For both gcc and clang, crc32 builtins generate better code than the inline asm. GCC improves, removing unneeded "mov" instructions. Clang does the same and unrolls the loops. GCC has no changes on i386, but Clang's code generation is vastly improved, due to Clang's "rm" constraint issue. The number of cycles improved by ~0.1% for GCC and ~1% for Clang, which is expected because of the "rm" issue. However, Clang's performance is better than GCC's by ~1.5%, most likely due to loop unrolling. Link: https://github.com/llvm/llvm-project/issues/20571#issuecomment-2649330009 Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx> Cc: Ingo Molnar <mingo@xxxxxxxxxx> Cc: Borislav Petkov <bp@xxxxxxxxx> Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx> Cc: x86@xxxxxxxxxx Cc: "H. Peter Anvin" <hpa@xxxxxxxxx> Cc: Eric Biggers <ebiggers@xxxxxxxxxx> Cc: Ard Biesheuvel <ardb@xxxxxxxxxx> Cc: Nathan Chancellor <nathan@xxxxxxxxxx> Cc: Nick Desaulniers <nick.desaulniers+lkml@xxxxxxxxx> Cc: Justin Stitt <justinstitt@xxxxxxxxxx> Cc: linux-kernel@xxxxxxxxxxxxxxx Cc: linux-crypto@xxxxxxxxxxxxxxx Cc: llvm@xxxxxxxxxxxxxxx Signed-off-by: Bill Wendling <morbo@xxxxxxxxxx> --- arch/x86/Makefile | 3 +++ arch/x86/lib/crc32-glue.c | 8 ++++---- 2 files changed, 7 insertions(+), 4 deletions(-) diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 5b773b34768d..241436da1473 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -114,6 +114,9 @@ else KBUILD_CFLAGS += $(call cc-option,-fcf-protection=none) endif +# Enables the use of CRC32 builtins. +KBUILD_CFLAGS += -mcrc32 + ifeq ($(CONFIG_X86_32),y) BITS := 32 UTS_MACHINE := i386 diff --git a/arch/x86/lib/crc32-glue.c b/arch/x86/lib/crc32-glue.c index 2dd18a886ded..fdb94bff25f4 100644 --- a/arch/x86/lib/crc32-glue.c +++ b/arch/x86/lib/crc32-glue.c @@ -48,9 +48,9 @@ u32 crc32_le_arch(u32 crc, const u8 *p, size_t len) EXPORT_SYMBOL(crc32_le_arch); #ifdef CONFIG_X86_64 -#define CRC32_INST "crc32q %1, %q0" +#define CRC32_INST __builtin_ia32_crc32di #else -#define CRC32_INST "crc32l %1, %0" +#define CRC32_INST __builtin_ia32_crc32si #endif /* @@ -78,10 +78,10 @@ u32 crc32c_le_arch(u32 crc, const u8 *p, size_t len) for (num_longs = len / sizeof(unsigned long); num_longs != 0; num_longs--, p += sizeof(unsigned long)) - asm(CRC32_INST : "+r" (crc) : "rm" (*(unsigned long *)p)); + crc = CRC32_INST(crc, *(unsigned long *)p); for (len %= sizeof(unsigned long); len; len--, p++) - asm("crc32b %1, %0" : "+r" (crc) : "rm" (*p)); + crc = __builtin_ia32_crc32qi(crc, *p); return crc; } -- 2.48.1.711.g2feabab25a-goog
