/*
 *  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/sched/clock.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
#include <linux/ktime.h>
#include <linux/rbtree.h>
#include <linux/ioprio.h>
#include <linux/blktrace_api.h>
#include <linux/blk-cgroup.h>
#include "blk.h"
#include "blk-wbt.h"

/*
 * tunables
 */
/* max queue in one round of service */
static const int cfq_quantum = 8;
static const u64 cfq_fifo_expire[2] = { NSEC_PER_SEC / 4, NSEC_PER_SEC / 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 u64 cfq_slice_sync = NSEC_PER_SEC / 10;
static u64 cfq_slice_async = NSEC_PER_SEC / 25;
static const int cfq_slice_async_rq = 2;
static u64 cfq_slice_idle = NSEC_PER_SEC / 125;
static u64 cfq_group_idle = NSEC_PER_SEC / 125;
static const u64 cfq_target_latency = (u64)NSEC_PER_SEC * 3/10; /* 300 ms */
static const int cfq_hist_divisor = 4;

/*
 * offset from end of queue service tree for idle class
 */
#define CFQ_IDLE_DELAY          (NSEC_PER_SEC / 5)
/* offset from end of group service tree under time slice mode */
#define CFQ_SLICE_MODE_GROUP_DELAY (NSEC_PER_SEC / 5)
/* offset from end of group service under IOPS mode */
#define CFQ_IOPS_MODE_GROUP_DELAY (HZ / 5)

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

#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)

/* blkio-related constants */
#define CFQ_WEIGHT_LEGACY_MIN   10
#define CFQ_WEIGHT_LEGACY_DFL   500
#define CFQ_WEIGHT_LEGACY_MAX   1000

struct cfq_ttime {
        u64 last_end_request;

        u64 ttime_total;
        u64 ttime_mean;
        unsigned long ttime_samples;
};

/*
 * 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_cached rb;
        struct rb_node *rb_rightmost;
        unsigned count;
        u64 min_vdisktime;
        struct cfq_ttime ttime;
};
#define CFQ_RB_ROOT     (struct cfq_rb_root) { .rb = RB_ROOT_CACHED, \
                        .rb_rightmost = NULL,                        \
                        .ttime = {.last_end_request = ktime_get_ns(),},}

/*
 * 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 */
        u64 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. */
        u64 dispatch_start;
        u64 allocated_slice;
        u64 slice_dispatch;
        /* time when first request from queue completed and slice started. */
        u64 slice_start;
        u64 slice_end;
        s64 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, org_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_class_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
        /* 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 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 */
        u64                             start_group_wait_time;
        u64                             start_idle_time;
        u64                             start_empty_time;
        uint16_t                        flags;
#endif  /* CONFIG_DEBUG_BLK_CGROUP */
#endif  /* CONFIG_CFQ_GROUP_IOSCHED */
};

/* Per-cgroup data */
struct cfq_group_data {
        /* must be the first member */
        struct blkcg_policy_data cpd;

        unsigned int weight;
        unsigned int leaf_weight;
};

/* 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;

        /*
         * The number of active cfqgs and sum of their weights under this
         * cfqg.  This covers this cfqg's leaf_weight and all children's
         * weights, but does not cover weights of further descendants.
         *
         * If a cfqg is on the service tree, it's active.  An active cfqg
         * also activates its parent and contributes to the children_weight
         * of the parent.
         */
        int nr_active;
        unsigned int children_weight;

        /*
         * vfraction is the fraction of vdisktime that the tasks in this
         * cfqg are entitled to.  This is determined by compounding the
         * ratios walking up from this cfqg to the root.
         *
         * It is in fixed point w/ CFQ_SERVICE_SHIFT and the sum of all
         * vfractions on a service tree is approximately 1.  The sum may
         * deviate a bit due to rounding errors and fluctuations caused by
         * cfqgs entering and leaving the service tree.
         */
        unsigned int vfraction;

        /*
         * There are two weights - (internal) weight is the weight of this
         * cfqg against the sibling cfqgs.  leaf_weight is the wight of
         * this cfqg against the child cfqgs.  For the root cfqg, both
         * weights are kept in sync for backward compatibility.
         */
        unsigned int weight;
        unsigned int new_weight;
        unsigned int dev_weight;

        unsigned int leaf_weight;
        unsigned int new_leaf_weight;
        unsigned int dev_leaf_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;

        u64 saved_wl_slice;
        enum wl_type_t saved_wl_type;
        enum wl_class_t saved_wl_class;

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

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

};

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_serial_nr; /* the current blkcg serial */
#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_class_t serving_wl_class;
        enum wl_type_t serving_wl_type;
        u64 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 hrtimer idle_slice_timer;
        struct work_struct unplug_work;

        struct cfq_queue *active_queue;
        struct cfq_io_cq *active_cic;

        sector_t last_position;

        /*
         * tunables, see top of file
         */
        unsigned int cfq_quantum;
        unsigned int cfq_back_penalty;
        unsigned int cfq_back_max;
        unsigned int cfq_slice_async_rq;
        unsigned int cfq_latency;
        u64 cfq_fifo_expire[2];
        u64 cfq_slice[2];
        u64 cfq_slice_idle;
        u64 cfq_group_idle;
        u64 cfq_target_latency;

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

        u64 last_delayed_sync;
};

static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd);
static void cfq_put_queue(struct cfq_queue *cfqq);

static struct cfq_rb_root *st_for(struct cfq_group *cfqg,
                                            enum wl_class_t class,
                                            enum wl_type_t type)
{
        if (!cfqg)
                return NULL;

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

        return &cfqg->service_trees[class][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

#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)
{
        u64 now;

        if (!cfqg_stats_waiting(stats))
                return;

        now = ktime_get_ns();
        if (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 = ktime_get_ns();
        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)
{
        u64 now;

        if (!cfqg_stats_empty(stats))
                return;

        now = ktime_get_ns();
        if (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_total(&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 = ktime_get_ns();
        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)) {
                u64 now = ktime_get_ns();

                if (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 = ktime_get_ns();
        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_total(&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 inline struct cfq_group *pd_to_cfqg(struct blkg_policy_data *pd)
{
        return pd ? container_of(pd, struct cfq_group, pd) : NULL;
}

static struct cfq_group_data
*cpd_to_cfqgd(struct blkcg_policy_data *cpd)
{
        return cpd ? container_of(cpd, struct cfq_group_data, cpd) : NULL;
}

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

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 struct cfq_group_data *blkcg_to_cfqgd(struct blkcg *blkcg)
{
        return cpd_to_cfqgd(blkcg_to_cpd(blkcg, &blkcg_policy_cfq));
}

static inline struct cfq_group *cfqg_parent(struct cfq_group *cfqg)
{
        struct blkcg_gq *pblkg = cfqg_to_blkg(cfqg)->parent;

        return pblkg ? blkg_to_cfqg(pblkg) : NULL;
}

static inline bool cfqg_is_descendant(struct cfq_group *cfqg,
                                      struct cfq_group *ancestor)
{
        return cgroup_is_descendant(cfqg_to_blkg(cfqg)->blkcg->css.cgroup,
                                    cfqg_to_blkg(ancestor)->blkcg->css.cgroup);
}

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 {                    \
        blk_add_cgroup_trace_msg((cfqd)->queue,                         \
                        cfqg_to_blkg((cfqq)->cfqg)->blkcg,              \
                        "cfq%d%c%c " fmt, (cfqq)->pid,                  \
                        cfq_cfqq_sync((cfqq)) ? 'S' : 'A',              \
                        cfqq_type((cfqq)) == SYNC_NOIDLE_WORKLOAD ? 'N' : ' ',\
                          ##args);                                      \
} while (0)

#define cfq_log_cfqg(cfqd, cfqg, fmt, args...)  do {                    \
        blk_add_cgroup_trace_msg((cfqd)->queue,                         \
                        cfqg_to_blkg(cfqg)->blkcg, fmt, ##args);        \
} while (0)

static inline void cfqg_stats_update_io_add(struct cfq_group *cfqg,
                                            struct cfq_group *curr_cfqg,
                                            unsigned int op)
{
        blkg_rwstat_add(&cfqg->stats.queued, op, 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,
                        uint64_t 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,
                                               unsigned int op)
{
        blkg_rwstat_add(&cfqg->stats.queued, op, -1);
}

