From d61931d89be506372d01a90d1755f6d0a9fafe2d Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Fri, 5 Mar 2010 17:34:46 +0100 Subject: x86: Add optimized popcnt variants Add support for the hardware version of the Hamming weight function, popcnt, present in CPUs which advertize it under CPUID, Function 0x0000_0001_ECX[23]. On CPUs which don't support it, we fallback to the default lib/hweight.c sw versions. A synthetic benchmark comparing popcnt with __sw_hweight64 showed almost a 3x speedup on a F10h machine. Signed-off-by: Borislav Petkov LKML-Reference: <20100318112015.GC11152@aftab> Signed-off-by: H. Peter Anvin --- arch/x86/Kconfig | 5 ++++ arch/x86/include/asm/alternative.h | 9 ++++-- arch/x86/include/asm/arch_hweight.h | 59 +++++++++++++++++++++++++++++++++++++ arch/x86/include/asm/bitops.h | 4 ++- 4 files changed, 73 insertions(+), 4 deletions(-) create mode 100644 arch/x86/include/asm/arch_hweight.h (limited to 'arch') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0eacb1ffb421..89d8c54cdd37 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -238,6 +238,11 @@ config X86_32_LAZY_GS def_bool y depends on X86_32 && !CC_STACKPROTECTOR +config ARCH_HWEIGHT_CFLAGS + string + default "-fcall-saved-ecx -fcall-saved-edx" if X86_32 + default "-fcall-saved-rdi -fcall-saved-rsi -fcall-saved-rdx -fcall-saved-rcx -fcall-saved-r8 -fcall-saved-r9 -fcall-saved-r10 -fcall-saved-r11" if X86_64 + config KTIME_SCALAR def_bool X86_32 source "init/Kconfig" diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index b09ec55650b3..67dae51e7fd0 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -39,9 +39,6 @@ #define LOCK_PREFIX "" #endif -/* This must be included *after* the definition of LOCK_PREFIX */ -#include - struct alt_instr { u8 *instr; /* original instruction */ u8 *replacement; @@ -95,6 +92,12 @@ static inline int alternatives_text_reserved(void *start, void *end) "663:\n\t" newinstr "\n664:\n" /* replacement */ \ ".previous" +/* + * This must be included *after* the definition of ALTERNATIVE due to + * + */ +#include + /* * Alternative instructions for different CPU types or capabilities. * diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h new file mode 100644 index 000000000000..d1fc3c219ae6 --- /dev/null +++ b/arch/x86/include/asm/arch_hweight.h @@ -0,0 +1,59 @@ +#ifndef _ASM_X86_HWEIGHT_H +#define _ASM_X86_HWEIGHT_H + +#ifdef CONFIG_64BIT +/* popcnt %rdi, %rax */ +#define POPCNT ".byte 0xf3,0x48,0x0f,0xb8,0xc7" +#define REG_IN "D" +#define REG_OUT "a" +#else +/* popcnt %eax, %eax */ +#define POPCNT ".byte 0xf3,0x0f,0xb8,0xc0" +#define REG_IN "a" +#define REG_OUT "a" +#endif + +/* + * __sw_hweightXX are called from within the alternatives below + * and callee-clobbered registers need to be taken care of. See + * ARCH_HWEIGHT_CFLAGS in for the respective + * compiler switches. + */ +static inline unsigned int __arch_hweight32(unsigned int w) +{ + unsigned int res = 0; + + asm (ALTERNATIVE("call __sw_hweight32", POPCNT, X86_FEATURE_POPCNT) + : "="REG_OUT (res) + : REG_IN (w)); + + return res; +} + +static inline unsigned int __arch_hweight16(unsigned int w) +{ + return __arch_hweight32(w & 0xffff); +} + +static inline unsigned int __arch_hweight8(unsigned int w) +{ + return __arch_hweight32(w & 0xff); +} + +static inline unsigned long __arch_hweight64(__u64 w) +{ + unsigned long res = 0; + +#ifdef CONFIG_X86_32 + return __arch_hweight32((u32)w) + + __arch_hweight32((u32)(w >> 32)); +#else + asm (ALTERNATIVE("call __sw_hweight64", POPCNT, X86_FEATURE_POPCNT) + : "="REG_OUT (res) + : REG_IN (w)); +#endif /* CONFIG_X86_32 */ + + return res; +} + +#endif diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 02b47a603fc8..545776efeb16 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -444,7 +444,9 @@ static inline int fls(int x) #define ARCH_HAS_FAST_MULTIPLIER 1 -#include +#include + +#include #endif /* __KERNEL__ */ -- cgit v1.2.3