diff options
| -rw-r--r-- | src/liblzma/check/crc32_fast.c | 2 | ||||
| -rw-r--r-- | src/liblzma/check/crc64_fast.c | 2 | ||||
| -rw-r--r-- | src/liblzma/check/crc_clmul.c | 45 | ||||
| -rw-r--r-- | src/liblzma/check/crc_common.h | 52 |
4 files changed, 51 insertions, 50 deletions
diff --git a/src/liblzma/check/crc32_fast.c b/src/liblzma/check/crc32_fast.c index add93d55..73659049 100644 --- a/src/liblzma/check/crc32_fast.c +++ b/src/liblzma/check/crc32_fast.c @@ -130,7 +130,7 @@ typedef uint32_t (*crc32_func_type)( static crc32_func_type crc32_resolve(void) { - return lzma_is_clmul_supported() ? &lzma_crc32_clmul : &crc32_generic; + return is_clmul_supported() ? &lzma_crc32_clmul : &crc32_generic; } #if defined(HAVE_FUNC_ATTRIBUTE_IFUNC) && defined(__clang__) diff --git a/src/liblzma/check/crc64_fast.c b/src/liblzma/check/crc64_fast.c index 8acdc713..4e6633db 100644 --- a/src/liblzma/check/crc64_fast.c +++ b/src/liblzma/check/crc64_fast.c @@ -94,7 +94,7 @@ typedef uint64_t (*crc64_func_type)( static crc64_func_type crc64_resolve(void) { - return lzma_is_clmul_supported() ? &lzma_crc64_clmul : &crc64_generic; + return is_clmul_supported() ? &lzma_crc64_clmul : &crc64_generic; } #if defined(HAVE_FUNC_ATTRIBUTE_IFUNC) && defined(__clang__) diff --git a/src/liblzma/check/crc_clmul.c b/src/liblzma/check/crc_clmul.c index 7110fd7e..640415e7 100644 --- a/src/liblzma/check/crc_clmul.c +++ b/src/liblzma/check/crc_clmul.c @@ -372,48 +372,3 @@ lzma_crc64_clmul(const uint8_t *buf, size_t size, uint64_t crc) && defined(_M_IX86) # pragma optimize("", on) #endif - - -//////////////////////// -// Detect CPU support // -//////////////////////// - -extern bool -lzma_is_clmul_supported(void) -{ - int success = 1; - uint32_t r[4]; // eax, ebx, ecx, edx - -#if defined(_MSC_VER) - // This needs <intrin.h> with MSVC. ICC has it as a built-in - // on all platforms. - __cpuid(r, 1); -#elif defined(HAVE_CPUID_H) - // Compared to just using __asm__ to run CPUID, this also checks - // that CPUID is supported and saves and restores ebx as that is - // needed with GCC < 5 with position-independent code (PIC). - success = __get_cpuid(1, &r[0], &r[1], &r[2], &r[3]); -#else - // Just a fallback that shouldn't be needed. - __asm__("cpuid\n\t" - : "=a"(r[0]), "=b"(r[1]), "=c"(r[2]), "=d"(r[3]) - : "a"(1), "c"(0)); -#endif - - // Returns true if these are supported: - // CLMUL (bit 1 in ecx) - // SSSE3 (bit 9 in ecx) - // SSE4.1 (bit 19 in ecx) - const uint32_t ecx_mask = (1 << 1) | (1 << 9) | (1 << 19); - return success && (r[2] & ecx_mask) == ecx_mask; - - // Alternative methods that weren't used: - // - ICC's _may_i_use_cpu_feature: the other methods should work too. - // - GCC >= 6 / Clang / ICX __builtin_cpu_supports("pclmul") - // - // CPUID decding is needed with MSVC anyway and older GCC. This keeps - // the feature checks in the build system simpler too. The nice thing - // about __builtin_cpu_supports would be that it generates very short - // code as is it only reads a variable set at startup but a few bytes - // doesn't matter here. -} diff --git a/src/liblzma/check/crc_common.h b/src/liblzma/check/crc_common.h index 51ddd9d5..1783b5e7 100644 --- a/src/liblzma/check/crc_common.h +++ b/src/liblzma/check/crc_common.h @@ -99,11 +99,57 @@ # elif defined(HAVE_CPUID_H) # include <cpuid.h> # endif + +// is_clmul_supported() must be inlined in this header file because the +// ifunc resolver function may not support calling a function in another +// translation unit. Depending on compiler-toolchain and flags, a call to +// a function defined in another translation unit could result in a +// reference to the PLT, which is unsafe to do in an ifunc resolver. The +// ifunc resolver runs very early when loading a shared library, so the PLT +// entries may not be setup at that time. Inlining this function duplicates +// the function body in crc32_resolve() and crc64_resolve(), but this is +// acceptable because the function results in very few instructions. +static inline bool +is_clmul_supported(void) +{ + int success = 1; + uint32_t r[4]; // eax, ebx, ecx, edx + +#if defined(_MSC_VER) + // This needs <intrin.h> with MSVC. ICC has it as a built-in + // on all platforms. + __cpuid(r, 1); +#elif defined(HAVE_CPUID_H) + // Compared to just using __asm__ to run CPUID, this also checks + // that CPUID is supported and saves and restores ebx as that is + // needed with GCC < 5 with position-independent code (PIC). + success = __get_cpuid(1, &r[0], &r[1], &r[2], &r[3]); +#else + // Just a fallback that shouldn't be needed. + __asm__("cpuid\n\t" + : "=a"(r[0]), "=b"(r[1]), "=c"(r[2]), "=d"(r[3]) + : "a"(1), "c"(0)); #endif -/// Detect at runtime if the CPU supports the x86 CLMUL instruction when -/// both the generic and CLMUL implementations are built. -extern bool lzma_is_clmul_supported(void); + // Returns true if these are supported: + // CLMUL (bit 1 in ecx) + // SSSE3 (bit 9 in ecx) + // SSE4.1 (bit 19 in ecx) + const uint32_t ecx_mask = (1 << 1) | (1 << 9) | (1 << 19); + return success && (r[2] & ecx_mask) == ecx_mask; + + // Alternative methods that weren't used: + // - ICC's _may_i_use_cpu_feature: the other methods should work too. + // - GCC >= 6 / Clang / ICX __builtin_cpu_supports("pclmul") + // + // CPUID decding is needed with MSVC anyway and older GCC. This keeps + // the feature checks in the build system simpler too. The nice thing + // about __builtin_cpu_supports would be that it generates very short + // code as is it only reads a variable set at startup but a few bytes + // doesn't matter here. +} + +#endif /// CRC32 implemented with the x86 CLMUL instruction. extern uint32_t lzma_crc32_clmul(const uint8_t *buf, size_t size, |