/*
 * Block rq-qos base io controller
 *
 * This works similar to wbt with a few exceptions
 *
 * - It's bio based, so the latency covers the whole block layer in addition to
 *   the actual io.
 * - We will throttle all IO that comes in here if we need to.
 * - We use the mean latency over the 100ms window.  This is because writes can
 *   be particularly fast, which could give us a false sense of the impact of
 *   other workloads on our protected workload.
 * - By default there's no throttling, we set the queue_depth to INT_MAX so that
 *   we can have as many outstanding bio's as we're allowed to.  Only at
 *   throttle time do we pay attention to the actual queue depth.
 *
 * The hierarchy works like the cpu controller does, we track the latency at
 * every configured node, and each configured node has it's own independent
 * queue depth.  This means that we only care about our latency targets at the
 * peer level.  Some group at the bottom of the hierarchy isn't going to affect
 * a group at the end of some other path if we're only configred at leaf level.
 *
 * Consider the following
 *
 *                   root blkg
 *             /                     \
 *        fast (target=5ms)     slow (target=10ms)
 *         /     \                  /        \
 *       a        b          normal(15ms)   unloved
 *
 * "a" and "b" have no target, but their combined io under "fast" cannot exceed
 * an average latency of 5ms.  If it does then we will throttle the "slow"
 * group.  In the case of "normal", if it exceeds its 15ms target, we will
 * throttle "unloved", but nobody else.
 *
 * In this example "fast", "slow", and "normal" will be the only groups actually
 * accounting their io latencies.  We have to walk up the heirarchy to the root
 * on every submit and complete so we can do the appropriate stat recording and
 * adjust the queue depth of ourselves if needed.
 *
 * There are 2 ways we throttle IO.
 *
 * 1) Queue depth throttling.  As we throttle down we will adjust the maximum
 * number of IO's we're allowed to have in flight.  This starts at (u64)-1 down
 * to 1.  If the group is only ever submitting IO for itself then this is the
 * only way we throttle.
 *
 * 2) Induced delay throttling.  This is for the case that a group is generating
 * IO that has to be issued by the root cg to avoid priority inversion. So think
 * REQ_META or REQ_SWAP.  If we are already at qd == 1 and we're getting a lot
 * of work done for us on behalf of the root cg and are being asked to scale
 * down more then we induce a latency at userspace return.  We accumulate the
 * total amount of time we need to be punished by doing
 *
 * total_time += min_lat_nsec - actual_io_completion
 *
 * and then at throttle time will do
 *
 * throttle_time = min(total_time, NSEC_PER_SEC)
 *
 * This induced delay will throttle back the activity that is generating the
 * root cg issued io's, wethere that's some metadata intensive operation or the
 * group is using so much memory that it is pushing us into swap.
 *
 * Copyright (C) 2018 Josef Bacik
 */
#include <linux/kernel.h>
#include <linux/blk_types.h>
#include <linux/backing-dev.h>
#include <linux/module.h>
#include <linux/timer.h>
#include <linux/memcontrol.h>
#include <linux/sched/signal.h>
#include <trace/events/block.h>
#include "blk-rq-qos.h"
#include "blk-stat.h"

#define DEFAULT_SCALE_COOKIE 1000000U

static struct blkcg_policy blkcg_policy_iolatency;
struct iolatency_grp;

struct blk_iolatency {
	struct rq_qos rqos;
	struct timer_list timer;
	atomic_t enabled;
};

static inline struct blk_iolatency *BLKIOLATENCY(struct rq_qos *rqos)
{
	return container_of(rqos, struct blk_iolatency, rqos);
}

static inline bool blk_iolatency_enabled(struct blk_iolatency *blkiolat)
{
	return atomic_read(&blkiolat->enabled) > 0;
}

struct child_latency_info {
	spinlock_t lock;

	/* Last time we adjusted the scale of everybody. */
	u64 last_scale_event;

