kprobes.c

Kernel code of linux kernel

		/* XXX(hch): why is there no hlist_move_head? */
		INIT_HLIST_NODE(&ri->hlist);
		kretprobe_table_lock(hash, &flags);
		hlist_add_head(&ri->hlist, &kretprobe_inst_table[hash]);
		kretprobe_table_unlock(hash, &flags);
	} else {
		rp->nmissed++;
		spin_unlock_irqrestore(&rp->lock, flags);
	}
	return 0;
}

static int __kprobes __register_kretprobe(struct kretprobe *rp,
					  unsigned long called_from)
{
	int ret = 0;
	struct kretprobe_instance *inst;
	int i;
	void *addr;

	if (kretprobe_blacklist_size) {
		addr = kprobe_addr(&rp->kp);
		if (!addr)
			return -EINVAL;

		for (i = 0; kretprobe_blacklist[i].name != NULL; i++) {
			if (kretprobe_blacklist[i].addr == addr)
				return -EINVAL;
		}
	}

	rp->kp.pre_handler = pre_handler_kretprobe;
	rp->kp.post_handler = NULL;
	rp->kp.fault_handler = NULL;
	rp->kp.break_handler = NULL;

	/* Pre-allocate memory for max kretprobe instances */
	if (rp->maxactive <= 0) {
#ifdef CONFIG_PREEMPT
		rp->maxactive = max(10, 2 * NR_CPUS);
#else
		rp->maxactive = NR_CPUS;
#endif
	}
	spin_lock_init(&rp->lock);
	INIT_HLIST_HEAD(&rp->free_instances);
	for (i = 0; i < rp->maxactive; i++) {
		inst = kmalloc(sizeof(struct kretprobe_instance) +
			       rp->data_size, GFP_KERNEL);
		if (inst == NULL) {
			free_rp_inst(rp);
			return -ENOMEM;
		}
		INIT_HLIST_NODE(&inst->hlist);
		hlist_add_head(&inst->hlist, &rp->free_instances);
	}

	rp->nmissed = 0;
	/* Establish function entry probe point */
	ret = __register_kprobe(&rp->kp, called_from);
	if (ret != 0)
		free_rp_inst(rp);
	return ret;
}

static int __register_kretprobes(struct kretprobe **rps, int num,
	unsigned long called_from)
{
	int ret = 0, i;

	if (num <= 0)
		return -EINVAL;
	for (i = 0; i < num; i++) {
		ret = __register_kretprobe(rps[i], called_from);
		if (ret < 0) {
			if (i > 0)
				unregister_kretprobes(rps, i);
			break;
		}
	}
	return ret;
}

int __kprobes register_kretprobe(struct kretprobe *rp)
{
	return __register_kretprobes(&rp, 1,
			(unsigned long)__builtin_return_address(0));
}

void __kprobes unregister_kretprobe(struct kretprobe *rp)
{
	unregister_kretprobes(&rp, 1);
}

int __kprobes register_kretprobes(struct kretprobe **rps, int num)
{
	return __register_kretprobes(rps, num,
			(unsigned long)__builtin_return_address(0));
}

void __kprobes unregister_kretprobes(struct kretprobe **rps, int num)
{
	int i;

	if (num <= 0)
		return;
	mutex_lock(&kprobe_mutex);
	for (i = 0; i < num; i++)
		if (__unregister_kprobe_top(&rps[i]->kp) < 0)
			rps[i]->kp.addr = NULL;
	mutex_unlock(&kprobe_mutex);

	synchronize_sched();
	for (i = 0; i < num; i++) {
		if (rps[i]->kp.addr) {
			__unregister_kprobe_bottom(&rps[i]->kp);
			cleanup_rp_inst(rps[i]);
		}
	}
}

#else /* CONFIG_KRETPROBES */
int __kprobes register_kretprobe(struct kretprobe *rp)
{
	return -ENOSYS;
}

int __kprobes register_kretprobes(struct kretprobe **rps, int num)
{
	return -ENOSYS;
}
void __kprobes unregister_kretprobe(struct kretprobe *rp)
{
}

void __kprobes unregister_kretprobes(struct kretprobe **rps, int num)
{
}

static int __kprobes pre_handler_kretprobe(struct kprobe *p,
					   struct pt_regs *regs)
{
	return 0;
}

