fios2-iosched.c

#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
 */
static const int cfq_alpha = 50;///xx - default alpha=50(0.5), 0 <= alpha < 100
static const int cfq_tservice = NSEC_PER_SEC / 125;///xx - Tservice, default=8ms, calc for anticipation
static const int cfq_tsrv_nr = 1;///xx
static const u64 cfq_tsrv_sum = NSEC_PER_SEC / 125;///xx
static const u64 cfq_epoch_slice = NSEC_PER_SEC / 8;///xx - nummer of an epoch timeslices

/* 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 };
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

/*
 * 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;
};
#define CFQ_RB_ROOT	(struct cfq_rb_root) { .rb = RB_ROOT_CACHED, \
			.rb_rightmost = NULL,}

/*
 * 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;

	u64 epoch_start;
	u64 epoch_slice;///xx

	/* 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 {};

/* 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 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];
	int			ioprio;		/* the current ioprio */
};

/*
 * 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_alpha;///xx - alpha threshold, for calc anticipation.
	unsigned int cfq_tservice;///xx - Tservice, for calc anticipation.
	unsigned int cfq_tsrv_nr;///xx - nummer of services for anticipating task
	unsigned int cfq_is_anti;///xx
	u64 cfq_tsrv_start;
	u64 cfq_tsrv_sum;///xx - sum of service time for anticipating task
	unsigned int cfq_quantum;
	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

#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(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 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);
}

/*
 * 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)
{
	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;

//////xx - read performance
	if (req_op(rq1) == req_op(rq2))
		return rq1;
	else
		return op_is_write(req_op(rq1)) ? rq2 : rq1;
//////xx
}

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);
}

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;
	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;

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

	/* 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_group_service_tree_del(st, cfqg);
	cfqg->saved_wl_slice = 0;
}

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_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);
}

/**
 * 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);
}

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;
}

/*
 * 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)]--;
	cfq_add_rq_rb(rq);
}

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--;
	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){}

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);

	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);
}

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);
		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;
	}

	cfqd->cfq_is_anti = 0;
}

static inline void cfq_slice_expired(struct cfq_data *cfqd, bool timed_out)
{
	//cfqd->cfq_is_anti = 0;
	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)
{
	struct cfq_queue *start_cfqq;

	if (!cfqq)
		cfqq = cfq_get_next_queue(cfqd);
	else															///xx
		goto set_active;											///xx

	if (!cfqq)
		return NULL;
	start_cfqq = cfqq;
	if (cfqq->epoch_slice >= cfq_epoch_slice)
		cfqq = cfq_get_next_queue(cfqd);
	else
		goto set_active;

	while (start_cfqq != cfqq) {
		if (cfqq->epoch_slice < cfq_epoch_slice && cfqq->queued[0] && cfqq->queued[1])
			goto set_active;
		cfqq = cfq_get_next_queue(cfqd);
	}

	cfqq->epoch_slice = 0;
	cfqq = cfq_get_next_queue(cfqd);
	while (start_cfqq != cfqq) {
		cfqq->epoch_slice = 0;
		cfqq = cfq_get_next_queue(cfqd);
	}
	return NULL;
	
set_active: 
	__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))
		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_io_cq *cic;
	u64 sl, group_idle = 0;

	/*
	 * 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;

	/*
	 * 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))
		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);
	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);

	cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]++;
	cfqq->nr_sectors += blk_rq_sectors(rq);
}

/*
 * return expired entry, or NULL to just start from scratch in rbtree
 */
static struct request *cfq_check_fifo(struct cfq_queue *cfqq)
{
	struct request *rq = NULL;

	if (cfq_cfqq_fifo_expire(cfqq))
		return NULL;

	cfq_mark_cfqq_fifo_expire(cfqq);

	if (list_empty(&cfqq->fifo))
		return NULL;

	rq = rq_entry_fifo(cfqq->fifo.next);
	if (ktime_get_ns() < rq->fifo_time)
		rq = NULL;

	return rq;
}

static inline int
cfq_prio_to_maxrq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	const int base_rq = cfqd->cfq_slice_async_rq;

	WARN_ON(cfqq->ioprio >= IOPRIO_BE_NR);

	return 2 * base_rq * (IOPRIO_BE_NR - cfqq->ioprio);
}

/*
 * Must be called with the queue_lock held.
 */
static int cfqq_process_refs(struct cfq_queue *cfqq)
{
	int process_refs, io_refs;

	io_refs = cfqq->allocated[READ] + cfqq->allocated[WRITE];
	process_refs = cfqq->ref - io_refs;
	BUG_ON(process_refs < 0);
	return process_refs;
}

static void cfq_setup_merge(struct cfq_queue *cfqq, struct cfq_queue *new_cfqq)
{
	int process_refs, new_process_refs;
	struct cfq_queue *__cfqq;

	/*
	 * If there are no process references on the new_cfqq, then it is
	 * unsafe to follow the ->new_cfqq chain as other cfqq's in the
	 * chain may have dropped their last reference (not just their
	 * last process reference).
	 */
	if (!cfqq_process_refs(new_cfqq))
		return;

	/* Avoid a circular list and skip interim queue merges */
	while ((__cfqq = new_cfqq->new_cfqq)) {
		if (__cfqq == cfqq)
			return;
		new_cfqq = __cfqq;
	}

	process_refs = cfqq_process_refs(cfqq);
	new_process_refs = cfqq_process_refs(new_cfqq);
	/*
	 * If the process for the cfqq has gone away, there is no
	 * sense in merging the queues.
	 */
	if (process_refs == 0 || new_process_refs == 0)
		return;

	/*
	 * Merge in the direction of the lesser amount of work.
	 */
	if (new_process_refs >= process_refs) {
		cfqq->new_cfqq = new_cfqq;
		new_cfqq->ref += process_refs;
	} else {
		new_cfqq->new_cfqq = cfqq;
		cfqq->ref += new_process_refs;
	}
}

static enum wl_type_t cfq_choose_wl_type(struct cfq_data *cfqd,
			struct cfq_group *cfqg, enum wl_class_t wl_class)
{
	struct cfq_queue *queue;
	int i;
	bool key_valid = false;
	u64 lowest_key = 0;
	enum wl_type_t cur_best = SYNC_NOIDLE_WORKLOAD;

	for (i = 0; i <= SYNC_WORKLOAD; ++i) {
		/* select the one with lowest rb_key */
		queue = cfq_rb_first(st_for(cfqg, wl_class, i));
		if (queue &&
		    (!key_valid || queue->rb_key < lowest_key)) {
			lowest_key = queue->rb_key;
			cur_best = i;
			key_valid = true;
		}
	}

	return cur_best;
}

static void
choose_wl_class_and_type(struct cfq_data *cfqd, struct cfq_group *cfqg)
{
	u64 slice;
	unsigned count;
	struct cfq_rb_root *st;
	u64 group_slice;
	enum wl_class_t original_class = cfqd->serving_wl_class;
	u64 now = ktime_get_ns();

	/* Choose next priority. RT > BE > IDLE */
	if (cfq_group_busy_queues_wl(RT_WORKLOAD, cfqd, cfqg))
		cfqd->serving_wl_class = RT_WORKLOAD;
	else if (cfq_group_busy_queues_wl(BE_WORKLOAD, cfqd, cfqg))
		cfqd->serving_wl_class = BE_WORKLOAD;
	else {
		cfqd->serving_wl_class = IDLE_WORKLOAD;
		cfqd->workload_expires = now + jiffies_to_nsecs(1);
		return;
	}

	if (original_class != cfqd->serving_wl_class)
		goto new_workload;

