linux-stable/include/linux/find.h
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

392 lines
12 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __LINUX_FIND_H_
#define __LINUX_FIND_H_
#ifndef __LINUX_BITMAP_H
#error only <linux/bitmap.h> can be included directly
#endif
#include <linux/bitops.h>
unsigned long _find_next_bit(const unsigned long *addr1, unsigned long nbits,
unsigned long start);
unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2,
unsigned long nbits, unsigned long start);
unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits,
unsigned long start);
extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size);
extern unsigned long _find_first_and_bit(const unsigned long *addr1,
const unsigned long *addr2, unsigned long size);
extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size);
extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size);
#ifdef __BIG_ENDIAN
unsigned long _find_first_zero_bit_le(const unsigned long *addr, unsigned long size);
unsigned long _find_next_zero_bit_le(const unsigned long *addr, unsigned
long size, unsigned long offset);
unsigned long _find_next_bit_le(const unsigned long *addr, unsigned
long size, unsigned long offset);
#endif
#ifndef find_next_bit
/**
* find_next_bit - find the next set bit in a memory region
* @addr: The address to base the search on
* @size: The bitmap size in bits
* @offset: The bitnumber to start searching at
*
* Returns the bit number for the next set bit
* If no bits are set, returns @size.
*/
static inline
unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
unsigned long offset)
{
if (small_const_nbits(size)) {
unsigned long val;
if (unlikely(offset >= size))
return size;
val = *addr & GENMASK(size - 1, offset);
return val ? __ffs(val) : size;
}
return _find_next_bit(addr, size, offset);
}
#endif
#ifndef find_next_and_bit
/**
* find_next_and_bit - find the next set bit in both memory regions
* @addr1: The first address to base the search on
* @addr2: The second address to base the search on
* @size: The bitmap size in bits
* @offset: The bitnumber to start searching at
*
* Returns the bit number for the next set bit
* If no bits are set, returns @size.
*/
static inline
unsigned long find_next_and_bit(const unsigned long *addr1,
const unsigned long *addr2, unsigned long size,
unsigned long offset)
{
if (small_const_nbits(size)) {
unsigned long val;
if (unlikely(offset >= size))
return size;
val = *addr1 & *addr2 & GENMASK(size - 1, offset);
return val ? __ffs(val) : size;
}
return _find_next_and_bit(addr1, addr2, size, offset);
}
#endif
#ifndef find_next_zero_bit
/**
* find_next_zero_bit - find the next cleared bit in a memory region
* @addr: The address to base the search on
* @size: The bitmap size in bits
* @offset: The bitnumber to start searching at
*
* Returns the bit number of the next zero bit
* If no bits are zero, returns @size.
*/
static inline
unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
unsigned long offset)
{
if (small_const_nbits(size)) {
unsigned long val;
if (unlikely(offset >= size))
return size;
val = *addr | ~GENMASK(size - 1, offset);
return val == ~0UL ? size : ffz(val);
}
return _find_next_zero_bit(addr, size, offset);
}
#endif
#ifndef find_first_bit
/**
* find_first_bit - find the first set bit in a memory region
* @addr: The address to start the search at
* @size: The maximum number of bits to search
*
* Returns the bit number of the first set bit.
* If no bits are set, returns @size.
*/
static inline
unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
{
if (small_const_nbits(size)) {
unsigned long val = *addr & GENMASK(size - 1, 0);
return val ? __ffs(val) : size;
}
return _find_first_bit(addr, size);
}
#endif
#ifndef find_first_and_bit
/**
* find_first_and_bit - find the first set bit in both memory regions
* @addr1: The first address to base the search on
* @addr2: The second address to base the search on
* @size: The bitmap size in bits
*
* Returns the bit number for the next set bit
* If no bits are set, returns @size.
