Commit 09d4e0ed authored by Paul Mackerras's avatar Paul Mackerras Committed by Benjamin Herrenschmidt

lib: Provide generic atomic64_t implementation

Many processor architectures have no 64-bit atomic instructions, but
we need atomic64_t in order to support the perf_counter subsystem.

This adds an implementation of 64-bit atomic operations using hashed
spinlocks to provide atomicity.  For each atomic operation, the address
of the atomic64_t variable is hashed to an index into an array of 16
spinlocks.  That spinlock is taken (with interrupts disabled) around the
operation, which can then be coded non-atomically within the lock.

On UP, all the spinlock manipulation goes away and we simply disable
interrupts around each operation.  In fact gcc eliminates the whole
atomic64_lock variable as well.
Signed-off-by: default avatarPaul Mackerras <paulus@samba.org>
Signed-off-by: default avatarBenjamin Herrenschmidt <benh@kernel.crashing.org>
parent 4c75f84f
/*
* Generic implementation of 64-bit atomics using spinlocks,
* useful on processors that don't have 64-bit atomic instructions.
*
* Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#ifndef _ASM_GENERIC_ATOMIC64_H
#define _ASM_GENERIC_ATOMIC64_H
typedef struct {
long long counter;
} atomic64_t;
#define ATOMIC64_INIT(i) { (i) }
extern long long atomic64_read(const atomic64_t *v);
extern void atomic64_set(atomic64_t *v, long long i);
extern void atomic64_add(long long a, atomic64_t *v);
extern long long atomic64_add_return(long long a, atomic64_t *v);
extern void atomic64_sub(long long a, atomic64_t *v);
extern long long atomic64_sub_return(long long a, atomic64_t *v);
extern long long atomic64_dec_if_positive(atomic64_t *v);
extern long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n);
extern long long atomic64_xchg(atomic64_t *v, long long new);
extern int atomic64_add_unless(atomic64_t *v, long long a, long long u);
#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0)
#define atomic64_inc(v) atomic64_add(1LL, (v))
#define atomic64_inc_return(v) atomic64_add_return(1LL, (v))
#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0)
#define atomic64_dec(v) atomic64_sub(1LL, (v))
#define atomic64_dec_return(v) atomic64_sub_return(1LL, (v))
#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0)
#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL)
#endif /* _ASM_GENERIC_ATOMIC64_H */
...@@ -194,4 +194,10 @@ config DISABLE_OBSOLETE_CPUMASK_FUNCTIONS ...@@ -194,4 +194,10 @@ config DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
config NLATTR config NLATTR
bool bool
#
# Generic 64-bit atomic support is selected if needed
#
config GENERIC_ATOMIC64
bool
endmenu endmenu
...@@ -95,6 +95,8 @@ obj-$(CONFIG_DMA_API_DEBUG) += dma-debug.o ...@@ -95,6 +95,8 @@ obj-$(CONFIG_DMA_API_DEBUG) += dma-debug.o
obj-$(CONFIG_GENERIC_CSUM) += checksum.o obj-$(CONFIG_GENERIC_CSUM) += checksum.o
obj-$(CONFIG_GENERIC_ATOMIC64) += atomic64.o
hostprogs-y := gen_crc32table hostprogs-y := gen_crc32table
clean-files := crc32table.h clean-files := crc32table.h
......
/*
* Generic implementation of 64-bit atomics using spinlocks,
* useful on processors that don't have 64-bit atomic instructions.
*
* Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/types.h>
#include <linux/cache.h>
#include <linux/spinlock.h>
#include <linux/init.h>
#include <asm/atomic.h>
/*
* We use a hashed array of spinlocks to provide exclusive access
* to each atomic64_t variable. Since this is expected to used on
* systems with small numbers of CPUs (<= 4 or so), we use a
* relatively small array of 16 spinlocks to avoid wasting too much
* memory on the spinlock array.
*/
#define NR_LOCKS 16
/*
* Ensure each lock is in a separate cacheline.
*/
static union {
spinlock_t lock;
char pad[L1_CACHE_BYTES];
} atomic64_lock[NR_LOCKS] __cacheline_aligned_in_smp;
static inline spinlock_t *lock_addr(const atomic64_t *v)
{
unsigned long addr = (unsigned long) v;
addr >>= L1_CACHE_SHIFT;
addr ^= (addr >> 8) ^ (addr >> 16);
return &atomic64_lock[addr & (NR_LOCKS - 1)].lock;
}
long long atomic64_read(const atomic64_t *v)
{
unsigned long flags;
spinlock_t *lock = lock_addr(v);
long long val;
spin_lock_irqsave(lock, flags);
val = v->counter;
spin_unlock_irqrestore(lock, flags);
return val;
}
void atomic64_set(atomic64_t *v, long long i)
{
unsigned long flags;
spinlock_t *lock = lock_addr(v);
spin_lock_irqsave(lock, flags);
v->counter = i;
spin_unlock_irqrestore(lock, flags);
}
void atomic64_add(long long a, atomic64_t *v)
{
unsigned long flags;
spinlock_t *lock = lock_addr(v);
spin_lock_irqsave(lock, flags);
v->counter += a;
spin_unlock_irqrestore(lock, flags);
}
long long atomic64_add_return(long long a, atomic64_t *v)
{
unsigned long flags;
spinlock_t *lock = lock_addr(v);
long long val;
spin_lock_irqsave(lock, flags);
val = v->counter += a;
spin_unlock_irqrestore(lock, flags);
return val;
}
void atomic64_sub(long long a, atomic64_t *v)
{
unsigned long flags;
spinlock_t *lock = lock_addr(v);
spin_lock_irqsave(lock, flags);
v->counter -= a;
spin_unlock_irqrestore(lock, flags);
}
long long atomic64_sub_return(long long a, atomic64_t *v)
{
unsigned long flags;
spinlock_t *lock = lock_addr(v);
long long val;
spin_lock_irqsave(lock, flags);
val = v->counter -= a;
spin_unlock_irqrestore(lock, flags);
return val;
}
long long atomic64_dec_if_positive(atomic64_t *v)
{
unsigned long flags;
spinlock_t *lock = lock_addr(v);
long long val;
spin_lock_irqsave(lock, flags);
val = v->counter - 1;
if (val >= 0)
v->counter = val;
spin_unlock_irqrestore(lock, flags);
return val;
}
long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n)
{
unsigned long flags;
spinlock_t *lock = lock_addr(v);
long long val;
spin_lock_irqsave(lock, flags);
val = v->counter;
if (val == o)
v->counter = n;
spin_unlock_irqrestore(lock, flags);
return val;
}
long long atomic64_xchg(atomic64_t *v, long long new)
{
unsigned long flags;
spinlock_t *lock = lock_addr(v);
long long val;
spin_lock_irqsave(lock, flags);
val = v->counter;
v->counter = new;
spin_unlock_irqrestore(lock, flags);
return val;
}
int atomic64_add_unless(atomic64_t *v, long long a, long long u)
{
unsigned long flags;
spinlock_t *lock = lock_addr(v);
int ret = 1;
spin_lock_irqsave(lock, flags);
if (v->counter != u) {
v->counter += a;
ret = 0;
}
spin_unlock_irqrestore(lock, flags);
return ret;
}
static int init_atomic64_lock(void)
{
int i;
for (i = 0; i < NR_LOCKS; ++i)
spin_lock_init(&atomic64_lock[i].lock);
return 0;
}
pure_initcall(init_atomic64_lock);
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment