Linux-libre 4.8.2-gnupck-4.8.2-gnu

29 files changed, 1006 insertions, 826 deletions

diff --git a/block/Kconfig b/block/Kconfig
index d4c2ff4b9..6da79e670 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -89,19 +89,6 @@ config BLK_DEV_INTEGRITY
 	T10/SCSI Data Integrity Field or the T13/ATA External Path
 	Protection.  If in doubt, say N.
 
-config BLK_DEV_DAX
-	bool "Block device DAX support"
-	depends on FS_DAX
-	depends on BROKEN
-	help
-	  When DAX support is available (CONFIG_FS_DAX) raw block
-	  devices can also support direct userspace access to the
-	  storage capacity via MMAP(2) similar to a file on a
-	  DAX-enabled filesystem.  However, the DAX I/O-path disables
-	  some standard I/O-statistics, and the MMAP(2) path has some
-	  operational differences due to bypassing the page
-	  cache.  If in doubt, say N.
-
 config BLK_DEV_THROTTLING
 	bool "Block layer bio throttling support"
 	depends on BLK_CGROUP=y
diff --git a/block/Makefile b/block/Makefile
index 3f2bee907..b7aa613b4 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -7,7 +7,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
 			blk-mq-sysfs.o blk-mq-cpu.o blk-mq-cpumap.o ioctl.o \
-			uuid.o genhd.o scsi_ioctl.o partition-generic.o ioprio.o \
+			genhd.o scsi_ioctl.o partition-generic.o ioprio.o \
 			badblocks.o partitions/
 
 obj-$(CONFIG_BOUNCE)	+= bounce.o
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 32cd8ab1c..569988bda 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -7,7 +7,9 @@
  * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
  *		      Paolo Valente <paolo.valente@unimore.it>
  *
- * Copyright (C) 2010 Paolo Valente <paolo.valente@unimore.it>
+ * Copyright (C) 2015 Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Copyright (C) 2016 Paolo Valente <paolo.valente@linaro.org>
  *
  * Licensed under the GPL-2 as detailed in the accompanying COPYING.BFQ
  * file.
@@ -162,6 +164,7 @@ static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg)
 static struct bfq_group *blkg_to_bfqg(struct blkcg_gq *blkg)
 {
 	struct blkg_policy_data *pd = blkg_to_pd(blkg, &blkcg_policy_bfq);
+
 	return pd_to_bfqg(pd);
 }
 
@@ -205,34 +208,38 @@ static void bfqg_put(struct bfq_group *bfqg)
 
 static void bfqg_stats_update_io_add(struct bfq_group *bfqg,
 				     struct bfq_queue *bfqq,
-				     int rw)
+				     int op, int op_flags)
 {
-	blkg_rwstat_add(&bfqg->stats.queued, rw, 1);
+	blkg_rwstat_add(&bfqg->stats.queued, op, op_flags, 1);
 	bfqg_stats_end_empty_time(&bfqg->stats);
 	if (!(bfqq == ((struct bfq_data *)bfqg->bfqd)->in_service_queue))
 		bfqg_stats_set_start_group_wait_time(bfqg, bfqq_group(bfqq));
 }
 
-static void bfqg_stats_update_io_remove(struct bfq_group *bfqg, int rw)
+static void bfqg_stats_update_io_remove(struct bfq_group *bfqg, int op,
+					int op_flags)
 {
-	blkg_rwstat_add(&bfqg->stats.queued, rw, -1);
+	blkg_rwstat_add(&bfqg->stats.queued, op, op_flags, -1);
 }
 
-static void bfqg_stats_update_io_merged(struct bfq_group *bfqg, int rw)
+static void bfqg_stats_update_io_merged(struct bfq_group *bfqg,  int op,
+					int op_flags)
 {
-	blkg_rwstat_add(&bfqg->stats.merged, rw, 1);
+	blkg_rwstat_add(&bfqg->stats.merged, op, op_flags, 1);
 }
 
 static void bfqg_stats_update_completion(struct bfq_group *bfqg,
-			uint64_t start_time, uint64_t io_start_time, int rw)
+			uint64_t start_time, uint64_t io_start_time, int op,
+			int op_flags)
 {
 	struct bfqg_stats *stats = &bfqg->stats;
 	unsigned long long now = sched_clock();
 
 	if (time_after64(now, io_start_time))
-		blkg_rwstat_add(&stats->service_time, rw, now - io_start_time);
+		blkg_rwstat_add(&stats->service_time, op, op_flags,
+				now - io_start_time);
 	if (time_after64(io_start_time, start_time))
-		blkg_rwstat_add(&stats->wait_time, rw,
+		blkg_rwstat_add(&stats->wait_time, op, op_flags,
 				io_start_time - start_time);
 }
 
@@ -600,6 +607,10 @@ static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd,
 	lockdep_assert_held(bfqd->queue->queue_lock);
 
 	bfqg = bfq_find_set_group(bfqd, blkcg);
+
+	if (unlikely(!bfqg))
+		bfqg = bfqd->root_group;
+
 	if (async_bfqq) {
 		entity = &async_bfqq->entity;
 
@@ -1123,13 +1134,17 @@ static struct cftype bfq_blkg_files[] = {
 #else /* CONFIG_BFQ_GROUP_IOSCHED */
 
 static inline void bfqg_stats_update_io_add(struct bfq_group *bfqg,
-			struct bfq_queue *bfqq, int rw) { }
-static inline void bfqg_stats_update_io_remove(struct bfq_group *bfqg, int rw) { }
-static inline void bfqg_stats_update_io_merged(struct bfq_group *bfqg, int rw) { }
+			struct bfq_queue *bfqq, int op, int op_flags) { }
+static inline void
+bfqg_stats_update_io_remove(struct bfq_group *bfqg, int op, int op_flags) { }
+static inline void
+bfqg_stats_update_io_merged(struct bfq_group *bfqg, int op, int op_flags) { }
 static inline void bfqg_stats_update_completion(struct bfq_group *bfqg,
-			uint64_t start_time, uint64_t io_start_time, int rw) { }
-static inline void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
-struct bfq_group *curr_bfqg) { }
+			uint64_t start_time, uint64_t io_start_time, int op,
+			int op_flags) { }
+static inline void
+bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
+				     struct bfq_group *curr_bfqg) { }
 static inline void bfqg_stats_end_empty_time(struct bfqg_stats *stats) { }
 static inline void bfqg_stats_update_dequeue(struct bfq_group *bfqg) { }
 static inline void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) { }
@@ -1141,6 +1156,7 @@ static void bfq_init_entity(struct bfq_entity *entity,
 			    struct bfq_group *bfqg)
 {
 	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
 	entity->weight = entity->new_weight;
 	entity->orig_weight = entity->new_weight;
 	if (bfqq) {
@@ -1154,6 +1170,7 @@ static struct bfq_group *
 bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio)
 {
 	struct bfq_data *bfqd = bic_to_bfqd(bic);
+
 	return bfqd->root_group;
 }
 
@@ -1163,7 +1180,7 @@ static void bfq_end_wr_async(struct bfq_data *bfqd)
 }
 
 static struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
-                                              struct blkcg *blkcg)
+					    struct blkcg *blkcg)
 {
 	return bfqd->root_group;
 }
@@ -1173,7 +1190,8 @@ static struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
 	return bfqq->bfqd->root_group;
 }
 
-static struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
+static struct bfq_group *
+bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
 {
 	struct bfq_group *bfqg;
 	int i;
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 76a701abf..9190a5554 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -7,7 +7,9 @@
  * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
  *		      Paolo Valente <paolo.valente@unimore.it>
  *
- * Copyright (C) 2016 Paolo Valente <paolo.valente@unimore.it>
+ * Copyright (C) 2015 Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Copyright (C) 2016 Paolo Valente <paolo.valente@linaro.org>
  *
  * Licensed under the GPL-2 as detailed in the accompanying COPYING.BFQ
  * file.
@@ -71,8 +73,8 @@
 #include "bfq.h"
 #include "blk.h"
 
-/* Expiration time of sync (0) and async (1) requests, in jiffies. */
-static const int bfq_fifo_expire[2] = { HZ / 4, HZ / 8 };
+/* Expiration time of sync (0) and async (1) requests, in ns. */
+static const u64 bfq_fifo_expire[2] = { NSEC_PER_SEC / 4, NSEC_PER_SEC / 8 };
 
 /* Maximum backwards seek, in KiB. */
 static const int bfq_back_max = 16 * 1024;
@@ -80,8 +82,8 @@ static const int bfq_back_max = 16 * 1024;
 /* Penalty of a backwards seek, in number of sectors. */
 static const int bfq_back_penalty = 2;
 
-/* Idling period duration, in jiffies. */
-static int bfq_slice_idle = HZ / 125;
+/* Idling period duration, in ns. */
+static u64 bfq_slice_idle = NSEC_PER_SEC / 125;
 
 /* Minimum number of assigned budgets for which stats are safe to compute. */
 static const int bfq_stats_min_budgets = 194;
@@ -102,13 +104,13 @@ static const int bfq_timeout = HZ / 8;
 struct kmem_cache *bfq_pool;
 
 /* Below this threshold (in ms), we consider thinktime immediate. */
-#define BFQ_MIN_TT		2
+#define BFQ_MIN_TT		(2 * NSEC_PER_MSEC)
 
 /* hw_tag detection: parallel requests threshold and min samples needed. */
 #define BFQ_HW_QUEUE_THRESHOLD	4
 #define BFQ_HW_QUEUE_SAMPLES	32
 
-#define BFQQ_SEEK_THR	 	(sector_t)(8 * 100)
+#define BFQQ_SEEK_THR		(sector_t)(8 * 100)
 #define BFQQ_CLOSE_THR		(sector_t)(8 * 1024)
 #define BFQQ_SEEKY(bfqq)	(hweight32(bfqq->seek_history) > 32/8)
 
@@ -191,10 +193,7 @@ static void bfq_schedule_dispatch(struct bfq_data *bfqd);
  */
 static int bfq_bio_sync(struct bio *bio)
 {
-	if (bio_data_dir(bio) == READ || (bio->bi_rw & REQ_SYNC))
-		return 1;
-
-	return 0;
+	return bio_data_dir(bio) == READ || (bio->bi_opf & REQ_SYNC);
 }
 
 /*
@@ -223,7 +222,7 @@ static struct request *bfq_choose_req(struct bfq_data *bfqd,
 	unsigned long back_max;
 #define BFQ_RQ1_WRAP	0x01 /* request 1 wraps */
 #define BFQ_RQ2_WRAP	0x02 /* request 2 wraps */
-	unsigned wrap = 0; /* bit mask: requests behind the disk head? */
+	unsigned int wrap = 0; /* bit mask: requests behind the disk head? */
 
 	if (!rq1 || rq1 == rq2)
 		return rq2;
@@ -278,12 +277,11 @@ static struct request *bfq_choose_req(struct bfq_data *bfqd,
 			return rq1;
 		else if (d2 < d1)
 			return rq2;
-		else {
-			if (s1 >= s2)
-				return rq1;
-			else
-				return rq2;
-		}
+
+		if (s1 >= s2)
+			return rq1;
+		else
+			return rq2;
 
 	case BFQ_RQ2_WRAP:
 		return rq1;
@@ -339,7 +337,7 @@ bfq_rq_pos_tree_lookup(struct bfq_data *bfqd, struct rb_root *root,
 		*rb_link = p;
 
 	bfq_log(bfqd, "rq_pos_tree_lookup %llu: returning %d",
-		(long long unsigned)sector,
+		(unsigned long long) sector,
 		bfqq ? bfqq->pid : 0);
 
 	return bfqq;
@@ -690,7 +688,7 @@ static void bfq_add_to_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 		 */
 		hlist_for_each_entry(bfqq_item, &bfqd->burst_list,
 				     burst_list_node) {
-		        bfq_mark_bfqq_in_large_burst(bfqq_item);
+			bfq_mark_bfqq_in_large_burst(bfqq_item);
 			bfq_log_bfqq(bfqd, bfqq_item, "marked in large burst");
 		}
 		bfq_mark_bfqq_in_large_burst(bfqq);
@@ -891,6 +889,7 @@ end:
 static int bfq_bfqq_budget_left(struct bfq_queue *bfqq)
 {
 	struct bfq_entity *entity = &bfqq->entity;
+
 	return entity->budget - entity->service;
 }
 
@@ -1062,7 +1061,7 @@ static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd,
 	}
 
 	entity->budget = max_t(unsigned long, bfqq->max_budget,
-			       bfq_serv_to_charge(bfqq->next_rq,bfqq));
+			       bfq_serv_to_charge(bfqq->next_rq, bfqq));
 	BUG_ON(entity->budget < 0);
 
 	bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
@@ -1200,9 +1199,9 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
 		 * bfq_bfqq_update_budg_for_activation for
 		 * details on the usage of the next variable.
 		 */
-		arrived_in_time = time_is_after_jiffies(
+		arrived_in_time =  ktime_get_ns() <=
 			RQ_BIC(rq)->ttime.last_end_request +
-			bfqd->bfq_slice_idle * 3);
+			bfqd->bfq_slice_idle * 3;
 
 	bfq_log_bfqq(bfqd, bfqq,
 		     "bfq_add_request non-busy: "
@@ -1217,7 +1216,7 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
 
 	BUG_ON(bfqq == bfqd->in_service_queue);
 	bfqg_stats_update_io_add(bfqq_group(RQ_BFQQ(rq)), bfqq,
-				 rq->cmd_flags);
+				 req_op(rq), rq->cmd_flags);
 
 	/*
 	 * bfqq deserves to be weight-raised if:
@@ -1458,7 +1457,7 @@ static void bfq_activate_request(struct request_queue *q, struct request *rq)
 	bfqd->rq_in_driver++;
 	bfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
 	bfq_log(bfqd, "activate_request: new bfqd->last_position %llu",
-		(long long unsigned)bfqd->last_position);
+		(unsigned long long) bfqd->last_position);
 }
 
 static void bfq_deactivate_request(struct request_queue *q, struct request *rq)
@@ -1523,7 +1522,8 @@ static void bfq_remove_request(struct request *rq)
 		BUG_ON(bfqq->meta_pending == 0);
 		bfqq->meta_pending--;
 	}
-	bfqg_stats_update_io_remove(bfqq_group(bfqq), rq->cmd_flags);
+	bfqg_stats_update_io_remove(bfqq_group(bfqq), req_op(rq),
+				    rq->cmd_flags);
 }
 
 static int bfq_merge(struct request_queue *q, struct request **req,
@@ -1533,7 +1533,7 @@ static int bfq_merge(struct request_queue *q, struct request **req,
 	struct request *__rq;
 
 	__rq = bfq_find_rq_fmerge(bfqd, bio);
-	if (__rq && elv_rq_merge_ok(__rq, bio)) {
+	if (__rq && elv_bio_merge_ok(__rq, bio)) {
 		*req = __rq;
 		return ELEVATOR_FRONT_MERGE;
 	}
@@ -1578,7 +1578,8 @@ static void bfq_merged_request(struct request_queue *q, struct request *req,
 static void bfq_bio_merged(struct request_queue *q, struct request *req,
 			   struct bio *bio)
 {
-	bfqg_stats_update_io_merged(bfqq_group(RQ_BFQQ(req)), bio->bi_rw);
+	bfqg_stats_update_io_merged(bfqq_group(RQ_BFQQ(req)), bio_op(bio),
+				    bio->bi_opf);
 }
 #endif
 
@@ -1598,7 +1599,7 @@ static void bfq_merged_requests(struct request_queue *q, struct request *rq,
 	 */
 	if (bfqq == next_bfqq &&
 	    !list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
-	    time_before(next->fifo_time, rq->fifo_time)) {
+	    next->fifo_time < rq->fifo_time) {
 		list_del_init(&rq->queuelist);
 		list_replace_init(&next->queuelist, &rq->queuelist);
 		rq->fifo_time = next->fifo_time;
@@ -1608,7 +1609,8 @@ static void bfq_merged_requests(struct request_queue *q, struct request *rq,
 		bfqq->next_rq = rq;
 
 	bfq_remove_request(next);
-	bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags);
+	bfqg_stats_update_io_merged(bfqq_group(bfqq), req_op(next),
+				    next->cmd_flags);
 }
 
 /* Must be called with bfqq != NULL */
@@ -1961,7 +1963,7 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
 		struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
 {
 	bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu",
-		(long unsigned)new_bfqq->pid);
+		     (unsigned long) new_bfqq->pid);
 	/* Save weight raising and idle window of the merged queues */
 	bfq_bfqq_save_state(bfqq);
 	bfq_bfqq_save_state(new_bfqq);
@@ -1983,11 +1985,10 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
 		new_bfqq->wr_cur_max_time = bfqq->wr_cur_max_time;
 		new_bfqq->last_wr_start_finish = bfqq->last_wr_start_finish;
 		if (bfq_bfqq_busy(new_bfqq))
-		    bfqd->wr_busy_queues++;
+			bfqd->wr_busy_queues++;
 		new_bfqq->entity.prio_changed = 1;
 		bfq_log_bfqq(bfqd, new_bfqq,
-			     "wr starting after merge with %d, "
-			     "rais_max_time %u",
+			     "wr start after merge with %d, rais_max_time %u",
 			     bfqq->pid,
 			     jiffies_to_msecs(bfqq->wr_cur_max_time));
 	}
@@ -2028,8 +2029,8 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
 	bfq_put_queue(bfqq);
 }
 
-static int bfq_allow_merge(struct request_queue *q, struct request *rq,
-			   struct bio *bio)
+static int bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
+			       struct bio *bio)
 {
 	struct bfq_data *bfqd = q->elevator->elevator_data;
 	struct bfq_io_cq *bic;
@@ -2039,7 +2040,7 @@ static int bfq_allow_merge(struct request_queue *q, struct request *rq,
 	 * Disallow merge of a sync bio into an async request.
 	 */
 	if (bfq_bio_sync(bio) && !rq_is_sync(rq))
-		return 0;
+		return false;
 
 	/*
 	 * Lookup the bfqq that this bio will be queued with. Allow
@@ -2048,7 +2049,7 @@ static int bfq_allow_merge(struct request_queue *q, struct request *rq,
 	 */
 	bic = bfq_bic_lookup(bfqd, current->io_context);
 	if (!bic)
-		return 0;
+		return false;
 
 	bfqq = bic_to_bfqq(bic, bfq_bio_sync(bio));
 	/*
@@ -2071,6 +2072,12 @@ static int bfq_allow_merge(struct request_queue *q, struct request *rq,
 	return bfqq == RQ_BFQQ(rq);
 }
 
+static int bfq_allow_rq_merge(struct request_queue *q, struct request *rq,
+			      struct request *next)
+{
+	return RQ_BFQQ(rq) == RQ_BFQQ(next);
+}
+
 /*
  * Set the maximum time for the in-service queue to consume its
  * budget. This prevents seeky processes from lowering the throughput.
@@ -2081,6 +2088,7 @@ static void bfq_set_budget_timeout(struct bfq_data *bfqd,
 				   struct bfq_queue *bfqq)
 {
 	unsigned int timeout_coeff;
+
 	if (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time)
 		timeout_coeff = 1;
 	else
@@ -2198,13 +2206,15 @@ static void bfq_arm_slice_timer(struct bfq_data *bfqd)
 	 */
 	if (BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1 &&
 	    bfq_symmetric_scenario(bfqd))
-		sl = min(sl, msecs_to_jiffies(BFQ_MIN_TT));
+		sl = min_t(u64, sl, BFQ_MIN_TT);
 
 	bfqd->last_idling_start = ktime_get();
-	mod_timer(&bfqd->idle_slice_timer, jiffies + sl);
+	hrtimer_start(&bfqd->idle_slice_timer, ns_to_ktime(sl),
+		      HRTIMER_MODE_REL);
 	bfqg_stats_set_start_idle_time(bfqq_group(bfqq));
-	bfq_log(bfqd, "arm idle: %u/%u ms",
-		jiffies_to_msecs(sl), jiffies_to_msecs(bfqd->bfq_slice_idle));
+	bfq_log(bfqd, "arm idle: %llu/%llu ms",
+		div_u64(sl, NSEC_PER_MSEC),
+		div_u64(bfqd->bfq_slice_idle, NSEC_PER_MSEC));
 }
 
 /*
@@ -2247,7 +2257,7 @@ static struct request *bfq_check_fifo(struct bfq_queue *bfqq)
 
 	rq = rq_entry_fifo(bfqq->fifo.next);
 
