Added the x86 implementation of word-at-a-time to the generic version, which previously only supported big-endian. Omitted the x86-specific load_unaligned_zeropad(), which in any case is also not present for the existing BE-only implementation of a word-at-a-time, and is only used under CONFIG_DCACHE_WORD_ACCESS. Added as a "generic-y" to the Kbuilds of all architectures that didn't previously have it. Signed-off-by: Chris Metcalf <cmetcalf@xxxxxxxxxx> --- arch/arc/include/asm/Kbuild | 1 + arch/avr32/include/asm/Kbuild | 1 + arch/blackfin/include/asm/Kbuild | 1 + arch/c6x/include/asm/Kbuild | 1 + arch/cris/include/asm/Kbuild | 1 + arch/frv/include/asm/Kbuild | 1 + arch/hexagon/include/asm/Kbuild | 1 + arch/ia64/include/asm/Kbuild | 1 + arch/m32r/include/asm/Kbuild | 1 + arch/metag/include/asm/Kbuild | 1 + arch/microblaze/include/asm/Kbuild | 1 + arch/mips/include/asm/Kbuild | 1 + arch/mn10300/include/asm/Kbuild | 1 + arch/nios2/include/asm/Kbuild | 1 + arch/powerpc/include/asm/Kbuild | 1 + arch/s390/include/asm/Kbuild | 1 + arch/score/include/asm/Kbuild | 1 + arch/tile/include/asm/Kbuild | 1 + arch/um/include/asm/Kbuild | 1 + arch/unicore32/include/asm/Kbuild | 1 + arch/xtensa/include/asm/Kbuild | 1 + include/asm-generic/word-at-a-time.h | 80 ++++++++++++++++++++++++++++++++---- 22 files changed, 93 insertions(+), 8 deletions(-) diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild index be0c39e76f7c..be895ef03a51 100644 --- a/arch/arc/include/asm/Kbuild +++ b/arch/arc/include/asm/Kbuild @@ -49,4 +49,5 @@ generic-y += types.h generic-y += ucontext.h generic-y += user.h generic-y += vga.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild index 528d70d47a54..10dd6e8470bd 100644 --- a/arch/avr32/include/asm/Kbuild +++ b/arch/avr32/include/asm/Kbuild @@ -20,4 +20,5 @@ generic-y += sections.h generic-y += topology.h generic-y += trace_clock.h generic-y += vga.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild index 4bd3c3cfc9ab..9705a527b7b0 100644 --- a/arch/blackfin/include/asm/Kbuild +++ b/arch/blackfin/include/asm/Kbuild @@ -46,4 +46,5 @@ generic-y += types.h generic-y += ucontext.h generic-y += unaligned.h generic-y += user.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild index ae0a51f5376c..535efdb0692d 100644 --- a/arch/c6x/include/asm/Kbuild +++ b/arch/c6x/include/asm/Kbuild @@ -59,4 +59,5 @@ generic-y += types.h generic-y += ucontext.h generic-y += user.h generic-y += vga.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild index 057e51859b0a..4991539a25f6 100644 --- a/arch/cris/include/asm/Kbuild +++ b/arch/cris/include/asm/Kbuild @@ -26,4 +26,5 @@ generic-y += sections.h generic-y += topology.h generic-y += trace_clock.h generic-y += vga.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild index e3f81b53578e..ca34d1cf2cdf 100644 --- a/arch/frv/include/asm/Kbuild +++ b/arch/frv/include/asm/Kbuild @@ -7,3 +7,4 @@ generic-y += mcs_spinlock.h generic-y += preempt.h generic-y += scatterlist.h generic-y += trace_clock.h +generic-y += word-at-a-time.h diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild index c7a99f860b40..872920fba0a6 100644 --- a/arch/hexagon/include/asm/Kbuild +++ b/arch/hexagon/include/asm/Kbuild @@ -58,4 +58,5 @@ generic-y += types.h generic-y += ucontext.h generic-y += unaligned.h generic-y += vga.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild index 9b41b4bcc073..614579fa1e49 100644 --- a/arch/ia64/include/asm/Kbuild +++ b/arch/ia64/include/asm/Kbuild @@ -8,3 +8,4 @@ generic-y += preempt.h generic-y += scatterlist.h generic-y += trace_clock.h generic-y += vtime.h +generic-y += word-at-a-time.h diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild index 2edc793372fc..36f850dd4a1e 100644 --- a/arch/m32r/include/asm/Kbuild +++ b/arch/m32r/include/asm/Kbuild @@ -9,3 +9,4 @@ generic-y += preempt.h generic-y += scatterlist.h generic-y += sections.h generic-y += trace_clock.h +generic-y += word-at-a-time.h diff --git a/arch/metag/include/asm/Kbuild b/arch/metag/include/asm/Kbuild index 0bf5d525b945..a291b3b2529e 100644 --- a/arch/metag/include/asm/Kbuild +++ b/arch/metag/include/asm/Kbuild @@ -54,4 +54,5 @@ generic-y += ucontext.h generic-y += unaligned.h generic-y += user.h generic-y += vga.