linux/arch/arm/include/asm/atomic.h
Catalin Marinas 200b812d00 Clear the exclusive monitor when returning from an exception
The patch adds a CLREX or dummy STREX to the exception return path. This
is needed because several atomic/locking operations use a pair of
LDREX/STREXEQ and the EQ condition may not always be satisfied. This
would leave the exclusive monitor status set and may cause problems with
atomic/locking operations in the interrupted code.

With this patch, the atomic_set() operation can be a simple STR
instruction (on SMP systems, the global exclusive monitor is cleared by
STR anyway). Clearing the exclusive monitor during context switch is no
longer needed as this is handled by the exception return path anyway.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Reported-by: Jamie Lokier <jamie@shareable.org>
2009-09-18 23:30:11 +01:00

241 lines
5.0 KiB
C

/*
* arch/arm/include/asm/atomic.h
*
* Copyright (C) 1996 Russell King.
* Copyright (C) 2002 Deep Blue Solutions Ltd.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#ifndef __ASM_ARM_ATOMIC_H
#define __ASM_ARM_ATOMIC_H
#include <linux/compiler.h>
#include <linux/types.h>
#include <asm/system.h>
#define ATOMIC_INIT(i) { (i) }
#ifdef __KERNEL__
/*
* On ARM, ordinary assignment (str instruction) doesn't clear the local
* strex/ldrex monitor on some implementations. The reason we can use it for
* atomic_set() is the clrex or dummy strex done on every exception return.
*/
#define atomic_read(v) ((v)->counter)
#define atomic_set(v,i) (((v)->counter) = (i))
#if __LINUX_ARM_ARCH__ >= 6
/*
* ARMv6 UP and SMP safe atomic ops. We use load exclusive and
* store exclusive to ensure that these are atomic. We may loop
* to ensure that the update happens.
*/
static inline void atomic_add(int i, atomic_t *v)
{
unsigned long tmp;
int result;
__asm__ __volatile__("@ atomic_add\n"
"1: ldrex %0, [%2]\n"
" add %0, %0, %3\n"
" strex %1, %0, [%2]\n"
" teq %1, #0\n"
" bne 1b"
: "=&r" (result), "=&r" (tmp)
: "r" (&v->counter), "Ir" (i)
: "cc");
}
static inline int atomic_add_return(int i, atomic_t *v)
{
unsigned long tmp;
int result;
smp_mb();
__asm__ __volatile__("@ atomic_add_return\n"
"1: ldrex %0, [%2]\n"
" add %0, %0, %3\n"
" strex %1, %0, [%2]\n"
" teq %1, #0\n"
" bne 1b"
: "=&r" (result), "=&r" (tmp)
: "r" (&v->counter), "Ir" (i)
: "cc");
smp_mb();
return result;
}
static inline void atomic_sub(int i, atomic_t *v)
{
unsigned long tmp;
int result;
__asm__ __volatile__("@ atomic_sub\n"
"1: ldrex %0, [%2]\n"
" sub %0, %0, %3\n"
" strex %1, %0, [%2]\n"
" teq %1, #0\n"
" bne 1b"
: "=&r" (result), "=&r" (tmp)
: "r" (&v->counter), "Ir" (i)
: "cc");
}
static inline int atomic_sub_return(int i, atomic_t *v)
{
unsigned long tmp;
int result;
smp_mb();
__asm__ __volatile__("@ atomic_sub_return\n"
"1: ldrex %0, [%2]\n"
" sub %0, %0, %3\n"
" strex %1, %0, [%2]\n"
" teq %1, #0\n"
" bne 1b"
: "=&r" (result), "=&r" (tmp)
: "r" (&v->counter), "Ir" (i)
: "cc");
smp_mb();
return result;
}
static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
{
unsigned long oldval, res;
smp_mb();
do {
__asm__ __volatile__("@ atomic_cmpxchg\n"
"ldrex %1, [%2]\n"
"mov %0, #0\n"
"teq %1, %3\n"
"strexeq %0, %4, [%2]\n"
: "=&r" (res), "=&r" (oldval)
: "r" (&ptr->counter), "Ir" (old), "r" (new)
: "cc");
} while (res);
smp_mb();
return oldval;
}
static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
{
unsigned long tmp, tmp2;
__asm__ __volatile__("@ atomic_clear_mask\n"
"1: ldrex %0, [%2]\n"
" bic %0, %0, %3\n"
" strex %1, %0, [%2]\n"
" teq %1, #0\n"
" bne 1b"
: "=&r" (tmp), "=&r" (tmp2)
: "r" (addr), "Ir" (mask)
: "cc");
}
#else /* ARM_ARCH_6 */
#ifdef CONFIG_SMP
#error SMP not supported on pre-ARMv6 CPUs
#endif
static inline int atomic_add_return(int i, atomic_t *v)
{
unsigned long flags;
int val;
raw_local_irq_save(flags);
val = v->counter;
v->counter = val += i;
raw_local_irq_restore(flags);
return val;
}
#define atomic_add(i, v) (void) atomic_add_return(i, v)
static inline int atomic_sub_return(int i, atomic_t *v)
{
unsigned long flags;
int val;
raw_local_irq_save(flags);
val = v->counter;
v->counter = val -= i;
raw_local_irq_restore(flags);
return val;
}
#define atomic_sub(i, v) (void) atomic_sub_return(i, v)
static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
{
int ret;
unsigned long flags;
raw_local_irq_save(flags);
ret = v->counter;
if (likely(ret == old))
v->counter = new;
raw_local_irq_restore(flags);
return ret;
}
static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
{
unsigned long flags;
raw_local_irq_save(flags);
*addr &= ~mask;
raw_local_irq_restore(flags);
}
#endif /* __LINUX_ARM_ARCH__ */
#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
static inline int atomic_add_unless(atomic_t *v, int a, int u)
{
int c, old;
c = atomic_read(v);
while (c != u && (old = atomic_cmpxchg((v), c, c + a)) != c)
c = old;
return c != u;
}
#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
#define atomic_inc(v) atomic_add(1, v)
#define atomic_dec(v) atomic_sub(1, v)
#define atomic_inc_and_test(v) (atomic_add_return(1, v) == 0)
#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0)
#define atomic_inc_return(v) (atomic_add_return(1, v))
#define atomic_dec_return(v) (atomic_sub_return(1, v))
#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
#define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)
#define smp_mb__before_atomic_dec() smp_mb()
#define smp_mb__after_atomic_dec() smp_mb()
#define smp_mb__before_atomic_inc() smp_mb()
#define smp_mb__after_atomic_inc() smp_mb()
#include <asm-generic/atomic-long.h>
#endif
#endif