/*
 * Interface for controlling IO bandwidth on a request queue
 *
 * Copyright (C) 2010 Vivek Goyal <vgoyal@redhat.com>
 */

#include <linux/module.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/bio.h>
#include <linux/blktrace_api.h>
#include "blk-cgroup.h"
#include "blk.h"

/* Max dispatch from a group in 1 round */
static int throtl_grp_quantum = 8;

/* Total max dispatch from all groups in one round */
static int throtl_quantum = 32;

/* Throttling is performed over 100ms slice and after that slice is renewed */
static unsigned long throtl_slice = HZ/10;	/* 100 ms */

static struct blkcg_policy blkcg_policy_throtl;

/* A workqueue to queue throttle related work */
static struct workqueue_struct *kthrotld_workqueue;
static void throtl_schedule_delayed_work(struct throtl_data *td,
				unsigned long delay);

struct throtl_rb_root {
	struct rb_root rb;
	struct rb_node *left;
	unsigned int count;
	unsigned long min_disptime;
};

#define THROTL_RB_ROOT	(struct throtl_rb_root) { .rb = RB_ROOT, .left = NULL, \
			.count = 0, .min_disptime = 0}

#define rb_entry_tg(node)	rb_entry((node), struct throtl_grp, rb_node)

/* Per-cpu group stats */
struct tg_stats_cpu {
	/* total bytes transferred */
	struct blkg_rwstat		service_bytes;
	/* total IOs serviced, post merge */
	struct blkg_rwstat		serviced;
};

struct throtl_grp {
	/* must be the first member */
	struct blkg_policy_data pd;

	/* active throtl group service_tree member */
	struct rb_node rb_node;

	/*
	 * Dispatch time in jiffies. This is the estimated time when group
	 * will unthrottle and is ready to dispatch more bio. It is used as
	 * key to sort active groups in service tree.
	 */
	unsigned long disptime;

	unsigned int flags;

	/* Two lists for READ and WRITE */
	struct bio_list bio_lists[2];

	/* Number of queued bios on READ and WRITE lists */
	unsigned int nr_queued[2];

	/* bytes per second rate limits */
	uint64_t bps[2];

	/* IOPS limits */
	unsigned int iops[2];

	/* Number of bytes disptached in current slice */
	uint64_t bytes_disp[2];
	/* Number of bio's dispatched in current slice */
	unsigned int io_disp[2];

	/* When did we start a new slice */
	unsigned long slice_start[2];
	unsigned long slice_end[2];

	/* Some throttle limits got updated for the group */
	int limits_changed;

	/* Per cpu stats pointer */
	struct tg_stats_cpu __percpu *stats_cpu;

	/* List of tgs waiting for per cpu stats memory to be allocated */
	struct list_head stats_alloc_node;
};

struct throtl_data
{
	/* service tree for active throtl groups */
	struct throtl_rb_root tg_service_tree;

	struct request_queue *queue;

	/* Total Number of queued bios on READ and WRITE lists */
	unsigned int nr_queued[2];

	/*
	 * number of total undestroyed groups
	 */
	unsigned int nr_undestroyed_grps;

	/* Work for dispatching throttled bios */
	struct delayed_work throtl_work;

	int limits_changed;
};

/* list and work item to allocate percpu group stats */
static DEFINE_SPINLOCK(tg_stats_alloc_lock);
static LIST_HEAD(tg_stats_alloc_list);

static void tg_stats_alloc_fn(struct work_struct *);
static DECLARE_DELAYED_WORK(tg_stats_alloc_work, tg_stats_alloc_fn);

static inline struct throtl_grp *pd_to_tg(struct blkg_policy_data *pd)
{
	return pd ? container_of(pd, struct throtl_grp, pd) : NULL;
}

static inline struct throtl_grp *blkg_to_tg(struct blkcg_gq *blkg)
{
	return pd_to_tg(blkg_to_pd(blkg, &blkcg_policy_throtl));
}

static inline struct blkcg_gq *tg_to_blkg(struct throtl_grp *tg)
{
	return pd_to_blkg(&tg->pd);
}

static inline struct throtl_grp *td_root_tg(struct throtl_data *td)
{
	return blkg_to_tg(td->queue->root_blkg);
}