From 1527bc8b928dd1399c3d3467dd47d9ede210978a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 1 Feb 2010 15:03:07 +0100 Subject: bitops: Optimize hweight() by making use of compile-time evaluation Rename the extisting runtime hweight() implementations to __arch_hweight(), rename the compile-time versions to __const_hweight() and then have hweight() pick between them. Suggested-by: H. Peter Anvin Signed-off-by: Peter Zijlstra LKML-Reference: <20100318111929.GB11152@aftab> Acked-by: H. Peter Anvin LKML-Reference: <1265028224.24455.154.camel@laptop> Signed-off-by: H. Peter Anvin --- arch/alpha/include/asm/bitops.h | 18 +++++++------ arch/ia64/include/asm/bitops.h | 11 ++++---- arch/sparc/include/asm/bitops_64.h | 11 ++++---- include/asm-generic/bitops/arch_hweight.h | 11 ++++++++ include/asm-generic/bitops/const_hweight.h | 42 ++++++++++++++++++++++++++++++ include/asm-generic/bitops/hweight.h | 8 ++---- include/linux/bitops.h | 25 ------------------ lib/hweight.c | 19 +++++++------- 8 files changed, 87 insertions(+), 58 deletions(-) create mode 100644 include/asm-generic/bitops/arch_hweight.h create mode 100644 include/asm-generic/bitops/const_hweight.h diff --git a/arch/alpha/include/asm/bitops.h b/arch/alpha/include/asm/bitops.h index 15f3ae25c511..296da1d5ed57 100644 --- a/arch/alpha/include/asm/bitops.h +++ b/arch/alpha/include/asm/bitops.h @@ -405,29 +405,31 @@ static inline int fls(int x) #if defined(CONFIG_ALPHA_EV6) && defined(CONFIG_ALPHA_EV67) /* Whee. EV67 can calculate it directly. */ -static inline unsigned long hweight64(unsigned long w) +static inline unsigned long __arch_hweight64(unsigned long w) { return __kernel_ctpop(w); } -static inline unsigned int hweight32(unsigned int w) +static inline unsigned int __arch_weight32(unsigned int w) { - return hweight64(w); + return __arch_hweight64(w); } -static inline unsigned int hweight16(unsigned int w) +static inline unsigned int __arch_hweight16(unsigned int w) { - return hweight64(w & 0xffff); + return __arch_hweight64(w & 0xffff); } -static inline unsigned int hweight8(unsigned int w) +static inline unsigned int __arch_hweight8(unsigned int w) { - return hweight64(w & 0xff); + return __arch_hweight64(w & 0xff); } #else -#include +#include #endif +#include + #endif /* __KERNEL__ */ #include diff --git a/arch/ia64/include/asm/bitops.h b/arch/ia64/include/asm/bitops.h index 6ebc229a1c51..9da3df6f1a52 100644 --- a/arch/ia64/include/asm/bitops.h +++ b/arch/ia64/include/asm/bitops.h @@ -437,17 +437,18 @@ __fls (unsigned long x) * hweightN: returns the hamming weight (i.e. the number * of bits set) of a N-bit word */ -static __inline__ unsigned long -hweight64 (unsigned long x) +static __inline__ unsigned long __arch_hweight64(unsigned long x) { unsigned long result; result = ia64_popcnt(x); return result; } -#define hweight32(x) (unsigned int) hweight64((x) & 0xfffffffful) -#define hweight16(x) (unsigned int) hweight64((x) & 0xfffful) -#define hweight8(x) (unsigned int) hweight64((x) & 0xfful) +#define __arch_hweight32(x) ((unsigned int) __arch_hweight64((x) & 0xfffffffful)) +#define __arch_hweight16(x) ((unsigned int) __arch_hweight64((x) & 0xfffful)) +#define __arch_hweight8(x) ((unsigned int) __arch_hweight64((x) & 0xfful)) + +#include #endif /* __KERNEL__ */ diff --git a/arch/sparc/include/asm/bitops_64.h b/arch/sparc/include/asm/bitops_64.h index e72ac9cdfb98..766121a67a24 100644 --- a/arch/sparc/include/asm/bitops_64.h +++ b/arch/sparc/include/asm/bitops_64.h @@ -44,7 +44,7 @@ extern void change_bit(unsigned long nr, volatile unsigned long *addr); #ifdef ULTRA_HAS_POPULATION_COUNT -static inline unsigned int hweight64(unsigned long w) +static