/**
 * @file cpu_buffer.c
 *
 * @remark Copyright 2002-2009 OProfile authors
 * @remark Read the file COPYING
 *
 * @author John Levon <levon@movementarian.org>
 * @author Barry Kasindorf <barry.kasindorf@amd.com>
 * @author Robert Richter <robert.richter@amd.com>
 *
 * Each CPU has a local buffer that stores PC value/event
 * pairs. We also log context switches when we notice them.
 * Eventually each CPU's buffer is processed into the global
 * event buffer by sync_buffer().
 *
 * We use a local buffer for two reasons: an NMI or similar
 * interrupt cannot synchronise, and high sampling rates
 * would lead to catastrophic global synchronisation if
 * a global buffer was used.
 */

#include <linux/sched.h>
#include <linux/oprofile.h>
#include <linux/errno.h>

#include "event_buffer.h"
#include "cpu_buffer.h"
#include "buffer_sync.h"
#include "oprof.h"

#define OP_BUFFER_FLAGS	0

static struct ring_buffer *op_ring_buffer;
DEFINE_PER_CPU(struct oprofile_cpu_buffer, op_cpu_buffer);

static void wq_sync_buffer(struct work_struct *work);

#define DEFAULT_TIMER_EXPIRE (HZ / 10)
static int work_enabled;

unsigned long oprofile_get_cpu_buffer_size(void)
{
	return oprofile_cpu_buffer_size;
}

void oprofile_cpu_buffer_inc_smpl_lost(void)
{
	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);

	cpu_buf->sample_lost_overflow++;
}

void free_cpu_buffers(void)
{
	if (op_ring_buffer)
		ring_buffer_free(op_ring_buffer);
	op_ring_buffer = NULL;
}

#define RB_EVENT_HDR_SIZE 4

int alloc_cpu_buffers(void)
{
	int i;

	unsigned long buffer_size = oprofile_cpu_buffer_size;
	unsigned long byte_size = buffer_size * (sizeof(struct op_sample) +
						 RB_EVENT_HDR_SIZE);

	op_ring_buffer = ring_buffer_alloc(byte_size, OP_BUFFER_FLAGS);
	if (!op_ring_buffer)
		goto fail;

	for_each_possible_cpu(i) {
		struct oprofile_cpu_buffer *b = &per_cpu(op_cpu_buffer, i);

		b->last_task = NULL;
		b->last_is_kernel = -1;
		b->tracing = 0;
		b->buffer_size = buffer_size;
		b->sample_received = 0;
		b->sample_lost_overflow = 0;
		b->backtrace_aborted = 0;
		b->sample_invalid_eip = 0;
		b->cpu = i;
		INIT_DELAYED_WORK(&b->work, wq_sync_buffer);
	}
	return 0;

fail:
	free_cpu_buffers();
	return -ENOMEM;
}

void start_cpu_work(void)
{
	int i;

	work_enabled = 1;

	for_each_online_cpu(i) {
		struct oprofile_cpu_buffer *b = &per_cpu(op_cpu_buffer, i);

		/*
		 * Spread the work by 1 jiffy per cpu so they dont all
		 * fire at once.
		 */
		schedule_delayed_work_on(i, &b->work, DEFAULT_TIMER_EXPIRE + i);
	}
}

void end_cpu_work(void)
{
	work_enabled = 0;
}

void flush_cpu_work(void)
{
	int i;

	for_each_online_cpu(i) {
		struct oprofile_cpu_buffer *b = &per_cpu(op_cpu_buffer, i);

		/* these works are per-cpu, no need for flush_sync */
		flush_delayed_work(&b->work);
	}
}

/*
 * This function prepares the cpu buffer to write a sample.
 *
 * Struct op_entry is used during operations on the ring buffer while
 * struct op_sample contains the data that is stored in the ring
 * buffer. Struct entry can be uninitialized. The function reserves a
 * data array that is specified by size. Use
 * op_cpu_buffer_write_commit() after preparing the sample. In case of
 * errors a null pointer is returned, otherwise the pointer to the
 * sample.
 *
 */
struct op_sample
*op_cpu_buffer_write_reserve(struct op_entry *entry, unsigned long size)
{
	entry->event = ring_buffer_lock_reserve
		(op_ring_buffer, sizeof(struct op_sample) +
		 size * sizeof(entry->sample->data[0]));
	if (!entry->event)
		return NULL;
	entry->sample = ring_buffer_event_data(entry->event);
	entry->size = size;
	entry->data = entry->sample->data;

	return entry->sample;
}

int op_cpu_buffer_write_commit(struct op_entry *entry)
{
	return ring_buffer_unlock_commit(op_ring_buffer, entry->event);
}

struct op_sample *op_cpu_buffer_read_entry(struct op_entry *entry, int cpu)
{
	struct ring_buffer_event *e;
	e = ring_buffer_consume(op_ring_buffer, cpu, NULL, NULL);
	if (!e)
		return NULL;

	entry->event = e;
	entry->sample = ring_buffer_event_data(e);
	entry->size = (ring_buffer_event_length(e) - sizeof(struct op_sample))