• C
    percpucounter: Optimize __percpu_counter_add a bit through the use of this_cpu() options. · 819a72af
    Christoph Lameter 提交于
    The this_cpu_* options can be used to optimize __percpu_counter_add a bit. Avoids
    some address arithmetic and saves 12 bytes.
    
    Before:
    
    
    00000000000001d3 <__percpu_counter_add>:
     1d3:	55                   	push   %rbp
     1d4:	48 89 e5             	mov    %rsp,%rbp
     1d7:	41 55                	push   %r13
     1d9:	41 54                	push   %r12
     1db:	53                   	push   %rbx
     1dc:	48 89 fb             	mov    %rdi,%rbx
     1df:	48 83 ec 08          	sub    $0x8,%rsp
     1e3:	4c 8b 67 30          	mov    0x30(%rdi),%r12
     1e7:	65 4c 03 24 25 00 00 	add    %gs:0x0,%r12
     1ee:	00 00
     1f0:	4d 63 2c 24          	movslq (%r12),%r13
     1f4:	48 63 c2             	movslq %edx,%rax
     1f7:	49 01 f5             	add    %rsi,%r13
     1fa:	49 39 c5             	cmp    %rax,%r13
     1fd:	7d 0a                	jge    209 <__percpu_counter_add+0x36>
     1ff:	f7 da                	neg    %edx
     201:	48 63 d2             	movslq %edx,%rdx
     204:	49 39 d5             	cmp    %rdx,%r13
     207:	7f 1e                	jg     227 <__percpu_counter_add+0x54>
     209:	48 89 df             	mov    %rbx,%rdi
     20c:	e8 00 00 00 00       	callq  211 <__percpu_counter_add+0x3e>
     211:	4c 01 6b 18          	add    %r13,0x18(%rbx)
     215:	48 89 df             	mov    %rbx,%rdi
     218:	41 c7 04 24 00 00 00 	movl   $0x0,(%r12)
     21f:	00
     220:	e8 00 00 00 00       	callq  225 <__percpu_counter_add+0x52>
     225:	eb 04                	jmp    22b <__percpu_counter_add+0x58>
     227:	45 89 2c 24          	mov    %r13d,(%r12)
     22b:	5b                   	pop    %rbx
     22c:	5b                   	pop    %rbx
     22d:	41 5c                	pop    %r12
     22f:	41 5d                	pop    %r13
     231:	c9                   	leaveq
     232:	c3                   	retq
    
    
    After:
    
    00000000000001d3 <__percpu_counter_add>:
     1d3:	55                   	push   %rbp
     1d4:	48 63 ca             	movslq %edx,%rcx
     1d7:	48 89 e5             	mov    %rsp,%rbp
     1da:	41 54                	push   %r12
     1dc:	53                   	push   %rbx
     1dd:	48 89 fb             	mov    %rdi,%rbx
     1e0:	48 8b 47 30          	mov    0x30(%rdi),%rax
     1e4:	65 44 8b 20          	mov    %gs:(%rax),%r12d
     1e8:	4d 63 e4             	movslq %r12d,%r12
     1eb:	49 01 f4             	add    %rsi,%r12
     1ee:	49 39 cc             	cmp    %rcx,%r12
     1f1:	7d 0a                	jge    1fd <__percpu_counter_add+0x2a>
     1f3:	f7 da                	neg    %edx
     1f5:	48 63 d2             	movslq %edx,%rdx
     1f8:	49 39 d4             	cmp    %rdx,%r12
     1fb:	7f 21                	jg     21e <__percpu_counter_add+0x4b>
     1fd:	48 89 df             	mov    %rbx,%rdi
     200:	e8 00 00 00 00       	callq  205 <__percpu_counter_add+0x32>
     205:	4c 01 63 18          	add    %r12,0x18(%rbx)
     209:	48 8b 43 30          	mov    0x30(%rbx),%rax
     20d:	48 89 df             	mov    %rbx,%rdi
     210:	65 c7 00 00 00 00 00 	movl   $0x0,%gs:(%rax)
     217:	e8 00 00 00 00       	callq  21c <__percpu_counter_add+0x49>
     21c:	eb 04                	jmp    222 <__percpu_counter_add+0x4f>
     21e:	65 44 89 20          	mov    %r12d,%gs:(%rax)
     222:	5b                   	pop    %rbx
     223:	41 5c                	pop    %r12
     225:	c9                   	leaveq
     226:	c3                   	retq
    Reviewed-by: NPekka Enberg <penberg@kernel.org>
    Reviewed-by: NTejun Heo <tj@kernel.org>
    Reviewed-by: NMathieu Desnoyers <mathieu.desnoyers@efficios.com>
    Acked-by: NH. Peter Anvin <hpa@zytor.com>
    Signed-off-by: NChristoph Lameter <cl@linux.com>
    Signed-off-by: NTejun Heo <tj@kernel.org>
    819a72af
percpu_counter.c 5.0 KB
/*
 * 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);
反馈
建议
客服 返回
顶部