Revision 38e87880666091fe9c572a7a2ed2e771d97ca5aa authored by Chris Mason on 10 June 2011, 20:36:57 UTC, committed by Chris Mason on 10 June 2011, 20:36:57 UTC
Josef recently changed the free extent cache to look in
the block group cluster for any bitmaps before trying to
add a new bitmap for the same offset.  This avoids BUG_ON()s due
covering duplicate ranges.

But it didn't go quite far enough.  A given free range might span
between one or more bitmaps or free space entries.  The code has
looping to cover this, but it doesn't check for clustered bitmaps
every time.

This shuffles our gotos to check for a bitmap in the cluster
for every new bitmap entry we try to add.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
1 parent 3473f3c
Raw File
percpu_counter.c
/*
 * Fast batching percpu counters.
 */

#include <linux/percpu_counter.h>
#include <linux/notifier.h>
#include <linux/mutex.h>
#include <linux/init.h>
#include <linux/cpu.h>
#include <linux/module.h>
#include <linux/debugobjects.h>

static LIST_HEAD(percpu_counters);
static DEFINE_MUTEX(percpu_counters_lock);

#ifdef CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER

static struct debug_obj_descr percpu_counter_debug_descr;

static int percpu_counter_fixup_free(void *addr, enum debug_obj_state state)
{
	struct percpu_counter *fbc = addr;

	switch (state) {
	case ODEBUG_STATE_ACTIVE:
		percpu_counter_destroy(fbc);
		debug_object_free(fbc, &percpu_counter_debug_descr);
		return 1;
	default:
		return 0;
	}
}

static struct debug_obj_descr percpu_counter_debug_descr = {
	.name		= "percpu_counter",
	.fixup_free	= percpu_counter_fixup_free,
};

static inline void debug_percpu_counter_activate(struct percpu_counter *fbc)
{
	debug_object_init(fbc, &percpu_counter_debug_descr);
	debug_object_activate(fbc, &percpu_counter_debug_descr);
}

static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc)
{
	debug_object_deactivate(fbc, &percpu_counter_debug_descr);
	debug_object_free(fbc, &percpu_counter_debug_descr);
}

#else	/* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */
static inline void debug_percpu_counter_activate(struct percpu_counter *fbc)
{ }
static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc)
{ }
#endif	/* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */

void percpu_counter_set(struct percpu_counter *fbc, s64 amount)
{
	int cpu;

	spin_lock(&fbc->lock);
	for_each_possible_cpu(cpu) {
		s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
		*pcount = 0;
	}
	fbc->count = amount;
	spin_unlock(&fbc->lock);
}
EXPORT_SYMBOL(percpu_counter_set);

void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch)
{
	s64 count;

	preempt_disable();
	count = __this_cpu_read(*fbc->counters) + amount;
	if (count >= batch || count <= -batch) {
		spin_lock(&fbc->lock);
		fbc->count += count;
		__this_cpu_write(*fbc->counters, 0);
		spin_unlock(&fbc->lock);
	} else {
		__this_cpu_write(*fbc->counters, count);
	}
	preempt_enable();
}
EXPORT_SYMBOL(__percpu_counter_add);

/*
 * Add up all the per-cpu counts, return the result.  This is a more accurate
 * but much slower version of percpu_counter_read_positive()
 */
s64 __percpu_counter_sum(struct percpu_counter *fbc)
{
	s64 ret;
	int cpu;

	spin_lock(&fbc->lock);
	ret = fbc->count;
	for_each_online_cpu(cpu) {
		s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
		ret += *pcount;
	}
	spin_unlock(&fbc->lock);
	return ret;
}
EXPORT_SYMBOL(__percpu_counter_sum);

int __percpu_counter_init(struct percpu_counter *fbc, s64 amount,
			  struct lock_class_key *key)
{
	spin_lock_init(&fbc->lock);
	lockdep_set_class(&fbc->lock, key);
	fbc->count = amount;
	fbc->counters = alloc_percpu(s32);
	if (!fbc->counters)
		return -ENOMEM;

	debug_percpu_counter_activate(fbc);

#ifdef CONFIG_HOTPLUG_CPU
	INIT_LIST_HEAD(&fbc->list);
	mutex_lock(&percpu_counters_lock);
	list_add(&fbc->list, &percpu_counters);
	mutex_unlock(&percpu_counters_lock);
#endif
	return 0;
}
EXPORT_SYMBOL(__percpu_counter_init);

void percpu_counter_destroy(struct percpu_counter *fbc)
{
	if (!fbc->counters)
		return;

	debug_percpu_counter_deactivate(fbc);

#ifdef CONFIG_HOTPLUG_CPU
	mutex_lock(&percpu_counters_lock);
	list_del(&fbc->list);
	mutex_unlock(&percpu_counters_lock);
#endif
	free_percpu(fbc->counters);
	fbc->counters = NULL;
}
EXPORT_SYMBOL(percpu_counter_destroy);

int percpu_counter_batch __read_mostly = 32;
EXPORT_SYMBOL(percpu_counter_batch);

static void compute_batch_value(void)
{
	int nr = num_online_cpus();

	percpu_counter_batch = max(32, nr*2);
}

static int __cpuinit percpu_counter_hotcpu_callback(struct notifier_block *nb,
					unsigned long action, void *hcpu)
{
#ifdef CONFIG_HOTPLUG_CPU
	unsigned int cpu;
	struct percpu_counter *fbc;

	compute_batch_value();
	if (action != CPU_DEAD)
		return NOTIFY_OK;

	cpu = (unsigned long)hcpu;
	mutex_lock(&percpu_counters_lock);
	list_for_each_entry(fbc, &percpu_counters, list) {
		s32 *pcount;
		unsigned long flags;

		spin_lock_irqsave(&fbc->lock, flags);
		pcount = per_cpu_ptr(fbc->counters, cpu);
		fbc->count += *pcount;
		*pcount = 0;
		spin_unlock_irqrestore(&fbc->lock, flags);
	}
	mutex_unlock(&percpu_counters_lock);
#endif
	return NOTIFY_OK;
}

/*
 * Compare counter against given value.
 * Return 1 if greater, 0 if equal and -1 if less
 */
int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs)
{
	s64	count;

	count = percpu_counter_read(fbc);
	/* Check to see if rough count will be sufficient for comparison */
	if (abs(count - rhs) > (percpu_counter_batch*num_online_cpus())) {
		if (count > rhs)
			return 1;
		else
			return -1;
	}
	/* Need to use precise count */
	count = percpu_counter_sum(fbc);
	if (count > rhs)
		return 1;
	else if (count < rhs)
		return -1;
	else
		return 0;
}
EXPORT_SYMBOL(percpu_counter_compare);

static int __init percpu_counter_startup(void)
{
	compute_batch_value();
	hotcpu_notifier(percpu_counter_hotcpu_callback, 0);
	return 0;
}
module_init(percpu_counter_startup);
back to top