	/*
	 * For RT and BE, we have to choose also the type
	 * (SYNC, SYNC_NOIDLE, ASYNC), and to compute a workload
	 * expiration time
	 */
	st = st_for(cfqg, cfqd->serving_wl_class, cfqd->serving_wl_type);
	count = st->count;

	/*
	 * check workload expiration, and that we still have other queues ready
	 */
	if (count && !(now > cfqd->workload_expires))
		return;

new_workload:
	/* otherwise select new workload type */
	cfqd->serving_wl_type = cfq_choose_wl_type(cfqd, cfqg,
					cfqd->serving_wl_class);
	st = st_for(cfqg, cfqd->serving_wl_class, cfqd->serving_wl_type);
	count = st->count;

	/*
	 * the workload slice is computed as a fraction of target latency
	 * proportional to the number of queues in that workload, over
	 * all the queues in the same priority class
	 */
	group_slice = cfq_group_slice(cfqd, cfqg);

	slice = div_u64(group_slice * count,
		max_t(unsigned, cfqg->busy_queues_avg[cfqd->serving_wl_class],
		      cfq_group_busy_queues_wl(cfqd->serving_wl_class, cfqd,
					cfqg)));

	if (cfqd->serving_wl_type == ASYNC_WORKLOAD) {
		u64 tmp;

		/*
		 * Async queues are currently system wide. Just taking
		 * proportion of queues with-in same group will lead to higher
		 * async ratio system wide as generally root group is going
		 * to have higher weight. A more accurate thing would be to
		 * calculate system wide asnc/sync ratio.
		 */
		tmp = cfqd->cfq_target_latency *
			cfqg_busy_async_queues(cfqd, cfqg);
		tmp = div_u64(tmp, cfqd->busy_queues);
		slice = min_t(u64, slice, tmp);

		/* async workload slice is scaled down according to
		 * the sync/async slice ratio. */
		slice = div64_u64(slice*cfqd->cfq_slice[0], cfqd->cfq_slice[1]);
	} else
		/* sync workload slice is at least 2 * cfq_slice_idle */
		slice = max(slice, 2 * cfqd->cfq_slice_idle);

	slice = max_t(u64, slice, CFQ_MIN_TT);
	cfq_log(cfqd, "workload slice:%llu", slice);
	cfqd->workload_expires = now + slice;
}

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

	if (RB_EMPTY_ROOT(&st->rb.rb_root))
		return NULL;
	cfqg = cfq_rb_first_group(st);
	return cfqg;
}

static void cfq_choose_cfqg(struct cfq_data *cfqd)
{
	struct cfq_group *cfqg = cfq_get_next_cfqg(cfqd);
	u64 now = ktime_get_ns();

	cfqd->serving_group = cfqg;

	/* Restore the workload type data */
	if (cfqg->saved_wl_slice) {
		cfqd->workload_expires = now + cfqg->saved_wl_slice;
		cfqd->serving_wl_type = cfqg->saved_wl_type;
		cfqd->serving_wl_class = cfqg->saved_wl_class;
	} else
		cfqd->workload_expires = now - 1;

	choose_wl_class_and_type(cfqd, cfqg);
}

/*
 * Select a queue for service. If we have a current active queue,
 * check whether to continue servicing it, or retrieve and set a new one.
 */
static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
{
	struct cfq_queue *cfqq, *new_cfqq = NULL;
	u64 now = ktime_get_ns();

	cfqq = cfqd->active_queue;
	if (!cfqq)
		goto new_queue;

	if (!cfqd->rq_queued)
		return NULL;

	/*
	 * We were waiting for group to get backlogged. Expire the queue
	 */
	if (cfq_cfqq_wait_busy(cfqq) && !RB_EMPTY_ROOT(&cfqq->sort_list))
		goto expire;

	/*
	 * The active queue has run out of time, expire it and select new.
	 */
	if (cfq_slice_used(cfqq) && !cfq_cfqq_must_dispatch(cfqq)) {
		/*
		 * If slice had not expired at the completion of last request
		 * we might not have turned on wait_busy flag. Don't expire
		 * the queue yet. Allow the group to get backlogged.
		 *
		 * The very fact that we have used the slice, that means we
		 * have been idling all along on this queue and it should be
		 * ok to wait for this request to complete.
		 */
		if (cfqq->cfqg->nr_cfqq == 1 && RB_EMPTY_ROOT(&cfqq->sort_list)
		    && cfqq->dispatched && cfq_should_idle(cfqd, cfqq)) {
			cfqq = NULL;
			goto keep_queue;
		} else
			goto check_group_idle;
	}

	/*
	 * The active queue has requests and isn't expired, allow it to
	 * dispatch.
	 */
	if (!RB_EMPTY_ROOT(&cfqq->sort_list))
		goto keep_queue;

	/*
	 * If another queue has a request waiting within our mean seek
	 * distance, let it run.  The expire code will check for close
	 * cooperators and put the close queue at the front of the service
	 * tree.  If possible, merge the expiring queue with the new cfqq.
	 */
	new_cfqq = cfq_close_cooperator(cfqd, cfqq);
	if (new_cfqq) {
		if (!cfqq->new_cfqq)
			cfq_setup_merge(cfqq, new_cfqq);
		goto expire;
	}

	/*
	 * No requests pending. If the active queue still has requests in
	 * flight or is idling for a new request, allow either of these
	 * conditions to happen (or time out) before selecting a new queue.
	 */
	if (hrtimer_active(&cfqd->idle_slice_timer)) {
		cfqq = NULL;
		goto keep_queue;
	}

	/*
	 * This is a deep seek queue, but the device is much faster than
	 * the queue can deliver, don't idle
	 **/
	if (CFQQ_SEEKY(cfqq) && cfq_cfqq_idle_window(cfqq) &&
	    (cfq_cfqq_slice_new(cfqq) ||
	    (cfqq->slice_end - now > now - cfqq->slice_start))) {
		cfq_clear_cfqq_deep(cfqq);
		cfq_clear_cfqq_idle_window(cfqq);
	}

	if (cfqq->dispatched && cfq_should_idle(cfqd, cfqq)) {
		cfqq = NULL;
		goto keep_queue;
	}

	/*
	 * If group idle is enabled and there are requests dispatched from
	 * this group, wait for requests to complete.
	 */
check_group_idle:
	if (cfqd->cfq_group_idle && cfqq->cfqg->nr_cfqq == 1 &&
	    cfqq->cfqg->dispatched) {
		cfqq = NULL;
		goto keep_queue;
	}

expire:
	cfq_slice_expired(cfqd, 0);
new_queue:
	/*
	 * Current queue expired. Check if we have to switch to a new
	 * service tree
	 */
	if (!new_cfqq)
		cfq_choose_cfqg(cfqd);

	cfqq = cfq_set_active_queue(cfqd, new_cfqq);
keep_queue:
	return cfqq;
}

static int __cfq_forced_dispatch_cfqq(struct cfq_queue *cfqq)
{
	int dispatched = 0;

	while (cfqq->next_rq) {
		cfq_dispatch_insert(cfqq->cfqd->queue, cfqq->next_rq);
		dispatched++;
	}

