable future. If a bigger size * is needed in the future, it is guaranteed that 2 * LZMA_VLI_MAX will diff --git a/src/liblzma/check/crc32_fast.c b/src/liblzma/check/crc32_fast.c index 3de02638d776..eed7350582e4 100644 --- a/src/liblzma/check/crc32_fast.c +++ b/src/liblzma/check/crc32_fast.c @@ -49,7 +49,7 @@ lzma_crc32(const uint8_t *buf, size_t size, uint32_t crc) // Calculate the CRC32 using the slice-by-eight algorithm. while (buf < limit) { - crc ^= *(const uint32_t *)(buf); + crc ^= aligned_read32ne(buf); buf += 4; crc = lzma_crc32_table[7][A(crc)] @@ -57,7 +57,7 @@ lzma_crc32(const uint8_t *buf, size_t size, uint32_t crc) ^ lzma_crc32_table[5][C(crc)] ^ lzma_crc32_table[4][D(crc)]; - const uint32_t tmp = *(const uint32_t *)(buf); + const uint32_t tmp = aligned_read32ne(buf); buf += 4; // At least with some compilers, it is critical for diff --git a/src/liblzma/check/crc32_table.c b/src/liblzma/check/crc32_table.c index 368874eb79d4..b11762ae0ac7 100644 --- a/src/liblzma/check/crc32_table.c +++ b/src/liblzma/check/crc32_table.c @@ -12,6 +12,9 @@ #include "common.h" +// Having the declaration here silences clang -Wmissing-variable-declarations. +extern const uint32_t lzma_crc32_table[8][256]; + #ifdef WORDS_BIGENDIAN # include "crc32_table_be.h" #else diff --git a/src/liblzma/check/crc64_fast.c b/src/liblzma/check/crc64_fast.c index 52af29ed48d8..8af54cda7b5c 100644 --- a/src/liblzma/check/crc64_fast.c +++ b/src/liblzma/check/crc64_fast.c @@ -47,9 +47,9 @@ lzma_crc64(const uint8_t *buf, size_t size, uint64_t crc) while (buf < limit) { #ifdef WORDS_BIGENDIAN const uint32_t tmp = (crc >> 32) - ^ *(const uint32_t *)(buf); + ^ aligned_read32ne(buf); #else - const uint32_t tmp = crc ^ *(const uint32_t *)(buf); + const uint32_t tmp = crc ^ aligned_read32ne(buf); #endif buf += 4; diff --git a/src/liblzma/check/crc64_table.c b/src/liblzma/check/crc64_table.c index 1fbcd94703c7..7560eb0a3b15 100644 --- a/src/liblzma/check/crc64_table.c +++ b/src/liblzma/check/crc64_table.c @@ -12,6 +12,9 @@ #include "common.h" +// Having the declaration here silences clang -Wmissing-variable-declarations. +extern const uint64_t lzma_crc64_table[4][256]; + #ifdef WORDS_BIGENDIAN # include "crc64_table_be.h" #else diff --git a/src/liblzma/common/alone_decoder.c b/src/liblzma/common/alone_decoder.c index 77d0a9b1002c..239b230ef19b 100644 --- a/src/liblzma/common/alone_decoder.c +++ b/src/liblzma/common/alone_decoder.c @@ -50,8 +50,7 @@ typedef struct { static lzma_ret -alone_decode(void *coder_ptr, - const lzma_allocator *allocator lzma_attribute((__unused__)), +alone_decode(void *coder_ptr, const lzma_allocator *allocator, const uint8_t *restrict in, size_t *restrict in_pos, size_t in_size, uint8_t *restrict out, size_t *restrict out_pos, size_t out_size, diff --git a/src/liblzma/common/alone_encoder.c b/src/liblzma/common/alone_encoder.c index 4853cfd1d648..96c1db70cc6a 100644 --- a/src/liblzma/common/alone_encoder.c +++ b/src/liblzma/common/alone_encoder.c @@ -1,7 +1,7 @@ /////////////////////////////////////////////////////////////////////////////// // -/// \file alone_decoder.c -/// \brief Decoder for LZMA_Alone files +/// \file alone_encoder.c +/// \brief Encoder for LZMA_Alone files // // Author: Lasse Collin // @@ -31,8 +31,7 @@ typedef struct { static lzma_ret -alone_encode(void *coder_ptr, - const lzma_allocator *allocator lzma_attribute((__unused__)), +alone_encode(void *coder_ptr, const lzma_allocator *allocator, const uint8_t *restrict in, size_t *restrict in_pos, size_t in_size, uint8_t *restrict out, size_t *restrict out_pos, size_t out_size, @@ -122,7 +121,7 @@ alone_encoder_init(lzma_next_coder *next, const lzma_allocator *allocator, if (d != UINT32_MAX) ++d; - unaligned_write32le(coder->header + 