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

static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
                                                u64 start_time_ns,
                                                u64 io_start_time_ns,
                                                unsigned int op)
{
        struct cfqg_stats *stats = &cfqg->stats;
        u64 now = ktime_get_ns();

        if (now > io_start_time_ns)
                blkg_rwstat_add(&stats->service_time, op,
                                now - io_start_time_ns);
        if (io_start_time_ns > start_time_ns)
                blkg_rwstat_add(&stats->wait_time, op,
                                io_start_time_ns - start_time_ns);
}

/* @stats = 0 */
static void cfqg_stats_reset(struct cfqg_stats *stats)
{
        /* queued stats shouldn't be cleared */
        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
}

/* @to += @from */
static void cfqg_stats_add_aux(struct cfqg_stats *to, struct cfqg_stats *from)
{
        /* queued stats shouldn't be cleared */
        blkg_rwstat_add_aux(&to->merged, &from->merged);
        blkg_rwstat_add_aux(&to->service_time, &from->service_time);
        blkg_rwstat_add_aux(&to->wait_time, &from->wait_time);
        blkg_stat_add_aux(&from->time, &from->time);
#ifdef CONFIG_DEBUG_BLK_CGROUP
        blkg_stat_add_aux(&to->unaccounted_time, &from->unaccounted_time);
        blkg_stat_add_aux(&to->avg_queue_size_sum, &from->avg_queue_size_sum);
        blkg_stat_add_aux(&to->avg_queue_size_samples, &from->avg_queue_size_samples);
        blkg_stat_add_aux(&to->dequeue, &from->dequeue);
        blkg_stat_add_aux(&to->group_wait_time, &from->group_wait_time);
        blkg_stat_add_aux(&to->idle_time, &from->idle_time);
        blkg_stat_add_aux(&to->empty_time, &from->empty_time);
#endif
}

/*
 * Transfer @cfqg's stats to its parent's aux counts so that the ancestors'
 * recursive stats can still account for the amount used by this cfqg after
 * it's gone.
 */
static void cfqg_stats_xfer_dead(struct cfq_group *cfqg)
{
        struct cfq_group *parent = cfqg_parent(cfqg);

        lockdep_assert_held(cfqg_to_blkg(cfqg)->q->queue_lock);

        if (unlikely(!parent))
                return;

        cfqg_stats_add_aux(&parent->stats, &cfqg->stats);
        cfqg_stats_reset(&cfqg->stats);
}

#else   /* CONFIG_CFQ_GROUP_IOSCHED */

static inline struct cfq_group *cfqg_parent(struct cfq_group *cfqg) { return NULL; }
static inline bool cfqg_is_descendant(struct cfq_group *cfqg,
                                      struct cfq_group *ancestor)
{
        return true;
}
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%c%c " fmt, (cfqq)->pid, \
                        cfq_cfqq_sync((cfqq)) ? 'S' : 'A',              \
                        cfqq_type((cfqq)) == SYNC_NOIDLE_WORKLOAD ? 'N' : ' ',\
                                ##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, unsigned int op) { }
static inline void cfqg_stats_update_timeslice_used(struct cfq_group *cfqg,
                        uint64_t time, unsigned long unaccounted_time) { }
static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg,
                        unsigned int op) { }
static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg,
                        unsigned int op) { }
static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
                                                u64 start_time_ns,
                                                u64 io_start_time_ns,
                                                unsigned int op) { }

#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)
{
        u64 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_class_t cfqq_class(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_class_t wl_class,
                                        struct cfq_data *cfqd,
                                        struct cfq_group *cfqg)
{
        if (wl_class == IDLE_WORKLOAD)
                return cfqg->service_tree_idle.count;

        return cfqg->service_trees[wl_class][ASYNC_WORKLOAD].count +
                cfqg->service_trees[wl_class][SYNC_NOIDLE_WORKLOAD].count +
                cfqg->service_trees[wl_class][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);

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;
}

/*
 * 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->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 u64 cfq_prio_slice(struct cfq_data *cfqd, bool sync,
                                 unsigned short prio)
{
        u64 base_slice = cfqd->cfq_slice[sync];
        u64 slice = div_u64(base_slice, CFQ_SLICE_SCALE);

        WARN_ON(prio >= IOPRIO_BE_NR);

        return base_slice + (slice * (4 - prio));
}

static inline u64
cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
        return cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio);
}

/**
 * cfqg_scale_charge - scale disk time charge according to cfqg weight
 * @charge: disk time being charged
 * @vfraction: vfraction of the cfqg, fixed point w/ CFQ_SERVICE_SHIFT
 *
 * Scale @charge according to @vfraction, which is in range (0, 1].  The
 * scaling is inversely proportional.
 *
 * scaled = charge / vfraction
 *
 * The result is also in fixed point w/ CFQ_SERVICE_SHIFT.
 */
static inline u64 cfqg_scale_charge(u64 charge,
                                    unsigned int vfraction)
{
        u64 c = charge << CFQ_SERVICE_SHIFT;    /* make it fixed point */

        /* charge / vfraction */
        c <<= CFQ_SERVICE_SHIFT;
        return div_u64(c, vfraction);
}

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 void update_min_vdisktime(struct cfq_rb_root *st)
{
        if (!RB_EMPTY_ROOT(&st->rb.rb_root)) {
                struct cfq_group *cfqg = rb_entry_cfqg(st->rb.rb_leftmost);

                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 u64
cfq_group_slice(struct cfq_data *cfqd, struct cfq_group *cfqg)
{
        return cfqd->cfq_target_latency * cfqg->vfraction >> CFQ_SERVICE_SHIFT;
}

static inline u64
cfq_scaled_cfqq_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
        u64 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));
                u64 sync_slice = cfqd->cfq_slice[1];
                u64 expect_latency = sync_slice * iq;
                u64 group_slice = cfq_group_slice(cfqd, cfqq->cfqg);

                if (expect_latency > group_slice) {
                        u64 base_low_slice = 2 * cfqd->cfq_slice_idle;
                        u64 low_slice;

                        /* scale low_slice according to IO priority
                         * and sync vs async */
                        low_slice = div64_u64(base_low_slice*slice, sync_slice);
                        low_slice = min(slice, low_slice);
                        /* the adapted slice value is scaled to fit all iqs
                         * into the target latency */
                        slice = div64_u64(slice*group_slice, expect_latency);
                        slice = max(slice, low_slice);
                }
        }
        return slice;
}

static inline void
cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
        u64 slice = cfq_scaled_cfqq_slice(cfqd, cfqq);
        u64 now = ktime_get_ns();

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

/*
 * 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 (ktime_get_ns() < 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;
        }
}

static struct cfq_queue *cfq_rb_first(struct cfq_rb_root *root)
{
        /* Service tree is empty */
        if (!root->count)
                return NULL;

        return rb_entry(rb_first_cached(&root->rb), struct cfq_queue, rb_node);
}

static struct cfq_group *cfq_rb_first_group(struct cfq_rb_root *root)
{
        return rb_entry_cfqg(rb_first_cached(&root->rb));
}

static void cfq_rb_erase(struct rb_node *n, struct cfq_rb_root *root)
{
        if (root->rb_rightmost == n)
                root->rb_rightmost = rb_prev(n);

        rb_erase_cached(n, &root->rb);
        RB_CLEAR_NODE(n);

        --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 u64 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_root.rb_node;
        struct rb_node *parent = NULL;
        struct cfq_group *__cfqg;
        s64 key = cfqg_key(st, cfqg);
        bool leftmost = true, rightmost = true;

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

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

        if (rightmost)
                st->rb_rightmost = &cfqg->rb_node;

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

/*
 * This has to be called only on activation of cfqg
 */
static void
cfq_update_group_weight(struct cfq_group *cfqg)
{
        if (cfqg->new_weight) {
                cfqg->weight = cfqg->new_weight;
                cfqg->new_weight = 0;
        }
}

static void
cfq_update_group_leaf_weight(struct cfq_group *cfqg)
{
        BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));

        if (cfqg->new_leaf_weight) {
                cfqg->leaf_weight = cfqg->new_leaf_weight;
                cfqg->new_leaf_weight = 0;
        }
}

static void
cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
{
        unsigned int vfr = 1 << CFQ_SERVICE_SHIFT;      /* start with 1 */
        struct cfq_group *pos = cfqg;
        struct cfq_group *parent;
        bool propagate;