	BUG_ON(!list_empty(&cfqq->fifo));

	/* By default cfqq is not expired if it is empty. Do it explicitly */
	__cfq_slice_expired(cfqq->cfqd, cfqq, 0);
	return dispatched;
}

/*
 * Drain our current requests. Used for barriers and when switching
 * io schedulers on-the-fly.
 */
static int cfq_forced_dispatch(struct cfq_data *cfqd)
{
	struct cfq_queue *cfqq;
	int dispatched = 0;

	/* Expire the timeslice of the current active queue first */
	cfq_slice_expired(cfqd, 0);
	while ((cfqq = cfq_get_next_queue_forced(cfqd)) != NULL) {
		__cfq_set_active_queue(cfqd, cfqq);
		dispatched += __cfq_forced_dispatch_cfqq(cfqq);
	}

	BUG_ON(cfqd->busy_queues);

	cfq_log(cfqd, "forced_dispatch=%d", dispatched);
	return dispatched;
}

static inline bool cfq_slice_used_soon(struct cfq_data *cfqd,
	struct cfq_queue *cfqq)
{
	u64 now = ktime_get_ns();

	/* the queue hasn't finished any request, can't estimate */
	if (cfq_cfqq_slice_new(cfqq))
		return true;
	if (now + cfqd->cfq_slice_idle * cfqq->dispatched > cfqq->slice_end)
		return true;

	return false;
}

static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	unsigned int max_dispatch;

	if (cfq_cfqq_must_dispatch(cfqq))
		return true;

	/*
	 * Drain async requests before we start sync IO
	 */
	if (cfq_should_idle(cfqd, cfqq) && cfqd->rq_in_flight[BLK_RW_ASYNC])
		return false;

	/*
	 * If this is an async queue and we have sync IO in flight, let it wait
	 */
	if (cfqd->rq_in_flight[BLK_RW_SYNC] && !cfq_cfqq_sync(cfqq))
		return false;

	max_dispatch = max_t(unsigned int, cfqd->cfq_quantum / 2, 1);
	if (cfq_class_idle(cfqq))
		max_dispatch = 1;

	/*
	 * Does this cfqq already have too much IO in flight?
	 */
	if (cfqq->dispatched >= max_dispatch) {
		bool promote_sync = false;
		/*
		 * idle queue must always only have a single IO in flight
		 */
		if (cfq_class_idle(cfqq))
			return false;

		/*
		 * If there is only one sync queue
		 * we can ignore async queue here and give the sync
		 * queue no dispatch limit. The reason is a sync queue can
		 * preempt async queue, limiting the sync queue doesn't make
		 * sense. This is useful for aiostress test.
		 */
		if (cfq_cfqq_sync(cfqq) && cfqd->busy_sync_queues == 1)
			promote_sync = true;

		/*
		 * We have other queues, don't allow more IO from this one
		 */
		if (cfqd->busy_queues > 1 && cfq_slice_used_soon(cfqd, cfqq) &&
				!promote_sync)
			return false;

		/*
		 * Sole queue user, no limit
		 */
		if (cfqd->busy_queues == 1 || promote_sync)
			max_dispatch = -1;
		else
			/*
			 * Normally we start throttling cfqq when cfq_quantum/2
			 * requests have been dispatched. But we can drive
			 * deeper queue depths at the beginning of slice
			 * subjected to upper limit of cfq_quantum.
			 * */
			max_dispatch = cfqd->cfq_quantum;
	}

	/*
	 * Async queues must wait a bit before being allowed dispatch.
	 * We also ramp up the dispatch depth gradually for async IO,
	 * based on the last sync IO we serviced
	 */
	if (!cfq_cfqq_sync(cfqq) && cfqd->cfq_latency) {
		u64 last_sync = ktime_get_ns() - cfqd->last_delayed_sync;
		unsigned int depth;

		depth = div64_u64(last_sync, cfqd->cfq_slice[1]);
		if (!depth && !cfqq->dispatched)
			depth = 1;
		if (depth < max_dispatch)
			max_dispatch = depth;
	}

	/*
	 * If we're below the current max, allow a dispatch
	 */
	return cfqq->dispatched < max_dispatch;
}

/*
 * Dispatch a request from cfqq, moving them to the request queue
 * dispatch list.
 */
static bool cfq_dispatch_request(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	struct request *rq;

	BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list));

	rq = cfq_check_fifo(cfqq);
	if (rq)
		cfq_mark_cfqq_must_dispatch(cfqq);

	if (!cfq_may_dispatch(cfqd, cfqq))
		return false;

	/*
	 * follow expired path, else get first next available
	 */
	if (!rq)
		rq = cfqq->next_rq;
	else
		cfq_log_cfqq(cfqq->cfqd, cfqq, "fifo=%p", rq);

	/*
	 * insert request into driver dispatch list
	 */
	cfq_dispatch_insert(cfqd->queue, rq);

	if (!cfqd->active_cic) {
		struct cfq_io_cq *cic = RQ_CIC(rq);

		atomic_long_inc(&cic->icq.ioc->refcount);
		cfqd->active_cic = cic;
	}

	return true;
}

/*
 * Find the cfqq that we need to service and move a request from that to the
 * dispatch list
 */
static int cfq_dispatch_requests(struct request_queue *q, int force)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;
	struct cfq_queue *cfqq;

	if (!cfqd->busy_queues)
		return 0;

	if (unlikely(force))
		return cfq_forced_dispatch(cfqd);

	cfqq = cfq_select_queue(cfqd);
	if (!cfqq)
		return 0;

	/*
	 * Dispatch a request from this cfqq, if it is allowed
	 */
	if (!cfq_dispatch_request(cfqd, cfqq))
		return 0;

	cfqq->epoch_start = ktime_get_ns();
	
	cfqq->slice_dispatch++;
	cfq_clear_cfqq_must_dispatch(cfqq);

	/*
	 * expire an async queue immediately if it has used up its slice. idle
	 * queue always expire after 1 dispatch round.
	 */
	if (cfqd->busy_queues > 1 && ((!cfq_cfqq_sync(cfqq) &&
	    cfqq->slice_dispatch >= cfq_prio_to_maxrq(cfqd, cfqq)) ||
	    cfq_class_idle(cfqq))) {
		cfqq->slice_end = ktime_get_ns() + 1;
		cfq_slice_expired(cfqd, 0);
	}

	cfq_log_cfqq(cfqd, cfqq, "dispatched a request");
	return 1;
}

/*
 * task holds one reference to the queue, dropped when task exits. each rq
 * in-flight on this queue also holds a reference, dropped when rq is freed.
 *
 * Each cfq queue took a reference on the parent group. Drop it now.
 * queue lock must be held here.
 */
static void cfq_put_queue(struct cfq_queue *cfqq)
{
	struct cfq_data *cfqd = cfqq->cfqd;
	struct cfq_group *cfqg;

	BUG_ON(cfqq->ref <= 0);

	cfqq->ref--;
	if (cfqq->ref)
		return;

	cfq_log_cfqq(cfqd, cfqq, "put_queue");
	BUG_ON(rb_first(&cfqq->sort_list));
	BUG_ON(cfqq->allocated[READ] + cfqq->allocated[WRITE]);
	cfqg = cfqq->cfqg;

	if (unlikely(cfqd->active_queue == cfqq)) {
		__cfq_slice_expired(cfqd, cfqq, 0);
		cfq_schedule_dispatch(cfqd);
	}