1, d); + write32le(coder->header + 1, d); // - Uncompressed size (always unknown and using EOPM) memset(coder->header + 1 + 4, 0xFF, 8); diff --git a/src/liblzma/common/block_header_decoder.c b/src/liblzma/common/block_header_decoder.c index 1dd982f6bd68..2e1135dd639a 100644 --- a/src/liblzma/common/block_header_decoder.c +++ b/src/liblzma/common/block_header_decoder.c @@ -67,7 +67,7 @@ lzma_block_header_decode(lzma_block *block, const size_t in_size = block->header_size - 4; // Verify CRC32 - if (lzma_crc32(in, in_size, 0) != unaligned_read32le(in + in_size)) + if (lzma_crc32(in, in_size, 0) != read32le(in + in_size)) return LZMA_DATA_ERROR; // Check for unsupported flags. @@ -98,7 +98,7 @@ lzma_block_header_decode(lzma_block *block, block->uncompressed_size = LZMA_VLI_UNKNOWN; // Filter Flags - const size_t filter_count = (in[1] & 3) + 1; + const size_t filter_count = (in[1] & 3U) + 1; for (size_t i = 0; i < filter_count; ++i) { const lzma_ret ret = lzma_filter_flags_decode( &block->filters[i], allocator, diff --git a/src/liblzma/common/block_header_encoder.c b/src/liblzma/common/block_header_encoder.c index 5c5f5424ae85..160425d27a35 100644 --- a/src/liblzma/common/block_header_encoder.c +++ b/src/liblzma/common/block_header_encoder.c @@ -126,7 +126,7 @@ lzma_block_header_encode(const lzma_block *block, uint8_t *out) memzero(out + out_pos, out_size - out_pos); // CRC32 - unaligned_write32le(out + out_size, lzma_crc32(out, out_size, 0)); + write32le(out + out_size, lzma_crc32(out, out_size, 0)); return LZMA_OK; } diff --git a/src/liblzma/common/block_util.c b/src/liblzma/common/block_util.c index 00c7fe8d5196..acb311142c21 100644 --- a/src/liblzma/common/block_util.c +++ b/src/liblzma/common/block_util.c @@ -1,6 +1,6 @@ /////////////////////////////////////////////////////////////////////////////// // -/// \file block_header.c +/// \file block_util.c /// \brief Utility functions to handle lzma_block // // Author: Lasse Collin diff --git a/src/liblzma/common/common.c b/src/liblzma/common/common.c index 57e3f8ebd62a..cf714e5e43b4 100644 --- a/src/liblzma/common/common.c +++ b/src/liblzma/common/common.c @@ -1,6 +1,6 @@ /////////////////////////////////////////////////////////////////////////////// // -/// \file common.h +/// \file common.c /// \brief Common functions needed in many places in liblzma // // Author: Lasse Collin @@ -99,7 +99,11 @@ lzma_bufcpy(const uint8_t *restrict in, size_t *restrict in_pos, const size_t out_avail = out_size - *out_pos; const size_t copy_size = my_min(in_avail, out_avail); - memcpy(out + *out_pos, in + *in_pos, copy_size); + // Call memcpy() only if there is something to copy. If there is + // nothing to copy, in or out might be NULL and then the memcpy() + // call would trigger undefined behavior. + if (copy_size > 0) + memcpy(out + *out_pos, in + *in_pos, copy_size); *in_pos += copy_size; *out_pos += copy_size; diff --git a/src/liblzma/common/filter_common.h b/src/liblzma/common/filter_common.h index 42a26a24a47f..9390305c26c1 100644 --- a/src/liblzma/common/filter_common.h +++ b/src/liblzma/common/filter_common.h @@ -1,6 +1,6 @@ /////////////////////////////////////////////////////////////////////////////// // -/// \file filter_common.c +/// \file filter_common.h /// \brief Filter-specific stuff common for both encoder and decoder // // Author: Lasse Collin diff --git a/src/liblzma/common/filter_decoder.h b/src/liblzma/common/filter_decoder.h index a2e255fe5f06..2dac60282826 100644 --- a/src/liblzma/common/filter_decoder.h +++ b/src/liblzma/common/filter_decoder.h @@ -1,6 +1,6 @@ /////////////////////////////////////////////////////////////////////////////// // -/// \file filter_decoder.c +/// \file filter_decoder.h /// \brief Filter ID mapping to filter-specific functions // // Author: Lasse Collin diff --git a/src/liblzma/common/filter_flags_encoder.c b/src/liblzma/common/filter_flags_encoder.c index d110566de99f..b57b9fd80b06 100644 --- a/src/liblzma/common/filter_flags_encoder.c +++ b/src/liblzma/common/filter_flags_encoder.c @@ -1,7 +1,7 @@ /////////////////////////////////////////////////////////////////////////////// // /// \file filter_flags_encoder.c -/// \brief Decodes a Filter Flags field +/// \brief Encodes a Filter Flags field // // Author: Lasse Collin // diff --git a/src/liblzma/common/hardware_physmem.c b/src/liblzma/common/hardware_physmem.c index 7405b658af76..a2bbbe29d4b4 100644 --- a/src/liblzma/common/hardware_physmem.c +++ b/src/liblzma/common/hardware_physmem.c @@ -19,7 +19,7 @@ extern LZMA_API(uint64_t) lzma_physmem(void) { // It is simpler to make lzma_physmem() a wrapper for - // tuklib_physmem() than to hack appropriate symbol visiblity + // tuklib_physmem() than to hack appropriate symbol visibility // support for the tuklib modules. return tuklib_physmem(); } diff --git a/src/liblzma/common/index.c b/src/liblzma/common/index.c index 26e4e519bc80..a41e8f33083b 100644 --- a/src/liblzma/common/index.c +++ b/src/liblzma/common/index.c @@ -105,7 +105,7 @@ typedef struct { typedef struct { - /// Every index_stream is a node in the tree of Sreams. + /// Every index_stream is a node in the tree of Streams. index_tree_node node; /// Number of this Stream (first one is 1) @@ -166,7 +166,7 @@ struct lzma_index_s { lzma_vli index_list_size; /// How many Records to allocate at once in lzma_index_append(). - /// This defaults to INDEX_GROUP_SIZE but can be overriden with + /// This defaults to INDEX_GROUP_SIZE but can be overridden with /// lzma_index_prealloc(). size_t prealloc; @@ -825,8 +825,8 @@ lzma_index_cat(lzma_index *restrict dest, lzma_index *restrict src, s->groups.root = &newg->node; } - if (s->groups.rightmost == &g->node) - s->groups.rightmost = &newg->node; + assert(s->groups.rightmost == &g->node); + s->groups.rightmost = &newg->node; lzma_free(g, allocator); diff --git a/src/liblzma/common/memcmplen.h b/src/liblzma/common/memcmplen.h index c1efc9e28b77..dcfd8d6f89d1 100644 --- a/src/liblzma/common/memcmplen.h +++ b/src/liblzma/common/memcmplen.h @@ -61,8 +61,7 @@ lzma_memcmplen(const uint8_t *buf1, const uint8_t *buf2, // to __builtin_clzll(). #define LZMA_MEMCMPLEN_EXTRA 8 while (len < limit) { - const uint64_t x = *(const uint64_t *)(buf1 + len) - - *(const uint64_t *)(buf2 + len); + const uint64_t x = read64ne(buf1 + len) - read64ne(buf2 + len); if (x != 0) { # if defined(_M_X64) // MSVC or Intel C compiler on Windows unsigned long tmp; @@ -99,15 +98,7 @@ lzma_memcmplen(const uint8_t *buf1, const uint8_t *buf2, _mm_loadu_si128((const __m128i *)(buf2 + len)))); if (x != 0) { -# if defined(__INTEL_COMPILER) - len += _bit_scan_forward(x); -# elif defined(_MSC_VER) - unsigned long tmp; - _BitScanForward(&tmp, x); - len += tmp; -# else - len += __builtin_ctz(x); -# endif + len += ctz32(x); return my_min(len, limit); } @@ -120,8 +111,7 @@ lzma_memcmplen(const uint8_t *buf1, const uint8_t *buf2, // Generic 32-bit little endian method # define LZMA_MEMCMPLEN_EXTRA 4 while (len < limit) { - uint32_t x = *(const uint32_t *)(buf1 + len) - - *(const uint32_t *)(buf2 + len); + uint32_t x = read32ne(buf1 + len) - read32ne(buf2 + len); if (x != 0) { if ((x & 0xFFFF) == 0) { len += 2; @@ -143,8 +133,7 @@ lzma_memcmplen(const uint8_t *buf1, const uint8_t *buf2, // Generic 32-bit big endian method # define LZMA_MEMCMPLEN_EXTRA 4 while (len < limit) { - uint32_t x = *(const uint32_t *)(buf1 + len) - ^ *(const uint32_t *)(buf2 + len); + uint32_t x = read32ne(buf1 + len) ^ read32ne(buf2 + len); if (x != 0) { if ((x & 0xFFFF0000) == 0) { len += 2; diff --git a/src/liblzma/common/stream_encoder_mt.c b/src/liblzma/common/stream_encoder_mt.c index 2efe44c2534f..01e40339750a 100644 --- a/src/liblzma/common/stream_encoder_mt.c +++ b/src/liblzma/common/stream_encoder_mt.c @@ -700,7 +700,7 @@ stream_encode_mt(void *coder_ptr, const lzma_allocator *allocator, ret = coder->thread_error; if (ret != LZMA_OK) { assert(ret != LZMA_STREAM_END); - break; + break; // Break out of mythread_sync. } // Try to read compressed data to out[]. @@ -958,7 +958,7 @@ stream_encoder_mt_init(lzma_next_coder *next, const lzma_allocator *allocator, // Validate the filter chain so that we can give an error in this // function instead of delaying it to the first call to lzma_code(). // The memory usage calculation verifies the filter chain as - // a side effect so we take advatange of that. + // a side effect so we take advantage of that. if (lzma_raw_encoder_memusage(filters) == UINT64_MAX) return LZMA_OPTIONS_ERROR; diff --git a/src/liblzma/common/stream_flags_decoder.c b/src/liblzma/common/stream_flags_decoder.c index 1bc2f97c5190..4e43e359e1ef 100644 --- a/src/liblzma/common/stream_flags_decoder.c +++ b/src/liblzma/common/stream_flags_decoder.c @@ -38,7 +38,7 @@ lzma_stream_header_decode(lzma_stream_flags *options, const uint8_t *in) // and unsupported files. const uint32_t crc = lzma_crc32(in + sizeof(lzma_header_magic), LZMA_STREAM_FLAGS_SIZE, 0); - if (crc != unaligned_read32le(in + sizeof(lzma_header_magic) + if (crc != read32le(in + sizeof(lzma_header_magic) + LZMA_STREAM_FLAGS_SIZE)) return LZMA_DATA_ERROR; @@ -67,7 +67,7 @@ lzma_stream_footer_decode(lzma_stream_flags *options, const uint8_t *in) // CRC32 const uint32_t crc = lzma_crc32(in + sizeof(uint32_t), sizeof(uint32_t) + LZMA_STREAM_FLAGS_SIZE, 0); - if (crc != unaligned_read32le(in)) + if (crc != read32le(in)) return LZMA_DATA_ERROR; // Stream Flags @@ -75,7 +75,7 @@ lzma_stream_footer_decode(lzma_stream_flags *options, const uint8_t *in) return LZMA_OPTIONS_ERROR; // Backward Size - options->backward_size = unaligned_read32le(in + sizeof(uint32_t)); + options->backward_size = read32le(in + sizeof(uint32_t)); options->backward_size = (options->backward_size + 1) * 4; return LZMA_OK; diff --git a/src/liblzma/common/stream_flags_encoder.c b/src/liblzma/common/stream_flags_encoder.c index 4e717159f1e7..b98ab17c456c 100644 --- a/src/liblzma/common/stream_flags_encoder.c +++ b/src/liblzma/common/stream_flags_encoder.c @@ -46,8 +46,8 @@ lzma_stream_header_encode(const lzma_stream_flags *options, uint8_t *out) const uint32_t crc = lzma_crc32(out + sizeof(lzma_header_magic), LZMA_STREAM_FLAGS_SIZE, 0); - unaligned_write32le(out + sizeof(lzma_header_magic) - + LZMA_STREAM_FLAGS_SIZE, crc); + write32le(out + sizeof(lzma_header_magic) + LZMA_STREAM_FLAGS_SIZE, + crc); return LZMA_OK; } @@ -66,7 +66,7 @@ lzma_stream_footer_encode(const lzma_stream_flags *options, uint8_t *out) if (!is_backward_size_valid(options)) return LZMA_PROG_ERROR; - unaligned_write32le(out + 4, options->backward_size / 4 - 1); + write32le(out + 4, options->backward_size / 4 - 1); // Stream Flags if (stream_flags_encode(options, out + 2 * 4)) @@ -76,7 +76,7 @@ lzma_stream_footer_encode(const lzma_stream_flags *options, uint8_t *out) const uint32_t crc = lzma_crc32( out + 4, 4 + LZMA_STREAM_FLAGS_SIZE, 0); - unaligned_write32le(out, crc); + write32le(out, crc); // Magic memcpy(out + 2 * 4 + LZMA_STREAM_FLAGS_SIZE, diff --git a/src/liblzma/common/vli_decoder.c b/src/liblzma/common/vli_decoder.c index c181828bf564..af2799d1fb90 100644 --- a/src/liblzma/common/vli_decoder.c +++ b/src/liblzma/common/vli_decoder.c @@ -72,7 +72,7 @@ lzma_vli_decode(lzma_vli *restrict vli, size_t *vli_pos, // corrupt. // // If we need bigger integers in future, old versions