trace.c

Kernel code of linux kernel

	if (cnt >= sizeof(buf))
		return -EINVAL;

	if (copy_from_user(&buf, ubuf, cnt))
		return -EFAULT;

	buf[cnt] = 0;

	ret = strict_strtoul(buf, 10, &val);
	if (ret < 0)
		return ret;

	val = !!val;

	mutex_lock(&trace_types_lock);
	if (tr->ctrl ^ val) {
		if (val)
			tracer_enabled = 1;
		else
			tracer_enabled = 0;

		tr->ctrl = val;

		if (current_trace && current_trace->ctrl_update)
			current_trace->ctrl_update(tr);
	}
	mutex_unlock(&trace_types_lock);

	filp->f_pos += cnt;

	return cnt;
}

static ssize_t
tracing_set_trace_read(struct file *filp, char __user *ubuf,
		       size_t cnt, loff_t *ppos)
{
	char buf[max_tracer_type_len+2];
	int r;

	mutex_lock(&trace_types_lock);
	if (current_trace)
		r = sprintf(buf, "%s\n", current_trace->name);
	else
		r = sprintf(buf, "\n");
	mutex_unlock(&trace_types_lock);

	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
}

static ssize_t
tracing_set_trace_write(struct file *filp, const char __user *ubuf,
			size_t cnt, loff_t *ppos)
{
	struct trace_array *tr = &global_trace;
	struct tracer *t;
	char buf[max_tracer_type_len+1];
	int i;

	if (cnt > max_tracer_type_len)
		cnt = max_tracer_type_len;

	if (copy_from_user(&buf, ubuf, cnt))
		return -EFAULT;

	buf[cnt] = 0;

	/* strip ending whitespace. */
	for (i = cnt - 1; i > 0 && isspace(buf[i]); i--)
		buf[i] = 0;

	mutex_lock(&trace_types_lock);
	for (t = trace_types; t; t = t->next) {
		if (strcmp(t->name, buf) == 0)
			break;
	}
	if (!t || t == current_trace)
		goto out;

	if (current_trace && current_trace->reset)
		current_trace->reset(tr);

	current_trace = t;
	if (t->init)
		t->init(tr);

 out:
	mutex_unlock(&trace_types_lock);

	filp->f_pos += cnt;

	return cnt;
}

static ssize_t
tracing_max_lat_read(struct file *filp, char __user *ubuf,
		     size_t cnt, loff_t *ppos)
{
	unsigned long *ptr = filp->private_data;
	char buf[64];
	int r;

	r = snprintf(buf, sizeof(buf), "%ld\n",
		     *ptr == (unsigned long)-1 ? -1 : nsecs_to_usecs(*ptr));
	if (r > sizeof(buf))
		r = sizeof(buf);
	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
}

static ssize_t
tracing_max_lat_write(struct file *filp, const char __user *ubuf,
		      size_t cnt, loff_t *ppos)
{
	long *ptr = filp->private_data;
	char buf[64];
	long val;
	int ret;

	if (cnt >= sizeof(buf))
		return -EINVAL;

	if (copy_from_user(&buf, ubuf, cnt))
		return -EFAULT;

	buf[cnt] = 0;

	ret = strict_strtoul(buf, 10, &val);
	if (ret < 0)
		return ret;

	*ptr = val * 1000;

	return cnt;
}

static atomic_t tracing_reader;

static int tracing_open_pipe(struct inode *inode, struct file *filp)
{
	struct trace_iterator *iter;

	if (tracing_disabled)
		return -ENODEV;

	/* We only allow for reader of the pipe */
	if (atomic_inc_return(&tracing_reader) != 1) {
		atomic_dec(&tracing_reader);
		return -EBUSY;
	}

	/* create a buffer to store the information to pass to userspace */
	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
	if (!iter)
		return -ENOMEM;

	mutex_lock(&trace_types_lock);
	iter->tr = &global_trace;
	iter->trace = current_trace;
	filp->private_data = iter;

	if (iter->trace->pipe_open)
		iter->trace->pipe_open(iter);
	mutex_unlock(&trace_types_lock);

	return 0;
}

static int tracing_release_pipe(struct inode *inode, struct file *file)
{
	struct trace_iterator *iter = file->private_data;

	kfree(iter);
	atomic_dec(&tracing_reader);

	return 0;
}

static unsigned int
tracing_poll_pipe(struct file *filp, poll_table *poll_table)
{
	struct trace_iterator *iter = filp->private_data;

	if (trace_flags & TRACE_ITER_BLOCK) {
		/*
		 * Always select as readable when in blocking mode
		 */
		return POLLIN | POLLRDNORM;
	} else {
		if (!trace_empty(iter))
			return POLLIN | POLLRDNORM;
		poll_wait(filp, &trace_wait, poll_table);
		if (!trace_empty(iter))
			return POLLIN | POLLRDNORM;

		return 0;
	}
}

/*
 * Consumer reader.
 */
static ssize_t
tracing_read_pipe(struct file *filp, char __user *ubuf,
		  size_t cnt, loff_t *ppos)
{
	struct trace_iterator *iter = filp->private_data;
	struct trace_array_cpu *data;
	static cpumask_t mask;
	unsigned long flags;
#ifdef CONFIG_FTRACE
	int ftrace_save;
#endif
	int cpu;
	ssize_t sret;

