mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-25 13:32:03 +07:00
ef4d6f6b27
The ror32 implementation (word >> shift) | (word << (32 - shift) has undefined behaviour if shift is outside the [1, 31] range. Similarly for the 64 bit variants. Most callers pass a compile-time constant (naturally in that range), but there's an UBSAN report that these may actually be called with a shift count of 0. Instead of special-casing that, we can make them DTRT for all values of shift while also avoiding UB. For some reason, this was already partly done for rol32 (which was well-defined for [0, 31]). gcc 8 recognizes these patterns as rotates, so for example __u32 rol32(__u32 word, unsigned int shift) { return (word << (shift & 31)) | (word >> ((-shift) & 31)); } compiles to 0000000000000020 <rol32>: 20: 89 f8 mov %edi,%eax 22: 89 f1 mov %esi,%ecx 24: d3 c0 rol %cl,%eax 26: c3 retq Older compilers unfortunately do not do as well, but this only affects the small minority of users that don't pass constants. Due to integer promotions, ro[lr]8 were already well-defined for shifts in [0, 8], and ro[lr]16 were mostly well-defined for shifts in [0, 16] (only mostly - u16 gets promoted to _signed_ int, so if bit 15 is set, word << 16 is undefined). For consistency, update those as well. Link: http://lkml.kernel.org/r/20190410211906.2190-1-linux@rasmusvillemoes.dk Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Reported-by: Ido Schimmel <idosch@mellanox.com> Tested-by: Ido Schimmel <idosch@mellanox.com> Reviewed-by: Will Deacon <will.deacon@arm.com> Cc: Vadim Pasternak <vadimp@mellanox.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Jacek Anaszewski <jacek.anaszewski@gmail.com> Cc: Pavel Machek <pavel@ucw.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
283 lines
6.7 KiB
C
283 lines
6.7 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_BITOPS_H
|
|
#define _LINUX_BITOPS_H
|
|
#include <asm/types.h>
|
|
#include <linux/bits.h>
|
|
|
|
#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE)
|
|
#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(long))
|
|
|
|
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 & 63)) | (word >> ((-shift) & 63));
|
|
}
|
|
|
|
/**
|
|
* 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 & 63)) | (word << ((-shift) & 63));
|
|
}
|
|
|
|
/**
|
|
* 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 & 31)) | (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 & 31)) | (word << ((-shift) & 31));
|
|
}
|
|
|
|
/**
|
|
* 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 & 15)) | (word >> ((-shift) & 15));
|
|
}
|
|
|
|
/**
|
|
* 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 & 15)) | (word << ((-shift) & 15));
|
|
}
|
|
|
|
/**
|
|
* 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 & 7)) | (word >> ((-shift) & 7));
|
|
}
|
|
|
|
/**
|
|
* 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 & 7)) | (word << ((-shift) & 7));
|
|
}
|
|
|
|
/**
|
|
* 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);
|
|
}
|
|
|
|
/**
|
|
* assign_bit - Assign value to a bit in memory
|
|
* @nr: the bit to set
|
|
* @addr: the address to start counting from
|
|
* @value: the value to assign
|
|
*/
|
|
static __always_inline void assign_bit(long nr, volatile unsigned long *addr,
|
|
bool value)
|
|
{
|
|
if (value)
|
|
set_bit(nr, addr);
|
|
else
|
|
clear_bit(nr, addr);
|
|
}
|
|
|
|
static __always_inline void __assign_bit(long nr, volatile unsigned long *addr,
|
|
bool value)
|
|
{
|
|
if (value)
|
|
__set_bit(nr, addr);
|
|
else
|
|
__clear_bit(nr, addr);
|
|
}
|
|
|
|
#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__ = READ_ONCE(*(ptr)); \
|
|
new__ = (old__ & ~mask__) | bits__; \
|
|
} while (cmpxchg(ptr, old__, new__) != old__); \
|
|
\
|
|
old__; \
|
|
})
|
|
#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__ = READ_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
|