cfq-iosched: Convert from jiffies to nanoseconds

Convert all time-keeping in CFQ IO scheduler from jiffies to nanoseconds
so that we can later make the intervals more fine-grained than jiffies.
One jiffie is several miliseconds and even for today's rotating disks
that is a noticeable amount of time and thus we leave disk unnecessarily
idle.
Signed-off-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

block/cfq-iosched.c

@@ -10,7 +10,7 @@
 #include <linux/slab.h>
 #include <linux/blkdev.h>
 #include <linux/elevator.h>
-#include <linux/jiffies.h>
+#include <linux/ktime.h>
 #include <linux/rbtree.h>
 #include <linux/ioprio.h>
 #include <linux/blktrace_api.h>
@@ -22,28 +22,28 @@
  */
 /* max queue in one round of service */
 static const int cfq_quantum = 8;
-static const int cfq_fifo_expire[2] = { HZ / 4, HZ / 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 int cfq_slice_sync = HZ / 10;
-static int cfq_slice_async = HZ / 25;
+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 int cfq_slice_idle = HZ / 125;
-static int cfq_group_idle = HZ / 125;
-static const int cfq_target_latency = HZ * 3/10; /* 300 ms */
+static 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 service tree
  */
-#define CFQ_IDLE_DELAY		(HZ / 5)
+#define CFQ_IDLE_DELAY		(NSEC_PER_SEC / 5)
 
 /*
  * below this threshold, we consider thinktime immediate
  */
-#define CFQ_MIN_TT		(2)
+#define CFQ_MIN_TT		(2 * NSEC_PER_SEC / HZ)
 
 #define CFQ_SLICE_SCALE		(5)
 #define CFQ_HW_QUEUE_MIN	(5)
@@ -73,11 +73,11 @@ static struct kmem_cache *cfq_pool;
 #define CFQ_WEIGHT_LEGACY_MAX	1000
 
 struct cfq_ttime {
-	unsigned long last_end_request;
+	u64 last_end_request;
 
-	unsigned long ttime_total;
+	u64 ttime_total;
+	u64 ttime_mean;
 	unsigned long ttime_samples;
-	unsigned long ttime_mean;
 };
 
 /*
@@ -94,7 +94,7 @@ struct cfq_rb_root {
 	struct cfq_ttime ttime;
 };
 #define CFQ_RB_ROOT	(struct cfq_rb_root) { .rb = RB_ROOT, \
-			.ttime = {.last_end_request = jiffies,},}
+			.ttime = {.last_end_request = ktime_get_ns(),},}
 
 /*
  * Per process-grouping structure
@@ -109,7 +109,7 @@ struct cfq_queue {
 	/* service_tree member */
 	struct rb_node rb_node;
 	/* service_tree key */
-	unsigned long rb_key;
+	u64 rb_key;
 	/* prio tree member */
 	struct rb_node p_node;
 	/* prio tree root we belong to, if any */
@@ -126,13 +126,13 @@ struct cfq_queue {
 	struct list_head fifo;
 
 	/* time when queue got scheduled in to dispatch first request. */
-	unsigned long dispatch_start;
-	unsigned int allocated_slice;
-	unsigned int slice_dispatch;
+	u64 dispatch_start;
+	u64 allocated_slice;
+	u64 slice_dispatch;
 	/* time when first request from queue completed and slice started. */
-	unsigned long slice_start;
-	unsigned long slice_end;
-	long slice_resid;
+	u64 slice_start;
+	u64 slice_end;
+	u64 slice_resid;
 
 	/* pending priority requests */
 	int prio_pending;
@@ -290,7 +290,7 @@ struct cfq_group {
 	struct cfq_rb_root service_trees[2][3];
 	struct cfq_rb_root service_tree_idle;
 
-	unsigned long saved_wl_slice;
+	u64 saved_wl_slice;
 	enum wl_type_t saved_wl_type;
 	enum wl_class_t saved_wl_class;
 
