aiot/waterDataDiscreteRateMining/main.c

/*
 *  CFQ, or complete fairness queueing, disk scheduler.
 *
 *  Based on ideas from a previously unfinished io
 *  scheduler (round robin per-process disk scheduling) and Andrea Arcangeli.
 *
 *  Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
 */
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
#include <linux/jiffies.h>
#include <linux/rbtree.h>
#include <linux/ioprio.h>
#include <linux/blktrace_api.h>
#include "blk.h"
#include "blk-cgroup.h"

/*
 * tunables
 */
/* max queue in one round of service */
static const int cfq_quantum = 8;
static const int cfq_fifo_expire[2] = { HZ / 4, HZ / 8 };
/* maximum backwards seek, in KiB */
static const int cfq_back_max = 16 * 1024;
/* penalty of a backwards seek */
static const int cfq_back_penalty = 2;
static const int cfq_slice_sync = HZ / 10;
static int cfq_slice_async = HZ / 25;
static const int cfq_slice_async_rq = 2;
static int cfq_slice_idle = HZ / 125;
static int cfq_group_idle = HZ / 125;
static const int cfq_target_latency = HZ * 3/10; /* 300 ms */
static const int cfq_hist_divisor = 4;

/*
 * offset from end of service tree
 */
#define CFQ_IDLE_DELAY		(HZ / 5)

/*
 * below this threshold, we consider thinktime immediate
 */
#define CFQ_MIN_TT		(2)

#define CFQ_SLICE_SCALE		(5)
#define CFQ_HW_QUEUE_MIN	(5)
#define CFQ_SERVICE_SHIFT       12

#define CFQQ_SEEK_THR		(sector_t)(8 * 100)
#define CFQQ_CLOSE_THR		(sector_t)(8 * 1024)
#define CFQQ_SECT_THR_NONROT	(sector_t)(2 * 32)
#define CFQQ_SEEKY(cfqq)	(hweight32(cfqq->seek_history) > 32/8)

#define RQ_CIC(rq)		icq_to_cic((rq)->elv.icq)
#define RQ_CFQQ(rq)		(struct cfq_queue *) ((rq)->elv.priv[0])
#define RQ_CFQG(rq)		(struct cfq_group *) ((rq)->elv.priv[1])

static struct kmem_cache *cfq_pool;

#define CFQ_PRIO_LISTS		IOPRIO_BE_NR
#define cfq_class_idle(cfqq)	((cfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
#define cfq_class_rt(cfqq)	((cfqq)->ioprio_class == IOPRIO_CLASS_RT)

#define sample_valid(samples)	((samples) > 80)
#define rb_entry_cfqg(node)	rb_entry((node), struct cfq_group, rb_node)

struct cfq_ttime {
	unsigned long last_end_request;

	unsigned long ttime_total;
	unsigned long ttime_samples;
	unsigned long ttime_mean;
};

/*
 * Most of our rbtree usage is for sorting with min extraction, so
 * if we cache the leftmost node we don't have to walk down the tree
 * to find it. Idea borrowed from Ingo Molnars CFS scheduler. We should
 * move this into the elevator for the rq sorting as well.
 */
struct cfq_rb_root {
	struct rb_root rb;
	struct rb_node *left;
	unsigned count;
	unsigned total_weight;
	u64 min_vdisktime;
	struct cfq_ttime ttime;
};
#define CFQ_RB_ROOT	(struct cfq_rb_root) { .rb = RB_ROOT, \
			.ttime = {.last_end_request = jiffies,},}

/*
 * Per process-grouping structure
 */
struct cfq_queue {
	/* reference count */
	int ref;
	/* various state flags, see below */
	unsigned int flags;
	/* parent cfq_data */
	struct cfq_data *cfqd;
	/* service_tree member */
	struct rb_node rb_node;
	/* service_tree key */
	unsigned long rb_key;
	/* prio tree member */
	struct rb_node p_node;
	/* prio tree root we belong to, if any */
	struct rb_root *p_root;
	/* sorted list of pending requests */
	struct rb_root sort_list;
	/* if fifo isn't expired, next request to serve */
	struct request *next_rq;
	/* requests queued in sort_list */
	int queued[2];
	/* currently allocated requests */
	int allocated[2];
	/* fifo list of requests in sort_list */
	struct list_head fifo;

	/* time when queue got scheduled in to dispatch first request. */
	unsigned long dispatch_start;
	unsigned int allocated_slice;
	unsigned int slice_dispatch;
	/* time when first request from queue completed and slice started. */
	unsigned long slice_start;
	unsigned long slice_end;
	long slice_resid;

	/* pending priority requests */
	int prio_pending;
	/* number of requests that are on the dispatch list or inside driver */
	int dispatched;

	/* io prio of this group */
	unsigned short ioprio, org_ioprio;
	unsigned short ioprio_class;

	pid_t pid;

	u32 seek_history;
	sector_t last_request_pos;

	struct cfq_rb_root *service_tree;
	struct cfq_queue *new_cfqq;
	struct cfq_group *cfqg;
	/* Number of sectors dispatched from queue in single dispatch round */
	unsigned long nr_sectors;
};

/*
 * First index in the service_trees.
 * IDLE is handled separately, so it has negative index
 */
enum wl_prio_t {
	BE_WORKLOAD = 0,
	RT_WORKLOAD = 1,
	IDLE_WORKLOAD = 2,
	CFQ_PRIO_NR,
};

/*
 * Second index in the service_trees.
 */
enum wl_type_t {
	ASYNC_WORKLOAD = 0,
	SYNC_NOIDLE_WORKLOAD = 1,
	SYNC_WORKLOAD = 2
};

struct cfqg_stats {
#ifdef CONFIG_CFQ_GROUP_IOSCHED
	/* total bytes transferred */
	struct blkg_rwstat		service_bytes;
	/* total IOs serviced, post merge */
	struct blkg_rwstat		serviced;
	/* number of ios merged */
	struct blkg_rwstat		merged;
	/* total time spent on device in ns, may not be accurate w/ queueing */
	struct blkg_rwstat		service_time;
	/* total time spent waiting in scheduler queue in ns */
	struct blkg_rwstat		wait_time;
	/* number of IOs queued up */
	struct blkg_rwstat		queued;
	/* total sectors transferred */
	struct blkg_stat		sectors;
	/* total disk time and nr sectors dispatched by this group */
	struct blkg_stat		time;
#ifdef CONFIG_DEBUG_BLK_CGROUP
	/* time not charged to this cgroup */
	struct blkg_stat		unaccounted_time;
	/* sum of number of ios queued across all samples */
	struct blkg_stat		avg_queue_size_sum;
	/* count of samples taken for average */
	struct blkg_stat		avg_queue_size_samples;
	/* how many times this group has been removed from service tree */
	struct blkg_stat		dequeue;
	/* total time spent waiting for it to be assigned a timeslice. */
	struct blkg_stat		group_wait_time;
	/* time spent idling for this blkcg_gq */
	struct blkg_stat		idle_time;
	/* total time with empty current active q with other requests queued */
	struct blkg_stat		empty_time;
	/* fields after this shouldn't be cleared on stat reset */
	uint64_t			start_group_wait_time;
	uint64_t			start_idle_time;
	uint64_t			start_empty_time;
	uint16_t			flags;
#endif	/* CONFIG_DEBUG_BLK_CGROUP */
#endif	/* CONFIG_CFQ_GROUP_IOSCHED */
};