*/
static inline
unsigned long find_first_and_bit(const unsigned long *addr1,
const unsigned long *addr2,
unsigned long size)
{
if (small_const_nbits(size)) {
unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0);
return val ? __ffs(val) : size;
}
return _find_first_and_bit(addr1, addr2, size);
}
#endif
#ifndef find_first_zero_bit
/**
* find_first_zero_bit - find the first cleared bit in a memory region
* @addr: The address to start the search at
* @size: The maximum number of bits to search
*
* Returns the bit number of the first cleared bit.
* If no bits are zero, returns @size.
*/
static inline
unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
{
if (small_const_nbits(size)) {
unsigned long val = *addr | ~GENMASK(size - 1, 0);
return val == ~0UL ? size : ffz(val);
}
return _find_first_zero_bit(addr, size);
}
#endif
#ifndef find_last_bit
/**
* find_last_bit - find the last set bit in a memory region
* @addr: The address to start the search at
* @size: The number of bits to search
*
* Returns the bit number of the last set bit, or size.
*/
static inline
unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
{
if (small_const_nbits(size)) {
unsigned long val = *addr & GENMASK(size - 1, 0);
return val ? __fls(val) : size;
}
return _find_last_bit(addr, size);
}
#endif
/**
* find_next_clump8 - find next 8-bit clump with set bits in a memory region
* @clump: location to store copy of found clump
* @addr: address to base the search on
* @size: bitmap size in number of bits
* @offset: bit offset at which to start searching
*
* Returns the bit offset for the next set clump; the found clump value is
* copied to the location pointed by @clump. If no bits are set, returns @size.
*/
extern unsigned long find_next_clump8(unsigned long *clump,
const unsigned long *addr,
unsigned long size, unsigned long offset);
#define find_first_clump8(clump, bits, size) \
find_next_clump8((clump), (bits), (size), 0)
#if defined(__LITTLE_ENDIAN)
static inline unsigned long find_next_zero_bit_le(const void *addr,
unsigned long size, unsigned long offset)
{
return find_next_zero_bit(addr, size, offset);
}
static inline unsigned long find_next_bit_le(const void *addr,
unsigned long size, unsigned long offset)
{
return find_next_bit(addr, size, offset);
}
static inline unsigned long find_first_zero_bit_le(const void *addr,
unsigned long size)
{
return find_first_zero_bit(addr, size);
}
#elif defined(__BIG_ENDIAN)
#ifndef find_next_zero_bit_le
static inline
unsigned long find_next_zero_bit_le(const void *addr, unsigned
long size, unsigned long offset)
{
if (small_const_nbits(size)) {
unsigned long val = *(const unsigned long *)addr;
if (unlikely(offset >= size))
return size;
val = swab(val) | ~GENMASK(size - 1, offset);
return val == ~0UL ? size : ffz(val);
}
return _find_next_zero_bit_le(addr, size, offset);
}
#endif
#ifndef find_first_zero_bit_le
static inline
unsigned long find_first_zero_bit_le(const void *addr, unsigned long size)
{
if (small_const_nbits(size)) {
unsigned long val = swab(*(const unsigned long *)addr) | ~GENMASK(size - 1, 0);
return val == ~0UL ? size : ffz(val);
}
return _find_first_zero_bit_le(addr, size);
}
#endif
#ifndef find_next_bit_le
static inline
unsigned long find_next_bit_le(const void *addr, unsigned
long size, unsigned long offset)
{
if (small_const_nbits(size)) {
unsigned long val = *(const unsigned long *)addr;
if (unlikely(offset >= size))
return size;
val = swab(val) & GENMASK(size - 1, offset);
return val ? __ffs(val) : size;
}
return _find_next_bit_le(addr, size, offset);
}
#endif
#else
#error "Please fix <asm/byteorder.h>"