@@ -329,7 +329,7 @@ struct cfq_data {
 	 */
 	enum wl_class_t serving_wl_class;
 	enum wl_type_t serving_wl_type;
-	unsigned long workload_expires;
+	u64 workload_expires;
 	struct cfq_group *serving_group;
 
 	/*
@@ -374,22 +374,22 @@ struct cfq_data {
 	 * tunables, see top of file
 	 */
 	unsigned int cfq_quantum;
-	unsigned int cfq_fifo_expire[2];
 	unsigned int cfq_back_penalty;
 	unsigned int cfq_back_max;
-	unsigned int cfq_slice[2];
 	unsigned int cfq_slice_async_rq;
-	unsigned int cfq_slice_idle;
-	unsigned int cfq_group_idle;
 	unsigned int cfq_latency;
-	unsigned int cfq_target_latency;
+	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;
 
-	unsigned long last_delayed_sync;
+	u64 last_delayed_sync;
 };
 
 static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd);
@@ -676,7 +676,7 @@ static inline void cfqg_stats_update_io_add(struct cfq_group *cfqg,
 }
 
 static inline void cfqg_stats_update_timeslice_used(struct cfq_group *cfqg,
-			unsigned long time, unsigned long unaccounted_time)
+			uint64_t time, unsigned long unaccounted_time)
 {
 	blkg_stat_add(&cfqg->stats.time, time);
 #ifdef CONFIG_DEBUG_BLK_CGROUP
@@ -788,7 +788,7 @@ static inline void cfqg_put(struct cfq_group *cfqg) { }
 static inline void cfqg_stats_update_io_add(struct cfq_group *cfqg,
 			struct cfq_group *curr_cfqg, int op, int op_flags) { }
 static inline void cfqg_stats_update_timeslice_used(struct cfq_group *cfqg,
-			unsigned long time, unsigned long unaccounted_time) { }
+			uint64_t time, unsigned long unaccounted_time) { }
 static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int op,
 			int op_flags) { }
 static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int op,
@@ -815,7 +815,7 @@ static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
 static inline bool cfq_io_thinktime_big(struct cfq_data *cfqd,
 	struct cfq_ttime *ttime, bool group_idle)
 {
-	unsigned long slice;
+	u64 slice;
 	if (!sample_valid(ttime->ttime_samples))
 		return false;
 	if (group_idle)
@@ -938,17 +938,18 @@ static inline void cfq_schedule_dispatch(struct cfq_data *cfqd)
  * if a queue is marked sync and has sync io queued. A sync queue with async
  * io only, should not get full sync slice length.
  */
-static inline int cfq_prio_slice(struct cfq_data *cfqd, bool sync,
+static inline u64 cfq_prio_slice(struct cfq_data *cfqd, bool sync,
 				 unsigned short prio)
 {
-	const int base_slice = cfqd->cfq_slice[sync];
+	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 + (base_slice/CFQ_SLICE_SCALE * (4 - prio));
+	return base_slice + (slice * (4 - prio));
 }
 
-static inline int
+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);
@@ -966,15 +967,14 @@ cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
  *
  * The result is also in fixed point w/ CFQ_SERVICE_SHIFT.
  */
-static inline u64 cfqg_scale_charge(unsigned long charge,
+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;
-	do_div(c, vfraction);
-	return c;
+	return div_u64(c, vfraction);
 }
 
 static inline u64 max_vdisktime(u64 min_vdisktime, u64 vdisktime)
@@ -1027,16 +1027,16 @@ static inline unsigned cfq_group_get_avg_queues(struct cfq_data *cfqd,
 	return cfqg->busy_queues_avg[rt];
 }
 