/* This is per cgroup per device grouping structure */
struct cfq_group {
	/* must be the first member */
	struct blkg_policy_data pd;

	/* group service_tree member */
	struct rb_node rb_node;

	/* group service_tree key */
	u64 vdisktime;
	unsigned int weight;
	unsigned int new_weight;
	unsigned int dev_weight;

	/* number of cfqq currently on this group */
	int nr_cfqq;

	/*
	 * Per group busy queues average. Useful for workload slice calc. We
	 * create the array for each prio class but at run time it is used
	 * only for RT and BE class and slot for IDLE class remains unused.
	 * This is primarily done to avoid confusion and a gcc warning.
	 */
	unsigned int busy_queues_avg[CFQ_PRIO_NR];
	/*
	 * rr lists of queues with requests. We maintain service trees for
	 * RT and BE classes. These trees are subdivided in subclasses
	 * of SYNC, SYNC_NOIDLE and ASYNC based on workload type. For IDLE
	 * class there is no subclassification and all the cfq queues go on
	 * a single tree service_tree_idle.
	 * Counts are embedded in the cfq_rb_root
	 */
	struct cfq_rb_root service_trees[2][3];
	struct cfq_rb_root service_tree_idle;

	unsigned long saved_workload_slice;
	enum wl_type_t saved_workload;
	enum wl_prio_t saved_serving_prio;

	/* number of requests that are on the dispatch list or inside driver */
	int dispatched;
	struct cfq_ttime ttime;
	struct cfqg_stats stats;
};

struct cfq_io_cq {
	struct io_cq		icq;		/* must be the first member */
	struct cfq_queue	*cfqq[2];
	struct cfq_ttime	ttime;
	int			ioprio;		/* the current ioprio */
#ifdef CONFIG_CFQ_GROUP_IOSCHED
	uint64_t		blkcg_id;	/* the current blkcg ID */
#endif
};

/*
 * Per block device queue structure
 */
struct cfq_data {
	struct request_queue *queue;
	/* Root service tree for cfq_groups */
	struct cfq_rb_root grp_service_tree;
	struct cfq_group *root_group;

	/*
	 * The priority currently being served
	 */
	enum wl_prio_t serving_prio;
	enum wl_type_t serving_type;
	unsigned long workload_expires;
	struct cfq_group *serving_group;

	/*
	 * Each priority tree is sorted by next_request position.  These
	 * trees are used when determining if two or more queues are
	 * interleaving requests (see cfq_close_cooperator).
	 */
	struct rb_root prio_trees[CFQ_PRIO_LISTS];

	unsigned int busy_queues;
	unsigned int busy_sync_queues;

	int rq_in_driver;
	int rq_in_flight[2];

	/*
	 * queue-depth detection
	 */
	int rq_queued;
	int hw_tag;
	/*
	 * hw_tag can be
	 * -1 => indeterminate, (cfq will behave as if NCQ is present, to allow better detection)
	 *  1 => NCQ is present (hw_tag_est_depth is the estimated max depth)
	 *  0 => no NCQ
	 */
	int hw_tag_est_depth;
	unsigned int hw_tag_samples;

	/*
	 * idle window management
	 */
	struct timer_list idle_slice_timer;
	struct work_struct unplug_work;

	struct cfq_queue *active_queue;
	struct cfq_io_cq *active_cic;

	/*
	 * async queue for each priority case
	 */
	struct cfq_queue *async_cfqq[2][IOPRIO_BE_NR];
	struct cfq_queue *async_idle_cfqq;

	sector_t last_position;

	/*
	 * tunables, see top of file
	 */
	unsigned int cfq_quantum;
	unsigned int cfq_fifo_expire[2];
	unsigned int cfq_back_penalty;
	unsigned int cfq_back_max;
	unsigned int cfq_slice[2];
	unsigned int cfq_slice_async_rq;
	unsigned int cfq_slice_idle;
	unsigned int cfq_group_idle;
	unsigned int cfq_latency;
	unsigned int cfq_target_latency;

	/*
	 * Fallback dummy cfqq for extreme OOM conditions
	 */
	struct cfq_queue oom_cfqq;

	unsigned long last_delayed_sync;
};

static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd);

static struct cfq_rb_root *service_tree_for(struct cfq_group *cfqg,
					    enum wl_prio_t prio,
					    enum wl_type_t type)
{
	if (!cfqg)
		return NULL;

	if (prio == IDLE_WORKLOAD)
		return &cfqg->service_tree_idle;

	return &cfqg->service_trees[prio][type];
}

enum cfqq_state_flags {
	CFQ_CFQQ_FLAG_on_rr = 0,	/* on round-robin busy list */
	CFQ_CFQQ_FLAG_wait_request,	/* waiting for a request */
	CFQ_CFQQ_FLAG_must_dispatch,	/* must be allowed a dispatch */
	CFQ_CFQQ_FLAG_must_alloc_slice,	/* per-slice must_alloc flag */
	CFQ_CFQQ_FLAG_fifo_expire,	/* FIFO checked in this slice */
	CFQ_CFQQ_FLAG_idle_window,	/* slice idling enabled */
	CFQ_CFQQ_FLAG_prio_changed,	/* task priority has changed */
	CFQ_CFQQ_FLAG_slice_new,	/* no requests dispatched in slice */
	CFQ_CFQQ_FLAG_sync,		/* synchronous queue */
	CFQ_CFQQ_FLAG_coop,		/* cfqq is shared */
	CFQ_CFQQ_FLAG_split_coop,	/* shared cfqq will be splitted */
	CFQ_CFQQ_FLAG_deep,		/* sync cfqq experienced large depth */
	CFQ_CFQQ_FLAG_wait_busy,	/* Waiting for next request */
};

#define CFQ_CFQQ_FNS(name)						\
static inline void cfq_mark_cfqq_##name(struct cfq_queue *cfqq)		\
{									\
	(cfqq)->flags |= (1 << CFQ_CFQQ_FLAG_##name);			\
}									\
static inline void cfq_clear_cfqq_##name(struct cfq_queue *cfqq)	\
{									\
	(cfqq)->flags &= ~(1 << CFQ_CFQQ_FLAG_##name);			\
}									\
static inline int cfq_cfqq_##name(const struct cfq_queue *cfqq)		\
{									\
	return ((cfqq)->flags & (1 << CFQ_CFQQ_FLAG_##name)) != 0;	\
}

CFQ_CFQQ_FNS(on_rr);
CFQ_CFQQ_FNS(wait_request);
CFQ_CFQQ_FNS(must_dispatch);
CFQ_CFQQ_FNS(must_alloc_slice);
CFQ_CFQQ_FNS(fifo_expire);
CFQ_CFQQ_FNS(idle_window);
CFQ_CFQQ_FNS(prio_changed);
CFQ_CFQQ_FNS(slice_new);
CFQ_CFQQ_FNS(sync);
CFQ_CFQQ_FNS(coop);
CFQ_CFQQ_FNS(split_coop);
CFQ_CFQQ_FNS(deep);
CFQ_CFQQ_FNS(wait_busy);
#undef CFQ_CFQQ_FNS

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

static inline struct blkcg_gq *cfqg_to_blkg(struct cfq_group *cfqg)
{
	return pd_to_blkg(&cfqg->pd);
}

#if defined(CONFIG_CFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)

/* cfqg stats flags */
enum cfqg_stats_flags {
	CFQG_stats_waiting = 0,
	CFQG_stats_idling,
	CFQG_stats_empty,
};

#define CFQG_FLAG_FNS(name)						\
static inline void cfqg_stats_mark_##name(struct cfqg_stats *stats)	\
{									\
	stats->flags |= (1 << CFQG_stats_##name);			\
}									\
static inline void cfqg_stats_clear_##name(struct cfqg_stats *stats)	\
{									\
	stats->flags &= ~(1 << CFQG_stats_##name);			\
}									\
static inline int cfqg_stats_##name(struct cfqg_stats *stats)		\
{									\
	return (stats->flags & (1 << CFQG_stats_##name)) != 0;		\
}									\

CFQG_FLAG_FNS(waiting)
CFQG_FLAG_FNS(idling)
CFQG_FLAG_FNS(empty)
#undef CFQG_FLAG_FNS

/* This should be called with the queue_lock held. */
static void cfqg_stats_update_group_wait_time(struct cfqg_stats *stats)
{
	unsigned long long now;

	if (!cfqg_stats_waiting(stats))
		return;

	now = sched_clock();
	if (time_after64(now, stats->start_group_wait_time))
		blkg_stat_add(&stats->group_wait_time,
			      now - stats->start_group_wait_time);
	cfqg_stats_clear_waiting(stats);
}

/* This should be called with the queue_lock held. */
static void cfqg_stats_set_start_group_wait_time(struct cfq_group *cfqg,
						 struct cfq_group *curr_cfqg)
{
	struct cfqg_stats *stats = &cfqg->stats;

	if (cfqg_stats_waiting(stats))
		return;
	if (cfqg == curr_cfqg)
		return;
	stats->start_group_wait_time = sched_clock();
	cfqg_stats_mark_waiting(stats);
}

/* This should be called with the queue_lock held. */
static void cfqg_stats_end_empty_time(struct cfqg_stats *stats)
{
	unsigned long long now;

	if (!cfqg_stats_empty(stats))
		return;

	now = sched_clock();
	if (time_after64(now, stats->start_empty_time))
		blkg_stat_add(&stats->empty_time,
			      now - stats->start_empty_time);
	cfqg_stats_clear_empty(stats);
}

static void cfqg_stats_update_dequeue(struct cfq_group *cfqg)
{
	blkg_stat_add(&cfqg->stats.dequeue, 1);
}

static void cfqg_stats_set_start_empty_time(struct cfq_group *cfqg)
{
	struct cfqg_stats *stats = &cfqg->stats;

	if (blkg_rwstat_sum(&stats->queued))
		return;

	/*
	 * group is already marked empty. This can happen if cfqq got new
	 * request in parent group and moved to this group while being added
	 * to service tree. Just ignore the event and move on.
	 */
	if (cfqg_stats_empty(stats))
		return;

	stats->start_empty_time = sched_clock();
	cfqg_stats_mark_empty(stats);
}

static void cfqg_stats_update_idle_time(struct cfq_group *cfqg)
{
	struct cfqg_stats *stats = &cfqg->stats;

	if (cfqg_stats_idling(stats)) {
		unsigned long long now = sched_clock();

		if (time_after64(now, stats->start_idle_time))
			blkg_stat_add(&stats->idle_time,
				      now - stats->start_idle_time);
		cfqg_stats_clear_idling(stats);
	}
}

static void cfqg_stats_set_start_idle_time(struct cfq_group *cfqg)
{
	struct cfqg_stats *stats = &cfqg->stats;

	BUG_ON(cfqg_stats_idling(stats));

	stats->start_idle_time = sched_clock();
	cfqg_stats_mark_idling(stats);
}

static void cfqg_stats_update_avg_queue_size(struct cfq_group *cfqg)
{
	struct cfqg_stats *stats = &cfqg->stats;

	blkg_stat_add(&stats->avg_queue_size_sum,
		      blkg_rwstat_sum(&stats->queued));
	blkg_stat_add(&stats->avg_queue_size_samples, 1);
	cfqg_stats_update_group_wait_time(stats);
}

#else	/* CONFIG_CFQ_GROUP_IOSCHED && CONFIG_DEBUG_BLK_CGROUP */

static inline void cfqg_stats_set_start_group_wait_time(struct cfq_group *cfqg, struct cfq_group *curr_cfqg) { }
static inline void cfqg_stats_end_empty_time(struct cfqg_stats *stats) { }
static inline void cfqg_stats_update_dequeue(struct cfq_group *cfqg) { }
static inline void cfqg_stats_set_start_empty_time(struct cfq_group *cfqg) { }
static inline void cfqg_stats_update_idle_time(struct cfq_group *cfqg) { }
static inline void cfqg_stats_set_start_idle_time(struct cfq_group *cfqg) { }
static inline void cfqg_stats_update_avg_queue_size(struct cfq_group *cfqg) { }

#endif	/* CONFIG_CFQ_GROUP_IOSCHED && CONFIG_DEBUG_BLK_CGROUP */

#ifdef CONFIG_CFQ_GROUP_IOSCHED

static struct blkcg_policy blkcg_policy_cfq;

static inline struct cfq_group *blkg_to_cfqg(struct blkcg_gq *blkg)
{
	return pd_to_cfqg(blkg_to_pd(blkg, &blkcg_policy_cfq));
}

static inline void cfqg_get(struct cfq_group *cfqg)
{
	return blkg_get(cfqg_to_blkg(cfqg));
}

static inline void cfqg_put(struct cfq_group *cfqg)
{
	return blkg_put(cfqg_to_blkg(cfqg));
}

#define cfq_log_cfqq(cfqd, cfqq, fmt, args...)	do {			\
	char __pbuf[128];						\
									\
	blkg_path(cfqg_to_blkg((cfqq)->cfqg), __pbuf, sizeof(__pbuf));	\
	blk_add_trace_msg((cfqd)->queue, "cfq%d%c %s " fmt, (cfqq)->pid, \
			  cfq_cfqq_sync((cfqq)) ? 'S' : 'A',		\
			  __pbuf, ##args);				\
} while (0)