-	if (time_is_after_jiffies(rq->fifo_time))
+	if (ktime_get_ns() < rq->fifo_time)
 		return NULL;
 
 	return rq;
@@ -2468,7 +2478,7 @@ static unsigned long bfq_calc_max_budget(struct bfq_data *bfqd)
 {
 	/*
 	 * The max_budget calculated when autotuning is equal to the
-	 * amount of sectors transfered in timeout at the
+	 * amount of sectors transferred in timeout at the
 	 * estimated peak rate.
 	 */
 	return bfqd->peak_rate * 1000 * jiffies_to_msecs(bfqd->bfq_timeout) >>
@@ -2527,9 +2537,10 @@ static bool bfq_update_peak_rate(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	/* Don't trust short/unrealistic values. */
 	if (delta_usecs < 1000 || delta_usecs >= LONG_MAX) {
 		if (blk_queue_nonrot(bfqd->queue))
-			*delta_ms = BFQ_MIN_TT; /* give same worst-case
-						   guarantees as
-						   idling for seeky
+			*delta_ms = BFQ_MIN_TT; /*
+						 * give same worst-case
+						 * guarantees as
+						 * idling for seeky
 						*/
 		else /* Charge at least one seek */
 			*delta_ms = jiffies_to_msecs(bfq_slice_idle);
@@ -2537,7 +2548,7 @@ static bool bfq_update_peak_rate(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	}
 
 	delta_ms_tmp = delta_usecs;
-	do_div(delta_ms_tmp, 1000);
+	do_div(delta_ms_tmp, NSEC_PER_MSEC);
 	*delta_ms = delta_ms_tmp;
 
 	/*
@@ -2602,6 +2613,7 @@ static bool bfq_update_peak_rate(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		if (bfqd->peak_rate_samples == BFQ_PEAK_RATE_SAMPLES &&
 		    update) {
 			int dev_type = blk_queue_nonrot(bfqd->queue);
+
 			if (bfqd->bfq_user_max_budget == 0) {
 				bfqd->bfq_max_budget =
 					bfq_calc_max_budget(bfqd);
@@ -2619,9 +2631,9 @@ static bool bfq_update_peak_rate(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 				bfqd->RT_prod = R_fast[dev_type] *
 						T_fast[dev_type];
 			}
-			bfq_log(bfqd, "dev_speed_class = %d (%d sects/sec), "
-				"thresh %d setcs/sec",
-				bfqd->device_speed,
+			bfq_log(bfqd,
+	"dev_type %d dev_speed_class = %d (%d sects/sec), thresh %d setcs/sec",
+				dev_type, bfqd->device_speed,
 				bfqd->device_speed == BFQ_BFQD_FAST ?
 				(1000000*R_fast[dev_type])>>BFQ_RATE_SHIFT :
 				(1000000*R_slow[dev_type])>>BFQ_RATE_SHIFT,
@@ -2641,8 +2653,7 @@ static bool bfq_update_peak_rate(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	}
 
 	bfq_log_bfqq(bfqd, bfqq,
-		     "update_peak_rate: bw %llu sect/s, peak rate %llu, "
-		     "slow %d",
+		"update_peak_rate: bw %llu sect/s, peak rate %llu, slow %d",
 		     (1000000*bw)>>BFQ_RATE_SHIFT,
 		     (1000000*bfqd->peak_rate)>>BFQ_RATE_SHIFT,
 		     bw < bfqd->peak_rate / 2);
@@ -2706,9 +2717,7 @@ static unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd,
 						struct bfq_queue *bfqq)
 {
 	bfq_log_bfqq(bfqd, bfqq,
-		     "softrt_next_start: service_blkg %lu "
-		     "soft_rate %u sects/sec"
-		     "interval %u",
+"softrt_next_start: service_blkg %lu soft_rate %u sects/sec interval %u",
 		     bfqq->service_from_backlogged,
 		     bfqd->bfq_wr_max_softrt_rate,
 		     jiffies_to_msecs(HZ * bfqq->service_from_backlogged /
@@ -2717,7 +2726,7 @@ static unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd,
 	return max(bfqq->last_idle_bklogged +
 		   HZ * bfqq->service_from_backlogged /
 		   bfqd->bfq_wr_max_softrt_rate,
-		   jiffies + bfqq->bfqd->bfq_slice_idle + 4);
+		   jiffies + nsecs_to_jiffies(bfqq->bfqd->bfq_slice_idle) + 4);
 }
 
 /*
@@ -2816,7 +2825,7 @@ static void bfq_bfqq_expire(struct bfq_data *bfqd,
 	BUG_ON(bfqq->entity.budget < bfqq->entity.service);
 
 	if (reason == BFQ_BFQQ_TOO_IDLE &&
-	    entity->service <= 2 * entity->budget / 10 )
+	    entity->service <= 2 * entity->budget / 10)
 		bfq_clear_bfqq_IO_bound(bfqq);
 
 	if (bfqd->low_latency && bfqq->wr_coeff == 1)
@@ -3042,7 +3051,7 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
 	 * (i)  each of these processes must get the same throughput as
 	 *      the others;
 	 * (ii) all these processes have the same I/O pattern
-	        (either sequential or random).
+	 *      (either sequential or random).
 	 * In fact, in such a scenario, the drive will tend to treat
 	 * the requests of each of these processes in about the same
 	 * way as the requests of the others, and thus to provide
@@ -3155,9 +3164,11 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
 	 * 2) idling either boosts the throughput (without issues), or
 	 *    is necessary to preserve service guarantees.
 	 */
-	bfq_log_bfqq(bfqd, bfqq, "may_idle: sync %d idling_boosts_thr %d "
-		     "wr_busy %d boosts %d IO-bound %d guar %d",
-		     bfq_bfqq_sync(bfqq), idling_boosts_thr,
+	bfq_log_bfqq(bfqd, bfqq, "may_idle: sync %d idling_boosts_thr %d",
+		     bfq_bfqq_sync(bfqq), idling_boosts_thr);
+
+	bfq_log_bfqq(bfqd, bfqq,
+		     "may_idle: wr_busy %d boosts %d IO-bound %d guar %d",
 		     bfqd->wr_busy_queues,
 		     idling_boosts_thr_without_issues,
 		     bfq_bfqq_IO_bound(bfqq),
@@ -3204,7 +3215,7 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
 	bfq_log_bfqq(bfqd, bfqq, "select_queue: already in-service queue");
 
 	if (bfq_may_expire_for_budg_timeout(bfqq) &&
-	    !timer_pending(&bfqd->idle_slice_timer) &&
+	    !hrtimer_active(&bfqd->idle_slice_timer) &&
 	    !bfq_bfqq_must_idle(bfqq))
 		goto expire;
 
@@ -3224,7 +3235,8 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
 			 * not disable disk idling even when a new request
 			 * arrives.
 			 */
-			if (timer_pending(&bfqd->idle_slice_timer)) {
+			if (bfq_bfqq_wait_request(bfqq)) {
+				BUG_ON(!hrtimer_active(&bfqd->idle_slice_timer));
 				/*
 				 * If we get here: 1) at least a new request
 				 * has arrived but we have not disabled the
@@ -3239,7 +3251,7 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
 				 * So we disable idling.
 				 */
 				bfq_clear_bfqq_wait_request(bfqq);
-				del_timer(&bfqd->idle_slice_timer);
+				hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
 				bfqg_stats_update_idle_time(bfqq_group(bfqq));
 			}
 			goto keep_queue;
@@ -3251,7 +3263,7 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
 	 * for a new request, or has requests waiting for a completion and
 	 * may idle after their completion, then keep it anyway.
 	 */
-	if (timer_pending(&bfqd->idle_slice_timer) ||
+	if (hrtimer_active(&bfqd->idle_slice_timer) ||
 	    (bfqq->dispatched != 0 && bfq_bfqq_may_idle(bfqq))) {
 		bfqq = NULL;
 		goto keep_queue;
@@ -3271,6 +3283,7 @@ keep_queue:
 static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 {
 	struct bfq_entity *entity = &bfqq->entity;
+
 	if (bfqq->wr_coeff > 1) { /* queue is being weight-raised */
 		bfq_log_bfqq(bfqd, bfqq,
 			"raising period dur %u/%u msec, old coeff %u, w %d(%d)",
@@ -3376,7 +3389,7 @@ static int bfq_dispatch_request(struct bfq_data *bfqd,
 	bfq_log_bfqq(bfqd, bfqq,
 			"dispatched %u sec req (%llu), budg left %d",
 			blk_rq_sectors(rq),
-			(long long unsigned)blk_rq_pos(rq),
+			(unsigned long long) blk_rq_pos(rq),
 			bfq_bfqq_budget_left(bfqq));
 
 	dispatched++;
@@ -3461,8 +3474,7 @@ static int bfq_dispatch_requests(struct request_queue *q, int force)
 
 	BUG_ON(bfqq->entity.budget < bfqq->entity.service);
 
-	bfq_clear_bfqq_wait_request(bfqq);
-	BUG_ON(timer_pending(&bfqd->idle_slice_timer));
+	BUG_ON(bfq_bfqq_wait_request(bfqq));
 
 	if (!bfq_dispatch_request(bfqd, bfqq))
 		return 0;
@@ -3554,9 +3566,7 @@ static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 
 static void bfq_init_icq(struct io_cq *icq)
 {
-	struct bfq_io_cq *bic = icq_to_bic(icq);
-
-	bic->ttime.last_end_request = bfq_smallest_from_now();
+	icq_to_bic(icq)->ttime.last_end_request = ktime_get_ns() - (1ULL<<32);
 }
 
 static void bfq_exit_icq(struct io_cq *icq)
@@ -3620,8 +3630,8 @@ static void bfq_set_next_ioprio_data(struct bfq_queue *bfqq,
 	}
 
 	if (bfqq->new_ioprio >= IOPRIO_BE_NR) {
-		printk(KERN_CRIT "bfq_set_next_ioprio_data: new_ioprio %d\n",
-				 bfqq->new_ioprio);
+		pr_crit("bfq_set_next_ioprio_data: new_ioprio %d\n",
+			bfqq->new_ioprio);
 		BUG();
 	}
 
@@ -3735,7 +3745,7 @@ static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
 
 	rcu_read_lock();
 
-	bfqg = bfq_find_set_group(bfqd,bio_blkcg(bio));
+	bfqg = bfq_find_set_group(bfqd, bio_blkcg(bio));
 	if (!bfqg) {
 		bfqq = &bfqd->oom_bfqq;
 		goto out;
@@ -3784,13 +3794,15 @@ out:
 static void bfq_update_io_thinktime(struct bfq_data *bfqd,
 				    struct bfq_io_cq *bic)
 {
-	unsigned long elapsed = jiffies - bic->ttime.last_end_request;
-	unsigned long ttime = min(elapsed, 2UL * bfqd->bfq_slice_idle);
+	struct bfq_ttime *ttime = &bic->ttime;
+	u64 elapsed = ktime_get_ns() - bic->ttime.last_end_request;
+
+	elapsed = min(elapsed, 2UL * bfqd->bfq_slice_idle);
 
-	bic->ttime.ttime_samples = (7*bic->ttime.ttime_samples + 256) / 8;
-	bic->ttime.ttime_total = (7*bic->ttime.ttime_total + 256*ttime) / 8;
-	bic->ttime.ttime_mean = (bic->ttime.ttime_total + 128) /
-				bic->ttime.ttime_samples;
+	ttime->ttime_samples = (7*bic->ttime.ttime_samples + 256) / 8;
+	ttime->ttime_total = div_u64(7*ttime->ttime_total + 256*elapsed,  8);
+	ttime->ttime_mean = div64_ul(ttime->ttime_total + 128,
+				     ttime->ttime_samples);
 }
 
 
@@ -3799,6 +3811,7 @@ bfq_update_io_seektime(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		       struct request *rq)
 {
 	sector_t sdist = 0;
+
 	if (bfqq->last_request_pos) {
 		if (bfqq->last_request_pos < blk_rq_pos(rq))
 			sdist = blk_rq_pos(rq) - bfqq->last_request_pos;
@@ -3906,7 +3919,7 @@ static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		 * timer.
 		 */
 		bfq_clear_bfqq_wait_request(bfqq);
-		del_timer(&bfqd->idle_slice_timer);
+		hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
 		bfqg_stats_update_idle_time(bfqq_group(bfqq));
 
 		/*
@@ -3964,7 +3977,8 @@ static void bfq_insert_request(struct request_queue *q, struct request *rq)
 
 	bfq_add_request(rq);
 
-	rq->fifo_time = jiffies + bfqd->bfq_fifo_expire[rq_is_sync(rq)];
+	rq->fifo_time = ktime_get_ns() +
+	  jiffies_to_nsecs(bfqd->bfq_fifo_expire[rq_is_sync(rq)]);
 	list_add_tail(&rq->queuelist, &bfqq->fifo);
 
 	bfq_rq_enqueued(bfqd, bfqq, rq);
@@ -4012,7 +4026,8 @@ static void bfq_completed_request(struct request_queue *q, struct request *rq)
 	bfqq->dispatched--;
 	bfqg_stats_update_completion(bfqq_group(bfqq),
 				     rq_start_time_ns(rq),
-				     rq_io_start_time_ns(rq), rq->cmd_flags);
+				     rq_io_start_time_ns(rq), req_op(rq),
+				     rq->cmd_flags);
 
 	if (!bfqq->dispatched && !bfq_bfqq_busy(bfqq)) {
 		BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list));
@@ -4028,7 +4043,7 @@ static void bfq_completed_request(struct request_queue *q, struct request *rq)
 					&bfqd->queue_weights_tree);
 	}
 
-	RQ_BIC(rq)->ttime.last_end_request = jiffies;
+	RQ_BIC(rq)->ttime.last_end_request = ktime_get_ns();
 
 	/*
 	 * If we are waiting to discover whether the request pattern
@@ -4079,7 +4094,7 @@ static int __bfq_may_queue(struct bfq_queue *bfqq)
 	return ELV_MQUEUE_MAY;
 }
 
-static int bfq_may_queue(struct request_queue *q, int rw)
+static int bfq_may_queue(struct request_queue *q, int op, int op_flags)
 {
 	struct bfq_data *bfqd = q->elevator->elevator_data;
 	struct task_struct *tsk = current;
@@ -4096,7 +4111,7 @@ static int bfq_may_queue(struct request_queue *q, int rw)
 	if (!bic)
 		return ELV_MQUEUE_MAY;
 
-	bfqq = bic_to_bfqq(bic, rw_is_sync(rw));
+	bfqq = bic_to_bfqq(bic, rw_is_sync(op, op_flags));
 	if (bfqq)
 		return __bfq_may_queue(bfqq);
 
@@ -4279,9 +4294,10 @@ static void bfq_kick_queue(struct work_struct *work)
  * Handler of the expiration of the timer running if the in-service queue
  * is idling inside its time slice.
  */
-static void bfq_idle_slice_timer(unsigned long data)
+static enum hrtimer_restart bfq_idle_slice_timer(struct hrtimer *timer)
 {
-	struct bfq_data *bfqd = (struct bfq_data *)data;
+	struct bfq_data *bfqd = container_of(timer, struct bfq_data,
+					     idle_slice_timer);
 	struct bfq_queue *bfqq;
 	unsigned long flags;
 	enum bfqq_expiration reason;
@@ -4299,6 +4315,8 @@ static void bfq_idle_slice_timer(unsigned long data)
 	 */
 	if (bfqq) {
 		bfq_log_bfqq(bfqd, bfqq, "slice_timer expired");
+		bfq_clear_bfqq_wait_request(bfqq);
+
 		if (bfq_bfqq_budget_timeout(bfqq))
 			/*
 			 * Also here the queue can be safely expired
@@ -4324,11 +4342,12 @@ schedule_dispatch:
 	bfq_schedule_dispatch(bfqd);
 
 	spin_unlock_irqrestore(bfqd->queue->queue_lock, flags);
+	return HRTIMER_NORESTART;
 }
 
 static void bfq_shutdown_timer_wq(struct bfq_data *bfqd)
 {
-	del_timer_sync(&bfqd->idle_slice_timer);
+	hrtimer_cancel(&bfqd->idle_slice_timer);
 	cancel_work_sync(&bfqd->unplug_work);
 }
 
@@ -4385,7 +4404,7 @@ static void bfq_exit_queue(struct elevator_queue *e)
 
 	bfq_shutdown_timer_wq(bfqd);
 
-	BUG_ON(timer_pending(&bfqd->idle_slice_timer));
+	BUG_ON(hrtimer_active(&bfqd->idle_slice_timer));
 
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
 	blkcg_deactivate_policy(q, &blkcg_policy_bfq);
@@ -4460,9 +4479,9 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	bfq_init_root_group(bfqd->root_group, bfqd);
 	bfq_init_entity(&bfqd->oom_bfqq.entity, bfqd->root_group);
 
-	init_timer(&bfqd->idle_slice_timer);
+	hrtimer_init(&bfqd->idle_slice_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL);
 	bfqd->idle_slice_timer.function = bfq_idle_slice_timer;
-	bfqd->idle_slice_timer.data = (unsigned long)bfqd;
 
 	bfqd->queue_weights_tree = RB_ROOT;
 	bfqd->group_weights_tree = RB_ROOT;
@@ -4528,8 +4547,7 @@ out_free:
 
 static void bfq_slab_kill(void)
 {
-	if (bfq_pool)
-		kmem_cache_destroy(bfq_pool);
+	kmem_cache_destroy(bfq_pool);
 }
 
 static int __init bfq_slab_setup(void)
@@ -4542,7 +4560,7 @@ static int __init bfq_slab_setup(void)
 
 static ssize_t bfq_var_show(unsigned int var, char *page)
 {
-	return sprintf(page, "%d\n", var);
+	return sprintf(page, "%u\n", var);
 }
 
 static ssize_t bfq_var_store(unsigned long *var, const char *page,
@@ -4560,6 +4578,7 @@ static ssize_t bfq_var_store(unsigned long *var, const char *page,
 static ssize_t bfq_wr_max_time_show(struct elevator_queue *e, char *page)
 {
 	struct bfq_data *bfqd = e->elevator_data;
+
 	return sprintf(page, "%d\n", bfqd->bfq_wr_max_time > 0 ?
 		       jiffies_to_msecs(bfqd->bfq_wr_max_time) :
 		       jiffies_to_msecs(bfq_wr_duration(bfqd)));
@@ -4578,25 +4597,29 @@ static ssize_t bfq_weights_show(struct elevator_queue *e, char *page)
 
 	num_char += sprintf(page + num_char, "Active:\n");
 	list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list) {
-	  num_char += sprintf(page + num_char,
-			      "pid%d: weight %hu, nr_queued %d %d, dur %d/%u\n",
-			      bfqq->pid,
-			      bfqq->entity.weight,
-			      bfqq->queued[0],
-			      bfqq->queued[1],
-			jiffies_to_msecs(jiffies - bfqq->last_wr_start_finish),
-			jiffies_to_msecs(bfqq->wr_cur_max_time));
+		num_char += sprintf(page + num_char,
+				    "pid%d: weight %hu, nr_queued %d %d, ",
+				    bfqq->pid,
+				    bfqq->entity.weight,
+				    bfqq->queued[0],
+				    bfqq->queued[1]);
+		num_char += sprintf(page + num_char,
+				    "dur %d/%u\n",
+				    jiffies_to_msecs(
+					    jiffies -
+					    bfqq->last_wr_start_finish),
+				    jiffies_to_msecs(bfqq->wr_cur_max_time));
 	}
 
 	num_char += sprintf(page + num_char, "Idle:\n");
 	list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list) {
-			num_char += sprintf(page + num_char,
-				"pid%d: weight %hu, dur %d/%u\n",
-				bfqq->pid,
-				bfqq->entity.weight,
-				jiffies_to_msecs(jiffies -
-					bfqq->last_wr_start_finish),
-				jiffies_to_msecs(bfqq->wr_cur_max_time));
+		num_char += sprintf(page + num_char,
+				    "pid%d: weight %hu, dur %d/%u\n",
+				    bfqq->pid,
+				    bfqq->entity.weight,
+				    jiffies_to_msecs(jiffies -
+						     bfqq->last_wr_start_finish),
+				    jiffies_to_msecs(bfqq->wr_cur_max_time));
 	}
 
 	spin_unlock_irq(bfqd->queue->queue_lock);
@@ -4608,16 +4631,18 @@ static ssize_t bfq_weights_show(struct elevator_queue *e, char *page)
 static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
 {									\
 	struct bfq_data *bfqd = e->elevator_data;			\
-	unsigned int __data = __VAR;					\
-	if (__CONV)							\
+	u64 __data = __VAR;						\
+	if (__CONV == 1)						\
 		__data = jiffies_to_msecs(__data);			\
+	else if (__CONV == 2)						\
+		__data = div_u64(__data, NSEC_PER_MSEC);		\
 	return bfq_var_show(__data, (page));				\
 }
-SHOW_FUNCTION(bfq_fifo_expire_sync_show, bfqd->bfq_fifo_expire[1], 1);
-SHOW_FUNCTION(bfq_fifo_expire_async_show, bfqd->bfq_fifo_expire[0], 1);
+SHOW_FUNCTION(bfq_fifo_expire_sync_show, bfqd->bfq_fifo_expire[1], 2);
+SHOW_FUNCTION(bfq_fifo_expire_async_show, bfqd->bfq_fifo_expire[0], 2);
 SHOW_FUNCTION(bfq_back_seek_max_show, bfqd->bfq_back_max, 0);
 SHOW_FUNCTION(bfq_back_seek_penalty_show, bfqd->bfq_back_penalty, 0);
-SHOW_FUNCTION(bfq_slice_idle_show, bfqd->bfq_slice_idle, 1);
+SHOW_FUNCTION(bfq_slice_idle_show, bfqd->bfq_slice_idle, 2);
 SHOW_FUNCTION(bfq_max_budget_show, bfqd->bfq_user_max_budget, 0);
 SHOW_FUNCTION(bfq_timeout_sync_show, bfqd->bfq_timeout, 1);
 SHOW_FUNCTION(bfq_strict_guarantees_show, bfqd->strict_guarantees, 0);
@@ -4630,6 +4655,17 @@ SHOW_FUNCTION(bfq_wr_min_inter_arr_async_show, bfqd->bfq_wr_min_inter_arr_async,
 SHOW_FUNCTION(bfq_wr_max_softrt_rate_show, bfqd->bfq_wr_max_softrt_rate, 0);
 #undef SHOW_FUNCTION
 
