mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-26 16:40:55 +07:00
252e5c6e2e
It causes double align requirement for __get_vm_area_node() if parameter size is power of 2 and VM_IOREMAP is set in parameter flags, for example size=0x10000 -> fls_long(0x10000)=17 -> align=0x20000 get_count_order_long() is implemented and can be used instead of fls_long() for fixing the bug, for example size=0x10000 -> get_count_order_long(0x10000)=16 -> align=0x10000 [akpm@linux-foundation.org: s/get_order_long()/get_count_order_long()/] [zijun_hu@zoho.com: fixes] Link: http://lkml.kernel.org/r/57AABC8B.1040409@zoho.com [akpm@linux-foundation.org: locate get_count_order_long() next to get_count_order()] [akpm@linux-foundation.org: move get_count_order[_long] definitions to pick up fls_long()] [zijun_hu@htc.com: move out get_count_order[_long]() from __KERNEL__ scope] Link: http://lkml.kernel.org/r/57B2C4CE.80303@zoho.com Link: http://lkml.kernel.org/r/fc045ecf-20fa-0722-b3ac-9a6140488fad@zoho.com Signed-off-by: zijun_hu <zijun_hu@htc.com> Cc: Tejun Heo <tj@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Minchan Kim <minchan@kernel.org> Cc: David Rientjes <rientjes@google.com> Signed-off-by: zijun_hu <zijun_hu@htc.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
276 lines
6.7 KiB
C
276 lines
6.7 KiB
C
#ifndef _LINUX_BITOPS_H
|
|
#define _LINUX_BITOPS_H
|
|
#include <asm/types.h>
|
|
|
|
#ifdef __KERNEL__
|
|
#define BIT(nr) (1UL << (nr))
|
|
#define BIT_ULL(nr) (1ULL << (nr))
|
|
#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG))
|
|
#define BIT_WORD(nr) ((nr) / BITS_PER_LONG)
|
|
#define BIT_ULL_MASK(nr) (1ULL << ((nr) % BITS_PER_LONG_LONG))
|
|
#define BIT_ULL_WORD(nr) ((nr) / BITS_PER_LONG_LONG)
|
|
#define BITS_PER_BYTE 8
|
|
#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
|
|
#endif
|
|
|
|
/*
|
|
* Create a contiguous bitmask starting at bit position @l and ending at
|
|
* position @h. For example
|
|
* GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
|
|
*/
|
|
#define GENMASK(h, l) \
|
|
(((~0UL) << (l)) & (~0UL >> (BITS_PER_LONG - 1 - (h))))
|
|
|
|
#define GENMASK_ULL(h, l) \
|
|
(((~0ULL) << (l)) & (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h))))
|
|
|
|
extern unsigned int __sw_hweight8(unsigned int w);
|
|
extern unsigned int __sw_hweight16(unsigned int w);
|
|
extern unsigned int __sw_hweight32(unsigned int w);
|
|
extern unsigned long __sw_hweight64(__u64 w);
|
|
|
|
/*
|
|
* Include this here because some architectures need generic_ffs/fls in
|
|
* scope
|
|
*/
|
|
#include <asm/bitops.h>
|
|
|
|
#define for_each_set_bit(bit, addr, size) \
|
|
for ((bit) = find_first_bit((addr), (size)); \
|
|
(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_first_zero_bit((addr), (size)); \
|
|
(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))
|
|
|
|
static inline int get_bitmask_order(unsigned int count)
|
|
{
|
|
int order;
|
|
|
|
order = fls(count);
|
|
return order; /* We could be slightly more clever with -1 here... */
|
|
}
|
|
|
|
static __always_inline unsigned long hweight_long(unsigned long w)
|
|
{
|
|
return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
|
|
}
|
|
|
|
/**
|
|
* rol64 - rotate a 64-bit value left
|
|
* @word: value to rotate
|
|
* @shift: bits to roll
|
|
*/
|
|
static inline __u64 rol64(__u64 word, unsigned int shift)
|
|
{
|
|
return (word << shift) | (word >> (64 - shift));
|
|
}
|
|
|
|
/**
|
|
* ror64 - rotate a 64-bit value right
|
|
* @word: value to rotate
|
|
* @shift: bits to roll
|
|
*/
|
|
static inline __u64 ror64(__u64 word, unsigned int shift)
|
|
{
|
|
return (word >> shift) | (word << (64 - shift));
|
|
}
|
|
|
|
/**
|
|
* rol32 - rotate a 32-bit value left
|
|
* @word: value to rotate
|
|
* @shift: bits to roll
|
|
*/
|
|
static inline __u32 rol32(__u32 word, unsigned int shift)
|
|
{
|
|
return (word << shift) | (word >> ((-shift) & 31));
|
|
}
|
|
|
|
/**
|
|
* ror32 - rotate a 32-bit value right
|
|
* @word: value to rotate
|
|
* @shift: bits to roll
|
|
*/
|
|
static inline __u32 ror32(__u32 word, unsigned int shift)
|
|
{
|
|
return (word >> shift) | (word << (32 - shift));
|
|
}
|
|
|
|
/**
|
|
* rol16 - rotate a 16-bit value left
|
|
* @word: value to rotate
|
|
* @shift: bits to roll
|
|
*/
|
|
static inline __u16 rol16(__u16 word, unsigned int shift)
|
|
{
|
|
return (word << shift) | (word >> (16 - shift));
|
|
}
|
|
|
|
/**
|
|
* ror16 - rotate a 16-bit value right
|
|
* @word: value to rotate
|
|
* @shift: bits to roll
|
|
*/
|
|
static inline __u16 ror16(__u16 word, unsigned int shift)
|
|
{
|
|
return (word >> shift) | (word << (16 - shift));
|
|
}
|
|
|
|
/**
|
|
* rol8 - rotate an 8-bit value left
|
|
* @word: value to rotate
|
|
* @shift: bits to roll
|
|
*/
|
|
static inline __u8 rol8(__u8 word, unsigned int shift)
|
|
{
|
|
return (word << shift) | (word >> (8 - shift));
|
|
}
|
|
|
|
/**
|
|
* ror8 - rotate an 8-bit value right
|
|
* @word: value to rotate
|
|
* @shift: bits to roll
|
|
*/
|
|
static inline __u8 ror8(__u8 word, unsigned int shift)
|
|
{
|
|
return (word >> shift) | (word << (8 - shift));
|
|
}
|
|
|
|
/**
|
|
* sign_extend32 - sign extend a 32-bit value using specified bit as sign-bit
|
|
* @value: value to sign extend
|
|
* @index: 0 based bit index (0<=index<32) to sign bit
|
|
*
|
|
* This is safe to use for 16- and 8-bit types as well.