        /* add to the service tree */
        BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));

        /*
         * Update leaf_weight.  We cannot update weight at this point
         * because cfqg might already have been activated and is
         * contributing its current weight to the parent's child_weight.
         */
        cfq_update_group_leaf_weight(cfqg);
        __cfq_group_service_tree_add(st, cfqg);

        /*
         * Activate @cfqg and calculate the portion of vfraction @cfqg is
         * entitled to.  vfraction is calculated by walking the tree
         * towards the root calculating the fraction it has at each level.
         * The compounded ratio is how much vfraction @cfqg owns.
         *
         * Start with the proportion tasks in this cfqg has against active
         * children cfqgs - its leaf_weight against children_weight.
         */
        propagate = !pos->nr_active++;
        pos->children_weight += pos->leaf_weight;
        vfr = vfr * pos->leaf_weight / pos->children_weight;

        /*
         * Compound ->weight walking up the tree.  Both activation and
         * vfraction calculation are done in the same loop.  Propagation
         * stops once an already activated node is met.  vfraction
         * calculation should always continue to the root.
         */
        while ((parent = cfqg_parent(pos))) {
                if (propagate) {
                        cfq_update_group_weight(pos);
                        propagate = !parent->nr_active++;
                        parent->children_weight += pos->weight;
                }
                vfr = vfr * pos->weight / parent->children_weight;
                pos = parent;
        }

        cfqg->vfraction = max_t(unsigned, vfr, 1);
}

static inline u64 cfq_get_cfqg_vdisktime_delay(struct cfq_data *cfqd)
{
        if (!iops_mode(cfqd))
                return CFQ_SLICE_MODE_GROUP_DELAY;
        else
                return CFQ_IOPS_MODE_GROUP_DELAY;
}

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 = st->rb_rightmost;
        if (n) {
                __cfqg = rb_entry_cfqg(n);
                cfqg->vdisktime = __cfqg->vdisktime +
                        cfq_get_cfqg_vdisktime_delay(cfqd);
        } 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)
{
        struct cfq_group *pos = cfqg;
        bool propagate;

        /*
         * Undo activation from cfq_group_service_tree_add().  Deactivate
         * @cfqg and propagate deactivation upwards.
         */
        propagate = !--pos->nr_active;
        pos->children_weight -= pos->leaf_weight;

        while (propagate) {
                struct cfq_group *parent = cfqg_parent(pos);

                /* @pos has 0 nr_active at this point */
                WARN_ON_ONCE(pos->children_weight);
                pos->vfraction = 0;

                if (!parent)
                        break;

                propagate = !--parent->nr_active;
                parent->children_weight -= pos->weight;
                pos = parent;
        }

        /* remove from the service tree */
        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_wl_slice = 0;
        cfqg_stats_update_dequeue(cfqg);
}

static inline u64 cfq_cfqq_slice_usage(struct cfq_queue *cfqq,
                                       u64 *unaccounted_time)
{
        u64 slice_used;
        u64 now = ktime_get_ns();

        /*
         * Queue got expired before even a single request completed or
         * got expired immediately after first request completion.
         */
        if (!cfqq->slice_start || cfqq->slice_start == now) {
                /*
                 * 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(u64, (now - cfqq->dispatch_start),
                                        jiffies_to_nsecs(1));
        } else {
                slice_used = now - cfqq->slice_start;
                if (slice_used > cfqq->allocated_slice) {
                        *unaccounted_time = slice_used - cfqq->allocated_slice;
                        slice_used = cfqq->allocated_slice;
                }
                if (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;
        u64 used_sl, charge, unaccounted_sl = 0;
        int nr_sync = cfqg->nr_cfqq - cfqg_busy_async_queues(cfqd, cfqg)
                        - cfqg->service_tree_idle.count;
        unsigned int vfr;
        u64 now = ktime_get_ns();

        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 on service tree and cfqg->vfraction
         * is valid only while on it.  Cache vfr, leave the service tree,
         * update vdisktime and go back on.  The re-addition to the tree
         * will also update the weights as necessary.
         */
        vfr = cfqg->vfraction;
        cfq_group_service_tree_del(st, cfqg);
        cfqg->vdisktime += cfqg_scale_charge(charge, vfr);
        cfq_group_service_tree_add(st, cfqg);

        /* This group is being expired. Save the context */
        if (cfqd->workload_expires > now) {
                cfqg->saved_wl_slice = cfqd->workload_expires - now;
                cfqg->saved_wl_type = cfqd->serving_wl_type;
                cfqg->saved_wl_class = cfqd->serving_wl_class;
        } else
                cfqg->saved_wl_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=%llu disp=%llu charge=%llu 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 = ktime_get_ns();
}

#ifdef CONFIG_CFQ_GROUP_IOSCHED
static int __cfq_set_weight(struct cgroup_subsys_state *css, u64 val,
                            bool on_dfl, bool reset_dev, bool is_leaf_weight);

static void cfqg_stats_exit(struct cfqg_stats *stats)
{
        blkg_rwstat_exit(&stats->merged);
        blkg_rwstat_exit(&stats->service_time);
        blkg_rwstat_exit(&stats->wait_time);
        blkg_rwstat_exit(&stats->queued);
        blkg_stat_exit(&stats->time);
#ifdef CONFIG_DEBUG_BLK_CGROUP
        blkg_stat_exit(&stats->unaccounted_time);
        blkg_stat_exit(&stats->avg_queue_size_sum);
        blkg_stat_exit(&stats->avg_queue_size_samples);
        blkg_stat_exit(&stats->dequeue);
        blkg_stat_exit(&stats->group_wait_time);
        blkg_stat_exit(&stats->idle_time);
        blkg_stat_exit(&stats->empty_time);
#endif
}

static int cfqg_stats_init(struct cfqg_stats *stats, gfp_t gfp)
{
        if (blkg_rwstat_init(&stats->merged, gfp) ||
            blkg_rwstat_init(&stats->service_time, gfp) ||
            blkg_rwstat_init(&stats->wait_time, gfp) ||
            blkg_rwstat_init(&stats->queued, gfp) ||
            blkg_stat_init(&stats->time, gfp))
                goto err;

#ifdef CONFIG_DEBUG_BLK_CGROUP
        if (blkg_stat_init(&stats->unaccounted_time, gfp) ||
            blkg_stat_init(&stats->avg_queue_size_sum, gfp) ||
            blkg_stat_init(&stats->avg_queue_size_samples, gfp) ||
            blkg_stat_init(&stats->dequeue, gfp) ||
            blkg_stat_init(&stats->group_wait_time, gfp) ||
            blkg_stat_init(&stats->idle_time, gfp) ||
            blkg_stat_init(&stats->empty_time, gfp))
                goto err;
#endif
        return 0;
err:
        cfqg_stats_exit(stats);
        return -ENOMEM;
}

static struct blkcg_policy_data *cfq_cpd_alloc(gfp_t gfp)
{
        struct cfq_group_data *cgd;

        cgd = kzalloc(sizeof(*cgd), gfp);
        if (!cgd)
                return NULL;
        return &cgd->cpd;
}

static void cfq_cpd_init(struct blkcg_policy_data *cpd)
{
        struct cfq_group_data *cgd = cpd_to_cfqgd(cpd);
        unsigned int weight = cgroup_subsys_on_dfl(io_cgrp_subsys) ?
                              CGROUP_WEIGHT_DFL : CFQ_WEIGHT_LEGACY_DFL;

        if (cpd_to_blkcg(cpd) == &blkcg_root)
                weight *= 2;

        cgd->weight = weight;
        cgd->leaf_weight = weight;
}

static void cfq_cpd_free(struct blkcg_policy_data *cpd)
{
        kfree(cpd_to_cfqgd(cpd));
}

static void cfq_cpd_bind(struct blkcg_policy_data *cpd)
{
        struct blkcg *blkcg = cpd_to_blkcg(cpd);
        bool on_dfl = cgroup_subsys_on_dfl(io_cgrp_subsys);
        unsigned int weight = on_dfl ? CGROUP_WEIGHT_DFL : CFQ_WEIGHT_LEGACY_DFL;

        if (blkcg == &blkcg_root)
                weight *= 2;