+#define USEC_SHOW_FUNCTION(__FUNC, __VAR)				\
+static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
+{									\
+	struct bfq_data *bfqd = e->elevator_data;			\
+	u64 __data = __VAR;						\
+	__data = div_u64(__data, NSEC_PER_USEC);			\
+	return bfq_var_show(__data, (page));				\
+}
+USEC_SHOW_FUNCTION(bfq_slice_idle_us_show, bfqd->bfq_slice_idle);
+#undef USEC_SHOW_FUNCTION
+
 #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
 static ssize_t								\
 __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
@@ -4641,20 +4677,22 @@ __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
 		__data = (MIN);						\
 	else if (__data > (MAX))					\
 		__data = (MAX);						\
-	if (__CONV)							\
+	if (__CONV == 1)						\
 		*(__PTR) = msecs_to_jiffies(__data);			\
+	else if (__CONV == 2)						\
+		*(__PTR) = (u64)__data * NSEC_PER_MSEC;			\
 	else								\
 		*(__PTR) = __data;					\
 	return ret;							\
 }
 STORE_FUNCTION(bfq_fifo_expire_sync_store, &bfqd->bfq_fifo_expire[1], 1,
-		INT_MAX, 1);
+		INT_MAX, 2);
 STORE_FUNCTION(bfq_fifo_expire_async_store, &bfqd->bfq_fifo_expire[0], 1,
-		INT_MAX, 1);
+		INT_MAX, 2);
 STORE_FUNCTION(bfq_back_seek_max_store, &bfqd->bfq_back_max, 0, INT_MAX, 0);
 STORE_FUNCTION(bfq_back_seek_penalty_store, &bfqd->bfq_back_penalty, 1,
 		INT_MAX, 0);
-STORE_FUNCTION(bfq_slice_idle_store, &bfqd->bfq_slice_idle, 0, INT_MAX, 1);
+STORE_FUNCTION(bfq_slice_idle_store, &bfqd->bfq_slice_idle, 0, INT_MAX, 2);
 STORE_FUNCTION(bfq_wr_coeff_store, &bfqd->bfq_wr_coeff, 1, INT_MAX, 0);
 STORE_FUNCTION(bfq_wr_max_time_store, &bfqd->bfq_wr_max_time, 0, INT_MAX, 1);
 STORE_FUNCTION(bfq_wr_rt_max_time_store, &bfqd->bfq_wr_rt_max_time, 0, INT_MAX,
@@ -4667,6 +4705,23 @@ STORE_FUNCTION(bfq_wr_max_softrt_rate_store, &bfqd->bfq_wr_max_softrt_rate, 0,
 		INT_MAX, 0);
 #undef STORE_FUNCTION
 
+#define USEC_STORE_FUNCTION(__FUNC, __PTR, MIN, MAX)			\
+static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)\
+{									\
+	struct bfq_data *bfqd = e->elevator_data;			\
+	unsigned long __data;						\
+	int ret = bfq_var_store(&__data, (page), count);		\
+	if (__data < (MIN))						\
+		__data = (MIN);						\
+	else if (__data > (MAX))					\
+		__data = (MAX);						\
+	*(__PTR) = (u64)__data * NSEC_PER_USEC;				\
+	return ret;							\
+}
+USEC_STORE_FUNCTION(bfq_slice_idle_us_store, &bfqd->bfq_slice_idle, 0,
+		    UINT_MAX);
+#undef USEC_STORE_FUNCTION
+
 /* do nothing for the moment */
 static ssize_t bfq_weights_store(struct elevator_queue *e,
 				    const char *page, size_t count)
@@ -4768,6 +4823,7 @@ static struct elv_fs_entry bfq_attrs[] = {
 	BFQ_ATTR(back_seek_max),
 	BFQ_ATTR(back_seek_penalty),
 	BFQ_ATTR(slice_idle),
+	BFQ_ATTR(slice_idle_us),
 	BFQ_ATTR(max_budget),
 	BFQ_ATTR(timeout_sync),
 	BFQ_ATTR(strict_guarantees),
@@ -4790,7 +4846,8 @@ static struct elevator_type iosched_bfq = {
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
 		.elevator_bio_merged_fn =	bfq_bio_merged,
 #endif
-		.elevator_allow_merge_fn =	bfq_allow_merge,
+		.elevator_allow_bio_merge_fn =	bfq_allow_bio_merge,
+		.elevator_allow_rq_merge_fn =	bfq_allow_rq_merge,
 		.elevator_dispatch_fn =		bfq_dispatch_requests,
 		.elevator_add_req_fn =		bfq_insert_request,
 		.elevator_activate_req_fn =	bfq_activate_request,
@@ -4836,12 +4893,6 @@ static int __init bfq_init(void)
 	int ret;
 	char msg[50] = "BFQ I/O-scheduler: v8r3";
 
-	/*
-	 * Can be 0 on HZ < 1000 setups.
-	 */
-	if (bfq_slice_idle == 0)
-		bfq_slice_idle = 1;
-
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
 	ret = blkcg_policy_register(&blkcg_policy_bfq);
 	if (ret)
diff --git a/block/bfq-sched.c b/block/bfq-sched.c
index 475a9a6e1..f8960a4e9 100644
--- a/block/bfq-sched.c
+++ b/block/bfq-sched.c
@@ -7,7 +7,9 @@
  * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
  *		      Paolo Valente <paolo.valente@unimore.it>
  *
- * Copyright (C) 2016 Paolo Valente <paolo.valente@unimore.it>
+ * Copyright (C) 2015 Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Copyright (C) 2016 Paolo Valente <paolo.valente@linaro.org>
  */
 
 static struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
@@ -167,7 +169,8 @@ static u64 bfq_delta(unsigned long service, unsigned long weight)
 static void bfq_calc_finish(struct bfq_entity *entity, unsigned long service)
 {
 	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
-	unsigned long long start, finish, delta ;
+	unsigned long long start, finish, delta;
+
 	BUG_ON(entity->weight == 0);
 
 	entity->finish = entity->start +
@@ -428,7 +431,7 @@ static void bfq_active_insert(struct bfq_service_tree *st,
 static unsigned short bfq_ioprio_to_weight(int ioprio)
 {
 	BUG_ON(ioprio < 0 || ioprio >= IOPRIO_BE_NR);
-	return (IOPRIO_BE_NR - ioprio) * BFQ_WEIGHT_CONVERSION_COEFF ;
+	return (IOPRIO_BE_NR - ioprio) * BFQ_WEIGHT_CONVERSION_COEFF;
 }
 
 /**
@@ -1243,6 +1246,12 @@ static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd,
 
 	BUG_ON(sd->in_service_entity);
 
+	/*
+	 * Choose from idle class, if needed to guarantee a minimum
+	 * bandwidth to this class. This should also mitigate
+	 * priority-inversion problems in case a low priority task is
+	 * holding file system resources.
+	 */
 	if (bfqd &&
 	    jiffies - bfqd->bfq_class_idle_last_service >
 	    BFQ_CL_IDLE_TIMEOUT) {
@@ -1250,11 +1259,12 @@ static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd,
 						  true);
 		if (entity) {
 			struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
 			if (bfqq)
 				bfq_log_bfqq(bfqd, bfqq,
 					     "idle chosen from st %p %d",
 					     st + BFQ_IOPRIO_CLASSES - 1,
-					BFQ_IOPRIO_CLASSES - 1) ;
+					BFQ_IOPRIO_CLASSES - 1);
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
 			else {
 				struct bfq_group *bfqg =
@@ -1263,7 +1273,7 @@ static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd,
 				bfq_log_bfqg(bfqd, bfqg,
 					     "idle chosen from st %p %d",
 					     st + BFQ_IOPRIO_CLASSES - 1,
-					BFQ_IOPRIO_CLASSES - 1) ;
+					BFQ_IOPRIO_CLASSES - 1);
 			}
 #endif
 			i = BFQ_IOPRIO_CLASSES - 1;
@@ -1276,10 +1286,11 @@ static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd,
 		if (entity) {
 			if (bfqd != NULL) {
 			struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
 			if (bfqq)
 				bfq_log_bfqq(bfqd, bfqq,
 					     "chosen from st %p %d",
-					     st + i, i) ;
+					     st + i, i);
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
 			else {
 				struct bfq_group *bfqg =
@@ -1287,7 +1298,7 @@ static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd,
 
 				bfq_log_bfqg(bfqd, bfqg,
 					     "chosen from st %p %d",
-					     st + i, i) ;
+					     st + i, i);
 			}
 #endif
 			}
@@ -1375,8 +1386,9 @@ static void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
 		bfqd->in_service_bic = NULL;
 	}
 
+	bfq_clear_bfqq_wait_request(bfqd->in_service_queue);
+	hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
 	bfqd->in_service_queue = NULL;
-	del_timer(&bfqd->idle_slice_timer);
 }
 
 static void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
diff --git a/block/bfq.h b/block/bfq.h
index 49d28b9dc..00142fcce 100644
--- a/block/bfq.h
+++ b/block/bfq.h
@@ -1,5 +1,5 @@
 /*
- * BFQ-v8r3 for 4.7.0: data structures and common functions prototypes.
+ * BFQ-v8r3 for 4.8.0: data structures and common functions prototypes.
  *
  * Based on ideas and code from CFQ:
  * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
@@ -7,7 +7,9 @@
  * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
  *		      Paolo Valente <paolo.valente@unimore.it>
  *
- * Copyright (C) 2010 Paolo Valente <paolo.valente@unimore.it>
+ * Copyright (C) 2015 Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Copyright (C) 2016 Paolo Valente <paolo.valente@linaro.org>
  */
 
 #ifndef _BFQ_H
@@ -55,8 +57,8 @@ struct bfq_service_tree {
 	/* tree for idle entities (i.e., not backlogged, with V <= F_i)*/
 	struct rb_root idle;
 
-	struct bfq_entity *first_idle; 	/* idle entity with minimum F_i */
-	struct bfq_entity *last_idle; 	/* idle entity with maximum F_i */
+	struct bfq_entity *first_idle;	/* idle entity with minimum F_i */
+	struct bfq_entity *last_idle;	/* idle entity with maximum F_i */
 
 	u64 vtime; /* scheduler virtual time */
 	/* scheduler weight sum; active and idle entities contribute to it */
@@ -158,7 +160,7 @@ struct bfq_entity {
 	/* budget, used also to calculate F_i: F_i = S_i + @budget / @weight */
 	int budget;
 
-	unsigned int weight; 	/* weight of the queue */
+	unsigned int weight;	 /* weight of the queue */
 	unsigned int new_weight; /* next weight if a change is in progress */
 
 	/* original weight, used to implement weight boosting */
@@ -304,11 +306,11 @@ struct bfq_queue {
  * struct bfq_ttime - per process thinktime stats.
  */
 struct bfq_ttime {
-	unsigned long last_end_request; /* completion time of last request */
+	u64 last_end_request; /* completion time of last request */
 
-	unsigned long ttime_total; /* total process thinktime */
+	u64 ttime_total; /* total process thinktime */
 	unsigned long ttime_samples; /* number of thinktime samples */
-	unsigned long ttime_mean; /* average process thinktime */
+	u64 ttime_mean; /* average process thinktime */
 
 };
 
@@ -417,7 +419,7 @@ struct bfq_data {
 	 * Timer set when idling (waiting) for the next request from
 	 * the queue in service.
 	 */
-	struct timer_list idle_slice_timer;
+	struct hrtimer idle_slice_timer;
 	/* delayed work to restart dispatching on the request queue */
 	struct work_struct unplug_work;
 
@@ -449,13 +451,13 @@ struct bfq_data {
 	 * Timeout for async/sync requests; when it fires, requests
 	 * are served in fifo order.
 	 */
-	unsigned int bfq_fifo_expire[2];
+	u64 bfq_fifo_expire[2];
 	/* weight of backward seeks wrt forward ones */
 	unsigned int bfq_back_penalty;
 	/* maximum allowed backward seek */
 	unsigned int bfq_back_max;
 	/* maximum idling time */
-	unsigned int bfq_slice_idle;
+	u64 bfq_slice_idle;
 	/* last time CLASS_IDLE was served */
 	u64 bfq_class_idle_last_service;
 
@@ -788,7 +790,7 @@ bfq_entity_service_tree(struct bfq_entity *entity)
 	if (bfqq)
 		bfq_log_bfqq(bfqq->bfqd, bfqq,
 			     "entity_service_tree %p %d",
-			     sched_data->service_tree + idx, idx) ;
+			     sched_data->service_tree + idx, idx);
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
 	else {
 		struct bfq_group *bfqg =
@@ -796,7 +798,7 @@ bfq_entity_service_tree(struct bfq_entity *entity)
 
 		bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg,
 			     "entity_service_tree %p %d",
-			     sched_data->service_tree + idx, idx) ;
+			     sched_data->service_tree + idx, idx);
 	}
 #endif
 	return sched_data->service_tree + idx;
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 711e4d8de..63f72f00c 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -26,6 +26,7 @@
 #include <linux/bio.h>
 #include <linux/workqueue.h>
 #include <linux/slab.h>
+#include "blk.h"
 
 #define BIP_INLINE_VECS	4
 
@@ -53,7 +54,6 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 {
 	struct bio_integrity_payload *bip;
 	struct bio_set *bs = bio->bi_pool;
-	unsigned long idx = BIO_POOL_NONE;
 	unsigned inline_vecs;
 
 	if (!bs || !bs->bio_integrity_pool) {
@@ -71,20 +71,22 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 	memset(bip, 0, sizeof(*bip));
 
 	if (nr_vecs > inline_vecs) {
+		unsigned long idx = 0;
+
 		bip->bip_vec = bvec_alloc(gfp_mask, nr_vecs, &idx,
 					  bs->bvec_integrity_pool);
 		if (!bip->bip_vec)
 			goto err;
 		bip->bip_max_vcnt = bvec_nr_vecs(idx);
+		bip->bip_slab = idx;
 	} else {
 		bip->bip_vec = bip->bip_inline_vecs;
 		bip->bip_max_vcnt = inline_vecs;
 	}
 
-	bip->bip_slab = idx;
 	bip->bip_bio = bio;
 	bio->bi_integrity = bip;
-	bio->bi_rw |= REQ_INTEGRITY;
+	bio->bi_opf |= REQ_INTEGRITY;
 
 	return bip;
 err:
@@ -110,9 +112,7 @@ void bio_integrity_free(struct bio *bio)
 		      bip->bip_vec->bv_offset);
 
 	if (bs && bs->bio_integrity_pool) {
-		if (bip->bip_slab != BIO_POOL_NONE)
-			bvec_free(bs->bvec_integrity_pool, bip->bip_vec,
-				  bip->bip_slab);
+		bvec_free(bs->bvec_integrity_pool, bip->bip_vec, bip->bip_slab);
 
 		mempool_free(bip, bs->bio_integrity_pool);
 	} else {
diff --git a/block/bio.c b/block/bio.c
index 462386908..aa7354088 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -43,7 +43,7 @@
  * unsigned short
  */
 #define BV(x) { .nr_vecs = x, .name = "biovec-"__stringify(x) }
-static struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] __read_mostly = {
+static struct biovec_slab bvec_slabs[BVEC_POOL_NR] __read_mostly = {
 	BV(1), BV(4), BV(16), BV(64), BV(128), BV(BIO_MAX_PAGES),
 };
 #undef BV
@@ -160,11 +160,15 @@ unsigned int bvec_nr_vecs(unsigned short idx)
 
 void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned int idx)
 {
-	BIO_BUG_ON(idx >= BIOVEC_NR_POOLS);
+	if (!idx)
+		return;
+	idx--;
+
+	BIO_BUG_ON(idx >= BVEC_POOL_NR);
 
-	if (idx == BIOVEC_MAX_IDX)
+	if (idx == BVEC_POOL_MAX) {
 		mempool_free(bv, pool);
-	else {
+	} else {
 		struct biovec_slab *bvs = bvec_slabs + idx;
 
 		kmem_cache_free(bvs->slab, bv);
@@ -206,7 +210,7 @@ struct bio_vec *bvec_alloc(gfp_t gfp_mask, int nr, unsigned long *idx,
 	 * idx now points to the pool we want to allocate from. only the
 	 * 1-vec entry pool is mempool backed.
 	 */
-	if (*idx == BIOVEC_MAX_IDX) {
+	if (*idx == BVEC_POOL_MAX) {
 fallback:
 		bvl = mempool_alloc(pool, gfp_mask);
 	} else {
@@ -226,11 +230,12 @@ fallback:
 		 */
 		bvl = kmem_cache_alloc(bvs->slab, __gfp_mask);
 		if (unlikely(!bvl && (gfp_mask & __GFP_DIRECT_RECLAIM))) {
-			*idx = BIOVEC_MAX_IDX;
+			*idx = BVEC_POOL_MAX;
 			goto fallback;
 		}
 	}
 
+	(*idx)++;
 	return bvl;
 }
 
@@ -250,8 +255,7 @@ static void bio_free(struct bio *bio)
 	__bio_free(bio);
 
 	if (bs) {
-		if (bio_flagged(bio, BIO_OWNS_VEC))
-			bvec_free(bs->bvec_pool, bio->bi_io_vec, BIO_POOL_IDX(bio));
+		bvec_free(bs->bvec_pool, bio->bi_io_vec, BVEC_POOL_IDX(bio));
 
 		/*
 		 * If we have front padding, adjust the bio pointer before freeing
@@ -420,7 +424,6 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 	gfp_t saved_gfp = gfp_mask;
 	unsigned front_pad;
 	unsigned inline_vecs;
-	unsigned long idx = BIO_POOL_NONE;
 	struct bio_vec *bvl = NULL;
 	struct bio *bio;
 	void *p;
@@ -480,6 +483,8 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 	bio_init(bio);
 
 	if (nr_iovecs > inline_vecs) {
+		unsigned long idx = 0;
+
 		bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, bs->bvec_pool);
 		if (!bvl && gfp_mask != saved_gfp) {
 			punt_bios_to_rescuer(bs);
@@ -490,13 +495,12 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 		if (unlikely(!bvl))
 			goto err_free;
 
-		bio_set_flag(bio, BIO_OWNS_VEC);
+		bio->bi_flags |= idx << BVEC_POOL_OFFSET;
 	} else if (nr_iovecs) {
 		bvl = bio->bi_inline_vecs;
 	}
 
 	bio->bi_pool = bs;
-	bio->bi_flags |= idx << BIO_POOL_OFFSET;
 	bio->bi_max_vecs = nr_iovecs;
 	bio->bi_io_vec = bvl;
 	return bio;
@@ -568,7 +572,7 @@ EXPORT_SYMBOL(bio_phys_segments);
  */
 void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
 {
-	BUG_ON(bio->bi_pool && BIO_POOL_IDX(bio) != BIO_POOL_NONE);
+	BUG_ON(bio->bi_pool && BVEC_POOL_IDX(bio));
 
 	/*
 	 * most users will be overriding ->bi_bdev with a new target,
@@ -576,7 +580,7 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
 	 */
 	bio->bi_bdev = bio_src->bi_bdev;
 	bio_set_flag(bio, BIO_CLONED);
-	bio->bi_rw = bio_src->bi_rw;
+	bio->bi_opf = bio_src->bi_opf;
 	bio->bi_iter = bio_src->bi_iter;
 	bio->bi_io_vec = bio_src->bi_io_vec;
 
@@ -658,24 +662,24 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
 	bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs);
 	if (!bio)
 		return NULL;
-
 	bio->bi_bdev		= bio_src->bi_bdev;
-	bio->bi_rw		= bio_src->bi_rw;
+	bio->bi_opf		= bio_src->bi_opf;
 	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
 	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
 
-	if (bio->bi_rw & REQ_DISCARD)
-		goto integrity_clone;
-
-	if (bio->bi_rw & REQ_WRITE_SAME) {
+	switch (bio_op(bio)) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_SECURE_ERASE:
+		break;
+	case REQ_OP_WRITE_SAME:
 		bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
-		goto integrity_clone;
+		break;
+	default:
+		bio_for_each_segment(bv, bio_src, iter)
+			bio->bi_io_vec[bio->bi_vcnt++] = bv;
+		break;
 	}
 
