/*
 * 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);
}

enum tg_state_flags {
	THROTL_TG_FLAG_on_rr = 0,	/* on round-robin busy list */
};

#define THROTL_TG_FNS(name)						\
static inline void throtl_mark_tg_##name(struct throtl_grp *tg)		\
{									\
	(tg)->flags |= (1 << THROTL_TG_FLAG_##name);			\
}									\
static inline void throtl_clear_tg_##name(struct throtl_grp *tg)	\
{									\
	(tg)->flags &= ~(1 << THROTL_TG_FLAG_##name);			\
}									\
static inline int throtl_tg_##name(const struct throtl_grp *tg)		\
{									\
	return ((tg)->flags & (1 << THROTL_TG_FLAG_##name)) != 0;	\
}

THROTL_TG_FNS(on_rr);

#define throtl_log_tg(td, tg, fmt, args...)	do {			\
	char __pbuf[128];						\
									\
	blkg_path(tg_to_blkg(tg), __pbuf, sizeof(__pbuf));		\
	blk_add_trace_msg((td)->queue, "throtl %s " fmt, __pbuf, ##args); \
} while (0)

#define throtl_log(td, fmt, args...)	\
	blk_add_trace_msg((td)->queue, "throtl " fmt, ##args)

static inline unsigned int total_nr_queued(struct throtl_data *td)
{
	return td->nr_queued[0] + td->nr_queued[1];
}

/*
 * Worker for allocating per cpu stat for tgs. This is scheduled on the
 * system_wq once there are some groups on the alloc_list waiting for
 * allocation.
 */
static void tg_stats_alloc_fn(struct work_struct *work)
{
	static struct tg_stats_cpu *stats_cpu;	/* this fn is non-reentrant */
	struct delayed_work *dwork = to_delayed_work(work);
	bool empty = false;

alloc_stats:
	if (!stats_cpu) {
		stats_cpu = alloc_percpu(struct tg_stats_cpu);
		if (!stats_cpu) {
			/* allocation failed, try again after some time */
			schedule_delayed_work(dwork, msecs_to_jiffies(10));
			return;
		}
	}

	spin_lock_irq(&tg_stats_alloc_lock);

	if (!list_empty(&tg_stats_alloc_list)) {
		struct throtl_grp *tg = list_first_entry(&tg_stats_alloc_list,
							 struct throtl_grp,
							 stats_alloc_node);
		swap(tg->stats_cpu, stats_cpu);
		list_del_init(&tg->stats_alloc_node);
	}

	empty = list_empty(&tg_stats_alloc_list);
	spin_unlock_irq(&tg_stats_alloc_lock);
	if (!empty)
		goto alloc_stats;
}

static void throtl_pd_init(struct blkcg_gq *blkg)
{
	struct throtl_grp *tg = blkg_to_tg(blkg);
	unsigned long flags;

	RB_CLEAR_NODE(&tg->rb_node);
	bio_list_init(&tg->bio_lists[0]);
	bio_list_init(&tg->bio_lists[1]);
	tg->limits_changed = false;

	tg->bps[READ] = -1;
	tg->bps[WRITE] = -1;
	tg->iops[READ] = -1;
	tg->iops[WRITE] = -1;

	/*
	 * Ugh... We need to perform per-cpu allocation for tg->stats_cpu
	 * but percpu allocator can't be called from IO path.  Queue tg on
	 * tg_stats_alloc_list and allocate from work item.
	 */
	spin_lock_irqsave(&tg_stats_alloc_lock, flags);
	list_add(&tg->stats_alloc_node, &tg_stats_alloc_list);
	schedule_delayed_work(&tg_stats_alloc_work, 0);
	spin_unlock_irqrestore(&tg_stats_alloc_lock, flags);
}

static void throtl_pd_exit(struct blkcg_gq *blkg)
{
	struct throtl_grp *tg = blkg_to_tg(blkg);
	unsigned long flags;

	spin_lock_irqsave(&tg_stats_alloc_lock, flags);
	list_del_init(&tg->stats_alloc_node);
	spin_unlock_irqrestore(&tg_stats_alloc_lock, flags);

	free_percpu(tg->stats_cpu);
}

static void throtl_pd_reset_stats(struct blkcg_gq *blkg)
{
	struct throtl_grp *tg = blkg_to_tg(blkg);
	int cpu;

	if (tg->stats_cpu == NULL)
		return;

	for_each_possible_cpu(cpu) {
		struct tg_stats_cpu *sc = per_cpu_ptr(tg->stats_cpu, cpu);

		blkg_rwstat_reset(&sc->service_bytes);
		blkg_rwstat_reset(&sc->serviced);
	}
}

static struct throtl_grp *throtl_lookup_tg(struct throtl_data *td,
					   struct blkcg *blkcg)
{
	/*
	 * This is the common case when there are no blkcgs.  Avoid lookup
	 * in this case
	 */
	if (blkcg == &blkcg_root)
		return td_root_tg(td);

	return blkg_to_tg(blkg_lookup(blkcg, td->queue));
}

static struct throtl_grp *throtl_lookup_create_tg(struct throtl_data *td,
						  struct blkcg *blkcg)
{
	struct request_queue *q = td->queue;
	struct throtl_grp *tg = NULL;

	/*
	 * This is the common case when there are no blkcgs.  Avoid lookup
	 * in this case
	 */
	if (blkcg == &blkcg_root) {
		tg = td_root_tg(td);
	} else {
		struct blkcg_gq *blkg;

		blkg = blkg_lookup_create(blkcg, q);

		/* if %NULL and @q is alive, fall back to root_tg */
		if (!IS_ERR(blkg))
			tg = blkg_to_tg(blkg);
		else if (!blk_queue_dying(q))
			tg = td_root_tg(td);
	}

	return tg;
}

static struct throtl_grp *throtl_rb_first(struct throtl_rb_root *root)
{
	/* Service tree is empty */
	if (!root->count)
		return NULL;

	if (!root->left)
		root->left = rb_first(&root->rb);

	if (root->left)
		return rb_entry_tg(root->left);