36126f8f2e
This changes the interfaces in <asm/word-at-a-time.h> to be a bit more complicated, but a lot more generic. In particular, it allows us to really do the operations efficiently on both little-endian and big-endian machines, pretty much regardless of machine details. For example, if you can rely on a fast population count instruction on your architecture, this will allow you to make your optimized <asm/word-at-a-time.h> file with that. NOTE! The "generic" version in include/asm-generic/word-at-a-time.h is not truly generic, it actually only works on big-endian. Why? Because on little-endian the generic algorithms are wasteful, since you can inevitably do better. The x86 implementation is an example of that. (The only truly non-generic part of the asm-generic implementation is the "find_zero()" function, and you could make a little-endian version of it. And if the Kbuild infrastructure allowed us to pick a particular header file, that would be lovely) The <asm/word-at-a-time.h> functions are as follows: - WORD_AT_A_TIME_CONSTANTS: specific constants that the algorithm uses. - has_zero(): take a word, and determine if it has a zero byte in it. It gets the word, the pointer to the constant pool, and a pointer to an intermediate "data" field it can set. This is the "quick-and-dirty" zero tester: it's what is run inside the hot loops. - "prep_zero_mask()": take the word, the data that has_zero() produced, and the constant pool, and generate an *exact* mask of which byte had the first zero. This is run directly *outside* the loop, and allows the "has_zero()" function to answer the "is there a zero byte" question without necessarily getting exactly *which* byte is the first one to contain a zero. If you do multiple byte lookups concurrently (eg "hash_name()", which looks for both NUL and '/' bytes), after you've done the prep_zero_mask() phase, the result of those can be or'ed together to get the "either or" case. - The result from "prep_zero_mask()" can then be fed into "find_zero()" (to find the byte offset of the first byte that was zero) or into "zero_bytemask()" (to find the bytemask of the bytes preceding the zero byte). The existence of zero_bytemask() is optional, and is not necessary for the normal string routines. But dentry name hashing needs it, so if you enable DENTRY_WORD_AT_A_TIME you need to expose it. This changes the generic strncpy_from_user() function and the dentry hashing functions to use these modified word-at-a-time interfaces. This gets us back to the optimized state of the x86 strncpy that we lost in the previous commit when moving over to the generic version. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
106 lines
2.5 KiB
C
106 lines
2.5 KiB
C
#ifndef _ASM_WORD_AT_A_TIME_H
|
|
#define _ASM_WORD_AT_A_TIME_H
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
/*
|
|
* 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);
|
|
}
|
|
|
|
/*
|
|
* Load an unaligned word from kernel space.
|
|
*
|
|
* In the (very unlikely) case of the word being a page-crosser
|
|
* and the next page not being mapped, take the exception and
|
|
* return zeroes in the non-existing part.
|
|
*/
|
|
static inline unsigned long load_unaligned_zeropad(const void *addr)
|
|
{
|
|
unsigned long ret, dummy;
|
|
|
|
asm(
|
|
"1:\tmov %2,%0\n"
|
|
"2:\n"
|
|
".section .fixup,\"ax\"\n"
|
|
"3:\t"
|
|
"lea %2,%1\n\t"
|
|
"and %3,%1\n\t"
|
|
"mov (%1),%0\n\t"
|
|
"leal %2,%%ecx\n\t"
|
|
"andl %4,%%ecx\n\t"
|
|
"shll $3,%%ecx\n\t"
|
|
"shr %%cl,%0\n\t"
|
|
"jmp 2b\n"
|
|
".previous\n"
|
|
_ASM_EXTABLE(1b, 3b)
|
|
:"=&r" (ret),"=&c" (dummy)
|
|
:"m" (*(unsigned long *)addr),
|
|
"i" (-sizeof(unsigned long)),
|
|
"i" (sizeof(unsigned long)-1));
|
|
return ret;
|
|
}
|
|
|
|
#endif /* _ASM_WORD_AT_A_TIME_H */
|