        WARN_ON_ONCE(__cfq_set_weight(&blkcg->css, weight, on_dfl, true, false));
        WARN_ON_ONCE(__cfq_set_weight(&blkcg->css, weight, on_dfl, true, true));
}

static struct blkg_policy_data *cfq_pd_alloc(gfp_t gfp, int node)
{
        struct cfq_group *cfqg;

        cfqg = kzalloc_node(sizeof(*cfqg), gfp, node);
        if (!cfqg)
                return NULL;

        cfq_init_cfqg_base(cfqg);
        if (cfqg_stats_init(&cfqg->stats, gfp)) {
                kfree(cfqg);
                return NULL;
        }

        return &cfqg->pd;
}

static void cfq_pd_init(struct blkg_policy_data *pd)
{
        struct cfq_group *cfqg = pd_to_cfqg(pd);
        struct cfq_group_data *cgd = blkcg_to_cfqgd(pd->blkg->blkcg);

        cfqg->weight = cgd->weight;
        cfqg->leaf_weight = cgd->leaf_weight;
}

static void cfq_pd_offline(struct blkg_policy_data *pd)
{
        struct cfq_group *cfqg = pd_to_cfqg(pd);
        int i;

        for (i = 0; i < IOPRIO_BE_NR; i++) {
                if (cfqg->async_cfqq[0][i])
                        cfq_put_queue(cfqg->async_cfqq[0][i]);
                if (cfqg->async_cfqq[1][i])
                        cfq_put_queue(cfqg->async_cfqq[1][i]);
        }

        if (cfqg->async_idle_cfqq)
                cfq_put_queue(cfqg->async_idle_cfqq);

        /*
         * @blkg is going offline and will be ignored by
         * blkg_[rw]stat_recursive_sum().  Transfer stats to the parent so
         * that they don't get lost.  If IOs complete after this point, the
         * stats for them will be lost.  Oh well...
         */
        cfqg_stats_xfer_dead(cfqg);
}

static void cfq_pd_free(struct blkg_policy_data *pd)
{
        struct cfq_group *cfqg = pd_to_cfqg(pd);

        cfqg_stats_exit(&cfqg->stats);
        return kfree(cfqg);
}

static void cfq_pd_reset_stats(struct blkg_policy_data *pd)
{
        struct cfq_group *cfqg = pd_to_cfqg(pd);

        cfqg_stats_reset(&cfqg->stats);
}

static struct cfq_group *cfq_lookup_cfqg(struct cfq_data *cfqd,
                                         struct blkcg *blkcg)
{
        struct blkcg_gq *blkg;

        blkg = blkg_lookup(blkcg, cfqd->queue);
        if (likely(blkg))
                return blkg_to_cfqg(blkg);
        return NULL;
}

static void cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg)
{
        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 seq_file *sf, void *v)
{
        blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
                          cfqg_prfill_weight_device, &blkcg_policy_cfq,
                          0, false);
        return 0;
}

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

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

static int cfqg_print_leaf_weight_device(struct seq_file *sf, void *v)
{
        blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
                          cfqg_prfill_leaf_weight_device, &blkcg_policy_cfq,
                          0, false);
        return 0;
}

static int cfq_print_weight(struct seq_file *sf, void *v)
{
        struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
        struct cfq_group_data *cgd = blkcg_to_cfqgd(blkcg);
        unsigned int val = 0;

        if (cgd)
                val = cgd->weight;

        seq_printf(sf, "%u\n", val);
        return 0;
}

static int cfq_print_leaf_weight(struct seq_file *sf, void *v)
{
        struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
        struct cfq_group_data *cgd = blkcg_to_cfqgd(blkcg);
        unsigned int val = 0;

        if (cgd)
                val = cgd->leaf_weight;

        seq_printf(sf, "%u\n", val);
        return 0;
}

static ssize_t __cfqg_set_weight_device(struct kernfs_open_file *of,
                                        char *buf, size_t nbytes, loff_t off,
                                        bool on_dfl, bool is_leaf_weight)
{
        unsigned int min = on_dfl ? CGROUP_WEIGHT_MIN : CFQ_WEIGHT_LEGACY_MIN;
        unsigned int max = on_dfl ? CGROUP_WEIGHT_MAX : CFQ_WEIGHT_LEGACY_MAX;
        struct blkcg *blkcg = css_to_blkcg(of_css(of));
        struct blkg_conf_ctx ctx;
        struct cfq_group *cfqg;
        struct cfq_group_data *cfqgd;
        int ret;
        u64 v;

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

        if (sscanf(ctx.body, "%llu", &v) == 1) {
                /* require "default" on dfl */
                ret = -ERANGE;
                if (!v && on_dfl)
                        goto out_finish;
        } else if (!strcmp(strim(ctx.body), "default")) {
                v = 0;
        } else {
                ret = -EINVAL;
                goto out_finish;
        }

        cfqg = blkg_to_cfqg(ctx.blkg);
        cfqgd = blkcg_to_cfqgd(blkcg);

        ret = -ERANGE;
        if (!v || (v >= min && v <= max)) {
                if (!is_leaf_weight) {
                        cfqg->dev_weight = v;
                        cfqg->new_weight = v ?: cfqgd->weight;
                } else {
                        cfqg->dev_leaf_weight = v;
                        cfqg->new_leaf_weight = v ?: cfqgd->leaf_weight;
                }
                ret = 0;
        }
out_finish:
        blkg_conf_finish(&ctx);
        return ret ?: nbytes;
}

static ssize_t cfqg_set_weight_device(struct kernfs_open_file *of,
                                      char *buf, size_t nbytes, loff_t off)
{
        return __cfqg_set_weight_device(of, buf, nbytes, off, false, false);
}

static ssize_t cfqg_set_leaf_weight_device(struct kernfs_open_file *of,
                                           char *buf, size_t nbytes, loff_t off)
{
        return __cfqg_set_weight_device(of, buf, nbytes, off, false, true);
}

static int __cfq_set_weight(struct cgroup_subsys_state *css, u64 val,
                            bool on_dfl, bool reset_dev, bool is_leaf_weight)
{
        unsigned int min = on_dfl ? CGROUP_WEIGHT_MIN : CFQ_WEIGHT_LEGACY_MIN;
        unsigned int max = on_dfl ? CGROUP_WEIGHT_MAX : CFQ_WEIGHT_LEGACY_MAX;
        struct blkcg *blkcg = css_to_blkcg(css);
        struct blkcg_gq *blkg;
        struct cfq_group_data *cfqgd;
        int ret = 0;

        if (val < min || val > max)
                return -ERANGE;

        spin_lock_irq(&blkcg->lock);
        cfqgd = blkcg_to_cfqgd(blkcg);
        if (!cfqgd) {
                ret = -EINVAL;
                goto out;
        }

        if (!is_leaf_weight)
                cfqgd->weight = val;
        else
                cfqgd->leaf_weight = val;

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

                if (!cfqg)
                        continue;

                if (!is_leaf_weight) {
                        if (reset_dev)
                                cfqg->dev_weight = 0;
                        if (!cfqg->dev_weight)
                                cfqg->new_weight = cfqgd->weight;
                } else {
                        if (reset_dev)
                                cfqg->dev_leaf_weight = 0;
                        if (!cfqg->dev_leaf_weight)
                                cfqg->new_leaf_weight = cfqgd->leaf_weight;
                }
        }

out:
        spin_unlock_irq(&blkcg->lock);
        return ret;
}

static int cfq_set_weight(struct cgroup_subsys_state *css, struct cftype *cft,
                          u64 val)
{
        return __cfq_set_weight(css, val, false, false, false);
}

static int cfq_set_leaf_weight(struct cgroup_subsys_state *css,
                               struct cftype *cft, u64 val)
{
        return __cfq_set_weight(css, val, false, false, true);
}

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

static int cfqg_print_rwstat(struct seq_file *sf, void *v)
{
        blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat,
                          &blkcg_policy_cfq, seq_cft(sf)->private, true);
        return 0;
}

static u64 cfqg_prfill_stat_recursive(struct seq_file *sf,
                                      struct blkg_policy_data *pd, int off)
{
        u64 sum = blkg_stat_recursive_sum(pd_to_blkg(pd),
                                          &blkcg_policy_cfq, off);
        return __blkg_prfill_u64(sf, pd, sum);
}

static u64 cfqg_prfill_rwstat_recursive(struct seq_file *sf,
                                        struct blkg_policy_data *pd, int off)
{
        struct blkg_rwstat sum = blkg_rwstat_recursive_sum(pd_to_blkg(pd),
                                                        &blkcg_policy_cfq, off);
        return __blkg_prfill_rwstat(sf, pd, &sum);
}