#define cfq_log_cfqg(cfqd, cfqg, fmt, args...)	do {			\
	char __pbuf[128];						\
									\
	blkg_path(cfqg_to_blkg(cfqg), __pbuf, sizeof(__pbuf));		\
	blk_add_trace_msg((cfqd)->queue, "%s " fmt, __pbuf, ##args);	\
} while (0)

static inline void cfqg_stats_update_io_add(struct cfq_group *cfqg,
					    struct cfq_group *curr_cfqg, int rw)
{
	blkg_rwstat_add(&cfqg->stats.queued, rw, 1);
	cfqg_stats_end_empty_time(&cfqg->stats);
	cfqg_stats_set_start_group_wait_time(cfqg, curr_cfqg);
}

static inline void cfqg_stats_update_timeslice_used(struct cfq_group *cfqg,
			unsigned long time, unsigned long unaccounted_time)
{
	blkg_stat_add(&cfqg->stats.time, time);
#ifdef CONFIG_DEBUG_BLK_CGROUP
	blkg_stat_add(&cfqg->stats.unaccounted_time, unaccounted_time);
#endif
}

static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int rw)
{
	blkg_rwstat_add(&cfqg->stats.queued, rw, -1);
}

static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int rw)
{
	blkg_rwstat_add(&cfqg->stats.merged, rw, 1);
}

static inline void cfqg_stats_update_dispatch(struct cfq_group *cfqg,
					      uint64_t bytes, int rw)
{
	blkg_stat_add(&cfqg->stats.sectors, bytes >> 9);
	blkg_rwstat_add(&cfqg->stats.serviced, rw, 1);
	blkg_rwstat_add(&cfqg->stats.service_bytes, rw, bytes);
}

static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
			uint64_t start_time, uint64_t io_start_time, int rw)
{
	struct cfqg_stats *stats = &cfqg->stats;
	unsigned long long now = sched_clock();

	if (time_after64(now, io_start_time))
		blkg_rwstat_add(&stats->service_time, rw, now - io_start_time);
	if (time_after64(io_start_time, start_time))
		blkg_rwstat_add(&stats->wait_time, rw,
				io_start_time - start_time);
}

static void cfq_pd_reset_stats(struct blkcg_gq *blkg)
{
	struct cfq_group *cfqg = blkg_to_cfqg(blkg);
	struct cfqg_stats *stats = &cfqg->stats;

	/* queued stats shouldn't be cleared */
	blkg_rwstat_reset(&stats->service_bytes);
	blkg_rwstat_reset(&stats->serviced);
	blkg_rwstat_reset(&stats->merged);
	blkg_rwstat_reset(&stats->service_time);
	blkg_rwstat_reset(&stats->wait_time);
	blkg_stat_reset(&stats->time);
#ifdef CONFIG_DEBUG_BLK_CGROUP
	blkg_stat_reset(&stats->unaccounted_time);
	blkg_stat_reset(&stats->avg_queue_size_sum);
	blkg_stat_reset(&stats->avg_queue_size_samples);
	blkg_stat_reset(&stats->dequeue);
	blkg_stat_reset(&stats->group_wait_time);
	blkg_stat_reset(&stats->idle_time);
	blkg_stat_reset(&stats->empty_time);
#endif
}

#else	/* CONFIG_CFQ_GROUP_IOSCHED */

static inline void cfqg_get(struct cfq_group *cfqg) { }
static inline void cfqg_put(struct cfq_group *cfqg) { }

#define cfq_log_cfqq(cfqd, cfqq, fmt, args...)	\
	blk_add_trace_msg((cfqd)->queue, "cfq%d " fmt, (cfqq)->pid, ##args)
#define cfq_log_cfqg(cfqd, cfqg, fmt, args...)		do {} while (0)

static inline void cfqg_stats_update_io_add(struct cfq_group *cfqg,
			struct cfq_group *curr_cfqg, int rw) { }
static inline void cfqg_stats_update_timeslice_used(struct cfq_group *cfqg,
			unsigned long time, unsigned long unaccounted_time) { }
static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int rw) { }
static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int rw) { }
static inline void cfqg_stats_update_dispatch(struct cfq_group *cfqg,
					      uint64_t bytes, int rw) { }
static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
			uint64_t start_time, uint64_t io_start_time, int rw) { }

#endif	/* CONFIG_CFQ_GROUP_IOSCHED */

#define cfq_log(cfqd, fmt, args...)	\
	blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args)

/* Traverses through cfq group service trees */
#define for_each_cfqg_st(cfqg, i, j, st) \
	for (i = 0; i <= IDLE_WORKLOAD; i++) \
		for (j = 0, st = i < IDLE_WORKLOAD ? &cfqg->service_trees[i][j]\
			: &cfqg->service_tree_idle; \
			(i < IDLE_WORKLOAD && j <= SYNC_WORKLOAD) || \
			(i == IDLE_WORKLOAD && j == 0); \
			j++, st = i < IDLE_WORKLOAD ? \
			&cfqg->service_trees[i][j]: NULL) \

static inline bool cfq_io_thinktime_big(struct cfq_data *cfqd,
	struct cfq_ttime *ttime, bool group_idle)
{
	unsigned long slice;
	if (!sample_valid(ttime->ttime_samples))
		return false;
	if (group_idle)
		slice = cfqd->cfq_group_idle;
	else
		slice = cfqd->cfq_slice_idle;
	return ttime->ttime_mean > slice;
}

static inline bool iops_mode(struct cfq_data *cfqd)
{
	/*
	 * If we are not idling on queues and it is a NCQ drive, parallel
	 * execution of requests is on and measuring time is not possible
	 * in most of the cases until and unless we drive shallower queue
	 * depths and that becomes a performance bottleneck. In such cases
	 * switch to start providing fairness in terms of number of IOs.
	 */
	if (!cfqd->cfq_slice_idle && cfqd->hw_tag)
		return true;
	else
		return false;
}

static inline enum wl_prio_t cfqq_prio(struct cfq_queue *cfqq)
{
	if (cfq_class_idle(cfqq))
		return IDLE_WORKLOAD;
	if (cfq_class_rt(cfqq))
		return RT_WORKLOAD;
	return BE_WORKLOAD;
}


static enum wl_type_t cfqq_type(struct cfq_queue *cfqq)
{
	if (!cfq_cfqq_sync(cfqq))
		return ASYNC_WORKLOAD;
	if (!cfq_cfqq_idle_window(cfqq))
		return SYNC_NOIDLE_WORKLOAD;
	return SYNC_WORKLOAD;
}

static inline int cfq_group_busy_queues_wl(enum wl_prio_t wl,
					struct cfq_data *cfqd,
					struct cfq_group *cfqg)
{
	if (wl == IDLE_WORKLOAD)
		return cfqg->service_tree_idle.count;

	return cfqg->service_trees[wl][ASYNC_WORKLOAD].count
		+ cfqg->service_trees[wl][SYNC_NOIDLE_WORKLOAD].count
		+ cfqg->service_trees[wl][SYNC_WORKLOAD].count;
}

static inline int cfqg_busy_async_queues(struct cfq_data *cfqd,
					struct cfq_group *cfqg)
{
	return cfqg->service_trees[RT_WORKLOAD][ASYNC_WORKLOAD].count
		+ cfqg->service_trees[BE_WORKLOAD][ASYNC_WORKLOAD].count;
}