	/* return any leftover data */
	sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
	if (sret != -EBUSY)
		return sret;
	sret = 0;

	trace_seq_reset(&iter->seq);

	mutex_lock(&trace_types_lock);
	if (iter->trace->read) {
		sret = iter->trace->read(iter, filp, ubuf, cnt, ppos);
		if (sret)
			goto out;
	}

	while (trace_empty(iter)) {

		if ((filp->f_flags & O_NONBLOCK)) {
			sret = -EAGAIN;
			goto out;
		}

		/*
		 * This is a make-shift waitqueue. The reason we don't use
		 * an actual wait queue is because:
		 *  1) we only ever have one waiter
		 *  2) the tracing, traces all functions, we don't want
		 *     the overhead of calling wake_up and friends
		 *     (and tracing them too)
		 *     Anyway, this is really very primitive wakeup.
		 */
		set_current_state(TASK_INTERRUPTIBLE);
		iter->tr->waiter = current;

		mutex_unlock(&trace_types_lock);

		/* sleep for 100 msecs, and try again. */
		schedule_timeout(HZ/10);

		mutex_lock(&trace_types_lock);

		iter->tr->waiter = NULL;

		if (signal_pending(current)) {
			sret = -EINTR;
			goto out;
		}

		if (iter->trace != current_trace)
			goto out;

		/*
		 * We block until we read something and tracing is disabled.
		 * We still block if tracing is disabled, but we have never
		 * read anything. This allows a user to cat this file, and
		 * then enable tracing. But after we have read something,
		 * we give an EOF when tracing is again disabled.
		 *
		 * iter->pos will be 0 if we haven't read anything.
		 */
		if (!tracer_enabled && iter->pos)
			break;

		continue;
	}

	/* stop when tracing is finished */
	if (trace_empty(iter))
		goto out;

	if (cnt >= PAGE_SIZE)
		cnt = PAGE_SIZE - 1;

	/* reset all but tr, trace, and overruns */
	memset(&iter->seq, 0,
	       sizeof(struct trace_iterator) -
	       offsetof(struct trace_iterator, seq));
	iter->pos = -1;

	/*
	 * We need to stop all tracing on all CPUS to read the
	 * the next buffer. This is a bit expensive, but is
	 * not done often. We fill all what we can read,
	 * and then release the locks again.
	 */

	cpus_clear(mask);
	local_irq_save(flags);
#ifdef CONFIG_FTRACE
	ftrace_save = ftrace_enabled;
	ftrace_enabled = 0;
#endif
	smp_wmb();
	for_each_tracing_cpu(cpu) {
		data = iter->tr->data[cpu];

		if (!head_page(data) || !data->trace_idx)
			continue;

		atomic_inc(&data->disabled);
		cpu_set(cpu, mask);
	}

	for_each_cpu_mask(cpu, mask) {
		data = iter->tr->data[cpu];
		__raw_spin_lock(&data->lock);

		if (data->overrun > iter->last_overrun[cpu])
			iter->overrun[cpu] +=
				data->overrun - iter->last_overrun[cpu];
		iter->last_overrun[cpu] = data->overrun;
	}

	while (find_next_entry_inc(iter) != NULL) {
		int ret;
		int len = iter->seq.len;

		ret = print_trace_line(iter);
		if (!ret) {
			/* don't print partial lines */
			iter->seq.len = len;
			break;
		}

		trace_consume(iter);

		if (iter->seq.len >= cnt)
			break;
	}

	for_each_cpu_mask(cpu, mask) {
		data = iter->tr->data[cpu];
		__raw_spin_unlock(&data->lock);
	}

	for_each_cpu_mask(cpu, mask) {
		data = iter->tr->data[cpu];
		atomic_dec(&data->disabled);
	}
#ifdef CONFIG_FTRACE
	ftrace_enabled = ftrace_save;
#endif
	local_irq_restore(flags);

	/* Now copy what we have to the user */
	sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
	if (iter->seq.readpos >= iter->seq.len)
		trace_seq_reset(&iter->seq);
	if (sret == -EBUSY)
		sret = 0;

out:
	mutex_unlock(&trace_types_lock);

	return sret;
}

static ssize_t
tracing_entries_read(struct file *filp, char __user *ubuf,
		     size_t cnt, loff_t *ppos)
{
	struct trace_array *tr = filp->private_data;
	char buf[64];
	int r;

	r = sprintf(buf, "%lu\n", tr->entries);
	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
}

static ssize_t
tracing_entries_write(struct file *filp, const char __user *ubuf,
		      size_t cnt, loff_t *ppos)
{
	unsigned long val;
	char buf[64];
	int i, ret;

	if (cnt >= sizeof(buf))
		return -EINVAL;

	if (copy_from_user(&buf, ubuf, cnt))
		return -EFAULT;

	buf[cnt] = 0;

	ret = strict_strtoul(buf, 10, &val);
	if (ret < 0)
		return ret;

