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>
52 lines
1.2 KiB
C
52 lines
1.2 KiB
C
#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>
|
|
|
|
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;
|
|
}
|
|
|
|
#endif /* _ASM_WORD_AT_A_TIME_H */
|