-	bio_for_each_segment(bv, bio_src, iter)
-		bio->bi_io_vec[bio->bi_vcnt++] = bv;
-
-integrity_clone:
 	if (bio_integrity(bio_src)) {
 		int ret;
 
@@ -858,21 +862,20 @@ static void submit_bio_wait_endio(struct bio *bio)
 
 /**
  * submit_bio_wait - submit a bio, and wait until it completes
- * @rw: whether to %READ or %WRITE, or maybe to %READA (read ahead)
  * @bio: The &struct bio which describes the I/O
  *
  * Simple wrapper around submit_bio(). Returns 0 on success, or the error from
  * bio_endio() on failure.
  */
-int submit_bio_wait(int rw, struct bio *bio)
+int submit_bio_wait(struct bio *bio)
 {
 	struct submit_bio_ret ret;
 
-	rw |= REQ_SYNC;
 	init_completion(&ret.event);
 	bio->bi_private = &ret;
 	bio->bi_end_io = submit_bio_wait_endio;
-	submit_bio(rw, bio);
+	bio->bi_opf |= REQ_SYNC;
+	submit_bio(bio);
 	wait_for_completion_io(&ret.event);
 
 	return ret.error;
@@ -1103,7 +1106,6 @@ int bio_uncopy_user(struct bio *bio)
 	bio_put(bio);
 	return ret;
 }
-EXPORT_SYMBOL(bio_uncopy_user);
 
 /**
  *	bio_copy_user_iov	-	copy user data to bio
@@ -1171,7 +1173,7 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 		goto out_bmd;
 
 	if (iter->type & WRITE)
-		bio->bi_rw |= REQ_WRITE;
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
 	ret = 0;
 
@@ -1341,7 +1343,7 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 	 * set data direction, and check if mapped pages need bouncing
 	 */
 	if (iter->type & WRITE)
-		bio->bi_rw |= REQ_WRITE;
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
 	bio_set_flag(bio, BIO_USER_MAPPED);
 
@@ -1398,7 +1400,6 @@ void bio_unmap_user(struct bio *bio)
 	__bio_unmap_user(bio);
 	bio_put(bio);
 }
-EXPORT_SYMBOL(bio_unmap_user);
 
 static void bio_map_kern_endio(struct bio *bio)
 {
@@ -1534,7 +1535,7 @@ struct bio *bio_copy_kern(struct request_queue *q, void *data, unsigned int len,
 		bio->bi_private = data;
 	} else {
 		bio->bi_end_io = bio_copy_kern_endio;
-		bio->bi_rw |= REQ_WRITE;
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 	}
 
 	return bio;
@@ -1544,7 +1545,6 @@ cleanup:
 	bio_put(bio);
 	return ERR_PTR(-ENOMEM);
 }
-EXPORT_SYMBOL(bio_copy_kern);
 
 /*
  * bio_set_pages_dirty() and bio_check_pages_dirty() are support functions
@@ -1789,7 +1789,7 @@ struct bio *bio_split(struct bio *bio, int sectors,
 	 * Discards need a mutable bio_vec to accommodate the payload
 	 * required by the DSM TRIM and UNMAP commands.
 	 */
-	if (bio->bi_rw & REQ_DISCARD)
+	if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE)
 		split = bio_clone_bioset(bio, gfp, bs);
 	else
 		split = bio_clone_fast(bio, gfp, bs);
@@ -1838,7 +1838,7 @@ EXPORT_SYMBOL_GPL(bio_trim);
  */
 mempool_t *biovec_create_pool(int pool_entries)
 {
-	struct biovec_slab *bp = bvec_slabs + BIOVEC_MAX_IDX;
+	struct biovec_slab *bp = bvec_slabs + BVEC_POOL_MAX;
 
 	return mempool_create_slab_pool(pool_entries, bp->slab);
 }
@@ -2026,7 +2026,7 @@ static void __init biovec_init_slabs(void)
 {
 	int i;
 
-	for (i = 0; i < BIOVEC_NR_POOLS; i++) {
+	for (i = 0; i < BVEC_POOL_NR; i++) {
 		int size;
 		struct biovec_slab *bvs = bvec_slabs + i;
 
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 66e6f1aae..dd38e5ced 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -905,7 +905,7 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 	return 0;
 }
 
-struct cftype blkcg_files[] = {
+static struct cftype blkcg_files[] = {
 	{
 		.name = "stat",
 		.flags = CFTYPE_NOT_ON_ROOT,
@@ -914,7 +914,7 @@ struct cftype blkcg_files[] = {
 	{ }	/* terminate */
 };
 
-struct cftype blkcg_legacy_files[] = {
+static struct cftype blkcg_legacy_files[] = {
 	{
 		.name = "reset_stats",
 		.write_u64 = blkcg_reset_stats,
diff --git a/block/blk-core.c b/block/blk-core.c
index 7bcf0e30a..cdcb188e8 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -49,8 +49,6 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug);
 
 DEFINE_IDA(blk_queue_ida);
 
-int trap_non_toi_io;
-
 /*
  * For the allocated request tables
  */
@@ -966,10 +964,10 @@ static void __freed_request(struct request_list *rl, int sync)
  * A request has just been released.  Account for it, update the full and
  * congestion status, wake up any waiters.   Called under q->queue_lock.
  */
-static void freed_request(struct request_list *rl, unsigned int flags)
+static void freed_request(struct request_list *rl, int op, unsigned int flags)
 {
 	struct request_queue *q = rl->q;
-	int sync = rw_is_sync(flags);
+	int sync = rw_is_sync(op, flags);
 
 	q->nr_rqs[sync]--;
 	rl->count[sync]--;
@@ -1036,7 +1034,7 @@ static bool blk_rq_should_init_elevator(struct bio *bio)
 	 * Flush requests do not use the elevator so skip initialization.
 	 * This allows a request to share the flush and elevator data.
 	 */
-	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA))
+	if (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA))
 		return false;
 
 	return true;
@@ -1061,7 +1059,8 @@ static struct io_context *rq_ioc(struct bio *bio)
 /**
  * __get_request - get a free request
  * @rl: request list to allocate from
- * @rw_flags: RW and SYNC flags
+ * @op: REQ_OP_READ/REQ_OP_WRITE
+ * @op_flags: rq_flag_bits
  * @bio: bio to allocate request for (can be %NULL)
  * @gfp_mask: allocation mask
  *
@@ -1072,21 +1071,22 @@ static struct io_context *rq_ioc(struct bio *bio)
  * Returns ERR_PTR on failure, with @q->queue_lock held.
  * Returns request pointer on success, with @q->queue_lock *not held*.
  */
-static struct request *__get_request(struct request_list *rl, int rw_flags,
-				     struct bio *bio, gfp_t gfp_mask)
+static struct request *__get_request(struct request_list *rl, int op,
+				     int op_flags, struct bio *bio,
+				     gfp_t gfp_mask)
 {
 	struct request_queue *q = rl->q;
 	struct request *rq;
 	struct elevator_type *et = q->elevator->type;
 	struct io_context *ioc = rq_ioc(bio);
 	struct io_cq *icq = NULL;
-	const bool is_sync = rw_is_sync(rw_flags) != 0;
+	const bool is_sync = rw_is_sync(op, op_flags) != 0;
 	int may_queue;
 
 	if (unlikely(blk_queue_dying(q)))
 		return ERR_PTR(-ENODEV);
 
-	may_queue = elv_may_queue(q, rw_flags);
+	may_queue = elv_may_queue(q, op, op_flags);
 	if (may_queue == ELV_MQUEUE_NO)
 		goto rq_starved;
 
@@ -1130,7 +1130,7 @@ static struct request *__get_request(struct request_list *rl, int rw_flags,
 
 	/*
 	 * Decide whether the new request will be managed by elevator.  If
-	 * so, mark @rw_flags and increment elvpriv.  Non-zero elvpriv will
+	 * so, mark @op_flags and increment elvpriv.  Non-zero elvpriv will
 	 * prevent the current elevator from being destroyed until the new
 	 * request is freed.  This guarantees icq's won't be destroyed and
 	 * makes creating new ones safe.
@@ -1139,14 +1139,14 @@ static struct request *__get_request(struct request_list *rl, int rw_flags,
 	 * it will be created after releasing queue_lock.
 	 */
 	if (blk_rq_should_init_elevator(bio) && !blk_queue_bypass(q)) {
-		rw_flags |= REQ_ELVPRIV;
+		op_flags |= REQ_ELVPRIV;
 		q->nr_rqs_elvpriv++;
 		if (et->icq_cache && ioc)
 			icq = ioc_lookup_icq(ioc, q);
 	}
 
 	if (blk_queue_io_stat(q))
-		rw_flags |= REQ_IO_STAT;
+		op_flags |= REQ_IO_STAT;
 	spin_unlock_irq(q->queue_lock);
 
 	/* allocate and init request */
@@ -1156,10 +1156,10 @@ static struct request *__get_request(struct request_list *rl, int rw_flags,
 
 	blk_rq_init(q, rq);
 	blk_rq_set_rl(rq, rl);
-	rq->cmd_flags = rw_flags | REQ_ALLOCED;
+	req_set_op_attrs(rq, op, op_flags | REQ_ALLOCED);
 
 	/* init elvpriv */
-	if (rw_flags & REQ_ELVPRIV) {
+	if (op_flags & REQ_ELVPRIV) {
 		if (unlikely(et->icq_cache && !icq)) {
 			if (ioc)
 				icq = ioc_create_icq(ioc, q, gfp_mask);
@@ -1185,7 +1185,7 @@ out:
 	if (ioc_batching(q, ioc))
 		ioc->nr_batch_requests--;
 
-	trace_block_getrq(q, bio, rw_flags & 1);
+	trace_block_getrq(q, bio, op);
 	return rq;
 
 fail_elvpriv:
@@ -1215,7 +1215,7 @@ fail_alloc:
 	 * queue, but this is pretty rare.
 	 */
 	spin_lock_irq(q->queue_lock);
-	freed_request(rl, rw_flags);
+	freed_request(rl, op, op_flags);
 
 	/*
 	 * in the very unlikely event that allocation failed and no
@@ -1233,7 +1233,8 @@ rq_starved:
 /**
  * get_request - get a free request
  * @q: request_queue to allocate request from
- * @rw_flags: RW and SYNC flags
+ * @op: REQ_OP_READ/REQ_OP_WRITE
+ * @op_flags: rq_flag_bits
  * @bio: bio to allocate request for (can be %NULL)
  * @gfp_mask: allocation mask
  *
@@ -1244,17 +1245,18 @@ rq_starved:
  * Returns ERR_PTR on failure, with @q->queue_lock held.
  * Returns request pointer on success, with @q->queue_lock *not held*.
  */
-static struct request *get_request(struct request_queue *q, int rw_flags,
-				   struct bio *bio, gfp_t gfp_mask)
+static struct request *get_request(struct request_queue *q, int op,
+				   int op_flags, struct bio *bio,
+				   gfp_t gfp_mask)
 {
-	const bool is_sync = rw_is_sync(rw_flags) != 0;
+	const bool is_sync = rw_is_sync(op, op_flags) != 0;
 	DEFINE_WAIT(wait);
 	struct request_list *rl;
 	struct request *rq;
 
 	rl = blk_get_rl(q, bio);	/* transferred to @rq on success */
 retry:
-	rq = __get_request(rl, rw_flags, bio, gfp_mask);
+	rq = __get_request(rl, op, op_flags, bio, gfp_mask);
 	if (!IS_ERR(rq))
 		return rq;
 
@@ -1267,7 +1269,7 @@ retry:
 	prepare_to_wait_exclusive(&rl->wait[is_sync], &wait,
 				  TASK_UNINTERRUPTIBLE);
 
-	trace_block_sleeprq(q, bio, rw_flags & 1);
+	trace_block_sleeprq(q, bio, op);
 
 	spin_unlock_irq(q->queue_lock);
 	io_schedule();
@@ -1296,11 +1298,16 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw,
 	create_io_context(gfp_mask, q->node);
 
 	spin_lock_irq(q->queue_lock);
-	rq = get_request(q, rw, NULL, gfp_mask);
-	if (IS_ERR(rq))
+	rq = get_request(q, rw, 0, NULL, gfp_mask);
+	if (IS_ERR(rq)) {
 		spin_unlock_irq(q->queue_lock);
-	/* q->queue_lock is unlocked at this point */
+		return rq;
+	}
 
+	/* q->queue_lock is unlocked at this point */
+	rq->__data_len = 0;
+	rq->__sector = (sector_t) -1;
+	rq->bio = rq->biotail = NULL;
 	return rq;
 }
 
@@ -1316,63 +1323,6 @@ struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
 EXPORT_SYMBOL(blk_get_request);
 
 /**
- * blk_make_request - given a bio, allocate a corresponding struct request.
- * @q: target request queue
- * @bio:  The bio describing the memory mappings that will be submitted for IO.
- *        It may be a chained-bio properly constructed by block/bio layer.
- * @gfp_mask: gfp flags to be used for memory allocation
- *
- * blk_make_request is the parallel of generic_make_request for BLOCK_PC
- * type commands. Where the struct request needs to be farther initialized by
- * the caller. It is passed a &struct bio, which describes the memory info of
- * the I/O transfer.
- *
- * The caller of blk_make_request must make sure that bi_io_vec
- * are set to describe the memory buffers. That bio_data_dir() will return
- * the needed direction of the request. (And all bio's in the passed bio-chain
- * are properly set accordingly)
- *
- * If called under none-sleepable conditions, mapped bio buffers must not
- * need bouncing, by calling the appropriate masked or flagged allocator,
- * suitable for the target device. Otherwise the call to blk_queue_bounce will
- * BUG.
- *
- * WARNING: When allocating/cloning a bio-chain, careful consideration should be
- * given to how you allocate bios. In particular, you cannot use
- * __GFP_DIRECT_RECLAIM for anything but the first bio in the chain. Otherwise
- * you risk waiting for IO completion of a bio that hasn't been submitted yet,
- * thus resulting in a deadlock. Alternatively bios should be allocated using
- * bio_kmalloc() instead of bio_alloc(), as that avoids the mempool deadlock.
- * If possible a big IO should be split into smaller parts when allocation
- * fails. Partial allocation should not be an error, or you risk a live-lock.
- */
-struct request *blk_make_request(struct request_queue *q, struct bio *bio,
-				 gfp_t gfp_mask)
-{
-	struct request *rq = blk_get_request(q, bio_data_dir(bio), gfp_mask);
-
-	if (IS_ERR(rq))
-		return rq;
-
-	blk_rq_set_block_pc(rq);
-
-	for_each_bio(bio) {
-		struct bio *bounce_bio = bio;
-		int ret;
-
-		blk_queue_bounce(q, &bounce_bio);
-		ret = blk_rq_append_bio(q, rq, bounce_bio);
-		if (unlikely(ret)) {
-			blk_put_request(rq);
-			return ERR_PTR(ret);
-		}
-	}
-
-	return rq;
-}
-EXPORT_SYMBOL(blk_make_request);
-
-/**
  * blk_rq_set_block_pc - initialize a request to type BLOCK_PC
  * @rq:		request to be initialized
  *
@@ -1380,9 +1330,6 @@ EXPORT_SYMBOL(blk_make_request);
 void blk_rq_set_block_pc(struct request *rq)
 {
 	rq->cmd_type = REQ_TYPE_BLOCK_PC;
-	rq->__data_len = 0;
-	rq->__sector = (sector_t) -1;
-	rq->bio = rq->biotail = NULL;
 	memset(rq->__cmd, 0, sizeof(rq->__cmd));
 }
 EXPORT_SYMBOL(blk_rq_set_block_pc);
@@ -1501,13 +1448,14 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 	 */
 	if (req->cmd_flags & REQ_ALLOCED) {
 		unsigned int flags = req->cmd_flags;
+		int op = req_op(req);
 		struct request_list *rl = blk_rq_rl(req);
 
 		BUG_ON(!list_empty(&req->queuelist));
 		BUG_ON(ELV_ON_HASH(req));
 
 		blk_free_request(rl, req);
-		freed_request(rl, flags);
+		freed_request(rl, op, flags);
 		blk_put_rl(rl);
 	}
 }
@@ -1564,7 +1512,7 @@ EXPORT_SYMBOL_GPL(blk_add_request_payload);
 bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
 			    struct bio *bio)
 {
-	const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
+	const int ff = bio->bi_opf & REQ_FAILFAST_MASK;
 
 	if (!ll_back_merge_fn(q, req, bio))
 		return false;
@@ -1586,7 +1534,7 @@ bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
 bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
 			     struct bio *bio)
 {
-	const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
+	const int ff = bio->bi_opf & REQ_FAILFAST_MASK;
 
 	if (!ll_front_merge_fn(q, req, bio))
 		return false;
@@ -1708,8 +1656,8 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 {
 	req->cmd_type = REQ_TYPE_FS;
 
-	req->cmd_flags |= bio->bi_rw & REQ_COMMON_MASK;
-	if (bio->bi_rw & REQ_RAHEAD)
+	req->cmd_flags |= bio->bi_opf & REQ_COMMON_MASK;
+	if (bio->bi_opf & REQ_RAHEAD)
 		req->cmd_flags |= REQ_FAILFAST_MASK;
 
 	req->errors = 0;
@@ -1720,12 +1668,12 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 
 static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 {
-	const bool sync = !!(bio->bi_rw & REQ_SYNC);
+	const bool sync = !!(bio->bi_opf & REQ_SYNC);
 	struct blk_plug *plug;
-	int el_ret, rw_flags, where = ELEVATOR_INSERT_SORT;
+	int el_ret, rw_flags = 0, where = ELEVATOR_INSERT_SORT;
 	struct request *req;
 	unsigned int request_count = 0;
-	bool wb_acct;
+	unsigned int wb_acct;
 
 	/*
 	 * low level driver can indicate that it wants pages above a
@@ -1742,7 +1690,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 		return BLK_QC_T_NONE;
 	}
 
-	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
+	if (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA)) {
 		spin_lock_irq(q->queue_lock);
 		where = ELEVATOR_INSERT_FLUSH;
 		goto get_rq;
@@ -1778,32 +1726,34 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 	}
 
 get_rq:
-	wb_acct = wbt_wait(q->rq_wb, bio->bi_rw, q->queue_lock);
+	wb_acct = wbt_wait(q->rq_wb, bio->bi_opf, q->queue_lock);
 
 	/*
 	 * This sync check and mask will be re-done in init_request_from_bio(),
 	 * but we need to set it earlier to expose the sync flag to the
 	 * rq allocator and io schedulers.
 	 */
-	rw_flags = bio_data_dir(bio);
 	if (sync)
 		rw_flags |= REQ_SYNC;
 
 	/*
+	 * Add in META/PRIO flags, if set, before we get to the IO scheduler
+	 */
+	rw_flags |= (bio->bi_opf & (REQ_META | REQ_PRIO));
+
+	/*
 	 * Grab a free request. This is might sleep but can not fail.
 	 * Returns with the queue unlocked.
 	 */
-	req = get_request(q, rw_flags, bio, GFP_NOIO);
+	req = get_request(q, bio_data_dir(bio), rw_flags, bio, GFP_NOIO);
 	if (IS_ERR(req)) {
-		if (wb_acct)
-			__wbt_done(q->rq_wb);
+		__wbt_done(q->rq_wb, wb_acct);
 		bio->bi_error = PTR_ERR(req);
 		bio_endio(bio);
 		goto out_unlock;
 	}
 
-	if (wb_acct)
-		wbt_mark_tracked(&req->wb_stat);
+	wbt_track(&req->wb_stat, wb_acct);
 
 	/*
 	 * After dropping the lock and possibly sleeping here, our request
@@ -1867,9 +1817,9 @@ static void handle_bad_sector(struct bio *bio)
 	char b[BDEVNAME_SIZE];
 
 	printk(KERN_INFO "attempt to access beyond end of device\n");
-	printk(KERN_INFO "%s: rw=%ld, want=%Lu, limit=%Lu\n",
+	printk(KERN_INFO "%s: rw=%d, want=%Lu, limit=%Lu\n",
 			bdevname(bio->bi_bdev, b),
-			bio->bi_rw,
+			bio->bi_opf,
 			(unsigned long long)bio_end_sector(bio),
 			(long long)(i_size_read(bio->bi_bdev->bd_inode) >> 9));
 }
@@ -1982,25 +1932,30 @@ generic_make_request_checks(struct bio *bio)
 	 * drivers without flush support don't have to worry
 	 * about them.
 	 */
-	if ((bio->bi_rw & (REQ_FLUSH | REQ_FUA)) &&
+	if ((bio->bi_opf & (REQ_PREFLUSH | REQ_FUA)) &&
 	    !test_bit(QUEUE_FLAG_WC, &q->queue_flags)) {
-		bio->bi_rw &= ~(REQ_FLUSH | REQ_FUA);
+		bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA);
 		if (!nr_sectors) {
 			err = 0;
 			goto end_io;
 		}
 	}
 