	BUG_ON(cfq_cfqq_on_rr(cfqq));
	kmem_cache_free(cfq_pool, cfqq);
}

static void cfq_put_cooperator(struct cfq_queue *cfqq)
{
	struct cfq_queue *__cfqq, *next;

	/*
	 * If this queue was scheduled to merge with another queue, be
	 * sure to drop the reference taken on that queue (and others in
	 * the merge chain).  See cfq_setup_merge and cfq_merge_cfqqs.
	 */
	__cfqq = cfqq->new_cfqq;
	while (__cfqq) {
		if (__cfqq == cfqq) {
			WARN(1, "cfqq->new_cfqq loop detected\n");
			break;
		}
		next = __cfqq->new_cfqq;
		cfq_put_queue(__cfqq);
		__cfqq = next;
	}
}

static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	if (unlikely(cfqq == cfqd->active_queue)) {
		__cfq_slice_expired(cfqd, cfqq, 0);
		cfq_schedule_dispatch(cfqd);
	}

	cfq_put_cooperator(cfqq);

	cfq_put_queue(cfqq);
}

static void cfq_init_icq(struct io_cq *icq){}

static void cfq_exit_icq(struct io_cq *icq)
{
	struct cfq_io_cq *cic = icq_to_cic(icq);
	struct cfq_data *cfqd = cic_to_cfqd(cic);

	if (cic_to_cfqq(cic, false)) {
		cfq_exit_cfqq(cfqd, cic_to_cfqq(cic, false));
		cic_set_cfqq(cic, NULL, false);
	}

	if (cic_to_cfqq(cic, true)) {
		cfq_exit_cfqq(cfqd, cic_to_cfqq(cic, true));
		cic_set_cfqq(cic, NULL, true);
	}
}

static void cfq_init_prio_data(struct cfq_queue *cfqq, struct cfq_io_cq *cic)
{
	struct task_struct *tsk = current;
	int ioprio_class;

	if (!cfq_cfqq_prio_changed(cfqq))
		return;

	ioprio_class = IOPRIO_PRIO_CLASS(cic->ioprio);
	switch (ioprio_class) {
	default:
		printk(KERN_ERR "cfq: bad prio %x\n", ioprio_class);
	case IOPRIO_CLASS_NONE:
		/*
		 * no prio set, inherit CPU scheduling settings
		 */
		cfqq->ioprio = task_nice_ioprio(tsk);
		cfqq->ioprio_class = task_nice_ioclass(tsk);
		break;
	case IOPRIO_CLASS_RT:
		cfqq->ioprio = IOPRIO_PRIO_DATA(cic->ioprio);
		cfqq->ioprio_class = IOPRIO_CLASS_RT;
		break;
	case IOPRIO_CLASS_BE:
		cfqq->ioprio = IOPRIO_PRIO_DATA(cic->ioprio);
		cfqq->ioprio_class = IOPRIO_CLASS_BE;
		break;
	case IOPRIO_CLASS_IDLE:
		cfqq->ioprio_class = IOPRIO_CLASS_IDLE;
		cfqq->ioprio = 7;
		cfq_clear_cfqq_idle_window(cfqq);
		break;
	}

	/*
	 * keep track of original prio settings in case we have to temporarily
	 * elevate the priority of this queue
	 */
	cfqq->org_ioprio = cfqq->ioprio;
	cfqq->org_ioprio_class = cfqq->ioprio_class;
	cfq_clear_cfqq_prio_changed(cfqq);
}

static void check_ioprio_changed(struct cfq_io_cq *cic, struct bio *bio)
{
	int ioprio = cic->icq.ioc->ioprio;
	struct cfq_data *cfqd = cic_to_cfqd(cic);
	struct cfq_queue *cfqq;

	/*
	 * Check whether ioprio has changed.  The condition may trigger
	 * spuriously on a newly created cic but there's no harm.
	 */
	if (unlikely(!cfqd) || likely(cic->ioprio == ioprio))
		return;

	cfqq = cic_to_cfqq(cic, false);
	if (cfqq) {
		cfq_put_queue(cfqq);
		cfqq = cfq_get_queue(cfqd, BLK_RW_ASYNC, cic, bio);
		cic_set_cfqq(cic, cfqq, false);
	}

	cfqq = cic_to_cfqq(cic, true);
	if (cfqq)
		cfq_mark_cfqq_prio_changed(cfqq);

	cic->ioprio = ioprio;
}

static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
			  pid_t pid, bool is_sync)
{
	RB_CLEAR_NODE(&cfqq->rb_node);
	RB_CLEAR_NODE(&cfqq->p_node);
	INIT_LIST_HEAD(&cfqq->fifo);

	cfqq->ref = 0;
	cfqq->cfqd = cfqd;

	cfq_mark_cfqq_prio_changed(cfqq);

	if (is_sync) {
		if (!cfq_class_idle(cfqq))
			cfq_mark_cfqq_idle_window(cfqq);
		cfq_mark_cfqq_sync(cfqq);
	}
	cfqq->pid = pid;	
	cfqq->epoch_slice = 0;///xx
}

static inline void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
{
}

static struct cfq_queue **
cfq_async_queue_prio(struct cfq_group *cfqg, int ioprio_class, int ioprio)
{
	switch (ioprio_class) {
	case IOPRIO_CLASS_RT:
		return &cfqg->async_cfqq[0][ioprio];
	case IOPRIO_CLASS_NONE:
		ioprio = IOPRIO_NORM;
		/* fall through */
	case IOPRIO_CLASS_BE:
		return &cfqg->async_cfqq[1][ioprio];
	case IOPRIO_CLASS_IDLE:
		return &cfqg->async_idle_cfqq;
	default:
		BUG();
	}
}

static struct cfq_queue *
cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct cfq_io_cq *cic,
	      struct bio *bio)
{
	int ioprio_class = IOPRIO_PRIO_CLASS(cic->ioprio);
	int ioprio = IOPRIO_PRIO_DATA(cic->ioprio);
	struct cfq_queue **async_cfqq = NULL;
	struct cfq_queue *cfqq;
	struct cfq_group *cfqg;

	rcu_read_lock();
	cfqg = cfq_lookup_cfqg(cfqd, bio_blkcg(bio));
	if (!cfqg) {
		cfqq = &cfqd->oom_cfqq;
		goto out;
	}

	if (!is_sync) {
		if (!ioprio_valid(cic->ioprio)) {
			struct task_struct *tsk = current;
			ioprio = task_nice_ioprio(tsk);
			ioprio_class = task_nice_ioclass(tsk);
		}
		async_cfqq = cfq_async_queue_prio(cfqg, ioprio_class, ioprio);
		cfqq = *async_cfqq;
		if (cfqq)
			goto out;
	}

	cfqq = kmem_cache_alloc_node(cfq_pool,
				     GFP_NOWAIT | __GFP_ZERO | __GFP_NOWARN,
				     cfqd->queue->node);
	if (!cfqq) {
		cfqq = &cfqd->oom_cfqq;
		goto out;
	}

