linux-next/lib/find_bit.c
Yury Norov e79864f316 lib/find_bit: optimize find_next_bit() functions
Over the past couple years, the function _find_next_bit() was extended
with parameters that modify its behavior to implement and- zero- and le-
flavors. The parameters are passed at compile time, but current design
prevents a compiler from optimizing out the conditionals.

As find_next_bit() API grows, I expect that more parameters will be added.
Current design would require more conditional code in _find_next_bit(),
which would bloat the helper even more and make it barely readable.

This patch replaces _find_next_bit() with a macro FIND_NEXT_BIT, and adds
a set of wrappers, so that the compile-time optimizations become possible.

The common logic is moved to the new macro, and all flavors may be
generated by providing a FETCH macro parameter, like in this example:

  #define FIND_NEXT_BIT(FETCH, MUNGE, size, start) ...

  find_next_xornot_and_bit(addr1, addr2, addr3, size, start)
  {
	return FIND_NEXT_BIT(addr1[idx] ^ ~addr2[idx] & addr3[idx],
				/* nop */, size, start);
  }

The FETCH may be of any complexity, as soon as it only refers the bitmap(s)
and an iterator idx.

MUNGE is here to support _le code generation for BE builds. May be
empty.

I ran find_bit_benchmark 16 times on top of 6.0-rc2 and 16 times on top
of 6.0-rc2 + this series. The results for kvm/x86_64 are:

                      v6.0-rc2  Optimized       Difference  Z-score
Random dense bitmap         ns         ns        ns      %
find_next_bit:          787735     670546    117189   14.9     3.97
find_next_zero_bit:     777492     664208    113284   14.6    10.51
find_last_bit:          830925     687573    143352   17.3     2.35
find_first_bit:        3874366    3306635    567731   14.7     1.84
find_first_and_bit:   40677125   37739887   2937238    7.2     1.36
find_next_and_bit:      347865     304456     43409   12.5     1.35

Random sparse bitmap
find_next_bit:           19816      14021      5795   29.2     6.10
find_next_zero_bit:    1318901    1223794     95107    7.2     1.41
find_last_bit:           14573      13514      1059    7.3     6.92
find_first_bit:        1313321    1249024     64297    4.9     1.53
find_first_and_bit:       8921       8098       823    9.2     4.56
find_next_and_bit:        9796       7176      2620   26.7     5.39

Where the statistics is significant (z-score > 3), the improvement
is ~15%.

According to the bloat-o-meter, the Image size is 10-11K less:

x86_64/defconfig:
add/remove: 32/14 grow/shrink: 61/782 up/down: 6344/-16521 (-10177)

arm64/defconfig:
add/remove: 3/2 grow/shrink: 50/714 up/down: 608/-11556 (-10948)

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Yury Norov <yury.norov@gmail.com>
2022-09-21 12:21:32 -07:00

200 lines
5.1 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/math.h>
#include <linux/minmax.h>
#include <linux/swab.h>
/*
* Common helper for find_bit() function family
* @FETCH: The expression that fetches and pre-processes each word of bitmap(s)
* @MUNGE: The expression that post-processes a word containing found bit (may be empty)
* @size: The bitmap size in bits
*/
#define FIND_FIRST_BIT(FETCH, MUNGE, size) \
({ \
unsigned long idx, val, sz = (size); \
\
for (idx = 0; idx * BITS_PER_LONG < sz; idx++) { \
val = (FETCH); \
if (val) { \
sz = min(idx * BITS_PER_LONG + __ffs(MUNGE(val)), sz); \
break; \
} \
} \
\
sz; \
})
/*
* Common helper for find_next_bit() function family
* @FETCH: The expression that fetches and pre-processes each word of bitmap(s)
* @MUNGE: The expression that post-processes a word containing found bit (may be empty)
* @size: The bitmap size in bits
* @start: The bitnumber to start searching at
*/
#define FIND_NEXT_BIT(FETCH, MUNGE, size, start) \
({ \
unsigned long mask, idx, tmp, sz = (size), __start = (start); \
\
if (unlikely(__start >= sz)) \
goto out; \
\
mask = MUNGE(BITMAP_FIRST_WORD_MASK(__start)); \
idx = __start / BITS_PER_LONG; \
\
for (tmp = (FETCH) & mask; !tmp; tmp = (FETCH)) { \
if ((idx + 1) * BITS_PER_LONG >= sz) \
goto out; \
idx++; \
} \
\
sz = min(idx * BITS_PER_LONG + __ffs(MUNGE(tmp)), sz); \
out: \
sz; \
})
#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)
{
return FIND_FIRST_BIT(addr[idx], /* nop */, size);
}
EXPORT_SYMBOL(_find_first_bit);
#endif
#ifndef find_first_and_bit
/*
* Find the first set bit in two memory regions.
*/
unsigned long _find_first_and_bit(const unsigned long *addr1,
const unsigned long *addr2,
unsigned long size)
{
return FIND_FIRST_BIT(addr1[idx] & addr2[idx], /* nop */, size);
}
EXPORT_SYMBOL(_find_first_and_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)
{
return FIND_FIRST_BIT(~addr[idx], /* nop */, size);
}
EXPORT_SYMBOL(_find_first_zero_bit);
#endif
#ifndef find_next_bit
unsigned long _find_next_bit(const unsigned long *addr, unsigned long nbits, unsigned long start)
{
return FIND_NEXT_BIT(addr[idx], /* nop */, nbits, start);
}
EXPORT_SYMBOL(_find_next_bit);
#endif
#ifndef find_next_and_bit
unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2,
unsigned long nbits, unsigned long start)
{
return FIND_NEXT_BIT(addr1[idx] & addr2[idx], /* nop */, nbits, start);
}
EXPORT_SYMBOL(_find_next_and_bit);
#endif
#ifndef find_next_zero_bit
unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits,
unsigned long start)
{
return FIND_NEXT_BIT(~addr[idx], /* nop */, nbits, start);
}
EXPORT_SYMBOL(_find_next_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
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);
#ifdef __BIG_ENDIAN
#ifndef find_first_zero_bit_le
/*
* Find the first cleared bit in an LE memory region.
*/
unsigned long _find_first_zero_bit_le(const unsigned long *addr, unsigned long size)
{
return FIND_FIRST_BIT(~addr[idx], swab, size);
}
EXPORT_SYMBOL(_find_first_zero_bit_le);
#endif
#ifndef find_next_zero_bit_le
unsigned long _find_next_zero_bit_le(const unsigned long *addr,
unsigned long size, unsigned long offset)
{
return FIND_NEXT_BIT(~addr[idx], swab, size, offset);
}
EXPORT_SYMBOL(_find_next_zero_bit_le);
#endif
#ifndef find_next_bit_le
unsigned long _find_next_bit_le(const unsigned long *addr,
unsigned long size, unsigned long offset)
{
return FIND_NEXT_BIT(addr[idx], swab, size, offset);
}
EXPORT_SYMBOL(_find_next_bit_le);
#endif
#endif /* __BIG_ENDIAN */