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

static int cfqg_print_rwstat_recursive(struct seq_file *sf, void *v)
{
        blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
                          cfqg_prfill_rwstat_recursive, &blkcg_policy_cfq,
                          seq_cft(sf)->private, true);
        return 0;
}

static u64 cfqg_prfill_sectors(struct seq_file *sf, struct blkg_policy_data *pd,
                               int off)
{
        u64 sum = blkg_rwstat_total(&pd->blkg->stat_bytes);

        return __blkg_prfill_u64(sf, pd, sum >> 9);
}

static int cfqg_print_stat_sectors(struct seq_file *sf, void *v)
{
        blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
                          cfqg_prfill_sectors, &blkcg_policy_cfq, 0, false);
        return 0;
}

static u64 cfqg_prfill_sectors_recursive(struct seq_file *sf,
                                         struct blkg_policy_data *pd, int off)
{
        struct blkg_rwstat tmp = blkg_rwstat_recursive_sum(pd->blkg, NULL,
                                        offsetof(struct blkcg_gq, stat_bytes));
        u64 sum = atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_READ]) +
                atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_WRITE]);

        return __blkg_prfill_u64(sf, pd, sum >> 9);
}

static int cfqg_print_stat_sectors_recursive(struct seq_file *sf, void *v)
{
        blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
                          cfqg_prfill_sectors_recursive, &blkcg_policy_cfq, 0,
                          false);
        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);
                v = div64_u64(v, samples);
        }
        __blkg_prfill_u64(sf, pd, v);
        return 0;
}

/* print avg_queue_size */
static int cfqg_print_avg_queue_size(struct seq_file *sf, void *v)
{
        blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
                          cfqg_prfill_avg_queue_size, &blkcg_policy_cfq,
                          0, false);
        return 0;
}
#endif  /* CONFIG_DEBUG_BLK_CGROUP */

static struct cftype cfq_blkcg_legacy_files[] = {
        /* on root, weight is mapped to leaf_weight */
        {
                .name = "weight_device",
                .flags = CFTYPE_ONLY_ON_ROOT,
                .seq_show = cfqg_print_leaf_weight_device,
                .write = cfqg_set_leaf_weight_device,
        },
        {
                .name = "weight",
                .flags = CFTYPE_ONLY_ON_ROOT,
                .seq_show = cfq_print_leaf_weight,
                .write_u64 = cfq_set_leaf_weight,
        },

        /* no such mapping necessary for !roots */
        {
                .name = "weight_device",
                .flags = CFTYPE_NOT_ON_ROOT,
                .seq_show = cfqg_print_weight_device,
                .write = cfqg_set_weight_device,
        },
        {
                .name = "weight",
                .flags = CFTYPE_NOT_ON_ROOT,
                .seq_show = cfq_print_weight,
                .write_u64 = cfq_set_weight,
        },

        {
                .name = "leaf_weight_device",
                .seq_show = cfqg_print_leaf_weight_device,
                .write = cfqg_set_leaf_weight_device,
        },
        {
                .name = "leaf_weight",
                .seq_show = cfq_print_leaf_weight,
                .write_u64 = cfq_set_leaf_weight,
        },

        /* statistics, covers only the tasks in the cfqg */
        {
                .name = "time",
                .private = offsetof(struct cfq_group, stats.time),
                .seq_show = cfqg_print_stat,
        },
        {
                .name = "sectors",
                .seq_show = cfqg_print_stat_sectors,
        },
        {
                .name = "io_service_bytes",
                .private = (unsigned long)&blkcg_policy_cfq,
                .seq_show = blkg_print_stat_bytes,
        },
        {
                .name = "io_serviced",
                .private = (unsigned long)&blkcg_policy_cfq,
                .seq_show = blkg_print_stat_ios,
        },
        {
                .name = "io_service_time",
                .private = offsetof(struct cfq_group, stats.service_time),
                .seq_show = cfqg_print_rwstat,
        },
        {
                .name = "io_wait_time",
                .private = offsetof(struct cfq_group, stats.wait_time),
                .seq_show = cfqg_print_rwstat,
        },
        {
                .name = "io_merged",
                .private = offsetof(struct cfq_group, stats.merged),
                .seq_show = cfqg_print_rwstat,
        },
        {
                .name = "io_queued",
                .private = offsetof(struct cfq_group, stats.queued),
                .seq_show = cfqg_print_rwstat,
        },

        /* the same statictics which cover the cfqg and its descendants */
        {
                .name = "time_recursive",
                .private = offsetof(struct cfq_group, stats.time),
                .seq_show = cfqg_print_stat_recursive,
        },
        {
                .name = "sectors_recursive",
                .seq_show = cfqg_print_stat_sectors_recursive,
        },
        {
                .name = "io_service_bytes_recursive",
                .private = (unsigned long)&blkcg_policy_cfq,
                .seq_show = blkg_print_stat_bytes_recursive,
        },
        {
                .name = "io_serviced_recursive",
                .private = (unsigned long)&blkcg_policy_cfq,
                .seq_show = blkg_print_stat_ios_recursive,
        },
        {
                .name = "io_service_time_recursive",
                .private = offsetof(struct cfq_group, stats.service_time),
                .seq_show = cfqg_print_rwstat_recursive,
        },
        {
                .name = "io_wait_time_recursive",
                .private = offsetof(struct cfq_group, stats.wait_time),
                .seq_show = cfqg_print_rwstat_recursive,
        },
        {
                .name = "io_merged_recursive",
                .private = offsetof(struct cfq_group, stats.merged),
                .seq_show = cfqg_print_rwstat_recursive,
        },
        {
                .name = "io_queued_recursive",
                .private = offsetof(struct cfq_group, stats.queued),
                .seq_show = cfqg_print_rwstat_recursive,
        },
#ifdef CONFIG_DEBUG_BLK_CGROUP
        {
                .name = "avg_queue_size",
                .seq_show = cfqg_print_avg_queue_size,
        },
        {
                .name = "group_wait_time",
                .private = offsetof(struct cfq_group, stats.group_wait_time),
                .seq_show = cfqg_print_stat,
        },
        {
                .name = "idle_time",
                .private = offsetof(struct cfq_group, stats.idle_time),
                .seq_show = cfqg_print_stat,
        },
        {
                .name = "empty_time",
                .private = offsetof(struct cfq_group, stats.empty_time),
                .seq_show = cfqg_print_stat,
        },
        {
                .name = "dequeue",
                .private = offsetof(struct cfq_group, stats.dequeue),
                .seq_show = cfqg_print_stat,
        },
        {
                .name = "unaccounted_time",
                .private = offsetof(struct cfq_group, stats.unaccounted_time),
                .seq_show = cfqg_print_stat,
        },
#endif  /* CONFIG_DEBUG_BLK_CGROUP */
        { }     /* terminate */
};

static int cfq_print_weight_on_dfl(struct seq_file *sf, void *v)
{
        struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
        struct cfq_group_data *cgd = blkcg_to_cfqgd(blkcg);

        seq_printf(sf, "default %u\n", cgd->weight);
        blkcg_print_blkgs(sf, blkcg, cfqg_prfill_weight_device,
                          &blkcg_policy_cfq, 0, false);
        return 0;
}

static ssize_t cfq_set_weight_on_dfl(struct kernfs_open_file *of,
                                     char *buf, size_t nbytes, loff_t off)
{
        char *endp;
        int ret;
        u64 v;

        buf = strim(buf);

        /* "WEIGHT" or "default WEIGHT" sets the default weight */
        v = simple_strtoull(buf, &endp, 0);
        if (*endp == '\0' || sscanf(buf, "default %llu", &v) == 1) {
                ret = __cfq_set_weight(of_css(of), v, true, false, false);
                return ret ?: nbytes;
        }