-	if ((bio->bi_rw & REQ_DISCARD) &&
-	    (!blk_queue_discard(q) ||
-	     ((bio->bi_rw & REQ_SECURE) && !blk_queue_secdiscard(q)))) {
-		err = -EOPNOTSUPP;
-		goto end_io;
-	}
-
-	if (bio->bi_rw & REQ_WRITE_SAME && !bdev_write_same(bio->bi_bdev)) {
-		err = -EOPNOTSUPP;
-		goto end_io;
+	switch (bio_op(bio)) {
+	case REQ_OP_DISCARD:
+		if (!blk_queue_discard(q))
+			goto not_supported;
+		break;
+	case REQ_OP_SECURE_ERASE:
+		if (!blk_queue_secure_erase(q))
+			goto not_supported;
+		break;
+	case REQ_OP_WRITE_SAME:
+		if (!bdev_write_same(bio->bi_bdev))
+			goto not_supported;
+		break;
+	default:
+		break;
 	}
 
 	/*
@@ -2017,6 +1972,8 @@ generic_make_request_checks(struct bio *bio)
 	trace_block_bio_queue(q, bio);
 	return true;
 
+not_supported:
+	err = -EOPNOTSUPP;
 end_io:
 	bio->bi_error = err;
 	bio_endio(bio);
@@ -2112,7 +2069,6 @@ EXPORT_SYMBOL(generic_make_request);
 
 /**
  * submit_bio - submit a bio to the block device layer for I/O
- * @rw: whether to %READ or %WRITE, or maybe to %READA (read ahead)
  * @bio: The &struct bio which describes the I/O
  *
  * submit_bio() is very similar in purpose to generic_make_request(), and
@@ -2120,13 +2076,8 @@ EXPORT_SYMBOL(generic_make_request);
  * interfaces; @bio must be presetup and ready for I/O.
  *
  */
-blk_qc_t submit_bio(int rw, struct bio *bio)
+blk_qc_t submit_bio(struct bio *bio)
 {
-	bio->bi_rw |= rw;
-
-	if (unlikely(trap_non_toi_io))
-		BUG_ON(!bio_flagged(bio, BIO_TOI));
-
 	/*
 	 * If it's a regular read/write or a barrier with data attached,
 	 * go through the normal accounting stuff before submission.
@@ -2134,12 +2085,12 @@ blk_qc_t submit_bio(int rw, struct bio *bio)
 	if (bio_has_data(bio)) {
 		unsigned int count;
 
-		if (unlikely(rw & REQ_WRITE_SAME))
+		if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME))
 			count = bdev_logical_block_size(bio->bi_bdev) >> 9;
 		else
 			count = bio_sectors(bio);
 
-		if (rw & WRITE) {
+		if (op_is_write(bio_op(bio))) {
 			count_vm_events(PGPGOUT, count);
 		} else {
 			task_io_account_read(bio->bi_iter.bi_size);
@@ -2150,7 +2101,7 @@ blk_qc_t submit_bio(int rw, struct bio *bio)
 			char b[BDEVNAME_SIZE];
 			printk(KERN_DEBUG "%s(%d): %s block %Lu on %s (%u sectors)\n",
 			current->comm, task_pid_nr(current),
-				(rw & WRITE) ? "WRITE" : "READ",
+				op_is_write(bio_op(bio)) ? "WRITE" : "READ",
 				(unsigned long long)bio->bi_iter.bi_sector,
 				bdevname(bio->bi_bdev, b),
 				count);
@@ -2181,7 +2132,7 @@ EXPORT_SYMBOL(submit_bio);
 static int blk_cloned_rq_check_limits(struct request_queue *q,
 				      struct request *rq)
 {
-	if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q, rq->cmd_flags)) {
+	if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q, req_op(rq))) {
 		printk(KERN_ERR "%s: over max size limit.\n", __func__);
 		return -EIO;
 	}
@@ -2237,7 +2188,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 	 */
 	BUG_ON(blk_queued_rq(rq));
 
-	if (rq->cmd_flags & (REQ_FLUSH|REQ_FUA))
+	if (rq->cmd_flags & (REQ_PREFLUSH | REQ_FUA))
 		where = ELEVATOR_INSERT_FLUSH;
 
 	add_acct_request(q, rq, where);
@@ -2282,7 +2233,7 @@ unsigned int blk_rq_err_bytes(const struct request *rq)
 	 * one.
 	 */
 	for (bio = rq->bio; bio; bio = bio->bi_next) {
-		if ((bio->bi_rw & ff) != ff)
+		if ((bio->bi_opf & ff) != ff)
 			break;
 		bytes += bio->bi_iter.bi_size;
 	}
@@ -2697,7 +2648,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	/* mixed attributes always follow the first bio */
 	if (req->cmd_flags & REQ_MIXED_MERGE) {
 		req->cmd_flags &= ~REQ_FAILFAST_MASK;
-		req->cmd_flags |= req->bio->bi_rw & REQ_FAILFAST_MASK;
+		req->cmd_flags |= req->bio->bi_opf & REQ_FAILFAST_MASK;
 	}
 
 	/*
@@ -3005,8 +2956,7 @@ EXPORT_SYMBOL_GPL(__blk_end_request_err);
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 		     struct bio *bio)
 {
-	/* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw */
-	rq->cmd_flags |= bio->bi_rw & REQ_WRITE;
+	req_set_op(rq, bio_op(bio));
 
 	if (bio_has_data(bio))
 		rq->nr_phys_segments = bio_phys_segments(q, bio);
@@ -3091,7 +3041,8 @@ EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
 static void __blk_rq_prep_clone(struct request *dst, struct request *src)
 {
 	dst->cpu = src->cpu;
-	dst->cmd_flags |= (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE;
+	req_set_op_attrs(dst, req_op(src),
+			 (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE);
 	dst->cmd_type = src->cmd_type;
 	dst->__sector = blk_rq_pos(src);
 	dst->__data_len = blk_rq_bytes(src);
@@ -3336,7 +3287,7 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 		/*
 		 * rq is already accounted, so use raw insert
 		 */
-		if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA))
+		if (rq->cmd_flags & (REQ_PREFLUSH | REQ_FUA))
 			__elv_add_request(q, rq, ELEVATOR_INSERT_FLUSH);
 		else
 			__elv_add_request(q, rq, ELEVATOR_INSERT_SORT_MERGE);
@@ -3403,6 +3354,7 @@ bool blk_poll(struct request_queue *q, blk_qc_t cookie)
 
 	return false;
 }
+EXPORT_SYMBOL_GPL(blk_poll);
 
 #ifdef CONFIG_PM
 /**
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 3fec8a29d..7ea04325d 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -62,7 +62,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 
 	/*
 	 * don't check dying flag for MQ because the request won't
-	 * be resued after dying flag is set
+	 * be reused after dying flag is set
 	 */
 	if (q->mq_ops) {
 		blk_mq_insert_request(rq, at_head, true, false);
diff --git a/block/blk-flush.c b/block/blk-flush.c
index b1c91d229..d308def81 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -10,8 +10,8 @@
  * optional steps - PREFLUSH, DATA and POSTFLUSH - according to the request
  * properties and hardware capability.
  *
- * If a request doesn't have data, only REQ_FLUSH makes sense, which
- * indicates a simple flush request.  If there is data, REQ_FLUSH indicates
+ * If a request doesn't have data, only REQ_PREFLUSH makes sense, which
+ * indicates a simple flush request.  If there is data, REQ_PREFLUSH indicates
  * that the device cache should be flushed before the data is executed, and
  * REQ_FUA means that the data must be on non-volatile media on request
  * completion.
@@ -20,16 +20,16 @@
  * difference.  The requests are either completed immediately if there's no
  * data or executed as normal requests otherwise.
  *
- * If the device has writeback cache and supports FUA, REQ_FLUSH is
+ * If the device has writeback cache and supports FUA, REQ_PREFLUSH is
  * translated to PREFLUSH but REQ_FUA is passed down directly with DATA.
  *
- * If the device has writeback cache and doesn't support FUA, REQ_FLUSH is
- * translated to PREFLUSH and REQ_FUA to POSTFLUSH.
+ * If the device has writeback cache and doesn't support FUA, REQ_PREFLUSH
+ * is translated to PREFLUSH and REQ_FUA to POSTFLUSH.
  *
  * The actual execution of flush is double buffered.  Whenever a request
  * needs to execute PRE or POSTFLUSH, it queues at
  * fq->flush_queue[fq->flush_pending_idx].  Once certain criteria are met, a
- * flush is issued and the pending_idx is toggled.  When the flush
+ * REQ_OP_FLUSH is issued and the pending_idx is toggled.  When the flush
  * completes, all the requests which were pending are proceeded to the next
  * step.  This allows arbitrary merging of different types of FLUSH/FUA
  * requests.
@@ -103,7 +103,7 @@ static unsigned int blk_flush_policy(unsigned long fflags, struct request *rq)
 		policy |= REQ_FSEQ_DATA;
 
 	if (fflags & (1UL << QUEUE_FLAG_WC)) {
-		if (rq->cmd_flags & REQ_FLUSH)
+		if (rq->cmd_flags & REQ_PREFLUSH)
 			policy |= REQ_FSEQ_PREFLUSH;
 		if (!(fflags & (1UL << QUEUE_FLAG_FUA)) &&
 		    (rq->cmd_flags & REQ_FUA))
@@ -330,7 +330,7 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
 	}
 
 	flush_rq->cmd_type = REQ_TYPE_FS;
-	flush_rq->cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ;
+	req_set_op_attrs(flush_rq, REQ_OP_FLUSH, WRITE_FLUSH | REQ_FLUSH_SEQ);
 	flush_rq->rq_disk = first_rq->rq_disk;
 	flush_rq->end_io = flush_end_io;
 
@@ -391,9 +391,9 @@ void blk_insert_flush(struct request *rq)
 
 	/*
 	 * @policy now records what operations need to be done.  Adjust
-	 * REQ_FLUSH and FUA for the driver.
+	 * REQ_PREFLUSH and FUA for the driver.
 	 */
-	rq->cmd_flags &= ~REQ_FLUSH;
+	rq->cmd_flags &= ~REQ_PREFLUSH;
 	if (!(fflags & (1UL << QUEUE_FLAG_FUA)))
 		rq->cmd_flags &= ~REQ_FUA;
 
@@ -485,8 +485,9 @@ int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
 
 	bio = bio_alloc(gfp_mask, 0);
 	bio->bi_bdev = bdev;
+	bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_FLUSH);
 
-	ret = submit_bio_wait(WRITE_FLUSH, bio);
+	ret = submit_bio_wait(bio);
 
 	/*
 	 * The driver must store the error location in ->bi_sector, if
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 9e29dc351..083e56f72 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -9,33 +9,46 @@
 
 #include "blk.h"
 
-static struct bio *next_bio(struct bio *bio, int rw, unsigned int nr_pages,
+static struct bio *next_bio(struct bio *bio, unsigned int nr_pages,
 		gfp_t gfp)
 {
 	struct bio *new = bio_alloc(gfp, nr_pages);
 
 	if (bio) {
 		bio_chain(bio, new);
-		submit_bio(rw, bio);
+		submit_bio(bio);
 	}
 
 	return new;
 }
 
 int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
-		sector_t nr_sects, gfp_t gfp_mask, int type, struct bio **biop)
+		sector_t nr_sects, gfp_t gfp_mask, int flags,
+		struct bio **biop)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
 	struct bio *bio = *biop;
 	unsigned int granularity;
+	enum req_op op;
 	int alignment;
 
 	if (!q)
 		return -ENXIO;
-	if (!blk_queue_discard(q))
-		return -EOPNOTSUPP;
-	if ((type & REQ_SECURE) && !blk_queue_secdiscard(q))
-		return -EOPNOTSUPP;
+
+	if (flags & BLKDEV_DISCARD_SECURE) {
+		if (flags & BLKDEV_DISCARD_ZERO)
+			return -EOPNOTSUPP;
+		if (!blk_queue_secure_erase(q))
+			return -EOPNOTSUPP;
+		op = REQ_OP_SECURE_ERASE;
+	} else {
+		if (!blk_queue_discard(q))
+			return -EOPNOTSUPP;
+		if ((flags & BLKDEV_DISCARD_ZERO) &&
+		    !q->limits.discard_zeroes_data)
+			return -EOPNOTSUPP;
+		op = REQ_OP_DISCARD;
+	}
 
 	/* Zero-sector (unknown) and one-sector granularities are the same.  */
 	granularity = max(q->limits.discard_granularity >> 9, 1U);
@@ -62,9 +75,10 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 			req_sects = end_sect - sector;
 		}
 
-		bio = next_bio(bio, type, 1, gfp_mask);
+		bio = next_bio(bio, 1, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		bio->bi_bdev = bdev;
+		bio_set_op_attrs(bio, op, 0);
 
 		bio->bi_iter.bi_size = req_sects << 9;
 		nr_sects -= req_sects;
@@ -98,20 +112,16 @@ EXPORT_SYMBOL(__blkdev_issue_discard);
 int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, unsigned long flags)
 {
-	int type = REQ_WRITE | REQ_DISCARD;
 	struct bio *bio = NULL;
 	struct blk_plug plug;
 	int ret;
 
-	if (flags & BLKDEV_DISCARD_SECURE)
-		type |= REQ_SECURE;
-
 	blk_start_plug(&plug);
-	ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, type,
+	ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, flags,
 			&bio);
 	if (!ret && bio) {
-		ret = submit_bio_wait(type, bio);
-		if (ret == -EOPNOTSUPP)
+		ret = submit_bio_wait(bio);
+		if (ret == -EOPNOTSUPP && !(flags & BLKDEV_DISCARD_ZERO))
 			ret = 0;
 		bio_put(bio);
 	}
@@ -148,13 +158,14 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 	max_write_same_sectors = UINT_MAX >> 9;
 
 	while (nr_sects) {
-		bio = next_bio(bio, REQ_WRITE | REQ_WRITE_SAME, 1, gfp_mask);
+		bio = next_bio(bio, 1, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		bio->bi_bdev = bdev;
 		bio->bi_vcnt = 1;
 		bio->bi_io_vec->bv_page = page;
 		bio->bi_io_vec->bv_offset = 0;
 		bio->bi_io_vec->bv_len = bdev_logical_block_size(bdev);
+		bio_set_op_attrs(bio, REQ_OP_WRITE_SAME, 0);
 
 		if (nr_sects > max_write_same_sectors) {
 			bio->bi_iter.bi_size = max_write_same_sectors << 9;
@@ -167,10 +178,10 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 	}
 
 	if (bio) {
-		ret = submit_bio_wait(REQ_WRITE | REQ_WRITE_SAME, bio);
+		ret = submit_bio_wait(bio);
 		bio_put(bio);
 	}
-	return ret != -EOPNOTSUPP ? ret : 0;
+	return ret;
 }
 EXPORT_SYMBOL(blkdev_issue_write_same);
 
@@ -193,11 +204,11 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 	unsigned int sz;
 
 	while (nr_sects != 0) {
-		bio = next_bio(bio, WRITE,
-				min(nr_sects, (sector_t)BIO_MAX_PAGES),
+		bio = next_bio(bio, min(nr_sects, (sector_t)BIO_MAX_PAGES),
 				gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		bio->bi_bdev   = bdev;
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
 		while (nr_sects != 0) {
 			sz = min((sector_t) PAGE_SIZE >> 9 , nr_sects);
@@ -210,7 +221,7 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 	}
 
 	if (bio) {
-		ret = submit_bio_wait(WRITE, bio);
+		ret = submit_bio_wait(bio);
 		bio_put(bio);
 		return ret;
 	}
@@ -241,11 +252,11 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 			 sector_t nr_sects, gfp_t gfp_mask, bool discard)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	if (discard && blk_queue_discard(q) && q->limits.discard_zeroes_data &&
-	    blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, 0) == 0)
-		return 0;
+	if (discard) {
+		if (!blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask,
+				BLKDEV_DISCARD_ZERO))
+			return 0;
+	}
 
 	if (bdev_write_same(bdev) &&
 	    blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
diff --git a/block/blk-map.c b/block/blk-map.c
index b9f88b775..b8657fa8d 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -9,21 +9,26 @@
 
 #include "blk.h"
 
-int blk_rq_append_bio(struct request_queue *q, struct request *rq,
-		      struct bio *bio)
+/*
+ * Append a bio to a passthrough request.  Only works can be merged into
+ * the request based on the driver constraints.
+ */
+int blk_rq_append_bio(struct request *rq, struct bio *bio)
 {
-	if (!rq->bio)
-		blk_rq_bio_prep(q, rq, bio);
-	else if (!ll_back_merge_fn(q, rq, bio))
-		return -EINVAL;
-	else {
+	if (!rq->bio) {
+		blk_rq_bio_prep(rq->q, rq, bio);
+	} else {
+		if (!ll_back_merge_fn(rq->q, rq, bio))
+			return -EINVAL;
+
 		rq->biotail->bi_next = bio;
 		rq->biotail = bio;
-
 		rq->__data_len += bio->bi_iter.bi_size;
 	}
+
 	return 0;
 }
+EXPORT_SYMBOL(blk_rq_append_bio);
 
 static int __blk_rq_unmap_user(struct bio *bio)
 {
@@ -71,7 +76,7 @@ static int __blk_rq_map_user_iov(struct request *rq,
 	 */
 	bio_get(bio);
 
-	ret = blk_rq_append_bio(q, rq, bio);
+	ret = blk_rq_append_bio(rq, bio);
 	if (ret) {
 		bio_endio(bio);
 		__blk_rq_unmap_user(orig_bio);
@@ -224,12 +229,12 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 		return PTR_ERR(bio);
 
 	if (!reading)
-		bio->bi_rw |= REQ_WRITE;
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
 	if (do_copy)
 		rq->cmd_flags |= REQ_COPY_USER;
 
-	ret = blk_rq_append_bio(q, rq, bio);
+	ret = blk_rq_append_bio(rq, bio);
 	if (unlikely(ret)) {
 		/* request is too big */
 		bio_put(bio);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index bea93441a..2642e5fc8 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -194,12 +194,18 @@ void blk_queue_split(struct request_queue *q, struct bio **bio,
 	struct bio *split, *res;
 	unsigned nsegs;
 
-	if ((*bio)->bi_rw & REQ_DISCARD)
+	switch (bio_op(*bio)) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_SECURE_ERASE:
 		split = blk_bio_discard_split(q, *bio, bs, &nsegs);
-	else if ((*bio)->bi_rw & REQ_WRITE_SAME)
+		break;
+	case REQ_OP_WRITE_SAME:
 		split = blk_bio_write_same_split(q, *bio, bs, &nsegs);
-	else
+		break;
+	default:
 		split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs);
+		break;
+	}
 
 	/* physical segments can be figured out during splitting */
 	res = split ? split : *bio;
@@ -208,7 +214,7 @@ void blk_queue_split(struct request_queue *q, struct bio **bio,
 
 	if (split) {
 		/* there isn't chance to merge the splitted bio */
-		split->bi_rw |= REQ_NOMERGE;
+		split->bi_opf |= REQ_NOMERGE;
 
 		bio_chain(split, *bio);
 		trace_block_split(q, split, (*bio)->bi_iter.bi_sector);
@@ -235,10 +241,10 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 	 * This should probably be returning 0, but blk_add_request_payload()
 	 * (Christoph!!!!)
 	 */
-	if (bio->bi_rw & REQ_DISCARD)
+	if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE)
 		return 1;
 
-	if (bio->bi_rw & REQ_WRITE_SAME)
+	if (bio_op(bio) == REQ_OP_WRITE_SAME)
 		return 1;
 
 	fbio = bio;
@@ -407,7 +413,9 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
 	nsegs = 0;
 	cluster = blk_queue_cluster(q);
 
