kernel_samsung_a53x/tools/include/linux/bitmap.h
Alexander Lobakin 7dca11aa19 bitmap: introduce generic optimized bitmap_size()
commit a37fbe666c016fd89e4460d0ebfcea05baba46dc upstream.

The number of times yet another open coded
`BITS_TO_LONGS(nbits) * sizeof(long)` can be spotted is huge.
Some generic helper is long overdue.

Add one, bitmap_size(), but with one detail.
BITS_TO_LONGS() uses DIV_ROUND_UP(). The latter works well when both
divident and divisor are compile-time constants or when the divisor
is not a pow-of-2. When it is however, the compilers sometimes tend
to generate suboptimal code (GCC 13):

48 83 c0 3f          	add    $0x3f,%rax
48 c1 e8 06          	shr    $0x6,%rax
48 8d 14 c5 00 00 00 00	lea    0x0(,%rax,8),%rdx

%BITS_PER_LONG is always a pow-2 (either 32 or 64), but GCC still does
full division of `nbits + 63` by it and then multiplication by 8.
Instead of BITS_TO_LONGS(), use ALIGN() and then divide by 8. GCC:

8d 50 3f             	lea    0x3f(%rax),%edx
c1 ea 03             	shr    $0x3,%edx
81 e2 f8 ff ff 1f    	and    $0x1ffffff8,%edx

Now it shifts `nbits + 63` by 3 positions (IOW performs fast division
by 8) and then masks bits[2:0]. bloat-o-meter:

add/remove: 0/0 grow/shrink: 20/133 up/down: 156/-773 (-617)

Clang does it better and generates the same code before/after starting
from -O1, except that with the ALIGN() approach it uses %edx and thus
still saves some bytes:

add/remove: 0/0 grow/shrink: 9/133 up/down: 18/-538 (-520)

Note that we can't expand DIV_ROUND_UP() by adding a check and using
this approach there, as it's used in array declarations where
expressions are not allowed.
Add this helper to tools/ as well.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Acked-by: Yury Norov <yury.norov@gmail.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2024-11-23 23:20:42 +01:00

182 lines
4.7 KiB
C
Executable file

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _PERF_BITOPS_H
#define _PERF_BITOPS_H
#include <string.h>
#include <linux/bitops.h>
#include <stdlib.h>
#include <linux/kernel.h>
#define DECLARE_BITMAP(name,bits) \
unsigned long name[BITS_TO_LONGS(bits)]
int __bitmap_weight(const unsigned long *bitmap, int bits);
void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, int bits);
int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits);
int __bitmap_equal(const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits);
void bitmap_clear(unsigned long *map, unsigned int start, int len);
#define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
#define BITMAP_LAST_WORD_MASK(nbits) \
( \
((nbits) % BITS_PER_LONG) ? \
(1UL<<((nbits) % BITS_PER_LONG))-1 : ~0UL \
)
#define small_const_nbits(nbits) \
(__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG)
#define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE)
static inline void bitmap_zero(unsigned long *dst, int nbits)
{
if (small_const_nbits(nbits))
*dst = 0UL;
else {
memset(dst, 0, bitmap_size(nbits));
}
}
static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
{
unsigned int nlongs = BITS_TO_LONGS(nbits);
if (!small_const_nbits(nbits)) {
unsigned int len = (nlongs - 1) * sizeof(unsigned long);
memset(dst, 0xff, len);
}
dst[nlongs - 1] = BITMAP_LAST_WORD_MASK(nbits);
}
static inline int bitmap_empty(const unsigned long *src, unsigned nbits)
{
if (small_const_nbits(nbits))
return ! (*src & BITMAP_LAST_WORD_MASK(nbits));
return find_first_bit(src, nbits) == nbits;
}
static inline int bitmap_full(const unsigned long *src, unsigned int nbits)
{
if (small_const_nbits(nbits))
return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits));
return find_first_zero_bit(src, nbits) == nbits;
}
static inline int bitmap_weight(const unsigned long *src, int nbits)
{
if (small_const_nbits(nbits))
return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits));
return __bitmap_weight(src, nbits);
}
static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
const unsigned long *src2, int nbits)
{
if (small_const_nbits(nbits))
*dst = *src1 | *src2;
else
__bitmap_or(dst, src1, src2, nbits);
}
/**
* test_and_set_bit - Set a bit and return its old value
* @nr: Bit to set
* @addr: Address to count from
*/
static inline int test_and_set_bit(int nr, unsigned long *addr)
{
unsigned long mask = BIT_MASK(nr);
unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
unsigned long old;
old = *p;
*p = old | mask;
return (old & mask) != 0;
}
/**
* test_and_clear_bit - Clear a bit and return its old value
* @nr: Bit to clear
* @addr: Address to count from
*/
static inline int test_and_clear_bit(int nr, unsigned long *addr)
{
unsigned long mask = BIT_MASK(nr);
unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
unsigned long old;
old = *p;
*p = old & ~mask;
return (old & mask) != 0;
}
/**
* bitmap_alloc - Allocate bitmap
* @nbits: Number of bits
*/
static inline unsigned long *bitmap_alloc(int nbits)
{
return calloc(1, bitmap_size(nbits));
}
/*
* bitmap_free - Free bitmap
* @bitmap: pointer to bitmap
*/
static inline void bitmap_free(unsigned long *bitmap)
{
free(bitmap);
}
/*
* bitmap_scnprintf - print bitmap list into buffer
* @bitmap: bitmap
* @nbits: size of bitmap
* @buf: buffer to store output
* @size: size of @buf
*/
size_t bitmap_scnprintf(unsigned long *bitmap, int nbits,
char *buf, size_t size);
/**
* bitmap_and - Do logical and on bitmaps
* @dst: resulting bitmap
* @src1: operand 1
* @src2: operand 2
* @nbits: size of bitmap
*/
static inline int bitmap_and(unsigned long *dst, const unsigned long *src1,
const unsigned long *src2, unsigned int nbits)
{
if (small_const_nbits(nbits))
return (*dst = *src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)) != 0;
return __bitmap_and(dst, src1, src2, nbits);
}
#ifdef __LITTLE_ENDIAN
#define BITMAP_MEM_ALIGNMENT 8
#else
#define BITMAP_MEM_ALIGNMENT (8 * sizeof(unsigned long))
#endif
#define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1)
#define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0)
static inline int bitmap_equal(const unsigned long *src1,
const unsigned long *src2, unsigned int nbits)
{
if (small_const_nbits(nbits))
return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits));
if (__builtin_constant_p(nbits & BITMAP_MEM_MASK) &&
IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT))
return !memcmp(src1, src2, nbits / 8);
return __bitmap_equal(src1, src2, nbits);
}
#endif /* _PERF_BITOPS_H */