linux_dsm_epyc7002/include/linux/bitops.h
Peter Zijlstra febdbfe8a9 arch: Prepare for smp_mb__{before,after}_atomic()
Since the smp_mb__{before,after}*() ops are fundamentally dependent on
how an arch can implement atomics it doesn't make sense to have 3
variants of them. They must all be the same.

Furthermore, the 3 variants suggest they're only valid for those 3
atomic ops, while we have many more where they could be applied.

So move away from
smp_mb__{before,after}_{atomic,clear}_{dec,inc,bit}() and reduce the
interface to just the two: smp_mb__{before,after}_atomic().

This patch prepares the way by introducing default implementations in
asm-generic/barrier.h that default to a full barrier and providing
__deprecated inlines for the previous 6 barriers if they're not
provided by the arch.

This should allow for a mostly painless transition (lots of deprecated
warns in the interim).

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/n/tip-wr59327qdyi9mbzn6x937s4e@git.kernel.org
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: "Chen, Gong" <gong.chen@linux.intel.com>
Cc: John Sullivan <jsrhbz@kanargh.force9.co.uk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mauro Carvalho Chehab <m.chehab@samsung.com>
Cc: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: linux-arch@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-04-18 11:40:30 +02:00

248 lines
6.1 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) (((U32_C(1) << ((h) - (l) + 1)) - 1) << (l))
#define GENMASK_ULL(h, l) (((U64_C(1) << ((h) - (l) + 1)) - 1) << (l))
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>
/*
* Provide __deprecated wrappers for the new interface, avoid flag day changes.
* We need the ugly external functions to break header recursion hell.
*/
#ifndef smp_mb__before_clear_bit
static inline void __deprecated smp_mb__before_clear_bit(void)
{
extern void __smp_mb__before_atomic(void);
__smp_mb__before_atomic();
}
#endif
#ifndef smp_mb__after_clear_bit
static inline void __deprecated smp_mb__after_clear_bit(void)
{
extern void __smp_mb__after_atomic(void);
__smp_mb__after_atomic();
}
#endif
#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 __inline__ int get_count_order(unsigned int count)
{
int order;
order = fls(count) - 1;
if (count & (count - 1))
order++;
return order;
}
static 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 >> (32 - shift));
}
/**
* 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
*/
static inline __s32 sign_extend32(__u32 value, int index)
{
__u8 shift = 31 - index;
return (__s32)(value << shift) >> shift;
}
static inline unsigned fls_long(unsigned long l)
{
if (sizeof(l) == 4)
return fls(l);
return fls64(l);
}
/**
* __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 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 maximum size to search
*
* Returns the bit number of the first set bit, or size.
*/
extern unsigned long find_last_bit(const unsigned long *addr,
unsigned long size);
#endif
#endif /* __KERNEL__ */
#endif