-	if (bio->bi_rw & REQ_DISCARD) {
+	switch (bio_op(bio)) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_SECURE_ERASE:
 		/*
 		 * This is a hack - drivers should be neither modifying the
 		 * biovec, nor relying on bi_vcnt - but because of
@@ -415,19 +423,16 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
 		 * a payload we need to set up here (thank you Christoph) and
 		 * bi_vcnt is really the only way of telling if we need to.
 		 */
-
-		if (bio->bi_vcnt)
-			goto single_segment;
-
-		return 0;
-	}
-
-	if (bio->bi_rw & REQ_WRITE_SAME) {
-single_segment:
+		if (!bio->bi_vcnt)
+			return 0;
+		/* Fall through */
+	case REQ_OP_WRITE_SAME:
 		*sg = sglist;
 		bvec = bio_iovec(bio);
 		sg_set_page(*sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset);
 		return 1;
+	default:
+		break;
 	}
 
 	for_each_bio(bio)
@@ -461,7 +466,7 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 	}
 
 	if (q->dma_drain_size && q->dma_drain_needed(rq)) {
-		if (rq->cmd_flags & REQ_WRITE)
+		if (op_is_write(req_op(rq)))
 			memset(q->dma_drain_buffer, 0, q->dma_drain_size);
 
 		sg_unmark_end(sg);
@@ -522,7 +527,7 @@ int ll_back_merge_fn(struct request_queue *q, struct request *req,
 	    integrity_req_gap_back_merge(req, bio))
 		return 0;
 	if (blk_rq_sectors(req) + bio_sectors(bio) >
-	    blk_rq_get_max_sectors(req)) {
+	    blk_rq_get_max_sectors(req, blk_rq_pos(req))) {
 		req->cmd_flags |= REQ_NOMERGE;
 		if (req == q->last_merge)
 			q->last_merge = NULL;
@@ -546,7 +551,7 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req,
 	    integrity_req_gap_front_merge(req, bio))
 		return 0;
 	if (blk_rq_sectors(req) + bio_sectors(bio) >
-	    blk_rq_get_max_sectors(req)) {
+	    blk_rq_get_max_sectors(req, bio->bi_iter.bi_sector)) {
 		req->cmd_flags |= REQ_NOMERGE;
 		if (req == q->last_merge)
 			q->last_merge = NULL;
@@ -592,7 +597,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 	 * Will it become too large?
 	 */
 	if ((blk_rq_sectors(req) + blk_rq_sectors(next)) >
-	    blk_rq_get_max_sectors(req))
+	    blk_rq_get_max_sectors(req, blk_rq_pos(req)))
 		return 0;
 
 	total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
@@ -638,9 +643,9 @@ void blk_rq_set_mixed_merge(struct request *rq)
 	 * Distributes the attributs to each bio.
 	 */
 	for (bio = rq->bio; bio; bio = bio->bi_next) {
-		WARN_ON_ONCE((bio->bi_rw & REQ_FAILFAST_MASK) &&
-			     (bio->bi_rw & REQ_FAILFAST_MASK) != ff);
-		bio->bi_rw |= ff;
+		WARN_ON_ONCE((bio->bi_opf & REQ_FAILFAST_MASK) &&
+			     (bio->bi_opf & REQ_FAILFAST_MASK) != ff);
+		bio->bi_opf |= ff;
 	}
 	rq->cmd_flags |= REQ_MIXED_MERGE;
 }
@@ -671,7 +676,7 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	if (!rq_mergeable(req) || !rq_mergeable(next))
 		return 0;
 
-	if (!blk_check_merge_flags(req->cmd_flags, next->cmd_flags))
+	if (req_op(req) != req_op(next))
 		return 0;
 
 	/*
@@ -685,7 +690,7 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	    || req_no_special_merge(next))
 		return 0;
 
-	if (req->cmd_flags & REQ_WRITE_SAME &&
+	if (req_op(req) == REQ_OP_WRITE_SAME &&
 	    !blk_write_same_mergeable(req->bio, next->bio))
 		return 0;
 
@@ -765,6 +770,12 @@ int attempt_front_merge(struct request_queue *q, struct request *rq)
 int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
 			  struct request *next)
 {
+	struct elevator_queue *e = q->elevator;
+
+	if (e->type->ops.elevator_allow_rq_merge_fn)
+		if (!e->type->ops.elevator_allow_rq_merge_fn(q, rq, next))
+			return 0;
+
 	return attempt_merge(q, rq, next);
 }
 
@@ -773,7 +784,7 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (!rq_mergeable(rq) || !bio_mergeable(bio))
 		return false;
 
-	if (!blk_check_merge_flags(rq->cmd_flags, bio->bi_rw))
+	if (req_op(rq) != bio_op(bio))
 		return false;
 
 	/* different data direction or already started, don't merge */
@@ -789,7 +800,7 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 		return false;
 
 	/* must be using the same buffer */
-	if (rq->cmd_flags & REQ_WRITE_SAME &&
+	if (req_op(rq) == REQ_OP_WRITE_SAME &&
 	    !blk_write_same_mergeable(rq->bio, bio))
 		return false;
 
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 2f68015f8..b66bbf13c 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -427,15 +427,13 @@ static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx)
 	return ret;
 }
 
-void blk_mq_unregister_disk(struct gendisk *disk)
+static void __blk_mq_unregister_disk(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
 	int i, j;
 
-	blk_mq_disable_hotplug();
-
 	queue_for_each_hw_ctx(q, hctx, i) {
 		blk_mq_unregister_hctx(hctx);
 
@@ -452,6 +450,12 @@ void blk_mq_unregister_disk(struct gendisk *disk)
 	kobject_put(&disk_to_dev(disk)->kobj);
 
 	q->mq_sysfs_init_done = false;
+}
+
+void blk_mq_unregister_disk(struct gendisk *disk)
+{
+	blk_mq_disable_hotplug();
+	__blk_mq_unregister_disk(disk);
 	blk_mq_enable_hotplug();
 }
 
@@ -497,7 +501,7 @@ int blk_mq_register_disk(struct gendisk *disk)
 	}
 
 	if (ret)
-		blk_mq_unregister_disk(disk);
+		__blk_mq_unregister_disk(disk);
 	else
 		q->mq_sysfs_init_done = true;
 out:
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 56a0c37a3..729bac3a6 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -485,6 +485,32 @@ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 }
 EXPORT_SYMBOL(blk_mq_tagset_busy_iter);
 
+int blk_mq_reinit_tagset(struct blk_mq_tag_set *set)
+{
+	int i, j, ret = 0;
+
+	if (!set->ops->reinit_request)
+		goto out;
+
+	for (i = 0; i < set->nr_hw_queues; i++) {
+		struct blk_mq_tags *tags = set->tags[i];
+
+		for (j = 0; j < tags->nr_tags; j++) {
+			if (!tags->rqs[j])
+				continue;
+
+			ret = set->ops->reinit_request(set->driver_data,
+						tags->rqs[j]);
+			if (ret)
+				goto out;
+		}
+	}
+
+out:
+	return ret;
+}
+EXPORT_SYMBOL_GPL(blk_mq_reinit_tagset);
+
 void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 		void *priv)
 {
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 23ff76a40..815e2ac02 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -161,16 +161,17 @@ bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
 EXPORT_SYMBOL(blk_mq_can_queue);
 
 static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
-			       struct request *rq, unsigned int rw_flags)
+			       struct request *rq, int op,
+			       unsigned int op_flags)
 {
 	if (blk_queue_io_stat(q))
-		rw_flags |= REQ_IO_STAT;
+		op_flags |= REQ_IO_STAT;
 
 	INIT_LIST_HEAD(&rq->queuelist);
 	/* csd/requeue_work/fifo_time is initialized before use */
 	rq->q = q;
 	rq->mq_ctx = ctx;
-	rq->cmd_flags |= rw_flags;
+	req_set_op_attrs(rq, op, op_flags);
 	/* do not touch atomic flags, it needs atomic ops against the timer */
 	rq->cpu = -1;
 	INIT_HLIST_NODE(&rq->hash);
@@ -205,11 +206,11 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 	rq->end_io_data = NULL;
 	rq->next_rq = NULL;
 
-	ctx->rq_dispatched[rw_is_sync(rw_flags)]++;
+	ctx->rq_dispatched[rw_is_sync(op, op_flags)]++;
 }
 
 static struct request *
-__blk_mq_alloc_request(struct blk_mq_alloc_data *data, int rw)
+__blk_mq_alloc_request(struct blk_mq_alloc_data *data, int op, int op_flags)
 {
 	struct request *rq;
 	unsigned int tag;
@@ -224,7 +225,7 @@ __blk_mq_alloc_request(struct blk_mq_alloc_data *data, int rw)
 		}
 
 		rq->tag = tag;
-		blk_mq_rq_ctx_init(data->q, data->ctx, rq, rw);
+		blk_mq_rq_ctx_init(data->q, data->ctx, rq, op, op_flags);
 		return rq;
 	}
 
@@ -248,7 +249,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 	blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
 
-	rq = __blk_mq_alloc_request(&alloc_data, rw);
+	rq = __blk_mq_alloc_request(&alloc_data, rw, 0);
 	if (!rq && !(flags & BLK_MQ_REQ_NOWAIT)) {
 		__blk_mq_run_hw_queue(hctx);
 		blk_mq_put_ctx(ctx);
@@ -256,7 +257,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
 		ctx = blk_mq_get_ctx(q);
 		hctx = q->mq_ops->map_queue(q, ctx->cpu);
 		blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
-		rq =  __blk_mq_alloc_request(&alloc_data, rw);
+		rq =  __blk_mq_alloc_request(&alloc_data, rw, 0);
 		ctx = alloc_data.ctx;
 	}
 	blk_mq_put_ctx(ctx);
@@ -264,10 +265,65 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
 		blk_queue_exit(q);
 		return ERR_PTR(-EWOULDBLOCK);
 	}
+
+	rq->__data_len = 0;
+	rq->__sector = (sector_t) -1;
+	rq->bio = rq->biotail = NULL;
 	return rq;
 }
 EXPORT_SYMBOL(blk_mq_alloc_request);
 
+struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw,
+		unsigned int flags, unsigned int hctx_idx)
+{
+	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_ctx *ctx;
+	struct request *rq;
+	struct blk_mq_alloc_data alloc_data;
+	int ret;
+
+	/*
+	 * If the tag allocator sleeps we could get an allocation for a
+	 * different hardware context.  No need to complicate the low level
+	 * allocator for this for the rare use case of a command tied to
+	 * a specific queue.
+	 */
+	if (WARN_ON_ONCE(!(flags & BLK_MQ_REQ_NOWAIT)))
+		return ERR_PTR(-EINVAL);
+
+	if (hctx_idx >= q->nr_hw_queues)
+		return ERR_PTR(-EIO);
+
+	ret = blk_queue_enter(q, true);
+	if (ret)
+		return ERR_PTR(ret);
+
+	/*
+	 * Check if the hardware context is actually mapped to anything.
+	 * If not tell the caller that it should skip this queue.
+	 */
+	hctx = q->queue_hw_ctx[hctx_idx];
+	if (!blk_mq_hw_queue_mapped(hctx)) {
+		ret = -EXDEV;
+		goto out_queue_exit;
+	}
+	ctx = __blk_mq_get_ctx(q, cpumask_first(hctx->cpumask));
+
+	blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
+	rq = __blk_mq_alloc_request(&alloc_data, rw, 0);
+	if (!rq) {
+		ret = -EWOULDBLOCK;
+		goto out_queue_exit;
+	}
+
+	return rq;
+
+out_queue_exit:
+	blk_queue_exit(q);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
+
 static void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx,
 				  struct blk_mq_ctx *ctx, struct request *rq)
 {
@@ -645,7 +701,20 @@ static void blk_mq_timeout_work(struct work_struct *work)
 	};
 	int i;
 
-	if (blk_queue_enter(q, true))
+	/* A deadlock might occur if a request is stuck requiring a
+	 * timeout at the same time a queue freeze is waiting
+	 * completion, since the timeout code would not be able to
+	 * acquire the queue reference here.
+	 *
+	 * That's why we don't use blk_queue_enter here; instead, we use
+	 * percpu_ref_tryget directly, because we need to be able to
+	 * obtain a reference even in the short window between the queue
+	 * starting to freeze, by dropping the first reference in
+	 * blk_mq_freeze_queue_start, and the moment the last request is
+	 * consumed, marked by the instant q_usage_counter reaches
+	 * zero.
+	 */
+	if (!percpu_ref_tryget(&q->q_usage_counter))
 		return;
 
 	blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &data);
@@ -753,11 +822,12 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 	struct list_head *dptr;
 	int queued;
 
-	WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask));
-
 	if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state)))
 		return;
 
+	WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) &&
+		cpu_online(hctx->next_cpu));
+
 	hctx->run++;
 
 	/*
@@ -801,7 +871,7 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 		switch (ret) {
 		case BLK_MQ_RQ_QUEUE_OK:
 			queued++;
-			continue;
+			break;
 		case BLK_MQ_RQ_QUEUE_BUSY:
 			list_add(&rq->queuelist, &rq_list);
 			__blk_mq_requeue_request(rq);
@@ -996,10 +1066,11 @@ void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
 EXPORT_SYMBOL(blk_mq_delay_queue);
 
 static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx,
-					    struct blk_mq_ctx *ctx,
 					    struct request *rq,
 					    bool at_head)
 {
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+
 	trace_block_rq_insert(hctx->queue, rq);
 
 	if (at_head)
@@ -1013,20 +1084,16 @@ static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 
-	__blk_mq_insert_req_list(hctx, ctx, rq, at_head);
+	__blk_mq_insert_req_list(hctx, rq, at_head);
 	blk_mq_hctx_mark_pending(hctx, ctx);
 }
 
 void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,
-		bool async)
+			   bool async)
 {
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
 	struct request_queue *q = rq->q;
 	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx = rq->mq_ctx, *current_ctx;
-
-	current_ctx = blk_mq_get_ctx(q);
-	if (!cpu_online(ctx->cpu))
-		rq->mq_ctx = ctx = current_ctx;
 
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
@@ -1036,8 +1103,6 @@ void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,
 
 	if (run_queue)
 		blk_mq_run_hw_queue(hctx, async);
-
-	blk_mq_put_ctx(current_ctx);
 }
 
 static void blk_mq_insert_requests(struct request_queue *q,
@@ -1048,14 +1113,9 @@ static void blk_mq_insert_requests(struct request_queue *q,
 
 {
 	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *current_ctx;
 
 	trace_block_unplug(q, depth, !from_schedule);
 
-	current_ctx = blk_mq_get_ctx(q);
-
-	if (!cpu_online(ctx->cpu))
-		ctx = current_ctx;
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
 	/*
@@ -1067,15 +1127,14 @@ static void blk_mq_insert_requests(struct request_queue *q,
 		struct request *rq;
 
 		rq = list_first_entry(list, struct request, queuelist);
+		BUG_ON(rq->mq_ctx != ctx);
 		list_del_init(&rq->queuelist);
-		rq->mq_ctx = ctx;
-		__blk_mq_insert_req_list(hctx, ctx, rq, false);
+		__blk_mq_insert_req_list(hctx, rq, false);
 	}
 	blk_mq_hctx_mark_pending(hctx, ctx);
 	spin_unlock(&ctx->lock);
 
 	blk_mq_run_hw_queue(hctx, from_schedule);
-	blk_mq_put_ctx(current_ctx);
 }
 
 static int plug_ctx_cmp(void *priv, struct list_head *a, struct list_head *b)
@@ -1186,28 +1245,29 @@ static struct request *blk_mq_map_request(struct request_queue *q,
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
 	struct request *rq;
-	int rw = bio_data_dir(bio);
+	int op = bio_data_dir(bio);
+	int op_flags = 0;
 	struct blk_mq_alloc_data alloc_data;
 
 	blk_queue_enter_live(q);
 	ctx = blk_mq_get_ctx(q);
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
-	if (rw_is_sync(bio->bi_rw))
-		rw |= REQ_SYNC;
+	if (rw_is_sync(bio_op(bio), bio->bi_opf))
+		op_flags |= REQ_SYNC;
 
-	trace_block_getrq(q, bio, rw);
+	trace_block_getrq(q, bio, op);
 	blk_mq_set_alloc_data(&alloc_data, q, BLK_MQ_REQ_NOWAIT, ctx, hctx);
-	rq = __blk_mq_alloc_request(&alloc_data, rw);
+	rq = __blk_mq_alloc_request(&alloc_data, op, op_flags);
 	if (unlikely(!rq)) {
 		__blk_mq_run_hw_queue(hctx);
 		blk_mq_put_ctx(ctx);
-		trace_block_sleeprq(q, bio, rw);
+		trace_block_sleeprq(q, bio, op);
 
 		ctx = blk_mq_get_ctx(q);
 		hctx = q->mq_ops->map_queue(q, ctx->cpu);
 		blk_mq_set_alloc_data(&alloc_data, q, 0, ctx, hctx);
-		rq = __blk_mq_alloc_request(&alloc_data, rw);
+		rq = __blk_mq_alloc_request(&alloc_data, op, op_flags);
 		ctx = alloc_data.ctx;
 		hctx = alloc_data.hctx;
 	}
@@ -1261,15 +1321,15 @@ static int blk_mq_direct_issue_request(struct request *rq, blk_qc_t *cookie)
  */
 static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 {
-	const int is_sync = rw_is_sync(bio->bi_rw);
-	const int is_flush_fua = bio->bi_rw & (REQ_FLUSH | REQ_FUA);
+	const int is_sync = rw_is_sync(bio_op(bio), bio->bi_opf);
+	const int is_flush_fua = bio->bi_opf & (REQ_PREFLUSH | REQ_FUA);
 	struct blk_map_ctx data;
 	struct request *rq;
 	unsigned int request_count = 0;
 	struct blk_plug *plug;
 	struct request *same_queue_rq = NULL;
 	blk_qc_t cookie;
-	bool wb_acct;
+	unsigned int wb_acct;
 
 	blk_queue_bounce(q, &bio);
 
@@ -1284,17 +1344,15 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	    blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
 		return BLK_QC_T_NONE;
 
-	wb_acct = wbt_wait(q->rq_wb, bio->bi_rw, NULL);
+	wb_acct = wbt_wait(q->rq_wb, bio->bi_opf, NULL);
 
 	rq = blk_mq_map_request(q, bio, &data);
 	if (unlikely(!rq)) {
-		if (wb_acct)
-			__wbt_done(q->rq_wb);
+		__wbt_done(q->rq_wb, wb_acct);
 		return BLK_QC_T_NONE;
 	}
 
-	if (wb_acct)
-		wbt_mark_tracked(&rq->wb_stat);
+	wbt_track(&rq->wb_stat, wb_acct);
 
 	cookie = blk_tag_to_qc_t(rq->tag, data.hctx->queue_num);
 
@@ -1364,14 +1422,14 @@ done:
  */
 static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 {
-	const int is_sync = rw_is_sync(bio->bi_rw);
-	const int is_flush_fua = bio->bi_rw & (REQ_FLUSH | REQ_FUA);
+	const int is_sync = rw_is_sync(bio_op(bio), bio->bi_opf);
+	const int is_flush_fua = bio->bi_opf & (REQ_PREFLUSH | REQ_FUA);
 	struct blk_plug *plug;
 	unsigned int request_count = 0;
 	struct blk_map_ctx data;
 	struct request *rq;
 	blk_qc_t cookie;
-	bool wb_acct;
+	unsigned int wb_acct;
 
 	blk_queue_bounce(q, &bio);
 
@@ -1388,17 +1446,15 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	} else
 		request_count = blk_plug_queued_count(q);
 
-	wb_acct = wbt_wait(q->rq_wb, bio->bi_rw, NULL);
+	wb_acct = wbt_wait(q->rq_wb, bio->bi_opf, NULL);
 
 	rq = blk_mq_map_request(q, bio, &data);
 	if (unlikely(!rq)) {
-		if (wb_acct)
-			__wbt_done(q->rq_wb);
+		__wbt_done(q->rq_wb, wb_acct);
 		return BLK_QC_T_NONE;
 	}
 
-	if (wb_acct)
-		wbt_mark_tracked(&rq->wb_stat);
+	wbt_track(&rq->wb_stat, wb_acct);
 
 	cookie = blk_tag_to_qc_t(rq->tag, data.hctx->queue_num);
 
@@ -1607,16 +1663,17 @@ static int blk_mq_alloc_bitmap(struct blk_mq_ctxmap *bitmap, int node)
 	return 0;
 }
 
+/*
+ * 'cpu' is going away. splice any existing rq_list entries from this
+ * software queue to the hw queue dispatch list, and ensure that it
+ * gets run.
+ */
 static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu)
 {
-	struct request_queue *q = hctx->queue;
 	struct blk_mq_ctx *ctx;
 	LIST_HEAD(tmp);
 
-	/*
-	 * Move ctx entries to new CPU, if this one is going away.
-	 */
-	ctx = __blk_mq_get_ctx(q, cpu);
+	ctx = __blk_mq_get_ctx(hctx->queue, cpu);
 
 	spin_lock(&ctx->lock);
 	if (!list_empty(&ctx->rq_list)) {
@@ -1628,24 +1685,11 @@ static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu)
 	if (list_empty(&tmp))
 		return NOTIFY_OK;
 
-	ctx = blk_mq_get_ctx(q);
-	spin_lock(&ctx->lock);
-
-	while (!list_empty(&tmp)) {
-		struct request *rq;
-
-		rq = list_first_entry(&tmp, struct request, queuelist);
-		rq->mq_ctx = ctx;
-		list_move_tail(&rq->queuelist, &ctx->rq_list);
-	}
-
-	hctx = q->mq_ops->map_queue(q, ctx->cpu);
-	blk_mq_hctx_mark_pending(hctx, ctx);
-
-	spin_unlock(&ctx->lock);
+	spin_lock(&hctx->lock);
+	list_splice_tail_init(&tmp, &hctx->dispatch);
+	spin_unlock(&hctx->lock);
 
 	blk_mq_run_hw_queue(hctx, true);
-	blk_mq_put_ctx(ctx);
 	return NOTIFY_OK;
 }
 
diff --git a/block/blk-stat.c b/block/blk-stat.c
index 8e3974d87..bdb16d84b 100644
--- a/block/blk-stat.c
+++ b/block/blk-stat.c
@@ -9,11 +9,29 @@
 #include "blk-stat.h"
 #include "blk-mq.h"
 