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index ab564a6db5c3..966f221b2d67 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -10,3 +10,4 @@ generic-y += preempt.h generic-y += scatterlist.h generic-y += syscalls.h generic-y += trace_clock.h +generic-y += word-at-a-time.h diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild index 526539cbc99f..c3cfb83aca1d 100644 --- a/arch/mips/include/asm/Kbuild +++ b/arch/mips/include/asm/Kbuild @@ -18,4 +18,5 @@ generic-y += serial.h generic-y += trace_clock.h generic-y += ucontext.h generic-y += user.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild index f892d9de47d9..30a06e2d6e42 100644 --- a/arch/mn10300/include/asm/Kbuild +++ b/arch/mn10300/include/asm/Kbuild @@ -9,3 +9,4 @@ generic-y += preempt.h generic-y += scatterlist.h generic-y += sections.h generic-y += trace_clock.h +generic-y += word-at-a-time.h diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild index 24b3d8999ac7..bc87081c0669 100644 --- a/arch/nios2/include/asm/Kbuild +++ b/arch/nios2/include/asm/Kbuild @@ -61,4 +61,5 @@ generic-y += types.h generic-y += unaligned.h generic-y += user.h generic-y += vga.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index 4b87205c230c..dfc61a151890 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -9,3 +9,4 @@ generic-y += rwsem.h generic-y += scatterlist.h generic-y += trace_clock.h generic-y += vtime.h +generic-y += word-at-a-time.h diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild index c631f98fd524..27c37b3d1dad 100644 --- a/arch/s390/include/asm/Kbuild +++ b/arch/s390/include/asm/Kbuild @@ -6,3 +6,4 @@ generic-y += mcs_spinlock.h generic-y += preempt.h generic-y += scatterlist.h generic-y += trace_clock.h +generic-y += word-at-a-time.h diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild index 83ed116d414c..16958f529aa7 100644 --- a/arch/score/include/asm/Kbuild +++ b/arch/score/include/asm/Kbuild @@ -13,3 +13,4 @@ generic-y += sections.h generic-y += trace_clock.h generic-y += xor.h generic-y += serial.h +generic-y += word-at-a-time.h diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild index f5433e0e34e0..0804122e579a 100644 --- a/arch/tile/include/asm/Kbuild +++ b/arch/tile/include/asm/Kbuild @@ -39,4 +39,5 @@ generic-y += termbits.h generic-y += termios.h generic-y += trace_clock.h generic-y += types.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild index 9176fa11d49b..ee02364d8922 100644 --- a/arch/um/include/asm/Kbuild +++ b/arch/um/include/asm/Kbuild @@ -26,4 +26,5 @@ generic-y += sections.h generic-y += switch_to.h generic-y += topology.h generic-y += trace_clock.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild index 3e0c19d0f4c5..f456bfa1dd54 100644 --- a/arch/unicore32/include/asm/Kbuild +++ b/arch/unicore32/include/asm/Kbuild @@ -62,4 +62,5 @@ generic-y += ucontext.h generic-y += unaligned.h generic-y += user.h generic-y += vga.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild index 86a9ab2e2ca9..6ac0a9ab3ea3 100644 --- a/arch/xtensa/include/asm/Kbuild +++ b/arch/xtensa/include/asm/Kbuild @@ -29,4 +29,5 @@ generic-y += statfs.h generic-y += termios.h generic-y += topology.h generic-y += trace_clock.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/include/asm-generic/word-at-a-time.h b/include/asm-generic/word-at-a-time.h index 94f9ea8abcae..011dde083f23 100644 --- a/include/asm-generic/word-at-a-time.h +++ b/include/asm-generic/word-at-a-time.h @@ -1,15 +1,10 @@ #ifndef _ASM_WORD_AT_A_TIME_H #define _ASM_WORD_AT_A_TIME_H -/* - * This says "generic", but it's actually big-endian only. - * Little-endian can use more efficient versions of these - * interfaces, see for example - * arch/x86/include/asm/word-at-a-time.h - * for those. - */ - #include <linux/kernel.h> +#include <asm/byteorder.h> + +#ifdef __BIG_ENDIAN struct word_at_a_time { const unsigned long high_bits, low_bits; @@ -53,4 +48,73 @@ static inline bool has_zero(unsigned long val, unsigned long *data, const struct #define zero_bytemask(mask) (~1ul << __fls(mask)) #endif +#else + +/* + * 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 /* __BIG_ENDIAN */ + #endif /* _ASM_WORD_AT_A_TIME_H */ -- 2.1.2 -- To unsubscribe from this list: send the line "unsubscribe linux-arch" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html