c53c70a90f
This change cleans up the string code in a number of ways: - For memcpy(), fix bug in prefetch and increase distance to 3 lines; optimize for unaligned data; do all loads before wh64 to make memcpy safe for forward-overlapping calls; etc. Performance is improved. - Use new copy_byte() function on tilegx to spread a single byte value out into a full word using the shufflebytes instruction. - Clean up header include ordering to be more canonical, and remove spurious #undefs of function names. Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
37 lines
1.1 KiB
C
37 lines
1.1 KiB
C
/*
|
|
* Copyright 2010 Tilera Corporation. All Rights Reserved.
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation, version 2.
|
|
*
|
|
* This program is distributed in the hope that it will be useful, but
|
|
* WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
|
|
* NON INFRINGEMENT. See the GNU General Public License for
|
|
* more details.
|
|
*/
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/string.h>
|
|
#include <linux/module.h>
|
|
|
|
size_t strlen(const char *s)
|
|
{
|
|
/* Get an aligned pointer. */
|
|
const uintptr_t s_int = (uintptr_t) s;
|
|
const uint32_t *p = (const uint32_t *)(s_int & -4);
|
|
|
|
/* Read the first word, but force bytes before the string to be nonzero.
|
|
* This expression works because we know shift counts are taken mod 32.
|
|
*/
|
|
uint32_t v = *p | ((1 << (s_int << 3)) - 1);
|
|
|
|
uint32_t bits;
|
|
while ((bits = __insn_seqb(v, 0)) == 0)
|
|
v = *++p;
|
|
|
|
return ((const char *)p) + (__insn_ctz(bits) >> 3) - s;
|
|
}
|
|
EXPORT_SYMBOL(strlen);
|