	/* The latency that we missed. */
	u64 scale_lat;

	/* Total io's from all of our children for the last summation. */
	u64 nr_samples;

	/* The guy who actually changed the latency numbers. */
	struct iolatency_grp *scale_grp;

	/* Cookie to tell if we need to scale up or down. */
	atomic_t scale_cookie;
};

struct iolatency_grp {
	struct blkg_policy_data pd;
	struct blk_rq_stat __percpu *stats;
	struct blk_iolatency *blkiolat;
	struct rq_depth rq_depth;
	struct rq_wait rq_wait;
	atomic64_t window_start;
	atomic_t scale_cookie;
	u64 min_lat_nsec;
	u64 cur_win_nsec;

	/* total running average of our io latency. */
	u64 total_lat_avg;
	u64 total_lat_nr;

	/* Our current number of IO's for the last summation. */
	u64 nr_samples;

	struct child_latency_info child_lat;
};

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

static inline struct iolatency_grp *blkg_to_lat(struct blkcg_gq *blkg)
{
	return pd_to_lat(blkg_to_pd(blkg, &blkcg_policy_iolatency));
}

static inline struct blkcg_gq *lat_to_blkg(struct iolatency_grp *iolat)
{
	return pd_to_blkg(&iolat->pd);
}

static inline bool iolatency_may_queue(struct iolatency_grp *iolat,
				       wait_queue_entry_t *wait,
				       bool first_block)
{
	struct rq_wait *rqw = &iolat->rq_wait;

	if (first_block && waitqueue_active(&rqw->wait) &&
	    rqw->wait.head.next != &wait->entry)
		return false;
	return rq_wait_inc_below(rqw, iolat->rq_depth.max_depth);
}

static void __blkcg_iolatency_throttle(struct rq_qos *rqos,
				       struct iolatency_grp *iolat,
				       spinlock_t *lock, bool issue_as_root,
				       bool use_memdelay)
	__releases(lock)
	__acquires(lock)
{
	struct rq_wait *rqw = &iolat->rq_wait;
	unsigned use_delay = atomic_read(&lat_to_blkg(iolat)->use_delay);
	DEFINE_WAIT(wait);
	bool first_block = true;

	if (use_delay)
		blkcg_schedule_throttle(rqos->q, use_memdelay);

	/*
	 * To avoid priority inversions we want to just take a slot if we are
	 * issuing as root.  If we're being killed off there's no point in
	 * delaying things, we may have been killed by OOM so throttling may
	 * make recovery take even longer, so just let the IO's through so the
	 * task can go away.
	 */
	if (issue_as_root || fatal_signal_pending(current)) {
		atomic_inc(&rqw->inflight);
		return;
	}

	if (iolatency_may_queue(iolat, &wait, first_block))
		return;

	do {
		prepare_to_wait_exclusive(&rqw->wait, &wait,
					  TASK_UNINTERRUPTIBLE);

		if (iolatency_may_queue(iolat, &wait, first_block))
			break;
		first_block = false;

		if (lock) {
			spin_unlock_irq(lock);
			io_schedule();
			spin_lock_irq(lock);
		} else {
			io_schedule();
		}
	} while (1);

	finish_wait(&rqw->wait, &wait);
}

#define SCALE_DOWN_FACTOR 2
#define SCALE_UP_FACTOR 4

static inline unsigned long scale_amount(unsigned long qd, bool up)
{
	return max(up ? qd >> SCALE_UP_FACTOR : qd >> SCALE_DOWN_FACTOR, 1UL);
}