|
|
*/
|
|
static inline __s32 sign_extend32(__u32 value, int index)
|
|
{
|
|
__u8 shift = 31 - index;
|
|
return (__s32)(value << shift) >> shift;
|
|
}
|
|
|
|
/**
|
|
* sign_extend64 - sign extend a 64-bit value using specified bit as sign-bit
|
|
* @value: value to sign extend
|
|
* @index: 0 based bit index (0<=index<64) to sign bit
|
|
*/
|
|
static inline __s64 sign_extend64(__u64 value, int index)
|
|
{
|
|
__u8 shift = 63 - index;
|
|
return (__s64)(value << shift) >> shift;
|
|
}
|
|
|
|
static inline unsigned fls_long(unsigned long l)
|
|
{
|
|
if (sizeof(l) == 4)
|
|
return fls(l);
|
|
return fls64(l);
|
|
}
|
|
|
|
static inline int get_count_order(unsigned int count)
|
|
{
|
|
int order;
|
|
|
|
order = fls(count) - 1;
|
|
if (count & (count - 1))
|
|
order++;
|
|
return order;
|
|
}
|
|
|
|
/**
|
|
* get_count_order_long - get order after rounding @l up to power of 2
|
|
* @l: parameter
|
|
*
|
|
* it is same as get_count_order() but with long type parameter
|
|
*/
|
|
static inline int get_count_order_long(unsigned long l)
|
|
{
|
|
if (l == 0UL)
|
|
return -1;
|
|
else if (l & (l - 1UL))
|
|
return (int)fls_long(l);
|
|
else
|
|
return (int)fls_long(l) - 1;
|
|
}
|
|
|
|
/**
|
|
* __ffs64 - find first set bit in a 64 bit word
|
|
* @word: The 64 bit word
|
|
*
|
|
* On 64 bit arches this is a synomyn for __ffs
|
|
* The result is not defined if no bits are set, so check that @word
|
|
* is non-zero before calling this.
|
|
*/
|
|
static inline unsigned long __ffs64(u64 word)
|
|
{
|
|
#if BITS_PER_LONG == 32
|
|
if (((u32)word) == 0UL)
|
|
return __ffs((u32)(word >> 32)) + 32;
|
|
#elif BITS_PER_LONG != 64
|
|
#error BITS_PER_LONG not 32 or 64
|
|
#endif
|
|
return __ffs((unsigned long)word);
|
|
}
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
#ifndef set_mask_bits
|
|
#define set_mask_bits(ptr, _mask, _bits) \
|
|
({ \
|
|
const typeof(*ptr) mask = (_mask), bits = (_bits); \
|
|
typeof(*ptr) old, new; \
|
|
\
|
|
do { \
|
|
old = ACCESS_ONCE(*ptr); \
|
|
new = (old & ~mask) | bits; \
|
|
} while (cmpxchg(ptr, old, new) != old); \
|
|
\
|
|
new; \
|
|
})
|
|
#endif
|
|
|
|
#ifndef bit_clear_unless
|
|
#define bit_clear_unless(ptr, _clear, _test) \
|
|
({ \
|
|
const typeof(*ptr) clear = (_clear), test = (_test); \
|
|
typeof(*ptr) old, new; \
|
|
\
|
|
do { \
|
|
old = ACCESS_ONCE(*ptr); \
|
|
new = old & ~clear; \
|
|
} while (!(old & test) && \
|
|
cmpxchg(ptr, old, new) != old); \
|
|
\
|
|
!(old & test); \
|
|
})
|
|
#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.
|
|
*/
|
|
extern unsigned long find_last_bit(const unsigned long *addr,
|
|
unsigned long size);
|
|
#endif
|
|
|
|
#endif /* __KERNEL__ */
|
|
#endif
|