#endif /* CONFIG_KRETPROBES */

static int __init init_kprobes(void)
{
	int i, err = 0;
	unsigned long offset = 0, size = 0;
	char *modname, namebuf[128];
	const char *symbol_name;
	void *addr;
	struct kprobe_blackpoint *kb;

	/* FIXME allocate the probe table, currently defined statically */
	/* initialize all list heads */
	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
		INIT_HLIST_HEAD(&kprobe_table[i]);
		INIT_HLIST_HEAD(&kretprobe_inst_table[i]);
		spin_lock_init(&(kretprobe_table_locks[i].lock));
	}

	/*
	 * Lookup and populate the kprobe_blacklist.
	 *
	 * Unlike the kretprobe blacklist, we'll need to determine
	 * the range of addresses that belong to the said functions,
	 * since a kprobe need not necessarily be at the beginning
	 * of a function.
	 */
	for (kb = kprobe_blacklist; kb->name != NULL; kb++) {
		kprobe_lookup_name(kb->name, addr);
		if (!addr)
			continue;

		kb->start_addr = (unsigned long)addr;
		symbol_name = kallsyms_lookup(kb->start_addr,
				&size, &offset, &modname, namebuf);
		if (!symbol_name)
			kb->range = 0;
		else
			kb->range = size;
	}

	if (kretprobe_blacklist_size) {
		/* lookup the function address from its name */
		for (i = 0; kretprobe_blacklist[i].name != NULL; i++) {
			kprobe_lookup_name(kretprobe_blacklist[i].name,
					   kretprobe_blacklist[i].addr);
			if (!kretprobe_blacklist[i].addr)
				printk("kretprobe: lookup failed: %s\n",
				       kretprobe_blacklist[i].name);
		}
	}

	/* By default, kprobes are enabled */
	kprobe_enabled = true;

	err = arch_init_kprobes();
	if (!err)
		err = register_die_notifier(&kprobe_exceptions_nb);
	kprobes_initialized = (err == 0);

	if (!err)
		init_test_probes();
	return err;
}

#ifdef CONFIG_DEBUG_FS
static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p,
		const char *sym, int offset,char *modname)
{
	char *kprobe_type;

	if (p->pre_handler == pre_handler_kretprobe)
		kprobe_type = "r";
	else if (p->pre_handler == setjmp_pre_handler)
		kprobe_type = "j";
	else
		kprobe_type = "k";
	if (sym)
		seq_printf(pi, "%p  %s  %s+0x%x  %s\n", p->addr, kprobe_type,
			sym, offset, (modname ? modname : " "));
	else
		seq_printf(pi, "%p  %s  %p\n", p->addr, kprobe_type, p->addr);
}

static void __kprobes *kprobe_seq_start(struct seq_file *f, loff_t *pos)
{
	return (*pos < KPROBE_TABLE_SIZE) ? pos : NULL;
}

static void __kprobes *kprobe_seq_next(struct seq_file *f, void *v, loff_t *pos)
{
	(*pos)++;
	if (*pos >= KPROBE_TABLE_SIZE)
		return NULL;
	return pos;
}

static void __kprobes kprobe_seq_stop(struct seq_file *f, void *v)
{
	/* Nothing to do */
}

static int __kprobes show_kprobe_addr(struct seq_file *pi, void *v)
{
	struct hlist_head *head;
	struct hlist_node *node;
	struct kprobe *p, *kp;
	const char *sym = NULL;
	unsigned int i = *(loff_t *) v;
	unsigned long offset = 0;
	char *modname, namebuf[128];

	head = &kprobe_table[i];
	preempt_disable();
	hlist_for_each_entry_rcu(p, node, head, hlist) {
		sym = kallsyms_lookup((unsigned long)p->addr, NULL,
					&offset, &modname, namebuf);
		if (p->pre_handler == aggr_pre_handler) {
			list_for_each_entry_rcu(kp, &p->list, list)
				report_probe(pi, kp, sym, offset, modname);
		} else
			report_probe(pi, p, sym, offset, modname);
	}
	preempt_enable();
	return 0;
}

static struct seq_operations kprobes_seq_ops = {
	.start = kprobe_seq_start,
	.next  = kprobe_seq_next,
	.stop  = kprobe_seq_stop,
	.show  = show_kprobe_addr
};

static int __kprobes kprobes_open(struct inode *inode, struct file *filp)
{
	return seq_open(filp, &kprobes_seq_ops);
}

static struct file_operations debugfs_kprobes_operations = {
	.open           = kprobes_open,
	.read           = seq_read,
	.llseek         = seq_lseek,
	.release        = seq_release,
};

static void __kprobes enable_all_kprobes(void)
{
	struct hlist_head *head;
	struct hlist_node *node;
	struct kprobe *p;
	unsigned int i;

	mutex_lock(&kprobe_mutex);