/*
 * We scale the qd down faster than we scale up, so we need to use this helper
 * to adjust the scale_cookie accordingly so we don't prematurely get
 * scale_cookie at DEFAULT_SCALE_COOKIE and unthrottle too much.
 *
 * Each group has their own local copy of the last scale cookie they saw, so if
 * the global scale cookie goes up or down they know which way they need to go
 * based on their last knowledge of it.
 */
static void scale_cookie_change(struct blk_iolatency *blkiolat,
				struct child_latency_info *lat_info,
				bool up)
{
	unsigned long qd = blk_queue_depth(blkiolat->rqos.q);
	unsigned long scale = scale_amount(qd, up);
	unsigned long old = atomic_read(&lat_info->scale_cookie);
	unsigned long max_scale = qd << 1;
	unsigned long diff = 0;

	if (old < DEFAULT_SCALE_COOKIE)
		diff = DEFAULT_SCALE_COOKIE - old;

	if (up) {
		if (scale + old > DEFAULT_SCALE_COOKIE)
			atomic_set(&lat_info->scale_cookie,
				   DEFAULT_SCALE_COOKIE);
		else if (diff > qd)
			atomic_inc(&lat_info->scale_cookie);
		else
			atomic_add(scale, &lat_info->scale_cookie);
	} else {
		/*
		 * We don't want to dig a hole so deep that it takes us hours to
		 * dig out of it.  Just enough that we don't throttle/unthrottle
		 * with jagged workloads but can still unthrottle once pressure
		 * has sufficiently dissipated.
		 */
		if (diff > qd) {
			if (diff < max_scale)
				atomic_dec(&lat_info->scale_cookie);
		} else {
			atomic_sub(scale, &lat_info->scale_cookie);
		}
	}
}

/*
 * Change the queue depth of the iolatency_grp.  We add/subtract 1/16th of the
 * queue depth at a time so we don't get wild swings and hopefully dial in to
 * fairer distribution of the overall queue depth.
 */
static void scale_change(struct iolatency_grp *iolat, bool up)
{
	unsigned long qd = blk_queue_depth(iolat->blkiolat->rqos.q);
	unsigned long scale = scale_amount(qd, up);
	unsigned long old = iolat->rq_depth.max_depth;
	bool changed = false;

	if (old > qd)
		old = qd;

	if (up) {
		if (old == 1 && blkcg_unuse_delay(lat_to_blkg(iolat)))
			return;

		if (old < qd) {
			changed = true;
			old += scale;
			old = min(old, qd);
			iolat->rq_depth.max_depth = old;
			wake_up_all(&iolat->rq_wait.wait);
		}
	} else if (old > 1) {
		old >>= 1;
		changed = true;
		iolat->rq_depth.max_depth = max(old, 1UL);
	}
}

/* Check our parent and see if the scale cookie has changed. */
static void check_scale_change(struct iolatency_grp *iolat)
{
	struct iolatency_grp *parent;
	struct child_latency_info *lat_info;
	unsigned int cur_cookie;
	unsigned int our_cookie = atomic_read(&iolat->scale_cookie);
	u64 scale_lat;
	unsigned int old;
	int direction = 0;

	if (lat_to_blkg(iolat)->parent == NULL)
		return;

	parent = blkg_to_lat(lat_to_blkg(iolat)->parent);
	if (!parent)
		return;

	lat_info = &parent->child_lat;
	cur_cookie = atomic_read(&lat_info->scale_cookie);
	scale_lat = READ_ONCE(lat_info->scale_lat);

	if (cur_cookie < our_cookie)
		direction = -1;
	else if (cur_cookie > our_cookie)
		direction = 1;
	else
		return;

	old = atomic_cmpxchg(&iolat->scale_cookie, our_cookie, cur_cookie);

	/* Somebody beat us to the punch, just bail. */
	if (old != our_cookie)
		return;

	if (direction < 0 && iolat->min_lat_nsec) {
		u64 samples_thresh;

		if (!scale_lat || iolat->min_lat_nsec <= scale_lat)
			return;

		/*
		 * Sometimes high priority groups are their own worst enemy, so
		 * instead of taking it out on some poor other group that did 5%
		 * or less of the IO's for the last summation just skip this
		 * scale down event.
		 */
		samples_thresh = lat_info->nr_samples * 5;
		samples_thresh = div64_u64(samples_thresh, 100);
		if (iolat->nr_samples <= samples_thresh)
			return;
	}