-static inline unsigned
+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 unsigned
+static inline u64
 cfq_scaled_cfqq_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
-	unsigned slice = cfq_prio_to_slice(cfqd, cfqq);
+	u64 slice = cfq_prio_to_slice(cfqd, cfqq);
 	if (cfqd->cfq_latency) {
 		/*
 		 * interested queues (we consider only the ones with the same
@@ -1044,20 +1044,22 @@ cfq_scaled_cfqq_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 		 */
 		unsigned iq = cfq_group_get_avg_queues(cfqd, cfqq->cfqg,
 						cfq_class_rt(cfqq));
-		unsigned sync_slice = cfqd->cfq_slice[1];
-		unsigned expect_latency = sync_slice * iq;
-		unsigned group_slice = cfq_group_slice(cfqd, cfqq->cfqg);
+		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) {
-			unsigned base_low_slice = 2 * cfqd->cfq_slice_idle;
+			u64 base_low_slice = 2 * cfqd->cfq_slice_idle;
+			u64 low_slice;
+
 			/* scale low_slice according to IO priority
 			 * and sync vs async */
-			unsigned low_slice =
-				min(slice, base_low_slice * slice / sync_slice);
+			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 = max(slice * group_slice / expect_latency,
-				    low_slice);
+			slice = div64_u64(slice*group_slice, expect_latency);
+			slice = max(slice, low_slice);
 		}
 	}
 	return slice;
@@ -1066,12 +1068,13 @@ cfq_scaled_cfqq_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 static inline void
 cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
-	unsigned slice = cfq_scaled_cfqq_slice(cfqd, cfqq);
+	u64 slice = cfq_scaled_cfqq_slice(cfqd, cfqq);
+	u64 now = ktime_get_ns();
 
-	cfqq->slice_start = jiffies;
-	cfqq->slice_end = jiffies + slice;
+	cfqq->slice_start = now;
+	cfqq->slice_end = now + slice;
 	cfqq->allocated_slice = slice;
-	cfq_log_cfqq(cfqd, cfqq, "set_slice=%lu", cfqq->slice_end - jiffies);
+	cfq_log_cfqq(cfqd, cfqq, "set_slice=%llu", cfqq->slice_end - now);
 }
 
 /*
@@ -1083,7 +1086,7 @@ static inline bool cfq_slice_used(struct cfq_queue *cfqq)
 {
 	if (cfq_cfqq_slice_new(cfqq))
 		return false;
-	if (time_before(jiffies, cfqq->slice_end))
+	if (ktime_get_ns() < cfqq->slice_end)
 		return false;
 
 	return true;
@@ -1249,7 +1252,7 @@ cfq_find_next_rq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	return cfq_choose_req(cfqd, next, prev, blk_rq_pos(last));
 }
 
-static unsigned long cfq_slice_offset(struct cfq_data *cfqd,
+static u64 cfq_slice_offset(struct cfq_data *cfqd,
 			    struct cfq_queue *cfqq)
 {
 	/*
@@ -1443,31 +1446,31 @@ cfq_group_notify_queue_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	cfqg_stats_update_dequeue(cfqg);
 }
 
-static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq,
-						unsigned int *unaccounted_time)
+static inline u64 cfq_cfqq_slice_usage(struct cfq_queue *cfqq,
+				       u64 *unaccounted_time)
 {
-	unsigned int slice_used;
+	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 == jiffies) {
+	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(unsigned, (jiffies - cfqq->dispatch_start),
-					1);
+		slice_used = max_t(u64, (now - cfqq->dispatch_start), 1);
 	} else {
-		slice_used = jiffies - cfqq->slice_start;
+		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 (time_after(cfqq->slice_start, cfqq->dispatch_start))
+		if (cfqq->slice_start > cfqq->dispatch_start)
 			*unaccounted_time += cfqq->slice_start -
 					cfqq->dispatch_start;
 	}
@@ -1479,10 +1482,11 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 				struct cfq_queue *cfqq)
 {
 	struct cfq_rb_root *st = &cfqd->grp_service_tree;
-	unsigned int used_sl, charge, unaccounted_sl = 0;
+	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);
@@ -1504,9 +1508,8 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 	cfq_group_service_tree_add(st, cfqg);
 
 	/* This group is being expired. Save the context */
-	if (time_after(cfqd->workload_expires, jiffies)) {
-		cfqg->saved_wl_slice = cfqd->workload_expires
-						- jiffies;
+	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
@@ -1515,7 +1518,7 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 	cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime,
 					st->min_vdisktime);
 	cfq_log_cfqq(cfqq->cfqd, cfqq,
-		     "sl_used=%u disp=%u charge=%u iops=%u sect=%lu",
+		     "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);
@@ -1538,7 +1541,7 @@ static void cfq_init_cfqg_base(struct cfq_group *cfqg)
 		*st = CFQ_RB_ROOT;
 	RB_CLEAR_NODE(&cfqg->rb_node);
 
