kernel_optimize_test/lib/find_bit.c
Yury Norov 7dfaa98f64 lib/find_bit.c: uninline helper _find_next_bit()
It saves 25% of .text for arm64, and more for BE architectures.

Before:
  $ size lib/find_bit.o
     text    data     bss     dec     hex filename
     1012      56       0    1068     42c lib/find_bit.o

After:
  $ size lib/find_bit.o
     text    data     bss     dec     hex filename
      776      56       0     832     340 lib/find_bit.o

Link: http://lkml.kernel.org/r/20200103202846.21616-3-yury.norov@gmail.com
Signed-off-by: Yury Norov <yury.norov@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Allison Randal <allison@lohutok.net>
Cc: William Breathitt Gray <vilhelm.gray@gmail.com>
Cc: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-01-31 10:30:41 -08:00

193 lines
4.5 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/* 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.
*/
#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) || \
!defined(find_next_bit_le) || !defined(find_next_zero_bit_le) || \
!defined(find_next_and_bit)
/*
* This is a common helper function for find_next_bit, find_next_zero_bit, and
* find_next_and_bit. The differences are:
* - The "invert" argument, which is XORed with each fetched word before
* searching it for one bits.
* - The optional "addr2", which is anded with "addr1" if present.
*/
static unsigned long _find_next_bit(const unsigned long *addr1,
const unsigned long *addr2, unsigned long nbits,
unsigned long start, unsigned long invert, unsigned long le)
{
unsigned long tmp, mask;
if (unlikely(start >= nbits))
return nbits;
tmp = addr1[start / BITS_PER_LONG];
if (addr2)
tmp &= addr2[start / BITS_PER_LONG];
tmp ^= invert;
/* Handle 1st word. */
mask = BITMAP_FIRST_WORD_MASK(start);
if (le)
mask = swab(mask);
tmp &= mask;
start = round_down(start, BITS_PER_LONG);
while (!tmp) {
start += BITS_PER_LONG;
if (start >= nbits)
return nbits;
tmp = addr1[start / BITS_PER_LONG];
if (addr2)
tmp &= addr2[start / BITS_PER_LONG];
tmp ^= invert;
}
if (le)
tmp = swab(tmp);
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, NULL, size, offset, 0UL, 0);
}
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, NULL, size, offset, ~0UL, 0);
}
EXPORT_SYMBOL(find_next_zero_bit);
#endif
#if !defined(find_next_and_bit)
unsigned long find_next_and_bit(const unsigned long *addr1,
const unsigned long *addr2, unsigned long size,
unsigned long offset)
{
return _find_next_bit(addr1, addr2, size, offset, 0UL, 0);
}
EXPORT_SYMBOL(find_next_and_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
#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(addr, NULL, size, offset, ~0UL, 1);
}
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(addr, NULL, size, offset, 0UL, 1);
}
EXPORT_SYMBOL(find_next_bit_le);
#endif
#endif /* __BIG_ENDIAN */
unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr,
unsigned long size, unsigned long offset)
{
offset = find_next_bit(addr, size, offset);
if (offset == size)
return size;
offset = round_down(offset, 8);
*clump = bitmap_get_value8(addr, offset);
return offset;
}
EXPORT_SYMBOL(find_next_clump8);