	/* We're as low as we can go. */
	if (iolat->rq_depth.max_depth == 1 && direction < 0) {
		blkcg_use_delay(lat_to_blkg(iolat));
		return;
	}

	/* We're back to the default cookie, unthrottle all the things. */
	if (cur_cookie == DEFAULT_SCALE_COOKIE) {
		blkcg_clear_delay(lat_to_blkg(iolat));
		iolat->rq_depth.max_depth = INT_MAX;
		wake_up_all(&iolat->rq_wait.wait);
		return;
	}

	scale_change(iolat, direction > 0);
}

static void blkcg_iolatency_throttle(struct rq_qos *rqos, struct bio *bio,
				     spinlock_t *lock)
{
	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
	struct blkcg *blkcg;
	struct blkcg_gq *blkg;
	struct request_queue *q = rqos->q;
	bool issue_as_root = bio_issue_as_root_blkg(bio);

	if (!blk_iolatency_enabled(blkiolat))
		return;

	rcu_read_lock();
	blkcg = bio_blkcg(bio);
	bio_associate_blkcg(bio, &blkcg->css);
	blkg = blkg_lookup(blkcg, q);
	if (unlikely(!blkg)) {
		if (!lock)
			spin_lock_irq(q->queue_lock);
		blkg = blkg_lookup_create(blkcg, q);
		if (IS_ERR(blkg))
			blkg = NULL;
		if (!lock)
			spin_unlock_irq(q->queue_lock);
	}
	if (!blkg)
		goto out;

	bio_issue_init(&bio->bi_issue, bio_sectors(bio));
	bio_associate_blkg(bio, blkg);
out:
	rcu_read_unlock();
	while (blkg && blkg->parent) {
		struct iolatency_grp *iolat = blkg_to_lat(blkg);
		if (!iolat) {
			blkg = blkg->parent;
			continue;
		}

		check_scale_change(iolat);
		__blkcg_iolatency_throttle(rqos, iolat, lock, issue_as_root,
				     (bio->bi_opf & REQ_SWAP) == REQ_SWAP);
		blkg = blkg->parent;
	}
	if (!timer_pending(&blkiolat->timer))
		mod_timer(&blkiolat->timer, jiffies + HZ);
}

static void iolatency_record_time(struct iolatency_grp *iolat,
				  struct bio_issue *issue, u64 now,
				  bool issue_as_root)
{
	struct blk_rq_stat *rq_stat;
	u64 start = bio_issue_time(issue);
	u64 req_time;

	if (now <= start)
		return;

	req_time = now - start;

	/*
	 * We don't want to count issue_as_root bio's in the cgroups latency
	 * statistics as it could skew the numbers downwards.
	 */
	if (unlikely(issue_as_root && iolat->rq_depth.max_depth != (u64)-1)) {
		u64 sub = iolat->min_lat_nsec;
		if (req_time < sub)
			blkcg_add_delay(lat_to_blkg(iolat), now, sub - req_time);
		return;
	}

	rq_stat = get_cpu_ptr(iolat->stats);
	blk_rq_stat_add(rq_stat, req_time);
	put_cpu_ptr(rq_stat);
}

#define BLKIOLATENCY_MIN_ADJUST_TIME (500 * NSEC_PER_MSEC)
#define BLKIOLATENCY_MIN_GOOD_SAMPLES 5

static void iolatency_check_latencies(struct iolatency_grp *iolat, u64 now)
{
	struct blkcg_gq *blkg = lat_to_blkg(iolat);
	struct iolatency_grp *parent;
	struct child_latency_info *lat_info;
	struct blk_rq_stat stat;
	unsigned long flags;
	int cpu;

	blk_rq_stat_init(&stat);
	preempt_disable();
	for_each_online_cpu(cpu) {
		struct blk_rq_stat *s;
		s = per_cpu_ptr(iolat->stats, cpu);
		blk_rq_stat_sum(&stat, s);
		blk_rq_stat_init(s);
	}
	preempt_enable();