	/* If kprobes are already enabled, just return */
	if (kprobe_enabled)
		goto already_enabled;

	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
		head = &kprobe_table[i];
		hlist_for_each_entry_rcu(p, node, head, hlist)
			arch_arm_kprobe(p);
	}

	kprobe_enabled = true;
	printk(KERN_INFO "Kprobes globally enabled\n");

already_enabled:
	mutex_unlock(&kprobe_mutex);
	return;
}

static void __kprobes disable_all_kprobes(void)
{
	struct hlist_head *head;
	struct hlist_node *node;
	struct kprobe *p;
	unsigned int i;

	mutex_lock(&kprobe_mutex);

	/* If kprobes are already disabled, just return */
	if (!kprobe_enabled)
		goto already_disabled;

	kprobe_enabled = false;
	printk(KERN_INFO "Kprobes globally disabled\n");
	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
		head = &kprobe_table[i];
		hlist_for_each_entry_rcu(p, node, head, hlist) {
			if (!arch_trampoline_kprobe(p))
				arch_disarm_kprobe(p);
		}
	}

	mutex_unlock(&kprobe_mutex);
	/* Allow all currently running kprobes to complete */
	synchronize_sched();
	return;

already_disabled:
	mutex_unlock(&kprobe_mutex);
	return;
}

/*
 * XXX: The debugfs bool file interface doesn't allow for callbacks
 * when the bool state is switched. We can reuse that facility when
 * available
 */
static ssize_t read_enabled_file_bool(struct file *file,
	       char __user *user_buf, size_t count, loff_t *ppos)
{
	char buf[3];

	if (kprobe_enabled)
		buf[0] = '1';
	else
		buf[0] = '0';
	buf[1] = '\n';
	buf[2] = 0x00;
	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
}

static ssize_t write_enabled_file_bool(struct file *file,
	       const char __user *user_buf, size_t count, loff_t *ppos)
{
	char buf[32];
	int buf_size;

	buf_size = min(count, (sizeof(buf)-1));
	if (copy_from_user(buf, user_buf, buf_size))
		return -EFAULT;

	switch (buf[0]) {
	case 'y':
	case 'Y':
	case '1':
		enable_all_kprobes();
		break;
	case 'n':
	case 'N':
	case '0':
		disable_all_kprobes();
		break;
	}

	return count;
}

static struct file_operations fops_kp = {
	.read =         read_enabled_file_bool,
	.write =        write_enabled_file_bool,
};

static int __kprobes debugfs_kprobe_init(void)
{
	struct dentry *dir, *file;
	unsigned int value = 1;

	dir = debugfs_create_dir("kprobes", NULL);
	if (!dir)
		return -ENOMEM;

	file = debugfs_create_file("list", 0444, dir, NULL,
				&debugfs_kprobes_operations);
	if (!file) {
		debugfs_remove(dir);
		return -ENOMEM;
	}

	file = debugfs_create_file("enabled", 0600, dir,
					&value, &fops_kp);
	if (!file) {
		debugfs_remove(dir);
		return -ENOMEM;
	}

	return 0;
}

late_initcall(debugfs_kprobe_init);
#endif /* CONFIG_DEBUG_FS */

module_init(init_kprobes);

EXPORT_SYMBOL_GPL(register_kprobe);
EXPORT_SYMBOL_GPL(unregister_kprobe);
EXPORT_SYMBOL_GPL(register_kprobes);
EXPORT_SYMBOL_GPL(unregister_kprobes);
EXPORT_SYMBOL_GPL(register_jprobe);
EXPORT_SYMBOL_GPL(unregister_jprobe);
EXPORT_SYMBOL_GPL(register_jprobes);
EXPORT_SYMBOL_GPL(unregister_jprobes);
EXPORT_SYMBOL_GPL(jprobe_return);
EXPORT_SYMBOL_GPL(register_kretprobe);
EXPORT_SYMBOL_GPL(unregister_kretprobe);
EXPORT_SYMBOL_GPL(register_kretprobes);
EXPORT_SYMBOL_GPL(unregister_kretprobes);