-	cfqg->ttime.last_end_request = jiffies;
+	cfqg->ttime.last_end_request = ktime_get_ns();
 }
 
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
@@ -2221,10 +2224,11 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 {
 	struct rb_node **p, *parent;
 	struct cfq_queue *__cfqq;
-	unsigned long rb_key;
+	u64 rb_key;
 	struct cfq_rb_root *st;
 	int left;
 	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)) {
@@ -2234,7 +2238,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			__cfqq = rb_entry(parent, struct cfq_queue, rb_node);
 			rb_key += __cfqq->rb_key;
 		} else
-			rb_key += jiffies;
+			rb_key += now;
 	} else if (!add_front) {
 		/*
 		 * Get our rb key offset. Subtract any residual slice
@@ -2242,13 +2246,13 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		 * count indicates slice overrun, and this should position
 		 * the next service time further away in the tree.
 		 */
-		rb_key = cfq_slice_offset(cfqd, cfqq) + jiffies;
+		rb_key = cfq_slice_offset(cfqd, cfqq) + now;
 		rb_key -= cfqq->slice_resid;
 		cfqq->slice_resid = 0;
 	} else {
-		rb_key = -HZ;
+		rb_key = -NSEC_PER_SEC;
 		__cfqq = cfq_rb_first(st);
-		rb_key += __cfqq ? __cfqq->rb_key : jiffies;
+		rb_key += __cfqq ? __cfqq->rb_key : now;
 	}
 
 	if (!RB_EMPTY_NODE(&cfqq->rb_node)) {
@@ -2274,7 +2278,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		/*
 		 * sort by key, that represents service time.
 		 */
-		if (time_before(rb_key, __cfqq->rb_key))
+		if (rb_key < __cfqq->rb_key)
 			p = &parent->rb_left;
 		else {
 			p = &parent->rb_right;
@@ -2574,7 +2578,7 @@ cfq_merged_requests(struct request_queue *q, struct request *rq,
 	 * reposition in fifo if next is older than rq
 	 */
 	if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
-	    time_before(next->fifo_time, rq->fifo_time) &&
+	    next->fifo_time < rq->fifo_time &&
 	    cfqq == RQ_CFQQ(next)) {
 		list_move(&rq->queuelist, &next->queuelist);
 		rq->fifo_time = next->fifo_time;
@@ -2635,7 +2639,7 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd,
 				cfqd->serving_wl_class, cfqd->serving_wl_type);
 		cfqg_stats_update_avg_queue_size(cfqq->cfqg);
 		cfqq->slice_start = 0;
-		cfqq->dispatch_start = jiffies;
+		cfqq->dispatch_start = ktime_get_ns();
 		cfqq->allocated_slice = 0;
 		cfqq->slice_end = 0;
 		cfqq->slice_dispatch = 0;
@@ -2684,8 +2688,8 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		if (cfq_cfqq_slice_new(cfqq))
 			cfqq->slice_resid = cfq_scaled_cfqq_slice(cfqd, cfqq);
 		else
-			cfqq->slice_resid = cfqq->slice_end - jiffies;
-		cfq_log_cfqq(cfqd, cfqq, "resid=%ld", cfqq->slice_resid);
+			cfqq->slice_resid = cfqq->slice_end - ktime_get_ns();
+		cfq_log_cfqq(cfqd, cfqq, "resid=%llu", cfqq->slice_resid);
 	}
 
 	cfq_group_served(cfqd, cfqq->cfqg, cfqq);
@@ -2919,7 +2923,8 @@ 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;
-	unsigned long sl, group_idle = 0;
+	u64 sl, group_idle = 0;
+	u64 now = ktime_get_ns();
 