	/*
	 * Our average exceeded our window, scale up our window so we are more
	 * accurate, but not more than the global timer.
	 */
	if (stat.mean > iolat->cur_win_nsec) {
		iolat->cur_win_nsec <<= 1;
		iolat->cur_win_nsec =
			max_t(u64, iolat->cur_win_nsec, NSEC_PER_SEC);
	}

	parent = blkg_to_lat(blkg->parent);
	if (!parent)
		return;

	lat_info = &parent->child_lat;

	iolat->total_lat_avg =
		div64_u64((iolat->total_lat_avg * iolat->total_lat_nr) +
			  stat.mean, iolat->total_lat_nr + 1);

	iolat->total_lat_nr++;

	/* Everything is ok and we don't need to adjust the scale. */
	if (stat.mean <= iolat->min_lat_nsec &&
	    atomic_read(&lat_info->scale_cookie) == DEFAULT_SCALE_COOKIE)
		return;

	/* Somebody beat us to the punch, just bail. */
	spin_lock_irqsave(&lat_info->lock, flags);
	lat_info->nr_samples -= iolat->nr_samples;
	lat_info->nr_samples += stat.nr_samples;
	iolat->nr_samples = stat.nr_samples;

	if ((lat_info->last_scale_event >= now ||
	    now - lat_info->last_scale_event < BLKIOLATENCY_MIN_ADJUST_TIME) &&
	    lat_info->scale_lat <= iolat->min_lat_nsec)
		goto out;

	if (stat.mean <= iolat->min_lat_nsec &&
	    stat.nr_samples >= BLKIOLATENCY_MIN_GOOD_SAMPLES) {
		if (lat_info->scale_grp == iolat) {
			lat_info->last_scale_event = now;
			scale_cookie_change(iolat->blkiolat, lat_info, true);
		}
	} else if (stat.mean > iolat->min_lat_nsec) {
		lat_info->last_scale_event = now;
		if (!lat_info->scale_grp ||
		    lat_info->scale_lat > iolat->min_lat_nsec) {
			WRITE_ONCE(lat_info->scale_lat, iolat->min_lat_nsec);
			lat_info->scale_grp = iolat;
		}
		scale_cookie_change(iolat->blkiolat, lat_info, false);
	}
out:
	spin_unlock_irqrestore(&lat_info->lock, flags);
}

static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio)
{
	struct blkcg_gq *blkg;
	struct rq_wait *rqw;
	struct iolatency_grp *iolat;
	u64 window_start;
	u64 now = ktime_to_ns(ktime_get());
	bool issue_as_root = bio_issue_as_root_blkg(bio);
	bool enabled = false;

	blkg = bio->bi_blkg;
	if (!blkg)
		return;

	iolat = blkg_to_lat(bio->bi_blkg);
	if (!iolat)
		return;

	enabled = blk_iolatency_enabled(iolat->blkiolat);
	while (blkg && blkg->parent) {
		iolat = blkg_to_lat(blkg);
		if (!iolat) {
			blkg = blkg->parent;
			continue;
		}
		rqw = &iolat->rq_wait;

		atomic_dec(&rqw->inflight);
		if (!enabled || iolat->min_lat_nsec == 0)
			goto next;
		iolatency_record_time(iolat, &bio->bi_issue, now,
				      issue_as_root);
		window_start = atomic64_read(&iolat->window_start);
		if (now > window_start &&
		    (now - window_start) >= iolat->cur_win_nsec) {
			if (atomic64_cmpxchg(&iolat->window_start,
					window_start, now) == window_start)
				iolatency_check_latencies(iolat, now);
		}
next:
		wake_up(&rqw->wait);
		blkg = blkg->parent;
	}
}

