intel_cacheinfo.c

linux 内核源代码

	if (new_l2) {
		l2 = new_l2;
#ifdef CONFIG_X86_HT
		per_cpu(cpu_llc_id, cpu) = l2_id;
#endif
	}

	if (new_l3) {
		l3 = new_l3;
#ifdef CONFIG_X86_HT
		per_cpu(cpu_llc_id, cpu) = l3_id;
#endif
	}

	if (trace)
		printk (KERN_INFO "CPU: Trace cache: %dK uops", trace);
	else if ( l1i )
		printk (KERN_INFO "CPU: L1 I cache: %dK", l1i);

	if (l1d)
		printk(", L1 D cache: %dK\n", l1d);
	else
		printk("\n");

	if (l2)
		printk(KERN_INFO "CPU: L2 cache: %dK\n", l2);

	if (l3)
		printk(KERN_INFO "CPU: L3 cache: %dK\n", l3);

	c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d));

	return l2;
}

/* pointer to _cpuid4_info array (for each cache leaf) */
static struct _cpuid4_info *cpuid4_info[NR_CPUS];
#define CPUID4_INFO_IDX(x,y)    (&((cpuid4_info[x])[y]))

#ifdef CONFIG_SMP
static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
{
	struct _cpuid4_info	*this_leaf, *sibling_leaf;
	unsigned long num_threads_sharing;
	int index_msb, i;
	struct cpuinfo_x86 *c = &cpu_data(cpu);

	this_leaf = CPUID4_INFO_IDX(cpu, index);
	num_threads_sharing = 1 + this_leaf->eax.split.num_threads_sharing;

	if (num_threads_sharing == 1)
		cpu_set(cpu, this_leaf->shared_cpu_map);
	else {
		index_msb = get_count_order(num_threads_sharing);

		for_each_online_cpu(i) {
			if (cpu_data(i).apicid >> index_msb ==
			    c->apicid >> index_msb) {
				cpu_set(i, this_leaf->shared_cpu_map);
				if (i != cpu && cpuid4_info[i])  {
					sibling_leaf = CPUID4_INFO_IDX(i, index);
					cpu_set(cpu, sibling_leaf->shared_cpu_map);
				}
			}
		}
	}
}
static void __cpuinit cache_remove_shared_cpu_map(unsigned int cpu, int index)
{
	struct _cpuid4_info	*this_leaf, *sibling_leaf;
	int sibling;

	this_leaf = CPUID4_INFO_IDX(cpu, index);
	for_each_cpu_mask(sibling, this_leaf->shared_cpu_map) {
		sibling_leaf = CPUID4_INFO_IDX(sibling, index);	
		cpu_clear(cpu, sibling_leaf->shared_cpu_map);
	}
}
#else
static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) {}
static void __cpuinit cache_remove_shared_cpu_map(unsigned int cpu, int index) {}
#endif

static void __cpuinit free_cache_attributes(unsigned int cpu)
{
	int i;

	for (i = 0; i < num_cache_leaves; i++)
		cache_remove_shared_cpu_map(cpu, i);

	kfree(cpuid4_info[cpu]);
	cpuid4_info[cpu] = NULL;
}

static int __cpuinit detect_cache_attributes(unsigned int cpu)
{
	struct _cpuid4_info	*this_leaf;
	unsigned long		j;
	int			retval;
	cpumask_t		oldmask;

	if (num_cache_leaves == 0)
		return -ENOENT;

	cpuid4_info[cpu] = kzalloc(
	    sizeof(struct _cpuid4_info) * num_cache_leaves, GFP_KERNEL);
	if (cpuid4_info[cpu] == NULL)
		return -ENOMEM;

	oldmask = current->cpus_allowed;
	retval = set_cpus_allowed(current, cpumask_of_cpu(cpu));
	if (retval)
		goto out;

	/* Do cpuid and store the results */
	for (j = 0; j < num_cache_leaves; j++) {
		this_leaf = CPUID4_INFO_IDX(cpu, j);
		retval = cpuid4_cache_lookup(j, this_leaf);
		if (unlikely(retval < 0)) {
			int i;

			for (i = 0; i < j; i++)
				cache_remove_shared_cpu_map(cpu, i);
			break;
		}
		cache_shared_cpu_map_setup(cpu, j);
	}
	set_cpus_allowed(current, oldmask);

out:
	if (retval) {
		kfree(cpuid4_info[cpu]);
		cpuid4_info[cpu] = NULL;
	}

	return retval;
}

#ifdef CONFIG_SYSFS

#include <linux/kobject.h>
#include <linux/sysfs.h>

extern struct sysdev_class cpu_sysdev_class; /* from drivers/base/cpu.c */

/* pointer to kobject for cpuX/cache */
static struct kobject * cache_kobject[NR_CPUS];

struct _index_kobject {
	struct kobject kobj;
	unsigned int cpu;
	unsigned short index;
};

