linux/arch/x86/include/asm/local.h
Peter Zijlstra 0c44c2d0f4 x86: Use asm goto to implement better modify_and_test() functions
Linus suggested using asm goto to get rid of the typical SETcc + TEST
instruction pair -- which also clobbers an extra register -- for our
typical modify_and_test() functions.

Because asm goto doesn't allow output fields it has to include an
unconditinal memory clobber when it changes a memory variable to force
a reload.

Luckily all atomic ops already imply a compiler barrier to go along
with their memory barrier semantics.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-0mtn9siwbeo1d33bap1422se@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-09-25 13:53:08 +02:00

162 lines
3.8 KiB
C

#ifndef _ASM_X86_LOCAL_H
#define _ASM_X86_LOCAL_H
#include <linux/percpu.h>
#include <linux/atomic.h>
#include <asm/asm.h>
typedef struct {
atomic_long_t a;
} local_t;
#define LOCAL_INIT(i) { ATOMIC_LONG_INIT(i) }
#define local_read(l) atomic_long_read(&(l)->a)
#define local_set(l, i) atomic_long_set(&(l)->a, (i))
static inline void local_inc(local_t *l)
{
asm volatile(_ASM_INC "%0"
: "+m" (l->a.counter));
}
static inline void local_dec(local_t *l)
{
asm volatile(_ASM_DEC "%0"
: "+m" (l->a.counter));
}
static inline void local_add(long i, local_t *l)
{
asm volatile(_ASM_ADD "%1,%0"
: "+m" (l->a.counter)
: "ir" (i));
}
static inline void local_sub(long i, local_t *l)
{
asm volatile(_ASM_SUB "%1,%0"
: "+m" (l->a.counter)
: "ir" (i));
}
/**
* local_sub_and_test - subtract value from variable and test result
* @i: integer value to subtract
* @l: pointer to type local_t
*
* Atomically subtracts @i from @l and returns
* true if the result is zero, or false for all
* other cases.
*/
static inline int local_sub_and_test(long i, local_t *l)
{
GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, i, "%0", "e");
}
/**
* local_dec_and_test - decrement and test
* @l: pointer to type local_t
*
* Atomically decrements @l by 1 and
* returns true if the result is 0, or false for all other
* cases.
*/
static inline int local_dec_and_test(local_t *l)
{
GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, "%0", "e");
}
/**
* local_inc_and_test - increment and test
* @l: pointer to type local_t
*
* Atomically increments @l by 1
* and returns true if the result is zero, or false for all
* other cases.
*/
static inline int local_inc_and_test(local_t *l)
{
GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, "%0", "e");
}
/**
* local_add_negative - add and test if negative
* @i: integer value to add
* @l: pointer to type local_t
*
* Atomically adds @i to @l and returns true
* if the result is negative, or false when
* result is greater than or equal to zero.
*/
static inline int local_add_negative(long i, local_t *l)
{
GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, i, "%0", "s");
}
/**
* local_add_return - add and return
* @i: integer value to add
* @l: pointer to type local_t
*
* Atomically adds @i to @l and returns @i + @l
*/
static inline long local_add_return(long i, local_t *l)
{
long __i = i;
asm volatile(_ASM_XADD "%0, %1;"
: "+r" (i), "+m" (l->a.counter)
: : "memory");
return i + __i;
}
static inline long local_sub_return(long i, local_t *l)
{
return local_add_return(-i, l);
}
#define local_inc_return(l) (local_add_return(1, l))
#define local_dec_return(l) (local_sub_return(1, l))
#define local_cmpxchg(l, o, n) \
(cmpxchg_local(&((l)->a.counter), (o), (n)))
/* Always has a lock prefix */
#define local_xchg(l, n) (xchg(&((l)->a.counter), (n)))
/**
* local_add_unless - add unless the number is a given value
* @l: pointer of type local_t
* @a: the amount to add to l...
* @u: ...unless l is equal to u.
*
* Atomically adds @a to @l, so long as it was not @u.
* Returns non-zero if @l was not @u, and zero otherwise.
*/
#define local_add_unless(l, a, u) \
({ \
long c, old; \
c = local_read((l)); \
for (;;) { \
if (unlikely(c == (u))) \
break; \
old = local_cmpxchg((l), c, c + (a)); \
if (likely(old == c)) \
break; \
c = old; \
} \
c != (u); \
})
#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
/* On x86_32, these are no better than the atomic variants.
* On x86-64 these are better than the atomic variants on SMP kernels
* because they dont use a lock prefix.
*/
#define __local_inc(l) local_inc(l)
#define __local_dec(l) local_dec(l)
#define __local_add(i, l) local_add((i), (l))
#define __local_sub(i, l) local_sub((i), (l))
#endif /* _ASM_X86_LOCAL_H */