	/* cfq_init_cfqq() assumes cfqq->ioprio_class is initialized. */
	cfqq->ioprio_class = IOPRIO_CLASS_NONE;
	cfq_init_cfqq(cfqd, cfqq, current->pid, is_sync);
	cfq_init_prio_data(cfqq, cic);
	cfq_link_cfqq_cfqg(cfqq, cfqg);
	cfq_log_cfqq(cfqd, cfqq, "alloced");

	if (async_cfqq) {
		/* a new async queue is created, pin and remember */
		cfqq->ref++;
		*async_cfqq = cfqq;
	}
out:
	cfqq->ref++;
	rcu_read_unlock();
	return cfqq;
}

static void
cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_queue *cfqq,
		       struct request *rq)
{
	sector_t sdist = 0;
	sector_t n_sec = blk_rq_sectors(rq);
	if (cfqq->last_request_pos) {
		if (cfqq->last_request_pos < blk_rq_pos(rq))
			sdist = blk_rq_pos(rq) - cfqq->last_request_pos;
		else
			sdist = cfqq->last_request_pos - blk_rq_pos(rq);
	}

	cfqq->seek_history <<= 1;
	if (blk_queue_nonrot(cfqd->queue))
		cfqq->seek_history |= (n_sec < CFQQ_SECT_THR_NONROT);
	else
		cfqq->seek_history |= (sdist > CFQQ_SEEK_THR);
}

static inline bool req_noidle(struct request *req)
{
	return req_op(req) == REQ_OP_WRITE &&
		(req->cmd_flags & (REQ_SYNC | REQ_IDLE)) == REQ_SYNC;
}

/*
 * Disable idle window if the process thinks too long or seeks so much that
 * it doesn't matter
 */
static void
cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
		       struct cfq_io_cq *cic)
{
	int old_idle, enable_idle;

	/*
	 * Don't idle for async or idle io prio class
	 */
	if (!cfq_cfqq_sync(cfqq) || cfq_class_idle(cfqq))
		return;

	enable_idle = old_idle = cfq_cfqq_idle_window(cfqq);

	if (cfqq->queued[0] + cfqq->queued[1] >= 4)
		cfq_mark_cfqq_deep(cfqq);

	if (cfqq->next_rq && req_noidle(cfqq->next_rq))
		enable_idle = 0;
	else if (!atomic_read(&cic->icq.ioc->active_ref) ||
		 !cfqd->cfq_slice_idle ||
		 (!cfq_cfqq_deep(cfqq) && CFQQ_SEEKY(cfqq)))
		enable_idle = 0;

	if (old_idle != enable_idle) {
		cfq_log_cfqq(cfqd, cfqq, "idle=%d", enable_idle);
		if (enable_idle)
			cfq_mark_cfqq_idle_window(cfqq);
		else
			cfq_clear_cfqq_idle_window(cfqq);
	}
}

/*
 * Check if new_cfqq should preempt the currently active queue. Return 0 for
 * no or if we aren't sure, a 1 will cause a preempt.
 */
static bool
cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
		   struct request *rq)
{
	struct cfq_queue *cfqq;

	cfqq = cfqd->active_queue;
	if (!cfqq)
		return false;

	if (cfq_class_idle(new_cfqq))
		return false;

	if (cfq_class_idle(cfqq))
		return true;

	/*
	 * Don't allow a non-RT request to preempt an ongoing RT cfqq timeslice.
	 */
	if (cfq_class_rt(cfqq) && !cfq_class_rt(new_cfqq))
		return false;

	/*
	 * if the new request is sync, but the currently running queue is
	 * not, let the sync request have priority.
	 */
	if (rq_is_sync(rq) && !cfq_cfqq_sync(cfqq) && !cfq_cfqq_must_dispatch(cfqq))
		return true;

	if (cfq_slice_used(cfqq))
		return true;

	/*
	 * Allow an RT request to pre-empt an ongoing non-RT cfqq timeslice.
	 */
	if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq))
		return true;

	WARN_ON_ONCE(cfqq->ioprio_class != new_cfqq->ioprio_class);
	/* Allow preemption only if we are idling on sync-noidle tree */
	if (cfqd->serving_wl_type == SYNC_NOIDLE_WORKLOAD &&
	    cfqq_type(new_cfqq) == SYNC_NOIDLE_WORKLOAD &&
	    RB_EMPTY_ROOT(&cfqq->sort_list))
		return true;

	/*
	 * So both queues are sync. Let the new request get disk time if
	 * it's a metadata request and the current queue is doing regular IO.
	 */
	if ((rq->cmd_flags & REQ_PRIO) && !cfqq->prio_pending)
		return true;

	/* An idle queue should not be idle now for some reason */
	if (RB_EMPTY_ROOT(&cfqq->sort_list) && !cfq_should_idle(cfqd, cfqq))
		return true;

	if (!cfqd->active_cic || !cfq_cfqq_wait_request(cfqq))
		return false;

	/*
	 * if this request is as-good as one we would expect from the
	 * current cfqq, let it preempt
	 */
	if (cfq_rq_close(cfqd, cfqq, rq))
		return true;

	return false;
}

/*
 * cfqq preempts the active queue. if we allowed preempt with no slice left,
 * let it have half of its nominal slice.
 */
static void cfq_preempt_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	enum wl_type_t old_type = cfqq_type(cfqd->active_queue);

	cfq_log_cfqq(cfqd, cfqq, "preempt");
	cfq_slice_expired(cfqd, 1);

	/*
	 * workload type is changed, don't save slice, otherwise preempt
	 * doesn't happen
	 */
	if (old_type != cfqq_type(cfqq))
		cfqq->cfqg->saved_wl_slice = 0;

	/*
	 * Put the new queue at the front of the of the current list,
	 * so we know that it will be selected next.
	 */
	BUG_ON(!cfq_cfqq_on_rr(cfqq));

	cfq_service_tree_add(cfqd, cfqq, 1);

	cfqq->slice_end = 0;
	cfq_mark_cfqq_slice_new(cfqq);
}

/*
 * Called when a new fs request (rq) is added (to cfqq). Check if there's
 * something we should do about it
 */
static void
cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
		struct request *rq)
{
	struct cfq_io_cq *cic = RQ_CIC(rq);

	cfqd->rq_queued++;
	if (rq->cmd_flags & REQ_PRIO)
		cfqq->prio_pending++;

	cfq_update_io_seektime(cfqd, cfqq, rq);
	cfq_update_idle_window(cfqd, cfqq, cic);

	cfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);

	if (cfqq == cfqd->active_queue) {
		/*
		 * Remember that we saw a request from this process, but
		 * don't start queuing just yet. Otherwise we risk seeing lots
		 * of tiny requests, because we disrupt the normal plugging
		 * and merging. If the request is already larger than a single
		 * page, let it rip immediately. For that case we assume that
		 * merging is already done. Ditto for a busy system that
		 * has other work pending, don't risk delaying until the
		 * idle timer unplug to continue working.
		 */
		if (cfq_cfqq_wait_request(cfqq)) {
			if (blk_rq_bytes(rq) > PAGE_SIZE ||
			    cfqd->busy_queues > 1) {
				cfq_del_timer(cfqd, cfqq);
				cfq_clear_cfqq_wait_request(cfqq);
				__blk_run_queue(cfqd->queue);
			} else {
				cfq_mark_cfqq_must_dispatch(cfqq);
			}
		}
	} else if (cfq_should_preempt(cfqd, cfqq, rq)) {
		/*
		 * not the active queue - expire current slice if it is
		 * idle and has expired it's mean thinktime or this new queue
		 * has some old slice time left and is of higher priority or
		 * this new queue is RT and the current one is BE
		 */
		cfq_preempt_queue(cfqd, cfqq);
		__blk_run_queue(cfqd->queue);
	}
}

static void cfq_insert_request(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, "insert_request");
	cfq_init_prio_data(cfqq, RQ_CIC(rq));

	rq->fifo_time = ktime_get_ns() + cfqd->cfq_fifo_expire[rq_is_sync(rq)];
	list_add_tail(&rq->queuelist, &cfqq->fifo);
	cfq_add_rq_rb(rq);
	cfq_rq_enqueued(cfqd, cfqq, rq);
}