liblzma - // will confusingly indicate the file being corrupt istead of + // will confusingly indicate the file being corrupt instead of // unsupported. I suppose it's still better this way, because // in the foreseeable future (writing this in 2008) the only // reason why files would appear having over 63-bit integers diff --git a/src/liblzma/delta/delta_decoder.c b/src/liblzma/delta/delta_decoder.c index 6859afa5cd76..13d8a28f0df6 100644 --- a/src/liblzma/delta/delta_decoder.c +++ b/src/liblzma/delta/delta_decoder.c @@ -70,7 +70,7 @@ lzma_delta_props_decode(void **options, const lzma_allocator *allocator, return LZMA_MEM_ERROR; opt->type = LZMA_DELTA_TYPE_BYTE; - opt->dist = props[0] + 1; + opt->dist = props[0] + 1U; *options = opt; diff --git a/src/liblzma/lz/lz_decoder.c b/src/liblzma/lz/lz_decoder.c index c7086440bfa9..09b574388f59 100644 --- a/src/liblzma/lz/lz_decoder.c +++ b/src/liblzma/lz/lz_decoder.c @@ -91,11 +91,17 @@ decode_buffer(lzma_coder *coder, in, in_pos, in_size); // Copy the decoded data from the dictionary to the out[] - // buffer. + // buffer. Do it conditionally because out can be NULL + // (in which case copy_size is always 0). Calling memcpy() + // with a null-pointer is undefined even if the third + // argument is 0. const size_t copy_size = coder->dict.pos - dict_start; assert(copy_size <= out_size - *out_pos); - memcpy(out + *out_pos, coder->dict.buf + dict_start, - copy_size); + + if (copy_size > 0) + memcpy(out + *out_pos, coder->dict.buf + dict_start, + copy_size); + *out_pos += copy_size; // Reset the dictionary if so requested by coder->lz.code(). @@ -125,8 +131,7 @@ decode_buffer(lzma_coder *coder, static lzma_ret -lz_decode(void *coder_ptr, - const lzma_allocator *allocator lzma_attribute((__unused__)), +lz_decode(void *coder_ptr, const lzma_allocator *allocator, const uint8_t *restrict in, size_t *restrict in_pos, size_t in_size, uint8_t *restrict out, size_t *restrict out_pos, size_t out_size, @@ -241,7 +246,7 @@ lzma_lz_decoder_init(lzma_next_coder *next, const lzma_allocator *allocator, if (lz_options.dict_size < 4096) lz_options.dict_size = 4096; - // Make dictionary size a multipe of 16. Some LZ-based decoders like + // Make dictionary size a multiple of 16. Some LZ-based decoders like // LZMA use the lowest bits lzma_dict.pos to know the alignment of the // data. Aligned buffer is also good when memcpying from the // dictionary to the output buffer, since applications are diff --git a/src/liblzma/lz/lz_encoder_hash.h b/src/liblzma/lz/lz_encoder_hash.h index 342a333d1682..fb15c58146db 100644 --- a/src/liblzma/lz/lz_encoder_hash.h +++ b/src/liblzma/lz/lz_encoder_hash.h @@ -39,7 +39,7 @@ // Endianness doesn't matter in hash_2_calc() (no effect on the output). #ifdef TUKLIB_FAST_UNALIGNED_ACCESS # define hash_2_calc() \ - const uint32_t hash_value = *(const uint16_t *)(cur) + const uint32_t hash_value = read16ne(cur) #else # define hash_2_calc() \ const uint32_t hash_value \ diff --git a/src/liblzma/lz/lz_encoder_mf.c b/src/liblzma/lz/lz_encoder_mf.c index 78520779f1b6..d03657a7c93a 100644 --- a/src/liblzma/lz/lz_encoder_mf.c +++ b/src/liblzma/lz/lz_encoder_mf.c @@ -113,7 +113,7 @@ normalize(lzma_mf *mf) // may be match finders that use larger resolution than one byte. const uint32_t subvalue = (MUST_NORMALIZE_POS - mf->cyclic_size); - // & (~(UINT32_C(1) << 10) - 1); + // & ~((UINT32_C(1) << 10) - 1); for (uint32_t i = 0; i < mf->hash_count; ++i) { // If the distance is greater than the dictionary size, diff --git a/src/liblzma/lzma/fastpos.h b/src/liblzma/lzma/fastpos.h index a3feea58d8d3..cba442c27e5c 100644 --- a/src/liblzma/lzma/fastpos.h +++ b/src/liblzma/lzma/fastpos.h @@ -101,7 +101,7 @@ extern const uint8_t lzma_fastpos[1 << FASTPOS_BITS]; (UINT32_C(1) << (FASTPOS_BITS + fastpos_shift(extra, n))) #define fastpos_result(dist, extra, n) \ - lzma_fastpos[(dist) >> fastpos_shift(extra, n)] \ + (uint32_t)(lzma_fastpos[(dist) >> fastpos_shift(extra, n)]) \ + 2 * fastpos_shift(extra, n) diff --git a/src/liblzma/lzma/fastpos_tablegen.c b/src/liblzma/lzma/fastpos_tablegen.c index c97e6f411c27..d4484c82d0b5 100644 --- a/src/liblzma/lzma/fastpos_tablegen.c +++ b/src/liblzma/lzma/fastpos_tablegen.c @@ -11,7 +11,6 @@ // /////////////////////////////////////////////////////////////////////////////// -#include <sys/types.h> #include <inttypes.h> #include <stdio.h> #include "fastpos.h" diff --git a/src/liblzma/lzma/lzma2_decoder.c b/src/liblzma/lzma/lzma2_decoder.c index 878c870ae1a2..cf1b5110aca8 100644 --- a/src/liblzma/lzma/lzma2_decoder.c +++ b/src/liblzma/lzma/lzma2_decoder.c @@ -136,7 +136,7 @@ lzma2_decode(void *coder_ptr, lzma_dict *restrict dict, break; case SEQ_UNCOMPRESSED_2: - coder->uncompressed_size += in[(*in_pos)++] + 1; + coder->uncompressed_size += in[(*in_pos)++] + 1U; coder->sequence = SEQ_COMPRESSED_0; coder->lzma.set_uncompressed(coder->lzma.coder, coder->uncompressed_size); @@ -148,7 +148,7 @@ lzma2_decode(void *coder_ptr, lzma_dict *restrict dict, break; case SEQ_COMPRESSED_1: - coder->compressed_size += in[(*in_pos)++] + 1; + coder->compressed_size += in[(*in_pos)++] + 1U; coder->sequence = coder->next_sequence; break; @@ -297,8 +297,8 @@ lzma_lzma2_props_decode(void **options, const lzma_allocator *allocator, if (props[0] == 40) { opt->dict_size = UINT32_MAX; } else { - opt->dict_size = 2 | (props[0] & 1); - opt->dict_size <<= props[0] / 2 + 11; + opt->dict_size = 2 | (props[0] & 1U); + opt->dict_size <<= props[0] / 2U + 11; } opt->preset_dict = NULL; diff --git a/src/liblzma/lzma/lzma_common.h b/src/liblzma/lzma/lzma_common.h index 09efd3872917..9d040d95bb2f 100644 --- a/src/liblzma/lzma/lzma_common.h +++ b/src/liblzma/lzma/lzma_common.h @@ -122,7 +122,8 @@ typedef enum { /// byte; and /// - the highest literal_context_bits bits of the previous byte. #define literal_subcoder(probs, lc, lp_mask, pos, prev_byte) \ - ((probs)[(((pos) & lp_mask) << lc) + ((prev_byte) >> (8 - lc))]) + ((probs)[(((pos) & (lp_mask)) << (lc)) \ + + ((uint32_t)(prev_byte) >> (8U - (lc)))]) static inline void diff --git a/src/liblzma/lzma/lzma_decoder.c b/src/liblzma/lzma/lzma_decoder.c index d0f29b763a3c..e605a0a916b2 100644 --- a/src/liblzma/lzma/lzma_decoder.c +++ b/src/liblzma/lzma/lzma_decoder.c @@ -398,7 +398,7 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr, // ("match byte") to "len" to minimize the // number of variables we need to store // between decoder calls. - len = dict_get(&dict, rep0) << 1; + len = (uint32_t)(dict_get(&dict, rep0)) << 1; // The usage of "offset" allows omitting some // branches, which should give tiny speed @@ -569,7 +569,7 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr, #ifdef HAVE_SMALL do { rc_bit(probs[symbol], , - rep0 += 1 << offset, + rep0 += 1U << offset, SEQ_DIST_MODEL); } while (++offset < limit); #else @@ -577,25 +577,25 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr, case 5: assert(offset == 0); rc_bit(probs[symbol], , - rep0 += 1, + rep0 += 1U, SEQ_DIST_MODEL); ++offset; --limit; case 4: rc_bit(probs[symbol], , - rep0 += 1 << offset, + rep0 += 1U << offset, SEQ_DIST_MODEL); ++offset; --limit; case 3: rc_bit(probs[symbol], , - rep0 += 1 << offset, + rep0 += 1U << offset, SEQ_DIST_MODEL); ++offset; --limit; case 2: rc_bit(probs[symbol], , - rep0 += 1 << offset, + rep0 += 1U << offset, SEQ_DIST_MODEL); ++offset; --limit; @@ -607,7 +607,7 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr, // the unneeded updating of // "symbol". rc_bit_last(probs[symbol], , - rep0 += 1 << offset, + rep0 += 1U << offset, SEQ_DIST_MODEL); } #endif @@ -635,7 +635,7 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr, do { rc_bit(coder->pos_align[ symbol], , - rep0 += 1 << offset, + rep0 += 1U << offset, SEQ_ALIGN); } while (++offset < ALIGN_BITS); #else @@ -1049,7 +1049,7 @@ lzma_lzma_props_decode(void **options, const lzma_allocator *allocator, // All dictionary sizes are accepted, including zero. LZ decoder // will automatically use a dictionary at least a few KiB even if // a smaller dictionary is requested. - opt->dict_size = unaligned_read32le(props + 1); + opt->dict_size = read32le(props + 1); opt->preset_dict = NULL; opt->preset_dict_size = 0; diff --git a/src/liblzma/lzma/lzma_encoder.c b/src/liblzma/lzma/lzma_encoder.c index ba9ce6989c01..07d2b87bc65b 100644 --- a/src/liblzma/lzma/lzma_encoder.c +++ b/src/liblzma/lzma/lzma_encoder.c @@ -663,7 +663,7 @@ lzma_lzma_props_encode(const void *options, uint8_t *out) if (lzma_lzma_lclppb_encode(opt, out)) return LZMA_PROG_ERROR; - unaligned_write32le(out + 1, opt->dict_size); + write32le(out + 1, opt->dict_size); return LZMA_OK; } diff --git a/src/liblzma/lzma/lzma_encoder_optimum_normal.c b/src/liblzma/lzma/lzma_encoder_optimum_normal.c index 59f77343ed79..101c8d479008 100644 --- a/src/liblzma/lzma/lzma_encoder_optimum_normal.c +++ b/src/liblzma/lzma/lzma_encoder_optimum_normal.c @@ -636,9 +636,10 @@ helper2(lzma_lzma1_encoder *coder, uint32_t *reps, const uint8_t *buf, uint32_t len_test_2 = len_test + 1; const uint32_t limit = my_min(buf_avail_full, len_test_2 + nice_len); - for (; len_test_2 < limit - && buf[len_test_2] == buf_back[len_test_2]; - ++len_test_2) ; + // NOTE: len_test_2 may be greater than limit so the call to + // lzma_memcmplen() must be done conditionally. + if (len_test_2 < limit) + len_test_2 = lzma_memcmplen(buf, buf_back, len_test_2, limit); len_test_2 -= len_test + 1; @@ -732,9 +733,12 @@ helper2(lzma_lzma1_encoder *coder, uint32_t *reps, const uint8_t *buf, const uint32_t limit = my_min(buf_avail_full, len_test_2 + nice_len); - for (; len_test_2 < limit && - buf[len_test_2] == buf_back[len_test_2]; - ++len_test_2) ; + // NOTE: len_test_2 may be greater than limit + // so the call to lzma_memcmplen() must be + // done conditionally. + if (len_test_2 < limit) + len_test_2 = lzma_memcmplen(buf, buf_back, + len_test_2, limit); len_test_2 -= len_test + 1; diff --git a/src/liblzma/lzma/lzma_encoder_private.h b/src/liblzma/lzma/lzma_encoder_private.h index a2da969f4958..2e34aace16ef 100644 --- a/src/liblzma/lzma/lzma_encoder_private.h +++ b/src/liblzma/lzma/lzma_encoder_private.h @@ -25,8 +25,7 @@ // MATCH_LEN_MIN bytes. Unaligned access gives tiny gain so there's no // reason to not use it when it is supported. #ifdef TUKLIB_FAST_UNALIGNED_ACCESS -# define not_equal_16(a, b) \ - (*(const uint16_t *)(a) != *(const uint16_t *)(b)) +# define not_equal_16(a, b) (read16ne(a) != read16ne(b)) #else # define not_equal_16(a, b) \ ((a)[0] != (b)[0] || (a)[1] != (b)[1]) diff --git a/src/liblzma/simple/arm.c b/src/liblzma/simple/arm.c index 181d0e3b2232..ff5073ae58f3 100644 --- a/src/liblzma/simple/arm.c +++ b/src/liblzma/simple/arm.c @@ -22,9 +22,9 @@ arm_code(void *simple lzma_attribute((__unused__)), size_t i; for (i = 0; i + 4 <= size; i += 4) { if (buffer[i + 3] == 0xEB) { - uint32_t src = (buffer[i + 2] << 16) - | (buffer[i + 1] << 8) - | (buffer[i + 0]); + uint32_t src = ((uint32_t)(buffer[i + 2]) << 16) + | ((uint32_t)(buffer[i + 1]) << 8) + | (uint32_t)(buffer[i + 0]); src <<= 2; uint32_t dest; diff --git a/src/liblzma/simple/armthumb.c b/src/liblzma/simple/armthumb.c index eab4862dd76d..a8da334a04f8 100644 --- a/src/liblzma/simple/armthumb.c +++ b/src/liblzma/simple/armthumb.c @@ -23,10 +23,10 @@ armthumb_code(void *simple