提交 a6e2f029 编写于 作者: C Chris Metcalf

Make asm/word-at-a-time.h available on all architectures

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: NChris Metcalf <cmetcalf@ezchip.com>
上级 d770e558
......@@ -47,4 +47,5 @@ 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
......@@ -19,4 +19,5 @@ 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
......@@ -45,4 +45,5 @@ 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
......@@ -58,4 +58,5 @@ 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
......@@ -25,4 +25,5 @@ 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
......@@ -6,3 +6,4 @@ generic-y += irq_work.h
generic-y += mcs_spinlock.h
generic-y += preempt.h
generic-y += trace_clock.h
generic-y += word-at-a-time.h
......@@ -57,4 +57,5 @@ 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
......@@ -7,3 +7,4 @@ generic-y += mcs_spinlock.h
generic-y += preempt.h
generic-y += trace_clock.h
generic-y += vtime.h
generic-y += word-at-a-time.h
......@@ -8,3 +8,4 @@ generic-y += module.h
generic-y += preempt.h
generic-y += sections.h
generic-y += trace_clock.h
generic-y += word-at-a-time.h
......@@ -53,4 +53,5 @@ 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
......@@ -9,3 +9,4 @@ generic-y += mcs_spinlock.h
generic-y += preempt.h
generic-y += syscalls.h
generic-y += trace_clock.h
generic-y += word-at-a-time.h
......@@ -17,4 +17,5 @@ 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
......@@ -8,3 +8,4 @@ generic-y += mcs_spinlock.h
generic-y += preempt.h
generic-y += sections.h
generic-y += trace_clock.h
generic-y += word-at-a-time.h
......@@ -60,4 +60,5 @@ 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
......@@ -8,3 +8,4 @@ generic-y += preempt.h
generic-y += rwsem.h
generic-y += trace_clock.h
generic-y += vtime.h
generic-y += word-at-a-time.h
......@@ -5,3 +5,4 @@ generic-y += irq_work.h
generic-y += mcs_spinlock.h
generic-y += preempt.h
generic-y += trace_clock.h
generic-y += word-at-a-time.h
......@@ -12,3 +12,4 @@ generic-y += sections.h
generic-y += trace_clock.h
generic-y += xor.h
generic-y += serial.h
generic-y += word-at-a-time.h
......@@ -38,4 +38,5 @@ 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
......@@ -24,4 +24,5 @@ generic-y += preempt.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
......@@ -61,4 +61,5 @@ 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
......@@ -28,4 +28,5 @@ 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
#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 */
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册