static void cfq_dispatch_insert(struct request_queue *, struct request *);
static struct cfq_queue *cfq_get_queue(struct cfq_data *cfqd, bool is_sync,
				       struct cfq_io_cq *cic, struct bio *bio,
				       gfp_t gfp_mask);

static inline struct cfq_io_cq *icq_to_cic(struct io_cq *icq)
{
	/* cic->icq is the first member, %NULL will convert to %NULL */
	return container_of(icq, struct cfq_io_cq, icq);
}

static inline struct cfq_io_cq *cfq_cic_lookup(struct cfq_data *cfqd,
					       struct io_context *ioc)
{
	if (ioc)
		return icq_to_cic(ioc_lookup_icq(ioc, cfqd->queue));
	return NULL;
}

static inline struct cfq_queue *cic_to_cfqq(struct cfq_io_cq *cic, bool is_sync)
{
	return cic->cfqq[is_sync];
}

static inline void cic_set_cfqq(struct cfq_io_cq *cic, struct cfq_queue *cfqq,
				bool is_sync)
{
	cic->cfqq[is_sync] = cfqq;
}

static inline struct cfq_data *cic_to_cfqd(struct cfq_io_cq *cic)
{
	return cic->icq.q->elevator->elevator_data;
}

/*
 * We regard a request as SYNC, if it's either a read or has the SYNC bit
 * set (in which case it could also be direct WRITE).
 */
static inline bool cfq_bio_sync(struct bio *bio)
{
	return bio_data_dir(bio) == READ || (bio->bi_rw & REQ_SYNC);
}

/*
 * scheduler run of queue, if there are requests pending and no one in the
 * driver that will restart queueing
 */
static inline void cfq_schedule_dispatch(struct cfq_data *cfqd)
{
	if (cfqd->busy_queues) {
		cfq_log(cfqd, "schedule dispatch");
		kblockd_schedule_work(cfqd->queue, &cfqd->unplug_work);
	}
}

/*
 * Scale schedule slice based on io priority. Use the sync time slice only
 * if a queue is marked sync and has sync io queued. A sync queue with async
 * io only, should not get full sync slice length.
 */
static inline int cfq_prio_slice(struct cfq_data *cfqd, bool sync,
				 unsigned short prio)
{
	const int base_slice = cfqd->cfq_slice[sync];

	WARN_ON(prio >= IOPRIO_BE_NR);

	return base_slice + (base_slice/CFQ_SLICE_SCALE * (4 - prio));
}

static inline int
cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	return cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio);
}

static inline u64 cfq_scale_slice(unsigned long delta, struct cfq_group *cfqg)
{
	u64 d = delta << CFQ_SERVICE_SHIFT;

	d = d * CFQ_WEIGHT_DEFAULT;
	do_div(d, cfqg->weight);
	return d;
}

static inline u64 max_vdisktime(u64 min_vdisktime, u64 vdisktime)
{
	s64 delta = (s64)(vdisktime - min_vdisktime);
	if (delta > 0)
		min_vdisktime = vdisktime;

	return min_vdisktime;
}

static inline u64 min_vdisktime(u64 min_vdisktime, u64 vdisktime)
{
	s64 delta = (s64)(vdisktime - min_vdisktime);
	if (delta < 0)
		min_vdisktime = vdisktime;

	return min_vdisktime;
}

static void update_min_vdisktime(struct cfq_rb_root *st)
{
	struct cfq_group *cfqg;

	if (st->left) {
		cfqg = rb_entry_cfqg(st->left);
		st->min_vdisktime = max_vdisktime(st->min_vdisktime,
						  cfqg->vdisktime);
	}
}

/*
 * get averaged number of queues of RT/BE priority.
 * average is updated, with a formula that gives more weight to higher numbers,
 * to quickly follows sudden increases and decrease slowly
 */

static inline unsigned cfq_group_get_avg_queues(struct cfq_data *cfqd,
					struct cfq_group *cfqg, bool rt)
{
	unsigned min_q, max_q;
	unsigned mult  = cfq_hist_divisor - 1;
	unsigned round = cfq_hist_divisor / 2;
	unsigned busy = cfq_group_busy_queues_wl(rt, cfqd, cfqg);

	min_q = min(cfqg->busy_queues_avg[rt], busy);
	max_q = max(cfqg->busy_queues_avg[rt], busy);
	cfqg->busy_queues_avg[rt] = (mult * max_q + min_q + round) /
		cfq_hist_divisor;
	return cfqg->busy_queues_avg[rt];
}

static inline unsigned
cfq_group_slice(struct cfq_data *cfqd, struct cfq_group *cfqg)
{
	struct cfq_rb_root *st = &cfqd->grp_service_tree;

	return cfqd->cfq_target_latency * cfqg->weight / st->total_weight;
}

static inline unsigned
cfq_scaled_cfqq_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	unsigned slice = cfq_prio_to_slice(cfqd, cfqq);
	if (cfqd->cfq_latency) {
		/*
		 * interested queues (we consider only the ones with the same
		 * priority class in the cfq group)
		 */
		unsigned iq = cfq_group_get_avg_queues(cfqd, cfqq->cfqg,
						cfq_class_rt(cfqq));
		unsigned sync_slice = cfqd->cfq_slice[1];
		unsigned expect_latency = sync_slice * iq;
		unsigned group_slice = cfq_group_slice(cfqd, cfqq->cfqg);

		if (expect_latency > group_slice) {
			unsigned base_low_slice = 2 * cfqd->cfq_slice_idle;
			/* scale low_slice according to IO priority
			 * and sync vs async */
			unsigned low_slice =
				min(slice, base_low_slice * slice / sync_slice);
			/* the adapted slice value is scaled to fit all iqs
			 * into the target latency */
			slice = max(slice * group_slice / expect_latency,
				    low_slice);
		}
	}
	return slice;
}

static inline void
cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	unsigned slice = cfq_scaled_cfqq_slice(cfqd, cfqq);

	cfqq->slice_start = jiffies;
	cfqq->slice_end = jiffies + slice;
	cfqq->allocated_slice = slice;
	cfq_log_cfqq(cfqd, cfqq, "set_slice=%lu", cfqq->slice_end - jiffies);
}

/*
 * We need to wrap this check in cfq_cfqq_slice_new(), since ->slice_end
 * isn't valid until the first request from the dispatch is activated
 * and the slice time set.
 */
static inline bool cfq_slice_used(struct cfq_queue *cfqq)
{
	if (cfq_cfqq_slice_new(cfqq))
		return false;
	if (time_before(jiffies, cfqq->slice_end))
		return false;

	return true;
}

/*
 * Lifted from AS - choose which of rq1 and rq2 that is best served now.
 * We choose the request that is closest to the head right now. Distance
 * behind the head is penalized and only allowed to a certain extent.
 */
static struct request *
cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2, sector_t last)
{
	sector_t s1, s2, d1 = 0, d2 = 0;
	unsigned long back_max;
#define CFQ_RQ1_WRAP	0x01 /* request 1 wraps */
#define CFQ_RQ2_WRAP	0x02 /* request 2 wraps */
	unsigned wrap = 0; /* bit mask: requests behind the disk head? */

	if (rq1 == NULL || rq1 == rq2)
		return rq2;
	if (rq2 == NULL)
		return rq1;

	if (rq_is_sync(rq1) != rq_is_sync(rq2))
		return rq_is_sync(rq1) ? rq1 : rq2;

	if ((rq1->cmd_flags ^ rq2->cmd_flags) & REQ_PRIO)
		return rq1->cmd_flags & REQ_PRIO ? rq1 : rq2;

	s1 = blk_rq_pos(rq1);
	s2 = blk_rq_pos(rq2);