+static void blk_stat_flush_batch(struct blk_rq_stat *stat)
+{
+	if (!stat->nr_batch)
+		return;
+	if (!stat->nr_samples)
+		stat->mean = div64_s64(stat->batch, stat->nr_batch);
+	else {
+		stat->mean = div64_s64((stat->mean * stat->nr_samples) +
+					stat->batch,
+					stat->nr_samples + stat->nr_batch);
+	}
+
+	stat->nr_samples += stat->nr_batch;
+	stat->nr_batch = stat->batch = 0;
+}
+
 void blk_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src)
 {
 	if (!src->nr_samples)
 		return;
 
+	blk_stat_flush_batch(src);
+
 	dst->min = min(dst->min, src->min);
 	dst->max = max(dst->max, src->max);
 
@@ -31,6 +49,7 @@ static void blk_mq_stat_get(struct request_queue *q, struct blk_rq_stat *dst)
 {
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
+	uint64_t latest = 0;
 	int i, j, nr;
 
 	blk_stat_init(&dst[0]);
@@ -58,6 +77,9 @@ static void blk_mq_stat_get(struct request_queue *q, struct blk_rq_stat *dst)
 		if (!newest)
 			break;
 
+		if (newest > latest)
+			latest = newest;
+
 		queue_for_each_hw_ctx(q, hctx, i) {
 			hctx_for_each_ctx(hctx, ctx, j) {
 				if (ctx->stat[0].time == newest) {
@@ -75,6 +97,8 @@ static void blk_mq_stat_get(struct request_queue *q, struct blk_rq_stat *dst)
 		 * Should be very rare.
 		 */
 	} while (!nr);
+
+	dst[0].time = dst[1].time = latest;
 }
 
 void blk_queue_stat_get(struct request_queue *q, struct blk_rq_stat *dst)
@@ -132,6 +156,7 @@ static void __blk_stat_init(struct blk_rq_stat *stat, s64 time_now)
 {
 	stat->min = -1ULL;
 	stat->max = stat->nr_samples = stat->mean = 0;
+	stat->batch = stat->nr_batch = 0;
 	stat->time = time_now & BLK_STAT_MASK;
 }
 
@@ -140,16 +165,26 @@ void blk_stat_init(struct blk_rq_stat *stat)
 	__blk_stat_init(stat, ktime_to_ns(ktime_get()));
 }
 
+static bool __blk_stat_is_current(struct blk_rq_stat *stat, s64 now)
+{
+	return (now & BLK_STAT_MASK) == (stat->time & BLK_STAT_MASK);
+}
+
+bool blk_stat_is_current(struct blk_rq_stat *stat)
+{
+	return __blk_stat_is_current(stat, ktime_to_ns(ktime_get()));
+}
+
 void blk_stat_add(struct blk_rq_stat *stat, struct request *rq)
 {
-	s64 delta, now, value;
+	s64 now, value;
 	u64 rq_time = wbt_issue_stat_get_time(&rq->wb_stat);
 
 	now = ktime_to_ns(ktime_get());
 	if (now < rq_time)
 		return;
 
-	if ((now & BLK_STAT_MASK) != (stat->time & BLK_STAT_MASK))
+	if (!__blk_stat_is_current(stat, now))
 		__blk_stat_init(stat, now);
 
 	value = now - rq_time;
@@ -158,11 +193,12 @@ void blk_stat_add(struct blk_rq_stat *stat, struct request *rq)
 	if (value < stat->min)
 		stat->min = value;
 
-	delta = value - stat->mean;
-	if (delta)
-		stat->mean += div64_s64(delta, stat->nr_samples + 1);
+	if (stat->batch + value < stat->batch ||
+	    stat->nr_batch + 1 == BLK_RQ_STAT_BATCH)
+		blk_stat_flush_batch(stat);
 
-	stat->nr_samples++;
+	stat->batch += value;
+	stat->nr_batch++;
 }
 
 void blk_stat_clear(struct request_queue *q)
diff --git a/block/blk-stat.h b/block/blk-stat.h
index d77548dbf..376a6ccd9 100644
--- a/block/blk-stat.h
+++ b/block/blk-stat.h
@@ -13,5 +13,6 @@ void blk_queue_stat_get(struct request_queue *, struct blk_rq_stat *);
 void blk_stat_clear(struct request_queue *q);
 void blk_stat_init(struct blk_rq_stat *);
 void blk_stat_sum(struct blk_rq_stat *, struct blk_rq_stat *);
+bool blk_stat_is_current(struct blk_rq_stat *);
 
 #endif
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index df194bf93..85c3dc223 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -445,6 +445,11 @@ static ssize_t queue_wc_store(struct request_queue *q, const char *page,
 	return count;
 }
 
+static ssize_t queue_dax_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(blk_queue_dax(q), page);
+}
+
 static ssize_t print_stat(char *page, struct blk_rq_stat *stat, const char *pre)
 {
 	return sprintf(page, "%s samples=%llu, mean=%lld, min=%lld, max=%lld\n",
@@ -602,6 +607,11 @@ static struct queue_sysfs_entry queue_wc_entry = {
 	.store = queue_wc_store,
 };
 
+static struct queue_sysfs_entry queue_dax_entry = {
+	.attr = {.name = "dax", .mode = S_IRUGO },
+	.show = queue_dax_show,
+};
+
 static struct queue_sysfs_entry queue_stats_entry = {
 	.attr = {.name = "stats", .mode = S_IRUGO },
 	.show = queue_stats_show,
@@ -645,6 +655,7 @@ static struct attribute *default_attrs[] = {
 	&queue_random_entry.attr,
 	&queue_poll_entry.attr,
 	&queue_wc_entry.attr,
+	&queue_dax_entry.attr,
 	&queue_stats_entry.attr,
 	&queue_wb_lat_entry.attr,
 	&queue_wb_win_entry.attr,
@@ -772,9 +783,15 @@ static void blk_wb_stat_clear(void *data)
 	blk_stat_clear(data);
 }
 
+static bool blk_wb_stat_is_current(struct blk_rq_stat *stat)
+{
+	return blk_stat_is_current(stat);
+}
+
 static struct wb_stat_ops wb_stat_ops = {
-	.get	= blk_wb_stat_get,
-	.clear	= blk_wb_stat_clear,
+	.get		= blk_wb_stat_get,
+	.is_current	= blk_wb_stat_is_current,
+	.clear		= blk_wb_stat_clear,
 };
 
 static void blk_wb_init(struct request_queue *q)
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 47a3e5406..a3ea8260c 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -145,11 +145,6 @@ struct throtl_data
 	/* Total Number of queued bios on READ and WRITE lists */
 	unsigned int nr_queued[2];
 
-	/*
-	 * number of total undestroyed groups
-	 */
-	unsigned int nr_undestroyed_grps;
-
 	/* Work for dispatching throttled bios */
 	struct work_struct dispatch_work;
 };
@@ -785,9 +780,11 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
 	/*
 	 * If previous slice expired, start a new one otherwise renew/extend
 	 * existing slice to make sure it is at least throtl_slice interval
-	 * long since now.
+	 * long since now. New slice is started only for empty throttle group.
+	 * If there is queued bio, that means there should be an active
+	 * slice and it should be extended instead.
 	 */
-	if (throtl_slice_used(tg, rw))
+	if (throtl_slice_used(tg, rw) && !(tg->service_queue.nr_queued[rw]))
 		throtl_start_new_slice(tg, rw);
 	else {
 		if (time_before(tg->slice_end[rw], jiffies + throtl_slice))
@@ -826,8 +823,8 @@ static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
 	 * second time when it eventually gets issued.  Set it when a bio
 	 * is being charged to a tg.
 	 */
-	if (!(bio->bi_rw & REQ_THROTTLED))
-		bio->bi_rw |= REQ_THROTTLED;
+	if (!(bio->bi_opf & REQ_THROTTLED))
+		bio->bi_opf |= REQ_THROTTLED;
 }
 
 /**
@@ -1404,7 +1401,7 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
 	/* see throtl_charge_bio() */
-	if ((bio->bi_rw & REQ_THROTTLED) || !tg->has_rules[rw])
+	if ((bio->bi_opf & REQ_THROTTLED) || !tg->has_rules[rw])
 		goto out;
 
 	spin_lock_irq(q->queue_lock);
@@ -1483,7 +1480,7 @@ out:
 	 * being issued.
 	 */
 	if (!throttled)
-		bio->bi_rw &= ~REQ_THROTTLED;
+		bio->bi_opf &= ~REQ_THROTTLED;
 	return throttled;
 }
 
diff --git a/block/blk.h b/block/blk.h
index 70e4aee9c..c37492f5e 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -64,8 +64,6 @@ void blk_exit_rl(struct request_list *rl);
 void init_request_from_bio(struct request *req, struct bio *bio);
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 			struct bio *bio);
-int blk_rq_append_bio(struct request_queue *q, struct request *rq,
-		      struct bio *bio);
 void blk_queue_bypass_start(struct request_queue *q);
 void blk_queue_bypass_end(struct request_queue *q);
 void blk_dequeue_request(struct request *rq);
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 49707ef43..fdcd5999d 100644
--- a/block/cfq-iosched.c
+++ b/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;
+	s64 slice_resid;
 
 	/* pending priority requests */
 	int prio_pending;
@@ -141,7 +141,7 @@ struct cfq_queue {
 
 	/* io prio of this group */
 	unsigned short ioprio, org_ioprio;
-	unsigned short ioprio_class;
+	unsigned short ioprio_class, org_ioprio_class;
 
 	pid_t pid;
 
@@ -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;
 
 	/*
@@ -362,7 +362,7 @@ struct cfq_data {
 	/*
 	 * idle window management
 	 */
-	struct timer_list idle_slice_timer;
+	struct hrtimer idle_slice_timer;
 	struct work_struct unplug_work;
 
 	struct cfq_queue *active_queue;
@@ -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);
@@ -667,15 +667,16 @@ static inline void cfqg_put(struct cfq_group *cfqg)
 } while (0)
 
 static inline void cfqg_stats_update_io_add(struct cfq_group *cfqg,
-					    struct cfq_group *curr_cfqg, int rw)
+					    struct cfq_group *curr_cfqg, int op,
+					    int op_flags)
 {
-	blkg_rwstat_add(&cfqg->stats.queued, rw, 1);
+	blkg_rwstat_add(&cfqg->stats.queued, op, op_flags, 1);
 	cfqg_stats_end_empty_time(&cfqg->stats);
 	cfqg_stats_set_start_group_wait_time(cfqg, curr_cfqg);
 }
 
 static inline void cfqg_stats_update_timeslice_used(struct cfq_group *cfqg,
-			unsigned long time, unsigned long unaccounted_time)
+			uint64_t time, unsigned long unaccounted_time)
 {
 	blkg_stat_add(&cfqg->stats.time, time);
 #ifdef CONFIG_DEBUG_BLK_CGROUP
@@ -683,26 +684,30 @@ static inline void cfqg_stats_update_timeslice_used(struct cfq_group *cfqg,
 #endif
 }
 
-static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int rw)
+static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int op,
+					       int op_flags)
 {
-	blkg_rwstat_add(&cfqg->stats.queued, rw, -1);
+	blkg_rwstat_add(&cfqg->stats.queued, op, op_flags, -1);
 }
 
-static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int rw)
+static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int op,
+					       int op_flags)
 {
-	blkg_rwstat_add(&cfqg->stats.merged, rw, 1);
+	blkg_rwstat_add(&cfqg->stats.merged, op, op_flags, 1);
 }
 
 static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
-			uint64_t start_time, uint64_t io_start_time, int rw)
+			uint64_t start_time, uint64_t io_start_time, int op,
+			int op_flags)
 {
 	struct cfqg_stats *stats = &cfqg->stats;
 	unsigned long long now = sched_clock();
 
 	if (time_after64(now, io_start_time))
-		blkg_rwstat_add(&stats->service_time, rw, now - io_start_time);
+		blkg_rwstat_add(&stats->service_time, op, op_flags,
+				now - io_start_time);
 	if (time_after64(io_start_time, start_time))
-		blkg_rwstat_add(&stats->wait_time, rw,
+		blkg_rwstat_add(&stats->wait_time, op, op_flags,
 				io_start_time - start_time);
 }
 
@@ -781,13 +786,16 @@ static inline void cfqg_put(struct cfq_group *cfqg) { }
 #define cfq_log_cfqg(cfqd, cfqg, fmt, args...)		do {} while (0)
 
 static inline void cfqg_stats_update_io_add(struct cfq_group *cfqg,
-			struct cfq_group *curr_cfqg, int rw) { }
+			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) { }
-static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int rw) { }
-static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int rw) { }
+			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,
+			int op_flags) { }
 static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
-			uint64_t start_time, uint64_t io_start_time, int rw) { }
+			uint64_t start_time, uint64_t io_start_time, int op,
+			int op_flags) { }
 
 #endif	/* CONFIG_CFQ_GROUP_IOSCHED */
 
@@ -807,7 +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)
@@ -910,7 +918,7 @@ static inline struct cfq_data *cic_to_cfqd(struct cfq_io_cq *cic)
  */
 static inline bool cfq_bio_sync(struct bio *bio)
 {
-	return bio_data_dir(bio) == READ || (bio->bi_rw & REQ_SYNC);
+	return bio_data_dir(bio) == READ || (bio->bi_opf & REQ_SYNC);
 }
 
 /*
@@ -930,17 +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);
@@ -958,15 +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)
@@ -1019,16 +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
@@ -1036,20 +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;
@@ -1058,12 +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);
 }
 
 /*
@@ -1075,7 +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;
@@ -1241,8 +1252,8 @@ 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,
-				      struct cfq_queue *cfqq)
+static u64 cfq_slice_offset(struct cfq_data *cfqd,
+			    struct cfq_queue *cfqq)
 {
 	/*
 	 * just an approximation, should be ok.
@@ -1435,31 +1446,32 @@ 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),
+					jiffies_to_nsecs(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;
 	}
@@ -1471,10 +1483,11 @@ 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);
@@ -1496,9 +1509,8 @@ 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
@@ -1507,7 +1519,7 @@ 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);
@@ -1530,7 +1542,7 @@ 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
@@ -2213,10 +2225,11 @@ 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)) {
@@ -2226,7 +2239,7 @@ 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
@@ -2234,13 +2247,13 @@ 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)) {
@@ -2266,7 +2279,7 @@ 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;
@@ -2461,10 +2474,10 @@ static void cfq_reposition_rq_rb(struct cfq_queue *cfqq, struct request *rq)
 {
 	elv_rb_del(&cfqq->sort_list, rq);
 	cfqq->queued[rq_is_sync(rq)]--;
-	cfqg_stats_update_io_remove(RQ_CFQG(rq), rq->cmd_flags);
+	cfqg_stats_update_io_remove(RQ_CFQG(rq), req_op(rq), rq->cmd_flags);
 	cfq_add_rq_rb(rq);
 	cfqg_stats_update_io_add(RQ_CFQG(rq), cfqq->cfqd->serving_group,
-				 rq->cmd_flags);
+				 req_op(rq), rq->cmd_flags);
 }
 
 static struct request *
@@ -2517,7 +2530,7 @@ static void cfq_remove_request(struct request *rq)
 	cfq_del_rq_rb(rq);
 
 	cfqq->cfqd->rq_queued--;
-	cfqg_stats_update_io_remove(RQ_CFQG(rq), rq->cmd_flags);
+	cfqg_stats_update_io_remove(RQ_CFQG(rq), req_op(rq), rq->cmd_flags);
 	if (rq->cmd_flags & REQ_PRIO) {
 		WARN_ON(!cfqq->prio_pending);
 		cfqq->prio_pending--;
@@ -2531,7 +2544,7 @@ static int cfq_merge(struct request_queue *q, struct request **req,
 	struct request *__rq;
 
 	__rq = cfq_find_rq_fmerge(cfqd, bio);
-	if (__rq && elv_rq_merge_ok(__rq, bio)) {
+	if (__rq && elv_bio_merge_ok(__rq, bio)) {
 		*req = __rq;
 		return ELEVATOR_FRONT_MERGE;
 	}
@@ -2552,7 +2565,7 @@ static void cfq_merged_request(struct request_queue *q, struct request *req,
 static void cfq_bio_merged(struct request_queue *q, struct request *req,
 				struct bio *bio)
 {
-	cfqg_stats_update_io_merged(RQ_CFQG(req), bio->bi_rw);
+	cfqg_stats_update_io_merged(RQ_CFQG(req), bio_op(bio), bio->bi_opf);
 }
 
 static void
@@ -2566,7 +2579,7 @@ 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;
@@ -2575,7 +2588,7 @@ cfq_merged_requests(struct request_queue *q, struct request *rq,
 	if (cfqq->next_rq == next)
 		cfqq->next_rq = rq;
 	cfq_remove_request(next);
-	cfqg_stats_update_io_merged(RQ_CFQG(rq), next->cmd_flags);
+	cfqg_stats_update_io_merged(RQ_CFQG(rq), req_op(next), next->cmd_flags);
 
 	cfqq = RQ_CFQQ(next);
 	/*
@@ -2588,8 +2601,8 @@ cfq_merged_requests(struct request_queue *q, struct request *rq,
 		cfq_del_cfqq_rr(cfqd, cfqq);
 }
 
-static int cfq_allow_merge(struct request_queue *q, struct request *rq,
-			   struct bio *bio)
+static int cfq_allow_bio_merge(struct request_queue *q, struct request *rq,
+			       struct bio *bio)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct cfq_io_cq *cic;
@@ -2613,9 +2626,15 @@ static int cfq_allow_merge(struct request_queue *q, struct request *rq,
 	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)
 {
-	del_timer(&cfqd->idle_slice_timer);
+	hrtimer_try_to_cancel(&cfqd->idle_slice_timer);
 	cfqg_stats_update_idle_time(cfqq->cfqg);
 }
 
@@ -2627,7 +2646,7 @@ 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;
@@ -2676,8 +2695,8 @@ __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=%lld", cfqq->slice_resid);
 	}
 
 	cfq_group_served(cfqd, cfqq->cfqg, cfqq);
@@ -2911,7 +2930,8 @@ 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
@@ -2954,8 +2974,8 @@ 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;
 	}
@@ -2976,9 +2996,10 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	else
 		sl = cfqd->cfq_slice_idle;
 
-	mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
+	hrtimer_start(&cfqd->idle_slice_timer, ns_to_ktime(sl),
+		      HRTIMER_MODE_REL);
 	cfqg_stats_set_start_idle_time(cfqq->cfqg);
-	cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu group_idle: %d", sl,
+	cfq_log_cfqq(cfqd, cfqq, "arm_idle: %llu group_idle: %d", sl,
 			group_idle ? 1 : 0);
 }
 
@@ -3018,7 +3039,7 @@ 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);
@@ -3096,14 +3117,14 @@ 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;
@@ -3116,11 +3137,12 @@ 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))
@@ -3129,7 +3151,7 @@ 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;
 	}
 
@@ -3147,7 +3169,7 @@ 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:
@@ -3164,13 +3186,13 @@ new_workload:
 	 */
 	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
@@ -3181,19 +3203,19 @@ new_workload:
 		 */
 		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)
@@ -3211,16 +3233,17 @@ 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);
 }
@@ -3232,6 +3255,7 @@ 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)
@@ -3292,7 +3316,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 	 * flight or is idling for a new request, allow either of these
 	 * conditions to happen (or time out) before selecting a new queue.
 	 */
-	if (timer_pending(&cfqd->idle_slice_timer)) {
+	if (hrtimer_active(&cfqd->idle_slice_timer)) {
 		cfqq = NULL;
 		goto keep_queue;
 	}
@@ -3303,7 +3327,7 @@ 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);
 	}
@@ -3381,11 +3405,12 @@ 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;
@@ -3460,10 +3485,10 @@ 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)
@@ -3546,7 +3571,7 @@ 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);
 	}
 
@@ -3624,7 +3649,7 @@ 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)
@@ -3682,6 +3707,7 @@ static void cfq_init_prio_data(struct cfq_queue *cfqq, struct cfq_io_cq *cic)
 	 * elevate the priority of this queue
 	 */
 	cfqq->org_ioprio = cfqq->ioprio;
+	cfqq->org_ioprio_class = cfqq->ioprio_class;
 	cfq_clear_cfqq_prio_changed(cfqq);
 }
 
