forked from luck/tmp_suning_uos_patched
71c5576fbd
Revert
commit 1f7c14c62c
Author: Mingming Cao <cmm@us.ibm.com>
Date: Thu Oct 9 12:50:59 2008 -0400
percpu counter: clean up percpu_counter_sum_and_set()
Before this patch we had the following:
percpu_counter_sum(): return the percpu_counter's value
percpu_counter_sum_and_set(): return the percpu_counter's value, copying
that value into the central value and zeroing the per-cpu counters before
returning.
After this patch, percpu_counter_sum_and_set() has gone, and
percpu_counter_sum() gets the old percpu_counter_sum_and_set()
functionality.
Problem is, as Eric points out, the old percpu_counter_sum_and_set()
functionality was racy and wrong. It zeroes out counters on "other" cpus,
without holding any locks which will prevent races agaist updates from
those other CPUS.
This patch reverts 1f7c14c62c. This means
that percpu_counter_sum_and_set() still has the race, but
percpu_counter_sum() does not.
Note that this is not a simple revert - ext4 has since started using
percpu_counter_sum() for its dirty_blocks counter as well.
Note that this revert patch changes percpu_counter_sum() semantics.
Before the patch, a call to percpu_counter_sum() will bring the counter's
central counter mostly up-to-date, so a following percpu_counter_read()
will return a close value.
After this patch, a call to percpu_counter_sum() will leave the counter's
central accumulator unaltered, so a subsequent call to
percpu_counter_read() can now return a significantly inaccurate result.
If there is any code in the tree which was introduced after
e8ced39d5e was merged, and which depends
upon the new percpu_counter_sum() semantics, that code will break.
Reported-by: Eric Dumazet <dada1@cosmosbay.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mingming Cao <cmm@us.ibm.com>
Cc: <linux-ext4@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
154 lines
3.3 KiB
C
154 lines
3.3 KiB
C
#ifndef _LINUX_PERCPU_COUNTER_H
|
|
#define _LINUX_PERCPU_COUNTER_H
|
|
/*
|
|
* A simple "approximate counter" for use in ext2 and ext3 superblocks.
|
|
*
|
|
* WARNING: these things are HUGE. 4 kbytes per counter on 32-way P4.
|
|
*/
|
|
|
|
#include <linux/spinlock.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/list.h>
|
|
#include <linux/threads.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/types.h>
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
struct percpu_counter {
|
|
spinlock_t lock;
|
|
s64 count;
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
struct list_head list; /* All percpu_counters are on a list */
|
|
#endif
|
|
s32 *counters;
|
|
};
|
|
|
|
#if NR_CPUS >= 16
|
|
#define FBC_BATCH (NR_CPUS*2)
|
|
#else
|
|
#define FBC_BATCH (NR_CPUS*4)
|
|
#endif
|
|
|
|
int percpu_counter_init(struct percpu_counter *fbc, s64 amount);
|
|
int percpu_counter_init_irq(struct percpu_counter *fbc, s64 amount);
|
|
void percpu_counter_destroy(struct percpu_counter *fbc);
|
|
void percpu_counter_set(struct percpu_counter *fbc, s64 amount);
|
|
void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch);
|
|
s64 __percpu_counter_sum(struct percpu_counter *fbc, int set);
|
|
|
|
static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount)
|
|
{
|
|
__percpu_counter_add(fbc, amount, FBC_BATCH);
|
|
}
|
|
|
|
static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc)
|
|
{
|
|
s64 ret = __percpu_counter_sum(fbc, 0);
|
|
return ret < 0 ? 0 : ret;
|
|
}
|
|
|
|
static inline s64 percpu_counter_sum_and_set(struct percpu_counter *fbc)
|
|
{
|
|
return __percpu_counter_sum(fbc, 1);
|
|
}
|
|
|
|
|
|
static inline s64 percpu_counter_sum(struct percpu_counter *fbc)
|
|
{
|
|
return __percpu_counter_sum(fbc, 0);
|
|
}
|
|
|
|
static inline s64 percpu_counter_read(struct percpu_counter *fbc)
|
|
{
|
|
return fbc->count;
|
|
}
|
|
|
|
/*
|
|
* It is possible for the percpu_counter_read() to return a small negative
|
|
* number for some counter which should never be negative.
|
|
*
|
|
*/
|
|
static inline s64 percpu_counter_read_positive(struct percpu_counter *fbc)
|
|
{
|
|
s64 ret = fbc->count;
|
|
|
|
barrier(); /* Prevent reloads of fbc->count */
|
|
if (ret >= 0)
|
|
return ret;
|
|
return 1;
|
|
}
|
|
|
|
#else
|
|
|
|
struct percpu_counter {
|
|
s64 count;
|
|
};
|
|
|
|
static inline int percpu_counter_init(struct percpu_counter *fbc, s64 amount)
|
|
{
|
|
fbc->count = amount;
|
|
return 0;
|
|
}
|
|
|
|
#define percpu_counter_init_irq percpu_counter_init
|
|
|
|
static inline void percpu_counter_destroy(struct percpu_counter *fbc)
|
|
{
|
|
}
|
|
|
|
static inline void percpu_counter_set(struct percpu_counter *fbc, s64 amount)
|
|
{
|
|
fbc->count = amount;
|
|
}
|
|
|
|
#define __percpu_counter_add(fbc, amount, batch) \
|
|
percpu_counter_add(fbc, amount)
|
|
|
|
static inline void
|
|
percpu_counter_add(struct percpu_counter *fbc, s64 amount)
|
|
{
|
|
preempt_disable();
|
|
fbc->count += amount;
|
|
preempt_enable();
|
|
}
|
|
|
|
static inline s64 percpu_counter_read(struct percpu_counter *fbc)
|
|
{
|
|
return fbc->count;
|
|
}
|
|
|
|
static inline s64 percpu_counter_read_positive(struct percpu_counter *fbc)
|
|
{
|
|
return fbc->count;
|
|
}
|
|
|
|
static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc)
|
|
{
|
|
return percpu_counter_read_positive(fbc);
|
|
}
|
|
|
|
static inline s64 percpu_counter_sum(struct percpu_counter *fbc)
|
|
{
|
|
return percpu_counter_read(fbc);
|
|
}
|
|
|
|
#endif /* CONFIG_SMP */
|
|
|
|
static inline void percpu_counter_inc(struct percpu_counter *fbc)
|
|
{
|
|
percpu_counter_add(fbc, 1);
|
|
}
|
|
|
|
static inline void percpu_counter_dec(struct percpu_counter *fbc)
|
|
{
|
|
percpu_counter_add(fbc, -1);
|
|
}
|
|
|
|
static inline void percpu_counter_sub(struct percpu_counter *fbc, s64 amount)
|
|
{
|
|
percpu_counter_add(fbc, -amount);
|
|
}
|
|
|
|
#endif /* _LINUX_PERCPU_COUNTER_H */
|