mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-21 07:52:50 +07:00
1a1d48a4a8
With this config: http://busybox.net/~vda/kernel_config_OPTIMIZE_INLINING_and_Os gcc-4.7.2 generates many copies of these tiny functions: bitmap_weight (55 copies): 55 push %rbp 48 89 e5 mov %rsp,%rbp e8 3f 3a 8b 00 callq __bitmap_weight 5d pop %rbp c3 retq hweight_long (23 copies): 55 push %rbp e8 b5 65 8e 00 callq __sw_hweight64 48 89 e5 mov %rsp,%rbp 5d pop %rbp c3 retq See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122 This patch fixes this via s/inline/__always_inline/ While at it, replaced two "__inline__" with usual "inline" (the rest of the source file uses the latter). text data bss dec filename 86971357 17195880 36659200 140826437 vmlinux.before 86971120 17195912 36659200 140826232 vmlinux Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: David Rientjes <rientjes@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Graf <tgraf@suug.ch> Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/r/1438697716-28121-1-git-send-email-dvlasenk@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
332 lines
12 KiB
C
332 lines
12 KiB
C
#ifndef __LINUX_BITMAP_H
|
|
#define __LINUX_BITMAP_H
|
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/bitops.h>
|
|
#include <linux/string.h>
|
|
#include <linux/kernel.h>
|
|
|
|
/*
|
|
* bitmaps provide bit arrays that consume one or more unsigned
|
|
* longs. The bitmap interface and available operations are listed
|
|
* here, in bitmap.h
|
|
*
|
|
* Function implementations generic to all architectures are in
|
|
* lib/bitmap.c. Functions implementations that are architecture
|
|
* specific are in various include/asm-<arch>/bitops.h headers
|
|
* and other arch/<arch> specific files.
|
|
*
|
|
* See lib/bitmap.c for more details.
|
|
*/
|
|
|
|
/*
|
|
* The available bitmap operations and their rough meaning in the
|
|
* case that the bitmap is a single unsigned long are thus:
|
|
*
|
|
* Note that nbits should be always a compile time evaluable constant.
|
|
* Otherwise many inlines will generate horrible code.
|
|
*
|
|
* bitmap_zero(dst, nbits) *dst = 0UL
|
|
* bitmap_fill(dst, nbits) *dst = ~0UL
|
|
* bitmap_copy(dst, src, nbits) *dst = *src
|
|
* bitmap_and(dst, src1, src2, nbits) *dst = *src1 & *src2
|
|
* bitmap_or(dst, src1, src2, nbits) *dst = *src1 | *src2
|
|
* bitmap_xor(dst, src1, src2, nbits) *dst = *src1 ^ *src2
|
|
* bitmap_andnot(dst, src1, src2, nbits) *dst = *src1 & ~(*src2)
|
|
* bitmap_complement(dst, src, nbits) *dst = ~(*src)
|
|
* bitmap_equal(src1, src2, nbits) Are *src1 and *src2 equal?
|
|
* bitmap_intersects(src1, src2, nbits) Do *src1 and *src2 overlap?
|
|
* bitmap_subset(src1, src2, nbits) Is *src1 a subset of *src2?
|
|
* bitmap_empty(src, nbits) Are all bits zero in *src?
|
|
* bitmap_full(src, nbits) Are all bits set in *src?
|
|
* bitmap_weight(src, nbits) Hamming Weight: number set bits
|
|
* bitmap_set(dst, pos, nbits) Set specified bit area
|
|
* bitmap_clear(dst, pos, nbits) Clear specified bit area
|
|
* bitmap_find_next_zero_area(buf, len, pos, n, mask) Find bit free area
|
|
* bitmap_find_next_zero_area_off(buf, len, pos, n, mask) as above
|
|
* bitmap_shift_right(dst, src, n, nbits) *dst = *src >> n
|
|
* bitmap_shift_left(dst, src, n, nbits) *dst = *src << n
|
|
* bitmap_remap(dst, src, old, new, nbits) *dst = map(old, new)(src)
|
|
* bitmap_bitremap(oldbit, old, new, nbits) newbit = map(old, new)(oldbit)
|
|
* bitmap_onto(dst, orig, relmap, nbits) *dst = orig relative to relmap
|
|
* bitmap_fold(dst, orig, sz, nbits) dst bits = orig bits mod sz
|
|
* bitmap_parse(buf, buflen, dst, nbits) Parse bitmap dst from kernel buf
|
|
* bitmap_parse_user(ubuf, ulen, dst, nbits) Parse bitmap dst from user buf
|
|
* bitmap_parselist(buf, dst, nbits) Parse bitmap dst from kernel buf
|
|
* bitmap_parselist_user(buf, dst, nbits) Parse bitmap dst from user buf
|
|
* bitmap_find_free_region(bitmap, bits, order) Find and allocate bit region
|
|
* bitmap_release_region(bitmap, pos, order) Free specified bit region
|
|
* bitmap_allocate_region(bitmap, pos, order) Allocate specified bit region
|
|
*/
|
|
|
|
/*
|
|
* Also the following operations in asm/bitops.h apply to bitmaps.
|
|
*
|
|
* set_bit(bit, addr) *addr |= bit
|
|
* clear_bit(bit, addr) *addr &= ~bit
|
|
* change_bit(bit, addr) *addr ^= bit
|
|
* test_bit(bit, addr) Is bit set in *addr?
|
|
* test_and_set_bit(bit, addr) Set bit and return old value
|
|
* test_and_clear_bit(bit, addr) Clear bit and return old value
|
|
* test_and_change_bit(bit, addr) Change bit and return old value
|
|
* find_first_zero_bit(addr, nbits) Position first zero bit in *addr
|
|
* find_first_bit(addr, nbits) Position first set bit in *addr
|
|
* find_next_zero_bit(addr, nbits, bit) Position next zero bit in *addr >= bit
|
|
* find_next_bit(addr, nbits, bit) Position next set bit in *addr >= bit
|
|
*/
|
|
|
|
/*
|
|
* The DECLARE_BITMAP(name,bits) macro, in linux/types.h, can be used
|
|
* to declare an array named 'name' of just enough unsigned longs to
|
|
* contain all bit positions from 0 to 'bits' - 1.
|
|
*/
|
|
|
|
/*
|
|
* lib/bitmap.c provides these functions:
|
|
*/
|
|
|
|
extern int __bitmap_empty(const unsigned long *bitmap, unsigned int nbits);
|
|
extern int __bitmap_full(const unsigned long *bitmap, unsigned int nbits);
|
|
extern int __bitmap_equal(const unsigned long *bitmap1,
|
|
const unsigned long *bitmap2, unsigned int nbits);
|
|
extern void __bitmap_complement(unsigned long *dst, const unsigned long *src,
|
|
unsigned int nbits);
|
|
extern void __bitmap_shift_right(unsigned long *dst, const unsigned long *src,
|
|
unsigned int shift, unsigned int nbits);
|
|
extern void __bitmap_shift_left(unsigned long *dst, const unsigned long *src,
|
|
unsigned int shift, unsigned int nbits);
|
|
extern int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
|
|
const unsigned long *bitmap2, unsigned int nbits);
|
|
extern void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
|
|
const unsigned long *bitmap2, unsigned int nbits);
|
|
extern void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
|
|
const unsigned long *bitmap2, unsigned int nbits);
|
|
extern int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
|
|
const unsigned long *bitmap2, unsigned int nbits);
|
|
extern int __bitmap_intersects(const unsigned long *bitmap1,
|
|
const unsigned long *bitmap2, unsigned int nbits);
|
|
extern int __bitmap_subset(const unsigned long *bitmap1,
|
|
const unsigned long *bitmap2, unsigned int nbits);
|
|
extern int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits);
|
|
|
|
extern void bitmap_set(unsigned long *map, unsigned int start, int len);
|
|
extern void bitmap_clear(unsigned long *map, unsigned int start, int len);
|
|
|
|
extern unsigned long bitmap_find_next_zero_area_off(unsigned long *map,
|
|
unsigned long size,
|
|
unsigned long start,
|
|
unsigned int nr,
|
|
unsigned long align_mask,
|
|
unsigned long align_offset);
|
|
|
|
/**
|
|
* bitmap_find_next_zero_area - find a contiguous aligned zero area
|
|
* @map: The address to base the search on
|
|
* @size: The bitmap size in bits
|
|
* @start: The bitnumber to start searching at
|
|
* @nr: The number of zeroed bits we're looking for
|
|
* @align_mask: Alignment mask for zero area
|
|
*
|
|
* The @align_mask should be one less than a power of 2; the effect is that
|
|
* the bit offset of all zero areas this function finds is multiples of that
|
|
* power of 2. A @align_mask of 0 means no alignment is required.