 	/*
 	 * SSD device without seek penalty, disable idling. But only do so
@@ -2962,8 +2967,8 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	 * time slice.
 	 */
 	if (sample_valid(cic->ttime.ttime_samples) &&
-	    (cfqq->slice_end - jiffies < cic->ttime.ttime_mean)) {
-		cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%lu",
+	    (cfqq->slice_end - now < cic->ttime.ttime_mean)) {
+		cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%llu",
 			     cic->ttime.ttime_mean);
 		return;
 	}
@@ -2984,9 +2989,9 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	else
 		sl = cfqd->cfq_slice_idle;
 
-	mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
+	mod_timer(&cfqd->idle_slice_timer, now + sl);
 	cfqg_stats_set_start_idle_time(cfqq->cfqg);
-	cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu group_idle: %d", sl,
+	cfq_log_cfqq(cfqd, cfqq, "arm_idle: %llu group_idle: %d", sl,
 			group_idle ? 1 : 0);
 }
 
@@ -3026,7 +3031,7 @@ static struct request *cfq_check_fifo(struct cfq_queue *cfqq)
 		return NULL;
 
 	rq = rq_entry_fifo(cfqq->fifo.next);
-	if (time_before(jiffies, rq->fifo_time))
+	if (ktime_get_ns() < rq->fifo_time)
 		rq = NULL;
 
 	cfq_log_cfqq(cfqq->cfqd, cfqq, "fifo=%p", rq);
@@ -3104,14 +3109,14 @@ static enum wl_type_t cfq_choose_wl_type(struct cfq_data *cfqd,
 	struct cfq_queue *queue;
 	int i;
 	bool key_valid = false;
-	unsigned long lowest_key = 0;
+	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 || time_before(queue->rb_key, lowest_key))) {
+		    (!key_valid || queue->rb_key < lowest_key)) {
 			lowest_key = queue->rb_key;
 			cur_best = i;
 			key_valid = true;
@@ -3124,11 +3129,12 @@ static enum wl_type_t cfq_choose_wl_type(struct cfq_data *cfqd,
 static void
 choose_wl_class_and_type(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
-	unsigned slice;
+	u64 slice;
 	unsigned count;
 	struct cfq_rb_root *st;
-	unsigned group_slice;
+	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))
@@ -3137,7 +3143,7 @@ choose_wl_class_and_type(struct cfq_data *cfqd, struct cfq_group *cfqg)
 		cfqd->serving_wl_class = BE_WORKLOAD;
 	else {
 		cfqd->serving_wl_class = IDLE_WORKLOAD;
-		cfqd->workload_expires = jiffies + 1;
+		cfqd->workload_expires = now + jiffies_to_nsecs(1);
 		return;
 	}
 
@@ -3155,7 +3161,7 @@ choose_wl_class_and_type(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	/*
 	 * check workload expiration, and that we still have other queues ready
 	 */
-	if (count && !time_after(jiffies, cfqd->workload_expires))
+	if (count && !(now > cfqd->workload_expires))
 		return;
 
 new_workload:
@@ -3172,13 +3178,13 @@ choose_wl_class_and_type(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	 */
 	group_slice = cfq_group_slice(cfqd, cfqg);
 
-	slice = group_slice * count /
+	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));
+					cfqg)));
 
 	if (cfqd->serving_wl_type == ASYNC_WORKLOAD) {
-		unsigned int tmp;
+		u64 tmp;
 
 		/*
 		 * Async queues are currently system wide. Just taking
@@ -3189,19 +3195,19 @@ choose_wl_class_and_type(struct cfq_data *cfqd, struct cfq_group *cfqg)
 		 */
 		tmp = cfqd->cfq_target_latency *
 			cfqg_busy_async_queues(cfqd, cfqg);
-		tmp = tmp/cfqd->busy_queues;
-		slice = min_t(unsigned, slice, tmp);
+		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 = slice * cfqd->cfq_slice[0] / cfqd->cfq_slice[1];
+		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(unsigned, slice, CFQ_MIN_TT);
-	cfq_log(cfqd, "workload slice:%d", slice);
-	cfqd->workload_expires = jiffies + slice;
+	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)
@@ -3219,16 +3225,17 @@ static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd)
 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 = jiffies + 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 = jiffies - 1;
+		cfqd->workload_expires = now - 1;
 
