mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-27 19:25:05 +07:00
e4afd2e556
This saves 32 bytes on my x86-64 build, mostly due to alignment considerations and sharing more code between find_next_bit and find_next_zero_bit, but it does save a couple of instructions. There's really two parts to this commit: - First, the first half of the test: (!nbits || start >= nbits) is trivially a subset of the second half, since nbits and start are both unsigned - Second, while looking at the disassembly, I noticed that GCC was predicting the branch taken. Since this is a failure case, it's clearly the less likely of the two branches, so add an unlikely() to override GCC's heuristics. [mawilcox@microsoft.com: v2] Link: http://lkml.kernel.org/r/1483709016-1834-1-git-send-email-mawilcox@linuxonhyperv.com Link: http://lkml.kernel.org/r/1483709016-1834-1-git-send-email-mawilcox@linuxonhyperv.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Acked-by: Yury Norov <ynorov@caviumnetworks.com> Acked-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
194 lines
4.5 KiB
C
194 lines
4.5 KiB
C
/* bit search implementation
|
|
*
|
|
* Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
|
|
* Written by David Howells (dhowells@redhat.com)
|
|
*
|
|
* Copyright (C) 2008 IBM Corporation
|
|
* 'find_last_bit' is written by Rusty Russell <rusty@rustcorp.com.au>
|
|
* (Inspired by David Howell's find_next_bit implementation)
|
|
*
|
|
* Rewritten by Yury Norov <yury.norov@gmail.com> to decrease
|
|
* size and improve performance, 2015.
|
|
*
|
|
* 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; either version
|
|
* 2 of the License, or (at your option) any later version.
|
|
*/
|
|
|
|
#include <linux/bitops.h>
|
|
#include <linux/bitmap.h>
|
|
#include <linux/export.h>
|
|
#include <linux/kernel.h>
|
|
|
|
#if !defined(find_next_bit) || !defined(find_next_zero_bit)
|
|
|
|
/*
|
|
* This is a common helper function for find_next_bit and
|
|
* find_next_zero_bit. The difference is the "invert" argument, which
|
|
* is XORed with each fetched word before searching it for one bits.
|
|
*/
|
|
static unsigned long _find_next_bit(const unsigned long *addr,
|
|
unsigned long nbits, unsigned long start, unsigned long invert)
|
|
{
|
|
unsigned long tmp;
|
|
|
|
if (unlikely(start >= nbits))
|
|
return nbits;
|
|
|
|
tmp = addr[start / BITS_PER_LONG] ^ invert;
|
|
|
|
/* Handle 1st word. */
|
|
tmp &= BITMAP_FIRST_WORD_MASK(start);
|
|
start = round_down(start, BITS_PER_LONG);
|
|
|
|
while (!tmp) {
|
|
start += BITS_PER_LONG;
|
|
if (start >= nbits)
|
|
return nbits;
|
|
|
|
tmp = addr[start / BITS_PER_LONG] ^ invert;
|
|
}
|
|
|
|
return min(start + __ffs(tmp), nbits);
|
|
}
|
|
#endif
|
|
|
|
#ifndef find_next_bit
|
|
/*
|
|
* Find the next set bit in a memory region.
|
|
*/
|
|
unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
|
|
unsigned long offset)
|
|
{
|
|
return _find_next_bit(addr, size, offset, 0UL);
|
|
}
|
|
EXPORT_SYMBOL(find_next_bit);
|
|
#endif
|
|
|
|
#ifndef find_next_zero_bit
|
|
unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
|
|
unsigned long offset)
|
|
{
|
|
return _find_next_bit(addr, size, offset, ~0UL);
|
|
}
|
|
EXPORT_SYMBOL(find_next_zero_bit);
|
|
#endif
|
|
|
|
#ifndef find_first_bit
|
|
/*
|
|
* Find the first set bit in a memory region.
|
|
*/
|
|
unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
|
|
{
|
|
unsigned long idx;
|
|
|
|
for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
|
|
if (addr[idx])
|
|
return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size);
|
|
}
|
|
|
|
return size;
|
|
}
|
|
EXPORT_SYMBOL(find_first_bit);
|
|
#endif
|
|
|
|
#ifndef find_first_zero_bit
|
|
/*
|
|
* Find the first cleared bit in a memory region.
|
|
*/
|
|
unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
|
|
{
|
|
unsigned long idx;
|
|
|
|
for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
|
|
if (addr[idx] != ~0UL)
|
|
return min(idx * BITS_PER_LONG + ffz(addr[idx]), size);
|
|
}
|
|
|
|
return size;
|
|
}
|
|
EXPORT_SYMBOL(find_first_zero_bit);
|
|
#endif
|
|
|
|
#ifndef find_last_bit
|
|
unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
|
|
{
|
|
if (size) {
|
|
unsigned long val = BITMAP_LAST_WORD_MASK(size);
|
|
unsigned long idx = (size-1) / BITS_PER_LONG;
|
|
|
|
do {
|
|
val &= addr[idx];
|
|
if (val)
|
|
return idx * BITS_PER_LONG + __fls(val);
|
|
|
|
val = ~0ul;
|
|
} while (idx--);
|
|
}
|
|
return size;
|
|
}
|
|
EXPORT_SYMBOL(find_last_bit);
|
|
#endif
|
|
|
|
#ifdef __BIG_ENDIAN
|
|
|
|
/* include/linux/byteorder does not support "unsigned long" type */
|
|
static inline unsigned long ext2_swab(const unsigned long y)
|
|
{
|
|
#if BITS_PER_LONG == 64
|
|
return (unsigned long) __swab64((u64) y);
|
|
#elif BITS_PER_LONG == 32
|
|
return (unsigned long) __swab32((u32) y);
|
|
#else
|
|
#error BITS_PER_LONG not defined
|
|
#endif
|
|
}
|
|
|
|
#if !defined(find_next_bit_le) || !defined(find_next_zero_bit_le)
|
|
static unsigned long _find_next_bit_le(const unsigned long *addr,
|
|
unsigned long nbits, unsigned long start, unsigned long invert)
|
|
{
|
|
unsigned long tmp;
|
|
|
|
if (unlikely(start >= nbits))
|
|
return nbits;
|
|
|
|
tmp = addr[start / BITS_PER_LONG] ^ invert;
|
|
|
|
/* Handle 1st word. */
|
|
tmp &= ext2_swab(BITMAP_FIRST_WORD_MASK(start));
|
|
start = round_down(start, BITS_PER_LONG);
|
|
|
|
while (!tmp) {
|
|
start += BITS_PER_LONG;
|
|
if (start >= nbits)
|
|
return nbits;
|
|
|
|
tmp = addr[start / BITS_PER_LONG] ^ invert;
|
|
}
|
|
|
|
return min(start + __ffs(ext2_swab(tmp)), nbits);
|
|
}
|
|
#endif
|
|
|
|
#ifndef find_next_zero_bit_le
|
|
unsigned long find_next_zero_bit_le(const void *addr, unsigned
|
|
long size, unsigned long offset)
|
|
{
|
|
return _find_next_bit_le(addr, size, offset, ~0UL);
|
|
}
|
|
EXPORT_SYMBOL(find_next_zero_bit_le);
|
|
#endif
|
|
|
|
#ifndef find_next_bit_le
|
|
unsigned long find_next_bit_le(const void *addr, unsigned
|
|
long size, unsigned long offset)
|
|
{
|
|
return _find_next_bit_le(addr, size, offset, 0UL);
|
|
}
|
|
EXPORT_SYMBOL(find_next_bit_le);
|
|
#endif
|
|
|
|
#endif /* __BIG_ENDIAN */
|