	/* must have at least 1 entry */
	if (!val)
		return -EINVAL;

	mutex_lock(&trace_types_lock);

	if (current_trace != &no_tracer) {
		cnt = -EBUSY;
		pr_info("ftrace: set current_tracer to none"
			" before modifying buffer size\n");
		goto out;
	}

	if (val > global_trace.entries) {
		long pages_requested;
		unsigned long freeable_pages;

		/* make sure we have enough memory before mapping */
		pages_requested =
			(val + (ENTRIES_PER_PAGE-1)) / ENTRIES_PER_PAGE;

		/* account for each buffer (and max_tr) */
		pages_requested *= tracing_nr_buffers * 2;

		/* Check for overflow */
		if (pages_requested < 0) {
			cnt = -ENOMEM;
			goto out;
		}

		freeable_pages = determine_dirtyable_memory();

		/* we only allow to request 1/4 of useable memory */
		if (pages_requested >
		    ((freeable_pages + tracing_pages_allocated) / 4)) {
			cnt = -ENOMEM;
			goto out;
		}

		while (global_trace.entries < val) {
			if (trace_alloc_page()) {
				cnt = -ENOMEM;
				goto out;
			}
			/* double check that we don't go over the known pages */
			if (tracing_pages_allocated > pages_requested)
				break;
		}

	} else {
		/* include the number of entries in val (inc of page entries) */
		while (global_trace.entries > val + (ENTRIES_PER_PAGE - 1))
			trace_free_page();
	}

	/* check integrity */
	for_each_tracing_cpu(i)
		check_pages(global_trace.data[i]);

	filp->f_pos += cnt;

	/* If check pages failed, return ENOMEM */
	if (tracing_disabled)
		cnt = -ENOMEM;
 out:
	max_tr.entries = global_trace.entries;
	mutex_unlock(&trace_types_lock);

	return cnt;
}

static struct file_operations tracing_max_lat_fops = {
	.open		= tracing_open_generic,
	.read		= tracing_max_lat_read,
	.write		= tracing_max_lat_write,
};

static struct file_operations tracing_ctrl_fops = {
	.open		= tracing_open_generic,
	.read		= tracing_ctrl_read,
	.write		= tracing_ctrl_write,
};

static struct file_operations set_tracer_fops = {
	.open		= tracing_open_generic,
	.read		= tracing_set_trace_read,
	.write		= tracing_set_trace_write,
};

static struct file_operations tracing_pipe_fops = {
	.open		= tracing_open_pipe,
	.poll		= tracing_poll_pipe,
	.read		= tracing_read_pipe,
	.release	= tracing_release_pipe,
};

static struct file_operations tracing_entries_fops = {
	.open		= tracing_open_generic,
	.read		= tracing_entries_read,
	.write		= tracing_entries_write,
};

#ifdef CONFIG_DYNAMIC_FTRACE

static ssize_t
tracing_read_long(struct file *filp, char __user *ubuf,
		  size_t cnt, loff_t *ppos)
{
	unsigned long *p = filp->private_data;
	char buf[64];
	int r;

	r = sprintf(buf, "%ld\n", *p);

	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
}

static struct file_operations tracing_read_long_fops = {
	.open		= tracing_open_generic,
	.read		= tracing_read_long,
};
#endif

static struct dentry *d_tracer;

struct dentry *tracing_init_dentry(void)
{
	static int once;

	if (d_tracer)
		return d_tracer;

	d_tracer = debugfs_create_dir("tracing", NULL);

	if (!d_tracer && !once) {
		once = 1;
		pr_warning("Could not create debugfs directory 'tracing'\n");
		return NULL;
	}

	return d_tracer;
}

#ifdef CONFIG_FTRACE_SELFTEST
/* Let selftest have access to static functions in this file */
#include "trace_selftest.c"
#endif

static __init void tracer_init_debugfs(void)
{
	struct dentry *d_tracer;
	struct dentry *entry;

	d_tracer = tracing_init_dentry();

	entry = debugfs_create_file("tracing_enabled", 0644, d_tracer,
				    &global_trace, &tracing_ctrl_fops);
	if (!entry)
		pr_warning("Could not create debugfs 'tracing_enabled' entry\n");

	entry = debugfs_create_file("iter_ctrl", 0644, d_tracer,
				    NULL, &tracing_iter_fops);
	if (!entry)
		pr_warning("Could not create debugfs 'iter_ctrl' entry\n");

	entry = debugfs_create_fil