	/*
	 * by definition, 1KiB is 2 sectors
	 */
	back_max = cfqd->cfq_back_max * 2;

	/*
	 * Strict one way elevator _except_ in the case where we allow
	 * short backward seeks which are biased as twice the cost of a
	 * similar forward seek.
	 */
	if (s1 >= last)
		d1 = s1 - last;
	else if (s1 + back_max >= last)
		d1 = (last - s1) * cfqd->cfq_back_penalty;
	else
		wrap |= CFQ_RQ1_WRAP;

	if (s2 >= last)
		d2 = s2 - last;
	else if (s2 + back_max >= last)
		d2 = (last - s2) * cfqd->cfq_back_penalty;
	else
		wrap |= CFQ_RQ2_WRAP;

	/* Found required data */

	/*
	 * By doing switch() on the bit mask "wrap" we avoid having to
	 * check two variables for all permutations: --> faster!
	 */
	switch (wrap) {
	case 0: /* common case for CFQ: rq1 and rq2 not wrapped */
		if (d1 < d2)
			return rq1;
		else if (d2 < d1)
			return rq2;
		else {
			if (s1 >= s2)
				return rq1;
			else
				return rq2;
		}

	case CFQ_RQ2_WRAP:
		return rq1;
	case CFQ_RQ1_WRAP:
		return rq2;
	case (CFQ_RQ1_WRAP|CFQ_RQ2_WRAP): /* both rqs wrapped */
	default:
		/*
		 * Since both rqs are wrapped,
		 * start with the one that's further behind head
		 * (--> only *one* back seek required),
		 * since back seek takes more time than forward.
		 */
		if (s1 <= s2)
			return rq1;
		else
			return rq2;
	}
}

/*
 * The below is leftmost cache rbtree addon
 */
static struct cfq_queue *cfq_rb_first(struct cfq_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(root->left, struct cfq_queue, rb_node);

	return NULL;
}

static struct cfq_group *cfq_rb_first_group(struct cfq_rb_root *root)
{
	if (!root->left)
		root->left = rb_first(&root->rb);

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

	return NULL;
}

static void rb_erase_init(struct rb_node *n, struct rb_root *root)
{
	rb_erase(n, root);
	RB_CLEAR_NODE(n);
}

static void cfq_rb_erase(struct rb_node *n, struct cfq_rb_root *root)
{
	if (root->left == n)
		root->left = NULL;
	rb_erase_init(n, &root->rb);
	--root->count;
}

/*
 * would be nice to take fifo expire time into account as well
 */
static struct request *
cfq_find_next_rq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
		  struct request *last)
{
	struct rb_node *rbnext = rb_next(&last->rb_node);
	struct rb_node *rbprev = rb_prev(&last->rb_node);
	struct request *next = NULL, *prev = NULL;

	BUG_ON(RB_EMPTY_NODE(&last->rb_node));

	if (rbprev)
		prev = rb_entry_rq(rbprev);

	if (rbnext)
		next = rb_entry_rq(rbnext);
	else {
		rbnext = rb_first(&cfqq->sort_list);
		if (rbnext && rbnext != &last->rb_node)
			next = rb_entry_rq(rbnext);
	}

	return cfq_choose_req(cfqd, next, prev, blk_rq_pos(last));
}

static unsigned long cfq_slice_offset(struct cfq_data *cfqd,
				      struct cfq_queue *cfqq)
{
	/*
	 * just an approximation, should be ok.
	 */
	return (cfqq->cfqg->nr_cfqq - 1) * (cfq_prio_slice(cfqd, 1, 0) -
		       cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio));
}

static inline s64
cfqg_key(struct cfq_rb_root *st, struct cfq_group *cfqg)
{
	return cfqg->vdisktime - st->min_vdisktime;
}

static void
__cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
{
	struct rb_node **node = &st->rb.rb_node;
	struct rb_node *parent = NULL;
	struct cfq_group *__cfqg;
	s64 key = cfqg_key(st, cfqg);
	int left = 1;

	while (*node != NULL) {
		parent = *node;
		__cfqg = rb_entry_cfqg(parent);

		if (key < cfqg_key(st, __cfqg))
			node = &parent->rb_left;
		else {
			node = &parent->rb_right;
			left = 0;
		}
	}

	if (left)
		st->left = &cfqg->rb_node;

	rb_link_node(&cfqg->rb_node, parent, node);
	rb_insert_color(&cfqg->rb_node, &st->rb);
}

static void
cfq_update_group_weight(struct cfq_group *cfqg)
{
	BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));
	if (cfqg->new_weight) {
		cfqg->weight = cfqg->new_weight;
		cfqg->new_weight = 0;
	}
}

static void
cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
{
	BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));

	cfq_update_group_weight(cfqg);
	__cfq_group_service_tree_add(st, cfqg);
	st->total_weight += cfqg->weight;
}

static void
cfq_group_notify_queue_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
{
	struct cfq_rb_root *st = &cfqd->grp_service_tree;
	struct cfq_group *__cfqg;
	struct rb_node *n;

	cfqg->nr_cfqq++;
	if (!RB_EMPTY_NODE(&cfqg->rb_node))
		return;

	/*
	 * Currently put the group at the end. Later implement something
	 * so that groups get lesser vtime based on their weights, so that
	 * if group does not loose all if it was not continuously backlogged.
	 */
	n = rb_last(&st->rb);
	if (n) {
		__cfqg = rb_entry_cfqg(n);
		cfqg->vdisktime = __cfqg->vdisktime + CFQ_IDLE_DELAY;
	} else
		cfqg->vdisktime = st->min_vdisktime;
	cfq_group_service_tree_add(st, cfqg);
}

static void
cfq_group_service_tree_del(struct cfq_rb_root *st, struct cfq_group *cfqg)
{
	st->total_weight -= cfqg->weight;
	if (!RB_EMPTY_NODE(&cfqg->rb_node))
		cfq_rb_erase(&cfqg->rb_node, st);
}

static void
cfq_group_notify_queue_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
{
	struct cfq_rb_root *st = &cfqd->grp_service_tree;

	BUG_ON(cfqg->nr_cfqq < 1);
	cfqg->nr_cfqq--;

	/* If there are other cfq queues under this group, don't delete it */
	if (cfqg->nr_cfqq)
		return;

	cfq_log_cfqg(cfqd, cfqg, "del_from_rr group");
	cfq_group_service_tree_del(st, cfqg);
	cfqg->saved_workload_slice = 0;
	cfqg_stats_update_dequeue(cfqg);
}

static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq,
						unsigned int *unaccounted_time)
{
	unsigned int slice_used;