@@ -3738,9 +3764,11 @@ static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
 	struct cfq_data *cfqd = cic_to_cfqd(cic);
 	struct cfq_queue *cfqq;
 	uint64_t serial_nr;
+	bool nonroot_cg;
 
 	rcu_read_lock();
 	serial_nr = bio_blkcg(bio)->css.serial_nr;
+	nonroot_cg = bio_blkcg(bio) != &blkcg_root;
 	rcu_read_unlock();
 
 	/*
@@ -3755,11 +3783,10 @@ static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
 	 * do proper throttling of writes. Turn off wbt for that
 	 * case.
 	 */
-	if (bio_blkcg(bio) != &blkcg_root) {
+	if (nonroot_cg) {
 		struct request_queue *q = cfqd->queue;
 
-		if (q->rq_wb)
-			wbt_disable(q->rq_wb);
+		wbt_disable(q->rq_wb);
 	}
 
 	/*
@@ -3857,14 +3884,15 @@ out:
 }
 
 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
@@ -4117,10 +4145,10 @@ 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,
+	cfqg_stats_update_io_add(RQ_CFQG(rq), cfqd->serving_group, req_op(rq),
 				 rq->cmd_flags);
 	cfq_rq_enqueued(cfqd, cfqq, rq);
 }
@@ -4165,6 +4193,7 @@ 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))
@@ -4183,7 +4212,7 @@ 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;
 
 	/*
@@ -4193,7 +4222,7 @@ 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;
@@ -4204,9 +4233,8 @@ 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));
 
@@ -4218,7 +4246,8 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 	cfqq->dispatched--;
 	(RQ_CFQG(rq))->dispatched--;
 	cfqg_stats_update_completion(cfqq->cfqg, rq_start_time_ns(rq),
-				     rq_io_start_time_ns(rq), rq->cmd_flags);
+				     rq_io_start_time_ns(rq), req_op(rq),
+				     rq->cmd_flags);
 
 	cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--;
 
@@ -4234,7 +4263,16 @@ 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))
+		/*
+		 * 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;
 	}
 
@@ -4259,10 +4297,10 @@ 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");
 		}
@@ -4287,6 +4325,24 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 		cfq_schedule_dispatch(cfqd);
 }
 
+static void cfqq_boost_on_prio(struct cfq_queue *cfqq, int op_flags)
+{
+	/*
+	 * 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_flags & 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)) {
@@ -4297,7 +4353,7 @@ static inline int __cfq_may_queue(struct cfq_queue *cfqq)
 	return ELV_MQUEUE_MAY;
 }
 
-static int cfq_may_queue(struct request_queue *q, int rw)
+static int cfq_may_queue(struct request_queue *q, int op, int op_flags)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct task_struct *tsk = current;
@@ -4314,9 +4370,10 @@ static int cfq_may_queue(struct request_queue *q, int rw)
 	if (!cic)
 		return ELV_MQUEUE_MAY;
 
-	cfqq = cic_to_cfqq(cic, rw_is_sync(rw));
+	cfqq = cic_to_cfqq(cic, rw_is_sync(op, op_flags));
 	if (cfqq) {
 		cfq_init_prio_data(cfqq, cic);
+		cfqq_boost_on_prio(cfqq, op_flags);
 
 		return __cfq_may_queue(cfqq);
 	}
@@ -4447,9 +4504,10 @@ static void cfq_kick_queue(struct work_struct *work)
 /*
  * Timer running if the active_queue is currently idling inside its time slice
  */
-static void cfq_idle_slice_timer(unsigned long data)
+static enum hrtimer_restart cfq_idle_slice_timer(struct hrtimer *timer)
 {
-	struct cfq_data *cfqd = (struct cfq_data *) data;
+	struct cfq_data *cfqd = container_of(timer, struct cfq_data,
+					     idle_slice_timer);
 	struct cfq_queue *cfqq;
 	unsigned long flags;
 	int timed_out = 1;
@@ -4498,11 +4556,12 @@ 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)
 {
-	del_timer_sync(&cfqd->idle_slice_timer);
+	hrtimer_cancel(&cfqd->idle_slice_timer);
 	cancel_work_sync(&cfqd->unplug_work);
 }
 
@@ -4598,9 +4657,9 @@ static int cfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	cfqg_put(cfqd->root_group);
 	spin_unlock_irq(q->queue_lock);
 
-	init_timer(&cfqd->idle_slice_timer);
+	hrtimer_init(&cfqd->idle_slice_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL);
 	cfqd->idle_slice_timer.function = cfq_idle_slice_timer;
-	cfqd->idle_slice_timer.data = (unsigned long) cfqd;
 
 	INIT_WORK(&cfqd->unplug_work, cfq_kick_queue);
 
@@ -4621,7 +4680,7 @@ 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:
@@ -4664,9 +4723,9 @@ 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);
@@ -4683,6 +4742,21 @@ SHOW_FUNCTION(cfq_low_latency_show, cfqd->cfq_latency, 0);
 SHOW_FUNCTION(cfq_target_latency_show, cfqd->cfq_target_latency, 1);
 #undef SHOW_FUNCTION
 
+#define USEC_SHOW_FUNCTION(__FUNC, __VAR)				\
+static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
+{									\
+	struct cfq_data *cfqd = e->elevator_data;			\
+	u64 __data = __VAR;						\
+	__data = div_u64(__data, NSEC_PER_USEC);			\
+	return cfq_var_show(__data, (page));				\
+}
+USEC_SHOW_FUNCTION(cfq_slice_idle_us_show, cfqd->cfq_slice_idle);
+USEC_SHOW_FUNCTION(cfq_group_idle_us_show, cfqd->cfq_group_idle);
+USEC_SHOW_FUNCTION(cfq_slice_sync_us_show, cfqd->cfq_slice[1]);
+USEC_SHOW_FUNCTION(cfq_slice_async_us_show, cfqd->cfq_slice[0]);
+USEC_SHOW_FUNCTION(cfq_target_latency_us_show, cfqd->cfq_target_latency);
+#undef USEC_SHOW_FUNCTION
+
 #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
 static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
 {									\
@@ -4694,7 +4768,7 @@ 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;							\
@@ -4717,6 +4791,26 @@ STORE_FUNCTION(cfq_low_latency_store, &cfqd->cfq_latency, 0, 1, 0);
 STORE_FUNCTION(cfq_target_latency_store, &cfqd->cfq_target_latency, 1, UINT_MAX, 1);
 #undef STORE_FUNCTION
 
+#define USEC_STORE_FUNCTION(__FUNC, __PTR, MIN, MAX)			\
+static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
+{									\
+	struct cfq_data *cfqd = e->elevator_data;			\
+	unsigned int __data;						\
+	int ret = cfq_var_store(&__data, (page), count);		\
+	if (__data < (MIN))						\
+		__data = (MIN);						\
+	else if (__data > (MAX))					\
+		__data = (MAX);						\
+	*(__PTR) = (u64)__data * NSEC_PER_USEC;				\
+	return ret;							\
+}
+USEC_STORE_FUNCTION(cfq_slice_idle_us_store, &cfqd->cfq_slice_idle, 0, UINT_MAX);
+USEC_STORE_FUNCTION(cfq_group_idle_us_store, &cfqd->cfq_group_idle, 0, UINT_MAX);
+USEC_STORE_FUNCTION(cfq_slice_sync_us_store, &cfqd->cfq_slice[1], 1, UINT_MAX);
+USEC_STORE_FUNCTION(cfq_slice_async_us_store, &cfqd->cfq_slice[0], 1, UINT_MAX);
+USEC_STORE_FUNCTION(cfq_target_latency_us_store, &cfqd->cfq_target_latency, 1, UINT_MAX);
+#undef USEC_STORE_FUNCTION
+
 #define CFQ_ATTR(name) \
 	__ATTR(name, S_IRUGO|S_IWUSR, cfq_##name##_show, cfq_##name##_store)
 
@@ -4727,12 +4821,17 @@ static struct elv_fs_entry cfq_attrs[] = {
 	CFQ_ATTR(back_seek_max),
 	CFQ_ATTR(back_seek_penalty),
 	CFQ_ATTR(slice_sync),
+	CFQ_ATTR(slice_sync_us),
 	CFQ_ATTR(slice_async),
+	CFQ_ATTR(slice_async_us),
 	CFQ_ATTR(slice_async_rq),
 	CFQ_ATTR(slice_idle),
+	CFQ_ATTR(slice_idle_us),
 	CFQ_ATTR(group_idle),
+	CFQ_ATTR(group_idle_us),
 	CFQ_ATTR(low_latency),
 	CFQ_ATTR(target_latency),
+	CFQ_ATTR(target_latency_us),
 	__ATTR_NULL
 };
 
@@ -4741,7 +4840,8 @@ static struct elevator_type iosched_cfq = {
 		.elevator_merge_fn = 		cfq_merge,
 		.elevator_merged_fn =		cfq_merged_request,
 		.elevator_merge_req_fn =	cfq_merged_requests,
-		.elevator_allow_merge_fn =	cfq_allow_merge,
+		.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,
@@ -4788,18 +4888,7 @@ 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;
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index d0dd7882d..55e0bb6d7 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -137,7 +137,7 @@ deadline_merge(struct request_queue *q, struct request **req, struct bio *bio)
 		if (__rq) {
 			BUG_ON(sector != blk_rq_pos(__rq));
 
-			if (elv_rq_merge_ok(__rq, bio)) {
+			if (elv_bio_merge_ok(__rq, bio)) {
 				ret = ELEVATOR_FRONT_MERGE;
 				goto out;
 			}
@@ -173,7 +173,8 @@ deadline_merged_requests(struct request_queue *q, struct request *req,
 	 * and move into next position (next will be deleted) in fifo
 	 */
 	if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) {
-		if (time_before(next->fifo_time, req->fifo_time)) {
+		if (time_before((unsigned long)next->fifo_time,
+				(unsigned long)req->fifo_time)) {
 			list_move(&req->queuelist, &next->queuelist);
 			req->fifo_time = next->fifo_time;
 		}
@@ -227,7 +228,7 @@ static inline int deadline_check_fifo(struct deadline_data *dd, int ddir)
 	/*
 	 * rq is expired!
 	 */
-	if (time_after_eq(jiffies, rq->fifo_time))
+	if (time_after_eq(jiffies, (unsigned long)rq->fifo_time))
 		return 1;
 
 	return 0;
diff --git a/block/elevator.c b/block/elevator.c
index c3555c9c6..f7d973a56 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -53,13 +53,13 @@ static LIST_HEAD(elv_list);
  * Query io scheduler to see if the current process issuing bio may be
  * merged with rq.
  */
-static int elv_iosched_allow_merge(struct request *rq, struct bio *bio)
+static int elv_iosched_allow_bio_merge(struct request *rq, struct bio *bio)
 {
 	struct request_queue *q = rq->q;
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_allow_merge_fn)
-		return e->type->ops.elevator_allow_merge_fn(q, rq, bio);
+	if (e->type->ops.elevator_allow_bio_merge_fn)
+		return e->type->ops.elevator_allow_bio_merge_fn(q, rq, bio);
 
 	return 1;
 }
@@ -67,17 +67,17 @@ static int elv_iosched_allow_merge(struct request *rq, struct bio *bio)
 /*
  * can we safely merge with this request?
  */
-bool elv_rq_merge_ok(struct request *rq, struct bio *bio)
+bool elv_bio_merge_ok(struct request *rq, struct bio *bio)
 {
 	if (!blk_rq_merge_ok(rq, bio))
-		return 0;
+		return false;
 
-	if (!elv_iosched_allow_merge(rq, bio))
-		return 0;
+	if (!elv_iosched_allow_bio_merge(rq, bio))
+		return false;
 
-	return 1;
+	return true;
 }
-EXPORT_SYMBOL(elv_rq_merge_ok);
+EXPORT_SYMBOL(elv_bio_merge_ok);
 
 static struct elevator_type *elevator_find(const char *name)
 {
@@ -366,8 +366,7 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq)
 	list_for_each_prev(entry, &q->queue_head) {
 		struct request *pos = list_entry_rq(entry);
 
-		if ((rq->cmd_flags & REQ_DISCARD) !=
-		    (pos->cmd_flags & REQ_DISCARD))
+		if (req_op(rq) != req_op(pos))
 			break;
 		if (rq_data_dir(rq) != rq_data_dir(pos))
 			break;
@@ -426,7 +425,7 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 	/*
 	 * First try one-hit cache.
 	 */
-	if (q->last_merge && elv_rq_merge_ok(q->last_merge, bio)) {
+	if (q->last_merge && elv_bio_merge_ok(q->last_merge, bio)) {
 		ret = blk_try_merge(q->last_merge, bio);
 		if (ret != ELEVATOR_NO_MERGE) {
 			*req = q->last_merge;
@@ -441,7 +440,7 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 	 * See if our hash lookup can find a potential backmerge.
 	 */
 	__rq = elv_rqhash_find(q, bio->bi_iter.bi_sector);
-	if (__rq && elv_rq_merge_ok(__rq, bio)) {
+	if (__rq && elv_bio_merge_ok(__rq, bio)) {
 		*req = __rq;
 		return ELEVATOR_BACK_MERGE;
 	}
@@ -717,12 +716,12 @@ void elv_put_request(struct request_queue *q, struct request *rq)
 		e->type->ops.elevator_put_req_fn(rq);
 }
 
-int elv_may_queue(struct request_queue *q, int rw)
+int elv_may_queue(struct request_queue *q, int op, int op_flags)
 {
 	struct elevator_queue *e = q->elevator;
 
 	if (e->type->ops.elevator_may_queue_fn)
-		return e->type->ops.elevator_may_queue_fn(q, rw);
+		return e->type->ops.elevator_may_queue_fn(q, op, op_flags);
 
 	return ELV_MQUEUE_MAY;
 }
diff --git a/block/genhd.c b/block/genhd.c
index a909bf8ba..fcd6d4fae 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -18,8 +18,6 @@
 #include <linux/kobj_map.h>
 #include <linux/mutex.h>
 #include <linux/idr.h>
-#include <linux/ctype.h>
-#include <linux/fs_uuid.h>
 #include <linux/log2.h>
 #include <linux/pm_runtime.h>
 #include <linux/badblocks.h>
@@ -508,7 +506,7 @@ static int exact_lock(dev_t devt, void *data)
 	return 0;
 }
 
-static void register_disk(struct gendisk *disk)
+static void register_disk(struct device *parent, struct gendisk *disk)
 {
 	struct device *ddev = disk_to_dev(disk);
 	struct block_device *bdev;
@@ -516,7 +514,7 @@ static void register_disk(struct gendisk *disk)
 	struct hd_struct *part;
 	int err;
 
-	ddev->parent = disk->driverfs_dev;
+	ddev->parent = parent;
 
 	dev_set_name(ddev, "%s", disk->disk_name);
 
@@ -575,7 +573,8 @@ exit:
 }
 
 /**
- * add_disk - add partitioning information to kernel list
+ * device_add_disk - add partitioning information to kernel list
+ * @parent: parent device for the disk
  * @disk: per-device partitioning information
  *
  * This function registers the partitioning information in @disk
@@ -583,7 +582,7 @@ exit:
  *
  * FIXME: error handling
  */
-void add_disk(struct gendisk *disk)
+void device_add_disk(struct device *parent, struct gendisk *disk)
 {
 	struct backing_dev_info *bdi;
 	dev_t devt;
@@ -619,7 +618,7 @@ void add_disk(struct gendisk *disk)
 
 	blk_register_region(disk_devt(disk), disk->minors, NULL,
 			    exact_match, exact_lock, disk);
-	register_disk(disk);
+	register_disk(parent, disk);
 	blk_register_queue(disk);
 
 	/*
@@ -635,7 +634,7 @@ void add_disk(struct gendisk *disk)
 	disk_add_events(disk);
 	blk_integrity_add(disk);
 }
-EXPORT_SYMBOL(add_disk);
+EXPORT_SYMBOL(device_add_disk);
 
 void del_gendisk(struct gendisk *disk)
 {
@@ -801,10 +800,9 @@ void __init printk_all_partitions(void)
 			       , disk_name(disk, part->partno, name_buf),
 			       part->info ? part->info->uuid : "");
 			if (is_part0) {
-				if (disk->driverfs_dev != NULL &&
-				    disk->driverfs_dev->driver != NULL)
+				if (dev->parent && dev->parent->driver)
 					printk(" driver: %s\n",
-					      disk->driverfs_dev->driver->name);
+					      dev->parent->driver->name);
 				else
 					printk(" (driver?)\n");
 			} else
@@ -1420,85 +1418,6 @@ int invalidate_partition(struct gendisk *disk, int partno)
 
 EXPORT_SYMBOL(invalidate_partition);
 
-dev_t blk_lookup_fs_info(struct fs_info *seek)
-{
-	dev_t devt = MKDEV(0, 0);
-	struct class_dev_iter iter;
-	struct device *dev;
-	int best_score = 0;
-
-	class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
-	while (best_score < 3 && (dev = class_dev_iter_next(&iter))) {
-		struct gendisk *disk = dev_to_disk(dev);
-		struct disk_part_iter piter;
-		struct hd_struct *part;
-
-		disk_part_iter_init(&piter, disk, DISK_PITER_INCL_PART0);
-
-		while (best_score < 3 && (part = disk_part_iter_next(&piter))) {
-			int score = part_matches_fs_info(part, seek);
-			if (score > best_score) {
-				devt = part_devt(part);
-				best_score = score;
-			}
-		}
-		disk_part_iter_exit(&piter);
-	}
-	class_dev_iter_exit(&iter);
-	return devt;
-}
-
-/* Caller uses NULL, key to start. For each match found, we return a bdev on
- * which we have done blkdev_get, and we do the blkdev_put on block devices
- * that are passed to us. When no more matches are found, we return NULL.
- */
-struct block_device *next_bdev_of_type(struct block_device *last,
-	const char *key)
-{
-	dev_t devt = MKDEV(0, 0);
-	struct class_dev_iter iter;
-	struct device *dev;
-	struct block_device *next = NULL, *bdev;
-	int got_last = 0;
-
-	if (!key)
-		goto out;
-
-	class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
-	while (!devt && (dev = class_dev_iter_next(&iter))) {
-		struct gendisk *disk = dev_to_disk(dev);
-		struct disk_part_iter piter;
-		struct hd_struct *part;
-
-		disk_part_iter_init(&piter, disk, DISK_PITER_INCL_PART0);
-
-		while ((part = disk_part_iter_next(&piter))) {
-			bdev = bdget(part_devt(part));
-			if (last && !got_last) {
-				if (last == bdev)
-					got_last = 1;
-				continue;
-			}
-
-			if (blkdev_get(bdev, FMODE_READ, 0))
-				continue;
-
-			if (bdev_matches_key(bdev, key)) {
-				next = bdev;
-				break;
-			}
-
-			blkdev_put(bdev, FMODE_READ);
-		}
-		disk_part_iter_exit(&piter);
-	}
-	class_dev_iter_exit(&iter);
-out:
-	if (last)
-		blkdev_put(last, FMODE_READ);
-	return next;
-}
-
 /*
  * Disk events - monitor disk events like media change and eject request.
  */
@@ -1605,12 +1524,7 @@ static void __disk_unblock_events(struct gendisk *disk, bool check_now)
 	if (--ev->block)
 		goto out_unlock;
 
-	/*
-	 * Not exactly a latency critical operation, set poll timer
-	 * slack to 25% and kick event check.
-	 */
 	intv = disk_events_poll_jiffies(disk);
-	set_timer_slack(&ev->dwork.timer, intv / 4);
 	if (check_now)
 		queue_delayed_work(system_freezable_power_efficient_wq,
 				&ev->dwork, 0);
diff --git a/block/partition-generic.c b/block/partition-generic.c
index d7eb77e1e..71d9ed9df 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -495,7 +495,6 @@ rescan:
 	/* add partitions */
 	for (p = 1; p < state->limit; p++) {
 		sector_t size, from;
-		struct partition_meta_info *info = NULL;
 
 		size = state->parts[p].size;
 		if (!size)
@@ -530,8 +529,6 @@ rescan:
 			}
 		}
 
-		if (state->parts[p].has_info)
-			info = &state->parts[p].info;
 		part = add_partition(disk, p, from, size,
 				     state->parts[p].flags,
 				     &state->parts[p].info);
diff --git a/block/partitions/atari.c b/block/partitions/atari.c
index 9875b05e8..ff1fb9371 100644
--- a/block/partitions/atari.c
+++ b/block/partitions/atari.c
@@ -42,6 +42,13 @@ int atari_partition(struct parsed_partitions *state)
 	int part_fmt = 0; /* 0:unknown, 1:AHDI, 2:ICD/Supra */
 #endif
 
+	/*
+	 * ATARI partition scheme supports 512 lba only.  If this is not
+	 * the case, bail early to avoid miscalculating hd_size.
+	 */
+	if (bdev_logical_block_size(state->bdev) != 512)
+		return 0;
+
 	rs = read_part_sector(state, 0, &sect);
 	if (!rs)
 		return -1;