mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-27 19:29:37 +00:00
![Chris Metcalf](/assets/img/avatar_default.png)
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@ezchip.com>
120 lines
2.7 KiB
C
120 lines
2.7 KiB
C
#ifndef _ASM_WORD_AT_A_TIME_H
|
|
#define _ASM_WORD_AT_A_TIME_H
|
|
|
|
#include <linux/kernel.h>
|
|
#include <asm/byteorder.h>
|
|
|
|
#ifdef __BIG_ENDIAN
|
|
|
|
struct word_at_a_time {
|
|
const unsigned long high_bits, low_bits;
|
|
};
|
|
|
|
#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0xfe) + 1, REPEAT_BYTE(0x7f) }
|
|
|
|
/* Bit set in the bytes that have a zero */
|
|
static inline long prep_zero_mask(unsigned long val, unsigned long rhs, const struct word_at_a_time *c)
|
|
{
|
|
unsigned long mask = (val & c->low_bits) + c->low_bits;
|
|
return ~(mask | rhs);
|
|
}
|
|
|
|
#define create_zero_mask(mask) (mask)
|
|
|
|
static inline long find_zero(unsigned long mask)
|
|
{
|
|
long byte = 0;
|
|
#ifdef CONFIG_64BIT
|
|
if (mask >> 32)
|
|
mask >>= 32;
|
|
else
|
|
byte = 4;
|
|
#endif
|
|
if (mask >> 16)
|
|
mask >>= 16;
|
|
else
|
|
byte += 2;
|
|
return (mask >> 8) ? byte : byte + 1;
|
|
}
|
|
|
|
static inline bool has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c)
|
|
{
|
|
unsigned long rhs = val | c->low_bits;
|
|
*data = rhs;
|
|
return (val + c->high_bits) & ~rhs;
|
|
}
|
|
|
|
#ifndef zero_bytemask
|
|
#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 */
|