inline unsigned int __arch_hweight64(unsigned long w) { unsigned int res; @@ -52,7 +52,7 @@ static inline unsigned int hweight64(unsigned long w) return res; } -static inline unsigned int hweight32(unsigned int w) +static inline unsigned int __arch_hweight32(unsigned int w) { unsigned int res; @@ -60,7 +60,7 @@ static inline unsigned int hweight32(unsigned int w) return res; } -static inline unsigned int hweight16(unsigned int w) +static inline unsigned int __arch_hweight16(unsigned int w) { unsigned int res; @@ -68,7 +68,7 @@ static inline unsigned int hweight16(unsigned int w) return res; } -static inline unsigned int hweight8(unsigned int w) +static inline unsigned int __arch_hweight8(unsigned int w) { unsigned int res; @@ -78,9 +78,10 @@ static inline unsigned int hweight8(unsigned int w) #else -#include +#include #endif +#include #include #endif /* __KERNEL__ */ diff --git a/include/asm-generic/bitops/arch_hweight.h b/include/asm-generic/bitops/arch_hweight.h new file mode 100644 index 000000000000..3a7be842cdce --- /dev/null +++ b/include/asm-generic/bitops/arch_hweight.h @@ -0,0 +1,11 @@ +#ifndef _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_ +#define _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_ + +#include + +extern unsigned int __arch_hweight32(unsigned int w); +extern unsigned int __arch_hweight16(unsigned int w); +extern unsigned int __arch_hweight8(unsigned int w); +extern unsigned long __arch_hweight64(__u64 w); + +#endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */ diff --git a/include/asm-generic/bitops/const_hweight.h b/include/asm-generic/bitops/const_hweight.h new file mode 100644 index 000000000000..fa2a50b7ee66 --- /dev/null +++ b/include/asm-generic/bitops/const_hweight.h @@ -0,0 +1,42 @@ +#ifndef _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_ +#define _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_ + +/* + * Compile time versions of __arch_hweightN() + */ +#define __const_hweight8(w) \ + ( (!!((w) & (1ULL << 0))) + \ + (!!((w) & (1ULL << 1))) + \ + (!!((w) & (1ULL << 2))) + \ + (!!((w) & (1ULL << 3))) + \ + (!!((w) & (1ULL << 4))) + \ + (!!((w) & (1ULL << 5))) + \ + (!!((w) & (1ULL << 6))) + \ + (!!((w) & (1ULL << 7))) ) + +#define __const_hweight16(w) (__const_hweight8(w) + __const_hweight8((w) >> 8 )) +#define __const_hweight32(w) (__const_hweight16(w) + __const_hweight16((w) >> 16)) +#define __const_hweight64(w) (__const_hweight32(w) + __const_hweight32((w) >> 32)) + +/* + * Generic interface. + */ +#define hweight8(w) (__builtin_constant_p(w) ? __const_hweight8(w) : __arch_hweight8(w)) +#define hweight16(w) (__builtin_constant_p(w) ? __const_hweight16(w) : __arch_hweight16(w)) +#define hweight32(w) (__builtin_constant_p(w) ? __const_hweight32(w) : __arch_hweight32(w)) +#define hweight64(w) (__builtin_constant_p(w) ? __const_hweight64(w) : __arch_hweight64(w)) + +/* + * Interface for known constant arguments + */ +#define HWEIGHT8(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight8(w)) +#define HWEIGHT16(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight16(w)) +#define HWEIGHT32(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight32(w)) +#define HWEIGHT64(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight64(w)) + +/* + * Type invariant interface to the compile time constant hweight functions. + */ +#define HWEIGHT(w) HWEIGHT64((u64)w) + +#endif /* _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_ */ diff --git a/include/asm-generic/bitops/hweight.h b/include/asm-generic/bitops/hweight.h index fbbc383771da..a94d6519c7ed 100644 --- a/include/asm-generic/bitops/hweight.h +++ b/include/asm-generic/bitops/hweight.h @@ -1,11 +1,7 @@ #ifndef _ASM_GENERIC_BITOPS_HWEIGHT_H_ #define _ASM_GENERIC_BITOPS_HWEIGHT_H_ -#include - -extern unsigned int hweight32(unsigned int w); -extern unsigned int hweight16(unsigned int w); -extern unsigned int hweight8(unsigned int w); -extern unsigned long hweight64(__u64 w); +#include +#include #endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */ diff --git a/include/linux/bitops.h b/include/linux/bitops.h index b79389879238..c55d5bc4ee58 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -47,31 +47,6 @@ static inline unsigned long hweight_long(unsigned long w) return sizeof(w) == 4 ? hweight32(w) : hweight64(w); } -/* - * Clearly slow versions of the hweightN() functions, their benefit is - * of course compile time evaluation of constant arguments. - */ -#define HWEIGHT8(w) \ - ( BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + \ - (!!((w) & (1ULL << 0))) + \ - (!!((w) & (1ULL << 1))) + \ - (!!((w) & (1ULL << 2))) + \ - (!!((w) & (1ULL << 3))) + \ - (!!((w) & (1ULL << 4))) + \ - (!!((w) & (1ULL << 5))) + \ - (!!((w) & (1ULL << 6))) + \ - (!!((w) & (1ULL << 7))) ) - -#define HWEIGHT16(w) (HWEIGHT8(w) + HWEIGHT8((w) >> 8)) -#define HWEIGHT32(w) (HWEIGHT16(w) + HWEIGHT16((w) >> 16)) -#define HWEIGHT64(w) (HWEIGHT32(w) + HWEIGHT32((w) >> 32)) - -/* - * Type invariant version that simply casts things to the - * largest type. - */ -#define HWEIGHT(w) HWEIGHT64((u64)(w)) - /** * rol32 - rotate a 32-bit value left * @word: value to rotate diff --git a/lib/hweight.c b/lib/hweight.c index 63ee4eb1228d..a6927e76840f 100644 --- a/lib/hweight.c +++ b/lib/hweight.c @@ -9,7 +9,7 @@ * The Hamming Weight of a number is the total number of bits set in it. */ -unsigned int hweight32(unsigned int w) +unsigned int __arch_hweight32(unsigned int w) { #ifdef ARCH_HAS_FAST_MULTIPLIER w -= (w >> 1) & 0x55555555; @@ -24,29 +24,30 @@ unsigned int hweight32(unsigned int w) return (res + (res >> 16)) & 0x000000FF; #endif } -EXPORT_SYMBOL(hweight32); +EXPORT_SYMBOL(__arch_hweight32); -unsigned int hweight16(unsigned int w) +unsigned int __arch_hweight16(unsigned int w) { unsigned int res = w - ((w >> 1) & 0x5555); res = (res & 0x3333) + ((res >> 2) & 0x3333); res = (res + (res >> 4)) & 0x0F0F; return (res + (res >> 8)) & 0x00FF; } -EXPORT_SYMBOL(hweight16); +EXPORT_SYMBOL(__arch_hweight16); -unsigned int hweight8(unsigned int w) +unsigned int __arch_hweight8(unsigned int w) { unsigned int res = w - ((w >> 1) & 0x55); res = (res & 0x33) + ((res >> 2) & 0x33); return (res + (res >> 4)) & 0x0F; } -EXPORT_SYMBOL(hweight8); +EXPORT_SYMBOL(__arch_hweight8); -unsigned long hweight64(__u64 w) +unsigned long __arch_hweight64(__u64 w) { #if BITS_PER_LONG == 32 - return hweight32((unsigned int)(w >> 32)) + hweight32((unsigned int)w); + return __arch_hweight32((unsigned int)(w >> 32)) + + __arch_hweight32((unsigned int)w); #elif BITS_PER_LONG == 64 #ifdef ARCH_HAS_FAST_MULTIPLIER w -= (w >> 1) & 0x5555555555555555ul; @@ -63,4 +64,4 @@ unsigned long hweight64(__u64 w) #endif #endif } -EXPORT_SYMBOL(hweight64); +EXPORT_SYMBOL(__arch_hweight64); -- cgit v1.2.3 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 ++- include/asm-generic/bitops/arch_hweight.h | 22 +++++++++--- lib/Makefile | 3 ++ lib/hweight.c | 20 +++++------ scripts/Makefile.lib | 4 +++ 8 files changed, 108 insertions(+), 18 deletions(-) create mode 100644 arch/x86/include/asm/arch_hweight.h 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__ */ diff --git a/include/asm-generic/bitops/arch_hweight.h b/include/asm-generic/bitops/arch_hweight.h index 3a7be842cdce..9a81c1e9436c 100644 --- a/include/asm-generic/bitops/arch_hweight.h +++ b/include/asm-generic/bitops/arch_hweight.h @@ -3,9 +3,23 @@ #include -extern unsigned int __arch_hweight32(unsigned int w); -extern unsigned int __arch_hweight16(unsigned int w); -extern unsigned int __arch_hweight8(unsigned int w); -extern unsigned long __arch_hweight64(__u64 w); +inline unsigned int __arch_hweight32(unsigned int w) +{ + return __sw_hweight32(w); +} +inline unsigned int __arch_hweight16(unsigned int w) +{ + return __sw_hweight16(w); +} + +inline unsigned int __arch_hweight8(unsigned int w) +{ + return __sw_hweight8(w); +} + +inline unsigned long __arch_hweight64(__u64 w) +{ + return __sw_hweight64(w); +} #endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */ diff --git a/lib/Makefile b/lib/Makefile index 2e152aed7198..abe63a8ad143 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -39,7 +39,10 @@ lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o lib-$(CONFIG_GENERIC_FIND_FIRST_BIT) += find_next_bit.o lib-$(CONFIG_GENERIC_FIND_NEXT_BIT) += find_next_bit.o obj-$(CONFIG_GENERIC_FIND_LAST_BIT) += find_last_bit.o + +CFLAGS_hweight.o = $(subst $(quote),,$(CONFIG_ARCH_HWEIGHT_CFLAGS)) obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o + obj-$(CONFIG_LOCK_KERNEL) += kernel_lock.o obj-$(CONFIG_BTREE) += btree.o obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o diff --git a/lib/hweight.c b/lib/hweight.c index a6927e76840f..3c79d50814cf 100644 --- a/lib/hweight.c +++ b/lib/hweight.c @@ -9,7 +9,7 @@ * The Hamming Weight of a number is the total number of bits set in it. */ -unsigned int __arch_hweight32(unsigned int w) +unsigned int __sw_hweight32(unsigned int w) { #ifdef ARCH_HAS_FAST_MULTIPLIER w -= (w >> 1) & 0x55555555; @@ -24,30 +24,30 @@ unsigned int __arch_hweight32(unsigned int w) return (res + (res >> 16)) & 0x000000FF; #endif } -EXPORT_SYMBOL(__arch_hweight32); +EXPORT_SYMBOL(__sw_hweight32); -unsigned int __arch_hweight16(unsigned int w) +unsigned int __sw_hweight16(unsigned int w) { unsigned int res = w - ((w >> 1) & 0x5555); res = (res & 0x3333) + ((res >> 2) & 0x3333); res = (res + (res >> 4)) & 0x0F0F; return (res + (res >> 8)) & 0x00FF; } -EXPORT_SYMBOL(__arch_hweight16); +EXPORT_SYMBOL(__sw_hweight16); -unsigned int __arch_hweight8(unsigned int w) +unsigned int __sw_hweight8(unsigned int w) { unsigned int res = w - ((w >> 1) & 0x55); res = (res & 0x33) + ((res >> 2) & 0x33); return (res + (res >> 4)) & 0x0F; } -EXPORT_SYMBOL(__arch_hweight8); +EXPORT_SYMBOL(__sw_hweight8); -unsigned long __arch_hweight64(__u64 w) +unsigned long __sw_hweight64(__u64 w) { #if BITS_PER_LONG == 32 - return __arch_hweight32((unsigned int)(w >> 32)) + - __arch_hweight32((unsigned int)w); + return __sw_hweight32((unsigned int)(w >> 32)) + + __sw_hweight32((unsigned int)w); #elif BITS_PER_LONG == 64 #ifdef ARCH_HAS_FAST_MULTIPLIER w -= (w >> 1) & 0x5555555555555555ul; @@ -64,4 +64,4 @@ unsigned long __arch_hweight64(__u64 w) #endif #endif } -EXPORT_SYMBOL(__arch_hweight64); +EXPORT_SYMBOL(__sw_hweight64); diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index f9bdf264473d..cbcd654215e6 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -245,3 +245,7 @@ quiet_cmd_lzo = LZO $@ cmd_lzo = (cat $(filter-out FORCE,$^) | \ lzop -9 && $(call size_append, $(filter-out FORCE,$^))) > $@ || \ (rm -f $@ ; false) + +# misc stuff +# --------------------------------------------------------------------------- +quote:=" -- cgit v1.2.3 From 4677d4a53e0d565742277e8913e91c821453e63e Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 3 May 2010 14:57:11 +0200 Subject: arch, hweight: Fix compilation errors Fix function prototype visibility issues when compiling for non-x86 architectures. Tested with crosstool (ftp://ftp.kernel.org/pub/tools/crosstool/) with alpha, ia64 and sparc targets. Signed-off-by: Borislav Petkov LKML-Reference: <20100503130736.GD26107@aftab> Signed-off-by: H. Peter Anvin --- include/asm-generic/bitops/arch_hweight.h | 8 ++++---- include/linux/bitops.h | 5 +++++ 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/include/asm-generic/bitops/arch_hweight.h b/include/asm-generic/bitops/arch_hweight.h index 9a81c1e9436c..6a211f40665c 100644 --- a/include/asm-generic/bitops/arch_hweight.h +++ b/include/asm-generic/bitops/arch_hweight.h @@ -3,22 +3,22 @@ #include -inline unsigned int __arch_hweight32(unsigned int w) +static inline unsigned int __arch_hweight32(unsigned int w) { return __sw_hweight32(w); } -inline unsigned int __arch_hweight16(unsigned int w) +static inline unsigned int __arch_hweight16(unsigned int w) { return __sw_hweight16(w); } -inline unsigned int __arch_hweight8(unsigned int w) +static inline unsigned int __arch_hweight8(unsigned int w) { return __sw_hweight8(w); } -inline unsigned long __arch_hweight64(__u64 w) +static inline unsigned long __arch_hweight64(__u64 w) { return __sw_hweight64(w); } diff --git a/include/linux/bitops.h b/include/linux/bitops.h index c55d5bc4ee58..26caa608ccd9 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -10,6 +10,11 @@ #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) #endif +extern unsigned int __sw_hweight8(unsigned int w); +extern unsigned int __sw_hweight16(unsigned int w); +extern unsigned int __sw_hweight32(unsigned int w); +extern unsigned long __sw_hweight64(__u64 w); + /* * Include this here because some architectures need generic_ffs/fls in * scope -- cgit v1.2.3 From c59bd5688299cddb71183e156e7a3c1409b90df2 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Mon, 17 May 2010 15:13:23 -0700 Subject: x86, hweight: Use a 32-bit popcnt for __arch_hweight32() Use a 32-bit popcnt instruction for __arch_hweight32(), even on x86-64. Even though the input register will *usually* be zero-extended due to the standard operation of the hardware, it isn't necessarily so if the input value was the result of truncating a 64-bit operation. Note: the POPCNT32 variant used on x86-64 has a technically unnecessary REX prefix to make it five bytes long, the same as a CALL instruction, therefore avoiding an unnecessary NOP. Reported-by: Linus Torvalds Signed-off-by: H. Peter Anvin Cc: Borislav Petkov LKML-Reference: --- arch/x86/include/asm/arch_hweight.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h index d1fc3c219ae6..9686c3d9ff73 100644 --- a/arch/x86/include/asm/arch_hweight.h +++ b/arch/x86/include/asm/arch_hweight.h @@ -2,13 +2,15 @@ #define _ASM_X86_HWEIGHT_H #ifdef CONFIG_64BIT +/* popcnt %edi, %eax -- redundant REX prefix for alignment */ +#define POPCNT32 ".byte 0xf3,0x40,0x0f,0xb8,0xc7" /* popcnt %rdi, %rax */ -#define POPCNT ".byte 0xf3,0x48,0x0f,0xb8,0xc7" +#define POPCNT64 ".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 POPCNT32 ".byte 0xf3,0x0f,0xb8,0xc0" #define REG_IN "a" #define REG_OUT "a" #endif @@ -23,7 +25,7 @@ static inline unsigned int __arch_hweight32(unsigned int w) { unsigned int res = 0; - asm (ALTERNATIVE("call __sw_hweight32", POPCNT, X86_FEATURE_POPCNT) + asm (ALTERNATIVE("call __sw_hweight32", POPCNT32, X86_FEATURE_POPCNT) : "="REG_OUT (res) : REG_IN (w)); @@ -48,7 +50,7 @@ static inline unsigned long __arch_hweight64(__u64 w) return __arch_hweight32((u32)w) + __arch_hweight32((u32)(w >> 32)); #else - asm (ALTERNATIVE("call __sw_hweight64", POPCNT, X86_FEATURE_POPCNT) + asm (ALTERNATIVE("call __sw_hweight64", POPCNT64, X86_FEATURE_POPCNT) : "="REG_OUT (res) : REG_IN (w)); #endif /* CONFIG_X86_32 */ -- cgit v1.2.3