static void blkcg_iolatency_cleanup(struct rq_qos *rqos, struct bio *bio)
{
	struct blkcg_gq *blkg;

	blkg = bio->bi_blkg;
	while (blkg && blkg->parent) {
		struct rq_wait *rqw;
		struct iolatency_grp *iolat;

		iolat = blkg_to_lat(blkg);
		if (!iolat)
			goto next;

		rqw = &iolat->rq_wait;
		atomic_dec(&rqw->inflight);
		wake_up(&rqw->wait);
next:
		blkg = blkg->parent;
	}
}

static void blkcg_iolatency_exit(struct rq_qos *rqos)
{
	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);

	del_timer_sync(&blkiolat->timer);
	blkcg_deactivate_policy(rqos->q, &blkcg_policy_iolatency);
	kfree(blkiolat);
}

static struct rq_qos_ops blkcg_iolatency_ops = {
	.throttle = blkcg_iolatency_throttle,
	.cleanup = blkcg_iolatency_cleanup,
	.done_bio = blkcg_iolatency_done_bio,
	.exit = blkcg_iolatency_exit,
};

static void blkiolatency_timer_fn(struct timer_list *t)
{
	struct blk_iolatency *blkiolat = from_timer(blkiolat, t, timer);
	struct blkcg_gq *blkg;
	struct cgroup_subsys_state *pos_css;
	u64 now = ktime_to_ns(ktime_get());

	rcu_read_lock();
	blkg_for_each_descendant_pre(blkg, pos_css,
				     blkiolat->rqos.q->root_blkg) {
		struct iolatency_grp *iolat;
		struct child_latency_info *lat_info;
		unsigned long flags;
		u64 cookie;

		/*
		 * We could be exiting, don't access the pd unless we have a
		 * ref on the blkg.
		 */
		if (!blkg_try_get(blkg))
			continue;

		iolat = blkg_to_lat(blkg);
		if (!iolat)
			continue;

		lat_info = &iolat->child_lat;
		cookie = atomic_read(&lat_info->scale_cookie);

		if (cookie >= DEFAULT_SCALE_COOKIE)
			goto next;

		spin_lock_irqsave(&lat_info->lock, flags);
		if (lat_info->last_scale_event >= now)
			goto next_lock;

		/*
		 * We scaled down but don't have a scale_grp, scale up and carry
		 * on.
		 */
		if (lat_info->scale_grp == NULL) {
			scale_cookie_change(iolat->blkiolat, lat_info, true);
			goto next_lock;
		}

		/*
		 * It's been 5 seconds since our last scale event, clear the
		 * scale grp in case the group that needed the scale down isn't
		 * doing any IO currently.
		 */
		if (now - lat_info->last_scale_event >=
		    ((u64)NSEC_PER_SEC * 5))
			lat_info->scale_grp = NULL;
next_lock:
		spin_unlock_irqrestore(&lat_info->lock, flags);
next:
		blkg_put(blkg);
	}
	rcu_read_unlock();
}

int blk_iolatency_init(struct request_queue *q)
{
	struct blk_iolatency *blkiolat;
	struct rq_qos *rqos;
	int ret;

	blkiolat = kzalloc(sizeof(*blkiolat), GFP_KERNEL);
	if (!blkiolat)
		return -ENOMEM;

	rqos = &blkiolat->rqos;
	rqos->id = RQ_QOS_CGROUP;
	rqos->ops = &blkcg_iolatency_ops;
	rqos->q = q;

	rq_qos_add(q, rqos);

	ret = blkcg_activate_policy(q, &blkcg_policy_iolatency);
	if (ret) {
		rq_qos_del(q, rqos);
		kfree(blkiolat);
		return ret;
	}

	timer_setup(&blkiolat->timer, blkiolatency_timer_fn, 0);