        /* "MAJ:MIN WEIGHT" */
        return __cfqg_set_weight_device(of, buf, nbytes, off, true, false);
}

static struct cftype cfq_blkcg_files[] = {
        {
                .name = "weight",
                .flags = CFTYPE_NOT_ON_ROOT,
                .seq_show = cfq_print_weight_on_dfl,
                .write = cfq_set_weight_on_dfl,
        },
        { }     /* terminate */
};

#else /* GROUP_IOSCHED */
static struct cfq_group *cfq_lookup_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;
        u64 rb_key;
        struct cfq_rb_root *st;
        bool leftmost = true;
        int new_cfqq = 1;
        u64 now = ktime_get_ns();

        st = st_for(cfqq->cfqg, cfqq_class(cfqq), cfqq_type(cfqq));
        if (cfq_class_idle(cfqq)) {
                rb_key = CFQ_IDLE_DELAY;
                parent = st->rb_rightmost;
                if (parent && parent != &cfqq->rb_node) {
                        __cfqq = rb_entry(parent, struct cfq_queue, rb_node);
                        rb_key += __cfqq->rb_key;
                } else
                        rb_key += now;
        } 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) + now;
                rb_key -= cfqq->slice_resid;
                cfqq->slice_resid = 0;
        } else {
                rb_key = -NSEC_PER_SEC;
                __cfqq = cfq_rb_first(st);
                rb_key += __cfqq ? __cfqq->rb_key : now;
        }

        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 == st)
                        return;

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

        parent = NULL;
        cfqq->service_tree = st;
        p = &st->rb.rb_root.rb_node;
        while (*p) {
                parent = *p;
                __cfqq = rb_entry(parent, struct cfq_queue, rb_node);

                /*
                 * sort by key, that represents service time.
                 */
                if (rb_key < __cfqq->rb_key)
                        p = &parent->rb_left;
                else {
                        p = &parent->rb_right;
                        leftmost = false;
                }
        }

        cfqq->rb_key = rb_key;
        rb_link_node(&cfqq->rb_node, parent, p);
        rb_insert_color_cached(&cfqq->rb_node, &st->rb, leftmost);
        st->count++;
        if (add_front || !new_cfqq)
                return;
        cfq_group_notify_queue_add(cfqd, cfqq->cfqg);
}

static struct cfq_queue *
cfq_prio_tree_lookup(struct cfq_data *cfqd, struct rb_root *root,
                     sector_t sector, struct rb_node **ret_parent,
                     struct rb_node ***rb_link)
{
        struct rb_node **p, *parent;
        struct cfq_queue *cfqq = NULL;

        parent = NULL;
        p = &root->rb_node;
        while (*p) {
                struct rb_node **n;

                parent = *p;
                cfqq = rb_entry(parent, struct cfq_queue, p_node);

                /*
                 * Sort strictly based on sector.  Smallest to the left,
                 * largest to the right.
                 */
                if (sector > blk_rq_pos(cfqq->next_rq))
                        n = &(*p)->rb_right;
                else if (sector < blk_rq_pos(cfqq->next_rq))
                        n = &(*p)->rb_left;
                else
                        break;
                p = n;
                cfqq = NULL;
        }

        *ret_parent = parent;
        if (rb_link)
                *rb_link = p;
        return cfqq;
}

static void cfq_prio_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
        struct rb_node **p, *parent;
        struct cfq_queue *__cfqq;

        if (cfqq->p_root) {
                rb_erase(&cfqq->p_node, cfqq->p_root);
                cfqq->p_root = NULL;
        }

        if (cfq_class_idle(cfqq))
                return;
        if (!cfqq->next_rq)
                return;

        cfqq->p_root = &cfqd->prio_trees[cfqq->org_ioprio];
        __cfqq = cfq_prio_tree_lookup(cfqd, cfqq->p_root,
                                      blk_rq_pos(cfqq->next_rq), &parent, &p);
        if (!__cfqq) {
                rb_link_node(&cfqq->p_node, parent, p);
                rb_insert_color(&cfqq->p_node, cfqq->p_root);
        } else
                cfqq->p_root = NULL;
}

/*
 * Update cfqq's position in the service tree.
 */
static void cfq_resort_rr_list(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
        /*
         * Resorting requires the cfqq to be on the RR list already.
         */
        if (cfq_cfqq_on_rr(cfqq)) {
                cfq_service_tree_add(cfqd, cfqq, 0);
                cfq_prio_tree_add(cfqd, cfqq);
        }
}

/*
 * add to busy list of queues for service, trying to be fair in ordering
 * the pending list according to last request service
 */
static void cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
        cfq_log_cfqq(cfqd, cfqq, "add_to_rr");
        BUG_ON(cfq_cfqq_on_rr(cfqq));
        cfq_mark_cfqq_on_rr(cfqq);
        cfqd->busy_queues++;
        if (cfq_cfqq_sync(cfqq))
                cfqd->busy_sync_queues++;

        cfq_resort_rr_list(cfqd, cfqq);
}

/*
 * Called when the cfqq no longer has requests pending, remove it from
 * the service tree.
 */
static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
        cfq_log_cfqq(cfqd, cfqq, "del_from_rr");
        BUG_ON(!cfq_cfqq_on_rr(cfqq));
        cfq_clear_cfqq_on_rr(cfqq);

        if (!RB_EMPTY_NODE(&cfqq->rb_node)) {
                cfq_rb_erase(&cfqq->rb_node, cfqq->service_tree);
                cfqq->service_tree = NULL;
        }
        if (cfqq->p_root) {
                rb_erase(&cfqq->p_node, cfqq->p_root);
                cfqq->p_root = NULL;
        }

        cfq_group_notify_queue_del(cfqd, cfqq->cfqg);
        BUG_ON(!cfqd->busy_queues);
        cfqd->busy_queues--;
        if (cfq_cfqq_sync(cfqq))
                cfqd->busy_sync_queues--;
}

/*
 * rb tree support functions
 */
static void cfq_del_rq_rb(struct request *rq)
{
        struct cfq_queue *cfqq = RQ_CFQQ(rq);
        const int sync = rq_is_sync(rq);

        BUG_ON(!cfqq->queued[sync]);
        cfqq->queued[sync]--;

        elv_rb_del(&cfqq->sort_list, rq);

        if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list)) {
                /*
                 * Queue will be deleted from service tree when we actually
                 * expire it later. Right now just remove it from prio tree
                 * as it is empty.
                 */
                if (cfqq->p_root) {
                        rb_erase(&cfqq->p_node, cfqq->p_root);
                        cfqq->p_root = NULL;
                }
        }
}

static void cfq_add_rq_rb(struct request *rq)
{
        struct cfq_queue *cfqq = RQ_CFQQ(rq);
        struct cfq_data *cfqd = cfqq->cfqd;
        struct request *prev;

        cfqq->queued[rq_is_sync(rq)]++;

        elv_rb_add(&cfqq->sort_list, rq);

        if (!cfq_cfqq_on_rr(cfqq))
                cfq_add_cfqq_rr(cfqd, cfqq);

        /*
         * check if this request is a better next-serve candidate
         */
        prev = cfqq->next_rq;
        cfqq->next_rq = cfq_choose_req(cfqd, cfqq->next_rq, rq, cfqd->last_position);

        /*
         * adjust priority tree position, if ->next_rq changes
         */
        if (prev != cfqq->next_rq)
                cfq_prio_tree_add(cfqd, cfqq);

        BUG_ON(!cfqq->next_rq);
}

static void cfq_reposition_rq_rb(struct cfq_queue *cfqq, struct request *rq)
{
        elv_rb_del(&cfqq->sort_list, rq);
        cfqq->queued[rq_is_sync(rq)]--;
        cfqg_stats_update_io_remove(RQ_CFQG(rq), rq->cmd_flags);
        cfq_add_rq_rb(rq);
        cfqg_stats_update_io_add(RQ_CFQG(rq), cfqq->cfqd->serving_group,
                                 rq->cmd_flags);
}

static struct request *
cfq_find_rq_fmerge(struct cfq_data *cfqd, struct bio *bio)
{
        struct task_struct *tsk = current;
        struct cfq_io_cq *cic;
        struct cfq_queue *cfqq;

        cic = cfq_cic_lookup(cfqd, tsk->io_context);
        if (!cic)
                return NULL;

        cfqq = cic_to_cfqq(cic, op_is_sync(bio->bi_opf));
        if (cfqq)
                return elv_rb_find(&cfqq->sort_list, bio_end_sector(bio));

        return NULL;
}

static void cfq_activate_request(struct request_queue *q, struct request *rq)
{
        struct cfq_data *cfqd = q->elevator->elevator_data;

        cfqd->rq_in_driver++;
        cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "activate rq, drv=%d",
                                                cfqd->rq_in_driver);

        cfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
}

static void cfq_deactivate_request(struct request_queue *q, struct request *rq)
{
        struct cfq_data *cfqd = q->elevator->elevator_data;