/*
 * Update hw_tag based on peak queue depth over 50 samples under
 * sufficient load.
 */
static void cfq_update_hw_tag(struct cfq_data *cfqd)
{
	struct cfq_queue *cfqq = cfqd->active_queue;

	if (cfqd->rq_in_driver > cfqd->hw_tag_est_depth)
		cfqd->hw_tag_est_depth = cfqd->rq_in_driver;

	if (cfqd->hw_tag == 1)
		return;

	if (cfqd->rq_queued <= CFQ_HW_QUEUE_MIN &&
	    cfqd->rq_in_driver <= CFQ_HW_QUEUE_MIN)
		return;

	/*
	 * If active queue hasn't enough requests and can idle, cfq might not
	 * dispatch sufficient requests to hardware. Don't zero hw_tag in this
	 * case
	 */
	if (cfqq && cfq_cfqq_idle_window(cfqq) &&
	    cfqq->dispatched + cfqq->queued[0] + cfqq->queued[1] <
	    CFQ_HW_QUEUE_MIN && cfqd->rq_in_driver < CFQ_HW_QUEUE_MIN)
		return;

	if (cfqd->hw_tag_samples++ < 50)
		return;

	if (cfqd->hw_tag_est_depth >= CFQ_HW_QUEUE_MIN)
		cfqd->hw_tag = 1;
	else
		cfqd->hw_tag = 0;
}

static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	u64 now = ktime_get_ns();

	/* If the queue already has requests, don't wait */
	if (!RB_EMPTY_ROOT(&cfqq->sort_list))
		return false;

	/* If there are other queues in the group, don't wait */
	if (cfqq->cfqg->nr_cfqq > 1)
		return false;

	if (cfq_slice_used(cfqq))
		return true;

	/*
	 * If think times is less than a jiffy than ttime_mean=0 and above
	 * will not be true. It might happen that slice has not expired yet
	 * but will expire soon (4-5 ns) during select_queue(). To cover the
	 * case where think time is less than a jiffy, mark the queue wait
	 * busy if only 1 jiffy is left in the slice.
	 */
	if (cfqq->slice_end - now <= jiffies_to_nsecs(1))
		return true;

	return false;
}

static void cfq_completed_request(struct request_queue *q, struct request *rq)
{
	struct cfq_queue *cfqq = RQ_CFQQ(rq);
	struct cfq_data *cfqd = cfqq->cfqd;
	const int sync = rq_is_sync(rq);
	u64 now = ktime_get_ns();
	int flag = 0;

	cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d", req_noidle(rq));

	cfq_update_hw_tag(cfqd);

	WARN_ON(!cfqd->rq_in_driver);
	WARN_ON(!cfqq->dispatched);
	cfqd->rq_in_driver--;
	cfqq->dispatched--;
	(RQ_CFQG(rq))->dispatched--;

	cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--;

	if (cfqd->cfq_is_anti) {
		cfqd->cfq_is_anti = 0;
		cfqd->cfq_tsrv_sum += (now - cfqd->cfq_tsrv_start);
		cfqd->cfq_tsrv_nr++;
		cfqd->cfq_tservice = cfqd->cfq_tsrv_sum / cfqd->cfq_tsrv_nr;
		cfqd->cfq_slice_idle = cfqd->cfq_tservice * (cfqd->cfq_alpha / (100 - cfqd->cfq_alpha));
		cfqd->cfq_tsrv_start = now;
	}

	if (sync) {
		struct cfq_rb_root *st;

		if (cfq_cfqq_on_rr(cfqq))
			st = cfqq->service_tree;
		else
			st = st_for(cfqq->cfqg, cfqq_class(cfqq),
					cfqq_type(cfqq));

		/*
		 * We have to do this check in jiffies since start_time is in
		 * jiffies and it is not trivial to convert to ns. If
		 * cfq_fifo_expire[1] ever comes close to 1 jiffie, this test
		 * will become problematic but so far we are fine (the default
		 * is 128 ms).
		 */
		if (!time_after(rq->start_time +
				  nsecs_to_jiffies(cfqd->cfq_fifo_expire[1]),
				jiffies))
			cfqd->last_delayed_sync = now;
	}

	cfqq->epoch_slice += (now - cfqq->epoch_start);
	if (cfqq->epoch_slice >= cfq_epoch_slice) {
		flag = 1;
	}

	/*
	 * If this is the active queue, check if it needs to be expired,
	 * or if we want to idle in case it has no pending requests.
	 */
	if (cfqd->active_queue == cfqq) {
		const bool cfqq_empty = RB_EMPTY_ROOT(&cfqq->sort_list);

		if (cfq_cfqq_slice_new(cfqq)) {
			cfq_set_prio_slice(cfqd, cfqq);
			cfq_clear_cfqq_slice_new(cfqq);
		}

		/*
		 * Should we wait for next request to come in before we expire
		 * the queue.
		 */
		if (cfq_should_wait_busy(cfqd, cfqq)) {
			cfqd->cfq_is_anti = 1; ///xx
			cfqd->cfq_tsrv_start = now;///xx
			u64 extend_sl = cfqd->cfq_slice_idle;
			if (!cfqd->cfq_slice_idle) 
				extend_sl = cfqd->cfq_group_idle;
			cfqq->slice_end = now + extend_sl;
			cfq_mark_cfqq_wait_busy(cfqq);
			cfq_log_cfqq(cfqd, cfqq, "will busy wait");
		}

		/*
		 * Idling is not enabled on:
		 * - expired queues
		 * - idle-priority queues
		 * - async queues
		 * - queues with still some requests queued
		 * - when there is a close cooperator
		 */
		if (cfq_slice_used(cfqq) || cfq_class_idle(cfqq))
			cfq_slice_expired(cfqd, 1);
		else if (sync && cfqq_empty &&
			 !cfq_close_cooperator(cfqd, cfqq)) {
			cfq_arm_slice_timer(cfqd);
		}
			 
		if (!cfqd->cfq_is_anti && !cfqq->queued[0] && !cfqq->queued[1]) {
			if (cfqd->active_queue)
				cfq_slice_expired(cfqd, 0);
		}

		if (flag && cfqd->active_queue)
			cfq_slice_expired(cfqd, 0);
	}

	if (!cfqd->rq_in_driver)
		cfq_schedule_dispatch(cfqd);
}

static void cfqq_boost_on_prio(struct cfq_queue *cfqq, unsigned int op)
{
	/*
	 * If REQ_PRIO is set, boost class and prio level, if it's below
	 * BE/NORM. If prio is not set, restore the potentially boosted
	 * class/prio level.
	 */
	if (!(op & REQ_PRIO)) {
		cfqq->ioprio_class = cfqq->org_ioprio_class;
		cfqq->ioprio = cfqq->org_ioprio;
	} else {
		if (cfq_class_idle(cfqq))
			cfqq->ioprio_class = IOPRIO_CLASS_BE;
		if (cfqq->ioprio > IOPRIO_NORM)
			cfqq->ioprio = IOPRIO_NORM;
	}
}

static inline int __cfq_may_queue(struct cfq_queue *cfqq)
{
	if (cfq_cfqq_wait_request(cfqq) && !cfq_cfqq_must_alloc_slice(cfqq)) {
		cfq_mark_cfqq_must_alloc_slice(cfqq);
		return ELV_MQUEUE_MUST;
	}

	return ELV_MQUEUE_MAY;
}

static int cfq_may_queue(struct request_queue *q, unsigned int op)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;
	struct task_struct *tsk = current;
	struct cfq_io_cq *cic;
	struct cfq_queue *cfqq;