	return 0;
}

static void iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val)
{
	struct iolatency_grp *iolat = blkg_to_lat(blkg);
	struct blk_iolatency *blkiolat = iolat->blkiolat;
	u64 oldval = iolat->min_lat_nsec;

	iolat->min_lat_nsec = val;
	iolat->cur_win_nsec = max_t(u64, val << 4, 100 * NSEC_PER_MSEC);
	iolat->cur_win_nsec = min_t(u64, iolat->cur_win_nsec, NSEC_PER_SEC);

	if (!oldval && val)
		atomic_inc(&blkiolat->enabled);
	if (oldval && !val)
		atomic_dec(&blkiolat->enabled);
}

static void iolatency_clear_scaling(struct blkcg_gq *blkg)
{
	if (blkg->parent) {
		struct iolatency_grp *iolat = blkg_to_lat(blkg->parent);
		struct child_latency_info *lat_info;
		if (!iolat)
			return;

		lat_info = &iolat->child_lat;
		spin_lock(&lat_info->lock);
		atomic_set(&lat_info->scale_cookie, DEFAULT_SCALE_COOKIE);
		lat_info->last_scale_event = 0;
		lat_info->scale_grp = NULL;
		lat_info->scale_lat = 0;
		spin_unlock(&lat_info->lock);
	}
}

static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf,
			     size_t nbytes, loff_t off)
{
	struct blkcg *blkcg = css_to_blkcg(of_css(of));
	struct blkcg_gq *blkg;
	struct blk_iolatency *blkiolat;
	struct blkg_conf_ctx ctx;
	struct iolatency_grp *iolat;
	char *p, *tok;
	u64 lat_val = 0;
	u64 oldval;
	int ret;

	ret = blkg_conf_prep(blkcg, &blkcg_policy_iolatency, buf, &ctx);
	if (ret)
		return ret;

	iolat = blkg_to_lat(ctx.blkg);
	blkiolat = iolat->blkiolat;
	p = ctx.body;

	ret = -EINVAL;
	while ((tok = strsep(&p, " "))) {
		char key[16];
		char val[21];	/* 18446744073709551616 */

		if (sscanf(tok, "%15[^=]=%20s", key, val) != 2)
			goto out;

		if (!strcmp(key, "target")) {
			u64 v;

			if (!strcmp(val, "max"))
				lat_val = 0;
			else if (sscanf(val, "%llu", &v) == 1)
				lat_val = v * NSEC_PER_USEC;
			else
				goto out;
		} else {
			goto out;
		}
	}

	/* Walk up the tree to see if our new val is lower than it should be. */
	blkg = ctx.blkg;
	oldval = iolat->min_lat_nsec;

	iolatency_set_min_lat_nsec(blkg, lat_val);
	if (oldval != iolat->min_lat_nsec) {
		iolatency_clear_scaling(blkg);
	}

	ret = 0;
out:
	blkg_conf_finish(&ctx);
	return ret ?: nbytes;
}

static u64 iolatency_prfill_limit(struct seq_file *sf,
				  struct blkg_policy_data *pd, int off)
{
	struct iolatency_grp *iolat = pd_to_lat(pd);
	const char *dname = blkg_dev_name(pd->blkg);

	if (!dname || !iolat->min_lat_nsec)
		return 0;
	seq_printf(sf, "%s target=%llu\n",
		   dname,
		   (unsigned long long)iolat->min_lat_nsec / NSEC_PER_USEC);
	return 0;
}

static int iolatency_print_limit(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
			  iolatency_prfill_limit,
			  &blkcg_policy_iolatency, seq_cft(sf)->private, false);
	return 0;
}

static size_t iolatency_pd_stat(struct blkg_policy_data *pd, char *buf,
				size_t size)
{
	struct iolatency_grp *iolat = pd_to_lat(pd);
	unsigned long long avg_lat = div64_u64(iolat->total_lat_avg, NSEC_PER_USEC);