 	choose_wl_class_and_type(cfqd, cfqg);
 }
@@ -3240,6 +3247,7 @@ static void cfq_choose_cfqg(struct cfq_data *cfqd)
 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)
@@ -3311,7 +3319,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 	 **/
 	if (CFQQ_SEEKY(cfqq) && cfq_cfqq_idle_window(cfqq) &&
 	    (cfq_cfqq_slice_new(cfqq) ||
-	    (cfqq->slice_end - jiffies > jiffies - cfqq->slice_start))) {
+	    (cfqq->slice_end - now > now - cfqq->slice_start))) {
 		cfq_clear_cfqq_deep(cfqq);
 		cfq_clear_cfqq_idle_window(cfqq);
 	}
@@ -3389,11 +3397,12 @@ static int cfq_forced_dispatch(struct cfq_data *cfqd)
 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 (time_after(jiffies + cfqd->cfq_slice_idle * cfqq->dispatched,
-		cfqq->slice_end))
+	if (now + cfqd->cfq_slice_idle * cfqq->dispatched > cfqq->slice_end)
 		return true;
 
 	return false;
@@ -3468,10 +3477,10 @@ static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	 * based on the last sync IO we serviced
 	 */
 	if (!cfq_cfqq_sync(cfqq) && cfqd->cfq_latency) {
-		unsigned long last_sync = jiffies - cfqd->last_delayed_sync;
+		u64 last_sync = ktime_get_ns() - cfqd->last_delayed_sync;
 		unsigned int depth;
 
-		depth = last_sync / cfqd->cfq_slice[1];
+		depth = div64_u64(last_sync, cfqd->cfq_slice[1]);
 		if (!depth && !cfqq->dispatched)
 			depth = 1;
 		if (depth < max_dispatch)
@@ -3554,7 +3563,7 @@ static int cfq_dispatch_requests(struct request_queue *q, int force)
 	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 = jiffies + 1;
+		cfqq->slice_end = ktime_get_ns() + 1;
 		cfq_slice_expired(cfqd, 0);
 	}
 
@@ -3632,7 +3641,7 @@ static void cfq_init_icq(struct io_cq *icq)
 {
 	struct cfq_io_cq *cic = icq_to_cic(icq);
 
-	cic->ttime.last_end_request = jiffies;
+	cic->ttime.last_end_request = ktime_get_ns();
 }
 
 static void cfq_exit_icq(struct io_cq *icq)
@@ -3853,14 +3862,15 @@ cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct cfq_io_cq *cic,
 }
 
 static void
-__cfq_update_io_thinktime(struct cfq_ttime *ttime, unsigned long slice_idle)
+__cfq_update_io_thinktime(struct cfq_ttime *ttime, u64 slice_idle)
 {
-	unsigned long elapsed = jiffies - ttime->last_end_request;
+	u64 elapsed = ktime_get_ns() - ttime->last_end_request;
 	elapsed = min(elapsed, 2UL * slice_idle);
 
 	ttime->ttime_samples = (7*ttime->ttime_samples + 256) / 8;
-	ttime->ttime_total = (7*ttime->ttime_total + 256*elapsed) / 8;
-	ttime->ttime_mean = (ttime->ttime_total + 128) / ttime->ttime_samples;
+	ttime->ttime_total = div_u64(7*ttime->ttime_total + 256*elapsed,  8);
+	ttime->ttime_mean = div64_ul(ttime->ttime_total + 128,
+				     ttime->ttime_samples);
 }
 
 static void
@@ -4113,7 +4123,7 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq)
 	cfq_log_cfqq(cfqd, cfqq, "insert_request");
 	cfq_init_prio_data(cfqq, RQ_CIC(rq));
 