/* pointer to array of kobjects for cpuX/cache/indexY */
static struct _index_kobject *index_kobject[NR_CPUS];
#define INDEX_KOBJECT_PTR(x,y)    (&((index_kobject[x])[y]))

#define show_one_plus(file_name, object, val)				\
static ssize_t show_##file_name						\
			(struct _cpuid4_info *this_leaf, char *buf)	\
{									\
	return sprintf (buf, "%lu\n", (unsigned long)this_leaf->object + val); \
}

show_one_plus(level, eax.split.level, 0);
show_one_plus(coherency_line_size, ebx.split.coherency_line_size, 1);
show_one_plus(physical_line_partition, ebx.split.physical_line_partition, 1);
show_one_plus(ways_of_associativity, ebx.split.ways_of_associativity, 1);
show_one_plus(number_of_sets, ecx.split.number_of_sets, 1);

static ssize_t show_size(struct _cpuid4_info *this_leaf, char *buf)
{
	return sprintf (buf, "%luK\n", this_leaf->size / 1024);
}

static ssize_t show_shared_cpu_map(struct _cpuid4_info *this_leaf, char *buf)
{
	char mask_str[NR_CPUS];
	cpumask_scnprintf(mask_str, NR_CPUS, this_leaf->shared_cpu_map);
	return sprintf(buf, "%s\n", mask_str);
}

static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf) {
	switch(this_leaf->eax.split.type) {
	    case CACHE_TYPE_DATA:
		return sprintf(buf, "Data\n");
		break;
	    case CACHE_TYPE_INST:
		return sprintf(buf, "Instruction\n");
		break;
	    case CACHE_TYPE_UNIFIED:
		return sprintf(buf, "Unified\n");
		break;
	    default:
		return sprintf(buf, "Unknown\n");
		break;
	}
}

struct _cache_attr {
	struct attribute attr;
	ssize_t (*show)(struct _cpuid4_info *, char *);
	ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count);
};

#define define_one_ro(_name) \
static struct _cache_attr _name = \
	__ATTR(_name, 0444, show_##_name, NULL)

define_one_ro(level);
define_one_ro(type);
define_one_ro(coherency_line_size);
define_one_ro(physical_line_partition);
define_one_ro(ways_of_associativity);
define_one_ro(number_of_sets);
define_one_ro(size);
define_one_ro(shared_cpu_map);

static struct attribute * default_attrs[] = {
	&type.attr,
	&level.attr,
	&coherency_line_size.attr,
	&physical_line_partition.attr,
	&ways_of_associativity.attr,
	&number_of_sets.attr,
	&size.attr,
	&shared_cpu_map.attr,
	NULL
};

#define to_object(k) container_of(k, struct _index_kobject, kobj)
#define to_attr(a) container_of(a, struct _cache_attr, attr)

static ssize_t show(struct kobject * kobj, struct attribute * attr, char * buf)
{
	struct _cache_attr *fattr = to_attr(attr);
	struct _index_kobject *this_leaf = to_object(kobj);
	ssize_t ret;

	ret = fattr->show ?
		fattr->show(CPUID4_INFO_IDX(this_leaf->cpu, this_leaf->index),
			buf) :
	       	0;
	return ret;
}

static ssize_t store(struct kobject * kobj, struct attribute * attr,
		     const char * buf, size_t count)
{
	return 0;
}

static struct sysfs_ops sysfs_ops = {
	.show   = show,
	.store  = store,
};

static struct kobj_type ktype_cache = {
	.sysfs_ops	= &sysfs_ops,
	.default_attrs	= default_attrs,
};

static struct kobj_type ktype_percpu_entry = {
	.sysfs_ops	= &sysfs_ops,
};

static void __cpuinit cpuid4_cache_sysfs_exit(unsigned int cpu)
{
	kfree(cache_kobject[cpu]);
	kfree(index_kobject[cpu]);
	cache_kobject[cpu] = NULL;
	index_kobject[cpu] = NULL;
	free_cache_attributes(cpu);
}

static int __cpuinit cpuid4_cache_sysfs_init(unsigned int cpu)
{
	int err;

	if (num_cache_leaves == 0)
		return -ENOENT;

	err = detect_cache_attributes(cpu);
	if (err)
		return err;