lzma_attribute((__unused__)), for (i = 0; i + 4 <= size; i += 2) { if ((buffer[i + 1] & 0xF8) == 0xF0 && (buffer[i + 3] & 0xF8) == 0xF8) { - uint32_t src = ((buffer[i + 1] & 0x7) << 19) - | (buffer[i + 0] << 11) - | ((buffer[i + 3] & 0x7) << 8) - | (buffer[i + 2]); + uint32_t src = (((uint32_t)(buffer[i + 1]) & 7) << 19) + | ((uint32_t)(buffer[i + 0]) << 11) + | (((uint32_t)(buffer[i + 3]) & 7) << 8) + | (uint32_t)(buffer[i + 2]); src <<= 1; diff --git a/src/liblzma/simple/ia64.c b/src/liblzma/simple/ia64.c index 580529e80860..6492d0a38469 100644 --- a/src/liblzma/simple/ia64.c +++ b/src/liblzma/simple/ia64.c @@ -70,7 +70,7 @@ ia64_code(void *simple lzma_attribute((__unused__)), inst_norm |= (uint64_t)(dest & 0x100000) << (36 - 20); - instruction &= (1 << bit_res) - 1; + instruction &= (1U << bit_res) - 1; instruction |= (inst_norm << bit_res); for (size_t j = 0; j < 6; j++) diff --git a/src/liblzma/simple/powerpc.c b/src/liblzma/simple/powerpc.c index 54dfbf102878..0b60e9b3fe3c 100644 --- a/src/liblzma/simple/powerpc.c +++ b/src/liblzma/simple/powerpc.c @@ -25,10 +25,11 @@ powerpc_code(void *simple lzma_attribute((__unused__)), if ((buffer[i] >> 2) == 0x12 && ((buffer[i + 3] & 3) == 1)) { - const uint32_t src = ((buffer[i + 0] & 3) << 24) - | (buffer[i + 1] << 16) - | (buffer[i + 2] << 8) - | (buffer[i + 3] & (~3)); + const uint32_t src + = (((uint32_t)(buffer[i + 0]) & 3) << 24) + | ((uint32_t)(buffer[i + 1]) << 16) + | ((uint32_t)(buffer[i + 2]) << 8) + | ((uint32_t)(buffer[i + 3]) & ~UINT32_C(3)); uint32_t dest; if (is_encoder) diff --git a/src/liblzma/simple/simple_coder.c b/src/liblzma/simple/simple_coder.c index 13ebabc76dcc..4f499befe95a 100644 --- a/src/liblzma/simple/simple_coder.c +++ b/src/liblzma/simple/simple_coder.c @@ -118,7 +118,15 @@ simple_code(void *coder_ptr, const lzma_allocator *allocator, // coder->pos and coder->size yet. This way the coder can be // restarted if the next filter in the chain returns e.g. // LZMA_MEM_ERROR. - memcpy(out + *out_pos, coder->buffer + coder->pos, buf_avail); + // + // Do the memcpy() conditionally because out can be NULL + // (in which case buf_avail is always 0). Calling memcpy() + // with a null-pointer is undefined even if the third + // argument is 0. + if (buf_avail > 0) + memcpy(out + *out_pos, coder->buffer + coder->pos, + buf_avail); + *out_pos += buf_avail; // Copy/Encode/Decode more data to out[]. diff --git a/src/liblzma/simple/simple_decoder.c b/src/liblzma/simple/simple_decoder.c index 1d864f2bf781..dc4d24151101 100644 --- a/src/liblzma/simple/simple_decoder.c +++ b/src/liblzma/simple/simple_decoder.c @@ -28,7 +28,7 @@ lzma_simple_props_decode(void **options, const lzma_allocator *allocator, if (opt == NULL) return LZMA_MEM_ERROR; - opt->start_offset = unaligned_read32le(props); + opt->start_offset = read32le(props); // Don't leave an options structure allocated if start_offset is zero. if (opt->start_offset == 0) diff --git a/src/liblzma/simple/simple_encoder.c b/src/liblzma/simple/simple_encoder.c index 8aa463bed220..d2cc03e58b81 100644 --- a/src/liblzma/simple/simple_encoder.c +++ b/src/liblzma/simple/simple_encoder.c @@ -32,7 +32,7 @@ lzma_simple_props_encode(const void *options, uint8_t *out) if (opt == NULL || opt->start_offset == 0) return LZMA_OK; - unaligned_write32le(out, opt->start_offset); + write32le(out, opt->start_offset); return LZMA_OK; } diff --git a/src/liblzma/simple/x86.c b/src/liblzma/simple/x86.c index 0b14807e900c..0e78909ccc0d 100644 --- a/src/liblzma/simple/x86.c +++ b/src/liblzma/simple/x86.c @@ -97,7 +97,7 @@ x86_code(void *simple_ptr, uint32_t now_pos, bool is_encoder, if (!Test86MSByte(b)) break; - src = dest ^ ((1 << (32 - i * 8)) - 1); + src = dest ^ ((1U << (32 - i * 8)) - 1); } buffer[buffer_pos + 4] |