        WARN_ON(!cfqd->rq_in_driver);
        cfqd->rq_in_driver--;
        cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "deactivate rq, drv=%d",
                                                cfqd->rq_in_driver);
}

static void cfq_remove_request(struct request *rq)
{
        struct cfq_queue *cfqq = RQ_CFQQ(rq);

        if (cfqq->next_rq == rq)
                cfqq->next_rq = cfq_find_next_rq(cfqq->cfqd, cfqq, rq);

        list_del_init(&rq->queuelist);
        cfq_del_rq_rb(rq);

        cfqq->cfqd->rq_queued--;
        cfqg_stats_update_io_remove(RQ_CFQG(rq), rq->cmd_flags);
        if (rq->cmd_flags & REQ_PRIO) {
                WARN_ON(!cfqq->prio_pending);
                cfqq->prio_pending--;
        }
}

static enum elv_merge cfq_merge(struct request_queue *q, struct request **req,
                     struct bio *bio)
{
        struct cfq_data *cfqd = q->elevator->elevator_data;
        struct request *__rq;

        __rq = cfq_find_rq_fmerge(cfqd, bio);
        if (__rq && elv_bio_merge_ok(__rq, bio)) {
                *req = __rq;
                return ELEVATOR_FRONT_MERGE;
        }

        return ELEVATOR_NO_MERGE;
}

static void cfq_merged_request(struct request_queue *q, struct request *req,
                               enum elv_merge type)
{
        if (type == ELEVATOR_FRONT_MERGE) {
                struct cfq_queue *cfqq = RQ_CFQQ(req);

                cfq_reposition_rq_rb(cfqq, req);
        }
}

static void cfq_bio_merged(struct request_queue *q, struct request *req,
                                struct bio *bio)
{
        cfqg_stats_update_io_merged(RQ_CFQG(req), bio->bi_opf);
}

static void
cfq_merged_requests(struct request_queue *q, struct request *rq,
                    struct request *next)
{
        struct cfq_queue *cfqq = RQ_CFQQ(rq);
        struct cfq_data *cfqd = q->elevator->elevator_data;

        /*
         * reposition in fifo if next is older than rq
         */
        if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
            next->fifo_time < rq->fifo_time &&
            cfqq == RQ_CFQQ(next)) {
                list_move(&rq->queuelist, &next->queuelist);
                rq->fifo_time = next->fifo_time;
        }

        if (cfqq->next_rq == next)
                cfqq->next_rq = rq;
        cfq_remove_request(next);
        cfqg_stats_update_io_merged(RQ_CFQG(rq), next->cmd_flags);

        cfqq = RQ_CFQQ(next);
        /*
         * all requests of this queue are merged to other queues, delete it
         * from the service tree. If it's the active_queue,
         * cfq_dispatch_requests() will choose to expire it or do idle
         */
        if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list) &&
            cfqq != cfqd->active_queue)
                cfq_del_cfqq_rr(cfqd, cfqq);
}

static int cfq_allow_bio_merge(struct request_queue *q, struct request *rq,
                               struct bio *bio)
{
        struct cfq_data *cfqd = q->elevator->elevator_data;
        bool is_sync = op_is_sync(bio->bi_opf);
        struct cfq_io_cq *cic;
        struct cfq_queue *cfqq;

        /*
         * Disallow merge of a sync bio into an async request.
         */
        if (is_sync && !rq_is_sync(rq))
                return false;

        /*
         * Lookup the cfqq that this bio will be queued with and allow
         * merge only if rq is queued there.
         */
        cic = cfq_cic_lookup(cfqd, current->io_context);
        if (!cic)
                return false;

        cfqq = cic_to_cfqq(cic, is_sync);
        return cfqq == RQ_CFQQ(rq);
}

static int cfq_allow_rq_merge(struct request_queue *q, struct request *rq,
                              struct request *next)
{
        return RQ_CFQQ(rq) == RQ_CFQQ(next);
}

static inline void cfq_del_timer(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
        hrtimer_try_to_cancel(&cfqd->idle_slice_timer);
        cfqg_stats_update_idle_time(cfqq->cfqg);
}

static void __cfq_set_active_queue(struct cfq_data *cfqd,
                                   struct cfq_queue *cfqq)
{
        if (cfqq) {
                cfq_log_cfqq(cfqd, cfqq, "set_active wl_class:%d wl_type:%d",
                                cfqd->serving_wl_class, cfqd->serving_wl_type);
                cfqg_stats_update_avg_queue_size(cfqq->cfqg);
                cfqq->slice_start = 0;
                cfqq->dispatch_start = ktime_get_ns();
                cfqq->allocated_slice = 0;
                cfqq->slice_end = 0;
                cfqq->slice_dispatch = 0;
                cfqq->nr_sectors = 0;

                cfq_clear_cfqq_wait_request(cfqq);
                cfq_clear_cfqq_must_dispatch(cfqq);
                cfq_clear_cfqq_must_alloc_slice(cfqq);
                cfq_clear_cfqq_fifo_expire(cfqq);
                cfq_mark_cfqq_slice_new(cfqq);

                cfq_del_timer(cfqd, cfqq);
        }

        cfqd->active_queue = cfqq;
}

/*
 * current cfqq expired its slice (or was too idle), select new one
 */
static void
__cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
                    bool timed_out)
{
        cfq_log_cfqq(cfqd, cfqq, "slice expired t=%d", timed_out);

        if (cfq_cfqq_wait_request(cfqq))
                cfq_del_timer(cfqd, cfqq);

        cfq_clear_cfqq_wait_request(cfqq);
        cfq_clear_cfqq_wait_busy(cfqq);

        /*
         * If this cfqq is shared between multiple processes, check to
         * make sure that those processes are still issuing I/Os within
         * the mean seek distance.  If not, it may be time to break the
         * queues apart again.
         */
        if (cfq_cfqq_coop(cfqq) && CFQQ_SEEKY(cfqq))
                cfq_mark_cfqq_split_coop(cfqq);

        /*
         * store what was left of this slice, if the queue idled/timed out
         */
        if (timed_out) {
                if (cfq_cfqq_slice_new(cfqq))
                        cfqq->slice_resid = cfq_scaled_cfqq_slice(cfqd, cfqq);
                else
                        cfqq->slice_resid = cfqq->slice_end - ktime_get_ns();
                cfq_log_cfqq(cfqd, cfqq, "resid=%lld", cfqq->slice_resid);
        }

        cfq_group_served(cfqd, cfqq->cfqg, cfqq);

        if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list))
                cfq_del_cfqq_rr(cfqd, cfqq);

        cfq_resort_rr_list(cfqd, cfqq);

        if (cfqq == cfqd->active_queue)
                cfqd->active_queue = NULL;

        if (cfqd->active_cic) {
                put_io_context(cfqd->active_cic->icq.ioc);
                cfqd->active_cic = NULL;
        }
}

static inline void cfq_slice_expired(struct cfq_data *cfqd, bool timed_out)
{
        struct cfq_queue *cfqq = cfqd->active_queue;

        if (cfqq)
                __cfq_slice_expired(cfqd, cfqq, timed_out);
}

/*
 * Get next queue for service. Unless we have a queue preemption,
 * we'll simply select the first cfqq in the service tree.
 */
static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd)
{
        struct cfq_rb_root *st = st_for(cfqd->serving_group,
                        cfqd->serving_wl_class, cfqd->serving_wl_type);

        if (!cfqd->rq_queued)
                return NULL;