|
|
*/
|
|
static inline unsigned long
|
|
bitmap_find_next_zero_area(unsigned long *map,
|
|
unsigned long size,
|
|
unsigned long start,
|
|
unsigned int nr,
|
|
unsigned long align_mask)
|
|
{
|
|
return bitmap_find_next_zero_area_off(map, size, start, nr,
|
|
align_mask, 0);
|
|
}
|
|
|
|
extern int __bitmap_parse(const char *buf, unsigned int buflen, int is_user,
|
|
unsigned long *dst, int nbits);
|
|
extern int bitmap_parse_user(const char __user *ubuf, unsigned int ulen,
|
|
unsigned long *dst, int nbits);
|
|
extern int bitmap_parselist(const char *buf, unsigned long *maskp,
|
|
int nmaskbits);
|
|
extern int bitmap_parselist_user(const char __user *ubuf, unsigned int ulen,
|
|
unsigned long *dst, int nbits);
|
|
extern void bitmap_remap(unsigned long *dst, const unsigned long *src,
|
|
const unsigned long *old, const unsigned long *new, unsigned int nbits);
|
|
extern int bitmap_bitremap(int oldbit,
|
|
const unsigned long *old, const unsigned long *new, int bits);
|
|
extern void bitmap_onto(unsigned long *dst, const unsigned long *orig,
|
|
const unsigned long *relmap, unsigned int bits);
|
|
extern void bitmap_fold(unsigned long *dst, const unsigned long *orig,
|
|
unsigned int sz, unsigned int nbits);
|
|
extern int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order);
|
|
extern void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order);
|
|
extern int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order);
|
|
#ifdef __BIG_ENDIAN
|
|
extern void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int nbits);
|
|
#else
|
|
#define bitmap_copy_le bitmap_copy
|
|
#endif
|
|
extern unsigned int bitmap_ord_to_pos(const unsigned long *bitmap, unsigned int ord, unsigned int nbits);
|
|
extern int bitmap_print_to_pagebuf(bool list, char *buf,
|
|
const unsigned long *maskp, int nmaskbits);
|
|
|
|
#define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
|
|
#define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1)))
|
|
|
|
#define small_const_nbits(nbits) \
|
|
(__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG)
|
|
|
|
static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
|
|
{
|
|
if (small_const_nbits(nbits))
|
|
*dst = 0UL;
|
|
else {
|
|
unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
|
|
memset(dst, 0, len);
|
|
}
|
|
}
|
|
|
|
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 void bitmap_copy(unsigned long *dst, const unsigned long *src,
|
|
unsigned int nbits)
|
|
{
|
|
if (small_const_nbits(nbits))
|
|
*dst = *src;
|
|
else {
|
|
unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
|
|
memcpy(dst, src, len);
|
|
}
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
|
|
const unsigned long *src2, unsigned int nbits)
|
|
{
|
|
if (small_const_nbits(nbits))
|
|
*dst = *src1 | *src2;
|
|
else
|
|
__bitmap_or(dst, src1, src2, nbits);
|
|
}
|
|
|
|
static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1,
|
|
const unsigned long *src2, unsigned int nbits)
|
|
{
|
|
if (small_const_nbits(nbits))
|
|
*dst = *src1 ^ *src2;
|
|
else
|
|
__bitmap_xor(dst, src1, src2, nbits);
|
|
}
|
|
|
|
static inline int bitmap_andnot(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_andnot(dst, src1, src2, nbits);
|
|
}
|
|
|
|
static inline void bitmap_complement(unsigned long *dst, const unsigned long *src,
|
|
unsigned int nbits)
|
|
{
|
|
if (small_const_nbits(nbits))
|
|
*dst = ~(*src);
|
|
else
|
|
__bitmap_complement(dst, src, nbits);
|
|
}
|
|
|
|
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));
|
|
else
|
|
return __bitmap_equal(src1, src2, nbits);
|
|
}
|
|
|
|
static inline int bitmap_intersects(const unsigned long *src1,
|
|
const unsigned long *src2, unsigned int nbits)
|
|
{
|
|
if (small_const_nbits(nbits))
|
|
return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
|
|
else
|
|
return __bitmap_intersects(src1, src2, nbits);
|
|
}
|
|
|
|
static inline int bitmap_subset(const unsigned long *src1,
|
|
const unsigned long *src2, unsigned int nbits)
|
|
{
|
|
if (small_const_nbits(nbits))
|
|
return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits));
|
|
else
|
|
return __bitmap_subset(src1, src2, 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 __always_inline int bitmap_weight(const unsigned long *src, unsigned 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_shift_right(unsigned long *dst, const unsigned long *src,
|
|
unsigned int shift, int nbits)
|
|
{
|
|
if (small_const_nbits(nbits))
|
|
*dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> shift;
|
|
else
|
|
__bitmap_shift_right(dst, src, shift, nbits);
|
|
}
|
|
|
|
static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *src,
|
|
unsigned int shift, unsigned int nbits)
|
|
{
|
|
if (small_const_nbits(nbits))
|
|
*dst = (*src << shift) & BITMAP_LAST_WORD_MASK(nbits);
|
|
else
|
|
__bitmap_shift_left(dst, src, shift, nbits);
|
|
}
|
|
|
|
static inline int bitmap_parse(const char *buf, unsigned int buflen,
|
|
unsigned long *maskp, int nmaskbits)
|
|
{
|
|
return __bitmap_parse(buf, buflen, 0, maskp, nmaskbits);
|
|
}
|
|
|
|
#endif /* __ASSEMBLY__ */
|
|
|
|
#endif /* __LINUX_BITMAP_H */
|