	if (iolat->rq_depth.max_depth == (u64)-1)
		return scnprintf(buf, size, " depth=max avg_lat=%llu",
				 avg_lat);

	return scnprintf(buf, size, " depth=%u avg_lat=%llu",
			 iolat->rq_depth.max_depth, avg_lat);
}


static struct blkg_policy_data *iolatency_pd_alloc(gfp_t gfp, int node)
{
	struct iolatency_grp *iolat;

	iolat = kzalloc_node(sizeof(*iolat), gfp, node);
	if (!iolat)
		return NULL;
	iolat->stats = __alloc_percpu_gfp(sizeof(struct blk_rq_stat),
				       __alignof__(struct blk_rq_stat), gfp);
	if (!iolat->stats) {
		kfree(iolat);
		return NULL;
	}
	return &iolat->pd;
}

static void iolatency_pd_init(struct blkg_policy_data *pd)
{
	struct iolatency_grp *iolat = pd_to_lat(pd);
	struct blkcg_gq *blkg = lat_to_blkg(iolat);
	struct rq_qos *rqos = blkcg_rq_qos(blkg->q);
	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
	u64 now = ktime_to_ns(ktime_get());
	int cpu;

	for_each_possible_cpu(cpu) {
		struct blk_rq_stat *stat;
		stat = per_cpu_ptr(iolat->stats, cpu);
		blk_rq_stat_init(stat);
	}

	rq_wait_init(&iolat->rq_wait);
	spin_lock_init(&iolat->child_lat.lock);
	iolat->rq_depth.queue_depth = blk_queue_depth(blkg->q);
	iolat->rq_depth.max_depth = INT_MAX;
	iolat->rq_depth.default_depth = iolat->rq_depth.queue_depth;
	iolat->blkiolat = blkiolat;
	iolat->cur_win_nsec = 100 * NSEC_PER_MSEC;
	atomic64_set(&iolat->window_start, now);

	/*
	 * We init things in list order, so the pd for the parent may not be
	 * init'ed yet for whatever reason.
	 */
	if (blkg->parent && blkg_to_pd(blkg->parent, &blkcg_policy_iolatency)) {
		struct iolatency_grp *parent = blkg_to_lat(blkg->parent);
		atomic_set(&iolat->scale_cookie,
			   atomic_read(&parent->child_lat.scale_cookie));
	} else {
		atomic_set(&iolat->scale_cookie, DEFAULT_SCALE_COOKIE);
	}

	atomic_set(&iolat->child_lat.scale_cookie, DEFAULT_SCALE_COOKIE);
}

static void iolatency_pd_offline(struct blkg_policy_data *pd)
{
	struct iolatency_grp *iolat = pd_to_lat(pd);
	struct blkcg_gq *blkg = lat_to_blkg(iolat);

	iolatency_set_min_lat_nsec(blkg, 0);
	iolatency_clear_scaling(blkg);
}

static void iolatency_pd_free(struct blkg_policy_data *pd)
{
	struct iolatency_grp *iolat = pd_to_lat(pd);
	free_percpu(iolat->stats);
	kfree(iolat);
}

static struct cftype iolatency_files[] = {
	{
		.name = "latency",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = iolatency_print_limit,
		.write = iolatency_set_limit,
	},
	{}
};

static struct blkcg_policy blkcg_policy_iolatency = {
	.dfl_cftypes	= iolatency_files,
	.pd_alloc_fn	= iolatency_pd_alloc,
	.pd_init_fn	= iolatency_pd_init,
	.pd_offline_fn	= iolatency_pd_offline,
	.pd_free_fn	= iolatency_pd_free,
	.pd_stat_fn	= iolatency_pd_stat,
};

static int __init iolatency_init(void)
{
	return blkcg_policy_register(&blkcg_policy_iolatency);
}

static void __exit iolatency_exit(void)
{
	return blkcg_policy_unregister(&blkcg_policy_iolatency);
}

module_init(iolatency_init);
module_exit(iolatency_exit);