	/*
	 * don't force setup of a queue from here, as a call to may_queue
	 * does not necessarily imply that a request actually will be queued.
	 * so just lookup a possibly existing queue, or return 'may queue'
	 * if that fails
	 */
	cic = cfq_cic_lookup(cfqd, tsk->io_context);
	if (!cic)
		return ELV_MQUEUE_MAY;

	cfqq = cic_to_cfqq(cic, op_is_sync(op));
	if (cfqq) {
		cfq_init_prio_data(cfqq, cic);
		cfqq_boost_on_prio(cfqq, op);

		return __cfq_may_queue(cfqq);
	}

	return ELV_MQUEUE_MAY;
}

/*
 * queue lock held here
 */
static void cfq_put_request(struct request *rq)
{
	struct cfq_queue *cfqq = RQ_CFQQ(rq);

	if (cfqq) {
		const int rw = rq_data_dir(rq);

		BUG_ON(!cfqq->allocated[rw]);
		cfqq->allocated[rw]--;

		/* Put down rq reference on cfqg */
		rq->elv.priv[0] = NULL;
		rq->elv.priv[1] = NULL;

		cfq_put_queue(cfqq);
	}
}

static struct cfq_queue *
cfq_merge_cfqqs(struct cfq_data *cfqd, struct cfq_io_cq *cic,
		struct cfq_queue *cfqq)
{
	cfq_log_cfqq(cfqd, cfqq, "merging with queue %p", cfqq->new_cfqq);
	cic_set_cfqq(cic, cfqq->new_cfqq, 1);
	cfq_mark_cfqq_coop(cfqq->new_cfqq);
	cfq_put_queue(cfqq);
	return cic_to_cfqq(cic, 1);
}

/*
 * Returns NULL if a new cfqq should be allocated, or the old cfqq if this
 * was the last process referring to said cfqq.
 */
static struct cfq_queue *
split_cfqq(struct cfq_io_cq *cic, struct cfq_queue *cfqq)
{
	if (cfqq_process_refs(cfqq) == 1) {
		cfqq->pid = current->pid;
		cfq_clear_cfqq_coop(cfqq);
		cfq_clear_cfqq_split_coop(cfqq);
		return cfqq;
	}

	cic_set_cfqq(cic, NULL, 1);

	cfq_put_cooperator(cfqq);

	cfq_put_queue(cfqq);
	return NULL;
}
/*
 * Allocate cfq data structures associated with this request.
 */
static int
cfq_set_request(struct request_queue *q, struct request *rq, struct bio *bio,
		gfp_t gfp_mask)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;
	struct cfq_io_cq *cic = icq_to_cic(rq->elv.icq);
	const int rw = rq_data_dir(rq);
	const bool is_sync = rq_is_sync(rq);
	struct cfq_queue *cfqq;

	spin_lock_irq(q->queue_lock);

	check_ioprio_changed(cic, bio);
	check_blkcg_changed(cic, bio);
new_queue:
	cfqq = cic_to_cfqq(cic, is_sync);
	if (!cfqq || cfqq == &cfqd->oom_cfqq) {
		if (cfqq)
			cfq_put_queue(cfqq);
		cfqq = cfq_get_queue(cfqd, is_sync, cic, bio);
		cic_set_cfqq(cic, cfqq, is_sync);
	} else {
		/*
		 * If the queue was seeky for too long, break it apart.
		 */
		if (cfq_cfqq_coop(cfqq) && cfq_cfqq_split_coop(cfqq)) {
			cfq_log_cfqq(cfqd, cfqq, "breaking apart cfqq");
			cfqq = split_cfqq(cic, cfqq);
			if (!cfqq)
				goto new_queue;
		}

		/*
		 * Check to see if this queue is scheduled to merge with
		 * another, closely cooperating queue.  The merging of
		 * queues happens here as it must be done in process context.
		 * The reference on new_cfqq was taken in merge_cfqqs.
		 */
		if (cfqq->new_cfqq)
			cfqq = cfq_merge_cfqqs(cfqd, cic, cfqq);
	}

	cfqq->allocated[rw]++;

	cfqq->ref++;
	rq->elv.priv[0] = cfqq;
	rq->elv.priv[1] = cfqq->cfqg;
	spin_unlock_irq(q->queue_lock);

	return 0;
}

static void cfq_kick_queue(struct work_struct *work)
{
	struct cfq_data *cfqd =
		container_of(work, struct cfq_data, unplug_work);
	struct request_queue *q = cfqd->queue;

	spin_lock_irq(q->queue_lock);
	__blk_run_queue(cfqd->queue);
	spin_unlock_irq(q->queue_lock);
}

/*
 * Timer running if the active_queue is currently idling inside its time slice
 */
static enum hrtimer_restart cfq_idle_slice_timer(struct hrtimer *timer)
{
	struct cfq_data *cfqd = container_of(timer, struct cfq_data,
					     idle_slice_timer);
	struct cfq_queue *cfqq;
	unsigned long flags;
	int timed_out = 1;

	cfq_log(cfqd, "idle timer fired");

	spin_lock_irqsave(cfqd->queue->queue_lock, flags);

	cfqq = cfqd->active_queue;
	if (cfqq) {
		timed_out = 0;

		/*
		 * We saw a request before the queue expired, let it through
		 */
		if (cfq_cfqq_must_dispatch(cfqq))
			goto out_kick;

		/*
		 * expired
		 */
		if (cfq_slice_used(cfqq))
			goto expire;

		/*
		 * only expire and reinvoke request handler, if there are
		 * other queues with pending requests
		 */
		if (!cfqd->busy_queues)
			goto out_cont;

		/*
		 * not expired and it has a request pending, let it dispatch
		 */
		if (!RB_EMPTY_ROOT(&cfqq->sort_list))
			goto out_kick;