        /* There is nothing to dispatch */
        if (!st)
                return NULL;
        if (RB_EMPTY_ROOT(&st->rb.rb_root))
                return NULL;
        return cfq_rb_first(st);
}

static struct cfq_queue *cfq_get_next_queue_forced(struct cfq_data *cfqd)
{
        struct cfq_group *cfqg;
        struct cfq_queue *cfqq;
        int i, j;
        struct cfq_rb_root *st;

        if (!cfqd->rq_queued)
                return NULL;

        cfqg = cfq_get_next_cfqg(cfqd);
        if (!cfqg)
                return NULL;

        for_each_cfqg_st(cfqg, i, j, st) {
                cfqq = cfq_rb_first(st);
                if (cfqq)
                        return cfqq;
        }
        return NULL;
}

/*
 * Get and set a new active queue for service.
 */
static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd,
                                              struct cfq_queue *cfqq)
{
        if (!cfqq)
                cfqq = cfq_get_next_queue(cfqd);

        __cfq_set_active_queue(cfqd, cfqq);
        return cfqq;
}

static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd,
                                          struct request *rq)
{
        if (blk_rq_pos(rq) >= cfqd->last_position)
                return blk_rq_pos(rq) - cfqd->last_position;
        else
                return cfqd->last_position - blk_rq_pos(rq);
}

static inline int cfq_rq_close(struct cfq_data *cfqd, struct cfq_queue *cfqq,
                               struct request *rq)
{
        return cfq_dist_from_last(cfqd, rq) <= CFQQ_CLOSE_THR;
}

static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
                                    struct cfq_queue *cur_cfqq)
{
        struct rb_root *root = &cfqd->prio_trees[cur_cfqq->org_ioprio];
        struct rb_node *parent, *node;
        struct cfq_queue *__cfqq;
        sector_t sector = cfqd->last_position;

        if (RB_EMPTY_ROOT(root))
                return NULL;

        /*
         * First, if we find a request starting at the end of the last
         * request, choose it.
         */
        __cfqq = cfq_prio_tree_lookup(cfqd, root, sector, &parent, NULL);
        if (__cfqq)
                return __cfqq;

        /*
         * If the exact sector wasn't found, the parent of the NULL leaf
         * will contain the closest sector.
         */
        __cfqq = rb_entry(parent, struct cfq_queue, p_node);
        if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq))
                return __cfqq;

        if (blk_rq_pos(__cfqq->next_rq) < sector)
                node = rb_next(&__cfqq->p_node);
        else
                node = rb_prev(&__cfqq->p_node);
        if (!node)
                return NULL;

        __cfqq = rb_entry(node, struct cfq_queue, p_node);
        if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq))
                return __cfqq;

        return NULL;
}

/*
 * cfqd - obvious
 * cur_cfqq - passed in so that we don't decide that the current queue is
 *            closely cooperating with itself.
 *
 * So, basically we're assuming that that cur_cfqq has dispatched at least
 * one request, and that cfqd->last_position reflects a position on the disk
 * associated with the I/O issued by cur_cfqq.  I'm not sure this is a valid
 * assumption.
 */
static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
                                              struct cfq_queue *cur_cfqq)
{
        struct cfq_queue *cfqq;

        if (cfq_class_idle(cur_cfqq))
                return NULL;
        if (!cfq_cfqq_sync(cur_cfqq))
                return NULL;
        if (CFQQ_SEEKY(cur_cfqq))
                return NULL;

        /*
         * Don't search priority tree if it's the only queue in the group.
         */
        if (cur_cfqq->cfqg->nr_cfqq == 1)
                return NULL;

        /*
         * We should notice if some of the queues are cooperating, eg
         * working closely on the same area of the disk. In that case,
         * we can group them together and don't waste time idling.
         */
        cfqq = cfqq_close(cfqd, cur_cfqq);
        if (!cfqq)
                return NULL;

        /* If new queue belongs to different cfq_group, don't choose it */
        if (cur_cfqq->cfqg != cfqq->cfqg)
                return NULL;

        /*
         * It only makes sense to merge sync queues.
         */
        if (!cfq_cfqq_sync(cfqq))
                return NULL;
        if (CFQQ_SEEKY(cfqq))
                return NULL;

        /*
         * Do not merge queues of different priority classes
         */
        if (cfq_class_rt(cfqq) != cfq_class_rt(cur_cfqq))
                return NULL;

        return cfqq;
}

/*
 * Determine whether we should enforce idle window for this queue.
 */

static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
        enum wl_class_t wl_class = cfqq_class(cfqq);
        struct cfq_rb_root *st = cfqq->service_tree;

        BUG_ON(!st);
        BUG_ON(!st->count);

        if (!cfqd->cfq_slice_idle)
                return false;

        /* We never do for idle class queues. */
        if (wl_class == IDLE_WORKLOAD)
                return false;

        /* We do for queues that were marked with idle window flag. */
        if (cfq_cfqq_idle_window(cfqq) &&
           !(blk_queue_nonrot(cfqd->queue) && cfqd->hw_tag))
                return true;

        /*
         * Otherwise, we do only if they are the last ones
         * in their service tree.
         */
        if (st->count == 1 && cfq_cfqq_sync(cfqq) &&
           !cfq_io_thinktime_big(cfqd, &st->ttime, false))
                return true;
        cfq_log_cfqq(cfqd, cfqq, "Not idling. st->count:%d", st->count);
        return false;
}

static void cfq_arm_slice_timer(struct cfq_data *cfqd)
{
        struct cfq_queue *cfqq = cfqd->active_queue;
        struct cfq_rb_root *st = cfqq->service_tree;
        struct cfq_io_cq *cic;
        u64 sl, group_idle = 0;
        u64 now = ktime_get_ns();

        /*
         * SSD device without seek penalty, disable idling. But only do so
         * for devices that support queuing, otherwise we still have a problem
         * with sync vs async workloads.
         */
        if (blk_queue_nonrot(cfqd->queue) && cfqd->hw_tag &&
                !cfqd->cfq_group_idle)
                return;

        WARN_ON(!RB_EMPTY_ROOT(&cfqq->sort_list));
        WARN_ON(cfq_cfqq_slice_new(cfqq));

        /*
         * idle is disabled, either manually or by past process history
         */
        if (!cfq_should_idle(cfqd, cfqq)) {
                /* no queue idling. Check for group idling */
                if (cfqd->cfq_group_idle)
                        group_idle = cfqd->cfq_group_idle;
                else
                        return;
        }

        /*
         * still active requests from this queue, don't idle
         */
        if (cfqq->dispatched)
                return;

        /*
         * task has exited, don't wait
         */
        cic = cfqd->active_cic;
        if (!cic || !atomic_read(&cic->icq.ioc->active_ref))
                return;

        /*
         * If our average think time is larger than the remaining time
         * slice, then don't idle. This avoids overrunning the allotted
         * time slice.
         */
        if (sample_valid(cic->ttime.ttime_samples) &&
            (cfqq->slice_end - now < cic->ttime.ttime_mean)) {
                cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%llu",
                             cic->ttime.ttime_mean);
                return;
        }

        /*
         * There are other queues in the group or this is the only group and
         * it has too big thinktime, don't do group idle.
         */
        if (group_idle &&
            (cfqq->cfqg->nr_cfqq > 1 ||
             cfq_io_thinktime_big(cfqd, &st->ttime, true)))
                return;

        cfq_mark_cfqq_wait_request(cfqq);

        if (group_idle)
                sl = cfqd->cfq_group_idle;
        else
                sl = cfqd->cfq_slice_idle;

        hrtimer_start(&cfqd->idle_slice_timer, ns_to_ktime(sl),
                      HRTIMER_MODE_REL);
        cfqg_stats_set_start_idle_time(cfqq->cfqg);
        cfq_log_cfqq(cfqd, cfqq, "arm_idle: %llu group_idle: %d", sl,
                        group_idle ? 1 : 0);
}

/*
 * Move request from internal lists to the request queue dispatch list.
 */
static void cfq_dispatch_insert(struct request_queue *q, struct request *rq)
{
        struct cfq_data *cfqd = q->elevator->elevator_data;
        struct cfq_queue *cfqq = RQ_CFQQ(rq);

        cfq_log_cfqq(cfqd, cfqq, "dispatch_insert");

        cfqq->next_rq = cfq_find_next_rq(cfqd, cfqq, rq);
        cfq_remove_request(rq);
        cfqq->dispatched++;
        (RQ_CFQG(rq))->dispatched++;
        elv_dispatch_sort(q, rq);