#endif
#define for_each_set_bit(bit, addr, size) \
for ((bit) = find_next_bit((addr), (size), 0); \
(bit) < (size); \
(bit) = find_next_bit((addr), (size), (bit) + 1))
/* same as for_each_set_bit() but use bit as value to start with */
#define for_each_set_bit_from(bit, addr, size) \
for ((bit) = find_next_bit((addr), (size), (bit)); \
(bit) < (size); \
(bit) = find_next_bit((addr), (size), (bit) + 1))
#define for_each_clear_bit(bit, addr, size) \
for ((bit) = find_next_zero_bit((addr), (size), 0); \
(bit) < (size); \
(bit) = find_next_zero_bit((addr), (size), (bit) + 1))
/* same as for_each_clear_bit() but use bit as value to start with */
#define for_each_clear_bit_from(bit, addr, size) \
for ((bit) = find_next_zero_bit((addr), (size), (bit)); \
(bit) < (size); \
(bit) = find_next_zero_bit((addr), (size), (bit) + 1))
/**
* for_each_set_bitrange - iterate over all set bit ranges [b; e)
* @b: bit offset of start of current bitrange (first set bit)
* @e: bit offset of end of current bitrange (first unset bit)
* @addr: bitmap address to base the search on
* @size: bitmap size in number of bits
*/
#define for_each_set_bitrange(b, e, addr, size) \
for ((b) = find_next_bit((addr), (size), 0), \
(e) = find_next_zero_bit((addr), (size), (b) + 1); \
(b) < (size); \
(b) = find_next_bit((addr), (size), (e) + 1), \
(e) = find_next_zero_bit((addr), (size), (b) + 1))
/**
* for_each_set_bitrange_from - iterate over all set bit ranges [b; e)
* @b: bit offset of start of current bitrange (first set bit); must be initialized
* @e: bit offset of end of current bitrange (first unset bit)
* @addr: bitmap address to base the search on
* @size: bitmap size in number of bits
*/
#define for_each_set_bitrange_from(b, e, addr, size) \
for ((b) = find_next_bit((addr), (size), (b)), \
(e) = find_next_zero_bit((addr), (size), (b) + 1); \
(b) < (size); \
(b) = find_next_bit((addr), (size), (e) + 1), \
(e) = find_next_zero_bit((addr), (size), (b) + 1))
/**
* for_each_clear_bitrange - iterate over all unset bit ranges [b; e)
* @b: bit offset of start of current bitrange (first unset bit)
* @e: bit offset of end of current bitrange (first set bit)
* @addr: bitmap address to base the search on
* @size: bitmap size in number of bits
*/
#define for_each_clear_bitrange(b, e, addr, size) \
for ((b) = find_next_zero_bit((addr), (size), 0), \
(e) = find_next_bit((addr), (size), (b) + 1); \
(b) < (size); \
(b) = find_next_zero_bit((addr), (size), (e) + 1), \
(e) = find_next_bit((addr), (size), (b) + 1))
/**
* for_each_clear_bitrange_from - iterate over all unset bit ranges [b; e)
* @b: bit offset of start of current bitrange (first set bit); must be initialized
* @e: bit offset of end of current bitrange (first unset bit)
* @addr: bitmap address to base the search on
* @size: bitmap size in number of bits
*/
#define for_each_clear_bitrange_from(b, e, addr, size) \
for ((b) = find_next_zero_bit((addr), (size), (b)), \
(e) = find_next_bit((addr), (size), (b) + 1); \
(b) < (size); \
(b) = find_next_zero_bit((addr), (size), (e) + 1), \
(e) = find_next_bit((addr), (size), (b) + 1))
/**
* for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits
* @start: bit offset to start search and to store the current iteration offset
* @clump: location to store copy of current 8-bit clump
* @bits: bitmap address to base the search on
* @size: bitmap size in number of bits
*/
#define for_each_set_clump8(start, clump, bits, size) \
for ((start) = find_first_clump8(&(clump), (bits), (size)); \
(start) < (size); \
(start) = find_next_clump8(&(clump), (bits), (size), (start) + 8))
#endif /*__LINUX_FIND_H_ */