-	rq->fifo_time = jiffies + cfqd->cfq_fifo_expire[rq_is_sync(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);
 	cfqg_stats_update_io_add(RQ_CFQG(rq), cfqd->serving_group, req_op(rq),
@@ -4161,6 +4171,7 @@ static void cfq_update_hw_tag(struct cfq_data *cfqd)
 static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	struct cfq_io_cq *cic = cfqd->active_cic;
+	u64 now = ktime_get_ns();
 
 	/* If the queue already has requests, don't wait */
 	if (!RB_EMPTY_ROOT(&cfqq->sort_list))
@@ -4179,7 +4190,7 @@ static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 
 	/* if slice left is less than think time, wait busy */
 	if (cic && sample_valid(cic->ttime.ttime_samples)
-	    && (cfqq->slice_end - jiffies < cic->ttime.ttime_mean))
+	    && (cfqq->slice_end - now < cic->ttime.ttime_mean))
 		return true;
 
 	/*
@@ -4189,7 +4200,7 @@ static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	 * 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 - jiffies == 1)
+	if (cfqq->slice_end - now <= jiffies_to_nsecs(1))
 		return true;
 
 	return false;
@@ -4200,9 +4211,8 @@ 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);
-	unsigned long now;
+	u64 now = ktime_get_ns();
 
-	now = jiffies;
 	cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d",
 		     !!(rq->cmd_flags & REQ_NOIDLE));
 
@@ -4231,7 +4241,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 					cfqq_type(cfqq));
 
 		st->ttime.last_end_request = now;
-		if (!time_after(rq->start_time + cfqd->cfq_fifo_expire[1], now))
+		if (!(rq->start_time + cfqd->cfq_fifo_expire[1] > now))
 			cfqd->last_delayed_sync = now;
 	}
 
@@ -4256,10 +4266,10 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 		 * the queue.
 		 */
 		if (cfq_should_wait_busy(cfqd, cfqq)) {
-			unsigned long extend_sl = cfqd->cfq_slice_idle;
+			u64 extend_sl = cfqd->cfq_slice_idle;
 			if (!cfqd->cfq_slice_idle)
 				extend_sl = cfqd->cfq_group_idle;
-			cfqq->slice_end = jiffies + extend_sl;
+			cfqq->slice_end = now + extend_sl;
 			cfq_mark_cfqq_wait_busy(cfqq);
 			cfq_log_cfqq(cfqd, cfqq, "will busy wait");
 		}
@@ -4618,7 +4628,7 @@ static int cfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	 * 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 = jiffies - HZ;
+	cfqd->last_delayed_sync = ktime_get_ns() - NSEC_PER_SEC;
 	return 0;
 
 out_free:
@@ -4661,9 +4671,9 @@ cfq_var_store(unsigned int *var, const char *page, size_t count)
 static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
 {									\
 	struct cfq_data *cfqd = e->elevator_data;			\
-	unsigned int __data = __VAR;					\
+	u64 __data = __VAR;						\
 	if (__CONV)							\
-		__data = jiffies_to_msecs(__data);			\
+		__data = div_u64(__data, NSEC_PER_MSEC);			\
 	return cfq_var_show(__data, (page));				\
 }
 SHOW_FUNCTION(cfq_quantum_show, cfqd->cfq_quantum, 0);
@@ -4691,7 +4701,7 @@ static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)
 	else if (__data > (MAX))					\
 		__data = (MAX);						\
 	if (__CONV)							\
-		*(__PTR) = msecs_to_jiffies(__data);			\
+		*(__PTR) = (u64)__data * NSEC_PER_MSEC;			\
 	else								\
 		*(__PTR) = __data;					\
 	return ret;							\
@@ -4785,18 +4795,7 @@ static int __init cfq_init(void)
 {
 	int ret;
 
-	/*
-	 * could be 0 on HZ < 1000 setups
-	 */
-	if (!cfq_slice_async)
-		cfq_slice_async = 1;
-	if (!cfq_slice_idle)
-		cfq_slice_idle = 1;
-
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
-	if (!cfq_group_idle)
-		cfq_group_idle = 1;
-
 	ret = blkcg_policy_register(&blkcg_policy_cfq);
 	if (ret)
 		return ret;