	/*
	 * Queue got expired before even a single request completed or
	 * got expired immediately after first request completion.
	 */
	if (!cfqq->slice_start || cfqq->slice_start == jiffies) {
		/*
		 * Also charge the seek time incurred to the group, otherwise
		 * if there are mutiple queues in the group, each can dispatch
		 * a single request on seeky media and cause lots of seek time
		 * and group will never know it.
		 */
		slice_used = max_t(unsigned, (jiffies - cfqq->dispatch_start),
					1);
	} else {
		slice_used = jiffies - cfqq->slice_start;
		if (slice_used > cfqq->allocated_slice) {
			*unaccounted_time = slice_used - cfqq->allocated_slice;
			slice_used = cfqq->allocated_slice;
		}
		if (time_after(cfqq->slice_start, cfqq->dispatch_start))
			*unaccounted_time += cfqq->slice_start -
					cfqq->dispatch_start;
	}

	return slice_used;
}

static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
				struct cfq_queue *cfqq)
{
	struct cfq_rb_root *st = &cfqd->grp_service_tree;
	unsigned int used_sl, charge, unaccounted_sl = 0;
	int nr_sync = cfqg->nr_cfqq - cfqg_busy_async_queues(cfqd, cfqg)
			- cfqg->service_tree_idle.count;

	BUG_ON(nr_sync < 0);
	used_sl = charge = cfq_cfqq_slice_usage(cfqq, &unaccounted_sl);

	if (iops_mode(cfqd))
		charge = cfqq->slice_dispatch;
	else if (!cfq_cfqq_sync(cfqq) && !nr_sync)
		charge = cfqq->allocated_slice;

	/* Can't update vdisktime while group is on service tree */
	cfq_group_service_tree_del(st, cfqg);
	cfqg->vdisktime += cfq_scale_slice(charge, cfqg);
	/* If a new weight was requested, update now, off tree */
	cfq_group_service_tree_add(st, cfqg);

	/* This group is being expired. Save the context */
	if (time_after(cfqd->workload_expires, jiffies)) {
		cfqg->saved_workload_slice = cfqd->workload_expires
						- jiffies;
		cfqg->saved_workload = cfqd->serving_type;
		cfqg->saved_serving_prio = cfqd->serving_prio;
	} else
		cfqg->saved_workload_slice = 0;

	cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime,
					st->min_vdisktime);
	cfq_log_cfqq(cfqq->cfqd, cfqq,
		     "sl_used=%u disp=%u charge=%u iops=%u sect=%lu",
		     used_sl, cfqq->slice_dispatch, charge,
		     iops_mode(cfqd), cfqq->nr_sectors);
	cfqg_stats_update_timeslice_used(cfqg, used_sl, unaccounted_sl);
	cfqg_stats_set_start_empty_time(cfqg);
}

/**
 * cfq_init_cfqg_base - initialize base part of a cfq_group
 * @cfqg: cfq_group to initialize
 *
 * Initialize the base part which is used whether %CONFIG_CFQ_GROUP_IOSCHED
 * is enabled or not.
 */
static void cfq_init_cfqg_base(struct cfq_group *cfqg)
{
	struct cfq_rb_root *st;
	int i, j;

	for_each_cfqg_st(cfqg, i, j, st)
		*st = CFQ_RB_ROOT;
	RB_CLEAR_NODE(&cfqg->rb_node);

	cfqg->ttime.last_end_request = jiffies;
}

#ifdef CONFIG_CFQ_GROUP_IOSCHED
static void cfq_pd_init(struct blkcg_gq *blkg)
{
	struct cfq_group *cfqg = blkg_to_cfqg(blkg);

	cfq_init_cfqg_base(cfqg);
	cfqg->weight = blkg->blkcg->cfq_weight;
}

/*
 * Search for the cfq group current task belongs to. request_queue lock must
 * be held.
 */
static struct cfq_group *cfq_lookup_create_cfqg(struct cfq_data *cfqd,
						struct blkcg *blkcg)
{
	struct request_queue *q = cfqd->queue;
	struct cfq_group *cfqg = NULL;

	/* avoid lookup for the common case where there's no blkcg */
	if (blkcg == &blkcg_root) {
		cfqg = cfqd->root_group;
	} else {
		struct blkcg_gq *blkg;

		blkg = blkg_lookup_create(blkcg, q);
		if (!IS_ERR(blkg))
			cfqg = blkg_to_cfqg(blkg);
	}

	return cfqg;
}

static void cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg)
{
	/* Currently, all async queues are mapped to root group */
	if (!cfq_cfqq_sync(cfqq))
		cfqg = cfqq->cfqd->root_group;

	cfqq->cfqg = cfqg;
	/* cfqq reference on cfqg */
	cfqg_get(cfqg);
}

static u64 cfqg_prfill_weight_device(struct seq_file *sf,
				     struct blkg_policy_data *pd, int off)
{
	struct cfq_group *cfqg = pd_to_cfqg(pd);

	if (!cfqg->dev_weight)
		return 0;
	return __blkg_prfill_u64(sf, pd, cfqg->dev_weight);
}

static int cfqg_print_weight_device(struct cgroup *cgrp, struct cftype *cft,
				    struct seq_file *sf)
{
	blkcg_print_blkgs(sf, cgroup_to_blkcg(cgrp),
			  cfqg_prfill_weight_device, &blkcg_policy_cfq, 0,
			  false);
	return 0;
}

static int cfq_print_weight(struct cgroup *cgrp, struct cftype *cft,
			    struct seq_file *sf)
{
	seq_printf(sf, "%u\n", cgroup_to_blkcg(cgrp)->cfq_weight);
	return 0;
}

static int cfqg_set_weight_device(struct cgroup *cgrp, struct cftype *cft,
				  const char *buf)
{
	struct blkcg *blkcg = cgroup_to_blkcg(cgrp);
	struct blkg_conf_ctx ctx;
	struct cfq_group *cfqg;
	int ret;

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

	ret = -EINVAL;
	cfqg = blkg_to_cfqg(ctx.blkg);
	if (!ctx.v || (ctx.v >= CFQ_WEIGHT_MIN && ctx.v <= CFQ_WEIGHT_MAX)) {
		cfqg->dev_weight = ctx.v;
		cfqg->new_weight = cfqg->dev_weight ?: blkcg->cfq_weight;
		ret = 0;
	}

	blkg_conf_finish(&ctx);
	return ret;
}

static int cfq_set_weight(struct cgroup *cgrp, struct cftype *cft, u64 val)
{
	struct blkcg *blkcg = cgroup_to_blkcg(cgrp);
	struct blkcg_gq *blkg;
	struct hlist_node *n;

	if (val < CFQ_WEIGHT_MIN || val > CFQ_WEIGHT_MAX)
		return -EINVAL;

	spin_lock_irq(&blkcg->lock);
	blkcg->cfq_weight = (unsigned int)val;

	hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
		struct cfq_group *cfqg = blkg_to_cfqg(blkg);

		if (cfqg && !cfqg->dev_weight)
			cfqg->new_weight = blkcg->cfq_weight;
	}

	spin_unlock_irq(&blkcg->lock);
	return 0;
}

static int cfqg_print_stat(struct cgroup *cgrp, struct cftype *cft,
			   struct seq_file *sf)
{
	struct blkcg *blkcg = cgroup_to_blkcg(cgrp);

	blkcg_print_blkgs(sf, blkcg, blkg_prfill_stat, &blkcg_policy_cfq,
			  cft->private, false);
	return 0;
}

static int cfqg_print_rwstat(struct cgroup *cgrp, struct cftype *cft,
			     struct seq_file *sf)
{
	struct blkcg *blkcg = cgroup_to_blkcg(cgrp);

	blkcg_print_blkgs(sf, blkcg, blkg_prfill_rwstat, &blkcg_policy_cfq,
			  cft->private, true);
	return 0;
}