		/*
		 * Queue depth flag is reset only when the idle didn't succeed
		 */
		cfq_clear_cfqq_deep(cfqq);
	}
expire:
	cfq_slice_expired(cfqd, timed_out);
out_kick:
	cfq_schedule_dispatch(cfqd);
out_cont:
	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
	return HRTIMER_NORESTART;
}

static void cfq_shutdown_timer_wq(struct cfq_data *cfqd)
{
	hrtimer_cancel(&cfqd->idle_slice_timer);
	cancel_work_sync(&cfqd->unplug_work);
}

static void cfq_exit_queue(struct elevator_queue *e)
{
	struct cfq_data *cfqd = e->elevator_data;
	struct request_queue *q = cfqd->queue;

	cfq_shutdown_timer_wq(cfqd);

	spin_lock_irq(q->queue_lock);

	if (cfqd->active_queue)
		__cfq_slice_expired(cfqd, cfqd->active_queue, 0);

	spin_unlock_irq(q->queue_lock);

	cfq_shutdown_timer_wq(cfqd);

	kfree(cfqd->root_group);
	kfree(cfqd);
}

static int cfq_init_queue(struct request_queue *q, struct elevator_type *e)
{
	struct cfq_data *cfqd;
	struct blkcg_gq *blkg __maybe_unused;
	int i, ret;
	struct elevator_queue *eq;

	eq = elevator_alloc(q, e);
	if (!eq)
		return -ENOMEM;

	cfqd = kzalloc_node(sizeof(*cfqd), GFP_KERNEL, q->node);
	if (!cfqd) {
		kobject_put(&eq->kobj);
		return -ENOMEM;
	}
	eq->elevator_data = cfqd;

	cfqd->queue = q;
	spin_lock_irq(q->queue_lock);
	q->elevator = eq;
	spin_unlock_irq(q->queue_lock);

	/* Init root service tree */
	cfqd->grp_service_tree = CFQ_RB_ROOT;

	/* Init root group and prefer root group over other groups by default */
	ret = -ENOMEM;
	cfqd->root_group = kzalloc_node(sizeof(*cfqd->root_group),
					GFP_KERNEL, cfqd->queue->node);
	if (!cfqd->root_group)
		goto out_free;

	cfq_init_cfqg_base(cfqd->root_group);
	cfqd->root_group->weight = 2 * CFQ_WEIGHT_LEGACY_DFL;
	cfqd->root_group->leaf_weight = 2 * CFQ_WEIGHT_LEGACY_DFL;

	/*
	 * Not strictly needed (since RB_ROOT just clears the node and we
	 * zeroed cfqd on alloc), but better be safe in case someone decides
	 * to add magic to the rb code
	 */
	for (i = 0; i < CFQ_PRIO_LISTS; i++)
		cfqd->prio_trees[i] = RB_ROOT;

	/*
	 * Our fallback cfqq if cfq_get_queue() runs into OOM issues.
	 * Grab a permanent reference to it, so that the normal code flow
	 * will not attempt to free it.  oom_cfqq is linked to root_group
	 * but shouldn't hold a reference as it'll never be unlinked.  Lose
	 * the reference from linking right away.
	 */
	cfq_init_cfqq(cfqd, &cfqd->oom_cfqq, 1, 0);
	cfqd->oom_cfqq.ref++;

	spin_lock_irq(q->queue_lock);
	cfq_link_cfqq_cfqg(&cfqd->oom_cfqq, cfqd->root_group);
	spin_unlock_irq(q->queue_lock);

	hrtimer_init(&cfqd->idle_slice_timer, CLOCK_MONOTONIC,
		     HRTIMER_MODE_REL);
	cfqd->idle_slice_timer.function = cfq_idle_slice_timer;

	INIT_WORK(&cfqd->unplug_work, cfq_kick_queue);

	cfqd->cfq_alpha = cfq_alpha;///xx
	cfqd->cfq_tservice = cfq_tservice;///xx
	cfqd->cfq_tsrv_nr = cfq_tsrv_nr;///xx
	cfqd->cfq_tsrv_sum = cfq_tsrv_sum;///xx
	cfqd->cfq_is_anti = 0;

	cfqd->cfq_quantum = cfq_quantum;
	cfqd->cfq_fifo_expire[0] = cfq_fifo_expire[0];
	cfqd->cfq_fifo_expire[1] = cfq_fifo_expire[1];
	cfqd->cfq_slice[0] = cfq_slice_async;
	cfqd->cfq_slice[1] = cfq_slice_sync;
	cfqd->cfq_target_latency = cfq_target_latency;
	cfqd->cfq_slice_async_rq = cfq_slice_async_rq;
	cfqd->cfq_slice_idle = cfq_slice_idle;
	cfqd->cfq_group_idle = cfq_group_idle;
	cfqd->cfq_latency = 1;
	cfqd->hw_tag = -1;
	/*
	 * we optimistically start assuming sync ops weren't delayed in last
	 * second, in order to have larger depth for async operations.
	 */
	cfqd->last_delayed_sync = ktime_get_ns() - NSEC_PER_SEC;
	return 0;

out_free:
	kfree(cfqd);
	kobject_put(&eq->kobj);
	return ret;
}

static void cfq_registered_queue(struct request_queue *q)
{
	struct elevator_queue *e = q->elevator;
	struct cfq_data *cfqd = e->elevator_data;
	
	cfqd->cfq_slice_idle = cfqd->cfq_tservice * (cfqd->cfq_alpha / (100 - cfqd->cfq_alpha));///xx
	wbt_disable_default(q);
}

static struct elv_fs_entry cfq_attrs[] = {
	__ATTR_NULL
};

static struct elevator_type iosched_cfq = {
	.ops.sq = {
		.elevator_merge_fn = 		cfq_merge,
		.elevator_merged_fn =		cfq_merged_request,
		.elevator_merge_req_fn =	cfq_merged_requests,
		.elevator_allow_bio_merge_fn =	cfq_allow_bio_merge,
		.elevator_allow_rq_merge_fn =	cfq_allow_rq_merge,
		.elevator_bio_merged_fn =	cfq_bio_merged,
		.elevator_dispatch_fn =		cfq_dispatch_requests,
		.elevator_add_req_fn =		cfq_insert_request,
		.elevator_activate_req_fn =	cfq_activate_request,
		.elevator_deactivate_req_fn =	cfq_deactivate_request,
		.elevator_completed_req_fn =	cfq_completed_request,
		.elevator_former_req_fn =	elv_rb_former_request,
		.elevator_latter_req_fn =	elv_rb_latter_request,
		.elevator_init_icq_fn =		cfq_init_icq,
		.elevator_exit_icq_fn =		cfq_exit_icq,
		.elevator_set_req_fn =		cfq_set_request,
		.elevator_put_req_fn =		cfq_put_request,
		.elevator_may_queue_fn =	cfq_may_queue,
		.elevator_init_fn =		cfq_init_queue,
		.elevator_exit_fn =		cfq_exit_queue,
		.elevator_registered_fn =	cfq_registered_queue,
	},
	.icq_size	=	sizeof(struct cfq_io_cq),
	.icq_align	=	__alignof__(struct cfq_io_cq),
	.elevator_attrs =	cfq_attrs,
	.elevator_name	=	"fios2",
	.elevator_owner =	THIS_MODULE,
};

static int __init cfq_init(void)
{
	int ret;
	cfq_group_idle = 0;

	ret = -ENOMEM;
	cfq_pool = KMEM_CACHE(cfq_queue, 0);
	if (!cfq_pool)
		goto err_pol_unreg;

	ret = elv_register(&iosched_cfq);
	if (ret)
		goto err_free_pool;

	return 0;

err_free_pool:
	kmem_cache_destroy(cfq_pool);
err_pol_unreg:
	return ret;
}

static void __exit cfq_exit(void)
{
	elv_unregister(&iosched_cfq);
	kmem_cache_destroy(cfq_pool);
}

module_init(cfq_init);
module_exit(cfq_exit);

MODULE_AUTHOR("Jens Axboe");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Completely Fair Queueing IO scheduler");