	/* Allocate all required memory */
	cache_kobject[cpu] = kzalloc(sizeof(struct kobject), GFP_KERNEL);
	if (unlikely(cache_kobject[cpu] == NULL))
		goto err_out;

	index_kobject[cpu] = kzalloc(
	    sizeof(struct _index_kobject ) * num_cache_leaves, GFP_KERNEL);
	if (unlikely(index_kobject[cpu] == NULL))
		goto err_out;

	return 0;

err_out:
	cpuid4_cache_sysfs_exit(cpu);
	return -ENOMEM;
}

static cpumask_t cache_dev_map = CPU_MASK_NONE;

/* Add/Remove cache interface for CPU device */
static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
{
	unsigned int cpu = sys_dev->id;
	unsigned long i, j;
	struct _index_kobject *this_object;
	int retval;

	retval = cpuid4_cache_sysfs_init(cpu);
	if (unlikely(retval < 0))
		return retval;

	cache_kobject[cpu]->parent = &sys_dev->kobj;
	kobject_set_name(cache_kobject[cpu], "%s", "cache");
	cache_kobject[cpu]->ktype = &ktype_percpu_entry;
	retval = kobject_register(cache_kobject[cpu]);
	if (retval < 0) {
		cpuid4_cache_sysfs_exit(cpu);
		return retval;
	}

	for (i = 0; i < num_cache_leaves; i++) {
		this_object = INDEX_KOBJECT_PTR(cpu,i);
		this_object->cpu = cpu;
		this_object->index = i;
		this_object->kobj.parent = cache_kobject[cpu];
		kobject_set_name(&(this_object->kobj), "index%1lu", i);
		this_object->kobj.ktype = &ktype_cache;
		retval = kobject_register(&(this_object->kobj));
		if (unlikely(retval)) {
			for (j = 0; j < i; j++) {
				kobject_unregister(
					&(INDEX_KOBJECT_PTR(cpu,j)->kobj));
			}
			kobject_unregister(cache_kobject[cpu]);
			cpuid4_cache_sysfs_exit(cpu);
			break;
		}
	}
	if (!retval)
		cpu_set(cpu, cache_dev_map);

	return retval;
}

static void __cpuinit cache_remove_dev(struct sys_device * sys_dev)
{
	unsigned int cpu = sys_dev->id;
	unsigned long i;

	if (cpuid4_info[cpu] == NULL)
		return;
	if (!cpu_isset(cpu, cache_dev_map))
		return;
	cpu_clear(cpu, cache_dev_map);

	for (i = 0; i < num_cache_leaves; i++)
		kobject_unregister(&(INDEX_KOBJECT_PTR(cpu,i)->kobj));
	kobject_unregister(cache_kobject[cpu]);
	cpuid4_cache_sysfs_exit(cpu);
}

static int __cpuinit cacheinfo_cpu_callback(struct notifier_block *nfb,
					unsigned long action, void *hcpu)
{
	unsigned int cpu = (unsigned long)hcpu;
	struct sys_device *sys_dev;

	sys_dev = get_cpu_sysdev(cpu);
	switch (action) {
	case CPU_ONLINE:
	case CPU_ONLINE_FROZEN:
		cache_add_dev(sys_dev);
		break;
	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
		cache_remove_dev(sys_dev);
		break;
	}
	return NOTIFY_OK;
}

static struct notifier_block __cpuinitdata cacheinfo_cpu_notifier =
{
	.notifier_call = cacheinfo_cpu_callback,
};

static int __cpuinit cache_sysfs_init(void)
{
	int i;

	if (num_cache_leaves == 0)
		return 0;

	for_each_online_cpu(i) {
		int err;
		struct sys_device *sys_dev = get_cpu_sysdev(i);

		err = cache_add_dev(sys_dev);
		if (err)
			return err;
	}
	register_hotcpu_notifier(&cacheinfo_cpu_notifier);
	return 0;
}

device_initcall(cache_sysfs_init);

#endif