From 4c74c330c2d84aec9f2b4e87827b08814c266b6b Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 23 Sep 2013 12:04:41 +1000 Subject: [PATCH] powerpc: Add little endian support for word-at-a-time functions The powerpc word-at-a-time functions are big endian specific. Bring in the x86 version in order to support little endian builds. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/word-at-a-time.h | 71 +++++++++++++++++++++++ 1 file changed, 71 insertions(+) diff --git a/arch/powerpc/include/asm/word-at-a-time.h b/arch/powerpc/include/asm/word-at-a-time.h index d0b6d4ac6dda..213a5f2b0717 100644 --- a/arch/powerpc/include/asm/word-at-a-time.h +++ b/arch/powerpc/include/asm/word-at-a-time.h @@ -8,6 +8,8 @@ #include #include +#ifdef __BIG_ENDIAN__ + struct word_at_a_time { const unsigned long high_bits, low_bits; }; @@ -38,4 +40,73 @@ static inline bool has_zero(unsigned long val, unsigned long *data, const struct return (val + c->high_bits) & ~rhs; } +#else + +/* + * This is largely generic for little-endian machines, but the + * optimal byte mask counting is probably going to be something + * that is architecture-specific. If you have a reliably fast + * bit count instruction, that might be better than the multiply + * and shift, for example. + */ +struct word_at_a_time { + const unsigned long one_bits, high_bits; +}; + +#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) } + +#ifdef CONFIG_64BIT + +/* + * Jan Achrenius on G+: microoptimized version of + * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56" + * that works for the bytemasks without having to + * mask them first. + */ +static inline long count_masked_bytes(unsigned long mask) +{ + return mask*0x0001020304050608ul >> 56; +} + +#else /* 32-bit case */ + +/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */ +static inline long count_masked_bytes(long mask) +{ + /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */ + long a = (0x0ff0001+mask) >> 23; + /* Fix the 1 for 00 case */ + return a & mask; +} + +#endif + +/* Return nonzero if it has a zero */ +static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c) +{ + unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits; + *bits = mask; + return mask; +} + +static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c) +{ + return bits; +} + +static inline unsigned long create_zero_mask(unsigned long bits) +{ + bits = (bits - 1) & ~bits; + return bits >> 7; +} + +/* The mask we created is directly usable as a bytemask */ +#define zero_bytemask(mask) (mask) + +static inline unsigned long find_zero(unsigned long mask) +{ + return count_masked_bytes(mask); +} +#endif + #endif /* _ASM_WORD_AT_A_TIME_H */ -- 2.20.1