#ifdef CONFIG_DEBUG_BLK_CGROUP
static u64 cfqg_prfill_avg_queue_size(struct seq_file *sf,
				      struct blkg_policy_data *pd, int off)
{
	struct cfq_group *cfqg = pd_to_cfqg(pd);
	u64 samples = blkg_stat_read(&cfqg->stats.avg_queue_size_samples);
	u64 v = 0;

	if (samples) {
		v = blkg_stat_read(&cfqg->stats.avg_queue_size_sum);
		do_div(v, samples);
	}
	__blkg_prfill_u64(sf, pd, v);
	return 0;
}

/* print avg_queue_size */
static int cfqg_print_avg_queue_size(struct cgroup *cgrp, struct cftype *cft,
				     struct seq_file *sf)
{
	struct blkcg *blkcg = cgroup_to_blkcg(cgrp);

	blkcg_print_blkgs(sf, blkcg, cfqg_prfill_avg_queue_size,
			  &blkcg_policy_cfq, 0, false);
	return 0;
}
#endif	/* CONFIG_DEBUG_BLK_CGROUP */

static struct cftype cfq_blkcg_files[] = {
	{
		.name = "weight_device",
		.read_seq_string = cfqg_print_weight_device,
		.write_string = cfqg_set_weight_device,
		.max_write_len = 256,
	},
	{
		.name = "weight",
		.read_seq_string = cfq_print_weight,
		.write_u64 = cfq_set_weight,
	},
	{
		.name = "time",
		.private = offsetof(struct cfq_group, stats.time),
		.read_seq_string = cfqg_print_stat,
	},
	{
		.name = "sectors",
		.private = offsetof(struct cfq_group, stats.sectors),
		.read_seq_string = cfqg_print_stat,
	},
	{
		.name = "io_service_bytes",
		.private = offsetof(struct cfq_group, stats.service_bytes),
		.read_seq_string = cfqg_print_rwstat,
	},
	{
		.name = "io_serviced",
		.private = offsetof(struct cfq_group, stats.serviced),
		.read_seq_string = cfqg_print_rwstat,
	},
	{
		.name = "io_service_time",
		.private = offsetof(struct cfq_group, stats.service_time),
		.read_seq_string = cfqg_print_rwstat,
	},
	{
		.name = "io_wait_time",
		.private = offsetof(struct cfq_group, stats.wait_time),
		.read_seq_string = cfqg_print_rwstat,
	},
	{
		.name = "io_merged",
		.private = offsetof(struct cfq_group, stats.merged),
		.read_seq_string = cfqg_print_rwstat,
	},
	{
		.name = "io_queued",
		.private = offsetof(struct cfq_group, stats.queued),
		.read_seq_string = cfqg_print_rwstat,
	},
#ifdef CONFIG_DEBUG_BLK_CGROUP
	{
		.name = "avg_queue_size",
		.read_seq_string = cfqg_print_avg_queue_size,
	},
	{
		.name = "group_wait_time",
		.private = offsetof(struct cfq_group, stats.group_wait_time),
		.read_seq_string = cfqg_print_stat,
	},
	{
		.name = "idle_time",
		.private = offsetof(struct cfq_group, stats.idle_time),
		.read_seq_string = cfqg_print_stat,
	},
	{
		.name = "empty_time",
		.private = offsetof(struct cfq_group, stats.empty_time),
		.read_seq_string = cfqg_print_stat,
	},
	{
		.name = "dequeue",
		.private = offsetof(struct cfq_group, stats.dequeue),
		.read_seq_string = cfqg_print_stat,
	},
	{
		.name = "unaccounted_time",
		.private = offsetof(struct cfq_group, stats.unaccounted_time),
		.read_seq_string = cfqg_print_stat,
	},
#endif	/* CONFIG_DEBUG_BLK_CGROUP */
	{ }	/* terminate */
};
#else /* GROUP_IOSCHED */
static struct cfq_group *cfq_lookup_create_cfqg(struct cfq_data *cfqd,
						struct blkcg *blkcg)
{
	return cfqd->root_group;
}

static inline void
cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg) {
	cfqq->cfqg = cfqg;
}

#endif /* GROUP_IOSCHED */

/*
 * The cfqd->service_trees holds all pending cfq_queue's that have
 * requests waiting to be processed. It is sorted in the order that
 * we will service the queues.
 */
static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
				 bool add_front)
{
	struct rb_node **p, *parent;
	struct cfq_queue *__cfqq;
	unsigned long rb_key;
	struct cfq_rb_root *service_tree;
	int left;
	int new_cfqq = 1;

	service_tree = service_tree_for(cfqq->cfqg, cfqq_prio(cfqq),
						cfqq_type(cfqq));
	if (cfq_class_idle(cfqq)) {
		rb_key = CFQ_IDLE_DELAY;
		parent = rb_last(&service_tree->rb);
		if (parent && parent != &cfqq->rb_node) {
			__cfqq = rb_entry(parent, struct cfq_queue, rb_node);
			rb_key += __cfqq->rb_key;
		} else
			rb_key += jiffies;
	} else if (!add_front) {
		/*
		 * Get our rb key offset. Subtract any residual slice
		 * value carried from last service. A negative resid
		 * count indicates slice overrun, and this should position
		 * the next service time further away in the tree.
		 */
		rb_key = cfq_slice_offset(cfqd, cfqq) + jiffies;
		rb_key -= cfqq->slice_resid;
		cfqq->slice_resid = 0;
	} else {
		rb_key = -HZ;
		__cfqq = cfq_rb_first(service_tree);
		rb_key += __cfqq ? __cfqq->rb_key : jiffies;
	}

	if (!RB_EMPTY_NODE(&cfqq->rb_node)) {
		new_cfqq = 0;
		/*
		 * same position, nothing more to do
		 */
		if (rb_key == cfqq->rb_key &&
		    cfqq->service_tree == service_tree)
			return;

		cfq_rb_erase(&cfqq->rb_node, cfqq->service_tree);
		cfqq->service_tree = NULL;
	}

	left = 1;
	parent = NULL;
	cfqq->service_tree = service_tree;
	p = &service_tree->rb.rb_node;
	while (*p) {
		struct rb_node **n;

		parent = *p;
		__cfqq = rb_entry(parent, struct cfq_queue, rb_node);